feat: add search relevance review lab
This commit is contained in:
@@ -12,6 +12,7 @@ from pathlib import Path
|
||||
|
||||
from search.minjust_opensearch import APP_VERSION, request_json
|
||||
from search.catalog import CATALOGS, labels
|
||||
from search.reviews import ReviewSnapshots, ReviewStore
|
||||
|
||||
|
||||
API_VERSION = "v1"
|
||||
@@ -75,6 +76,9 @@ def openapi() -> dict:
|
||||
{"name": "sort", "in": "query", "schema": {"type": "string", "enum": ["relevance", "date"]}},
|
||||
]}},
|
||||
"/search/filters": {"get": {"responses": responses}},
|
||||
"/search-reviews": {"post": {"responses": {"201": {"description": "Review saved"}, "400": {"description": "Invalid review"}}}},
|
||||
"/search-reviews/export": {"get": {"responses": responses}},
|
||||
"/review": {"get": {"responses": {"200": {"description": "Review interface"}}}},
|
||||
"/documents/{code}": {"get": {"responses": responses, "parameters": [{"name": "code", "in": "path", "required": True, "schema": {"type": "string", "pattern": "^[0-9]+$"}}]}},
|
||||
"/documents/{code}/editions": {"get": {"responses": responses, "parameters": [{"name": "code", "in": "path", "required": True, "schema": {"type": "string", "pattern": "^[0-9]+$"}}]}},
|
||||
"/documents/{code}/editions/{edition}": {"get": {"responses": responses, "parameters": [{"name": "code", "in": "path", "required": True, "schema": {"type": "string", "pattern": "^[0-9]+$"}}, {"name": "edition", "in": "path", "required": True, "schema": {"type": "string", "pattern": "^[0-9]+$"}}]}},
|
||||
@@ -83,10 +87,12 @@ def openapi() -> dict:
|
||||
|
||||
|
||||
class Api:
|
||||
def __init__(self, base_url: str, index: str, data_root: Path):
|
||||
def __init__(self, base_url: str, index: str, data_root: Path, reviews_db: Path | str = ":memory:", review_secret: bytes | None = None):
|
||||
self.base_url = base_url.rstrip("/")
|
||||
self.index = index
|
||||
self.data_root = data_root
|
||||
self.review_store = ReviewStore(reviews_db)
|
||||
self.review_snapshots = ReviewSnapshots(review_secret)
|
||||
|
||||
def search_url(self, suffix: str) -> str:
|
||||
return f"{self.base_url}/{urllib.parse.quote(self.index, safe='')}/{suffix}"
|
||||
@@ -142,7 +148,9 @@ class Api:
|
||||
hits = response["hits"]["hits"]
|
||||
except (KeyError, TypeError) as error:
|
||||
raise ApiError(502, "search backend returned an incomplete response") from error
|
||||
return {"api_version": API_VERSION, "query": text, "language": language, "page": page, "page_size": page_size, "has_next": len(hits) > page_size, "results": [self.search_hit(hit, language) for hit in hits[:page_size]]}
|
||||
results = [self.search_hit(hit, language) for hit in hits[:page_size]]
|
||||
snapshot_results = [{"rank": rank, **result} for rank, result in enumerate(results, 1)]
|
||||
return {"api_version": API_VERSION, "query": text, "language": language, "page": page, "page_size": page_size, "has_next": len(hits) > page_size, "results": results, "review_token": self.review_snapshots.create(text, language, self.index, snapshot_results)}
|
||||
|
||||
@staticmethod
|
||||
def search_hit(hit: dict, language: str) -> dict:
|
||||
@@ -221,12 +229,60 @@ class Api:
|
||||
raise ApiError(404, "edition language not found")
|
||||
return {"api_version": API_VERSION, "edition": metadata, "content": content}
|
||||
|
||||
def handle(self, method: str, path: str) -> tuple[int, dict]:
|
||||
if method != "GET":
|
||||
raise ApiError(405, "method not allowed")
|
||||
def save_review(self, body: dict) -> dict:
|
||||
if not isinstance(body, dict):
|
||||
raise ApiError(400, "request body must be an object")
|
||||
try:
|
||||
snapshot = self.review_snapshots.verify(body["review_token"])
|
||||
reviewer = body["reviewer"].strip()
|
||||
overall_comment = body.get("overall_comment", "").strip()
|
||||
submitted = body["results"]
|
||||
except (KeyError, AttributeError, TypeError, ValueError) as error:
|
||||
raise ApiError(400, "review_token, reviewer and results are required") from error
|
||||
if not reviewer or len(reviewer) > 120:
|
||||
raise ApiError(400, "reviewer must be between 1 and 120 characters")
|
||||
if len(overall_comment) > 4000:
|
||||
raise ApiError(400, "overall_comment is too long")
|
||||
if not isinstance(submitted, list):
|
||||
raise ApiError(400, "results must be an array")
|
||||
by_rank = {item["rank"]: item for item in snapshot["results"]}
|
||||
results = []
|
||||
for item in submitted:
|
||||
if not isinstance(item, dict) or not isinstance(item.get("rank"), int) or item["rank"] not in by_rank:
|
||||
raise ApiError(400, "review result rank is invalid")
