view i18n/hggettext @ 22860:1dd178277cf5

revset-_descendant: rework the whole sorting and combining logic

We use the & operator to combine with subset (since this is more likely to be
optimised than filter) and we enforce the sorting of the result. Without this
enforced sorting, we may result in a different iteration order than the set
_descendent was computed from.

This reverts a bad `test-glog.t` change from 69402eb72115.

Another side effect is that `test-mq.t` shows `qparent::` including `-1` if
`qparent is -1`. This sound like a positive change.

This has good and bad impacts on the benchmarks, here is a good ones:

revset: 0::
before) wall 0.045489 comb 0.040000 user 0.040000 sys 0.000000 (best of 100)
after)  wall 0.034330 comb 0.030000 user 0.030000 sys 0.000000 (best of 100)

revset: roots((0::) - (0::tip))
before)  wall 0.134090 comb 0.140000 user 0.140000 sys 0.000000 (best of 63)
after) wall 0.128346 comb 0.130000 user 0.130000 sys 0.000000 (best of 69)

revset: ::p1(p1(tip))::
before) wall 0.143892 comb 0.140000 user 0.140000 sys 0.000000 (best of 55)
after)  wall 0.124502 comb 0.130000 user 0.130000 sys 0.000000 (best of 65)

revset: roots((0:tip)::)
before) wall 0.204966 comb 0.200000 user 0.200000 sys 0.000000 (best of 43)
after) wall 0.184455 comb 0.180000 user 0.180000 sys 0.000000 (best of 47)

Here is a bad one:

revset: (20000::) - (20000)
before) wall 0.009592 comb 0.010000 user 0.010000 sys 0.000000 (best of 222)
after)  wall 0.029837 comb 0.030000 user 0.030000 sys 0.000000 (best of 100)

#!/usr/bin/env python
#
# hggettext - carefully extract docstrings for Mercurial
#
# Copyright 2009 Matt Mackall <[e-mail]> and others
#
# This software may be used and distributed according to the terms of the
# GNU General Public License version 2 or any later version.

# The normalize function is taken from pygettext which is distributed
# with Python under the Python License, which is GPL compatible.

"""Extract docstrings from Mercurial commands.

Compared to pygettext, this script knows about the cmdtable and table
dictionaries used by Mercurial, and will only extract docstrings from
functions mentioned therein.

Use xgettext like normal to extract strings marked as translatable and
join the message cataloges to get the final catalog.
"""

import os, sys, inspect


def escape(s):
    # The order is important, the backslash must be escaped first
    # since the other replacements introduce new backslashes
    # themselves.
    s = s.replace('\\', '\\\\')
    s = s.replace('\n', '\\n')
    s = s.replace('\r', '\\r')
    s = s.replace('\t', '\\t')
    s = s.replace('"', '\\"')
    return s


def normalize(s):
    # This converts the various Python string types into a format that
    # is appropriate for .po files, namely much closer to C style.
    lines = s.split('\n')
    if len(lines) == 1:
        s = '"' + escape(s) + '"'
    else:
        if not lines[-1]:
            del lines[-1]
            lines[-1] = lines[-1] + '\n'
        lines = map(escape, lines)
        lineterm = '\\n"\n"'
        s = '""\n"' + lineterm.join(lines) + '"'
    return s


def poentry(path, lineno, s):
    return ('#: %s:%d\n' % (path, lineno) +
            'msgid %s\n' % normalize(s) +
            'msgstr ""\n')


def offset(src, doc, name, default):
    """Compute offset or issue a warning on stdout."""
    # Backslashes in doc appear doubled in src.
    end = src.find(doc.replace('\\', '\\\\'))
    if end == -1:
        # This can happen if the docstring contains unnecessary escape
        # sequences such as \" in a triple-quoted string. The problem
        # is that \" is turned into " and so doc wont appear in src.
        sys.stderr.write("warning: unknown offset in %s, assuming %d lines\n"
                         % (name, default))
        return default
    else:
        return src.count('\n', 0, end)


def importpath(path):
    """Import a path like foo/bar/baz.py and return the baz module."""
    if path.endswith('.py'):
        path = path[:-3]
    if path.endswith('/__init__'):
        path = path[:-9]
    path = path.replace('/', '.')
    mod = __import__(path)
    for comp in path.split('.')[1:]:
        mod = getattr(mod, comp)
    return mod


def docstrings(path):
    """Extract docstrings from path.

    This respects the Mercurial cmdtable/table convention and will
    only extract docstrings from functions mentioned in these tables.
    """
    mod = importpath(path)
    if mod.__doc__:
        src = open(path).read()
        lineno = 1 + offset(src, mod.__doc__, path, 7)
        print poentry(path, lineno, mod.__doc__)

    functions = list(getattr(mod, 'i18nfunctions', []))
    functions = [(f, True) for f in functions]

    cmdtable = getattr(mod, 'cmdtable', {})
    if not cmdtable:
        # Maybe we are processing mercurial.commands?
        cmdtable = getattr(mod, 'table', {})
    functions.extend((c[0], False) for c in cmdtable.itervalues())

    for func, rstrip in functions:
        if func.__doc__:
            src = inspect.getsource(func)
            name = "%s.%s" % (path, func.__name__)
            lineno = func.func_code.co_firstlineno
            doc = func.__doc__
            if rstrip:
                doc = doc.rstrip()
            lineno += offset(src, doc, name, 1)
            print poentry(path, lineno, doc)


def rawtext(path):
    src = open(path).read()
    print poentry(path, 1, src)


if __name__ == "__main__":
    # It is very important that we import the Mercurial modules from
    # the source tree where hggettext is executed. Otherwise we might
    # accidentally import and extract strings from a Mercurial
    # installation mentioned in PYTHONPATH.
    sys.path.insert(0, os.getcwd())
    from mercurial import demandimport; demandimport.enable()
    for path in sys.argv[1:]:
        if path.endswith('.txt'):
            rawtext(path)
        else:
            docstrings(path)