######################################################################
# regexps used by ZWiki

# in order to support more flexible numbers in wikinames, eg
# Issue0001, Issue0001SubjectHeading etc while not compromising
# simplicity, how about: "one or more digits is equivalent to a single
# capital letter" ?
# hmm getting a bit tricky

import re

# international (latin?) characters
intl_char_entities = (
    ('\300', '&Agrave;'),     #À#<--char
    ('\302', '&Acirc;'),      #Â#
    ('\311', '&Eacute;'),     #É#
    ('\312', '&Ecirc;'),      #Ê#
    ('\316', '&Icirc;'),      #Î#
    ('\324', '&Ocirc;'),      #Ô#
    ('\333', '&Ucirc;'),      #Û#
    ('\340', '&agrave;'),     #à#
    ('\342', '&acirc;'),      #â#
    ('\347', '&ccedil;'),     #ç#
    ('\350', '&egrave;'),     #è#
    ('\351', '&eacute;'),     #é#
    ('\352', '&ecirc;'),      #ê#
    ('\356', '&icirc;'),      #î#
    ('\364', '&ocirc;'),      #ô#
    ('\371', '&ugrave;'),     #ù#
    ('\373', '&ucirc;'),      #û#
#    ('\253', '&#171;'),       #«#
#    ('\273', '&#187;'),       #»#
#    ('(r)', '&#174;'),
#    ('(tm)', '&#153;'),
#    ('^s', '&nbsp;')
)

# regular expressions (worth compiling these ?)

# use urllib/urlparse ?
urlchars         = r'[A-Za-z0-9/:@_%~#=&\.\-\?\+\$]+'
urlendchar       = r'[A-Za-z0-9/]'
url              = r'["=]?((about|gopher|http|https|ftp|mailto|file):%s)' % (urlchars)
# I think this got complicated in an attempt to co-exist with stx's references
# or perhaps it's this way so it can be used to strip the brackets as well
bracketedexpr    = r'\[([^\]0-9][^]]*)\]'
wikiname1        = r'\b[A-Z]+[a-z]+[A-Z][A-Za-z]*[0-9]*'
wikiname2        = r'\b[A-Z][A-Z]+[a-z][A-Za-z]*[0-9]*'
simplewikilink   = r'!?(%s|%s|%s)' % (wikiname1, wikiname2, url)
wikilink         = r'!?(%s|%s|%s|%s)' % (wikiname1,wikiname2,bracketedexpr,url)
interwikilink    = r'!?((?P<local>%s):(?P<remote>%s))' % \
                   (wikilink, urlchars+urlendchar)
remotewikiurl    = r'(?m)RemoteWikiURL[:\s]*([^\s]+)\s*$'
pagesubscribers  = r'(?m)PageSubscribers[:\s]*(.*)$'
protected_line   = r'(?m)^!(.*)$'

# intl. regexps - won't work because we convert intl. chars to
# entities to protect them from browser textareas
#IU = intlupper   = '\300\302\311\312\316\324\333'
#IL = intllower   = '\340\342\347\350\351\352\356\364\371\373'
#IA = intlall     = IU+IL
#url              = r'["=]?((http|ftp|mailto|file):[A-Za-z0-9/:@_%~\.\-\?'+IA+']+)'
#wikiname1        = r'[A-Z'+IU+']+[a-z'+IL+']+[A-Z'+IU+'][A-Za-z'+IA+']*'
#wikiname2        = r'[A-Z]'+IU+'[A-Z'+IU+']+[a-z'+IL+'][A-Za-z'+IA+']*'


# CMFWiki version:
#
#urlchars          = (r'[A-Za-z0-9/:@_%~#=&\.\-\?]+')
#url               = (r'["=]?((http|https|ftp|mailto|file|about):%s)'
#                     % (urlchars))
#urlexp            = re.compile(url)
## trying to co-exist with stx references:
#bracketedexpr     = r'\[([^\]0-9][^]]*)\]'
#bracketedexprexp  = re.compile(bracketedexpr)
#underlinedexpr    = r'_([^_]+)_'
#underlinedexprexp = re.compile(underlinedexpr)
#wikiname1         = r'\b[A-Z]+[a-z~]+[A-Z0-9][A-Z0-9a-z~]*'
#wikiname2         = r'\b[A-Z][A-Z0-9]+[a-z~][A-Z0-9a-z~]*'
#simplewikilinkexp = re.compile(r'!?(%s|%s)' % (wikiname1, wikiname2))
#
#wikiending        = r"[ \t\n\r\f\v:;.,<)!?']"
#urllinkending     = r'[^A-Za-z0-9/:@_%~\.\-\?]'
#wikilink          = (r'!?(%s%s|%s%s|%s|%s%s)'
#                    % (wikiname1,wikiending,
#                       wikiname2,wikiending,
#                       bracketedexpr,url,urllinkending))
#wikilinkexp       = re.compile(wikilink)
#wikilink_         = r'!?(%s|%s|%s|%s)' % \
#                     (wikiname1,wikiname2,bracketedexpr,url)
#interwikilinkexp  = re.compile(r'!?((?P<local>%s):(?P<remote>[\w]+))'
#                              % (wikilink_))
#remotewikiurlexp  = re.compile(r'(?m)RemoteWikiURL[:\s]*(.*)$')
#protected_lineexp = re.compile(r'(?m)^!(.*)$')
#
#antidecaptext     = '<!--antidecapitationkludge-->\n'
#antidecapexp      = re.compile(antidecaptext)
#
#commentsdelim = "<hr solid id=comments_below>"
#preexp = re.compile(r'<pre>')
#unpreexp = re.compile(r'</pre>')
#citedexp = re.compile(r'^\s*>')
## Match group 1 is citation prefix, group 2 is leading whitespace:
#cite_prefixexp = re.compile('([\s>]*>)?([\s]*)')