|
||||
source = by_rank[item["rank"]]
|
||||
if item.get("code") != source["code"]:
|
||||
raise ApiError(400, "review result document does not match the search snapshot")
|
||||
rating = item.get("rating")
|
||||
if rating is not None and (isinstance(rating, bool) or not isinstance(rating, int) or not 0 <= rating <= 3):
|
||||
raise ApiError(400, "rating must be an integer from 0 to 3")
|
||||
comment = item.get("comment", "")
|
||||
if not isinstance(comment, str) or len(comment) > 4000:
|
||||
raise ApiError(400, "result comment is too long")
|
||||
results.append({**source, "rating": rating, "comment": comment.strip()})
|
||||
if not results:
|
||||
raise ApiError(400, "at least one result must be reviewed")
|
||||
review = {"created_at": datetime.datetime.now(datetime.timezone.utc).isoformat(), "reviewer": reviewer, "query": snapshot["query"], "language": snapshot["language"], "index_name": snapshot["index_name"], "top_result_code": snapshot["results"][0]["code"] if snapshot["results"] else None, "results": results, "overall_comment": overall_comment}
|
||||
review_id = self.review_store.save(review)
|
||||
return {"api_version": API_VERSION, "id": review_id, "created_at": review["created_at"]}
|
||||
|
||||
@staticmethod
|
||||
def review_page() -> str:
|
||||
try:
|
||||
return Path(__file__).with_name("review.html").read_text(encoding="utf-8")
|
||||
except (OSError, UnicodeError) as error:
|
||||
raise ApiError(500, "review interface is unavailable") from error
|
||||
|
||||
def handle(self, method: str, path: str, body: dict | None = None) -> tuple[int, dict]:
|
||||
parsed = urllib.parse.urlsplit(path)
|
||||
query = urllib.parse.parse_qs(parsed.query, keep_blank_values=True)
|
||||
parts = [urllib.parse.unquote(part) for part in parsed.path.split("/") if part]
|
||||
if method == "POST" and parts == ["search-reviews"]:
|
||||
return 201, self.save_review(body)
|
||||
if method == "GET" and parts == ["search-reviews", "export"]:
|
||||
return 200, {"api_version": API_VERSION, "reviews": self.review_store.export()}
|
||||
if method != "GET":
|
||||
raise ApiError(405, "method not allowed")
|
||||
if parts == ["openapi.json"]:
|
||||
return 200, openapi()
|
||||
if parts == ["search"]:
|
||||
@@ -246,7 +302,23 @@ def handler(api: Api):
|
||||
class RequestHandler(BaseHTTPRequestHandler):
|
||||
def respond(self, method: str):
|
||||
try:
|
||||
status, payload = api.handle(method, self.path)
|
||||
if method == "GET" and urllib.parse.urlsplit(self.path).path == "/review":
|
||||
body = api.review_page().encode()
|
||||
self.send_response(200)
|
||||
self.send_header("Content-Type", "text/html; charset=utf-8")
|
||||
self.send_header("Content-Length", str(len(body)))
|
||||
self.end_headers()
|
||||
self.wfile.write(body)
|
||||
return
|
||||
body = None
|
||||
if method == "POST":
|
||||
length = int(self.headers.get("Content-Length", "0"))
|
||||
if length > 1_000_000:
|
||||
raise ApiError(413, "request body is too large")
|
||||
body = json.loads(self.rfile.read(length) or b"{}")
|
||||
status, payload = api.handle(method, self.path, body)
|
||||
except json.JSONDecodeError:
|
||||
status, payload = 400, {"api_version": API_VERSION, "error": "request body must be valid JSON"}
|
||||
except ApiError as error:
|
||||
status, payload = error.status, {"api_version": API_VERSION, "error": error.message}
|
||||
body = json.dumps(payload, ensure_ascii=False).encode()
|
||||
@@ -273,11 +345,14 @@ def main() -> int:
|
||||
parser.add_argument("--url", default="http://127.0.0.1:9200")
|
||||
parser.add_argument("--index", default="akyldash-fragments-current")
|
||||
parser.add_argument("--data", type=Path, default=Path("data/minjust-normalized"))
|
||||
parser.add_argument("--reviews-db", type=Path, default=Path("data/search-reviews.sqlite3"))
|
||||
parser.add_argument("--review-secret", default=None)
|
||||
parser.add_argument("--host", default="127.0.0.1")
|
||||
parser.add_argument("--port", type=int, default=8080)
|
||||
parser.add_argument("--version", action="version", version=APP_VERSION)
|
||||
arguments = parser.parse_args()
|
||||
ThreadingHTTPServer((arguments.host, arguments.port), handler(Api(arguments.url, arguments.index, arguments.data))).serve_forever()
|
||||
secret = arguments.review_secret.encode() if arguments.review_secret else None
|
||||
ThreadingHTTPServer((arguments.host, arguments.port), handler(Api(arguments.url, arguments.index, arguments.data, arguments.reviews_db, secret))).serve_forever()
|
||||
return 0
|
||||
|
||||
|
||||
|
||||
Reference in New Issue
Block a user