mirror of
https://github.com/kovidgoyal/calibre.git
synced 2025-07-08 18:54:09 -04:00
Merge branch 'misc-fixups' of https://github.com/eli-schwartz/calibre
This commit is contained in:
Kovid Goyal
commit
1372fe239b
@ -632,6 +632,16 @@
|
||||
}
|
||||
},
|
||||
|
||||
{
|
||||
"name": "sgmllib3k",
|
||||
"python": 3,
|
||||
"unix": {
|
||||
"filename": "sgmllib3k-1.0.0.tar.gz",
|
||||
"hash": "sha256:7868fb1c8bfa764c1ac563d3cf369c381d1325d36124933a726f29fcdaa812e9",
|
||||
"urls": ["pypi"]
|
||||
}
|
||||
},
|
||||
|
||||
{
|
||||
"name": "markdown",
|
||||
"unix": {
|
||||
|
||||
@ -8,7 +8,7 @@ import subprocess
|
||||
import sys
|
||||
import unittest
|
||||
|
||||
from setup import SRC, Command, islinux, ismacos, iswindows
|
||||
from setup import SRC, Command, isbsd, islinux, ismacos, iswindows
|
||||
|
||||
TEST_MODULES = frozenset('srv db polish opf css docx cfi matcher icu smartypants build misc dbcli ebooks'.split())
|
||||
|
||||
@ -50,8 +50,10 @@ class TestImports(unittest.TestCase):
|
||||
exclude_modules |= {
|
||||
'calibre.linux',
|
||||
'calibre.utils.linux_trash', 'calibre.utils.open_with.linux',
|
||||
'calibre.gui2.linux_file_dialogs', 'calibre.devices.usbms.hal',
|
||||
'calibre.gui2.linux_file_dialogs',
|
||||
}
|
||||
if not isbsd:
|
||||
exclude_modules.add('calibre.devices.usbms.hal')
|
||||
self.assertGreater(self.base_check(os.path.join(SRC, 'odf'), exclude_packages, exclude_modules), 10)
|
||||
base = os.path.join(SRC, 'calibre')
|
||||
self.assertGreater(self.base_check(base, exclude_packages, exclude_modules), 1000)
|
||||
|
||||
@ -750,7 +750,7 @@ def initialize_plugins(perf=False):
|
||||
times[plugin.name] = time.time() - st
|
||||
_initialized_plugins.append(plugin)
|
||||
except:
|
||||
print('Failed to initialize plugin:', repr(zfp))
|
||||
print('Failed to initialize plugin:', repr(zfp), file=sys.stderr)
|
||||
if DEBUG:
|
||||
traceback.print_exc()
|
||||
# Prevent a custom plugin from overriding stdout/stderr as this breaks
|
||||
|
||||
@ -182,7 +182,8 @@ class Convert:
|
||||
indent = float(style.text_indent[:-2]) + indent
|
||||
style.text_indent = '%.3gpt' % indent
|
||||
parent.text = tabs[-1].tail or ''
|
||||
list(map(parent.remove, tabs))
|
||||
for i in tabs:
|
||||
parent.remove(i)
|
||||
|
||||
self.images.rid_map = orig_rid_map
|
||||
|
||||
|
||||
@ -65,8 +65,8 @@ class TAGX: # {{{
|
||||
'''
|
||||
TAGX block for the Primary index header of a periodical
|
||||
'''
|
||||
list(map(self.add_tag, (1, 2, 3, 4, 5, 21, 22, 23, 0, 69, 70, 71, 72,
|
||||
73, 0)))
|
||||
for i in (1, 2, 3, 4, 5, 21, 22, 23, 0, 69, 70, 71, 72,73, 0):
|
||||
self.add_tag(i)
|
||||
return self.header(2) + bytes(self.byts)
|
||||
|
||||
@property
|
||||
@ -74,7 +74,8 @@ class TAGX: # {{{
|
||||
'''
|
||||
TAGX block for the secondary index header of a periodical
|
||||
'''
|
||||
list(map(self.add_tag, (11, 0)))
|
||||
for i in (11, 0):
|
||||
self.add_tag(i)
|
||||
return self.header(1) + bytes(self.byts)
|
||||
|
||||
@property
|
||||
@ -82,7 +83,8 @@ class TAGX: # {{{
|
||||
'''
|
||||
TAGX block for the primary index header of a flat book
|
||||
'''
|
||||
list(map(self.add_tag, (1, 2, 3, 4, 0)))
|
||||
for i in (1, 2, 3, 4, 0):
|
||||
self.add_tag(i)
|
||||
return self.header(1) + bytes(self.byts)
|
||||
|
||||
|
||||
|
||||
@ -65,7 +65,8 @@ def merge_multiple_html_heads_and_bodies(root, log=None):
|
||||
