view i18n/posplit @ 25867:a74e9806d17d stable

highlight: produce correct markup when there's a blank line just before EOF Due to how the colorized output from pygments was stripped of <pre> elements, when there was an empty line at the end of a file, highlight extension produced an incorrect markup (no closing tags from the fileline/annotateline template). It wasn't usually noticeable, because browsers were smart enough to see where the missing tags should've been, but in monoblue style it resulted in the last line having twice the normal height. Instead of awkwardly trying to strip outer <pre></pre> tags, let's make the formatter with nowrap=True, which should do what we need in pygments since at least 0.5 (2006-10-30). Example from monoblue style: Before: <div class="source"> <div style="font-family:monospace" class="parity0"> <pre><a class="linenr" href="#l1" id="l1"> 1</a> </pre> </div> <div style="font-family:monospace" class="parity1"> <pre><a class="linenr" href="#l2" id="l2"> 2</a> </div> Now: <div class="source"> <div style="font-family:monospace" class="parity0"> <pre><a class="linenr" href="#l1" id="l1"> 1</a> </pre> </div> <div style="font-family:monospace" class="parity1"> <pre><a class="linenr" href="#l2" id="l2"> 2</a> </pre> </div> </div> (Notice the missing </pre></div> now in place)
author Anton Shestakov <av6@dwimlabs.net>
date Wed, 22 Jul 2015 10:19:17 +0800
parents e3ee7ec85a15
children a1924bc6e267
line wrap: on
line source

#!/usr/bin/env python
#
# posplit - split messages in paragraphs on .po/.pot files
#
# license: MIT/X11/Expat
#

import re
import sys
import polib

def addentry(po, entry, cache):
    e = cache.get(entry.msgid)
    if e:
        e.occurrences.extend(entry.occurrences)
    else:
        po.append(entry)
        cache[entry.msgid] = entry

def mkentry(orig, delta, msgid, msgstr):
    entry = polib.POEntry()
    entry.merge(orig)
    entry.msgid = msgid or orig.msgid
    entry.msgstr = msgstr or orig.msgstr
    entry.occurrences = [(p, int(l) + delta) for (p, l) in orig.occurrences]
    return entry

if __name__ == "__main__":
    po = polib.pofile(sys.argv[1])

    cache = {}
    entries = po[:]
    po[:] = []
    findd = re.compile(r' *\.\. (\w+)::') # for finding directives
    for entry in entries:
        msgids = entry.msgid.split(u'\n\n')
        if entry.msgstr:
            msgstrs = entry.msgstr.split(u'\n\n')
        else:
            msgstrs = [u''] * len(msgids)

        if len(msgids) != len(msgstrs):
            # places the whole existing translation as a fuzzy
            # translation for each paragraph, to give the
            # translator a chance to recover part of the old
            # translation - erasing extra paragraphs is
            # probably better than retranslating all from start
            if 'fuzzy' not in entry.flags:
                entry.flags.append('fuzzy')
            msgstrs = [entry.msgstr] * len(msgids)

        delta = 0
        for msgid, msgstr in zip(msgids, msgstrs):
            if msgid and msgid != '::':
                newentry = mkentry(entry, delta, msgid, msgstr)
                mdirective = findd.match(msgid)
                if mdirective:
                    if not msgid[mdirective.end():].rstrip():
                        # only directive, nothing to translate here
                        continue
                    directive = mdirective.group(1)
                    if directive in ('container', 'include'):
                        if msgid.rstrip('\n').count('\n') == 0:
                            # only rst syntax, nothing to translate
                            continue
                        else:
                            # lines following directly, unexpected
                            print 'Warning: text follows line with directive' \
                                  ' %s' % directive
                    comment = 'do not translate: .. %s::' % directive
                    if not newentry.comment:
                        newentry.comment = comment
                    elif comment not in newentry.comment:
                        newentry.comment += '\n' + comment
                addentry(po, newentry, cache)
            delta += 2 + msgid.count('\n')
    po.save()