Dec 20, 2021 · Oct 25, 2022 · Oct 26, 2022 · Oct 14, 2023 · Aug 27, 2024 · Oct 28, 2022
diff --git a/scripts/format_differences.py b/scripts/format_differences.py
 import collections
 importos
 importglob

 importre
 importsys
 from pathlib import Path
 from pprint import pprint

 import polib  # fades

 PO_DIR = os.path.abspath(
    os.path.join(
        os.path.dirname(__file__),
        '..',
    ))



 DELIMITERS = ("``", "*")

 def has_delimiters(x):
    for d in DELIMITERS:
        if d in x:
            return True
    return False

 def main():
    files_with_differences = collections.defaultdict(list)

    for i, pofilename in enumerate(glob.glob(PO_DIR + '**/**/*.po')):
 from typing import List

 import polib

 _patterns = [
    ":c:func:`[^`]+`",
    ":c:type:`[^`]+`",
    ":c:macro:`[^`]+`",
    ":c:member:`[^`]+`",
    ":c:data:`[^`]+`",
    ":py:data:`[^`]+`",
    ":py:mod:`[^`]+`",
    ":func:`[^`]+`",
    ":mod:`[^`]+`",
    ":ref:`[^`]+`",
    ":class:`[^`]+`",
    ":pep:`[^`]+`",
    ":data:`[^`]+`",
    ":exc:`[^`]+`",
    ":term:`[^`]+`",
    ":meth:`[^`]+`",
    ":envvar:`[^`]+`",
    ":file:`[^`]+`",
    ":attr:`[^`]+`",
    ":const:`[^`]+`",
    ":issue:`[^`]+`",
    ":opcode:`[^`]+`",
    ":option:`[^`]+`",
    ":program:`[^`]+`",
    ":keyword:`[^`]+`",
    ":RFC:`[^`]+`",
    ":rfc:`[^`]+`",
    ":doc:`[^`]+`",
    "``[^`]+``",
    "`[^`]+`__",
    "`[^`]+`_",
    r"\*\*[^\*]+\*\*",  # bold text between **
    r"\*[^\*]+\*",  # italic text between *
 ]

 _exps = [re.compile(e) for e in _patterns]


 def get_sphinx_directives(s: str) -> List[str]:
    """
    Parameters:
        string containing the text to translate

    Returns:
        dictionary containing all the placeholder text as keys
        and the correct value.
    """

    output: List[str] = []
    for exp in _exps:
        matches = exp.findall(s)
        for match in matches:
            output.append(match)
            # remove the found pattern from the original string
            s = s.replace(match, "")
    return output

 def ind(level=0):
    return f"{' ' * 4 * level}"

 if __name__ == "__main__":
    PO_DIR = Path(__file__).resolve().parent.parent
    VENV_DIR = PO_DIR / "venv"

    if len(sys.argv) > 1:
        filename = sys.argv[1]
        files = []
        if filename:
            if Path(filename).is_dir():
                files = [i for i in PO_DIR.glob(f"{filename}/*.po") if not i.is_relative_to(VENV_DIR)]
            elif not Path(filename).is_file():
                print(f"File not found: '{filename}'")
                sys.exit(-1)
            else:
                files = [filename]
    else:
        files = [i for i in PO_DIR.glob("**/**/*.po") if not i.is_relative_to(VENV_DIR)]

    for pofilename in files:
        print(f"\n> Processing {pofilename}")
        po = polib.pofile(pofilename)
        if po.percent_translated() < 85:
            continue

        for entry in po:
            words = []
            wordsid = wordsstr = list()

            if has_delimiters(entry.msgid):
                wordsid = [word for word in entry.msgid.split() if has_delimiters(word)]

            if has_delimiters(entry.msgstr):
                wordsstr = [word for word in entry.msgstr.split() if has_delimiters(word)]

            if len(wordsid) != len(wordsstr):
                key = pofilename.replace(PO_DIR, '')
                files_with_differences[key].append({
                    'occurrences': entry.occurrences,
                    'words': {
                        'original': wordsid,
                        'translated': wordsstr,
                    },
                })
            directives_id = get_sphinx_directives(entry.msgid)
            directives_str = get_sphinx_directives(entry.msgstr)

    return files_with_differences
            # Check if any of them is not empty
            if directives_id or directives_str:

                # Check if the directives are the same
                for ori, dst in zip(directives_id, directives_str):
                    if ori == dst:
                        continue

 pprint(main())
                    if ori != dst:
                        occs = [f"{ind(2)}{t[0]}:{t[1]}" for t in entry.occurrences]
                        print(f"\n{ind(1)}{pofilename}:{entry.linenum}")
                        print(f"\n".join(occs))
                        print(f"{ind(3)}{ori}")
                        print(f"{ind(3)}{dst}")
Original file line number	Diff line number	Diff line change
		@@ -1,56 +1,111 @@
		import collections
		importos
		importglob

		importre
		importsys
		from pathlib import Path
		from pprint import pprint

		import polib # fades

		PO_DIR = os.path.abspath(
		os.path.join(
		os.path.dirname(__file__),
		'..',
		))



