#!/usr/bin/env python3
# Part of JoeyLib, Copyright (c) 2026 Scott Duensing, under the MIT License.
# See LICENSE.md for license information.
# SPDX-License-Identifier: MIT
#
"""checkDocsCode.py - fail when the built manual shows source code with a
character that is not ASCII.

Asciidoctor's replacements turn `->` into an arrow, `...` into an ellipsis and
a backtick next to an apostrophe into a curly quote, even inside a backtick
code span, so code the reader copies out of the manual would not compile.
Write such a span as `+text+`, which Asciidoctor leaves as it is.

Usage:   scripts/lib/checkDocsCode.py MANUAL.html
Exit:    0 every code span and block is ASCII; 1 otherwise (each one listed).
"""

import html
import re
import sys

CODE = re.compile(r"<(code|pre)\b[^>]*>(.*?)</\1>", re.S)
TAG = re.compile(r"<[^>]+>")
SAMPLE_CHARS = 70


def main():
    if len(sys.argv) != 2:
        print(__doc__.strip().split("\n\n")[-1], file=sys.stderr)
        return 2
    page = open(sys.argv[1], encoding="utf-8").read()
    bad = 0
    for match in CODE.finditer(page):
        text = html.unescape(TAG.sub("", match.group(2)))
        glyphs = sorted({ch for ch in text if ord(ch) > 127})
        if glyphs:
            bad += 1
            names = " ".join(f"U+{ord(ch):04X}" for ch in glyphs)
            print(f"checkDocsCode: {names} in <{match.group(1)}>: {text[:SAMPLE_CHARS]!r}", file=sys.stderr)
    if bad:
        print(f"checkDocsCode: {bad} code span(s) or block(s) not ASCII; write them as `+text+`", file=sys.stderr)
        return 1
    return 0


sys.exit(main())