#!/usr/bin/env python3
"""Check the frontend's CSS against the tokens its stylesheet declares.

`services/design_stylesheet.check_code_against_tokens` answers "does this code
use the sheet correctly?", but inside the app it is fed only recorded SNIPPETS.
The app's own components, where unresolvable references live quietly, need a
check of their own.

That is structural. The drift panel runs in the browser and cannot read source
files, and the server has no repo access. CI is the only place holding both the
component sources and the ability to run the check, and `theme.css` is a
generated artifact — so the source of truth is a local file, with no network
and no credentials.

INSTANCE-AGNOSTIC ON PURPOSE. Nothing here knows what a token should
be called or which literals are discouraged. Both come from the stylesheet: the
declarations, and the `SUPERSEDES` block the generator emits. Point it at a
different install's sheet and it checks that install's rules.

Two severities, and the split is deliberate:

  FAIL   an unresolvable `var()` reference. Currently zero, so this is a ratchet
         that holds a line already reached rather than a backlog that keeps CI
         red. It also cannot false-positive: either the name is declared or it
         is not.
  REPORT superseded literals and raw colour literals. Hundreds today, so gating
         on them would mean a permanently failing job that everyone learns to
         ignore — which is worse than no check.
"""
from __future__ import annotations

import argparse
import pathlib
import re
import sys

# A declaration is `--name:`; a reference is `var(--name)` or `var(--name, …)`.
DECLARATION = re.compile(r"(?<![\w-])(--[A-Za-z0-9_-]+)\s*:")
REFERENCE = re.compile(r"var\(\s*(--[A-Za-z0-9_-]+)")
SUPERSEDES_LINE = re.compile(r"^\s*\*\s*(\S+)\s*->\s*(--[A-Za-z0-9_-]+)\s*$")
HEX_LITERAL = re.compile(r"#[0-9a-fA-F]{3,8}\b")
STYLE_BLOCK = re.compile(r"<style[^>]*>(.*?)</style>", re.S)
CSS_COMMENT = re.compile(r"/\*.*?\*/", re.S)


def declared_tokens(sheet: str) -> set[str]:
    """Every custom property the stylesheet declares.

    Anchored on the colon alone. Anchoring on `{` or `;` instead silently drops
    every declaration that follows a comment — a mistake made once already, which
    lost `--color-bg` and 2 others without erroring.
    """
    return set(DECLARATION.findall(sheet))


def superseded_literals(sheet: str) -> dict[str, str]:
    """`{literal: token}` from the generator's SUPERSEDES block, lowercased."""
    out: dict[str, str] = {}
    for line in sheet.splitlines():
        match = SUPERSEDES_LINE.match(line)
        if match:
            out[match.group(1).lower()] = match.group(2)
    return out


def _literal_pattern(literal: str) -> re.Pattern:
    """Match a literal without matching a longer one containing it.

    `#fff` must not fire inside `#ffffff`: different colours, and a finding on
    the wrong one sends someone to change correct code.
    """
    return re.compile(
        r"(?<![0-9A-Za-z_#-])" + re.escape(literal) + r"(?![0-9A-Za-z_-])",
        re.IGNORECASE,
    )


def style_source(path: pathlib.Path) -> str:
    """The CSS in a file — `<style>` blocks for an SFC, the whole of a .css.

    Comments are stripped, and that is load-bearing rather than tidy. A comment
    EXPLAINING a rule mentions the very literal the rule forbids: this file's own
    stylesheet documents why it avoids `#fff`, and the first run of this checker
    reported that explanation as a violation. A checker that flags the
    documentation of a rule teaches people to stop documenting rules.
    """
    text = path.read_text(encoding="utf-8", errors="replace")
    css = "\n".join(STYLE_BLOCK.findall(text)) if path.suffix == ".vue" else text
    return CSS_COMMENT.sub(" ", css)


# A rule that paints text with a colour token AND its own -bg tint of the same
# token. The pair looks harmonious and is close to illegible: a 12% tint of a
# hue sits near the surface, so the hue as text on it lands around 2:1 against
# an AA floor of 4.5. Measured across the whole Grimoire ladder in 2026-08:
# every one of the six pairs failed on the dark palette, worst 1.60:1.
#
# The fix is always the same and always available — the token's `-fg` sibling,
# which is the hue mixed toward --fs-text-primary far enough to clear AA. So
# this FAILS rather than reports: unlike a raw literal, there is nothing to
# weigh up.
SAME_TOKEN_PAIR = re.compile(
    r"color\s*:\s*var\(\s*(--fs-[\w-]+?)\s*\)"          # color: var(--fs-X)
    r"|background(?:-color)?\s*:\s*var\(\s*(--fs-[\w-]+?)-bg\s*\)"
)


def same_hue_text_on_tint(css: str) -> tuple[list[str], list[str]]:
    """Tokens used as TEXT on a tint of themselves, within one rule block.

    TWO SPELLINGS of the same background, because the first version of this
    check only knew the first and missed four live instances:

      background: var(--fs-X-bg)                       the token
      background: color-mix(in srgb, var(--fs-X) N%, transparent)   inline

    The inline form is what the project-status pills used, and it is the more
    dangerous of the two — it does not even name a `-bg` token, so nothing
    about it looks like the pattern until you measure it.

