# -*- coding: utf-8 -*-
"""D1 §10 Python emoji gate — Windows grep silently fails to match multibyte emoji (the D0
grep-gate zero was a false negative). This scans templates by Unicode codepoint.

Run from controller/:  python scripts/emoji_gate.py
Exit 1 if any emoji/pictograph remains in web+setup templates.
"""
import io, os, sys, unicodedata

sys.path.insert(0, os.path.dirname(os.path.abspath(__file__)))
import i18n_bundle  # noqa: E402

ROOTS = [
    os.path.join("internal", "web", "templates"),
    os.path.join("internal", "setup", "templates"),
]

# Codepoint ranges that count as "emoji / pictographs / dingbats" for UI-copy purposes.
# Deliberately does NOT flag Hungarian letters, typographic quotes/dashes, the middle dot (·),
# arrows used as affordances (→ ↗ ↻ ↑ ↓), the multiplication sign (×), or box-drawing.
def is_emoji(ch):
    o = ord(ch)
    ranges = [
        (0x1F300, 0x1FAFF),  # Misc symbols & pictographs, emoticons, transport, supplemental, symbols-ext
        (0x2600, 0x26FF),    # Misc symbols (☀ ⚙ ⚠ ☁ …)
        (0x2700, 0x27BF),    # Dingbats (✅ ✂ ✈ ✏ ✓? no — see allow)
        (0x1F000, 0x1F0FF),  # Mahjong/dominoes/cards
        (0xFE00, 0xFE0F),    # Variation selectors (emoji presentation)
        (0x1F1E6, 0x1F1FF),  # Regional indicators
    ]
    if any(a <= o <= b for a, b in ranges):
        return True
    return False

# Dingbat codepoints that are legitimate UI glyphs (checkmarks/crosses used as plain text marks,
# not emoji). We keep these OUT of the ban — they render as monochrome text, not color emoji.
ALLOW = set("✓✗✔✘•●○■▶")  # ✓ ✗ ✔ ✘ • ● ○ ■ ▶


def scan(path):
    # v0.247.0: the copy of a converted template lives in the i18n bundle -- scan every language's
    # expansion, so an emoji in a translation is caught where it would render.
    hits = []
    for lang in i18n_bundle.LANGS:
        for h in _scan_text(i18n_bundle.read_template(path, lang)):
            if h not in hits:
                hits.append(h)
    return hits


def _scan_text(text):
    hits = []
    for lineno, line in enumerate(text.split("\n"), 1):
        for ch in line:
            if ch in ALLOW:
                continue
            if is_emoji(ch):
                try:
                    name = unicodedata.name(ch)
                except ValueError:
                    name = "U+%04X" % ord(ch)
                hits.append((lineno, ch, name))
    return hits


def _html_files(root):
    # R-421 (2026-09-01): AT ANY DEPTH. This was `os.listdir`, one level only. There are no
    # template subdirectories today, so the gate was green and correct — and would have stayed
    # green the moment anyone added `templates/partials/`, which is an ordinary thing to do.
    # Measured: a planted template in a new partials/ directory passed every listdir-based gate
    # and was caught by the two that already used os.walk. See AUDIT-gate-decoys-2026-09-01.md.
    out = []
    for dirpath, _dirs, names in os.walk(root):
        for fn in sorted(names):
            if fn.endswith('.html'):
                out.append(os.path.join(dirpath, fn))
    return sorted(out)


def main():
    total = 0
    for root in ROOTS:
        for path in _html_files(root):
            fn = os.path.relpath(path, root)
            for lineno, ch, name in scan(path):
                total += 1
                print("%s:%d  %s  %s" % (fn, lineno, ch, name))
    if total:
        print("EMOJI GATE FAILED: %d emoji found" % total)
        sys.exit(1)
    print("emoji gate OK — no emoji in web/setup templates")


if __name__ == "__main__":
    main()