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
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
#![allow(missing_docs)] // FIXME: Document this

pub mod fs;
mod string;
use errors::Error;
use regex::Regex;

use pulldown_cmark::{
    html, Event, Options, Parser, Tag, OPTION_ENABLE_FOOTNOTES, OPTION_ENABLE_TABLES,
};

use std::borrow::Cow;

pub use self::string::{take_lines, RangeArgument};

/// Replaces multiple consecutive whitespace characters with a single space character.
pub fn collapse_whitespace<'a>(text: &'a str) -> Cow<'a, str> {
    lazy_static! {
        static ref RE: Regex = Regex::new(r"\s\s+").unwrap();
    }
    RE.replace_all(text, " ")
}

/// Convert the given string to a valid HTML element ID
pub fn normalize_id(content: &str) -> String {
    let mut ret = content
        .chars()
        .filter_map(|ch| {
            if ch.is_alphanumeric() || ch == '_' || ch == '-' {
                Some(ch.to_ascii_lowercase())
            } else if ch.is_whitespace() {
                Some('-')
            } else {
                None
            }
        }).collect::<String>();
    // Ensure that the first character is [A-Za-z]
    if ret
        .chars()
        .next()
        .map_or(false, |c| !c.is_ascii_alphabetic())
    {
        ret.insert(0, 'a');
    }
    ret
}

/// Generate an ID for use with anchors which is derived from a "normalised"
/// string.
pub fn id_from_content(content: &str) -> String {
    let mut content = content.to_string();

    // Skip any tags or html-encoded stuff
    const REPL_SUB: &[&str] = &[
        "<em>",
        "</em>",
        "<code>",
        "</code>",
        "<strong>",
        "</strong>",
        "&lt;",
        "&gt;",
        "&amp;",
        "&#39;",
        "&quot;",
    ];
    for sub in REPL_SUB {
        content = content.replace(sub, "");
    }

    // Remove spaces and hashes indicating a header
    let trimmed = content.trim().trim_left_matches('#').trim();

    normalize_id(trimmed)
}

fn adjust_links(event: Event) -> Event {
    lazy_static! {
        static ref HTTP_LINK: Regex = Regex::new("^https?://").unwrap();
        static ref MD_LINK: Regex = Regex::new("(?P<link>.*).md(?P<anchor>#.*)?").unwrap();
    }

    match event {
        Event::Start(Tag::Link(dest, title)) => {
            if !HTTP_LINK.is_match(&dest) {
                if let Some(caps) = MD_LINK.captures(&dest) {
                    let mut html_link = [&caps["link"], ".html"].concat();

                    if let Some(anchor) = caps.name("anchor") {
                        html_link.push_str(anchor.as_str());
                    }

                    return Event::Start(Tag::Link(Cow::from(html_link), title));
                }
            }

            Event::Start(Tag::Link(dest, title))
        }
        _ => event,
    }
}

/// Wrapper around the pulldown-cmark parser for rendering markdown to HTML.
pub fn render_markdown(text: &str, curly_quotes: bool) -> String {
    let mut s = String::with_capacity(text.len() * 3 / 2);

    let mut opts = Options::empty();
    opts.insert(OPTION_ENABLE_TABLES);
    opts.insert(OPTION_ENABLE_FOOTNOTES);

    let p = Parser::new_ext(text, opts);
    let mut converter = EventQuoteConverter::new(curly_quotes);
    let events = p
        .map(clean_codeblock_headers)
        .map(adjust_links)
        .map(|event| converter.convert(event));

    html::push_html(&mut s, events);
    s
}

struct EventQuoteConverter {
    enabled: bool,
    convert_text: bool,
}

impl EventQuoteConverter {
    fn new(enabled: bool) -> Self {
        EventQuoteConverter {
            enabled: enabled,
            convert_text: true,
        }
    }

    fn convert<'a>(&mut self, event: Event<'a>) -> Event<'a> {
        if !self.enabled {
            return event;
        }

        match event {
            Event::Start(Tag::CodeBlock(_)) | Event::Start(Tag::Code) => {
                self.convert_text = false;
                event
            }
            Event::End(Tag::CodeBlock(_)) | Event::End(Tag::Code) => {
                self.convert_text = true;
                event
            }
            Event::Text(ref text) if self.convert_text => {
                Event::Text(Cow::from(convert_quotes_to_curly(text)))
            }
            _ => event,
        }
    }
}

fn clean_codeblock_headers(event: Event) -> Event {
    match event {
        Event::Start(Tag::CodeBlock(ref info)) => {
            let info: String = info.chars().filter(|ch| !ch.is_whitespace()).collect();

