From 363101190133199122414fc2064468c8aee34a97 Mon Sep 17 00:00:00 2001 From: Charles Haley <> Date: Tue, 16 Apr 2013 10:38:31 +0200 Subject: [PATCH 01/36] 1) Disable edit and remove VL menus when no VLs exist 2) Fix problem with random "color problem" messages when using a null icon --- resources/images/empty.png | Bin 0 -> 1164 bytes src/calibre/gui2/search_restriction_mixin.py | 55 ++++++++++--------- 2 files changed, 28 insertions(+), 27 deletions(-) create mode 100644 resources/images/empty.png diff --git a/resources/images/empty.png b/resources/images/empty.png new file mode 100644 index 0000000000000000000000000000000000000000..f3f05d30921c094cd3fe03faf641aa7058877b22 GIT binary patch literal 1164 zcmeAS@N?(olHy`uVBq!ia0vp^4Is?H3?#oinD~={ftew|C&cytC>RZa5gY>h^*j<8 z7#JB!g8YIRMsPTQyv{ZKiw&@N;4JWnEM{QfI|9OtQ?>b|fr4tDE{-7;x85FPWCZe> i6#lQz^Kbw$k->X5hXw{lxz^>vAW=_OKbLh*2~7Yf{2Dv} literal 0 HcmV?d00001 diff --git a/src/calibre/gui2/search_restriction_mixin.py b/src/calibre/gui2/search_restriction_mixin.py index 4cdb1574d4..0137cd1027 100644 --- a/src/calibre/gui2/search_restriction_mixin.py +++ b/src/calibre/gui2/search_restriction_mixin.py @@ -299,7 +299,7 @@ class SearchRestrictionMixin(object): def __init__(self): self.checked = QIcon(I('ok.png')) - self.empty = QIcon() + self.empty = QIcon(I('empty.png')) self.search_based_vl_name = None self.search_based_vl = None @@ -315,21 +315,24 @@ class SearchRestrictionMixin(object): self.search_restriction.setVisible(False) self.search_count.setText(_("(all books)")) self.ar_menu = QMenu(_('Additional restriction')) + self.edit_menu = QMenu(_('Edit Virtual Library')) + self.rm_menu = QMenu(_('Remove Virtual Library')) + def add_virtual_library(self, db, name, search): virt_libs = db.prefs.get('virtual_libraries', {}) virt_libs[name] = search db.prefs.set('virtual_libraries', virt_libs) - def do_create_edit(self, editing=None): + def do_create_edit(self, name=None): db = self.library_view.model().db virt_libs = db.prefs.get('virtual_libraries', {}) - cd = CreateVirtualLibrary(self, virt_libs.keys(), editing=editing) + cd = CreateVirtualLibrary(self, virt_libs.keys(), editing=name) if cd.exec_() == cd.Accepted: - if editing: - self._remove_vl(editing, reapply=False) + if name: + self._remove_vl(name, reapply=False) self.add_virtual_library(db, cd.library_name, cd.library_search) - if not editing or editing == db.data.get_base_restriction_name(): + if not name or name == db.data.get_base_restriction_name(): self.apply_virtual_library(cd.library_name) def virtual_library_clicked(self): @@ -337,16 +340,14 @@ class SearchRestrictionMixin(object): m.clear() a = m.addAction(_('Create Virtual Library')) - a.triggered.connect(partial(self.do_create_edit, editing=None)) + a.triggered.connect(partial(self.do_create_edit, name=None)) - self.edit_menu = a = QMenu() - a.setTitle(_('Edit Virtual Library')) - a.aboutToShow.connect(partial(self.build_virtual_library_list, remove=False)) + a = self.edit_menu + self.build_virtual_library_list(a, self.do_create_edit) m.addMenu(a) - self.rm_menu = a = QMenu() - a.setTitle(_('Remove Virtual Library')) - a.aboutToShow.connect(partial(self.build_virtual_library_list, remove=True)) + a = self.rm_menu + self.build_virtual_library_list(a, self.remove_vl_triggered) m.addMenu(a) m.addSeparator() @@ -356,7 +357,7 @@ class SearchRestrictionMixin(object): a = self.ar_menu a.clear() a.setIcon(self.checked if db.data.get_search_restriction_name() else self.empty) - a.aboutToShow.connect(self.build_search_restriction_list) + self.build_search_restriction_list() m.addMenu(a) m.addSeparator() @@ -426,24 +427,24 @@ class SearchRestrictionMixin(object): self._apply_search_restriction(db.data.get_search_restriction(), db.data.get_search_restriction_name()) - def build_virtual_library_list(self, remove=False): + def build_virtual_library_list(self, menu, handler): db = self.library_view.model().db virt_libs = db.prefs.get('virtual_libraries', {}) - if remove: - m = self.rm_menu - else: - m = self.edit_menu - m.clear() + menu.clear() + menu.setIcon(self.empty) def add_action(name, search): - a = m.addAction(name) - if remove: - a.triggered.connect(partial(self.remove_vl_triggered, name=name)) - else: - a.triggered.connect(partial(self.do_create_edit, editing=name)) + a = menu.addAction(name) + a.triggered.connect(partial(handler, name=name)) + a.setIcon(self.empty) - for n in sorted(virt_libs.keys(), key=sort_key): - add_action(n, virt_libs[n]) + libs = sorted(virt_libs.keys(), key=sort_key) + if libs: + menu.setEnabled(True) + for n in libs: + add_action(n, virt_libs[n]) + else: + menu.setEnabled(False) def remove_vl_triggered(self, name=None): if not question_dialog(self, _('Are you sure?'), From a5b66f0b1cb7b4cf8a74b23cbdf6c67e8a88f8b1 Mon Sep 17 00:00:00 2001 From: Charles Haley <> Date: Tue, 16 Apr 2013 13:33:08 +0200 Subject: [PATCH 02/36] Test replacement search query parser --- src/calibre/utils/pyparsing.py | 7234 +++++++++++----------- src/calibre/utils/search_query_parser.py | 205 +- 2 files changed, 3756 insertions(+), 3683 deletions(-) diff --git a/src/calibre/utils/pyparsing.py b/src/calibre/utils/pyparsing.py index 149ccaf1b0..5d3b050879 100644 --- a/src/calibre/utils/pyparsing.py +++ b/src/calibre/utils/pyparsing.py @@ -23,78 +23,78 @@ # #from __future__ import generators -__doc__ = \ -""" -pyparsing module - Classes and methods to define and execute parsing grammars - -The pyparsing module is an alternative approach to creating and executing simple grammars, -vs. the traditional lex/yacc approach, or the use of regular expressions. With pyparsing, you -don't need to learn a new syntax for defining grammars or matching expressions - the parsing module -provides a library of classes that you use to construct the grammar directly in Python. - -Here is a program to parse "Hello, World!" (or any greeting of the form C{", !"}):: - - from pyparsing import Word, alphas - - # define grammar of a greeting - greet = Word( alphas ) + "," + Word( alphas ) + "!" - - hello = "Hello, World!" - print hello, "->", greet.parseString( hello ) - -The program outputs the following:: - - Hello, World! -> ['Hello', ',', 'World', '!'] - -The Python representation of the grammar is quite readable, owing to the self-explanatory -class names, and the use of '+', '|' and '^' operators. - -The parsed results returned from C{parseString()} can be accessed as a nested list, a dictionary, or an -object with named attributes. - -The pyparsing module handles some of the problems that are typically vexing when writing text parsers: - - extra or missing whitespace (the above program will also handle "Hello,World!", "Hello , World !", etc.) - - quoted strings - - embedded comments -""" - -__version__ = "1.5.7" -__versionTime__ = "17 November 2012 16:18" -__author__ = "Paul McGuire " - -import string -from weakref import ref as wkref -import copy -import sys -import warnings -import re -import sre_constants -#~ sys.stderr.write( "testing pyparsing module, version %s, %s\n" % (__version__,__versionTime__ ) ) - -__all__ = [ -'And', 'CaselessKeyword', 'CaselessLiteral', 'CharsNotIn', 'Combine', 'Dict', 'Each', 'Empty', -'FollowedBy', 'Forward', 'GoToColumn', 'Group', 'Keyword', 'LineEnd', 'LineStart', 'Literal', -'MatchFirst', 'NoMatch', 'NotAny', 'OneOrMore', 'OnlyOnce', 'Optional', 'Or', -'ParseBaseException', 'ParseElementEnhance', 'ParseException', 'ParseExpression', 'ParseFatalException', -'ParseResults', 'ParseSyntaxException', 'ParserElement', 'QuotedString', 'RecursiveGrammarException', -'Regex', 'SkipTo', 'StringEnd', 'StringStart', 'Suppress', 'Token', 'TokenConverter', 'Upcase', -'White', 'Word', 'WordEnd', 'WordStart', 'ZeroOrMore', -'alphanums', 'alphas', 'alphas8bit', 'anyCloseTag', 'anyOpenTag', 'cStyleComment', 'col', -'commaSeparatedList', 'commonHTMLEntity', 'countedArray', 'cppStyleComment', 'dblQuotedString', -'dblSlashComment', 'delimitedList', 'dictOf', 'downcaseTokens', 'empty', 'hexnums', -'htmlComment', 'javaStyleComment', 'keepOriginalText', 'line', 'lineEnd', 'lineStart', 'lineno', -'makeHTMLTags', 'makeXMLTags', 'matchOnlyAtCol', 'matchPreviousExpr', 'matchPreviousLiteral', -'nestedExpr', 'nullDebugAction', 'nums', 'oneOf', 'opAssoc', 'operatorPrecedence', 'printables', -'punc8bit', 'pythonStyleComment', 'quotedString', 'removeQuotes', 'replaceHTMLEntity', -'replaceWith', 'restOfLine', 'sglQuotedString', 'srange', 'stringEnd', -'stringStart', 'traceParseAction', 'unicodeString', 'upcaseTokens', 'withAttribute', -'indentedBlock', 'originalTextFor', 'ungroup', 'infixNotation', -] - -_MAX_INT = sys.maxint -range = xrange -set = lambda s : dict( [(c,0) for c in s] ) - +# __doc__ = \ +# """ +# pyparsing module - Classes and methods to define and execute parsing grammars +# +# The pyparsing module is an alternative approach to creating and executing simple grammars, +# vs. the traditional lex/yacc approach, or the use of regular expressions. With pyparsing, you +# don't need to learn a new syntax for defining grammars or matching expressions - the parsing module +# provides a library of classes that you use to construct the grammar directly in Python. +# +# Here is a program to parse "Hello, World!" (or any greeting of the form C{", !"}):: +# +# from pyparsing import Word, alphas +# +# # define grammar of a greeting +# greet = Word( alphas ) + "," + Word( alphas ) + "!" +# +# hello = "Hello, World!" +# print hello, "->", greet.parseString( hello ) +# +# The program outputs the following:: +# +# Hello, World! -> ['Hello', ',', 'World', '!'] +# +# The Python representation of the grammar is quite readable, owing to the self-explanatory +# class names, and the use of '+', '|' and '^' operators. +# +# The parsed results returned from C{parseString()} can be accessed as a nested list, a dictionary, or an +# object with named attributes. +# +# The pyparsing module handles some of the problems that are typically vexing when writing text parsers: +# - extra or missing whitespace (the above program will also handle "Hello,World!", "Hello , World !", etc.) +# - quoted strings +# - embedded comments +# """ +# +# __version__ = "1.5.7" +# __versionTime__ = "17 November 2012 16:18" +# __author__ = "Paul McGuire " +# +# import string +# from weakref import ref as wkref +# import copy +# import sys +# import warnings +# import re +# import sre_constants +# #~ sys.stderr.write( "testing pyparsing module, version %s, %s\n" % (__version__,__versionTime__ ) ) +# +# __all__ = [ +# 'And', 'CaselessKeyword', 'CaselessLiteral', 'CharsNotIn', 'Combine', 'Dict', 'Each', 'Empty', +# 'FollowedBy', 'Forward', 'GoToColumn', 'Group', 'Keyword', 'LineEnd', 'LineStart', 'Literal', +# 'MatchFirst', 'NoMatch', 'NotAny', 'OneOrMore', 'OnlyOnce', 'Optional', 'Or', +# 'ParseBaseException', 'ParseElementEnhance', 'ParseException', 'ParseExpression', 'ParseFatalException', +# 'ParseResults', 'ParseSyntaxException', 'ParserElement', 'QuotedString', 'RecursiveGrammarException', +# 'Regex', 'SkipTo', 'StringEnd', 'StringStart', 'Suppress', 'Token', 'TokenConverter', 'Upcase', +# 'White', 'Word', 'WordEnd', 'WordStart', 'ZeroOrMore', +# 'alphanums', 'alphas', 'alphas8bit', 'anyCloseTag', 'anyOpenTag', 'cStyleComment', 'col', +# 'commaSeparatedList', 'commonHTMLEntity', 'countedArray', 'cppStyleComment', 'dblQuotedString', +# 'dblSlashComment', 'delimitedList', 'dictOf', 'downcaseTokens', 'empty', 'hexnums', +# 'htmlComment', 'javaStyleComment', 'keepOriginalText', 'line', 'lineEnd', 'lineStart', 'lineno', +# 'makeHTMLTags', 'makeXMLTags', 'matchOnlyAtCol', 'matchPreviousExpr', 'matchPreviousLiteral', +# 'nestedExpr', 'nullDebugAction', 'nums', 'oneOf', 'opAssoc', 'operatorPrecedence', 'printables', +# 'punc8bit', 'pythonStyleComment', 'quotedString', 'removeQuotes', 'replaceHTMLEntity', +# 'replaceWith', 'restOfLine', 'sglQuotedString', 'srange', 'stringEnd', +# 'stringStart', 'traceParseAction', 'unicodeString', 'upcaseTokens', 'withAttribute', +# 'indentedBlock', 'originalTextFor', 'ungroup', 'infixNotation', +# ] +# +# _MAX_INT = sys.maxint +# range = xrange +# set = lambda s : dict( [(c,0) for c in s] ) +# def _ustr(obj): """Drop-in replacement for str(obj) that tries to be Unicode friendly. It first tries str(obj). If that fails with a UnicodeEncodeError, then it tries unicode(obj). It @@ -122,35 +122,35 @@ def _ustr(obj): #return unicode(obj).encode(sys.getdefaultencoding(), 'replace') # ... -# build list of single arg builtins, tolerant of Python version, that can be used as parse actions -singleArgBuiltins = [] -import __builtin__ -for fname in "sum len sorted reversed list tuple set any all min max".split(): - try: - singleArgBuiltins.append(getattr(__builtin__,fname)) - except AttributeError: - continue - -def _xml_escape(data): - """Escape &, <, >, ", ', etc. in a string of data.""" - - # ampersand must be replaced first - from_symbols = '&><"\'' - to_symbols = ['&'+s+';' for s in "amp gt lt quot apos".split()] - for from_,to_ in zip(from_symbols, to_symbols): - data = data.replace(from_, to_) - return data - -class _Constants(object): - pass - -alphas = string.ascii_lowercase + string.ascii_uppercase -nums = "0123456789" -hexnums = nums + "ABCDEFabcdef" -alphanums = alphas + nums -_bslash = chr(92) -printables = "".join( [ c for c in string.printable if c not in string.whitespace ] ) - +# # build list of single arg builtins, tolerant of Python version, that can be used as parse actions +# singleArgBuiltins = [] +# import __builtin__ +# for fname in "sum len sorted reversed list tuple set any all min max".split(): +# try: +# singleArgBuiltins.append(getattr(__builtin__,fname)) +# except AttributeError: +# continue +# +# def _xml_escape(data): +# """Escape &, <, >, ", ', etc. in a string of data.""" +# +# # ampersand must be replaced first +# from_symbols = '&><"\'' +# to_symbols = ['&'+s+';' for s in "amp gt lt quot apos".split()] +# for from_,to_ in zip(from_symbols, to_symbols): +# data = data.replace(from_, to_) +# return data +# +# class _Constants(object): +# pass +# +# alphas = string.ascii_lowercase + string.ascii_uppercase +# nums = "0123456789" +# hexnums = nums + "ABCDEFabcdef" +# alphanums = alphas + nums +# _bslash = chr(92) +# printables = "".join( [ c for c in string.printable if c not in string.whitespace ] ) +# class ParseBaseException(Exception): """base exception class for all parsing runtime exceptions""" # Performance tuning: we construct a *lot* of these, so keep this @@ -172,11 +172,11 @@ class ParseBaseException(Exception): - line - returns the line containing the exception text """ if( aname == "lineno" ): - return lineno( self.loc, self.pstr ) + return 1 #lineno( self.loc, self.pstr ) elif( aname in ("col", "column") ): - return col( self.loc, self.pstr ) + return 1 #col( self.loc, self.pstr ) elif( aname == "line" ): - return line( self.loc, self.pstr ) + return 1 #line( self.loc, self.pstr ) else: raise AttributeError(aname) @@ -208,3518 +208,3518 @@ class ParseException(ParseBaseException): """ pass -class ParseFatalException(ParseBaseException): - """user-throwable exception thrown when inconsistent parse content - is found; stops all parsing immediately""" - pass - -class ParseSyntaxException(ParseFatalException): - """just like C{L{ParseFatalException}}, but thrown internally when an - C{L{ErrorStop}} ('-' operator) indicates that parsing is to stop immediately because - an unbacktrackable syntax error has been found""" - def __init__(self, pe): - super(ParseSyntaxException, self).__init__( - pe.pstr, pe.loc, pe.msg, pe.parserElement) - -#~ class ReparseException(ParseBaseException): - #~ """Experimental class - parse actions can raise this exception to cause - #~ pyparsing to reparse the input string: - #~ - with a modified input string, and/or - #~ - with a modified start location - #~ Set the values of the ReparseException in the constructor, and raise the - #~ exception in a parse action to cause pyparsing to use the new string/location. - #~ Setting the values as None causes no change to be made. - #~ """ - #~ def __init_( self, newstring, restartLoc ): - #~ self.newParseText = newstring - #~ self.reparseLoc = restartLoc - -class RecursiveGrammarException(Exception): - """exception thrown by C{validate()} if the grammar could be improperly recursive""" - def __init__( self, parseElementList ): - self.parseElementTrace = parseElementList - - def __str__( self ): - return "RecursiveGrammarException: %s" % self.parseElementTrace - -class _ParseResultsWithOffset(object): - def __init__(self,p1,p2): - self.tup = (p1,p2) - def __getitem__(self,i): - return self.tup[i] - def __repr__(self): - return repr(self.tup) - def setOffset(self,i): - self.tup = (self.tup[0],i) - -class ParseResults(object): - """Structured parse results, to provide multiple means of access to the parsed data: - - as a list (C{len(results)}) - - by list index (C{results[0], results[1]}, etc.) - - by attribute (C{results.}) - """ - #~ __slots__ = ( "__toklist", "__tokdict", "__doinit", "__name", "__parent", "__accumNames", "__weakref__" ) - def __new__(cls, toklist, name=None, asList=True, modal=True ): - if isinstance(toklist, cls): - return toklist - retobj = object.__new__(cls) - retobj.__doinit = True - return retobj - - # Performance tuning: we construct a *lot* of these, so keep this - # constructor as small and fast as possible - def __init__( self, toklist, name=None, asList=True, modal=True, isinstance=isinstance ): - if self.__doinit: - self.__doinit = False - self.__name = None - self.__parent = None - self.__accumNames = {} - if isinstance(toklist, list): - self.__toklist = toklist[:] - else: - self.__toklist = [toklist] - self.__tokdict = dict() - - if name is not None and name: - if not modal: - self.__accumNames[name] = 0 - if isinstance(name,int): - name = _ustr(name) # will always return a str, but use _ustr for consistency - self.__name = name - if not toklist in (None,'',[]): - if isinstance(toklist,basestring): - toklist = [ toklist ] - if asList: - if isinstance(toklist,ParseResults): - self[name] = _ParseResultsWithOffset(toklist.copy(),0) - else: - self[name] = _ParseResultsWithOffset(ParseResults(toklist[0]),0) - self[name].__name = name - else: - try: - self[name] = toklist[0] - except (KeyError,TypeError,IndexError): - self[name] = toklist - - def __getitem__( self, i ): - if isinstance( i, (int,slice) ): - return self.__toklist[i] - else: - if i not in self.__accumNames: - return self.__tokdict[i][-1][0] - else: - return ParseResults([ v[0] for v in self.__tokdict[i] ]) - - def __setitem__( self, k, v, isinstance=isinstance ): - if isinstance(v,_ParseResultsWithOffset): - self.__tokdict[k] = self.__tokdict.get(k,list()) + [v] - sub = v[0] - elif isinstance(k,int): - self.__toklist[k] = v - sub = v - else: - self.__tokdict[k] = self.__tokdict.get(k,list()) + [_ParseResultsWithOffset(v,0)] - sub = v - if isinstance(sub,ParseResults): - sub.__parent = wkref(self) - - def __delitem__( self, i ): - if isinstance(i,(int,slice)): - mylen = len( self.__toklist ) - del self.__toklist[i] - - # convert int to slice - if isinstance(i, int): - if i < 0: - i += mylen - i = slice(i, i+1) - # get removed indices - removed = list(range(*i.indices(mylen))) - removed.reverse() - # fixup indices in token dictionary - for name in self.__tokdict: - occurrences = self.__tokdict[name] - for j in removed: - for k, (value, position) in enumerate(occurrences): - occurrences[k] = _ParseResultsWithOffset(value, position - (position > j)) - else: - del self.__tokdict[i] - - def __contains__( self, k ): - return k in self.__tokdict - - def __len__( self ): return len( self.__toklist ) - def __bool__(self): return len( self.__toklist ) > 0 - __nonzero__ = __bool__ - def __iter__( self ): return iter( self.__toklist ) - def __reversed__( self ): return iter( self.__toklist[::-1] ) - def keys( self ): - """Returns all named result keys.""" - return self.__tokdict.keys() - - def pop( self, index=-1 ): - """Removes and returns item at specified index (default=last). - Will work with either numeric indices or dict-key indicies.""" - ret = self[index] - del self[index] - return ret - - def get(self, key, defaultValue=None): - """Returns named result matching the given key, or if there is no - such name, then returns the given C{defaultValue} or C{None} if no - C{defaultValue} is specified.""" - if key in self: - return self[key] - else: - return defaultValue - - def insert( self, index, insStr ): - """Inserts new element at location index in the list of parsed tokens.""" - self.__toklist.insert(index, insStr) - # fixup indices in token dictionary - for name in self.__tokdict: - occurrences = self.__tokdict[name] - for k, (value, position) in enumerate(occurrences): - occurrences[k] = _ParseResultsWithOffset(value, position + (position > index)) - - def items( self ): - """Returns all named result keys and values as a list of tuples.""" - return [(k,self[k]) for k in self.__tokdict] - - def values( self ): - """Returns all named result values.""" - return [ v[-1][0] for v in self.__tokdict.values() ] - - def __getattr__( self, name ): - if True: #name not in self.__slots__: - if name in self.__tokdict: - if name not in self.__accumNames: - return self.__tokdict[name][-1][0] - else: - return ParseResults([ v[0] for v in self.__tokdict[name] ]) - else: - return "" - return None - - def __add__( self, other ): - ret = self.copy() - ret += other - return ret - - def __iadd__( self, other ): - if other.__tokdict: - offset = len(self.__toklist) - addoffset = ( lambda a: (a<0 and offset) or (a+offset) ) - otheritems = other.__tokdict.items() - otherdictitems = [(k, _ParseResultsWithOffset(v[0],addoffset(v[1])) ) - for (k,vlist) in otheritems for v in vlist] - for k,v in otherdictitems: - self[k] = v - if isinstance(v[0],ParseResults): - v[0].__parent = wkref(self) - - self.__toklist += other.__toklist - self.__accumNames.update( other.__accumNames ) - return self - - def __radd__(self, other): - if isinstance(other,int) and other == 0: - return self.copy() - - def __repr__( self ): - return "(%s, %s)" % ( repr( self.__toklist ), repr( self.__tokdict ) ) - - def __str__( self ): - out = [] - for i in self.__toklist: - if isinstance(i, ParseResults): - out.append(_ustr(i)) - else: - out.append(repr(i)) - return '[' + ', '.join(out) + ']' - - def _asStringList( self, sep='' ): - out = [] - for item in self.__toklist: - if out and sep: - out.append(sep) - if isinstance( item, ParseResults ): - out += item._asStringList() - else: - out.append( _ustr(item) ) - return out - - def asList( self ): - """Returns the parse results as a nested list of matching tokens, all converted to strings.""" - out = [] - for res in self.__toklist: - if isinstance(res,ParseResults): - out.append( res.asList() ) - else: - out.append( res ) - return out - - def asDict( self ): - """Returns the named parse results as dictionary.""" - return dict( self.items() ) - - def copy( self ): - """Returns a new copy of a C{ParseResults} object.""" - ret = ParseResults( self.__toklist ) - ret.__tokdict = self.__tokdict.copy() - ret.__parent = self.__parent - ret.__accumNames.update( self.__accumNames ) - ret.__name = self.__name - return ret - - def asXML( self, doctag=None, namedItemsOnly=False, indent="", formatted=True ): - """Returns the parse results as XML. Tags are created for tokens and lists that have defined results names.""" - nl = "\n" - out = [] - namedItems = dict( [ (v[1],k) for (k,vlist) in self.__tokdict.items() - for v in vlist ] ) - nextLevelIndent = indent + " " - - # collapse out indents if formatting is not desired - if not formatted: - indent = "" - nextLevelIndent = "" - nl = "" - - selfTag = None - if doctag is not None: - selfTag = doctag - else: - if self.__name: - selfTag = self.__name - - if not selfTag: - if namedItemsOnly: - return "" - else: - selfTag = "ITEM" - - out += [ nl, indent, "<", selfTag, ">" ] - - worklist = self.__toklist - for i,res in enumerate(worklist): - if isinstance(res,ParseResults): - if i in namedItems: - out += [ res.asXML(namedItems[i], - namedItemsOnly and doctag is None, - nextLevelIndent, - formatted)] - else: - out += [ res.asXML(None, - namedItemsOnly and doctag is None, - nextLevelIndent, - formatted)] - else: - # individual token, see if there is a name for it - resTag = None - if i in namedItems: - resTag = namedItems[i] - if not resTag: - if namedItemsOnly: - continue - else: - resTag = "ITEM" - xmlBodyText = _xml_escape(_ustr(res)) - out += [ nl, nextLevelIndent, "<", resTag, ">", - xmlBodyText, - "" ] - - out += [ nl, indent, "" ] - return "".join(out) - - def __lookup(self,sub): - for k,vlist in self.__tokdict.items(): - for v,loc in vlist: - if sub is v: - return k - return None - - def getName(self): - """Returns the results name for this token expression.""" - if self.__name: - return self.__name - elif self.__parent: - par = self.__parent() - if par: - return par.__lookup(self) - else: - return None - elif (len(self) == 1 and - len(self.__tokdict) == 1 and - self.__tokdict.values()[0][0][1] in (0,-1)): - return self.__tokdict.keys()[0] - else: - return None - - def dump(self,indent='',depth=0): - """Diagnostic method for listing out the contents of a C{ParseResults}. - Accepts an optional C{indent} argument so that this string can be embedded - in a nested display of other data.""" - out = [] - out.append( indent+_ustr(self.asList()) ) - keys = self.items() - keys.sort() - for k,v in keys: - if out: - out.append('\n') - out.append( "%s%s- %s: " % (indent,(' '*depth), k) ) - if isinstance(v,ParseResults): - if v.keys(): - out.append( v.dump(indent,depth+1) ) - else: - out.append(_ustr(v)) - else: - out.append(_ustr(v)) - return "".join(out) - - # add support for pickle protocol - def __getstate__(self): - return ( self.__toklist, - ( self.__tokdict.copy(), - self.__parent is not None and self.__parent() or None, - self.__accumNames, - self.__name ) ) - - def __setstate__(self,state): - self.__toklist = state[0] - (self.__tokdict, - par, - inAccumNames, - self.__name) = state[1] - self.__accumNames = {} - self.__accumNames.update(inAccumNames) - if par is not None: - self.__parent = wkref(par) - else: - self.__parent = None - - def __dir__(self): - return dir(super(ParseResults,self)) + list(self.keys()) - -def col (loc,strg): - """Returns current column within a string, counting newlines as line separators. - The first column is number 1. - - Note: the default parsing behavior is to expand tabs in the input string - before starting the parsing process. See L{I{ParserElement.parseString}} for more information - on parsing strings containing C{}s, and suggested methods to maintain a - consistent view of the parsed string, the parse location, and line and column - positions within the parsed string. - """ - return (loc} for more information - on parsing strings containing C{}s, and suggested methods to maintain a - consistent view of the parsed string, the parse location, and line and column - positions within the parsed string. - """ - return strg.count("\n",0,loc) + 1 - -def line( loc, strg ): - """Returns the line of text containing loc within a string, counting newlines as line separators. - """ - lastCR = strg.rfind("\n", 0, loc) - nextCR = strg.find("\n", loc) - if nextCR >= 0: - return strg[lastCR+1:nextCR] - else: - return strg[lastCR+1:] - -def _defaultStartDebugAction( instring, loc, expr ): - print ("Match " + _ustr(expr) + " at loc " + _ustr(loc) + "(%d,%d)" % ( lineno(loc,instring), col(loc,instring) )) - -def _defaultSuccessDebugAction( instring, startloc, endloc, expr, toks ): - print ("Matched " + _ustr(expr) + " -> " + str(toks.asList())) - -def _defaultExceptionDebugAction( instring, loc, expr, exc ): - print ("Exception raised:" + _ustr(exc)) - -def nullDebugAction(*args): - """'Do-nothing' debug action, to suppress debugging output during parsing.""" - pass - -'decorator to trim function calls to match the arity of the target' -def _trim_arity(func, maxargs=2): - if func in singleArgBuiltins: - return lambda s,l,t: func(t) - limit = [0] - foundArity = [False] - def wrapper(*args): - while 1: - try: - ret = func(*args[limit[0]:]) - foundArity[0] = True - return ret - except TypeError: - if limit[0] <= maxargs and not foundArity[0]: - limit[0] += 1 - continue - raise - return wrapper - -class ParserElement(object): - """Abstract base level parser element class.""" - DEFAULT_WHITE_CHARS = " \n\t\r" - verbose_stacktrace = False - - def setDefaultWhitespaceChars( chars ): - """Overrides the default whitespace chars - """ - ParserElement.DEFAULT_WHITE_CHARS = chars - setDefaultWhitespaceChars = staticmethod(setDefaultWhitespaceChars) - - def inlineLiteralsUsing(cls): - """ - Set class to be used for inclusion of string literals into a parser. - """ - ParserElement.literalStringClass = cls - inlineLiteralsUsing = staticmethod(inlineLiteralsUsing) - - def __init__( self, savelist=False ): - self.parseAction = list() - self.failAction = None - #~ self.name = "" # don't define self.name, let subclasses try/except upcall - self.strRepr = None - self.resultsName = None - self.saveAsList = savelist - self.skipWhitespace = True - self.whiteChars = ParserElement.DEFAULT_WHITE_CHARS - self.copyDefaultWhiteChars = True - self.mayReturnEmpty = False # used when checking for left-recursion - self.keepTabs = False - self.ignoreExprs = list() - self.debug = False - self.streamlined = False - self.mayIndexError = True # used to optimize exception handling for subclasses that don't advance parse index - self.errmsg = "" - self.modalResults = True # used to mark results names as modal (report only last) or cumulative (list all) - self.debugActions = ( None, None, None ) #custom debug actions - self.re = None - self.callPreparse = True # used to avoid redundant calls to preParse - self.callDuringTry = False - - def copy( self ): - """Make a copy of this C{ParserElement}. Useful for defining different parse actions - for the same parsing pattern, using copies of the original parse element.""" - cpy = copy.copy( self ) - cpy.parseAction = self.parseAction[:] - cpy.ignoreExprs = self.ignoreExprs[:] - if self.copyDefaultWhiteChars: - cpy.whiteChars = ParserElement.DEFAULT_WHITE_CHARS - return cpy - - def setName( self, name ): - """Define name for this expression, for use in debugging.""" - self.name = name - self.errmsg = "Expected " + self.name - if hasattr(self,"exception"): - self.exception.msg = self.errmsg - return self - - def setResultsName( self, name, listAllMatches=False ): - """Define name for referencing matching tokens as a nested attribute - of the returned parse results. - NOTE: this returns a *copy* of the original C{ParserElement} object; - this is so that the client can define a basic element, such as an - integer, and reference it in multiple places with different names. - - You can also set results names using the abbreviated syntax, - C{expr("name")} in place of C{expr.setResultsName("name")} - - see L{I{__call__}<__call__>}. - """ - newself = self.copy() - if name.endswith("*"): - name = name[:-1] - listAllMatches=True - newself.resultsName = name - newself.modalResults = not listAllMatches - return newself - - def setBreak(self,breakFlag = True): - """Method to invoke the Python pdb debugger when this element is - about to be parsed. Set C{breakFlag} to True to enable, False to - disable. - """ - if breakFlag: - _parseMethod = self._parse - def breaker(instring, loc, doActions=True, callPreParse=True): - import pdb - pdb.set_trace() - return _parseMethod( instring, loc, doActions, callPreParse ) - breaker._originalParseMethod = _parseMethod - self._parse = breaker - else: - if hasattr(self._parse,"_originalParseMethod"): - self._parse = self._parse._originalParseMethod - return self - - def setParseAction( self, *fns, **kwargs ): - """Define action to perform when successfully matching parse element definition. - Parse action fn is a callable method with 0-3 arguments, called as C{fn(s,loc,toks)}, - C{fn(loc,toks)}, C{fn(toks)}, or just C{fn()}, where: - - s = the original string being parsed (see note below) - - loc = the location of the matching substring - - toks = a list of the matched tokens, packaged as a C{L{ParseResults}} object - If the functions in fns modify the tokens, they can return them as the return - value from fn, and the modified list of tokens will replace the original. - Otherwise, fn does not need to return any value. - - Note: the default parsing behavior is to expand tabs in the input string - before starting the parsing process. See L{I{parseString}} for more information - on parsing strings containing C{}s, and suggested methods to maintain a - consistent view of the parsed string, the parse location, and line and column - positions within the parsed string. - """ - self.parseAction = list(map(_trim_arity, list(fns))) - self.callDuringTry = ("callDuringTry" in kwargs and kwargs["callDuringTry"]) - return self - - def addParseAction( self, *fns, **kwargs ): - """Add parse action to expression's list of parse actions. See L{I{setParseAction}}.""" - self.parseAction += list(map(_trim_arity, list(fns))) - self.callDuringTry = self.callDuringTry or ("callDuringTry" in kwargs and kwargs["callDuringTry"]) - return self - - def setFailAction( self, fn ): - """Define action to perform if parsing fails at this expression. - Fail acton fn is a callable function that takes the arguments - C{fn(s,loc,expr,err)} where: - - s = string being parsed - - loc = location where expression match was attempted and failed - - expr = the parse expression that failed - - err = the exception thrown - The function returns no value. It may throw C{L{ParseFatalException}} - if it is desired to stop parsing immediately.""" - self.failAction = fn - return self - - def _skipIgnorables( self, instring, loc ): - exprsFound = True - while exprsFound: - exprsFound = False - for e in self.ignoreExprs: - try: - while 1: - loc,dummy = e._parse( instring, loc ) - exprsFound = True - except ParseException: - pass - return loc - - def preParse( self, instring, loc ): - if self.ignoreExprs: - loc = self._skipIgnorables( instring, loc ) - - if self.skipWhitespace: - wt = self.whiteChars - instrlen = len(instring) - while loc < instrlen and instring[loc] in wt: - loc += 1 - - return loc - - def parseImpl( self, instring, loc, doActions=True ): - return loc, [] - - def postParse( self, instring, loc, tokenlist ): - return tokenlist - - #~ @profile - def _parseNoCache( self, instring, loc, doActions=True, callPreParse=True ): - debugging = ( self.debug ) #and doActions ) - - if debugging or self.failAction: - #~ print ("Match",self,"at loc",loc,"(%d,%d)" % ( lineno(loc,instring), col(loc,instring) )) - if (self.debugActions[0] ): - self.debugActions[0]( instring, loc, self ) - if callPreParse and self.callPreparse: - preloc = self.preParse( instring, loc ) - else: - preloc = loc - tokensStart = preloc - try: - try: - loc,tokens = self.parseImpl( instring, preloc, doActions ) - except IndexError: - raise ParseException( instring, len(instring), self.errmsg, self ) - except ParseBaseException, err: - #~ print ("Exception raised:", err) - err = None - if self.debugActions[2]: - self.debugActions[2]( instring, tokensStart, self, err ) - if self.failAction: - self.failAction( instring, tokensStart, self, err ) - raise - else: - if callPreParse and self.callPreparse: - preloc = self.preParse( instring, loc ) - else: - preloc = loc - tokensStart = preloc - if self.mayIndexError or loc >= len(instring): - try: - loc,tokens = self.parseImpl( instring, preloc, doActions ) - except IndexError: - raise ParseException( instring, len(instring), self.errmsg, self ) - else: - loc,tokens = self.parseImpl( instring, preloc, doActions ) - - tokens = self.postParse( instring, loc, tokens ) - - retTokens = ParseResults( tokens, self.resultsName, asList=self.saveAsList, modal=self.modalResults ) - if self.parseAction and (doActions or self.callDuringTry): - if debugging: - try: - for fn in self.parseAction: - tokens = fn( instring, tokensStart, retTokens ) - if tokens is not None: - retTokens = ParseResults( tokens, - self.resultsName, - asList=self.saveAsList and isinstance(tokens,(ParseResults,list)), - modal=self.modalResults ) - except ParseBaseException, err: - #~ print "Exception raised in user parse action:", err - if (self.debugActions[2] ): - self.debugActions[2]( instring, tokensStart, self, err ) - raise - else: - for fn in self.parseAction: - tokens = fn( instring, tokensStart, retTokens ) - if tokens is not None: - retTokens = ParseResults( tokens, - self.resultsName, - asList=self.saveAsList and isinstance(tokens,(ParseResults,list)), - modal=self.modalResults ) - - if debugging: - #~ print ("Matched",self,"->",retTokens.asList()) - if (self.debugActions[1] ): - self.debugActions[1]( instring, tokensStart, loc, self, retTokens ) - - return loc, retTokens - - def tryParse( self, instring, loc ): - try: - return self._parse( instring, loc, doActions=False )[0] - except ParseFatalException: - raise ParseException( instring, loc, self.errmsg, self) - - # this method gets repeatedly called during backtracking with the same arguments - - # we can cache these arguments and save ourselves the trouble of re-parsing the contained expression - def _parseCache( self, instring, loc, doActions=True, callPreParse=True ): - lookup = (self,instring,loc,callPreParse,doActions) - if lookup in ParserElement._exprArgCache: - value = ParserElement._exprArgCache[ lookup ] - if isinstance(value, Exception): - raise value - return (value[0],value[1].copy()) - else: - try: - value = self._parseNoCache( instring, loc, doActions, callPreParse ) - ParserElement._exprArgCache[ lookup ] = (value[0],value[1].copy()) - return value - except ParseBaseException, pe: - ParserElement._exprArgCache[ lookup ] = pe - raise - - _parse = _parseNoCache - - # argument cache for optimizing repeated calls when backtracking through recursive expressions - _exprArgCache = {} - def resetCache(): - ParserElement._exprArgCache.clear() - resetCache = staticmethod(resetCache) - - _packratEnabled = False - def enablePackrat(): - """Enables "packrat" parsing, which adds memoizing to the parsing logic. - Repeated parse attempts at the same string location (which happens - often in many complex grammars) can immediately return a cached value, - instead of re-executing parsing/validating code. Memoizing is done of - both valid results and parsing exceptions. - - This speedup may break existing programs that use parse actions that - have side-effects. For this reason, packrat parsing is disabled when - you first import pyparsing. To activate the packrat feature, your - program must call the class method C{ParserElement.enablePackrat()}. If - your program uses C{psyco} to "compile as you go", you must call - C{enablePackrat} before calling C{psyco.full()}. If you do not do this, - Python will crash. For best results, call C{enablePackrat()} immediately - after importing pyparsing. - """ - if not ParserElement._packratEnabled: - ParserElement._packratEnabled = True - ParserElement._parse = ParserElement._parseCache - enablePackrat = staticmethod(enablePackrat) - - def parseString( self, instring, parseAll=False ): - """Execute the parse expression with the given string. - This is the main interface to the client code, once the complete - expression has been built. - - If you want the grammar to require that the entire input string be - successfully parsed, then set C{parseAll} to True (equivalent to ending - the grammar with C{L{StringEnd()}}). - - Note: C{parseString} implicitly calls C{expandtabs()} on the input string, - in order to report proper column numbers in parse actions. - If the input string contains tabs and - the grammar uses parse actions that use the C{loc} argument to index into the - string being parsed, you can ensure you have a consistent view of the input - string by: - - calling C{parseWithTabs} on your grammar before calling C{parseString} - (see L{I{parseWithTabs}}) - - define your parse action using the full C{(s,loc,toks)} signature, and - reference the input string using the parse action's C{s} argument - - explictly expand the tabs in your input string before calling - C{parseString} - """ - ParserElement.resetCache() - if not self.streamlined: - self.streamline() - #~ self.saveAsList = True - for e in self.ignoreExprs: - e.streamline() - if not self.keepTabs: - instring = instring.expandtabs() - try: - loc, tokens = self._parse( instring, 0 ) - if parseAll: - loc = self.preParse( instring, loc ) - se = Empty() + StringEnd() - se._parse( instring, loc ) - except ParseBaseException, exc: - if ParserElement.verbose_stacktrace: - raise - else: - # catch and re-raise exception from here, clears out pyparsing internal stack trace - raise exc - else: - return tokens - - def scanString( self, instring, maxMatches=_MAX_INT, overlap=False ): - """Scan the input string for expression matches. Each match will return the - matching tokens, start location, and end location. May be called with optional - C{maxMatches} argument, to clip scanning after 'n' matches are found. If - C{overlap} is specified, then overlapping matches will be reported. - - Note that the start and end locations are reported relative to the string - being parsed. See L{I{parseString}} for more information on parsing - strings with embedded tabs.""" - if not self.streamlined: - self.streamline() - for e in self.ignoreExprs: - e.streamline() - - if not self.keepTabs: - instring = _ustr(instring).expandtabs() - instrlen = len(instring) - loc = 0 - preparseFn = self.preParse - parseFn = self._parse - ParserElement.resetCache() - matches = 0 - try: - while loc <= instrlen and matches < maxMatches: - try: - preloc = preparseFn( instring, loc ) - nextLoc,tokens = parseFn( instring, preloc, callPreParse=False ) - except ParseException: - loc = preloc+1 - else: - if nextLoc > loc: - matches += 1 - yield tokens, preloc, nextLoc - if overlap: - nextloc = preparseFn( instring, loc ) - if nextloc > loc: - loc = nextLoc - else: - loc += 1 - else: - loc = nextLoc - else: - loc = preloc+1 - except ParseBaseException, exc: - if ParserElement.verbose_stacktrace: - raise - else: - # catch and re-raise exception from here, clears out pyparsing internal stack trace - raise exc - - def transformString( self, instring ): - """Extension to C{L{scanString}}, to modify matching text with modified tokens that may - be returned from a parse action. To use C{transformString}, define a grammar and - attach a parse action to it that modifies the returned token list. - Invoking C{transformString()} on a target string will then scan for matches, - and replace the matched text patterns according to the logic in the parse - action. C{transformString()} returns the resulting transformed string.""" - out = [] - lastE = 0 - # force preservation of s, to minimize unwanted transformation of string, and to - # keep string locs straight between transformString and scanString - self.keepTabs = True - try: - for t,s,e in self.scanString( instring ): - out.append( instring[lastE:s] ) - if t: - if isinstance(t,ParseResults): - out += t.asList() - elif isinstance(t,list): - out += t - else: - out.append(t) - lastE = e - out.append(instring[lastE:]) - out = [o for o in out if o] - return "".join(map(_ustr,_flatten(out))) - except ParseBaseException, exc: - if ParserElement.verbose_stacktrace: - raise - else: - # catch and re-raise exception from here, clears out pyparsing internal stack trace - raise exc - - def searchString( self, instring, maxMatches=_MAX_INT ): - """Another extension to C{L{scanString}}, simplifying the access to the tokens found - to match the given parse expression. May be called with optional - C{maxMatches} argument, to clip searching after 'n' matches are found. - """ - try: - return ParseResults([ t for t,s,e in self.scanString( instring, maxMatches ) ]) - except ParseBaseException, exc: - if ParserElement.verbose_stacktrace: - raise - else: - # catch and re-raise exception from here, clears out pyparsing internal stack trace - raise exc - - def __add__(self, other ): - """Implementation of + operator - returns C{L{And}}""" - if isinstance( other, basestring ): - other = ParserElement.literalStringClass( other ) - if not isinstance( other, ParserElement ): - warnings.warn("Cannot combine element of type %s with ParserElement" % type(other), - SyntaxWarning, stacklevel=2) - return None - return And( [ self, other ] ) - - def __radd__(self, other ): - """Implementation of + operator when left operand is not a C{L{ParserElement}}""" - if isinstance( other, basestring ): - other = ParserElement.literalStringClass( other ) - if not isinstance( other, ParserElement ): - warnings.warn("Cannot combine element of type %s with ParserElement" % type(other), - SyntaxWarning, stacklevel=2) - return None - return other + self - - def __sub__(self, other): - """Implementation of - operator, returns C{L{And}} with error stop""" - if isinstance( other, basestring ): - other = ParserElement.literalStringClass( other ) - if not isinstance( other, ParserElement ): - warnings.warn("Cannot combine element of type %s with ParserElement" % type(other), - SyntaxWarning, stacklevel=2) - return None - return And( [ self, And._ErrorStop(), other ] ) - - def __rsub__(self, other ): - """Implementation of - operator when left operand is not a C{L{ParserElement}}""" - if isinstance( other, basestring ): - other = ParserElement.literalStringClass( other ) - if not isinstance( other, ParserElement ): - warnings.warn("Cannot combine element of type %s with ParserElement" % type(other), - SyntaxWarning, stacklevel=2) - return None - return other - self - - def __mul__(self,other): - """Implementation of * operator, allows use of C{expr * 3} in place of - C{expr + expr + expr}. Expressions may also me multiplied by a 2-integer - tuple, similar to C{{min,max}} multipliers in regular expressions. Tuples - may also include C{None} as in: - - C{expr*(n,None)} or C{expr*(n,)} is equivalent - to C{expr*n + L{ZeroOrMore}(expr)} - (read as "at least n instances of C{expr}") - - C{expr*(None,n)} is equivalent to C{expr*(0,n)} - (read as "0 to n instances of C{expr}") - - C{expr*(None,None)} is equivalent to C{L{ZeroOrMore}(expr)} - - C{expr*(1,None)} is equivalent to C{L{OneOrMore}(expr)} - - Note that C{expr*(None,n)} does not raise an exception if - more than n exprs exist in the input stream; that is, - C{expr*(None,n)} does not enforce a maximum number of expr - occurrences. If this behavior is desired, then write - C{expr*(None,n) + ~expr} - - """ - if isinstance(other,int): - minElements, optElements = other,0 - elif isinstance(other,tuple): - other = (other + (None, None))[:2] - if other[0] is None: - other = (0, other[1]) - if isinstance(other[0],int) and other[1] is None: - if other[0] == 0: - return ZeroOrMore(self) - if other[0] == 1: - return OneOrMore(self) - else: - return self*other[0] + ZeroOrMore(self) - elif isinstance(other[0],int) and isinstance(other[1],int): - minElements, optElements = other - optElements -= minElements - else: - raise TypeError("cannot multiply 'ParserElement' and ('%s','%s') objects", type(other[0]),type(other[1])) - else: - raise TypeError("cannot multiply 'ParserElement' and '%s' objects", type(other)) - - if minElements < 0: - raise ValueError("cannot multiply ParserElement by negative value") - if optElements < 0: - raise ValueError("second tuple value must be greater or equal to first tuple value") - if minElements == optElements == 0: - raise ValueError("cannot multiply ParserElement by 0 or (0,0)") - - if (optElements): - def makeOptionalList(n): - if n>1: - return Optional(self + makeOptionalList(n-1)) - else: - return Optional(self) - if minElements: - if minElements == 1: - ret = self + makeOptionalList(optElements) - else: - ret = And([self]*minElements) + makeOptionalList(optElements) - else: - ret = makeOptionalList(optElements) - else: - if minElements == 1: - ret = self - else: - ret = And([self]*minElements) - return ret - - def __rmul__(self, other): - return self.__mul__(other) - - def __or__(self, other ): - """Implementation of | operator - returns C{L{MatchFirst}}""" - if isinstance( other, basestring ): - other = ParserElement.literalStringClass( other ) - if not isinstance( other, ParserElement ): - warnings.warn("Cannot combine element of type %s with ParserElement" % type(other), - SyntaxWarning, stacklevel=2) - return None - return MatchFirst( [ self, other ] ) - - def __ror__(self, other ): - """Implementation of | operator when left operand is not a C{L{ParserElement}}""" - if isinstance( other, basestring ): - other = ParserElement.literalStringClass( other ) - if not isinstance( other, ParserElement ): - warnings.warn("Cannot combine element of type %s with ParserElement" % type(other), - SyntaxWarning, stacklevel=2) - return None - return other | self - - def __xor__(self, other ): - """Implementation of ^ operator - returns C{L{Or}}""" - if isinstance( other, basestring ): - other = ParserElement.literalStringClass( other ) - if not isinstance( other, ParserElement ): - warnings.warn("Cannot combine element of type %s with ParserElement" % type(other), - SyntaxWarning, stacklevel=2) - return None - return Or( [ self, other ] ) - - def __rxor__(self, other ): - """Implementation of ^ operator when left operand is not a C{L{ParserElement}}""" - if isinstance( other, basestring ): - other = ParserElement.literalStringClass( other ) - if not isinstance( other, ParserElement ): - warnings.warn("Cannot combine element of type %s with ParserElement" % type(other), - SyntaxWarning, stacklevel=2) - return None - return other ^ self - - def __and__(self, other ): - """Implementation of & operator - returns C{L{Each}}""" - if isinstance( other, basestring ): - other = ParserElement.literalStringClass( other ) - if not isinstance( other, ParserElement ): - warnings.warn("Cannot combine element of type %s with ParserElement" % type(other), - SyntaxWarning, stacklevel=2) - return None - return Each( [ self, other ] ) - - def __rand__(self, other ): - """Implementation of & operator when left operand is not a C{L{ParserElement}}""" - if isinstance( other, basestring ): - other = ParserElement.literalStringClass( other ) - if not isinstance( other, ParserElement ): - warnings.warn("Cannot combine element of type %s with ParserElement" % type(other), - SyntaxWarning, stacklevel=2) - return None - return other & self - - def __invert__( self ): - """Implementation of ~ operator - returns C{L{NotAny}}""" - return NotAny( self ) - - def __call__(self, name): - """Shortcut for C{L{setResultsName}}, with C{listAllMatches=default}:: - userdata = Word(alphas).setResultsName("name") + Word(nums+"-").setResultsName("socsecno") - could be written as:: - userdata = Word(alphas)("name") + Word(nums+"-")("socsecno") - - If C{name} is given with a trailing C{'*'} character, then C{listAllMatches} will be - passed as C{True}. - """ - return self.setResultsName(name) - - def suppress( self ): - """Suppresses the output of this C{ParserElement}; useful to keep punctuation from - cluttering up returned output. - """ - return Suppress( self ) - - def leaveWhitespace( self ): - """Disables the skipping of whitespace before matching the characters in the - C{ParserElement}'s defined pattern. This is normally only used internally by - the pyparsing module, but may be needed in some whitespace-sensitive grammars. - """ - self.skipWhitespace = False - return self - - def setWhitespaceChars( self, chars ): - """Overrides the default whitespace chars - """ - self.skipWhitespace = True - self.whiteChars = chars - self.copyDefaultWhiteChars = False - return self - - def parseWithTabs( self ): - """Overrides default behavior to expand C{}s to spaces before parsing the input string. - Must be called before C{parseString} when the input grammar contains elements that - match C{} characters.""" - self.keepTabs = True - return self - - def ignore( self, other ): - """Define expression to be ignored (e.g., comments) while doing pattern - matching; may be called repeatedly, to define multiple comment or other - ignorable patterns. - """ - if isinstance( other, Suppress ): - if other not in self.ignoreExprs: - self.ignoreExprs.append( other.copy() ) - else: - self.ignoreExprs.append( Suppress( other.copy() ) ) - return self - - def setDebugActions( self, startAction, successAction, exceptionAction ): - """Enable display of debugging messages while doing pattern matching.""" - self.debugActions = (startAction or _defaultStartDebugAction, - successAction or _defaultSuccessDebugAction, - exceptionAction or _defaultExceptionDebugAction) - self.debug = True - return self - - def setDebug( self, flag=True ): - """Enable display of debugging messages while doing pattern matching. - Set C{flag} to True to enable, False to disable.""" - if flag: - self.setDebugActions( _defaultStartDebugAction, _defaultSuccessDebugAction, _defaultExceptionDebugAction ) - else: - self.debug = False - return self - - def __str__( self ): - return self.name - - def __repr__( self ): - return _ustr(self) - - def streamline( self ): - self.streamlined = True - self.strRepr = None - return self - - def checkRecursion( self, parseElementList ): - pass - - def validate( self, validateTrace=[] ): - """Check defined expressions for valid structure, check for infinite recursive definitions.""" - self.checkRecursion( [] ) - - def parseFile( self, file_or_filename, parseAll=False ): - """Execute the parse expression on the given file or filename. - If a filename is specified (instead of a file object), - the entire file is opened, read, and closed before parsing. - """ - try: - file_contents = file_or_filename.read() - except AttributeError: - f = open(file_or_filename, "r") - file_contents = f.read() - f.close() - try: - return self.parseString(file_contents, parseAll) - except ParseBaseException, exc: - if ParserElement.verbose_stacktrace: - raise - else: - # catch and re-raise exception from here, clears out pyparsing internal stack trace - raise exc - - def getException(self): - return ParseException("",0,self.errmsg,self) - - def __getattr__(self,aname): - if aname == "myException": - self.myException = ret = self.getException(); - return ret; - else: - raise AttributeError("no such attribute " + aname) - - def __eq__(self,other): - if isinstance(other, ParserElement): - return self is other or self.__dict__ == other.