{
  "id": "#1030",
  "pr": 1030,
  "title": "perf: translate for canonicalize_name",
  "merged": "2026-01-05",
  "after_ultra_release": false,
  "known": [
    {
      "id": "unicode-lowercase",
      "match": {
        "probe": "P1",
        "traits": "non-ascii"
      },
      "fixed_by": 1064,
      "status": "verified",
      "discovered_by": "breakwater"
    }
  ],
  "provider": "tokenfactory",
  "targets": [
    {
      "target": "packaging.utils:canonicalize_name",
      "image": "bw-pair:d09088ff31a7e098",
      "run_id": "adj-1030-be4055",
      "samples": 3,
      "usd": 0.0212,
      "verdicts": [
        {
          "signature": "P1|value|differs|non-ascii",
          "label": "likely-bug",
          "votes": {
            "likely-bug": 3
          },
          "rationale": "The PR aims only to speed up canonicalize_name while preserving the original semantics (lower‑casing per PEP 503). The new implementation only lower‑cases ASCII letters, so non‑ASCII characters like ‘İ’ are not lower‑cased, changing the output.",
          "evidence": [
            "Emulates ``re.sub(r",
            "perf: translate for canonicalize_name",
            "# Emulates ``re.sub(r'[-_.]+', '-', name).lower()`` from PEP 503",
            "# About 2x faster, safe since packages only support alphanumeric characters",
            "About 2x faster, safe since packages only support alphanumeric characters"
          ],
          "rejected": [
            "# Emulates ``re.sub(r[-_.]+, -, name).lower()`` from PEP 503",
            "_letters_translate = {c: c.lower() for c in ABCDEFGHIJKLMNOPQRSTUVWXYZ}"
          ],
          "reason": "",
          "known": [
            "unicode-lowercase"
          ],
          "facts": "Output `value` differs. Input [\"İ\"]: base gives \"i̇\", head gives \"İ\"."
        },
        {
          "signature": "P1|value|differs|non-ascii+whitespace",
          "label": "likely-bug",
          "votes": {
            "likely-bug": 3
          },
          "rationale": "Same root cause as C1 – the translation table lacks mappings for non‑ASCII letters, so trailing characters are left unchanged, diverging from the original ``.lower()`` behavior.",
          "evidence": [
            "Emulates ``re.sub(r",
            "perf: translate for canonicalize_name",
            "# Emulates ``re.sub(r'[-_.]+', '-', name).lower()`` from PEP 503",
            "# About 2x faster, safe since packages only support alphanumeric characters",
            "About 2x faster, safe since packages only support alphanumeric characters"
          ],
          "rejected": [
            "# Emulates ``re.sub(r[-_.]+, -, name).lower()`` from PEP 503",
            "_letters_translate = {c: c.lower() for c in ABCDEFGHIJKLMNOPQRSTUVWXYZ}"
          ],
          "reason": "",
          "known": [
            "unicode-lowercase"
          ],
          "facts": "Output `value` differs. Input [\"İ \"]: base gives \"i̇ \", head gives \"İ \"."
        },
        {
          "signature": "P1|value|differs|control+non-ascii",
          "label": "likely-bug",
          "votes": {
            "likely-bug": 3
          },
          "rationale": "Identical to C1/C2; the null byte is preserved but the capital İ is not lower‑cased, contrary to the documented intent to emulate ``.lower()``.",
          "evidence": [
            "Emulates ``re.sub(r",
            "perf: translate for canonicalize_name",
            "# Emulates ``re.sub(r'[-_.]+', '-', name).lower()`` from PEP 503",
            "# About 2x faster, safe since packages only support alphanumeric characters",
            "About 2x faster, safe since packages only support alphanumeric characters"
          ],
          "rejected": [
            "# Emulates ``re.sub(r[-_.]+, -, name).lower()`` from PEP 503",
            "_letters_translate = {c: c.lower() for c in ABCDEFGHIJKLMNOPQRSTUVWXYZ}"
          ],
          "reason": "",
          "known": [
            "unicode-lowercase"
          ],
          "facts": "Output `value` differs. Input [\"İ\\u0000\"]: base gives \"i̇\\u0000\", head gives \"İ\\u0000\"."
