aboutsummaryrefslogtreecommitdiff
path: root/helix-core/src/shellwords.rs
blob: 9d873c366c994ac2b7aac32ff88f7680eaae8bf2 (plain) (blame)
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
use std::borrow::Cow;

/// Auto escape for shellwords usage.
pub fn escape(input: Cow<str>) -> Cow<str> {
    if !input.chars().any(|x| x.is_ascii_whitespace()) {
        input
    } else if cfg!(unix) {
        Cow::Owned(input.chars().fold(String::new(), |mut buf, c| {
            if c.is_ascii_whitespace() {
                buf.push('\\');
            }
            buf.push(c);
            buf
        }))
    } else {
        Cow::Owned(format!("\"{}\"", input))
    }
}

enum State {
    OnWhitespace,
    Unquoted,
    UnquotedEscaped,
    Quoted,
    QuoteEscaped,
    Dquoted,
    DquoteEscaped,
}

pub struct Shellwords<'a> {
    state: State,
    /// Shellwords where whitespace and escapes has been resolved.
    words: Vec<Cow<'a, str>>,
    /// The parts of the input that are divided into shellwords. This can be
    /// used to retrieve the original text for a given word by looking up the
    /// same index in the Vec as the word in `words`.
    parts: Vec<&'a str>,
}

impl<'a> From<&'a str> for Shellwords<'a> {
    fn from(input: &'a str) -> Self {
        use State::*;

        let mut state = Unquoted;
        let mut words = Vec::new();
        let mut parts = Vec::new();
        let mut escaped = String::with_capacity(input.len());

        let mut part_start = 0;
        let mut unescaped_start = 0;
        let mut end = 0;

        for (i, c) in input.char_indices() {
            state = match state {
                OnWhitespace => match c {
                    '"' => {
                        end = i;
                        Dquoted
                    }
                    '\'' => {
                        end = i;
                        Quoted
                    }
                    '\\' => {
                        if cfg!(unix) {
                            escaped.push_str(&input[unescaped_start..i]);
                            unescaped_start = i + 1;
                            UnquotedEscaped
                        } else {
                            OnWhitespace
                        }
                    }
                    c if c.is_ascii_whitespace() => {
                        end = i;
                        OnWhitespace
                    }
                    _ => Unquoted,
                },
                Unquoted => match c {
                    '\\' => {
                        if cfg!(unix) {
                            escaped.push_str(&input[unescaped_start..i]);
                            unescaped_start = i + 1;
                            UnquotedEscaped
                        } else {
                            Unquoted
                        }
                    }
                    c if c.is_ascii_whitespace() => {
                        end = i;
                        OnWhitespace
                    }
                    _ => Unquoted,
                },
                UnquotedEscaped => Unquoted,
                Quoted => match c {
                    '\\' => {
                        if cfg!(unix) {
                            escaped.push_str(&input[unescaped_start..i]);
                            unescaped_start = i + 1;
                            QuoteEscaped
                        } else {
                            Quoted
                        }
                    }
                    '\'' => {
                        end = i;
                        OnWhitespace
                    }
                    _ => Quoted,
                },
                QuoteEscaped => Quoted,
                Dquoted => match c {
                    '\\' => {
                        if cfg!(unix) {
                            escaped.push_str(&input[unescaped_start..i]);
                            unescaped_start = i + 1;
                            DquoteEscaped
                        } else {
                            Dquoted
                        }
                    }
                    '"' => {
                        end = i;
                        OnWhitespace
                    }
                    _ => Dquoted,
                },
                DquoteEscaped => Dquoted,
            };

            let c_len = c.len_utf8();
            if i == input.len() - c_len && end == 0 {
                end = i + c_len;
            }

            if end > 0 {
                let esc_trim = escaped.trim();
                let inp = &input[unescaped_start..end];

                if !(esc_trim.is_empty() && inp.trim().is_empty()) {
                    if esc_trim.is_empty() {
                        words.push(inp.into());
                        parts.push(inp);
                    } else {
                        words.push([escaped, inp.into()].concat().into());
                        parts.push(&input[part_start..end]);
                        escaped = "".to_string();
                    }
                }
                unescaped_start = i + 1;
                part_start = i + 1;
                end = 0;
            }
        }

        debug_assert!(words.len() == parts.len());

        Self {
            state,
            words,
            parts,
        }
    }
}

impl<'a> Shellwords<'a> {
    /// Checks that the input ends with a whitespace character which is not escaped.
    ///
    /// # Examples
    ///
    /// ```rust
    /// use helix_core::shellwords::Shellwords;
    /// assert_eq!(Shellwords::from(" ").ends_with_whitespace(), true);
    /// assert_eq!(Shellwords::from(":open ").ends_with_whitespace(), true);
    /// assert_eq!(Shellwords::from(":open foo.txt ").ends_with_whitespace(), true);
    /// assert_eq!(Shellwords::from(":open").ends_with_whitespace(), false);
    /// #[cfg(unix)]
    /// assert_eq!(Shellwords::from(":open a\\ ").ends_with_whitespace(), false);
    /// #[cfg(unix)]
    /// assert_eq!(Shellwords::from(":open a\\ b.txt").ends_with_whitespace(), false);
    /// ```
    pub fn ends_with_whitespace(&self) -> bool {
        matches!(self.state, State::OnWhitespace)
    }

    /// Returns the list of shellwords calculated from the input string.
    pub fn words(&self) -> &[Cow<'a, str>] {
        &self.words
    }

