Uh oh!
There was an error while loading.Please reload this page.
- Notifications
You must be signed in to change notification settings - Fork43
Add a script for machine-translation#76
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to ourterms of service andprivacy statement. We’ll occasionally send you account related emails.
Already on GitHub?Sign in to your account
Merged
Uh oh!
There was an error while loading.Please reload this page.
Merged
Changes fromall commits
Commits
File filter
Filter by extension
Conversations
Failed to load comments.
Loading
Uh oh!
There was an error while loading.Please reload this page.
Jump to
Jump to file
Failed to load files.
Loading
Uh oh!
There was an error while loading.Please reload this page.
Diff view
Diff view
There are no files selected for viewing
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -2,3 +2,4 @@ poutils | ||
| tqdm | ||
| pre-commit | ||
| polib | ||
| deep_translator | ||
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,148 @@ | ||
| import os | ||
| import re | ||
| import sys | ||
| import polib | ||
| from deep_translator import DeeplTranslator, GoogleTranslator | ||
| from typing import Dict, Tuple | ||
| from argparse import ArgumentParser | ||
| parser = ArgumentParser() | ||
| parser.add_argument("filename", help="File to translate") | ||
| parser.add_argument("-t", "--translator", choices=["google", "deepl"], default="deepl", help="Translator to use") | ||
| parser.add_argument( | ||
| "-a", | ||
| "--api-key", | ||
| required="deepl" in list(map(lambda x: x.casefold(), sys.argv)), | ||
| help="API key for DeepL (required if using DeepL)", | ||
| ) | ||
| parser.add_argument("-v", "--verbose", action="store_true", help="Verbose mode") | ||
| parser.add_argument("-d", "--debug", action="store_true", help="Debug mode") | ||
| parser.add_argument("-s", "--skip-translated-entries", choices=[True, False], default=True, help="Skip already translated entries") | ||
| args = parser.parse_args() | ||
| VERBOSE = args.verbose | ||
| DEBUG = args.debug | ||
| SKIP_TRANSLATED_ENTRIES = args.skip_translated_entries | ||
| _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:`[^`]+`", | ||
| ":source:`[^`]+`", | ||
| ":manpage:`[^`]+`", | ||
| ":mimetype:`[^`]+`", | ||
| ":sup:`[^`]+`", | ||
| ":kbd:`[^`]+`", | ||
| ":const:`[^`]+`", | ||
| "``[^`]+``", | ||
| "`[^`]+`__", | ||
| "`[^`]+`_", | ||
| r"\*\*[^\*]+\*\*", # bold text between ** | ||
| r"\*[^\*]+\*", # italic text between * | ||
| ] | ||
| _exps = [re.compile(e) for e in _patterns] | ||
| def protect_sphinx_directives(s: str) -> Tuple[dict, str]: | ||
| """ | ||
| Parameters: | ||
| string containing the text to translate | ||
| Returns: | ||
| dictionary containing all the placeholder text as keys | ||
| and the correct value. | ||
| """ | ||
| d: Dict[str, str] = {} | ||
| for index, exp in enumerate(_exps): | ||
| matches = exp.findall(s) | ||
| if DEBUG: | ||
| print(exp, matches) | ||
| for match in matches: | ||
| ph = f"XASDF{str(index).zfill(2)}" | ||
| s = s.replace(match, ph) | ||
| if ph in d and VERBOSE: | ||
| print(f"Error: {ph} is already in the dictionary") | ||
| print("new", match) | ||
| print("old", d[ph]) | ||
| d[ph] = match | ||
| return d, s | ||
| def undo_sphinx_directives_protection(placeholders: dict, translated_text: str) -> str: | ||
| for ph, value in placeholders.items(): | ||
| translated_text = translated_text.replace(ph, value) | ||
| if DEBUG: | ||
| print(ph, value) | ||
| print(translated_text) | ||
| return translated_text | ||
| if __name__ == "__main__": | ||
| filename = args.filename | ||
| if not os.path.isfile(filename): | ||
| print(f"File not found: '{filename}'") | ||
| sys.exit(-1) | ||
| po = polib.pofile(filename) | ||
| if args.translator.lower() == "google": | ||
| translator = GoogleTranslator(source="en", target="tr") | ||
| elif args.translator.lower() == "deepl": | ||
| translator = DeeplTranslator(api_key=args.api_key, source="en", target="tr", use_free_api=True) | ||
| else: | ||
| raise ValueError("Invalid translator") | ||
| for entry in po: | ||
| # If the entry has already a translation, skip. | ||
| if SKIP_TRANSLATED_ENTRIES and entry.msgstr: | ||
| continue | ||
| print("\nEN |", entry.msgid) | ||
| placeholders, temp_text = protect_sphinx_directives(entry.msgid) | ||
| if VERBOSE: | ||
| print(temp_text) | ||
| print(placeholders) | ||
| # Translate the temporary text without sphinx statements | ||
| translated_text = translator.translate(temp_text) | ||
| # Recover sphinx statements | ||
| real_text = undo_sphinx_directives_protection(placeholders, translated_text) | ||
| print("TR |", real_text) | ||
| # Replace the po file translated entry | ||
| entry.msgstr = real_text | ||
| # Add fuzzy flag so a real-human can review later | ||
| entry.flags.append("fuzzy") | ||
| # Save the file after all the entries are translated | ||
| po.save() |
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.