def lint_utf8_ascii()

in scripts/asciicheck.py [0:0]

• 46 lines of code
• 14 McCabe index (conditional complexity)

def lint_utf8_ascii(filename: Path, fix: bool) -> bool:
    """Returns True if an error was printed."""
    try:
        with open(filename, "rb") as f:
            raw = f.read()
        text = raw.decode("utf-8")
    except UnicodeDecodeError as e:
        print("UTF-8 decoding error:")
        print(f"  byte offset: {e.start}")
        print(f"  reason: {e.reason}")
        # Attempt to find line/column
        partial = raw[: e.start]
        line = partial.count(b"\n") + 1
        col = e.start - (partial.rfind(b"\n") if b"\n" in partial else -1)
        print(f"  location: line {line}, column {col}")
        return True

    errors = []
    for lineno, line in enumerate(text.splitlines(keepends=True), 1):
        for colno, char in enumerate(line, 1):
            codepoint = ord(char)
            if char == "\n":
                continue
            if (
                not (0x20 <= codepoint <= 0x7E)
                and codepoint not in allowed_unicode_codepoints
            ):
                errors.append((lineno, colno, char, codepoint))

    if errors:
        for lineno, colno, char, codepoint in errors:
            safe_char = repr(char)[1:-1]  # nicely escape things like \u202f
            print(
                f"Invalid character at line {lineno}, column {colno}: U+{codepoint:04X} ({safe_char})"
            )

    if errors and fix:
        print(f"Attempting to fix {filename}...")
        num_replacements = 0
        new_contents = ""
        for char in text:
            codepoint = ord(char)
            if codepoint in substitutions:
                num_replacements += 1
                new_contents += substitutions[codepoint]
            else:
                new_contents += char
        with open(filename, "w", encoding="utf-8") as f:
            f.write(new_contents)
        print(f"Fixed {num_replacements} of {len(errors)} errors in {filename}.")

    return bool(errors)