forked from diesel-rs/diesel
-
Notifications
You must be signed in to change notification settings - Fork 0
Expand file tree
/
Copy pathlib.rs.html
More file actions
633 lines (587 loc) · 32.9 KB
/
Copy pathlib.rs.html
File metadata and controls
633 lines (587 loc) · 32.9 KB
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
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
<!DOCTYPE html><html lang="en"><head><meta charset="utf-8"><meta name="viewport" content="width=device-width, initial-scale=1.0"><meta name="generator" content="rustdoc"><meta name="description" content="Source of the Rust file `/home/runner/.cargo/registry/src/github.com-1ecc6299db9ec823/regex-syntax-0.6.26/src/lib.rs`."><meta name="keywords" content="rust, rustlang, rust-lang"><title>lib.rs - source</title><link rel="preload" as="font" type="font/woff2" crossorigin href="../../SourceSerif4-Regular.ttf.woff2"><link rel="preload" as="font" type="font/woff2" crossorigin href="../../FiraSans-Regular.woff2"><link rel="preload" as="font" type="font/woff2" crossorigin href="../../FiraSans-Medium.woff2"><link rel="preload" as="font" type="font/woff2" crossorigin href="../../SourceCodePro-Regular.ttf.woff2"><link rel="preload" as="font" type="font/woff2" crossorigin href="../../SourceSerif4-Bold.ttf.woff2"><link rel="preload" as="font" type="font/woff2" crossorigin href="../../SourceCodePro-Semibold.ttf.woff2"><link rel="stylesheet" type="text/css" href="../../normalize.css"><link rel="stylesheet" type="text/css" href="../../rustdoc.css" id="mainThemeStyle"><link rel="stylesheet" type="text/css" href="../../ayu.css" disabled><link rel="stylesheet" type="text/css" href="../../dark.css" disabled><link rel="stylesheet" type="text/css" href="../../light.css" id="themeStyle"><script id="default-settings" ></script><script src="../../storage.js"></script><script defer src="../../source-script.js"></script><script defer src="../../source-files.js"></script><script defer src="../../main.js"></script><noscript><link rel="stylesheet" href="../../noscript.css"></noscript><link rel="alternate icon" type="image/png" href="../../favicon-16x16.png"><link rel="alternate icon" type="image/png" href="../../favicon-32x32.png"><link rel="icon" type="image/svg+xml" href="../../favicon.svg"></head><body class="rustdoc source"><!--[if lte IE 11]><div class="warning">This old browser is unsupported and will most likely display funky things.</div><![endif]--><nav class="mobile-topbar"><button class="sidebar-menu-toggle">☰</button><a class="sidebar-logo" href="../../regex_syntax/index.html"><div class="logo-container"><img class="rust-logo" src="../../rust-logo.svg" alt="logo"></div>
</a><h2 class="location"></h2>
</nav>
<nav class="sidebar"><a class="sidebar-logo" href="../../regex_syntax/index.html"><div class="logo-container"><img class="rust-logo" src="../../rust-logo.svg" alt="logo"></div>
</a></nav><main><div class="width-limiter"><div class="sub-container"><a class="sub-logo-container" href="../../regex_syntax/index.html"><img class="rust-logo" src="../../rust-logo.svg" alt="logo"></a><nav class="sub"><form class="search-form"><div class="search-container"><span></span><input class="search-input" name="search" autocomplete="off" spellcheck="false" placeholder="Click or press ‘S’ to search, ‘?’ for more options…" type="search"><div id="help-button" title="help" tabindex="-1"><button type="button">?</button></div><div id="settings-menu" tabindex="-1">
<a href="../../settings.html" title="settings"><img width="22" height="22" alt="Change settings" src="../../wheel.svg"></a></div>
</div></form></nav></div><section id="main-content" class="content"><div class="example-wrap"><pre class="line-numbers"><span id="1">1</span>
<span id="2">2</span>
<span id="3">3</span>
<span id="4">4</span>
<span id="5">5</span>
<span id="6">6</span>
<span id="7">7</span>
<span id="8">8</span>
<span id="9">9</span>
<span id="10">10</span>
<span id="11">11</span>
<span id="12">12</span>
<span id="13">13</span>
<span id="14">14</span>
<span id="15">15</span>
<span id="16">16</span>
