bibtex-parser 0.3.0

BibTeX parser for Rust
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

//! Optimized delimiter finding using memchr

/// Find the next BibTeX delimiter (@, {, }, =, ,) using memchr
/// Uses two passes but returns the earliest delimiter found
#[inline]
#[must_use]
pub fn find_delimiter(haystack: &[u8], start: usize) -> Option<(usize, u8)> {
    if start >= haystack.len() {
        return None;
    }

    let search_bytes = &haystack[start..];

    // First pass: most common delimiters {, }, , (based on profiling)
    let result1 =
        memchr::memchr3(b'{', b'}', b',', search_bytes).map(|pos| (start + pos, search_bytes[pos]));

    // Third pass: parenthesis delimiters (, )
    let result3 =
        memchr::memchr2(b'(', b')', search_bytes).map(|pos| (start + pos, search_bytes[pos]));

    // Second pass: less common delimiters @, =
    let result2 =
        memchr::memchr2(b'@', b'=', search_bytes).map(|pos| (start + pos, search_bytes[pos]));

    // Return whichever delimiter appears first
    let mut earliest = None;

    for (pos, byte) in [result1, result2, result3].into_iter().flatten() {
        match earliest {
            Some((earliest_pos, _)) if pos < earliest_pos => earliest = Some((pos, byte)),
            None => earliest = Some((pos, byte)),
            _ => {}
        }
    }

    earliest
}

/// Find brace or backslash for balanced brace parsing
#[inline]
#[must_use]
pub fn find_brace_delimiter(haystack: &[u8], start: usize) -> Option<(usize, u8)> {
    if start >= haystack.len() {
        return None;
    }

    memchr::memchr3(b'{', b'}', b'\\', &haystack[start..])
        .map(|pos| (start + pos, haystack[start + pos]))
}

/// Find delimiters in quoted strings (\, ", {, })
#[inline]
#[must_use]
pub fn find_quote_delimiter(haystack: &[u8], start: usize) -> Option<(usize, u8)> {
    if start >= haystack.len() {
        return None;
    }

    let search_bytes = &haystack[start..];

    // Search for \, ", { (most common in quoted strings)
    let result1 = memchr::memchr3(b'\\', b'"', b'{', search_bytes)
        .map(|pos| (start + pos, search_bytes[pos]));

    // Also need to check for } when inside braces
    let result2 = memchr::memchr(b'}', search_bytes).map(|pos| (start + pos, b'}'));

    // Return whichever delimiter appears first
    match (result1, result2) {
        (Some((pos1, byte1)), Some((pos2, _))) => {
            if pos1 <= pos2 {
                Some((pos1, byte1))
            } else {
                Some((pos2, b'}'))
            }
        }
        (Some(r), None) | (None, Some(r)) => Some(r),
        (None, None) => None,
    }
}

/// Find a single specific delimiter
#[must_use]
pub fn find_byte(haystack: &[u8], needle: u8, start: usize) -> Option<usize> {
    if start >= haystack.len() {
        return None;
    }

    memchr::memchr(needle, &haystack[start..]).map(|pos| start + pos)
}

/// Find any of 2 delimiters
#[must_use]
pub fn find_bytes2(haystack: &[u8], needle1: u8, needle2: u8, start: usize) -> Option<(usize, u8)> {
    if start >= haystack.len() {
        return None;
    }

    memchr::memchr2(needle1, needle2, &haystack[start..])
        .map(|pos| (start + pos, haystack[start + pos]))
}

/// Find any of 3 delimiters
#[must_use]
pub fn find_bytes3(
    haystack: &[u8],
    needle1: u8,
    needle2: u8,
    needle3: u8,
    start: usize,
) -> Option<(usize, u8)> {
    if start >= haystack.len() {
        return None;
    }

    memchr::memchr3(needle1, needle2, needle3, &haystack[start..])
        .map(|pos| (start + pos, haystack[start + pos]))
}

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

    #[test]
    fn test_find_delimiter() {
        let input = b"hello @ world { test } = value, end";

        assert_eq!(find_delimiter(input, 0), Some((6, b'@')));
        assert_eq!(find_delimiter(input, 7), Some((14, b'{')));
        assert_eq!(find_delimiter(input, 15), Some((21, b'}')));
        assert_eq!(find_delimiter(input, 22), Some((23, b'=')));
        assert_eq!(find_delimiter(input, 24), Some((30, b',')));
        assert_eq!(find_delimiter(input, 31), None);
    }

    #[test]
    fn test_find_delimiter_with_parentheses() {
        let input = b"hello ( world ) test @ end";

        assert_eq!(find_delimiter(input, 0), Some((6, b'(')));
        assert_eq!(find_delimiter(input, 7), Some((14, b')')));
        assert_eq!(find_delimiter(input, 15), Some((21, b'@')));
        assert_eq!(find_delimiter(input, 22), None);
    }

    #[test]
    fn test_specialized_searches() {
        let input = b"test {nested} string";

        assert_eq!(find_brace_delimiter(input, 0), Some((5, b'{')));
        assert_eq!(find_brace_delimiter(input, 6), Some((12, b'}')));
        assert_eq!(find_byte(input, b'}', 0), Some(12));
        assert_eq!(find_byte(input, b'}', 13), None);
    }
}