#!/usr/bin/env python3
"""Write aac-core's keyboard/compose_table.rs: every precomposed letter of the
Latin, Greek and Cyrillic blocks whose canonical decomposition is one letter
and one combining mark, as (letter, mark, composed) — the composition step of
NFC for the letters a keyboard puts a mark on (edit::mark). Characters Unicode
excludes from composition are left out, as NFC leaves them.

usage: python3 tools/keyboard/build_compose.py   (from aac/aac-rs)
"""
import sys
import unicodedata
from pathlib import Path

OUT = Path(__file__).resolve().parents[2] / "crates/aac-core/src/keyboard/compose_table.rs"
RANGES = [(0x00C0, 0x024F), (0x0370, 0x03FF), (0x0400, 0x04FF), (0x1E00, 0x1EFF), (0x1F00, 0x1FFF)]

rows = []
for lo, hi in RANGES:
    for n in range(lo, hi + 1):
        c = chr(n)
        d = unicodedata.decomposition(c)
        if not d or d.startswith("<"):
            continue
        parts = [chr(int(x, 16)) for x in d.split()]
        if len(parts) != 2 or not unicodedata.combining(parts[1]):
            continue
        # A composition exclusion (or a singleton) does not survive NFC.
        if unicodedata.normalize("NFC", parts[0] + parts[1]) != c:
            continue
        rows.append((ord(parts[0]), ord(parts[1]), n))
rows.sort()
body = "\n".join(f"    (0x{a:04X}, 0x{m:04X}, 0x{c:04X})," for a, m, c in rows)
OUT.write_text(f"""//! Generated by `tools/keyboard/build_compose.py` (Unicode {unicodedata.unidata_version}); do not edit by hand.
//!
//! Every precomposed Latin, Greek and Cyrillic letter that NFC composes from
//! one letter and one combining mark: `(letter, mark, composed)`, sorted.
//! Derived from the Unicode Character Database, Copyright © 1991-2026
//! Unicode, Inc., under the Unicode License v3
//! (https://www.unicode.org/license.txt).

pub(super) const COMPOSE: [(u32, u32, u32); {len(rows)}] = [
{body}
];
""", encoding="utf-8")
print(f"{len(rows)} compositions -> {OUT}", file=sys.stderr)