__dict__ - elif isinstance(other, basestring): - try: - self.parseString(_ustr(other), parseAll=True) - return True - except ParseBaseException: - return False - else: - return super(ParserElement,self)==other - - def __ne__(self,other): - return not (self == other) - - def __hash__(self): - return hash(id(self)) - - def __req__(self,other): - return self == other - - def __rne__(self,other): - return not (self == other) - - -class Token(ParserElement): - """Abstract C{ParserElement} subclass, for defining atomic matching patterns.""" - def __init__( self ): - super(Token,self).__init__( savelist=False ) - - def setName(self, name): - s = super(Token,self).setName(name) - self.errmsg = "Expected " + self.name - return s - - -class Empty(Token): - """An empty token, will always match.""" - def __init__( self ): - super(Empty,self).__init__() - self.name = "Empty" - self.mayReturnEmpty = True - self.mayIndexError = False - - -class NoMatch(Token): - """A token that will never match.""" - def __init__( self ): - super(NoMatch,self).__init__() - self.name = "NoMatch" - self.mayReturnEmpty = True - self.mayIndexError = False - self.errmsg = "Unmatchable token" - - def parseImpl( self, instring, loc, doActions=True ): - exc = self.myException - exc.loc = loc - exc.pstr = instring - raise exc - - -class Literal(Token): - """Token to exactly match a specified string.""" - def __init__( self, matchString ): - super(Literal,self).__init__() - self.match = matchString - self.matchLen = len(matchString) - try: - self.firstMatchChar = matchString[0] - except IndexError: - warnings.warn("null string passed to Literal; use Empty() instead", - SyntaxWarning, stacklevel=2) - self.__class__ = Empty - self.name = '"%s"' % _ustr(self.match) - self.errmsg = "Expected " + self.name - self.mayReturnEmpty = False - self.mayIndexError = False - - # Performance tuning: this routine gets called a *lot* - # if this is a single character match string and the first character matches, - # short-circuit as quickly as possible, and avoid calling startswith - #~ @profile - def parseImpl( self, instring, loc, doActions=True ): - if (instring[loc] == self.firstMatchChar and - (self.matchLen==1 or instring.startswith(self.match,loc)) ): - return loc+self.matchLen, self.match - #~ raise ParseException( instring, loc, self.errmsg ) - exc = self.myException - exc.loc = loc - exc.pstr = instring - raise exc -_L = Literal -ParserElement.literalStringClass = Literal - -class Keyword(Token): - """Token to exactly match a specified string as a keyword, that is, it must be - immediately followed by a non-keyword character. Compare with C{L{Literal}}:: - Literal("if") will match the leading C{'if'} in C{'ifAndOnlyIf'}. - Keyword("if") will not; it will only match the leading C{'if'} in C{'if x=1'}, or C{'if(y==2)'} - Accepts two optional constructor arguments in addition to the keyword string: - C{identChars} is a string of characters that would be valid identifier characters, - defaulting to all alphanumerics + "_" and "$"; C{caseless} allows case-insensitive - matching, default is C{False}. - """ - DEFAULT_KEYWORD_CHARS = alphanums+"_$" - - def __init__( self, matchString, identChars=DEFAULT_KEYWORD_CHARS, caseless=False ): - super(Keyword,self).__init__() - self.match = matchString - self.matchLen = len(matchString) - try: - self.firstMatchChar = matchString[0] - except IndexError: - warnings.warn("null string passed to Keyword; use Empty() instead", - SyntaxWarning, stacklevel=2) - self.name = '"%s"' % self.match - self.errmsg = "Expected " + self.name - self.mayReturnEmpty = False - self.mayIndexError = False - self.caseless = caseless - if caseless: - self.caselessmatch = matchString.upper() - identChars = identChars.upper() - self.identChars = set(identChars) - - def parseImpl( self, instring, loc, doActions=True ): - if self.caseless: - if ( (instring[ loc:loc+self.matchLen ].upper() == self.caselessmatch) and - (loc >= len(instring)-self.matchLen or instring[loc+self.matchLen].upper() not in self.identChars) and - (loc == 0 or instring[loc-1].upper() not in self.identChars) ): - return loc+self.matchLen, self.match - else: - if (instring[loc] == self.firstMatchChar and - (self.matchLen==1 or instring.startswith(self.match,loc)) and - (loc >= len(instring)-self.matchLen or instring[loc+self.matchLen] not in self.identChars) and - (loc == 0 or instring[loc-1] not in self.identChars) ): - return loc+self.matchLen, self.match - #~ raise ParseException( instring, loc, self.errmsg ) - exc = self.myException - exc.loc = loc - exc.pstr = instring - raise exc - - def copy(self): - c = super(Keyword,self).copy() - c.identChars = Keyword.DEFAULT_KEYWORD_CHARS - return c - - def setDefaultKeywordChars( chars ): - """Overrides the default Keyword chars - """ - Keyword.DEFAULT_KEYWORD_CHARS = chars - setDefaultKeywordChars = staticmethod(setDefaultKeywordChars) - -class CaselessLiteral(Literal): - """Token to match a specified string, ignoring case of letters. - Note: the matched results will always be in the case of the given - match string, NOT the case of the input text. - """ - def __init__( self, matchString ): - super(CaselessLiteral,self).__init__( matchString.upper() ) - # Preserve the defining literal. - self.returnString = matchString - self.name = "'%s'" % self.returnString - self.errmsg = "Expected " + self.name - - def parseImpl( self, instring, loc, doActions=True ): - if instring[ loc:loc+self.matchLen ].upper() == self.match: - return loc+self.matchLen, self.returnString - #~ raise ParseException( instring, loc, self.errmsg ) - exc = self.myException - exc.loc = loc - exc.pstr = instring - raise exc - -class CaselessKeyword(Keyword): - def __init__( self, matchString, identChars=Keyword.DEFAULT_KEYWORD_CHARS ): - super(CaselessKeyword,self).__init__( matchString, identChars, caseless=True ) - - def parseImpl( self, instring, loc, doActions=True ): - if ( (instring[ loc:loc+self.matchLen ].upper() == self.caselessmatch) and - (loc >= len(instring)-self.matchLen or instring[loc+self.matchLen].upper() not in self.identChars) ): - return loc+self.matchLen, self.match - #~ raise ParseException( instring, loc, self.errmsg ) - exc = self.myException - exc.loc = loc - exc.pstr = instring - raise exc - -class Word(Token): - """Token for matching words composed of allowed character sets. - Defined with string containing all allowed initial characters, - an optional string containing allowed body characters (if omitted, - defaults to the initial character set), and an optional minimum, - maximum, and/or exact length. The default value for C{min} is 1 (a - minimum value < 1 is not valid); the default values for C{max} and C{exact} - are 0, meaning no maximum or exact length restriction. An optional - C{exclude} parameter can list characters that might be found in - the input C{bodyChars} string; useful to define a word of all printables - except for one or two characters, for instance. - """ - def __init__( self, initChars, bodyChars=None, min=1, max=0, exact=0, asKeyword=False, excludeChars=None ): - super(Word,self).__init__() - if excludeChars: - initChars = ''.join([c for c in initChars if c not in excludeChars]) - if bodyChars: - bodyChars = ''.join([c for c in bodyChars if c not in excludeChars]) - self.initCharsOrig = initChars - self.initChars = set(initChars) - if bodyChars : - self.bodyCharsOrig = bodyChars - self.bodyChars = set(bodyChars) - else: - self.bodyCharsOrig = initChars - self.bodyChars = set(initChars) - - self.maxSpecified = max > 0 - - if min < 1: - raise ValueError("cannot specify a minimum length < 1; use Optional(Word()) if zero-length word is permitted") - - self.minLen = min - - if max > 0: - self.maxLen = max - else: - self.maxLen = _MAX_INT - - if exact > 0: - self.maxLen = exact - self.minLen = exact - - self.name = _ustr(self) - self.errmsg = "Expected " + self.name - self.mayIndexError = False - self.asKeyword = asKeyword - - if ' ' not in self.initCharsOrig+self.bodyCharsOrig and (min==1 and max==0 and exact==0): - if self.bodyCharsOrig == self.initCharsOrig: - self.reString = "[%s]+" % _escapeRegexRangeChars(self.initCharsOrig) - elif len(self.bodyCharsOrig) == 1: - self.reString = "%s[%s]*" % \ - (re.escape(self.initCharsOrig), - _escapeRegexRangeChars(self.bodyCharsOrig),) - else: - self.reString = "[%s][%s]*" % \ - (_escapeRegexRangeChars(self.initCharsOrig), - _escapeRegexRangeChars(self.bodyCharsOrig),) - if self.asKeyword: - self.reString = r"\b"+self.reString+r"\b" - try: - self.re = re.compile( self.reString ) - except: - self.re = None - - def parseImpl( self, instring, loc, doActions=True ): - if self.re: - result = self.re.match(instring,loc) - if not result: - exc = self.myException - exc.loc = loc - exc.pstr = instring - raise exc - - loc = result.end() - return loc, result.group() - - if not(instring[ loc ] in self.initChars): - #~ raise ParseException( instring, loc, self.errmsg ) - exc = self.myException - exc.loc = loc - exc.pstr = instring - raise exc - start = loc - loc += 1 - instrlen = len(instring) - bodychars = self.bodyChars - maxloc = start + self.maxLen - maxloc = min( maxloc, instrlen ) - while loc < maxloc and instring[loc] in bodychars: - loc += 1 - - throwException = False - if loc - start < self.minLen: - throwException = True - if self.maxSpecified and loc < instrlen and instring[loc] in bodychars: - throwException = True - if self.asKeyword: - if (start>0 and instring[start-1] in bodychars) or (loc4: - return s[:4]+"..." - else: - return s - - if ( self.initCharsOrig != self.bodyCharsOrig ): - self.strRepr = "W:(%s,%s)" % ( charsAsStr(self.initCharsOrig), charsAsStr(self.bodyCharsOrig) ) - else: - self.strRepr = "W:(%s)" % charsAsStr(self.initCharsOrig) - - return self.strRepr - - -class Regex(Token): - """Token for matching strings that match a given regular expression. - Defined with string specifying the regular expression in a form recognized by the inbuilt Python re module. - """ - compiledREtype = type(re.compile("[A-Z]")) - def __init__( self, pattern, flags=0): - """The parameters C{pattern} and C{flags} are passed to the C{re.compile()} function as-is. See the Python C{re} module for an explanation of the acceptable patterns and flags.""" - super(Regex,self).__init__() - - if isinstance(pattern, basestring): - if len(pattern) == 0: - warnings.warn("null string passed to Regex; use Empty() instead", - SyntaxWarning, stacklevel=2) - - self.pattern = pattern - self.flags = flags - - try: - self.re = re.compile(self.pattern, self.flags) - self.reString = self.pattern - except sre_constants.error: - warnings.warn("invalid pattern (%s) passed to Regex" % pattern, - SyntaxWarning, stacklevel=2) - raise - - elif isinstance(pattern, Regex.compiledREtype): - self.re = pattern - self.pattern = \ - self.reString = str(pattern) - self.flags = flags - - else: - raise ValueError("Regex may only be constructed with a string or a compiled RE object") - - self.name = _ustr(self) - self.errmsg = "Expected " + self.name - self.mayIndexError = False - self.mayReturnEmpty = True - - def parseImpl( self, instring, loc, doActions=True ): - result = self.re.match(instring,loc) - if not result: - exc = self.myException - exc.loc = loc - exc.pstr = instring - raise exc - - loc = result.end() - d = result.groupdict() - ret = ParseResults(result.group()) - if d: - for k in d: - ret[k] = d[k] - return loc,ret - - def __str__( self ): - try: - return super(Regex,self).__str__() - except: - pass - - if self.strRepr is None: - self.strRepr = "Re:(%s)" % repr(self.pattern) - - return self.strRepr - - -class QuotedString(Token): - """Token for matching strings that are delimited by quoting characters. - """ - def __init__( self, quoteChar, escChar=None, escQuote=None, multiline=False, unquoteResults=True, endQuoteChar=None): - """ - Defined with the following parameters: - - quoteChar - string of one or more characters defining the quote delimiting string - - escChar - character to escape quotes, typically backslash (default=None) - - escQuote - special quote sequence to escape an embedded quote string (such as SQL's "" to escape an embedded ") (default=None) - - multiline - boolean indicating whether quotes can span multiple lines (default=C{False}) - - unquoteResults - boolean indicating whether the matched text should be unquoted (default=C{True}) - - endQuoteChar - string of one or more characters defining the end of the quote delimited string (default=C{None} => same as quoteChar) - """ - super(QuotedString,self).__init__() - - # remove white space from quote chars - wont work anyway - quoteChar = quoteChar.strip() - if len(quoteChar) == 0: - warnings.warn("quoteChar cannot be the empty string",SyntaxWarning,stacklevel=2) - raise SyntaxError() - - if endQuoteChar is None: - endQuoteChar = quoteChar - else: - endQuoteChar = endQuoteChar.strip() - if len(endQuoteChar) == 0: - warnings.warn("endQuoteChar cannot be the empty string",SyntaxWarning,stacklevel=2) - raise SyntaxError() - - self.quoteChar = quoteChar - self.quoteCharLen = len(quoteChar) - self.firstQuoteChar = quoteChar[0] - self.endQuoteChar = endQuoteChar - self.endQuoteCharLen = len(endQuoteChar) - self.escChar = escChar - self.escQuote = escQuote - self.unquoteResults = unquoteResults - - if multiline: - self.flags = re.MULTILINE | re.DOTALL - self.pattern = r'%s(?:[^%s%s]' % \ - ( re.escape(self.quoteChar), - _escapeRegexRangeChars(self.endQuoteChar[0]), - (escChar is not None and _escapeRegexRangeChars(escChar) or '') ) - else: - self.flags = 0 - self.pattern = r'%s(?:[^%s\n\r%s]' % \ - ( re.escape(self.quoteChar), - _escapeRegexRangeChars(self.endQuoteChar[0]), - (escChar is not None and _escapeRegexRangeChars(escChar) or '') ) - if len(self.endQuoteChar) > 1: - self.pattern += ( - '|(?:' + ')|(?:'.join(["%s[^%s]" % (re.escape(self.endQuoteChar[:i]), - _escapeRegexRangeChars(self.endQuoteChar[i])) - for i in range(len(self.endQuoteChar)-1,0,-1)]) + ')' - ) - if escQuote: - self.pattern += (r'|(?:%s)' % re.escape(escQuote)) - if escChar: - self.pattern += (r'|(?:%s.)' % re.escape(escChar)) - charset = ''.join(set(self.quoteChar[0]+self.endQuoteChar[0])).replace('^',r'\^').replace('-',r'\-') - self.escCharReplacePattern = re.escape(self.escChar)+("([%s])" % charset) - self.pattern += (r')*%s' % re.escape(self.endQuoteChar)) - - try: - self.re = re.compile(self.pattern, self.flags) - self.reString = self.pattern - except sre_constants.error: - warnings.warn("invalid pattern (%s) passed to Regex" % self.pattern, - SyntaxWarning, stacklevel=2) - raise - - self.name = _ustr(self) - self.errmsg = "Expected " + self.name - self.mayIndexError = False - self.mayReturnEmpty = True - - def parseImpl( self, instring, loc, doActions=True ): - result = instring[loc] == self.firstQuoteChar and self.re.match(instring,loc) or None - if not result: - exc = self.myException - exc.loc = loc - exc.pstr = instring - raise exc - - loc = result.end() - ret = result.group() - - if self.unquoteResults: - - # strip off quotes - ret = ret[self.quoteCharLen:-self.endQuoteCharLen] - - if isinstance(ret,basestring): - # replace escaped characters - if self.escChar: - ret = re.sub(self.escCharReplacePattern,"\g<1>",ret) - - # replace escaped quotes - if self.escQuote: - ret = ret.replace(self.escQuote, self.endQuoteChar) - - return loc, ret - - def __str__( self ): - try: - return super(QuotedString,self).__str__() - except: - pass - - if self.strRepr is None: - self.strRepr = "quoted string, starting with %s ending with %s" % (self.quoteChar, self.endQuoteChar) - - return self.strRepr - - -class CharsNotIn(Token): - """Token for matching words composed of characters *not* in a given set. - Defined with string containing all disallowed characters, and an optional - minimum, maximum, and/or exact length. The default value for C{min} is 1 (a - minimum value < 1 is not valid); the default values for C{max} and C{exact} - are 0, meaning no maximum or exact length restriction. - """ - def __init__( self, notChars, min=1, max=0, exact=0 ): - super(CharsNotIn,self).__init__() - self.skipWhitespace = False - self.notChars = notChars - - if min < 1: - raise ValueError("cannot specify a minimum length < 1; use Optional(CharsNotIn()) if zero-length char group is permitted") - - self.minLen = min - - if max > 0: - self.maxLen = max - else: - self.maxLen = _MAX_INT - - if exact > 0: - self.maxLen = exact - self.minLen = exact - - self.name = _ustr(self) - self.errmsg = "Expected " + self.name - self.mayReturnEmpty = ( self.minLen == 0 ) - self.mayIndexError = False - - def parseImpl( self, instring, loc, doActions=True ): - if instring[loc] in self.notChars: - #~ raise ParseException( instring, loc, self.errmsg ) - exc = self.myException - exc.loc = loc - exc.pstr = instring - raise exc - - start = loc - loc += 1 - notchars = self.notChars - maxlen = min( start+self.maxLen, len(instring) ) - while loc < maxlen and \ - (instring[loc] not in notchars): - loc += 1 - - if loc - start < self.minLen: - #~ raise ParseException( instring, loc, self.errmsg ) - exc = self.myException - exc.loc = loc - exc.pstr = instring - raise exc - - return loc, instring[start:loc] - - def __str__( self ): - try: - return super(CharsNotIn, self).__str__() - except: - pass - - if self.strRepr is None: - if len(self.notChars) > 4: - self.strRepr = "!W:(%s...)" % self.notChars[:4] - else: - self.strRepr = "!W:(%s)" % self.notChars - - return self.strRepr - -class White(Token): - """Special matching class for matching whitespace. Normally, whitespace is ignored - by pyparsing grammars. This class is included when some whitespace structures - are significant. Define with a string containing the whitespace characters to be - matched; default is C{" \\t\\r\\n"}. Also takes optional C{min}, C{max}, and C{exact} arguments, - as defined for the C{L{Word}} class.""" - whiteStrs = { - " " : "", - "\t": "", - "\n": "", - "\r": "", - "\f": "", - } - def __init__(self, ws=" \t\r\n", min=1, max=0, exact=0): - super(White,self).__init__() - self.matchWhite = ws - self.setWhitespaceChars( "".join([c for c in self.whiteChars if c not in self.matchWhite]) ) - #~ self.leaveWhitespace() - self.name = ("".join([White.whiteStrs[c] for c in self.matchWhite])) - self.mayReturnEmpty = True - self.errmsg = "Expected " + self.name - - self.minLen = min - - if max > 0: - self.maxLen = max - else: - self.maxLen = _MAX_INT - - if exact > 0: - self.maxLen = exact - self.minLen = exact - - def parseImpl( self, instring, loc, doActions=True ): - if not(instring[ loc ] in self.matchWhite): - #~ raise ParseException( instring, loc, self.errmsg ) - exc = self.myException - exc.loc = loc - exc.pstr = instring - raise exc - start = loc - loc += 1 - maxloc = start + self.maxLen - maxloc = min( maxloc, len(instring) ) - while loc < maxloc and instring[loc] in self.matchWhite: - loc += 1 - - if loc - start < self.minLen: - #~ raise ParseException( instring, loc, self.errmsg ) - exc = self.myException - exc.loc = loc - exc.pstr = instring - raise exc - - return loc, instring[start:loc] - - -class _PositionToken(Token): - def __init__( self ): - super(_PositionToken,self).__init__() - self.name=self.__class__.__name__ - self.mayReturnEmpty = True - self.mayIndexError = False - -class GoToColumn(_PositionToken): - """Token to advance to a specific column of input text; useful for tabular report scraping.""" - def __init__( self, colno ): - super(GoToColumn,self).__init__() - self.col = colno - - def preParse( self, instring, loc ): - if col(loc,instring) != self.col: - instrlen = len(instring) - if self.ignoreExprs: - loc = self._skipIgnorables( instring, loc ) - while loc < instrlen and instring[loc].isspace() and col( loc, instring ) != self.col : - loc += 1 - return loc - - def parseImpl( self, instring, loc, doActions=True ): - thiscol = col( loc, instring ) - if thiscol > self.col: - raise ParseException( instring, loc, "Text not in expected column", self ) - newloc = loc + self.col - thiscol - ret = instring[ loc: newloc ] - return newloc, ret - -class LineStart(_PositionToken): - """Matches if current position is at the beginning of a line within the parse string""" - def __init__( self ): - super(LineStart,self).__init__() - self.setWhitespaceChars( ParserElement.DEFAULT_WHITE_CHARS.replace("\n","") ) - self.errmsg = "Expected start of line" - - def preParse( self, instring, loc ): - preloc = super(LineStart,self).preParse(instring,loc) - if instring[preloc] == "\n": - loc += 1 - return loc - - def parseImpl( self, instring, loc, doActions=True ): - if not( loc==0 or - (loc == self.preParse( instring, 0 )) or - (instring[loc-1] == "\n") ): #col(loc, instring) != 1: - #~ raise ParseException( instring, loc, "Expected start of line" ) - exc = self.myException - exc.loc = loc - exc.pstr = instring - raise exc - return loc, [] - -class LineEnd(_PositionToken): - """Matches if current position is at the end of a line within the parse string""" - def __init__( self ): - super(LineEnd,self).__init__() - self.setWhitespaceChars( ParserElement.DEFAULT_WHITE_CHARS.replace("\n","") ) - self.errmsg = "Expected end of line" - - def parseImpl( self, instring, loc, doActions=True ): - if loc len(instring): - return loc, [] - else: - exc = self.myException - exc.loc = loc - exc.pstr = instring - raise exc - -class WordStart(_PositionToken): - """Matches if the current position is at the beginning of a Word, and - is not preceded by any character in a given set of C{wordChars} - (default=C{printables}). To emulate the C{\b} behavior of regular expressions, - use C{WordStart(alphanums)}. C{WordStart} will also match at the beginning of - the string being parsed, or at the beginning of a line. - """ - def __init__(self, wordChars = printables): - super(WordStart,self).__init__() - self.wordChars = set(wordChars) - self.errmsg = "Not at the start of a word" - - def parseImpl(self, instring, loc, doActions=True ): - if loc != 0: - if (instring[loc-1] in self.wordChars or - instring[loc] not in self.wordChars): - exc = self.myException - exc.loc = loc - exc.pstr = instring - raise exc - return loc, [] - -class WordEnd(_PositionToken): - """Matches if the current position is at the end of a Word, and - is not followed by any character in a given set of C{wordChars} - (default=C{printables}). To emulate the C{\b} behavior of regular expressions, - use C{WordEnd(alphanums)}. C{WordEnd} will also match at the end of - the string being parsed, or at the end of a line. - """ - def __init__(self, wordChars = printables): - super(WordEnd,self).__init__() - self.wordChars = set(wordChars) - self.skipWhitespace = False - self.errmsg = "Not at the end of a word" - - def parseImpl(self, instring, loc, doActions=True ): - instrlen = len(instring) - if instrlen>0 and loc maxExcLoc: - maxException = err - maxExcLoc = err.loc - except IndexError: - if len(instring) > maxExcLoc: - maxException = ParseException(instring,len(instring),e.errmsg,self) - maxExcLoc = len(instring) - else: - if loc2 > maxMatchLoc: - maxMatchLoc = loc2 - maxMatchExp = e - - if maxMatchLoc < 0: - if maxException is not None: - raise maxException - else: - raise ParseException(instring, loc, "no defined alternatives to match", self) - - return maxMatchExp._parse( instring, loc, doActions ) - - def __ixor__(self, other ): - if isinstance( other, basestring ): - other = ParserElement.literalStringClass( other ) - return self.append( other ) #Or( [ self, other ] ) - - def __str__( self ): - if hasattr(self,"name"): - return self.name - - if self.strRepr is None: - self.strRepr = "{" + " ^ ".join( [ _ustr(e) for e in self.exprs ] ) + "}" - - return self.strRepr - - def checkRecursion( self, parseElementList ): - subRecCheckList = parseElementList[:] + [ self ] - for e in self.exprs: - e.checkRecursion( subRecCheckList ) - - -class MatchFirst(ParseExpression): - """Requires that at least one C{ParseExpression} is found. - If two expressions match, the first one listed is the one that will match. - May be constructed using the C{'|'} operator. - """ - def __init__( self, exprs, savelist = False ): - super(MatchFirst,self).__init__(exprs, savelist) - if exprs: - self.mayReturnEmpty = False - for e in self.exprs: - if e.mayReturnEmpty: - self.mayReturnEmpty = True - break - else: - self.mayReturnEmpty = True - - def parseImpl( self, instring, loc, doActions=True ): - maxExcLoc = -1 - maxException = None - for e in self.exprs: - try: - ret = e._parse( instring, loc, doActions ) - return ret - except ParseException, err: - if err.loc > maxExcLoc: - maxException = err - maxExcLoc = err.loc - except IndexError: - if len(instring) > maxExcLoc: - maxException = ParseException(instring,len(instring),e.errmsg,self) - maxExcLoc = len(instring) - - # only got here if no expression matched, raise exception for match that made it the furthest - else: - if maxException is not None: - raise maxException - else: - raise ParseException(instring, loc, "no defined alternatives to match", self) - - def __ior__(self, other ): - if isinstance( other, basestring ): - other = ParserElement.literalStringClass( other ) - return self.append( other ) #MatchFirst( [ self, other ] ) - - def __str__( self ): - if hasattr(self,"name"): - return self.name - - if self.strRepr is None: - self.strRepr = "{" + " | ".join( [ _ustr(e) for e in self.exprs ] ) + "}" - - return self.strRepr - - def checkRecursion( self, parseElementList ): - subRecCheckList = parseElementList[:] + [ self ] - for e in self.exprs: - e.checkRecursion( subRecCheckList ) - - -class Each(ParseExpression): - """Requires all given C{ParseExpression}s to be found, but in any order. - Expressions may be separated by whitespace. - May be constructed using the C{'&'} operator. - """ - def __init__( self, exprs, savelist = True ): - super(Each,self).__init__(exprs, savelist) - self.mayReturnEmpty = True - for e in self.exprs: - if not e.mayReturnEmpty: - self.mayReturnEmpty = False - break - self.skipWhitespace = True - self.initExprGroups = True - - def parseImpl( self, instring, loc, doActions=True ): - if self.initExprGroups: - opt1 = [ e.expr for e in self.exprs if isinstance(e,Optional) ] - opt2 = [ e for e in self.exprs if e.mayReturnEmpty and e not in opt1 ] - self.optionals = opt1 + opt2 - self.multioptionals = [ e.expr for e in self.exprs if isinstance(e,ZeroOrMore) ] - self.multirequired = [ e.expr for e in self.exprs if isinstance(e,OneOrMore) ] - self.required = [ e for e in self.exprs if not isinstance(e,(Optional,ZeroOrMore,OneOrMore)) ] - self.required += self.multirequired - self.initExprGroups = False - tmpLoc = loc - tmpReqd = self.required[:] - tmpOpt = self.optionals[:] - matchOrder = [] - - keepMatching = True - while keepMatching: - tmpExprs = tmpReqd + tmpOpt + self.multioptionals + self.multirequired - failed = [] - for e in tmpExprs: - try: - tmpLoc = e.tryParse( instring, tmpLoc ) - except ParseException: - failed.append(e) - else: - matchOrder.append(e) - if e in tmpReqd: - tmpReqd.remove(e) - elif e in tmpOpt: - tmpOpt.remove(e) - if len(failed) == len(tmpExprs): - keepMatching = False - - if tmpReqd: - missing = ", ".join( [ _ustr(e) for e in tmpReqd ] ) - raise ParseException(instring,loc,"Missing one or more required elements (%s)" % missing ) - - # add any unmatched Optionals, in case they have default values defined - matchOrder += [e for e in self.exprs if isinstance(e,Optional) and e.expr in tmpOpt] - - resultlist = [] - for e in matchOrder: - loc,results = e._parse(instring,loc,doActions) - resultlist.append(results) - - finalResults = ParseResults([]) - for r in resultlist: - dups = {} - for k in r.keys(): - if k in finalResults.keys(): - tmp = ParseResults(finalResults[k]) - tmp += ParseResults(r[k]) - dups[k] = tmp - finalResults += ParseResults(r) - for k,v in dups.items(): - finalResults[k] = v - return loc, finalResults - - def __str__( self ): - if hasattr(self,"name"): - return self.name - - if self.strRepr is None: - self.strRepr = "{" + " & ".join( [ _ustr(e) for e in self.exprs ] ) + "}" - - return self.strRepr - - def checkRecursion( self, parseElementList ): - subRecCheckList = parseElementList[:] + [ self ] - for e in self.exprs: - e.checkRecursion( subRecCheckList ) - - -class ParseElementEnhance(ParserElement): - """Abstract subclass of C{ParserElement}, for combining and post-processing parsed tokens.""" - def __init__( self, expr, savelist=False ): - super(ParseElementEnhance,self).__init__(savelist) - if isinstance( expr, basestring ): - expr = Literal(expr) - self.expr = expr - self.strRepr = None - if expr is not None: - self.mayIndexError = expr.mayIndexError - self.mayReturnEmpty = expr.mayReturnEmpty - self.setWhitespaceChars( expr.whiteChars ) - self.skipWhitespace = expr.skipWhitespace - self.saveAsList = expr.saveAsList - self.callPreparse = expr.callPreparse - self.ignoreExprs.extend(expr.ignoreExprs) - - def parseImpl( self, instring, loc, doActions=True ): - if self.expr is not None: - return self.expr._parse( instring, loc, doActions, callPreParse=False ) - else: - raise ParseException("",loc,self.errmsg,self) - - def leaveWhitespace( self ): - self.skipWhitespace = False - self.expr = self.expr.copy() - if self.expr is not None: - self.expr.leaveWhitespace() - return self - - def ignore( self, other ): - if isinstance( other, Suppress ): - if other not in self.ignoreExprs: - super( ParseElementEnhance, self).ignore( other ) - if self.expr is not None: - self.expr.ignore( self.ignoreExprs[-1] ) - else: - super( ParseElementEnhance, self).ignore( other ) - if self.expr is not None: - self.expr.ignore( self.ignoreExprs[-1] ) - return self - - def streamline( self ): - super(ParseElementEnhance,self).streamline() - if self.expr is not None: - self.expr.streamline() - return self - - def checkRecursion( self, parseElementList ): - if self in parseElementList: - raise RecursiveGrammarException( parseElementList+[self] ) - subRecCheckList = parseElementList[:] + [ self ] - if self.expr is not None: - self.expr.checkRecursion( subRecCheckList ) - - def validate( self, validateTrace=[] ): - tmp = validateTrace[:]+[self] - if self.expr is not None: - self.expr.validate(tmp) - self.checkRecursion( [] ) - - def __str__( self ): - try: - return super(ParseElementEnhance,self).__str__() - except: - pass - - if self.strRepr is None and self.expr is not None: - self.strRepr = "%s:(%s)" % ( self.__class__.__name__, _ustr(self.expr) ) - return self.strRepr - - -class FollowedBy(ParseElementEnhance): - """Lookahead matching of the given parse expression. C{FollowedBy} - does *not* advance the parsing position within the input string, it only - verifies that the specified parse expression matches at the current - position. C{FollowedBy} always returns a null token list.""" - def __init__( self, expr ): - super(FollowedBy,self).__init__(expr) - self.mayReturnEmpty = True - - def parseImpl( self, instring, loc, doActions=True ): - self.expr.tryParse( instring, loc ) - return loc, [] - - -class NotAny(ParseElementEnhance): - """Lookahead to disallow matching with the given parse expression. C{NotAny} - does *not* advance the parsing position within the input string, it only - verifies that the specified parse expression does *not* match at the current - position. Also, C{NotAny} does *not* skip over leading whitespace. C{NotAny} - always returns a null token list. May be constructed using the '~' operator.""" - def __init__( self, expr ): - super(NotAny,self).__init__(expr) - #~ self.leaveWhitespace() - self.skipWhitespace = False # do NOT use self.leaveWhitespace(), don't want to propagate to exprs - self.mayReturnEmpty = True - self.errmsg = "Found unwanted token, "+_ustr(self.expr) - - def parseImpl( self, instring, loc, doActions=True ): - try: - self.expr.tryParse( instring, loc ) - except (ParseException,IndexError): - pass - else: - #~ raise ParseException(instring, loc, self.errmsg ) - exc = self.myException - exc.loc = loc - exc.pstr = instring - raise exc - return loc, [] - - def __str__( self ): - if hasattr(self,"name"): - return self.name - - if self.strRepr is None: - self.strRepr = "~{" + _ustr(self.expr) + "}" - - return self.strRepr - - -class ZeroOrMore(ParseElementEnhance): - """Optional repetition of zero or more of the given expression.""" - def __init__( self, expr ): - super(ZeroOrMore,self).__init__(expr) - self.mayReturnEmpty = True - - def parseImpl( self, instring, loc, doActions=True ): - tokens = [] - try: - loc, tokens = self.expr._parse( instring, loc, doActions, callPreParse=False ) - hasIgnoreExprs = ( len(self.ignoreExprs) > 0 ) - while 1: - if hasIgnoreExprs: - preloc = self._skipIgnorables( instring, loc ) - else: - preloc = loc - loc, tmptokens = self.expr._parse( instring, preloc, doActions ) - if tmptokens or tmptokens.keys(): - tokens += tmptokens - except (ParseException,IndexError): - pass - - return loc, tokens - - def __str__( self ): - if hasattr(self,"name"): - return self.name - - if self.strRepr is None: - self.strRepr = "[" + _ustr(self.expr) + "]..." - - return self.strRepr - - def setResultsName( self, name, listAllMatches=False ): - ret = super(ZeroOrMore,self).setResultsName(name,listAllMatches) - ret.saveAsList = True - return ret - - -class OneOrMore(ParseElementEnhance): - """Repetition of one or more of the given expression.""" - def parseImpl( self, instring, loc, doActions=True ): - # must be at least one - loc, tokens = self.expr._parse( instring, loc, doActions, callPreParse=False ) - try: - hasIgnoreExprs = ( len(self.ignoreExprs) > 0 ) - while 1: - if hasIgnoreExprs: - preloc = self._skipIgnorables( instring, loc ) - else: - preloc = loc - loc, tmptokens = self.expr._parse( instring, preloc, doActions ) - if tmptokens or tmptokens.keys(): - tokens += tmptokens - except (ParseException,IndexError): - pass - - return loc, tokens - - def __str__( self ): - if hasattr(self,"name"): - return self.name - - if self.strRepr is None: - self.strRepr = "{" + _ustr(self.expr) + "}..." - - return self.strRepr - - def setResultsName( self, name, listAllMatches=False ): - ret = super(OneOrMore,self).setResultsName(name,listAllMatches) - ret.saveAsList = True - return ret - -class _NullToken(object): - def __bool__(self): - return False - __nonzero__ = __bool__ - def __str__(self): - return "" - -_optionalNotMatched = _NullToken() -class Optional(ParseElementEnhance): - """Optional matching of the given expression. - A default return string can also be specified, if the optional expression - is not found. - """ - def __init__( self, exprs, default=_optionalNotMatched ): - super(Optional,self).__init__( exprs, savelist=False ) - self.defaultValue = default - self.mayReturnEmpty = True - - def parseImpl( self, instring, loc, doActions=True ): - try: - loc, tokens = self.expr._parse( instring, loc, doActions, callPreParse=False ) - except (ParseException,IndexError): - if self.defaultValue is not _optionalNotMatched: - if self.expr.resultsName: - tokens = ParseResults([ self.defaultValue ]) - tokens[self.expr.resultsName] = self.defaultValue - else: - tokens = [ self.defaultValue ] - else: - tokens = [] - return loc, tokens - - def __str__( self ): - if hasattr(self,"name"): - return self.name - - if self.strRepr is None: - self.strRepr = "[" + _ustr(self.expr) + "]" - - return self.strRepr - - -class SkipTo(ParseElementEnhance): - """Token for skipping over all undefined text until the matched expression is found. - If C{include} is set to true, the matched expression is also parsed (the skipped text - and matched expression are returned as a 2-element list). The C{ignore} - argument is used to define grammars (typically quoted strings and comments) that - might contain false matches. - """ - def __init__( self, other, include=False, ignore=None, failOn=None ): - super( SkipTo, self ).__init__( other ) - self.ignoreExpr = ignore - self.mayReturnEmpty = True - self.mayIndexError = False - self.includeMatch = include - self.asList = False - if failOn is not None and isinstance(failOn, basestring): - self.failOn = Literal(failOn) - else: - self.failOn = failOn - self.errmsg = "No match found for "+_ustr(self.expr) - - def parseImpl( self, instring, loc, doActions=True ): - startLoc = loc - instrlen = len(instring) - expr = self.expr - failParse = False - while loc <= instrlen: - try: - if self.failOn: - try: - self.failOn.tryParse(instring, loc) - except ParseBaseException: - pass - else: - failParse = True - raise ParseException(instring, loc, "Found expression " + str(self.failOn)) - failParse = False - if self.ignoreExpr is not None: - while 1: - try: - loc = self.ignoreExpr.tryParse(instring,loc) - # print "found ignoreExpr, advance to", loc - except ParseBaseException: - break - expr._parse( instring, loc, doActions=False, callPreParse=False ) - skipText = instring[startLoc:loc] - if self.includeMatch: - loc,mat = expr._parse(instring,loc,doActions,callPreParse=False) - if mat: - skipRes = ParseResults( skipText ) - skipRes += mat - return loc, [ skipRes ] - else: - return loc, [ skipText ] - else: - return loc, [ skipText ] - except (ParseException,IndexError): - if failParse: - raise - else: - loc += 1 - exc = self.myException - exc.loc = loc - exc.pstr = instring - raise exc - -class Forward(ParseElementEnhance): - """Forward declaration of an expression to be defined later - - used for recursive grammars, such as algebraic infix notation. - When the expression is known, it is assigned to the C{Forward} variable using the '<<' operator. - - Note: take care when assigning to C{Forward} not to overlook precedence of operators. - Specifically, '|' has a lower precedence than '<<', so that:: - fwdExpr << a | b | c - will actually be evaluated as:: - (fwdExpr << a) | b | c - thereby leaving b and c out as parseable alternatives. It is recommended that you - explicitly group the values inserted into the C{Forward}:: - fwdExpr << (a | b | c) - Converting to use the '<<=' operator instead will avoid this problem. - """ - def __init__( self, other=None ): - super(Forward,self).__init__( other, savelist=False ) - - def __lshift__( self, other ): - if isinstance( other, basestring ): - other = ParserElement.literalStringClass(other) - self.expr = other - self.mayReturnEmpty = other.mayReturnEmpty - self.strRepr = None - self.mayIndexError = self.expr.mayIndexError - self.mayReturnEmpty = self.expr.mayReturnEmpty - self.setWhitespaceChars( self.expr.whiteChars ) - self.skipWhitespace = self.expr.skipWhitespace - self.saveAsList = self.expr.saveAsList - self.ignoreExprs.extend(self.expr.ignoreExprs) - return None - __ilshift__ = __lshift__ - - def leaveWhitespace( self ): - self.skipWhitespace = False - return self - - def streamline( self ): - if not self.streamlined: - self.streamlined = True - if self.expr is not None: - self.expr.streamline() - return self - - def validate( self, validateTrace=[] ): - if self not in validateTrace: - tmp = validateTrace[:]+[self] - if self.expr is not None: - self.expr.validate(tmp) - self.checkRecursion([]) - - def __str__( self ): - if hasattr(self,"name"): - return self.name - - self._revertClass = self.__class__ - self.__class__ = _ForwardNoRecurse - try: - if self.expr is not None: - retString = _ustr(self.expr) - else: - retString = "None" - finally: - self.__class__ = self._revertClass - return self.__class__.__name__ + ": " + retString - - def copy(self): - if self.expr is not None: - return super(Forward,self).copy() - else: - ret = Forward() - ret << self - return ret - -class _ForwardNoRecurse(Forward): - def __str__( self ): - return "..." - -class TokenConverter(ParseElementEnhance): - """Abstract subclass of C{ParseExpression}, for converting parsed results.""" - def __init__( self, expr, savelist=False ): - super(TokenConverter,self).__init__( expr )#, savelist ) - self.saveAsList = False - -class Upcase(TokenConverter): - """Converter to upper case all matching tokens.""" - def __init__(self, *args): - super(Upcase,self).__init__(*args) - warnings.warn("Upcase class is deprecated, use upcaseTokens parse action instead", - DeprecationWarning,stacklevel=2) - - def postParse( self, instring, loc, tokenlist ): - return list(map( str.upper, tokenlist )) - - -class Combine(TokenConverter): - """Converter to concatenate all matching tokens to a single string. - By default, the matching patterns must also be contiguous in the input string; - this can be disabled by specifying C{'adjacent=False'} in the constructor. - """ - def __init__( self, expr, joinString="", adjacent=True ): - super(Combine,self).__init__( expr ) - # suppress whitespace-stripping in contained parse expressions, but re-enable it on the Combine itself - if adjacent: - self.leaveWhitespace() - self.adjacent = adjacent - self.skipWhitespace = True - self.joinString = joinString - self.callPreparse = True - - def ignore( self, other ): - if self.adjacent: - ParserElement.ignore(self, other) - else: - super( Combine, self).ignore( other ) - return self - - def postParse( self, instring, loc, tokenlist ): - retToks = tokenlist.copy() - del retToks[:] - retToks += ParseResults([ "".join(tokenlist._asStringList(self.joinString)) ], modal=self.modalResults) - - if self.resultsName and len(retToks.keys())>0: - return [ retToks ] - else: - return retToks - -class Group(TokenConverter): - """Converter to return the matched tokens as a list - useful for returning tokens of C{L{ZeroOrMore}} and C{L{OneOrMore}} expressions.""" - def __init__( self, expr ): - super(Group,self).__init__( expr ) - self.saveAsList = True - - def postParse( self, instring, loc, tokenlist ): - return [ tokenlist ] - -class Dict(TokenConverter): - """Converter to return a repetitive expression as a list, but also as a dictionary. - Each element can also be referenced using the first token in the expression as its key. - Useful for tabular report scraping when the first column can be used as a item key. - """ - def __init__( self, exprs ): - super(Dict,self).__init__( exprs ) - self.saveAsList = True - - def postParse( self, instring, loc, tokenlist ): - for i,tok in enumerate(tokenlist): - if len(tok) == 0: - continue - ikey = tok[0] - if isinstance(ikey,int): - ikey = _ustr(tok[0]).strip() - if len(tok)==1: - tokenlist[ikey] = _ParseResultsWithOffset("",i) - elif len(tok)==2 and not isinstance(tok[1],ParseResults): - tokenlist[ikey] = _ParseResultsWithOffset(tok[1],i) - else: - dictvalue = tok.copy() #ParseResults(i) - del dictvalue[0] - if len(dictvalue)!= 1 or (isinstance(dictvalue,ParseResults) and dictvalue.keys()): - tokenlist[ikey] = _ParseResultsWithOffset(dictvalue,i) - else: - tokenlist[ikey] = _ParseResultsWithOffset(dictvalue[0],i) - - if self.resultsName: - return [ tokenlist ] - else: - return tokenlist - - -class Suppress(TokenConverter): - """Converter for ignoring the results of a parsed expression.""" - def postParse( self, instring, loc, tokenlist ): - return [] - - def suppress( self ): - return self - - -class OnlyOnce(object): - """Wrapper for parse actions, to ensure they are only called once.""" - def __init__(self, methodCall): - self.callable = _trim_arity(methodCall) - self.called = False - def __call__(self,s,l,t): - if not self.called: - results = self.callable(s,l,t) - self.called = True - return results - raise ParseException(s,l,"") - def reset(self): - self.called = False - -def traceParseAction(f): - """Decorator for debugging parse actions.""" - f = _trim_arity(f) - def z(*paArgs): - thisFunc = f.func_name - s,l,t = paArgs[-3:] - if len(paArgs)>3: - thisFunc = paArgs[0].__class__.__name__ + '.' + thisFunc - sys.stderr.write( ">>entering %s(line: '%s', %d, %s)\n" % (thisFunc,line(l,s),l,t) ) - try: - ret = f(*paArgs) - except Exception, exc: - sys.stderr.write( "<}} ('-' operator) indicates that parsing is to stop immediately because +# an unbacktrackable syntax error has been found""" +# def __init__(self, pe): +# super(ParseSyntaxException, self).__init__( +# pe.pstr, pe.loc, pe.msg, pe.parserElement) # -def delimitedList( expr, delim=",", combine=False ): - """Helper to define a delimited list of expressions - the delimiter defaults to ','. - By default, the list elements and delimiters can have intervening whitespace, and - comments, but this can be overridden by passing C{combine=True} in the constructor. - If C{combine} is set to C{True}, the matching tokens are returned as a single token - string, with the delimiters included; otherwise, the matching tokens are returned - as a list of tokens, with the delimiters suppressed. - """ - dlName = _ustr(expr)+" ["+_ustr(delim)+" "+_ustr(expr)+"]..." - if combine: - return Combine( expr + ZeroOrMore( delim + expr ) ).setName(dlName) - else: - return ( expr + ZeroOrMore( Suppress( delim ) + expr ) ).setName(dlName) - -def countedArray( expr, intExpr=None ): - """Helper to define a counted list of expressions. - This helper defines a pattern of the form:: - integer expr expr expr... - where the leading integer tells how many expr expressions follow. - The matched tokens returns the array of expr tokens as a list - the leading count token is suppressed. - """ - arrayExpr = Forward() - def countFieldParseAction(s,l,t): - n = t[0] - arrayExpr << (n and Group(And([expr]*n)) or Group(empty)) - return [] - if intExpr is None: - intExpr = Word(nums).setParseAction(lambda t:int(t[0])) - else: - intExpr = intExpr.copy() - intExpr.setName("arrayLen") - intExpr.addParseAction(countFieldParseAction, callDuringTry=True) - return ( intExpr + arrayExpr ) - -def _flatten(L): - ret = [] - for i in L: - if isinstance(i,list): - ret.extend(_flatten(i)) - else: - ret.append(i) - return ret - -def matchPreviousLiteral(expr): - """Helper to define an expression that is indirectly defined from - the tokens matched in a previous expression, that is, it looks - for a 'repeat' of a previous expression. For example:: - first = Word(nums) - second = matchPreviousLiteral(first) - matchExpr = first + ":" + second - will match C{"1:1"}, but not C{"1:2"}. Because this matches a - previous literal, will also match the leading C{"1:1"} in C{"1:10"}. - If this is not desired, use C{matchPreviousExpr}. - Do *not* use with packrat parsing enabled. - """ - rep = Forward() - def copyTokenToRepeater(s,l,t): - if t: - if len(t) == 1: - rep << t[0] - else: - # flatten t tokens - tflat = _flatten(t.asList()) - rep << And( [ Literal(tt) for tt in tflat ] ) - else: - rep << Empty() - expr.addParseAction(copyTokenToRepeater, callDuringTry=True) - return rep - -def matchPreviousExpr(expr): - """Helper to define an expression that is indirectly defined from - the tokens matched in a previous expression, that is, it looks - for a 'repeat' of a previous expression. For example:: - first = Word(nums) - second = matchPreviousExpr(first) - matchExpr = first + ":" + second - will match C{"1:1"}, but not C{"1:2"}. Because this matches by - expressions, will *not* match the leading C{"1:1"} in C{"1:10"}; - the expressions are evaluated first, and then compared, so - C{"1"} is compared with C{"10"}. - Do *not* use with packrat parsing enabled. - """ - rep = Forward() - e2 = expr.copy() - rep << e2 - def copyTokenToRepeater(s,l,t): - matchTokens = _flatten(t.asList()) - def mustMatchTheseTokens(s,l,t): - theseTokens = _flatten(t.asList()) - if theseTokens != matchTokens: - raise ParseException("",0,"") - rep.setParseAction( mustMatchTheseTokens, callDuringTry=True ) - expr.addParseAction(copyTokenToRepeater, callDuringTry=True) - return rep - -def _escapeRegexRangeChars(s): - #~ escape these chars: ^-] - for c in r"\^-]": - s = s.replace(c,_bslash+c) - s = s.replace("\n",r"\n") - s = s.replace("\t",r"\t") - return _ustr(s) - -def oneOf( strs, caseless=False, useRegex=True ): - """Helper to quickly define a set of alternative Literals, and makes sure to do - longest-first testing when there is a conflict, regardless of the input order, - but returns a C{L{MatchFirst}} for best performance. - - Parameters: - - strs - a string of space-delimited literals, or a list of string literals - - caseless - (default=False) - treat all literals as caseless - - useRegex - (default=True) - as an optimization, will generate a Regex - object; otherwise, will generate a C{MatchFirst} object (if C{caseless=True}, or - if creating a C{Regex} raises an exception) - """ - if caseless: - isequal = ( lambda a,b: a.upper() == b.upper() ) - masks = ( lambda a,b: b.upper().startswith(a.upper()) ) - parseElementClass = CaselessLiteral - else: - isequal = ( lambda a,b: a == b ) - masks = ( lambda a,b: b.startswith(a) ) - parseElementClass = Literal - - if isinstance(strs,(list,tuple)): - symbols = list(strs[:]) - elif isinstance(strs,basestring): - symbols = strs.split() - else: - warnings.warn("Invalid argument to oneOf, expected string or list", - SyntaxWarning, stacklevel=2) - - i = 0 - while i < len(symbols)-1: - cur = symbols[i] - for j,other in enumerate(symbols[i+1:]): - if ( isequal(other, cur) ): - del symbols[i+j+1] - break - elif ( masks(cur, other) ): - del symbols[i+j+1] - symbols.insert(i,other) - cur = other - break - else: - i += 1 - - if not caseless and useRegex: - #~ print (strs,"->", "|".join( [ _escapeRegexChars(sym) for sym in symbols] )) - try: - if len(symbols)==len("".join(symbols)): - return Regex( "[%s]" % "".join( [ _escapeRegexRangeChars(sym) for sym in symbols] ) ) - else: - return Regex( "|".join( [ re.escape(sym) for sym in symbols] ) ) - except: - warnings.warn("Exception creating Regex for oneOf, building MatchFirst", - SyntaxWarning, stacklevel=2) - - - # last resort, just use MatchFirst - return MatchFirst( [ parseElementClass(sym) for sym in symbols ] ) - -def dictOf( key, value ): - """Helper to easily and clearly define a dictionary by specifying the respective patterns - for the key and value. Takes care of defining the C{L{Dict}}, C{L{ZeroOrMore}}, and C{L{Group}} tokens - in the proper order. The key pattern can include delimiting markers or punctuation, - as long as they are suppressed, thereby leaving the significant key text. The value - pattern can include named results, so that the C{Dict} results can include named token - fields. - """ - return Dict( ZeroOrMore( Group ( key + value ) ) ) - -def originalTextFor(expr, asString=True): - """Helper to return the original, untokenized text for a given expression. Useful to - restore the parsed fields of an HTML start tag into the raw tag text itself, or to - revert separate tokens with intervening whitespace back to the original matching - input text. Simpler to use than the parse action C{L{keepOriginalText}}, and does not - require the inspect module to chase up the call stack. By default, returns a - string containing the original parsed text. - - If the optional C{asString} argument is passed as C{False}, then the return value is a - C{L{ParseResults}} containing any results names that were originally matched, and a - single token containing the original matched text from the input string. So if - the expression passed to C{L{originalTextFor}} contains expressions with defined - results names, you must set C{asString} to C{False} if you want to preserve those - results name values.""" - locMarker = Empty().setParseAction(lambda s,loc,t: loc) - endlocMarker = locMarker.copy() - endlocMarker.callPreparse = False - matchExpr = locMarker("_original_start") + expr + endlocMarker("_original_end") - if asString: - extractText = lambda s,l,t: s[t._original_start:t._original_end] - else: - def extractText(s,l,t): - del t[:] - t.insert(0, s[t._original_start:t._original_end]) - del t["_original_start"] - del t["_original_end"] - matchExpr.setParseAction(extractText) - return matchExpr - -def ungroup(expr): - """Helper to undo pyparsing's default grouping of And expressions, even - if all but one are non-empty.""" - return TokenConverter(expr).setParseAction(lambda t:t[0]) - -# convenience constants for positional expressions -empty = Empty().setName("empty") -lineStart = LineStart().setName("lineStart") -lineEnd = LineEnd().setName("lineEnd") -stringStart = StringStart().setName("stringStart") -stringEnd = StringEnd().setName("stringEnd") - -_escapedPunc = Word( _bslash, r"\[]-*.$+^?()~ ", exact=2 ).setParseAction(lambda s,l,t:t[0][1]) -_printables_less_backslash = "".join([ c for c in printables if c not in r"\]" ]) -_escapedHexChar = Regex(r"\\0?[xX][0-9a-fA-F]+").setParseAction(lambda s,l,t:unichr(int(t[0].lstrip(r'\0x'),16))) -_escapedOctChar = Regex(r"\\0[0-7]+").setParseAction(lambda s,l,t:unichr(int(t[0][1:],8))) -_singleChar = _escapedPunc | _escapedHexChar | _escapedOctChar | Word(_printables_less_backslash,exact=1) -_charRange = Group(_singleChar + Suppress("-") + _singleChar) -_reBracketExpr = Literal("[") + Optional("^").setResultsName("negate") + Group( OneOrMore( _charRange | _singleChar ) ).setResultsName("body") + "]" - -_expanded = lambda p: (isinstance(p,ParseResults) and ''.join([ unichr(c) for c in range(ord(p[0]),ord(p[1])+1) ]) or p) - -def srange(s): - r"""Helper to easily define string ranges for use in Word construction. Borrows - syntax from regexp '[]' string range definitions:: - srange("[0-9]") -> "0123456789" - srange("[a-z]") -> "abcdefghijklmnopqrstuvwxyz" - srange("[a-z$_]") -> "abcdefghijklmnopqrstuvwxyz$_" - The input string must be enclosed in []'s, and the returned string is the expanded - character set joined into a single string. - The values enclosed in the []'s may be:: - a single character - an escaped character with a leading backslash (such as \- or \]) - an escaped hex character with a leading '\x' (\x21, which is a '!' character) - (\0x## is also supported for backwards compatibility) - an escaped octal character with a leading '\0' (\041, which is a '!' character) - a range of any of the above, separated by a dash ('a-z', etc.) - any combination of the above ('aeiouy', 'a-zA-Z0-9_$', etc.) - """ - try: - return "".join([_expanded(part) for part in _reBracketExpr.parseString(s).body]) - except: - return "" - -def matchOnlyAtCol(n): - """Helper method for defining parse actions that require matching at a specific - column in the input text. - """ - def verifyCol(strg,locn,toks): - if col(locn,strg) != n: - raise ParseException(strg,locn,"matched token not at column %d" % n) - return verifyCol - -def replaceWith(replStr): - """Helper method for common parse actions that simply return a literal value. Especially - useful when used with C{L{transformString}()}. - """ - def _replFunc(*args): - return [replStr] - return _replFunc - -def removeQuotes(s,l,t): - """Helper parse action for removing quotation marks from parsed quoted strings. - To use, add this parse action to quoted string using:: - quotedString.setParseAction( removeQuotes ) - """ - return t[0][1:-1] - -def upcaseTokens(s,l,t): - """Helper parse action to convert tokens to upper case.""" - return [ tt.upper() for tt in map(_ustr,t) ] - -def downcaseTokens(s,l,t): - """Helper parse action to convert tokens to lower case.""" - return [ tt.lower() for tt in map(_ustr,t) ] - -def keepOriginalText(s,startLoc,t): - """DEPRECATED - use new helper method C{L{originalTextFor}}. - Helper parse action to preserve original parsed text, - overriding any nested parse actions.""" - try: - endloc = getTokensEndLoc() - except ParseException: - raise ParseFatalException("incorrect usage of keepOriginalText - may only be called as a parse action") - del t[:] - t += ParseResults(s[startLoc:endloc]) - return t - -def getTokensEndLoc(): - """Method to be called from within a parse action to determine the end - location of the parsed tokens.""" - import inspect - fstack = inspect.stack() - try: - # search up the stack (through intervening argument normalizers) for correct calling routine - for f in fstack[2:]: - if f[3] == "_parseNoCache": - endloc = f[0].f_locals["loc"] - return endloc - else: - raise ParseFatalException("incorrect usage of getTokensEndLoc - may only be called from within a parse action") - finally: - del fstack - -def _makeTags(tagStr, xml): - """Internal helper to construct opening and closing tag expressions, given a tag name""" - if isinstance(tagStr,basestring): - resname = tagStr - tagStr = Keyword(tagStr, caseless=not xml) - else: - resname = tagStr.name - - tagAttrName = Word(alphas,alphanums+"_-:") - if (xml): - tagAttrValue = dblQuotedString.copy().setParseAction( removeQuotes ) - openTag = Suppress("<") + tagStr("tag") + \ - Dict(ZeroOrMore(Group( tagAttrName + Suppress("=") + tagAttrValue ))) + \ - Optional("/",default=[False]).setResultsName("empty").setParseAction(lambda s,l,t:t[0]=='/') + Suppress(">") - else: - printablesLessRAbrack = "".join( [ c for c in printables if c not in ">" ] ) - tagAttrValue = quotedString.copy().setParseAction( removeQuotes ) | Word(printablesLessRAbrack) - openTag = Suppress("<") + tagStr("tag") + \ - Dict(ZeroOrMore(Group( tagAttrName.setParseAction(downcaseTokens) + \ - Optional( Suppress("=") + tagAttrValue ) ))) + \ - Optional("/",default=[False]).setResultsName("empty").setParseAction(lambda s,l,t:t[0]=='/') + Suppress(">") - closeTag = Combine(_L("") - - openTag = openTag.setResultsName("start"+"".join(resname.replace(":"," ").title().split())).setName("<%s>" % tagStr) - closeTag = closeTag.setResultsName("end"+"".join(resname.replace(":"," ").title().split())).setName("" % tagStr) - openTag.tag = resname - closeTag.tag = resname - return openTag, closeTag - -def makeHTMLTags(tagStr): - """Helper to construct opening and closing tag expressions for HTML, given a tag name""" - return _makeTags( tagStr, False ) - -def makeXMLTags(tagStr): - """Helper to construct opening and closing tag expressions for XML, given a tag name""" - return _makeTags( tagStr, True ) - -def withAttribute(*args,**attrDict): - """Helper to create a validating parse action to be used with start tags created - with C{L{makeXMLTags}} or C{L{makeHTMLTags}}. Use C{withAttribute} to qualify a starting tag - with a required attribute value, to avoid false matches on common tags such as - C{} or C{
