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
// Copyright 2014-2015 The Rust Project Developers. See the COPYRIGHT
// file at the top-level directory of this distribution and at
// http://rust-lang.org/COPYRIGHT.
//
// Licensed under the Apache License, Version 2.0 <LICENSE-APACHE or
// http://www.apache.org/licenses/LICENSE-2.0> or the MIT license
// <LICENSE-MIT or http://opensource.org/licenses/MIT>, at your
// option. This file may not be copied, modified, or distributed
// except according to those terms.

/// The set of user configurable options for compiling zero or more regexes.
#[derive(Clone, Debug)]
#[allow(missing_docs)]
pub struct RegexOptions {
    pub pats: Vec<String>,
    pub size_limit: usize,
    pub dfa_size_limit: usize,
    pub case_insensitive: bool,
    pub multi_line: bool,
    pub dot_matches_new_line: bool,
    pub swap_greed: bool,
    pub ignore_whitespace: bool,
    pub unicode: bool,
}

impl Default for RegexOptions {
    fn default() -> Self {
        RegexOptions {
            pats: vec![],
            size_limit: 10 * (1<<20),
            dfa_size_limit: 2 * (1<<20),
            case_insensitive: false,
            multi_line: false,
            dot_matches_new_line: false,
            swap_greed: false,
            ignore_whitespace: false,
            unicode: true,
        }
    }
}

macro_rules! define_builder {
    ($name:ident, $regex_mod:ident, $only_utf8:expr) => {
        pub mod $name {
            use error::Error;
            use exec::ExecBuilder;
            use super::RegexOptions;

            use $regex_mod::Regex;

/// A configurable builder for a regular expression.
///
/// A builder can be used to configure how the regex is built, for example, by
/// setting the default flags (which can be overridden in the expression
/// itself) or setting various limits.
pub struct RegexBuilder(RegexOptions);

impl RegexBuilder {
    /// Create a new regular expression builder with the given pattern.
    ///
    /// If the pattern is invalid, then an error will be returned when
    /// `build` is called.
    pub fn new(pattern: &str) -> RegexBuilder {
        let mut builder = RegexBuilder(RegexOptions::default());
        builder.0.pats.push(pattern.to_owned());
        builder
    }

    /// Consume the builder and compile the regular expression.
    ///
    /// Note that calling `as_str` on the resulting `Regex` will produce the
    /// pattern given to `new` verbatim. Notably, it will not incorporate any
    /// of the flags set on this builder.
    pub fn build(&self) -> Result<Regex, Error> {
        ExecBuilder::new_options(self.0.clone())
            .only_utf8($only_utf8)
            .build()
            .map(Regex::from)
    }

    /// Set the value for the case insensitive (`i`) flag.
    ///
    /// When enabled, letters in the pattern will match both upper case and
    /// lower case variants.
    pub fn case_insensitive(&mut self, yes: bool) -> &mut RegexBuilder {
        self.0.case_insensitive = yes;
        self
    }

    /// Set the value for the multi-line matching (`m`) flag.
    ///
    /// When enabled, `^` matches the beginning of lines and `$` matches the
    /// end of lines.
    ///
    /// By default, they match beginning/end of the input.
    pub fn multi_line(&mut self, yes: bool) -> &mut RegexBuilder {
        self.0.multi_line = yes;
        self
    }

    /// Set the value for the any character (`s`) flag, where in `.` matches
    /// anything when `s` is set and matches anything except for new line when
    /// it is not set (the default).
    ///
    /// N.B. "matches anything" means "any byte" for `regex::bytes::Regex`
    /// expressions and means "any Unicode scalar value" for `regex::Regex`
    /// expressions.
    pub fn dot_matches_new_line(&mut self, yes: bool) -> &mut RegexBuilder {
        self.0.dot_matches_new_line = yes;
        self
    }

    /// Set the value for the greedy swap (`U`) flag.
    ///
    /// When enabled, a pattern like `a*` is lazy (tries to find shortest
    /// match) and `a*?` is greedy (tries to find longest match).
    ///
    /// By default, `a*` is greedy and `a*?` is lazy.
    pub fn swap_greed(&mut self, yes: bool) -> &mut RegexBuilder {
        self.0.swap_greed = yes;
        self
    }

    /// Set the value for the ignore whitespace (`x`) flag.
    ///
    /// When enabled, whitespace such as new lines and spaces will be ignored
    /// between expressions of the pattern, and `#` can be used to start a
    /// comment until the next new line.
    pub fn ignore_whitespace(&mut self, yes: bool) -> &mut RegexBuilder {
        self.0.ignore_whitespace = yes;
        self
    }

    /// Set the value for the Unicode (`u`) flag.
    ///
    /// Enabled by default. When disabled, character classes such as `\w` only
    /// match ASCII word characters instead of all Unicode word characters.
    pub fn unicode(&mut self, yes: bool) -> &mut RegexBuilder {
        self.0.unicode = yes;
        self
    }