        },
        {
          "signature": "P2|outcome|exc:builtins.TypeError|exc:builtins.AttributeError|nested",
          "label": "likely-bug",
          "votes": {
            "likely-bug": 3
          },
          "rationale": "The change introduces a different exception type (AttributeError vs TypeError) when processing the same input, which is not mentioned in the PR title, docs, or tests and therefore is an unintended regression.",
          "evidence": [
            "perf: translate for canonicalize_name",
            "Emulates ``re.sub(r",
            "# Emulates ``re.sub(r'[-_.]+', '-', name).lower()`` from PEP 503",
            "# About 2x faster, safe since packages only support alphanumeric characters",
            "value = name.translate(_canonicalize_table)",
            "About 2x faster, safe since packages only support alphanumeric characters"
          ],
          "rejected": [],
          "reason": "",
          "known": [],
          "facts": "Outcome differs. Input [[\"İ\"]]: base raises builtins.TypeError, head raises builtins.AttributeError. (neither exception type subclasses the other.)"
        },
        {
          "signature": "P3|gt|False|True",
          "label": "likely-bug",
          "votes": {
            "likely-bug": 3
          },
          "rationale": "Ordering changes because the new code no longer lower‑cases Unicode letters, so comparison results differ from the original specification that required ``.lower()``.",
          "evidence": [
            "Emulates ``re.sub(r",
            "perf: translate for canonicalize_name",
            "# Emulates ``re.sub(r'[-_.]+', '-', name).lower()`` from PEP 503",
            "# About 2x faster, safe since packages only support alphanumeric characters",
            "About 2x faster, safe since packages only support alphanumeric characters"
          ],
          "rejected": [
            "# Emulates ``re.sub(r[-_.]+, -, name).lower()`` from PEP 503"
          ],
          "reason": "",
          "known": [],
          "facts": "Relation `a > b` differs for a = target(*[\"İ\"]), b = target(*[\"py3\"]): base False, head True."
        },
        {
          "signature": "P3|gt|True|False",
          "label": "likely-bug",
          "votes": {
            "likely-bug": 3
          },
          "rationale": "Same as C5 – the missing Unicode lower‑casing flips the ordering for characters such as ‘ẞ’ and ‘K’.",
          "evidence": [
            "Emulates ``re.sub(r",
            "perf: translate for canonicalize_name",
            "# Emulates ``re.sub(r'[-_.]+', '-', name).lower()`` from PEP 503",
            "# About 2x faster, safe since packages only support alphanumeric characters",
            "About 2x faster, safe since packages only support alphanumeric characters"
          ],
          "rejected": [
            "# Emulates ``re.sub(r[-_.]+, -, name).lower()`` from PEP 503"
          ],
          "reason": "",
          "known": [],
          "facts": "Relation `a > b` differs for a = target(*[\"ẞ\"]), b = target(*[\"K\"]): base True, head False."
        },
        {
          "signature": "P3|lt|True|False",
          "label": "likely-bug",
          "votes": {
            "likely-bug": 3
          },
          "rationale": "Opposite ordering result caused by the same loss of Unicode lower‑casing.",
          "evidence": [
            "Emulates ``re.sub(r",
            "perf: translate for canonicalize_name",
            "# Emulates ``re.sub(r'[-_.]+', '-', name).lower()`` from PEP 503",
            "# About 2x faster, safe since packages only support alphanumeric characters",
            "About 2x faster, safe since packages only support alphanumeric characters"
          ],
          "rejected": [
            "# Emulates ``re.sub(r[-_.]+, -, name).lower()`` from PEP 503"
          ],
          "reason": "",
          "known": [],
          "facts": "Relation `a < b` differs for a = target(*[\"İ\"]), b = target(*[\"py3\"]): base True, head False."
        },
        {
          "signature": "P3|lt|False|True",
          "label": "likely-bug",
          "votes": {
            "likely-bug": 3
          },
          "rationale": "Ordering reversal for ‘ẞ’ vs ‘K’ stems from the new implementation not applying ``.lower()`` to non‑ASCII letters.",
          "evidence": [
            "Emulates ``re.sub(r",
            "perf: translate for canonicalize_name",
            "# Emulates ``re.sub(r'[-_.]+', '-', name).lower()`` from PEP 503",
            "# About 2x faster, safe since packages only support alphanumeric characters",
            "About 2x faster, safe since packages only support alphanumeric characters"
          ],
          "rejected": [
            "# Emulates ``re.sub(r[-_.]+, -, name).lower()`` from PEP 503"
          ],
          "reason": "",
          "known": [],
          "facts": "Relation `a < b` differs for a = target(*[\"ẞ\"]), b = target(*[\"K\"]): base False, head True."
        }
      ]
    }
  ]
}