view i18n/posplit @ 49568:da48f170d203

rust-status: query fs traversal metadata lazily

Currently, any time the status algorithm needs to read a directory from the
filesystem (because the stat-only optimization is not available), it also
stats each directory entry eagerly.

Stat'ing the entries is only needed in a few cases (like when checking
the mtime of a directory for caching): this patch creates a wrapper struct
`DirEntry` that only stats the directory entry it represents when needed.

Excerpt of an `strace` before this change on Mozilla Central:

```
openat(AT_FDCWD, ".", O_RDONLY|O_NONBLOCK|O_CLOEXEC|O_DIRECTORY) = 3
newfstatat(3, "", {st_mode=S_IFDIR|0755, st_size=3540, ...}, AT_EMPTY_PATH) = 0
getdents64(3, 0x55dc970bd440 /* 139 entries */, 32768) = 5072
statx(3, ".hg", AT_STATX_SYNC_AS_STAT|AT_SYMLINK_NOFOLLOW, STATX_ALL, {stx_mask=STATX_ALL|STATX_MNT_ID, stx_attributes=0, stx_mode=S_IFDIR|0755, stx_size=772, ...}) = 0

[... 135 other successful `statx` calls]

getdents64(3, 0x55dc970bd440 /* 0 entries */, 32768) = 0
close(3)                                = 0
```

After this change:

```
openat(AT_FDCWD, ".", O_RDONLY|O_NONBLOCK|O_CLOEXEC|O_DIRECTORY) = 3
newfstatat(3, "", {st_mode=S_IFDIR|0755, st_size=3540, ...}, AT_EMPTY_PATH) = 0
getdents64(3, 0x561567c10190 /* 139 entries */, 32768) = 5072
getdents64(3, 0x561567c10190 /* 0 entries */, 32768) = 0
close(3)                                = 0
```

#!/usr/bin/env python3
#
# posplit - split messages in paragraphs on .po/.pot files
#
# license: MIT/X11/Expat
#


import polib
import re
import sys


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

        # merge comments from entry
        for comment in entry.comment.split('\n'):
            if comment and comment not in e.comment:
                if not e.comment:
                    e.comment = comment
                else:
                    e.comment += '\n' + comment
    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()