Shortcuts on this page
r m x toggle line displays
j k next/prev highlighted chunk
0 (zero) top of page
1 (one) first highlighted chunk
1"""Stage 3: Statistical bigram scoring.
3Note: ``from __future__ import annotations`` is intentionally omitted because
4this module is compiled with mypyc, which does not support PEP 563 string
5annotations.
6"""
8from chardet.models import BigramProfile, score_best_language
9from chardet.pipeline import DetectionResult
10from chardet.registry import EncodingInfo
13def score_candidates(
14 data: bytes, candidates: tuple[EncodingInfo, ...]
15) -> list[DetectionResult]:
16 """Score all candidates and return results sorted by confidence descending.
18 :param data: The raw byte data to score.
19 :param candidates: Encoding candidates to evaluate.
20 :returns: A list of :class:`DetectionResult` sorted by confidence.
21 """
22 if not data or not candidates:
23 return []
25 profile = BigramProfile(data)
26 scores: list[tuple[str, float, str | None]] = []
28 for enc in candidates:
29 s, lang = score_best_language(data, enc.name, profile=profile)
30 if s > 0.0:
31 scores.append((enc.name, s, lang))
33 scores.sort(key=lambda x: x[1], reverse=True)
34 return [
35 DetectionResult(encoding=name, confidence=s, language=lang)
36 for name, s, lang in scores
37 ]