agent/akyldash
1
1
Fork 0
Code Issues 4 Pull Requests 1 Actions Packages Projects Releases Wiki Activity

fix: restrict search to current editions

Browse Source
This commit is contained in:
Codex Agent
2026-08-21 07:24:16 +03:00
parent 73ff287b20
commit 0bef90debd
5 changed files with 30 additions and 11 deletions
Download Patch File Download Diff File Expand all files Collapse all files

19
backend/search/api.py
View File

@@ -55,11 +55,12 @@ def date(value: str | None, name: str) -> str | None:
def openapi() -> dict:
responses = {"200": {"description": "Successful response"}, "400": {"description": "Invalid request"}, "404": {"description": "Not found"}, "502": {"description": "Search backend unavailable"}}
return {
"openapi": "3.0.3",
"info": {"title": "Akyldash Search API", "version": API_VERSION},
"paths": {
"/search": {"get": {"parameters": [
"/search": {"get": {"responses": responses, "parameters": [
{"name": "q", "in": "query", "required": True, "schema": {"type": "string"}},
{"name": "language", "in": "query", "schema": {"type": "string", "enum": ["ru", "ky"]}},
{"name": "page", "in": "query", "schema": {"type": "integer", "minimum": 1}},
@@ -71,10 +72,10 @@ def openapi() -> dict:
{"name": "date_to", "in": "query", "schema": {"type": "string", "format": "date"}},
{"name": "sort", "in": "query", "schema": {"type": "string", "enum": ["relevance", "date"]}},
]}},
"/search/filters": {"get": {}},
"/documents/{code}": {"get": {}},
"/documents/{code}/editions": {"get": {}},
"/documents/{code}/editions/{edition}": {"get": {}},
"/search/filters": {"get": {"responses": responses}},
"/documents/{code}": {"get": {"responses": responses}},
"/documents/{code}/editions": {"get": {"responses": responses}},
"/documents/{code}/editions/{edition}": {"get": {"responses": responses}},
},
}
@@ -108,7 +109,7 @@ class Api:
sort = one(query, "sort") or "relevance"
if sort not in {"relevance", "date"}:
raise ApiError(400, "sort must be relevance or date")
filters: list[dict] = [{"term": {"language": language}}]
filters: list[dict] = [{"term": {"language": language}}, {"term": {"is_current_edition": True}}]
fields = {"document_type": f"document_type_{language}", "status": f"status_{language}", "authority": f"authority_paths_{language}"}
for parameter, field in fields.items():
value = one(query, parameter)
@@ -149,13 +150,13 @@ 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": f"document_type_{language}", "statuses": f"status_{language}", "authorities": f"authority_paths_{language}"}
body = {"size": 0, "aggs": {name: {"terms": {"field": field, "size": 1000}} for name, field in fields.items()}}
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()}}
response = self.query_opensearch(body)
try:
aggregations = response["aggregations"]
values = {
name: [{"code": item["key"], "label": item["key"], "count": item["doc_count"]} for item in aggregations[name]["buckets"]]
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
}
except (KeyError, TypeError) as error:

1
backend/search/minjust-fragments-index.json
View File

@@ -12,6 +12,7 @@
"schema_version": { "type": "keyword" },
"document_code": { "type": "keyword" },
"edition_code": { "type": "keyword" },
"is_current_edition": { "type": "boolean" },
"language": { "type": "keyword" },
"position": { "type": "integer" },
"fragment_type": { "type": "keyword" },

10
backend/search/minjust_opensearch.py
View File

@@ -42,7 +42,7 @@ def paths(document: dict, field: str, language: str) -> list[str]:
return [" > ".join(item[language]) for item in document.get(field, []) if item.get(language)]
def search_document(document: dict, fragment: dict, expected: tuple[str, str, str, int]) -> dict:
def search_document(document: dict, fragment: dict, expected: tuple[str, str, str, int], current_edition: str) -> dict:
document_code, edition_code, language, position = expected
fragment_id = f"document:{document_code}:edition:{edition_code}:lang:{language}:fragment:{position}"
required = ("id", "document_code", "edition_code", "language", "position", "type", "text", "text_sha256", "source_path", "source_sha256")
@@ -64,6 +64,7 @@ def search_document(document: dict, fragment: dict, expected: tuple[str, str, st
"schema_version": document["schema_version"],
"document_code": document_code,
"edition_code": edition_code,
"is_current_edition": edition_code == current_edition,
"language": language,
"position": position,
"fragment_type": fragment["type"],
@@ -118,13 +119,18 @@ def bulk_pairs(
document = read_json(directory / "document.json")
if document.get("source_code") != directory.name:
raise ValueError(f"Document identity does not match its path: {directory}")
edition_root = directory / "editions"
editions = [path.name for path in edition_root.iterdir() if path.is_dir()] if edition_root.is_dir() else []
if not editions:
continue
current_edition = max(editions, key=lambda value: (not value.isdigit(), int(value) if value.isdigit() else value))
for fragment_path in sorted(directory.glob("editions/*/*/fragments.json")):
edition_code, language = fragment_path.parts[-3:-1]
values = read_json(fragment_path)
if not isinstance(values, list):
raise ValueError(f"Fragments must be a list: {fragment_path}")
for position, fragment in enumerate(values, 1):
source = search_document(document, fragment, (directory.name, edition_code, language, position))
source = search_document(document, fragment, (directory.name, edition_code, language, position), current_edition)
action = json.dumps({"index": {"_index": index, "_id": fragment["id"]}}, ensure_ascii=False, allow_nan=False)
body = json.dumps(source, ensure_ascii=False, allow_nan=False)
yield directory.name, f"{action}\n{body}\n".encode()