discussion_indexer.patch

--- discussion_indexer.py   2010-08-26 09:37:19.000000000 -0300
+++ discussion_indexer2.py  2010-08-26 13:04:50.000000000 -0300
@@ -1,28 +1,59 @@
 import re, time
-MONTHS = ('January', 'February', 'March', 'April', 'May',
+MONTHS = {
+'en' : ('January', 'February', 'March', 'April', 'May',
        'June', 'July', 'August', 'September', 'October',
        'November', 'December')
+'pt' : ('Janeiro', 'Fevereiro', 'Março', 'Abril', 'Maio',
+       'Junho', 'Julho', 'Agosto', 'Setembro', 'Outubro',
+       'Novembro', 'Dezembro')
+}
+
+#TODO: How to use $dateFormats from /languages/messages/MessagesXX.php ?
+# en: 'dmy both' => 'H:i, j F Y'
+# pt: 'dmy both' => 'H\hi\m\i\n \d\e j \d\e F \d\e Y'
+
+TIMESTAMPS = {
+'en' : ur'^(.*?)([0-9]{2}\:[0-9]{2}\,' + \
+       ' [0-9]{1,2} (?:%s) [0-9]{4})' % \
+       '|'.join(MONTHS['en']) + ' \(UTC\)\s*$'
+'pt' : ur'^(.*?)([0-9]{2}h[0-9]{2}min' + \
+       ' de [0-9]{1,2} de (?:%s) de [0-9]{4})' % \
+       '|'.join(MONTHS['pt']) + ' \(UTC\)\s*$'
+}
+
+TIMESTAMPS2 = {
+'en' : '%H:%M, %d %B %Y'
+'pt' : '%Hh%Mmin de %d de %B de %Y'
+}
+
+USERS = {
+'en' : ur'.*\[\[[Uu]ser(?:[ _]talk)?\:([^]|]*)'
+'pt' : ur'.*\[\[[Uu]suário(?:[ _]Discussão)?\:([^]|]*)'
+}

 import mwclient
 import cgitb; cgitb.enable(format = 'text')

 class DiscussionIndexer(object):
+   LANG = 'en' #TODO: How to get $wgLanguageCode for the current project?
    def __init__(self, site):
        self.site = site

        self.cache = {}

-   r_timestamp = re.compile(ur'^(.*?)([0-9]{2}\:[0-9]{2}\,' + \
-       ' [0-9]{1,2} (?:%s) [0-9]{4})' % \
-       '|'.join(MONTHS) + ' \(UTC\)\s*$', re.MULTILINE)
-   r_user = re.compile(ur'.*\[\[[Uu]ser(?:[ _]talk)?\:([^]|]*)')
+   r_timestamp = re.compile(TIMESTAMPS[LANG], re.MULTILINE)
+   r_user = re.compile(USERS[LANG])
    def get_last_comment(self, section):
        """ Returns a tuple (user, timestamp) of the
        last comment made to the section."""

        comments = self.r_timestamp.findall(section)
+       for c in comments:
+           for m in range(12):
+               c[1] = re.sub(MONTHS['pt'][m], MONTHS['en'][m], c[1])
+
        comments = [(self.r_user.search(line), time.strptime(timestamp,
-           '%H:%M, %d %B %Y')) for line, timestamp in comments]
+           TIMESTAMPS2[LANG])) for line, timestamp in comments]

        comments.sort(cmp = lambda x, y: -cmp(x[1], y[1]))

@@ -73,7 +104,7 @@
        items = []
        for page, title, user, timestamp in sections:
            if timestamp:
-               timestamp = time.strftime('%H:%M, %d %B %Y', timestamp)
+               timestamp = time.strftime(TIMESTAMPS2[LANG], timestamp)
            else:
                timestamp = u''