<span id="17">17</span>
<span id="18">18</span>
<span id="19">19</span>
<span id="20">20</span>
<span id="21">21</span>
<span id="22">22</span>
<span id="23">23</span>
<span id="24">24</span>
<span id="25">25</span>
<span id="26">26</span>
<span id="27">27</span>
<span id="28">28</span>
<span id="29">29</span>
<span id="30">30</span>
<span id="31">31</span>
<span id="32">32</span>
<span id="33">33</span>
<span id="34">34</span>
<span id="35">35</span>
<span id="36">36</span>
<span id="37">37</span>
<span id="38">38</span>
<span id="39">39</span>
<span id="40">40</span>
<span id="41">41</span>
<span id="42">42</span>
<span id="43">43</span>
<span id="44">44</span>
<span id="45">45</span>
<span id="46">46</span>
<span id="47">47</span>
<span id="48">48</span>
<span id="49">49</span>
<span id="50">50</span>
<span id="51">51</span>
<span id="52">52</span>
<span id="53">53</span>
<span id="54">54</span>
<span id="55">55</span>
<span id="56">56</span>
<span id="57">57</span>
<span id="58">58</span>
<span id="59">59</span>
<span id="60">60</span>
<span id="61">61</span>
<span id="62">62</span>
<span id="63">63</span>
<span id="64">64</span>
<span id="65">65</span>
<span id="66">66</span>
<span id="67">67</span>
<span id="68">68</span>
<span id="69">69</span>
<span id="70">70</span>
<span id="71">71</span>
<span id="72">72</span>
<span id="73">73</span>
<span id="74">74</span>
<span id="75">75</span>
<span id="76">76</span>
<span id="77">77</span>
<span id="78">78</span>
<span id="79">79</span>
<span id="80">80</span>
<span id="81">81</span>
<span id="82">82</span>
<span id="83">83</span>
<span id="84">84</span>
<span id="85">85</span>
<span id="86">86</span>
<span id="87">87</span>
<span id="88">88</span>
<span id="89">89</span>
<span id="90">90</span>
<span id="91">91</span>
<span id="92">92</span>
<span id="93">93</span>
<span id="94">94</span>
<span id="95">95</span>
<span id="96">96</span>
<span id="97">97</span>
<span id="98">98</span>
<span id="99">99</span>
<span id="100">100</span>
<span id="101">101</span>
<span id="102">102</span>
<span id="103">103</span>
<span id="104">104</span>
<span id="105">105</span>
<span id="106">106</span>
<span id="107">107</span>
<span id="108">108</span>
<span id="109">109</span>
<span id="110">110</span>
<span id="111">111</span>
<span id="112">112</span>
<span id="113">113</span>
<span id="114">114</span>
<span id="115">115</span>
<span id="116">116</span>
<span id="117">117</span>
<span id="118">118</span>
<span id="119">119</span>
<span id="120">120</span>
<span id="121">121</span>
<span id="122">122</span>
<span id="123">123</span>
<span id="124">124</span>
<span id="125">125</span>
<span id="126">126</span>
<span id="127">127</span>
<span id="128">128</span>
<span id="129">129</span>
<span id="130">130</span>
<span id="131">131</span>
<span id="132">132</span>
<span id="133">133</span>
<span id="134">134</span>
<span id="135">135</span>
<span id="136">136</span>
<span id="137">137</span>
<span id="138">138</span>
<span id="139">139</span>
<span id="140">140</span>
<span id="141">141</span>
<span id="142">142</span>
<span id="143">143</span>
<span id="144">144</span>
<span id="145">145</span>
<span id="146">146</span>
<span id="147">147</span>
<span id="148">148</span>
<span id="149">149</span>
<span id="150">150</span>
<span id="151">151</span>
<span id="152">152</span>
<span id="153">153</span>
<span id="154">154</span>
<span id="155">155</span>
<span id="156">156</span>
<span id="157">157</span>
<span id="158">158</span>
<span id="159">159</span>
<span id="160">160</span>
<span id="161">161</span>
<span id="162">162</span>
<span id="163">163</span>
<span id="164">164</span>
<span id="165">165</span>
<span id="166">166</span>
<span id="167">167</span>
<span id="168">168</span>
<span id="169">169</span>
<span id="170">170</span>
<span id="171">171</span>
<span id="172">172</span>
<span id="173">173</span>
<span id="174">174</span>
<span id="175">175</span>
<span id="176">176</span>
<span id="177">177</span>
<span id="178">178</span>
<span id="179">179</span>
