def __call__(self):
text = self.orig
if text is None:
text = ''
if not isinstance(text, unicode):
text = unicode(text, 'utf-8', 'replace')
# Do & separately, else, it may replace an already-inserted & from
# an entity with &, so < becomes < becomes &lt;
text = text.replace('&', '&')
# Make funny characters into html entity defs
for entity, letter in entitydefs.items():
if entity != 'amp':
text = text.replace(
letter.decode('latin-1'), '&' + entity + ';')
text = self.urlRegexp.subn(self.replaceURL, text)[0]
text = self.emailRegexp.subn(self.replaceEmail, text)[0]
text = self.indentRegexp.subn(self.indentWhitespace, text)[0]
# convert windows line endings
text = text.replace('\r\n', '\n')
# Finally, make \n's into br's
text = text.replace('\n', '<br />')
text = text.encode('utf-8')
return text
def __call__(self):
text = self.orig
if text is None:
text = ''
if not isinstance(text, unicode):
text = unicode(text, 'utf-8', 'replace')
# Do & separately, else, it may replace an already-inserted & from
# an entity with &, so < becomes < becomes &lt;
text = text.replace('&', '&')
# Make funny characters into html entity defs
for entity, letter in entitydefs.items():
if entity != 'amp':
text = text.replace(letter.decode('latin-1'),
'&' + entity + ';')
text = self.urlRegexp.subn(self.replaceURL, text)[0]
text = self.emailRegexp.subn(self.replaceEmail, text)[0]
text = self.indentRegexp.subn(self.indentWhitespace, text)[0]
# convert windows line endings
text = text.replace('\r\n', '\n')
# Finally, make \n's into br's
text = text.replace('\n', '<br />')
text = text.encode('utf-8')
return text
def _parse_dates(self):
'''
Also, strptime returns datetime objects when
we really want date objects.
Possible formats:
* Friday, July 1, 2011 > Single
* October 10 - 21, 2011 > Duration - Same Month
* June 27 - August 26, 2011 > Duration - Different Month
* October 17, 2011 - January 13, 2012
> Duration - Different month and year
* March 21, 2011 - January 8, 2012
and October 24, 2011 - January 8, 2012
> Multiple durations
'''
# Clean Up
## Replace any HTML entities and codes with a <space>
for entity,code in entitydefs.items():
self._when_text = self._when_text.replace('&'+entity+';', ' ')
self._when_text = self._when_text.replace(code, ' ')
## Force to ascii
self._when_text = self._when_text.encode('ascii', 'replace')
## Replace \xFFFD with <space>
self._when_text = self._when_text.replace(u'\xFFFD', ' ')
## Normalize spacing
self._when_text = re.sub('\s+', ' ', self._when_text)
for duration in self._when_text.split('and'):
date_split = duration.strip().split('-')
start_date = None
start_text = date_split[0].strip()
end_date = None
if len(date_split) == 1:
try:
start_date = datetime.strptime(start_text,
UCFAcademicCalendar._Event._DF_SINGLE)
except ValueError, e:
log.error('Unable to parse single date: ' + start_text)
raise UCFAcademicCalendar._Event.ParsingError()
elif len(date_split) == 2:
end_text = date_split[1].strip()
same_month = False
try: # Month Day Year
end_date = datetime.strptime(end_text,
UCFAcademicCalendar._Event._DF_MONTH_DAY_YEAR)
except ValueError, e:
try: # Day, Year
end_date = datetime.strptime(end_text,\
UCFAcademicCalendar._Event._DF_DAY_YEAR)
same_month = True
except ValueError, e:
log.error('Unable to parse start date: ' + end_text)
raise UCFAcademicCalendar._Event.ParsingFailure()
def __entitytoletter(self, s):
newdefs = []
for k, v in entitydefs.items():
newdefs.append(('&'+k+';', v))
for k, v in newdefs:
s = s.replace(k, v)
return s
def _expand_entities(self, body):
body = body.replace(' ', ' ')
for entity, letter in entitydefs.items():
