def parse(self, text):
"""Parses and renders a text as HTML regarding current format"""
if self.format == 'markdown':
try:
import markdown
except ImportError:
raise RuntimeError(u"Looks like markdown is not installed")
return markdown.markdown(text)
elif self.format == 'restructuredtext':
try:
from rst import html_parts, html_body
except ImportError:
raise RuntimeError(u"Looks like docutils are not installed")
html = html_body(text, input_encoding=self.encoding,
output_encoding=self.encoding)
html = re.sub(r'<div.*?>\n', r'', html, re.DOTALL | re.UNICODE)
html = re.sub(r'</div>\n', r'', html, re.DOTALL | re.UNICODE)
html = re.sub(r'<hr class=".*?" />\n', r'<hr />\n', html,
re.DOTALL | re.UNICODE)
return html
else:
raise NotImplementedError(u"Unsupported format %s, cannot parse"
% self.format)
def parse(self, text):
"""Parses and renders a text as HTML regarding current format."""
if self.format == 'markdown':
try:
import markdown
except ImportError:
raise RuntimeError(u"Looks like markdown is not installed")
return markdown.markdown(text, self.extensions)
elif self.format == 'restructuredtext':
try:
from rst import html_parts, html_body
except ImportError:
raise RuntimeError(u"Looks like docutils are not installed")
html = html_body(text, input_encoding=self.encoding)
html = re.sub(r'<p class="sys.+\n.+ion\.', r'', html,
re.DOTALL | re.UNICODE) # Pretty hackish
html = re.sub(r'<h1 class="title">', r'<h1>', html,
re.DOTALL | re.UNICODE)
html = re.sub(r'<hr class=".*?" />\n', r'<hr />\n', html,
re.DOTALL | re.UNICODE)
return html
else:
raise NotImplementedError(u"Unsupported format %s, cannot parse"
% self.format)
def parse(self, text):
"""Parses and renders a text as HTML regarding current format.
"""
if self.format == 'markdown':
try:
import markdown
except ImportError:
raise RuntimeError(u"Looks like markdown is not installed")
return markdown.markdown(text, self.md_extensions)
elif self.format == 'restructuredtext':
try:
from rst import html_body
except ImportError:
raise RuntimeError(u"Looks like docutils are not installed")
html = html_body(text, input_encoding=self.encoding)
# RST generates pretty much markup to be removed in our case
for (pattern, replacement, mode) in self.RST_REPLACEMENTS:
html = re.sub(pattern, replacement, html, mode)
return html.strip()
elif self.format == 'textile':
try:
import textile
except ImportError:
raise RuntimeError(u"Looks like textile is not installed")
return textile.textile(text, encoding=self.encoding)
else:
raise NotImplementedError(u"Unsupported format %s, cannot parse"
% self.format)
def parse(self, text):
"""Parses and renders a text as HTML regarding current format.
"""
if self.format == 'markdown':
try:
import markdown
except ImportError:
raise RuntimeError(u"Looks like markdown is not installed")
if text.startswith(u'\ufeff'): # check for unicode BOM
text = text[1:]
return markdown.markdown(text, self.md_extensions)
elif self.format == 'restructuredtext':
try:
from rst import html_body
except ImportError:
raise RuntimeError(u"Looks like docutils are not installed")
html = html_body(text, input_encoding=self.encoding)
# RST generates pretty much markup to be removed in our case
for (pattern, replacement, mode) in self.RST_REPLACEMENTS:
html = re.sub(re.compile(pattern, mode), replacement, html, 0)
return html.strip()
elif self.format == 'textile':
try:
import textile
except ImportError:
raise RuntimeError(u"Looks like textile is not installed")
return textile.textile(text, encoding=self.encoding)
else:
raise NotImplementedError(u"Unsupported format %s, cannot parse" %
self.format)
def parse(self, text):
"""Parses and renders a text as HTML regarding current format."""