		DELIMITERS = ("``", "*")

		def has_delimiters(x):
		for d in DELIMITERS:
		if d in x:
		return True
		return False

		def main():
		files_with_differences = collections.defaultdict(list)

		for i, pofilename in enumerate(glob.glob(PO_DIR + '//*.po')):
		from typing import List

		import polib

		_patterns = [
		":c:func:`[^`]+`",
		":c:type:`[^`]+`",
		":c:macro:`[^`]+`",
		":c:member:`[^`]+`",
		":c:data:`[^`]+`",
		":py:data:`[^`]+`",
		":py:mod:`[^`]+`",
		":func:`[^`]+`",
		":mod:`[^`]+`",
Comment on lines +11 to +19 Copy link Collaborator humitosOct 28, 2022• edited Loading Choose a reason for hiding this comment The reason will be displayed to describe this comment to others.Learn more. Yo creo que esto se podría escribir de una forma más genérica usando más regex: : +[a-z]+:`[a-z]+` Esa por ejemplo, encuentra "uno o más espacios luego del primer`:`" :[a-z]+: +`[a-z]+` Encuentra un "un espacio luego del segundo`:`" De esta forma, solo tenemos que escribir "un par de regex" para encontrar los espacios en todas las posibles variaciones de todos los roles de Sphinx. ¿Qué te parece? Lo mismo se puede hacer para cursiva y negrita. Copy link CollaboratorAuthor cmaureirAug 27, 2024 Choose a reason for hiding this comment The reason will be displayed to describe this comment to others.Learn more. me parece super :D
		":ref:`[^`]+`",
		":class:`[^`]+`",
		":pep:`[^`]+`",
		":data:`[^`]+`",
		":exc:`[^`]+`",
		":term:`[^`]+`",
		":meth:`[^`]+`",
		":envvar:`[^`]+`",
		":file:`[^`]+`",
		":attr:`[^`]+`",
		":const:`[^`]+`",
		":issue:`[^`]+`",
		":opcode:`[^`]+`",
		":option:`[^`]+`",
		":program:`[^`]+`",
		":keyword:`[^`]+`",
		":RFC:`[^`]+`",
		":rfc:`[^`]+`",
		":doc:`[^`]+`",
		"``[^`]+``",
		"`[^`]+`__",
		"`[^`]+`_",
		r"\\[^\]+\\", # bold text between *
		r"\[^\]+\", # italic text between
		]

		_exps = [re.compile(e) for e in _patterns]


		def get_sphinx_directives(s: str) -> List[str]:
		"""
		Parameters:
		string containing the text to translate

		Returns:
		dictionary containing all the placeholder text as keys
		and the correct value.
		"""

		output: List[str] = []
		for exp in _exps:
		matches = exp.findall(s)
		for match in matches:
		output.append(match)
		# remove the found pattern from the original string
		s = s.replace(match, "")
		return output

		def ind(level=0):
		return f"{' ' * 4 * level}"

		if __name__ == "__main__":
		PO_DIR = Path(__file__).resolve().parent.parent
		VENV_DIR = PO_DIR / "venv"

		if len(sys.argv) > 1:
		filename = sys.argv[1]
		files = []
		if filename:
		if Path(filename).is_dir():
		files = [i for i in PO_DIR.glob(f"{filename}/*.po") if not i.is_relative_to(VENV_DIR)]
		elif not Path(filename).is_file():
		print(f"File not found: '{filename}'")
		sys.exit(-1)
		else:
		files = [filename]
		else:
		files = [i for i in PO_DIR.glob("//*.po") if not i.is_relative_to(VENV_DIR)]

		for pofilename in files:
		print(f"\n> Processing {pofilename}")
		po = polib.pofile(pofilename)
		if po.percent_translated() < 85:
		continue

		for entry in po:
		words = []
		wordsid = wordsstr = list()

		if has_delimiters(entry.msgid):
		wordsid = [word for word in entry.msgid.split() if has_delimiters(word)]

		if has_delimiters(entry.msgstr):
		wordsstr = [word for word in entry.msgstr.split() if has_delimiters(word)]

		if len(wordsid) != len(wordsstr):
		key = pofilename.replace(PO_DIR, '')
		files_with_differences[key].append({
		'occurrences': entry.occurrences,
		'words': {
		'original': wordsid,
		'translated': wordsstr,
		},
		})
		directives_id = get_sphinx_directives(entry.msgid)
		directives_str = get_sphinx_directives(entry.msgstr)

		return files_with_differences
		# Check if any of them is not empty
		if directives_id or directives_str:

		# Check if the directives are the same
		for ori, dst in zip(directives_id, directives_str):
		if ori == dst:
		continue

		pprint(main())
		if ori != dst:
		occs = [f"{ind(2)}{t[0]}:{t[1]}" for t in entry.occurrences]
		print(f"\n{ind(1)}{pofilename}:{entry.linenum}")
		print(f"\n".join(occs))
		print(f"{ind(3)}{ori}")
		print(f"{ind(3)}{dst}")