mirror of
https://github.com/kovidgoyal/calibre.git
synced 2025-06-23 15:30:45 -04:00
Update Python Markdown to version 2.0
This commit is contained in:
John Schember
parent
9912bdd78f
commit
6fc606bfa6
@ -1,7 +0,0 @@
|
||||
''' Package defines lightweight markup language for processing of txt files'''
|
||||
# Initialize extensions
|
||||
from calibre.ebooks.markdown import mdx_footnotes
|
||||
from calibre.ebooks.markdown import mdx_tables
|
||||
from calibre.ebooks.markdown import mdx_toc
|
||||
|
||||
mdx_footnotes, mdx_tables, mdx_toc
|
||||
95
src/calibre/ebooks/markdown/blockparser.py
Normal file
95
src/calibre/ebooks/markdown/blockparser.py
Normal file
@ -0,0 +1,95 @@
|
||||
|
||||
import markdown
|
||||
|
||||
class State(list):
|
||||
""" Track the current and nested state of the parser.
|
||||
|
||||
This utility class is used to track the state of the BlockParser and
|
||||
support multiple levels if nesting. It's just a simple API wrapped around
|
||||
a list. Each time a state is set, that state is appended to the end of the
|
||||
list. Each time a state is reset, that state is removed from the end of
|
||||
the list.
|
||||
|
||||
Therefore, each time a state is set for a nested block, that state must be
|
||||
reset when we back out of that level of nesting or the state could be
|
||||
corrupted.
|
||||
|
||||
While all the methods of a list object are available, only the three
|
||||
defined below need be used.
|
||||
|
||||
"""
|
||||
|
||||
def set(self, state):
|
||||
""" Set a new state. """
|
||||
self.append(state)
|
||||
|
||||
def reset(self):
|
||||
""" Step back one step in nested state. """
|
||||
self.pop()
|
||||
|
||||
def isstate(self, state):
|
||||
""" Test that top (current) level is of given state. """
|
||||
if len(self):
|
||||
return self[-1] == state
|
||||
else:
|
||||
return False
|
||||
|
||||
class BlockParser:
|
||||
""" Parse Markdown blocks into an ElementTree object.
|
||||
|
||||
A wrapper class that stitches the various BlockProcessors together,
|
||||
looping through them and creating an ElementTree object.
|
||||
"""
|
||||
|
||||
def __init__(self):
|
||||
self.blockprocessors = markdown.odict.OrderedDict()
|
||||
self.state = State()
|
||||
|
||||
def parseDocument(self, lines):
|
||||
""" Parse a markdown document into an ElementTree.
|
||||
|
||||
Given a list of lines, an ElementTree object (not just a parent Element)
|
||||
is created and the root element is passed to the parser as the parent.
|
||||
The ElementTree object is returned.
|
||||
|
||||
This should only be called on an entire document, not pieces.
|
||||
|
||||
"""
|
||||
# Create a ElementTree from the lines
|
||||
self.root = markdown.etree.Element(markdown.DOC_TAG)
|
||||
self.parseChunk(self.root, '\n'.join(lines))
|
||||
return markdown.etree.ElementTree(self.root)
|
||||
|
||||
def parseChunk(self, parent, text):
|
||||
""" Parse a chunk of markdown text and attach to given etree node.
|
||||
|
||||
While the ``text`` argument is generally assumed to contain multiple
|
||||
blocks which will be split on blank lines, it could contain only one
|
||||
block. Generally, this method would be called by extensions when
|
||||
block parsing is required.
|
||||
|
||||
The ``parent`` etree Element passed in is altered in place.
|
||||
Nothing is returned.
|
||||
|
||||
"""
|
||||
self.parseBlocks(parent, text.split('\n\n'))
|
||||
|
||||
def parseBlocks(self, parent, blocks):
|
||||
""" Process blocks of markdown text and attach to given etree node.
|
||||
|
||||
Given a list of ``blocks``, each blockprocessor is stepped through
|
||||
until there are no blocks left. While an extension could potentially
|
||||
call this method directly, it's generally expected to be used internally.
|
||||
|
||||
This is a public method as an extension may need to add/alter additional
|
||||
BlockProcessors which call this method to recursively parse a nested
|
||||
block.
|
||||
|
||||
"""
|
||||
while blocks:
|
||||
for processor in self.blockprocessors.values():
|
||||
if processor.test(parent, blocks[0]):
|
||||
processor.run(parent, blocks)
|
||||
break
|
||||
|
||||
|
||||
460
src/calibre/ebooks/markdown/blockprocessors.py
Normal file
460
src/calibre/ebooks/markdown/blockprocessors.py
Normal file
@ -0,0 +1,460 @@
|
||||
"""
|
||||
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
|
||||
blocks, lists, quotes, etc.
|
||||
|
||||
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.
|
||||
|
||||
"""
|
||||
|
||||
import re
|
||||
import markdown
|
||||
|
||||
class BlockProcessor:
|
||||
""" 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
|
||||
whether the current block should be processed by this processor. If the
|
||||
test passes, the parser will call the processors ``run`` method.
|
||||
|
||||
"""
|
||||
|
||||
def __init__(self, parser=None):
|
||||
self.parser = parser
|
||||
|
||||
def lastChild(self, parent):
|
||||
""" Return the last child of an etree element. """
|
||||
if len(parent):
|
||||
return parent[-1]
|
||||
else:
|
||||
return None
|
||||
|
||||
def detab(self, text):
|
||||
""" Remove a tab from the front of each line of the given text. """
|
||||
newtext = []
|
||||
lines = text.split('\n')
|
||||
for line in lines:
|
||||
if line.startswith(' '*markdown.TAB_LENGTH):
|
||||
newtext.append(line[markdown.TAB_LENGTH:])
|
||||
elif not line.strip():
|
||||
newtext.append('')
|
||||
else:
|
||||
break
|
||||
return '\n'.join(newtext), '\n'.join(lines[len(newtext):])
|
||||
|
||||
def looseDetab(self, text, level=1):
|
||||
""" Remove a tab from front of lines but allowing dedented lines. """
|
||||
lines = text.split('\n')
|
||||
for i in range(len(lines)):
|
||||
if lines[i].startswith(' '*markdown.TAB_LENGTH*level):
|
||||
lines[i] = lines[i][markdown.TAB_LENGTH*level:]
|
||||
return '\n'.join(lines)
|
||||
|
||||
def test(self, parent, block):
|
||||
""" 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
|
||||
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
|
||||
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
|
||||
blank lines.
|
||||
"""
|
||||
pass
|
||||
|
||||
def run(self, parent, blocks):
|
||||
""" 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.
|
||||
|
||||
Note that both the ``parent`` and ``etree`` keywords are pointers
|
||||
to instances of the objects which should be edited in place. Each
|
||||
processor must make changes to the existing objects as there is no
|
||||
mechanism to return new/different objects to replace them.
|
||||
|
||||
This means that this method should be adding SubElements or adding text
|
||||
to the parent, and should remove (``pop``) or add (``insert``) items to
|
||||
the list of blocks.
|
||||
|
||||
Keywords:
|
||||
|
||||
* ``parent``: A etree element which is the parent of the current block.
|
||||
* ``blocks``: A list of all remaining blocks of the document.
|
||||
"""
|
||||
pass
|
||||
|
||||
|
||||
class ListIndentProcessor(BlockProcessor):
|
||||
""" Process children of list items.
|
||||
|
||||
Example:
|
||||
* a list item
|
||||
process this part
|
||||
|
||||
or this part
|
||||
|
||||
"""
|
||||
|
||||
INDENT_RE = re.compile(r'^(([ ]{%s})+)'% markdown.TAB_LENGTH)
|
||||
ITEM_TYPES = ['li']
|
||||
LIST_TYPES = ['ul', 'ol']
|
||||
|
||||
def test(self, parent, block):
|
||||
return block.startswith(' '*markdown.TAB_LENGTH) and \
|
||||
not self.parser.state.isstate('detabbed') and \
|
||||
(parent.tag in self.ITEM_TYPES or \
|
||||
(len(parent) and parent[-1] and \
|
||||
(parent[-1].tag in self.LIST_TYPES)
|
||||
)
|
||||
)
|
||||
|
||||
def run(self, parent, blocks):
|
||||
block = blocks.pop(0)
|
||||
level, sibling = self.get_level(parent, block)
|
||||
block = self.looseDetab(block, level)
|
||||
|
||||
self.parser.state.set('detabbed')
|
||||
if parent.tag in self.ITEM_TYPES:
|
||||
# The parent is already a li. Just parse the child block.
|
||||
self.parser.parseBlocks(parent, [block])
|
||||
elif sibling.tag in self.ITEM_TYPES:
|
||||
# The sibling is a li. Use it as parent.
|
||||
self.parser.parseBlocks(sibling, [block])
|
||||
elif len(sibling) and sibling[-1].tag in self.ITEM_TYPES:
|
||||
# The parent is a list (``ol`` or ``ul``) which has children.
|
||||
# Assume the last child li is the parent of this block.
|
||||
if sibling[-1].text:
|
||||
# If the parent li has text, that text needs to be moved to a p
|
||||
block = '%s\n\n%s' % (sibling[-1].text, block)
|
||||
sibling[-1].text = ''
|
||||
self.parser.parseChunk(sibling[-1], block)
|
||||
else:
|
||||
self.create_item(sibling, block)
|
||||
self.parser.state.reset()
|
||||
|
||||
def create_item(self, parent, block):
|
||||
""" 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
|
||||
m = self.INDENT_RE.match(block)
|
||||
if m:
|
||||
indent_level = len(m.group(1))/markdown.TAB_LENGTH
|
||||
else:
|
||||
indent_level = 0
|
||||
if self.parser.state.isstate('list'):
|
||||
# We're in a tightlist - so we already are at correct parent.
|
||||
level = 1
|
||||
else:
|
||||
# We're in a looselist - so we need to find parent.
|
||||
level = 0
|
||||
# Step through children of tree to find matching indent level.
|
||||
while indent_level > level:
|
||||
child = self.lastChild(parent)
|
||||
if child and (child.tag in self.LIST_TYPES or child.tag in self.ITEM_TYPES):
|
||||
if child.tag in self.LIST_TYPES:
|
||||
level += 1
|
||||
parent = child
|
||||
else:
|
||||
# No more child levels. If we're short of indent_level,
|
||||
# we have a code block. So we stop here.
|
||||
break
|
||||
return level, parent
|
||||
|
||||
|
||||
class CodeBlockProcessor(BlockProcessor):
|
||||
""" Process code blocks. """
|
||||
|
||||
def test(self, parent, block):
|
||||
return block.startswith(' '*markdown.TAB_LENGTH)
|
||||
|
||||
def run(self, parent, blocks):
|
||||
sibling = self.lastChild(parent)
|
||||
block = blocks.pop(0)
|
||||
theRest = ''
|
||||
if sibling and sibling.tag == "pre" and len(sibling) \
|
||||
and sibling[0].tag == "code":
|
||||
# The previous block was a code block. As blank lines do not start
|
||||
# new code blocks, append this block to the previous, adding back
|
||||
# linebreaks removed from the split into a list.
|
||||
code = sibling[0]
|
||||
block, theRest = self.detab(block)
|
||||
code.text = markdown.AtomicString('%s\n%s\n' % (code.text, block.rstrip()))
|
||||
else:
|
||||
# This is a new codeblock. Create the elements and insert text.
|
||||
pre = markdown.etree.SubElement(parent, 'pre')
|
||||
code = markdown.etree.SubElement(pre, 'code')
|
||||
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
|
||||
# line. Insert these lines as the first block of the master blocks
|
||||
# list for future processing.
|
||||
blocks.insert(0, theRest)
|
||||
|
||||
|
||||
class BlockQuoteProcessor(BlockProcessor):
|
||||
|
||||
RE = re.compile(r'(^|\n)[ ]{0,3}>[ ]?(.*)')
|
||||
|
||||
def test(self, parent, block):
|
||||
return bool(self.RE.search(block))
|
||||
|
||||
def run(self, parent, blocks):
|
||||
block = blocks.pop(0)
|
||||
m = self.RE.search(block)
|
||||
if m:
|
||||
before = block[:m.start()] # Lines before blockquote
|
||||
# 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[m.start():].split('\n')])
|
||||
sibling = self.lastChild(parent)
|
||||
if sibling and sibling.tag == "blockquote":
|
||||
# Previous block was a blockquote so set that as this blocks parent
|
||||
quote = sibling
|
||||
else:
|
||||
# This is a new blockquote. Create a new parent element.
|
||||
quote = markdown.etree.SubElement(parent, 'blockquote')
|
||||
# Recursively parse block with blockquote as parent.
|
||||
self.parser.parseChunk(quote, block)
|
||||
|
||||
def clean(self, line):
|
||||
""" Remove ``>`` from beginning of a line. """
|
||||
m = self.RE.match(line)
|
||||
if line.strip() == ">":
|
||||
return ""
|
||||
elif m:
|
||||
return m.group(2)
|
||||
else:
|
||||
return line
|
||||
|
||||
class OListProcessor(BlockProcessor):
|
||||
""" Process ordered list blocks. """
|
||||
|
||||
TAG = 'ol'
|
||||
# Detect an item (``1. item``). ``group(1)`` contains contents of item.
|
||||
RE = re.compile(r'^[ ]{0,3}\d+\.[ ](.*)')
|
||||
# Detect items on secondary lines. they can be of either list type.
|
||||
CHILD_RE = re.compile(r'^[ ]{0,3}((\d+\.)|[*+-])[ ](.*)')
|
||||
# Detect indented (nested) items of either type
|
||||
INDENT_RE = re.compile(r'^[ ]{4,7}((\d+\.)|[*+-])[ ].*')
|
||||
|
||||
def test(self, parent, block):
|
||||
return bool(self.RE.match(block))
|
||||
|
||||
def run(self, parent, blocks):
|
||||
# Check fr multiple items in one block.
|
||||
items = self.get_items(blocks.pop(0))
|
||||
sibling = self.lastChild(parent)
|
||||
if sibling and sibling.tag in ['ol', 'ul']:
|
||||
# Previous block was a list item, so set that as parent
|
||||
lst = sibling
|
||||
# make sure previous item is in a p.
|
||||
if len(lst) and lst[-1].text and not len(lst[-1]):
|
||||
p = markdown.etree.SubElement(lst[-1], 'p')
|
||||
p.text = lst[-1].text
|
||||
lst[-1].text = ''
|
||||
# parse first block differently as it gets wrapped in a p.
|
||||
li = markdown.etree.SubElement(lst, 'li')
|
||||
self.parser.state.set('looselist')
|
||||
firstitem = items.pop(0)
|
||||
self.parser.parseBlocks(li, [firstitem])
|
||||
self.parser.state.reset()
|
||||
else:
|
||||
# This is a new list so create parent with appropriate tag.
|
||||
lst = markdown.etree.SubElement(parent, self.TAG)
|
||||
self.parser.state.set('list')
|
||||
# Loop through items in block, recursively parsing each with the
|
||||
# appropriate parent.
|
||||
for item in items:
|
||||
if item.startswith(' '*markdown.TAB_LENGTH):
|
||||
# Item is indented. Parse with last item as parent
|
||||
self.parser.parseBlocks(lst[-1], [item])
|
||||
else:
|
||||
# New item. Create li and parse with it as parent
|
||||
li = markdown.etree.SubElement(lst, 'li')
|
||||
self.parser.parseBlocks(li, [item])
|
||||
self.parser.state.reset()
|
||||
|
||||
def get_items(self, block):
|
||||
""" Break a block into list items. """
|
||||
items = []
|
||||
for line in block.split('\n'):
|
||||
m = self.CHILD_RE.match(line)
|
||||
if m:
|
||||
# This is a new item. Append
|
||||
items.append(m.group(3))
|
||||
elif self.INDENT_RE.match(line):
|
||||
# This is an indented (possibly nested) item.
|
||||
if items[-1].startswith(' '*markdown.TAB_LENGTH):
|
||||
# Previous item was indented. Append to that item.
|
||||
items[-1] = '%s\n%s' % (items[-1], line)
|
||||
else:
|
||||
items.append(line)
|
||||
else:
|
||||
# This is another line of previous item. Append to that item.
|
||||
items[-1] = '%s\n%s' % (items[-1], line)
|
||||
return items
|
||||
|
||||
|
||||
class UListProcessor(OListProcessor):
|
||||
""" Process unordered list blocks. """
|
||||
|
||||
TAG = 'ul'
|
||||
RE = re.compile(r'^[ ]{0,3}[*+-][ ](.*)')
|
||||
|
||||
|
||||
class HashHeaderProcessor(BlockProcessor):
|
||||
""" Process Hash Headers. """
|
||||
|
||||
# Detect a header at start of any line in block
|
||||
RE = re.compile(r'(^|\n)(?P<level>#{1,6})(?P<header>.*?)#*(\n|$)')
|
||||
|
||||
def test(self, parent, block):
|
||||
return bool(self.RE.search(block))
|
||||
|
||||
def run(self, parent, blocks):
|
||||
block = blocks.pop(0)
|
||||
m = self.RE.search(block)
|
||||
if m:
|
||||
before = block[:m.start()] # All lines before header
|
||||
after = block[m.end():] # All lines after header
|
||||
if before:
|
||||
# As the header was not the first line of the block and the
|
||||
# lines before the header must be parsed first,
|
||||
# recursively parse this lines as a block.
|
||||
self.parser.parseBlocks(parent, [before])
|
||||
# Create header using named groups from RE
|
||||
h = markdown.etree.SubElement(parent, 'h%d' % len(m.group('level')))
|
||||
h.text = m.group('header').strip()
|
||||
if after:
|
||||
# Insert remaining lines as first block for future parsing.
|
||||
blocks.insert(0, after)
|
||||
else:
|
||||
# This should never happen, but just in case...
|
||||
message(CRITICAL, "We've got a problem header!")
|
||||
|
||||
|
||||
class SetextHeaderProcessor(BlockProcessor):
|
||||
""" Process Setext-style Headers. """
|
||||
|
||||
# Detect Setext-style header. Must be first 2 lines of block.
|
||||
RE = re.compile(r'^.*?\n[=-]{3,}', re.MULTILINE)
|
||||
|
||||
def test(self, parent, block):
|
||||
return bool(self.RE.match(block))
|
||||
|
||||
def run(self, parent, blocks):
|
||||
lines = blocks.pop(0).split('\n')
|
||||
# Determine level. ``=`` is 1 and ``-`` is 2.
|
||||
if lines[1].startswith('='):
|
||||
level = 1
|
||||
else:
|
||||
level = 2
|
||||
h = markdown.etree.SubElement(parent, 'h%d' % level)
|
||||
h.text = lines[0].strip()
|
||||
if len(lines) > 2:
|
||||
# Block contains additional lines. Add to master blocks for later.
|
||||
blocks.insert(0, '\n'.join(lines[2:]))
|
||||
|
||||
|
||||
class HRProcessor(BlockProcessor):
|
||||
""" Process Horizontal Rules. """
|
||||
|
||||
RE = r'[ ]{0,3}(?P<ch>[*_-])[ ]?((?P=ch)[ ]?){2,}[ ]*'
|
||||
# Detect hr on any line of a block.
|
||||
SEARCH_RE = re.compile(r'(^|\n)%s(\n|$)' % RE)
|
||||
# Match a hr on a single line of text.
|
||||
MATCH_RE = re.compile(r'^%s$' % RE)
|
||||
|
||||
def test(self, parent, block):
|
||||
return bool(self.SEARCH_RE.search(block))
|
||||
|
||||
def run(self, parent, blocks):
|
||||
lines = blocks.pop(0).split('\n')
|
||||
prelines = []
|
||||
# Check for lines in block before hr.
|
||||
for line in lines:
|
||||
m = self.MATCH_RE.match(line)
|
||||
if m:
|
||||
break
|
||||
else:
|
||||
prelines.append(line)
|
||||
if len(prelines):
|
||||
# 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')
|
||||
# check for lines in block after hr.
|
||||
lines = lines[len(prelines)+1:]
|
||||
if len(lines):
|
||||
# Add lines after hr to master blocks for later parsing.
|
||||
blocks.insert(0, '\n'.join(lines))
|
||||
|
||||
|
||||
class EmptyBlockProcessor(BlockProcessor):
|
||||
""" Process blocks and start with an empty line. """
|
||||
|
||||
# Detect a block that only contains whitespace
|
||||
# or only whitespace on the first line.
|
||||
RE = re.compile(r'^\s*\n')
|
||||
|
||||
def test(self, parent, block):
|
||||
return bool(self.RE.match(block))
|
||||
|
||||
def run(self, parent, blocks):
|
||||
block = blocks.pop(0)
|
||||
m = self.RE.match(block)
|
||||
if m:
|
||||
# Add remaining line to master blocks for later.
|
||||
blocks.insert(0, block[m.end():])
|
||||
sibling = self.lastChild(parent)
|
||||
if sibling and sibling.tag == 'pre' and sibling[0] and \
|
||||
sibling[0].tag == 'code':
|
||||
# Last block is a codeblock. Append to preserve whitespace.
|
||||
sibling[0].text = markdown.AtomicString('%s/n/n/n' % sibling[0].text )
|
||||
|
||||
|
||||
class ParagraphProcessor(BlockProcessor):
|
||||
""" Process Paragraph blocks. """
|
||||
|
||||
def test(self, parent, block):
|
||||
return True
|
||||
|
||||
def run(self, parent, blocks):
|
||||
block = blocks.pop(0)
|
||||
if block.strip():
|
||||
# Not a blank block. Add to parent, otherwise throw it away.
|
||||
if self.parser.state.isstate('list'):
|
||||
# The parent is a tight-list. Append to parent.text
|
||||
if parent.text:
|
||||
parent.text = '%s\n%s' % (parent.text, block)
|
||||
else:
|
||||
parent.text = block.lstrip()
|
||||
else:
|
||||
# Create a regular paragraph
|
||||
p = markdown.etree.SubElement(parent, 'p')
|
||||
p.text = block.lstrip()
|
||||
96
src/calibre/ebooks/markdown/commandline.py
Normal file
96
src/calibre/ebooks/markdown/commandline.py
Normal file
@ -0,0 +1,96 @@
|
||||
"""
|
||||
COMMAND-LINE SPECIFIC STUFF
|
||||
=============================================================================
|
||||
|
||||
The rest of the code is specifically for handling the case where Python
|
||||
Markdown is called from the command line.
|
||||
"""
|
||||
|
||||
import markdown
|
||||
import sys
|
||||
import logging
|
||||
from logging import DEBUG, INFO, WARN, ERROR, CRITICAL
|
||||
|
||||
EXECUTABLE_NAME_FOR_USAGE = "python markdown.py"
|
||||
""" The name used in the usage statement displayed for python versions < 2.3.
|
||||
(With python 2.3 and higher the usage statement is generated by optparse
|
||||
and uses the actual name of the executable called.) """
|
||||
|
||||
OPTPARSE_WARNING = """
|
||||
Python 2.3 or higher required for advanced command line options.
|
||||
For lower versions of Python use:
|
||||
|
||||
%s INPUT_FILE > OUTPUT_FILE
|
||||
|
||||
""" % EXECUTABLE_NAME_FOR_USAGE
|
||||
|
||||
def parse_options():
|
||||
"""
|
||||
Define and parse `optparse` options for command-line usage.
|
||||
"""
|
||||
|
||||
try:
|
||||
optparse = __import__("optparse")
|
||||
except:
|
||||
if len(sys.argv) == 2:
|
||||
return {'input': sys.argv[1],
|
||||
'output': None,
|
||||
'safe': False,
|
||||
'extensions': [],
|
||||
'encoding': None }, CRITICAL
|
||||
else:
|
||||
print OPTPARSE_WARNING
|
||||
return None, None
|
||||
|
||||
parser = optparse.OptionParser(usage="%prog INPUTFILE [options]")
|
||||
parser.add_option("-f", "--file", dest="filename", default=sys.stdout,
|
||||
help="write output to OUTPUT_FILE",
|
||||
metavar="OUTPUT_FILE")
|
||||
parser.add_option("-e", "--encoding", dest="encoding",
|
||||
help="encoding for input and output files",)
|
||||
parser.add_option("-q", "--quiet", default = CRITICAL,
|
||||
action="store_const", const=CRITICAL+10, dest="verbose",
|
||||
help="suppress all messages")
|
||||
parser.add_option("-v", "--verbose",
|
||||
action="store_const", const=INFO, dest="verbose",
|
||||
help="print info messages")
|
||||
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",
|
||||
default='xhtml1', metavar="OUTPUT_FORMAT",
|
||||
help="Format of output. One of 'xhtml1' (default) or 'html4'.")
|
||||
parser.add_option("--noisy",
|
||||
action="store_const", const=DEBUG, dest="verbose",
|
||||
help="print debug messages")
|
||||
parser.add_option("-x", "--extension", action="append", dest="extensions",
|
||||
help = "load extension EXTENSION", metavar="EXTENSION")
|
||||
|
||||
(options, args) = parser.parse_args()
|
||||
|
||||
if not len(args) == 1:
|
||||
parser.print_help()
|
||||
return None, None
|
||||
else:
|
||||
input_file = args[0]
|
||||
|
||||
if not options.extensions:
|
||||
options.extensions = []
|
||||
|
||||
return {'input': input_file,
|
||||
'output': options.filename,
|
||||
'safe_mode': options.safe,
|
||||
'extensions': options.extensions,
|
||||
'encoding': options.encoding,
|
||||
'output_format': options.output_format}, options.verbose
|
||||
|
||||
def run():
|
||||
"""Run Markdown from the command line."""
|
||||
|
||||
# Parse options and adjust logging level if necessary
|
||||
options, logging_level = parse_options()
|
||||
if not options: sys.exit(0)
|
||||
if logging_level: logging.getLogger('MARKDOWN').setLevel(logging_level)
|
||||
|
||||
# Run
|
||||
markdown.markdownFromFile(**options)
|
||||
33
src/calibre/ebooks/markdown/etree_loader.py
Normal file
33
src/calibre/ebooks/markdown/etree_loader.py
Normal file
@ -0,0 +1,33 @@
|
||||
|
||||
from markdown import message, CRITICAL
|
||||
import sys
|
||||
|
||||
## Import
|
||||
def importETree():
|
||||
"""Import the best implementation of ElementTree, return a module object."""
|
||||
etree_in_c = None
|
||||
try: # Is it Python 2.5+ with C implemenation of ElementTree installed?
|
||||
import xml.etree.cElementTree as etree_in_c
|
||||
except ImportError:
|
||||
try: # Is it Python 2.5+ with Python implementation of ElementTree?
|
||||
import xml.etree.ElementTree as etree
|
||||
except ImportError:
|
||||
try: # An earlier version of Python with cElementTree installed?
|
||||
import cElementTree as etree_in_c
|
||||
except ImportError:
|
||||
try: # An earlier version of Python with Python ElementTree?
|
||||
import elementtree.ElementTree as etree
|
||||
except ImportError:
|
||||
message(CRITICAL, "Failed to import ElementTree")
|
||||
sys.exit(1)
|
||||
if etree_in_c and etree_in_c.VERSION < "1.0":
|
||||
message(CRITICAL, "For cElementTree version 1.0 or higher is required.")
|
||||
sys.exit(1)
|
||||
elif etree_in_c :
|
||||
return etree_in_c
|
||||
elif etree.VERSION < "1.1":
|
||||
message(CRITICAL, "For ElementTree version 1.1 or higher is required")
|
||||
sys.exit(1)
|
||||
else :
|
||||
return etree
|
||||
|
||||
0
src/calibre/ebooks/markdown/extensions/__init__.py
Normal file
0
src/calibre/ebooks/markdown/extensions/__init__.py
Normal file
96
src/calibre/ebooks/markdown/extensions/abbr.py
Normal file
96
src/calibre/ebooks/markdown/extensions/abbr.py
Normal file
@ -0,0 +1,96 @@
|
||||
'''
|
||||
Abbreviation Extension for Python-Markdown
|
||||
==========================================
|
||||
|
||||
This extension adds abbreviation handling to Python-Markdown.
|
||||
|
||||
Simple Usage:
|
||||
|
||||
>>> import markdown
|
||||
>>> text = """
|
||||
... Some text with an ABBR and a REF. Ignore REFERENCE and ref.
|
||||
...
|
||||
... *[ABBR]: Abbreviation
|
||||
... *[REF]: Abbreviation Reference
|
||||
... """
|
||||
>>> markdown.markdown(text, ['abbr'])
|
||||
u'<p>Some text with an <abbr title="Abbreviation">ABBR</abbr> and a <abbr title="Abbreviation Reference">REF</abbr>. Ignore REFERENCE and ref.</p>'
|
||||
|
||||
Copyright 2007-2008
|
||||
* [Waylan Limberg](http://achinghead.com/)
|
||||
* [Seemant Kulleen](http://www.kulleen.org/)
|
||||
|
||||
|
||||
'''
|
||||
|
||||
import re
|
||||
import calibre.ebooks.markdown.markdown as markdown
|
||||
from calibre.ebooks.markdown.markdown import etree
|
||||
|
||||
# Global Vars
|
||||
ABBR_REF_RE = re.compile(r'[*]\[(?P<abbr>[^\]]*)\][ ]?:\s*(?P<title>.*)')
|
||||
|
||||
class AbbrExtension(markdown.Extension):
|
||||
""" Abbreviation Extension for Python-Markdown. """
|
||||
|
||||
def extendMarkdown(self, md, md_globals):
|
||||
""" Insert AbbrPreprocessor before ReferencePreprocessor. """
|
||||
md.preprocessors.add('abbr', AbbrPreprocessor(md), '<reference')
|
||||
|
||||
|
||||
class AbbrPreprocessor(markdown.preprocessors.Preprocessor):
|
||||
""" Abbreviation Preprocessor - parse text for abbr references. """
|
||||
|
||||
def run(self, lines):
|
||||
'''
|
||||
Find and remove all Abbreviation references from the text.
|
||||
Each reference is set as a new AbbrPattern in the markdown instance.
|
||||
|
||||
'''
|
||||
new_text = []
|
||||
for line in lines:
|
||||
m = ABBR_REF_RE.match(line)
|
||||
if m:
|
||||
abbr = m.group('abbr').strip()
|
||||
title = m.group('title').strip()
|
||||
self.markdown.inlinePatterns['abbr-%s'%abbr] = \
|
||||
AbbrPattern(self._generate_pattern(abbr), title)
|
||||
else:
|
||||
new_text.append(line)
|
||||
return new_text
|
||||
|
||||
def _generate_pattern(self, text):
|
||||
'''
|
||||
Given a string, returns an regex pattern to match that string.
|
||||
|
||||
'HTML' -> r'(?P<abbr>[H][T][M][L])'
|
||||
|
||||
Note: we force each char as a literal match (in brackets) as we don't
|
||||
know what they will be beforehand.
|
||||
|
||||
'''
|
||||
chars = list(text)
|
||||
for i in range(len(chars)):
|
||||
chars[i] = r'[%s]' % chars[i]
|
||||
return r'(?P<abbr>\b%s\b)' % (r''.join(chars))
|
||||
|
||||
|
||||
class AbbrPattern(markdown.inlinepatterns.Pattern):
|
||||
""" Abbreviation inline pattern. """
|
||||
|
||||
def __init__(self, pattern, title):
|
||||
markdown.inlinepatterns.Pattern.__init__(self, pattern)
|
||||
self.title = title
|
||||
|
||||
def handleMatch(self, m):
|
||||
abbr = etree.Element('abbr')
|
||||
abbr.text = m.group('abbr')
|
||||
abbr.set('title', self.title)
|
||||
return abbr
|
||||
|
||||
def makeExtension(configs=None):
|
||||
return AbbrExtension(configs=configs)
|
||||
|
||||
if __name__ == "__main__":
|
||||
import doctest
|
||||
doctest.testmod()
|
||||
224
src/calibre/ebooks/markdown/extensions/codehilite.py
Normal file
224
src/calibre/ebooks/markdown/extensions/codehilite.py
Normal file
@ -0,0 +1,224 @@
|
||||
#!/usr/bin/python
|
||||
|
||||
"""
|
||||
CodeHilite Extension for Python-Markdown
|
||||
========================================
|
||||
|
||||
Adds code/syntax highlighting to standard Python-Markdown code blocks.
|
||||
|
||||
Copyright 2006-2008 [Waylan Limberg](http://achinghead.com/).
|
||||
|
||||
Project website: <http://www.freewisdom.org/project/python-markdown/CodeHilite>
|
||||
Contact: markdown@freewisdom.org
|
||||
|
||||
License: BSD (see ../docs/LICENSE for details)
|
||||
|
||||
Dependencies:
|
||||
* [Python 2.3+](http://python.org/)
|
||||
* [Markdown 2.0+](http://www.freewisdom.org/projects/python-markdown/)
|
||||
* [Pygments](http://pygments.org/)
|
||||
|
||||
"""
|
||||
|
||||
import calibre.ebooks.markdown.markdown as markdown
|
||||
|
||||
# --------------- CONSTANTS YOU MIGHT WANT TO MODIFY -----------------
|
||||
|
||||
try:
|
||||
TAB_LENGTH = markdown.TAB_LENGTH
|
||||
except AttributeError:
|
||||
TAB_LENGTH = 4
|
||||
|
||||
|
||||
# ------------------ The Main CodeHilite Class ----------------------
|
||||
class CodeHilite:
|
||||
"""
|
||||
Determine language of source code, and pass it into the pygments hilighter.
|
||||
|
||||
Basic Usage:
|
||||
>>> code = CodeHilite(src = 'some text')
|
||||
>>> html = code.hilite()
|
||||
|
||||
* src: Source string or any object with a .readline attribute.
|
||||
|
||||
* linenos: (Boolen) Turn line numbering 'on' or 'off' (off by default).
|
||||
|
||||
* css_class: Set class name of wrapper div ('codehilite' by default).
|
||||
|
||||
Low Level Usage:
|
||||
>>> code = CodeHilite()
|
||||
>>> code.src = 'some text' # String or anything with a .readline attr.
|
||||
>>> code.linenos = True # True or False; Turns line numbering on or of.
|
||||
>>> html = code.hilite()
|
||||
|
||||
"""
|
||||
|
||||
def __init__(self, src=None, linenos=False, css_class="codehilite"):
|
||||
self.src = src
|
||||
self.lang = None
|
||||
self.linenos = linenos
|
||||
self.css_class = css_class
|
||||
|
||||
def hilite(self):
|
||||
"""
|
||||
Pass code to the [Pygments](http://pygments.pocoo.org/) highliter with
|
||||
optional line numbers. The output should then be styled with css to
|
||||
your liking. No styles are applied by default - only styling hooks
|
||||
(i.e.: <span class="k">).
|
||||
|
||||
returns : A string of html.
|
||||
|
||||
"""
|
||||
|
||||
self.src = self.src.strip('\n')
|
||||
|
||||
self._getLang()
|
||||
|
||||
try:
|
||||
from pygments import highlight
|
||||
from pygments.lexers import get_lexer_by_name, guess_lexer, \
|
||||
TextLexer
|
||||
from pygments.formatters import HtmlFormatter
|
||||
except ImportError:
|
||||
# just escape and pass through
|
||||
txt = self._escape(self.src)
|
||||
if self.linenos:
|
||||
txt = self._number(txt)
|
||||
else :
|
||||
txt = '<div class="%s"><pre>%s</pre></div>\n'% \
|
||||
(self.css_class, txt)
|
||||
return txt
|
||||
else:
|
||||
try:
|
||||
lexer = get_lexer_by_name(self.lang)
|
||||
except ValueError:
|
||||
try:
|
||||
lexer = guess_lexer(self.src)
|
||||
except ValueError:
|
||||
lexer = TextLexer()
|
||||
formatter = HtmlFormatter(linenos=self.linenos,
|
||||
cssclass=self.css_class)
|
||||
return highlight(self.src, lexer, formatter)
|
||||
|
||||
def _escape(self, txt):
|
||||
""" basic html escaping """
|
||||
txt = txt.replace('&', '&')
|
||||
txt = txt.replace('<', '<')
|
||||
txt = txt.replace('>', '>')
|
||||
txt = txt.replace('"', '"')
|
||||
return txt
|
||||
|
||||
def _number(self, txt):
|
||||
""" Use <ol> for line numbering """
|
||||
# Fix Whitespace
|
||||
txt = txt.replace('\t', ' '*TAB_LENGTH)
|
||||
txt = txt.replace(" "*4, " ")
|
||||
txt = txt.replace(" "*3, " ")
|
||||
txt = txt.replace(" "*2, " ")
|
||||
|
||||
# Add line numbers
|
||||
lines = txt.splitlines()
|
||||
txt = '<div class="codehilite"><pre><ol>\n'
|
||||
for line in lines:
|
||||
txt += '\t<li>%s</li>\n'% line
|
||||
txt += '</ol></pre></div>\n'
|
||||
return txt
|
||||
|
||||
|
||||
def _getLang(self):
|
||||
"""
|
||||
Determines language of a code block from shebang lines and whether said
|
||||
line should be removed or left in place. If the sheband line contains a
|
||||
path (even a single /) then it is assumed to be a real shebang lines and
|
||||
left alone. However, if no path is given (e.i.: #!python or :::python)
|
||||
then it is assumed to be a mock shebang for language identifitation of a
|
||||
code fragment and removed from the code block prior to processing for
|
||||
code highlighting. When a mock shebang (e.i: #!python) is found, line
|
||||
numbering is turned on. When colons are found in place of a shebang
|
||||
(e.i.: :::python), line numbering is left in the current state - off
|
||||
by default.
|
||||
|
||||
"""
|
||||
|
||||
import re
|
||||
|
||||
#split text into lines
|
||||
lines = self.src.split("\n")
|
||||
#pull first line to examine
|
||||
fl = lines.pop(0)
|
||||
|
||||
c = re.compile(r'''
|
||||
(?:(?:::+)|(?P<shebang>[#]!)) # Shebang or 2 or more colons.
|
||||
(?P<path>(?:/\w+)*[/ ])? # Zero or 1 path
|
||||
(?P<lang>[\w+-]*) # The language
|
||||
''', re.VERBOSE)
|
||||
# search first line for shebang
|
||||
m = c.search(fl)
|
||||
if m:
|
||||
# we have a match
|
||||
try:
|
||||
self.lang = m.group('lang').lower()
|
||||
except IndexError:
|
||||
self.lang = None
|
||||
if m.group('path'):
|
||||
# path exists - restore first line
|
||||
lines.insert(0, fl)
|
||||
if m.group('shebang'):
|
||||
# shebang exists - use line numbers
|
||||
self.linenos = True
|
||||
else:
|
||||
# No match
|
||||
lines.insert(0, fl)
|
||||
|
||||
self.src = "\n".join(lines).strip("\n")
|
||||
|
||||
|
||||
|
||||
# ------------------ The Markdown Extension -------------------------------
|
||||
class HiliteTreeprocessor(markdown.treeprocessors.Treeprocessor):
|
||||
""" Hilight source code in code blocks. """
|
||||
|
||||
def run(self, root):
|
||||
""" Find code blocks and store in htmlStash. """
|
||||
blocks = root.getiterator('pre')
|
||||
for block in blocks:
|
||||
children = block.getchildren()
|
||||
if len(children) == 1 and children[0].tag == 'code':
|
||||
code = CodeHilite(children[0].text,
|
||||
linenos=self.config['force_linenos'][0],
|
||||
css_class=self.config['css_class'][0])
|
||||
placeholder = self.markdown.htmlStash.store(code.hilite(),
|
||||
safe=True)
|
||||
# Clear codeblock in etree instance
|
||||
block.clear()
|
||||
# Change to p element which will later
|
||||
# be removed when inserting raw html
|
||||
block.tag = 'p'
|
||||
block.text = placeholder
|
||||
|
||||
|
||||
class CodeHiliteExtension(markdown.Extension):
|
||||
""" Add source code hilighting to markdown codeblocks. """
|
||||
|
||||
def __init__(self, configs):
|
||||
# define default configs
|
||||
self.config = {
|
||||
'force_linenos' : [False, "Force line numbers - Default: False"],
|
||||
'css_class' : ["codehilite",
|
||||
"Set class name for wrapper <div> - Default: codehilite"],
|
||||
}
|
||||
|
||||
# Override defaults with user settings
|
||||
for key, value in configs:
|
||||
self.setConfig(key, value)
|
||||
|
||||
def extendMarkdown(self, md, md_globals):
|
||||
""" Add HilitePostprocessor to Markdown instance. """
|
||||
hiliter = HiliteTreeprocessor(md)
|
||||
hiliter.config = self.config
|
||||
md.treeprocessors.add("hilite", hiliter, "_begin")
|
||||
|
||||
|
||||
def makeExtension(configs={}):
|
||||
return CodeHiliteExtension(configs=configs)
|
||||
|
||||
105
src/calibre/ebooks/markdown/extensions/def_list.py
Normal file
105
src/calibre/ebooks/markdown/extensions/def_list.py
Normal file
@ -0,0 +1,105 @@
|
||||
#!/usr/bin/env Python
|
||||
"""
|
||||
Definition List Extension for Python-Markdown
|
||||
=============================================
|
||||
|
||||
Added parsing of Definition Lists to Python-Markdown.
|
||||
|
||||
A simple example:
|
||||
|
||||
Apple
|
||||
: Pomaceous fruit of plants of the genus Malus in
|
||||
the family Rosaceae.
|
||||
: An american computer company.
|
||||
|
||||
Orange
|
||||
: The fruit of an evergreen tree of the genus Citrus.
|
||||
|
||||
Copyright 2008 - [Waylan Limberg](http://achinghead.com)
|
||||
|
||||
"""
|
||||
|
||||
import re
|
||||
import calibre.ebooks.markdown.markdown as markdown
|
||||
from calibre.ebooks.markdown.markdown import etree
|
||||
|
||||
|
||||
class DefListProcessor(markdown.blockprocessors.BlockProcessor):
|
||||
""" Process Definition Lists. """
|
||||
|
||||
RE = re.compile(r'(^|\n)[ ]{0,3}:[ ]{1,3}(.*?)(\n|$)')
|
||||
|
||||
def test(self, parent, block):
|
||||
return bool(self.RE.search(block))
|
||||
|
||||
def run(self, parent, blocks):
|
||||
block = blocks.pop(0)
|
||||
m = self.RE.search(block)
|
||||
terms = [l.strip() for l in block[:m.start()].split('\n') if l.strip()]
|
||||
d, theRest = self.detab(block[m.end():])
|
||||
if d:
|
||||
d = '%s\n%s' % (m.group(2), d)
|
||||
else:
|
||||
d = m.group(2)
|
||||
#import ipdb; ipdb.set_trace()
|
||||
sibling = self.lastChild(parent)
|
||||
if not terms and sibling.tag == 'p':
|
||||
# The previous paragraph contains the terms
|
||||
state = 'looselist'
|
||||
terms = sibling.text.split('\n')
|
||||
parent.remove(sibling)
|
||||
# Aquire new sibling
|
||||
sibling = self.lastChild(parent)
|
||||
else:
|
||||
state = 'list'
|
||||
|
||||
if sibling and sibling.tag == 'dl':
|
||||
# This is another item on an existing list
|
||||
dl = sibling
|
||||
if len(dl) and dl[-1].tag == 'dd' and len(dl[-1]):
|
||||
state = 'looselist'
|
||||
else:
|
||||
# This is a new list
|
||||
dl = etree.SubElement(parent, 'dl')
|
||||
# Add terms
|
||||
for term in terms:
|
||||
dt = etree.SubElement(dl, 'dt')
|
||||
dt.text = term
|
||||
# Add definition
|
||||
self.parser.state.set(state)
|
||||
dd = etree.SubElement(dl, 'dd')
|
||||
self.parser.parseBlocks(dd, [d])
|
||||
self.parser.state.reset()
|
||||
|
||||
if theRest:
|
||||
blocks.insert(0, theRest)
|
||||
|
||||
class DefListIndentProcessor(markdown.blockprocessors.ListIndentProcessor):
|
||||
""" Process indented children of definition list items. """
|
||||
|
||||
ITEM_TYPES = ['dd']
|
||||
LIST_TYPES = ['dl']
|
||||
|
||||
def create_item(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):
|
||||
""" Add definition lists to Markdown. """
|
||||
|
||||
def extendMarkdown(self, md, md_globals):
|
||||
""" Add an instance of DefListProcessor to BlockParser. """
|
||||
md.parser.blockprocessors.add('defindent',
|
||||
DefListIndentProcessor(md.parser),
|
||||
'>indent')
|
||||
md.parser.blockprocessors.add('deflist',
|
||||
DefListProcessor(md.parser),
|
||||
'>ulist')
|
||||
|
||||
|
||||
def makeExtension(configs={}):
|
||||
return DefListExtension(configs=configs)
|
||||
|
||||
49
src/calibre/ebooks/markdown/extensions/extra.py
Normal file
49
src/calibre/ebooks/markdown/extensions/extra.py
Normal file
@ -0,0 +1,49 @@
|
||||
#!/usr/bin/env python
|
||||
"""
|
||||
Python-Markdown Extra Extension
|
||||
===============================
|
||||
|
||||
A compilation of various Python-Markdown extensions that imitates
|
||||
[PHP Markdown Extra](http://michelf.com/projects/php-markdown/extra/).
|
||||
|
||||
Note that each of the individual extensions still need to be available
|
||||
on your PYTHONPATH. This extension simply wraps them all up as a
|
||||
convenience so that only one extension needs to be listed when
|
||||
initiating Markdown. See the documentation for each individual
|
||||
extension for specifics about that extension.
|
||||
|
||||
In the event that one or more of the supported extensions are not
|
||||
available for import, Markdown will issue a warning and simply continue
|
||||
without that extension.
|
||||
|
||||
There may be additional extensions that are distributed with
|
||||
Python-Markdown that are not included here in Extra. Those extensions
|
||||
are not part of PHP Markdown Extra, and therefore, not part of
|
||||
Python-Markdown Extra. If you really would like Extra to include
|
||||
additional extensions, we suggest creating your own clone of Extra
|
||||
under a differant name. You could also edit the `extensions` global
|
||||
variable defined below, but be aware that such changes may be lost
|
||||
when you upgrade to any future version of Python-Markdown.
|
||||
|
||||
"""
|
||||
|
||||
import calibre.ebooks.markdown.markdown as markdown
|
||||
|
||||
extensions = ['fenced_code',
|
||||
'footnotes',
|
||||
'headerid',
|
||||
'def_list',
|
||||
'tables',
|
||||
'abbr',
|
||||
]
|
||||
|
||||
|
||||
class ExtraExtension(markdown.Extension):
|
||||
""" Add various extensions to Markdown class."""
|
||||
|
||||
def extendMarkdown(self, md, md_globals):
|
||||
""" Register extension instances. """
|
||||
md.registerExtensions(extensions, self.config)
|
||||
|
||||
def makeExtension(configs={}):
|
||||
return ExtraExtension(configs=dict(configs))
|
||||
118
src/calibre/ebooks/markdown/extensions/fenced_code.py
Normal file
118
src/calibre/ebooks/markdown/extensions/fenced_code.py
Normal file
@ -0,0 +1,118 @@
|
||||
#!/usr/bin/env python
|
||||
|
||||
"""
|
||||
Fenced Code Extension for Python Markdown
|
||||
=========================================
|
||||
|
||||
This extension adds Fenced Code Blocks to Python-Markdown.
|
||||
|
||||
>>> import markdown
|
||||
>>> text = '''
|
||||
... A paragraph before a fenced code block:
|
||||
...
|
||||
... ~~~
|
||||
... Fenced code block
|
||||
... ~~~
|
||||
... '''
|
||||
>>> html = markdown.markdown(text, extensions=['fenced_code'])
|
||||
>>> html
|
||||
u'<p>A paragraph before a fenced code block:</p>\\n<pre><code>Fenced code block\\n</code></pre>'
|
||||
|
||||
Works with safe_mode also (we check this because we are using the HtmlStash):
|
||||
|
||||
>>> markdown.markdown(text, extensions=['fenced_code'], safe_mode='replace')
|
||||
u'<p>A paragraph before a fenced code block:</p>\\n<pre><code>Fenced code block\\n</code></pre>'
|
||||
|
||||
Include tilde's in a code block and wrap with blank lines:
|
||||
|
||||
>>> text = '''
|
||||
... ~~~~~~~~
|
||||
...
|
||||
... ~~~~
|
||||
...
|
||||
... ~~~~~~~~'''
|
||||
>>> markdown.markdown(text, extensions=['fenced_code'])
|
||||
u'<pre><code>\\n~~~~\\n\\n</code></pre>'
|
||||
|
||||
Multiple blocks and language tags:
|
||||
|
||||
>>> text = '''
|
||||
... ~~~~{.python}
|
||||
... block one
|
||||
... ~~~~
|
||||
...
|
||||
... ~~~~.html
|
||||
... <p>block two</p>
|
||||
... ~~~~'''
|
||||
>>> markdown.markdown(text, extensions=['fenced_code'])
|
||||
u'<pre><code class="python">block one\\n</code></pre>\\n\\n<pre><code class="html"><p>block two</p>\\n</code></pre>'
|
||||
|
||||
Copyright 2007-2008 [Waylan Limberg](http://achinghead.com/).
|
||||
|
||||
Project website: <http://www.freewisdom.org/project/python-markdown/Fenced__Code__Blocks>
|
||||
Contact: markdown@freewisdom.org
|
||||
|
||||
License: BSD (see ../docs/LICENSE for details)
|
||||
|
||||
Dependencies:
|
||||
* [Python 2.3+](http://python.org)
|
||||
* [Markdown 2.0+](http://www.freewisdom.org/projects/python-markdown/)
|
||||
|
||||
"""
|
||||
|
||||
import re
|
||||
import calibre.ebooks.markdown.markdown as markdown
|
||||
|
||||
# Global vars
|
||||
FENCED_BLOCK_RE = re.compile( \
|
||||
r'(?P<fence>^~{3,})[ ]*(\{?\.(?P<lang>[a-zA-Z0-9_-]*)\}?)?[ ]*\n(?P<code>.*?)(?P=fence)[ ]*$',
|
||||
re.MULTILINE|re.DOTALL
|
||||
)
|
||||
CODE_WRAP = '<pre><code%s>%s</code></pre>'
|
||||
LANG_TAG = ' class="%s"'
|
||||
|
||||
|
||||
class FencedCodeExtension(markdown.Extension):
|
||||
|
||||
def extendMarkdown(self, md, md_globals):
|
||||
""" Add FencedBlockPreprocessor to the Markdown instance. """
|
||||
|
||||
md.preprocessors.add('fenced_code_block',
|
||||
FencedBlockPreprocessor(md),
|
||||
"_begin")
|
||||
|
||||
|
||||
class FencedBlockPreprocessor(markdown.preprocessors.Preprocessor):
|
||||
|
||||
def run(self, lines):
|
||||
""" Match and store Fenced Code Blocks in the HtmlStash. """
|
||||
text = "\n".join(lines)
|
||||
while 1:
|
||||
m = FENCED_BLOCK_RE.search(text)
|
||||
if m:
|
||||
lang = ''
|
||||
if m.group('lang'):
|
||||
lang = LANG_TAG % m.group('lang')
|
||||
code = CODE_WRAP % (lang, self._escape(m.group('code')))
|
||||
placeholder = self.markdown.htmlStash.store(code, safe=True)
|
||||
text = '%s\n%s\n%s'% (text[:m.start()], placeholder, text[m.end():])
|
||||
else:
|
||||
break
|
||||
return text.split("\n")
|
||||
|
||||
def _escape(self, txt):
|
||||
""" basic html escaping """
|
||||
txt = txt.replace('&', '&')
|
||||
txt = txt.replace('<', '<')
|
||||
txt = txt.replace('>', '>')
|
||||
txt = txt.replace('"', '"')
|
||||
return txt
|
||||
|
||||
|
||||
def makeExtension(configs=None):
|
||||
return FencedCodeExtension()
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
import doctest
|
||||
doctest.testmod()
|
||||
294
src/calibre/ebooks/markdown/extensions/footnotes.py
Normal file
294
src/calibre/ebooks/markdown/extensions/footnotes.py
Normal file
@ -0,0 +1,294 @@
|
||||
"""
|
||||
========================= FOOTNOTES =================================
|
||||
|
||||
This section adds footnote handling to markdown. It can be used as
|
||||
an example for extending python-markdown with relatively complex
|
||||
functionality. While in this case the extension is included inside
|
||||
the module itself, it could just as easily be added from outside the
|
||||
module. Not that all markdown classes above are ignorant about
|
||||
footnotes. All footnote functionality is provided separately and
|
||||
then added to the markdown instance at the run time.
|
||||
|
||||
Footnote functionality is attached by calling extendMarkdown()
|
||||
method of FootnoteExtension. The method also registers the
|
||||
extension to allow it's state to be reset by a call to reset()
|
||||
method.
|
||||
|
||||
Example:
|
||||
Footnotes[^1] have a label[^label] and a definition[^!DEF].
|
||||
|
||||
[^1]: This is a footnote
|
||||
[^label]: A footnote on "label"
|
||||
[^!DEF]: The footnote for definition
|
||||
|
||||
"""
|
||||
|
||||
import re
|
||||
import calibre.ebooks.markdown.markdown as markdown
|
||||
from calibre.ebooks.markdown.markdown import etree
|
||||
|
||||
FN_BACKLINK_TEXT = "zz1337820767766393qq"
|
||||
NBSP_PLACEHOLDER = "qq3936677670287331zz"
|
||||
DEF_RE = re.compile(r'(\ ?\ ?\ ?)\[\^([^\]]*)\]:\s*(.*)')
|
||||
TABBED_RE = re.compile(r'((\t)|( ))(.*)')
|
||||
|
||||
class FootnoteExtension(markdown.Extension):
|
||||
""" Footnote Extension. """
|
||||
|
||||
def __init__ (self, configs):
|
||||
""" Setup configs. """
|
||||
self.config = {'PLACE_MARKER':
|
||||
["///Footnotes Go Here///",
|
||||
"The text string that marks where the footnotes go"]}
|
||||
|
||||
for key, value in configs:
|
||||
self.config[key][0] = value
|
||||
|
||||
self.reset()
|
||||
|
||||
def extendMarkdown(self, md, md_globals):
|
||||
""" Add pieces to Markdown. """
|
||||
md.registerExtension(self)
|
||||
self.parser = md.parser
|
||||
# Insert a preprocessor before ReferencePreprocessor
|
||||
md.preprocessors.add("footnote", FootnotePreprocessor(self),
|
||||
"<reference")
|
||||
# Insert an inline pattern before ImageReferencePattern
|
||||
FOOTNOTE_RE = r'\[\^([^\]]*)\]' # blah blah [^1] blah
|
||||
md.inlinePatterns.add("footnote", FootnotePattern(FOOTNOTE_RE, self),
|
||||
"<reference")
|
||||
# Insert a tree-processor that would actually add the footnote div
|
||||
# This must be before the inline treeprocessor so inline patterns
|
||||
# run on the contents of the div.
|
||||
md.treeprocessors.add("footnote", FootnoteTreeprocessor(self),
|
||||
"<inline")
|
||||
# Insert a postprocessor after amp_substitute oricessor
|
||||
md.postprocessors.add("footnote", FootnotePostprocessor(self),
|
||||
">amp_substitute")
|
||||
|
||||
def reset(self):
|
||||
""" Clear the footnotes on reset. """
|
||||
self.footnotes = markdown.odict.OrderedDict()
|
||||
|
||||
def findFootnotesPlaceholder(self, root):
|
||||
""" Return ElementTree Element that contains Footnote placeholder. """
|
||||
def finder(element):
|
||||
for child in element:
|
||||
if child.text:
|
||||
if child.text.find(self.getConfig("PLACE_MARKER")) > -1:
|
||||
return child, True
|
||||
if child.tail:
|
||||
if child.tail.find(self.getConfig("PLACE_MARKER")) > -1:
|
||||
return (child, element), False
|
||||
finder(child)
|
||||
return None
|
||||
|
||||
res = finder(root)
|
||||
return res
|
||||
|
||||
def setFootnote(self, id, text):
|
||||
""" Store a footnote for later retrieval. """
|
||||
self.footnotes[id] = text
|
||||
|
||||
def makeFootnoteId(self, id):
|
||||
""" Return footnote link id. """
|
||||
return 'fn:%s' % id
|
||||
|
||||
def makeFootnoteRefId(self, id):
|
||||
""" Return footnote back-link id. """
|
||||
return 'fnref:%s' % id
|
||||
|
||||
def makeFootnotesDiv(self, root):
|
||||
""" Return div of footnotes as et Element. """
|
||||
|
||||
if not self.footnotes.keys():
|
||||
return None
|
||||
|
||||
div = etree.Element("div")
|
||||
div.set('class', 'footnote')
|
||||
hr = etree.SubElement(div, "hr")
|
||||
ol = etree.SubElement(div, "ol")
|
||||
|
||||
for id in self.footnotes.keys():
|
||||
li = etree.SubElement(ol, "li")
|
||||
li.set("id", self.makeFootnoteId(id))
|
||||
self.parser.parseChunk(li, self.footnotes[id])
|
||||
backlink = etree.Element("a")
|
||||
backlink.set("href", "#" + self.makeFootnoteRefId(id))
|
||||
backlink.set("rev", "footnote")
|
||||
backlink.set("title", "Jump back to footnote %d in the text" % \
|
||||
(self.footnotes.index(id)+1))
|
||||
backlink.text = FN_BACKLINK_TEXT
|
||||
|
||||
if li.getchildren():
|
||||
node = li[-1]
|
||||
if node.tag == "p":
|
||||
node.text = node.text + NBSP_PLACEHOLDER
|
||||
node.append(backlink)
|
||||
else:
|
||||
p = etree.SubElement(li, "p")
|
||||
p.append(backlink)
|
||||
return div
|
||||
|
||||
|
||||
class FootnotePreprocessor(markdown.preprocessors.Preprocessor):
|
||||
""" Find all footnote references and store for later use. """
|
||||
|
||||
def __init__ (self, footnotes):
|
||||
self.footnotes = footnotes
|
||||
|
||||
def run(self, lines):
|
||||
lines = self._handleFootnoteDefinitions(lines)
|
||||
text = "\n".join(lines)
|
||||
return text.split("\n")
|
||||
|
||||
def _handleFootnoteDefinitions(self, lines):
|
||||
"""
|
||||
Recursively find all footnote definitions in lines.
|
||||
|
||||
Keywords:
|
||||
|
||||
* lines: A list of lines of text
|
||||
|
||||
Return: A list of lines with footnote definitions removed.
|
||||
|
||||
"""
|
||||
i, id, footnote = self._findFootnoteDefinition(lines)
|
||||
|
||||
if id :
|
||||
plain = lines[:i]
|
||||
detabbed, theRest = self.detectTabbed(lines[i+1:])
|
||||
self.footnotes.setFootnote(id,
|
||||
footnote + "\n"
|
||||
+ "\n".join(detabbed))
|
||||
more_plain = self._handleFootnoteDefinitions(theRest)
|
||||
return plain + [""] + more_plain
|
||||
else :
|
||||
return lines
|
||||
|
||||
def _findFootnoteDefinition(self, lines):
|
||||
"""
|
||||
Find the parts of a footnote definition.
|
||||
|
||||
Keywords:
|
||||
|
||||
* 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
|
||||
definition.
|
||||
|
||||
"""
|
||||
counter = 0
|
||||
for line in lines:
|
||||
m = DEF_RE.match(line)
|
||||
if m:
|
||||
return counter, m.group(2), m.group(3)
|
||||
counter += 1
|
||||
return counter, None, None
|
||||
|
||||
def detectTabbed(self, lines):
|
||||
""" Find indented text and remove indent before further proccesing.
|
||||
|
||||
Keyword arguments:
|
||||
|
||||
* lines: an array of strings
|
||||
|
||||
Returns: a list of post processed items and the unused
|
||||
remainder of the original list
|
||||
|
||||
"""
|
||||
items = []
|
||||
item = -1
|
||||
i = 0 # to keep track of where we are
|
||||
|
||||
def detab(line):
|
||||
match = TABBED_RE.match(line)
|
||||
if match:
|
||||
return match.group(4)
|
||||
|
||||
for line in lines:
|
||||
if line.strip(): # Non-blank line
|
||||
line = detab(line)
|
||||
if line:
|
||||
items.append(line)
|
||||
i += 1
|
||||
continue
|
||||
else:
|
||||
return items, lines[i:]
|
||||
|
||||
else: # Blank line: _maybe_ we are done.
|
||||
i += 1 # advance
|
||||
|
||||
# Find the next non-blank line
|
||||
for j in range(i, len(lines)):
|
||||
if lines[j].strip():
|
||||
next_line = lines[j]; break
|
||||
else:
|
||||
break # There is no more text; we are done.
|
||||
|
||||
# Check if the next non-blank line is tabbed
|
||||
if detab(next_line): # Yes, more work to do.
|
||||
items.append("")
|
||||
continue
|
||||
else:
|
||||
break # No, we are done.
|
||||
else:
|
||||
i += 1
|
||||
|
||||
return items, lines[i:]
|
||||
|
||||
|
||||
class FootnotePattern(markdown.inlinepatterns.Pattern):
|
||||
""" InlinePattern for footnote markers in a document's body text. """
|
||||
|
||||
def __init__(self, pattern, footnotes):
|
||||
markdown.inlinepatterns.Pattern.__init__(self, pattern)
|
||||
self.footnotes = footnotes
|
||||
|
||||
def handleMatch(self, m):
|
||||
sup = etree.Element("sup")
|
||||
a = etree.SubElement(sup, "a")
|
||||
id = m.group(2)
|
||||
sup.set('id', self.footnotes.makeFootnoteRefId(id))
|
||||
a.set('href', '#' + self.footnotes.makeFootnoteId(id))
|
||||
a.set('rel', 'footnote')
|
||||
a.text = str(self.footnotes.footnotes.index(id) + 1)
|
||||
return sup
|
||||
|
||||
|
||||
class FootnoteTreeprocessor(markdown.treeprocessors.Treeprocessor):
|
||||
""" Build and append footnote div to end of document. """
|
||||
|
||||
def __init__ (self, footnotes):
|
||||
self.footnotes = footnotes
|
||||
|
||||
def run(self, root):
|
||||
footnotesDiv = self.footnotes.makeFootnotesDiv(root)
|
||||
if footnotesDiv:
|
||||
result = self.footnotes.findFootnotesPlaceholder(root)
|
||||
if result:
|
||||
node, isText = result
|
||||
if isText:
|
||||
node.text = None
|
||||
node.getchildren().insert(0, footnotesDiv)
|
||||
else:
|
||||
child, element = node
|
||||
ind = element.getchildren().find(child)
|
||||
element.getchildren().insert(ind + 1, footnotesDiv)
|
||||
child.tail = None
|
||||
fnPlaceholder.parent.replaceChild(fnPlaceholder, footnotesDiv)
|
||||
else:
|
||||
root.append(footnotesDiv)
|
||||
|
||||
class FootnotePostprocessor(markdown.postprocessors.Postprocessor):
|
||||
""" Replace placeholders with html entities. """
|
||||
|
||||
def run(self, text):
|
||||
text = text.replace(FN_BACKLINK_TEXT, "↩")
|
||||
return text.replace(NBSP_PLACEHOLDER, " ")
|
||||
|
||||
def makeExtension(configs=[]):
|
||||
""" Return an instance of the FootnoteExtension """
|
||||
return FootnoteExtension(configs=configs)
|
||||
|
||||
195
src/calibre/ebooks/markdown/extensions/headerid.py
Normal file
195
src/calibre/ebooks/markdown/extensions/headerid.py
Normal file
@ -0,0 +1,195 @@
|
||||
#!/usr/bin/python
|
||||
|
||||
"""
|
||||
HeaderID Extension for Python-Markdown
|
||||
======================================
|
||||
|
||||
Adds ability to set HTML IDs for headers.
|
||||
|
||||
Basic usage:
|
||||
|
||||
>>> import markdown
|
||||
>>> text = "# Some Header # {#some_id}"
|
||||
>>> md = markdown.markdown(text, ['headerid'])
|
||||
>>> md
|
||||
u'<h1 id="some_id">Some Header</h1>'
|
||||
|
||||
All header IDs are unique:
|
||||
|
||||
>>> text = '''
|
||||
... #Header
|
||||
... #Another Header {#header}
|
||||
... #Third Header {#header}'''
|
||||
>>> md = markdown.markdown(text, ['headerid'])
|
||||
>>> md
|
||||
u'<h1 id="header">Header</h1>\\n<h1 id="header_1">Another Header</h1>\\n<h1 id="header_2">Third Header</h1>'
|
||||
|
||||
To fit within a html template's hierarchy, set the header base level:
|
||||
|
||||
>>> text = '''
|
||||
... #Some Header
|
||||
... ## Next Level'''
|
||||
>>> md = markdown.markdown(text, ['headerid(level=3)'])
|
||||
>>> md
|
||||
u'<h3 id="some_header">Some Header</h3>\\n<h4 id="next_level">Next Level</h4>'
|
||||
|
||||
Turn off auto generated IDs:
|
||||
|
||||
>>> text = '''
|
||||
... # Some Header
|
||||
... # Header with ID # { #foo }'''
|
||||
>>> md = markdown.markdown(text, ['headerid(forceid=False)'])
|
||||
>>> md
|
||||
u'<h1>Some Header</h1>\\n<h1 id="foo">Header with ID</h1>'
|
||||
|
||||
Use with MetaData extension:
|
||||
|
||||
>>> text = '''header_level: 2
|
||||
... header_forceid: Off
|
||||
...
|
||||
... # A Header'''
|
||||
>>> md = markdown.markdown(text, ['headerid', 'meta'])
|
||||
>>> md
|
||||
u'<h2>A Header</h2>'
|
||||
|
||||
Copyright 2007-2008 [Waylan Limberg](http://achinghead.com/).
|
||||
|
||||
Project website: <http://www.freewisdom.org/project/python-markdown/HeaderId>
|
||||
Contact: markdown@freewisdom.org
|
||||
|
||||
License: BSD (see ../docs/LICENSE for details)
|
||||
|
||||
Dependencies:
|
||||
* [Python 2.3+](http://python.org)
|
||||
* [Markdown 2.0+](http://www.freewisdom.org/projects/python-markdown/)
|
||||
|
||||
"""
|
||||
|
||||
import calibre.ebooks.markdown.markdown as markdown
|
||||
from calibre.ebooks.markdown.markdown import etree
|
||||
import re
|
||||
from string import ascii_lowercase, digits, punctuation
|
||||
|
||||
ID_CHARS = ascii_lowercase + digits + '-_'
|
||||
IDCOUNT_RE = re.compile(r'^(.*)_([0-9]+)$')
|
||||
|
||||
|
||||
class HeaderIdProcessor(markdown.blockprocessors.BlockProcessor):
|
||||
""" Replacement BlockProcessor for Header IDs. """
|
||||
|
||||
# Detect a header at start of any line in block
|
||||
RE = re.compile(r"""(^|\n)
|
||||
(?P<level>\#{1,6}) # group('level') = string of hashes
|
||||
(?P<header>.*?) # group('header') = Header text
|
||||
\#* # optional closing hashes
|
||||
(?:[ \t]*\{[ \t]*\#(?P<id>[-_:a-zA-Z0-9]+)[ \t]*\})?
|
||||
(\n|$) # ^^ group('id') = id attribute
|
||||
""",
|
||||
re.VERBOSE)
|
||||
|
||||
IDs = []
|
||||
|
||||
def test(self, parent, block):
|
||||
return bool(self.RE.search(block))
|
||||
|
||||
def run(self, parent, blocks):
|
||||
block = blocks.pop(0)
|
||||
m = self.RE.search(block)
|
||||
if m:
|
||||
before = block[:m.start()] # All lines before header
|
||||
after = block[m.end():] # All lines after header
|
||||
if before:
|
||||
# As the header was not the first line of the block and the
|
||||
# lines before the header must be parsed first,
|
||||
# recursively parse this lines as a block.
|
||||
self.parser.parseBlocks(parent, [before])
|
||||
# Create header using named groups from RE
|
||||
start_level, force_id = self._get_meta()
|
||||
level = len(m.group('level')) + start_level
|
||||
if level > 6:
|
||||
level = 6
|
||||
h = markdown.etree.SubElement(parent, 'h%d' % level)
|
||||
h.text = m.group('header').strip()
|
||||
if m.group('id'):
|
||||
h.set('id', self._unique_id(m.group('id')))
|
||||
elif force_id:
|
||||
h.set('id', self._create_id(m.group('header').strip()))
|
||||
if after:
|
||||
# Insert remaining lines as first block for future parsing.
|
||||
blocks.insert(0, after)
|
||||
else:
|
||||
# This should never happen, but just in case...
|
||||
message(CRITICAL, "We've got a problem header!")
|
||||
|
||||
def _get_meta(self):
|
||||
""" Return meta data suported by this ext as a tuple """
|
||||
level = int(self.config['level'][0]) - 1
|
||||
force = self._str2bool(self.config['forceid'][0])
|
||||
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'):
|
||||
force = self._str2bool(self.md.Meta['header_forceid'][0])
|
||||
return level, force
|
||||
|
||||
def _str2bool(self, s, default=False):
|
||||
""" Convert a string to a booleen value. """
|
||||
s = str(s)
|
||||
if s.lower() in ['0', 'f', 'false', 'off', 'no', 'n']:
|
||||
return False
|
||||
elif s.lower() in ['1', 't', 'true', 'on', 'yes', 'y']:
|
||||
return True
|
||||
return default
|
||||
|
||||
def _unique_id(self, id):
|
||||
""" Ensure ID is unique. Append '_1', '_2'... if not """
|
||||
while id in self.IDs:
|
||||
m = IDCOUNT_RE.match(id)
|
||||
if m:
|
||||
id = '%s_%d'% (m.group(1), int(m.group(2))+1)
|
||||
else:
|
||||
id = '%s_%d'% (id, 1)
|
||||
self.IDs.append(id)
|
||||
return id
|
||||
|
||||
def _create_id(self, header):
|
||||
""" Return ID from Header text. """
|
||||
h = ''
|
||||
for c in header.lower().replace(' ', '_'):
|
||||
if c in ID_CHARS:
|
||||
h += c
|
||||
elif c not in punctuation:
|
||||
h += '+'
|
||||
return self._unique_id(h)
|
||||
|
||||
|
||||
class HeaderIdExtension (markdown.Extension):
|
||||
def __init__(self, configs):
|
||||
# set defaults
|
||||
self.config = {
|
||||
'level' : ['1', 'Base level for headers.'],
|
||||
'forceid' : ['True', 'Force all headers to have an id.']
|
||||
}
|
||||
|
||||
for key, value in configs:
|
||||
self.setConfig(key, value)
|
||||
|
||||
def extendMarkdown(self, md, md_globals):
|
||||
md.registerExtension(self)
|
||||
self.processor = HeaderIdProcessor(md.parser)
|
||||
self.processor.md = md
|
||||
self.processor.config = self.config
|
||||
# Replace existing hasheader in place.
|
||||
md.parser.blockprocessors['hashheader'] = self.processor
|
||||
|
||||
def reset(self):
|
||||
self.processor.IDs = []
|
||||
|
||||
|
||||
def makeExtension(configs=None):
|
||||
return HeaderIdExtension(configs=configs)
|
||||
|
||||
if __name__ == "__main__":
|
||||
import doctest
|
||||
doctest.testmod()
|
||||
|
||||
91
src/calibre/ebooks/markdown/extensions/meta.py
Normal file
91
src/calibre/ebooks/markdown/extensions/meta.py
Normal file
@ -0,0 +1,91 @@
|
||||
#!usr/bin/python
|
||||
|
||||
"""
|
||||
Meta Data Extension for Python-Markdown
|
||||
=======================================
|
||||
|
||||
This extension adds Meta Data handling to markdown.
|
||||
|
||||
Basic Usage:
|
||||
|
||||
>>> import markdown
|
||||
>>> text = '''Title: A Test Doc.
|
||||
... Author: Waylan Limberg
|
||||
... John Doe
|
||||
... Blank_Data:
|
||||
...
|
||||
... The body. This is paragraph one.
|
||||
... '''
|
||||
>>> md = markdown.Markdown(['meta'])
|
||||
>>> md.convert(text)
|
||||
u'<p>The body. This is paragraph one.</p>'
|
||||
>>> md.Meta
|
||||
{u'blank_data': [u''], u'author': [u'Waylan Limberg', u'John Doe'], u'title': [u'A Test Doc.']}
|
||||
|
||||
Make sure text without Meta Data still works (markdown < 1.6b returns a <p>).
|
||||
|
||||
>>> text = ' Some Code - not extra lines of meta data.'
|
||||
>>> md = markdown.Markdown(['meta'])
|
||||
>>> md.convert(text)
|
||||
u'<pre><code>Some Code - not extra lines of meta data.\\n</code></pre>'
|
||||
>>> md.Meta
|
||||
{}
|
||||
|
||||
Copyright 2007-2008 [Waylan Limberg](http://achinghead.com).
|
||||
|
||||
Project website: <http://www.freewisdom.org/project/python-markdown/Meta-Data>
|
||||
Contact: markdown@freewisdom.org
|
||||
|
||||
License: BSD (see ../docs/LICENSE for details)
|
||||
|
||||
"""
|
||||
|
||||
import re
|
||||
import calibre.ebooks.markdown.markdown as markdown
|
||||
|
||||
# Global Vars
|
||||
META_RE = re.compile(r'^[ ]{0,3}(?P<key>[A-Za-z0-9_-]+):\s*(?P<value>.*)')
|
||||
META_MORE_RE = re.compile(r'^[ ]{4,}(?P<value>.*)')
|
||||
|
||||
class MetaExtension (markdown.Extension):
|
||||
""" Meta-Data extension for Python-Markdown. """
|
||||
|
||||
def extendMarkdown(self, md, md_globals):
|
||||
""" Add MetaPreprocessor to Markdown instance. """
|
||||
|
||||
md.preprocessors.add("meta", MetaPreprocessor(md), "_begin")
|
||||
|
||||
|
||||
class MetaPreprocessor(markdown.preprocessors.Preprocessor):
|
||||
""" Get Meta-Data. """
|
||||
|
||||
def run(self, lines):
|
||||
""" Parse Meta-Data and store in Markdown.Meta. """
|
||||
meta = {}
|
||||
key = None
|
||||
while 1:
|
||||
line = lines.pop(0)
|
||||
if line.strip() == '':
|
||||
break # blank line - done
|
||||
m1 = META_RE.match(line)
|
||||
if m1:
|
||||
key = m1.group('key').lower().strip()
|
||||
meta[key] = [m1.group('value').strip()]
|
||||
else:
|
||||
m2 = META_MORE_RE.match(line)
|
||||
if m2 and key:
|
||||
# Add another line to existing key
|
||||
meta[key].append(m2.group('value').strip())
|
||||
else:
|
||||
lines.insert(0, line)
|
||||
break # no meta data - done
|
||||
self.markdown.Meta = meta
|
||||
return lines
|
||||
|
||||
|
||||
def makeExtension(configs={}):
|
||||
return MetaExtension(configs=configs)
|
||||
|
||||
if __name__ == "__main__":
|
||||
import doctest
|
||||
doctest.testmod()
|
||||
114
src/calibre/ebooks/markdown/extensions/rss.py
Normal file
114
src/calibre/ebooks/markdown/extensions/rss.py
Normal file
@ -0,0 +1,114 @@
|
||||
import calibre.ebooks.markdown.markdown as markdown
|
||||
from calibre.ebooks.markdown.markdown import etree
|
||||
|
||||
DEFAULT_URL = "http://www.freewisdom.org/projects/python-markdown/"
|
||||
DEFAULT_CREATOR = "Yuri Takhteyev"
|
||||
DEFAULT_TITLE = "Markdown in Python"
|
||||
GENERATOR = "http://www.freewisdom.org/projects/python-markdown/markdown2rss"
|
||||
|
||||
month_map = { "Jan" : "01",
|
||||
"Feb" : "02",
|
||||
"March" : "03",
|
||||
"April" : "04",
|
||||
"May" : "05",
|
||||
"June" : "06",
|
||||
"July" : "07",
|
||||
"August" : "08",
|
||||
"September" : "09",
|
||||
"October" : "10",
|
||||
"November" : "11",
|
||||
"December" : "12" }
|
||||
|
||||
def get_time(heading):
|
||||
|
||||
heading = heading.split("-")[0]
|
||||
heading = heading.strip().replace(",", " ").replace(".", " ")
|
||||
|
||||
month, date, year = heading.split()
|
||||
month = month_map[month]
|
||||
|
||||
return rdftime(" ".join((month, date, year, "12:00:00 AM")))
|
||||
|
||||
def rdftime(time):
|
||||
|
||||
time = time.replace(":", " ")
|
||||
time = time.replace("/", " ")
|
||||
time = time.split()
|
||||
return "%s-%s-%sT%s:%s:%s-08:00" % (time[0], time[1], time[2],
|
||||
time[3], time[4], time[5])
|
||||
|
||||
|
||||
def get_date(text):
|
||||
return "date"
|
||||
|
||||
class RssExtension (markdown.Extension):
|
||||
|
||||
def extendMarkdown(self, md, md_globals):
|
||||
|
||||
self.config = { 'URL' : [DEFAULT_URL, "Main URL"],
|
||||
'CREATOR' : [DEFAULT_CREATOR, "Feed creator's name"],
|
||||
'TITLE' : [DEFAULT_TITLE, "Feed title"] }
|
||||
|
||||
md.xml_mode = True
|
||||
|
||||
# Insert a tree-processor that would actually add the title tag
|
||||
treeprocessor = RssTreeProcessor(md)
|
||||
treeprocessor.ext = self
|
||||
md.treeprocessors['rss'] = treeprocessor
|
||||
md.stripTopLevelTags = 0
|
||||
md.docType = '<?xml version="1.0" encoding="utf-8"?>\n'
|
||||
|
||||
class RssTreeProcessor(markdown.treeprocessors.Treeprocessor):
|
||||
|
||||
def run (self, root):
|
||||
|
||||
rss = etree.Element("rss")
|
||||
rss.set("version", "2.0")
|
||||
|
||||
channel = etree.SubElement(rss, "channel")
|
||||
|
||||
for tag, text in (("title", self.ext.getConfig("TITLE")),
|
||||
("link", self.ext.getConfig("URL")),
|
||||
("description", None)):
|
||||
|
||||
element = etree.SubElement(channel, tag)
|
||||
element.text = text
|
||||
|
||||
for child in root:
|
||||
|
||||
if child.tag in ["h1", "h2", "h3", "h4", "h5"]:
|
||||
|
||||
heading = child.text.strip()
|
||||
item = etree.SubElement(channel, "item")
|
||||
link = etree.SubElement(item, "link")
|
||||
link.text = self.ext.getConfig("URL")
|
||||
title = etree.SubElement(item, "title")
|
||||
title.text = heading
|
||||
|
||||
guid = ''.join([x for x in heading if x.isalnum()])
|
||||
guidElem = etree.SubElement(item, "guid")
|
||||
guidElem.text = guid
|
||||
guidElem.set("isPermaLink", "false")
|
||||
|
||||
elif child.tag in ["p"]:
|
||||
try:
|
||||
description = etree.SubElement(item, "description")
|
||||
except UnboundLocalError:
|
||||
# Item not defined - moving on
|
||||
pass
|
||||
else:
|
||||
if len(child):
|
||||
content = "\n".join([etree.tostring(node)
|
||||
for node in child])
|
||||
else:
|
||||
content = child.text
|
||||
pholder = self.markdown.htmlStash.store(
|
||||
"<![CDATA[ %s]]>" % content)
|
||||
description.text = pholder
|
||||
|
||||
return rss
|
||||
|
||||
|
||||
def makeExtension(configs):
|
||||
|
||||
return RssExtension(configs)
|
||||
97
src/calibre/ebooks/markdown/extensions/tables.py
Normal file
97
src/calibre/ebooks/markdown/extensions/tables.py
Normal file
@ -0,0 +1,97 @@
|
||||
#!/usr/bin/env Python
|
||||
"""
|
||||
Tables Extension for Python-Markdown
|
||||
====================================
|
||||
|
||||
Added parsing of tables to Python-Markdown.
|
||||
|
||||
A simple example:
|
||||
|
||||
First Header | Second Header
|
||||
------------- | -------------
|
||||
Content Cell | Content Cell
|
||||
Content Cell | Content Cell
|
||||
|
||||
Copyright 2009 - [Waylan Limberg](http://achinghead.com)
|
||||
"""
|
||||
import calibre.ebooks.markdown.markdown as markdown
|
||||
from calibre.ebooks.markdown.markdown import etree
|
||||
|
||||
|
||||
class TableProcessor(markdown.blockprocessors.BlockProcessor):
|
||||
""" Process Tables. """
|
||||
|
||||
def test(self, parent, block):
|
||||
rows = block.split('\n')
|
||||
return (len(rows) > 2 and '|' in rows[0] and
|
||||
'|' in rows[1] and '-' in rows[1] and
|
||||
rows[1][0] in ['|', ':', '-'])
|
||||
|
||||
def run(self, parent, blocks):
|
||||
""" Parse a table block and build table. """
|
||||
block = blocks.pop(0).split('\n')
|
||||
header = block[:2]
|
||||
rows = block[2:]
|
||||
# Get format type (bordered by pipes or not)
|
||||
border = False
|
||||
if header[0].startswith('|'):
|
||||
border = True
|
||||
# Get alignment of columns
|
||||
align = []
|
||||
for c in self._split_row(header[1], border):
|
||||
if c.startswith(':') and c.endswith(':'):
|
||||
align.append('center')
|
||||
elif c.startswith(':'):
|
||||
align.append('left')
|
||||
elif c.endswith(':'):
|
||||
align.append('right')
|
||||
else:
|
||||
align.append(None)
|
||||
# Build table
|
||||
table = etree.SubElement(parent, 'table')
|
||||
thead = etree.SubElement(table, 'thead')
|
||||
self._build_row(header[0], thead, align, border)
|
||||
tbody = etree.SubElement(table, 'tbody')
|
||||
for row in rows:
|
||||
self._build_row(row, tbody, align, border)
|
||||
|
||||
def _build_row(self, row, parent, align, border):
|
||||
""" Given a row of text, build table cells. """
|
||||
tr = etree.SubElement(parent, 'tr')
|
||||
tag = 'td'
|
||||
if parent.tag == 'thead':
|
||||
tag = 'th'
|
||||
cells = self._split_row(row, border)
|
||||
# We use align here rather than cells to ensure every row
|
||||
# contains the same number of columns.
|
||||
for i, a in enumerate(align):
|
||||
c = etree.SubElement(tr, tag)
|
||||
try:
|
||||
c.text = cells[i].strip()
|
||||
except IndexError:
|
||||
c.text = ""
|
||||
if a:
|
||||
c.set('align', a)
|
||||
|
||||
def _split_row(self, row, border):
|
||||
""" split a row of text into list of cells. """
|
||||
if border:
|
||||
if row.startswith('|'):
|
||||
row = row[1:]
|
||||
if row.endswith('|'):
|
||||
row = row[:-1]
|
||||
return row.split('|')
|
||||
|
||||
|
||||
class TableExtension(markdown.Extension):
|
||||
""" Add tables to Markdown. """
|
||||
|
||||
def extendMarkdown(self, md, md_globals):
|
||||
""" Add an instance of TableProcessor to BlockParser. """
|
||||
md.parser.blockprocessors.add('table',
|
||||
TableProcessor(md.parser),
|
||||
'<hashheader')
|
||||
|
||||
|
||||
def makeExtension(configs={}):
|
||||
return TableExtension(configs=configs)
|
||||
140
src/calibre/ebooks/markdown/extensions/toc.py
Normal file
140
src/calibre/ebooks/markdown/extensions/toc.py
Normal file
@ -0,0 +1,140 @@
|
||||
"""
|
||||
Table of Contents Extension for Python-Markdown
|
||||
* * *
|
||||
|
||||
(c) 2008 [Jack Miller](http://codezen.org)
|
||||
|
||||
Dependencies:
|
||||
* [Markdown 2.0+](http://www.freewisdom.org/projects/python-markdown/)
|
||||
|
||||
"""
|
||||
import calibre.ebooks.markdown.markdown as markdown
|
||||
from calibre.ebooks.markdown.markdown import etree
|
||||
import re
|
||||
|
||||
class TocTreeprocessor(markdown.treeprocessors.Treeprocessor):
|
||||
# Iterator wrapper to get parent and child all at once
|
||||
def iterparent(self, root):
|
||||
for parent in root.getiterator():
|
||||
for child in parent:
|
||||
yield parent, child
|
||||
|
||||
def run(self, doc):
|
||||
div = etree.Element("div")
|
||||
div.attrib["class"] = "toc"
|
||||
last_li = None
|
||||
|
||||
# Add title to the div
|
||||
if self.config["title"][0]:
|
||||
header = etree.SubElement(div, "span")
|
||||
header.attrib["class"] = "toctitle"
|
||||
header.text = self.config["title"][0]
|
||||
|
||||
level = 0
|
||||
list_stack=[div]
|
||||
header_rgx = re.compile("[Hh][123456]")
|
||||
|
||||
# Get a list of id attributes
|
||||
used_ids = []
|
||||
for c in doc.getiterator():
|
||||
if "id" in c.attrib:
|
||||
used_ids.append(c.attrib["id"])
|
||||
|
||||
for (p, c) in self.iterparent(doc):
|
||||
if not c.text:
|
||||
continue
|
||||
|
||||
# To keep the output from screwing up the
|
||||
# validation by putting a <div> inside of a <p>
|
||||
# we actually replace the <p> in its entirety.
|
||||
# We do not allow the marker inside a header as that
|
||||
# would causes an enless loop of placing a new TOC
|
||||
# inside previously generated TOC.
|
||||
|
||||
if c.text.find(self.config["marker"][0]) > -1 and not header_rgx.match(c.tag):
|
||||
for i in range(len(p)):
|
||||
if p[i] == c:
|
||||
p[i] = div
|
||||
break
|
||||
|
||||
if header_rgx.match(c.tag):
|
||||
tag_level = int(c.tag[-1])
|
||||
|
||||
# Regardless of how many levels we jumped
|
||||
# only one list should be created, since
|
||||
# empty lists containing lists are illegal.
|
||||
|
||||
if tag_level < level:
|
||||
list_stack.pop()
|
||||
level = tag_level
|
||||
|
||||
if tag_level > level:
|
||||
newlist = etree.Element("ul")
|
||||
if last_li:
|
||||
last_li.append(newlist)
|
||||
else:
|
||||
list_stack[-1].append(newlist)
|
||||
list_stack.append(newlist)
|
||||
level = tag_level
|
||||
|
||||
# Do not override pre-existing ids
|
||||
if not "id" in c.attrib:
|
||||
id = self.config["slugify"][0](c.text)
|
||||
if id in used_ids:
|
||||
ctr = 1
|
||||
while "%s_%d" % (id, ctr) in used_ids:
|
||||
ctr += 1
|
||||
id = "%s_%d" % (id, ctr)
|
||||
used_ids.append(id)
|
||||
c.attrib["id"] = id
|
||||
else:
|
||||
id = c.attrib["id"]
|
||||
|
||||
# List item link, to be inserted into the toc div
|
||||
last_li = etree.Element("li")
|
||||
link = etree.SubElement(last_li, "a")
|
||||
link.text = c.text
|
||||
link.attrib["href"] = '#' + id
|
||||
|
||||
if int(self.config["anchorlink"][0]):
|
||||
anchor = etree.SubElement(c, "a")
|
||||
anchor.text = c.text
|
||||
anchor.attrib["href"] = "#" + id
|
||||
anchor.attrib["class"] = "toclink"
|
||||
c.text = ""
|
||||
|
||||
list_stack[-1].append(last_li)
|
||||
|
||||
class TocExtension(markdown.Extension):
|
||||
def __init__(self, configs):
|
||||
self.config = { "marker" : ["[TOC]",
|
||||
"Text to find and replace with Table of Contents -"
|
||||
"Defaults to \"[TOC]\""],
|
||||
"slugify" : [self.slugify,
|
||||
"Function to generate anchors based on header text-"
|
||||
"Defaults to a built in slugify function."],
|
||||
"title" : [None,
|
||||
"Title to insert into TOC <div> - "
|
||||
"Defaults to None"],
|
||||
"anchorlink" : [0,
|
||||
"1 if header should be a self link"
|
||||
"Defaults to 0"]}
|
||||
|
||||
for key, value in configs:
|
||||
self.setConfig(key, value)
|
||||
|
||||
# This is exactly the same as Django's slugify
|
||||
def slugify(self, value):
|
||||
""" Slugify a string, to make it URL friendly. """
|
||||
import unicodedata
|
||||
value = unicodedata.normalize('NFKD', value).encode('ascii', 'ignore')
|
||||
value = unicode(re.sub('[^\w\s-]', '', value).strip().lower())
|
||||
return re.sub('[-\s]+','-',value)
|
||||
|
||||
def extendMarkdown(self, md, md_globals):
|
||||
tocext = TocTreeprocessor(md)
|
||||
tocext.config = self.config
|
||||
md.treeprocessors.add("toc", tocext, "_begin")
|
||||
|
||||
def makeExtension(configs={}):
|
||||
return TocExtension(configs=configs)
|
||||
155
src/calibre/ebooks/markdown/extensions/wikilinks.py
Normal file
155
src/calibre/ebooks/markdown/extensions/wikilinks.py
Normal file
@ -0,0 +1,155 @@
|
||||
#!/usr/bin/env python
|
||||
|
||||
'''
|
||||
WikiLinks Extension for Python-Markdown
|
||||
======================================
|
||||
|
||||
Converts [[WikiLinks]] to relative links. Requires Python-Markdown 2.0+
|
||||
|
||||
Basic usage:
|
||||
|
||||
>>> import markdown
|
||||
>>> text = "Some text with a [[WikiLink]]."
|
||||
>>> html = markdown.markdown(text, ['wikilinks'])
|
||||
>>> html
|
||||
u'<p>Some text with a <a class="wikilink" href="/WikiLink/">WikiLink</a>.</p>'
|
||||
|
||||
Whitespace behavior:
|
||||
|
||||
>>> markdown.markdown('[[ foo bar_baz ]]', ['wikilinks'])
|
||||
u'<p><a class="wikilink" href="/foo_bar_baz/">foo bar_baz</a></p>'
|
||||
>>> markdown.markdown('foo [[ ]] bar', ['wikilinks'])
|
||||
u'<p>foo bar</p>'
|
||||
|
||||
To define custom settings the simple way:
|
||||
|
||||
>>> markdown.markdown(text,
|
||||
... ['wikilinks(base_url=/wiki/,end_url=.html,html_class=foo)']
|
||||
... )
|
||||
u'<p>Some text with a <a class="foo" href="/wiki/WikiLink.html">WikiLink</a>.</p>'
|
||||
|
||||
Custom settings the complex way:
|
||||
|
||||
>>> md = markdown.Markdown(
|
||||
... extensions = ['wikilinks'],
|
||||
... extension_configs = {'wikilinks': [
|
||||
... ('base_url', 'http://example.com/'),
|
||||
... ('end_url', '.html'),
|
||||
... ('html_class', '') ]},
|
||||
... safe_mode = True)
|
||||
>>> md.convert(text)
|
||||
u'<p>Some text with a <a href="http://example.com/WikiLink.html">WikiLink</a>.</p>'
|
||||
|
||||
Use MetaData with mdx_meta.py (Note the blank html_class in MetaData):
|
||||
|
||||
>>> text = """wiki_base_url: http://example.com/
|
||||
... wiki_end_url: .html
|
||||
... wiki_html_class:
|
||||
...
|
||||
... Some text with a [[WikiLink]]."""
|
||||
>>> md = markdown.Markdown(extensions=['meta', 'wikilinks'])
|
||||
>>> md.convert(text)
|
||||
u'<p>Some text with a <a href="http://example.com/WikiLink.html">WikiLink</a>.</p>'
|
||||
|
||||
MetaData should not carry over to next document:
|
||||
|
||||
>>> md.convert("No [[MetaData]] here.")
|
||||
u'<p>No <a class="wikilink" href="/MetaData/">MetaData</a> here.</p>'
|
||||
|
||||
Define a custom URL builder:
|
||||
|
||||
>>> def my_url_builder(label, base, end):
|
||||
... return '/bar/'
|
||||
>>> md = markdown.Markdown(extensions=['wikilinks'],
|
||||
... extension_configs={'wikilinks' : [('build_url', my_url_builder)]})
|
||||
>>> md.convert('[[foo]]')
|
||||
u'<p><a class="wikilink" href="/bar/">foo</a></p>'
|
||||
|
||||
From the command line:
|
||||
|
||||
python markdown.py -x wikilinks(base_url=http://example.com/,end_url=.html,html_class=foo) src.txt
|
||||
|
||||
By [Waylan Limberg](http://achinghead.com/).
|
||||
|
||||
License: [BSD](http://www.opensource.org/licenses/bsd-license.php)
|
||||
|
||||
Dependencies:
|
||||
* [Python 2.3+](http://python.org)
|
||||
* [Markdown 2.0+](http://www.freewisdom.org/projects/python-markdown/)
|
||||
'''
|
||||
|
||||
import calibre.ebooks.markdown.markdown as markdown
|
||||
import re
|
||||
|
||||
def build_url(label, base, end):
|
||||
""" Build a url from the label, a base, and an end. """
|
||||
clean_label = re.sub(r'([ ]+_)|(_[ ]+)|([ ]+)', '_', label)
|
||||
return '%s%s%s'% (base, clean_label, end)
|
||||
|
||||
|
||||
class WikiLinkExtension(markdown.Extension):
|
||||
def __init__(self, configs):
|
||||
# set extension defaults
|
||||
self.config = {
|
||||
'base_url' : ['/', 'String to append to beginning or URL.'],
|
||||
'end_url' : ['/', 'String to append to end of URL.'],
|
||||
'html_class' : ['wikilink', 'CSS hook. Leave blank for none.'],
|
||||
'build_url' : [build_url, 'Callable formats URL from label.'],
|
||||
}
|
||||
|
||||
# Override defaults with user settings
|
||||
for key, value in configs :
|
||||
self.setConfig(key, value)
|
||||
|
||||
def extendMarkdown(self, md, md_globals):
|
||||
self.md = md
|
||||
|
||||
# append to end of inline patterns
|
||||
WIKILINK_RE = r'\[\[([A-Za-z0-9_ -]+)\]\]'
|
||||
wikilinkPattern = WikiLinks(WIKILINK_RE, self.config)
|
||||
wikilinkPattern.md = md
|
||||
md.inlinePatterns.add('wikilink', wikilinkPattern, "<not_strong")
|
||||
|
||||
|
||||
class WikiLinks(markdown.inlinepatterns.Pattern):
|
||||
def __init__(self, pattern, config):
|
||||
markdown.inlinepatterns.Pattern.__init__(self, pattern)
|
||||
self.config = config
|
||||
|
||||
def handleMatch(self, m):
|
||||
if m.group(2).strip():
|
||||
base_url, end_url, html_class = self._getMeta()
|
||||
label = m.group(2).strip()
|
||||
url = self.config['build_url'][0](label, base_url, end_url)
|
||||
a = markdown.etree.Element('a')
|
||||
a.text = label
|
||||
a.set('href', url)
|
||||
if html_class:
|
||||
a.set('class', html_class)
|
||||
else:
|
||||
a = ''
|
||||
return a
|
||||
|
||||
def _getMeta(self):
|
||||
""" Return meta data or config data. """
|
||||
base_url = self.config['base_url'][0]
|
||||
end_url = self.config['end_url'][0]
|
||||
html_class = self.config['html_class'][0]
|
||||
if hasattr(self.md, 'Meta'):
|
||||
if self.md.Meta.has_key('wiki_base_url'):
|
||||
base_url = self.md.Meta['wiki_base_url'][0]
|
||||
if self.md.Meta.has_key('wiki_end_url'):
|
||||
end_url = self.md.Meta['wiki_end_url'][0]
|
||||
if self.md.Meta.has_key('wiki_html_class'):
|
||||
html_class = self.md.Meta['wiki_html_class'][0]
|
||||
return base_url, end_url, html_class
|
||||
|
||||
|
||||
def makeExtension(configs=None) :
|
||||
return WikiLinkExtension(configs=configs)
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
import doctest
|
||||
doctest.testmod()
|
||||
|
||||
274
src/calibre/ebooks/markdown/html4.py
Normal file
274
src/calibre/ebooks/markdown/html4.py
Normal file
@ -0,0 +1,274 @@
|
||||
# markdown/html4.py
|
||||
#
|
||||
# Add html4 serialization to older versions of Elementree
|
||||
# Taken from ElementTree 1.3 preview with slight modifications
|
||||
#
|
||||
# Copyright (c) 1999-2007 by Fredrik Lundh. All rights reserved.
|
||||
#
|
||||
# fredrik@pythonware.com
|
||||
# http://www.pythonware.com
|
||||
#
|
||||
# --------------------------------------------------------------------
|
||||
# The ElementTree toolkit is
|
||||
#
|
||||
# Copyright (c) 1999-2007 by Fredrik Lundh
|
||||
#
|
||||
# By obtaining, using, and/or copying this software and/or its
|
||||
# associated documentation, you agree that you have read, understood,
|
||||
# and will comply with the following terms and conditions:
|
||||
#
|
||||
# Permission to use, copy, modify, and distribute this software and
|
||||
# its associated documentation for any purpose and without fee is
|
||||
# hereby granted, provided that the above copyright notice appears in
|
||||
# all copies, and that both that copyright notice and this permission
|
||||
# notice appear in supporting documentation, and that the name of
|
||||
# Secret Labs AB or the author not be used in advertising or publicity
|
||||
# pertaining to distribution of the software without specific, written
|
||||
# prior permission.
|
||||
#
|
||||
# SECRET LABS AB AND THE AUTHOR DISCLAIMS ALL WARRANTIES WITH REGARD
|
||||
# TO THIS SOFTWARE, INCLUDING ALL IMPLIED WARRANTIES OF MERCHANT-
|
||||
# ABILITY AND FITNESS. IN NO EVENT SHALL SECRET LABS AB OR THE AUTHOR
|
||||
# BE LIABLE FOR ANY SPECIAL, INDIRECT OR CONSEQUENTIAL DAMAGES OR ANY
|
||||
# DAMAGES WHATSOEVER RESULTING FROM LOSS OF USE, DATA OR PROFITS,
|
||||
# WHETHER IN AN ACTION OF CONTRACT, NEGLIGENCE OR OTHER TORTIOUS
|
||||
# ACTION, ARISING OUT OF OR IN CONNECTION WITH THE USE OR PERFORMANCE
|
||||
# OF THIS SOFTWARE.
|
||||
# --------------------------------------------------------------------
|
||||
|
||||
|
||||
import markdown
|
||||
ElementTree = markdown.etree.ElementTree
|
||||
QName = markdown.etree.QName
|
||||
Comment = markdown.etree.Comment
|
||||
PI = markdown.etree.PI
|
||||
ProcessingInstruction = markdown.etree.ProcessingInstruction
|
||||
|
||||
HTML_EMPTY = ("area", "base", "basefont", "br", "col", "frame", "hr",
|
||||
"img", "input", "isindex", "link", "meta" "param")
|
||||
|
||||
try:
|
||||
HTML_EMPTY = set(HTML_EMPTY)
|
||||
except NameError:
|
||||
pass
|
||||
|
||||
_namespace_map = {
|
||||
# "well-known" namespace prefixes
|
||||
"http://www.w3.org/XML/1998/namespace": "xml",
|
||||
"http://www.w3.org/1999/xhtml": "html",
|
||||
"http://www.w3.org/1999/02/22-rdf-syntax-ns#": "rdf",
|
||||
"http://schemas.xmlsoap.org/wsdl/": "wsdl",
|
||||
# xml schema
|
||||
"http://www.w3.org/2001/XMLSchema": "xs",
|
||||
"http://www.w3.org/2001/XMLSchema-instance": "xsi",
|
||||
# dublic core
|
||||
"http://purl.org/dc/elements/1.1/": "dc",
|
||||
}
|
||||
|
||||
|
||||
def _raise_serialization_error(text):
|
||||
raise TypeError(
|
||||
"cannot serialize %r (type %s)" % (text, type(text).__name__)
|
||||
)
|
||||
|
||||
def _encode(text, encoding):
|
||||
try:
|
||||
return text.encode(encoding, "xmlcharrefreplace")
|
||||
except (TypeError, AttributeError):
|
||||
_raise_serialization_error(text)
|
||||
|
||||
def _escape_cdata(text, encoding):
|
||||
# escape character data
|
||||
try:
|
||||
# it's worth avoiding do-nothing calls for strings that are
|
||||
# shorter than 500 character, or so. assume that's, by far,
|
||||
# the most common case in most applications.
|
||||
if "&" in text:
|
||||
text = text.replace("&", "&")
|
||||
if "<" in text:
|
||||
text = text.replace("<", "<")
|
||||
if ">" in text:
|
||||
text = text.replace(">", ">")
|
||||
return text.encode(encoding, "xmlcharrefreplace")
|
||||
except (TypeError, AttributeError):
|
||||
_raise_serialization_error(text)
|
||||
|
||||
|
||||
def _escape_attrib(text, encoding):
|
||||
# escape attribute value
|
||||
try:
|
||||
if "&" in text:
|
||||
text = text.replace("&", "&")
|
||||
if "<" in text:
|
||||
text = text.replace("<", "<")
|
||||
if ">" in text:
|
||||
text = text.replace(">", ">")
|
||||
if "\"" in text:
|
||||
text = text.replace("\"", """)
|
||||
if "\n" in text:
|
||||
text = text.replace("\n", " ")
|
||||
return text.encode(encoding, "xmlcharrefreplace")
|
||||
except (TypeError, AttributeError):
|
||||
_raise_serialization_error(text)
|
||||
|
||||
def _escape_attrib_html(text, encoding):
|
||||
# escape attribute value
|
||||
try:
|
||||
if "&" in text:
|
||||
text = text.replace("&", "&")
|
||||
if ">" in text:
|
||||
text = text.replace(">", ">")
|
||||
if "\"" in text:
|
||||
text = text.replace("\"", """)
|
||||
return text.encode(encoding, "xmlcharrefreplace")
|
||||
except (TypeError, AttributeError):
|
||||
_raise_serialization_error(text)
|
||||
|
||||
|
||||
def _serialize_html(write, elem, encoding, qnames, namespaces):
|
||||
tag = elem.tag
|
||||
text = elem.text
|
||||
if tag is Comment:
|
||||
write("<!--%s-->" % _escape_cdata(text, encoding))
|
||||
elif tag is ProcessingInstruction:
|
||||
write("<?%s?>" % _escape_cdata(text, encoding))
|
||||
else:
|
||||
tag = qnames[tag]
|
||||
if tag is None:
|
||||
if text:
|
||||
write(_escape_cdata(text, encoding))
|
||||
for e in elem:
|
||||
_serialize_html(write, e, encoding, qnames, None)
|
||||
else:
|
||||
write("<" + tag)
|
||||
items = elem.items()
|
||||
if items or namespaces:
|
||||
items.sort() # lexical order
|
||||
for k, v in items:
|
||||
if isinstance(k, QName):
|
||||
k = k.text
|
||||
if isinstance(v, QName):
|
||||
v = qnames[v.text]
|
||||
else:
|
||||
v = _escape_attrib_html(v, encoding)
|
||||
# FIXME: handle boolean attributes
|
||||
write(" %s=\"%s\"" % (qnames[k], v))
|
||||
if namespaces:
|
||||
items = namespaces.items()
|
||||
items.sort(key=lambda x: x[1]) # sort on prefix
|
||||
for v, k in items:
|
||||
if k:
|
||||
k = ":" + k
|
||||
write(" xmlns%s=\"%s\"" % (
|
||||
k.encode(encoding),
|
||||
_escape_attrib(v, encoding)
|
||||
))
|
||||
write(">")
|
||||
tag = tag.lower()
|
||||
if text:
|
||||
if tag == "script" or tag == "style":
|
||||
write(_encode(text, encoding))
|
||||
else:
|
||||
write(_escape_cdata(text, encoding))
|
||||
for e in elem:
|
||||
_serialize_html(write, e, encoding, qnames, None)
|
||||
if tag not in HTML_EMPTY:
|
||||
write("</" + tag + ">")
|
||||
if elem.tail:
|
||||
write(_escape_cdata(elem.tail, encoding))
|
||||
|
||||
def write_html(root, f,
|
||||
# keyword arguments
|
||||
encoding="us-ascii",
|
||||
default_namespace=None):
|
||||
assert root is not None
|
||||
if not hasattr(f, "write"):
|
||||
f = open(f, "wb")
|
||||
write = f.write
|
||||
if not encoding:
|
||||
encoding = "us-ascii"
|
||||
qnames, namespaces = _namespaces(
|
||||
root, encoding, default_namespace
|
||||
)
|
||||
_serialize_html(
|
||||
write, root, encoding, qnames, namespaces
|
||||
)
|
||||
|
||||
# --------------------------------------------------------------------
|
||||
# serialization support
|
||||
|
||||
def _namespaces(elem, encoding, default_namespace=None):
|
||||
# identify namespaces used in this tree
|
||||
|
||||
# maps qnames to *encoded* prefix:local names
|
||||
qnames = {None: None}
|
||||
|
||||
# maps uri:s to prefixes
|
||||
namespaces = {}
|
||||
if default_namespace:
|
||||
namespaces[default_namespace] = ""
|
||||
|
||||
def encode(text):
|
||||
return text.encode(encoding)
|
||||
|
||||
def add_qname(qname):
|
||||
# calculate serialized qname representation
|
||||
try:
|
||||
if qname[:1] == "{":
|
||||
uri, tag = qname[1:].split("}", 1)
|
||||
prefix = namespaces.get(uri)
|
||||
if prefix is None:
|
||||
prefix = _namespace_map.get(uri)
|
||||
if prefix is None:
|
||||
prefix = "ns%d" % len(namespaces)
|
||||
if prefix != "xml":
|
||||
namespaces[uri] = prefix
|
||||
if prefix:
|
||||
qnames[qname] = encode("%s:%s" % (prefix, tag))
|
||||
else:
|
||||
qnames[qname] = encode(tag) # default element
|
||||
else:
|
||||
if default_namespace:
|
||||
# FIXME: can this be handled in XML 1.0?
|
||||
raise ValueError(
|
||||
"cannot use non-qualified names with "
|
||||
"default_namespace option"
|
||||
)
|
||||
qnames[qname] = encode(qname)
|
||||
except TypeError:
|
||||
_raise_serialization_error(qname)
|
||||
|
||||
# populate qname and namespaces table
|
||||
try:
|
||||
iterate = elem.iter
|
||||
except AttributeError:
|
||||
iterate = elem.getiterator # cET compatibility
|
||||
for elem in iterate():
|
||||
tag = elem.tag
|
||||
if isinstance(tag, QName) and tag.text not in qnames:
|
||||
add_qname(tag.text)
|
||||
elif isinstance(tag, basestring):
|
||||
if tag not in qnames:
|
||||
add_qname(tag)
|
||||
elif tag is not None and tag is not Comment and tag is not PI:
|
||||
_raise_serialization_error(tag)
|
||||
for key, value in elem.items():
|
||||
if isinstance(key, QName):
|
||||
key = key.text
|
||||
if key not in qnames:
|
||||
add_qname(key)
|
||||
if isinstance(value, QName) and value.text not in qnames:
|
||||
add_qname(value.text)
|
||||
text = elem.text
|
||||
if isinstance(text, QName) and text.text not in qnames:
|
||||
add_qname(text.text)
|
||||
return qnames, namespaces
|
||||
|
||||
def to_html_string(element, encoding=None):
|
||||
class dummy:
|
||||
pass
|
||||
data = []
|
||||
file = dummy()
|
||||
file.write = data.append
|
||||
write_html(ElementTree(element).getroot(),file,encoding)
|
||||
return "".join(data)
|
||||
371
src/calibre/ebooks/markdown/inlinepatterns.py
Normal file
371
src/calibre/ebooks/markdown/inlinepatterns.py
Normal file
@ -0,0 +1,371 @@
|
||||
"""
|
||||
INLINE PATTERNS
|
||||
=============================================================================
|
||||
|
||||
Inline patterns such as *emphasis* are handled by means of auxiliary
|
||||
objects, one per pattern. Pattern objects must be instances of classes
|
||||
that extend markdown.Pattern. Each pattern object uses a single regular
|
||||
expression and needs support the following methods:
|
||||
|
||||
pattern.getCompiledRegExp() # returns a regular expression
|
||||
|
||||
pattern.handleMatch(m) # takes a match object and returns
|
||||
# an ElementTree element or just plain text
|
||||
|
||||
All of python markdown's built-in patterns subclass from Pattern,
|
||||
but you can add additional patterns that don't.
|
||||
|
||||
Also note that all the regular expressions used by inline must
|
||||
capture the whole block. For this reason, they all start with
|
||||
'^(.*)' and end with '(.*)!'. In case with built-in expression
|
||||
Pattern takes care of adding the "^(.*)" and "(.*)!".
|
||||
|
||||
Finally, the order in which regular expressions are applied is very
|
||||
important - e.g. if we first replace http://.../ links with <a> tags
|
||||
and _then_ try to replace inline html, we would end up with a mess.
|
||||
So, we apply the expressions in the following order:
|
||||
|
||||
* escape and backticks have to go before everything else, so
|
||||
that we can preempt any markdown patterns by escaping them.
|
||||
|
||||
* then we handle auto-links (must be done before inline html)
|
||||
|
||||
* then we handle inline HTML. At this point we will simply
|
||||
replace all inline HTML strings with a placeholder and add
|
||||
the actual HTML to a hash.
|
||||
|
||||
* then inline images (must be done before links)
|
||||
|
||||
* then bracketed links, first regular then reference-style
|
||||
|
||||
* finally we apply strong and emphasis
|
||||
"""
|
||||
|
||||
import markdown
|
||||
import re
|
||||
from urlparse import urlparse, urlunparse
|
||||
import sys
|
||||
if sys.version >= "3.0":
|
||||
from html import entities as htmlentitydefs
|
||||
else:
|
||||
import htmlentitydefs
|
||||
|
||||
"""
|
||||
The actual regular expressions for patterns
|
||||
-----------------------------------------------------------------------------
|
||||
"""
|
||||
|
||||
NOBRACKET = r'[^\]\[]*'
|
||||
BRK = ( r'\[('
|
||||
+ (NOBRACKET + r'(\[')*6
|
||||
+ (NOBRACKET+ r'\])*')*6
|
||||
+ NOBRACKET + r')\]' )
|
||||
NOIMG = r'(?<!\!)'
|
||||
|
||||
BACKTICK_RE = r'(?<!\\)(`+)(.+?)(?<!`)\2(?!`)' # `e=f()` or ``e=f("`")``
|
||||
ESCAPE_RE = r'\\(.)' # \<
|
||||
EMPHASIS_RE = r'(\*)([^\*]*)\2' # *emphasis*
|
||||
STRONG_RE = r'(\*{2}|_{2})(.*?)\2' # **strong**
|
||||
STRONG_EM_RE = r'(\*{3}|_{3})(.*?)\2' # ***strong***
|
||||
|
||||
if markdown.SMART_EMPHASIS:
|
||||
EMPHASIS_2_RE = r'(?<!\S)(_)(\S.*?)\2' # _emphasis_
|
||||
else:
|
||||
EMPHASIS_2_RE = r'(_)(.*?)\2' # _emphasis_
|
||||
|
||||
LINK_RE = NOIMG + BRK + \
|
||||
r'''\(\s*(<.*?>|((?:(?:\(.*?\))|[^\(\)]))*?)\s*((['"])(.*)\12)?\)'''
|
||||
# [text](url) or [text](<url>)
|
||||
|
||||
IMAGE_LINK_RE = r'\!' + BRK + r'\s*\((<.*?>|([^\)]*))\)'
|
||||
#  or 
|
||||
REFERENCE_RE = NOIMG + BRK+ r'\s*\[([^\]]*)\]' # [Google][3]
|
||||
IMAGE_REFERENCE_RE = r'\!' + BRK + '\s*\[([^\]]*)\]' # ![alt text][2]
|
||||
NOT_STRONG_RE = r'( \* )' # stand-alone * or _
|
||||
AUTOLINK_RE = r'<((?:f|ht)tps?://[^>]*)>' # <http://www.123.com>
|
||||
AUTOMAIL_RE = r'<([^> \!]*@[^> ]*)>' # <me@example.com>
|
||||
|
||||
HTML_RE = r'(\<([a-zA-Z/][^\>]*?|\!--.*?--)\>)' # <...>
|
||||
ENTITY_RE = r'(&[\#a-zA-Z0-9]*;)' # &
|
||||
LINE_BREAK_RE = r' \n' # two spaces at end of line
|
||||
LINE_BREAK_2_RE = r' $' # two spaces at end of text
|
||||
|
||||
|
||||
def dequote(string):
|
||||
"""Remove quotes from around a string."""
|
||||
if ( ( string.startswith('"') and string.endswith('"'))
|
||||
or (string.startswith("'") and string.endswith("'")) ):
|
||||
return string[1:-1]
|
||||
else:
|
||||
return string
|
||||
|
||||
ATTR_RE = re.compile("\{@([^\}]*)=([^\}]*)}") # {@id=123}
|
||||
|
||||
def handleAttributes(text, parent):
|
||||
"""Set values of an element based on attribute definitions ({@id=123})."""
|
||||
def attributeCallback(match):
|
||||
parent.set(match.group(1), match.group(2).replace('\n', ' '))
|
||||
return ATTR_RE.sub(attributeCallback, text)
|
||||
|
||||
|
||||
"""
|
||||
The pattern classes
|
||||
-----------------------------------------------------------------------------
|
||||
"""
|
||||
|
||||
class Pattern:
|
||||
"""Base class that inline patterns subclass. """
|
||||
|
||||
def __init__ (self, pattern, markdown_instance=None):
|
||||
"""
|
||||
Create an instant of an inline pattern.
|
||||
|
||||
Keyword arguments:
|
||||
|
||||
* pattern: A regular expression that matches a pattern
|
||||
|
||||
"""
|
||||
self.pattern = pattern
|
||||
self.compiled_re = re.compile("^(.*?)%s(.*?)$" % pattern, re.DOTALL)
|
||||
|
||||
# Api for Markdown to pass safe_mode into instance
|
||||
self.safe_mode = False
|
||||
if markdown_instance:
|
||||
self.markdown = markdown_instance
|
||||
|
||||
def getCompiledRegExp (self):
|
||||
""" Return a compiled regular expression. """
|
||||
return self.compiled_re
|
||||
|
||||
def handleMatch(self, m):
|
||||
"""Return a ElementTree element from the given match.
|
||||
|
||||
Subclasses should override this method.
|
||||
|
||||
Keyword arguments:
|
||||
|
||||
* m: A re match object containing a match of the pattern.
|
||||
|
||||
"""
|
||||
pass
|
||||
|
||||
def type(self):
|
||||
""" Return class name, to define pattern type """
|
||||
return self.__class__.__name__
|
||||
|
||||
BasePattern = Pattern # for backward compatibility
|
||||
|
||||
class SimpleTextPattern (Pattern):
|
||||
""" Return a simple text of group(2) of a Pattern. """
|
||||
def handleMatch(self, m):
|
||||
text = m.group(2)
|
||||
if text == markdown.INLINE_PLACEHOLDER_PREFIX:
|
||||
return None
|
||||
return text
|
||||
|
||||
class SimpleTagPattern (Pattern):
|
||||
"""
|
||||
Return element of type `tag` with a text attribute of group(3)
|
||||
of a Pattern.
|
||||
|
||||
"""
|
||||
def __init__ (self, pattern, tag):
|
||||
Pattern.__init__(self, pattern)
|
||||
self.tag = tag
|
||||
|
||||
def handleMatch(self, m):
|
||||
el = markdown.etree.Element(self.tag)
|
||||
el.text = m.group(3)
|
||||
return el
|
||||
|
||||
|
||||
class SubstituteTagPattern (SimpleTagPattern):
|
||||
""" Return a eLement of type `tag` with no children. """
|
||||
def handleMatch (self, m):
|
||||
return markdown.etree.Element(self.tag)
|
||||
|
||||
|
||||
class BacktickPattern (Pattern):
|
||||
""" Return a `<code>` element containing the matching text. """
|
||||
def __init__ (self, pattern):
|
||||
Pattern.__init__(self, pattern)
|
||||
self.tag = "code"
|
||||
|
||||
def handleMatch(self, m):
|
||||
el = markdown.etree.Element(self.tag)
|
||||
el.text = markdown.AtomicString(m.group(3).strip())
|
||||
return el
|
||||
|
||||
|
||||
class DoubleTagPattern (SimpleTagPattern):
|
||||
"""Return a ElementTree element nested in tag2 nested in tag1.
|
||||
|
||||
Useful for strong emphasis etc.
|
||||
|
||||
"""
|
||||
def handleMatch(self, m):
|
||||
tag1, tag2 = self.tag.split(",")
|
||||
el1 = markdown.etree.Element(tag1)
|
||||
el2 = markdown.etree.SubElement(el1, tag2)
|
||||
el2.text = m.group(3)
|
||||
return el1
|
||||
|
||||
|
||||
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
|
||||
|
||||
|
||||
class LinkPattern (Pattern):
|
||||
""" Return a link element from the given match. """
|
||||
def handleMatch(self, m):
|
||||
el = markdown.etree.Element("a")
|
||||
el.text = m.group(2)
|
||||
title = m.group(11)
|
||||
href = m.group(9)
|
||||
|
||||
if href:
|
||||
if href[0] == "<":
|
||||
href = href[1:-1]
|
||||
el.set("href", self.sanitize_url(href.strip()))
|
||||
else:
|
||||
el.set("href", "")
|
||||
|
||||
if title:
|
||||
title = dequote(title) #.replace('"', """)
|
||||
el.set("title", title)
|
||||
return el
|
||||
|
||||
def sanitize_url(self, url):
|
||||
"""
|
||||
Sanitize a url against xss attacks in "safe_mode".
|
||||
|
||||
Rather than specifically blacklisting `javascript:alert("XSS")` and all
|
||||
its aliases (see <http://ha.ckers.org/xss.html>), we whitelist known
|
||||
safe url formats. Most urls contain a network location, however some
|
||||
are known not to (i.e.: mailto links). Script urls do not contain a
|
||||
location. Additionally, for `javascript:...`, the scheme would be
|
||||
"javascript" but some aliases will appear to `urlparse()` to have no
|
||||
scheme. On top of that relative links (i.e.: "foo/bar.html") have no
|
||||
scheme. Therefore we must check "path", "parameters", "query" and
|
||||
"fragment" for any literal colons. We don't check "scheme" for colons
|
||||
because it *should* never have any and "netloc" must allow the form:
|
||||
`username:password@host:port`.
|
||||
|
||||
"""
|
||||
locless_schemes = ['', 'mailto', 'news']
|
||||
scheme, netloc, path, params, query, fragment = url = urlparse(url)
|
||||
safe_url = False
|
||||
if netloc != '' or scheme in locless_schemes:
|
||||
safe_url = True
|
||||
|
||||
for part in url[2:]:
|
||||
if ":" in part:
|
||||
safe_url = False
|
||||
|
||||
if self.markdown.safeMode and not safe_url:
|
||||
return ''
|
||||
else:
|
||||
return urlunparse(url)
|
||||
|
||||
class ImagePattern(LinkPattern):
|
||||
""" Return a img element from the given match. """
|
||||
def handleMatch(self, m):
|
||||
el = markdown.etree.Element("img")
|
||||
src_parts = m.group(9).split()
|
||||
if src_parts:
|
||||
src = src_parts[0]
|
||||
if src[0] == "<" and src[-1] == ">":
|
||||
src = src[1:-1]
|
||||
el.set('src', self.sanitize_url(src))
|
||||
else:
|
||||
el.set('src', "")
|
||||
if len(src_parts) > 1:
|
||||
el.set('title', dequote(" ".join(src_parts[1:])))
|
||||
|
||||
if markdown.ENABLE_ATTRIBUTES:
|
||||
truealt = handleAttributes(m.group(2), el)
|
||||
else:
|
||||
truealt = m.group(2)
|
||||
|
||||
el.set('alt', truealt)
|
||||
return el
|
||||
|
||||
class ReferencePattern(LinkPattern):
|
||||
""" Match to a stored reference and return link element. """
|
||||
def handleMatch(self, m):
|
||||
if m.group(9):
|
||||
id = m.group(9).lower()
|
||||
else:
|
||||
# if we got something like "[Google][]"
|
||||
# we'll use "google" as the id
|
||||
id = m.group(2).lower()
|
||||
|
||||
if not id in self.markdown.references: # ignore undefined refs
|
||||
return None
|
||||
href, title = self.markdown.references[id]
|
||||
|
||||
text = m.group(2)
|
||||
return self.makeTag(href, title, text)
|
||||
|
||||
def makeTag(self, href, title, text):
|
||||
el = markdown.etree.Element('a')
|
||||
|
||||
el.set('href', self.sanitize_url(href))
|
||||
if title:
|
||||
el.set('title', title)
|
||||
|
||||
el.text = text
|
||||
return el
|
||||
|
||||
|
||||
class ImageReferencePattern (ReferencePattern):
|
||||
""" Match to a stored reference and return img element. """
|
||||
def makeTag(self, href, title, text):
|
||||
el = markdown.etree.Element("img")
|
||||
el.set("src", self.sanitize_url(href))
|
||||
if title:
|
||||
el.set("title", title)
|
||||
el.set("alt", text)
|
||||
return el
|
||||
|
||||
|
||||
class AutolinkPattern (Pattern):
|
||||
""" Return a link Element given an autolink (`<http://example/com>`). """
|
||||
def handleMatch(self, m):
|
||||
el = markdown.etree.Element("a")
|
||||
el.set('href', m.group(2))
|
||||
el.text = markdown.AtomicString(m.group(2))
|
||||
return el
|
||||
|
||||
class AutomailPattern (Pattern):
|
||||
"""
|
||||
Return a mailto link Element given an automail link (`<foo@example.com>`).
|
||||
"""
|
||||
def handleMatch(self, m):
|
||||
el = markdown.etree.Element('a')
|
||||
email = m.group(2)
|
||||
if email.startswith("mailto:"):
|
||||
email = email[len("mailto:"):]
|
||||
|
||||
def codepoint2name(code):
|
||||
"""Return entity definition by code, or the code if not defined."""
|
||||
entity = htmlentitydefs.codepoint2name.get(code)
|
||||
if entity:
|
||||
return "%s%s;" % (markdown.AMP_SUBSTITUTE, entity)
|
||||
else:
|
||||
return "%s#%d;" % (markdown.AMP_SUBSTITUTE, code)
|
||||
|
||||
letters = [codepoint2name(ord(letter)) for letter in email]
|
||||
el.text = markdown.AtomicString(''.join(letters))
|
||||
|
||||
mailto = "mailto:" + email
|
||||
mailto = "".join([markdown.AMP_SUBSTITUTE + '#%d;' %
|
||||
ord(letter) for letter in mailto])
|
||||
el.set('href', mailto)
|
||||
return el
|
||||
|
||||
File diff suppressed because it is too large
Load Diff
@ -1,257 +0,0 @@
|
||||
"""
|
||||
========================= FOOTNOTES =================================
|
||||
|
||||
This section adds footnote handling to markdown. It can be used as
|
||||
an example for extending python-markdown with relatively complex
|
||||
functionality. While in this case the extension is included inside
|
||||
the module itself, it could just as easily be added from outside the
|
||||
module. Not that all markdown classes above are ignorant about
|
||||
footnotes. All footnote functionality is provided separately and
|
||||
then added to the markdown instance at the run time.
|
||||
|
||||
Footnote functionality is attached by calling extendMarkdown()
|
||||
method of FootnoteExtension. The method also registers the
|
||||
extension to allow it's state to be reset by a call to reset()
|
||||
method.
|
||||
"""
|
||||
|
||||
FN_BACKLINK_TEXT = "zz1337820767766393qq"
|
||||
|
||||
|
||||
import re, markdown, random
|
||||
|
||||
class FootnoteExtension (markdown.Extension):
|
||||
|
||||
DEF_RE = re.compile(r'(\ ?\ ?\ ?)\[\^([^\]]*)\]:\s*(.*)')
|
||||
SHORT_USE_RE = re.compile(r'\[\^([^\]]*)\]', re.M) # [^a]
|
||||
|
||||
def __init__ (self, configs) :
|
||||
|
||||
self.config = {'PLACE_MARKER' :
|
||||
["///Footnotes Go Here///",
|
||||
"The text string that marks where the footnotes go"]}
|
||||
|
||||
for key, value in configs :
|
||||
self.config[key][0] = value
|
||||
|
||||
self.reset()
|
||||
|
||||
def extendMarkdown(self, md, md_globals) :
|
||||
|
||||
self.md = md
|
||||
|
||||
# Stateless extensions do not need to be registered
|
||||
md.registerExtension(self)
|
||||
|
||||
# Insert a preprocessor before ReferencePreprocessor
|
||||
index = md.preprocessors.index(md_globals['REFERENCE_PREPROCESSOR'])
|
||||
preprocessor = FootnotePreprocessor(self)
|
||||
preprocessor.md = md
|
||||
md.preprocessors.insert(index, preprocessor)
|
||||
|
||||
# Insert an inline pattern before ImageReferencePattern
|
||||
FOOTNOTE_RE = r'\[\^([^\]]*)\]' # blah blah [^1] blah
|
||||
index = md.inlinePatterns.index(md_globals['IMAGE_REFERENCE_PATTERN'])
|
||||
md.inlinePatterns.insert(index, FootnotePattern(FOOTNOTE_RE, self))
|
||||
|
||||
# Insert a post-processor that would actually add the footnote div
|
||||
postprocessor = FootnotePostprocessor(self)
|
||||
postprocessor.extension = self
|
||||
|
||||
md.postprocessors.append(postprocessor)
|
||||
|
||||
textPostprocessor = FootnoteTextPostprocessor(self)
|
||||
|
||||
md.textPostprocessors.append(textPostprocessor)
|
||||
|
||||
|
||||
def reset(self) :
|
||||
# May be called by Markdown is state reset is desired
|
||||
|
||||
self.footnote_suffix = "-" + str(int(random.random()*1000000000))
|
||||
self.used_footnotes={}
|
||||
self.footnotes = {}
|
||||
|
||||
def findFootnotesPlaceholder(self, doc) :
|
||||
def findFootnotePlaceholderFn(node=None, indent=0):
|
||||
if node.type == 'text':
|
||||
if node.value.find(self.getConfig("PLACE_MARKER")) > -1 :
|
||||
return True
|
||||
|
||||
fn_div_list = doc.find(findFootnotePlaceholderFn)
|
||||
if fn_div_list :
|
||||
return fn_div_list[0]
|
||||
|
||||
|
||||
def setFootnote(self, id, text) :
|
||||
self.footnotes[id] = text
|
||||
|
||||
def makeFootnoteId(self, num) :
|
||||
return 'fn%d%s' % (num, self.footnote_suffix)
|
||||
|
||||
def makeFootnoteRefId(self, num) :
|
||||
return 'fnr%d%s' % (num, self.footnote_suffix)
|
||||
|
||||
def makeFootnotesDiv (self, doc) :
|
||||
"""Creates the div with class='footnote' and populates it with
|
||||
the text of the footnotes.
|
||||
|
||||
@returns: the footnote div as a dom element """
|
||||
|
||||
if not self.footnotes.keys() :
|
||||
return None
|
||||
|
||||
div = doc.createElement("div")
|
||||
div.setAttribute('class', 'footnote')
|
||||
hr = doc.createElement("hr")
|
||||
div.appendChild(hr)
|
||||
ol = doc.createElement("ol")
|
||||
div.appendChild(ol)
|
||||
|
||||
footnotes = [(self.used_footnotes[id], id)
|
||||
for id in self.footnotes.keys()]
|
||||
footnotes.sort()
|
||||
|
||||
for i, id in footnotes :
|
||||
li = doc.createElement('li')
|
||||
li.setAttribute('id', self.makeFootnoteId(i))
|
||||
|
||||
self.md._processSection(li, self.footnotes[id].split("\n"), looseList=1)
|
||||
|
||||
#li.appendChild(doc.createTextNode(self.footnotes[id]))
|
||||
|
||||
backlink = doc.createElement('a')
|
||||
backlink.setAttribute('href', '#' + self.makeFootnoteRefId(i))
|
||||
backlink.setAttribute('class', 'footnoteBackLink')
|
||||
backlink.setAttribute('title',
|
||||
'Jump back to footnote %d in the text' % 1)
|
||||
backlink.appendChild(doc.createTextNode(FN_BACKLINK_TEXT))
|
||||
|
||||
if li.childNodes :
|
||||
node = li.childNodes[-1]
|
||||
if node.type == "text" :
|
||||
li.appendChild(backlink)
|
||||
elif node.nodeName == "p":
|
||||
node.appendChild(backlink)
|
||||
else:
|
||||
p = doc.createElement('p')
|
||||
p.appendChild(backlink)
|
||||
li.appendChild(p)
|
||||
|
||||
ol.appendChild(li)
|
||||
|
||||
return div
|
||||
|
||||
|
||||
class FootnotePreprocessor :
|
||||
|
||||
def __init__ (self, footnotes) :
|
||||
self.footnotes = footnotes
|
||||
|
||||
def run(self, lines) :
|
||||
|
||||
self.blockGuru = markdown.BlockGuru()
|
||||
lines = self._handleFootnoteDefinitions (lines)
|
||||
|
||||
# Make a hash of all footnote marks in the text so that we
|
||||
# know in what order they are supposed to appear. (This
|
||||
# function call doesn't really substitute anything - it's just
|
||||
# a way to get a callback for each occurence.
|
||||
|
||||
text = "\n".join(lines)
|
||||
self.footnotes.SHORT_USE_RE.sub(self.recordFootnoteUse, text)
|
||||
|
||||
return text.split("\n")
|
||||
|
||||
|
||||
def recordFootnoteUse(self, match) :
|
||||
|
||||
id = match.group(1)
|
||||
id = id.strip()
|
||||
nextNum = len(self.footnotes.used_footnotes.keys()) + 1
|
||||
self.footnotes.used_footnotes[id] = nextNum
|
||||
|
||||
|
||||
def _handleFootnoteDefinitions(self, lines) :
|
||||
"""Recursively finds all footnote definitions in the lines.
|
||||
|
||||
@param lines: a list of lines of text
|
||||
@returns: a string representing the text with footnote
|
||||
definitions removed """
|
||||
|
||||
i, id, footnote = self._findFootnoteDefinition(lines)
|
||||
|
||||
if id :
|
||||
|
||||
plain = lines[:i]
|
||||
|
||||
detabbed, theRest = self.blockGuru.detectTabbed(lines[i+1:])
|
||||
|
||||
self.footnotes.setFootnote(id,
|
||||
footnote + "\n"
|
||||
+ "\n".join(detabbed))
|
||||
|
||||
more_plain = self._handleFootnoteDefinitions(theRest)
|
||||
return plain + [""] + more_plain
|
||||
|
||||
else :
|
||||
return lines
|
||||
|
||||
def _findFootnoteDefinition(self, lines) :
|
||||
"""Finds the first line of a footnote definition.
|
||||
|
||||
@param lines: a list of lines of text
|
||||
@returns: the index of the line containing a footnote definition """
|
||||
|
||||
counter = 0
|
||||
for line in lines :
|
||||
m = self.footnotes.DEF_RE.match(line)
|
||||
if m :
|
||||
return counter, m.group(2), m.group(3)
|
||||
counter += 1
|
||||
return counter, None, None
|
||||
|
||||
|
||||
class FootnotePattern (markdown.Pattern) :
|
||||
|
||||
def __init__ (self, pattern, footnotes) :
|
||||
|
||||
markdown.Pattern.__init__(self, pattern)
|
||||
self.footnotes = footnotes
|
||||
|
||||
def handleMatch(self, m, doc) :
|
||||
sup = doc.createElement('sup')
|
||||
a = doc.createElement('a')
|
||||
sup.appendChild(a)
|
||||
id = m.group(2)
|
||||
num = self.footnotes.used_footnotes[id]
|
||||
sup.setAttribute('id', self.footnotes.makeFootnoteRefId(num))
|
||||
a.setAttribute('href', '#' + self.footnotes.makeFootnoteId(num))
|
||||
a.appendChild(doc.createTextNode(str(num)))
|
||||
return sup
|
||||
|
||||
class FootnotePostprocessor (markdown.Postprocessor):
|
||||
|
||||
def __init__ (self, footnotes) :
|
||||
self.footnotes = footnotes
|
||||
|
||||
def run(self, doc) :
|
||||
footnotesDiv = self.footnotes.makeFootnotesDiv(doc)
|
||||
if footnotesDiv :
|
||||
fnPlaceholder = self.extension.findFootnotesPlaceholder(doc)
|
||||
if fnPlaceholder :
|
||||
fnPlaceholder.parent.replaceChild(fnPlaceholder, footnotesDiv)
|
||||
else :
|
||||
doc.documentElement.appendChild(footnotesDiv)
|
||||
|
||||
class FootnoteTextPostprocessor (markdown.Postprocessor):
|
||||
|
||||
def __init__ (self, footnotes) :
|
||||
self.footnotes = footnotes
|
||||
|
||||
def run(self, text) :
|
||||
return text.replace(FN_BACKLINK_TEXT, "↩")
|
||||
|
||||
def makeExtension(configs=None) :
|
||||
return FootnoteExtension(configs=configs)
|
||||
|
||||
@ -1,65 +0,0 @@
|
||||
#!/usr/bin/env python
|
||||
|
||||
"""
|
||||
Table extension for Python-Markdown
|
||||
"""
|
||||
|
||||
import markdown
|
||||
|
||||
|
||||
class TablePattern(markdown.Pattern) :
|
||||
def __init__ (self, md):
|
||||
markdown.Pattern.__init__(self, r'^\|([^\n]*)\|(\n|$)')
|
||||
self.md = md
|
||||
|
||||
def handleMatch(self, m, doc) :
|
||||
# a single line represents a row
|
||||
tr = doc.createElement('tr')
|
||||
tr.appendChild(doc.createTextNode('\n'))
|
||||
# chunks between pipes represent cells
|
||||
for t in m.group(2).split('|'):
|
||||
if len(t) >= 2 and t.startswith('*') and t.endswith('*'):
|
||||
# if a cell is bounded by asterisks, it is a <th>
|
||||
td = doc.createElement('th')
|
||||
t = t[1:-1]
|
||||
else:
|
||||
# otherwise it is a <td>
|
||||
td = doc.createElement('td')
|
||||
# apply inline patterns on chunks
|
||||
for n in self.md._handleInline(t):
|
||||
if(type(n) == unicode):
|
||||
td.appendChild(doc.createTextNode(n))
|
||||
else:
|
||||
td.appendChild(n)
|
||||
tr.appendChild(td)
|
||||
# very long lines are evil
|
||||
tr.appendChild(doc.createTextNode('\n'))
|
||||
return tr
|
||||
|
||||
|
||||
class TablePostprocessor:
|
||||
def run(self, doc):
|
||||
# markdown wrapped our <tr>s in a <p>, we fix that here
|
||||
def test_for_p(element):
|
||||
return element.type == 'element' and element.nodeName == 'p'
|
||||
# replace "p > tr" with "table > tr"
|
||||
for element in doc.find(test_for_p):
|
||||
for node in element.childNodes:
|
||||
if(node.type == 'text' and node.value.strip() == ''):
|
||||
# skip leading whitespace
|
||||
continue
|
||||
if (node.type == 'element' and node.nodeName == 'tr'):
|
||||
element.nodeName = 'table'
|
||||
break
|
||||
|
||||
|
||||
class TableExtension(markdown.Extension):
|
||||
def extendMarkdown(self, md, md_globals):
|
||||
md.inlinePatterns.insert(0, TablePattern(md))
|
||||
md.postprocessors.append(TablePostprocessor())
|
||||
|
||||
|
||||
def makeExtension(configs):
|
||||
return TableExtension(configs)
|
||||
|
||||
|
||||
@ -1,170 +0,0 @@
|
||||
## To access this file as plain text go to
|
||||
## http://freewisdom.org/projects/python-markdown/mdx_toc.raw_content
|
||||
|
||||
"""
|
||||
Chris Clark - clach04 -at- sf.net
|
||||
|
||||
My markdown extensions for adding:
|
||||
Table of Contents (aka toc)
|
||||
"""
|
||||
|
||||
import re
|
||||
import markdown
|
||||
|
||||
DEFAULT_TITLE = None
|
||||
|
||||
def extract_alphanumeric(in_str=None):
|
||||
"""take alpha-numeric (7bit ascii) and return as a string
|
||||
"""
|
||||
# I'm sure this is really inefficient and
|
||||
# could be done with a lambda/map()
|
||||
#x.strip(). title().replace(' ', "")
|
||||
out_str=[]
|
||||
for x in in_str:
|
||||
x = icu_title(x)
|
||||
if x.isalnum(): out_str.append(x)
|
||||
return ''.join(out_str)
|
||||
|
||||
class TitlePostprocessor (markdown.Postprocessor):
|
||||
|
||||
def __init__ (self, extension) :
|
||||
self.extension = extension
|
||||
|
||||
def run(self, doc) :
|
||||
titleElement = self.extension.createTitle(doc)
|
||||
if titleElement :
|
||||
doc.documentElement.insertChild(0, titleElement)
|
||||
|
||||
|
||||
class TocExtension (markdown.Extension):
|
||||
"""Markdown extension: generate a Table Of Contents (aka toc)
|
||||
toc is returned in a div tag with class='toc'
|
||||
toc is either:
|
||||
appended to end of document
|
||||
OR
|
||||
replaces first string occurence of "///Table of Contents Goes Here///"
|
||||
"""
|
||||
|
||||
def __init__ (self, configs={}) :
|
||||
#maybe add these as parameters to the class init?
|
||||
self.TOC_INCLUDE_MARKER = "///Table of Contents///"
|
||||
self.TOC_TITLE = "Table Of Contents"
|
||||
self.auto_toc_heading_type=2
|
||||
self.toc_heading_type=3
|
||||
self.configs = configs
|
||||
|
||||
def extendMarkdown(self, md, md_globals) :
|
||||
# Just insert in the end
|
||||
md.postprocessors.append(TocPostprocessor(self))
|
||||
# Stateless extensions do not need to be registered, so we don't
|
||||
# register.
|
||||
|
||||
def findTocPlaceholder(self, doc) :
|
||||
def findTocPlaceholderFn(node=None, indent=0):
|
||||
if node.type == 'text':
|
||||
if node.value.find(self.TOC_INCLUDE_MARKER) > -1 :
|
||||
return True
|
||||
|
||||
toc_div_list = doc.find(findTocPlaceholderFn)
|
||||
if toc_div_list :
|
||||
return toc_div_list[0]
|
||||
|
||||
|
||||
def createTocDiv(self, doc) :
|
||||
"""
|
||||
Creates Table Of Contents based on headers.
|
||||
|
||||
@returns: toc as a single as a dom element
|
||||
in a <div> tag with class='toc'
|
||||
"""
|
||||
|
||||
# Find headers
|
||||
headers_compiled_re = re.compile("h[123456]", re.IGNORECASE)
|
||||
def findHeadersFn(element=None):
|
||||
if element.type=='element':
|
||||
if headers_compiled_re.match(element.nodeName):
|
||||
return True
|
||||
|
||||
headers_doc_list = doc.find(findHeadersFn)
|
||||
|
||||
# Insert anchor tags into dom
|
||||
generated_anchor_id=0
|
||||
headers_list=[]
|
||||
min_header_size_found = 6
|
||||
for element in headers_doc_list:
|
||||
heading_title = element.childNodes[0].value
|
||||
if heading_title.strip() !="":
|
||||
heading_type = int(element.nodeName[-1:])
|
||||
if heading_type == self.auto_toc_heading_type:
|
||||
min_header_size_found=min(min_header_size_found,
|
||||
heading_type)
|
||||
|
||||
html_anchor_name= (extract_alphanumeric(heading_title)
|
||||
+'__MD_autoTOC_%d' % (generated_anchor_id))
|
||||
|
||||
# insert anchor tag inside header tags
|
||||
html_anchor = doc.createElement("a")
|
||||
html_anchor.setAttribute('name', html_anchor_name)
|
||||
element.appendChild(html_anchor)
|
||||
|
||||
headers_list.append( (heading_type, heading_title,
|
||||
html_anchor_name) )
|
||||
generated_anchor_id = generated_anchor_id + 1
|
||||
|
||||
# create dom for toc
|
||||
if headers_list != []:
|
||||
# Create list
|
||||
toc_doc_list = doc.createElement("ul")
|
||||
for (heading_type, heading_title, html_anchor_name) in headers_list:
|
||||
if heading_type == self.auto_toc_heading_type:
|
||||
toc_doc_entry = doc.createElement("li")
|
||||
toc_doc_link = doc.createElement("a")
|
||||
toc_doc_link.setAttribute('href', '#'+html_anchor_name)
|
||||
toc_doc_text = doc.createTextNode(heading_title)
|
||||
toc_doc_link.appendChild(toc_doc_text)
|
||||
toc_doc_entry.appendChild(toc_doc_link)
|
||||
toc_doc_list.appendChild(toc_doc_entry)
|
||||
|
||||
|
||||
# Put list into div
|
||||
div = doc.createElement("div")
|
||||
div.setAttribute('class', 'toc')
|
||||
if self.TOC_TITLE:
|
||||
toc_header = doc.createElement("h%d"%(self.toc_heading_type) )
|
||||
toc_header_text = doc.createTextNode(self.TOC_TITLE)
|
||||
toc_header.appendChild(toc_header_text)
|
||||
div.appendChild(toc_header)
|
||||
div.appendChild(toc_doc_list)
|
||||
#hr = doc.createElement("hr")
|
||||
#div.appendChild(hr)
|
||||
|
||||
return div
|
||||
|
||||
|
||||
class TocPostprocessor (markdown.Postprocessor):
|
||||
|
||||
def __init__ (self, toc) :
|
||||
self.toc = toc
|
||||
|
||||
def run(self, doc):
|
||||
tocPlaceholder = self.toc.findTocPlaceholder(doc)
|
||||
|
||||
if self.toc.configs.get("disable_toc", False):
|
||||
if tocPlaceholder:
|
||||
tocPlaceholder.parent.replaceChild(tocPlaceholder, "")
|
||||
else:
|
||||
|
||||
tocDiv = self.toc.createTocDiv(doc)
|
||||
|
||||
if tocDiv:
|
||||
if tocPlaceholder :
|
||||
# Replace "magic" pattern with toc
|
||||
tocPlaceholder.parent.replaceChild(tocPlaceholder, tocDiv)
|
||||
else :
|
||||
# Dump at the end of the DOM
|
||||
# Probably want to use CSS to position div
|
||||
doc.documentElement.appendChild(tocDiv)
|
||||
|
||||
|
||||
def makeExtension(configs={}):
|
||||
return TocExtension(configs=configs)
|
||||
162
src/calibre/ebooks/markdown/odict.py
Normal file
162
src/calibre/ebooks/markdown/odict.py
Normal file
@ -0,0 +1,162 @@
|
||||
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.
|
||||
|
||||
"""
|
||||
def __new__(cls, *args, **kwargs):
|
||||
instance = super(OrderedDict, cls).__new__(cls, *args, **kwargs)
|
||||
instance.keyOrder = []
|
||||
return instance
|
||||
|
||||
def __init__(self, data=None):
|
||||
if data is None:
|
||||
data = {}
|
||||
super(OrderedDict, self).__init__(data)
|
||||
if isinstance(data, dict):
|
||||
self.keyOrder = data.keys()
|
||||
else:
|
||||
self.keyOrder = []
|
||||
for key, value in data:
|
||||
if key not in self.keyOrder:
|
||||
self.keyOrder.append(key)
|
||||
|
||||
def __deepcopy__(self, memo):
|
||||
from copy import deepcopy
|
||||
return self.__class__([(key, deepcopy(value, memo))
|
||||
for key, value in self.iteritems()])
|
||||
|
||||
def __setitem__(self, key, value):
|
||||
super(OrderedDict, self).__setitem__(key, value)
|
||||
if key not in self.keyOrder:
|
||||
self.keyOrder.append(key)
|
||||
|
||||
def __delitem__(self, key):
|
||||
super(OrderedDict, self).__delitem__(key)
|
||||
self.keyOrder.remove(key)
|
||||
|
||||
def __iter__(self):
|
||||
for k in self.keyOrder:
|
||||
yield k
|
||||
|
||||
def pop(self, k, *args):
|
||||
result = super(OrderedDict, self).pop(k, *args)
|
||||
try:
|
||||
self.keyOrder.remove(k)
|
||||
except ValueError:
|
||||
# Key wasn't in the dictionary in the first place. No problem.
|
||||
pass
|
||||
return result
|
||||
|
||||
def popitem(self):
|
||||
result = super(OrderedDict, self).popitem()
|
||||
self.keyOrder.remove(result[0])
|
||||
return result
|
||||
|
||||
def items(self):
|
||||
return zip(self.keyOrder, self.values())
|
||||
|
||||
def iteritems(self):
|
||||
for key in self.keyOrder:
|
||||
yield key, super(OrderedDict, self).__getitem__(key)
|
||||
|
||||
def keys(self):
|
||||
return self.keyOrder[:]
|
||||
|
||||
def iterkeys(self):
|
||||
return iter(self.keyOrder)
|
||||
|
||||
def values(self):
|
||||
return [super(OrderedDict, self).__getitem__(k) for k in self.keyOrder]
|
||||
|
||||
def itervalues(self):
|
||||
for key in self.keyOrder:
|
||||
yield super(OrderedDict, self).__getitem__(key)
|
||||
|
||||
def update(self, dict_):
|
||||
for k, v in dict_.items():
|
||||
self.__setitem__(k, v)
|
||||
|
||||
def setdefault(self, key, default):
|
||||
if key not in self.keyOrder:
|
||||
self.keyOrder.append(key)
|
||||
return super(OrderedDict, self).setdefault(key, default)
|
||||
|
||||
def value_for_index(self, index):
|
||||
"""Return the value of the item at the given zero-based index."""
|
||||
return self[self.keyOrder[index]]
|
||||
|
||||
def insert(self, index, key, value):
|
||||
"""Insert the key, value pair before the item with the given index."""
|
||||
if key in self.keyOrder:
|
||||
n = self.keyOrder.index(key)
|
||||
del self.keyOrder[n]
|
||||
if n < index:
|
||||
index -= 1
|
||||
self.keyOrder.insert(index, key)
|
||||
super(OrderedDict, self).__setitem__(key, value)
|
||||
|
||||
def copy(self):
|
||||
"""Return a copy of this object."""
|
||||
# This way of initializing the copy means it works for subclasses, too.
|
||||
obj = self.__class__(self)
|
||||
obj.keyOrder = self.keyOrder[:]
|
||||
return obj
|
||||
|
||||
def __repr__(self):
|
||||
"""
|
||||
Replace the normal dict.__repr__ with a version that returns the keys
|
||||
in their sorted order.
|
||||
"""
|
||||
return '{%s}' % ', '.join(['%r: %r' % (k, v) for k, v in self.items()])
|
||||
|
||||
def clear(self):
|
||||
super(OrderedDict, self).clear()
|
||||
self.keyOrder = []
|
||||
|
||||
def index(self, key):
|
||||
""" Return the index of a given key. """
|
||||
return self.keyOrder.index(key)
|
||||
|
||||
def index_for_location(self, location):
|
||||
""" Return index or None for a given location. """
|
||||
if location == '_begin':
|
||||
i = 0
|
||||
elif location == '_end':
|
||||
i = None
|
||||
elif location.startswith('<') or location.startswith('>'):
|
||||
i = self.index(location[1:])
|
||||
if location.startswith('>'):
|
||||
if i >= len(self):
|
||||
# last item
|
||||
i = None
|
||||
else:
|
||||
i += 1
|
||||
else:
|
||||
raise ValueError('Not a valid location: "%s". Location key '
|
||||
'must start with a ">" or "<".' % location)
|
||||
return i
|
||||
|
||||
def add(self, key, value, location):
|
||||
""" Insert by key location. """
|
||||
i = self.index_for_location(location)
|
||||
if i is not None:
|
||||
self.insert(i, key, value)
|
||||
else:
|
||||
self.__setitem__(key, value)
|
||||
|
||||
def link(self, key, location):
|
||||
""" Change location of an existing item. """
|
||||
n = self.keyOrder.index(key)
|
||||
del self.keyOrder[n]
|
||||
i = self.index_for_location(location)
|
||||
try:
|
||||
if i is not None:
|
||||
self.keyOrder.insert(i, key)
|
||||
else:
|
||||
self.keyOrder.append(key)
|
||||
except Error:
|
||||
# restore to prevent data loss and reraise
|
||||
self.keyOrder.insert(n, key)
|
||||
raise Error
|
||||
77
src/calibre/ebooks/markdown/postprocessors.py
Normal file
77
src/calibre/ebooks/markdown/postprocessors.py
Normal file
@ -0,0 +1,77 @@
|
||||
"""
|
||||
POST-PROCESSORS
|
||||
=============================================================================
|
||||
|
||||
Markdown also allows post-processors, which are similar to preprocessors in
|
||||
that they need to implement a "run" method. However, they are run after core
|
||||
processing.
|
||||
|
||||
"""
|
||||
|
||||
|
||||
import markdown
|
||||
|
||||
class Processor:
|
||||
def __init__(self, markdown_instance=None):
|
||||
if markdown_instance:
|
||||
self.markdown = markdown_instance
|
||||
|
||||
class Postprocessor(Processor):
|
||||
"""
|
||||
Postprocessors are run after the ElementTree it converted back into text.
|
||||
|
||||
Each Postprocessor implements a "run" method that takes a pointer to a
|
||||
text string, modifies it as necessary and returns a text string.
|
||||
|
||||
Postprocessors must extend markdown.Postprocessor.
|
||||
|
||||
"""
|
||||
|
||||
def run(self, text):
|
||||
"""
|
||||
Subclasses of Postprocessor should implement a `run` method, which
|
||||
takes the html document as a single text string and returns a
|
||||
(possibly modified) string.