for b in bodies:
|
||||
for x in b:
|
||||
body.append(x)
|
||||
tuple(map(root.append, (head, body)))
|
||||
for x in (head, body):
|
||||
root.append(x)
|
||||
if log is not None:
|
||||
log.warn('Merging multiple <head> and <body> sections')
|
||||
return root
|
||||
|
||||
@ -221,7 +221,8 @@ class Pool:
|
||||
if not sip.isdeleted(x):
|
||||
sip.delete(x)
|
||||
|
||||
tuple(map(safe_delete, self.workers))
|
||||
for i in self.workers:
|
||||
safe_delete(i)
|
||||
self.workers = []
|
||||
|
||||
|
||||
|
||||
@ -410,7 +410,8 @@ def check_external_links(container, progress_callback=(lambda num, total:None),
|
||||
return []
|
||||
items = Queue()
|
||||
ans = []
|
||||
tuple(map(items.put, iteritems(external_links)))
|
||||
for el in iteritems(external_links):
|
||||
items.put(el)
|
||||
progress_callback(0, len(external_links))
|
||||
done = []
|
||||
downloaded_html_ids = {}
|
||||
|
||||
@ -825,7 +825,8 @@ class Container(ContainerBase): # {{{
|
||||
imap = {name:item_id for item_id, name in iteritems(imap)}
|
||||
items = [item for item, name, linear in self.spine_iter]
|
||||
tail, last_tail = (items[0].tail, items[-1].tail) if items else ('\n ', '\n ')
|
||||
tuple(map(self.remove_from_xml, items))
|
||||
for i in items:
|
||||
self.remove_from_xml(i)
|
||||
spine = self.opf_xpath('//opf:spine')[0]
|
||||
spine.text = tail
|
||||
for name, linear in spine_items:
|
||||
|
||||
@ -384,7 +384,8 @@ def remove_links_to(container, predicate):
|
||||
removed = remove_links_in_sheet(partial(container.href_to_name, base=name), container.parsed(name), predicate)
|
||||
if removed:
|
||||
changed.add(name)
|
||||
tuple(map(container.dirty, changed))
|
||||
for i in changed:
|
||||
container.dirty(i)
|
||||
return changed
|
||||
|
||||
|
||||
|
||||
@ -455,8 +455,8 @@ def add_anchors_markup(root, uuid, anchors):
|
||||
# rescale the viewport
|
||||
a.tail = '\n'
|
||||
div.append(a)
|
||||
a.count = 0
|
||||
tuple(map(a, anchors))
|
||||
for anchor in anchors:
|
||||
a(anchor)
|
||||
a(uuid)
|
||||
|
||||
|
||||
|
||||
@ -490,7 +490,8 @@ def get_cover(metadata):
|
||||
|
||||
def get_covers(themes, dialog, num_of_workers=8):
|
||||
items = Queue()
|
||||
tuple(map(items.put, themes))
|
||||
for i in themes:
|
||||
items.put(i)
|
||||
|
||||
def callback(metadata, x):
|
||||
if not sip.isdeleted(dialog) and not dialog.dialog_closed:
|
||||
|
||||
@ -305,7 +305,7 @@ def main(args=sys.argv, logger=None):
|
||||
return 1
|
||||
pid = os.fork() if (islinux or isbsd) else -1
|
||||
if pid <= 0:
|
||||
override = 'calibre-lrf-viewer' if islinux else None
|
||||
override = 'calibre-lrfviewer' if islinux else None
|
||||
app = Application(args, override_program_name=override)
|
||||
app.setWindowIcon(QIcon(I('viewer.png')))
|
||||
opts = normalize_settings(parser, opts)
|
||||
|
||||
@ -217,7 +217,7 @@ class Choices(QComboBox):
|
||||
self.setEditable(False)
|
||||
opt = options[name]
|
||||
self.choices = opt.choices
|
||||
tuple(map(self.addItem, opt.choices))
|
||||
self.addItems(opt.choices)
|
||||
self.currentIndexChanged.connect(self.changed_signal.emit)
|
||||
init_opt(self, opt, layout)
|
||||
|
||||
|
||||
@ -600,8 +600,8 @@ class TagBrowserBar(QWidget): # {{{
|
||||
find_shown = self.toggle_search_button.isChecked()
|
||||
self.toggle_search_button.setVisible(not find_shown)
|
||||
l = self.layout()
|
||||
items = [l.itemAt(i) for i in range(l.count())]