}. - - Call C{withAttribute} with a series of attribute names and values. Specify the list - of filter attributes names and values as: - - keyword arguments, as in C{(align="right")}, or - - as an explicit dict with C{**} operator, when an attribute name is also a Python - reserved word, as in C{**{"class":"Customer", "align":"right"}} - - a list of name-value tuples, as in ( ("ns1:class", "Customer"), ("ns2:align","right") ) - For attribute names with a namespace prefix, you must use the second form. Attribute - names are matched insensitive to upper/lower case. - - To verify that the attribute exists, but without specifying a value, pass - C{withAttribute.ANY_VALUE} as the value. - """ - if args: - attrs = args[:] - else: - attrs = attrDict.items() - attrs = [(k,v) for k,v in attrs] - def pa(s,l,tokens): - for attrName,attrValue in attrs: - if attrName not in tokens: - raise ParseException(s,l,"no matching attribute " + attrName) - if attrValue != withAttribute.ANY_VALUE and tokens[attrName] != attrValue: - raise ParseException(s,l,"attribute '%s' has value '%s', must be '%s'" % - (attrName, tokens[attrName], attrValue)) - return pa -withAttribute.ANY_VALUE = object() - -opAssoc = _Constants() -opAssoc.LEFT = object() -opAssoc.RIGHT = object() - -def infixNotation( baseExpr, opList, lpar=Suppress('('), rpar=Suppress(')') ): - """Helper method for constructing grammars of expressions made up of - operators working in a precedence hierarchy. Operators may be unary or - binary, left- or right-associative. Parse actions can also be attached - to operator expressions. - - Parameters: - - baseExpr - expression representing the most basic element for the nested - - opList - list of tuples, one for each operator precedence level in the - expression grammar; each tuple is of the form - (opExpr, numTerms, rightLeftAssoc, parseAction), where: - - opExpr is the pyparsing expression for the operator; - may also be a string, which will be converted to a Literal; - if numTerms is 3, opExpr is a tuple of two expressions, for the - two operators separating the 3 terms - - numTerms is the number of terms for this operator (must - be 1, 2, or 3) - - rightLeftAssoc is the indicator whether the operator is - right or left associative, using the pyparsing-defined - constants C{opAssoc.RIGHT} and C{opAssoc.LEFT}. - - parseAction is the parse action to be associated with - expressions matching this operator expression (the - parse action tuple member may be omitted) - - lpar - expression for matching left-parentheses (default=Suppress('(')) - - rpar - expression for matching right-parentheses (default=Suppress(')')) - """ - ret = Forward() - lastExpr = baseExpr | ( lpar + ret + rpar ) - for i,operDef in enumerate(opList): - opExpr,arity,rightLeftAssoc,pa = (operDef + (None,))[:4] - if arity == 3: - if opExpr is None or len(opExpr) != 2: - raise ValueError("if numterms=3, opExpr must be a tuple or list of two expressions") - opExpr1, opExpr2 = opExpr - thisExpr = Forward()#.setName("expr%d" % i) - if rightLeftAssoc == opAssoc.LEFT: - if arity == 1: - matchExpr = FollowedBy(lastExpr + opExpr) + Group( lastExpr + OneOrMore( opExpr ) ) - elif arity == 2: - if opExpr is not None: - matchExpr = FollowedBy(lastExpr + opExpr + lastExpr) + Group( lastExpr + OneOrMore( opExpr + lastExpr ) ) - else: - matchExpr = FollowedBy(lastExpr+lastExpr) + Group( lastExpr + OneOrMore(lastExpr) ) - elif arity == 3: - matchExpr = FollowedBy(lastExpr + opExpr1 + lastExpr + opExpr2 + lastExpr) + \ - Group( lastExpr + opExpr1 + lastExpr + opExpr2 + lastExpr ) - else: - raise ValueError("operator must be unary (1), binary (2), or ternary (3)") - elif rightLeftAssoc == opAssoc.RIGHT: - if arity == 1: - # try to avoid LR with this extra test - if not isinstance(opExpr, Optional): - opExpr = Optional(opExpr) - matchExpr = FollowedBy(opExpr.expr + thisExpr) + Group( opExpr + thisExpr ) - elif arity == 2: - if opExpr is not None: - matchExpr = FollowedBy(lastExpr + opExpr + thisExpr) + Group( lastExpr + OneOrMore( opExpr + thisExpr ) ) - else: - matchExpr = FollowedBy(lastExpr + thisExpr) + Group( lastExpr + OneOrMore( thisExpr ) ) - elif arity == 3: - matchExpr = FollowedBy(lastExpr + opExpr1 + thisExpr + opExpr2 + thisExpr) + \ - Group( lastExpr + opExpr1 + thisExpr + opExpr2 + thisExpr ) - else: - raise ValueError("operator must be unary (1), binary (2), or ternary (3)") - else: - raise ValueError("operator must indicate right or left associativity") - if pa: - matchExpr.setParseAction( pa ) - thisExpr << ( matchExpr | lastExpr ) - lastExpr = thisExpr - ret << lastExpr - return ret -operatorPrecedence = infixNotation - -dblQuotedString = Regex(r'"(?:[^"\n\r\\]|(?:"")|(?:\\x[0-9a-fA-F]+)|(?:\\.))*"').setName("string enclosed in double quotes") -sglQuotedString = Regex(r"'(?:[^'\n\r\\]|(?:'')|(?:\\x[0-9a-fA-F]+)|(?:\\.))*'").setName("string enclosed in single quotes") -quotedString = Regex(r'''(?:"(?:[^"\n\r\\]|(?:"")|(?:\\x[0-9a-fA-F]+)|(?:\\.))*")|(?:'(?:[^'\n\r\\]|(?:'')|(?:\\x[0-9a-fA-F]+)|(?:\\.))*')''').setName("quotedString using single or double quotes") -unicodeString = Combine(_L('u') + quotedString.copy()) - -def nestedExpr(opener="(", closer=")", content=None, ignoreExpr=quotedString.copy()): - """Helper method for defining nested lists enclosed in opening and closing - delimiters ("(" and ")" are the default). - - Parameters: - - opener - opening character for a nested list (default="("); can also be a pyparsing expression - - closer - closing character for a nested list (default=")"); can also be a pyparsing expression - - content - expression for items within the nested lists (default=None) - - ignoreExpr - expression for ignoring opening and closing delimiters (default=quotedString) - - If an expression is not provided for the content argument, the nested - expression will capture all whitespace-delimited content between delimiters - as a list of separate values. - - Use the C{ignoreExpr} argument to define expressions that may contain - opening or closing characters that should not be treated as opening - or closing characters for nesting, such as quotedString or a comment - expression. Specify multiple expressions using an C{L{Or}} or C{L{MatchFirst}}. - The default is L{quotedString}, but if no expressions are to be ignored, - then pass C{None} for this argument. - """ - if opener == closer: - raise ValueError("opening and closing strings cannot be the same") - if content is None: - if isinstance(opener,basestring) and isinstance(closer,basestring): - if len(opener) == 1 and len(closer)==1: - if ignoreExpr is not None: - content = (Combine(OneOrMore(~ignoreExpr + - CharsNotIn(opener+closer+ParserElement.DEFAULT_WHITE_CHARS,exact=1)) - ).setParseAction(lambda t:t[0].strip())) - else: - content = (empty.copy()+CharsNotIn(opener+closer+ParserElement.DEFAULT_WHITE_CHARS - ).setParseAction(lambda t:t[0].strip())) - else: - if ignoreExpr is not None: - content = (Combine(OneOrMore(~ignoreExpr + - ~Literal(opener) + ~Literal(closer) + - CharsNotIn(ParserElement.DEFAULT_WHITE_CHARS,exact=1)) - ).setParseAction(lambda t:t[0].strip())) - else: - content = (Combine(OneOrMore(~Literal(opener) + ~Literal(closer) + - CharsNotIn(ParserElement.DEFAULT_WHITE_CHARS,exact=1)) - ).setParseAction(lambda t:t[0].strip())) - else: - raise ValueError("opening and closing arguments must be strings if no content expression is given") - ret = Forward() - if ignoreExpr is not None: - ret << Group( Suppress(opener) + ZeroOrMore( ignoreExpr | ret | content ) + Suppress(closer) ) - else: - ret << Group( Suppress(opener) + ZeroOrMore( ret | content ) + Suppress(closer) ) - return ret - -def indentedBlock(blockStatementExpr, indentStack, indent=True): - """Helper method for defining space-delimited indentation blocks, such as - those used to define block statements in Python source code. - - Parameters: - - blockStatementExpr - expression defining syntax of statement that - is repeated within the indented block - - indentStack - list created by caller to manage indentation stack - (multiple statementWithIndentedBlock expressions within a single grammar - should share a common indentStack) - - indent - boolean indicating whether block must be indented beyond the - the current level; set to False for block of left-most statements - (default=True) - - A valid block must contain at least one C{blockStatement}. - """ - def checkPeerIndent(s,l,t): - if l >= len(s): return - curCol = col(l,s) - if curCol != indentStack[-1]: - if curCol > indentStack[-1]: - raise ParseFatalException(s,l,"illegal nesting") - raise ParseException(s,l,"not a peer entry") - - def checkSubIndent(s,l,t): - curCol = col(l,s) - if curCol > indentStack[-1]: - indentStack.append( curCol ) - else: - raise ParseException(s,l,"not a subentry") - - def checkUnindent(s,l,t): - if l >= len(s): return - curCol = col(l,s) - if not(indentStack and curCol < indentStack[-1] and curCol <= indentStack[-2]): - raise ParseException(s,l,"not an unindent") - indentStack.pop() - - NL = OneOrMore(LineEnd().setWhitespaceChars("\t ").suppress()) - INDENT = Empty() + Empty().setParseAction(checkSubIndent) - PEER = Empty().setParseAction(checkPeerIndent) - UNDENT = Empty().setParseAction(checkUnindent) - if indent: - smExpr = Group( Optional(NL) + - #~ FollowedBy(blockStatementExpr) + - INDENT + (OneOrMore( PEER + Group(blockStatementExpr) + Optional(NL) )) + UNDENT) - else: - smExpr = Group( Optional(NL) + - (OneOrMore( PEER + Group(blockStatementExpr) + Optional(NL) )) ) - blockStatementExpr.ignore(_bslash + LineEnd()) - return smExpr - -alphas8bit = srange(r"[\0xc0-\0xd6\0xd8-\0xf6\0xf8-\0xff]") -punc8bit = srange(r"[\0xa1-\0xbf\0xd7\0xf7]") - -anyOpenTag,anyCloseTag = makeHTMLTags(Word(alphas,alphanums+"_:")) -commonHTMLEntity = Combine(_L("&") + oneOf("gt lt amp nbsp quot").setResultsName("entity") +";").streamline() -_htmlEntityMap = dict(zip("gt lt amp nbsp quot".split(),'><& "')) -replaceHTMLEntity = lambda t : t.entity in _htmlEntityMap and _htmlEntityMap[t.entity] or None - -# it's easy to get these comment structures wrong - they're very common, so may as well make them available -cStyleComment = Regex(r"/\*(?:[^*]*\*+)+?/").setName("C style comment") - -htmlComment = Regex(r"") -restOfLine = Regex(r".*").leaveWhitespace() -dblSlashComment = Regex(r"\/\/(\\\n|.)*").setName("// comment") -cppStyleComment = Regex(r"/(?:\*(?:[^*]*\*+)+?/|/[^\n]*(?:\n[^\n]*)*?(?:(?" + str(tokenlist)) - print ("tokens = " + str(tokens)) - print ("tokens.columns = " + str(tokens.columns)) - print ("tokens.tables = " + str(tokens.tables)) - print (tokens.asXML("SQL",True)) - except ParseBaseException, err: - print (teststring + "->") - print (err.line) - print (" "*(err.column-1) + "^") - print (err) - print() - - selectToken = CaselessLiteral( "select" ) - fromToken = CaselessLiteral( "from" ) - - ident = Word( alphas, alphanums + "_$" ) - columnName = delimitedList( ident, ".", combine=True ).setParseAction( upcaseTokens ) - columnNameList = Group( delimitedList( columnName ) )#.setName("columns") - tableName = delimitedList( ident, ".", combine=True ).setParseAction( upcaseTokens ) - tableNameList = Group( delimitedList( tableName ) )#.setName("tables") - simpleSQL = ( selectToken + \ - ( '*' | columnNameList ).setResultsName( "columns" ) + \ - fromToken + \ - tableNameList.setResultsName( "tables" ) ) - - test( "SELECT * from XYZZY, ABC" ) - test( "select * from SYS.XYZZY" ) - test( "Select A from Sys.dual" ) - test( "Select AA,BB,CC from Sys.dual" ) - test( "Select A, B, C from Sys.dual" ) - test( "Select A, B, C from Sys.dual" ) - test( "Xelect A, B, C from Sys.dual" ) - test( "Select A, B, C frox Sys.dual" ) - test( "Select" ) - test( "Select ^^^ frox Sys.dual" ) - test( "Select A, B, C from Sys.dual, Table2 " ) +# #~ class ReparseException(ParseBaseException): +# #~ """Experimental class - parse actions can raise this exception to cause +# #~ pyparsing to reparse the input string: +# #~ - with a modified input string, and/or +# #~ - with a modified start location +# #~ Set the values of the ReparseException in the constructor, and raise the +# #~ exception in a parse action to cause pyparsing to use the new string/location. +# #~ Setting the values as None causes no change to be made. +# #~ """ +# #~ def __init_( self, newstring, restartLoc ): +# #~ self.newParseText = newstring +# #~ self.reparseLoc = restartLoc +# +# class RecursiveGrammarException(Exception): +# """exception thrown by C{validate()} if the grammar could be improperly recursive""" +# def __init__( self, parseElementList ): +# self.parseElementTrace = parseElementList +# +# def __str__( self ): +# return "RecursiveGrammarException: %s" % self.parseElementTrace +# +# class _ParseResultsWithOffset(object): +# def __init__(self,p1,p2): +# self.tup = (p1,p2) +# def __getitem__(self,i): +# return self.tup[i] +# def __repr__(self): +# return repr(self.tup) +# def setOffset(self,i): +# self.tup = (self.tup[0],i) +# +# class ParseResults(object): +# """Structured parse results, to provide multiple means of access to the parsed data: +# - as a list (C{len(results)}) +# - by list index (C{results[0], results[1]}, etc.) +# - by attribute (C{results.}) +# """ +# #~ __slots__ = ( "__toklist", "__tokdict", "__doinit", "__name", "__parent", "__accumNames", "__weakref__" ) +# def __new__(cls, toklist, name=None, asList=True, modal=True ): +# if isinstance(toklist, cls): +# return toklist +# retobj = object.__new__(cls) +# retobj.__doinit = True +# return retobj +# +# # Performance tuning: we construct a *lot* of these, so keep this +# # constructor as small and fast as possible +# def __init__( self, toklist, name=None, asList=True, modal=True, isinstance=isinstance ): +# if self.__doinit: +# self.__doinit = False +# self.__name = None +# self.__parent = None +# self.__accumNames = {} +# if isinstance(toklist, list): +# self.__toklist = toklist[:] +# else: +# self.__toklist = [toklist] +# self.__tokdict = dict() +# +# if name is not None and name: +# if not modal: +# self.__accumNames[name] = 0 +# if isinstance(name,int): +# name = _ustr(name) # will always return a str, but use _ustr for consistency +# self.__name = name +# if not toklist in (None,'',[]): +# if isinstance(toklist,basestring): +# toklist = [ toklist ] +# if asList: +# if isinstance(toklist,ParseResults): +# self[name] = _ParseResultsWithOffset(toklist.copy(),0) +# else: +# self[name] = _ParseResultsWithOffset(ParseResults(toklist[0]),0) +# self[name].__name = name +# else: +# try: +# self[name] = toklist[0] +# except (KeyError,TypeError,IndexError): +# self[name] = toklist +# +# def __getitem__( self, i ): +# if isinstance( i, (int,slice) ): +# return self.__toklist[i] +# else: +# if i not in self.__accumNames: +# return self.__tokdict[i][-1][0] +# else: +# return ParseResults([ v[0] for v in self.__tokdict[i] ]) +# +# def __setitem__( self, k, v, isinstance=isinstance ): +# if isinstance(v,_ParseResultsWithOffset): +# self.__tokdict[k] = self.__tokdict.get(k,list()) + [v] +# sub = v[0] +# elif isinstance(k,int): +# self.__toklist[k] = v +# sub = v +# else: +# self.__tokdict[k] = self.__tokdict.get(k,list()) + [_ParseResultsWithOffset(v,0)] +# sub = v +# if isinstance(sub,ParseResults): +# sub.__parent = wkref(self) +# +# def __delitem__( self, i ): +# if isinstance(i,(int,slice)): +# mylen = len( self.__toklist ) +# del self.__toklist[i] +# +# # convert int to slice +# if isinstance(i, int): +# if i < 0: +# i += mylen +# i = slice(i, i+1) +# # get removed indices +# removed = list(range(*i.indices(mylen))) +# removed.reverse() +# # fixup indices in token dictionary +# for name in self.__tokdict: +# occurrences = self.__tokdict[name] +# for j in removed: +# for k, (value, position) in enumerate(occurrences): +# occurrences[k] = _ParseResultsWithOffset(value, position - (position > j)) +# else: +# del self.__tokdict[i] +# +# def __contains__( self, k ): +# return k in self.__tokdict +# +# def __len__( self ): return len( self.__toklist ) +# def __bool__(self): return len( self.__toklist ) > 0 +# __nonzero__ = __bool__ +# def __iter__( self ): return iter( self.__toklist ) +# def __reversed__( self ): return iter( self.__toklist[::-1] ) +# def keys( self ): +# """Returns all named result keys.""" +# return self.__tokdict.keys() +# +# def pop( self, index=-1 ): +# """Removes and returns item at specified index (default=last). +# Will work with either numeric indices or dict-key indicies.""" +# ret = self[index] +# del self[index] +# return ret +# +# def get(self, key, defaultValue=None): +# """Returns named result matching the given key, or if there is no +# such name, then returns the given C{defaultValue} or C{None} if no +# C{defaultValue} is specified.""" +# if key in self: +# return self[key] +# else: +# return defaultValue +# +# def insert( self, index, insStr ): +# """Inserts new element at location index in the list of parsed tokens.""" +# self.__toklist.insert(index, insStr) +# # fixup indices in token dictionary +# for name in self.__tokdict: +# occurrences = self.__tokdict[name] +# for k, (value, position) in enumerate(occurrences): +# occurrences[k] = _ParseResultsWithOffset(value, position + (position > index)) +# +# def items( self ): +# """Returns all named result keys and values as a list of tuples.""" +# return [(k,self[k]) for k in self.__tokdict] +# +# def values( self ): +# """Returns all named result values.""" +# return [ v[-1][0] for v in self.__tokdict.values() ] +# +# def __getattr__( self, name ): +# if True: #name not in self.__slots__: +# if name in self.__tokdict: +# if name not in self.__accumNames: +# return self.__tokdict[name][-1][0] +# else: +# return ParseResults([ v[0] for v in self.__tokdict[name] ]) +# else: +# return "" +# return None +# +# def __add__( self, other ): +# ret = self.copy() +# ret += other +# return ret +# +# def __iadd__( self, other ): +# if other.__tokdict: +# offset = len(self.__toklist) +# addoffset = ( lambda a: (a<0 and offset) or (a+offset) ) +# otheritems = other.__tokdict.items() +# otherdictitems = [(k, _ParseResultsWithOffset(v[0],addoffset(v[1])) ) +# for (k,vlist) in otheritems for v in vlist] +# for k,v in otherdictitems: +# self[k] = v +# if isinstance(v[0],ParseResults): +# v[0].__parent = wkref(self) +# +# self.__toklist += other.__toklist +# self.__accumNames.update( other.__accumNames ) +# return self +# +# def __radd__(self, other): +# if isinstance(other,int) and other == 0: +# return self.copy() +# +# def __repr__( self ): +# return "(%s, %s)" % ( repr( self.__toklist ), repr( self.__tokdict ) ) +# +# def __str__( self ): +# out = [] +# for i in self.__toklist: +# if isinstance(i, ParseResults): +# out.append(_ustr(i)) +# else: +# out.append(repr(i)) +# return '[' + ', '.join(out) + ']' +# +# def _asStringList( self, sep='' ): +# out = [] +# for item in self.__toklist: +# if out and sep: +# out.append(sep) +# if isinstance( item, ParseResults ): +# out += item._asStringList() +# else: +# out.append( _ustr(item) ) +# return out +# +# def asList( self ): +# """Returns the parse results as a nested list of matching tokens, all converted to strings.""" +# out = [] +# for res in self.__toklist: +# if isinstance(res,ParseResults): +# out.append( res.asList() ) +# else: +# out.append( res ) +# return out +# +# def asDict( self ): +# """Returns the named parse results as dictionary.""" +# return dict( self.items() ) +# +# def copy( self ): +# """Returns a new copy of a C{ParseResults} object.""" +# ret = ParseResults( self.__toklist ) +# ret.__tokdict = self.__tokdict.copy() +# ret.__parent = self.__parent +# ret.__accumNames.update( self.__accumNames ) +# ret.__name = self.__name +# return ret +# +# def asXML( self, doctag=None, namedItemsOnly=False, indent="", formatted=True ): +# """Returns the parse results as XML. Tags are created for tokens and lists that have defined results names.""" +# nl = "\n" +# out = [] +# namedItems = dict( [ (v[1],k) for (k,vlist) in self.__tokdict.items() +# for v in vlist ] ) +# nextLevelIndent = indent + " " +# +# # collapse out indents if formatting is not desired +# if not formatted: +# indent = "" +# nextLevelIndent = "" +# nl = "" +# +# selfTag = None +# if doctag is not None: +# selfTag = doctag +# else: +# if self.__name: +# selfTag = self.__name +# +# if not selfTag: +# if namedItemsOnly: +# return "" +# else: +# selfTag = "ITEM" +# +# out += [ nl, indent, "<", selfTag, ">" ] +# +# worklist = self.__toklist +# for i,res in enumerate(worklist): +# if isinstance(res,ParseResults): +# if i in namedItems: +# out += [ res.asXML(namedItems[i], +# namedItemsOnly and doctag is None, +# nextLevelIndent, +# formatted)] +# else: +# out += [ res.asXML(None, +# namedItemsOnly and doctag is None, +# nextLevelIndent, +# formatted)] +# else: +# # individual token, see if there is a name for it +# resTag = None +# if i in namedItems: +# resTag = namedItems[i] +# if not resTag: +# if namedItemsOnly: +# continue +# else: +# resTag = "ITEM" +# xmlBodyText = _xml_escape(_ustr(res)) +# out += [ nl, nextLevelIndent, "<", resTag, ">", +# xmlBodyText, +# "" ] +# +# out += [ nl, indent, "" ] +# return "".join(out) +# +# def __lookup(self,sub): +# for k,vlist in self.__tokdict.items(): +# for v,loc in vlist: +# if sub is v: +# return k +# return None +# +# def getName(self): +# """Returns the results name for this token expression.""" +# if self.__name: +# return self.__name +# elif self.__parent: +# par = self.__parent() +# if par: +# return par.__lookup(self) +# else: +# return None +# elif (len(self) == 1 and +# len(self.__tokdict) == 1 and +# self.__tokdict.values()[0][0][1] in (0,-1)): +# return self.__tokdict.keys()[0] +# else: +# return None +# +# def dump(self,indent='',depth=0): +# """Diagnostic method for listing out the contents of a C{ParseResults}. +# Accepts an optional C{indent} argument so that this string can be embedded +# in a nested display of other data.""" +# out = [] +# out.append( indent+_ustr(self.asList()) ) +# keys = self.items() +# keys.sort() +# for k,v in keys: +# if out: +# out.append('\n') +# out.append( "%s%s- %s: " % (indent,(' '*depth), k) ) +# if isinstance(v,ParseResults): +# if v.keys(): +# out.append( v.dump(indent,depth+1) ) +# else: +# out.append(_ustr(v)) +# else: +# out.append(_ustr(v)) +# return "".join(out) +# +# # add support for pickle protocol +# def __getstate__(self): +# return ( self.__toklist, +# ( self.__tokdict.copy(), +# self.__parent is not None and self.__parent() or None, +# self.__accumNames, +# self.__name ) ) +# +# def __setstate__(self,state): +# self.__toklist = state[0] +# (self.__tokdict, +# par, +# inAccumNames, +# self.__name) = state[1] +# self.__accumNames = {} +# self.__accumNames.update(inAccumNames) +# if par is not None: +# self.__parent = wkref(par) +# else: +# self.__parent = None +# +# def __dir__(self): +# return dir(super(ParseResults,self)) + list(self.keys()) +# +# def col (loc,strg): +# """Returns current column within a string, counting newlines as line separators. +# The first column is number 1. +# +# Note: the default parsing behavior is to expand tabs in the input string +# before starting the parsing process. See L{I{ParserElement.parseString}} for more information +# on parsing strings containing C{}s, and suggested methods to maintain a +# consistent view of the parsed string, the parse location, and line and column +# positions within the parsed string. +# """ +# return (loc} for more information +# on parsing strings containing C{}s, and suggested methods to maintain a +# consistent view of the parsed string, the parse location, and line and column +# positions within the parsed string. +# """ +# return strg.count("\n",0,loc) + 1 +# +# def line( loc, strg ): +# """Returns the line of text containing loc within a string, counting newlines as line separators. +# """ +# lastCR = strg.rfind("\n", 0, loc) +# nextCR = strg.find("\n", loc) +# if nextCR >= 0: +# return strg[lastCR+1:nextCR] +# else: +# return strg[lastCR+1:] +# +# def _defaultStartDebugAction( instring, loc, expr ): +# print ("Match " + _ustr(expr) + " at loc " + _ustr(loc) + "(%d,%d)" % ( lineno(loc,instring), col(loc,instring) )) +# +# def _defaultSuccessDebugAction( instring, startloc, endloc, expr, toks ): +# print ("Matched " + _ustr(expr) + " -> " + str(toks.asList())) +# +# def _defaultExceptionDebugAction( instring, loc, expr, exc ): +# print ("Exception raised:" + _ustr(exc)) +# +# def nullDebugAction(*args): +# """'Do-nothing' debug action, to suppress debugging output during parsing.""" +# pass +# +# 'decorator to trim function calls to match the arity of the target' +# def _trim_arity(func, maxargs=2): +# if func in singleArgBuiltins: +# return lambda s,l,t: func(t) +# limit = [0] +# foundArity = [False] +# def wrapper(*args): +# while 1: +# try: +# ret = func(*args[limit[0]:]) +# foundArity[0] = True +# return ret +# except TypeError: +# if limit[0] <= maxargs and not foundArity[0]: +# limit[0] += 1 +# continue +# raise +# return wrapper +# +# class ParserElement(object): +# """Abstract base level parser element class.""" +# DEFAULT_WHITE_CHARS = " \n\t\r" +# verbose_stacktrace = False +# +# def setDefaultWhitespaceChars( chars ): +# """Overrides the default whitespace chars +# """ +# ParserElement.DEFAULT_WHITE_CHARS = chars +# setDefaultWhitespaceChars = staticmethod(setDefaultWhitespaceChars) +# +# def inlineLiteralsUsing(cls): +# """ +# Set class to be used for inclusion of string literals into a parser. +# """ +# ParserElement.literalStringClass = cls +# inlineLiteralsUsing = staticmethod(inlineLiteralsUsing) +# +# def __init__( self, savelist=False ): +# self.parseAction = list() +# self.failAction = None +# #~ self.name = "" # don't define self.name, let subclasses try/except upcall +# self.strRepr = None +# self.resultsName = None +# self.saveAsList = savelist +# self.skipWhitespace = True +# self.whiteChars = ParserElement.DEFAULT_WHITE_CHARS +# self.copyDefaultWhiteChars = True +# self.mayReturnEmpty = False # used when checking for left-recursion +# self.keepTabs = False +# self.ignoreExprs = list() +# self.debug = False +# self.streamlined = False +# self.mayIndexError = True # used to optimize exception handling for subclasses that don't advance parse index +# self.errmsg = "" +# self.modalResults = True # used to mark results names as modal (report only last) or cumulative (list all) +# self.debugActions = ( None, None, None ) #custom debug actions +# self.re = None +# self.callPreparse = True # used to avoid redundant calls to preParse +# self.callDuringTry = False +# +# def copy( self ): +# """Make a copy of this C{ParserElement}. Useful for defining different parse actions +# for the same parsing pattern, using copies of the original parse element.""" +# cpy = copy.copy( self ) +# cpy.parseAction = self.parseAction[:] +# cpy.ignoreExprs = self.ignoreExprs[:] +# if self.copyDefaultWhiteChars: +# cpy.whiteChars = ParserElement.DEFAULT_WHITE_CHARS +# return cpy +# +# def setName( self, name ): +# """Define name for this expression, for use in debugging.""" +# self.name = name +# self.errmsg = "Expected " + self.name +# if hasattr(self,"exception"): +# self.exception.msg = self.errmsg +# return self +# +# def setResultsName( self, name, listAllMatches=False ): +# """Define name for referencing matching tokens as a nested attribute +# of the returned parse results. +# NOTE: this returns a *copy* of the original C{ParserElement} object; +# this is so that the client can define a basic element, such as an +# integer, and reference it in multiple places with different names. +# +# You can also set results names using the abbreviated syntax, +# C{expr("name")} in place of C{expr.setResultsName("name")} - +# see L{I{__call__}<__call__>}. +# """ +# newself = self.copy() +# if name.endswith("*"): +# name = name[:-1] +# listAllMatches=True +# newself.resultsName = name +# newself.modalResults = not listAllMatches +# return newself +# +# def setBreak(self,breakFlag = True): +# """Method to invoke the Python pdb debugger when this element is +# about to be parsed. Set C{breakFlag} to True to enable, False to +# disable. +# """ +# if breakFlag: +# _parseMethod = self._parse +# def breaker(instring, loc, doActions=True, callPreParse=True): +# import pdb +# pdb.set_trace() +# return _parseMethod( instring, loc, doActions, callPreParse ) +# breaker._originalParseMethod = _parseMethod +# self._parse = breaker +# else: +# if hasattr(self._parse,"_originalParseMethod"): +# self._parse = self._parse._originalParseMethod +# return self +# +# def setParseAction( self, *fns, **kwargs ): +# """Define action to perform when successfully matching parse element definition. +# Parse action fn is a callable method with 0-3 arguments, called as C{fn(s,loc,toks)}, +# C{fn(loc,toks)}, C{fn(toks)}, or just C{fn()}, where: +# - s = the original string being parsed (see note below) +# - loc = the location of the matching substring +# - toks = a list of the matched tokens, packaged as a C{L{ParseResults}} object +# If the functions in fns modify the tokens, they can return them as the return +# value from fn, and the modified list of tokens will replace the original. +# Otherwise, fn does not need to return any value. +# +# Note: the default parsing behavior is to expand tabs in the input string +# before starting the parsing process. See L{I{parseString}} for more information +# on parsing strings containing C{}s, and suggested methods to maintain a +# consistent view of the parsed string, the parse location, and line and column +# positions within the parsed string. +# """ +# self.parseAction = list(map(_trim_arity, list(fns))) +# self.callDuringTry = ("callDuringTry" in kwargs and kwargs["callDuringTry"]) +# return self +# +# def addParseAction( self, *fns, **kwargs ): +# """Add parse action to expression's list of parse actions. See L{I{setParseAction}}.""" +# self.parseAction += list(map(_trim_arity, list(fns))) +# self.callDuringTry = self.callDuringTry or ("callDuringTry" in kwargs and kwargs["callDuringTry"]) +# return self +# +# def setFailAction( self, fn ): +# """Define action to perform if parsing fails at this expression. +# Fail acton fn is a callable function that takes the arguments +# C{fn(s,loc,expr,err)} where: +# - s = string being parsed +# - loc = location where expression match was attempted and failed +# - expr = the parse expression that failed +# - err = the exception thrown +# The function returns no value. It may throw C{L{ParseFatalException}} +# if it is desired to stop parsing immediately.""" +# self.failAction = fn +# return self +# +# def _skipIgnorables( self, instring, loc ): +# exprsFound = True +# while exprsFound: +# exprsFound = False +# for e in self.ignoreExprs: +# try: +# while 1: +# loc,dummy = e._parse( instring, loc ) +# exprsFound = True +# except ParseException: +# pass +# return loc +# +# def preParse( self, instring, loc ): +# if self.ignoreExprs: +# loc = self._skipIgnorables( instring, loc ) +# +# if self.skipWhitespace: +# wt = self.whiteChars +# instrlen = len(instring) +# while loc < instrlen and instring[loc] in wt: +# loc += 1 +# +# return loc +# +# def parseImpl( self, instring, loc, doActions=True ): +# return loc, [] +# +# def postParse( self, instring, loc, tokenlist ): +# return tokenlist +# +# #~ @profile +# def _parseNoCache( self, instring, loc, doActions=True, callPreParse=True ): +# debugging = ( self.debug ) #and doActions ) +# +# if debugging or self.failAction: +# #~ print ("Match",self,"at loc",loc,"(%d,%d)" % ( lineno(loc,instring), col(loc,instring) )) +# if (self.debugActions[0] ): +# self.debugActions[0]( instring, loc, self ) +# if callPreParse and self.callPreparse: +# preloc = self.preParse( instring, loc ) +# else: +# preloc = loc +# tokensStart = preloc +# try: +# try: +# loc,tokens = self.parseImpl( instring, preloc, doActions ) +# except IndexError: +# raise ParseException( instring, len(instring), self.errmsg, self ) +# except ParseBaseException, err: +# #~ print ("Exception raised:", err) +# err = None +# if self.debugActions[2]: +# self.debugActions[2]( instring, tokensStart, self, err ) +# if self.failAction: +# self.failAction( instring, tokensStart, self, err ) +# raise +# else: +# if callPreParse and self.callPreparse: +# preloc = self.preParse( instring, loc ) +# else: +# preloc = loc +# tokensStart = preloc +# if self.mayIndexError or loc >= len(instring): +# try: +# loc,tokens = self.parseImpl( instring, preloc, doActions ) +# except IndexError: +# raise ParseException( instring, len(instring), self.errmsg, self ) +# else: +# loc,tokens = self.parseImpl( instring, preloc, doActions ) +# +# tokens = self.postParse( instring, loc, tokens ) +# +# retTokens = ParseResults( tokens, self.resultsName, asList=self.saveAsList, modal=self.modalResults ) +# if self.parseAction and (doActions or self.callDuringTry): +# if debugging: +# try: +# for fn in self.parseAction: +# tokens = fn( instring, tokensStart, retTokens ) +# if tokens is not None: +# retTokens = ParseResults( tokens, +# self.resultsName, +# asList=self.saveAsList and isinstance(tokens,(ParseResults,list)), +# modal=self.modalResults ) +# except ParseBaseException, err: +# #~ print "Exception raised in user parse action:", err +# if (self.debugActions[2] ): +# self.debugActions[2]( instring, tokensStart, self, err ) +# raise +# else: +# for fn in self.parseAction: +# tokens = fn( instring, tokensStart, retTokens ) +# if tokens is not None: +# retTokens = ParseResults( tokens, +# self.resultsName, +# asList=self.saveAsList and isinstance(tokens,(ParseResults,list)), +# modal=self.modalResults ) +# +# if debugging: +# #~ print ("Matched",self,"->",retTokens.asList()) +# if (self.debugActions[1] ): +# self.debugActions[1]( instring, tokensStart, loc, self, retTokens ) +# +# return loc, retTokens +# +# def tryParse( self, instring, loc ): +# try: +# return self._parse( instring, loc, doActions=False )[0] +# except ParseFatalException: +# raise ParseException( instring, loc, self.errmsg, self) +# +# # this method gets repeatedly called during backtracking with the same arguments - +# # we can cache these arguments and save ourselves the trouble of re-parsing the contained expression +# def _parseCache( self, instring, loc, doActions=True, callPreParse=True ): +# lookup = (self,instring,loc,callPreParse,doActions) +# if lookup in ParserElement._exprArgCache: +# value = ParserElement._exprArgCache[ lookup ] +# if isinstance(value, Exception): +# raise value +# return (value[0],value[1].copy()) +# else: +# try: +# value = self._parseNoCache( instring, loc, doActions, callPreParse ) +# ParserElement._exprArgCache[ lookup ] = (value[0],value[1].copy()) +# return value +# except ParseBaseException, pe: +# ParserElement._exprArgCache[ lookup ] = pe +# raise +# +# _parse = _parseNoCache +# +# # argument cache for optimizing repeated calls when backtracking through recursive expressions +# _exprArgCache = {} +# def resetCache(): +# ParserElement._exprArgCache.clear() +# resetCache = staticmethod(resetCache) +# +# _packratEnabled = False +# def enablePackrat(): +# """Enables "packrat" parsing, which adds memoizing to the parsing logic. +# Repeated parse attempts at the same string location (which happens +# often in many complex grammars) can immediately return a cached value, +# instead of re-executing parsing/validating code. Memoizing is done of +# both valid results and parsing exceptions. +# +# This speedup may break existing programs that use parse actions that +# have side-effects. For this reason, packrat parsing is disabled when +# you first import pyparsing. To activate the packrat feature, your +# program must call the class method C{ParserElement.enablePackrat()}. If +# your program uses C{psyco} to "compile as you go", you must call +# C{enablePackrat} before calling C{psyco.full()}. If you do not do this, +# Python will crash. For best results, call C{enablePackrat()} immediately +# after importing pyparsing. +# """ +# if not ParserElement._packratEnabled: +# ParserElement._packratEnabled = True +# ParserElement._parse = ParserElement._parseCache +# enablePackrat = staticmethod(enablePackrat) +# +# def parseString( self, instring, parseAll=False ): +# """Execute the parse expression with the given string. +# This is the main interface to the client code, once the complete +# expression has been built. +# +# If you want the grammar to require that the entire input string be +# successfully parsed, then set C{parseAll} to True (equivalent to ending +# the grammar with C{L{StringEnd()}}). +# +# Note: C{parseString} implicitly calls C{expandtabs()} on the input string, +# in order to report proper column numbers in parse actions. +# If the input string contains tabs and +# the grammar uses parse actions that use the C{loc} argument to index into the +# string being parsed, you can ensure you have a consistent view of the input +# string by: +# - calling C{parseWithTabs} on your grammar before calling C{parseString} +# (see L{I{parseWithTabs}}) +# - define your parse action using the full C{(s,loc,toks)} signature, and +# reference the input string using the parse action's C{s} argument +# - explictly expand the tabs in your input string before calling +# C{parseString} +# """ +# ParserElement.resetCache() +# if not self.streamlined: +# self.streamline() +# #~ self.saveAsList = True +# for e in self.ignoreExprs: +# e.streamline() +# if not self.keepTabs: +# instring = instring.expandtabs() +# try: +# loc, tokens = self._parse( instring, 0 ) +# if parseAll: +# loc = self.preParse( instring, loc ) +# se = Empty() + StringEnd() +# se._parse( instring, loc ) +# except ParseBaseException, exc: +# if ParserElement.verbose_stacktrace: +# raise +# else: +# # catch and re-raise exception from here, clears out pyparsing internal stack trace +# raise exc +# else: +# return tokens +# +# def scanString( self, instring, maxMatches=_MAX_INT, overlap=False ): +# """Scan the input string for expression matches. Each match will return the +# matching tokens, start location, and end location. May be called with optional +# C{maxMatches} argument, to clip scanning after 'n' matches are found. If +# C{overlap} is specified, then overlapping matches will be reported. +# +# Note that the start and end locations are reported relative to the string +# being parsed. See L{I{parseString}} for more information on parsing +# strings with embedded tabs.""" +# if not self.streamlined: +# self.streamline() +# for e in self.ignoreExprs: +# e.streamline() +# +# if not self.keepTabs: +# instring = _ustr(instring).expandtabs() +# instrlen = len(instring) +# loc = 0 +# preparseFn = self.preParse +# parseFn = self._parse +# ParserElement.resetCache() +# matches = 0 +# try: +# while loc <= instrlen and matches < maxMatches: +# try: +# preloc = preparseFn( instring, loc ) +# nextLoc,tokens = parseFn( instring, preloc, callPreParse=False ) +# except ParseException: +# loc = preloc+1 +# else: +# if nextLoc > loc: +# matches += 1 +# yield tokens, preloc, nextLoc +# if overlap: +# nextloc = preparseFn( instring, loc ) +# if nextloc > loc: +# loc = nextLoc +# else: +# loc += 1 +# else: +# loc = nextLoc +# else: +# loc = preloc+1 +# except ParseBaseException, exc: +# if ParserElement.verbose_stacktrace: +# raise +# else: +# # catch and re-raise exception from here, clears out pyparsing internal stack trace +# raise exc +# +# def transformString( self, instring ): +# """Extension to C{L{scanString}}, to modify matching text with modified tokens that may +# be returned from a parse action. To use C{transformString}, define a grammar and +# attach a parse action to it that modifies the returned token list. +# Invoking C{transformString()} on a target string will then scan for matches, +# and replace the matched text patterns according to the logic in the parse +# action. C{transformString()} returns the resulting transformed string.""" +# out = [] +# lastE = 0 +# # force preservation of s, to minimize unwanted transformation of string, and to +# # keep string locs straight between transformString and scanString +# self.keepTabs = True +# try: +# for t,s,e in self.scanString( instring ): +# out.append( instring[lastE:s] ) +# if t: +# if isinstance(t,ParseResults): +# out += t.asList() +# elif isinstance(t,list): +# out += t +# else: +# out.append(t) +# lastE = e +# out.append(instring[lastE:]) +# out = [o for o in out if o] +# return "".join(map(_ustr,_flatten(out))) +# except ParseBaseException, exc: +# if ParserElement.verbose_stacktrace: +# raise +# else: +# # catch and re-raise exception from here, clears out pyparsing internal stack trace +# raise exc +# +# def searchString( self, instring, maxMatches=_MAX_INT ): +# """Another extension to C{L{scanString}}, simplifying the access to the tokens found +# to match the given parse expression. May be called with optional +# C{maxMatches} argument, to clip searching after 'n' matches are found. +# """ +# try: +# return ParseResults([ t for t,s,e in self.scanString( instring, maxMatches ) ]) +# except ParseBaseException, exc: +# if ParserElement.verbose_stacktrace: +# raise +# else: +# # catch and re-raise exception from here, clears out pyparsing internal stack trace +# raise exc +# +# def __add__(self, other ): +# """Implementation of + operator - returns C{L{And}}""" +# if isinstance( other, basestring ): +# other = ParserElement.literalStringClass( other ) +# if not isinstance( other, ParserElement ): +# warnings.warn("Cannot combine element of type %s with ParserElement" % type(other), +# SyntaxWarning, stacklevel=2) +# return None +# return And( [ self, other ] ) +# +# def __radd__(self, other ): +# """Implementation of + operator when left operand is not a C{L{ParserElement}}""" +# if isinstance( other, basestring ): +# other = ParserElement.literalStringClass( other ) +# if not isinstance( other, ParserElement ): +# warnings.warn("Cannot combine element of type %s with ParserElement" % type(other), +# SyntaxWarning, stacklevel=2) +# return None +# return other + self +# +# def __sub__(self, other): +# """Implementation of - operator, returns C{L{And}} with error stop""" +# if isinstance( other, basestring ): +# other = ParserElement.literalStringClass( other ) +# if not isinstance( other, ParserElement ): +# warnings.warn("Cannot combine element of type %s with ParserElement" % type(other), +# SyntaxWarning, stacklevel=2) +# return None +# return And( [ self, And._ErrorStop(), other ] ) +# +# def __rsub__(self, other ): +# """Implementation of - operator when left operand is not a C{L{ParserElement}}""" +# if isinstance( other, basestring ): +# other = ParserElement.literalStringClass( other ) +# if not isinstance( other, ParserElement ): +# warnings.warn("Cannot combine element of type %s with ParserElement" % type(other), +# SyntaxWarning, stacklevel=2) +# return None +# return other - self +# +# def __mul__(self,other): +# """Implementation of * operator, allows use of C{expr * 3} in place of +# C{expr + expr + expr}. Expressions may also me multiplied by a 2-integer +# tuple, similar to C{{min,max}} multipliers in regular expressions. Tuples +# may also include C{None} as in: +# - C{expr*(n,None)} or C{expr*(n,)} is equivalent +# to C{expr*n + L{ZeroOrMore}(expr)} +# (read as "at least n instances of C{expr}") +# - C{expr*(None,n)} is equivalent to C{expr*(0,n)} +# (read as "0 to n instances of C{expr}") +# - C{expr*(None,None)} is equivalent to C{L{ZeroOrMore}(expr)} +# - C{expr*(1,None)} is equivalent to C{L{OneOrMore}(expr)} +# +# Note that C{expr*(None,n)} does not raise an exception if +# more than n exprs exist in the input stream; that is, +# C{expr*(None,n)} does not enforce a maximum number of expr +# occurrences. If this behavior is desired, then write +# C{expr*(None,n) + ~expr} +# +# """ +# if isinstance(other,int): +# minElements, optElements = other,0 +# elif isinstance(other,tuple): +# other = (other + (None, None))[:2] +# if other[0] is None: +# other = (0, other[1]) +# if isinstance(other[0],int) and other[1] is None: +# if other[0] == 0: +# return ZeroOrMore(self) +# if other[0] == 1: +# return OneOrMore(self) +# else: +# return self*other[0] + ZeroOrMore(self) +# elif isinstance(other[0],int) and isinstance(other[1],int): +# minElements, optElements = other +# optElements -= minElements +# else: +# raise TypeError("cannot multiply 'ParserElement' and ('%s','%s') objects", type(other[0]),type(other[1])) +# else: +# raise TypeError("cannot multiply 'ParserElement' and '%s' objects", type(other)) +# +# if minElements < 0: +# raise ValueError("cannot multiply ParserElement by negative value") +# if optElements < 0: +# raise ValueError("second tuple value must be greater or equal to first tuple value") +# if minElements == optElements == 0: +# raise ValueError("cannot multiply ParserElement by 0 or (0,0)") +# +# if (optElements): +# def makeOptionalList(n): +# if n>1: +# return Optional(self + makeOptionalList(n-1)) +# else: +# return Optional(self) +# if minElements: +# if minElements == 1: +# ret = self + makeOptionalList(optElements) +# else: +# ret = And([self]*minElements) + makeOptionalList(optElements) +# else: +# ret = makeOptionalList(optElements) +# else: +# if minElements == 1: +# ret = self +# else: +# ret = And([self]*minElements) +# return ret +# +# def __rmul__(self, other): +# return self.__mul__(other) +# +# def __or__(self, other ): +# """Implementation of | operator - returns C{L{MatchFirst}}""" +# if isinstance( other, basestring ): +# other = ParserElement.literalStringClass( other ) +# if not isinstance( other, ParserElement ): +# warnings.warn("Cannot combine element of type %s with ParserElement" % type(other), +# SyntaxWarning, stacklevel=2) +# return None +# return MatchFirst( [ self, other ] ) +# +# def __ror__(self, other ): +# """Implementation of | operator when left operand is not a C{L{ParserElement}}""" +# if isinstance( other, basestring ): +# other = ParserElement.literalStringClass( other ) +# if not isinstance( other, ParserElement ): +# warnings.warn("Cannot combine element of type %s with ParserElement" % type(other), +# SyntaxWarning, stacklevel=2) +# return None +# return other | self +# +# def __xor__(self, other ): +# """Implementation of ^ operator - returns C{L{Or}}""" +# if isinstance( other, basestring ): +# other = ParserElement.literalStringClass( other ) +# if not isinstance( other, ParserElement ): +# warnings.warn("Cannot combine element of type %s with ParserElement" % type(other), +# SyntaxWarning, stacklevel=2) +# return None +# return Or( [ self, other ] ) +# +# def __rxor__(self, other ): +# """Implementation of ^ operator when left operand is not a C{L{ParserElement}}""" +# if isinstance( other, basestring ): +# other = ParserElement.literalStringClass( other ) +# if not isinstance( other, ParserElement ): +# warnings.warn("Cannot combine element of type %s with ParserElement" % type(other), +# SyntaxWarning, stacklevel=2) +# return None +# return other ^ self +# +# def __and__(self, other ): +# """Implementation of & operator - returns C{L{Each}}""" +# if isinstance( other, basestring ): +# other = ParserElement.literalStringClass( other ) +# if not isinstance( other, ParserElement ): +# warnings.warn("Cannot combine element of type %s with ParserElement" % type(other), +# SyntaxWarning, stacklevel=2) +# return None +# return Each( [ self, other ] ) +# +# def __rand__(self, other ): +# """Implementation of & operator when left operand is not a C{L{ParserElement}}""" +# if isinstance( other, basestring ): +# other = ParserElement.literalStringClass( other ) +# if not isinstance( other, ParserElement ): +# warnings.warn("Cannot combine element of type %s with ParserElement" % type(other), +# SyntaxWarning, stacklevel=2) +# return None +# return other & self +# +# def __invert__( self ): +# """Implementation of ~ operator - returns C{L{NotAny}}""" +# return NotAny( self ) +# +# def __call__(self, name): +# """Shortcut for C{L{setResultsName}}, with C{listAllMatches=default}:: +# userdata = Word(alphas).setResultsName("name") + Word(nums+"-").setResultsName("socsecno") +# could be written as:: +# userdata = Word(alphas)("name") + Word(nums+"-")("socsecno") +# +# If C{name} is given with a trailing C{'*'} character, then C{listAllMatches} will be +# passed as C{True}. +# """ +# return self.setResultsName(name) +# +# def suppress( self ): +# """Suppresses the output of this C{ParserElement}; useful to keep punctuation from +# cluttering up returned output. +# """ +# return Suppress( self ) +# +# def leaveWhitespace( self ): +# """Disables the skipping of whitespace before matching the characters in the +# C{ParserElement}'s defined pattern. This is normally only used internally by +# the pyparsing module, but may be needed in some whitespace-sensitive grammars. +# """ +# self.skipWhitespace = False +# return self +# +# def setWhitespaceChars( self, chars ): +# """Overrides the default whitespace chars +# """ +# self.skipWhitespace = True +# self.whiteChars = chars +# self.copyDefaultWhiteChars = False +# return self +# +# def parseWithTabs( self ): +# """Overrides default behavior to expand C{}s to spaces before parsing the input string. +# Must be called before C{parseString} when the input grammar contains elements that +# match C{} characters.""" +# self.keepTabs = True +# return self +# +# def ignore( self, other ): +# """Define expression to be ignored (e.g., comments) while doing pattern +# matching; may be called repeatedly, to define multiple comment or other +# ignorable patterns. +# """ +# if isinstance( other, Suppress ): +# if other not in self.ignoreExprs: +# self.ignoreExprs.append( other.copy() ) +# else: +# self.ignoreExprs.append( Suppress( other.copy() ) ) +# return self +# +# def setDebugActions( self, startAction, successAction, exceptionAction ): +# """Enable display of debugging messages while doing pattern matching.""" +# self.debugActions = (startAction or _defaultStartDebugAction, +# successAction or _defaultSuccessDebugAction, +# exceptionAction or _defaultExceptionDebugAction) +# self.debug = True +# return self +# +# def setDebug( self, flag=True ): +# """Enable display of debugging messages while doing pattern matching. +# Set C{flag} to True to enable, False to disable.""" +# if flag: +# self.setDebugActions( _defaultStartDebugAction, _defaultSuccessDebugAction, _defaultExceptionDebugAction ) +# else: +# self.debug = False +# return self +# +# def __str__( self ): +# return self.name +# +# def __repr__( self ): +# return _ustr(self) +# +# def streamline( self ): +# self.streamlined = True +# self.strRepr = None +# return self +# +# def checkRecursion( self, parseElementList ): +# pass +# +# def validate( self, validateTrace=[] ): +# """Check defined expressions for valid structure, check for infinite recursive definitions.""" +# self.checkRecursion( [] ) +# +# def parseFile( self, file_or_filename, parseAll=False ): +# """Execute the parse expression on the given file or filename. +# If a filename is specified (instead of a file object), +# the entire file is opened, read, and closed before parsing. +# """ +# try: +# file_contents = file_or_filename.read() +# except AttributeError: +# f = open(file_or_filename, "r") +# file_contents = f.read() +# f.close() +# try: +# return self.parseString(file_contents, parseAll) +# except ParseBaseException, exc: +# if ParserElement.verbose_stacktrace: +# raise +# else: +# # catch and re-raise exception from here, clears out pyparsing internal stack trace +# raise exc +# +# def getException(self): +# return ParseException("",0,self.errmsg,self) +# +# def __getattr__(self,aname): +# if aname == "myException": +# self.myException = ret = self.getException(); +# return ret; +# else: +# raise AttributeError("no such attribute " + aname) +# +# def __eq__(self,other): +# if isinstance(other, ParserElement): +# return self is other or self.__dict__ == other.