# Let plone.intelligenttext handle < and >, or else we may be
# creating what looks like tags.
if entity != 'lt' and entity != 'gt':
body = body.replace('&' + entity + ';',
letter.decode('latin-1'))
return body
def convert(self, orig, data, **kwargs):
# "encoding" is both the encoding of orig, and the expected encoding of
# the data in data.
if kwargs['encoding'] not in ['utf-8', 'utf_8', 'U8', 'UTF', 'utf8']:
raise ValueError('Only support unicode, not %s' % kwargs['encoding'])
if os.path.isfile(TTM_BINARY):
p = subprocess.Popen(
[
TTM_BINARY,
'-a', # Try to convert picture elements
'-e3', # inline epsfbox w/no icon
'-r', # Don't output a pre/postamble
'-u2', # Unicode please
],
stdin=subprocess.PIPE,
stdout=subprocess.PIPE,
stderr=subprocess.PIPE,
)
(out, err) = p.communicate(input=(LATEX_PREAMBLE + orig + LATEX_POSTAMBLE))
if '****' in err:
# Probably an error, show it.
data.setData('<pre class="ttm-output error">%s</pre>\n<div class="ttm-output">%s</div>' % (
cgi.escape(err.strip()),
out.strip(),
))
else:
data.setData('<div class="ttm-output">%s</div>' % (
out.strip(),
))
else:
out = convertWebIntelligentPlainTextToHtml(orig.decode(kwargs['encoding'])).decode('utf8')
# Bodge back entities, to save space
from htmlentitydefs import entitydefs
for entity, letter in entitydefs.items():
if entity not in ('amp', 'lt', 'gt',):
out = out.replace('&' + entity + ';', letter.decode('latin-1'))
data.setData('<div class="parse-as-tex">%s</div>' % out.encode(kwargs['encoding']))
return data
def cleanHTML(text, skipchars=[], extra_careful=1):
# This is an attempt to get rid of " ä " etc within a string
# Still working on it ... any help appreicated.
entitydefs_inverted = {}
for k,v in entitydefs.items():
entitydefs_inverted[v] = k
_badchars_regex = re.compile('|'.join(entitydefs.values()))
_been_fixed_regex = re.compile('&\w+;|&#[0-9]+;')
# if extra_careful we don't attempt to do anything to
# the string if it might have been converted already.
if extra_careful and _been_fixed_regex.findall(text):
return text
if type(skipchars) == type('s'):
skipchars = [skipchars]
keyholder= {}
for x in _badchars_regex.findall(text):
if x not in skipchars:
keyholder[x] = 1
text = text.replace('&','&')
text = text.replace('\x80', '€')
for each in keyholder.keys():
if each == '&':
continue
better = entitydefs_inverted[each]
if not better.startswith('&#'):
better = '&%s;'%entitydefs_inverted[each]
text = text.replace(each, better)
return text
match_movie_url = re.compile(r""".*\.(mpg|mpeg|avi)$""", re.I).match
match_movie = re.compile("^(\x00\x00\x01\xba|RIFF....AVI LIST)").match
match_enum_url = re.compile("(.*?)(\d+)(\.\w{3,4})?$").match
enum_blacklisted = re.compile("^http://[^\.]*.yimg.com").match
# matches html entities
from htmlentitydefs import entitydefs
entities = []
for (e, s) in entitydefs.items():
if len(s) == 1: entities.append(e)
entity_sub = re.compile("&(%s);" % '|'.join(entities)).sub
get_match_entitydef = lambda match: entitydefs[match.group(1)]
#unescapes html entities
def unentify(s):
return entity_sub(get_match_entitydef, s)
import Queue
class MultiQueue(Queue.Queue):
def _init(self, (maxq, maxsize)):
self.maxsize = maxsize
if size < 1024.0:
import math
if math.floor(size) == size:
return "%d %s" % (int(size), final_unit)
else:
return "%3.1f %s" % (size, final_unit)
if unit != "Yotta":
size /= 1024.0
return "%3.1f %s" % (size, final_unit)
entitydefs_inverted = {}
for k, v in entitydefs.items():
entitydefs_inverted[v] = k
_badchars_regex = re.compile("|".join(entitydefs.values()))
_been_fixed_regex = re.compile("&\w+;|&#[0-9]+;")
def html_entity_fixer(text, skipchars=[], extra_careful=1):
