fix: complete search API contract

This commit is contained in:
2026-08-25 07:29:06 +03:00
parent 0bef90debd
commit 9b629d93e3
8 changed files with 90 additions and 23 deletions

View File

@@ -3,6 +3,7 @@
from __future__ import annotations
import argparse
import base64
import datetime
import json
import re
@@ -17,6 +18,7 @@ API_VERSION = "v1"
LANGUAGES = {"ru", "ky"}
CODE = re.compile(r"^[0-9]+$")
MAX_PAGE_SIZE = 100
MAX_RESULT_WINDOW = 10_000
class ApiError(Exception):
@@ -54,6 +56,26 @@ def date(value: str | None, name: str) -> str | None:
return value
def catalog_code(name: str, labels: tuple[str | None, str | None]) -> str:
value = json.dumps(labels, ensure_ascii=False, separators=(",", ":")).encode()
return f"{name}:v1:{base64.urlsafe_b64encode(value).decode().rstrip('=')}"
def catalog_label(name: str, code: str, language: str) -> str:
prefix = f"{name}:v1:"
if not code.startswith(prefix):
raise ApiError(400, f"{name} must be a catalog code")
try:
encoded = code[len(prefix):]
values = json.loads(base64.urlsafe_b64decode(encoded + "=" * (-len(encoded) % 4)))
value = values[0 if language == "ru" else 1]
except (IndexError, TypeError, ValueError, UnicodeError, json.JSONDecodeError) as error:
raise ApiError(400, f"{name} must be a catalog code") from error
if not isinstance(values, list) or len(values) != 2 or not isinstance(value, str):
raise ApiError(400, f"{name} must be a catalog code")
return value
def openapi() -> dict:
responses = {"200": {"description": "Successful response"}, "400": {"description": "Invalid request"}, "404": {"description": "Not found"}, "502": {"description": "Search backend unavailable"}}
return {
@@ -73,9 +95,9 @@ def openapi() -> dict:
{"name": "sort", "in": "query", "schema": {"type": "string", "enum": ["relevance", "date"]}},
]}},
"/search/filters": {"get": {"responses": responses}},
"/documents/{code}": {"get": {"responses": responses}},
"/documents/{code}/editions": {"get": {"responses": responses}},
"/documents/{code}/editions/{edition}": {"get": {"responses": responses}},
"/documents/{code}": {"get": {"responses": responses, "parameters": [{"name": "code", "in": "path", "required": True, "schema": {"type": "string", "pattern": "^[0-9]+$"}}]}},
"/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]+$"}}]}},
},
}
@@ -106,6 +128,8 @@ class Api:
raise ApiError(400, "language must be ru or ky")
page = parse_positive(one(query, "page"), "page", 1, 1_000_000)
page_size = parse_positive(one(query, "page_size"), "page_size", 20, MAX_PAGE_SIZE)
if page * page_size >= MAX_RESULT_WINDOW:
raise ApiError(400, f"page and page_size must stay within {MAX_RESULT_WINDOW} results")
sort = one(query, "sort") or "relevance"
if sort not in {"relevance", "date"}:
raise ApiError(400, "sort must be relevance or date")
@@ -114,7 +138,7 @@ class Api:
for parameter, field in fields.items():
value = one(query, parameter)
if value:
filters.append({"term": {field: value}})
filters.append({"term": {field: catalog_label(parameter, value, language)}})
date_from, date_to = date(one(query, "date_from"), "date_from"), date(one(query, "date_to"), "date_to")
if date_from and date_to and date_from > date_to:
raise ApiError(400, "date_from must not be later than date_to")
@@ -150,14 +174,14 @@ class Api:
language = one(query, "language") or "ru"
if language not in LANGUAGES:
raise ApiError(400, "language must be ru or ky")
fields = {"document_types": ("document_type_ru", "document_type_ky"), "statuses": ("status_ru", "status_ky"), "authorities": ("authority_paths_ru", "authority_paths_ky")}
body = {"size": 0, "aggs": {name: {"multi_terms": {"terms": [{"field": field} for field in pair], "size": 1000}, "aggs": {"documents": {"cardinality": {"field": "document_code", "precision_threshold": 40000}}}} for name, pair in fields.items()}}
fields = {"document_types": ("document_type", "document_type_ru", "document_type_ky"), "statuses": ("status", "status_ru", "status_ky"), "authorities": ("authority", "authority_paths_ru", "authority_paths_ky")}
body = {"size": 0, "query": {"term": {"is_current_edition": True}}, "aggs": {name: {"multi_terms": {"terms": [{"field": field} for field in pair[1:]], "size": 1000}, "aggs": {"documents": {"cardinality": {"field": "document_code", "precision_threshold": 40000}}}} for name, pair in fields.items()}}
response = self.query_opensearch(body)
try:
aggregations = response["aggregations"]
values = {
name: [{"code": item["key"][0 if language == "ru" else 1], "labels": {"ru": item["key"][0], "ky": item["key"][1]}, "count": item["documents"]["value"]} for item in aggregations[name]["buckets"]]
for name in fields
name: [{"code": catalog_code(pair[0], (item["key"][0], item["key"][1])), "labels": {"ru": item["key"][0], "ky": item["key"][1]}, "count": item["documents"]["value"]} for item in aggregations[name]["buckets"]]
for name, pair in fields.items()
}
except (KeyError, TypeError) as error:
raise ApiError(502, "search backend returned incomplete filters") from error