recon/lib/wiki_rewrite_api_test.py

73 lines
2.6 KiB
Python
Raw Normal View History

recon: add /api/wiki-rewrite endpoint (extraction #5 prep, additive) (#9) Per-tag HTTP wrapper over wiki_rewrite.rewrite_wiki_link so the (future) navi-places service can rewrite OSM wiki tags to local Kiwix URLs over HTTP instead of importing recon's wiki_rewrite module (which talks to Kiwix on localhost:8430 and the wiki_cache table in /opt/recon/data/place_cache.db). Companion to PR #8 (/api/wiki-enrich) — Matt picked option B (HTTP-couple the Kiwix offline-wiki rewriting too, since it matters in prod). GET /api/wiki-rewrite?tag=<wikipedia|wikidata|wikivoyage|appropedia>&value=<raw> -> 200 {url, status} where status is "local" | "public" | "original" -> 400 on missing value or unknown tag -> no 404 (unclassifiable value echoes back with status "original", mirroring rewrite_wiki_link) Public (no auth), like /api/place/* and /api/wiki-enrich. Changes (additive only): - lib/wiki_rewrite_api.py: new wiki_rewrite_bp blueprint. Thin route directly over the existing rewrite_wiki_link(tag, value) — no extraction needed (it's already a clean standalone function, unlike wiki-enrich's lookup). - lib/api.py: register the blueprint (one block). - lib/wiki_rewrite_api_test.py: 5 tests (local Kiwix hit, public fallback, unclassifiable -> original, missing value -> 400, unknown tag -> 400), stubbing check_kiwix_has_article (no Kiwix/DB), plain-assert + __main__ runner. Verified green against recon's venv (flask 3.1.2). Does NOT touch place_detail's in-process _enrich_wiki_links — that gets removed in a later PR once navi-places is live (same as PR #8). wiki_cache stays in recon's own place_cache.db post-cutover (harmless positive-cache duplication). Co-authored-by: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
2026-05-22 14:08:18 -06:00
"""Tests for the /api/wiki-rewrite endpoint (extraction #5 prep).
Plain-assert style (recon's venv has no pytest). Builds a minimal Flask app
with only wiki_rewrite_bp registered. Mocks `wiki_rewrite.check_kiwix_has_article`
to control the local-Kiwix-hit vs. fallback paths without touching Kiwix or the
wiki_cache DB. classify_wiki_link (pure regex) runs for real. Run with pytest,
or directly: python -m lib.wiki_rewrite_api_test
"""
from flask import Flask
from lib import wiki_rewrite
from lib.wiki_rewrite_api import wiki_rewrite_bp
def _client(kiwix_hit):
"""kiwix_hit: (found_bool, url) returned by a stubbed check_kiwix_has_article."""
wiki_rewrite.check_kiwix_has_article = lambda source_type, article_id: kiwix_hit
app = Flask(__name__)
app.register_blueprint(wiki_rewrite_bp)
return app.test_client()
def test_local_kiwix_hit():
url = "https://wiki.echo6.co/content/wikipedia/Filer,_Idaho"
c = _client((True, url))
resp = c.get("/api/wiki-rewrite?tag=wikipedia&value=Filer, Idaho")
assert resp.status_code == 200, resp.status_code
d = resp.get_json()
assert d["status"] == "local"
assert d["url"] == url
def test_public_fallback_when_not_in_kiwix():
c = _client((False, None)) # not in Kiwix -> canonical public URL
resp = c.get("/api/wiki-rewrite?tag=wikipedia&value=Filer")
assert resp.status_code == 200, resp.status_code
d = resp.get_json()
assert d["status"] == "public"
assert d["url"] == "https://en.wikipedia.org/wiki/Filer"
def test_unclassifiable_returns_original():
# 'wikidata' requires a Q-id; a non-matching value -> classify None -> original.
c = _client((False, None))
resp = c.get("/api/wiki-rewrite?tag=wikidata&value=not-a-qid")
assert resp.status_code == 200, resp.status_code
d = resp.get_json()
assert d["status"] == "original"
assert d["url"] == "not-a-qid"
def test_missing_value_400():
c = _client((False, None))
assert c.get("/api/wiki-rewrite?tag=wikipedia").status_code == 400
def test_unknown_tag_400():
c = _client((False, None))
assert c.get("/api/wiki-rewrite?tag=facebook&value=x").status_code == 400
if __name__ == "__main__":
failures = 0
for _name, _fn in sorted(globals().items()):
if _name.startswith("test_") and callable(_fn):
try:
_fn()
print(f"PASS {_name}")
except Exception as exc: # noqa: BLE001
failures += 1
print(f"FAIL {_name}: {exc!r}")
print("OK" if failures == 0 else f"{failures} FAILED")
raise SystemExit(1 if failures else 0)