__dict__ +# elif isinstance(other, basestring): +# try: +# self.parseString(_ustr(other), parseAll=True) +# return True +# except ParseBaseException: +# return False +# else: +# return super(ParserElement,self)==other +# +# def __ne__(self,other): +# return not (self == other) +# +# def __hash__(self): +# return hash(id(self)) +# +# def __req__(self,other): +# return self == other +# +# def __rne__(self,other): +# return not (self == other) +# +# +# class Token(ParserElement): +# """Abstract C{ParserElement} subclass, for defining atomic matching patterns.""" +# def __init__( self ): +# super(Token,self).__init__( savelist=False ) +# +# def setName(self, name): +# s = super(Token,self).setName(name) +# self.errmsg = "Expected " + self.name +# return s +# +# +# class Empty(Token): +# """An empty token, will always match.""" +# def __init__( self ): +# super(Empty,self).__init__() +# self.name = "Empty" +# self.mayReturnEmpty = True +# self.mayIndexError = False +# +# +# class NoMatch(Token): +# """A token that will never match.""" +# def __init__( self ): +# super(NoMatch,self).__init__() +# self.name = "NoMatch" +# self.mayReturnEmpty = True +# self.mayIndexError = False +# self.errmsg = "Unmatchable token" +# +# def parseImpl( self, instring, loc, doActions=True ): +# exc = self.myException +# exc.loc = loc +# exc.pstr = instring +# raise exc +# +# +# class Literal(Token): +# """Token to exactly match a specified string.""" +# def __init__( self, matchString ): +# super(Literal,self).__init__() +# self.match = matchString +# self.matchLen = len(matchString) +# try: +# self.firstMatchChar = matchString[0] +# except IndexError: +# warnings.warn("null string passed to Literal; use Empty() instead", +# SyntaxWarning, stacklevel=2) +# self.__class__ = Empty +# self.name = '"%s"' % _ustr(self.match) +# self.errmsg = "Expected " + self.name +# self.mayReturnEmpty = False +# self.mayIndexError = False +# +# # Performance tuning: this routine gets called a *lot* +# # if this is a single character match string and the first character matches, +# # short-circuit as quickly as possible, and avoid calling startswith +# #~ @profile +# def parseImpl( self, instring, loc, doActions=True ): +# if (instring[loc] == self.firstMatchChar and +# (self.matchLen==1 or instring.startswith(self.match,loc)) ): +# return loc+self.matchLen, self.match +# #~ raise ParseException( instring, loc, self.errmsg ) +# exc = self.myException +# exc.loc = loc +# exc.pstr = instring +# raise exc +# _L = Literal +# ParserElement.literalStringClass = Literal +# +# class Keyword(Token): +# """Token to exactly match a specified string as a keyword, that is, it must be +# immediately followed by a non-keyword character. Compare with C{L{Literal}}:: +# Literal("if") will match the leading C{'if'} in C{'ifAndOnlyIf'}. +# Keyword("if") will not; it will only match the leading C{'if'} in C{'if x=1'}, or C{'if(y==2)'} +# Accepts two optional constructor arguments in addition to the keyword string: +# C{identChars} is a string of characters that would be valid identifier characters, +# defaulting to all alphanumerics + "_" and "$"; C{caseless} allows case-insensitive +# matching, default is C{False}. +# """ +# DEFAULT_KEYWORD_CHARS = alphanums+"_$" +# +# def __init__( self, matchString, identChars=DEFAULT_KEYWORD_CHARS, caseless=False ): +# super(Keyword,self).__init__() +# self.match = matchString +# self.matchLen = len(matchString) +# try: +# self.firstMatchChar = matchString[0] +# except IndexError: +# warnings.warn("null string passed to Keyword; use Empty() instead", +# SyntaxWarning, stacklevel=2) +# self.name = '"%s"' % self.match +# self.errmsg = "Expected " + self.name +# self.mayReturnEmpty = False +# self.mayIndexError = False +# self.caseless = caseless +# if caseless: +# self.caselessmatch = matchString.upper() +# identChars = identChars.upper() +# self.identChars = set(identChars) +# +# def parseImpl( self, instring, loc, doActions=True ): +# if self.caseless: +# if ( (instring[ loc:loc+self.matchLen ].upper() == self.caselessmatch) and +# (loc >= len(instring)-self.matchLen or instring[loc+self.matchLen].upper() not in self.identChars) and +# (loc == 0 or instring[loc-1].upper() not in self.identChars) ): +# return loc+self.matchLen, self.match +# else: +# if (instring[loc] == self.firstMatchChar and +# (self.matchLen==1 or instring.startswith(self.match,loc)) and +# (loc >= len(instring)-self.matchLen or instring[loc+self.matchLen] not in self.identChars) and +# (loc == 0 or instring[loc-1] not in self.identChars) ): +# return loc+self.matchLen, self.match +# #~ raise ParseException( instring, loc, self.errmsg ) +# exc = self.myException +# exc.loc = loc +# exc.pstr = instring +# raise exc +# +# def copy(self): +# c = super(Keyword,self).copy() +# c.identChars = Keyword.DEFAULT_KEYWORD_CHARS +# return c +# +# def setDefaultKeywordChars( chars ): +# """Overrides the default Keyword chars +# """ +# Keyword.DEFAULT_KEYWORD_CHARS = chars +# setDefaultKeywordChars = staticmethod(setDefaultKeywordChars) +# +# class CaselessLiteral(Literal): +# """Token to match a specified string, ignoring case of letters. +# Note: the matched results will always be in the case of the given +# match string, NOT the case of the input text. +# """ +# def __init__( self, matchString ): +# super(CaselessLiteral,self).__init__( matchString.upper() ) +# # Preserve the defining literal. +# self.returnString = matchString +# self.name = "'%s'" % self.returnString +# self.errmsg = "Expected " + self.name +# +# def parseImpl( self, instring, loc, doActions=True ): +# if instring[ loc:loc+self.matchLen ].upper() == self.match: +# return loc+self.matchLen, self.returnString +# #~ raise ParseException( instring, loc, self.errmsg ) +# exc = self.myException +# exc.loc = loc +# exc.pstr = instring +# raise exc +# +# class CaselessKeyword(Keyword): +# def __init__( self, matchString, identChars=Keyword.DEFAULT_KEYWORD_CHARS ): +# super(CaselessKeyword,self).__init__( matchString, identChars, caseless=True ) +# +# def parseImpl( self, instring, loc, doActions=True ): +# if ( (instring[ loc:loc+self.matchLen ].upper() == self.caselessmatch) and +# (loc >= len(instring)-self.matchLen or instring[loc+self.matchLen].upper() not in self.identChars) ): +# return loc+self.matchLen, self.match +# #~ raise ParseException( instring, loc, self.errmsg ) +# exc = self.myException +# exc.loc = loc +# exc.pstr = instring +# raise exc +# +# class Word(Token): +# """Token for matching words composed of allowed character sets. +# Defined with string containing all allowed initial characters, +# an optional string containing allowed body characters (if omitted, +# defaults to the initial character set), and an optional minimum, +# maximum, and/or exact length. The default value for C{min} is 1 (a +# minimum value < 1 is not valid); the default values for C{max} and C{exact} +# are 0, meaning no maximum or exact length restriction. An optional +# C{exclude} parameter can list characters that might be found in +# the input C{bodyChars} string; useful to define a word of all printables +# except for one or two characters, for instance. +# """ +# def __init__( self, initChars, bodyChars=None, min=1, max=0, exact=0, asKeyword=False, excludeChars=None ): +# super(Word,self).__init__() +# if excludeChars: +# initChars = ''.join([c for c in initChars if c not in excludeChars]) +# if bodyChars: +# bodyChars = ''.join([c for c in bodyChars if c not in excludeChars]) +# self.initCharsOrig = initChars +# self.initChars = set(initChars) +# if bodyChars : +# self.bodyCharsOrig = bodyChars +# self.bodyChars = set(bodyChars) +# else: +# self.bodyCharsOrig = initChars +# self.bodyChars = set(initChars) +# +# self.maxSpecified = max > 0 +# +# if min < 1: +# raise ValueError("cannot specify a minimum length < 1; use Optional(Word()) if zero-length word is permitted") +# +# self.minLen = min +# +# if max > 0: +# self.maxLen = max +# else: +# self.maxLen = _MAX_INT +# +# if exact > 0: +# self.maxLen = exact +# self.minLen = exact +# +# self.name = _ustr(self) +# self.errmsg = "Expected " + self.name +# self.mayIndexError = False +# self.asKeyword = asKeyword +# +# if ' ' not in self.initCharsOrig+self.bodyCharsOrig and (min==1 and max==0 and exact==0): +# if self.bodyCharsOrig == self.initCharsOrig: +# self.reString = "[%s]+" % _escapeRegexRangeChars(self.initCharsOrig) +# elif len(self.bodyCharsOrig) == 1: +# self.reString = "%s[%s]*" % \ +# (re.escape(self.initCharsOrig), +# _escapeRegexRangeChars(self.bodyCharsOrig),) +# else: +# self.reString = "[%s][%s]*" % \ +# (_escapeRegexRangeChars(self.initCharsOrig), +# _escapeRegexRangeChars(self.bodyCharsOrig),) +# if self.asKeyword: +# self.reString = r"\b"+self.reString+r"\b" +# try: +# self.re = re.compile( self.reString ) +# except: +# self.re = None +# +# def parseImpl( self, instring, loc, doActions=True ): +# if self.re: +# result = self.re.match(instring,loc) +# if not result: +# exc = self.myException +# exc.loc = loc +# exc.pstr = instring +# raise exc +# +# loc = result.end() +# return loc, result.group() +# +# if not(instring[ loc ] in self.initChars): +# #~ raise ParseException( instring, loc, self.errmsg ) +# exc = self.myException +# exc.loc = loc +# exc.pstr = instring +# raise exc +# start = loc +# loc += 1 +# instrlen = len(instring) +# bodychars = self.bodyChars +# maxloc = start + self.maxLen +# maxloc = min( maxloc, instrlen ) +# while loc < maxloc and instring[loc] in bodychars: +# loc += 1 +# +# throwException = False +# if loc - start < self.minLen: +# throwException = True +# if self.maxSpecified and loc < instrlen and instring[loc] in bodychars: +# throwException = True +# if self.asKeyword: +# if (start>0 and instring[start-1] in bodychars) or (loc4: +# return s[:4]+"..." +# else: +# return s +# +# if ( self.initCharsOrig != self.bodyCharsOrig ): +# self.strRepr = "W:(%s,%s)" % ( charsAsStr(self.initCharsOrig), charsAsStr(self.bodyCharsOrig) ) +# else: +# self.strRepr = "W:(%s)" % charsAsStr(self.initCharsOrig) +# +# return self.strRepr +# +# +# class Regex(Token): +# """Token for matching strings that match a given regular expression. +# Defined with string specifying the regular expression in a form recognized by the inbuilt Python re module. +# """ +# compiledREtype = type(re.compile("[A-Z]")) +# def __init__( self, pattern, flags=0): +# """The parameters C{pattern} and C{flags} are passed to the C{re.compile()} function as-is. See the Python C{re} module for an explanation of the acceptable patterns and flags.""" +# super(Regex,self).__init__() +# +# if isinstance(pattern, basestring): +# if len(pattern) == 0: +# warnings.warn("null string passed to Regex; use Empty() instead", +# SyntaxWarning, stacklevel=2) +# +# self.pattern = pattern +# self.flags = flags +# +# try: +# self.re = re.compile(self.pattern, self.flags) +# self.reString = self.pattern +# except sre_constants.error: +# warnings.warn("invalid pattern (%s) passed to Regex" % pattern, +# SyntaxWarning, stacklevel=2) +# raise +# +# elif isinstance(pattern, Regex.compiledREtype): +# self.re = pattern +# self.pattern = \ +# self.reString = str(pattern) +# self.flags = flags +# +# else: +# raise ValueError("Regex may only be constructed with a string or a compiled RE object") +# +# self.name = _ustr(self) +# self.errmsg = "Expected " + self.name +# self.mayIndexError = False +# self.mayReturnEmpty = True +# +# def parseImpl( self, instring, loc, doActions=True ): +# result = self.re.match(instring,loc) +# if not result: +# exc = self.myException +# exc.loc = loc +# exc.pstr = instring +# raise exc +# +# loc = result.end() +# d = result.groupdict() +# ret = ParseResults(result.group()) +# if d: +# for k in d: +# ret[k] = d[k] +# return loc,ret +# +# def __str__( self ): +# try: +# return super(Regex,self).__str__() +# except: +# pass +# +# if self.strRepr is None: +# self.strRepr = "Re:(%s)" % repr(self.pattern) +# +# return self.strRepr +# +# +# class QuotedString(Token): +# """Token for matching strings that are delimited by quoting characters. +# """ +# def __init__( self, quoteChar, escChar=None, escQuote=None, multiline=False, unquoteResults=True, endQuoteChar=None): +# """ +# Defined with the following parameters: +# - quoteChar - string of one or more characters defining the quote delimiting string +# - escChar - character to escape quotes, typically backslash (default=None) +# - escQuote - special quote sequence to escape an embedded quote string (such as SQL's "" to escape an embedded ") (default=None) +# - multiline - boolean indicating whether quotes can span multiple lines (default=C{False}) +# - unquoteResults - boolean indicating whether the matched text should be unquoted (default=C{True}) +# - endQuoteChar - string of one or more characters defining the end of the quote delimited string (default=C{None} => same as quoteChar) +# """ +# super(QuotedString,self).__init__() +# +# # remove white space from quote chars - wont work anyway +# quoteChar = quoteChar.strip() +# if len(quoteChar) == 0: +# warnings.warn("quoteChar cannot be the empty string",SyntaxWarning,stacklevel=2) +# raise SyntaxError() +# +# if endQuoteChar is None: +# endQuoteChar = quoteChar +# else: +# endQuoteChar = endQuoteChar.strip() +# if len(endQuoteChar) == 0: +# warnings.warn("endQuoteChar cannot be the empty string",SyntaxWarning,stacklevel=2) +# raise SyntaxError() +# +# self.quoteChar = quoteChar +# self.quoteCharLen = len(quoteChar) +# self.firstQuoteChar = quoteChar[0] +# self.endQuoteChar = endQuoteChar +# self.endQuoteCharLen = len(endQuoteChar) +# self.escChar = escChar +# self.escQuote = escQuote +# self.unquoteResults = unquoteResults +# +# if multiline: +# self.flags = re.MULTILINE | re.DOTALL +# self.pattern = r'%s(?:[^%s%s]' % \ +# ( re.escape(self.quoteChar), +# _escapeRegexRangeChars(self.endQuoteChar[0]), +# (escChar is not None and _escapeRegexRangeChars(escChar) or '') ) +# else: +# self.flags = 0 +# self.pattern = r'%s(?:[^%s\n\r%s]' % \ +# ( re.escape(self.quoteChar), +# _escapeRegexRangeChars(self.endQuoteChar[0]), +# (escChar is not None and _escapeRegexRangeChars(escChar) or '') ) +# if len(self.endQuoteChar) > 1: +# self.pattern += ( +# '|(?:' + ')|(?:'.join(["%s[^%s]" % (re.escape(self.endQuoteChar[:i]), +# _escapeRegexRangeChars(self.endQuoteChar[i])) +# for i in range(len(self.endQuoteChar)-1,0,-1)]) + ')' +# ) +# if escQuote: +# self.pattern += (r'|(?:%s)' % re.escape(escQuote)) +# if escChar: +# self.pattern += (r'|(?:%s.)' % re.escape(escChar)) +# charset = ''.join(set(self.quoteChar[0]+self.endQuoteChar[0])).replace('^',r'\^').replace('-',r'\-') +# self.escCharReplacePattern = re.escape(self.escChar)+("([%s])" % charset) +# self.pattern += (r')*%s' % re.escape(self.endQuoteChar)) +# +# try: +# self.re = re.compile(self.pattern, self.flags) +# self.reString = self.pattern +# except sre_constants.error: +# warnings.warn("invalid pattern (%s) passed to Regex" % self.pattern, +# SyntaxWarning, stacklevel=2) +# raise +# +# self.name = _ustr(self) +# self.errmsg = "Expected " + self.name +# self.mayIndexError = False +# self.mayReturnEmpty = True +# +# def parseImpl( self, instring, loc, doActions=True ): +# result = instring[loc] == self.firstQuoteChar and self.re.match(instring,loc) or None +# if not result: +# exc = self.myException +# exc.loc = loc +# exc.pstr = instring +# raise exc +# +# loc = result.end() +# ret = result.group() +# +# if self.unquoteResults: +# +# # strip off quotes +# ret = ret[self.quoteCharLen:-self.endQuoteCharLen] +# +# if isinstance(ret,basestring): +# # replace escaped characters +# if self.escChar: +# ret = re.sub(self.escCharReplacePattern,"\g<1>",ret) +# +# # replace escaped quotes +# if self.escQuote: +# ret = ret.replace(self.escQuote, self.endQuoteChar) +# +# return loc, ret +# +# def __str__( self ): +# try: +# return super(QuotedString,self).__str__() +# except: +# pass +# +# if self.strRepr is None: +# self.strRepr = "quoted string, starting with %s ending with %s" % (self.quoteChar, self.endQuoteChar) +# +# return self.strRepr +# +# +# class CharsNotIn(Token): +# """Token for matching words composed of characters *not* in a given set. +# Defined with string containing all disallowed characters, and an optional +# minimum, maximum, and/or exact length. The default value for C{min} is 1 (a +# minimum value < 1 is not valid); the default values for C{max} and C{exact} +# are 0, meaning no maximum or exact length restriction. +# """ +# def __init__( self, notChars, min=1, max=0, exact=0 ): +# super(CharsNotIn,self).__init__() +# self.skipWhitespace = False +# self.notChars = notChars +# +# if min < 1: +# raise ValueError("cannot specify a minimum length < 1; use Optional(CharsNotIn()) if zero-length char group is permitted") +# +# self.minLen = min +# +# if max > 0: +# self.maxLen = max +# else: +# self.maxLen = _MAX_INT +# +# if exact > 0: +# self.maxLen = exact +# self.minLen = exact +# +# self.name = _ustr(self) +# self.errmsg = "Expected " + self.name +# self.mayReturnEmpty = ( self.minLen == 0 ) +# self.mayIndexError = False +# +# def parseImpl( self, instring, loc, doActions=True ): +# if instring[loc] in self.notChars: +# #~ raise ParseException( instring, loc, self.errmsg ) +# exc = self.myException +# exc.loc = loc +# exc.pstr = instring +# raise exc +# +# start = loc +# loc += 1 +# notchars = self.notChars +# maxlen = min( start+self.maxLen, len(instring) ) +# while loc < maxlen and \ +# (instring[loc] not in notchars): +# loc += 1 +# +# if loc - start < self.minLen: +# #~ raise ParseException( instring, loc, self.errmsg ) +# exc = self.myException +# exc.loc = loc +# exc.pstr = instring +# raise exc +# +# return loc, instring[start:loc] +# +# def __str__( self ): +# try: +# return super(CharsNotIn, self).__str__() +# except: +# pass +# +# if self.strRepr is None: +# if len(self.notChars) > 4: +# self.strRepr = "!W:(%s...)" % self.notChars[:4] +# else: +# self.strRepr = "!W:(%s)" % self.notChars +# +# return self.strRepr +# +# class White(Token): +# """Special matching class for matching whitespace. Normally, whitespace is ignored +# by pyparsing grammars. This class is included when some whitespace structures +# are significant. Define with a string containing the whitespace characters to be +# matched; default is C{" \\t\\r\\n"}. Also takes optional C{min}, C{max}, and C{exact} arguments, +# as defined for the C{L{Word}} class.""" +# whiteStrs = { +# " " : "", +# "\t": "", +# "\n": "", +# "\r": "", +# "\f": "", +# } +# def __init__(self, ws=" \t\r\n", min=1, max=0, exact=0): +# super(White,self).__init__() +# self.matchWhite = ws +# self.setWhitespaceChars( "".join([c for c in self.whiteChars if c not in self.matchWhite]) ) +# #~ self.leaveWhitespace() +# self.name = ("".join([White.whiteStrs[c] for c in self.matchWhite])) +# self.mayReturnEmpty = True +# self.errmsg = "Expected " + self.name +# +# self.minLen = min +# +# if max > 0: +# self.maxLen = max +# else: +# self.maxLen = _MAX_INT +# +# if exact > 0: +# self.maxLen = exact +# self.minLen = exact +# +# def parseImpl( self, instring, loc, doActions=True ): +# if not(instring[ loc ] in self.matchWhite): +# #~ raise ParseException( instring, loc, self.errmsg ) +# exc = self.myException +# exc.loc = loc +# exc.pstr = instring +# raise exc +# start = loc +# loc += 1 +# maxloc = start + self.maxLen +# maxloc = min( maxloc, len(instring) ) +# while loc < maxloc and instring[loc] in self.matchWhite: +# loc += 1 +# +# if loc - start < self.minLen: +# #~ raise ParseException( instring, loc, self.errmsg ) +# exc = self.myException +# exc.loc = loc +# exc.pstr = instring +# raise exc +# +# return loc, instring[start:loc] +# +# +# class _PositionToken(Token): +# def __init__( self ): +# super(_PositionToken,self).__init__() +# self.name=self.__class__.__name__ +# self.mayReturnEmpty = True +# self.mayIndexError = False +# +# class GoToColumn(_PositionToken): +# """Token to advance to a specific column of input text; useful for tabular report scraping.""" +# def __init__( self, colno ): +# super(GoToColumn,self).__init__() +# self.col = colno +# +# def preParse( self, instring, loc ): +# if col(loc,instring) != self.col: +# instrlen = len(instring) +# if self.ignoreExprs: +# loc = self._skipIgnorables( instring, loc ) +# while loc < instrlen and instring[loc].isspace() and col( loc, instring ) != self.col : +# loc += 1 +# return loc +# +# def parseImpl( self, instring, loc, doActions=True ): +# thiscol = col( loc, instring ) +# if thiscol > self.col: +# raise ParseException( instring, loc, "Text not in expected column", self ) +# newloc = loc + self.col - thiscol +# ret = instring[ loc: newloc ] +# return newloc, ret +# +# class LineStart(_PositionToken): +# """Matches if current position is at the beginning of a line within the parse string""" +# def __init__( self ): +# super(LineStart,self).__init__() +# self.setWhitespaceChars( ParserElement.DEFAULT_WHITE_CHARS.replace("\n","") ) +# self.errmsg = "Expected start of line" +# +# def preParse( self, instring, loc ): +# preloc = super(LineStart,self).preParse(instring,loc) +# if instring[preloc] == "\n": +# loc += 1 +# return loc +# +# def parseImpl( self, instring, loc, doActions=True ): +# if not( loc==0 or +# (loc == self.preParse( instring, 0 )) or +# (instring[loc-1] == "\n") ): #col(loc, instring) != 1: +# #~ raise ParseException( instring, loc, "Expected start of line" ) +# exc = self.myException +# exc.loc = loc +# exc.pstr = instring +# raise exc +# return loc, [] +# +# class LineEnd(_PositionToken): +# """Matches if current position is at the end of a line within the parse string""" +# def __init__( self ): +# super(LineEnd,self).__init__() +# self.setWhitespaceChars( ParserElement.DEFAULT_WHITE_CHARS.replace("\n","") ) +# self.errmsg = "Expected end of line" +# +# def parseImpl( self, instring, loc, doActions=True ): +# if loc len(instring): +# return loc, [] +# else: +# exc = self.myException +# exc.loc = loc +# exc.pstr = instring +# raise exc +# +# class WordStart(_PositionToken): +# """Matches if the current position is at the beginning of a Word, and +# is not preceded by any character in a given set of C{wordChars} +# (default=C{printables}). To emulate the C{\b} behavior of regular expressions, +# use C{WordStart(alphanums)}. C{WordStart} will also match at the beginning of +# the string being parsed, or at the beginning of a line. +# """ +# def __init__(self, wordChars = printables): +# super(WordStart,self).__init__() +# self.wordChars = set(wordChars) +# self.errmsg = "Not at the start of a word" +# +# def parseImpl(self, instring, loc, doActions=True ): +# if loc != 0: +# if (instring[loc-1] in self.wordChars or +# instring[loc] not in self.wordChars): +# exc = self.myException +# exc.loc = loc +# exc.pstr = instring +# raise exc +# return loc, [] +# +# class WordEnd(_PositionToken): +# """Matches if the current position is at the end of a Word, and +# is not followed by any character in a given set of C{wordChars} +# (default=C{printables}). To emulate the C{\b} behavior of regular expressions, +# use C{WordEnd(alphanums)}. C{WordEnd} will also match at the end of +# the string being parsed, or at the end of a line. +# """ +# def __init__(self, wordChars = printables): +# super(WordEnd,self).__init__() +# self.wordChars = set(wordChars) +# self.skipWhitespace = False +# self.errmsg = "Not at the end of a word" +# +# def parseImpl(self, instring, loc, doActions=True ): +# instrlen = len(instring) +# if instrlen>0 and loc maxExcLoc: +# maxException = err +# maxExcLoc = err.loc +# except IndexError: +# if len(instring) > maxExcLoc: +# maxException = ParseException(instring,len(instring),e.errmsg,self) +# maxExcLoc = len(instring) +# else: +# if loc2 > maxMatchLoc: +# maxMatchLoc = loc2 +# maxMatchExp = e +# +# if maxMatchLoc < 0: +# if maxException is not None: +# raise maxException +# else: +# raise ParseException(instring, loc, "no defined alternatives to match", self) +# +# return maxMatchExp._parse( instring, loc, doActions ) +# +# def __ixor__(self, other ): +# if isinstance( other, basestring ): +# other = ParserElement.literalStringClass( other ) +# return self.append( other ) #Or( [ self, other ] ) +# +# def __str__( self ): +# if hasattr(self,"name"): +# return self.name +# +# if self.strRepr is None: +# self.strRepr = "{" + " ^ ".join( [ _ustr(e) for e in self.exprs ] ) + "}" +# +# return self.strRepr +# +# def checkRecursion( self, parseElementList ): +# subRecCheckList = parseElementList[:] + [ self ] +# for e in self.exprs: +# e.checkRecursion( subRecCheckList ) +# +# +# class MatchFirst(ParseExpression): +# """Requires that at least one C{ParseExpression} is found. +# If two expressions match, the first one listed is the one that will match. +# May be constructed using the C{'|'} operator. +# """ +# def __init__( self, exprs, savelist = False ): +# super(MatchFirst,self).__init__(exprs, savelist) +# if exprs: +# self.mayReturnEmpty = False +# for e in self.exprs: +# if e.mayReturnEmpty: +# self.mayReturnEmpty = True +# break +# else: +# self.mayReturnEmpty = True +# +# def parseImpl( self, instring, loc, doActions=True ): +# maxExcLoc = -1 +# maxException = None +# for e in self.exprs: +# try: +# ret = e._parse( instring, loc, doActions ) +# return ret +# except ParseException, err: +# if err.loc > maxExcLoc: +# maxException = err +# maxExcLoc = err.loc +# except IndexError: +# if len(instring) > maxExcLoc: +# maxException = ParseException(instring,len(instring),e.errmsg,self) +# maxExcLoc = len(instring) +# +# # only got here if no expression matched, raise exception for match that made it the furthest +# else: +# if maxException is not None: +# raise maxException +# else: +# raise ParseException(instring, loc, "no defined alternatives to match", self) +# +# def __ior__(self, other ): +# if isinstance( other, basestring ): +# other = ParserElement.literalStringClass( other ) +# return self.append( other ) #MatchFirst( [ self, other ] ) +# +# def __str__( self ): +# if hasattr(self,"name"): +# return self.name +# +# if self.strRepr is None: +# self.strRepr = "{" + " | ".join( [ _ustr(e) for e in self.exprs ] ) + "}" +# +# return self.strRepr +# +# def checkRecursion( self, parseElementList ): +# subRecCheckList = parseElementList[:] + [ self ] +# for e in self.exprs: +# e.checkRecursion( subRecCheckList ) +# +# +# class Each(ParseExpression): +# """Requires all given C{ParseExpression}s to be found, but in any order. +# Expressions may be separated by whitespace. +# May be constructed using the C{'&'} operator. +# """ +# def __init__( self, exprs, savelist = True ): +# super(Each,self).__init__(exprs, savelist) +# self.mayReturnEmpty = True +# for e in self.exprs: +# if not e.mayReturnEmpty: +# self.mayReturnEmpty = False +# break +# self.skipWhitespace = True +# self.initExprGroups = True +# +# def parseImpl( self, instring, loc, doActions=True ): +# if self.initExprGroups: +# opt1 = [ e.expr for e in self.exprs if isinstance(e,Optional) ] +# opt2 = [ e for e in self.exprs if e.mayReturnEmpty and e not in opt1 ] +# self.optionals = opt1 + opt2 +# self.multioptionals = [ e.expr for e in self.exprs if isinstance(e,ZeroOrMore) ] +# self.multirequired = [ e.expr for e in self.exprs if isinstance(e,OneOrMore) ] +# self.required = [ e for e in self.exprs if not isinstance(e,(Optional,ZeroOrMore,OneOrMore)) ] +# self.required += self.multirequired +# self.initExprGroups = False +# tmpLoc = loc +# tmpReqd = self.required[:] +# tmpOpt = self.optionals[:] +# matchOrder = [] +# +# keepMatching = True +# while keepMatching: +# tmpExprs = tmpReqd + tmpOpt + self.multioptionals + self.multirequired +# failed = [] +# for e in tmpExprs: +# try: +# tmpLoc = e.tryParse( instring, tmpLoc ) +# except ParseException: +# failed.append(e) +# else: +# matchOrder.append(e) +# if e in tmpReqd: +# tmpReqd.remove(e) +# elif e in tmpOpt: +# tmpOpt.remove(e) +# if len(failed) == len(tmpExprs): +# keepMatching = False +# +# if tmpReqd: +# missing = ", ".join( [ _ustr(e) for e in tmpReqd ] ) +# raise ParseException(instring,loc,"Missing one or more required elements (%s)" % missing ) +# +# # add any unmatched Optionals, in case they have default values defined +# matchOrder += [e for e in self.exprs if isinstance(e,Optional) and e.expr in tmpOpt] +# +# resultlist = [] +# for e in matchOrder: +# loc,results = e._parse(instring,loc,doActions) +# resultlist.append(results) +# +# finalResults = ParseResults([]) +# for r in resultlist: +# dups = {} +# for k in r.keys(): +# if k in finalResults.keys(): +# tmp = ParseResults(finalResults[k]) +# tmp += ParseResults(r[k]) +# dups[k] = tmp +# finalResults += ParseResults(r) +# for k,v in dups.items(): +# finalResults[k] = v +# return loc, finalResults +# +# def __str__( self ): +# if hasattr(self,"name"): +# return self.name +# +# if self.strRepr is None: +# self.strRepr = "{" + " & ".join( [ _ustr(e) for e in self.exprs ] ) + "}" +# +# return self.strRepr +# +# def checkRecursion( self, parseElementList ): +# subRecCheckList = parseElementList[:] + [ self ] +# for e in self.exprs: +# e.checkRecursion( subRecCheckList ) +# +# +# class ParseElementEnhance(ParserElement): +# """Abstract subclass of C{ParserElement}, for combining and post-processing parsed tokens.""" +# def __init__( self, expr, savelist=False ): +# super(ParseElementEnhance,self).__init__(savelist) +# if isinstance( expr, basestring ): +# expr = Literal(expr) +# self.expr = expr +# self.strRepr = None +# if expr is not None: +# self.mayIndexError = expr.mayIndexError +# self.mayReturnEmpty = expr.mayReturnEmpty +# self.setWhitespaceChars( expr.whiteChars ) +# self.skipWhitespace = expr.skipWhitespace +# self.saveAsList = expr.saveAsList +# self.callPreparse = expr.callPreparse +# self.ignoreExprs.extend(expr.ignoreExprs) +# +# def parseImpl( self, instring, loc, doActions=True ): +# if self.expr is not None: +# return self.expr._parse( instring, loc, doActions, callPreParse=False ) +# else: +# raise ParseException("",loc,self.errmsg,self) +# +# def leaveWhitespace( self ): +# self.skipWhitespace = False +# self.expr = self.expr.copy() +# if self.expr is not None: +# self.expr.leaveWhitespace() +# return self +# +# def ignore( self, other ): +# if isinstance( other, Suppress ): +# if other not in self.ignoreExprs: +# super( ParseElementEnhance, self).ignore( other ) +# if self.expr is not None: +# self.expr.ignore( self.ignoreExprs[-1] ) +# else: +# super( ParseElementEnhance, self).ignore( other ) +# if self.expr is not None: +# self.expr.ignore( self.ignoreExprs[-1] ) +# return self +# +# def streamline( self ): +# super(ParseElementEnhance,self).streamline() +# if self.expr is not None: +# self.expr.streamline() +# return self +# +# def checkRecursion( self, parseElementList ): +# if self in parseElementList: +# raise RecursiveGrammarException( parseElementList+[self] ) +# subRecCheckList = parseElementList[:] + [ self ] +# if self.expr is not None: +# self.expr.checkRecursion( subRecCheckList ) +# +# def validate( self, validateTrace=[] ): +# tmp = validateTrace[:]+[self] +# if self.expr is not None: +# self.expr.validate(tmp) +# self.checkRecursion( [] ) +# +# def __str__( self ): +# try: +# return super(ParseElementEnhance,self).__str__() +# except: +# pass +# +# if self.strRepr is None and self.expr is not None: +# self.strRepr = "%s:(%s)" % ( self.__class__.__name__, _ustr(self.expr) ) +# return self.strRepr +# +# +# class FollowedBy(ParseElementEnhance): +# """Lookahead matching of the given parse expression. C{FollowedBy} +# does *not* advance the parsing position within the input string, it only +# verifies that the specified parse expression matches at the current +# position. C{FollowedBy} always returns a null token list.""" +# def __init__( self, expr ): +# super(FollowedBy,self).__init__(expr) +# self.mayReturnEmpty = True +# +# def parseImpl( self, instring, loc, doActions=True ): +# self.expr.tryParse( instring, loc ) +# return loc, [] +# +# +# class NotAny(ParseElementEnhance): +# """Lookahead to disallow matching with the given parse expression. C{NotAny} +# does *not* advance the parsing position within the input string, it only +# verifies that the specified parse expression does *not* match at the current +# position. Also, C{NotAny} does *not* skip over leading whitespace. C{NotAny} +# always returns a null token list. May be constructed using the '~' operator.""" +# def __init__( self, expr ): +# super(NotAny,self).__init__(expr) +# #~ self.leaveWhitespace() +# self.skipWhitespace = False # do NOT use self.leaveWhitespace(), don't want to propagate to exprs +# self.mayReturnEmpty = True +# self.errmsg = "Found unwanted token, "+_ustr(self.expr) +# +# def parseImpl( self, instring, loc, doActions=True ): +# try: +# self.expr.tryParse( instring, loc ) +# except (ParseException,IndexError): +# pass +# else: +# #~ raise ParseException(instring, loc, self.errmsg ) +# exc = self.myException +# exc.loc = loc +# exc.pstr = instring +# raise exc +# return loc, [] +# +# def __str__( self ): +# if hasattr(self,"name"): +# return self.name +# +# if self.strRepr is None: +# self.strRepr = "~{" + _ustr(self.expr) + "}" +# +# return self.strRepr +# +# +# class ZeroOrMore(ParseElementEnhance): +# """Optional repetition of zero or more of the given expression.""" +# def __init__( self, expr ): +# super(ZeroOrMore,self).__init__(expr) +# self.mayReturnEmpty = True +# +# def parseImpl( self, instring, loc, doActions=True ): +# tokens = [] +# try: +# loc, tokens = self.expr._parse( instring, loc, doActions, callPreParse=False ) +# hasIgnoreExprs = ( len(self.ignoreExprs) > 0 ) +# while 1: +# if hasIgnoreExprs: +# preloc = self._skipIgnorables( instring, loc ) +# else: +# preloc = loc +# loc, tmptokens = self.expr._parse( instring, preloc, doActions ) +# if tmptokens or tmptokens.keys(): +# tokens += tmptokens +# except (ParseException,IndexError): +# pass +# +# return loc, tokens +# +# def __str__( self ): +# if hasattr(self,"name"): +# return self.name +# +# if self.strRepr is None: +# self.strRepr = "[" + _ustr(self.expr) + "]..." +# +# return self.strRepr +# +# def setResultsName( self, name, listAllMatches=False ): +# ret = super(ZeroOrMore,self).setResultsName(name,listAllMatches) +# ret.saveAsList = True +# return ret +# +# +# class OneOrMore(ParseElementEnhance): +# """Repetition of one or more of the given expression.""" +# def parseImpl( self, instring, loc, doActions=True ): +# # must be at least one +# loc, tokens = self.expr._parse( instring, loc, doActions, callPreParse=False ) +# try: +# hasIgnoreExprs = ( len(self.ignoreExprs) > 0 ) +# while 1: +# if hasIgnoreExprs: +# preloc = self._skipIgnorables( instring, loc ) +# else: +# preloc = loc +# loc, tmptokens = self.expr._parse( instring, preloc, doActions ) +# if tmptokens or tmptokens.keys(): +# tokens += tmptokens +# except (ParseException,IndexError): +# pass +# +# return loc, tokens +# +# def __str__( self ): +# if hasattr(self,"name"): +# return self.name +# +# if self.strRepr is None: +# self.strRepr = "{" + _ustr(self.expr) + "}..." +# +# return self.strRepr +# +# def setResultsName( self, name, listAllMatches=False ): +# ret = super(OneOrMore,self).setResultsName(name,listAllMatches) +# ret.saveAsList = True +# return ret +# +# class _NullToken(object): +# def __bool__(self): +# return False +# __nonzero__ = __bool__ +# def __str__(self): +# return "" +# +# _optionalNotMatched = _NullToken() +# class Optional(ParseElementEnhance): +# """Optional matching of the given expression. +# A default return string can also be specified, if the optional expression +# is not found. +# """ +# def __init__( self, exprs, default=_optionalNotMatched ): +# super(Optional,self).__init__( exprs, savelist=False ) +# self.defaultValue = default +# self.mayReturnEmpty = True +# +# def parseImpl( self, instring, loc, doActions=True ): +# try: +# loc, tokens = self.expr._parse( instring, loc, doActions, callPreParse=False ) +# except (ParseException,IndexError): +# if self.defaultValue is not _optionalNotMatched: +# if self.expr.resultsName: +# tokens = ParseResults([ self.defaultValue ]) +# tokens[self.expr.resultsName] = self.defaultValue +# else: +# tokens = [ self.defaultValue ] +# else: +# tokens = [] +# return loc, tokens +# +# def __str__( self ): +# if hasattr(self,"name"): +# return self.name +# +# if self.strRepr is None: +# self.strRepr = "[" + _ustr(self.expr) + "]" +# +# return self.strRepr +# +# +# class SkipTo(ParseElementEnhance): +# """Token for skipping over all undefined text until the matched expression is found. +# If C{include} is set to true, the matched expression is also parsed (the skipped text +# and matched expression are returned as a 2-element list). The C{ignore} +# argument is used to define grammars (typically quoted strings and comments) that +# might contain false matches. +# """ +# def __init__( self, other, include=False, ignore=None, failOn=None ): +# super( SkipTo, self ).__init__( other ) +# self.ignoreExpr = ignore +# self.mayReturnEmpty = True +# self.mayIndexError = False +# self.includeMatch = include +# self.asList = False +# if failOn is not None and isinstance(failOn, basestring): +# self.failOn = Literal(failOn) +# else: +# self.failOn = failOn +# self.errmsg = "No match found for "+_ustr(self.expr) +# +# def parseImpl( self, instring, loc, doActions=True ): +# startLoc = loc +# instrlen = len(instring) +# expr = self.expr +# failParse = False +# while loc <= instrlen: +# try: +# if self.failOn: +# try: +# self.failOn.tryParse(instring, loc) +# except ParseBaseException: +# pass +# else: +# failParse = True +# raise ParseException(instring, loc, "Found expression " + str(self.failOn)) +# failParse = False +# if self.ignoreExpr is not None: +# while 1: +# try: +# loc = self.ignoreExpr.tryParse(instring,loc) +# # print "found ignoreExpr, advance to", loc +# except ParseBaseException: +# break +# expr._parse( instring, loc, doActions=False, callPreParse=False ) +# skipText = instring[startLoc:loc] +# if self.includeMatch: +# loc,mat = expr._parse(instring,loc,doActions,callPreParse=False) +# if mat: +# skipRes = ParseResults( skipText ) +# skipRes += mat +# return loc, [ skipRes ] +# else: +# return loc, [ skipText ] +# else: +# return loc, [ skipText ] +# except (ParseException,IndexError): +# if failParse: +# raise +# else: +# loc += 1 +# exc = self.myException +# exc.loc = loc +# exc.pstr = instring +# raise exc +# +# class Forward(ParseElementEnhance): +# """Forward declaration of an expression to be defined later - +# used for recursive grammars, such as algebraic infix notation. +# When the expression is known, it is assigned to the C{Forward} variable using the '<<' operator. +# +# Note: take care when assigning to C{Forward} not to overlook precedence of operators. +# Specifically, '|' has a lower precedence than '<<', so that:: +# fwdExpr << a | b | c +# will actually be evaluated as:: +# (fwdExpr << a) | b | c +# thereby leaving b and c out as parseable alternatives. It is recommended that you +# explicitly group the values inserted into the C{Forward}:: +# fwdExpr << (a | b | c) +# Converting to use the '<<=' operator instead will avoid this problem. +# """ +# def __init__( self, other=None ): +# super(Forward,self).__init__( other, savelist=False ) +# +# def __lshift__( self, other ): +# if isinstance( other, basestring ): +# other = ParserElement.literalStringClass(other) +# self.expr = other +# self.mayReturnEmpty = other.mayReturnEmpty +# self.strRepr = None +# self.mayIndexError = self.expr.mayIndexError +# self.mayReturnEmpty = self.expr.mayReturnEmpty +# self.setWhitespaceChars( self.expr.whiteChars ) +# self.skipWhitespace = self.expr.skipWhitespace +# self.saveAsList = self.expr.saveAsList +# self.ignoreExprs.extend(self.expr.ignoreExprs) +# return None +# __ilshift__ = __lshift__ +# +# def leaveWhitespace( self ): +# self.skipWhitespace = False +# return self +# +# def streamline( self ): +# if not self.streamlined: +# self.streamlined = True +# if self.expr is not None: +# self.expr.streamline() +# return self +# +# def validate( self, validateTrace=[] ): +# if self not in validateTrace: +# tmp = validateTrace[:]+[self] +# if self.expr is not None: +# self.expr.validate(tmp) +# self.checkRecursion([]) +# +# def __str__( self ): +# if hasattr(self,"name"): +# return self.name +# +# self._revertClass = self.__class__ +# self.__class__ = _ForwardNoRecurse +# try: +# if self.expr is not None: +# retString = _ustr(self.expr) +# else: +# retString = "None" +# finally: +# self.__class__ = self._revertClass +# return self.__class__.__name__ + ": " + retString +# +# def copy(self): +# if self.expr is not None: +# return super(Forward,self).copy() +# else: +# ret = Forward() +# ret << self +# return ret +# +# class _ForwardNoRecurse(Forward): +# def __str__( self ): +# return "..." +# +# class TokenConverter(ParseElementEnhance): +# """Abstract subclass of C{ParseExpression}, for converting parsed results.""" +# def __init__( self, expr, savelist=False ): +# super(TokenConverter,self).__init__( expr )#, savelist ) +# self.saveAsList = False +# +# class Upcase(TokenConverter): +# """Converter to upper case all matching tokens.""" +# def __init__(self, *args): +# super(Upcase,self).__init__(*args) +# warnings.warn("Upcase class is deprecated, use upcaseTokens parse action instead", +# DeprecationWarning,stacklevel=2) +# +# def postParse( self, instring, loc, tokenlist ): +# return list(map( str.upper, tokenlist )) +# +# +# class Combine(TokenConverter): +# """Converter to concatenate all matching tokens to a single string. +# By default, the matching patterns must also be contiguous in the input string; +# this can be disabled by specifying C{'adjacent=False'} in the constructor. +# """ +# def __init__( self, expr, joinString="", adjacent=True ): +# super(Combine,self).__init__( expr ) +# # suppress whitespace-stripping in contained parse expressions, but re-enable it on the Combine itself +# if adjacent: +# self.leaveWhitespace() +# self.adjacent = adjacent +# self.skipWhitespace = True +# self.joinString = joinString +# self.callPreparse = True +# +# def ignore( self, other ): +# if self.adjacent: +# ParserElement.ignore(self, other) +# else: +# super( Combine, self).ignore( other ) +# return self +# +# def postParse( self, instring, loc, tokenlist ): +# retToks = tokenlist.copy() +# del retToks[:] +# retToks += ParseResults([ "".join(tokenlist._asStringList(self.joinString)) ], modal=self.modalResults) +# +# if self.resultsName and len(retToks.keys())>0: +# return [ retToks ] +# else: +# return retToks +# +# class Group(TokenConverter): +# """Converter to return the matched tokens as a list - useful for returning tokens of C{L{ZeroOrMore}} and C{L{OneOrMore}} expressions.""" +# def __init__( self, expr ): +# super(Group,self).__init__( expr ) +# self.saveAsList = True +# +# def postParse( self, instring, loc, tokenlist ): +# return [ tokenlist ] +# +# class Dict(TokenConverter): +# """Converter to return a repetitive expression as a list, but also as a dictionary. +# Each element can also be referenced using the first token in the expression as its key. +# Useful for tabular report scraping when the first column can be used as a item key. +# """ +# def __init__( self, exprs ): +# super(Dict,self).__init__( exprs ) +# self.saveAsList = True +# +# def postParse( self, instring, loc, tokenlist ): +# for i,tok in enumerate(tokenlist): +# if len(tok) == 0: +# continue +# ikey = tok[0] +# if isinstance(ikey,int): +# ikey = _ustr(tok[0]).strip() +# if len(tok)==1: +# tokenlist[ikey] = _ParseResultsWithOffset("",i) +# elif len(tok)==2 and not isinstance(tok[1],ParseResults): +# tokenlist[ikey] = _ParseResultsWithOffset(tok[1],i) +# else: +# dictvalue = tok.copy() #ParseResults(i) +# del dictvalue[0] +# if len(dictvalue)!= 1 or (isinstance(dictvalue,ParseResults) and dictvalue.keys()): +# tokenlist[ikey] = _ParseResultsWithOffset(dictvalue,i) +# else: +# tokenlist[ikey] = _ParseResultsWithOffset(dictvalue[0],i) +# +# if self.resultsName: +# return [ tokenlist ] +# else: +# return tokenlist +# +# +# class Suppress(TokenConverter): +# """Converter for ignoring the results of a parsed expression.""" +# def postParse( self, instring, loc, tokenlist ): +# return [] +# +# def suppress( self ): +# return self +# +# +# class OnlyOnce(object): +# """Wrapper for parse actions, to ensure they are only called once.""" +# def __init__(self, methodCall): +# self.callable = _trim_arity(methodCall) +# self.called = False +# def __call__(self,s,l,t): +# if not self.called: +# results = self.callable(s,l,t) +# self.called = True +# return results +# raise ParseException(s,l,"") +# def reset(self): +# self.called = False +# +# def traceParseAction(f): +# """Decorator for debugging parse actions.""" +# f = _trim_arity(f) +# def z(*paArgs): +# thisFunc = f.func_name +# s,l,t = paArgs[-3:] +# if len(paArgs)>3: +# thisFunc = paArgs[0].__class__.__name__ + '.' + thisFunc +# sys.stderr.write( ">>entering %s(line: '%s', %d, %s)\n" % (thisFunc,line(l,s),l,t) ) +# try: +# ret = f(*paArgs) +# except Exception, exc: +# sys.stderr.write( "<", "|".join( [ _escapeRegexChars(sym) for sym in symbols] )) +# try: +# if len(symbols)==len("".join(symbols)): +# return Regex( "[%s]" % "".join( [ _escapeRegexRangeChars(sym) for sym in symbols] ) ) +# else: +# return Regex( "|".join( [ re.escape(sym) for sym in symbols] ) ) +# except: +# warnings.warn("Exception creating Regex for oneOf, building MatchFirst", +# SyntaxWarning, stacklevel=2) +# +# +# # last resort, just use MatchFirst +# return MatchFirst( [ parseElementClass(sym) for sym in symbols ] ) +# +# def dictOf( key, value ): +# """Helper to easily and clearly define a dictionary by specifying the respective patterns +# for the key and value. Takes care of defining the C{L{Dict}}, C{L{ZeroOrMore}}, and C{L{Group}} tokens +# in the proper order. The key pattern can include delimiting markers or punctuation, +# as long as they are suppressed, thereby leaving the significant key text. The value +# pattern can include named results, so that the C{Dict} results can include named token +# fields. +# """ +# return Dict( ZeroOrMore( Group ( key + value ) ) ) +# +# def originalTextFor(expr, asString=True): +# """Helper to return the original, untokenized text for a given expression. Useful to +# restore the parsed fields of an HTML start tag into the raw tag text itself, or to +# revert separate tokens with intervening whitespace back to the original matching +# input text. Simpler to use than the parse action C{L{keepOriginalText}}, and does not +# require the inspect module to chase up the call stack. By default, returns a +# string containing the original parsed text. +# +# If the optional C{asString} argument is passed as C{False}, then the return value is a +# C{L{ParseResults}} containing any results names that were originally matched, and a +# single token containing the original matched text from the input string. So if +# the expression passed to C{L{originalTextFor}} contains expressions with defined +# results names, you must set C{asString} to C{False} if you want to preserve those +# results name values.""" +# locMarker = Empty().setParseAction(lambda s,loc,t: loc) +# endlocMarker = locMarker.copy() +# endlocMarker.callPreparse = False +# matchExpr = locMarker("_original_start") + expr + endlocMarker("_original_end") +# if asString: +# extractText = lambda s,l,t: s[t._original_start:t._original_end] +# else: +# def extractText(s,l,t): +# del t[:] +# t.insert(0, s[t._original_start:t._original_end]) +# del t["_original_start"] +# del t["_original_end"] +# matchExpr.setParseAction(extractText) +# return matchExpr +# +# def ungroup(expr): +# """Helper to undo pyparsing's default grouping of And expressions, even +# if all but one are non-empty.""" +# return TokenConverter(expr).setParseAction(lambda t:t[0]) +# +# # convenience constants for positional expressions +# empty = Empty().setName("empty") +# lineStart = LineStart().setName("lineStart") +# lineEnd = LineEnd().setName("lineEnd") +# stringStart = StringStart().setName("stringStart") +# stringEnd = StringEnd().setName("stringEnd") +# +# _escapedPunc = Word( _bslash, r"\[]-*.$+^?()~ ", exact=2 ).setParseAction(lambda s,l,t:t[0][1]) +# _printables_less_backslash = "".join([ c for c in printables if c not in r"\]" ]) +# _escapedHexChar = Regex(r"\\0?[xX][0-9a-fA-F]+").setParseAction(lambda s,l,t:unichr(int(t[0].lstrip(r'\0x'),16))) +# _escapedOctChar = Regex(r"\\0[0-7]+").setParseAction(lambda s,l,t:unichr(int(t[0][1:],8))) +# _singleChar = _escapedPunc | _escapedHexChar | _escapedOctChar | Word(_printables_less_backslash,exact=1) +# _charRange = Group(_singleChar + Suppress("-") + _singleChar) +# _reBracketExpr = Literal("[") + Optional("^").setResultsName("negate") + Group( OneOrMore( _charRange | _singleChar ) ).setResultsName("body") + "]" +# +# _expanded = lambda p: (isinstance(p,ParseResults) and ''.join([ unichr(c) for c in range(ord(p[0]),ord(p[1])+1) ]) or p) +# +# def srange(s): +# r"""Helper to easily define string ranges for use in Word construction. Borrows +# syntax from regexp '[]' string range definitions:: +# srange("[0-9]") -> "0123456789" +# srange("[a-z]") -> "abcdefghijklmnopqrstuvwxyz" +# srange("[a-z$_]") -> "abcdefghijklmnopqrstuvwxyz$_" +# The input string must be enclosed in []'s, and the returned string is the expanded +# character set joined into a single string. +# The values enclosed in the []'s may be:: +# a single character +# an escaped character with a leading backslash (such as \- or \]) +# an escaped hex character with a leading '\x' (\x21, which is a '!' character) +# (\0x## is also supported for backwards compatibility) +# an escaped octal character with a leading '\0' (\041, which is a '!' character) +# a range of any of the above, separated by a dash ('a-z', etc.) +# any combination of the above ('aeiouy', 'a-zA-Z0-9_$', etc.) +# """ +# try: +# return "".join([_expanded(part) for part in _reBracketExpr.parseString(s).body]) +# except: +# return "" +# +# def matchOnlyAtCol(n): +# """Helper method for defining parse actions that require matching at a specific +# column in the input text. +# """ +# def verifyCol(strg,locn,toks): +# if col(locn,strg) != n: +# raise ParseException(strg,locn,"matched token not at column %d" % n) +# return verifyCol +# +# def replaceWith(replStr): +# """Helper method for common parse actions that simply return a literal value. Especially +# useful when used with C{L{transformString}()}. +# """ +# def _replFunc(*args): +# return [replStr] +# return _replFunc +# +# def removeQuotes(s,l,t): +# """Helper parse action for removing quotation marks from parsed quoted strings. +# To use, add this parse action to quoted string using:: +# quotedString.setParseAction( removeQuotes ) +# """ +# return t[0][1:-1] +# +# def upcaseTokens(s,l,t): +# """Helper parse action to convert tokens to upper case.""" +# return [ tt.upper() for tt in map(_ustr,t) ] +# +# def downcaseTokens(s,l,t): +# """Helper parse action to convert tokens to lower case.""" +# return [ tt.lower() for tt in map(_ustr,t) ] +# +# def keepOriginalText(s,startLoc,t): +# """DEPRECATED - use new helper method C{L{originalTextFor}}. +# Helper parse action to preserve original parsed text, +# overriding any nested parse actions.""" +# try: +# endloc = getTokensEndLoc() +# except ParseException: +# raise ParseFatalException("incorrect usage of keepOriginalText - may only be called as a parse action") +# del t[:] +# t += ParseResults(s[startLoc:endloc]) +# return t +# +# def getTokensEndLoc(): +# """Method to be called from within a parse action to determine the end +# location of the parsed tokens.""" +# import inspect +# fstack = inspect.stack() +# try: +# # search up the stack (through intervening argument normalizers) for correct calling routine +# for f in fstack[2:]: +# if f[3] == "_parseNoCache": +# endloc = f[0].f_locals["loc"] +# return endloc +# else: +# raise ParseFatalException("incorrect usage of getTokensEndLoc - may only be called from within a parse action") +# finally: +# del fstack +# +# def _makeTags(tagStr, xml): +# """Internal helper to construct opening and closing tag expressions, given a tag name""" +# if isinstance(tagStr,basestring): +# resname = tagStr +# tagStr = Keyword(tagStr, caseless=not xml) +# else: +# resname = tagStr.name +# +# tagAttrName = Word(alphas,alphanums+"_-:") +# if (xml): +# tagAttrValue = dblQuotedString.copy().setParseAction( removeQuotes ) +# openTag = Suppress("<") + tagStr("tag") + \ +# Dict(ZeroOrMore(Group( tagAttrName + Suppress("=") + tagAttrValue ))) + \ +# Optional("/",default=[False]).setResultsName("empty").setParseAction(lambda s,l,t:t[0]=='/') + Suppress(">") +# else: +# printablesLessRAbrack = "".join( [ c for c in printables if c not in ">" ] ) +# tagAttrValue = quotedString.copy().setParseAction( removeQuotes ) | Word(printablesLessRAbrack) +# openTag = Suppress("<") + tagStr("tag") + \ +# Dict(ZeroOrMore(Group( tagAttrName.setParseAction(downcaseTokens) + \ +# Optional( Suppress("=") + tagAttrValue ) ))) + \ +# Optional("/",default=[False]).setResultsName("empty").setParseAction(lambda s,l,t:t[0]=='/') + Suppress(">") +# closeTag = Combine(_L("") +# +# openTag = openTag.setResultsName("start"+"".join(resname.replace(":"," ").title().split())).setName("<%s>" % tagStr) +# closeTag = closeTag.setResultsName("end"+"".join(resname.replace(":"," ").title().split())).setName("" % tagStr) +# openTag.tag = resname +# closeTag.tag = resname +# return openTag, closeTag +# +# def makeHTMLTags(tagStr): +# """Helper to construct opening and closing tag expressions for HTML, given a tag name""" +# return _makeTags( tagStr, False ) +# +# def makeXMLTags(tagStr): +# """Helper to construct opening and closing tag expressions for XML, given a tag name""" +# return _makeTags( tagStr, True ) +# +# def withAttribute(*args,**attrDict): +# """Helper to create a validating parse action to be used with start tags created +# with C{L{makeXMLTags}} or C{L{makeHTMLTags}}. Use C{withAttribute} to qualify a starting tag +# with a required attribute value, to avoid false matches on common tags such as +# C{} or C{
