"""
Word error rate — server-26#163's eval harness needs a real number to compare
against, not a vibe. Standard definition: word-level Levenshtein distance
between a human-verified reference and the machine hypothesis, divided by the
reference's own word count. Case-insensitive, punctuation-insensitive — this
measures whether the right WORDS came out, not transcript formatting.
"""
import re
from typing import Optional


def _tokenize(text: str) -> list[str]:
    return re.findall(r"[\w']+", (text or "").lower())


def word_error_rate(reference: str, hypothesis: str) -> Optional[float]:
    """
    (substitutions + deletions + insertions) / len(reference words).

    None when the reference has no words — WER is undefined there, not 0.0;
    a caller that defaults a None to 0.0 would report a perfect score for a
    call nobody actually transcribed.
    """
    ref = _tokenize(reference)
    hyp = _tokenize(hypothesis)
    if not ref:
        return None
    if not hyp:
        return 1.0

    n, m = len(ref), len(hyp)
    # Single-row DP over Levenshtein distance — O(n*m) time, O(m) space.
    row = list(range(m + 1))
    for i in range(1, n + 1):
        prev_diag = row[0]
        row[0] = i
        for j in range(1, m + 1):
            prev_row_j = row[j]
            if ref[i - 1] == hyp[j - 1]:
                row[j] = prev_diag
            else:
                row[j] = 1 + min(prev_diag, row[j], row[j - 1])
            prev_diag = prev_row_j
    return row[m] / n