feat(i18n): skip do-not-translate entries in backfill_po

The backfill only checked for an empty msgstr, so it filled entries a human
translator had deliberately left blank — e.g. the ru catalog's "# Не переводить"
(do-not-translate) markers on literal tokens. This translated strings that must
stay identical to the source: icon names (`bolt` -> the  Explore control
icon), d3 enum values (`step-after`/`step-before`), API field names
(`error_message`), SQL keywords, code constants, and example placeholders.

Add `_is_do_not_translate`, consulted when collecting untranslated entries. An
entry is skipped if its msgid is in the curated `DO_NOT_TRANSLATE` set (seeded
from the ru translator's markers; language-independent) or if it carries an
explicit do-not-translate translator comment in any catalog. Skipped entries are
reported and left untranslated (source-token fallback).

Adds unit tests for the curated set, translator-comment honoring (incl. the
Cyrillic marker), and the normal-entry pass-through.

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
This commit is contained in:
Amin Ghadersohi
2026-07-01 18:24:21 -07:00
parent 8be255de40
commit fb8af9caec
3 changed files with 95 additions and 0 deletions

View File

@@ -436,3 +436,29 @@ def test_resilient_translate_propagates_runtime_error(
monkeypatch.setattr(backfill_po, "translate_batch", _boom)
with pytest.raises(RuntimeError):
backfill_po._resilient_translate("m", "fr", [_qitem("Alpha")], {})
# --- _is_do_not_translate: never machine-fill literal tokens -------------------
def test_is_do_not_translate_curated_msgid() -> None:
"""A msgid in the curated DO_NOT_TRANSLATE set is protected (icon names,
enum values, SQL keywords, API field names, placeholders)."""
for msgid in ("bolt", "error_message", "step-after", "GROUP BY"):
assert backfill_po._is_do_not_translate(polib.POEntry(msgid=msgid, msgstr=""))
def test_is_do_not_translate_honors_translator_comment() -> None:
"""An explicit do-not-translate translator comment is honored, in any
language (e.g. the ru catalog's Cyrillic marker) and phrasing."""
for comment in ("Не переводить", "do not translate", "DO-NOT-TRANSLATE"):
entry = polib.POEntry(msgid="Some label", msgstr="")
entry.tcomment = comment
assert backfill_po._is_do_not_translate(entry)
def test_is_do_not_translate_allows_normal_entry() -> None:
"""An ordinary translatable string is not flagged."""
entry = polib.POEntry(msgid="Save dashboard", msgstr="")
entry.tcomment = "Machine-translated via backfill_po.py (claude-x) [no refs]"
assert not backfill_po._is_do_not_translate(entry)