}. +# +# Call C{withAttribute} with a series of attribute names and values. Specify the list +# of filter attributes names and values as: +# - keyword arguments, as in C{(align="right")}, or +# - as an explicit dict with C{**} operator, when an attribute name is also a Python +# reserved word, as in C{**{"class":"Customer", "align":"right"}} +# - a list of name-value tuples, as in ( ("ns1:class", "Customer"), ("ns2:align","right") ) +# For attribute names with a namespace prefix, you must use the second form. Attribute +# names are matched insensitive to upper/lower case. +# +# To verify that the attribute exists, but without specifying a value, pass +# C{withAttribute.ANY_VALUE} as the value. +# """ +# if args: +# attrs = args[:] +# else: +# attrs = attrDict.items() +# attrs = [(k,v) for k,v in attrs] +# def pa(s,l,tokens): +# for attrName,attrValue in attrs: +# if attrName not in tokens: +# raise ParseException(s,l,"no matching attribute " + attrName) +# if attrValue != withAttribute.ANY_VALUE and tokens[attrName] != attrValue: +# raise ParseException(s,l,"attribute '%s' has value '%s', must be '%s'" % +# (attrName, tokens[attrName], attrValue)) +# return pa +# withAttribute.ANY_VALUE = object() +# +# opAssoc = _Constants() +# opAssoc.LEFT = object() +# opAssoc.RIGHT = object() +# +# def infixNotation( baseExpr, opList, lpar=Suppress('('), rpar=Suppress(')') ): +# """Helper method for constructing grammars of expressions made up of +# operators working in a precedence hierarchy. Operators may be unary or +# binary, left- or right-associative. Parse actions can also be attached +# to operator expressions. +# +# Parameters: +# - baseExpr - expression representing the most basic element for the nested +# - opList - list of tuples, one for each operator precedence level in the +# expression grammar; each tuple is of the form +# (opExpr, numTerms, rightLeftAssoc, parseAction), where: +# - opExpr is the pyparsing expression for the operator; +# may also be a string, which will be converted to a Literal; +# if numTerms is 3, opExpr is a tuple of two expressions, for the +# two operators separating the 3 terms +# - numTerms is the number of terms for this operator (must +# be 1, 2, or 3) +# - rightLeftAssoc is the indicator whether the operator is +# right or left associative, using the pyparsing-defined +# constants C{opAssoc.RIGHT} and C{opAssoc.LEFT}. +# - parseAction is the parse action to be associated with +# expressions matching this operator expression (the +# parse action tuple member may be omitted) +# - lpar - expression for matching left-parentheses (default=Suppress('(')) +# - rpar - expression for matching right-parentheses (default=Suppress(')')) +# """ +# ret = Forward() +# lastExpr = baseExpr | ( lpar + ret + rpar ) +# for i,operDef in enumerate(opList): +# opExpr,arity,rightLeftAssoc,pa = (operDef + (None,))[:4] +# if arity == 3: +# if opExpr is None or len(opExpr) != 2: +# raise ValueError("if numterms=3, opExpr must be a tuple or list of two expressions") +# opExpr1, opExpr2 = opExpr +# thisExpr = Forward()#.setName("expr%d" % i) +# if rightLeftAssoc == opAssoc.LEFT: +# if arity == 1: +# matchExpr = FollowedBy(lastExpr + opExpr) + Group( lastExpr + OneOrMore( opExpr ) ) +# elif arity == 2: +# if opExpr is not None: +# matchExpr = FollowedBy(lastExpr + opExpr + lastExpr) + Group( lastExpr + OneOrMore( opExpr + lastExpr ) ) +# else: +# matchExpr = FollowedBy(lastExpr+lastExpr) + Group( lastExpr + OneOrMore(lastExpr) ) +# elif arity == 3: +# matchExpr = FollowedBy(lastExpr + opExpr1 + lastExpr + opExpr2 + lastExpr) + \ +# Group( lastExpr + opExpr1 + lastExpr + opExpr2 + lastExpr ) +# else: +# raise ValueError("operator must be unary (1), binary (2), or ternary (3)") +# elif rightLeftAssoc == opAssoc.RIGHT: +# if arity == 1: +# # try to avoid LR with this extra test +# if not isinstance(opExpr, Optional): +# opExpr = Optional(opExpr) +# matchExpr = FollowedBy(opExpr.expr + thisExpr) + Group( opExpr + thisExpr ) +# elif arity == 2: +# if opExpr is not None: +# matchExpr = FollowedBy(lastExpr + opExpr + thisExpr) + Group( lastExpr + OneOrMore( opExpr + thisExpr ) ) +# else: +# matchExpr = FollowedBy(lastExpr + thisExpr) + Group( lastExpr + OneOrMore( thisExpr ) ) +# elif arity == 3: +# matchExpr = FollowedBy(lastExpr + opExpr1 + thisExpr + opExpr2 + thisExpr) + \ +# Group( lastExpr + opExpr1 + thisExpr + opExpr2 + thisExpr ) +# else: +# raise ValueError("operator must be unary (1), binary (2), or ternary (3)") +# else: +# raise ValueError("operator must indicate right or left associativity") +# if pa: +# matchExpr.setParseAction( pa ) +# thisExpr << ( matchExpr | lastExpr ) +# lastExpr = thisExpr +# ret << lastExpr +# return ret +# operatorPrecedence = infixNotation +# +# dblQuotedString = Regex(r'"(?:[^"\n\r\\]|(?:"")|(?:\\x[0-9a-fA-F]+)|(?:\\.))*"').setName("string enclosed in double quotes") +# sglQuotedString = Regex(r"'(?:[^'\n\r\\]|(?:'')|(?:\\x[0-9a-fA-F]+)|(?:\\.))*'").setName("string enclosed in single quotes") +# quotedString = Regex(r'''(?:"(?:[^"\n\r\\]|(?:"")|(?:\\x[0-9a-fA-F]+)|(?:\\.))*")|(?:'(?:[^'\n\r\\]|(?:'')|(?:\\x[0-9a-fA-F]+)|(?:\\.))*')''').setName("quotedString using single or double quotes") +# unicodeString = Combine(_L('u') + quotedString.copy()) +# +# def nestedExpr(opener="(", closer=")", content=None, ignoreExpr=quotedString.copy()): +# """Helper method for defining nested lists enclosed in opening and closing +# delimiters ("(" and ")" are the default). +# +# Parameters: +# - opener - opening character for a nested list (default="("); can also be a pyparsing expression +# - closer - closing character for a nested list (default=")"); can also be a pyparsing expression +# - content - expression for items within the nested lists (default=None) +# - ignoreExpr - expression for ignoring opening and closing delimiters (default=quotedString) +# +# If an expression is not provided for the content argument, the nested +# expression will capture all whitespace-delimited content between delimiters +# as a list of separate values. +# +# Use the C{ignoreExpr} argument to define expressions that may contain +# opening or closing characters that should not be treated as opening +# or closing characters for nesting, such as quotedString or a comment +# expression. Specify multiple expressions using an C{L{Or}} or C{L{MatchFirst}}. +# The default is L{quotedString}, but if no expressions are to be ignored, +# then pass C{None} for this argument. +# """ +# if opener == closer: +# raise ValueError("opening and closing strings cannot be the same") +# if content is None: +# if isinstance(opener,basestring) and isinstance(closer,basestring): +# if len(opener) == 1 and len(closer)==1: +# if ignoreExpr is not None: +# content = (Combine(OneOrMore(~ignoreExpr + +# CharsNotIn(opener+closer+ParserElement.DEFAULT_WHITE_CHARS,exact=1)) +# ).setParseAction(lambda t:t[0].strip())) +# else: +# content = (empty.copy()+CharsNotIn(opener+closer+ParserElement.DEFAULT_WHITE_CHARS +# ).setParseAction(lambda t:t[0].strip())) +# else: +# if ignoreExpr is not None: +# content = (Combine(OneOrMore(~ignoreExpr + +# ~Literal(opener) + ~Literal(closer) + +# CharsNotIn(ParserElement.DEFAULT_WHITE_CHARS,exact=1)) +# ).setParseAction(lambda t:t[0].strip())) +# else: +# content = (Combine(OneOrMore(~Literal(opener) + ~Literal(closer) + +# CharsNotIn(ParserElement.DEFAULT_WHITE_CHARS,exact=1)) +# ).setParseAction(lambda t:t[0].strip())) +# else: +# raise ValueError("opening and closing arguments must be strings if no content expression is given") +# ret = Forward() +# if ignoreExpr is not None: +# ret << Group( Suppress(opener) + ZeroOrMore( ignoreExpr | ret | content ) + Suppress(closer) ) +# else: +# ret << Group( Suppress(opener) + ZeroOrMore( ret | content ) + Suppress(closer) ) +# return ret +# +# def indentedBlock(blockStatementExpr, indentStack, indent=True): +# """Helper method for defining space-delimited indentation blocks, such as +# those used to define block statements in Python source code. +# +# Parameters: +# - blockStatementExpr - expression defining syntax of statement that +# is repeated within the indented block +# - indentStack - list created by caller to manage indentation stack +# (multiple statementWithIndentedBlock expressions within a single grammar +# should share a common indentStack) +# - indent - boolean indicating whether block must be indented beyond the +# the current level; set to False for block of left-most statements +# (default=True) +# +# A valid block must contain at least one C{blockStatement}. +# """ +# def checkPeerIndent(s,l,t): +# if l >= len(s): return +# curCol = col(l,s) +# if curCol != indentStack[-1]: +# if curCol > indentStack[-1]: +# raise ParseFatalException(s,l,"illegal nesting") +# raise ParseException(s,l,"not a peer entry") +# +# def checkSubIndent(s,l,t): +# curCol = col(l,s) +# if curCol > indentStack[-1]: +# indentStack.append( curCol ) +# else: +# raise ParseException(s,l,"not a subentry") +# +# def checkUnindent(s,l,t): +# if l >= len(s): return +# curCol = col(l,s) +# if not(indentStack and curCol < indentStack[-1] and curCol <= indentStack[-2]): +# raise ParseException(s,l,"not an unindent") +# indentStack.pop() +# +# NL = OneOrMore(LineEnd().setWhitespaceChars("\t ").suppress()) +# INDENT = Empty() + Empty().setParseAction(checkSubIndent) +# PEER = Empty().setParseAction(checkPeerIndent) +# UNDENT = Empty().setParseAction(checkUnindent) +# if indent: +# smExpr = Group( Optional(NL) + +# #~ FollowedBy(blockStatementExpr) + +# INDENT + (OneOrMore( PEER + Group(blockStatementExpr) + Optional(NL) )) + UNDENT) +# else: +# smExpr = Group( Optional(NL) + +# (OneOrMore( PEER + Group(blockStatementExpr) + Optional(NL) )) ) +# blockStatementExpr.ignore(_bslash + LineEnd()) +# return smExpr +# +# alphas8bit = srange(r"[\0xc0-\0xd6\0xd8-\0xf6\0xf8-\0xff]") +# punc8bit = srange(r"[\0xa1-\0xbf\0xd7\0xf7]") +# +# anyOpenTag,anyCloseTag = makeHTMLTags(Word(alphas,alphanums+"_:")) +# commonHTMLEntity = Combine(_L("&") + oneOf("gt lt amp nbsp quot").setResultsName("entity") +";").streamline() +# _htmlEntityMap = dict(zip("gt lt amp nbsp quot".split(),'><& "')) +# replaceHTMLEntity = lambda t : t.entity in _htmlEntityMap and _htmlEntityMap[t.entity] or None +# +# # it's easy to get these comment structures wrong - they're very common, so may as well make them available +# cStyleComment = Regex(r"/\*(?:[^*]*\*+)+?/").setName("C style comment") +# +# htmlComment = Regex(r"") +# restOfLine = Regex(r".*").leaveWhitespace() +# dblSlashComment = Regex(r"\/\/(\\\n|.)*").setName("// comment") +# cppStyleComment = Regex(r"/(?:\*(?:[^*]*\*+)+?/|/[^\n]*(?:\n[^\n]*)*?(?:(?" + str(tokenlist)) +# print ("tokens = " + str(tokens)) +# print ("tokens.columns = " + str(tokens.columns)) +# print ("tokens.tables = " + str(tokens.tables)) +# print (tokens.asXML("SQL",True)) +# except ParseBaseException, err: +# print (teststring + "->") +# print (err.line) +# print (" "*(err.column-1) + "^") +# print (err) +# print() +# +# selectToken = CaselessLiteral( "select" ) +# fromToken = CaselessLiteral( "from" ) +# +# ident = Word( alphas, alphanums + "_$" ) +# columnName = delimitedList( ident, ".", combine=True ).setParseAction( upcaseTokens ) +# columnNameList = Group( delimitedList( columnName ) )#.setName("columns") +# tableName = delimitedList( ident, ".", combine=True ).setParseAction( upcaseTokens ) +# tableNameList = Group( delimitedList( tableName ) )#.setName("tables") +# simpleSQL = ( selectToken + \ +# ( '*' | columnNameList ).setResultsName( "columns" ) + \ +# fromToken + \ +# tableNameList.setResultsName( "tables" ) ) +# +# test( "SELECT * from XYZZY, ABC" ) +# test( "select * from SYS.XYZZY" ) +# test( "Select A from Sys.dual" ) +# test( "Select AA,BB,CC from Sys.dual" ) +# test( "Select A, B, C from Sys.dual" ) +# test( "Select A, B, C from Sys.dual" ) +# test( "Xelect A, B, C from Sys.dual" ) +# test( "Select A, B, C frox Sys.dual" ) +# test( "Select" ) +# test( "Select ^^^ frox Sys.dual" ) +# test( "Select A, B, C from Sys.dual, Table2 " ) diff --git a/src/calibre/utils/search_query_parser.py b/src/calibre/utils/search_query_parser.py index cbf1e1b245..ecf3e11ce8 100644 --- a/src/calibre/utils/search_query_parser.py +++ b/src/calibre/utils/search_query_parser.py @@ -16,11 +16,9 @@ methods :method:`SearchQueryParser.universal_set` and If this module is run, it will perform a series of unit tests. ''' -import sys, operator, weakref +import sys, operator, weakref, re -from calibre.utils.pyparsing import (CaselessKeyword, Group, Forward, - CharsNotIn, Suppress, OneOrMore, MatchFirst, CaselessLiteral, - Optional, NoMatch, ParseException, QuotedString) +from calibre.utils.pyparsing import ParseException from calibre.constants import preferred_encoding from calibre.utils.icu import sort_key from calibre import prints @@ -96,6 +94,138 @@ def saved_searches(): global ss return ss +''' +Parse a search expression into a series of potentially recursive operations. + +The syntax is a bit twisted. + +prog ::= or_expression + +or_expression ::= and_expression [ 'or' or_expression ] + +and_expression ::= not_expression [ ( [ 'and' ] and_expression ) | ( '(' or_expression ')' ) ] + +not_expression ::= [ 'not' ] base_token + +base_token ::= location_expression | ( '(' or_expression ')' ) + +location_expression ::= [ word [ ':' word ]* +''' +class Parser(object): + + def __init__(self): + self.current_token = 0 + self.tokens = None + + OPCODE = 1 + WORD = 2 + EOF = 3 + + # Had to translate named constants to numeric values + lex_scanner = re.Scanner([ + (r'[():]', lambda x,t: (1, t)), + (r'[^ "():]+', lambda x,t: (2, unicode(t))), + (r'".*?((?= len(self.tokens) + + def advance(self): + self.current_token += 1 + + def parse(self, expr, locations): + self.locations = locations + self.tokens = self.lex_scanner.scan(icu_lower(expr))[0] + self.current_token = 0 + prog = self.or_expression() + if not self.is_eof(): + raise ParseException(_('Extra characters at end of search')) + # prints(self.tokens, '\n', prog) + return prog + + def or_expression(self): + lhs = self.and_expression() + if self.is_eof(): + return lhs + if self.token() == 'or': + self.advance() + return ['or', lhs, self.or_expression()] + return lhs + + def and_expression(self): + lhs = self.not_expression() + if self.is_eof(): + return lhs + if self.token() == 'and': + self.advance() + return ['and', lhs, self.and_expression()] + + # Account for the optional 'and' + if self.token_type() == self.WORD and self.token() != 'or': + return ['and', lhs, self.and_expression()] + elif self.token() == '(': + self.advance() + rhs = self.or_expression() + if self.token() != ')': + raise ParseException('missing )') + else: + self.advance(); + return ['and', lhs, rhs] + return lhs + + def not_expression(self): + if self.token() == 'not': + self.advance() + return ['not', self.not_expression()] + return self.base_token() + + def base_token(self): + if self.token() == '(': + self.advance() + res = self.or_expression() + if self.token() != ')': + raise ParseException('missing )') + self.advance() + return res + if self.token_type() != self.WORD: + raise ParseException('Invalid syntax. Expected a lookup name or a word') + + return self.location_expression() + + def location_expression(self): + loc = self.token() + self.advance() + if self.token() == ':': + if loc in self.locations: + val = '' + else: + val = loc + ':' + loc = 'all' + + self.advance() + while True: + val += self.token() + self.advance() + if self.token() == ':': + val += ':' + self.advance() + else: + break + return ['token', loc, val] + return ['token', 'all', loc] + class SearchQueryParser(object): ''' Parses a search query. @@ -139,65 +269,9 @@ class SearchQueryParser(object): self.sqp_initialize(locations, optimize=self.optimize) def sqp_initialize(self, locations, test=False, optimize=False): + self.locations = locations self._tests_failed = False self.optimize = optimize - # Define a token - standard_locations = map(lambda x : CaselessLiteral(x)+Suppress(':'), - locations) - location = NoMatch() - for l in standard_locations: - location |= l - location = Optional(location, default='all') - word_query = CharsNotIn(u'\t\r\n\u00a0 ' + u'()') - #quoted_query = Suppress('"')+CharsNotIn('"')+Suppress('"') - quoted_query = QuotedString('"', escChar='\\') - query = quoted_query | word_query - Token = Group(location + query).setResultsName('token') - - if test: - print 'Testing Token parser:' - Token.validate() - failed = SearchQueryParser.run_tests(Token, 'token', - ( - ('tag:asd', ['tag', 'asd']), - (u'ddsä', ['all', u'ddsä']), - ('"one \\"two"', ['all', 'one "two']), - ('title:"one \\"1.5\\" two"', ['title', 'one "1.5" two']), - ('title:abc"def', ['title', 'abc"def']), - ) - ) - - Or = Forward() - - Parenthesis = Group( - Suppress('(') + Or + Suppress(')') - ).setResultsName('parenthesis') | Token - - - Not = Forward() - Not << (Group( - Suppress(CaselessKeyword("not")) + Not - ).setResultsName("not") | Parenthesis) - - And = Forward() - And << (Group( - Not + Suppress(CaselessKeyword("and")) + And - ).setResultsName("and") | Group( - Not + OneOrMore(~MatchFirst(list(map(CaselessKeyword, - ('and', 'or')))) + And) - ).setResultsName("and") | Not) - - Or << (Group( - And + Suppress(CaselessKeyword("or")) + Or - ).setResultsName("or") | And) - - if test: - #Or.validate() - self._tests_failed = bool(failed) - - self._parser = Or - self._parser.setDebug(False) - def parse(self, query): # empty the list of searches used for recursion testing @@ -213,9 +287,8 @@ class SearchQueryParser(object): def _parse(self, query, candidates=None): self.recurse_level += 1 try: - res = self._parser.parseString(query)[0] + res = Parser().parse(query, self.locations) except RuntimeError: - import repr raise ParseException('Failed to parse query, recursion limit reached: %s'%repr(query)) if candidates is None: candidates = self.universal_set() @@ -227,7 +300,7 @@ class SearchQueryParser(object): return getattr(self, 'evaluate_'+group_name) def evaluate(self, parse_result, candidates): - return self.method(parse_result.getName())(parse_result, candidates) + return self.method(parse_result[0])(parse_result[1:], candidates) def evaluate_and(self, argument, candidates): # RHS checks only those items matched by LHS @@ -249,8 +322,8 @@ class SearchQueryParser(object): # return self.universal_set().difference(self.evaluate(argument[0])) return candidates.difference(self.evaluate(argument[0], candidates)) - def evaluate_parenthesis(self, argument, candidates): - return self.evaluate(argument[0], candidates) +# def evaluate_parenthesis(self, argument, candidates): +# return self.evaluate(argument[0], candidates) def evaluate_token(self, argument, candidates): location = argument[0] From 1ca302c9b99a291367a490628b2593e9afb2ad0f Mon Sep 17 00:00:00 2001 From: davidfor Date: Wed, 17 Apr 2013 23:41:30 +1000 Subject: [PATCH 03/36] Update to support Kobo firmware 2.5.0 - Updated supported DBVersion - Added checking of firmware version - Added support for covers on the SD card --- src/calibre/devices/kobo/driver.py | 122 ++++++++++++++++++++++------- 1 file changed, 94 insertions(+), 28 deletions(-) diff --git a/src/calibre/devices/kobo/driver.py b/src/calibre/devices/kobo/driver.py index dc2ff0e400..1d4e4f73b2 100644 --- a/src/calibre/devices/kobo/driver.py +++ b/src/calibre/devices/kobo/driver.py @@ -35,11 +35,11 @@ class KOBO(USBMS): gui_name = 'Kobo Reader' description = _('Communicate with the Kobo Reader') author = 'Timothy Legge and David Forrester' - version = (2, 0, 7) + version = (2, 0, 8) dbversion = 0 fwversion = 0 - supported_dbversion = 75 + supported_dbversion = 80 has_kepubs = False supported_platforms = ['windows', 'osx', 'linux'] @@ -419,7 +419,7 @@ class KOBO(USBMS): # If all this succeeds we need to delete the images files via the ImageID return ImageID - def delete_images(self, ImageID): + def delete_images(self, ImageID, book_path): if ImageID != None: path_prefix = '.kobo/images/' path = self._main_prefix + path_prefix + ImageID @@ -449,7 +449,7 @@ class KOBO(USBMS): ImageID = self.delete_via_sql(ContentID, ContentType) #print " We would now delete the Images for" + ImageID - self.delete_images(ImageID) + self.delete_images(ImageID, path) if os.path.exists(path): # Delete the ebook @@ -1204,10 +1204,16 @@ class KOBOTOUCH(KOBO): description = 'Communicate with the Kobo Touch, Glo and Mini firmware. Based on the existing Kobo driver by %s.' % (KOBO.author) # icon = I('devices/kobotouch.jpg') - supported_dbversion = 75 - min_supported_dbversion = 53 - min_dbversion_series = 65 - min_dbversion_archive = 71 + supported_dbversion = 80 + min_supported_dbversion = 53 + min_dbversion_series = 65 + min_dbversion_archive = 71 + min_dbversion_images_on_sdcard = 77 + + max_supported_fwversion = (2,5,1) + min_fwversion_images_on_sdcard = (2,4,1) + + has_kepubs = True booklist_class = KTCollectionsBookList book_class = Book @@ -1354,14 +1360,13 @@ class KOBOTOUCH(KOBO): # Determine the firmware version try: - with open(self.normalize_path(self._main_prefix + '.kobo/version'), - 'rb') as f: + with open(self.normalize_path(self._main_prefix + '.kobo/version'), 'rb') as f: self.fwversion = f.readline().split(',')[2] + self.fwversion = tuple((int(x) for x in self.fwversion.split('.'))) except: - self.fwversion = 'unknown' + self.fwversion = (0,0,0) + - if self.fwversion != '1.0' and self.fwversion != '1.4': - self.has_kepubs = True debug_print('Version of driver:', self.version, 'Has kepubs:', self.has_kepubs) debug_print('Version of firmware:', self.fwversion, 'Has kepubs:', self.has_kepubs) @@ -1466,6 +1471,7 @@ class KOBOTOUCH(KOBO): if show_debug: self.debug_index = idx debug_print("KoboTouch:update_booklist - idx=%d"%idx) + debug_print("KoboTouch:update_booklist - lpath=%s"%lpath) debug_print('KoboTouch:update_booklist - bl[idx].device_collections=', bl[idx].device_collections) debug_print('KoboTouch:update_booklist - playlist_map=', playlist_map) debug_print('KoboTouch:update_booklist - bookshelves=', bookshelves) @@ -1477,7 +1483,7 @@ class KOBOTOUCH(KOBO): bl_cache[lpath] = None if ImageID is not None: - imagename = self.imagefilename_from_imageID(ImageID) + imagename = self.imagefilename_from_imageID(prefix, ImageID) if imagename is not None: bl[idx].thumbnail = ImageWrapper(imagename) if (ContentType == '6' and MimeType != 'application/x-kobo-epub+zip'): @@ -1717,12 +1723,14 @@ class KOBOTOUCH(KOBO): debug_print("KoboTouch:books - end - oncard='%s'"%oncard) return bl - def imagefilename_from_imageID(self, ImageID): + def imagefilename_from_imageID(self, prefix, ImageID): show_debug = self.is_debugging_title(ImageID) + path = self.images_path(prefix) + path = self.normalize_path(path.replace('/', os.sep)) + for ending, cover_options in self.cover_file_endings().items(): - fpath = self._main_prefix + '.kobo/images/' + ImageID + ending - fpath = self.normalize_path(fpath.replace('/', os.sep)) + fpath = path + ImageID + ending if os.path.exists(fpath): if show_debug: debug_print("KoboTouch:imagefilename_from_imageID - have cover image fpath=%s" % (fpath)) @@ -1764,7 +1772,7 @@ class KOBOTOUCH(KOBO): if not self.copying_covers(): imageID = self.imageid_from_contentid(contentID) - self.delete_images(imageID) + self.delete_images(imageID, fname) connection.commit() cursor.close() @@ -1821,11 +1829,11 @@ class KOBOTOUCH(KOBO): return imageId - def delete_images(self, ImageID): + def delete_images(self, ImageID, book_path): debug_print("KoboTouch:delete_images - ImageID=", ImageID) if ImageID != None: - path_prefix = '.kobo/images/' - path = self._main_prefix + path_prefix + ImageID + path = self.images_path(book_path) + path = path + ImageID for ending in self.cover_file_endings().keys(): fpath = path + ending @@ -1872,12 +1880,14 @@ class KOBOTOUCH(KOBO): def get_content_type_from_extension(self, extension): debug_print("KoboTouch:get_content_type_from_extension - start") # With new firmware, ContentType appears to be 6 for all types of sideloaded books. - if self.fwversion.startswith('2.'): + if self.fwversion >= (1,9,17) or extension == '.kobo' or extension == '.mobi': debug_print("KoboTouch:get_content_type_from_extension - V2 firmware") ContentType = 6 + # For older firmware, it depends on the type of file. + elif extension == '.kobo' or extension == '.mobi': + ContentType = 6 else: - debug_print("KoboTouch:get_content_type_from_extension - calling super") - ContentType = super(KOBOTOUCH, self).get_content_type_from_extension(extension) + ContentType = 901 return ContentType def update_device_database_collections(self, booklists, collections_attributes, oncard): @@ -2088,8 +2098,8 @@ class KOBOTOUCH(KOBO): # debug_print('KoboTouch: not uploading cover') return - # Don't upload covers if book is on the SD card - if self._card_a_prefix and path.startswith(self._card_a_prefix): + # Only upload covers to SD card if that is supported + if self._card_a_prefix and path.startswith(self._card_a_prefix) and not self.supports_covers_on_sdcard(): return if not opts.extra_customization[self.OPT_UPLOAD_GRAYSCALE_COVERS]: @@ -2111,6 +2121,16 @@ class KOBOTOUCH(KOBO): ImageID = ImageID.replace('.', '_') return ImageID + + def images_path(self, path): + if self._card_a_prefix and path.startswith(self._card_a_prefix) and self.supports_covers_on_sdcard(): + path_prefix = 'koboExtStorage/images/' + path = self._card_a_prefix + path_prefix + else: + path_prefix = '.kobo/images/' + path = self._main_prefix + path_prefix + return path + def _upload_cover(self, path, filename, metadata, filepath, uploadgrayscale, keep_cover_aspect=False): from calibre.utils.magick.draw import save_cover_data_to, identify_data debug_print("KoboTouch:_upload_cover - filename='%s' uploadgrayscale='%s' "%(filename, uploadgrayscale)) @@ -2151,8 +2171,8 @@ class KOBOTOUCH(KOBO): cursor.close() if ImageID != None: - path_prefix = '.kobo/images/' - path = self._main_prefix + path_prefix + ImageID + path = self.images_path(path) + ImageID + if show_debug: debug_print("KoboTouch:_upload_cover - About to loop over cover endings") @@ -2524,6 +2544,52 @@ class KOBOTOUCH(KOBO): def supports_kobo_archive(self): return self.dbversion >= self.min_dbversion_archive + def supports_covers_on_sdcard(self): + return self.dbversion >= 77 and self.fwversion >= self.min_fwversion_images_on_sdcard + + def modify_database_check(self, function): + # Checks to see whether the database version is supported + # and whether the user has chosen to support the firmware version +# debug_print("KoboTouch:modify_database_check - self.fwversion <= self.max_supported_fwversion=", self.fwversion > self.max_supported_fwversion) + if self.dbversion > self.supported_dbversion or self.fwversion > self.max_supported_fwversion: + # Unsupported database + opts = self.settings() + if not opts.extra_customization[self.OPT_SUPPORT_NEWER_FIRMWARE]: + debug_print('The database has been upgraded past supported version') + self.report_progress(1.0, _('Removing books from device...')) + from calibre.devices.errors import UserFeedback + raise UserFeedback(_("Kobo database version unsupported - See details"), + _('Your Kobo is running an updated firmware/database version.' + ' As calibre does not know about this updated firmware,' + ' database editing is disabled, to prevent corruption.' + ' You can still send books to your Kobo with calibre, ' + ' but deleting books and managing collections is disabled.' + ' If you are willing to experiment and know how to reset' + ' your Kobo to Factory defaults, you can override this' + ' check by right clicking the device icon in calibre and' + ' selecting "Configure this device" and then the ' + ' "Attempt to support newer firmware" option.' + ' Doing so may require you to perform a factory reset of' + ' your Kobo.' + ), + UserFeedback.WARN) + + return False + else: + # The user chose to edit the database anyway + return True + else: + # Supported database version + return True + +# @classmethod +# def get_gui_name(cls): +# if hasattr(cls, 'gui_name'): +# return cls.gui_name +# if hasattr(cls, '__name__'): +# return cls.__name__ +# return cls.name + @classmethod def is_debugging_title(cls, title): From 5fc450313ceb35aa8e7191c98c23f789d89b34b3 Mon Sep 17 00:00:00 2001 From: Charles Haley <> Date: Thu, 18 Apr 2013 11:33:44 +0200 Subject: [PATCH 04/36] Improvements to the new query parser. In particular, handle more degenerate cases where colons are significant in the query. Also make the implementation and the grammer more closely resemble each other. --- src/calibre/utils/search_query_parser.py | 122 ++++++++++++----------- 1 file changed, 64 insertions(+), 58 deletions(-) diff --git a/src/calibre/utils/search_query_parser.py b/src/calibre/utils/search_query_parser.py index ecf3e11ce8..29573cb9c9 100644 --- a/src/calibre/utils/search_query_parser.py +++ b/src/calibre/utils/search_query_parser.py @@ -97,19 +97,28 @@ def saved_searches(): ''' Parse a search expression into a series of potentially recursive operations. -The syntax is a bit twisted. +Note that the interpreter wants binary operators, not n-ary ops. This is why we +recurse instead of iterating when building sequences of the same op. + +The syntax is more than a bit twisted. In particular, the handling of colons +in the base token requires semantic analysis. + +Also note that the query string is lowercased before analysis. This is OK because +calibre's searches are all case-insensitive. + +Grammar: prog ::= or_expression or_expression ::= and_expression [ 'or' or_expression ] -and_expression ::= not_expression [ ( [ 'and' ] and_expression ) | ( '(' or_expression ')' ) ] +and_expression ::= not_expression [ [ 'and' ] and_expression ] -not_expression ::= [ 'not' ] base_token +not_expression ::= [ 'not' ] location_expression -base_token ::= location_expression | ( '(' or_expression ')' ) +location_expression ::= base_token | ( '(' or_expression ')' ) -location_expression ::= [ word [ ':' word ]* +base_token ::= a sequence of letters and colons, perhaps quoted ''' class Parser(object): @@ -119,20 +128,24 @@ class Parser(object): OPCODE = 1 WORD = 2 - EOF = 3 + QUOTED_WORD = 3 + EOF = 4 # Had to translate named constants to numeric values lex_scanner = re.Scanner([ - (r'[():]', lambda x,t: (1, t)), - (r'[^ "():]+', lambda x,t: (2, unicode(t))), - (r'".*?((? 1 and words[0] in self.locations: + loc = words[0] + words = words[1:] + if len(words) == 1 and self.token_type() == self.QUOTED_WORD: + return ['token', loc, self.token(advance=True)] + return ['token', loc, ':'.join(words)] + + return ['token', 'all', ':'.join(words)] class SearchQueryParser(object): ''' @@ -264,6 +269,7 @@ class SearchQueryParser(object): def __init__(self, locations, test=False, optimize=False): self.sqp_initialize(locations, test=test, optimize=optimize) + self.parser = Parser() def sqp_change_locations(self, locations): self.sqp_initialize(locations, optimize=self.optimize) @@ -287,7 +293,7 @@ class SearchQueryParser(object): def _parse(self, query, candidates=None): self.recurse_level += 1 try: - res = Parser().parse(query, self.locations) + res = self.parser.parse(query, self.locations) except RuntimeError: raise ParseException('Failed to parse query, recursion limit reached: %s'%repr(query)) if candidates is None: From a9e3e679e2da331e393d57caf3ab6735d11e12f4 Mon Sep 17 00:00:00 2001 From: Kovid Goyal Date: Sat, 20 Apr 2013 09:35:49 +0530 Subject: [PATCH 05/36] Fix #1169590 (Updated recipe for Financial Times, UK and US edition) --- recipes/financial_times_uk.recipe | 6 +-- recipes/financial_times_us.recipe | 63 +++++++++++++++---------------- 2 files changed, 34 insertions(+), 35 deletions(-) diff --git a/recipes/financial_times_uk.recipe b/recipes/financial_times_uk.recipe index 8105a9777f..6aa926a076 100644 --- a/recipes/financial_times_uk.recipe +++ b/recipes/financial_times_uk.recipe @@ -1,7 +1,7 @@ __license__ = 'GPL v3' -__copyright__ = '2010-2012, Darko Miletic ' +__copyright__ = '2010-2013, Darko Miletic ' ''' -www.ft.com/uk-edition +www.ft.com/intl/uk-edition ''' import datetime @@ -29,7 +29,7 @@ class FinancialTimes(BasicNewsRecipe): masthead_url = 'http://im.media.ft.com/m/img/masthead_main.jpg' LOGIN = 'https://registration.ft.com/registration/barrier/login' LOGIN2 = 'http://media.ft.com/h/subs3.html' - INDEX = 'http://www.ft.com/uk-edition' + INDEX = 'http://www.ft.com/intl/uk-edition' PREFIX = 'http://www.ft.com' conversion_options = { diff --git a/recipes/financial_times_us.recipe b/recipes/financial_times_us.recipe index 3821e5ea0e..7d8eed92f9 100644 --- a/recipes/financial_times_us.recipe +++ b/recipes/financial_times_us.recipe @@ -1,20 +1,21 @@ __license__ = 'GPL v3' -__copyright__ = '2013, Darko Miletic ' +__copyright__ = '2010-2013, Darko Miletic ' ''' -http://www.ft.com/intl/us-edition +www.ft.com/intl/international-edition ''' import datetime from calibre.ptempfile import PersistentTemporaryFile from calibre import strftime from calibre.web.feeds.news import BasicNewsRecipe +from collections import OrderedDict class FinancialTimes(BasicNewsRecipe): - title = 'Financial Times (US) printed edition' + title = 'Financial Times (International) printed edition' __author__ = 'Darko Miletic' description = "The Financial Times (FT) is one of the world's leading business news and information organisations, recognised internationally for its authority, integrity and accuracy." publisher = 'The Financial Times Ltd.' - category = 'news, finances, politics, UK, World' + category = 'news, finances, politics, World' oldest_article = 2 language = 'en' max_articles_per_feed = 250 @@ -28,7 +29,7 @@ class FinancialTimes(BasicNewsRecipe): masthead_url = 'http://im.media.ft.com/m/img/masthead_main.jpg' LOGIN = 'https://registration.ft.com/registration/barrier/login' LOGIN2 = 'http://media.ft.com/h/subs3.html' - INDEX = 'http://www.ft.com/intl/us-edition' + INDEX = 'http://www.ft.com/intl/international-edition' PREFIX = 'http://www.ft.com' conversion_options = { @@ -93,7 +94,7 @@ class FinancialTimes(BasicNewsRecipe): try: urlverified = self.browser.open_novisit(url).geturl() # resolve redirect. except: - continue + continue title = self.tag_to_string(item) date = strftime(self.timefmt) articles.append({ @@ -105,29 +106,30 @@ class FinancialTimes(BasicNewsRecipe): return articles def parse_index(self): - feeds = [] + feeds = OrderedDict() soup = self.index_to_soup(self.INDEX) - dates= self.tag_to_string(soup.find('div', attrs={'class':'btm-links'}).find('div')) - self.timefmt = ' [%s]'%dates - wide = soup.find('div',attrs={'class':'wide'}) - if not wide: - return feeds - allsections = wide.findAll(attrs={'class':lambda x: x and 'footwell' in x.split()}) - if not allsections: - return feeds - count = 0 - for item in allsections: - count = count + 1 - if self.test and count > 2: - return feeds - fitem = item.h3 - if not fitem: - fitem = item.h4 - ftitle = self.tag_to_string(fitem) - self.report_progress(0, _('Fetching feed')+' %s...'%(ftitle)) - feedarts = self.get_artlinks(item.ul) - feeds.append((ftitle,feedarts)) - return feeds + #dates= self.tag_to_string(soup.find('div', attrs={'class':'btm-links'}).find('div')) + #self.timefmt = ' [%s]'%dates + section_title = 'Untitled' + + for column in soup.findAll('div', attrs = {'class':'feedBoxes clearfix'}): + for section in column. findAll('div', attrs = {'class':'feedBox'}): + sectiontitle=self.tag_to_string(section.find('h4')) + if '...' not in sectiontitle: section_title=sectiontitle + for article in section.ul.findAll('li'): + articles = [] + title=self.tag_to_string(article.a) + url=article.a['href'] + articles.append({'title':title, 'url':url, 'description':'', 'date':''}) + + if articles: + if section_title not in feeds: + feeds[section_title] = [] + feeds[section_title] += articles + + + ans = [(key, val) for key, val in feeds.iteritems()] + return ans def preprocess_html(self, soup): items = ['promo-box','promo-title', @@ -174,9 +176,6 @@ class FinancialTimes(BasicNewsRecipe): count += 1 tfile = PersistentTemporaryFile('_fa.html') tfile.write(html) - tfile.close() + tfile.close() self.temp_files.append(tfile) return tfile.name - - def cleanup(self): - self.browser.open('https://registration.ft.com/registration/login/logout?location=') \ No newline at end of file From f6bb116c2dd710d322f3c631eb2c29f257b59a3d Mon Sep 17 00:00:00 2001 From: Kovid Goyal Date: Sat, 20 Apr 2013 09:40:15 +0530 Subject: [PATCH 06/36] ... --- recipes/lightspeed_magazine.recipe | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/recipes/lightspeed_magazine.recipe b/recipes/lightspeed_magazine.recipe index 9bb5ec913f..ab20f81387 100644 --- a/recipes/lightspeed_magazine.recipe +++ b/recipes/lightspeed_magazine.recipe @@ -4,7 +4,7 @@ class AdvancedUserRecipe1366025923(BasicNewsRecipe): title = u'Lightspeed Magazine' language = 'en' __author__ = 'Jose Pinto' - oldest_article = 7 + oldest_article = 31 max_articles_per_feed = 100 auto_cleanup = True use_embedded_content = False From 6be40de8f14ba18c929ddbb123f0f3ee8ec52236 Mon Sep 17 00:00:00 2001 From: Kovid Goyal Date: Sat, 20 Apr 2013 10:19:21 +0530 Subject: [PATCH 07/36] Driver for Droid 4. Fixes #1170763 (Droid 4 not detected) --- src/calibre/devices/android/driver.py | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) diff --git a/src/calibre/devices/android/driver.py b/src/calibre/devices/android/driver.py index 36ab076417..9d5ce152d3 100644 --- a/src/calibre/devices/android/driver.py +++ b/src/calibre/devices/android/driver.py @@ -71,6 +71,7 @@ class ANDROID(USBMS): 0x42f7 : [0x216], 0x4365 : [0x216], 0x4366 : [0x216], + 0x4371 : [0x216], }, # Freescale 0x15a2 : { @@ -239,7 +240,7 @@ class ANDROID(USBMS): 'ADVANCED', 'SGH-I727', 'USB_FLASH_DRIVER', 'ANDROID', 'S5830I_CARD', 'MID7042', 'LINK-CREATE', '7035', 'VIEWPAD_7E', 'NOVO7', 'MB526', '_USB#WYK7MSF8KE', 'TABLET_PC', 'F', 'MT65XX_MS', - 'ICS', 'E400', '__FILE-STOR_GADG', 'ST80208-1', 'GT-S5660M_CARD'] + 'ICS', 'E400', '__FILE-STOR_GADG', 'ST80208-1', 'GT-S5660M_CARD', 'XT894'] WINDOWS_CARD_A_MEM = ['ANDROID_PHONE', 'GT-I9000_CARD', 'SGH-I897', 'FILE-STOR_GADGET', 'SGH-T959_CARD', 'SGH-T959', 'SAMSUNG_ANDROID', 'GT-P1000_CARD', 'A70S', 'A101IT', '7', 'INCREDIBLE', 'A7EB', 'SGH-T849_CARD', @@ -250,7 +251,7 @@ class ANDROID(USBMS): 'FILE-CD_GADGET', 'GT-I9001_CARD', 'USB_2.0', 'XT875', 'UMS_COMPOSITE', 'PRO', '.KOBO_VOX', 'SGH-T989_CARD', 'SGH-I727', 'USB_FLASH_DRIVER', 'ANDROID', 'MID7042', '7035', 'VIEWPAD_7E', - 'NOVO7', 'ADVANCED', 'TABLET_PC', 'F', 'E400_SD_CARD', 'ST80208-1'] + 'NOVO7', 'ADVANCED', 'TABLET_PC', 'F', 'E400_SD_CARD', 'ST80208-1', 'XT894'] OSX_MAIN_MEM = 'Android Device Main Memory' From 00b8c40c635c3e9d2159e73558e4a2e1544a42c7 Mon Sep 17 00:00:00 2001 From: Kovid Goyal Date: Sat, 20 Apr 2013 10:20:23 +0530 Subject: [PATCH 08/36] Fix #1170798 (Metro NL site changed, updated recipe) --- recipes/metro_news_nl.recipe | 17 ++++++++++++----- 1 file changed, 12 insertions(+), 5 deletions(-) diff --git a/recipes/metro_news_nl.recipe b/recipes/metro_news_nl.recipe index 81a184b7dc..0995719939 100644 --- a/recipes/metro_news_nl.recipe +++ b/recipes/metro_news_nl.recipe @@ -36,6 +36,9 @@ from BeautifulSoup import BeautifulSoup Changed order of regex to speedup proces Version 1.9.3 23-05-2012 Updated Cover image + Version 1.9.4 19-04-2013 + Added regex filter for mailto + Updated for new layout of metro-site ''' class AdvancedUserRecipe1306097511(BasicNewsRecipe): @@ -43,7 +46,7 @@ class AdvancedUserRecipe1306097511(BasicNewsRecipe): oldest_article = 1.2 max_articles_per_feed = 25 __author__ = u'DrMerry' - description = u'Metro Nederland' + description = u'Metro Nederland v1.9.4 2013-04-19' language = u'nl' simultaneous_downloads = 5 masthead_url = 'http://blog.metronieuws.nl/wp-content/themes/metro/images/header.gif' @@ -68,13 +71,17 @@ class AdvancedUserRecipe1306097511(BasicNewsRecipe): #(re.compile('( Date: Sat, 20 Apr 2013 12:01:00 +0530 Subject: [PATCH 09/36] Fix #1169910 (Html links in zip output contain backslashes on Windows) --- src/calibre/ebooks/conversion/plugins/html_output.py | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) diff --git a/src/calibre/ebooks/conversion/plugins/html_output.py b/src/calibre/ebooks/conversion/plugins/html_output.py index 3821ba41a4..68d32d1aec 100644 --- a/src/calibre/ebooks/conversion/plugins/html_output.py +++ b/src/calibre/ebooks/conversion/plugins/html_output.py @@ -4,12 +4,15 @@ __copyright__ = '2010, Fabian Grassl ' __docformat__ = 'restructuredtext en' import os, re, shutil -from os.path import dirname, abspath, relpath, exists, basename +from os.path import dirname, abspath, relpath as _relpath, exists, basename from calibre.customize.conversion import OutputFormatPlugin, OptionRecommendation from calibre import CurrentDir from calibre.ptempfile import PersistentTemporaryDirectory +def relpath(*args): + return _relpath(*args).replace(os.sep, '/') + class HTMLOutput(OutputFormatPlugin): name = 'HTML Output' From 3e2b7691cd9a9444f8d38c7b2caa2504d11ff9af Mon Sep 17 00:00:00 2001 From: Charles Haley <> Date: Sat, 20 Apr 2013 08:39:27 +0200 Subject: [PATCH 10/36] Get rid of the redundant empty.png --- resources/images/empty.png | Bin 1164 -> 0 bytes src/calibre/gui2/search_restriction_mixin.py | 2 +- 2 files changed, 1 insertion(+), 1 deletion(-) delete mode 100644 resources/images/empty.png diff --git a/resources/images/empty.png b/resources/images/empty.png deleted file mode 100644 index f3f05d30921c094cd3fe03faf641aa7058877b22..0000000000000000000000000000000000000000 GIT binary patch literal 0 HcmV?d00001 literal 1164 zcmeAS@N?(olHy`uVBq!ia0vp^4Is?H3?#oinD~={ftew|C&cytC>RZa5gY>h^*j<8 z7#JB!g8YIRMsPTQyv{ZKiw&@N;4JWnEM{QfI|9OtQ?>b|fr4tDE{-7;x85FPWCZe> i6#lQz^Kbw$k->X5hXw{lxz^>vAW=_OKbLh*2~7Yf{2Dv} diff --git a/src/calibre/gui2/search_restriction_mixin.py b/src/calibre/gui2/search_restriction_mixin.py index 0137cd1027..9abf9bcfa2 100644 --- a/src/calibre/gui2/search_restriction_mixin.py +++ b/src/calibre/gui2/search_restriction_mixin.py @@ -299,7 +299,7 @@ class SearchRestrictionMixin(object): def __init__(self): self.checked = QIcon(I('ok.png')) - self.empty = QIcon(I('empty.png')) + self.empty = QIcon(I('blank.png')) self.search_based_vl_name = None self.search_based_vl = None From e7d4bec981e57183a215c8867347f1fea4ab9bd6 Mon Sep 17 00:00:00 2001 From: Charles Haley <> Date: Sat, 20 Apr 2013 10:05:55 +0200 Subject: [PATCH 11/36] Eliminate pyparsing. Simplify ParseException --- src/calibre/db/search.py | 15 +- src/calibre/gui2/library/models.py | 2 +- src/calibre/gui2/search_restriction_mixin.py | 2 +- src/calibre/library/caches.py | 25 +- src/calibre/utils/pyparsing.py | 3725 ------------------ src/calibre/utils/search_query_parser.py | 23 +- src/calibre/web/feeds/recipes/model.py | 2 +- 7 files changed, 37 insertions(+), 3757 deletions(-) delete mode 100644 src/calibre/utils/pyparsing.py diff --git a/src/calibre/db/search.py b/src/calibre/db/search.py index c7fed18f9d..4a6eace0f7 100644 --- a/src/calibre/db/search.py +++ b/src/calibre/db/search.py @@ -195,13 +195,13 @@ class DateSearch(object): # {{{ try: qd = now() - timedelta(int(num)) except: - raise ParseException(query, len(query), 'Number conversion error') + raise ParseException(_('Number conversion error: {0}').format(num)) field_count = 3 else: try: qd = parse_date(query, as_utc=False) except: - raise ParseException(query, len(query), 'Date conversion error') + raise ParseException(_('Date conversion error: {0}').format(query)) if '-' in query: field_count = query.count('-') + 1 else: @@ -285,8 +285,8 @@ class NumericSearch(object): # {{{ try: q = cast(query) * mult except: - raise ParseException(query, len(query), - 'Non-numeric value in query: %r'%query) + raise ParseException( + _('Non-numeric value in query: {0}').format(query)) for val, book_ids in field_iter(): if val is None: @@ -351,8 +351,8 @@ class KeyPairSearch(object): # {{{ if ':' in query: q = [q.strip() for q in query.split(':')] if len(q) != 2: - raise ParseException(query, len(query), - 'Invalid query format for colon-separated search') + raise ParseException( + _('Invalid query format for colon-separated search: {0}').format(query)) keyq, valq = q keyq_mkind, keyq = _matchkind(keyq) valq_mkind, valq = _matchkind(valq) @@ -465,7 +465,8 @@ class Parser(SearchQueryParser): if invert: matches = self.all_book_ids - matches return matches - raise ParseException(query, len(query), 'Recursive query group detected') + raise ParseException( + _('Recursive query group detected: {0}').format(query)) # If the user has asked to restrict searching over all field, apply # that restriction diff --git a/src/calibre/gui2/library/models.py b/src/calibre/gui2/library/models.py index a08c13c79b..536f63d169 100644 --- a/src/calibre/gui2/library/models.py +++ b/src/calibre/gui2/library/models.py @@ -12,7 +12,7 @@ from PyQt4.Qt import (QAbstractTableModel, Qt, pyqtSignal, QIcon, QImage, QModelIndex, QVariant, QDateTime, QColor, QPixmap) from calibre.gui2 import NONE, UNDEFINED_QDATETIME, error_dialog -from calibre.utils.pyparsing import ParseException +from calibre.utils.search_query_parser import ParseException from calibre.ebooks.metadata import fmt_sidx, authors_to_string, string_to_authors from calibre.ebooks.metadata.book.base import SafeFormat from calibre.ptempfile import PersistentTemporaryFile diff --git a/src/calibre/gui2/search_restriction_mixin.py b/src/calibre/gui2/search_restriction_mixin.py index 9abf9bcfa2..967cf9c04c 100644 --- a/src/calibre/gui2/search_restriction_mixin.py +++ b/src/calibre/gui2/search_restriction_mixin.py @@ -13,7 +13,7 @@ from PyQt4.Qt import ( from calibre.gui2 import error_dialog, question_dialog from calibre.gui2.widgets import ComboBoxWithHelp from calibre.utils.icu import sort_key -from calibre.utils.pyparsing import ParseException +from calibre.utils.search_query_parser import ParseException from calibre.utils.search_query_parser import saved_searches class SelectNames(QDialog): # {{{ diff --git a/src/calibre/library/caches.py b/src/calibre/library/caches.py index 048288ef71..2b46ab922b 100644 --- a/src/calibre/library/caches.py +++ b/src/calibre/library/caches.py @@ -14,7 +14,7 @@ from threading import Thread from calibre.utils.config import tweaks, prefs from calibre.utils.date import parse_date, now, UNDEFINED_DATE, clean_date_for_sort from calibre.utils.search_query_parser import SearchQueryParser -from calibre.utils.pyparsing import ParseException +from calibre.utils.search_query_parser import ParseException from calibre.utils.localization import (canonicalize_lang, lang_map, get_udc) from calibre.db.search import CONTAINS_MATCH, EQUALS_MATCH, REGEXP_MATCH, _match from calibre.ebooks.metadata import title_sort, author_to_author_sort @@ -366,25 +366,18 @@ class ResultCache(SearchQueryParser): # {{{ elif query in self.local_thismonth: qd = now() field_count = 2 - elif query.endswith(self.local_daysago): + elif query.endswith(self.local_daysago) or query.endswith(self.untrans_daysago): num = query[0:-self.local_daysago_len] try: qd = now() - timedelta(int(num)) except: - raise ParseException(query, len(query), 'Number conversion error', self) - field_count = 3 - elif query.endswith(self.untrans_daysago): - num = query[0:-self.untrans_daysago_len] - try: - qd = now() - timedelta(int(num)) - except: - raise ParseException(query, len(query), 'Number conversion error', self) + raise ParseException(_('Number conversion error: {0}').format(num)) field_count = 3 else: try: qd = parse_date(query, as_utc=False) except: - raise ParseException(query, len(query), 'Date conversion error', self) + raise ParseException(_('Date conversion error: {0}').format(query)) if '-' in query: field_count = query.count('-') + 1 else: @@ -460,8 +453,7 @@ class ResultCache(SearchQueryParser): # {{{ try: q = cast(query) * mult except: - raise ParseException(query, len(query), - 'Non-numeric value in query', self) + raise ParseException(_('Non-numeric value in query: {0}').format(query)) for id_ in candidates: item = self._data[id_] @@ -501,12 +493,13 @@ class ResultCache(SearchQueryParser): # {{{ return matches def get_keypair_matches(self, location, query, candidates): + print query matches = set([]) if query.find(':') >= 0: q = [q.strip() for q in query.split(':')] if len(q) != 2: - raise ParseException(query, len(query), - 'Invalid query format for colon-separated search', self) + raise ParseException( + _('Invalid query format for colon-separated search: {0}').format(query)) (keyq, valq) = q keyq_mkind, keyq = self._matchkind(keyq) valq_mkind, valq = self._matchkind(valq) @@ -655,7 +648,7 @@ class ResultCache(SearchQueryParser): # {{{ if invert: matches = self.universal_set() - matches return matches - raise ParseException(query, len(query), 'Recursive query group detected', self) + raise ParseException(_('Recursive query group detected: {0}').format(query)) # apply the limit if appropriate if location == 'all' and prefs['limit_search_columns'] and \ diff --git a/src/calibre/utils/pyparsing.py b/src/calibre/utils/pyparsing.py deleted file mode 100644 index 5d3b050879..0000000000 --- a/src/calibre/utils/pyparsing.py +++ /dev/null @@ -1,3725 +0,0 @@ -# module pyparsing.py -# -# Copyright (c) 2003-2011 Paul T. McGuire -# -# Permission is hereby granted, free of charge, to any person obtaining -# a copy of this software and associated documentation files (the -# "Software"), to deal in the Software without restriction, including -# without limitation the rights to use, copy, modify, merge, publish, -# distribute, sublicense, and/or sell copies of the Software, and to -# permit persons to whom the Software is furnished to do so, subject to -# the following conditions: -# -# The above copyright notice and this permission notice shall be -# included in all copies or substantial portions of the Software. -# -# THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, -# EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF -# MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. -# IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY -# CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, -# TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH THE -# SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE. -# -#from __future__ import generators - -# __doc__ = \ -# """ -# pyparsing module - Classes and methods to define and execute parsing grammars -# -# The pyparsing module is an alternative approach to creating and executing simple grammars, -# vs. the traditional lex/yacc approach, or the use of regular expressions. With pyparsing, you -# don't need to learn a new syntax for defining grammars or matching expressions - the parsing module -# provides a library of classes that you use to construct the grammar directly in Python. -# -# Here is a program to parse "Hello, World!" (or any greeting of the form C{", !"}):: -# -# from pyparsing import Word, alphas -# -# # define grammar of a greeting -# greet = Word( alphas ) + "," + Word( alphas ) + "!" -# -# hello = "Hello, World!" -# print hello, "->", greet.parseString( hello ) -# -# The program outputs the following:: -# -# Hello, World! -> ['Hello', ',', 'World', '!'] -# -# The Python representation of the grammar is quite readable, owing to the self-explanatory -# class names, and the use of '+', '|' and '^' operators. -# -# The parsed results returned from C{parseString()} can be accessed as a nested list, a dictionary, or an -# object with named attributes. -# -# The pyparsing module handles some of the problems that are typically vexing when writing text parsers: -# - extra or missing whitespace (the above program will also handle "Hello,World!", "Hello , World !", etc.) -# - quoted strings -# - embedded comments -# """ -# -# __version__ = "1.5.7" -# __versionTime__ = "17 November 2012 16:18" -# __author__ = "Paul McGuire " -# -# import string -# from weakref import ref as wkref -# import copy -# import sys -# import warnings -# import re -# import sre_constants -# #~ sys.stderr.write( "testing pyparsing module, version %s, %s\n" % (__version__,__versionTime__ ) ) -# -# __all__ = [ -# 'And', 'CaselessKeyword', 'CaselessLiteral', 'CharsNotIn', 'Combine', 'Dict', 'Each', 'Empty', -# 'FollowedBy', 'Forward', 'GoToColumn', 'Group', 'Keyword', 'LineEnd', 'LineStart', 'Literal', -# 'MatchFirst', 'NoMatch', 'NotAny', 'OneOrMore', 'OnlyOnce', 'Optional', 'Or', -# 'ParseBaseException', 'ParseElementEnhance', 'ParseException', 'ParseExpression', 'ParseFatalException', -# 'ParseResults', 'ParseSyntaxException', 'ParserElement', 'QuotedString', 'RecursiveGrammarException', -# 'Regex', 'SkipTo', 'StringEnd', 'StringStart', 'Suppress', 'Token', 'TokenConverter', 'Upcase', -# 'White', 'Word', 'WordEnd', 'WordStart', 'ZeroOrMore', -# 'alphanums', 'alphas', 'alphas8bit', 'anyCloseTag', 'anyOpenTag', 'cStyleComment', 'col', -# 'commaSeparatedList', 'commonHTMLEntity', 'countedArray', 'cppStyleComment', 'dblQuotedString', -# 'dblSlashComment', 'delimitedList', 'dictOf', 'downcaseTokens', 'empty', 'hexnums', -# 'htmlComment', 'javaStyleComment', 'keepOriginalText', 'line', 'lineEnd', 'lineStart', 'lineno', -# 'makeHTMLTags', 'makeXMLTags', 'matchOnlyAtCol', 'matchPreviousExpr', 'matchPreviousLiteral', -# 'nestedExpr', 'nullDebugAction', 'nums', 'oneOf', 'opAssoc', 'operatorPrecedence', 'printables', -# 'punc8bit', 'pythonStyleComment', 'quotedString', 'removeQuotes', 'replaceHTMLEntity', -# 'replaceWith', 'restOfLine', 'sglQuotedString', 'srange', 'stringEnd', -# 'stringStart', 'traceParseAction', 'unicodeString', 'upcaseTokens', 'withAttribute', -# 'indentedBlock', 'originalTextFor', 'ungroup', 'infixNotation', -# ] -# -# _MAX_INT = sys.maxint -# range = xrange -# set = lambda s : dict( [(c,0) for c in s] ) -# -def _ustr(obj): - """Drop-in replacement for str(obj) that tries to be Unicode friendly. It first tries - str(obj). If that fails with a UnicodeEncodeError, then it tries unicode(obj). It - then < returns the unicode object | encodes it with the default encoding | ... >. - """ - if isinstance(obj,unicode): - return obj - - try: - # If this works, then _ustr(obj) has the same behaviour as str(obj), so - # it won't break any existing code. - return str(obj) - - except UnicodeEncodeError: - # The Python docs (http://docs.python.org/ref/customization.html#l2h-182) - # state that "The return value must be a string object". However, does a - # unicode object (being a subclass of basestring) count as a "string - # object"? - # If so, then return a unicode object: - return unicode(obj) - # Else encode it... but how? There are many choices... :) - # Replace unprintables with escape codes? - #return unicode(obj).encode(sys.getdefaultencoding(), 'backslashreplace_errors') - # Replace unprintables with question marks? - #return unicode(obj).encode(sys.getdefaultencoding(), 'replace') - # ... - -# # build list of single arg builtins, tolerant of Python version, that can be used as parse actions -# singleArgBuiltins = [] -# import __builtin__ -# for fname in "sum len sorted reversed list tuple set any all min max".split(): -# try: -# singleArgBuiltins.append(getattr(__builtin__,fname)) -# except AttributeError: -# continue -# -# def _xml_escape(data): -# """Escape &, <, >, ", ', etc. in a string of data.""" -# -# # ampersand must be replaced first -# from_symbols = '&><"\'' -# to_symbols = ['&'+s+';' for s in "amp gt lt quot apos".split()] -# for from_,to_ in zip(from_symbols, to_symbols): -# data = data.replace(from_, to_) -# return data -# -# class _Constants(object): -# pass -# -# alphas = string.ascii_lowercase + string.ascii_uppercase -# nums = "0123456789" -# hexnums = nums + "ABCDEFabcdef" -# alphanums = alphas + nums -# _bslash = chr(92) -# printables = "".join( [ c for c in string.printable if c not in string.whitespace ] ) -# -class ParseBaseException(Exception): - """base exception class for all parsing runtime exceptions""" - # Performance tuning: we construct a *lot* of these, so keep this - # constructor as small and fast as possible - def __init__( self, pstr, loc=0, msg=None, elem=None ): - self.loc = loc - if msg is None: - self.msg = pstr - self.pstr = "" - else: - self.msg = msg - self.pstr = pstr - self.parserElement = elem - - def __getattr__( self, aname ): - """supported attributes by name are: - - lineno - returns the line number of the exception text - - col - returns the column number of the exception text - - line - returns the line containing the exception text - """ - if( aname == "lineno" ): - return 1 #lineno( self.loc, self.pstr ) - elif( aname in ("col", "column") ): - return 1 #col( self.loc, self.pstr ) - elif( aname == "line" ): - return 1 #line( self.loc, self.pstr ) - else: - raise AttributeError(aname) - - def __str__( self ): - return "%s (at char %d), (line:%d, col:%d)" % \ - ( self.msg, self.loc, self.lineno, self.column ) - def __repr__( self ): - return _ustr(self) - def markInputline( self, markerString = ">!