scripts/import_translation.py: import human-made whole-article translations

Decomposes a pasted full translation with the same align_article validation as article-mode LLM results and stores proper Data.trans fragments, instead of the translation editor's one monolithic patch that silently goes stale hunk by hunk. Runs against the kanta database directly, with the server stopped. Verified on a scratch copy of the localhost db: swe/app fi (qwen3.8 trial output) imports 43/43 blocks and serves through the hybrid; the degenerate qwen3-next output is rejected on anchor validation.
2026-09-20 23:23:37 +00:00
parent f1324e8387
commit 277a75ae23
1 changed files with 80 additions and 0 deletions
@@ -0,0 +1,80 @@
+#!/usr/bin/env python3
+"""Import a human-made whole-article translation into the fragment store.
+
+A full translation produced outside the pipeline (e.g. by ChatGPT, pasted
+into a file) is decomposed with the same alignment and validation as an
+article-mode LLM result (pagerite.translate.align_article): blocks are
+stored as proper Data.trans fragments, so later source edits invalidate
+and re-translate per chunk instead of letting one monolithic user patch
+silently go stale hunk by hunk.
+
+Run with the Pagerite server STOPPED (the script opens the same kanta
+database). Blocks that fail validation stay untranslated — the translator
+service picks them up as scoped jobs on the next run.
+
+Usage:
+    uv run python scripts/import_translation.py PATH LANG FILE.md [--db DB]
+
+PATH is the page path without leading slash ("" = front page), LANG the
+target language base tag (e.g. fi), FILE.md the translated Markdown.
+"""
+
+import argparse
+import asyncio
+import sys
+
+from kanta import Kanta
+
+from pagerite.data import Data, node_markdown, resolve
+from pagerite.i18n import base_tag, primary_lang
+from pagerite.translate import TransResult, align_article, store_results
+
+
+async def main() -> None:
+    p = argparse.ArgumentParser(
+        description=__doc__, formatter_class=argparse.RawDescriptionHelpFormatter
+    )
+    p.add_argument("path", help="page path without leading slash ('' = front page)")
+    p.add_argument("lang", help="target language base tag (e.g. fi)")
+    p.add_argument("file", help="Markdown file holding the translation")
+    p.add_argument(
+        "--db",
+        default="localhost/content.kantadb",
+        help="kanta database (default: localhost/content.kantadb)",
+    )
+    args = p.parse_args()
+    path = args.path.strip("/")
+    lang = base_tag(args.lang)
+    translated = open(args.file).read()
+
+    data = Data()
+    kanta = Kanta(args.db, data, migrations="pagerite.migrations")
+    await kanta.open(create=False, log=False)
+    try:
+        chain = resolve(data.menu, path)
+        node = chain[-1] if chain else None
+        if node is None or node.chunks is None:
+            sys.exit(f"no such page: {args.path!r}")
+        if primary_lang(data.menu, path) == lang:
+            sys.exit(f"{args.path!r} is already in {lang} (its primary language)")
+        pairs = align_article(node_markdown(data, node) or "", translated)
+        if pairs is None:
+            sys.exit(
+                "rejected: an anchor block (code fence, raw HTML, container fence) "
+                "is missing or altered — the translation does not preserve the "
+                "page structure"
+            )
+        if not pairs:
+            sys.exit("nothing to import: no blocks aligned")
+        with kanta.transaction(f"translate:{lang}:import", user="import"):
+            pages = store_results(
+                data, lang, [TransResult(key=k, text=t) for k, t in pairs]
+            )
+        print(f"imported {len(pairs)} blocks for [{lang}]; pages: {', '.join(pages)}")
+        print("untranslated blocks stay pending for the translator service")
+    finally:
+        await kanta.close()
+
+
+if __name__ == "__main__":
+    asyncio.run(main())