package lexer

import "github.com/mmakaay/toml/parser"

// There are four ways to express strings: basic, multi-line basic, literal,
// and multi-line literal. All strings must contain only valid UTF-8 characters.
func stateStringValue(l *parser.Parser) parser.StateFn {
	switch {
	case l.SkipMatching(doubleQuote, doubleQuote, doubleQuote):
		// Multi-line basic strings are surrounded by three quotation marks on each side.
		return stateMultiLineBasicString
	case l.SkipMatching(doubleQuote):
		// Basic strings are surrounded by quotation marks.
		return stateSingleLineBasicString
	}
	return l.UnexpectedInputError("a string value")
}

func stateSingleLineBasicString(l *parser.Parser) parser.StateFn {
	if l.Upcoming(doubleQuote, doubleQuote) {
		return stateMultiLineBasicString
	}
	return stateBasicString
}

func stateMultiLineBasicString(l *parser.Parser) parser.StateFn {
	l.EmitError("Not yet implemented")
	return nil
}

// Any Unicode character may be used except those that must be escaped:
// quotation mark, backslash, and the control characters (U+0000 to U+001F, U+007F).
const invalidBasicStringCharacters string = "\"\\" +
	"\u0000\u0001\u0002\u0003\u0004\u0005\u0006\u0007" +
	"\u0008\u0009\u000A\u000B\u000C\u000D\u000E\u000F" +
	"\u0010\u0011\u0012\u0013\u0014\u0015\u0016\u0017" +
	"\u0018\u0019\u001A\u001B\u001C\u001D\u001E\u001F" +
	"\u007F"

func stateParseBasicString(l *parser.Parser) parser.StateFn {
	for {
		switch {
		case l.AtEndOfFile():
			return l.UnexpectedEndOfFile("basic string token")
		case l.SkipMatching(doubleQuote):
			return l.PopState()
		case l.AcceptMatching(backslash, escapeChars):
			// For convenience, some popular characters have a compact escape sequence.
			// \b         - backspace       (U+0008)
			// \t         - tab             (U+0009)
			// \n         - linefeed        (U+000A)
			// \f         - form feed       (U+000C)
			// \r         - carriage return (U+000D)
			// \"         - quote           (U+0022)
			// \\         - backslash       (U+005C)
		case l.AcceptMatching(backslash, shortUtf8Escape, hex, hex, hex, hex):
			// \uXXXX     - unicode         (U+XXXX)
		case l.AcceptMatching(backslash, longUtf8Escape, hex, hex, hex, hex, hex, hex, hex, hex):
			// \UXXXXXXXX - unicode         (U+XXXXXXXX)
		case l.Upcoming(backslash):
			// All other escape sequences not listed above are reserved and,
			// if used, TOML should produce an error.
			return l.EmitError("Invalid escape sequence in basic string")
		case l.Upcoming(invalidBasicStringCharacters):
			// Any Unicode character may be used except those that must be escaped:
			// quotation mark, backslash, and the control characters (U+0000 to U+001F, U+007F).
			r, _, _ := l.Match(invalidBasicStringCharacters)
			l.EmitError("Invalid character in basic string: %q (must be escaped)", r[0])
			return nil
		default:
			if !l.AcceptAny() {
				return nil
			}
		}
	}
}

func stateBasicString(l *parser.Parser) parser.StateFn {
	l.PushState(func(l *parser.Parser) parser.StateFn {
		err := l.EmitInterpreted(ItemString)
		if err != nil {
			l.EmitError("Invalid data in string: %s", err)
			return nil
		}
		return stateKeyValuePair
	})
	return stateParseBasicString
}