ftml 0.5.0

Foundation Text Markup Language - a library to render Wikidot text as HTML
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

/*
 * preproc/whitespace.rs
 *
 * ftml - Library to parse Wikidot text
 * Copyright (C) 2019-2021 Wikijump Team
 *
 * This program is free software: you can redistribute it and/or modify
 * it under the terms of the GNU Affero 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 Affero General Public License for more details.
 *
 * You should have received a copy of the GNU Affero General Public License
 * along with this program. If not, see <http://www.gnu.org/licenses/>.
 */

//! This performs the various miscellaneous substitutions that Wikidot does
//! in preparation for its parsing and handling processes. These are:
//! * Replacing DOS and legacy Mac newlines
//! * Trimming whitespace lines
//! * Concatenating lines that end with backslashes
//! * Convert tabs to four spaces
//! * Compress groups of 3+ newlines into 2 newlines
//!
//! Note on the first item:
//! It was originally implemented in the parser, however it was moved here
//! to prevent typography from converting the `--` in `[!--` and `--]` into
//! em dashes.

use regex::{Regex, RegexBuilder};

lazy_static! {
    static ref WHITESPACE: Regex = {
        RegexBuilder::new(r"^\s+$")
            .multi_line(true)
            .build()
            .unwrap()
    };
    static ref LEADING_NEWLINES: Regex = Regex::new(r"^\n+").unwrap();
    static ref TRAILING_NEWLINES: Regex = Regex::new(r"\n+$").unwrap();
}

pub fn substitute(log: &slog::Logger, text: &mut String) {
    // Replace DOS and Mac newlines
    str_replace(log, text, "\r\n", "\n");
    str_replace(log, text, "\r", "\n");

    // Strip lines with only whitespace
    regex_replace(log, text, &*WHITESPACE, "");

    // Join concatenated lines (ending with '\')
    str_replace(log, text, "\\\n", "");

    // Tabs to spaces
    str_replace(log, text, "\t", "    ");

    // Remove leading and trailing newlines,
    // save one at the end
    regex_replace(log, text, &*LEADING_NEWLINES, "");
    regex_replace(log, text, &*TRAILING_NEWLINES, "");
}

fn str_replace(log: &slog::Logger, text: &mut String, pattern: &str, replacement: &str) {
    debug!(
        log,
        "Replacing miscellaneous static string";
        "type" => "string",
        "text" => &*text,
        "pattern" => pattern,
        "replacement" => replacement,
    );

    while let Some(idx) = text.find(pattern) {
        let range = idx..idx + pattern.len();
        text.replace_range(range, replacement);
    }
}

fn regex_replace(
    log: &slog::Logger,
    text: &mut String,
    regex: &Regex,
    replacement: &str,
) {
    debug!(
        log,
        "Replacing miscellaneous regular expression";
        "type" => "regex",
        "text" => &*text,
        "pattern" => regex.as_str(),
        "replacement" => replacement,
    );

    while let Some(mtch) = regex.find(text) {
        let range = mtch.start()..mtch.end();
        text.replace_range(range, replacement);
    }
}

#[cfg(test)]
const TEST_CASES: [(&str, &str); 6] = [
    (
        "\tapple\n\tbanana\tcherry\n",
        "    apple\n    banana    cherry",
    ),
    (
        "newlines:\r\n* apple\r* banana\r\ncherry\n\r* durian",
        "newlines:\n* apple\n* banana\ncherry\n\n* durian",
    ),
    (
        "apple\nbanana\n\ncherry\n\n\npineapple\n\n\n\nstrawberry\n\n\n\n\nblueberry\n\n\n\n\n\n",
        "apple\nbanana\n\ncherry\n\npineapple\n\nstrawberry\n\nblueberry",
    ),
    (
        "apple\rbanana\r\rcherry\r\r\rpineapple\r\r\r\rstrawberry\r\r\r\r\rblueberry\r\r\r\r\r\r",
        "apple\nbanana\n\ncherry\n\npineapple\n\nstrawberry\n\nblueberry",
    ),
    (
        "concat:\napple banana \\\nCherry\\\nPineapple \\ grape\nblueberry\n",
        "concat:\napple banana CherryPineapple \\ grape\nblueberry",
    ),
    ("<\n        \n      \n  \n      \n>", "<\n\n>"),
];

#[test]
fn regexes() {
    let _ = &*WHITESPACE;
}

#[test]
fn test_substitute() {
    use super::test::test_substitution;

    test_substitution("miscellaneous", substitute, &TEST_CASES);
}