ucifer 0.3.0

OpenWrt UCI Parser and Exporter
Documentation 
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158

/* Copyright © 2025 CZ.NIC z.s.p.o. (http://www.nic.cz/)
 *
 * This file is part of the ucifer library
 *
 * Ucifer is free software: you can redistribute it and/or modify it under
 * the terms of the GNU General Public License as published by the Free
 * Software Foundation, either version 3 of the License, or (at your option)
 * any later version.
 *
 * Ucifer is distributed in the hope that it will be useful, but WITHOUT ANY
 * WARRANTY; without even the implied warranty of MERCHANTABILITY or FITNESS
 * FOR A PARTICULAR PURPOSE. See the GNU General Public License for more
 * details.
 *
 * For more information, see /LICENSE.txt
 */

//! Contains token and lexing definition for the file format
//!
//! Currently based on [`logos`].
//!
//! Token is an implementation detail of the parser and should not be exposed as
//! public API.

use {crate::CowStr, alloc::borrow::Cow, descape::InvalidEscape, logos::Logos};

/// Specific [`Lexer`] type instance for UCI
pub type Lexer<'a> = logos::Lexer<'a, Token<'a>>;

/// Result with module-local error type default
type Result<T, E = Error> = core::result::Result<T, E>;

/// A unit of source code
#[derive(Clone, Debug, PartialEq, Eq, Logos)]
#[logos(error = Error)]
#[logos(skip r"[ \t\f]+|[#;].*")]
pub enum Token<'a> {
	/// Identifier-like string
	///
	/// As non-quoted strings can't contain escapes, this is always just a
	/// borrow.
	#[regex("[0-9A-Za-z_-]+")]
	UnquotedString(&'a str),

	/// String quoted in either `'` or `"`
	#[regex(r"'[^']*'", single_quoted)]
	#[regex(r#""([^"\\]|\\.)*""#, double_quoted)]
	QuotedString(CowStr<'a>),

	/// Newline a directive separator
	#[token("\n")]
	LineBreak,
}

impl<'a> Token<'a> {
	/// Get internaly [`Cow`] string, no matter if quoted or unquoted.
	pub fn into_cow_str(self) -> CowStr<'a> {
		match self {
			Self::UnquotedString(s) => Cow::Borrowed(s),
			Self::QuotedString(cow) => cow,
			Self::LineBreak => Cow::Borrowed("\n"),
		}
	}
}

/// Describes lexing error
#[derive(Clone, Copy, Debug, Default, PartialEq, Eq)]
pub enum Error {
	/// Invalid string escape
	Escape(InvalidEscape),
	/// We were inside a pattern but didn't get finished
	UnexpectedEndOfPattern,
	/// Lexer failed to lex token, may be end of input
	#[default]
	InvalidToken,
}

/// Single quoted strings just cut the quotation marks, do not support any kind
/// of escaping.
fn single_quoted<'a>(lexer: &Lexer<'a>) -> Result<CowStr<'a>> {
	get_without_surrounding_chars(lexer).map(Cow::Borrowed)
}

/// Double quoted strings support escapes. This returns in-[`Some`] wrapped
/// [`Cow::Owned`] if escaping was required, otherwise keep [`Cow::Borrowed`]
/// as-is.
fn double_quoted<'a>(lexer: &Lexer<'a>) -> Result<CowStr<'a>> {
	let slice = get_without_surrounding_chars(lexer)?;
	descape::UnescapeExt::to_unescaped(slice).map_err(Error::Escape)
}

/// Remove surrounding characters from current lexeme, usually a quotation mark.
fn get_without_surrounding_chars<'a>(lexer: &Lexer<'a>) -> Result<&'a str> {
	let slice = lexer.slice();
	slice
		.get(1..slice.len() - 1)
		.ok_or(Error::UnexpectedEndOfPattern)
}

#[cfg(test)]
mod tests {
	use super::*;

	impl Token<'_> {
		fn as_str(&self) -> &'_ str {
			match self {
				Token::UnquotedString(s) => s,
				Token::QuotedString(cow) => cow,
				Token::LineBreak => "\n",
			}
		}
	}

	#[test]
	fn lex_unquoted() {
		assert_eq!(lex_one_token("simple_ident").as_str(), "simple_ident");
		assert_eq!(lex_one_token("133t").as_str(), "133t");
	}

	#[test]
	fn lex_quoted() {
		assert_eq!(lex_one_token("'single quoted'").as_str(), "single quoted");
		assert_eq!(
			lex_one_token(r#""doubly quoted""#).as_str(),
			"doubly quoted"
		);
	}

	#[test]
	fn lex_quoted_escapes() {
		assert_eq!(
			lex_one_token(r#""string's cake""#).as_str(),
			"string's cake"
		);
	}

	#[test]
	fn comments() {
		let input = "#comment\n#comment";
		let mut lexer = Token::lexer(input);

		assert_eq!(lexer.next(), Some(Ok(Token::LineBreak)));
		assert_eq!(lexer.next(), None);
	}

	/// Helper function, get **exactly** one single valid token or panics.
	#[track_caller]
	fn lex_one_token(input: &str) -> Token<'_> {
		let mut lexer = Token::lexer(input);
		let token = lexer
			.next()
			.expect("expected at least one token")
			.expect("expected valid parse");

		assert_eq!(lexer.next(), None, "required at most one token");
		token
	}
}