<" ): - """Extracts the exception line from the input string, and marks - the location of the exception with a special symbol. - """ - line_str = self.line - line_column = self.column - 1 - if markerString: - line_str = "".join( [line_str[:line_column], - markerString, line_str[line_column:]]) - return line_str.strip() - def __dir__(self): - return "loc msg pstr parserElement lineno col line " \ - "markInputline __str__ __repr__".split() - -class ParseException(ParseBaseException): - """exception thrown when parse expressions don't match class; - supported attributes by name are: - - lineno - returns the line number of the exception text - - col - returns the column number of the exception text - - line - returns the line containing the exception text - """ - pass - -# class ParseFatalException(ParseBaseException): -# """user-throwable exception thrown when inconsistent parse content -# is found; stops all parsing immediately""" -# pass -# -# class ParseSyntaxException(ParseFatalException): -# """just like C{L{ParseFatalException}}, but thrown internally when an -# C{L{ErrorStop}} ('-' operator) indicates that parsing is to stop immediately because -# an unbacktrackable syntax error has been found""" -# def __init__(self, pe): -# super(ParseSyntaxException, self).__init__( -# pe.pstr, pe.loc, pe.msg, pe.parserElement) -# -# #~ class ReparseException(ParseBaseException): -# #~ """Experimental class - parse actions can raise this exception to cause -# #~ pyparsing to reparse the input string: -# #~ - with a modified input string, and/or -# #~ - with a modified start location -# #~ Set the values of the ReparseException in the constructor, and raise the -# #~ exception in a parse action to cause pyparsing to use the new string/location. -# #~ Setting the values as None causes no change to be made. -# #~ """ -# #~ def __init_( self, newstring, restartLoc ): -# #~ self.newParseText = newstring -# #~ self.reparseLoc = restartLoc -# -# class RecursiveGrammarException(Exception): -# """exception thrown by C{validate()} if the grammar could be improperly recursive""" -# def __init__( self, parseElementList ): -# self.parseElementTrace = parseElementList -# -# def __str__( self ): -# return "RecursiveGrammarException: %s" % self.parseElementTrace -# -# class _ParseResultsWithOffset(object): -# def __init__(self,p1,p2): -# self.tup = (p1,p2) -# def __getitem__(self,i): -# return self.tup[i] -# def __repr__(self): -# return repr(self.tup) -# def setOffset(self,i): -# self.tup = (self.tup[0],i) -# -# class ParseResults(object): -# """Structured parse results, to provide multiple means of access to the parsed data: -# - as a list (C{len(results)}) -# - by list index (C{results[0], results[1]}, etc.) -# - by attribute (C{results.}) -# """ -# #~ __slots__ = ( "__toklist", "__tokdict", "__doinit", "__name", "__parent", "__accumNames", "__weakref__" ) -# def __new__(cls, toklist, name=None, asList=True, modal=True ): -# if isinstance(toklist, cls): -# return toklist -# retobj = object.__new__(cls) -# retobj.__doinit = True -# return retobj -# -# # Performance tuning: we construct a *lot* of these, so keep this -# # constructor as small and fast as possible -# def __init__( self, toklist, name=None, asList=True, modal=True, isinstance=isinstance ): -# if self.__doinit: -# self.__doinit = False -# self.__name = None -# self.__parent = None -# self.__accumNames = {} -# if isinstance(toklist, list): -# self.__toklist = toklist[:] -# else: -# self.__toklist = [toklist] -# self.__tokdict = dict() -# -# if name is not None and name: -# if not modal: -# self.__accumNames[name] = 0 -# if isinstance(name,int): -# name = _ustr(name) # will always return a str, but use _ustr for consistency -# self.__name = name -# if not toklist in (None,'',[]): -# if isinstance(toklist,basestring): -# toklist = [ toklist ] -# if asList: -# if isinstance(toklist,ParseResults): -# self[name] = _ParseResultsWithOffset(toklist.copy(),0) -# else: -# self[name] = _ParseResultsWithOffset(ParseResults(toklist[0]),0) -# self[name].__name = name -# else: -# try: -# self[name] = toklist[0] -# except (KeyError,TypeError,IndexError): -# self[name] = toklist -# -# def __getitem__( self, i ): -# if isinstance( i, (int,slice) ): -# return self.__toklist[i] -# else: -# if i not in self.__accumNames: -# return self.__tokdict[i][-1][0] -# else: -# return ParseResults([ v[0] for v in self.__tokdict[i] ]) -# -# def __setitem__( self, k, v, isinstance=isinstance ): -# if isinstance(v,_ParseResultsWithOffset): -# self.__tokdict[k] = self.__tokdict.get(k,list()) + [v] -# sub = v[0] -# elif isinstance(k,int): -# self.__toklist[k] = v -# sub = v -# else: -# self.__tokdict[k] = self.__tokdict.get(k,list()) + [_ParseResultsWithOffset(v,0)] -# sub = v -# if isinstance(sub,ParseResults): -# sub.__parent = wkref(self) -# -# def __delitem__( self, i ): -# if isinstance(i,(int,slice)): -# mylen = len( self.__toklist ) -# del self.__toklist[i] -# -# # convert int to slice -# if isinstance(i, int): -# if i < 0: -# i += mylen -# i = slice(i, i+1) -# # get removed indices -# removed = list(range(*i.indices(mylen))) -# removed.reverse() -# # fixup indices in token dictionary -# for name in self.__tokdict: -# occurrences = self.__tokdict[name] -# for j in removed: -# for k, (value, position) in enumerate(occurrences): -# occurrences[k] = _ParseResultsWithOffset(value, position - (position > j)) -# else: -# del self.__tokdict[i] -# -# def __contains__( self, k ): -# return k in self.__tokdict -# -# def __len__( self ): return len( self.__toklist ) -# def __bool__(self): return len( self.__toklist ) > 0 -# __nonzero__ = __bool__ -# def __iter__( self ): return iter( self.__toklist ) -# def __reversed__( self ): return iter( self.__toklist[::-1] ) -# def keys( self ): -# """Returns all named result keys.""" -# return self.__tokdict.keys() -# -# def pop( self, index=-1 ): -# """Removes and returns item at specified index (default=last). -# Will work with either numeric indices or dict-key indicies.""" -# ret = self[index] -# del self[index] -# return ret -# -# def get(self, key, defaultValue=None): -# """Returns named result matching the given key, or if there is no -# such name, then returns the given C{defaultValue} or C{None} if no -# C{defaultValue} is specified.""" -# if key in self: -# return self[key] -# else: -# return defaultValue -# -# def insert( self, index, insStr ): -# """Inserts new element at location index in the list of parsed tokens.""" -# self.__toklist.insert(index, insStr) -# # fixup indices in token dictionary -# for name in self.__tokdict: -# occurrences = self.__tokdict[name] -# for k, (value, position) in enumerate(occurrences): -# occurrences[k] = _ParseResultsWithOffset(value, position + (position > index)) -# -# def items( self ): -# """Returns all named result keys and values as a list of tuples.""" -# return [(k,self[k]) for k in self.__tokdict] -# -# def values( self ): -# """Returns all named result values.""" -# return [ v[-1][0] for v in self.__tokdict.values() ] -# -# def __getattr__( self, name ): -# if True: #name not in self.__slots__: -# if name in self.__tokdict: -# if name not in self.__accumNames: -# return self.__tokdict[name][-1][0] -# else: -# return ParseResults([ v[0] for v in self.__tokdict[name] ]) -# else: -# return "" -# return None -# -# def __add__( self, other ): -# ret = self.copy() -# ret += other -# return ret -# -# def __iadd__( self, other ): -# if other.__tokdict: -# offset = len(self.__toklist) -# addoffset = ( lambda a: (a<0 and offset) or (a+offset) ) -# otheritems = other.__tokdict.items() -# otherdictitems = [(k, _ParseResultsWithOffset(v[0],addoffset(v[1])) ) -# for (k,vlist) in otheritems for v in vlist] -# for k,v in otherdictitems: -# self[k] = v -# if isinstance(v[0],ParseResults): -# v[0].__parent = wkref(self) -# -# self.__toklist += other.__toklist -# self.__accumNames.update( other.__accumNames ) -# return self -# -# def __radd__(self, other): -# if isinstance(other,int) and other == 0: -# return self.copy() -# -# def __repr__( self ): -# return "(%s, %s)" % ( repr( self.__toklist ), repr( self.__tokdict ) ) -# -# def __str__( self ): -# out = [] -# for i in self.__toklist: -# if isinstance(i, ParseResults): -# out.append(_ustr(i)) -# else: -# out.append(repr(i)) -# return '[' + ', '.join(out) + ']' -# -# def _asStringList( self, sep='' ): -# out = [] -# for item in self.__toklist: -# if out and sep: -# out.append(sep) -# if isinstance( item, ParseResults ): -# out += item._asStringList() -# else: -# out.append( _ustr(item) ) -# return out -# -# def asList( self ): -# """Returns the parse results as a nested list of matching tokens, all converted to strings.""" -# out = [] -# for res in self.__toklist: -# if isinstance(res,ParseResults): -# out.append( res.asList() ) -# else: -# out.append( res ) -# return out -# -# def asDict( self ): -# """Returns the named parse results as dictionary.""" -# return dict( self.items() ) -# -# def copy( self ): -# """Returns a new copy of a C{ParseResults} object.""" -# ret = ParseResults( self.__toklist ) -# ret.__tokdict = self.__tokdict.copy() -# ret.__parent = self.__parent -# ret.__accumNames.update( self.__accumNames ) -# ret.__name = self.__name -# return ret -# -# def asXML( self, doctag=None, namedItemsOnly=False, indent="", formatted=True ): -# """Returns the parse results as XML. Tags are created for tokens and lists that have defined results names.""" -# nl = "\n" -# out = [] -# namedItems = dict( [ (v[1],k) for (k,vlist) in self.__tokdict.items() -# for v in vlist ] ) -# nextLevelIndent = indent + " " -# -# # collapse out indents if formatting is not desired -# if not formatted: -# indent = "" -# nextLevelIndent = "" -# nl = "" -# -# selfTag = None -# if doctag is not None: -# selfTag = doctag -# else: -# if self.__name: -# selfTag = self.__name -# -# if not selfTag: -# if namedItemsOnly: -# return "" -# else: -# selfTag = "ITEM" -# -# out += [ nl, indent, "<", selfTag, ">" ] -# -# worklist = self.__toklist -# for i,res in enumerate(worklist): -# if isinstance(res,ParseResults): -# if i in namedItems: -# out += [ res.asXML(namedItems[i], -# namedItemsOnly and doctag is None, -# nextLevelIndent, -# formatted)] -# else: -# out += [ res.asXML(None, -# namedItemsOnly and doctag is None, -# nextLevelIndent, -# formatted)] -# else: -# # individual token, see if there is a name for it -# resTag = None -# if i in namedItems: -# resTag = namedItems[i] -# if not resTag: -# if namedItemsOnly: -# continue -# else: -# resTag = "ITEM" -# xmlBodyText = _xml_escape(_ustr(res)) -# out += [ nl, nextLevelIndent, "<", resTag, ">", -# xmlBodyText, -# "" ] -# -# out += [ nl, indent, "" ] -# return "".join(out) -# -# def __lookup(self,sub): -# for k,vlist in self.__tokdict.items(): -# for v,loc in vlist: -# if sub is v: -# return k -# return None -# -# def getName(self): -# """Returns the results name for this token expression.""" -# if self.__name: -# return self.__name -# elif self.__parent: -# par = self.__parent() -# if par: -# return par.__lookup(self) -# else: -# return None -# elif (len(self) == 1 and -# len(self.__tokdict) == 1 and -# self.__tokdict.values()[0][0][1] in (0,-1)): -# return self.__tokdict.keys()[0] -# else: -# return None -# -# def dump(self,indent='',depth=0): -# """Diagnostic method for listing out the contents of a C{ParseResults}. -# Accepts an optional C{indent} argument so that this string can be embedded -# in a nested display of other data.""" -# out = [] -# out.append( indent+_ustr(self.asList()) ) -# keys = self.items() -# keys.sort() -# for k,v in keys: -# if out: -# out.append('\n') -# out.append( "%s%s- %s: " % (indent,(' '*depth), k) ) -# if isinstance(v,ParseResults): -# if v.keys(): -# out.append( v.dump(indent,depth+1) ) -# else: -# out.append(_ustr(v)) -# else: -# out.append(_ustr(v)) -# return "".join(out) -# -# # add support for pickle protocol -# def __getstate__(self): -# return ( self.__toklist, -# ( self.__tokdict.copy(), -# self.__parent is not None and self.__parent() or None, -# self.__accumNames, -# self.__name ) ) -# -# def __setstate__(self,state): -# self.__toklist = state[0] -# (self.__tokdict, -# par, -# inAccumNames, -# self.__name) = state[1] -# self.__accumNames = {} -# self.__accumNames.update(inAccumNames) -# if par is not None: -# self.__parent = wkref(par) -# else: -# self.__parent = None -# -# def __dir__(self): -# return dir(super(ParseResults,self)) + list(self.keys()) -# -# def col (loc,strg): -# """Returns current column within a string, counting newlines as line separators. -# The first column is number 1. -# -# Note: the default parsing behavior is to expand tabs in the input string -# before starting the parsing process. See L{I{ParserElement.parseString}} for more information -# on parsing strings containing C{}s, and suggested methods to maintain a -# consistent view of the parsed string, the parse location, and line and column -# positions within the parsed string. -# """ -# return (loc} for more information -# on parsing strings containing C{}s, and suggested methods to maintain a -# consistent view of the parsed string, the parse location, and line and column -# positions within the parsed string. -# """ -# return strg.count("\n",0,loc) + 1 -# -# def line( loc, strg ): -# """Returns the line of text containing loc within a string, counting newlines as line separators. -# """ -# lastCR = strg.rfind("\n", 0, loc) -# nextCR = strg.find("\n", loc) -# if nextCR >= 0: -# return strg[lastCR+1:nextCR] -# else: -# return strg[lastCR+1:] -# -# def _defaultStartDebugAction( instring, loc, expr ): -# print ("Match " + _ustr(expr) + " at loc " + _ustr(loc) + "(%d,%d)" % ( lineno(loc,instring), col(loc,instring) )) -# -# def _defaultSuccessDebugAction( instring, startloc, endloc, expr, toks ): -# print ("Matched " + _ustr(expr) + " -> " + str(toks.asList())) -# -# def _defaultExceptionDebugAction( instring, loc, expr, exc ): -# print ("Exception raised:" + _ustr(exc)) -# -# def nullDebugAction(*args): -# """'Do-nothing' debug action, to suppress debugging output during parsing.""" -# pass -# -# 'decorator to trim function calls to match the arity of the target' -# def _trim_arity(func, maxargs=2): -# if func in singleArgBuiltins: -# return lambda s,l,t: func(t) -# limit = [0] -# foundArity = [False] -# def wrapper(*args): -# while 1: -# try: -# ret = func(*args[limit[0]:]) -# foundArity[0] = True -# return ret -# except TypeError: -# if limit[0] <= maxargs and not foundArity[0]: -# limit[0] += 1 -# continue -# raise -# return wrapper -# -# class ParserElement(object): -# """Abstract base level parser element class.""" -# DEFAULT_WHITE_CHARS = " \n\t\r" -# verbose_stacktrace = False -# -# def setDefaultWhitespaceChars( chars ): -# """Overrides the default whitespace chars -# """ -# ParserElement.DEFAULT_WHITE_CHARS = chars -# setDefaultWhitespaceChars = staticmethod(setDefaultWhitespaceChars) -# -# def inlineLiteralsUsing(cls): -# """ -# Set class to be used for inclusion of string literals into a parser. -# """ -# ParserElement.literalStringClass = cls -# inlineLiteralsUsing = staticmethod(inlineLiteralsUsing) -# -# def __init__( self, savelist=False ): -# self.parseAction = list() -# self.failAction = None -# #~ self.name = "" # don't define self.name, let subclasses try/except upcall -# self.strRepr = None -# self.resultsName = None -# self.saveAsList = savelist -# self.skipWhitespace = True -# self.whiteChars = ParserElement.DEFAULT_WHITE_CHARS -# self.copyDefaultWhiteChars = True -# self.mayReturnEmpty = False # used when checking for left-recursion -# self.keepTabs = False -# self.ignoreExprs = list() -# self.debug = False -# self.streamlined = False -# self.mayIndexError = True # used to optimize exception handling for subclasses that don't advance parse index -# self.errmsg = "" -# self.modalResults = True # used to mark results names as modal (report only last) or cumulative (list all) -# self.debugActions = ( None, None, None ) #custom debug actions -# self.re = None -# self.callPreparse = True # used to avoid redundant calls to preParse -# self.callDuringTry = False -# -# def copy( self ): -# """Make a copy of this C{ParserElement}. Useful for defining different parse actions -# for the same parsing pattern, using copies of the original parse element.""" -# cpy = copy.copy( self ) -# cpy.parseAction = self.parseAction[:] -# cpy.ignoreExprs = self.ignoreExprs[:] -# if self.copyDefaultWhiteChars: -# cpy.whiteChars = ParserElement.DEFAULT_WHITE_CHARS -# return cpy -# -# def setName( self, name ): -# """Define name for this expression, for use in debugging.""" -# self.name = name -# self.errmsg = "Expected " + self.name -# if hasattr(self,"exception"): -# self.exception.msg = self.errmsg -# return self -# -# def setResultsName( self, name, listAllMatches=False ): -# """Define name for referencing matching tokens as a nested attribute -# of the returned parse results. -# NOTE: this returns a *copy* of the original C{ParserElement} object; -# this is so that the client can define a basic element, such as an -# integer, and reference it in multiple places with different names. -# -# You can also set results names using the abbreviated syntax, -# C{expr("name")} in place of C{expr.setResultsName("name")} - -# see L{I{__call__}<__call__>}. -# """ -# newself = self.copy() -# if name.endswith("*"): -# name = name[:-1] -# listAllMatches=True -# newself.resultsName = name -# newself.modalResults = not listAllMatches -# return newself -# -# def setBreak(self,breakFlag = True): -# """Method to invoke the Python pdb debugger when this element is -# about to be parsed. Set C{breakFlag} to True to enable, False to -# disable. -# """ -# if breakFlag: -# _parseMethod = self._parse -# def breaker(instring, loc, doActions=True, callPreParse=True): -# import pdb -# pdb.set_trace() -# return _parseMethod( instring, loc, doActions, callPreParse ) -# breaker._originalParseMethod = _parseMethod -# self._parse = breaker -# else: -# if hasattr(self._parse,"_originalParseMethod"): -# self._parse = self._parse._originalParseMethod -# return self -# -# def setParseAction( self, *fns, **kwargs ): -# """Define action to perform when successfully matching parse element definition. -# Parse action fn is a callable method with 0-3 arguments, called as C{fn(s,loc,toks)}, -# C{fn(loc,toks)}, C{fn(toks)}, or just C{fn()}, where: -# - s = the original string being parsed (see note below) -# - loc = the location of the matching substring -# - toks = a list of the matched tokens, packaged as a C{L{ParseResults}} object -# If the functions in fns modify the tokens, they can return them as the return -# value from fn, and the modified list of tokens will replace the original. -# Otherwise, fn does not need to return any value. -# -# Note: the default parsing behavior is to expand tabs in the input string -# before starting the parsing process. See L{I{parseString}} for more information -# on parsing strings containing C{}s, and suggested methods to maintain a -# consistent view of the parsed string, the parse location, and line and column -# positions within the parsed string. -# """ -# self.parseAction = list(map(_trim_arity, list(fns))) -# self.callDuringTry = ("callDuringTry" in kwargs and kwargs["callDuringTry"]) -# return self -# -# def addParseAction( self, *fns, **kwargs ): -# """Add parse action to expression's list of parse actions. See L{I{setParseAction}}.""" -# self.parseAction += list(map(_trim_arity, list(fns))) -# self.callDuringTry = self.callDuringTry or ("callDuringTry" in kwargs and kwargs["callDuringTry"]) -# return self -# -# def setFailAction( self, fn ): -# """Define action to perform if parsing fails at this expression. -# Fail acton fn is a callable function that takes the arguments -# C{fn(s,loc,expr,err)} where: -# - s = string being parsed -# - loc = location where expression match was attempted and failed -# - expr = the parse expression that failed -# - err = the exception thrown -# The function returns no value. It may throw C{L{ParseFatalException}} -# if it is desired to stop parsing immediately.""" -# self.failAction = fn -# return self -# -# def _skipIgnorables( self, instring, loc ): -# exprsFound = True -# while exprsFound: -# exprsFound = False -# for e in self.ignoreExprs: -# try: -# while 1: -# loc,dummy = e._parse( instring, loc ) -# exprsFound = True -# except ParseException: -# pass -# return loc -# -# def preParse( self, instring, loc ): -# if self.ignoreExprs: -# loc = self._skipIgnorables( instring, loc ) -# -# if self.skipWhitespace: -# wt = self.whiteChars -# instrlen = len(instring) -# while loc < instrlen and instring[loc] in wt: -# loc += 1 -# -# return loc -# -# def parseImpl( self, instring, loc, doActions=True ): -# return loc, [] -# -# def postParse( self, instring, loc, tokenlist ): -# return tokenlist -# -# #~ @profile -# def _parseNoCache( self, instring, loc, doActions=True, callPreParse=True ): -# debugging = ( self.debug ) #and doActions ) -# -# if debugging or self.failAction: -# #~ print ("Match",self,"at loc",loc,"(%d,%d)" % ( lineno(loc,instring), col(loc,instring) )) -# if (self.debugActions[0] ): -# self.debugActions[0]( instring, loc, self ) -# if callPreParse and self.callPreparse: -# preloc = self.preParse( instring, loc ) -# else: -# preloc = loc -# tokensStart = preloc -# try: -# try: -# loc,tokens = self.parseImpl( instring, preloc, doActions ) -# except IndexError: -# raise ParseException( instring, len(instring), self.errmsg, self ) -# except ParseBaseException, err: -# #~ print ("Exception raised:", err) -# err = None -# if self.debugActions[2]: -# self.debugActions[2]( instring, tokensStart, self, err ) -# if self.failAction: -# self.failAction( instring, tokensStart, self, err ) -# raise -# else: -# if callPreParse and self.callPreparse: -# preloc = self.preParse( instring, loc ) -# else: -# preloc = loc -# tokensStart = preloc -# if self.mayIndexError or loc >= len(instring): -# try: -# loc,tokens = self.parseImpl( instring, preloc, doActions ) -# except IndexError: -# raise ParseException( instring, len(instring), self.errmsg, self ) -# else: -# loc,tokens = self.parseImpl( instring, preloc, doActions ) -# -# tokens = self.postParse( instring, loc, tokens ) -# -# retTokens = ParseResults( tokens, self.resultsName, asList=self.saveAsList, modal=self.modalResults ) -# if self.parseAction and (doActions or self.callDuringTry): -# if debugging: -# try: -# for fn in self.parseAction: -# tokens = fn( instring, tokensStart, retTokens ) -# if tokens is not None: -# retTokens = ParseResults( tokens, -# self.resultsName, -# asList=self.saveAsList and isinstance(tokens,(ParseResults,list)), -# modal=self.modalResults ) -# except ParseBaseException, err: -# #~ print "Exception raised in user parse action:", err -# if (self.debugActions[2] ): -# self.debugActions[2]( instring, tokensStart, self, err ) -# raise -# else: -# for fn in self.parseAction: -# tokens = fn( instring, tokensStart, retTokens ) -# if tokens is not None: -# retTokens = ParseResults( tokens, -# self.resultsName, -# asList=self.saveAsList and isinstance(tokens,(ParseResults,list)), -# modal=self.modalResults ) -# -# if debugging: -# #~ print ("Matched",self,"->",retTokens.asList()) -# if (self.debugActions[1] ): -# self.debugActions[1]( instring, tokensStart, loc, self, retTokens ) -# -# return loc, retTokens -# -# def tryParse( self, instring, loc ): -# try: -# return self._parse( instring, loc, doActions=False )[0] -# except ParseFatalException: -# raise ParseException( instring, loc, self.errmsg, self) -# -# # this method gets repeatedly called during backtracking with the same arguments - -# # we can cache these arguments and save ourselves the trouble of re-parsing the contained expression -# def _parseCache( self, instring, loc, doActions=True, callPreParse=True ): -# lookup = (self,instring,loc,callPreParse,doActions) -# if lookup in ParserElement._exprArgCache: -# value = ParserElement._exprArgCache[ lookup ] -# if isinstance(value, Exception): -# raise value -# return (value[0],value[1].copy()) -# else: -# try: -# value = self._parseNoCache( instring, loc, doActions, callPreParse ) -# ParserElement._exprArgCache[ lookup ] = (value[0],value[1].copy()) -# return value -# except ParseBaseException, pe: -# ParserElement._exprArgCache[ lookup ] = pe -# raise -# -# _parse = _parseNoCache -# -# # argument cache for optimizing repeated calls when backtracking through recursive expressions -# _exprArgCache = {} -# def resetCache(): -# ParserElement._exprArgCache.clear() -# resetCache = staticmethod(resetCache) -# -# _packratEnabled = False -# def enablePackrat(): -# """Enables "packrat" parsing, which adds memoizing to the parsing logic. -# Repeated parse attempts at the same string location (which happens -# often in many complex grammars) can immediately return a cached value, -# instead of re-executing parsing/validating code. Memoizing is done of -# both valid results and parsing exceptions. -# -# This speedup may break existing programs that use parse actions that -# have side-effects. For this reason, packrat parsing is disabled when -# you first import pyparsing. To activate the packrat feature, your -# program must call the class method C{ParserElement.enablePackrat()}. If -# your program uses C{psyco} to "compile as you go", you must call -# C{enablePackrat} before calling C{psyco.full()}. If you do not do this, -# Python will crash. For best results, call C{enablePackrat()} immediately -# after importing pyparsing. -# """ -# if not ParserElement._packratEnabled: -# ParserElement._packratEnabled = True -# ParserElement._parse = ParserElement._parseCache -# enablePackrat = staticmethod(enablePackrat) -# -# def parseString( self, instring, parseAll=False ): -# """Execute the parse expression with the given string. -# This is the main interface to the client code, once the complete -# expression has been built. -# -# If you want the grammar to require that the entire input string be -# successfully parsed, then set C{parseAll} to True (equivalent to ending -# the grammar with C{L{StringEnd()}}). -# -# Note: C{parseString} implicitly calls C{expandtabs()} on the input string, -# in order to report proper column numbers in parse actions. -# If the input string contains tabs and -# the grammar uses parse actions that use the C{loc} argument to index into the -# string being parsed, you can ensure you have a consistent view of the input -# string by: -# - calling C{parseWithTabs} on your grammar before calling C{parseString} -# (see L{I{parseWithTabs}}) -# - define your parse action using the full C{(s,loc,toks)} signature, and -# reference the input string using the parse action's C{s} argument -# - explictly expand the tabs in your input string before calling -# C{parseString} -# """ -# ParserElement.resetCache() -# if not self.streamlined: -# self.streamline() -# #~ self.saveAsList = True -# for e in self.ignoreExprs: -# e.streamline() -# if not self.keepTabs: -# instring = instring.expandtabs() -# try: -# loc, tokens = self._parse( instring, 0 ) -# if parseAll: -# loc = self.preParse( instring, loc ) -# se = Empty() + StringEnd() -# se._parse( instring, loc ) -# except ParseBaseException, exc: -# if ParserElement.verbose_stacktrace: -# raise -# else: -# # catch and re-raise exception from here, clears out pyparsing internal stack trace -# raise exc -# else: -# return tokens -# -# def scanString( self, instring, maxMatches=_MAX_INT, overlap=False ): -# """Scan the input string for expression matches. Each match will return the -# matching tokens, start location, and end location. May be called with optional -# C{maxMatches} argument, to clip scanning after 'n' matches are found. If -# C{overlap} is specified, then overlapping matches will be reported. -# -# Note that the start and end locations are reported relative to the string -# being parsed. See L{I{parseString}} for more information on parsing -# strings with embedded tabs.""" -# if not self.streamlined: -# self.streamline() -# for e in self.ignoreExprs: -# e.streamline() -# -# if not self.keepTabs: -# instring = _ustr(instring).expandtabs() -# instrlen = len(instring) -# loc = 0 -# preparseFn = self.preParse -# parseFn = self._parse -# ParserElement.resetCache() -# matches = 0 -# try: -# while loc <= instrlen and matches < maxMatches: -# try: -# preloc = preparseFn( instring, loc ) -# nextLoc,tokens = parseFn( instring, preloc, callPreParse=False ) -# except ParseException: -# loc = preloc+1 -# else: -# if nextLoc > loc: -# matches += 1 -# yield tokens, preloc, nextLoc -# if overlap: -# nextloc = preparseFn( instring, loc ) -# if nextloc > loc: -# loc = nextLoc -# else: -# loc += 1 -# else: -# loc = nextLoc -# else: -# loc = preloc+1 -# except ParseBaseException, exc: -# if ParserElement.verbose_stacktrace: -# raise -# else: -# # catch and re-raise exception from here, clears out pyparsing internal stack trace -# raise exc -# -# def transformString( self, instring ): -# """Extension to C{L{scanString}}, to modify matching text with modified tokens that may -# be returned from a parse action. To use C{transformString}, define a grammar and -# attach a parse action to it that modifies the returned token list. -# Invoking C{transformString()} on a target string will then scan for matches, -# and replace the matched text patterns according to the logic in the parse -# action. C{transformString()} returns the resulting transformed string.""" -# out = [] -# lastE = 0 -# # force preservation of s, to minimize unwanted transformation of string, and to -# # keep string locs straight between transformString and scanString -# self.keepTabs = True -# try: -# for t,s,e in self.scanString( instring ): -# out.append( instring[lastE:s] ) -# if t: -# if isinstance(t,ParseResults): -# out += t.asList() -# elif isinstance(t,list): -# out += t -# else: -# out.append(t) -# lastE = e -# out.append(instring[lastE:]) -# out = [o for o in out if o] -# return "".join(map(_ustr,_flatten(out))) -# except ParseBaseException, exc: -# if ParserElement.verbose_stacktrace: -# raise -# else: -# # catch and re-raise exception from here, clears out pyparsing internal stack trace -# raise exc -# -# def searchString( self, instring, maxMatches=_MAX_INT ): -# """Another extension to C{L{scanString}}, simplifying the access to the tokens found -# to match the given parse expression. May be called with optional -# C{maxMatches} argument, to clip searching after 'n' matches are found. -# """ -# try: -# return ParseResults([ t for t,s,e in self.scanString( instring, maxMatches ) ]) -# except ParseBaseException, exc: -# if ParserElement.verbose_stacktrace: -# raise -# else: -# # catch and re-raise exception from here, clears out pyparsing internal stack trace -# raise exc -# -# def __add__(self, other ): -# """Implementation of + operator - returns C{L{And}}""" -# if isinstance( other, basestring ): -# other = ParserElement.literalStringClass( other ) -# if not isinstance( other, ParserElement ): -# warnings.warn("Cannot combine element of type %s with ParserElement" % type(other), -# SyntaxWarning, stacklevel=2) -# return None -# return And( [ self, other ] ) -# -# def __radd__(self, other ): -# """Implementation of + operator when left operand is not a C{L{ParserElement}}""" -# if isinstance( other, basestring ): -# other = ParserElement.literalStringClass( other ) -# if not isinstance( other, ParserElement ): -# warnings.warn("Cannot combine element of type %s with ParserElement" % type(other), -# SyntaxWarning, stacklevel=2) -# return None -# return other + self -# -# def __sub__(self, other): -# """Implementation of - operator, returns C{L{And}} with error stop""" -# if isinstance( other, basestring ): -# other = ParserElement.literalStringClass( other ) -# if not isinstance( other, ParserElement ): -# warnings.warn("Cannot combine element of type %s with ParserElement" % type(other), -# SyntaxWarning, stacklevel=2) -# return None -# return And( [ self, And._ErrorStop(), other ] ) -# -# def __rsub__(self, other ): -# """Implementation of - operator when left operand is not a C{L{ParserElement}}""" -# if isinstance( other, basestring ): -# other = ParserElement.literalStringClass( other ) -# if not isinstance( other, ParserElement ): -# warnings.warn("Cannot combine element of type %s with ParserElement" % type(other), -# SyntaxWarning, stacklevel=2) -# return None -# return other - self -# -# def __mul__(self,other): -# """Implementation of * operator, allows use of C{expr * 3} in place of -# C{expr + expr + expr}. Expressions may also me multiplied by a 2-integer -# tuple, similar to C{{min,max}} multipliers in regular expressions. Tuples -# may also include C{None} as in: -# - C{expr*(n,None)} or C{expr*(n,)} is equivalent -# to C{expr*n + L{ZeroOrMore}(expr)} -# (read as "at least n instances of C{expr}") -# - C{expr*(None,n)} is equivalent to C{expr*(0,n)} -# (read as "0 to n instances of C{expr}") -# - C{expr*(None,None)} is equivalent to C{L{ZeroOrMore}(expr)} -# - C{expr*(1,None)} is equivalent to C{L{OneOrMore}(expr)} -# -# Note that C{expr*(None,n)} does not raise an exception if -# more than n exprs exist in the input stream; that is, -# C{expr*(None,n)} does not enforce a maximum number of expr -# occurrences. If this behavior is desired, then write -# C{expr*(None,n) + ~expr} -# -# """ -# if isinstance(other,int): -# minElements, optElements = other,0 -# elif isinstance(other,tuple): -# other = (other + (None, None))[:2] -# if other[0] is None: -# other = (0, other[1]) -# if isinstance(other[0],int) and other[1] is None: -# if other[0] == 0: -# return ZeroOrMore(self) -# if other[0] == 1: -# return OneOrMore(self) -# else: -# return self*other[0] + ZeroOrMore(self) -# elif isinstance(other[0],int) and isinstance(other[1],int): -# minElements, optElements = other -# optElements -= minElements -# else: -# raise TypeError("cannot multiply 'ParserElement' and ('%s','%s') objects", type(other[0]),type(other[1])) -# else: -# raise TypeError("cannot multiply 'ParserElement' and '%s' objects", type(other)) -# -# if minElements < 0: -# raise ValueError("cannot multiply ParserElement by negative value") -# if optElements < 0: -# raise ValueError("second tuple value must be greater or equal to first tuple value") -# if minElements == optElements == 0: -# raise ValueError("cannot multiply ParserElement by 0 or (0,0)") -# -# if (optElements): -# def makeOptionalList(n): -# if n>1: -# return Optional(self + makeOptionalList(n-1)) -# else: -# return Optional(self) -# if minElements: -# if minElements == 1: -# ret = self + makeOptionalList(optElements) -# else: -# ret = And([self]*minElements) + makeOptionalList(optElements) -# else: -# ret = makeOptionalList(optElements) -# else: -# if minElements == 1: -# ret = self -# else: -# ret = And([self]*minElements) -# return ret -# -# def __rmul__(self, other): -# return self.__mul__(other) -# -# def __or__(self, other ): -# """Implementation of | operator - returns C{L{MatchFirst}}""" -# if isinstance( other, basestring ): -# other = ParserElement.literalStringClass( other ) -# if not isinstance( other, ParserElement ): -# warnings.warn("Cannot combine element of type %s with ParserElement" % type(other), -# SyntaxWarning, stacklevel=2) -# return None -# return MatchFirst( [ self, other ] ) -# -# def __ror__(self, other ): -# """Implementation of | operator when left operand is not a C{L{ParserElement}}""" -# if isinstance( other, basestring ): -# other = ParserElement.literalStringClass( other ) -# if not isinstance( other, ParserElement ): -# warnings.warn("Cannot combine element of type %s with ParserElement" % type(other), -# SyntaxWarning, stacklevel=2) -# return None -# return other | self -# -# def __xor__(self, other ): -# """Implementation of ^ operator - returns C{L{Or}}""" -# if isinstance( other, basestring ): -# other = ParserElement.literalStringClass( other ) -# if not isinstance( other, ParserElement ): -# warnings.warn("Cannot combine element of type %s with ParserElement" % type(other), -# SyntaxWarning, stacklevel=2) -# return None -# return Or( [ self, other ] ) -# -# def __rxor__(self, other ): -# """Implementation of ^ operator when left operand is not a C{L{ParserElement}}""" -# if isinstance( other, basestring ): -# other = ParserElement.literalStringClass( other ) -# if not isinstance( other, ParserElement ): -# warnings.warn("Cannot combine element of type %s with ParserElement" % type(other), -# SyntaxWarning, stacklevel=2) -# return None -# return other ^ self -# -# def __and__(self, other ): -# """Implementation of & operator - returns C{L{Each}}""" -# if isinstance( other, basestring ): -# other = ParserElement.literalStringClass( other ) -# if not isinstance( other, ParserElement ): -# warnings.warn("Cannot combine element of type %s with ParserElement" % type(other), -# SyntaxWarning, stacklevel=2) -# return None -# return Each( [ self, other ] ) -# -# def __rand__(self, other ): -# """Implementation of & operator when left operand is not a C{L{ParserElement}}""" -# if isinstance( other, basestring ): -# other = ParserElement.literalStringClass( other ) -# if not isinstance( other, ParserElement ): -# warnings.warn("Cannot combine element of type %s with ParserElement" % type(other), -# SyntaxWarning, stacklevel=2) -# return None -# return other & self -# -# def __invert__( self ): -# """Implementation of ~ operator - returns C{L{NotAny}}""" -# return NotAny( self ) -# -# def __call__(self, name): -# """Shortcut for C{L{setResultsName}}, with C{listAllMatches=default}:: -# userdata = Word(alphas).setResultsName("name") + Word(nums+"-").setResultsName("socsecno") -# could be written as:: -# userdata = Word(alphas)("name") + Word(nums+"-")("socsecno") -# -# If C{name} is given with a trailing C{'*'} character, then C{listAllMatches} will be -# passed as C{True}. -# """ -# return self.setResultsName(name) -# -# def suppress( self ): -# """Suppresses the output of this C{ParserElement}; useful to keep punctuation from -# cluttering up returned output. -# """ -# return Suppress( self ) -# -# def leaveWhitespace( self ): -# """Disables the skipping of whitespace before matching the characters in the -# C{ParserElement}'s defined pattern. This is normally only used internally by -# the pyparsing module, but may be needed in some whitespace-sensitive grammars. -# """ -# self.skipWhitespace = False -# return self -# -# def setWhitespaceChars( self, chars ): -# """Overrides the default whitespace chars -# """ -# self.skipWhitespace = True -# self.whiteChars = chars -# self.copyDefaultWhiteChars = False -# return self -# -# def parseWithTabs( self ): -# """Overrides default behavior to expand C{}s to spaces before parsing the input string. -# Must be called before C{parseString} when the input grammar contains elements that -# match C{} characters.""" -# self.keepTabs = True -# return self -# -# def ignore( self, other ): -# """Define expression to be ignored (e.g., comments) while doing pattern -# matching; may be called repeatedly, to define multiple comment or other -# ignorable patterns. -# """ -# if isinstance( other, Suppress ): -# if other not in self.ignoreExprs: -# self.ignoreExprs.append( other.copy() ) -# else: -# self.ignoreExprs.append( Suppress( other.copy() ) ) -# return self -# -# def setDebugActions( self, startAction, successAction, exceptionAction ): -# """Enable display of debugging messages while doing pattern matching.""" -# self.debugActions = (startAction or _defaultStartDebugAction, -# successAction or _defaultSuccessDebugAction, -# exceptionAction or _defaultExceptionDebugAction) -# self.debug = True -# return self -# -# def setDebug( self, flag=True ): -# """Enable display of debugging messages while doing pattern matching. -# Set C{flag} to True to enable, False to disable.""" -# if flag: -# self.setDebugActions( _defaultStartDebugAction, _defaultSuccessDebugAction, _defaultExceptionDebugAction ) -# else: -# self.debug = False -# return self -# -# def __str__( self ): -# return self.name -# -# def __repr__( self ): -# return _ustr(self) -# -# def streamline( self ): -# self.streamlined = True -# self.strRepr = None -# return self -# -# def checkRecursion( self, parseElementList ): -# pass -# -# def validate( self, validateTrace=[] ): -# """Check defined expressions for valid structure, check for infinite recursive definitions.""" -# self.checkRecursion( [] ) -# -# def parseFile( self, file_or_filename, parseAll=False ): -# """Execute the parse expression on the given file or filename. -# If a filename is specified (instead of a file object), -# the entire file is opened, read, and closed before parsing. -# """ -# try: -# file_contents = file_or_filename.read() -# except AttributeError: -# f = open(file_or_filename, "r") -# file_contents = f.read() -# f.close() -# try: -# return self.parseString(file_contents, parseAll) -# except ParseBaseException, exc: -# if ParserElement.verbose_stacktrace: -# raise -# else: -# # catch and re-raise exception from here, clears out pyparsing internal stack trace -# raise exc -# -# def getException(self): -# return ParseException("",0,self.errmsg,self) -# -# def __getattr__(self,aname): -# if aname == "myException": -# self.myException = ret = self.getException(); -# return ret; -# else: -# raise AttributeError("no such attribute " + aname) -# -# def __eq__(self,other): -# if isinstance(other, ParserElement): -# return self is other or self.__dict__ == other.__dict__ -# elif isinstance(other, basestring): -# try: -# self.parseString(_ustr(other), parseAll=True) -# return True -# except ParseBaseException: -# return False -# else: -# return super(ParserElement,self)==other -# -# def __ne__(self,other): -# return not (self == other) -# -# def __hash__(self): -# return hash(id(self)) -# -# def __req__(self,other): -# return self == other -# -# def __rne__(self,other): -# return not (self == other) -# -# -# class Token(ParserElement): -# """Abstract C{ParserElement} subclass, for defining atomic matching patterns.""" -# def __init__( self ): -# super(Token,self).__init__( savelist=False ) -# -# def setName(self, name): -# s = super(Token,self).setName(name) -# self.errmsg = "Expected " + self.name -# return s -# -# -# class Empty(Token): -# """An empty token, will always match.""" -# def __init__( self ): -# super(Empty,self).__init__() -# self.name = "Empty" -# self.mayReturnEmpty = True -# self.mayIndexError = False -# -# -# class NoMatch(Token): -# """A token that will never match.""" -# def __init__( self ): -# super(NoMatch,self).__init__() -# self.name = "NoMatch" -# self.mayReturnEmpty = True -# self.mayIndexError = False -# self.errmsg = "Unmatchable token" -# -# def parseImpl( self, instring, loc, doActions=True ): -# exc = self.myException -# exc.loc = loc -# exc.pstr = instring -# raise exc -# -# -# class Literal(Token): -# """Token to exactly match a specified string.""" -# def __init__( self, matchString ): -# super(Literal,self).__init__() -# self.match = matchString -# self.matchLen = len(matchString) -# try: -# self.firstMatchChar = matchString[0] -# except IndexError: -# warnings.warn("null string passed to Literal; use Empty() instead", -# SyntaxWarning, stacklevel=2) -# self.__class__ = Empty -# self.name = '"%s"' % _ustr(self.match) -# self.errmsg = "Expected " + self.name -# self.mayReturnEmpty = False -# self.mayIndexError = False -# -# # Performance tuning: this routine gets called a *lot* -# # if this is a single character match string and the first character matches, -# # short-circuit as quickly as possible, and avoid calling startswith -# #~ @profile -# def parseImpl( self, instring, loc, doActions=True ): -# if (instring[loc] == self.firstMatchChar and -# (self.matchLen==1 or instring.startswith(self.match,loc)) ): -# return loc+self.matchLen, self.match -# #~ raise ParseException( instring, loc, self.errmsg ) -# exc = self.myException -# exc.loc = loc -# exc.pstr = instring -# raise exc -# _L = Literal -# ParserElement.literalStringClass = Literal -# -# class Keyword(Token): -# """Token to exactly match a specified string as a keyword, that is, it must be -# immediately followed by a non-keyword character. Compare with C{L{Literal}}:: -# Literal("if") will match the leading C{'if'} in C{'ifAndOnlyIf'}. -# Keyword("if") will not; it will only match the leading C{'if'} in C{'if x=1'}, or C{'if(y==2)'} -# Accepts two optional constructor arguments in addition to the keyword string: -# C{identChars} is a string of characters that would be valid identifier characters, -# defaulting to all alphanumerics + "_" and "$"; C{caseless} allows case-insensitive -# matching, default is C{False}. -# """ -# DEFAULT_KEYWORD_CHARS = alphanums+"_$" -# -# def __init__( self, matchString, identChars=DEFAULT_KEYWORD_CHARS, caseless=False ): -# super(Keyword,self).__init__() -# self.match = matchString -# self.matchLen = len(matchString) -# try: -# self.firstMatchChar = matchString[0] -# except IndexError: -# warnings.warn("null string passed to Keyword; use Empty() instead", -# SyntaxWarning, stacklevel=2) -# self.name = '"%s"' % self.match -# self.errmsg = "Expected " + self.name -# self.mayReturnEmpty = False -# self.mayIndexError = False -# self.caseless = caseless -# if caseless: -# self.caselessmatch = matchString.upper() -# identChars = identChars.upper() -# self.identChars = set(identChars) -# -# def parseImpl( self, instring, loc, doActions=True ): -# if self.caseless: -# if ( (instring[ loc:loc+self.matchLen ].upper() == self.caselessmatch) and -# (loc >= len(instring)-self.matchLen or instring[loc+self.matchLen].upper() not in self.identChars) and -# (loc == 0 or instring[loc-1].upper() not in self.identChars) ): -# return loc+self.matchLen, self.match -# else: -# if (instring[loc] == self.firstMatchChar and -# (self.matchLen==1 or instring.startswith(self.match,loc)) and -# (loc >= len(instring)-self.matchLen or instring[loc+self.matchLen] not in self.identChars) and -# (loc == 0 or instring[loc-1] not in self.identChars) ): -# return loc+self.matchLen, self.match -# #~ raise ParseException( instring, loc, self.errmsg ) -# exc = self.myException -# exc.loc = loc -# exc.pstr = instring -# raise exc -# -# def copy(self): -# c = super(Keyword,self).copy() -# c.identChars = Keyword.DEFAULT_KEYWORD_CHARS -# return c -# -# def setDefaultKeywordChars( chars ): -# """Overrides the default Keyword chars -# """ -# Keyword.DEFAULT_KEYWORD_CHARS = chars -# setDefaultKeywordChars = staticmethod(setDefaultKeywordChars) -# -# class CaselessLiteral(Literal): -# """Token to match a specified string, ignoring case of letters. -# Note: the matched results will always be in the case of the given -# match string, NOT the case of the input text. -# """ -# def __init__( self, matchString ): -# super(CaselessLiteral,self).__init__( matchString.upper() ) -# # Preserve the defining literal. -# self.returnString = matchString -# self.name = "'%s'" % self.returnString -# self.errmsg = "Expected " + self.name -# -# def parseImpl( self, instring, loc, doActions=True ): -# if instring[ loc:loc+self.matchLen ].upper() == self.match: -# return loc+self.matchLen, self.returnString -# #~ raise ParseException( instring, loc, self.errmsg ) -# exc = self.myException -# exc.loc = loc -# exc.pstr = instring -# raise exc -# -# class CaselessKeyword(Keyword): -# def __init__( self, matchString, identChars=Keyword.DEFAULT_KEYWORD_CHARS ): -# super(CaselessKeyword,self).__init__( matchString, identChars, caseless=True ) -# -# def parseImpl( self, instring, loc, doActions=True ): -# if ( (instring[ loc:loc+self.matchLen ].upper() == self.caselessmatch) and -# (loc >= len(instring)-self.matchLen or instring[loc+self.matchLen].upper() not in self.identChars) ): -# return loc+self.matchLen, self.match -# #~ raise ParseException( instring, loc, self.errmsg ) -# exc = self.myException -# exc.loc = loc -# exc.pstr = instring -# raise exc -# -# class Word(Token): -# """Token for matching words composed of allowed character sets. -# Defined with string containing all allowed initial characters, -# an optional string containing allowed body characters (if omitted, -# defaults to the initial character set), and an optional minimum, -# maximum, and/or exact length. The default value for C{min} is 1 (a -# minimum value < 1 is not valid); the default values for C{max} and C{exact} -# are 0, meaning no maximum or exact length restriction. An optional -# C{exclude} parameter can list characters that might be found in -# the input C{bodyChars} string; useful to define a word of all printables -# except for one or two characters, for instance. -# """ -# def __init__( self, initChars, bodyChars=None, min=1, max=0, exact=0, asKeyword=False, excludeChars=None ): -# super(Word,self).__init__() -# if excludeChars: -# initChars = ''.join([c for c in initChars if c not in excludeChars]) -# if bodyChars: -# bodyChars = ''.join([c for c in bodyChars if c not in excludeChars]) -# self.initCharsOrig = initChars -# self.initChars = set(initChars) -# if bodyChars : -# self.bodyCharsOrig = bodyChars -# self.bodyChars = set(bodyChars) -# else: -# self.bodyCharsOrig = initChars -# self.bodyChars = set(initChars) -# -# self.maxSpecified = max > 0 -# -# if min < 1: -# raise ValueError("cannot specify a minimum length < 1; use Optional(Word()) if zero-length word is permitted") -# -# self.minLen = min -# -# if max > 0: -# self.maxLen = max -# else: -# self.maxLen = _MAX_INT -# -# if exact > 0: -# self.maxLen = exact -# self.minLen = exact -# -# self.name = _ustr(self) -# self.errmsg = "Expected " + self.name -# self.mayIndexError = False -# self.asKeyword = asKeyword -# -# if ' ' not in self.initCharsOrig+self.bodyCharsOrig and (min==1 and max==0 and exact==0): -# if self.bodyCharsOrig == self.initCharsOrig: -# self.reString = "[%s]+" % _escapeRegexRangeChars(self.initCharsOrig) -# elif len(self.bodyCharsOrig) == 1: -# self.reString = "%s[%s]*" % \ -# (re.escape(self.initCharsOrig), -# _escapeRegexRangeChars(self.bodyCharsOrig),) -# else: -# self.reString = "[%s][%s]*" % \ -# (_escapeRegexRangeChars(self.initCharsOrig), -# _escapeRegexRangeChars(self.bodyCharsOrig),) -# if self.asKeyword: -# self.reString = r"\b"+self.reString+r"\b" -# try: -# self.re = re.compile( self.reString ) -# except: -# self.re = None -# -# def parseImpl( self, instring, loc, doActions=True ): -# if self.re: -# result = self.re.match(instring,loc) -# if not result: -# exc = self.myException -# exc.loc = loc -# exc.pstr = instring -# raise exc -# -# loc = result.end() -# return loc, result.group() -# -# if not(instring[ loc ] in self.initChars): -# #~ raise ParseException( instring, loc, self.errmsg ) -# exc = self.myException -# exc.loc = loc -# exc.pstr = instring -# raise exc -# start = loc -# loc += 1 -# instrlen = len(instring) -# bodychars = self.bodyChars -# maxloc = start + self.maxLen -# maxloc = min( maxloc, instrlen ) -# while loc < maxloc and instring[loc] in bodychars: -# loc += 1 -# -# throwException = False -# if loc - start < self.minLen: -# throwException = True -# if self.maxSpecified and loc < instrlen and instring[loc] in bodychars: -# throwException = True -# if self.asKeyword: -# if (start>0 and instring[start-1] in bodychars) or (loc4: -# return s[:4]+"..." -# else: -# return s -# -# if ( self.initCharsOrig != self.bodyCharsOrig ): -# self.strRepr = "W:(%s,%s)" % ( charsAsStr(self.initCharsOrig), charsAsStr(self.bodyCharsOrig) ) -# else: -# self.strRepr = "W:(%s)" % charsAsStr(self.initCharsOrig) -# -# return self.strRepr -# -# -# class Regex(Token): -# """Token for matching strings that match a given regular expression. -# Defined with string specifying the regular expression in a form recognized by the inbuilt Python re module. -# """ -# compiledREtype = type(re.compile("[A-Z]")) -# def __init__( self, pattern, flags=0): -# """The parameters C{pattern} and C{flags} are passed to the C{re.compile()} function as-is. See the Python C{re} module for an explanation of the acceptable patterns and flags.""" -# super(Regex,self).__init__() -# -# if isinstance(pattern, basestring): -# if len(pattern) == 0: -# warnings.warn("null string passed to Regex; use Empty() instead", -# SyntaxWarning, stacklevel=2) -# -# self.pattern = pattern -# self.flags = flags -# -# try: -# self.re = re.compile(self.pattern, self.flags) -# self.reString = self.pattern -# except sre_constants.error: -# warnings.warn("invalid pattern (%s) passed to Regex" % pattern, -# SyntaxWarning, stacklevel=2) -# raise -# -# elif isinstance(pattern, Regex.compiledREtype): -# self.re = pattern -# self.pattern = \ -# self.reString = str(pattern) -# self.flags = flags -# -# else: -# raise ValueError("Regex may only be constructed with a string or a compiled RE object") -# -# self.name = _ustr(self) -# self.errmsg = "Expected " + self.name -# self.mayIndexError = False -# self.mayReturnEmpty = True -# -# def parseImpl( self, instring, loc, doActions=True ): -# result = self.re.match(instring,loc) -# if not result: -# exc = self.myException -# exc.loc = loc -# exc.pstr = instring -# raise exc -# -# loc = result.end() -# d = result.groupdict() -# ret = ParseResults(result.group()) -# if d: -# for k in d: -# ret[k] = d[k] -# return loc,ret -# -# def __str__( self ): -# try: -# return super(Regex,self).