<span id="180">180</span>
<span id="181">181</span>
<span id="182">182</span>
<span id="183">183</span>
<span id="184">184</span>
<span id="185">185</span>
<span id="186">186</span>
<span id="187">187</span>
<span id="188">188</span>
<span id="189">189</span>
<span id="190">190</span>
<span id="191">191</span>
<span id="192">192</span>
<span id="193">193</span>
<span id="194">194</span>
<span id="195">195</span>
<span id="196">196</span>
<span id="197">197</span>
<span id="198">198</span>
<span id="199">199</span>
<span id="200">200</span>
<span id="201">201</span>
<span id="202">202</span>
<span id="203">203</span>
<span id="204">204</span>
<span id="205">205</span>
<span id="206">206</span>
<span id="207">207</span>
<span id="208">208</span>
<span id="209">209</span>
<span id="210">210</span>
<span id="211">211</span>
<span id="212">212</span>
<span id="213">213</span>
<span id="214">214</span>
<span id="215">215</span>
<span id="216">216</span>
<span id="217">217</span>
<span id="218">218</span>
<span id="219">219</span>
<span id="220">220</span>
<span id="221">221</span>
<span id="222">222</span>
<span id="223">223</span>
<span id="224">224</span>
<span id="225">225</span>
<span id="226">226</span>
<span id="227">227</span>
<span id="228">228</span>
<span id="229">229</span>
<span id="230">230</span>
<span id="231">231</span>
<span id="232">232</span>
<span id="233">233</span>
<span id="234">234</span>
<span id="235">235</span>
<span id="236">236</span>
<span id="237">237</span>
<span id="238">238</span>
<span id="239">239</span>
<span id="240">240</span>
<span id="241">241</span>
<span id="242">242</span>
<span id="243">243</span>
<span id="244">244</span>
<span id="245">245</span>
<span id="246">246</span>
<span id="247">247</span>
<span id="248">248</span>
<span id="249">249</span>
<span id="250">250</span>
<span id="251">251</span>
<span id="252">252</span>
<span id="253">253</span>
<span id="254">254</span>
<span id="255">255</span>
<span id="256">256</span>
<span id="257">257</span>
<span id="258">258</span>
<span id="259">259</span>
<span id="260">260</span>
<span id="261">261</span>
<span id="262">262</span>
<span id="263">263</span>
<span id="264">264</span>
<span id="265">265</span>
<span id="266">266</span>
<span id="267">267</span>
<span id="268">268</span>
<span id="269">269</span>
<span id="270">270</span>
<span id="271">271</span>
<span id="272">272</span>
<span id="273">273</span>
<span id="274">274</span>
<span id="275">275</span>
<span id="276">276</span>
<span id="277">277</span>
<span id="278">278</span>
<span id="279">279</span>
<span id="280">280</span>
<span id="281">281</span>
<span id="282">282</span>
<span id="283">283</span>
<span id="284">284</span>
<span id="285">285</span>
<span id="286">286</span>
<span id="287">287</span>
<span id="288">288</span>
<span id="289">289</span>
<span id="290">290</span>
<span id="291">291</span>
<span id="292">292</span>
<span id="293">293</span>
<span id="294">294</span>
<span id="295">295</span>
<span id="296">296</span>
<span id="297">297</span>
<span id="298">298</span>
<span id="299">299</span>
<span id="300">300</span>
<span id="301">301</span>
<span id="302">302</span>
<span id="303">303</span>
<span id="304">304</span>
<span id="305">305</span>
<span id="306">306</span>
<span id="307">307</span>
<span id="308">308</span>
<span id="309">309</span>
<span id="310">310</span>
<span id="311">311</span>
<span id="312">312</span>
</pre><pre class="rust"><code><span class="doccomment">/*!
This crate provides a robust regular expression parser.
This crate defines two primary types:
* [`Ast`](ast/enum.Ast.html) is the abstract syntax of a regular expression.
An abstract syntax corresponds to a *structured representation* of the
concrete syntax of a regular expression, where the concrete syntax is the
pattern string itself (e.g., `foo(bar)+`). Given some abstract syntax, it
can be converted back to the original concrete syntax (modulo some details,
like whitespace). To a first approximation, the abstract syntax is complex
and difficult to analyze.