if self.format == 'markdown':
try:
import markdown
except ImportError:
raise RuntimeError(u"Looks like markdown is not installed")
return markdown.markdown(text)
elif self.format == 'restructuredtext':
try:
from rst import html_parts, html_body
except ImportError:
raise RuntimeError(u"Looks like docutils are not installed")
html = html_body(text, input_encoding=self.encoding)
html = re.sub(r'<div.*?>', r'', html, re.UNICODE)
html = re.sub(r'</div>', r'', html, re.UNICODE)
html = re.sub(r'<p class="system-message-\w+">.*?</p>', r'', html,
re.UNICODE)
html = re.sub(r'Document or section may not begin with a transition\.',
r'', html, re.UNICODE)
html = re.sub(r'<h(\d+?).*?>', r'<h\1>', html,
re.DOTALL | re.UNICODE)
html = re.sub(r'<hr.*?>\n', r'<hr />\n', html,
re.DOTALL | re.UNICODE)
return html.strip()
else:
raise NotImplementedError(u"Unsupported format %s, cannot parse"
% self.format)
def parse(self, text):
"""Parses and renders a text as HTML regarding current format.
"""
if self.format == 'markdown':
try:
import markdown
except ImportError:
raise RuntimeError(u"Looks like markdown is not installed")
if text.startswith(u'\ufeff'): # check for unicode BOM
text = text[1:]
return markdown.markdown(text, self.md_extensions)
elif self.format == 'restructuredtext':
try:
from rst import html_body
except ImportError:
raise RuntimeError(u"Looks like docutils are not installed")
html = html_body(text, input_encoding=self.encoding)
# RST generates pretty much markup to be removed in our case
if re.search('<hr.*?>', html): #writing with Manual hr
for (pattern, replacement, mode) in self.RST_REPLACEMENTS+self.RST_REPLACEMENTS_WITH_HR:
html = re.sub(re.compile(pattern, mode), replacement, html, 0)
else: # we add hr before every <hx>
for (pattern, replacement, mode) in self.RST_REPLACEMENTS+self.RST_REPLACEMENTS_WITHOUT_HR:
html = re.sub(re.compile(pattern, mode), replacement, html, 0)
html = re.sub('<hr />', '', html, 1) # replace the first one
return html.strip()
elif self.format == 'textile':
try:
import textile
except ImportError:
raise RuntimeError(u"Looks like textile is not installed")
return textile.textile(text, encoding=self.encoding)
else:
raise NotImplementedError(u"Unsupported format %s, cannot parse"
% self.format)
def parse(self, text):
"""Parses and renders a text as HTML regarding current format"""
if self.format == 'markdown':
try:
import markdown
except ImportError:
raise RuntimeError(u"Looks like markdown is not installed")
return markdown.markdown(text)
elif self.format == 'restructuredtext':
try:
from rst import html_parts, html_body
except ImportError:
raise RuntimeError(u"Looks like docutils are not installed")
html = html_body(text, input_encoding=self.encoding,
output_encoding=self.encoding)
classless_html = re.sub(' class=".+"', '', html)
return classless_html.replace('<div>', '').replace('</div>', '')
else:
raise NotImplementedError(u"Unsupported format, cannot parse")
# -*- coding: utf-8 -*-
# print "Latin-1:", "unicode über alles!".decode('utf-8').encode('latin-1')
# print "Utf-8:", "unicode über alles!".decode('utf-8').encode('utf-8')
# print "Windows:", "unicode über alles!".decode('utf-8').encode('cp1252')
import sys, os
reload(sys)
sys.setdefaultencoding("utf-8")
from rst import html_body
import codecs
# USAGE:
# python parse.py doc/index.rst
if len(sys.argv) > 1:
f = sys.argv[1]
else:
print 'Error:no file'
if os.path.isfile(f):
with codecs.open(f,'r', 'utf-8') as rst:
d = rst.read()
# XXX: output to stdout will raise a error if not set default encoding
# http://stackoverflow.com/questions/3828723/why-we-need-sys-setdefaultencodingutf-8-in-a-py-script
# print d.decode('utf8')
print html_body(d.decode('utf8'))
else:
print 'Error:not a valid file'
