#!/usr/bin/env python3
"""
tests/support/toml_smoke_check.py — Validate TOML files generated by Phase 1 adapters.

Usage:
    python tests/support/toml_smoke_check.py path/to/file.toml

Exit 0 if the file parses under the subset of TOML features used in Phase 1:
    - Standard [table] headers
    - Quoted table names: [mcp_servers."Google Calendar"]
    - key = "string"
    - key = true / false
    - key = ["a", "b"]  (array of strings)
    - env = { KEY = "VALUE" }  (inline table)
    - Comments (# ...)
    - Blank lines
    - key = '''...''' (multiline literal string, any content)
    - key = \"\"\"...\"\"\" (multiline basic string, any content)

Exit 1 with a clear error message if parsing fails.
"""

import re
import sys


# ---------------------------------------------------------------------------
# Token patterns for Phase 1 TOML subset
# ---------------------------------------------------------------------------

# Blank line or comment
RE_BLANK = re.compile(r'^\s*(#.*)?$')

# Standard table header: [agents] or [mcp_servers.Gmail]
RE_TABLE = re.compile(r'^\[([A-Za-z0-9_.-]+)\]\s*(#.*)?$')

# TOML basic string content used inside quoted table keys for this test suite.
# The generated keys only need literal characters plus escaped quote/backslash.
# Keeping the subset narrow helps catch accidental raw backslashes such as
# [mcp_servers."foo\bar"], which would change the key meaning.
_TOML_ESCAPE = r'\\(?:["\\])'
_TOML_SAFE_CHAR = r'[^"\\]'
_TOML_QSTR = rf'(?:{_TOML_SAFE_CHAR}|{_TOML_ESCAPE})*'

# Quoted table header: [mcp_servers."Google Calendar"]
RE_TABLE_QUOTED = re.compile(
    rf'^\[([A-Za-z0-9_.-]+"{_TOML_QSTR}")\]\s*(#.*)?$'
)

# key = "string"
RE_KEY_STRING = re.compile(r'^[A-Za-z0-9_.-]+\s*=\s*"([^"\\]|\\.)*"\s*(#.*)?$')

# key = true or key = false
RE_KEY_BOOL = re.compile(r'^[A-Za-z0-9_.-]+\s*=\s*(true|false)\s*(#.*)?$')

# key = integer
RE_KEY_INT = re.compile(r'^[A-Za-z0-9_.-]+\s*=\s*-?\d+\s*(#.*)?$')

# key = ["a", "b", ...]  (array of strings — may span a single line only)
RE_KEY_ARRAY = re.compile(r'^[A-Za-z0-9_.-]+\s*=\s*\[.*\]\s*(#.*)?$')

# key = { KEY = "VALUE", ... }  (inline table — single line)
RE_KEY_INLINE_TABLE = re.compile(r'^[A-Za-z0-9_.-]+\s*=\s*\{.*\}\s*(#.*)?$')

# key = ''' (start of multiline literal string)
RE_MULTILINE_LIT_START = re.compile(r"^[A-Za-z0-9_.-]+\s*=\s*'''")

# key = """ (start of multiline basic string)
RE_MULTILINE_BASIC_START = re.compile(r'^[A-Za-z0-9_.-]+\s*=\s*"""')

# Closing delimiter for multiline literal: line that is exactly ''' or ends with '''
RE_MULTILINE_LIT_END = re.compile(r"'''$")

# Closing delimiter for multiline basic: line that is exactly """ or ends with """
RE_MULTILINE_BASIC_END = re.compile(r'"""$')

# Collect all line-level patterns (order matters — most specific first)
LINE_PATTERNS = [
    RE_BLANK,
    RE_TABLE_QUOTED,
    RE_TABLE,
    RE_KEY_STRING,
    RE_KEY_BOOL,
    RE_KEY_INT,
    RE_KEY_ARRAY,
    RE_KEY_INLINE_TABLE,
    RE_MULTILINE_LIT_START,
    RE_MULTILINE_BASIC_START,
]


def check_file(path: str) -> None:
    try:
        with open(path, encoding='utf-8') as fh:
            lines = fh.readlines()
    except FileNotFoundError:
        print(f"ERROR: File not found: {path}", file=sys.stderr)
        sys.exit(1)
    except OSError as exc:
        print(f"ERROR: Cannot read {path}: {exc}", file=sys.stderr)
        sys.exit(1)

    errors = []
    in_multiline_lit = False   # inside ''' ... '''
    in_multiline_basic = False  # inside """ ... """

    for lineno, raw in enumerate(lines, start=1):
        line = raw.rstrip('\n')

        # Inside a multiline literal string: any content is valid until '''
        if in_multiline_lit:
            if RE_MULTILINE_LIT_END.search(line):
                in_multiline_lit = False
            # All lines inside a multiline literal are valid — no error
            continue

        # Inside a multiline basic string: any content is valid until """
        if in_multiline_basic:
            if RE_MULTILINE_BASIC_END.search(line):
                in_multiline_basic = False
            # All lines inside a multiline basic string are valid — no error
            continue

        # Check if this line opens a multiline string
        if RE_MULTILINE_LIT_START.match(line):
            # Check if it's also closed on the same line (inline)
            rest = re.sub(r"^[A-Za-z0-9_.-]+\s*=\s*'''", "", line)
            if rest.endswith("'''"):
                pass  # Single-line multiline literal (unusual but valid)
            else:
                in_multiline_lit = True
            continue

        if RE_MULTILINE_BASIC_START.match(line):
            rest = re.sub(r'^[A-Za-z0-9_.-]+\s*=\s*"""', "", line)
            if rest.endswith('"""'):
                pass  # Single-line multiline basic (unusual but valid)
            else:
                in_multiline_basic = True
            continue

        matched = any(pat.match(line) for pat in LINE_PATTERNS)
        if not matched:
            errors.append(f"  line {lineno}: unexpected syntax: {line!r}")

    if in_multiline_lit:
        errors.append("  Unterminated multiline literal string (''' not closed)")
    if in_multiline_basic:
        errors.append('  Unterminated multiline basic string (""" not closed)')

    if errors:
        print(f"TOML parse error in {path}:", file=sys.stderr)
        for err in errors:
            print(err, file=sys.stderr)
        sys.exit(1)

    print(f"OK: {path}")


if __name__ == '__main__':
    if len(sys.argv) != 2:
        print(f"Usage: {sys.argv[0]} <file.toml>", file=sys.stderr)
        sys.exit(2)
    check_file(sys.argv[1])