* [`Hir`](hir/struct.Hir.html) is the high-level intermediate representation
("HIR" or "high-level IR" for short) of regular expression. It corresponds to
an intermediate state of a regular expression that sits between the abstract
syntax and the low level compiled opcodes that are eventually responsible for
executing a regular expression search. Given some high-level IR, it is not
possible to produce the original concrete syntax (although it is possible to
produce an equivalent concrete syntax, but it will likely scarcely resemble
the original pattern). To a first approximation, the high-level IR is simple
and easy to analyze.
These two types come with conversion routines:
* An [`ast::parse::Parser`](ast/parse/struct.Parser.html) converts concrete
syntax (a `&str`) to an [`Ast`](ast/enum.Ast.html).
* A [`hir::translate::Translator`](hir/translate/struct.Translator.html)
converts an [`Ast`](ast/enum.Ast.html) to a [`Hir`](hir/struct.Hir.html).
As a convenience, the above two conversion routines are combined into one via
the top-level [`Parser`](struct.Parser.html) type. This `Parser` will first
convert your pattern to an `Ast` and then convert the `Ast` to an `Hir`.
# Example
This example shows how to parse a pattern string into its HIR:
```
use regex_syntax::Parser;
use regex_syntax::hir::{self, Hir};
let hir = Parser::new().parse("a|b").unwrap();
assert_eq!(hir, Hir::alternation(vec![
Hir::literal(hir::Literal::Unicode('a')),
Hir::literal(hir::Literal::Unicode('b')),
]));
```
# Concrete syntax supported
The concrete syntax is documented as part of the public API of the
[`regex` crate](https://docs.rs/regex/%2A/regex/#syntax).
# Input safety
A key feature of this library is that it is safe to use with end user facing
input. This plays a significant role in the internal implementation. In
particular:
1. Parsers provide a `nest_limit` option that permits callers to control how
deeply nested a regular expression is allowed to be. This makes it possible
to do case analysis over an `Ast` or an `Hir` using recursion without
worrying about stack overflow.
2. Since relying on a particular stack size is brittle, this crate goes to
great lengths to ensure that all interactions with both the `Ast` and the
`Hir` do not use recursion. Namely, they use constant stack space and heap
space proportional to the size of the original pattern string (in bytes).
This includes the type's corresponding destructors. (One exception to this
is literal extraction, but this will eventually get fixed.)
# Error reporting
The `Display` implementations on all `Error` types exposed in this library
provide nice human readable errors that are suitable for showing to end users
in a monospace font.
# Literal extraction
This crate provides limited support for
[literal extraction from `Hir` values](hir/literal/struct.Literals.html).
Be warned that literal extraction currently uses recursion, and therefore,
stack size proportional to the size of the `Hir`.
The purpose of literal extraction is to speed up searches. That is, if you
know a regular expression must match a prefix or suffix literal, then it is
often quicker to search for instances of that literal, and then confirm or deny
the match using the full regular expression engine. These optimizations are
done automatically in the `regex` crate.
# Crate features
An important feature provided by this crate is its Unicode support. This
includes things like case folding, boolean properties, general categories,
scripts and Unicode-aware support for the Perl classes `\w`, `\s` and `\d`.
However, a downside of this support is that it requires bundling several
Unicode data tables that are substantial in size.
A fair number of use cases do not require full Unicode support. For this
reason, this crate exposes a number of features to control which Unicode
data is available.
If a regular expression attempts to use a Unicode feature that is not available
because the corresponding crate feature was disabled, then translating that
regular expression to an `Hir` will return an error. (It is still possible
construct an `Ast` for such a regular expression, since Unicode data is not
used until translation to an `Hir`.) Stated differently, enabling or disabling
any of the features below can only add or subtract from the total set of valid
regular expressions. Enabling or disabling a feature will never modify the
match semantics of a regular expression.
The following features are available:
* **unicode** -
Enables all Unicode features. This feature is enabled by default, and will
always cover all Unicode features, even if more are added in the future.
* **unicode-age** -
Provide the data for the
[Unicode `Age` property](https://www.unicode.org/reports/tr44/tr44-24.html#Character_Age).
This makes it possible to use classes like `\p{Age:6.0}` to refer to all
codepoints first introduced in Unicode 6.0
* **unicode-bool** -
Provide the data for numerous Unicode boolean properties. The full list
is not included here, but contains properties like `Alphabetic`, `Emoji`,
`Lowercase`, `Math`, `Uppercase` and `White_Space`.
* **unicode-case** -
Provide the data for case insensitive matching using
[Unicode's "simple loose matches" specification](https://www.unicode.org/reports/tr18/#Simple_Loose_Matches).
