Dirk Riemann
1e340c82fa
Lands the two remaining provenance-subsystem pieces:
mapper.py — map_segment_refs_to_provenance:
- For each LLM SegmentCitation, pick seg-ids per source_type
(`value` vs `value_and_context`), cap at max_sources_per_field,
resolve each via SegmentIndex, track invalid references.
- Resolve field values by dot-path (`result.items[0].name` supported —
`[N]` bracket notation is normalised to `.N` before traversal).
- Skip fields that resolve to zero valid sources (spec §9.4).
- Write quality_metrics with fields_with_provenance / total_fields /
coverage_rate / invalid_references.
verify.py — verify_field + apply_reliability_flags:
- Dispatches per Pydantic field type: date → parse-both-sides compare;
int/float/Decimal → normalize + whole-snippet / numeric-token scan;
IBAN (detected via `iban` in field name) → upper+strip compare;
Literal / None → flags stay None; else string substring.
- _unwrap_optional handles BOTH typing.Union AND types.UnionType so
`Decimal | None` (PEP 604, what get_type_hints emits on 3.12+) resolves
correctly — caught by the integration-style test_writes_flags_and_counters.
- Number comparator scans numeric tokens in the snippet so labels
("Closing balance CHF 1'234.56") don't mask the match.
- apply_reliability_flags mutates the passed ProvenanceData in place and
writes verified_fields / text_agreement_fields to quality_metrics.
Tests cover each comparator, Literal/None skip, short-value skip (strings
and numerics), Decimal via optional union, and end-to-end flag+counter
writing against a Pydantic use-case schema that mirrors bank_statement_header.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
41 lines
1.2 KiB
Python
41 lines
1.2 KiB
Python
"""Provenance subsystem — normalisers, mapper, verifier.
|
|
|
|
Three pieces compose the reliability check:
|
|
|
|
* :mod:`ix.provenance.normalize` — pure text/number/date/IBAN normalisers
|
|
used to compare OCR snippets to extracted values.
|
|
* :mod:`ix.provenance.mapper` — resolves LLM-emitted segment IDs to
|
|
:class:`~ix.contracts.provenance.FieldProvenance` entries.
|
|
* :mod:`ix.provenance.verify` — per-field-type dispatcher that writes the
|
|
``provenance_verified`` / ``text_agreement`` flags.
|
|
|
|
Only :mod:`normalize` is exported from the package at this step; the mapper
|
|
and verifier land in task 1.8.
|
|
"""
|
|
|
|
from __future__ import annotations
|
|
|
|
from ix.provenance.mapper import (
|
|
map_segment_refs_to_provenance,
|
|
resolve_nested_path,
|
|
)
|
|
from ix.provenance.normalize import (
|
|
normalize_date,
|
|
normalize_iban,
|
|
normalize_number,
|
|
normalize_string,
|
|
should_skip_text_agreement,
|
|
)
|
|
from ix.provenance.verify import apply_reliability_flags, verify_field
|
|
|
|
__all__ = [
|
|
"apply_reliability_flags",
|
|
"map_segment_refs_to_provenance",
|
|
"normalize_date",
|
|
"normalize_iban",
|
|
"normalize_number",
|
|
"normalize_string",
|
|
"resolve_nested_path",
|
|
"should_skip_text_agreement",
|
|
"verify_field",
|
|
]
|