mirror of
https://github.com/paperless-ngx/paperless-ngx.git
synced 2026-08-20 09:43:29 +00:00
Trenton Holmes
8cf4b0c997
PublicField duplicated seven fields whoosh-compat's own FieldSpec already has (name/kind/aliases/comma_values/date_only/fast/subpaths), and _registry.py hand-copied all of them across on every registry build. FieldSpec is a frozen dataclass with analyzer/pattern_normalizer already optional (default None), so PUBLIC_FIELDS can just BE the FieldSpec tuple - _schema.py only ever read name/kind/fast off it and needs no changes. _registry.py now attaches the per-language analyzer/pattern_normalizer via dataclasses.replace() instead of reconstructing every field from scratch. FieldSpec.__post_init__ normalizes subpaths into a MappingProxyType, so test_fields.py's exact-tuple-equality subpath assertions become set comparisons; a genuinely empty subpaths is now `not field.subpaths` rather than `== ()`. Verified test_api_trash.py::test_api_trash's "Schema error: An index exists but the schema does not match" failure is a pre-existing, unrelated local environment issue (a stale, untracked data/index/ directory in this checkout) - reproduces identically with this commit's changes stashed out.
57 lines
1.8 KiB
Python
57 lines
1.8 KiB
Python
from __future__ import annotations
|
|
|
|
import dataclasses
|
|
|
|
from whoosh_compat import FieldKind
|
|
from whoosh_compat import FieldRegistry
|
|
|
|
from documents.search._fields import PUBLIC_FIELDS
|
|
from documents.search._tokenizer import ascii_fold
|
|
from documents.search._tokenizer import paperless_text_analyzer
|
|
|
|
_registry_cache: dict[str | None, FieldRegistry] = {}
|
|
|
|
|
|
def _identity_analyzer(text: str) -> list[str]:
|
|
"""Analyzer for KEYWORD fields indexed with the raw tokenizer (no splitting)."""
|
|
return [text]
|
|
|
|
|
|
def _pattern_normalizer(text: str) -> str:
|
|
"""Normalize wildcard/regex query patterns: lowercase -> ascii_fold.
|
|
|
|
Mirrors the lowercase -> ascii_fold steps of the index-time analyzers
|
|
(paperless_text) without stemming, so pattern queries (e.g. "run*")
|
|
match tokens that were folded the same way at index time but are not
|
|
run through a stemmer, which would corrupt wildcard/regex semantics.
|
|
"""
|
|
return ascii_fold(text.lower())
|
|
|
|
|
|
def get_field_registry(language: str | None) -> FieldRegistry:
|
|
"""Build (or return the cached) FieldRegistry for the given search language.
|
|
|
|
Cached keyed by language, rebuilt on the same trigger register_tokenizers()
|
|
uses (settings.SEARCH_LANGUAGE change) — a fresh call with a new language
|
|
builds and caches a new registry rather than mutating the old one.
|
|
"""
|
|
if language in _registry_cache:
|
|
return _registry_cache[language]
|
|
|
|
text_analyzer = paperless_text_analyzer(language).analyze
|
|
|
|
specs = [
|
|
dataclasses.replace(
|
|
field,
|
|
analyzer=_identity_analyzer
|
|
if field.kind is FieldKind.KEYWORD
|
|
else text_analyzer,
|
|
pattern_normalizer=_pattern_normalizer,
|
|
)
|
|
for field in PUBLIC_FIELDS
|
|
]
|
|
|
|
registry = FieldRegistry(specs)
|
|
_registry_cache[language] = registry
|
|
return registry
|