    /// Returns a list of strings which correspond to [`Self::words`] but represent the original
    /// text in the input string - including escape characters - without separating whitespace.
    pub fn parts(&self) -> &[&'a str] {
        &self.parts
    }
}

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

    #[test]
    #[cfg(windows)]
    fn test_normal() {
        let input = r#":o single_word twó wörds \three\ \"with\ escaping\\"#;
        let shellwords = Shellwords::from(input);
        let result = shellwords.words().to_vec();
        let expected = vec![
            Cow::from(":o"),
            Cow::from("single_word"),
            Cow::from("twó"),
            Cow::from("wörds"),
            Cow::from("\\three\\"),
            Cow::from("\\"),
            Cow::from("with\\ escaping\\\\"),
        ];
        // TODO test is_owned and is_borrowed, once they get stabilized.
        assert_eq!(expected, result);
    }

    #[test]
    #[cfg(unix)]
    fn test_normal() {
        let input = r#":o single_word twó wörds \three\ \"with\ escaping\\"#;
        let shellwords = Shellwords::from(input);
        let result = shellwords.words().to_vec();
        let expected = vec![
            Cow::from(":o"),
            Cow::from("single_word"),
            Cow::from("twó"),
            Cow::from("wörds"),
            Cow::from(r#"three "with escaping\"#),
        ];
        // TODO test is_owned and is_borrowed, once they get stabilized.
        assert_eq!(expected, result);
    }

    #[test]
    #[cfg(unix)]
    fn test_quoted() {
        let quoted =
            r#":o 'single_word' 'twó wörds' '' ' ''\three\' \"with\ escaping\\' 'quote incomplete"#;
        let shellwords = Shellwords::from(quoted);
        let result = shellwords.words().to_vec();
        let expected = vec![
            Cow::from(":o"),
            Cow::from("single_word"),
            Cow::from("twó wörds"),
            Cow::from(r#"three' "with escaping\"#),
            Cow::from("quote incomplete"),
        ];
        assert_eq!(expected, result);
    }

    #[test]
    #[cfg(unix)]
    fn test_dquoted() {
        let dquoted = r#":o "single_word" "twó wörds" "" "  ""\three\' \"with\ escaping\\" "dquote incomplete"#;
        let shellwords = Shellwords::from(dquoted);
        let result = shellwords.words().to_vec();
        let expected = vec![
            Cow::from(":o"),
            Cow::from("single_word"),
            Cow::from("twó wörds"),
            Cow::from(r#"three' "with escaping\"#),
            Cow::from("dquote incomplete"),
        ];
        assert_eq!(expected, result);
    }

    #[test]
    #[cfg(unix)]
    fn test_mixed() {
        let dquoted = r#":o single_word 'twó wörds' "\three\' \"with\ escaping\\""no space before"'and after' $#%^@ "%^&(%^" ')(*&^%''a\\\\\b' '"#;
        let shellwords = Shellwords::from(dquoted);
        let result = shellwords.words().to_vec();
        let expected = vec![
            Cow::from(":o"),
            Cow::from("single_word"),
            Cow::from("twó wörds"),
            Cow::from("three' \"with escaping\\"),
            Cow::from("no space before"),
            Cow::from("and after"),
            Cow::from("$#%^@"),
            Cow::from("%^&(%^"),
            Cow::from(")(*&^%"),
            Cow::from(r#"a\\b"#),
            //last ' just changes to quoted but since we dont have anything after it, it should be ignored
        ];
        assert_eq!(expected, result);
    }

    #[test]
    fn test_lists() {
        let input =
            r#":set statusline.center ["file-type","file-encoding"] '["list", "in", "quotes"]'"#;
        let shellwords = Shellwords::from(input);
        let result = shellwords.words().to_vec();
        let expected = vec![
            Cow::from(":set"),
            Cow::from("statusline.center"),
            Cow::from(r#"["file-type","file-encoding"]"#),
            Cow::from(r#"["list", "in", "quotes"]"#),
        ];
        assert_eq!(expected, result);
    }

    #[test]
    #[cfg(unix)]
    fn test_escaping_unix() {
        assert_eq!(escape("foobar".into()), Cow::Borrowed("foobar"));
        assert_eq!(escape("foo bar".into()), Cow::Borrowed("foo\\ bar"));
        assert_eq!(escape("foo\tbar".into()), Cow::Borrowed("foo\\\tbar"));
    }

    #[test]
    #[cfg(windows)]
    fn test_escaping_windows() {
        assert_eq!(escape("foobar".into()), Cow::Borrowed("foobar"));
        assert_eq!(escape("foo bar".into()), Cow::Borrowed("\"foo bar\""));
    }

    #[test]
    #[cfg(unix)]
    fn test_parts() {
        assert_eq!(Shellwords::from(":o a").parts(), &[":o", "a"]);
        assert_eq!(Shellwords::from(":o a\\ ").parts(), &[":o", "a\\ "]);
    }

    #[test]
    #[cfg(windows)]
    fn test_parts() {
        assert_eq!(Shellwords::from(":o a").parts(), &[":o", "a"]);
        assert_eq!(Shellwords::from(":o a\\ ").parts(), &[":o", "a\\"]);
    }

    #[test]
    fn test_multibyte_at_end() {
        assert_eq!(Shellwords::from("𒀀").parts(), &["𒀀"]);
        assert_eq!(
            Shellwords::from(":sh echo 𒀀").parts(),
            &[":sh", "echo", "𒀀"]
        );
        assert_eq!(
            Shellwords::from(":sh echo 𒀀 hello world𒀀").parts(),
            &[":sh", "echo", "𒀀", "hello", "world𒀀"]
        );
    }
}