# if extra_careful we don't attempt to do anything to
# the string if it might have been converted already.
if extra_careful and _been_fixed_regex.findall(text):
return text
if type(skipchars) == type("s"):
skipchars = [skipchars]
from math import floor
from htmlentitydefs import entitydefs
import warnings, pytz
import logging
# import line used by textify
import formatter, htmllib, StringIO
try:
import markdown
markdown_converter = markdown.Markdown(safe_mode="escape")
except ImportError:
markdown_converter = None
entitydefs_inverted = {}
for k, v in entitydefs.items():
entitydefs_inverted[v] = k
# zope
from Products.PythonScripts.standard import html_quote, newline_to_br, \
url_quote, url_quote_plus
try:
# >= Zope 2.12
from zope.structuredtext import stx2html
except ImportError:
# < Zope 2.12
from StructuredText.StructuredText import HTML as stx2html
def structured_text(txt):
referlink = re.compile(r"""(http|ftp)://(.*?)(http|ftp)://""", re.I).match
match_movie_url = re.compile(r""".*\.(mpg|mpeg|avi)$""", re.I).match
match_movie = re.compile("^(\x00\x00\x01\xba|RIFF....AVI LIST)").match
match_enum_url = re.compile("(.*?)(\d+)(\.\w{3,4})?$").match
enum_blacklisted = re.compile("^http://[^\.]*.yimg.com").match
# matches html entities
from htmlentitydefs import entitydefs
entities = []
for (e, s) in entitydefs.items():
if len(s) == 1: entities.append(e)
entity_sub = re.compile("&(%s);" % '|'.join(entities)).sub
get_match_entitydef = lambda match: entitydefs[match.group(1)]
#unescapes html entities
def unentify(s):
return entity_sub(get_match_entitydef, s)
import Queue
class MultiQueue(Queue.Queue):
def decodeentities(string):
for (htmlent, ch) in entitydefs.items():
string = string.replace('&'+htmlent+';', ch)
return string
entitydefs['nbsp'] = ' '
sgmlentity = {
'lt': '<',
'gt': '>',
'amp': '&',
'quot': '"',
'apos': '\'',
'ndash': '-'
}
sgmlentityget = sgmlentity.get
_sgmlentkeys = sgmlentity.keys()
entcharrefs = {}
entcharrefsget = entcharrefs.get
for _k, _v in entitydefs.items():
if _k in _sgmlentkeys: continue
if _v[0:2] == '&#':
dec_code = _v[1:-1]
_v = unichr(int(_v[2:-1]))
entcharrefs[dec_code] = _v
else:
dec_code = '#' + str(ord(_v))
_v = unicode(_v, 'latin_1', 'replace')
entcharrefs[dec_code] = _v
entcharrefs[_k] = _v
del _sgmlentkeys, _k, _v
entcharrefs['#160'] = u' '
entcharrefs['#xA0'] = u' '
entcharrefs['#xa0'] = u' '
entcharrefs['#XA0'] = u' '
("gacute", 501), ("Hacek", 711), ("Breve", 728),
("DiacriticalDot", 729), ("ring", 730), ("ogon", 731),
("DiacriticalTilde", 732),
("DiacriticalDoubleAcute", 733), ("DownBreve", 785),
("UnderBar", 818), ("varepsilon", 949),
("varsigma", 962), ("varphi", 966), ("vartheta", 977),
("Upsi", 978), ("straightphi", 981), ("varpi", 982),