|
||||
tuple(map(l.removeItem, items))
|
||||
for i in (l.itemAt(i) for i in range(l.count())):
|
||||
l.removeItem(i)
|
||||
if find_shown:
|
||||
l.addWidget(self.alter_tb)
|
||||
self.alter_tb.setToolButtonStyle(Qt.ToolButtonStyle.ToolButtonIconOnly)
|
||||
|
||||
@ -391,7 +391,8 @@ class Boss(QObject):
|
||||
if ef:
|
||||
if isinstance(ef, str):
|
||||
ef = [ef]
|
||||
tuple(map(self.gui.file_list.request_edit, ef))
|
||||
for i in ef:
|
||||
self.gui.file_list.request_edit(i)
|
||||
else:
|
||||
if tprefs['restore_book_state']:
|
||||
self.restore_book_edit_state()
|
||||
|
||||
@ -1129,7 +1129,8 @@ class MergeDialog(QDialog): # {{{
|
||||
|
||||
buttons = self.buttons = [QRadioButton(n) for n in names]
|
||||
buttons[0].setChecked(True)
|
||||
tuple(map(w.l.addWidget, buttons))
|
||||
for i in buttons:
|
||||
w.l.addWidget(i)
|
||||
sa.setWidget(w)
|
||||
|
||||
self.resize(self.sizeHint() + QSize(150, 20))
|
||||
|
||||
@ -70,7 +70,7 @@ def _run(args, notify=None):
|
||||
parser = option_parser()
|
||||
opts, args = parser.parse_args(args)
|
||||
decouple('edit-book-'), set_gui_prefs(tprefs)
|
||||
override = 'calibre-edit-book' if islinux else None
|
||||
override = 'calibre-ebook-edit' if islinux else None
|
||||
app = Application(args, override_program_name=override, color_prefs=tprefs, windows_app_uid=EDITOR_APP_UID)
|
||||
app.file_event_hook = EventAccumulator()
|
||||
app.load_builtin_fonts()
|
||||
|
||||
@ -431,6 +431,7 @@ class EbookViewer(MainWindow):
|
||||
if not hasattr(set_book_path, 'pathtoebook'):
|
||||
error_dialog(self, _('Cannot print book'), _(
|
||||
'No book is currently open'), show=True)
|
||||
return
|
||||
from .printing import print_book
|
||||
print_book(set_book_path.pathtoebook, book_title=self.current_book_data['metadata']['title'], parent=self)
|
||||
|
||||
|
||||
@ -254,7 +254,8 @@ class RequestData: # {{{
|
||||
|
||||
def filesystem_file_with_custom_etag(self, output, *etag_parts):
|
||||
etag = hashlib.sha1()
|
||||
tuple(map(lambda x:etag.update(str(x).encode('utf-8')), etag_parts))
|
||||
for i in etag_parts:
|
||||
etag.update(str(i).encode('utf-8'))
|
||||
return ETaggedFile(output, etag.hexdigest())
|
||||
|
||||
def filesystem_file_with_constant_etag(self, output, etag_as_hexencoded_string):
|
||||
|
||||
@ -194,7 +194,8 @@ def toc_anchor_map(toc):
|
||||
if name and node['id'] not in seen_map[name]:
|
||||
ans[name].append({'id':node['id'], 'frag':node['frag']})
|
||||
seen_map[name].add(node['id'])
|
||||
tuple(map(process_node, node['children']))
|
||||
for i in node['children']:
|
||||
process_node(i)
|
||||
|
||||
process_node(toc)
|
||||
return dict(ans)
|
||||
|
||||
@ -266,14 +266,15 @@ def main(args):
|
||||
|
||||
for c in chars:
|
||||
if '-' in c:
|
||||
parts = [x.strip() for x in c.split('-')]
|
||||
parts = tuple(x.strip() for x in c.split('-'))
|
||||
if len(parts) != 2:
|
||||
prints('Invalid range:', c, file=sys.stderr)
|
||||
raise SystemExit(1)
|
||||
if opts.codes:
|
||||
parts = tuple(map(conv_code, parts))
|
||||
tuple(map(not_single, parts))
|
||||
ranges.add(tuple(parts))
|
||||
for i in parts:
|
||||
not_single(i)
|
||||
ranges.add(parts)
|
||||
else:
|
||||
if opts.codes:
|
||||
c = conv_code(c)
|
||||
|
||||
574
src/sgmllib.py
574
src/sgmllib.py
@ -1,574 +0,0 @@
|
||||
"""A parser for SGML, using the derived class as a static DTD."""
