crecord: call prevsibling() and nextsibling() directly
The 3 classes for items used in crecord (uiheader, uihunk, uihunkline) all have
prevsibling() and nextsibling() methods. The two methods are used to get the
previous/next item of the same type of the same parent element as the current
one: when `a` is a uihunkline instance, a.nextsibling() returns the next line
in this hunk (or None, if `a` is the last line).
There are also two similar methods: previtem() and nextitem(). When called with
constrainlevel=True (the default) they simply returned the result of
prevsibling()/nextsibling(). Only when called with constrainlevel=False they
did something different: they returned previous/next item regardless of its
type (so if `a` is the last line in a hunk, a.nextitem(constrainlevel=False)
could return the next hunk or the next file -- something that is not a line).
Let's simplify this logic and make code call -sibling() methods when only
siblings are needed and -item() methods when any item would do, and then remove
the constrainlevel argument from previtem() and nextitem().
#!/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
delta += 2
continue
directive = mdirective.group(1)
if directive in ('container', 'include'):
if msgid.rstrip('\n').count('\n') == 0:
# only rst syntax, nothing to translate
delta += 2
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()