__str__() -# except: -# pass -# -# if self.strRepr is None: -# self.strRepr = "Re:(%s)" % repr(self.pattern) -# -# return self.strRepr -# -# -# class QuotedString(Token): -# """Token for matching strings that are delimited by quoting characters. -# """ -# def __init__( self, quoteChar, escChar=None, escQuote=None, multiline=False, unquoteResults=True, endQuoteChar=None): -# """ -# Defined with the following parameters: -# - quoteChar - string of one or more characters defining the quote delimiting string -# - escChar - character to escape quotes, typically backslash (default=None) -# - escQuote - special quote sequence to escape an embedded quote string (such as SQL's "" to escape an embedded ") (default=None) -# - multiline - boolean indicating whether quotes can span multiple lines (default=C{False}) -# - unquoteResults - boolean indicating whether the matched text should be unquoted (default=C{True}) -# - endQuoteChar - string of one or more characters defining the end of the quote delimited string (default=C{None} => same as quoteChar) -# """ -# super(QuotedString,self).__init__() -# -# # remove white space from quote chars - wont work anyway -# quoteChar = quoteChar.strip() -# if len(quoteChar) == 0: -# warnings.warn("quoteChar cannot be the empty string",SyntaxWarning,stacklevel=2) -# raise SyntaxError() -# -# if endQuoteChar is None: -# endQuoteChar = quoteChar -# else: -# endQuoteChar = endQuoteChar.strip() -# if len(endQuoteChar) == 0: -# warnings.warn("endQuoteChar cannot be the empty string",SyntaxWarning,stacklevel=2) -# raise SyntaxError() -# -# self.quoteChar = quoteChar -# self.quoteCharLen = len(quoteChar) -# self.firstQuoteChar = quoteChar[0] -# self.endQuoteChar = endQuoteChar -# self.endQuoteCharLen = len(endQuoteChar) -# self.escChar = escChar -# self.escQuote = escQuote -# self.unquoteResults = unquoteResults -# -# if multiline: -# self.flags = re.MULTILINE | re.DOTALL -# self.pattern = r'%s(?:[^%s%s]' % \ -# ( re.escape(self.quoteChar), -# _escapeRegexRangeChars(self.endQuoteChar[0]), -# (escChar is not None and _escapeRegexRangeChars(escChar) or '') ) -# else: -# self.flags = 0 -# self.pattern = r'%s(?:[^%s\n\r%s]' % \ -# ( re.escape(self.quoteChar), -# _escapeRegexRangeChars(self.endQuoteChar[0]), -# (escChar is not None and _escapeRegexRangeChars(escChar) or '') ) -# if len(self.endQuoteChar) > 1: -# self.pattern += ( -# '|(?:' + ')|(?:'.join(["%s[^%s]" % (re.escape(self.endQuoteChar[:i]), -# _escapeRegexRangeChars(self.endQuoteChar[i])) -# for i in range(len(self.endQuoteChar)-1,0,-1)]) + ')' -# ) -# if escQuote: -# self.pattern += (r'|(?:%s)' % re.escape(escQuote)) -# if escChar: -# self.pattern += (r'|(?:%s.)' % re.escape(escChar)) -# charset = ''.join(set(self.quoteChar[0]+self.endQuoteChar[0])).replace('^',r'\^').replace('-',r'\-') -# self.escCharReplacePattern = re.escape(self.escChar)+("([%s])" % charset) -# self.pattern += (r')*%s' % re.escape(self.endQuoteChar)) -# -# try: -# self.re = re.compile(self.pattern, self.flags) -# self.reString = self.pattern -# except sre_constants.error: -# warnings.warn("invalid pattern (%s) passed to Regex" % self.pattern, -# SyntaxWarning, stacklevel=2) -# raise -# -# self.name = _ustr(self) -# self.errmsg = "Expected " + self.name -# self.mayIndexError = False -# self.mayReturnEmpty = True -# -# def parseImpl( self, instring, loc, doActions=True ): -# result = instring[loc] == self.firstQuoteChar and self.re.match(instring,loc) or None -# if not result: -# exc = self.myException -# exc.loc = loc -# exc.pstr = instring -# raise exc -# -# loc = result.end() -# ret = result.group() -# -# if self.unquoteResults: -# -# # strip off quotes -# ret = ret[self.quoteCharLen:-self.endQuoteCharLen] -# -# if isinstance(ret,basestring): -# # replace escaped characters -# if self.escChar: -# ret = re.sub(self.escCharReplacePattern,"\g<1>",ret) -# -# # replace escaped quotes -# if self.escQuote: -# ret = ret.replace(self.escQuote, self.endQuoteChar) -# -# return loc, ret -# -# def __str__( self ): -# try: -# return super(QuotedString,self).__str__() -# except: -# pass -# -# if self.strRepr is None: -# self.strRepr = "quoted string, starting with %s ending with %s" % (self.quoteChar, self.endQuoteChar) -# -# return self.strRepr -# -# -# class CharsNotIn(Token): -# """Token for matching words composed of characters *not* in a given set. -# Defined with string containing all disallowed characters, and an optional -# minimum, maximum, and/or exact length. The default value for C{min} is 1 (a -# minimum value < 1 is not valid); the default values for C{max} and C{exact} -# are 0, meaning no maximum or exact length restriction. -# """ -# def __init__( self, notChars, min=1, max=0, exact=0 ): -# super(CharsNotIn,self).__init__() -# self.skipWhitespace = False -# self.notChars = notChars -# -# if min < 1: -# raise ValueError("cannot specify a minimum length < 1; use Optional(CharsNotIn()) if zero-length char group is permitted") -# -# self.minLen = min -# -# if max > 0: -# self.maxLen = max -# else: -# self.maxLen = _MAX_INT -# -# if exact > 0: -# self.maxLen = exact -# self.minLen = exact -# -# self.name = _ustr(self) -# self.errmsg = "Expected " + self.name -# self.mayReturnEmpty = ( self.minLen == 0 ) -# self.mayIndexError = False -# -# def parseImpl( self, instring, loc, doActions=True ): -# if instring[loc] in self.notChars: -# #~ raise ParseException( instring, loc, self.errmsg ) -# exc = self.myException -# exc.loc = loc -# exc.pstr = instring -# raise exc -# -# start = loc -# loc += 1 -# notchars = self.notChars -# maxlen = min( start+self.maxLen, len(instring) ) -# while loc < maxlen and \ -# (instring[loc] not in notchars): -# loc += 1 -# -# if loc - start < self.minLen: -# #~ raise ParseException( instring, loc, self.errmsg ) -# exc = self.myException -# exc.loc = loc -# exc.pstr = instring -# raise exc -# -# return loc, instring[start:loc] -# -# def __str__( self ): -# try: -# return super(CharsNotIn, self).__str__() -# except: -# pass -# -# if self.strRepr is None: -# if len(self.notChars) > 4: -# self.strRepr = "!W:(%s...)" % self.notChars[:4] -# else: -# self.strRepr = "!W:(%s)" % self.notChars -# -# return self.strRepr -# -# class White(Token): -# """Special matching class for matching whitespace. Normally, whitespace is ignored -# by pyparsing grammars. This class is included when some whitespace structures -# are significant. Define with a string containing the whitespace characters to be -# matched; default is C{" \\t\\r\\n"}. Also takes optional C{min}, C{max}, and C{exact} arguments, -# as defined for the C{L{Word}} class.""" -# whiteStrs = { -# " " : "", -# "\t": "", -# "\n": "", -# "\r": "", -# "\f": "", -# } -# def __init__(self, ws=" \t\r\n", min=1, max=0, exact=0): -# super(White,self).__init__() -# self.matchWhite = ws -# self.setWhitespaceChars( "".join([c for c in self.whiteChars if c not in self.matchWhite]) ) -# #~ self.leaveWhitespace() -# self.name = ("".join([White.whiteStrs[c] for c in self.matchWhite])) -# self.mayReturnEmpty = True -# self.errmsg = "Expected " + self.name -# -# self.minLen = min -# -# if max > 0: -# self.maxLen = max -# else: -# self.maxLen = _MAX_INT -# -# if exact > 0: -# self.maxLen = exact -# self.minLen = exact -# -# def parseImpl( self, instring, loc, doActions=True ): -# if not(instring[ loc ] in self.matchWhite): -# #~ raise ParseException( instring, loc, self.errmsg ) -# exc = self.myException -# exc.loc = loc -# exc.pstr = instring -# raise exc -# start = loc -# loc += 1 -# maxloc = start + self.maxLen -# maxloc = min( maxloc, len(instring) ) -# while loc < maxloc and instring[loc] in self.matchWhite: -# loc += 1 -# -# if loc - start < self.minLen: -# #~ raise ParseException( instring, loc, self.errmsg ) -# exc = self.myException -# exc.loc = loc -# exc.pstr = instring -# raise exc -# -# return loc, instring[start:loc] -# -# -# class _PositionToken(Token): -# def __init__( self ): -# super(_PositionToken,self).__init__() -# self.name=self.__class__.__name__ -# self.mayReturnEmpty = True -# self.mayIndexError = False -# -# class GoToColumn(_PositionToken): -# """Token to advance to a specific column of input text; useful for tabular report scraping.""" -# def __init__( self, colno ): -# super(GoToColumn,self).__init__() -# self.col = colno -# -# def preParse( self, instring, loc ): -# if col(loc,instring) != self.col: -# instrlen = len(instring) -# if self.ignoreExprs: -# loc = self._skipIgnorables( instring, loc ) -# while loc < instrlen and instring[loc].isspace() and col( loc, instring ) != self.col : -# loc += 1 -# return loc -# -# def parseImpl( self, instring, loc, doActions=True ): -# thiscol = col( loc, instring ) -# if thiscol > self.col: -# raise ParseException( instring, loc, "Text not in expected column", self ) -# newloc = loc + self.col - thiscol -# ret = instring[ loc: newloc ] -# return newloc, ret -# -# class LineStart(_PositionToken): -# """Matches if current position is at the beginning of a line within the parse string""" -# def __init__( self ): -# super(LineStart,self).__init__() -# self.setWhitespaceChars( ParserElement.DEFAULT_WHITE_CHARS.replace("\n","") ) -# self.errmsg = "Expected start of line" -# -# def preParse( self, instring, loc ): -# preloc = super(LineStart,self).preParse(instring,loc) -# if instring[preloc] == "\n": -# loc += 1 -# return loc -# -# def parseImpl( self, instring, loc, doActions=True ): -# if not( loc==0 or -# (loc == self.preParse( instring, 0 )) or -# (instring[loc-1] == "\n") ): #col(loc, instring) != 1: -# #~ raise ParseException( instring, loc, "Expected start of line" ) -# exc = self.myException -# exc.loc = loc -# exc.pstr = instring -# raise exc -# return loc, [] -# -# class LineEnd(_PositionToken): -# """Matches if current position is at the end of a line within the parse string""" -# def __init__( self ): -# super(LineEnd,self).__init__() -# self.setWhitespaceChars( ParserElement.DEFAULT_WHITE_CHARS.replace("\n","") ) -# self.errmsg = "Expected end of line" -# -# def parseImpl( self, instring, loc, doActions=True ): -# if loc len(instring): -# return loc, [] -# else: -# exc = self.myException -# exc.loc = loc -# exc.pstr = instring -# raise exc -# -# class WordStart(_PositionToken): -# """Matches if the current position is at the beginning of a Word, and -# is not preceded by any character in a given set of C{wordChars} -# (default=C{printables}). To emulate the C{\b} behavior of regular expressions, -# use C{WordStart(alphanums)}. C{WordStart} will also match at the beginning of -# the string being parsed, or at the beginning of a line. -# """ -# def __init__(self, wordChars = printables): -# super(WordStart,self).__init__() -# self.wordChars = set(wordChars) -# self.errmsg = "Not at the start of a word" -# -# def parseImpl(self, instring, loc, doActions=True ): -# if loc != 0: -# if (instring[loc-1] in self.wordChars or -# instring[loc] not in self.wordChars): -# exc = self.myException -# exc.loc = loc -# exc.pstr = instring -# raise exc -# return loc, [] -# -# class WordEnd(_PositionToken): -# """Matches if the current position is at the end of a Word, and -# is not followed by any character in a given set of C{wordChars} -# (default=C{printables}). To emulate the C{\b} behavior of regular expressions, -# use C{WordEnd(alphanums)}. C{WordEnd} will also match at the end of -# the string being parsed, or at the end of a line. -# """ -# def __init__(self, wordChars = printables): -# super(WordEnd,self).__init__() -# self.wordChars = set(wordChars) -# self.skipWhitespace = False -# self.errmsg = "Not at the end of a word" -# -# def parseImpl(self, instring, loc, doActions=True ): -# instrlen = len(instring) -# if instrlen>0 and loc maxExcLoc: -# maxException = err -# maxExcLoc = err.loc -# except IndexError: -# if len(instring) > maxExcLoc: -# maxException = ParseException(instring,len(instring),e.errmsg,self) -# maxExcLoc = len(instring) -# else: -# if loc2 > maxMatchLoc: -# maxMatchLoc = loc2 -# maxMatchExp = e -# -# if maxMatchLoc < 0: -# if maxException is not None: -# raise maxException -# else: -# raise ParseException(instring, loc, "no defined alternatives to match", self) -# -# return maxMatchExp._parse( instring, loc, doActions ) -# -# def __ixor__(self, other ): -# if isinstance( other, basestring ): -# other = ParserElement.literalStringClass( other ) -# return self.append( other ) #Or( [ self, other ] ) -# -# def __str__( self ): -# if hasattr(self,"name"): -# return self.name -# -# if self.strRepr is None: -# self.strRepr = "{" + " ^ ".join( [ _ustr(e) for e in self.exprs ] ) + "}" -# -# return self.strRepr -# -# def checkRecursion( self, parseElementList ): -# subRecCheckList = parseElementList[:] + [ self ] -# for e in self.exprs: -# e.checkRecursion( subRecCheckList ) -# -# -# class MatchFirst(ParseExpression): -# """Requires that at least one C{ParseExpression} is found. -# If two expressions match, the first one listed is the one that will match. -# May be constructed using the C{'|'} operator. -# """ -# def __init__( self, exprs, savelist = False ): -# super(MatchFirst,self).__init__(exprs, savelist) -# if exprs: -# self.mayReturnEmpty = False -# for e in self.exprs: -# if e.mayReturnEmpty: -# self.mayReturnEmpty = True -# break -# else: -# self.mayReturnEmpty = True -# -# def parseImpl( self, instring, loc, doActions=True ): -# maxExcLoc = -1 -# maxException = None -# for e in self.exprs: -# try: -# ret = e._parse( instring, loc, doActions ) -# return ret -# except ParseException, err: -# if err.loc > maxExcLoc: -# maxException = err -# maxExcLoc = err.loc -# except IndexError: -# if len(instring) > maxExcLoc: -# maxException = ParseException(instring,len(instring),e.errmsg,self) -# maxExcLoc = len(instring) -# -# # only got here if no expression matched, raise exception for match that made it the furthest -# else: -# if maxException is not None: -# raise maxException -# else: -# raise ParseException(instring, loc, "no defined alternatives to match", self) -# -# def __ior__(self, other ): -# if isinstance( other, basestring ): -# other = ParserElement.literalStringClass( other ) -# return self.append( other ) #MatchFirst( [ self, other ] ) -# -# def __str__( self ): -# if hasattr(self,"name"): -# return self.name -# -# if self.strRepr is None: -# self.strRepr = "{" + " | ".join( [ _ustr(e) for e in self.exprs ] ) + "}" -# -# return self.strRepr -# -# def checkRecursion( self, parseElementList ): -# subRecCheckList = parseElementList[:] + [ self ] -# for e in self.exprs: -# e.checkRecursion( subRecCheckList ) -# -# -# class Each(ParseExpression): -# """Requires all given C{ParseExpression}s to be found, but in any order. -# Expressions may be separated by whitespace. -# May be constructed using the C{'&'} operator. -# """ -# def __init__( self, exprs, savelist = True ): -# super(Each,self).__init__(exprs, savelist) -# self.mayReturnEmpty = True -# for e in self.exprs: -# if not e.mayReturnEmpty: -# self.mayReturnEmpty = False -# break -# self.skipWhitespace = True -# self.initExprGroups = True -# -# def parseImpl( self, instring, loc, doActions=True ): -# if self.initExprGroups: -# opt1 = [ e.expr for e in self.exprs if isinstance(e,Optional) ] -# opt2 = [ e for e in self.exprs if e.mayReturnEmpty and e not in opt1 ] -# self.optionals = opt1 + opt2 -# self.multioptionals = [ e.expr for e in self.exprs if isinstance(e,ZeroOrMore) ] -# self.multirequired = [ e.expr for e in self.exprs if isinstance(e,OneOrMore) ] -# self.required = [ e for e in self.exprs if not isinstance(e,(Optional,ZeroOrMore,OneOrMore)) ] -# self.required += self.multirequired -# self.initExprGroups = False -# tmpLoc = loc -# tmpReqd = self.required[:] -# tmpOpt = self.optionals[:] -# matchOrder = [] -# -# keepMatching = True -# while keepMatching: -# tmpExprs = tmpReqd + tmpOpt + self.multioptionals + self.multirequired -# failed = [] -# for e in tmpExprs: -# try: -# tmpLoc = e.tryParse( instring, tmpLoc ) -# except ParseException: -# failed.append(e) -# else: -# matchOrder.append(e) -# if e in tmpReqd: -# tmpReqd.remove(e) -# elif e in tmpOpt: -# tmpOpt.remove(e) -# if len(failed) == len(tmpExprs): -# keepMatching = False -# -# if tmpReqd: -# missing = ", ".join( [ _ustr(e) for e in tmpReqd ] ) -# raise ParseException(instring,loc,"Missing one or more required elements (%s)" % missing ) -# -# # add any unmatched Optionals, in case they have default values defined -# matchOrder += [e for e in self.exprs if isinstance(e,Optional) and e.expr in tmpOpt] -# -# resultlist = [] -# for e in matchOrder: -# loc,results = e._parse(instring,loc,doActions) -# resultlist.append(results) -# -# finalResults = ParseResults([]) -# for r in resultlist: -# dups = {} -# for k in r.keys(): -# if k in finalResults.keys(): -# tmp = ParseResults(finalResults[k]) -# tmp += ParseResults(r[k]) -# dups[k] = tmp -# finalResults += ParseResults(r) -# for k,v in dups.items(): -# finalResults[k] = v -# return loc, finalResults -# -# def __str__( self ): -# if hasattr(self,"name"): -# return self.name -# -# if self.strRepr is None: -# self.strRepr = "{" + " & ".join( [ _ustr(e) for e in self.exprs ] ) + "}" -# -# return self.strRepr -# -# def checkRecursion( self, parseElementList ): -# subRecCheckList = parseElementList[:] + [ self ] -# for e in self.exprs: -# e.checkRecursion( subRecCheckList ) -# -# -# class ParseElementEnhance(ParserElement): -# """Abstract subclass of C{ParserElement}, for combining and post-processing parsed tokens.""" -# def __init__( self, expr, savelist=False ): -# super(ParseElementEnhance,self).__init__(savelist) -# if isinstance( expr, basestring ): -# expr = Literal(expr) -# self.expr = expr -# self.strRepr = None -# if expr is not None: -# self.mayIndexError = expr.mayIndexError -# self.mayReturnEmpty = expr.mayReturnEmpty -# self.setWhitespaceChars( expr.whiteChars ) -# self.skipWhitespace = expr.skipWhitespace -# self.saveAsList = expr.saveAsList -# self.callPreparse = expr.callPreparse -# self.ignoreExprs.extend(expr.ignoreExprs) -# -# def parseImpl( self, instring, loc, doActions=True ): -# if self.expr is not None: -# return self.expr._parse( instring, loc, doActions, callPreParse=False ) -# else: -# raise ParseException("",loc,self.errmsg,self) -# -# def leaveWhitespace( self ): -# self.skipWhitespace = False -# self.expr = self.expr.copy() -# if self.expr is not None: -# self.expr.leaveWhitespace() -# return self -# -# def ignore( self, other ): -# if isinstance( other, Suppress ): -# if other not in self.ignoreExprs: -# super( ParseElementEnhance, self).ignore( other ) -# if self.expr is not None: -# self.expr.ignore( self.ignoreExprs[-1] ) -# else: -# super( ParseElementEnhance, self).ignore( other ) -# if self.expr is not None: -# self.expr.ignore( self.ignoreExprs[-1] ) -# return self -# -# def streamline( self ): -# super(ParseElementEnhance,self).streamline() -# if self.expr is not None: -# self.expr.streamline() -# return self -# -# def checkRecursion( self, parseElementList ): -# if self in parseElementList: -# raise RecursiveGrammarException( parseElementList+[self] ) -# subRecCheckList = parseElementList[:] + [ self ] -# if self.expr is not None: -# self.expr.checkRecursion( subRecCheckList ) -# -# def validate( self, validateTrace=[] ): -# tmp = validateTrace[:]+[self] -# if self.expr is not None: -# self.expr.validate(tmp) -# self.checkRecursion( [] ) -# -# def __str__( self ): -# try: -# return super(ParseElementEnhance,self).__str__() -# except: -# pass -# -# if self.strRepr is None and self.expr is not None: -# self.strRepr = "%s:(%s)" % ( self.__class__.__name__, _ustr(self.expr) ) -# return self.strRepr -# -# -# class FollowedBy(ParseElementEnhance): -# """Lookahead matching of the given parse expression. C{FollowedBy} -# does *not* advance the parsing position within the input string, it only -# verifies that the specified parse expression matches at the current -# position. C{FollowedBy} always returns a null token list.""" -# def __init__( self, expr ): -# super(FollowedBy,self).__init__(expr) -# self.mayReturnEmpty = True -# -# def parseImpl( self, instring, loc, doActions=True ): -# self.expr.tryParse( instring, loc ) -# return loc, [] -# -# -# class NotAny(ParseElementEnhance): -# """Lookahead to disallow matching with the given parse expression. C{NotAny} -# does *not* advance the parsing position within the input string, it only -# verifies that the specified parse expression does *not* match at the current -# position. Also, C{NotAny} does *not* skip over leading whitespace. C{NotAny} -# always returns a null token list. May be constructed using the '~' operator.""" -# def __init__( self, expr ): -# super(NotAny,self).__init__(expr) -# #~ self.leaveWhitespace() -# self.skipWhitespace = False # do NOT use self.leaveWhitespace(), don't want to propagate to exprs -# self.mayReturnEmpty = True -# self.errmsg = "Found unwanted token, "+_ustr(self.expr) -# -# def parseImpl( self, instring, loc, doActions=True ): -# try: -# self.expr.tryParse( instring, loc ) -# except (ParseException,IndexError): -# pass -# else: -# #~ raise ParseException(instring, loc, self.errmsg ) -# exc = self.myException -# exc.loc = loc -# exc.pstr = instring -# raise exc -# return loc, [] -# -# def __str__( self ): -# if hasattr(self,"name"): -# return self.name -# -# if self.strRepr is None: -# self.strRepr = "~{" + _ustr(self.expr) + "}" -# -# return self.strRepr -# -# -# class ZeroOrMore(ParseElementEnhance): -# """Optional repetition of zero or more of the given expression.""" -# def __init__( self, expr ): -# super(ZeroOrMore,self).__init__(expr) -# self.mayReturnEmpty = True -# -# def parseImpl( self, instring, loc, doActions=True ): -# tokens = [] -# try: -# loc, tokens = self.expr._parse( instring, loc, doActions, callPreParse=False ) -# hasIgnoreExprs = ( len(self.ignoreExprs) > 0 ) -# while 1: -# if hasIgnoreExprs: -# preloc = self._skipIgnorables( instring, loc ) -# else: -# preloc = loc -# loc, tmptokens = self.expr._parse( instring, preloc, doActions ) -# if tmptokens or tmptokens.keys(): -# tokens += tmptokens -# except (ParseException,IndexError): -# pass -# -# return loc, tokens -# -# def __str__( self ): -# if hasattr(self,"name"): -# return self.name -# -# if self.strRepr is None: -# self.strRepr = "[" + _ustr(self.expr) + "]..." -# -# return self.strRepr -# -# def setResultsName( self, name, listAllMatches=False ): -# ret = super(ZeroOrMore,self).setResultsName(name,listAllMatches) -# ret.saveAsList = True -# return ret -# -# -# class OneOrMore(ParseElementEnhance): -# """Repetition of one or more of the given expression.""" -# def parseImpl( self, instring, loc, doActions=True ): -# # must be at least one -# loc, tokens = self.expr._parse( instring, loc, doActions, callPreParse=False ) -# try: -# hasIgnoreExprs = ( len(self.ignoreExprs) > 0 ) -# while 1: -# if hasIgnoreExprs: -# preloc = self._skipIgnorables( instring, loc ) -# else: -# preloc = loc -# loc, tmptokens = self.expr._parse( instring, preloc, doActions ) -# if tmptokens or tmptokens.keys(): -# tokens += tmptokens -# except (ParseException,IndexError): -# pass -# -# return loc, tokens -# -# def __str__( self ): -# if hasattr(self,"name"): -# return self.name -# -# if self.strRepr is None: -# self.strRepr = "{" + _ustr(self.expr) + "}..." -# -# return self.strRepr -# -# def setResultsName( self, name, listAllMatches=False ): -# ret = super(OneOrMore,self).setResultsName(name,listAllMatches) -# ret.saveAsList = True -# return ret -# -# class _NullToken(object): -# def __bool__(self): -# return False -# __nonzero__ = __bool__ -# def __str__(self): -# return "" -# -# _optionalNotMatched = _NullToken() -# class Optional(ParseElementEnhance): -# """Optional matching of the given expression. -# A default return string can also be specified, if the optional expression -# is not found. -# """ -# def __init__( self, exprs, default=_optionalNotMatched ): -# super(Optional,self).__init__( exprs, savelist=False ) -# self.defaultValue = default -# self.mayReturnEmpty = True -# -# def parseImpl( self, instring, loc, doActions=True ): -# try: -# loc, tokens = self.expr._parse( instring, loc, doActions, callPreParse=False ) -# except (ParseException,IndexError): -# if self.defaultValue is not _optionalNotMatched: -# if self.expr.resultsName: -# tokens = ParseResults([ self.defaultValue ]) -# tokens[self.expr.resultsName] = self.defaultValue -# else: -# tokens = [ self.defaultValue ] -# else: -# tokens = [] -# return loc, tokens -# -# def __str__( self ): -# if hasattr(self,"name"): -# return self.name -# -# if self.strRepr is None: -# self.strRepr = "[" + _ustr(self.expr) + "]" -# -# return self.strRepr -# -# -# class SkipTo(ParseElementEnhance): -# """Token for skipping over all undefined text until the matched expression is found. -# If C{include} is set to true, the matched expression is also parsed (the skipped text -# and matched expression are returned as a 2-element list). The C{ignore} -# argument is used to define grammars (typically quoted strings and comments) that -# might contain false matches. -# """ -# def __init__( self, other, include=False, ignore=None, failOn=None ): -# super( SkipTo, self ).__init__( other ) -# self.ignoreExpr = ignore -# self.mayReturnEmpty = True -# self.mayIndexError = False -# self.includeMatch = include -# self.asList = False -# if failOn is not None and isinstance(failOn, basestring): -# self.failOn = Literal(failOn) -# else: -# self.failOn = failOn -# self.errmsg = "No match found for "+_ustr(self.expr) -# -# def parseImpl( self, instring, loc, doActions=True ): -# startLoc = loc -# instrlen = len(instring) -# expr = self.expr -# failParse = False -# while loc <= instrlen: -# try: -# if self.failOn: -# try: -# self.failOn.tryParse(instring, loc) -# except ParseBaseException: -# pass -# else: -# failParse = True -# raise ParseException(instring, loc, "Found expression " + str(self.failOn)) -# failParse = False -# if self.ignoreExpr is not None: -# while 1: -# try: -# loc = self.ignoreExpr.tryParse(instring,loc) -# # print "found ignoreExpr, advance to", loc -# except ParseBaseException: -# break -# expr._parse( instring, loc, doActions=False, callPreParse=False ) -# skipText = instring[startLoc:loc] -# if self.includeMatch: -# loc,mat = expr._parse(instring,loc,doActions,callPreParse=False) -# if mat: -# skipRes = ParseResults( skipText ) -# skipRes += mat -# return loc, [ skipRes ] -# else: -# return loc, [ skipText ] -# else: -# return loc, [ skipText ] -# except (ParseException,IndexError): -# if failParse: -# raise -# else: -# loc += 1 -# exc = self.myException -# exc.loc = loc -# exc.pstr = instring -# raise exc -# -# class Forward(ParseElementEnhance): -# """Forward declaration of an expression to be defined later - -# used for recursive grammars, such as algebraic infix notation. -# When the expression is known, it is assigned to the C{Forward} variable using the '<<' operator. -# -# Note: take care when assigning to C{Forward} not to overlook precedence of operators. -# Specifically, '|' has a lower precedence than '<<', so that:: -# fwdExpr << a | b | c -# will actually be evaluated as:: -# (fwdExpr << a) | b | c -# thereby leaving b and c out as parseable alternatives. It is recommended that you -# explicitly group the values inserted into the C{Forward}:: -# fwdExpr << (a | b | c) -# Converting to use the '<<=' operator instead will avoid this problem. -# """ -# def __init__( self, other=None ): -# super(Forward,self).__init__( other, savelist=False ) -# -# def __lshift__( self, other ): -# if isinstance( other, basestring ): -# other = ParserElement.literalStringClass(other) -# self.expr = other -# self.mayReturnEmpty = other.mayReturnEmpty -# self.strRepr = None -# self.mayIndexError = self.expr.mayIndexError -# self.mayReturnEmpty = self.expr.mayReturnEmpty -# self.setWhitespaceChars( self.expr.whiteChars ) -# self.skipWhitespace = self.expr.skipWhitespace -# self.saveAsList = self.expr.saveAsList -# self.ignoreExprs.extend(self.expr.ignoreExprs) -# return None -# __ilshift__ = __lshift__ -# -# def leaveWhitespace( self ): -# self.skipWhitespace = False -# return self -# -# def streamline( self ): -# if not self.streamlined: -# self.streamlined = True -# if self.expr is not None: -# self.expr.streamline() -# return self -# -# def validate( self, validateTrace=[] ): -# if self not in validateTrace: -# tmp = validateTrace[:]+[self] -# if self.expr is not None: -# self.expr.validate(tmp) -# self.checkRecursion([]) -# -# def __str__( self ): -# if hasattr(self,"name"): -# return self.name -# -# self._revertClass = self.__class__ -# self.__class__ = _ForwardNoRecurse -# try: -# if self.expr is not None: -# retString = _ustr(self.expr) -# else: -# retString = "None" -# finally: -# self.__class__ = self._revertClass -# return self.__class__.__name__ + ": " + retString -# -# def copy(self): -# if self.expr is not None: -# return super(Forward,self).copy() -# else: -# ret = Forward() -# ret << self -# return ret -# -# class _ForwardNoRecurse(Forward): -# def __str__( self ): -# return "..." -# -# class TokenConverter(ParseElementEnhance): -# """Abstract subclass of C{ParseExpression}, for converting parsed results.""" -# def __init__( self, expr, savelist=False ): -# super(TokenConverter,self).__init__( expr )#, savelist ) -# self.saveAsList = False -# -# class Upcase(TokenConverter): -# """Converter to upper case all matching tokens.""" -# def __init__(self, *args): -# super(Upcase,self).__init__(*args) -# warnings.warn("Upcase class is deprecated, use upcaseTokens parse action instead", -# DeprecationWarning,stacklevel=2) -# -# def postParse( self, instring, loc, tokenlist ): -# return list(map( str.upper, tokenlist )) -# -# -# class Combine(TokenConverter): -# """Converter to concatenate all matching tokens to a single string. -# By default, the matching patterns must also be contiguous in the input string; -# this can be disabled by specifying C{'adjacent=False'} in the constructor. -# """ -# def __init__( self, expr, joinString="", adjacent=True ): -# super(Combine,self).__init__( expr ) -# # suppress whitespace-stripping in contained parse expressions, but re-enable it on the Combine itself -# if adjacent: -# self.leaveWhitespace() -# self.adjacent = adjacent -# self.skipWhitespace = True -# self.joinString = joinString -# self.callPreparse = True -# -# def ignore( self, other ): -# if self.adjacent: -# ParserElement.ignore(self, other) -# else: -# super( Combine, self).ignore( other ) -# return self -# -# def postParse( self, instring, loc, tokenlist ): -# retToks = tokenlist.copy() -# del retToks[:] -# retToks += ParseResults([ "".join(tokenlist._asStringList(self.joinString)) ], modal=self.modalResults) -# -# if self.resultsName and len(retToks.keys())>0: -# return [ retToks ] -# else: -# return retToks -# -# class Group(TokenConverter): -# """Converter to return the matched tokens as a list - useful for returning tokens of C{L{ZeroOrMore}} and C{L{OneOrMore}} expressions.""" -# def __init__( self, expr ): -# super(Group,self).__init__( expr ) -# self.saveAsList = True -# -# def postParse( self, instring, loc, tokenlist ): -# return [ tokenlist ] -# -# class Dict(TokenConverter): -# """Converter to return a repetitive expression as a list, but also as a dictionary. -# Each element can also be referenced using the first token in the expression as its key. -# Useful for tabular report scraping when the first column can be used as a item key. -# """ -# def __init__( self, exprs ): -# super(Dict,self).__init__( exprs ) -# self.saveAsList = True -# -# def postParse( self, instring, loc, tokenlist ): -# for i,tok in enumerate(tokenlist): -# if len(tok) == 0: -# continue -# ikey = tok[0] -# if isinstance(ikey,int): -# ikey = _ustr(tok[0]).strip() -# if len(tok)==1: -# tokenlist[ikey] = _ParseResultsWithOffset("",i) -# elif len(tok)==2 and not isinstance(tok[1],ParseResults): -# tokenlist[ikey] = _ParseResultsWithOffset(tok[1],i) -# else: -# dictvalue = tok.copy() #ParseResults(i) -# del dictvalue[0] -# if len(dictvalue)!= 1 or (isinstance(dictvalue,ParseResults) and dictvalue.keys()): -# tokenlist[ikey] = _ParseResultsWithOffset(dictvalue,i) -# else: -# tokenlist[ikey] = _ParseResultsWithOffset(dictvalue[0],i) -# -# if self.resultsName: -# return [ tokenlist ] -# else: -# return tokenlist -# -# -# class Suppress(TokenConverter): -# """Converter for ignoring the results of a parsed expression.""" -# def postParse( self, instring, loc, tokenlist ): -# return [] -# -# def suppress( self ): -# return self -# -# -# class OnlyOnce(object): -# """Wrapper for parse actions, to ensure they are only called once.""" -# def __init__(self, methodCall): -# self.callable = _trim_arity(methodCall) -# self.called = False -# def __call__(self,s,l,t): -# if not self.called: -# results = self.callable(s,l,t) -# self.called = True -# return results -# raise ParseException(s,l,"") -# def reset(self): -# self.called = False -# -# def traceParseAction(f): -# """Decorator for debugging parse actions.""" -# f = _trim_arity(f) -# def z(*paArgs): -# thisFunc = f.func_name -# s,l,t = paArgs[-3:] -# if len(paArgs)>3: -# thisFunc = paArgs[0].__class__.__name__ + '.' + thisFunc -# sys.stderr.write( ">>entering %s(line: '%s', %d, %s)\n" % (thisFunc,line(l,s),l,t) ) -# try: -# ret = f(*paArgs) -# except Exception, exc: -# sys.stderr.write( "<", "|".join( [ _escapeRegexChars(sym) for sym in symbols] )) -# try: -# if len(symbols)==len("".join(symbols)): -# return Regex( "[%s]" % "".join( [ _escapeRegexRangeChars(sym) for sym in symbols] ) ) -# else: -# return Regex( "|".join( [ re.escape(sym) for sym in symbols] ) ) -# except: -# warnings.warn("Exception creating Regex for oneOf, building MatchFirst", -# SyntaxWarning, stacklevel=2) -# -# -# # last resort, just use MatchFirst -# return MatchFirst( [ parseElementClass(sym) for sym in symbols ] ) -# -# def dictOf( key, value ): -# """Helper to easily and clearly define a dictionary by specifying the respective patterns -# for the key and value. Takes care of defining the C{L{Dict}}, C{L{ZeroOrMore}}, and C{L{Group}} tokens -# in the proper order. The key pattern can include delimiting markers or punctuation, -# as long as they are suppressed, thereby leaving the significant key text. The value -# pattern can include named results, so that the C{Dict} results can include named token -# fields. -# """ -# return Dict( ZeroOrMore( Group ( key + value ) ) ) -# -# def originalTextFor(expr, asString=True): -# """Helper to return the original, untokenized text for a given expression. Useful to -# restore the parsed fields of an HTML start tag into the raw tag text itself, or to -# revert separate tokens with intervening whitespace back to the original matching -# input text. Simpler to use than the parse action C{L{keepOriginalText}}, and does not -# require the inspect module to chase up the call stack. By default, returns a -# string containing the original parsed text. -# -# If the optional C{asString} argument is passed as C{False}, then the return value is a -# C{L{ParseResults}} containing any results names that were originally matched, and a -# single token containing the original matched text from the input string. So if -# the expression passed to C{L{originalTextFor}} contains expressions with defined -# results names, you must set C{asString} to C{False} if you want to preserve those -# results name values.""" -# locMarker = Empty().setParseAction(lambda s,loc,t: loc) -# endlocMarker = locMarker.copy() -# endlocMarker.callPreparse = False -# matchExpr = locMarker("_original_start") + expr + endlocMarker("_original_end") -# if asString: -# extractText = lambda s,l,t: s[t._original_start:t._original_end] -# else: -# def extractText(s,l,t): -# del t[:] -# t.insert(0, s[t._original_start:t._original_end]) -# del t["_original_start"] -# del t["_original_end"] -# matchExpr.setParseAction(extractText) -# return matchExpr -# -# def ungroup(expr): -# """Helper to undo pyparsing's default grouping of And expressions, even -# if all but one are non-empty.""" -# return TokenConverter(expr).setParseAction(lambda t:t[0]) -# -# # convenience constants for positional expressions -# empty = Empty().setName("empty") -# lineStart = LineStart().setName("lineStart") -# lineEnd = LineEnd().setName("lineEnd") -# stringStart = StringStart().setName("stringStart") -# stringEnd = StringEnd().setName("stringEnd") -# -# _escapedPunc = Word( _bslash, r"\[]-*.$+^?()~ ", exact=2 ).setParseAction(lambda s,l,t:t[0][1]) -# _printables_less_backslash = "".join([ c for c in printables if c not in r"\]" ]) -# _escapedHexChar = Regex(r"\\0?[xX][0-9a-fA-F]+").setParseAction(lambda s,l,t:unichr(int(t[0].lstrip(r'\0x'),16))) -# _escapedOctChar = Regex(r"\\0[0-7]+").setParseAction(lambda s,l,t:unichr(int(t[0][1:],8))) -# _singleChar = _escapedPunc | _escapedHexChar | _escapedOctChar | Word(_printables_less_backslash,exact=1) -# _charRange = Group(_singleChar + Suppress("-") + _singleChar) -# _reBracketExpr = Literal("[") + Optional("^").setResultsName("negate") + Group( OneOrMore( _charRange | _singleChar ) ).setResultsName("body") + "]" -# -# _expanded = lambda p: (isinstance(p,ParseResults) and ''.join([ unichr(c) for c in range(ord(p[0]),ord(p[1])+1) ]) or p) -# -# def srange(s): -# r"""Helper to easily define string ranges for use in Word construction. Borrows -# syntax from regexp '[]' string range definitions:: -# srange("[0-9]") -> "0123456789" -# srange("[a-z]") -> "abcdefghijklmnopqrstuvwxyz" -# srange("[a-z$_]") -> "abcdefghijklmnopqrstuvwxyz$_" -# The input string must be enclosed in []'s, and the returned string is the expanded -# character set joined into a single string. -# The values enclosed in the []'s may be:: -# a single character -# an escaped character with a leading backslash (such as \- or \]) -# an escaped hex character with a leading '\x' (\x21, which is a '!' character) -# (\0x## is also supported for backwards compatibility) -# an escaped octal character with a leading '\0' (\041, which is a '!' character) -# a range of any of the above, separated by a dash ('a-z', etc.) -# any combination of the above ('aeiouy', 'a-zA-Z0-9_$', etc.) -# """ -# try: -# return "".join([_expanded(part) for part in _reBracketExpr.parseString(s).body]) -# except: -# return "" -# -# def matchOnlyAtCol(n): -# """Helper method for defining parse actions that require matching at a specific -# column in the input text. -# """ -# def verifyCol(strg,locn,toks): -# if col(locn,strg) != n: -# raise ParseException(strg,locn,"matched token not at column %d" % n) -# return verifyCol -# -# def replaceWith(replStr): -# """Helper method for common parse actions that simply return a literal value. Especially -# useful when used with C{L{transformString}()}. -# """ -# def _replFunc(*args): -# return [replStr] -# return _replFunc -# -# def removeQuotes(s,l,t): -# """Helper parse action for removing quotation marks from parsed quoted strings. -# To use, add this parse action to quoted string using:: -# quotedString.setParseAction( removeQuotes ) -# """ -# return t[0][1:-1] -# -# def upcaseTokens(s,l,t): -# """Helper parse action to convert tokens to upper case.""" -# return [ tt.upper() for tt in map(_ustr,t) ] -# -# def downcaseTokens(s,l,t): -# """Helper parse action to convert tokens to lower case.""" -# return [ tt.lower() for tt in map(_ustr,t) ] -# -# def keepOriginalText(s,startLoc,t): -# """DEPRECATED - use new helper method C{L{originalTextFor}}. -# Helper parse action to preserve original parsed text, -# overriding any nested parse actions.""" -# try: -# endloc = getTokensEndLoc() -# except ParseException: -# raise ParseFatalException("incorrect usage of keepOriginalText - may only be called as a parse action") -# del t[:] -# t += ParseResults(s[startLoc:endloc]) -# return t -# -# def getTokensEndLoc(): -# """Method to be called from within a parse action to determine the end -# location of the parsed tokens.""" -# import inspect -# fstack = inspect.stack() -# try: -# # search up the stack (through intervening argument normalizers) for correct calling routine -# for f in fstack[2:]: -# if f[3] == "_parseNoCache": -# endloc = f[0].f_locals["loc"] -# return endloc -# else: -# raise ParseFatalException("incorrect usage of getTokensEndLoc - may only be called from within a parse action") -# finally: -# del fstack -# -# def _makeTags(tagStr, xml): -# """Internal helper to construct opening and closing tag expressions, given a tag name""" -# if isinstance(tagStr,basestring): -# resname = tagStr -# tagStr = Keyword(tagStr, caseless=not xml) -# else: -# resname = tagStr.name -# -# tagAttrName = Word(alphas,alphanums+"_-:") -# if (xml): -# tagAttrValue = dblQuotedString.copy().setParseAction( removeQuotes ) -# openTag = Suppress("<") + tagStr("tag") + \ -# Dict(ZeroOrMore(Group( tagAttrName + Suppress("=") + tagAttrValue ))) + \ -# Optional("/",default=[False]).setResultsName("empty").setParseAction(lambda s,l,t:t[0]=='/') + Suppress(">") -# else: -# printablesLessRAbrack = "".join( [ c for c in printables if c not in ">" ] ) -# tagAttrValue = quotedString.copy().setParseAction( removeQuotes ) | Word(printablesLessRAbrack) -# openTag = Suppress("<") + tagStr("tag") + \ -# Dict(ZeroOrMore(Group( tagAttrName.setParseAction(downcaseTokens) + \ -# Optional( Suppress("=") + tagAttrValue ) ))) + \ -# Optional("/",default=[False]).setResultsName("empty").setParseAction(lambda s,l,t:t[0]=='/') + Suppress(">") -# closeTag = Combine(_L("") -# -# openTag = openTag.setResultsName("start"+"".join(resname.replace(":"," ").title().split())).setName("<%s>" % tagStr) -# closeTag = closeTag.setResultsName("end"+"".join(resname.replace(":"," ").title().split())).setName("" % tagStr) -# openTag.tag = resname -# closeTag.tag = resname -# return openTag, closeTag -# -# def makeHTMLTags(tagStr): -# """Helper to construct opening and closing tag expressions for HTML, given a tag name""" -# return _makeTags( tagStr, False ) -# -# def makeXMLTags(tagStr): -# """Helper to construct opening and closing tag expressions for XML, given a tag name""" -# return _makeTags( tagStr, True ) -# -# def withAttribute(*args,**attrDict): -# """Helper to create a validating parse action to be used with start tags created -# with C{L{makeXMLTags}} or C{L{makeHTMLTags}}. Use C{withAttribute} to qualify a starting tag -# with a required attribute value, to avoid false matches on common tags such as -# C{} or C{
}. -# -# Call C{withAttribute} with a series of attribute names and values. Specify the list -# of filter attributes names and values as: -# - keyword arguments, as in C{(align="right")}, or -# - as an explicit dict with C{**} operator, when an attribute name is also a Python -# reserved word, as in C{**{"class":"Customer", "align":"right"}} -# - a list of name-value tuples, as in ( ("ns1:class", "Customer"), ("ns2:align","right") ) -# For attribute names with a namespace prefix, you must use the second form. Attribute -# names are matched insensitive to upper/lower case. -# -# To verify that the attribute exists, but without specifying a value, pass -# C{withAttribute.ANY_VALUE} as the value. -# """ -# if args: -# attrs = args[:] -# else: -# attrs = attrDict.items() -# attrs = [(k,v) for k,v in attrs] -# def pa(s,l,tokens): -# for attrName,attrValue in attrs: -# if attrName not in tokens: -# raise ParseException(s,l,"no matching attribute " + attrName) -# if attrValue != withAttribute.ANY_VALUE and tokens[attrName] != attrValue: -# raise ParseException(s,l,"attribute '%s' has value '%s', must be '%s'" % -# (attrName, tokens[attrName], attrValue)) -# return pa -# withAttribute.ANY_VALUE = object() -# -# opAssoc = _Constants() -# opAssoc.LEFT = object() -# opAssoc.RIGHT = object() -# -# def infixNotation( baseExpr, opList, lpar=Suppress('('), rpar=Suppress(')') ): -# """Helper method for constructing grammars of expressions made up of -# operators working in a precedence hierarchy. Operators may be unary or -# binary, left- or right-associative. Parse actions can also be attached -# to operator expressions. -# -# Parameters: -# - baseExpr - expression representing the most basic element for the nested -# - opList - list of tuples, one for each operator precedence level in the -# expression grammar; each tuple is of the form -# (opExpr, numTerms, rightLeftAssoc, parseAction), where: -# - opExpr is the pyparsing expression for the operator; -# may also be a string, which will be converted to a Literal; -# if numTerms is 3, opExpr is a tuple of two expressions, for the -# two operators separating the 3 terms -# - numTerms is the number of terms for this operator (must -# be 1, 2, or 3) -# - rightLeftAssoc is the indicator whether the operator is -# right or left associative, using the pyparsing-defined -# constants C{opAssoc.RIGHT} and C{opAssoc.LEFT}. -# - parseAction is the parse action to be associated with -# expressions matching this operator expression (the -# parse action tuple member may be omitted) -# - lpar - expression for matching left-parentheses (default=Suppress('(')) -# - rpar - expression for matching right-parentheses (default=Suppress(')')) -# """ -# ret = Forward() -# lastExpr = baseExpr | ( lpar + ret + rpar ) -# for i,operDef in enumerate(opList): -# opExpr,arity,rightLeftAssoc,pa = (operDef + (None,))[:4] -# if arity == 3: -# if opExpr is None or len(opExpr) != 2: -# raise ValueError("if numterms=3, opExpr must be a tuple or list of two expressions") -# opExpr1, opExpr2 = opExpr -# thisExpr = Forward()#.setName("expr%d" % i) -# if rightLeftAssoc == opAssoc.LEFT: -# if arity == 1: -# matchExpr = FollowedBy(lastExpr + opExpr) + Group( lastExpr + OneOrMore( opExpr ) ) -# elif arity == 2: -# if opExpr is not None: -# matchExpr = FollowedBy(lastExpr + opExpr + lastExpr) + Group( lastExpr + OneOrMore( opExpr + lastExpr ) ) -# else: -# matchExpr = FollowedBy(lastExpr+lastExpr) + Group( lastExpr + OneOrMore(lastExpr) ) -# elif arity == 3: -# matchExpr = FollowedBy(lastExpr + opExpr1 + lastExpr + opExpr2 + lastExpr) + \ -# Group( lastExpr + opExpr1 + lastExpr + opExpr2 + lastExpr ) -# else: -# raise ValueError("operator must be unary (1), binary (2), or ternary (3)") -# elif rightLeftAssoc == opAssoc.RIGHT: -# if arity == 1: -# # try to avoid LR with this extra test -# if not isinstance(opExpr, Optional): -# opExpr = Optional(opExpr) -# matchExpr = FollowedBy(opExpr.expr + thisExpr) + Group( opExpr + thisExpr ) -# elif arity == 2: -# if opExpr is not None: -# matchExpr = FollowedBy(lastExpr + opExpr + thisExpr) + Group( lastExpr + OneOrMore( opExpr + thisExpr ) ) -# else: -# matchExpr = FollowedBy(lastExpr + thisExpr) + Group( lastExpr + OneOrMore( thisExpr ) ) -# elif arity == 3: -# matchExpr = FollowedBy(lastExpr + opExpr1 + thisExpr + opExpr2 + thisExpr) + \ -# Group( lastExpr + opExpr1 + thisExpr + opExpr2 + thisExpr ) -# else: -# raise ValueError("operator must be unary (1), binary (2), or ternary (3)") -# else: -# raise ValueError("operator must indicate right or left associativity") -# if pa: -# matchExpr.setParseAction( pa ) -# thisExpr << ( matchExpr | lastExpr ) -# lastExpr = thisExpr -# ret << lastExpr -# return ret -# operatorPrecedence = infixNotation -# -# dblQuotedString = Regex(r'"(?:[^"\n\r\\]|(?:"")|(?:\\x[0-9a-fA-F]+)|(?:\\.))*"').setName("string enclosed in double quotes") -# sglQuotedString = Regex(r"'(?:[^'\n\r\\]|(?:'')|(?:\\x[0-9a-fA-F]+)|(?:\\.))*'").setName("string enclosed in single quotes") -# quotedString = Regex(r'''(?:"(?:[^"\n\r\\]|(?:"")|(?:\\x[0-9a-fA-F]+)|(?:\\.))*")|(?:'(?:[^'\n\r\\]|(?:'')|(?:\\x[0-9a-fA-F]+)|(?:\\.))*')''').setName("quotedString using single or double quotes") -# unicodeString = Combine(_L('u') + quotedString.copy()) -# -# def nestedExpr(opener="(", closer=")", content=None, ignoreExpr=quotedString.copy()): -# """Helper method for defining nested lists enclosed in opening and closing -# delimiters ("(" and ")" are the default). -# -# Parameters: -# - opener - opening character for a nested list (default="("); can also be a pyparsing expression -# - closer - closing character for a nested list (default=")"); can also be a pyparsing expression -# - content - expression for items within the nested lists (default=None) -# - ignoreExpr - expression for ignoring opening and closing delimiters (default=quotedString) -# -# If an expression is not provided for the content argument, the nested -# expression will capture all whitespace-delimited content between delimiters -# as a list of separate values. -# -# Use the C{ignoreExpr} argument to define expressions that may contain -# opening or closing characters that should not be treated as opening -# or closing characters for nesting, such as quotedString or a comment -# expression. Specify multiple expressions using an C{L{Or}} or C{L{MatchFirst}}. -# The default is L{quotedString}, but if no expressions are to be ignored, -# then pass C{None} for this argument. -# """ -# if opener == closer: -# raise ValueError("opening and closing strings cannot be the same") -# if content is None: -# if isinstance(opener,basestring) and isinstance(closer,basestring): -# if len(opener) == 1 and len(closer)==1: -# if ignoreExpr is not None: -# content = (Combine(OneOrMore(~ignoreExpr + -# CharsNotIn(opener+closer+ParserElement.DEFAULT_WHITE_CHARS,exact=1)) -# ).setParseAction(lambda t:t[0].strip())) -# else: -# content = (empty.copy()+CharsNotIn(opener+closer+ParserElement.DEFAULT_WHITE_CHARS -# ).setParseAction(lambda t:t[0].strip())) -# else: -# if ignoreExpr is not None: -# content = (Combine(OneOrMore(~ignoreExpr + -# ~Literal(opener) + ~Literal(closer) + -# CharsNotIn(ParserElement.DEFAULT_WHITE_CHARS,exact=1)) -# ).setParseAction(lambda t:t[0].strip())) -# else: -# content = (Combine(OneOrMore(~Literal(opener) + ~Literal(closer) + -# CharsNotIn(ParserElement.DEFAULT_WHITE_CHARS,exact=1)) -# ).setParseAction(lambda t:t[0].strip())) -# else: -# raise ValueError("opening and closing arguments must be strings if no content expression is given") -# ret = Forward() -# if ignoreExpr is not None: -# ret << Group( Suppress(opener) + ZeroOrMore( ignoreExpr | ret | content ) + Suppress(closer) ) -# else: -# ret << Group( Suppress(opener) + ZeroOrMore( ret | content ) + Suppress(closer) ) -# return ret -# -# def indentedBlock(blockStatementExpr, indentStack, indent=True): -# """Helper method for defining space-delimited indentation blocks, such as -# those used to define block statements in Python source code. -# -# Parameters: -# - blockStatementExpr - expression defining syntax of statement that -# is repeated within the indented block -# - indentStack - list created by caller to manage indentation stack -# (multiple statementWithIndentedBlock expressions within a single grammar -# should share a common indentStack) -# - indent - boolean indicating whether block must be indented beyond the -# the current level; set to False for block of left-most statements -# (default=True) -# -# A valid block must contain at least one C{blockStatement}. -# """ -# def checkPeerIndent(s,l,t): -# if l >= len(s): return -# curCol = col(l,s) -# if curCol != indentStack[-1]: -# if curCol > indentStack[-1]: -# raise ParseFatalException(s,l,"illegal nesting") -# raise ParseException(s,l,"not a peer entry") -# -# def checkSubIndent(s,l,t): -# curCol = col(l,s) -# if curCol > indentStack[-1]: -# indentStack.append( curCol ) -# else: -# raise ParseException(s,l,"not a subentry") -# -# def checkUnindent(s,l,t): -# if l >= len(s): return -# curCol = col(l,s) -# if not(indentStack and curCol < indentStack[-1] and curCol <= indentStack[-2]): -# raise ParseException(s,l,"not an unindent") -# indentStack.pop() -# -# NL = OneOrMore(LineEnd().setWhitespaceChars("\t ").suppress()) -# INDENT = Empty() + Empty().setParseAction(checkSubIndent) -# PEER = Empty().setParseAction(checkPeerIndent) -# UNDENT = Empty().setParseAction(checkUnindent) -# if indent: -# smExpr = Group( Optional(NL) + -# #~ FollowedBy(blockStatementExpr) + -# INDENT + (OneOrMore( PEER + Group(blockStatementExpr) + Optional(NL) )) + UNDENT) -# else: -# smExpr = Group( Optional(NL) + -# (OneOrMore( PEER + Group(blockStatementExpr) + Optional(NL) )) ) -# blockStatementExpr.ignore(_bslash + LineEnd()) -# return smExpr -# -# alphas8bit = srange(r"[\0xc0-\0xd6\0xd8-\0xf6\0xf8-\0xff]") -# punc8bit = srange(r"[\0xa1-\0xbf\0xd7\0xf7]") -# -# anyOpenTag,anyCloseTag = makeHTMLTags(Word(alphas,alphanums+"_:")) -# commonHTMLEntity = Combine(_L("&") + oneOf("gt lt amp nbsp quot").setResultsName("entity") +";").streamline() -# _htmlEntityMap = dict(zip("gt lt amp nbsp quot".split(),'><& "')) -# replaceHTMLEntity = lambda t : t.entity in _htmlEntityMap and _htmlEntityMap[t.entity] or None -# -# # it's easy to get these comment structures wrong - they're very common, so may as well make them available -# cStyleComment = Regex(r"/\*(?:[^*]*\*+)+?/").setName("C style comment") -# -# htmlComment = Regex(r"") -# restOfLine = Regex(r".*").leaveWhitespace() -# dblSlashComment = Regex(r"\/\/(\\\n|.)*").setName("// comment") -# cppStyleComment = Regex(r"/(?:\*(?:[^*]*\*+)+?/|/[^\n]*(?:\n[^\n]*)*?