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
|
// bibiman - a TUI for managing BibLaTeX databases
// Copyright (C) 2025 lukeflo
//
// This program 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.
//
// This program 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.
//
// You should have received a copy of the GNU General Public License
// along with this program. If not, see <https://www.gnu.org/licenses/>.
/////
use fancy_regex::Regex;
use unicodeit::replace as unicode_replace;
use crate::bibiman::bibisetup::{BibiData, SanitizedBibiData};
/// Sanitizing process rules as regex cmds.
///
/// Only macros that are not already covered by unicodeit should be processed in this way.
///
// Regex to capture content between brackets: `(\{(?:[^{}]++|(\1))*+\})`
// Alternative without capturing the outer brackets: `\{((?:(\{(?:[^}{]|(\1))*+\})|[^{])*?)\}`
//
const SANITIZE_REGEX: &[(&str, &str)] = &[
(
r"\\mkbibquote\{((?:(\{(?:[^}{]|(\1))*+\})|[^{])*?)\}",
"\"${1}\"",
),
(r"\\hyphen", "-"),
];
/// Function to build the sanitization regex vector:
fn regex_vector() -> Vec<(Regex, &'static str)> {
let mut regex: Vec<(Regex, &str)> = Vec::with_capacity(SANITIZE_REGEX.len());
// build regex
for (search, replace) in SANITIZE_REGEX {
regex.push((Regex::new(search).unwrap(), replace));
}
regex
}
fn optimized_sanitize(input_text: Vec<&str>, regex: &Vec<(Regex, &str)>) -> Vec<String> {
let mut result: Vec<String> = input_text.into_iter().map(|s| s.to_string()).collect();
// process strings
let result_len = result.len();
for (re, replace) in regex {
for i in 0..result_len {
result[i] = re.replace_all(&result[i], *replace).to_string();
}
}
for i in 0..result_len {
result[i] = unicode_replace(&result[i]);
}
// return result
result
}
/// Helper macro to sanitize bibidata structs.
/// Here lives the code that generates SanitizedBibiData
/// structs from BibiData structs.
macro_rules! optimized_sanitize_bibidata {
($bibidata:expr, $regex:expr) => {
match &$bibidata.subtitle {
None => {
let sanitized_data =
optimized_sanitize(vec![&$bibidata.title, &$bibidata.abstract_text], &$regex);
SanitizedBibiData {
title: sanitized_data[0].clone(),
subtitle: None,
abstract_text: sanitized_data[1].clone(),
}
}
Some(subtitle) => {
let sanitized_data = optimized_sanitize(
vec![&$bibidata.title, subtitle, &$bibidata.abstract_text],
&$regex,
);
SanitizedBibiData {
title: sanitized_data[0].clone(),
subtitle: Some(sanitized_data[1].clone()),
abstract_text: sanitized_data[2].clone(),
}
}
}
};
}
/// Sanitize one BibiData and return a SanitizedBibiData struct.
/// This function does ignore any existing sanitization of the bibidata struct.
pub fn sanitize_one_bibidata(bibidata: &BibiData) -> SanitizedBibiData {
let regex = regex_vector();
optimized_sanitize_bibidata!(bibidata, regex)
}
/// Sanitize one String with LaTeX Macros into a more readable one without.
///
/// If one is going to mass-sanitize strings, one should use the [`sanitize`]
/// function for performance reasons instead, to process multiple strings at once.
///
/// This is just a shortcut for the sanitize function.
pub fn sanitize_one(input_text: &str) -> String {
// This does not panic, the sanitize function always returns
// as many elements in the returned list as it get's elements
// in the input vector.
sanitize(vec![input_text]).get(0).unwrap().to_string()
}
/// Sanitize multiple Strings with LaTeX Macros into more readable unicode equivalents.
///
/// This function does always return the same amount of Strings as it gets in the input list.
pub fn sanitize(input_text: Vec<&str>) -> Vec<String> {
optimized_sanitize(input_text, ®ex_vector())
}
/// Sanitize a whole `Vec<BibiData>`, returning a new sanitized one.
pub fn mass_sanitize(bibidata: Vec<BibiData>) -> Vec<BibiData> {
let regex: Vec<(Regex, &str)> = regex_vector();
let mut result: Vec<BibiData> = Vec::with_capacity(bibidata.len());
for entry in bibidata {
result.push(BibiData {
sanitized_bibi_data: Some(optimized_sanitize_bibidata!(entry, regex)),
..entry
});
}
result
}
|