            Event::Start(Tag::CodeBlock(Cow::from(info)))
        }
        _ => event,
    }
}

fn convert_quotes_to_curly(original_text: &str) -> String {
    // We'll consider the start to be "whitespace".
    let mut preceded_by_whitespace = true;

    original_text
        .chars()
        .map(|original_char| {
            let converted_char = match original_char {
                '\'' => {
                    if preceded_by_whitespace {
                        '‘'
                    } else {
                        '’'
                    }
                }
                '"' => {
                    if preceded_by_whitespace {
                        '“'
                    } else {
                        '”'
                    }
                }
                _ => original_char,
            };

            preceded_by_whitespace = original_char.is_whitespace();

            converted_char
        }).collect()
}

/// Prints a "backtrace" of some `Error`.
pub fn log_backtrace(e: &Error) {
    error!("Error: {}", e);

    for cause in e.iter().skip(1) {
        error!("\tCaused By: {}", cause);
    }
}

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

        #[test]
        fn preserves_external_links() {
            assert_eq!(
                render_markdown("[example](https://www.rust-lang.org/)", false),
                "<p><a href=\"https://www.rust-lang.org/\">example</a></p>\n"
            );
        }

        #[test]
        fn it_can_adjust_markdown_links() {
            assert_eq!(
                render_markdown("[example](example.md)", false),
                "<p><a href=\"example.html\">example</a></p>\n"
            );
            assert_eq!(
                render_markdown("[example_anchor](example.md#anchor)", false),
                "<p><a href=\"example.html#anchor\">example_anchor</a></p>\n"
            );
        }

        #[test]
        fn it_can_keep_quotes_straight() {
            assert_eq!(render_markdown("'one'", false), "<p>'one'</p>\n");
        }

        #[test]
        fn it_can_make_quotes_curly_except_when_they_are_in_code() {
            let input = r#"
'one'
```
'two'
```
`'three'` 'four'"#;
            let expected = r#"<p>‘one’</p>
<pre><code>'two'
</code></pre>
<p><code>'three'</code> ‘four’</p>
"#;
            assert_eq!(render_markdown(input, true), expected);
        }

        #[test]
        fn whitespace_outside_of_codeblock_header_is_preserved() {
            let input = r#"
some text with spaces
```rust
fn main() {
// code inside is unchanged
}
```
more text with spaces
"#;

            let expected = r#"<p>some text with spaces</p>
<pre><code class="language-rust">fn main() {
// code inside is unchanged
}
</code></pre>
<p>more text with spaces</p>
"#;
            assert_eq!(render_markdown(input, false), expected);
            assert_eq!(render_markdown(input, true), expected);
        }

        #[test]
        fn rust_code_block_properties_are_passed_as_space_delimited_class() {
            let input = r#"
```rust,no_run,should_panic,property_3
```
"#;

            let expected =
                r#"<pre><code class="language-rust,no_run,should_panic,property_3"></code></pre>
"#;
            assert_eq!(render_markdown(input, false), expected);
            assert_eq!(render_markdown(input, true), expected);
        }

        #[test]
        fn rust_code_block_properties_with_whitespace_are_passed_as_space_delimited_class() {
            let input = r#"
```rust,    no_run,,,should_panic , ,property_3
```
"#;

            let expected =
                r#"<pre><code class="language-rust,no_run,,,should_panic,,property_3"></code></pre>
"#;
            assert_eq!(render_markdown(input, false), expected);
            assert_eq!(render_markdown(input, true), expected);
        }

        #[test]
        fn rust_code_block_without_properties_has_proper_html_class() {
            let input = r#"
```rust
```
"#;

            let expected = r#"<pre><code class="language-rust"></code></pre>
"#;
            assert_eq!(render_markdown(input, false), expected);
            assert_eq!(render_markdown(input, true), expected);

            let input = r#"
```rust
```
"#;
            assert_eq!(render_markdown(input, false), expected);
            assert_eq!(render_markdown(input, true), expected);
        }
    }

    mod html_munging {
        use super::super::{id_from_content, normalize_id};

        #[test]
        fn it_generates_anchors() {
            assert_eq!(
                id_from_content("## `--passes`: add more rustdoc passes"),
                "a--passes-add-more-rustdoc-passes"
            );
            assert_eq!(
                id_from_content("## Method-call expressions"),
                "method-call-expressions"
            );
        }

        #[test]
        fn it_normalizes_ids() {
            assert_eq!(
                normalize_id("`--passes`: add more rustdoc passes"),
                "a--passes-add-more-rustdoc-passes"
            );
            assert_eq!(
                normalize_id("Method-call 🐙 expressions \u{1f47c}"),
                "method-call--expressions-"
            );
            assert_eq!(normalize_id("_-_12345"), "a_-_12345");
            assert_eq!(normalize_id("12345"), "a12345");
            assert_eq!(normalize_id(""), "");
        }
    }

    mod convert_quotes_to_curly {
        use super::super::convert_quotes_to_curly;

        #[test]
        fn it_converts_single_quotes() {
            assert_eq!(
                convert_quotes_to_curly("'one', 'two'"),
                "‘one’, ‘two’"
            );
        }

        #[test]
        fn it_converts_double_quotes() {
            assert_eq!(
                convert_quotes_to_curly(r#""one", "two""#),
                "“one”, “two”"
            );
        }

        #[test]
        fn it_treats_tab_as_whitespace() {
            assert_eq!(convert_quotes_to_curly("\t'one'"), "\t‘one’");
        }
    }
}