bibclean: slugs, and whether the one a record has still names it

parity/oracle/slug.py

@@ -0,0 +1,50 @@
+"""Judge slugs the way the Python pipeline judges them.
+
+Reads one `{"slug", "author", "title", "id"}` object per line and writes what
+the slug module makes of each.
+
+    CATENA_PARITY_PYTHONPATH=/path/to/book-pipeline/src \
+        python3 oracle/slug.py < cases/slug/records.ndjson
+"""
+
+import json
+import os
+import sys
+
+for path in os.environ.get("CATENA_PARITY_PYTHONPATH", "").split(os.pathsep):
+    if path:
+        sys.path.insert(0, path)
+
+from slugify import slugify  # noqa: E402
+
+from book_pipeline import slugs  # noqa: E402
+
+
+def main() -> int:
+    out = sys.stdout
+    for line in sys.stdin.buffer.read().decode("utf-8").split("\n"):
+        if not line.strip():
+            continue
+        record = json.loads(line)
+        author, title, book_id = record.get("author"), record.get("title"), record["id"]
+        proposal = slugs.evaluate("x", record["slug"], author, title, book_id)
+        out.write(
+            json.dumps(
+                {
+                    "slugify": slugify(title or ""),
+                    "slug_for": slugs.slug_for(author, title, book_id),
+                    "lead_author": slugs._lead_author(author),
+                    "tier": proposal.tier if proposal else None,
+                    "proposed": proposal.proposed_slug if proposal else None,
+                    "reasons": proposal.reasons if proposal else [],
+                },
+                ensure_ascii=False,
+                sort_keys=True,
+            )
+            + "\n"
+        )
+    return 0
+
+
+if __name__ == "__main__":
+    raise SystemExit(main())