    /// Set the approximate size limit of the compiled regular expression.
    ///
    /// This roughly corresponds to the number of bytes occupied by a single
    /// compiled program. If the program exceeds this number, then a
    /// compilation error is returned.
    pub fn size_limit(&mut self, limit: usize) -> &mut RegexBuilder {
        self.0.size_limit = limit;
        self
    }

    /// Set the approximate size of the cache used by the DFA.
    ///
    /// This roughly corresponds to the number of bytes that the DFA will
    /// use while searching.
    ///
    /// Note that this is a *per thread* limit. There is no way to set a global
    /// limit. In particular, if a regex is used from multiple threads
    /// simultaneously, then each thread may use up to the number of bytes
    /// specified here.
    pub fn dfa_size_limit(&mut self, limit: usize) -> &mut RegexBuilder {
        self.0.dfa_size_limit = limit;
        self
    }
}
        }
    }
}

define_builder!(bytes, re_bytes, false);
define_builder!(unicode, re_unicode, true);

macro_rules! define_set_builder {
    ($name:ident, $regex_mod:ident, $only_utf8:expr) => {
        pub mod $name {
            use error::Error;
            use exec::ExecBuilder;
            use super::RegexOptions;

            use re_set::$regex_mod::RegexSet;

/// A configurable builder for a set of regular expressions.
///
/// A builder can be used to configure how the regexes are built, for example,
/// by setting the default flags (which can be overridden in the expression
/// itself) or setting various limits.
pub struct RegexSetBuilder(RegexOptions);

impl RegexSetBuilder {
    /// Create a new regular expression builder with the given pattern.
    ///
    /// If the pattern is invalid, then an error will be returned when
    /// `build` is called.
    pub fn new<I, S>(patterns: I) -> RegexSetBuilder
            where S: AsRef<str>, I: IntoIterator<Item=S> {
        let mut builder = RegexSetBuilder(RegexOptions::default());
        for pat in patterns {
            builder.0.pats.push(pat.as_ref().to_owned());
        }
        builder
    }

    /// Consume the builder and compile the regular expressions into a set.
    pub fn build(&self) -> Result<RegexSet, Error> {
        ExecBuilder::new_options(self.0.clone())
            .only_utf8($only_utf8)
            .build()
            .map(RegexSet::from)
    }

    /// Set the value for the case insensitive (`i`) flag.
    pub fn case_insensitive(&mut self, yes: bool) -> &mut RegexSetBuilder {
        self.0.case_insensitive = yes;
        self
    }

    /// Set the value for the multi-line matching (`m`) flag.
    pub fn multi_line(&mut self, yes: bool) -> &mut RegexSetBuilder {
        self.0.multi_line = yes;
        self
    }

    /// Set the value for the any character (`s`) flag, where in `.` matches
    /// anything when `s` is set and matches anything except for new line when
    /// it is not set (the default).
    ///
    /// N.B. "matches anything" means "any byte" for `regex::bytes::RegexSet`
    /// expressions and means "any Unicode scalar value" for `regex::RegexSet`
    /// expressions.
    pub fn dot_matches_new_line(&mut self, yes: bool) -> &mut RegexSetBuilder {
        self.0.dot_matches_new_line = yes;
        self
    }

    /// Set the value for the greedy swap (`U`) flag.
    pub fn swap_greed(&mut self, yes: bool) -> &mut RegexSetBuilder {
        self.0.swap_greed = yes;
        self
    }

    /// Set the value for the ignore whitespace (`x`) flag.
    pub fn ignore_whitespace(&mut self, yes: bool) -> &mut RegexSetBuilder {
        self.0.ignore_whitespace = yes;
        self
    }

    /// Set the value for the Unicode (`u`) flag.
    pub fn unicode(&mut self, yes: bool) -> &mut RegexSetBuilder {
        self.0.unicode = yes;
        self
    }

    /// Set the approximate size limit of the compiled regular expression.
    ///
    /// This roughly corresponds to the number of bytes occupied by a single
    /// compiled program. If the program exceeds this number, then a
    /// compilation error is returned.
    pub fn size_limit(&mut self, limit: usize) -> &mut RegexSetBuilder {
        self.0.size_limit = limit;
        self
    }

    /// Set the approximate size of the cache used by the DFA.
    ///
    /// This roughly corresponds to the number of bytes that the DFA will
    /// use while searching.
    ///
    /// Note that this is a *per thread* limit. There is no way to set a global
    /// limit. In particular, if a regex is used from multiple threads
    /// simulanteously, then each thread may use up to the number of bytes
    /// specified here.
    pub fn dfa_size_limit(&mut self, limit: usize) -> &mut RegexSetBuilder {
        self.0.dfa_size_limit = limit;
        self
    }
}
        }
    }
}

define_set_builder!(set_bytes, bytes, false);
define_set_builder!(set_unicode, unicode, true);