diff options
Diffstat (limited to 'wiki2text.py')
| -rw-r--r-- | wiki2text.py | 20 |
1 files changed, 12 insertions, 8 deletions
diff --git a/wiki2text.py b/wiki2text.py index 916391e..5041ea0 100644 --- a/wiki2text.py +++ b/wiki2text.py @@ -6,28 +6,32 @@ # it under the terms of the GNU General Public License as published by # the Free Software Foundation; either version 3, or (at your option) # any later version. # # This program is distributed in the hope that it will be useful, # but WITHOUT ANY WARRANTY; without even the implied warranty of # MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the # GNU General Public License for more details. # # You should have received a copy of the GNU General Public License # along with this program. If not, see <http://www.gnu.org/licenses/>. -from wikimarkup import * -from wikins import wiki_ns_re, wiki_ns +from wit.wikimarkup import * +from wit.wikins import wiki_ns_re, wiki_ns import re -import urllib +try: + from urllib import quote as url_quote +except ImportError: + from urllib.parse import quote as url_quote + class TextWikiMarkup (WikiMarkup): """ A (general-purpose Wiki->Text translator class. """ # Output width width = 78 # Do not show references. references = False # Provide a minimum markup markup = True @@ -49,79 +53,79 @@ class TextWikiMarkup (WikiMarkup): return "%s (see %s) " % (text, target) else: return "see " + target def wiki_ns_name(self, str): if str in wiki_ns[self.lang]: return wiki_ns[self.lang][str] elif str in wiki_ns_re[self.lang]: for elt in wiki_ns_re[self.lang][str]: if str.beginswith(elt[0]) and str.endswith(elt[1]): return elt[2] return None - + def mktgt(self, tgt, lang = None): if not lang: lang = self.lang - return self.html_base % { 'lang' : lang } + urllib.quote(tgt) + return self.html_base % { 'lang' : lang } + url_quote(tgt) def fmtlink(self, elt, istmpl): arg = self.format(elt['content'][0]) if len(elt['content']) > 1: s = [x for x in map(self.format, elt['content'])] text = s[1] else: s = None text = None if s: if s[0] == 'disambigR' or s[0] == 'wikiquote': return "" if len(s) > 1 and s[1] == 'thumb': return "" (qual,sep,tgt) = arg.partition(':') if tgt != '': ns = self.wiki_ns_name(qual) if ns: if ns == 'NS_IMAGE': if not self.references: return "" text = "[%s: %s]" % (qual, text if text else arg) tgt = self.image_base + '/' + \ - urllib.quote(tgt) + \ - '/250px-' + urllib.quote(tgt) + url_quote(tgt) + \ + '/250px-' + url_quote(tgt) elif ns == 'NS_MEDIA': text = "[%s]" % (qual) else: tgt = self.mktgt(tgt) elif not istmpl and qual in self.langtab: text = self.langtab[qual] + ": " + tgt tgt = self.mktgt(tgt, qual) else: tgt = self.mktgt(tgt) else: tgt = self.mktgt(arg) if self.references: return "%s (see %s) " % (text, tgt) elif not text or text == '': return arg else: return text def indent (self, lev, text): if text.find('\n') == -1: s = (" " * lev) + text else: s = "" - for elt in text.split('\n'): + for elt in text.decode("utf-8").split('\n'): if elt: s += (" " * lev) + elt + '\n' if not text.endswith('\n'): s = s.rstrip('\n') # print "IN: '%s'" % (text) # print "OUT: '%s'" % (s) return s def fmtpara(self, input): output = "" linebuf = "" length = 0 |