("Gammad", 988), ("digamma", 989), ("varkappa", 1008),
("varrho", 1009), ("straightepsilon", 1013),
("backepsilon", 1014)]
from htmlentitydefs import entitydefs
entitydefs['apos'] = "'" # only XML entity that isn't an HTML entity as well
List_HTML_Entities = []
for name, value in entitydefs.items():
List_HTML_Entities.append((name, value[2:-1] or str(ord(value))))
for (name, value) in List_MathML2_Entities:
assert name not in entitydefs
List_HTML_Entities.append((name, str(value)))
########## CSS properties ##########
List_CSS_Props = "color display font font-family font-size font-style font-weight list-style margin margin-bottom margin-left margin-right margin-top max-width opacity padding padding-bottom padding-left padding-right padding-top page-break-after page-break-before text-align text-decoration text-indent text-underline white-space word-wrap"
########## CSS colors ##########
# array of name/value for css colors, value is what goes inside MKRGB()
# based on https://developer.mozilla.org/en/CSS/color_value
# TODO: add more colors
List_CSS_Colors = [
def convertWebIntelligentPlainTextToHtml(orig, tab_width=4):
"""Converts text/x-web-intelligent to text/html
"""
# very long urls are abbreviated to allow nicer layout
def abbreviateUrl(url, max = 60, ellipsis = "[…]"):
if len(url) < max:
return url
protocolend = url.find("//")
if protocolend == -1:
protocol = ""
else:
protocol = url[0 : protocolend+2]
url = url[protocolend+2 : ]
list = url.split("/")
if len(list) < 3 or len(list[0])+len(list[-1] )>max:
url = protocol + url
center = (max-5)/2
return url[:center] + ellipsis + url[-center:]
return protocol + list[0] +"/" +ellipsis + "/" + list[-1]
urlRegexp = re.compile(r'((?:ftp|https?)://(localhost|([12]?[0-9]{1,2}.){3}([12]?[0-9]{1,2})|(?:[a-z0-9](?:[-a-z0-9]*[a-z0-9])?\.)+(?:com|edu|biz|org|gov|int|info|mil|net|name|museum|coop|aero|[a-z][a-z]))\b(?::\d+)?(?:\/[^"\'<>()\[\]{}\s\x7f-\xff]*(?:[.,?]+[^"\'<>()\[\]{}\s\x7f-\xff]+)*)?)', re.I|re.S|re.U)
emailRegexp = re.compile(r'["=]?(\b[A-Z0-9._%-]+@[A-Z0-9._%-]+\.[A-Z]{2,4}\b)', re.I|re.S|re.U)
indentRegexp = re.compile(r'^(\s+)', re.M|re.U)
text = orig
if text is None:
text = ''
if not isinstance(text, unicode):
text = unicode(text, 'utf-8', 'replace')
# Do & separately, else, it may replace an already-inserted & from
# an entity with &, so < becomes < becomes &lt;
text = text.replace('&', '&')
# Make funny characters into html entity defs
for entity, letter in entitydefs.items():
if entity != 'amp':
text = text.replace(letter.decode('latin-1'), '&' + entity + ';')
# Replace hyperlinks with clickable <a> tags
def replaceURL(match):
url = match.groups()[0]
linktext = abbreviateUrl(url)
