def registerExtensions(self, extensions, configs):
"""
Register extensions with this instance of Markdown.
Keyword aurguments:
* extensions: A list of extensions, which can either
be strings or objects. See the docstring on Markdown.
* configs: A dictionary mapping module names to config options.
"""
for ext in extensions:
if isinstance(ext, basestring):
ext = load_extension(ext, configs.get(ext, []))
if isinstance(ext, Extension):
try:
ext.extendMarkdown(self, globals())
except NotImplementedError, e:
message(ERROR, e)
else:
message(
ERROR,
'Extension "%s.%s" must be of type: "markdown.Extension".'
% (ext.__class__.__module__, ext.__class__.__name__),
)
def set_output_format(self, format):
""" Set the output format for the class instance. """
try:
self.serializer = self.output_formats[format.lower()]
except KeyError:
message(CRITICAL,
'Invalid Output Format: "%s". Use one of %s.' \
% (format, self.output_formats.keys()))
def set_output_format(self, format):
""" Set the output format for the class instance. """
try:
self.serializer = self.output_formats[format.lower()]
except KeyError:
message(CRITICAL,
'Invalid Output Format: "%s". Use one of %s.' \
% (format, self.output_formats.keys()))
def build_extension(self, ext_name, configs=[]):
"""Build extension by name, then return the module.
The extension name may contain arguments as part of the string in the
following format: "extname(key1=value1,key2=value2)"
"""
# Parse extensions config params (ignore the order)
configs = dict(configs)
pos = ext_name.find("(") # find the first "("
if pos > 0:
ext_args = ext_name[pos + 1:-1]
ext_name = ext_name[:pos]
pairs = [x.split("=") for x in ext_args.split(",")]
configs.update([(x.strip(), y.strip()) for (x, y) in pairs])
# Setup the module names
ext_module = 'markdown.extensions'
module_name_new_style = '.'.join([ext_module, ext_name])
module_name_old_style = '_'.join(['mdx', ext_name])
# Try loading the extention first from one place, then another
try: # New style (markdown.extensons.<extension>)
module = __import__(module_name_new_style, {}, {}, [ext_module])
except ImportError:
try: # Old style (mdx_<extension>)
module = __import__(module_name_old_style)
except ImportError:
message(
WARN, "Failed loading extension '%s' from '%s' or '%s'" %
(ext_name, module_name_new_style, module_name_old_style))
# Return None so we don't try to initiate none-existant extension
return None
# If the module is loaded successfully, we expect it to define a
# function called makeExtension()
try:
return module.makeExtension(configs.items())
except AttributeError, e:
message(CRITICAL,
"Failed to initiate extension '%s': %s" % (ext_name, e))
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:
# This should never happen, but just in case...
message(CRITICAL, "We've got a problem header!")
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
from xml.etree.ElementTree import Comment
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
from elementtree.ElementTree import Comment
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:
if etree_in_c.VERSION < "1.0":
message(CRITICAL,
"cElementTree version 1.0 or higher is required.")
sys.exit(1)
# Third party serializers (including ours) test with non-c Comment
etree_in_c.test_comment = Comment
return etree_in_c
elif etree.VERSION < "1.1":
message(CRITICAL, "ElementTree version 1.1 or higher is required")
sys.exit(1)
else:
return etree
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
def build_extension(self, ext_name, configs = []):
"""Build extension by name, then return the module.
The extension name may contain arguments as part of the string in the
following format: "extname(key1=value1,key2=value2)"
"""
# Parse extensions config params (ignore the order)
configs = dict(configs)
pos = ext_name.find("(") # find the first "("
if pos > 0:
ext_args = ext_name[pos+1:-1]
ext_name = ext_name[:pos]
pairs = [x.split("=") for x in ext_args.split(",")]
configs.update([(x.strip(), y.strip()) for (x, y) in pairs])
# Setup the module names
ext_module = 'markdown.extensions'
module_name_new_style = '.'.join([ext_module, ext_name])
module_name_old_style = '_'.join(['mdx', ext_name])
# Try loading the extention first from one place, then another
try: # New style (markdown.extensons.<extension>)
module = __import__(module_name_new_style, {}, {}, [ext_module])
except ImportError:
try: # Old style (mdx_<extension>)
module = __import__(module_name_old_style)
except ImportError:
message(WARN, "Failed loading extension '%s' from '%s' or '%s'"
% (ext_name, module_name_new_style, module_name_old_style))
# Return None so we don't try to initiate none-existant extension
return None
# If the module is loaded successfully, we expect it to define a
# function called makeExtension()
try:
return module.makeExtension(configs.items())
except AttributeError, e:
message(CRITICAL, "Failed to initiate extension '%s': %s" % (ext_name, e))
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
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
from xml.etree.ElementTree import Comment
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
from elementtree.ElementTree import Comment
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:
if etree_in_c.VERSION < "1.0":
message(CRITICAL, "cElementTree version 1.0 or higher is required.")
sys.exit(1)
# Third party serializers (including ours) test with non-c Comment
etree_in_c.test_comment = Comment
return etree_in_c
elif etree.VERSION < "1.1":
message(CRITICAL, "ElementTree version 1.1 or higher is required")
sys.exit(1)
else:
return etree
def registerExtensions(self, extensions, configs):
"""
Register extensions with this instance of Markdown.