* **unicode-gencat** -
Provide the data for
[Uncode general categories](https://www.unicode.org/reports/tr44/tr44-24.html#General_Category_Values).
This includes, but is not limited to, `Decimal_Number`, `Letter`,
`Math_Symbol`, `Number` and `Punctuation`.
* **unicode-perl** -
Provide the data for supporting the Unicode-aware Perl character classes,
corresponding to `\w`, `\s` and `\d`. This is also necessary for using
Unicode-aware word boundary assertions. Note that if this feature is
disabled, the `\s` and `\d` character classes are still available if the
`unicode-bool` and `unicode-gencat` features are enabled, respectively.
* **unicode-script** -
Provide the data for
[Unicode scripts and script extensions](https://www.unicode.org/reports/tr24/).
This includes, but is not limited to, `Arabic`, `Cyrillic`, `Hebrew`,
`Latin` and `Thai`.
* **unicode-segment** -
Provide the data necessary to provide the properties used to implement the
[Unicode text segmentation algorithms](https://www.unicode.org/reports/tr29/).
This enables using classes like `\p{gcb=Extend}`, `\p{wb=Katakana}` and
`\p{sb=ATerm}`.
*/</span>
<span class="attribute">#![<span class="ident">deny</span>(<span class="ident">missing_docs</span>)]</span>
<span class="attribute">#![<span class="ident">warn</span>(<span class="ident">missing_debug_implementations</span>)]</span>
<span class="attribute">#![<span class="ident">forbid</span>(<span class="ident">unsafe_code</span>)]</span>
<span class="kw">pub</span> <span class="kw">use</span> <span class="ident"><span class="kw">crate</span>::error</span>::{<span class="ident">Error</span>, <span class="prelude-ty">Result</span>};
<span class="kw">pub</span> <span class="kw">use</span> <span class="ident"><span class="kw">crate</span>::parser</span>::{<span class="ident">Parser</span>, <span class="ident">ParserBuilder</span>};
<span class="kw">pub</span> <span class="kw">use</span> <span class="ident"><span class="kw">crate</span>::unicode::UnicodeWordError</span>;
<span class="kw">pub</span> <span class="kw">mod</span> <span class="ident">ast</span>;
<span class="kw">mod</span> <span class="ident">either</span>;
<span class="kw">mod</span> <span class="ident">error</span>;
<span class="kw">pub</span> <span class="kw">mod</span> <span class="ident">hir</span>;
<span class="kw">mod</span> <span class="ident">parser</span>;
<span class="kw">mod</span> <span class="ident">unicode</span>;
<span class="kw">mod</span> <span class="ident">unicode_tables</span>;
<span class="kw">pub</span> <span class="kw">mod</span> <span class="ident">utf8</span>;
<span class="doccomment">/// Escapes all regular expression meta characters in `text`.</span>
<span class="doccomment">///</span>
<span class="doccomment">/// The string returned may be safely used as a literal in a regular</span>
<span class="doccomment">/// expression.</span>
<span class="kw">pub</span> <span class="kw">fn</span> <span class="ident">escape</span>(<span class="ident">text</span>: <span class="kw-2">&</span><span class="ident">str</span>) -> <span class="ident">String</span> {
<span class="kw">let</span> <span class="kw-2">mut</span> <span class="ident">quoted</span> <span class="op">=</span> <span class="ident">String::new</span>();
<span class="ident">escape_into</span>(<span class="ident">text</span>, <span class="kw-2">&mut</span> <span class="ident">quoted</span>);
<span class="ident">quoted</span>
}
<span class="doccomment">/// Escapes all meta characters in `text` and writes the result into `buf`.</span>
<span class="doccomment">///</span>
<span class="doccomment">/// This will append escape characters into the given buffer. The characters</span>
<span class="doccomment">/// that are appended are safe to use as a literal in a regular expression.</span>
<span class="kw">pub</span> <span class="kw">fn</span> <span class="ident">escape_into</span>(<span class="ident">text</span>: <span class="kw-2">&</span><span class="ident">str</span>, <span class="ident">buf</span>: <span class="kw-2">&mut</span> <span class="ident">String</span>) {
<span class="ident">buf</span>.<span class="ident">reserve</span>(<span class="ident">text</span>.<span class="ident">len</span>());
<span class="kw">for</span> <span class="ident">c</span> <span class="kw">in</span> <span class="ident">text</span>.<span class="ident">chars</span>() {
<span class="kw">if</span> <span class="ident">is_meta_character</span>(<span class="ident">c</span>) {
