From c7bf67e6c3cc430e3d7a9b26befdcaaca216c8f0 Mon Sep 17 00:00:00 2001 From: Kovid Goyal Date: Sat, 3 Sep 2011 14:42:04 -0600 Subject: [PATCH] Various fixes to markdown found by the automatic python checker --- setup/check.py | 8 ++-- .../ebooks/markdown/blockprocessors.py | 44 +++++++++---------- src/calibre/ebooks/markdown/commandline.py | 4 +- src/calibre/ebooks/markdown/etree_loader.py | 2 + .../ebooks/markdown/extensions/def_list.py | 8 ++-- .../ebooks/markdown/extensions/footnotes.py | 16 +++---- .../ebooks/markdown/extensions/headerid.py | 9 ++-- src/calibre/ebooks/markdown/inlinepatterns.py | 2 +- src/calibre/ebooks/markdown/odict.py | 6 +-- src/calibre/ebooks/markdown/treeprocessors.py | 8 ++-- 10 files changed, 53 insertions(+), 54 deletions(-) diff --git a/setup/check.py b/setup/check.py index 6c0acd78ae..9142de27c1 100644 --- a/setup/check.py +++ b/setup/check.py @@ -63,10 +63,10 @@ class Check(Command): for f in x[-1]: y = self.j(x[0], f) mtime = os.stat(y).st_mtime - if f.endswith('.py') and f not in ('ptempfile.py', 'feedparser.py', - 'pyparsing.py', 'markdown.py') and \ - 'genshi' not in y and cache.get(y, 0) != mtime and \ - 'prs500/driver.py' not in y: + if (f.endswith('.py') and f not in ('ptempfile.py', 'feedparser.py', + 'pyparsing.py', 'markdown.py') and + 'genshi' not in y and cache.get(y, 0) != mtime and + 'prs500/driver.py' not in y): yield y, mtime for x in os.walk(self.j(self.d(self.SRC), 'recipes')): diff --git a/src/calibre/ebooks/markdown/blockprocessors.py b/src/calibre/ebooks/markdown/blockprocessors.py index 79f4db93bc..e42d0f55e6 100644 --- a/src/calibre/ebooks/markdown/blockprocessors.py +++ b/src/calibre/ebooks/markdown/blockprocessors.py @@ -3,10 +3,10 @@ CORE MARKDOWN BLOCKPARSER ============================================================================= This parser handles basic parsing of Markdown blocks. It doesn't concern itself -with inline elements such as **bold** or *italics*, but rather just catches +with inline elements such as **bold** or *italics*, but rather just catches blocks, lists, quotes, etc. -The BlockParser is made up of a bunch of BlockProssors, each handling a +The BlockParser is made up of a bunch of BlockProssors, each handling a different type of block. Extensions may add/replace/remove BlockProcessors as they need to alter how markdown blocks are parsed. @@ -16,8 +16,8 @@ import re import markdown class BlockProcessor: - """ Base class for block processors. - + """ Base class for block processors. + Each subclass will provide the methods below to work with the source and tree. Each processor will need to define it's own ``test`` and ``run`` methods. The ``test`` method should return True or False, to indicate @@ -58,32 +58,32 @@ class BlockProcessor: return '\n'.join(lines) def test(self, parent, block): - """ Test for block type. Must be overridden by subclasses. - + """ Test for block type. Must be overridden by subclasses. + As the parser loops through processors, it will call the ``test`` method on each to determine if the given block of text is of that type. This method must return a boolean ``True`` or ``False``. The actual method of - testing is left to the needs of that particular block type. It could + testing is left to the needs of that particular block type. It could be as simple as ``block.startswith(some_string)`` or a complex regular expression. As the block type may be different depending on the parent - of the block (i.e. inside a list), the parent etree element is also + of the block (i.e. inside a list), the parent etree element is also provided and may be used as part of the test. Keywords: - + * ``parent``: A etree element which will be the parent of the block. - * ``block``: A block of text from the source which has been split at + * ``block``: A block of text from the source which has been split at blank lines. """ pass def run(self, parent, blocks): - """ Run processor. Must be overridden by subclasses. - + """ Run processor. Must be overridden by subclasses. + When the