hainenber commented on code in PR #41651:
URL: https://github.com/apache/superset/pull/41651#discussion_r3525364767
##########
scripts/translations/backfill_po.py:
##########
@@ -152,6 +152,61 @@ def _is_missing(entry: polib.POEntry) -> bool:
return not entry.msgstr
+# Canonical registry of msgids that must never be machine-translated: literal
+# tokens compared against source (SQL keywords, confirmation words), enum
values
+# (d3 interpolation modes), icon names (e.g. "bolt" -> the ⚡ Explore control
+# icon), API field names, code constants, and example placeholders. Translating
+# them can break icon lookups, enum matching, or API contracts, or is simply
+# meaningless (proper nouns, example values). apply_do_not_translate.py stamps
+# these msgids in messages.pot with a `#. MACHINE_READ-DO_NOT_TRANSLATE`
+# extracted comment that propagates to every catalog on `pybabel update`.
+DO_NOT_TRANSLATE_REGISTRY: Path = TRANSLATIONS_DIR / "do-not-translate.txt"
+
+
+def _load_do_not_translate(path: Path = DO_NOT_TRANSLATE_REGISTRY) ->
frozenset[str]:
+ """Load the do-not-translate msgids (skips comment/blank lines).
+
+ Lines are stripped before the blank/comment checks, matching the parsing in
+ apply_do_not_translate.py, so trailing whitespace or an indented comment
+ never yields a msgid that fails to match a catalog entry.
+ """
+ if not path.exists():
+ return frozenset()
+ return frozenset(
+ stripped
+ for line in path.read_text(encoding="utf-8").splitlines()
+ if (stripped := line.strip()) and not stripped.startswith("#")
+ )
+
+
+DO_NOT_TRANSLATE: frozenset[str] = _load_do_not_translate()
+
+# An explicit do-not-translate marker on an entry, matched in either the
+# extracted comment (`#. MACHINE_READ-DO_NOT_TRANSLATE`, the standard
propagated
+# from the .pot) or a translator comment (e.g. the ru catalog's legacy
+# "# Не переводить"). Honored so a human's deliberate decision is never
+# overridden even if a msgid is missing from the registry.
+_DO_NOT_TRANSLATE_COMMENT: re.Pattern[str] = re.compile(
+ r"machine_read-do_not_translate|не\s+переводить"
Review Comment:
Can we switch the legacy Russian translator comment to use the standard
marker? Or it should be on a follow up PR?
--
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
To unsubscribe, e-mail: [email protected]
For queries about this service, please contact Infrastructure at:
[email protected]
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
