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

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()