parser determines the appropriate type of a block, the parser will call the corresponding processor's ``run`` method. This method should parse the individual lines of the block and append them to - the etree. + the etree. Note that both the ``parent`` and ``etree`` keywords are pointers to instances of the objects which should be edited in place. Each @@ -103,8 +103,8 @@ class BlockProcessor: class ListIndentProcessor(BlockProcessor): - """ Process children of list items. - + """ Process children of list items. + Example: * a list item process this part @@ -154,7 +154,7 @@ class ListIndentProcessor(BlockProcessor): """ Create a new li and parse the block with it as the parent. """ li = markdown.etree.SubElement(parent, 'li') self.parser.parseBlocks(li, [block]) - + def get_level(self, parent, block): """ Get level of indent based on list level. """ # Get indent level @@ -188,7 +188,7 @@ class CodeBlockProcessor(BlockProcessor): def test(self, parent, block): return block.startswith(' '*markdown.TAB_LENGTH) - + def run(self, parent, blocks): sibling = self.lastChild(parent) block = blocks.pop(0) @@ -208,7 +208,7 @@ class CodeBlockProcessor(BlockProcessor): block, theRest = self.detab(block) code.text = markdown.AtomicString('%s\n' % block.rstrip()) if theRest: - # This block contained unindented line(s) after the first indented + # This block contained unindented line(s) after the first indented # line. Insert these lines as the first block of the master blocks # list for future processing. blocks.insert(0, theRest) @@ -229,7 +229,7 @@ class BlockQuoteProcessor(BlockProcessor): # Pass lines before blockquote in recursively for parsing forst. self.parser.parseBlocks(parent, [before]) # Remove ``> `` from begining of each line. - block = '\n'.join([self.clean(line) for line in + block = '\n'.join([self.clean(line) for line in block[m.start():].split('\n')]) sibling = self.lastChild(parent) if sibling and sibling.tag == "blockquote": @@ -355,7 +355,7 @@ class HashHeaderProcessor(BlockProcessor): blocks.insert(0, after) else: # This should never happen, but just in case... - message(CRITICAL, "We've got a problem header!") + print("We've got a problem header!") class SetextHeaderProcessor(BlockProcessor): @@ -407,7 +407,7 @@ class HRProcessor(BlockProcessor): # Recursively parse lines before hr so they get parsed first. self.parser.parseBlocks(parent, ['\n'.join(prelines)]) # create hr - hr = markdown.etree.SubElement(parent, 'hr') + markdown.etree.SubElement(parent, 'hr') # check for lines in block after hr. lines = lines[len(prelines)+1:] if len(lines): @@ -418,7 +418,7 @@ class HRProcessor(BlockProcessor): class EmptyBlockProcessor(BlockProcessor): """ Process blocks and start with an empty line. """ - # Detect a block that only contains whitespace + # Detect a block that only contains whitespace # or only whitespace on the first line. RE = re.compile(r'^\s*\n') diff --git a/src/calibre/ebooks/markdown/commandline.py b/src/calibre/ebooks/markdown/commandline.py index 1eedc6dbb1..9be4026444 100644 --- a/src/calibre/ebooks/markdown/commandline.py +++ b/src/calibre/ebooks/markdown/commandline.py @@ -9,7 +9,7 @@ Markdown is called from the command line. import markdown import sys import logging -from logging import DEBUG, INFO, WARN, ERROR, CRITICAL +from logging import DEBUG, INFO, CRITICAL EXECUTABLE_NAME_FOR_USAGE = "python markdown.py" """ The name used in the usage statement displayed for python versions < 2.3. @@ -57,7 +57,7 @@ def parse_options(): parser.add_option("-s", "--safe", dest="safe", default=False, metavar="SAFE_MODE", help="safe mode ('replace', 'remove' or 'escape' user's HTML tag)") - parser.add_option("-o", "--output_format", dest="output_format", + parser.add_option("-o", "--output_format", dest="output_format", default='xhtml1', metavar="OUTPUT_FORMAT", help="Format of output. One of 'xhtml1' (default) or 'html4'.") parser.add_option("--noisy", diff --git a/src/calibre/ebooks/markdown/etree_loader.py b/src/calibre/ebooks/markdown/etree_loader.py