raeq/disarm#957: is_confusable fires on printable ASCII (", |, backtick are TR39 sources) — reproduction

is_confusable_ascii_repro.py

"""is_confusable fires on printable ASCII: `"`, `|` and backtick are TR39 sources.

Run from a disarm checkout (the four prose files are read relative to it) with disarm
importable. Expected output on disarm 0.15.0 at da174c83 (tables Unicode 17.0.0,
confusables 17.0.0):

    disarm 0.15.0
    is_confusable('"')                                 True
    is_confusable('|')                                 True
    is_confusable('`')                                 True
    is_confusable("'")                                 False
    is_confusable('say "hi"')                          True
    is_confusable('Hello, World!')                     False
    is_confusable('{"user": "alice", "role": "admin"}') True
    has_anomalies('say "hi"')      False
    normalize_confusables('"')     "''"
    normalize_confusables('|')     'l'
    normalize_confusables('`')     "'"
    repo prose (README.md, CONTRIBUTING.md, docs/user-guide/llm-pipelines.md, docs/limitations.md):
      1684 non-empty lines, 1342 pure ASCII
      is_confusable fires on 588 of the 1342 ASCII lines
      588 of those 588 contain " or | or `
      0 fire once " | ` are removed
"""

from __future__ import annotations

import disarm

FILES = (
    "README.md",
    "CONTRIBUTING.md",
    "docs/user-guide/llm-pipelines.md",
    "docs/limitations.md",
)


def main() -> None:
    print("disarm", disarm.__version__)
    for s in ['"', "|", "`", "'", 'say "hi"', "Hello, World!", '{"user": "alice", "role": "admin"}']:
        print(f"is_confusable({s!r})".ljust(50) + f" {disarm.is_confusable(s)}")
    print(f"has_anomalies('say \"hi\"')      {bool(disarm.has_anomalies('say \"hi\"'))}")
    for c in '"|`':
        print(f"normalize_confusables({c!r})     {disarm.normalize_confusables(c)!r}")
    total = ascii_lines = fires = fires_with_mark = fires_without = 0
    for path in FILES:
        with open(path, encoding="utf-8") as fh:
            for line in fh:
                line = line.rstrip("\n")
                if not line.strip():
                    continue
                total += 1
                if not line.isascii():
                    continue
                ascii_lines += 1
                if disarm.is_confusable(line):
                    fires += 1
                    if any(c in line for c in '"|`'):
                        fires_with_mark += 1
                stripped = line.replace('"', "").replace("|", "").replace("`", "")
                if disarm.is_confusable(stripped):
                    fires_without += 1
    print(f"repo prose ({', '.join(FILES)}):")
    print(f"  {total} non-empty lines, {ascii_lines} pure ASCII")
    print(f"  is_confusable fires on {fires} of the {ascii_lines} ASCII lines")
    print(f"  {fires_with_mark} of those {fires} contain \" or | or `")
    print(f"  {fires_without} fire once \" | ` are removed")


if __name__ == "__main__":
    main()