|
||||
# Needed for feedparser under python 3 where this module has been removed
|
||||
|
||||
# XXX This only supports those SGML features used by HTML.
|
||||
|
||||
# XXX There should be a way to distinguish between PCDATA (parsed
|
||||
# character data -- the normal case), RCDATA (replaceable character
|
||||
# data -- only char and entity references and end tags are special)
|
||||
# and CDATA (character data -- only end tags are special). RCDATA is
|
||||
# not supported at all.
|
||||
|
||||
import _markupbase
|
||||
import re
|
||||
|
||||
__all__ = ["SGMLParser", "SGMLParseError"]
|
||||
|
||||
# Regular expressions used for parsing
|
||||
|
||||
interesting = re.compile('[&<]')
|
||||
incomplete = re.compile(
|
||||
'&([a-zA-Z][a-zA-Z0-9]*|#[0-9]*)?|'
|
||||
'<([a-zA-Z][^<>]*|'
|
||||
'/([a-zA-Z][^<>]*)?|'
|
||||
'![^<>]*)?'
|
||||
)
|
||||
|
||||
entityref = re.compile('&([a-zA-Z][-.a-zA-Z0-9]*)[^a-zA-Z0-9]')
|
||||
charref = re.compile('&#([0-9]+)[^0-9]')
|
||||
|
||||
starttagopen = re.compile('<[>a-zA-Z]')
|
||||
shorttagopen = re.compile('<[a-zA-Z][-.a-zA-Z0-9]*/')
|
||||
shorttag = re.compile('<([a-zA-Z][-.a-zA-Z0-9]*)/([^/]*)/')
|
||||
piclose = re.compile('>')
|
||||
endbracket = re.compile('[<>]')
|
||||
tagfind = re.compile('[a-zA-Z][-_.a-zA-Z0-9]*')
|
||||
attrfind = re.compile(
|
||||
r'\s*([a-zA-Z_][-:.a-zA-Z_0-9]*)(\s*=\s*'
|
||||
r'(\'[^\']*\'|"[^"]*"|[][\-a-zA-Z0-9./,:;+*%?!&$\(\)_#=~\'"@]*))?'
|
||||
)
|
||||
|
||||
|
||||
class SGMLParseError(RuntimeError):
|
||||
"""Exception raised for all parse errors."""
|
||||
pass
|
||||
|
||||
|
||||
# SGML parser base class -- find tags and call handler functions.
|
||||
# Usage: p = SGMLParser(); p.feed(data); ...; p.close().
|
||||
# The dtd is defined by deriving a class which defines methods
|
||||
# with special names to handle tags: start_foo and end_foo to handle
|
||||
# <foo> and </foo>, respectively, or do_foo to handle <foo> by itself.
|
||||
# (Tags are converted to lower case for this purpose.) The data
|
||||
# between tags is passed to the parser by calling self.handle_data()
|
||||
# with some data as argument (the data may be split up in arbitrary
|
||||
# chunks). Entity references are passed by calling
|
||||
# self.handle_entityref() with the entity reference as argument.
|
||||
|
||||
|
||||
class SGMLParser(_markupbase.ParserBase):
|
||||
# Definition of entities -- derived classes may override
|
||||
entity_or_charref = re.compile(
|
||||
'&(?:'
|
||||
'([a-zA-Z][-.a-zA-Z0-9]*)|#([0-9]+)'
|
||||
')(;?)'
|
||||
)
|
||||
|
||||
def __init__(self, verbose=0):
|
||||
"""Initialize and reset this instance."""
|
||||
self.verbose = verbose
|
||||
self.reset()
|
||||
|
||||
def reset(self):
|
||||
"""Reset this instance. Loses all unprocessed data."""
|
||||
self.__starttag_text = None
|
||||
self.rawdata = ''
|
||||
self.stack = []
|
||||
self.lasttag = '???'
|
||||
self.nomoretags = 0
|
||||
self.literal = 0
|
||||
_markupbase.ParserBase.reset(self)
|
||||
|
||||
def setnomoretags(self):
|
||||
"""Enter literal mode (CDATA) till EOF.
|
||||
|
||||
Intended for derived classes only.