index e2599b2cb9..2591328084 100644 --- a/src/calibre/ebooks/markdown/etree_loader.py +++ b/src/calibre/ebooks/markdown/etree_loader.py @@ -8,9 +8,11 @@ def importETree(): etree_in_c = None try: # Is it Python 2.5+ with C implemenation of ElementTree installed? import xml.etree.cElementTree as etree_in_c + etree_in_c except ImportError: try: # Is it Python 2.5+ with Python implementation of ElementTree? import xml.etree.ElementTree as etree + etree except ImportError: try: # An earlier version of Python with cElementTree installed? import cElementTree as etree_in_c diff --git a/src/calibre/ebooks/markdown/extensions/def_list.py b/src/calibre/ebooks/markdown/extensions/def_list.py index 5bc1eb56b0..b5419bdfd2 100644 --- a/src/calibre/ebooks/markdown/extensions/def_list.py +++ b/src/calibre/ebooks/markdown/extensions/def_list.py @@ -8,7 +8,7 @@ Added parsing of Definition Lists to Python-Markdown. A simple example: Apple - : Pomaceous fruit of plants of the genus Malus in + : Pomaceous fruit of plants of the genus Malus in the family Rosaceae. : An american computer company. @@ -80,11 +80,11 @@ class DefListIndentProcessor(markdown.blockprocessors.ListIndentProcessor): ITEM_TYPES = ['dd'] LIST_TYPES = ['dl'] - def create_item(parent, block): + def create_item(self, parent, block): """ Create a new dd and parse the block with it as the parent. """ dd = markdown.etree.SubElement(parent, 'dd') self.parser.parseBlocks(dd, [block]) - + class DefListExtension(markdown.Extension): @@ -95,7 +95,7 @@ class DefListExtension(markdown.Extension): md.parser.blockprocessors.add('defindent', DefListIndentProcessor(md.parser), '>indent') - md.parser.blockprocessors.add('deflist', + md.parser.blockprocessors.add('deflist', DefListProcessor(md.parser), '>ulist') diff --git a/src/calibre/ebooks/markdown/extensions/footnotes.py b/src/calibre/ebooks/markdown/extensions/footnotes.py index 729b49b2e6..df137f5d53 100644 --- a/src/calibre/ebooks/markdown/extensions/footnotes.py +++ b/src/calibre/ebooks/markdown/extensions/footnotes.py @@ -43,7 +43,7 @@ class FootnoteExtension(markdown.Extension): for key, value in configs: self.config[key][0] = value - + self.reset() def extendMarkdown(self, md, md_globals): @@ -82,7 +82,7 @@ class FootnoteExtension(markdown.Extension): return (child, element), False finder(child) return None - + res = finder(root) return res @@ -106,7 +106,7 @@ class FootnoteExtension(markdown.Extension): div = etree.Element("div") div.set('class', 'footnote') - hr = etree.SubElement(div, "hr") + etree.SubElement(div, "hr") ol = etree.SubElement(div, "ol") for id in self.footnotes.keys(): @@ -149,9 +149,9 @@ class FootnotePreprocessor(markdown.preprocessors.Preprocessor): Keywords: * lines: A list of lines of text - + Return: A list of lines with footnote definitions removed. - + """ i, id, footnote = self._findFootnoteDefinition(lines) @@ -175,9 +175,9 @@ class FootnotePreprocessor(markdown.preprocessors.Preprocessor): * lines: A list of lines of text. Return: A three item tuple containing the index of the first line of a - footnote definition, the id of the definition and the body of the + footnote definition, the id of the definition and the body of the definition. - + """ counter = 0 for line in lines: @@ -199,7 +199,6 @@ class FootnotePreprocessor(markdown.preprocessors.Preprocessor): """ items = [] - item = -1 i = 0 # to keep track of where we are def detab(line): @@ -277,7 +276,6 @@ class FootnoteTreeprocessor(markdown.treeprocessors.Treeprocessor): ind = element.getchildren().find(child) element.getchildren().insert(ind + 1, footnotesDiv) child.tail = None - fnPlaceholder.parent.replaceChild(fnPlaceholder, footnotesDiv) else: root.append(footnotesDiv) diff --git a/src/calibre/ebooks/markdown/extensions/headerid.py b/src/calibre/ebooks/markdown/extensions/headerid.py index 7433673736..0ffd91ee93 100644 --- a/src/calibre/ebooks/markdown/extensions/headerid.py +++ b/src/calibre/ebooks/markdown/extensions/headerid.py @@ -57,7 +57,7 @@ Copyright 2007-2008 [Waylan