Keyword aurguments:
* extensions: A list of extensions, which can either
be strings or objects. See the docstring on Markdown.
* configs: A dictionary mapping module names to config options.
"""
for ext in extensions:
if isinstance(ext, basestring):
ext = self.build_extension(ext, configs.get(ext, []))
if isinstance(ext, Extension):
try:
ext.extendMarkdown(self, globals())
except NotImplementedError, e:
message(ERROR, e)
else:
message(ERROR,
'Extension "%s.%s" must be of type: "markdown.Extension".' \
% (ext.__class__.__module__, ext.__class__.__name__))
def convert(self, source):
"""
Convert markdown to serialized XHTML or HTML.
Keyword arguments:
* source: Source text as a Unicode string.
Markdown processing takes place in five steps:
1. A bunch of "preprocessors" munge the input text.
2. BlockParser() parses the high-level structural elements of the
pre-processed text into an ElementTree.
3. A bunch of "treeprocessors" are run against the ElementTree. One
such treeprocessor runs InlinePatterns against the ElementTree,
detecting inline markup.
4. Some post-processors are run against the text after the ElementTree
has been serialized into text.
5. The output is written to a string.
"""
# Fixup the source text
if not source.strip():
return u"" # a blank unicode string
try:
source = unicode(source)
except UnicodeDecodeError:
message(
CRITICAL,
'UnicodeDecodeError: Markdown only accepts unicode or ascii input.'
)
return u""
source = source.replace(util.STX, "").replace(util.ETX, "")
source = source.replace("\r\n", "\n").replace("\r", "\n") + "\n\n"
source = re.sub(r'\n\s+\n', '\n\n', source)
source = source.expandtabs(self.tab_length)
# Split into lines and run the line preprocessors.
self.lines = source.split("\n")
for prep in self.preprocessors.values():
self.lines = prep.run(self.lines)
# Parse the high-level elements.
root = self.parser.parseDocument(self.lines).getroot()
# Run the tree-processors
for treeprocessor in self.treeprocessors.values():
newRoot = treeprocessor.run(root)
if newRoot:
root = newRoot
# Serialize _properly_. Strip top-level tags.
output, length = codecs.utf_8_decode(
self.serializer(root, encoding="utf-8"))
if self.stripTopLevelTags:
try:
start = output.index('<%s>' % self.doc_tag) + len(
self.doc_tag) + 2
end = output.rindex('</%s>' % self.doc_tag)
output = output[start:end].strip()
except ValueError:
if output.strip().endswith('<%s />' % self.doc_tag):
# We have an empty document
output = ''
else:
# We have a serious problem
message(CRITICAL, 'Failed to strip top level tags.')
# Run the text post-processors
for pp in self.postprocessors.values():
output = pp.run(output)
return output.strip()
def convert(self, source):
"""
Convert markdown to serialized XHTML or HTML.
Keyword arguments:
* source: Source text as a Unicode string.
Markdown processing takes place in five steps:
1. A bunch of "preprocessors" munge the input text.
2. BlockParser() parses the high-level structural elements of the
pre-processed text into an ElementTree.
3. A bunch of "treeprocessors" are run against the ElementTree. One
such treeprocessor runs InlinePatterns against the ElementTree,
detecting inline markup.
4. Some post-processors are run against the text after the ElementTree
has been serialized into text.
5. The output is written to a string.
"""
# Fixup the source text
if not source.strip():
return u"" # a blank unicode string
try:
source = unicode(source)
except UnicodeDecodeError:
message(CRITICAL,
'UnicodeDecodeError: Markdown only accepts unicode or ascii input.')
return u""
source = source.replace(util.STX, "").replace(util.ETX, "")
source = source.replace("\r\n", "\n").replace("\r", "\n") + "\n\n"
source = re.sub(r'\n\s+\n', '\n\n', source)
source = source.expandtabs(self.tab_length)
# Split into lines and run the line preprocessors.
self.lines = source.split("\n")
for prep in self.preprocessors.values():
self.lines = prep.run(self.lines)
# Parse the high-level elements.
root = self.parser.parseDocument(self.lines).getroot()
# Run the tree-processors
for treeprocessor in self.treeprocessors.values():
newRoot = treeprocessor.run(root)
if newRoot:
root = newRoot
# Serialize _properly_. Strip top-level tags.
output, length = codecs.utf_8_decode(self.serializer(root, encoding="utf-8"))
if self.stripTopLevelTags:
try:
start = output.index('<%s>'%self.doc_tag)+len(self.doc_tag)+2
end = output.rindex('</%s>'%self.doc_tag)
output = output[start:end].strip()
except ValueError:
if output.strip().endswith('<%s />'%self.doc_tag):
# We have an empty document
output = ''
else:
# We have a serious problem
message(CRITICAL, 'Failed to strip top level tags.')
# Run the text post-processors
for pp in self.postprocessors.values():
output = pp.run(output)
return output.strip()