|
||||
"""
|
||||
self.nomoretags = self.literal = 1
|
||||
|
||||
def setliteral(self, *args):
|
||||
"""Enter literal mode (CDATA).
|
||||
|
||||
Intended for derived classes only.
|
||||
"""
|
||||
self.literal = 1
|
||||
|
||||
def feed(self, data):
|
||||
"""Feed some data to the parser.
|
||||
|
||||
Call this as often as you want, with as little or as much text
|
||||
as you want (may include '\n'). (This just saves the text,
|
||||
all the processing is done by goahead().)
|
||||
"""
|
||||
|
||||
self.rawdata = self.rawdata + data
|
||||
self.goahead(0)
|
||||
|
||||
def close(self):
|
||||
"""Handle the remaining data."""
|
||||
self.goahead(1)
|
||||
|
||||
def error(self, message):
|
||||
raise SGMLParseError(message)
|
||||
|
||||
# Internal -- handle data as far as reasonable. May leave state
|
||||
# and data to be processed by a subsequent call. If 'end' is
|
||||
# true, force handling all data as if followed by EOF marker.
|
||||
def goahead(self, end):
|
||||
rawdata = self.rawdata
|
||||
i = 0
|
||||
n = len(rawdata)
|
||||
while i < n:
|
||||
if self.nomoretags:
|
||||
self.handle_data(rawdata[i:n])
|
||||
i = n
|
||||
break
|
||||
match = interesting.search(rawdata, i)
|
||||
if match:
|
||||
j = match.start()
|
||||
else:
|
||||
j = n
|
||||
if i < j:
|
||||
self.handle_data(rawdata[i:j])
|
||||
i = j
|
||||
if i == n:
|
||||
break
|
||||
if rawdata[i] == '<':
|
||||
if starttagopen.match(rawdata, i):
|
||||
if self.literal:
|
||||
self.handle_data(rawdata[i])
|
||||
i = i + 1
|
||||
continue
|
||||
k = self.parse_starttag(i)
|
||||
if k < 0:
|
||||
break
|
||||
i = k
|
||||
continue
|
||||
if rawdata.startswith("</", i):
|
||||
k = self.parse_endtag(i)
|
||||
if k < 0:
|
||||
break
|
||||
i = k
|
||||
self.literal = 0
|
||||
continue
|
||||
if self.literal:
|
||||
if n > (i + 1):
|
||||
self.handle_data("<")
|
||||
i = i + 1
|
||||
else:
|
||||
# incomplete
|
||||
break
|
||||
continue
|
||||
if rawdata.startswith("<!--", i):
|
||||
# Strictly speaking, a comment is --.*--
|
||||
# within a declaration tag <!...>.
|
||||
# This should be removed,
|
||||
# and comments handled only in parse_declaration.
|
||||
k = self.parse_comment(i)
|
||||
if k < 0:
|
||||
break
|
||||
i = k
|
||||
continue
|
||||
if rawdata.startswith("<?", i):
|
||||
k = self.parse_pi(i)
|
||||
if k < 0:
|
||||
break
|
||||
i = i + k
|
||||
continue
|
||||
if rawdata.startswith("<!", i):
|
||||
# This is some sort of declaration; in "HTML as
|
||||
# deployed," this should only be the document type
|
||||
# declaration ("<!DOCTYPE html...>").
|
||||
k = self.parse_declaration(i)
|
||||
if k < 0:
|
||||
break
|
||||
i = k
|
||||
continue
|
||||
elif rawdata[i] == '&':
|
||||
if self.literal:
|
||||
self.handle_data(rawdata[i])
|
||||
i = i + 1
|
||||
continue
|
||||
match = charref.match(rawdata, i)
|
||||
if match:
|
||||
name = match.group(1)
|
||||
self.handle_charref(name)
|
||||
i = match.end(0)
|
||||
if rawdata[i - 1] != ';':
|
||||
i = i - 1
|
||||
continue
|
||||
match = entityref.match(rawdata, i)
|
||||
if match:
|
||||
name = match.group(1)
|
||||
self.handle_entityref(name)
|
||||
i = match.end(0)
|
||||
if rawdata[i - 1] != ';':
|
||||
i = i - 1
|
||||
continue
|
||||
else:
|
||||
self.error('neither < nor & ??')