Limberg](http://achinghead.com/). Project website: Contact: markdown@freewisdom.org -License: BSD (see ../docs/LICENSE for details) +License: BSD (see ../docs/LICENSE for details) Dependencies: * [Python 2.3+](http://python.org) @@ -66,7 +66,6 @@ Dependencies: """ import calibre.ebooks.markdown.markdown as markdown -from calibre.ebooks.markdown.markdown import etree import re from string import ascii_lowercase, digits, punctuation @@ -106,7 +105,7 @@ class HeaderIdProcessor(markdown.blockprocessors.BlockProcessor): # Create header using named groups from RE start_level, force_id = self._get_meta() level = len(m.group('level')) + start_level - if level > 6: + if level > 6: level = 6 h = markdown.etree.SubElement(parent, 'h%d' % level) h.text = m.group('header').strip() @@ -119,7 +118,7 @@ class HeaderIdProcessor(markdown.blockprocessors.BlockProcessor): blocks.insert(0, after) else: # This should never happen, but just in case... - message(CRITICAL, "We've got a problem header!") + print ("We've got a problem header!") def _get_meta(self): """ Return meta data suported by this ext as a tuple """ @@ -128,7 +127,7 @@ class HeaderIdProcessor(markdown.blockprocessors.BlockProcessor): if hasattr(self.md, 'Meta'): if self.md.Meta.has_key('header_level'): level = int(self.md.Meta['header_level'][0]) - 1 - if self.md.Meta.has_key('header_forceid'): + if self.md.Meta.has_key('header_forceid'): force = self._str2bool(self.md.Meta['header_forceid'][0]) return level, force diff --git a/src/calibre/ebooks/markdown/inlinepatterns.py b/src/calibre/ebooks/markdown/inlinepatterns.py index 89fa3b2ef4..217697ed8d 100644 --- a/src/calibre/ebooks/markdown/inlinepatterns.py +++ b/src/calibre/ebooks/markdown/inlinepatterns.py @@ -47,6 +47,7 @@ from urlparse import urlparse, urlunparse import sys if sys.version >= "3.0": from html import entities as htmlentitydefs + htmlentitydefs else: import htmlentitydefs @@ -215,7 +216,6 @@ class HtmlPattern (Pattern): """ Store raw inline html and return a placeholder. """ def handleMatch (self, m): rawhtml = m.group(2) - inline = True place_holder = self.markdown.htmlStash.store(rawhtml) return place_holder diff --git a/src/calibre/ebooks/markdown/odict.py b/src/calibre/ebooks/markdown/odict.py index bf3ef07182..277cd4ebba 100644 --- a/src/calibre/ebooks/markdown/odict.py +++ b/src/calibre/ebooks/markdown/odict.py @@ -1,7 +1,7 @@ class OrderedDict(dict): """ A dictionary that keeps its keys in the order in which they're inserted. - + Copied from Django's SortedDict with some modifications. """ @@ -156,7 +156,7 @@ class OrderedDict(dict): self.keyOrder.insert(i, key) else: self.keyOrder.append(key) - except Error: + except Exception as e: # restore to prevent data loss and reraise self.keyOrder.insert(n, key) - raise Error + raise e diff --git a/src/calibre/ebooks/markdown/treeprocessors.py b/src/calibre/ebooks/markdown/treeprocessors.py index 1dc612a95e..0604b1970f 100644 --- a/src/calibre/ebooks/markdown/treeprocessors.py +++ b/src/calibre/ebooks/markdown/treeprocessors.py @@ -24,8 +24,8 @@ class Treeprocessor(Processor): def run(self, root): """ Subclasses of Treeprocessor should implement a `run` method, which - takes a root ElementTree. This method can return another ElementTree - object, and the existing root ElementTree will be replaced, or it can + takes a root ElementTree. This method can return another ElementTree + object, and the existing root ElementTree will be replaced, or it can modify the current tree and return None. """ pass @@ -185,7 +185,7 @@ class InlineProcessor(Treeprocessor): result.append(node) else: # wrong placeholder - end = index + len(prefix) + end = index + len(self.__placeholder_prefix) linkText(data[strartIndex:end]) strartIndex = end else: @@ -278,7 +278,7 @@ class InlineProcessor(Treeprocessor): for element, lst in insertQueue: if element.text: element.text = \ - markdown.inlinepatterns.handleAttributes(element.text, + markdown.inlinepatterns.handleAttributes(element.text, element) i = 0 for newChild in lst: