1
0
Fork 0
mirror of https://github.com/morpheus65535/bazarr synced 2024-12-27 18:17:46 +00:00
bazarr/libs/markdown/blockprocessors.py
2018-09-16 20:33:04 -04:00

573 lines
22 KiB
Python

"""
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.
"""
from __future__ import absolute_import
from __future__ import division
from __future__ import unicode_literals
import logging
import re
from . import util
from .blockparser import BlockParser
logger = logging.getLogger('MARKDOWN')
def build_block_parser(md_instance, **kwargs):
""" Build the default block parser used by Markdown. """
parser = BlockParser(md_instance)
parser.blockprocessors['empty'] = EmptyBlockProcessor(parser)
parser.blockprocessors['indent'] = ListIndentProcessor(parser)
parser.blockprocessors['code'] = CodeBlockProcessor(parser)
parser.blockprocessors['hashheader'] = HashHeaderProcessor(parser)
parser.blockprocessors['setextheader'] = SetextHeaderProcessor(parser)
parser.blockprocessors['hr'] = HRProcessor(parser)
parser.blockprocessors['olist'] = OListProcessor(parser)
parser.blockprocessors['ulist'] = UListProcessor(parser)
parser.blockprocessors['quote'] = BlockQuoteProcessor(parser)
parser.blockprocessors['paragraph'] = ParagraphProcessor(parser)
return parser
class BlockProcessor(object):
""" 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):
self.parser = parser
self.tab_length = parser.markdown.tab_length
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(' '*self.tab_length):
newtext.append(line[self.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(' '*self.tab_length*level):
lines[i] = lines[i][self.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 # pragma: no cover
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 # pragma: no cover
class ListIndentProcessor(BlockProcessor):
""" Process children of list items.
Example:
* a list item
process this part
or this part
"""
ITEM_TYPES = ['li']
LIST_TYPES = ['ul', 'ol']
def __init__(self, *args):
super(ListIndentProcessor, self).__init__(*args)
self.INDENT_RE = re.compile(r'^(([ ]{%s})+)' % self.tab_length)
def test(self, parent, block):
return block.startswith(' '*self.tab_length) and \
not self.parser.state.isstate('detabbed') and \
(parent.tag in self.ITEM_TYPES or
(len(parent) and parent[-1] is not None 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:
# It's possible that this parent has a 'ul' or 'ol' child list
# with a member. If that is the case, then that should be the
# parent. This is intended to catch the edge case of an indented
# list whose first member was parsed previous to this point
# see OListProcessor
if len(parent) and parent[-1].tag in self.LIST_TYPES:
self.parser.parseBlocks(parent[-1], [block])
else:
# 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
# The p must be 'inserted' at beginning of list in the event
# that other children already exist i.e.; a nested sublist.
p = util.etree.Element('p')
p.text = sibling[-1].text
sibling[-1].text = ''
sibling[-1].insert(0, p)
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 = util.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))/self.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 is not None 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(' '*self.tab_length)
def run(self, parent, blocks):
sibling = self.lastChild(parent)
block = blocks.pop(0)
theRest = ''
if (sibling is not None 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 = util.AtomicString(
'%s\n%s\n' % (code.text, block.rstrip())
)
else:
# This is a new codeblock. Create the elements and insert text.
pre = util.etree.SubElement(parent, 'pre')
code = util.etree.SubElement(pre, 'code')
block, theRest = self.detab(block)
code.text = util.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 is not None 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 = util.etree.SubElement(parent, 'blockquote')
# Recursively parse block with blockquote as parent.
# change parser state so blockquotes embedded in lists use p tags
self.parser.state.set('blockquote')
self.parser.parseChunk(quote, block)
self.parser.state.reset()
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'
# The integer (python string) with which the lists starts (default=1)
# Eg: If list is intialized as)
# 3. Item
# The ol tag will get starts="3" attribute
STARTSWITH = '1'
# List of allowed sibling tags.
SIBLING_TAGS = ['ol', 'ul']
def __init__(self, parser):
super(OListProcessor, self).__init__(parser)
# Detect an item (``1. item``). ``group(1)`` contains contents of item.
self.RE = re.compile(r'^[ ]{0,%d}\d+\.[ ]+(.*)' % (self.tab_length - 1))
# Detect items on secondary lines. they can be of either list type.
self.CHILD_RE = re.compile(r'^[ ]{0,%d}((\d+\.)|[*+-])[ ]+(.*)' %
(self.tab_length - 1))
# Detect indented (nested) items of either type
self.INDENT_RE = re.compile(r'^[ ]{%d,%d}((\d+\.)|[*+-])[ ]+.*' %
(self.tab_length, self.tab_length * 2 - 1))
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 is not None and sibling.tag in self.SIBLING_TAGS:
# Previous block was a list item, so set that as parent
lst = sibling
# make sure previous item is in a p- if the item has text,
# then it isn't in a p
if lst[-1].text:
# since it's possible there are other children for this
# sibling, we can't just SubElement the p, we need to
# insert it as the first item.
p = util.etree.Element('p')
p.text = lst[-1].text
lst[-1].text = ''
lst[-1].insert(0, p)
# if the last item has a tail, then the tail needs to be put in a p
# likely only when a header is not followed by a blank line
lch = self.lastChild(lst[-1])
if lch is not None and lch.tail:
p = util.etree.SubElement(lst[-1], 'p')
p.text = lch.tail.lstrip()
lch.tail = ''
# parse first block differently as it gets wrapped in a p.
li = util.etree.SubElement(lst, 'li')
self.parser.state.set('looselist')
firstitem = items.pop(0)
self.parser.parseBlocks(li, [firstitem])
self.parser.state.reset()
elif parent.tag in ['ol', 'ul']:
# this catches the edge case of a multi-item indented list whose
# first item is in a blank parent-list item:
# * * subitem1
# * subitem2
# see also ListIndentProcessor
lst = parent
else:
# This is a new list so create parent with appropriate tag.
lst = util.etree.SubElement(parent, self.TAG)
# Check if a custom start integer is set
if not self.parser.markdown.lazy_ol and self.STARTSWITH != '1':
lst.attrib['start'] = self.STARTSWITH
self.parser.state.set('list')
# Loop through items in block, recursively parsing each with the
# appropriate parent.
for item in items:
if item.startswith(' '*self.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 = util.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 list item
# Check first item for the start index
if not items and self.TAG == 'ol':
# Detect the integer value of first list item
INTEGER_RE = re.compile(r'(\d+)')
self.STARTSWITH = INTEGER_RE.match(m.group(1)).group()
# Append to the list
items.append(m.group(3))
elif self.INDENT_RE.match(line):
# This is an indented (possibly nested) item.
if items[-1].startswith(' '*self.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'
def __init__(self, parser):
super(UListProcessor, self).__init__(parser)
# Detect an item (``1. item``). ``group(1)`` contains contents of item.
self.RE = re.compile(r'^[ ]{0,%d}[*+-][ ]+(.*)' % (self.tab_length - 1))
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|$)')
def test(self, parent, block):
return bool(self.RE.search(block))
def run(self, parent, blocks):
block = blocks.pop(0)
m = self.RE.search(block)
if m:
before = block[:m.start()] # All lines before header
after = block[m.end():] # All lines after header
if before:
# As the header was not the first line of the block and the
# lines before the header must be parsed first,
# recursively parse this lines as a block.
self.parser.parseBlocks(parent, [before])
# Create header using named groups from RE
h = util.etree.SubElement(parent, 'h%d' % len(m.group('level')))
h.text = m.group('header').strip()
if after:
# Insert remaining lines as first block for future parsing.
blocks.insert(0, after)
else: # pragma: no cover
# This should never happen, but just in case...
logger.warn("We've got a problem header: %r" % block)
class SetextHeaderProcessor(BlockProcessor):
""" Process Setext-style Headers. """
# Detect Setext-style header. Must be first 2 lines of block.
RE = re.compile(r'^.*?\n[=-]+[ ]*(\n|$)', 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 = util.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}((-+[ ]{0,2}){3,}|(_+[ ]{0,2}){3,}|(\*+[ ]{0,2}){3,})[ ]*'
# Detect hr on any line of a block.
SEARCH_RE = re.compile(RE, re.MULTILINE)
def test(self, parent, block):
m = self.SEARCH_RE.search(block)
# No atomic grouping in python so we simulate it here for performance.
# The regex only matches what would be in the atomic group - the HR.
# Then check if we are at end of block or if next char is a newline.
if m and (m.end() == len(block) or block[m.end()] == '\n'):
# Save match object on class instance so we can use it later.
self.match = m
return True
return False
def run(self, parent, blocks):
block = blocks.pop(0)
match = self.match
# Check for lines in block before hr.
prelines = block[:match.start()].rstrip('\n')
if prelines:
# Recursively parse lines before hr so they get parsed first.
self.parser.parseBlocks(parent, [prelines])
# create hr
util.etree.SubElement(parent, 'hr')
# check for lines in block after hr.
postlines = block[match.end():].lstrip('\n')
if postlines:
# Add lines after hr to master blocks for later parsing.
blocks.insert(0, postlines)
class EmptyBlockProcessor(BlockProcessor):
""" Process blocks that are empty or start with an empty line. """
def test(self, parent, block):
return not block or block.startswith('\n')
def run(self, parent, blocks):
block = blocks.pop(0)
filler = '\n\n'
if block:
# Starts with empty line
# Only replace a single line.
filler = '\n'
# Save the rest for later.
theRest = block[1:]
if theRest:
# Add remaining lines to master blocks for later.
blocks.insert(0, theRest)
sibling = self.lastChild(parent)
if (sibling is not None and sibling.tag == 'pre' and
len(sibling) and sibling[0].tag == 'code'):
# Last block is a codeblock. Append to preserve whitespace.
sibling[0].text = util.AtomicString(
'%s%s' % (sibling[0].text, filler)
)
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.
#
# Check for any children. This will likely only happen in a
# tight-list when a header isn't followed by a blank line.
# For example:
#
# * # Header
# Line 2 of list item - not part of header.
sibling = self.lastChild(parent)
if sibling is not None:
# Insetrt after sibling.
if sibling.tail:
sibling.tail = '%s\n%s' % (sibling.tail, block)
else:
sibling.tail = '\n%s' % block
else:
# 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 = util.etree.SubElement(parent, 'p')
p.text = block.lstrip()