# In urls we need the revert our earlier change to the ampersands.
# We do not want something like:
# http://google.com/ask?question=everything&answer=42
url = url.replace('&', '&')
# Also with <some link> we should only link to some link, not
# including the brackets.
end = ''
# XXX Probably better to fix the regex above. Maurits
if url.endswith('>'):
url = url[:-len('>')]
linktext = linktext[:-len('>')]
end = '>'
# rel="nofollow" shall avoid spamming
return '<a href="%s" rel="nofollow">%s</a>%s' % (url, linktext, end)
text = urlRegexp.subn(replaceURL, text)[0]
# Replace email strings with mailto: links
def replaceEmail(match):
url = match.groups()[0]
# following unicode substitutions shall avoid email spam crawlers to pickup email addresses
url = url.replace('@', '@');
return '<a href="mailto:%s">%s</a>' % (url, url)
text = emailRegexp.subn(replaceEmail, text)[0]
# Make leading whitespace on a line into to preserve indents
def indentWhitespace(match):
indent = match.groups()[0]
indent = indent.replace(' ', ' ')
return indent.replace('\t', ' ' * tab_width)
text = indentRegexp.subn(indentWhitespace, text)[0]
# Finally, make \n's into br's
text = text.replace('\n', '<br />')
text = text.encode('utf-8')
return text
def _build_entiries_re():
p=[]
for k,v in entitydefs.items():
if v.startswith('&'): continue
p.append(re.escape(k))
return re.compile("&(%s);" % "|".join(p), re.I)
return string.split(pwd.getpwnam(user.id)[4], ",")[0]
except: pass
return ""
def urlquote(s): return urllib.quote_plus(s, "")
def urlunquote(s): return urllib.unquote_plus(s)
def quotedtext(text):
def quotedline(line):
return "> %s" % line
return string.join(map(quotedline, string.split(text, "\n")), "\n")
replace_char = {"\n": "<br>\n", "\t": " " * 4}
for key, value in entitydefs.items():
replace_char[value] = "&%s;" % key
def escape(s, spaces=0):
nbsp = entitydefs["nbsp"]
last = ""
new = StringIO()
for char in s:
if spaces and char == " " and last in [" ", nbsp]:
char = nbsp
new.write(replace_char.get(char, char))
last = char
newstr = new.getvalue()
if spaces and newstr and newstr[0] == " ":
return " %s" % newstr[1:]
def convertHtmlToWebIntelligentPlainText(orig):
"""Converts text/html to text/x-web-intelligent.
"""
preRegex = re.compile(r'<\s*pre[^>]*>(.*?)<\s*/pre\s*>', re.I | re.S)
tagWhitespaceRegex = re.compile(r'\s+((<[^>]+>)\s+)+')
whitespaceRegex = re.compile(r'\s+')
tdRegex = re.compile(r'<\s*(td)([^>])*>', re.I)
breakRegex = re.compile(r'<\s*(br)\s*/?>', re.I)
startBlockRegex = re.compile(r'<\s*(dt)[^>]*>', re.I)
endBlockRegex = re.compile(r'<\s*/\s*(p|div|tr|ul|ol|dl)[^>]*>', re.I)
indentBlockRegex = re.compile(r'<\s*(blockquote|dd)[^>]*>', re.I)
listBlockRegex = re.compile(r'<\s*(li)[^>]*>', re.I)
tagRegex = re.compile(r'<[^>]+>', re.I | re.M)
# Save all <pre> sections and restore after other transforms
preSections = {}
def savePres(match):
marker = '__pre_marker__%d__' % (len(preSections),)
preSections[marker] = match.group(1)
return marker
if orig is None:
orig = ''
text = preRegex.sub(savePres, orig)
# Make whitespace-tag-whitespace into whitespace-tag. Repeat this
# in case there are directly nested tags
def fixTagWhitespace(match):
# Remove any superfluous whitespace, but preserve one leading space
return ' ' + whitespaceRegex.sub('', match.group(0))
text = tagWhitespaceRegex.sub(fixTagWhitespace, text)
# Make all whitespace into a single space
text = whitespaceRegex.sub(' ', text)
# Fix entities
text = text.replace(' ', ' ')
for entity, letter in entitydefs.items():
# Do < and > later, else we may be creating what looks like
# tags
if entity != 'lt' and entity != 'gt':
text = text.replace('&' + entity + ';', letter)