(?:(?" + str(tokenlist)) -# print ("tokens = " + str(tokens)) -# print ("tokens.columns = " + str(tokens.columns)) -# print ("tokens.tables = " + str(tokens.tables)) -# print (tokens.asXML("SQL",True)) -# except ParseBaseException, err: -# print (teststring + "->") -# print (err.line) -# print (" "*(err.column-1) + "^") -# print (err) -# print() -# -# selectToken = CaselessLiteral( "select" ) -# fromToken = CaselessLiteral( "from" ) -# -# ident = Word( alphas, alphanums + "_$" ) -# columnName = delimitedList( ident, ".", combine=True ).setParseAction( upcaseTokens ) -# columnNameList = Group( delimitedList( columnName ) )#.setName("columns") -# tableName = delimitedList( ident, ".", combine=True ).setParseAction( upcaseTokens ) -# tableNameList = Group( delimitedList( tableName ) )#.setName("tables") -# simpleSQL = ( selectToken + \ -# ( '*' | columnNameList ).setResultsName( "columns" ) + \ -# fromToken + \ -# tableNameList.setResultsName( "tables" ) ) -# -# test( "SELECT * from XYZZY, ABC" ) -# test( "select * from SYS.XYZZY" ) -# test( "Select A from Sys.dual" ) -# test( "Select AA,BB,CC from Sys.dual" ) -# test( "Select A, B, C from Sys.dual" ) -# test( "Select A, B, C from Sys.dual" ) -# test( "Xelect A, B, C from Sys.dual" ) -# test( "Select A, B, C frox Sys.dual" ) -# test( "Select" ) -# test( "Select ^^^ frox Sys.dual" ) -# test( "Select A, B, C from Sys.dual, Table2 " ) diff --git a/src/calibre/utils/search_query_parser.py b/src/calibre/utils/search_query_parser.py index 29573cb9c9..cc90e53bac 100644 --- a/src/calibre/utils/search_query_parser.py +++ b/src/calibre/utils/search_query_parser.py @@ -18,7 +18,6 @@ If this module is run, it will perform a series of unit tests. import sys, operator, weakref, re -from calibre.utils.pyparsing import ParseException from calibre.constants import preferred_encoding from calibre.utils.icu import sort_key from calibre import prints @@ -197,10 +196,10 @@ class Parser(object): self.advance() res = self.or_expression() if self.token(advance=True) != ')': - raise ParseException('missing )') + raise ParseException(_('missing )')) return res if self.token_type() not in [ self.WORD, self.QUOTED_WORD ]: - raise ParseException('Invalid syntax. Expected a lookup name or a word') + raise ParseException(_('Invalid syntax. Expected a lookup name or a word')) return self.base_token() @@ -231,6 +230,14 @@ class Parser(object): return ['token', 'all', ':'.join(words)] +class ParseException(Exception): + + @property + def msg(self): + if len(self.args) > 0: + return self.args[0] + return "" + class SearchQueryParser(object): ''' Parses a search query. @@ -295,7 +302,7 @@ class SearchQueryParser(object): try: res = self.parser.parse(query, self.locations) except RuntimeError: - raise ParseException('Failed to parse query, recursion limit reached: %s'%repr(query)) + raise ParseException(_('Failed to parse query, recursion limit reached: %s')%repr(query)) if candidates is None: candidates = self.universal_set() t = self.evaluate(res, candidates) @@ -339,12 +346,16 @@ class SearchQueryParser(object): query = query[1:] try: if query in self.searches_seen: - raise ParseException(query, len(query), 'undefined saved search', self) + raise ParseException(_('Recursive saved search: {0}').format(query)) if self.recurse_level > 5: self.searches_seen.add(query) return self._parse(saved_searches().lookup(query), candidates) + except ParseException as e: + raise e except: # convert all exceptions (e.g., missing key) to a parse error - raise ParseException(query, len(query), 'undefined saved search', self) + import traceback + traceback.print_exc() + raise ParseException(_('Unknown error in saved search: {0}').format(query)) return self._get_matches(location, query, candidates) def _get_matches(self, location, query, candidates): diff --git a/src/calibre/web/feeds/recipes/model.py b/src/calibre/web/feeds/recipes/model.py index 60b74585af..b5c123bd4f 100644 --- a/src/calibre/web/feeds/recipes/model.py +++ b/src/calibre/web/feeds/recipes/model.py @@ -19,7 +19,7 @@ from calibre.web.feeds.recipes.collection import \ SchedulerConfig, download_builtin_recipe, update_custom_recipe, \ add_custom_recipe, remove_custom_recipe, get_custom_recipe, \ get_builtin_recipe -from calibre.utils.pyparsing import ParseException +from calibre.utils.search_query_parser import ParseException class NewsTreeItem(object): From 3ee801d1be95216f47705bdc06ed6275b186f157 Mon Sep 17 00:00:00 2001 From: Kovid Goyal Date: Sat, 20 Apr 2013 14:59:27 +0530 Subject: [PATCH 12/36] Voice of America by Krittika Goyal --- recipes/voice_of_america.recipe | 28 ++++++++++++++++++++++++++++ 1 file changed, 28 insertions(+) create mode 100644 recipes/voice_of_america.recipe diff --git a/recipes/voice_of_america.recipe b/recipes/voice_of_america.recipe new file mode 100644 index 0000000000..564a55bc94 --- /dev/null +++ b/recipes/voice_of_america.recipe @@ -0,0 +1,28 @@ +from calibre.web.feeds.news import BasicNewsRecipe +from calibre.ebooks.BeautifulSoup import BeautifulSoup + +class HindustanTimes(BasicNewsRecipe): + title = u'Voice of America' + language = 'en' + __author__ = 'Krittika Goyal' + oldest_article = 15 #days + max_articles_per_feed = 25 + #encoding = 'cp1252' + use_embedded_content = False + + no_stylesheets = True + auto_cleanup = True + + + feeds = [ +('All Zones', + 'http://learningenglish.voanews.com/rss/?count=20'), +('World', + 'http://learningenglish.voanews.com/rss/?count=20&zoneid=957'), +('USA', + 'http://learningenglish.voanews.com/rss/?count=20&zoneid=958'), +('Health', + 'http://learningenglish.voanews.com/rss/?count=20&zoneid=955'), + +] + From 01b125350dc881d348d9380fa699c9d31ef27754 Mon Sep 17 00:00:00 2001 From: Kovid Goyal Date: Sat, 20 Apr 2013 15:11:30 +0530 Subject: [PATCH 13/36] Allow importing of PArseException from pyparsing for backwards compatibility with plugins --- src/calibre/utils/pyparsing.py | 11 +++++++++++ 1 file changed, 11 insertions(+) create mode 100644 src/calibre/utils/pyparsing.py diff --git a/src/calibre/utils/pyparsing.py b/src/calibre/utils/pyparsing.py new file mode 100644 index 0000000000..8c3521f69f --- /dev/null +++ b/src/calibre/utils/pyparsing.py @@ -0,0 +1,11 @@ +#!/usr/bin/env python +# vim:fileencoding=utf-8 +from __future__ import (unicode_literals, division, absolute_import, + print_function) + +__license__ = 'GPL v3' +__copyright__ = '2013, Kovid Goyal ' + +# Dummy file for backwards compatibility with older plugins +from calibre.utils.search_query_parser import ParseException # noqa + From bf391cf726801950c12c35823e258f6347031ef2 Mon Sep 17 00:00:00 2001 From: Kovid Goyal Date: Sat, 20 Apr 2013 15:11:44 +0530 Subject: [PATCH 14/36] ... --- recipes/voice_of_america.recipe | 1 - 1 file changed, 1 deletion(-) diff --git a/recipes/voice_of_america.recipe b/recipes/voice_of_america.recipe index 564a55bc94..6fc90eba9d 100644 --- a/recipes/voice_of_america.recipe +++ b/recipes/voice_of_america.recipe @@ -1,5 +1,4 @@ from calibre.web.feeds.news import BasicNewsRecipe -from calibre.ebooks.BeautifulSoup import BeautifulSoup class HindustanTimes(BasicNewsRecipe): title = u'Voice of America' From 1dd6a3d9b77ab0a8e674b8a9af7c75c7061772a9 Mon Sep 17 00:00:00 2001 From: Kovid Goyal Date: Sat, 20 Apr 2013 16:38:49 +0530 Subject: [PATCH 15/36] Book polishing: Fix inserting cover into an epub with no cover could lead to incorrect guide entry if the opf is not at the root of the epub. Fixes #1167941 (Polish book - Update cover) --- src/calibre/ebooks/oeb/polish/cover.py | 16 +++++++++------- 1 file changed, 9 insertions(+), 7 deletions(-) diff --git a/src/calibre/ebooks/oeb/polish/cover.py b/src/calibre/ebooks/oeb/polish/cover.py index 01b9e25e59..5cee827d72 100644 --- a/src/calibre/ebooks/oeb/polish/cover.py +++ b/src/calibre/ebooks/oeb/polish/cover.py @@ -46,10 +46,11 @@ def is_raster_image(media_type): return media_type and media_type.lower() in { 'image/png', 'image/jpeg', 'image/jpg', 'image/gif'} -COVER_TYPES = { 'coverimagestandard', 'other.ms-coverimage-standard', - 'other.ms-titleimage-standard', 'other.ms-titleimage', - 'other.ms-coverimage', 'other.ms-thumbimage-standard', - 'other.ms-thumbimage', 'thumbimagestandard', 'cover'} +COVER_TYPES = { + 'coverimagestandard', 'other.ms-coverimage-standard', + 'other.ms-titleimage-standard', 'other.ms-titleimage', + 'other.ms-coverimage', 'other.ms-thumbimage-standard', + 'other.ms-thumbimage', 'thumbimagestandard', 'cover'} def find_cover_image(container): 'Find a raster image marked as a cover in the OPF' @@ -92,7 +93,8 @@ def find_cover_page(container): def find_cover_image_in_page(container, cover_page): root = container.parsed(cover_page) body = XPath('//h:body')(root) - if len(body) != 1: return + if len(body) != 1: + return body = body[0] images = [] for img in XPath('descendant::h:img[@src]|descendant::svg:svg/descendant::svg:image')(body): @@ -152,7 +154,7 @@ def create_epub_cover(container, cover_path): ar = 'xMidYMid meet' if keep_aspect else 'none' templ = CoverManager.SVG_TEMPLATE.replace('__ar__', ar) templ = templ.replace('__viewbox__', '0 0 %d %d'%(width, height)) - templ = templ.replace('__width__', str(width)) + templ = templ.replace('__width__', str(width)) templ = templ.replace('__height__', str(height)) titlepage_item = container.generate_item('titlepage.xhtml', id_prefix='titlepage') @@ -179,7 +181,7 @@ def create_epub_cover(container, cover_path): guide = container.opf_get_or_create('guide') container.insert_into_xml(guide, guide.makeelement( OPF('reference'), type='cover', title=_('Cover'), - href=container.name_to_href(titlepage))) + href=container.name_to_href(titlepage, base=container.opf_name))) metadata = container.opf_get_or_create('metadata') meta = metadata.makeelement(OPF('meta'), name='cover') meta.set('content', raster_cover_item.get('id')) From 4f3bf4296a1edf496947e7695faa8f01e7a7e7a0 Mon Sep 17 00:00:00 2001 From: Kovid Goyal Date: Sun, 21 Apr 2013 08:24:26 +0530 Subject: [PATCH 16/36] Fix #1171043 ([ENHANCE] Keyboard access to Restore Defaults) --- src/calibre/gui2/convert/single.py | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/src/calibre/gui2/convert/single.py b/src/calibre/gui2/convert/single.py index 469091162b..1a915288a8 100644 --- a/src/calibre/gui2/convert/single.py +++ b/src/calibre/gui2/convert/single.py @@ -75,7 +75,7 @@ class GroupModel(QAbstractListModel): def get_preferred_input_format_for_book(db, book_id): recs = load_specifics(db, book_id) if recs: - return recs.get('gui_preferred_input_format', None) + return recs.get('gui_preferred_input_format', None) def get_available_formats_for_book(db, book_id): available_formats = db.formats(book_id, index_is_id=True) @@ -147,6 +147,7 @@ class Config(ResizableDialog, Ui_Dialog): self.connect(self.groups, SIGNAL('entered(QModelIndex)'), self.show_group_help) rb = self.buttonBox.button(self.buttonBox.RestoreDefaults) + rb.setText(_('Restore &Defaults')) self.connect(rb, SIGNAL('clicked()'), self.restore_defaults) self.groups.setMouseTracking(True) geom = gprefs.get('convert_single_dialog_geom', None) @@ -188,7 +189,6 @@ class Config(ResizableDialog, Ui_Dialog): return cls(self.stack, self.plumber.get_option_by_name, self.plumber.get_option_help, self.db, self.book_id) - self.mw = widget_factory(MetadataWidget) self.setWindowTitle(_('Convert')+ ' ' + unicode(self.mw.title.text())) lf = widget_factory(LookAndFeelWidget) @@ -209,7 +209,8 @@ class Config(ResizableDialog, Ui_Dialog): self.plumber.get_option_help, self.db, self.book_id) while True: c = self.stack.currentWidget() - if not c: break + if not c: + break self.stack.removeWidget(c) widgets = [self.mw, lf, hw, ps, sd, toc, sr] @@ -234,7 +235,6 @@ class Config(ResizableDialog, Ui_Dialog): except: pass - def setup_input_output_formats(self, db, book_id, preferred_input_format, preferred_output_format): if preferred_output_format: From 6cd338ad41b5d850b9a465951fb6eeb3410a594a Mon Sep 17 00:00:00 2001 From: Kovid Goyal Date: Sun, 21 Apr 2013 08:44:54 +0530 Subject: [PATCH 17/36] PDF Output: Fix hyperlinks not working when converting an EPUB whose individual files have names with URL unsafe characters. Fixes #1169795 (Private bug) --- src/calibre/ebooks/pdf/render/links.py | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/src/calibre/ebooks/pdf/render/links.py b/src/calibre/ebooks/pdf/render/links.py index 97a6551dbd..c9d4d8d43c 100644 --- a/src/calibre/ebooks/pdf/render/links.py +++ b/src/calibre/ebooks/pdf/render/links.py @@ -51,7 +51,7 @@ class Links(object): for link in self.links: path, href, frag = link[0] page, rect = link[1:] - combined_path = os.path.abspath(os.path.join(os.path.dirname(path), *href.split('/'))) + combined_path = os.path.abspath(os.path.join(os.path.dirname(path), *unquote(href).split('/'))) is_local = not href or combined_path in self.anchors annot = Dictionary({ 'Type':Name('Annot'), 'Subtype':Name('Link'), From 6358ff4c412d9f487fe8ac769fb0ffb115790586 Mon Sep 17 00:00:00 2001 From: Kovid Goyal Date: Sun, 21 Apr 2013 08:53:00 +0530 Subject: [PATCH 18/36] Fix bug in Danish translation causing books with language Ingush being incorrectly translated as Engelsk --- setup/iso_639/da.po | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/setup/iso_639/da.po b/setup/iso_639/da.po index 716f4db0cd..fc6300ceb8 100644 --- a/setup/iso_639/da.po +++ b/setup/iso_639/da.po @@ -10253,7 +10253,7 @@ msgstr "" #. name for inh msgid "Ingush" -msgstr "Engelsk" +msgstr "Ingush" #. name for inj msgid "Inga; Jungle" From 81994d99c71013338eb4a8e3768807d4deffaa2e Mon Sep 17 00:00:00 2001 From: Kovid Goyal Date: Sun, 21 Apr 2013 15:43:08 +0530 Subject: [PATCH 19/36] ... --- src/calibre/gui2/preferences/adding.ui | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/src/calibre/gui2/preferences/adding.ui b/src/calibre/gui2/preferences/adding.ui index b98a476864..8b9b9c0cd1 100644 --- a/src/calibre/gui2/preferences/adding.ui +++ b/src/calibre/gui2/preferences/adding.ui @@ -164,7 +164,7 @@ Author matching is exact. - Ignore files with the following extensions when automatically adding + <b>Ignore</b> files with the following extensions when automatically adding true From d0791145c73dd6a4ebb84fc74a87cb93967eab82 Mon Sep 17 00:00:00 2001 From: John Schember Date: Sun, 21 Apr 2013 09:17:16 -0400 Subject: [PATCH 20/36] Store: Update Kobo program links. --- src/calibre/gui2/store/stores/kobo_plugin.py | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/src/calibre/gui2/store/stores/kobo_plugin.py b/src/calibre/gui2/store/stores/kobo_plugin.py index 44f4f4001c..62652ca855 100644 --- a/src/calibre/gui2/store/stores/kobo_plugin.py +++ b/src/calibre/gui2/store/stores/kobo_plugin.py @@ -1,7 +1,7 @@ # -*- coding: utf-8 -*- from __future__ import (unicode_literals, division, absolute_import, print_function) -store_version = 1 # Needed for dynamic plugin loading +store_version = 2 # Needed for dynamic plugin loading __license__ = 'GPL 3' __copyright__ = '2011, John Schember ' @@ -31,10 +31,10 @@ class KoboStore(BasicStoreConfig, StorePlugin): if random.randint(1, 10) in (1, 2, 3): pub_id = '0dsO3kDu/AU' - murl = 'http://click.linksynergy.com/fs-bin/click?id=%s&offerid=268429.4&type=3&subid=0' % pub_id + murl = 'http://click.linksynergy.com/fs-bin/click?id=%s&subid=&offerid=280046.1&type=10&tmpid=9310&RD_PARM1=http%%3A%%2F%%2Fkobo.com' % pub_id if detail_item: - purl = 'http://click.linksynergy.com/link?id=%s&offerid=268429&type=2&murl=%s' % (pub_id, urllib.quote_plus(detail_item)) + purl = 'http://click.linksynergy.com/link?id=%s&offerid=280046&type=2&murl=%s' % (pub_id, urllib.quote_plus(detail_item)) url = purl else: purl = None From 62b8af88a3526923f25c0d51f378184ed2570003 Mon Sep 17 00:00:00 2001 From: John Schember Date: Sun, 21 Apr 2013 09:28:37 -0400 Subject: [PATCH 21/36] Store: Remove affilate program from Google books because they are retiring the program. --- src/calibre/customize/builtins.py | 1 - .../gui2/store/stores/google_books_plugin.py | 22 ++----------------- 2 files changed, 2 insertions(+), 21 deletions(-) diff --git a/src/calibre/customize/builtins.py b/src/calibre/customize/builtins.py index d0a04dae26..baf32ea017 100644 --- a/src/calibre/customize/builtins.py +++ b/src/calibre/customize/builtins.py @@ -1448,7 +1448,6 @@ class StoreGoogleBooksStore(StoreBase): headquarters = 'US' formats = ['EPUB', 'PDF', 'TXT'] - affiliate = True class StoreGutenbergStore(StoreBase): name = 'Project Gutenberg' diff --git a/src/calibre/gui2/store/stores/google_books_plugin.py b/src/calibre/gui2/store/stores/google_books_plugin.py index f6f91fd81d..65a7ccdfb4 100644 --- a/src/calibre/gui2/store/stores/google_books_plugin.py +++ b/src/calibre/gui2/store/stores/google_books_plugin.py @@ -1,7 +1,7 @@ # -*- coding: utf-8 -*- from __future__ import (unicode_literals, division, absolute_import, print_function) -store_version = 1 # Needed for dynamic plugin loading +store_version = 2 # Needed for dynamic plugin loading __license__ = 'GPL 3' __copyright__ = '2011, John Schember ' @@ -25,25 +25,7 @@ from calibre.gui2.store.web_store_dialog import WebStoreDialog class GoogleBooksStore(BasicStoreConfig, StorePlugin): def open(self, parent=None, detail_item=None, external=False): - aff_id = { - 'lid': '41000000033185143', - 'pubid': '21000000000352219', - 'ganpub': 'k352219', - 'ganclk': 'GOOG_1335334761', - } - # Use Kovid's affiliate id 30% of the time. - if random.randint(1, 10) in (1, 2, 3): - aff_id = { - 'lid': '41000000031855266', - 'pubid': '21000000000352583', - 'ganpub': 'k352583', - 'ganclk': 'GOOG_1335335464', - } - - url = 'http://gan.doubleclick.net/gan_click?lid=%(lid)s&pubid=%(pubid)s' % aff_id - if detail_item: - detail_item += '&ganpub=%(ganpub)s&ganclk=%(ganclk)s' % aff_id - + url = 'http://books.google.com/books' if external or self.config.get('open_external', False): open_url(QUrl(url_slash_cleaner(detail_item if detail_item else url))) else: From 5301f28eb327c9724b17d05da09b99e380e385e7 Mon Sep 17 00:00:00 2001 From: Kovid Goyal Date: Mon, 22 Apr 2013 09:43:55 +0530 Subject: [PATCH 22/36] ... --- src/calibre/gui2/preferences/server.ui | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/src/calibre/gui2/preferences/server.ui b/src/calibre/gui2/preferences/server.ui index 674e4bdbc2..85d27eab57 100644 --- a/src/calibre/gui2/preferences/server.ui +++ b/src/calibre/gui2/preferences/server.ui @@ -129,7 +129,7 @@ - Max. OPDS &ungrouped items: + Max. &ungrouped items: opt_max_opds_ungrouped_items From 6031fa67b818d5e4975d99212fbfd3bbd2ef69b3 Mon Sep 17 00:00:00 2001 From: Kovid Goyal Date: Mon, 22 Apr 2013 10:43:30 +0530 Subject: [PATCH 23/36] Metadata download: WHen showing downloaded covers, allow right clicking on a cover to view a full size version. Fixes #1170544 ((enhancement) Zooming in on searched cover images) --- src/calibre/gui2/metadata/single_download.py | 52 +++++++++++++------- src/calibre/gui2/viewer/image_popup.py | 21 +++++--- 2 files changed, 48 insertions(+), 25 deletions(-) diff --git a/src/calibre/gui2/metadata/single_download.py b/src/calibre/gui2/metadata/single_download.py index ffa83b6ea8..3e9bb87687 100644 --- a/src/calibre/gui2/metadata/single_download.py +++ b/src/calibre/gui2/metadata/single_download.py @@ -21,7 +21,7 @@ from PyQt4.Qt import ( QDialog, QVBoxLayout, QLabel, QDialogButtonBox, QStyle, QStackedWidget, QWidget, QTableView, QGridLayout, QFontInfo, QPalette, QTimer, pyqtSignal, QAbstractTableModel, QVariant, QSize, QListView, QPixmap, QModelIndex, - QAbstractListModel, QColor, QRect, QTextBrowser, QStringListModel) + QAbstractListModel, QColor, QRect, QTextBrowser, QStringListModel, QMenu, QCursor) from PyQt4.QtWebKit import QWebView from calibre.customize.ui import metadata_plugins @@ -40,7 +40,7 @@ from calibre.utils.ipc.simple_worker import fork_job, WorkerError from calibre.ptempfile import TemporaryDirectory # }}} -class RichTextDelegate(QStyledItemDelegate): # {{{ +class RichTextDelegate(QStyledItemDelegate): # {{{ def __init__(self, parent=None, max_width=160): QStyledItemDelegate.__init__(self, parent) @@ -77,7 +77,7 @@ class RichTextDelegate(QStyledItemDelegate): # {{{ painter.restore() # }}} -class CoverDelegate(QStyledItemDelegate): # {{{ +class CoverDelegate(QStyledItemDelegate): # {{{ needs_redraw = pyqtSignal() @@ -143,7 +143,7 @@ class CoverDelegate(QStyledItemDelegate): # {{{ # }}} -class ResultsModel(QAbstractTableModel): # {{{ +class ResultsModel(QAbstractTableModel): # {{{ COLUMNS = ( '#', _('Title'), _('Published'), _('Has cover'), _('Has summary') @@ -182,7 +182,6 @@ class ResultsModel(QAbstractTableModel): # {{{ p = book.publisher if book.publisher else '' return '%s
%s' % (d, p) - def data(self, index, role): row, col = index.row(), index.column() try: @@ -233,7 +232,7 @@ class ResultsModel(QAbstractTableModel): # {{{ # }}} -class ResultsView(QTableView): # {{{ +class ResultsView(QTableView): # {{{ show_details_signal = pyqtSignal(object) book_selected = pyqtSignal(object) @@ -316,7 +315,7 @@ class ResultsView(QTableView): # {{{ # }}} -class Comments(QWebView): # {{{ +class Comments(QWebView): # {{{ def __init__(self, parent=None): QWebView.__init__(self, parent) @@ -384,7 +383,7 @@ class Comments(QWebView): # {{{ return QSize(800, 300) # }}} -class IdentifyWorker(Thread): # {{{ +class IdentifyWorker(Thread): # {{{ def __init__(self, log, abort, title, authors, identifiers, caches): Thread.__init__(self) @@ -441,7 +440,7 @@ class IdentifyWorker(Thread): # {{{ # }}} -class IdentifyWidget(QWidget): # {{{ +class IdentifyWidget(QWidget): # {{{ rejected = pyqtSignal() results_found = pyqtSignal() @@ -552,12 +551,11 @@ class IdentifyWidget(QWidget): # {{{ self.results_view.show_results(self.worker.results) self.results_found.emit() - def cancel(self): self.abort.set() # }}} -class CoverWorker(Thread): # {{{ +class CoverWorker(Thread): # {{{ def __init__(self, log, abort, title, authors, identifiers, caches): Thread.__init__(self) @@ -609,7 +607,8 @@ class CoverWorker(Thread): # {{{ def scan_once(self, tdir, seen): for x in list(os.listdir(tdir)): - if x in seen: continue + if x in seen: + continue if x.endswith('.cover') and os.path.exists(os.path.join(tdir, x+'.done')): name = x.rpartition('.')[0] @@ -635,7 +634,7 @@ class CoverWorker(Thread): # {{{ # }}} -class CoversModel(QAbstractListModel): # {{{ +class CoversModel(QAbstractListModel): # {{{ def __init__(self, current_cover, parent=None): QAbstractListModel.__init__(self, parent) @@ -770,7 +769,7 @@ class CoversModel(QAbstractListModel): # {{{ # }}} -class CoversView(QListView): # {{{ +class CoversView(QListView): # {{{ chosen = pyqtSignal() @@ -793,6 +792,8 @@ class CoversView(QListView): # {{{ type=Qt.QueuedConnection) self.doubleClicked.connect(self.chosen, type=Qt.QueuedConnection) + self.setContextMenuPolicy(Qt.CustomContextMenu) + self.customContextMenuRequested.connect(self.show_context_menu) def select(self, num): current = self.model().index(num) @@ -814,9 +815,24 @@ class CoversView(QListView): # {{{ else: self.select(self.m.index_from_pointer(pointer).row()) + def show_context_menu(self, point): + idx = self.currentIndex() + if idx and idx.isValid() and not idx.data(Qt.UserRole).toPyObject(): + m = QMenu() + m.addAction(QIcon(I('view.png')), _('View this cover at full size'), self.show_cover) + m.exec_(QCursor.pos()) + + def show_cover(self): + idx = self.currentIndex() + pmap = self.model().cover_pixmap(idx) + if pmap is not None: + from calibre.gui2.viewer.image_popup import ImageView + d = ImageView(self, pmap, unicode(idx.data(Qt.DisplayRole).toString()), geom_name='metadata_download_cover_popup_geom') + d(use_exec=True) + # }}} -class CoversWidget(QWidget): # {{{ +class CoversWidget(QWidget): # {{{ chosen = pyqtSignal() finished = pyqtSignal() @@ -922,7 +938,7 @@ class CoversWidget(QWidget): # {{{ # }}} -class LogViewer(QDialog): # {{{ +class LogViewer(QDialog): # {{{ def __init__(self, log, parent=None): QDialog.__init__(self, parent) @@ -970,7 +986,7 @@ class LogViewer(QDialog): # {{{ # }}} -class FullFetch(QDialog): # {{{ +class FullFetch(QDialog): # {{{ def __init__(self, current_cover=None, parent=None): QDialog.__init__(self, parent) @@ -1085,7 +1101,7 @@ class FullFetch(QDialog): # {{{ return self.exec_() # }}} -class CoverFetch(QDialog): # {{{ +class CoverFetch(QDialog): # {{{ def __init__(self, current_cover=None, parent=None): QDialog.__init__(self, parent) diff --git a/src/calibre/gui2/viewer/image_popup.py b/src/calibre/gui2/viewer/image_popup.py index 075143f3c3..1b616a12b3 100644 --- a/src/calibre/gui2/viewer/image_popup.py +++ b/src/calibre/gui2/viewer/image_popup.py @@ -15,16 +15,17 @@ from calibre.gui2 import choose_save_file, gprefs class ImageView(QDialog): - def __init__(self, parent, current_img, current_url): + def __init__(self, parent, current_img, current_url, geom_name='viewer_image_popup_geometry'): QDialog.__init__(self) dw = QApplication.instance().desktop() self.avail_geom = dw.availableGeometry(parent) self.current_img = current_img self.current_url = current_url self.factor = 1.0 + self.geom_name = geom_name self.label = l = QLabel() - l.setBackgroundRole(QPalette.Base); + l.setBackgroundRole(QPalette.Base) l.setSizePolicy(QSizePolicy.Ignored, QSizePolicy.Ignored) l.setScaledContents(True) @@ -88,21 +89,27 @@ class ImageView(QDialog): self.label.setPixmap(pm) self.label.adjustSize() - def __call__(self): + def __call__(self, use_exec=False): geom = self.avail_geom self.label.setPixmap(self.current_img) self.label.adjustSize() self.resize(QSize(int(geom.width()/2.5), geom.height()-50)) - geom = gprefs.get('viewer_image_popup_geometry', None) + geom = gprefs.get(self.geom_name, None) if geom is not None: self.restoreGeometry(geom) - self.current_image_name = unicode(self.current_url.toString()).rpartition('/')[-1] + try: + self.current_image_name = unicode(self.current_url.toString()).rpartition('/')[-1] + except AttributeError: + self.current_image_name = self.current_url title = _('View Image: %s')%self.current_image_name self.setWindowTitle(title) - self.show() + if use_exec: + self.exec_() + else: + self.show() def done(self, e): - gprefs['viewer_image_popup_geometry'] = bytearray(self.saveGeometry()) + gprefs[self.geom_name] = bytearray(self.saveGeometry()) return QDialog.done(self, e) def wheelEvent(self, event): From 4dc99bfcaa09f6d124829bfc0667af7988eb11ad Mon Sep 17 00:00:00 2001 From: Kovid Goyal Date: Mon, 22 Apr 2013 16:37:08 +0530 Subject: [PATCH 24/36] Device driver: Detect Laser EB720 with newer firmware. Fixes #1171341 (Calibre wont recognise Laser EB720 ereader) --- src/calibre/devices/teclast/driver.py | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/src/calibre/devices/teclast/driver.py b/src/calibre/devices/teclast/driver.py index acd20308ad..95d8c3cf3f 100644 --- a/src/calibre/devices/teclast/driver.py +++ b/src/calibre/devices/teclast/driver.py @@ -58,8 +58,8 @@ class PICO(NEWSMY): gui_name = 'Pico' description = _('Communicate with the Pico reader.') - VENDOR_NAME = ['TECLAST', 'IMAGIN', 'LASER-', ''] - WINDOWS_MAIN_MEM = ['USBDISK__USER', 'EB720'] + VENDOR_NAME = ['TECLAST', 'IMAGIN', 'LASER-', 'LASER', ''] + WINDOWS_MAIN_MEM = WINDOWS_CARD_A_MEM = ['USBDISK__USER', 'EB720', 'EBOOK-EB720'] EBOOK_DIR_MAIN = 'Books' FORMATS = ['EPUB', 'FB2', 'TXT', 'LRC', 'PDB', 'PDF', 'HTML', 'WTXT'] SCAN_FROM_ROOT = True From 5ff3b9e811c5c77da2526b9be75f553c610a02da Mon Sep 17 00:00:00 2001 From: Kovid Goyal Date: Mon, 22 Apr 2013 17:11:02 +0530 Subject: [PATCH 25/36] ... --- src/calibre/ebooks/conversion/plugins/epub_input.py | 1 - 1 file changed, 1 deletion(-) diff --git a/src/calibre/ebooks/conversion/plugins/epub_input.py b/src/calibre/ebooks/conversion/plugins/epub_input.py index b602ac9cd0..b6024c9b84 100644 --- a/src/calibre/ebooks/conversion/plugins/epub_input.py +++ b/src/calibre/ebooks/conversion/plugins/epub_input.py @@ -188,7 +188,6 @@ class EPUBInput(InputFormatPlugin): raise DRMError(os.path.basename(path)) self.encrypted_fonts = self._encrypted_font_uris - if len(parts) > 1 and parts[0]: delta = '/'.join(parts[:-1])+'/' for elem in opf.itermanifest(): From 68959f76527ba0d0ed7041d7d070019ab28802e2 Mon Sep 17 00:00:00 2001 From: Kovid Goyal Date: Mon, 22 Apr 2013 17:38:21 +0530 Subject: [PATCH 26/36] ... --- src/calibre/ebooks/oeb/reader.py | 30 ++++++++++++++++++------------ 1 file changed, 18 insertions(+), 12 deletions(-) diff --git a/src/calibre/ebooks/oeb/reader.py b/src/calibre/ebooks/oeb/reader.py index d0474fa7e8..8d63f30526 100644 --- a/src/calibre/ebooks/oeb/reader.py +++ b/src/calibre/ebooks/oeb/reader.py @@ -148,7 +148,6 @@ class OEBReader(object): if not has_aut: m.add('creator', self.oeb.translate(__('Unknown')), role='aut') - def _manifest_prune_invalid(self): ''' Remove items from manifest that contain invalid data. This prevents @@ -293,7 +292,7 @@ class OEBReader(object): continue try: href = item.abshref(urlnormalize(href)) - except ValueError: # Malformed URL + except ValueError: # Malformed URL continue if href not in manifest.hrefs: continue @@ -394,9 +393,9 @@ class OEBReader(object): authorElement = xpath(child, 'descendant::calibre:meta[@name = "author"]') - if authorElement : + if authorElement: author = authorElement[0].text - else : + else: author = None descriptionElement = xpath(child, @@ -406,7 +405,7 @@ class OEBReader(object): method='text', encoding=unicode).strip() if not description: description = None - else : + else: description = None index_image = xpath(child, @@ -497,7 +496,8 @@ class OEBReader(object): titles = [] headers = [] for item in self.oeb.spine: - if not item.linear: continue + if not item.linear: + continue html = item.data title = ''.join(xpath(html, '/h:html/h:head/h:title/text()')) title = COLLAPSE_RE.sub(' ', title.strip()) @@ -515,17 +515,21 @@ class OEBReader(object): if len(titles) > len(set(titles)): use = headers for title, item in izip(use, self.oeb.spine): - if not item.linear: continue + if not item.linear: + continue toc.add(title, item.href) return True def _toc_from_opf(self, opf, item): self.oeb.auto_generated_toc = False - if self._toc_from_ncx(item): return + if self._toc_from_ncx(item): + return # Prefer HTML to tour based TOC, since several LIT files # have good HTML TOCs but bad tour based TOCs - if self._toc_from_html(opf): return - if self._toc_from_tour(opf): return + if self._toc_from_html(opf): + return + if self._toc_from_tour(opf): + return self._toc_from_spine(opf) self.oeb.auto_generated_toc = True @@ -589,8 +593,10 @@ class OEBReader(object): return True def _pages_from_opf(self, opf, item): - if self._pages_from_ncx(opf, item): return - if self._pages_from_page_map(opf): return + if self._pages_from_ncx(opf, item): + return + if self._pages_from_page_map(opf): + return return def _cover_from_html(self, hcover): From 763c92110855bd446cbcf0e1b060a7f6bcac30de Mon Sep 17 00:00:00 2001 From: Kovid Goyal Date: Mon, 22 Apr 2013 17:44:58 +0530 Subject: [PATCH 27/36] pep8 --- src/calibre/ebooks/oeb/base.py | 28 ++++++++++++++-------------- 1 file changed, 14 insertions(+), 14 deletions(-) diff --git a/src/calibre/ebooks/oeb/base.py b/src/calibre/ebooks/oeb/base.py index 2a2d89b894..29a809e190 100644 --- a/src/calibre/ebooks/oeb/base.py +++ b/src/calibre/ebooks/oeb/base.py @@ -40,11 +40,11 @@ CALIBRE_NS = 'http://calibre.kovidgoyal.net/2009/metadata' RE_NS = 'http://exslt.org/regular-expressions' MBP_NS = 'http://www.mobipocket.com' -XPNSMAP = {'h' : XHTML_NS, 'o1' : OPF1_NS, 'o2' : OPF2_NS, - 'd09': DC09_NS, 'd10': DC10_NS, 'd11': DC11_NS, - 'xsi': XSI_NS, 'dt' : DCTERMS_NS, 'ncx': NCX_NS, - 'svg': SVG_NS, 'xl' : XLINK_NS, 're': RE_NS, - 'mbp': MBP_NS, 'calibre': CALIBRE_NS } +XPNSMAP = {'h': XHTML_NS, 'o1': OPF1_NS, 'o2': OPF2_NS, + 'd09': DC09_NS, 'd10': DC10_NS, 'd11': DC11_NS, + 'xsi': XSI_NS, 'dt': DCTERMS_NS, 'ncx': NCX_NS, + 'svg': SVG_NS, 'xl': XLINK_NS, 're': RE_NS, + 'mbp': MBP_NS, 'calibre': CALIBRE_NS} OPF1_NSMAP = {'dc': DC11_NS, 'oebpackage': OPF1_NS} OPF2_NSMAP = {'opf': OPF2_NS, 'dc': DC11_NS, 'dcterms': DCTERMS_NS, @@ -142,7 +142,6 @@ def iterlinks(root, find_links_in_css=True): if attr in link_attrs: yield (el, attr, attribs[attr], 0) - if not find_links_in_css: continue if tag == XHTML('style') and el.text: @@ -497,7 +496,7 @@ class DirContainer(object): return False try: path = os.path.join(self.rootdir, self._unquote(path)) - except ValueError: #Happens if path contains quoted special chars + except ValueError: # Happens if path contains quoted special chars return False try: return os.path.isfile(path) @@ -577,12 +576,13 @@ class Metadata(object): allowed = self.allowed if allowed is not None and term not in allowed: raise AttributeError( - 'attribute %r not valid for metadata term %r' \ + 'attribute %r not valid for metadata term %r' % (self.attr(term), barename(obj.term))) return self.attr(term) def __get__(self, obj, cls): - if obj is None: return None + if obj is None: + return None return obj.attrib.get(self.term_attr(obj), '') def __set__(self, obj, value): @@ -628,8 +628,8 @@ class Metadata(object): self.value = value return property(fget=fget, fset=fset) - scheme = Attribute(lambda term: 'scheme' if \ - term == OPF('meta') else OPF('scheme'), + scheme = Attribute(lambda term: 'scheme' if + term == OPF('meta') else OPF('scheme'), [DC('identifier'), OPF('meta')]) file_as = Attribute(OPF('file-as'), [DC('creator'), DC('contributor'), DC('title')]) @@ -882,7 +882,6 @@ class Manifest(object): return self._parse_xhtml(convert_markdown(data, title=title)) - def _parse_css(self, data): from cssutils import CSSParser, log, resolveImports log.setLevel(logging.WARN) @@ -935,7 +934,7 @@ class Manifest(object): data = self._loader(getattr(self, 'html_input_href', self.href)) if not isinstance(data, basestring): - pass # already parsed + pass # already parsed elif self.media_type.lower() in OEB_DOCS: data = self._parse_xhtml(data) elif self.media_type.lower()[-4:] in ('+xml', '/xml'): @@ -1022,7 +1021,8 @@ class Manifest(object): target, frag = urldefrag(href) target = target.split('/') for index in xrange(min(len(base), len(target))): - if base[index] != target[index]: break + if base[index] != target[index]: + break else: index += 1 relhref = (['..'] * (len(base) - index)) + target[index:] From 6dbd826c513628e11d974428ca9b87fd2365d7da Mon Sep 17 00:00:00 2001 From: Kovid Goyal Date: Mon, 22 Apr 2013 18:23:36 +0530 Subject: [PATCH 28/36] EPUB Input: Fix handling of EPUB files that contain images with non-ascii filenames. Fixes #1171186 (Private bug) --- src/calibre/ebooks/oeb/base.py | 18 +++++++++++++++--- src/calibre/ebooks/oeb/reader.py | 2 ++ .../ebooks/oeb/transforms/trimmanifest.py | 2 ++ 3 files changed, 19 insertions(+), 3 deletions(-) diff --git a/src/calibre/ebooks/oeb/base.py b/src/calibre/ebooks/oeb/base.py index 29a809e190..21c0c60a55 100644 --- a/src/calibre/ebooks/oeb/base.py +++ b/src/calibre/ebooks/oeb/base.py @@ -1,7 +1,6 @@ ''' Basic support for manipulating OEB 1.x/2.0 content and metadata. ''' -from __future__ import with_statement __license__ = 'GPL v3' __copyright__ = '2008, Marshall T. Vandegrift ' @@ -11,7 +10,7 @@ import os, re, uuid, logging from collections import defaultdict from itertools import count from urlparse import urldefrag, urlparse, urlunparse, urljoin -from urllib import unquote as urlunquote +from urllib import unquote from lxml import etree, html from calibre.constants import filesystem_encoding, __version__ @@ -372,6 +371,19 @@ def urlquote(href): result.append(char) return ''.join(result) +def urlunquote(href): + # unquote must run on a bytestring and will return a bytestring + # If it runs on a unicode object, it returns a double encoded unicode + # string: unquote(u'%C3%A4') != unquote(b'%C3%A4').decode('utf-8') + # and the latter is correct + want_unicode = isinstance(href, unicode) + if want_unicode: + href = href.encode('utf-8') + href = unquote(href) + if want_unicode: + href = href.decode('utf-8') + return href + def urlnormalize(href): """Convert a URL into normalized form, with all and only URL-unsafe characters URL quoted. @@ -468,7 +480,7 @@ class DirContainer(object): return def _unquote(self, path): - # urlunquote must run on a bytestring and will return a bytestring + # unquote must run on a bytestring and will return a bytestring # If it runs on a unicode object, it returns a double encoded unicode # string: unquote(u'%C3%A4') != unquote(b'%C3%A4').decode('utf-8') # and the latter is correct diff --git a/src/calibre/ebooks/oeb/reader.py b/src/calibre/ebooks/oeb/reader.py index 8d63f30526..6a3747d2d3 100644 --- a/src/calibre/ebooks/oeb/reader.py +++ b/src/calibre/ebooks/oeb/reader.py @@ -196,6 +196,8 @@ class OEBReader(object): item.media_type[-4:] in ('/xml', '+xml')): hrefs = [r[2] for r in iterlinks(data)] for href in hrefs: + if isinstance(href, bytes): + href = href.decode('utf-8') href, _ = urldefrag(href) if not href: continue diff --git a/src/calibre/ebooks/oeb/transforms/trimmanifest.py b/src/calibre/ebooks/oeb/transforms/trimmanifest.py index 3d56f0ef3d..67d55a581e 100644 --- a/src/calibre/ebooks/oeb/transforms/trimmanifest.py +++ b/src/calibre/ebooks/oeb/transforms/trimmanifest.py @@ -47,6 +47,8 @@ class ManifestTrimmer(object): item.data is not None: hrefs = [r[2] for r in iterlinks(item.data)] for href in hrefs: + if isinstance(href, bytes): + href = href.decode('utf-8') try: href = item.abshref(urlnormalize(href)) except: From c0d5f59d5b2e31302fa4849feeb70d054bd94453 Mon Sep 17 00:00:00 2001 From: Kovid Goyal Date: Mon, 22 Apr 2013 18:44:02 +0530 Subject: [PATCH 29/36] ... --- src/calibre/ebooks/oeb/base.py | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/src/calibre/ebooks/oeb/base.py b/src/calibre/ebooks/oeb/base.py index 21c0c60a55..eb5b0042e7 100644 --- a/src/calibre/ebooks/oeb/base.py +++ b/src/calibre/ebooks/oeb/base.py @@ -361,7 +361,9 @@ URL_SAFE = set('ABCDEFGHIJKLMNOPQRSTUVWXYZ' URL_UNSAFE = [ASCII_CHARS - URL_SAFE, UNIBYTE_CHARS - URL_SAFE] def urlquote(href): - """Quote URL-unsafe characters, allowing IRI-safe characters.""" + """ Quote URL-unsafe characters, allowing IRI-safe characters. + That is, this function returns valid IRIs not valid URIs. In particular, + IRIs can contain non-ascii characters. """ result = [] unsafe = 0 if isinstance(href, unicode) else 1 unsafe = URL_UNSAFE[unsafe] From d3a58c69ea004246a3f7ef6876eb3409769e8997 Mon Sep 17 00:00:00 2001 From: Kovid Goyal Date: Tue, 23 Apr 2013 10:30:47 +0530 Subject: [PATCH 30/36] Driver for Easy player cyber book e touch. Fixes #1171633 (Unrecognized Device) --- src/calibre/devices/misc.py | 20 +++++++++++--------- 1 file changed, 11 insertions(+), 9 deletions(-) diff --git a/src/calibre/devices/misc.py b/src/calibre/devices/misc.py index f033fb9a2f..4a2e6aa864 100644 --- a/src/calibre/devices/misc.py +++ b/src/calibre/devices/misc.py @@ -95,7 +95,6 @@ class PDNOVEL(USBMS): SUPPORTS_SUB_DIRS = False DELETE_EXTS = ['.jpg', '.jpeg', '.png'] - def upload_cover(self, path, filename, metadata, filepath): coverdata = getattr(metadata, 'thumbnail', None) if coverdata and coverdata[2]: @@ -226,9 +225,9 @@ class TREKSTOR(USBMS): VENDOR_ID = [0x1e68] PRODUCT_ID = [0x0041, 0x0042, 0x0052, 0x004e, 0x0056, - 0x0067, # This is for the Pyrus Mini - 0x003e, # This is for the EBOOK_PLAYER_5M https://bugs.launchpad.net/bugs/792091 - 0x5cL, # This is for the 4ink http://www.mobileread.com/forums/showthread.php?t=191318 + 0x0067, # This is for the Pyrus Mini + 0x003e, # This is for the EBOOK_PLAYER_5M https://bugs.launchpad.net/bugs/792091 + 0x5cL, # This is for the 4ink http://www.mobileread.com/forums/showthread.php?t=191318 ] BCD = [0x0002, 0x100] @@ -427,8 +426,8 @@ class WAYTEQ(USBMS): EBOOK_DIR_MAIN = 'Documents' SCAN_FROM_ROOT = True - VENDOR_NAME = 'ROCKCHIP' - WINDOWS_MAIN_MEM = WINDOWS_CARD_A_MEM = 'RK28_SDK_DEMO' + VENDOR_NAME = ['ROCKCHIP', 'CBR'] + WINDOWS_MAIN_MEM = WINDOWS_CARD_A_MEM = ['RK28_SDK_DEMO', 'EINK_EBOOK_READE'] SUPPORTS_SUB_DIRS = True def get_gui_name(self): @@ -445,7 +444,8 @@ class WAYTEQ(USBMS): return self.EBOOK_DIR_CARD_A def windows_sort_drives(self, drives): - if len(drives) < 2: return drives + if len(drives) < 2: + return drives main = drives.get('main', None) carda = drives.get('carda', None) if main and carda: @@ -455,7 +455,8 @@ class WAYTEQ(USBMS): def linux_swap_drives(self, drives): # See https://bugs.launchpad.net/bugs/1151901 - if len(drives) < 2 or not drives[1] or not drives[2]: return drives + if len(drives) < 2 or not drives[1] or not drives[2]: + return drives drives = list(drives) t = drives[0] drives[0] = drives[1] @@ -463,7 +464,8 @@ class WAYTEQ(USBMS): return tuple(drives) def osx_sort_names(self, names): - if len(names) < 2: return names + if len(names) < 2: + return names main = names.get('main', None) card = names.get('carda', None) From f0396d021cf940353487fec0fe782229965d72cb Mon Sep 17 00:00:00 2001 From: Kovid Goyal Date: Tue, 23 Apr 2013 12:58:36 +0530 Subject: [PATCH 31/36] Implement refresh() --- src/calibre/db/cache.py | 13 +++++++++++++ src/calibre/db/legacy.py | 20 ++++++++++++++++++++ src/calibre/db/tests/legacy.py | 12 ++++++++++++ src/calibre/db/view.py | 8 ++++++++ 4 files changed, 53 insertions(+) diff --git a/src/calibre/db/cache.py b/src/calibre/db/cache.py index 0fa280d997..7c2176ec31 100644 --- a/src/calibre/db/cache.py +++ b/src/calibre/db/cache.py @@ -114,6 +114,19 @@ class Cache(object): if self.dirtied_cache: self.dirtied_sequence = max(self.dirtied_cache.itervalues())+1 + @write_api + def initialize_template_cache(self): + self.formatter_template_cache = {} + + @write_api + def refresh(self): + self._initialize_template_cache() + for field in self.fields.itervalues(): + if hasattr(field, 'clear_cache'): + field.clear_cache() # Clear the composite cache + if hasattr(field, 'table'): + field.table.read(self.backend) # Reread data from metadata.db + @property def field_metadata(self): return self.backend.field_metadata diff --git a/src/calibre/db/legacy.py b/src/calibre/db/legacy.py index d1b76cd8bd..3c06f21fed 100644 --- a/src/calibre/db/legacy.py +++ b/src/calibre/db/legacy.py @@ -12,6 +12,7 @@ from functools import partial from calibre.db.backend import DB from calibre.db.cache import Cache from calibre.db.view import View +from calibre.utils.date import utcnow class LibraryDatabase(object): @@ -50,6 +51,8 @@ class LibraryDatabase(object): setattr(self, prop, partial(self.get_property, loc=self.FIELD_MAP[fm])) + self.last_update_check = self.last_modified() + def close(self): self.backend.close() @@ -74,6 +77,11 @@ class LibraryDatabase(object): def last_modified(self): return self.backend.last_modified() + def check_if_modified(self): + if self.last_modified() > self.last_update_check: + self.refresh() + self.last_update_check = utcnow() + @property def custom_column_num_map(self): return self.backend.custom_column_num_map @@ -86,9 +94,21 @@ class LibraryDatabase(object): def FIELD_MAP(self): return self.backend.FIELD_MAP + @property + def formatter_template_cache(self): + return self.data.cache.formatter_template_cache + + def initialize_template_cache(self): + self.data.cache.initialize_template_cache() + def all_ids(self): for book_id in self.data.cache.all_book_ids(): yield book_id + + def refresh(self, field=None, ascending=True): + self.data.cache.refresh() + self.data.refresh(field=field, ascending=ascending) + # }}} diff --git a/src/calibre/db/tests/legacy.py b/src/calibre/db/tests/legacy.py index 6d5734d6b5..2eba15c375 100644 --- a/src/calibre/db/tests/legacy.py +++ b/src/calibre/db/tests/legacy.py @@ -64,3 +64,15 @@ class LegacyTest(BaseTest): # }}} + def test_refresh(self): # {{{ + ' Test refreshing the view after a change to metadata.db ' + db = self.init_legacy() + db2 = self.init_legacy() + self.assertEqual(db2.data.cache.set_field('title', {1:'xxx'}), set([1])) + db2.close() + del db2 + self.assertNotEqual(db.title(1, index_is_id=True), 'xxx') + db.check_if_modified() + self.assertEqual(db.title(1, index_is_id=True), 'xxx') + # }}} + diff --git a/src/calibre/db/view.py b/src/calibre/db/view.py index 4ffa1dd074..ff41f20614 100644 --- a/src/calibre/db/view.py +++ b/src/calibre/db/view.py @@ -294,3 +294,11 @@ class View(object): self.marked_ids = dict(izip(id_dict.iterkeys(), imap(unicode, id_dict.itervalues()))) + def refresh(self, field=None, ascending=True): + self._map = tuple(self.cache.all_book_ids()) + self._map_filtered = tuple(self._map) + if field is not None: + self.sort(field, ascending) + if self.search_restriction or self.base_restriction: + self.search('', return_matches=False) + From b28a069e187cd33fb854bde8b090c2e96768709b Mon Sep 17 00:00:00 2001 From: Kovid Goyal Date: Tue, 23 Apr 2013 15:45:13 +0530 Subject: [PATCH 32/36] Add tests for legacy getters --- src/calibre/db/legacy.py | 19 +++++++++++++++++++ src/calibre/db/tests/legacy.py | 18 +++++++++++++++++- 2 files changed, 36 insertions(+), 1 deletion(-) diff --git a/src/calibre/db/legacy.py b/src/calibre/db/legacy.py index 3c06f21fed..0c07814ab1 100644 --- a/src/calibre/db/legacy.py +++ b/src/calibre/db/legacy.py @@ -74,6 +74,14 @@ class LibraryDatabase(object): def library_id(self): return self.backend.library_id + @property + def library_path(self): + return self.backend.library_path + + @property + def dbpath(self): + return self.backend.dbpath + def last_modified(self): return self.backend.last_modified() @@ -111,4 +119,15 @@ class LibraryDatabase(object): # }}} + def path(self, index, index_is_id=False): + 'Return the relative path to the directory containing this books files as a unicode string.' + book_id = index if index_is_id else self.data.index_to_id(index) + return self.data.cache.field_for('path', book_id).replace('/', os.sep) + + def abspath(self, index, index_is_id=False, create_dirs=True): + 'Return the absolute path to the directory containing this books files as a unicode string.' + path = os.path.join(self.library_path, self.path(index, index_is_id=index_is_id)) + if create_dirs and not os.path.exists(path): + os.makedirs(path) + return path diff --git a/src/calibre/db/tests/legacy.py b/src/calibre/db/tests/legacy.py index 2eba15c375..0f378c566c 100644 --- a/src/calibre/db/tests/legacy.py +++ b/src/calibre/db/tests/legacy.py @@ -16,7 +16,7 @@ class LegacyTest(BaseTest): 'Test library wide properties' def get_props(db): props = ('user_version', 'is_second_db', 'library_id', 'field_metadata', - 'custom_column_label_map', 'custom_column_num_map') + 'custom_column_label_map', 'custom_column_num_map', 'library_path', 'dbpath') fprops = ('last_modified', ) ans = {x:getattr(db, x) for x in props} ans.update({x:getattr(db, x)() for x in fprops}) @@ -76,3 +76,19 @@ class LegacyTest(BaseTest): self.assertEqual(db.title(1, index_is_id=True), 'xxx') # }}} + def test_legacy_getters(self): # {{{ + old = self.init_old() + getters = ('path', 'abspath', 'title', 'authors', 'series', + 'publisher', 'author_sort', 'authors', 'comments', + 'comment', 'publisher', 'rating', 'series_index', 'tags', + 'timestamp', 'uuid', 'pubdate', 'ondevice', + 'metadata_last_modified', 'languages') + oldvals = {g:tuple(getattr(old, g)(x) for x in xrange(3)) for g in getters} + old.close() + db = self.init_legacy() + newvals = {g:tuple(getattr(db, g)(x) for x in xrange(3)) for g in getters} + for x in (oldvals, newvals): + x['tags'] = tuple(set(y.split(',')) if y else y for y in x['tags']) + self.assertEqual(oldvals, newvals) + # }}} + From 568faa1952bdb2fa46e739139f697e0d06327c61 Mon Sep 17 00:00:00 2001 From: Kovid Goyal Date: Tue, 23 Apr 2013 15:50:42 +0530 Subject: [PATCH 33/36] ... --- src/calibre/db/tests/legacy.py | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/src/calibre/db/tests/legacy.py b/src/calibre/db/tests/legacy.py index 0f378c566c..7c9385f8df 100644 --- a/src/calibre/db/tests/legacy.py +++ b/src/calibre/db/tests/legacy.py @@ -83,10 +83,10 @@ class LegacyTest(BaseTest): 'comment', 'publisher', 'rating', 'series_index', 'tags', 'timestamp', 'uuid', 'pubdate', 'ondevice', 'metadata_last_modified', 'languages') - oldvals = {g:tuple(getattr(old, g)(x) for x in xrange(3)) for g in getters} + oldvals = {g:tuple(getattr(old, g)(x) for x in xrange(3)) + tuple(getattr(old, g)(x, True) for x in (1,2,3)) for g in getters} old.close() db = self.init_legacy() - newvals = {g:tuple(getattr(db, g)(x) for x in xrange(3)) for g in getters} + newvals = {g:tuple(getattr(db, g)(x) for x in xrange(3)) + tuple(getattr(db, g)(x, True) for x in (1,2,3)) for g in getters} for x in (oldvals, newvals): x['tags'] = tuple(set(y.split(',')) if y else y for y in x['tags']) self.assertEqual(oldvals, newvals) From e54625a320ed3be96f4927c9902ddcf3464e3a66 Mon Sep 17 00:00:00 2001 From: Kovid Goyal Date: Tue, 23 Apr 2013 15:57:47 +0530 Subject: [PATCH 34/36] Fix test_get_property to ignore series_sort when lang is not eng --- src/calibre/db/tests/legacy.py | 5 +++++ 1 file changed, 5 insertions(+) diff --git a/src/calibre/db/tests/legacy.py b/src/calibre/db/tests/legacy.py index 7c9385f8df..353e1bc4b5 100644 --- a/src/calibre/db/tests/legacy.py +++ b/src/calibre/db/tests/legacy.py @@ -51,6 +51,11 @@ class LegacyTest(BaseTest): if label in {'tags', 'formats'}: # Order is random in the old db for these ans[label] = tuple(set(x.split(',')) if x else x for x in ans[label]) + if label == 'series_sort': + # The old db code did not take book language into account + # when generating series_sort values (the first book has + # lang=deu) + ans[label] = ans[label][1:] return ans old = self.init_old() From 9548ad62069d8ded50568e0d654801ec5cc21534 Mon Sep 17 00:00:00 2001 From: Kovid Goyal Date: Tue, 23 Apr 2013 16:10:15 +0530 Subject: [PATCH 35/36] Legacy listeners interface --- src/calibre/db/legacy.py | 19 ++++++++++++++++++- 1 file changed, 18 insertions(+), 1 deletion(-) diff --git a/src/calibre/db/legacy.py b/src/calibre/db/legacy.py index 0c07814ab1..36e6fa152d 100644 --- a/src/calibre/db/legacy.py +++ b/src/calibre/db/legacy.py @@ -6,7 +6,7 @@ from __future__ import (unicode_literals, division, absolute_import, __license__ = 'GPL v3' __copyright__ = '2013, Kovid Goyal ' -import os +import os, traceback from functools import partial from calibre.db.backend import DB @@ -30,6 +30,7 @@ class LibraryDatabase(object): progress_callback=lambda x, y:True, restore_all_prefs=False): self.is_second_db = is_second_db # TODO: Use is_second_db + self.listeners = set([]) backend = self.backend = DB(library_path, default_prefs=default_prefs, read_only=read_only, restore_all_prefs=restore_all_prefs, @@ -117,6 +118,22 @@ class LibraryDatabase(object): self.data.cache.refresh() self.data.refresh(field=field, ascending=ascending) + def add_listener(self, listener): + ''' + Add a listener. Will be called on change events with two arguments. + Event name and list of affected ids. + ''' + self.listeners.add(listener) + + def notify(self, event, ids=[]): + 'Notify all listeners' + for listener in self.listeners: + try: + listener(event, ids) + except: + traceback.print_exc() + continue + # }}} def path(self, index, index_is_id=False): From d244bbd93fa354e09472c0d089090beb83b27922 Mon Sep 17 00:00:00 2001 From: davidfor Date: Tue, 23 Apr 2013 21:34:25 +1000 Subject: [PATCH 36/36] Add support for Kobo Aura HD - Add device id for Aura HD - Add cover image sixes - Change gui_name to show model names - Display correct model when connected - Bug#1169571 --- src/calibre/devices/kobo/driver.py | 56 ++++++++++++++++++++---------- 1 file changed, 37 insertions(+), 19 deletions(-) diff --git a/src/calibre/devices/kobo/driver.py b/src/calibre/devices/kobo/driver.py index 1d4e4f73b2..800dfd9d88 100644 --- a/src/calibre/devices/kobo/driver.py +++ b/src/calibre/devices/kobo/driver.py @@ -1199,9 +1199,9 @@ class KOBO(USBMS): class KOBOTOUCH(KOBO): name = 'KoboTouch' - gui_name = 'Kobo Touch' + gui_name = 'Kobo Touch/Glo/Mini/Aura HD' author = 'David Forrester' - description = 'Communicate with the Kobo Touch, Glo and Mini firmware. Based on the existing Kobo driver by %s.' % (KOBO.author) + description = 'Communicate with the Kobo Touch, Glo, Mini and Aura HD ereaders. Based on the existing Kobo driver by %s.' % (KOBO.author) # icon = I('devices/kobotouch.jpg') supported_dbversion = 80 @@ -1297,12 +1297,13 @@ class KOBOTOUCH(KOBO): TIMESTAMP_STRING = "%Y-%m-%dT%H:%M:%SZ" - GLO_PRODUCT_ID = [0x4173] - MINI_PRODUCT_ID = [0x4183] - TOUCH_PRODUCT_ID = [0x4163] - PRODUCT_ID = GLO_PRODUCT_ID + MINI_PRODUCT_ID + TOUCH_PRODUCT_ID + AURA_HD_PRODUCT_ID = [0x4193] + GLO_PRODUCT_ID = [0x4173] + MINI_PRODUCT_ID = [0x4183] + TOUCH_PRODUCT_ID = [0x4163] + PRODUCT_ID = AURA_HD_PRODUCT_ID + GLO_PRODUCT_ID + MINI_PRODUCT_ID + TOUCH_PRODUCT_ID - BCD = [0x0110, 0x0326] + BCD = [0x0110, 0x0326] # Image file name endings. Made up of: image size, min_dbversion, max_dbversion, COVER_FILE_ENDINGS = { @@ -1319,6 +1320,11 @@ class KOBOTOUCH(KOBO): # ' - N3_LIBRARY_LIST.parsed':[(60,90),0, 53,], # ' - N3_LIBRARY_SHELF.parsed': [(40,60),0, 52,], } + AURA_HD_COVER_FILE_ENDINGS = { + ' - N3_FULL.parsed': [(1080,1440), 0, 99,True,], # Used for screensaver, home screen + ' - N3_LIBRARY_FULL.parsed':[(355, 471), 0, 99,False,], # Used for Details screen + ' - N3_LIBRARY_GRID.parsed':[(149, 198), 0, 99,False,], # Used for library lists + } #Following are the sizes used with pre2.1.4 firmware # COVER_FILE_ENDINGS = { # ' - N3_LIBRARY_FULL.parsed':[(355,530),0, 99,], # Used for Details screen @@ -1334,6 +1340,10 @@ class KOBOTOUCH(KOBO): super(KOBOTOUCH, self).initialize() self.bookshelvelist = [] + def get_device_information(self, end_session=True): + self.set_device_name() + return super(KOBOTOUCH, self).get_device_information(end_session) + def books(self, oncard=None, end_session=True): debug_print("KoboTouch:books - oncard='%s'"%oncard) from calibre.ebooks.metadata.meta import path_to_ext @@ -1366,7 +1376,7 @@ class KOBOTOUCH(KOBO): except: self.fwversion = (0,0,0) - + debug_print('Kobo device: %s' % self.gui_name) debug_print('Version of driver:', self.version, 'Has kepubs:', self.has_kepubs) debug_print('Version of firmware:', self.fwversion, 'Has kepubs:', self.has_kepubs) @@ -1379,7 +1389,7 @@ class KOBOTOUCH(KOBO): debug_print(opts.extra_customization) if opts.extra_customization: debugging_title = opts.extra_customization[self.OPT_DEBUGGING_TITLE] - debug_print("KoboTouch:books - set_debugging_title to", debugging_title ) + debug_print("KoboTouch:books - set_debugging_title to '%s'" % debugging_title ) bl.set_debugging_title(debugging_title) debug_print("KoboTouch:books - length bl=%d"%len(bl)) need_sync = self.parse_metadata_cache(bl, prefix, self.METADATA_CACHE) @@ -1930,7 +1940,7 @@ class KOBOTOUCH(KOBO): delete_empty_shelves = opts.extra_customization[self.OPT_DELETE_BOOKSHELVES] and self.supports_bookshelves() update_series_details = opts.extra_customization[self.OPT_UPDATE_SERIES_DETAILS] and self.supports_series() debugging_title = opts.extra_customization[self.OPT_DEBUGGING_TITLE] - debug_print("KoboTouch:update_device_database_collections - set_debugging_title to", debugging_title ) + debug_print("KoboTouch:update_device_database_collections - set_debugging_title to '%s'" % debugging_title ) booklists.set_debugging_title(debugging_title) else: delete_empty_shelves = False @@ -2516,6 +2526,8 @@ class KOBOTOUCH(KOBO): return opts + def isAuraHD(self): + return self.detected_device.idProduct in self.AURA_HD_PRODUCT_ID def isGlo(self): return self.detected_device.idProduct in self.GLO_PRODUCT_ID def isMini(self): @@ -2524,7 +2536,21 @@ class KOBOTOUCH(KOBO): return self.detected_device.idProduct in self.TOUCH_PRODUCT_ID def cover_file_endings(self): - return self.GLO_COVER_FILE_ENDINGS if self.isGlo() else self.COVER_FILE_ENDINGS + return self.GLO_COVER_FILE_ENDINGS if self.isGlo() else self.AURA_HD_COVER_FILE_ENDINGS if self.isAuraHD() else self.COVER_FILE_ENDINGS + + def set_device_name(self): + device_name = self.gui_name + if self.isAuraHD(): + device_name = 'Kobo Aura HD' + elif self.isGlo(): + device_name = 'Kobo Glo' + elif self.isMini(): + device_name = 'Kobo Mini' + elif self.isTouch(): + device_name = 'Kobo Touch' + self.__class__.gui_name = device_name + return device_name + def copying_covers(self): opts = self.settings() @@ -2582,14 +2608,6 @@ class KOBOTOUCH(KOBO): # Supported database version return True -# @classmethod -# def get_gui_name(cls): -# if hasattr(cls, 'gui_name'): -# return cls.gui_name -# if hasattr(cls, '__name__'): -# return cls.__name__ -# return cls.name - @classmethod def is_debugging_title(cls, title):