    Returned separately because they were paid down separately — the token
    form first (7 badge pairs), then the inline form (46 sites across 18
    files, 26 of them --fs-accent). Both are clean now, so BOTH gate. The
    split is kept because the two spellings need different error text: one
    names a -bg token you can search for, the other names nothing at all.
    """
    token_form, inline_form = [], []
    for body in re.findall(r"\{([^{}]*)\}", css):
        # (?<![-\w]) or `border-color`, `border-left-color` and `outline-color`
        # all match as if they were text. They are not: a border is a non-text
        # graphic and its floor is 3:1, not 4.5. Without this the check reported
        # seven rules that were already correct — and a check that cries wolf on
        # correct code is one that gets muted.
        fg = set(re.findall(r"(?<![-\w])color\s*:\s*var\(\s*(--fs-[\w-]+?)\s*\)", body))
        bg_tok = set(re.findall(r"background(?:-color)?\s*:\s*var\(\s*(--fs-[\w-]+?)-bg\s*\)", body))
        bg_inl = set(re.findall(
            r"background(?:-color)?\s*:\s*color-mix\([^;]*?var\(\s*(--fs-[\w-]+?)\s*\)[^;]*?\)",
            body,
        ))
        token_form.extend(sorted(fg & bg_tok))
        inline_form.extend(sorted(fg & (bg_inl - bg_tok)))
    return token_form, inline_form


def main() -> int:
    parser = argparse.ArgumentParser(description=__doc__)
    parser.add_argument("--sheet", default="frontend/src/assets/theme.css")
    parser.add_argument("--root", default="frontend/src")
    parser.add_argument(
        "--report-literals", action="store_true",
        help="also list raw colour literals (advisory, never fails)",
    )
    args = parser.parse_args()

    sheet_path = pathlib.Path(args.sheet)
    if not sheet_path.is_file():
        print(f"error: stylesheet not found: {sheet_path}", file=sys.stderr)
        return 2

    sheet = sheet_path.read_text()
    declared = declared_tokens(sheet)
    supersedes = superseded_literals(sheet)
    print(f"{sheet_path}: {len(declared)} tokens declared, "
          f"{len(supersedes)} superseded literals recorded\n")

    root = pathlib.Path(args.root)
    sources = sorted(
        [p for p in root.rglob("*.vue")] + [p for p in root.rglob("*.css")]
    )

    unresolved: list[tuple[pathlib.Path, str]] = []
    same_hue_hits: list[tuple[pathlib.Path, str]] = []
    inline_tint_hits: list[tuple[pathlib.Path, str]] = []
    superseded_hits: list[tuple[pathlib.Path, str, str]] = []
    literal_count = 0

    for path in sources:
        if path == sheet_path:
            continue
        css = style_source(path)
        if not css.strip():
            continue

        # A component may legitimately declare a local custom property; a
        # reference to it is not unresolved.
        local = set(DECLARATION.findall(css))
        for name in sorted(set(REFERENCE.findall(css))):
            if name not in declared and name not in local:
                unresolved.append((path, name))

        for literal, token in supersedes.items():
            if _literal_pattern(literal).search(css):
                superseded_hits.append((path, literal, token))

        literal_count += len(HEX_LITERAL.findall(css))

        tok_hits, inl_hits = same_hue_text_on_tint(css)
        for tok in tok_hits:
            same_hue_hits.append((path, tok))
        for tok in inl_hits:
            inline_tint_hits.append((path, tok))

    if unresolved:
        print(f"FAIL — {len(unresolved)} unresolvable var() reference(s).")
        print("  These render as the fallback if given one, or as nothing at all.")
        print("  Either way nothing errors, which is why they survive.\n")
        for path, name in unresolved:
            print(f"    {path}: {name}")
        print()
    else:
        print("OK — every var() reference resolves to a declared token.\n")

    if superseded_hits:
        print(f"REPORT — {len(superseded_hits)} superseded literal(s). "
              "The sheet says what to write instead:")
        seen: set[tuple[str, str]] = set()
        for path, literal, token in superseded_hits:
            key = (str(path), literal)
            if key in seen:
                continue
            seen.add(key)
            print(f"    {path}: {literal} -> {token}")
        print()

    if same_hue_hits:
        print(f"FAIL — {len(same_hue_hits)} rule(s) paint text with a token on a "
              f"tint of that same token.")
        print("  A 12% tint sits near the surface, so the hue as text on it lands "
              "around 2:1 against AA's 4.5.")
        print("  Use the token's -fg sibling, which is mixed toward "
              "--fs-text-primary until it clears the floor.\n")
        for path, tok in same_hue_hits:
            print(f"    {path}: color: var({tok}) on var({tok}-bg) -> var({tok}-fg)")
        print()
    else:
        print("OK — no text painted with a token on a tint of its own -bg.\n")

    if inline_tint_hits:
        print(f"FAIL — {len(inline_tint_hits)} rule(s) paint text with a token on an "
              f"INLINE color-mix tint of that same token.")
        print("  Identical defect to the block above, spelled without a -bg token —")
        print("  which is what let it hide: nothing about it LOOKS like the pattern.")
        print("  Use the token's -fg sibling.\n")
        for path, tok in inline_tint_hits:
            print(f"    {path}: color: var({tok}) on an inline tint -> var({tok}-fg)")
        print()
    else:
        print("OK — no text painted with a token on an inline tint of itself.\n")

    if args.report_literals:
        print(f"REPORT — {literal_count} raw colour literal(s) in component CSS.")
        print("  Advisory: a literal is a value stated outside the system, so it "
              "cannot follow a palette change.\n")

    return 1 if (unresolved or same_hue_hits or inline_tint_hits) else 0


if __name__ == "__main__":
    sys.exit(main())