# XXX: Remove <head>, <script>, <style> ?
# Make tabs out of td's
text = tdRegex.sub('\t', text)
# Make br's and li's into newlines
text = breakRegex.sub('\n', text)
# Make the start of list blocks into paragraphs
text = startBlockRegex.sub('\n\n', text)
# Make the close of p's, div's and tr's into paragraphs
text = endBlockRegex.sub('\n\n', text)
# Make blockquotes and dd blocks indented
text = indentBlockRegex.sub('\n\n ', text)
# Make list items indented and prefixed with -
text = listBlockRegex.sub('\n\n - ', text)
# Remove other tags
text = tagRegex.sub('', text)
# Fix < and > entities
text = text.replace('<', '<')
text = text.replace('>', '>')
# Restore pres
for marker, section in preSections.items():
text = text.replace(marker, '\n\n' + section + '\n\n')
return text
#!/usrbin/env python # -*- coding: us-ascii -*- # vim: syntax=python # # 2-clause BSD license # Copyright 2009 Noriyuki Hosaka [email protected] # import sys import os.path from htmlentitydefs import entitydefs from tonic.lineparser import LineParser _d = dict([(value, '&'+key+';') for key, value in entitydefs.items()]) def escape(s): return ''.join([_d.get(c, c) for c in s]) def resource(name): if not name.startswith(os.path.sep): name = os.path.join(os.path.split( os.path.abspath(__file__))[0], name) f = file(name, 'rb') try: return f.read(-1) finally: f.close() class Formatter(LineParser): css_src = resource('python.css')
lastKey=lastKey)
# Handle HTML/XML/SGML entities.
from htmlentitydefs import entitydefs
entitydefs = entitydefs.copy()
entitydefsget = entitydefs.get
entitydefs['nbsp'] = ' '
sgmlentity = {'lt': '<', 'gt': '>', 'amp': '&', 'quot': '"', 'apos': '\''}
sgmlentityget = sgmlentity.get
_sgmlentkeys = sgmlentity.keys()
entcharrefs = {}
entcharrefsget = entcharrefs.get
for _k, _v in entitydefs.items():
if _k in _sgmlentkeys: continue
if _v[0:2] == '&#':
dec_code = _v[1:-1]
_v = unichr(int(_v[2:-1]))
entcharrefs[dec_code] = _v
else:
dec_code = '#' + str(ord(_v))
_v = unicode(_v, 'latin_1', 'replace')
entcharrefs[dec_code] = _v
entcharrefs[_k] = _v
del _sgmlentkeys, _k, _v
entcharrefs['#160'] = u' '
entcharrefs['#xA0'] = u' '
entcharrefs['#xa0'] = u' '
entcharrefs['#XA0'] = u' '
def htmlEncode(s):
_entitymap = dict((val, key) for (key,val) in entitydefs.items())
return ''.join("&" + _entitymap[ch] + ";"
if ch in _entitymap or str(ch) in _entitymap
else ch
for ch in s)
########## HTML and XML entities ##########
Template_Entities_Comment = """\
// map of entity names to their Unicode runes, cf.