|
||||
|
||||
"""
|
||||
pass
|
||||
|
||||
|
||||
class RawHtmlPostprocessor(Postprocessor):
|
||||
""" Restore raw html to the document. """
|
||||
|
||||
def run(self, text):
|
||||
""" Iterate over html stash and restore "safe" html. """
|
||||
for i in range(self.markdown.htmlStash.html_counter):
|
||||
html, safe = self.markdown.htmlStash.rawHtmlBlocks[i]
|
||||
if self.markdown.safeMode and not safe:
|
||||
if str(self.markdown.safeMode).lower() == 'escape':
|
||||
html = self.escape(html)
|
||||
elif str(self.markdown.safeMode).lower() == 'remove':
|
||||
html = ''
|
||||
else:
|
||||
html = markdown.HTML_REMOVED_TEXT
|
||||
if safe or not self.markdown.safeMode:
|
||||
text = text.replace("<p>%s</p>" %
|
||||
(markdown.preprocessors.HTML_PLACEHOLDER % i),
|
||||
html + "\n")
|
||||
text = text.replace(markdown.preprocessors.HTML_PLACEHOLDER % i,
|
||||
html)
|
||||
return text
|
||||
|
||||
def escape(self, html):
|
||||
""" Basic html escaping """
|
||||
html = html.replace('&', '&')
|
||||
html = html.replace('<', '<')
|
||||
html = html.replace('>', '>')
|
||||
return html.replace('"', '"')
|
||||
|
||||
|
||||
class AndSubstitutePostprocessor(Postprocessor):
|
||||
""" Restore valid entities """
|
||||
def __init__(self):
|
||||
pass
|
||||
|
||||
def run(self, text):
|
||||
text = text.replace(markdown.AMP_SUBSTITUTE, "&")
|
||||
return text
|
||||
214
src/calibre/ebooks/markdown/preprocessors.py
Normal file
214
src/calibre/ebooks/markdown/preprocessors.py
Normal file
@ -0,0 +1,214 @@
|
||||
|
||||
"""
|
||||
PRE-PROCESSORS
|
||||
=============================================================================
|
||||
|
||||
Preprocessors work on source text before we start doing anything too
|
||||
complicated.
|
||||
"""
|
||||
|
||||
import re
|
||||
import markdown
|
||||
|
||||
HTML_PLACEHOLDER_PREFIX = markdown.STX+"wzxhzdk:"
|
||||
HTML_PLACEHOLDER = HTML_PLACEHOLDER_PREFIX + "%d" + markdown.ETX
|
||||
|
||||
class Processor:
|
||||
def __init__(self, markdown_instance=None):
|
||||
if markdown_instance:
|
||||
self.markdown = markdown_instance
|
||||
|
||||
class Preprocessor (Processor):
|
||||
"""
|
||||
Preprocessors are run after the text is broken into lines.
|
||||
|
||||
Each preprocessor implements a "run" method that takes a pointer to a
|
||||
list of lines of the document, modifies it as necessary and returns
|
||||
either the same pointer or a pointer to a new list.
|
||||
|
||||
Preprocessors must extend markdown.Preprocessor.
|
||||
|
||||
"""
|
||||
def run(self, lines):
|
||||
"""
|
||||
Each subclass of Preprocessor should override the `run` method, which
|
||||
takes the document as a list of strings split by newlines and returns
|
||||
the (possibly modified) list of lines.
|
||||
|
||||
"""
|
||||
pass
|
||||
|
||||
class HtmlStash:
|
||||
"""
|
||||
This class is used for stashing HTML objects that we extract
|
||||
in the beginning and replace with place-holders.
|
||||
"""
|
||||
|
||||
def __init__ (self):
|
||||
""" Create a HtmlStash. """
|
||||
self.html_counter = 0 # for counting inline html segments
|
||||
self.rawHtmlBlocks=[]
|
||||
|
||||
def store(self, html, safe=False):
|
||||
"""
|
||||
Saves an HTML segment for later reinsertion. Returns a
|
||||
placeholder string that needs to be inserted into the
|
||||
document.
|
||||
|
||||
Keyword arguments:
|
||||
|
||||
* html: an html segment
|
||||
* safe: label an html segment as safe for safemode
|
||||
|
||||
Returns : a placeholder string
|
||||
|
||||
"""
|
||||
self.rawHtmlBlocks.append((html, safe))
|
||||
placeholder = HTML_PLACEHOLDER % self.html_counter
|
||||
self.html_counter += 1
|
||||
return placeholder
|
||||
|
||||
def reset(self):
|
||||
self.html_counter = 0
|
||||
self.rawHtmlBlocks = []
|
||||
|
||||
|
||||
class HtmlBlockPreprocessor(Preprocessor):
|
||||
"""Remove html blocks from the text and store them for later retrieval."""
|
||||
|
||||
right_tag_patterns = ["</%s>", "%s>"]
|
||||
|
||||
def _get_left_tag(self, block):
|
||||
return block[1:].replace(">", " ", 1).split()[0].lower()
|
||||
|
||||
def _get_right_tag(self, left_tag, block):
|
||||
for p in self.right_tag_patterns:
|
||||
tag = p % left_tag
|
||||
i = block.rfind(tag)
|
||||
if i > 2:
|
||||
return tag.lstrip("<").rstrip(">"), i + len(p)-2 + len(left_tag)
|
||||
return block.rstrip()[-len(left_tag)-2:-1].lower(), len(block)
|
||||
|
||||
def _equal_tags(self, left_tag, right_tag):
|
||||
if left_tag == 'div' or left_tag[0] in ['?', '@', '%']: # handle PHP, etc.
|
||||
return True
|
||||
if ("/" + left_tag) == right_tag:
|
||||
return True
|
||||
if (right_tag == "--" and left_tag == "--"):
|
||||
return True
|
||||
elif left_tag == right_tag[1:] \
|
||||
and right_tag[0] != "<":
|
||||
return True
|
||||
else:
|
||||
return False
|
||||
|
||||
def _is_oneliner(self, tag):
|
||||
return (tag in ['hr', 'hr/'])
|
||||
|
||||
def run(self, lines):
|
||||
text = "\n".join(lines)
|
||||
new_blocks = []
|
||||
text = text.split("\n\n")
|
||||
items = []
|
||||
left_tag = ''
|
||||
right_tag = ''
|
||||
in_tag = False # flag
|
||||
|
||||
while text:
|
||||
block = text[0]
|
||||
if block.startswith("\n"):
|
||||
block = block[1:]
|
||||
text = text[1:]
|
||||
|
||||
if block.startswith("\n"):
|
||||
block = block[1:]
|
||||
|
||||
if not in_tag:
|
||||
if block.startswith("<"):
|
||||
left_tag = self._get_left_tag(block)
|
||||
right_tag, data_index = self._get_right_tag(left_tag, block)
|
||||
|
||||
if data_index < len(block):
|
||||
text.insert(0, block[data_index:])
|
||||
block = block[:data_index]
|
||||
|
||||
if not (markdown.isBlockLevel(left_tag) \
|
||||
or block[1] in ["!", "?", "@", "%"]):
|
||||
new_blocks.append(block)
|
||||
continue
|
||||
|
||||
if self._is_oneliner(left_tag):
|
||||
new_blocks.append(block.strip())
|
||||
continue
|
||||
|
||||
if block[1] == "!":
|
||||
# is a comment block
|
||||
left_tag = "--"
|
||||
right_tag, data_index = self._get_right_tag(left_tag, block)
|
||||
# keep checking conditions below and maybe just append
|
||||
|
||||
if block.rstrip().endswith(">") \
|
||||
and self._equal_tags(left_tag, right_tag):
|
||||
new_blocks.append(
|
||||
self.markdown.htmlStash.store(block.strip()))
|
||||
continue
|
||||
else: #if not block[1] == "!":
|
||||
# if is block level tag and is not complete
|
||||
|
||||
if markdown.isBlockLevel(left_tag) or left_tag == "--" \
|
||||
and not block.rstrip().endswith(">"):
|
||||
items.append(block.strip())
|
||||
in_tag = True
|
||||
else:
|
||||
new_blocks.append(
|
||||
self.markdown.htmlStash.store(block.strip()))
|
||||
|
||||
continue
|
||||
|
||||
new_blocks.append(block)
|
||||
|
||||
else:
|
||||
items.append(block.strip())
|
||||
|
||||
right_tag, data_index = self._get_right_tag(left_tag, block)
|
||||
|
||||
if self._equal_tags(left_tag, right_tag):
|
||||
# if find closing tag
|
||||
in_tag = False
|
||||
new_blocks.append(
|
||||
self.markdown.htmlStash.store('\n\n'.join(items)))
|
||||
items = []
|
||||
|
||||
if items:
|
||||
new_blocks.append(self.markdown.htmlStash.store('\n\n'.join(items)))
|
||||
new_blocks.append('\n')
|
||||
|
||||
new_text = "\n\n".join(new_blocks)
|
||||
return new_text.split("\n")
|
||||
|
||||
|
||||
class ReferencePreprocessor(Preprocessor):
|
||||
""" Remove reference definitions from text and store for later use. """
|
||||
|
||||
RE = re.compile(r'^(\ ?\ ?\ ?)\[([^\]]*)\]:\s*([^ ]*)(.*)$', re.DOTALL)
|
||||
|
||||
def run (self, lines):
|
||||
new_text = [];
|
||||
for line in lines:
|
||||
m = self.RE.match(line)
|
||||
if m:
|
||||
id = m.group(2).strip().lower()
|
||||
t = m.group(4).strip() # potential title
|
||||
if not t:
|
||||
self.markdown.references[id] = (m.group(3), t)
|
||||
elif (len(t) >= 2
|
||||
and (t[0] == t[-1] == "\""
|
||||
or t[0] == t[-1] == "\'"
|
||||
or (t[0] == "(" and t[-1] == ")") ) ):
|
||||
self.markdown.references[id] = (m.group(3), t[1:-1])
|
||||
else:
|
||||
new_text.append(line)
|
||||
else:
|
||||
new_text.append(line)
|
||||
|
||||
return new_text #+ "\n"
|
||||
329
src/calibre/ebooks/markdown/treeprocessors.py
Normal file
329
src/calibre/ebooks/markdown/treeprocessors.py
Normal file
@ -0,0 +1,329 @@
|
||||
import markdown
|
||||
import re
|
||||
|
||||
def isString(s):
|
||||
""" Check if it's string """
|
||||
return isinstance(s, unicode) or isinstance(s, str)
|
||||
|
||||
class Processor:
|
||||
def __init__(self, markdown_instance=None):
|
||||
if markdown_instance:
|
||||
self.markdown = markdown_instance
|
||||
|
||||
class Treeprocessor(Processor):
|
||||
"""
|
||||
Treeprocessors are run on the ElementTree object before serialization.
|
||||
|
||||
Each Treeprocessor implements a "run" method that takes a pointer to an
|
||||
ElementTree, modifies it as necessary and returns an ElementTree
|
||||
object.
|
||||
|
||||
Treeprocessors must extend markdown.Treeprocessor.
|
||||
|
||||
"""
|
||||
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
|
||||
modify the current tree and return None.
|
||||
"""
|
||||
pass
|
||||
|
||||
|
||||
class InlineProcessor(Treeprocessor):
|
||||
"""
|
||||
A Treeprocessor that traverses a tree, applying inline patterns.
|
||||
"""
|
||||
|
||||
def __init__ (self, md):
|
||||
self.__placeholder_prefix = markdown.INLINE_PLACEHOLDER_PREFIX
|
||||
self.__placeholder_suffix = markdown.ETX
|
||||
self.__placeholder_length = 4 + len(self.__placeholder_prefix) \
|
||||
+ len(self.__placeholder_suffix)
|
||||
self.__placeholder_re = re.compile(markdown.INLINE_PLACEHOLDER % r'([0-9]{4})')
|
||||
self.markdown = md
|
||||
|
||||
def __makePlaceholder(self, type):
|
||||
""" Generate a placeholder """
|
||||
id = "%04d" % len(self.stashed_nodes)
|
||||
hash = markdown.INLINE_PLACEHOLDER % id
|
||||
return hash, id
|
||||
|
||||
def __findPlaceholder(self, data, index):
|
||||
"""
|
||||
Extract id from data string, start from index
|
||||
|
||||
Keyword arguments:
|
||||
|
||||
* data: string
|
||||
* index: index, from which we start search
|
||||
|
||||
Returns: placeholder id and string index, after the found placeholder.
|
||||
"""
|
||||
|
||||
m = self.__placeholder_re.search(data, index)
|
||||
if m:
|
||||
return m.group(1), m.end()
|
||||
else:
|
||||
return None, index + 1
|
||||
|
||||
def __stashNode(self, node, type):
|
||||
""" Add node to stash """
|
||||
placeholder, id = self.__makePlaceholder(type)
|
||||
self.stashed_nodes[id] = node
|
||||
return placeholder
|
||||
|
||||
def __handleInline(self, data, patternIndex=0):
|
||||
"""
|
||||
Process string with inline patterns and replace it
|
||||
with placeholders
|
||||
|
||||
Keyword arguments:
|
||||
|
||||
* data: A line of Markdown text
|
||||
* patternIndex: The index of the inlinePattern to start with
|
||||
|
||||
Returns: String with placeholders.
|
||||
|
||||
"""
|
||||
if not isinstance(data, markdown.AtomicString):
|
||||
startIndex = 0
|
||||
while patternIndex < len(self.markdown.inlinePatterns):
|
||||
data, matched, startIndex = self.__applyPattern(
|
||||
self.markdown.inlinePatterns.value_for_index(patternIndex),
|
||||
data, patternIndex, startIndex)
|
||||
if not matched:
|
||||
patternIndex += 1
|
||||
return data
|
||||
|
||||
def __processElementText(self, node, subnode, isText=True):
|
||||
"""
|
||||
Process placeholders in Element.text or Element.tail
|
||||
of Elements popped from self.stashed_nodes.
|
||||
|
||||
Keywords arguments:
|
||||
|
||||
* node: parent node
|
||||
* subnode: processing node
|
||||
* isText: bool variable, True - it's text, False - it's tail
|
||||
|
||||
Returns: None
|
||||
|
||||
"""
|
||||
if isText:
|
||||
text = subnode.text
|
||||
subnode.text = None
|
||||
else:
|
||||
text = subnode.tail
|
||||
subnode.tail = None
|
||||
|
||||
childResult = self.__processPlaceholders(text, subnode)
|
||||
|
||||
if not isText and node is not subnode:
|
||||
pos = node.getchildren().index(subnode)
|
||||
node.remove(subnode)
|
||||
else:
|
||||
pos = 0
|
||||
|
||||
childResult.reverse()
|
||||
for newChild in childResult:
|
||||
node.insert(pos, newChild)
|
||||
|
||||
def __processPlaceholders(self, data, parent):
|
||||
"""
|
||||
Process string with placeholders and generate ElementTree tree.
|
||||
|
||||
Keyword arguments:
|
||||
|
||||
* data: string with placeholders instead of ElementTree elements.
|
||||
* parent: Element, which contains processing inline data
|
||||
|
||||
Returns: list with ElementTree elements with applied inline patterns.
|
||||
"""
|
||||
def linkText(text):
|
||||
if text:
|
||||
if result:
|
||||
if result[-1].tail:
|
||||
result[-1].tail += text
|
||||
else:
|
||||
result[-1].tail = text
|
||||
else:
|
||||
if parent.text:
|
||||
parent.text += text
|
||||
else:
|
||||
parent.text = text
|
||||
|
||||
result = []
|
||||
strartIndex = 0
|
||||
while data:
|
||||
index = data.find(self.__placeholder_prefix, strartIndex)
|
||||
if index != -1:
|
||||
id, phEndIndex = self.__findPlaceholder(data, index)
|
||||
|
||||
if id in self.stashed_nodes:
|
||||
node = self.stashed_nodes.get(id)
|
||||
|
||||
if index > 0:
|
||||
text = data[strartIndex:index]
|
||||
linkText(text)
|
||||
|
||||
if not isString(node): # it's Element
|
||||
for child in [node] + node.getchildren():
|
||||
if child.tail:
|
||||
if child.tail.strip():
|
||||
self.__processElementText(node, child, False)
|
||||
if child.text:
|
||||
if child.text.strip():
|
||||
self.__processElementText(child, child)
|
||||
else: # it's just a string
|
||||
linkText(node)
|
||||
strartIndex = phEndIndex
|
||||
continue
|
||||
|
||||
strartIndex = phEndIndex
|
||||
result.append(node)
|
||||
|
||||
else: # wrong placeholder
|
||||
end = index + len(prefix)
|
||||
linkText(data[strartIndex:end])
|
||||
strartIndex = end
|
||||
else:
|
||||
text = data[strartIndex:]
|
||||
linkText(text)
|
||||
data = ""
|
||||
|
||||
return result
|
||||
|
||||
def __applyPattern(self, pattern, data, patternIndex, startIndex=0):
|
||||
"""
|
||||
Check if the line fits the pattern, create the necessary
|
||||
elements, add it to stashed_nodes.
|
||||
|
||||
Keyword arguments:
|
||||
|
||||
* data: the text to be processed
|
||||
* pattern: the pattern to be checked
|
||||
* patternIndex: index of current pattern
|
||||
* startIndex: string index, from which we starting search
|
||||
|
||||
Returns: String with placeholders instead of ElementTree elements.
|
||||
|
||||
"""
|
||||
match = pattern.getCompiledRegExp().match(data[startIndex:])
|
||||
leftData = data[:startIndex]
|
||||
|
||||
if not match:
|
||||
return data, False, 0
|
||||
|
||||
node = pattern.handleMatch(match)
|
||||
|
||||
if node is None:
|
||||
return data, True, len(leftData) + match.span(len(match.groups()))[0]
|
||||
|
||||
if not isString(node):
|
||||
if not isinstance(node.text, markdown.AtomicString):
|
||||
# We need to process current node too
|
||||
for child in [node] + node.getchildren():
|
||||
if not isString(node):
|
||||
if child.text:
|
||||
child.text = self.__handleInline(child.text,
|
||||
patternIndex + 1)
|
||||
if child.tail:
|
||||
child.tail = self.__handleInline(child.tail,
|
||||
patternIndex)
|
||||
|
||||
placeholder = self.__stashNode(node, pattern.type())
|
||||
|
||||
return "%s%s%s%s" % (leftData,
|
||||
match.group(1),
|
||||
placeholder, match.groups()[-1]), True, 0
|
||||
|
||||
def run(self, tree):
|
||||
"""Apply inline patterns to a parsed Markdown tree.
|
||||
|
||||
Iterate over ElementTree, find elements with inline tag, apply inline
|
||||
patterns and append newly created Elements to tree. If you don't
|
||||
want process your data with inline paterns, instead of normal string,
|
||||
use subclass AtomicString:
|
||||
|
||||
node.text = markdown.AtomicString("data won't be processed with inline patterns")
|
||||
|
||||
Arguments:
|
||||
|
||||
* markdownTree: ElementTree object, representing Markdown tree.
|
||||
|
||||
Returns: ElementTree object with applied inline patterns.
|
||||
|
||||
"""
|
||||
self.stashed_nodes = {}
|
||||
|
||||
stack = [tree]
|
||||
|
||||
while stack:
|
||||
currElement = stack.pop()
|
||||
insertQueue = []
|
||||
for child in currElement.getchildren():
|
||||
if child.text and not isinstance(child.text, markdown.AtomicString):
|
||||
text = child.text
|
||||
child.text = None
|
||||
lst = self.__processPlaceholders(self.__handleInline(
|
||||
text), child)
|
||||
stack += lst
|
||||
insertQueue.append((child, lst))
|
||||
|
||||
if child.getchildren():
|
||||
stack.append(child)
|
||||
|
||||
for element, lst in insertQueue:
|
||||
if element.text:
|
||||
element.text = \
|
||||
markdown.inlinepatterns.handleAttributes(element.text,
|
||||
element)
|
||||
i = 0
|
||||
for newChild in lst:
|
||||
# Processing attributes
|
||||
if newChild.tail:
|
||||
newChild.tail = \
|
||||
markdown.inlinepatterns.handleAttributes(newChild.tail,
|
||||
element)
|
||||
if newChild.text:
|
||||
newChild.text = \
|
||||
markdown.inlinepatterns.handleAttributes(newChild.text,
|
||||
newChild)
|
||||
element.insert(i, newChild)
|
||||
i += 1
|
||||
return tree
|
||||
|
||||
|
||||
class PrettifyTreeprocessor(Treeprocessor):
|
||||
""" Add linebreaks to the html document. """
|
||||
|
||||
def _prettifyETree(self, elem):
|
||||
""" Recursively add linebreaks to ElementTree children. """
|
||||
|
||||
i = "\n"
|
||||
if markdown.isBlockLevel(elem.tag) and elem.tag not in ['code', 'pre']:
|
||||
if (not elem.text or not elem.text.strip()) \
|
||||
and len(elem) and markdown.isBlockLevel(elem[0].tag):
|
||||
elem.text = i
|
||||
for e in elem:
|
||||
if markdown.isBlockLevel(e.tag):
|
||||
self._prettifyETree(e)
|
||||
if not elem.tail or not elem.tail.strip():
|
||||
elem.tail = i
|
||||
if not elem.tail or not elem.tail.strip():
|
||||
elem.tail = i
|
||||
|
||||
def run(self, root):
|
||||
""" Add linebreaks to ElementTree root object. """
|
||||
|
||||
self._prettifyETree(root)
|
||||
# Do <br />'s seperately as they are often in the middle of
|
||||
# inline content and missed by _prettifyETree.
|
||||
brs = root.getiterator('br')
|
||||
for br in brs:
|
||||
if not br.tail or not br.tail.strip():
|
||||
br.tail = '\n'
|
||||
else:
|
||||
br.tail = '\n%s' % br.tail
|
||||
@ -96,9 +96,11 @@ def convert_basic(txt, title='', epub_split_size_kb=0):
|
||||
|
||||
def convert_markdown(txt, title='', disable_toc=False):
|
||||
from calibre.ebooks.markdown import markdown
|
||||
extensions=['footnotes', 'tables']
|
||||
if not disable_toc:
|
||||
extensions.append('toc')
|
||||
md = markdown.Markdown(
|
||||
extensions=['footnotes', 'tables', 'toc'],
|
||||
extension_configs={"toc": {"disable_toc": disable_toc}},
|
||||
extensions,
|
||||
safe_mode=False)
|
||||
return HTML_TEMPLATE % (title, md.convert(txt))
|
||||
|
||||
|
||||
Loading…
x
Reference in New Issue
Block a user