|
||||
# We get here only if incomplete matches but
|
||||
# nothing else
|
||||
match = incomplete.match(rawdata, i)
|
||||
if not match:
|
||||
self.handle_data(rawdata[i])
|
||||
i = i + 1
|
||||
continue
|
||||
j = match.end(0)
|
||||
if j == n:
|
||||
break # Really incomplete
|
||||
self.handle_data(rawdata[i:j])
|
||||
i = j
|
||||
# end while
|
||||
if end and i < n:
|
||||
self.handle_data(rawdata[i:n])
|
||||
i = n
|
||||
self.rawdata = rawdata[i:]
|
||||
# XXX if end: check for empty stack
|
||||
|
||||
# Extensions for the DOCTYPE scanner:
|
||||
_decl_otherchars = '='
|
||||
|
||||
# Internal -- parse processing instr, return length or -1 if not terminated
|
||||
def parse_pi(self, i):
|
||||
rawdata = self.rawdata
|
||||
if rawdata[i:i + 2] != '<?':
|
||||
self.error('unexpected call to parse_pi()')
|
||||
match = piclose.search(rawdata, i + 2)
|
||||
if not match:
|
||||
return -1
|
||||
j = match.start(0)
|
||||
self.handle_pi(rawdata[i + 2:j])
|
||||
j = match.end(0)
|
||||
return j - i
|
||||
|
||||
def get_starttag_text(self):
|
||||
return self.__starttag_text
|
||||
|
||||
# Internal -- handle starttag, return length or -1 if not terminated
|
||||
def parse_starttag(self, i):
|
||||
self.__starttag_text = None
|
||||
start_pos = i
|
||||
rawdata = self.rawdata
|
||||
if shorttagopen.match(rawdata, i):
|
||||
# SGML shorthand: <tag/data/ == <tag>data</tag>
|
||||
# XXX Can data contain &... (entity or char refs)?
|
||||
# XXX Can data contain < or > (tag characters)?
|
||||
# XXX Can there be whitespace before the first /?
|
||||
match = shorttag.match(rawdata, i)
|
||||
if not match:
|
||||
return -1
|
||||
tag, data = match.group(1, 2)
|
||||
self.__starttag_text = '<%s/' % tag
|
||||
tag = tag.lower()
|
||||
k = match.end(0)
|
||||
self.finish_shorttag(tag, data)
|
||||
self.__starttag_text = rawdata[start_pos:match.end(1) + 1]
|
||||
return k
|
||||
# XXX The following should skip matching quotes (' or ")
|
||||
# As a shortcut way to exit, this isn't so bad, but shouldn't
|
||||
# be used to locate the actual end of the start tag since the
|
||||
# < or > characters may be embedded in an attribute value.
|
||||
match = endbracket.search(rawdata, i + 1)
|
||||
if not match:
|
||||
return -1
|
||||
j = match.start(0)
|
||||
# Now parse the data between i+1 and j into a tag and attrs
|
||||
attrs = []
|
||||
if rawdata[i:i + 2] == '<>':
|
||||
# SGML shorthand: <> == <last open tag seen>
|
||||
k = j
|
||||
tag = self.lasttag
|
||||
else:
|
||||
match = tagfind.match(rawdata, i + 1)
|
||||
if not match:
|
||||
self.error('unexpected call to parse_starttag')
|
||||
k = match.end(0)
|
||||
tag = rawdata[i + 1:k].lower()
|
||||
self.lasttag = tag
|
||||
while k < j:
|
||||
match = attrfind.match(rawdata, k)
|
||||
if not match:
|
||||
break
|
||||
attrname, rest, attrvalue = match.group(1, 2, 3)
|
||||
if not rest:
|
||||
attrvalue = attrname
|
||||
else:
|
||||
if (
|
||||
attrvalue[:1] == "'" == attrvalue[-1:] or
|
||||
attrvalue[:1] == '"' == attrvalue[-1:]
|
||||
):
|
||||
# strip quotes
|
||||
attrvalue = attrvalue[1:-1]
|
||||
attrvalue = self.entity_or_charref.sub(self._convert_ref, attrvalue)
|
||||
attrs.append((attrname.lower(), attrvalue))
|
||||
k = match.end(0)
|
||||
if rawdata[j] == '>':
|
||||
j = j + 1
|
||||
self.__starttag_text = rawdata[start_pos:j]
|
||||
self.finish_starttag(tag, attrs)
|
||||
return j
|
||||
|
||||
# Internal -- convert entity or character reference
|
||||
def _convert_ref(self, match):
|
||||
if match.group(2):
|
||||
return self.convert_charref(match.group(2)) or \
|
||||
'&#%s%s' % match.groups()[1:]
|
||||
elif match.group(3):
|
||||
return self.convert_entityref(match.group(1)) or \
|
||||
'&%s;' % match.group(1)
|
||||
else:
|
||||
return '&%s' % match.group(1)
|
||||
|
||||
# Internal -- parse endtag
|
||||
def parse_endtag(self, i):
|
||||
rawdata = self.rawdata
|
||||
match = endbracket.search(rawdata, i + 1)
|
||||
if not match:
|
||||
return -1
|
||||
j = match.start(0)
|
||||
tag = rawdata[i + 2:j].strip().lower()
|
||||
if rawdata[j] == '>':
|
||||
j = j + 1
|
||||
self.finish_endtag(tag)
|
||||
return j
|
||||
|
||||
# Internal -- finish parsing of <tag/data/ (same as <tag>data</tag>)
|
||||
def finish_shorttag(self, tag, data):
|
||||
self.finish_starttag(tag, [])
|
||||
self.handle_data(data)
|
||||
self.finish_endtag(tag)
|
||||
|
||||
# Internal -- finish processing of start tag
|
||||
# Return -1 for unknown tag, 0 for open-only tag, 1 for balanced tag
|
||||
def finish_starttag(self, tag, attrs):
|
||||
try:
|
||||
method = getattr(self, 'start_' + tag)
|
||||
except AttributeError:
|
||||
try:
|
||||
method = getattr(self, 'do_' + tag)
|
||||
except AttributeError:
|
||||
self.unknown_starttag(tag, attrs)
|
||||
return -1
|
||||
else:
|
||||
self.handle_starttag(tag, method, attrs)
|
||||
return 0
|
||||
else:
|
||||
self.stack.append(tag)
|
||||
self.handle_starttag(tag, method, attrs)
|
||||
return 1
|
||||
|
||||
# Internal -- finish processing of end tag
|
||||
def finish_endtag(self, tag):
|
||||
if not tag:
|
||||
found = len(self.stack) - 1
|
||||
if found < 0:
|
||||
self.unknown_endtag(tag)
|
||||
return
|
||||
else:
|
||||
if tag not in self.stack:
|
||||
try:
|
||||
method = getattr(self, 'end_' + tag)
|
||||
except AttributeError:
|
||||
self.unknown_endtag(tag)
|
||||
else:
|
||||
self.report_unbalanced(tag)
|
||||
return
|
||||
found = len(self.stack)
|
||||
for i in range(found):
|
||||
if self.stack[i] == tag:
|
||||
found = i
|
||||
while len(self.stack) > found:
|
||||
tag = self.stack[-1]
|
||||
try:
|
||||
method = getattr(self, 'end_' + tag)
|
||||
except AttributeError:
|
||||
method = None
|
||||
if method:
|
||||
self.handle_endtag(tag, method)
|
||||
else:
|
||||
self.unknown_endtag(tag)
|
||||
del self.stack[-1]
|
||||
|
||||
# Overridable -- handle start tag
|
||||
def handle_starttag(self, tag, method, attrs):
|
||||
method(attrs)
|
||||
|
||||
# Overridable -- handle end tag
|
||||
def handle_endtag(self, tag, method):
|
||||
method()
|
||||
|
||||
# Example -- report an unbalanced </...> tag.
|
||||
def report_unbalanced(self, tag):
|
||||
if self.verbose:
|
||||
print('*** Unbalanced </' + tag + '>')
|
||||
print('*** Stack:', self.stack)
|
||||
|
||||
def convert_charref(self, name):
|
||||
"""Convert character reference, may be overridden."""
|
||||
try:
|
||||
n = int(name)
|
||||
except ValueError:
|
||||
return
|
||||
if not 0 <= n <= 127:
|
||||
return
|
||||
return self.convert_codepoint(n)
|
||||
|
||||
def convert_codepoint(self, codepoint):
|
||||
return chr(codepoint)
|
||||
|
||||
def handle_charref(self, name):
|
||||
"""Handle character reference, no need to override."""
|
||||
replacement = self.convert_charref(name)
|
||||
if replacement is None:
|
||||
self.unknown_charref(name)
|
||||
else:
|
||||
self.handle_data(replacement)
|
||||
|
||||
# Definition of entities -- derived classes may override
|
||||
entitydefs = \
|
||||
{'lt': '<', 'gt': '>', 'amp': '&', 'quot': '"', 'apos': '\''}
|
||||
|
||||
def convert_entityref(self, name):
|
||||
"""Convert entity references.
|
||||
|
||||
As an alternative to overriding this method; one can tailor the
|
||||
results by setting up the self.entitydefs mapping appropriately.
|
||||
"""
|
||||
table = self.entitydefs
|
||||
if name in table:
|
||||
return table[name]
|
||||
else:
|
||||
return
|
||||
|
||||
def handle_entityref(self, name):
|
||||
"""Handle entity references, no need to override."""
|
||||
replacement = self.convert_entityref(name)
|
||||
if replacement is None:
|
||||
self.unknown_entityref(name)
|
||||
else:
|
||||
self.handle_data(replacement)
|
||||
|
||||
# Example -- handle data, should be overridden
|
||||
def handle_data(self, data):
|
||||
pass
|
||||
|
||||
# Example -- handle comment, could be overridden
|
||||
def handle_comment(self, data):
|
||||
pass
|
||||
|
||||
# Example -- handle declaration, could be overridden
|
||||
def handle_decl(self, decl):
|
||||
pass
|
||||
|
||||
# Example -- handle processing instruction, could be overridden
|
||||
def handle_pi(self, data):
|
||||
pass
|
||||
|
||||
# To be overridden -- handlers for unknown objects
|
||||
def unknown_starttag(self, tag, attrs):
|
||||
pass
|
||||
|
||||
def unknown_endtag(self, tag):
|
||||
pass
|
||||
|
||||
def unknown_charref(self, ref):
|
||||
pass
|
||||
|
||||
def unknown_entityref(self, ref):
|
||||
pass
|
||||
|
||||
|
||||
class TestSGMLParser(SGMLParser):
|
||||
|
||||
def __init__(self, verbose=0):
|
||||
self.testdata = ""
|
||||
SGMLParser.__init__(self, verbose)
|
||||
|
||||
def handle_data(self, data):
|
||||
self.testdata = self.testdata + data
|
||||
if len(repr(self.testdata)) >= 70:
|
||||
self.flush()
|
||||
|
||||
def flush(self):
|
||||
data = self.testdata
|
||||
if data:
|
||||
self.testdata = ""
|
||||
print('data:', repr(data))
|
||||
|
||||
def handle_comment(self, data):
|
||||
self.flush()
|
||||
r = repr(data)
|
||||
if len(r) > 68:
|
||||
r = r[:32] + '...' + r[-32:]
|
||||
print('comment:', r)
|
||||
|
||||
def unknown_starttag(self, tag, attrs):
|
||||
self.flush()
|
||||
if not attrs:
|
||||
print('start tag: <' + tag + '>')
|
||||
else:
|
||||
print('start tag: <' + tag, end=' ')
|
||||
for name, value in attrs:
|
||||
print(name + '=' + '"' + value + '"', end=' ')
|
||||
print('>')
|
||||
|
||||
def unknown_endtag(self, tag):
|
||||
self.flush()
|
||||
print('end tag: </' + tag + '>')
|
||||
|
||||
def unknown_entityref(self, ref):
|
||||
self.flush()
|
||||
print('*** unknown entity ref: &' + ref + ';')
|
||||
|
||||
def unknown_charref(self, ref):
|
||||
self.flush()
|
||||
print('*** unknown char ref: &#' + ref + ';')
|
||||
|
||||
def unknown_decl(self, data):
|
||||
self.flush()
|
||||
print('*** unknown decl: [' + data + ']')
|
||||
|
||||
def close(self):
|
||||
SGMLParser.close(self)
|
||||
self.flush()
|
||||
|
||||
|
||||
def test(args=None):
|
||||
import sys
|
||||
|
||||
if args is None:
|
||||
args = sys.argv[1:]
|
||||
|
||||
if args and args[0] == '-s':
|
||||
args = args[1:]
|
||||
klass = SGMLParser
|
||||
else:
|
||||
klass = TestSGMLParser
|
||||
|
||||
if args:
|
||||
file = args[0]
|
||||
else:
|
||||
file = 'test.html'
|
||||
|
||||
if file == '-':
|
||||
f = sys.stdin
|
||||
else:
|
||||
try:
|
||||
f = open(file, 'r')
|
||||
except IOError as msg:
|
||||
print(file, ":", msg)
|
||||
sys.exit(1)
|
||||
|
||||
data = f.read()
|
||||
if f is not sys.stdin:
|
||||
f.close()
|
||||
|
||||
x = klass()
|
||||
for c in data:
|
||||
x.feed(c)
|
||||
x.close()
|
||||
|
||||
|
||||
if __name__ == '__main__':
|
||||
test()
|
||||
Loading…
x
Reference in New Issue
Block a user