// http://en.wikipedia.org/wiki/List_of_XML_and_HTML_character_entity_references
// and http://www.w3.org/TR/MathML2/bycodes.html
"""
# selection of MathML2 entities that aren't HTML entities
List_MathML2_Entities = [("DoubleDot", 168), ("OverBar", 175), ("PlusMinus", 177), ("Cedilla", 184), ("Amacr", 256), ("amacr", 257), ("Abreve", 258), ("abreve", 259), ("Aogon", 260), ("aogon", 261), ("Cacute", 262), ("cacute", 263), ("Ccirc", 264), ("ccirc", 265), ("Cdot", 266), ("cdot", 267), ("Ccaron", 268), ("ccaron", 269), ("Dcaron", 270), ("dcaron", 271), ("Dstrok", 272), ("dstrok", 273), ("Emacr", 274), ("emacr", 275), ("Edot", 278), ("edot", 279), ("Eogon", 280), ("eogon", 281), ("Ecaron", 282), ("ecaron", 283), ("Gcirc", 284), ("gcirc", 285), ("Gbreve", 286), ("gbreve", 287), ("Gdot", 288), ("gdot", 289), ("Gcedil", 290), ("Hcirc", 292), ("hcirc", 293), ("Hstrok", 294), ("hstrok", 295), ("Itilde", 296), ("itilde", 297), ("Imacr", 298), ("imacr", 299), ("Iogon", 302), ("iogon", 303), ("Idot", 304), ("IJlig", 306), ("ijlig", 307), ("Jcirc", 308), ("jcirc", 309), ("Kcedil", 310), ("kcedil", 311), ("kgreen", 312), ("Lacute", 313), ("lacute", 314), ("Lcedil", 315), ("lcedil", 316), ("Lcaron", 317), ("lcaron", 318), ("Lmidot", 319), ("lmidot", 320), ("Lstrok", 321), ("lstrok", 322), ("Nacute", 323), ("nacute", 324), ("Ncedil", 325), ("ncedil", 326), ("Ncaron", 327), ("ncaron", 328), ("napos", 329), ("ENG", 330), ("eng", 331), ("Omacr", 332), ("omacr", 333), ("Odblac", 336), ("odblac", 337), ("Racute", 340), ("racute", 341), ("Rcedil", 342), ("rcedil", 343), ("Rcaron", 344), ("rcaron", 345), ("Sacute", 346), ("sacute", 347), ("Scirc", 348), ("scirc", 349), ("Scedil", 350), ("scedil", 351), ("Tcedil", 354), ("tcedil", 355), ("Tcaron", 356), ("tcaron", 357), ("Tstrok", 358), ("tstrok", 359), ("Utilde", 360), ("utilde", 361), ("Umacr", 362), ("umacr", 363), ("Ubreve", 364), ("ubreve", 365), ("Uring", 366), ("uring", 367), ("Udblac", 368), ("udblac", 369), ("Uogon", 370), ("uogon", 371), ("Wcirc", 372), ("wcirc", 373), ("Ycirc", 374), ("ycirc", 375), ("Zacute", 377), ("zacute", 378), ("Zdot", 379), ("zdot", 380), ("Zcaron", 381), ("zcaron", 382), ("imped", 437), ("gacute", 501), ("Hacek", 711), ("Breve", 728), ("DiacriticalDot", 729), ("ring", 730), ("ogon", 731), ("DiacriticalTilde", 732), ("DiacriticalDoubleAcute", 733), ("DownBreve", 785), ("UnderBar", 818), ("varepsilon", 949), ("varsigma", 962), ("varphi", 966), ("vartheta", 977), ("Upsi", 978), ("straightphi", 981), ("varpi", 982), ("Gammad", 988), ("digamma", 989), ("varkappa", 1008), ("varrho", 1009), ("straightepsilon", 1013), ("backepsilon", 1014)]
from htmlentitydefs import entitydefs
entitydefs['apos'] = "'" # only XML entity that isn't an HTML entity as well
List_HTML_Entities = []
for name, value in entitydefs.items():
List_HTML_Entities.append((name, value[2:-1] or str(ord(value))))
for (name, value) in List_MathML2_Entities:
assert name not in entitydefs
List_HTML_Entities.append((name, str(value)))
########## CSS properties ##########
List_CSS_Props = "color display font font-family font-size font-style font-weight list-style margin margin-bottom margin-left margin-right margin-top max-width padding padding-bottom padding-left padding-right padding-top page-break-after page-break-before text-align text-decoration text-indent text-underline white-space word-wrap"
########## CSS colors ##########
# array of name/value for css colors, value is what goes inside MKRGB()
# based on https://developer.mozilla.org/en/CSS/color_value
# TODO: add more colors
List_CSS_Colors = [
def decodeentities(string):
for (htmlent, ch) in entitydefs.items():
string = string.replace('&' + htmlent + ';', ch)
return string
