revlog: flag processor
Add the ability for revlog objects to process revision flags and apply
registered transforms on read/write operations.
This patch introduces:
- the 'revlog._processflags()' method that looks at revision flags and applies
flag processors registered on them. Due to the need to handle non-commutative
operations, flag transforms are applied in stable order but the order in which
the transforms are applied is reversed between read and write operations.
- the 'addflagprocessor()' method allowing to register processors on flags.
Flag processors are defined as a 3-tuple of (read, write, raw) functions to be
applied depending on the operation being performed.
- an update on 'revlog.addrevision()' behavior. The current flagprocessor design
relies on extensions to wrap around 'addrevision()' to set flags on revision
data, and on the flagprocessor to perform the actual transformation of its
contents. In the lfs case, this means we need to process flags before we meet
the 2GB size check, leading to performing some operations before it happens:
- if flags are set on the revision data, we assume some extensions might be
modifying the contents using the flag processor next, and we compute the
node for the original revision data (still allowing extension to override
the node by wrapping around 'addrevision()').
- we then invoke the flag processor to apply registered transforms (in lfs's
case, drastically reducing the size of large blobs).
- finally, we proceed with the 2GB size check.
Note: In the case a cachedelta is passed to 'addrevision()' and we detect the
flag processor modified the revision data, we chose to trust the flag processor
and drop the cachedelta.
#!/usr/bin/env python
#
# posplit - split messages in paragraphs on .po/.pot files
#
# license: MIT/X11/Expat
#
from __future__ import absolute_import, print_function
import polib
import re
import sys
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()