<span class="ident">buf</span>.<span class="ident">push</span>(<span class="string">'\\'</span>);
}
<span class="ident">buf</span>.<span class="ident">push</span>(<span class="ident">c</span>);
}
}
<span class="doccomment">/// Returns true if the give character has significance in a regex.</span>
<span class="doccomment">///</span>
<span class="doccomment">/// These are the only characters that are allowed to be escaped, with one</span>
<span class="doccomment">/// exception: an ASCII space character may be escaped when extended mode (with</span>
<span class="doccomment">/// the `x` flag) is enabled. In particular, `is_meta_character(' ')` returns</span>
<span class="doccomment">/// `false`.</span>
<span class="doccomment">///</span>
<span class="doccomment">/// Note that the set of characters for which this function returns `true` or</span>
<span class="doccomment">/// `false` is fixed and won't change in a semver compatible release.</span>
<span class="kw">pub</span> <span class="kw">fn</span> <span class="ident">is_meta_character</span>(<span class="ident">c</span>: <span class="ident">char</span>) -> <span class="ident">bool</span> {
<span class="kw">match</span> <span class="ident">c</span> {
<span class="string">'\\'</span> <span class="op">|</span> <span class="string">'.'</span> <span class="op">|</span> <span class="string">'+'</span> <span class="op">|</span> <span class="string">'*'</span> <span class="op">|</span> <span class="string">'?'</span> <span class="op">|</span> <span class="string">'('</span> <span class="op">|</span> <span class="string">')'</span> <span class="op">|</span> <span class="string">'|'</span> <span class="op">|</span> <span class="string">'['</span> <span class="op">|</span> <span class="string">']'</span> <span class="op">|</span> <span class="string">'{'</span>
<span class="op">|</span> <span class="string">'}'</span> <span class="op">|</span> <span class="string">'^'</span> <span class="op">|</span> <span class="string">'$'</span> <span class="op">|</span> <span class="string">'#'</span> <span class="op">|</span> <span class="string">'&'</span> <span class="op">|</span> <span class="string">'-'</span> <span class="op">|</span> <span class="string">'~'</span> => <span class="bool-val">true</span>,
<span class="kw">_</span> => <span class="bool-val">false</span>,
}
}
<span class="doccomment">/// Returns true if and only if the given character is a Unicode word</span>
<span class="doccomment">/// character.</span>
<span class="doccomment">///</span>
<span class="doccomment">/// A Unicode word character is defined by</span>
<span class="doccomment">/// [UTS#18 Annex C](https://unicode.org/reports/tr18/#Compatibility_Properties).</span>
<span class="doccomment">/// In particular, a character</span>
<span class="doccomment">/// is considered a word character if it is in either of the `Alphabetic` or</span>
<span class="doccomment">/// `Join_Control` properties, or is in one of the `Decimal_Number`, `Mark`</span>
<span class="doccomment">/// or `Connector_Punctuation` general categories.</span>
<span class="doccomment">///</span>
<span class="doccomment">/// # Panics</span>
<span class="doccomment">///</span>
<span class="doccomment">/// If the `unicode-perl` feature is not enabled, then this function panics.</span>
<span class="doccomment">/// For this reason, it is recommended that callers use</span>
<span class="doccomment">/// [`try_is_word_character`](fn.try_is_word_character.html)</span>
<span class="doccomment">/// instead.</span>
<span class="kw">pub</span> <span class="kw">fn</span> <span class="ident">is_word_character</span>(<span class="ident">c</span>: <span class="ident">char</span>) -> <span class="ident">bool</span> {
<span class="ident">try_is_word_character</span>(<span class="ident">c</span>).<span class="ident">expect</span>(<span class="string">"unicode-perl feature must be enabled"</span>)
}
<span class="doccomment">/// Returns true if and only if the given character is a Unicode word</span>
<span class="doccomment">/// character.</span>
<span class="doccomment">///</span>
<span class="doccomment">/// A Unicode word character is defined by</span>
<span class="doccomment">/// [UTS#18 Annex C](https://unicode.org/reports/tr18/#Compatibility_Properties).</span>
<span class="doccomment">/// In particular, a character</span>
<span class="doccomment">/// is considered a word character if it is in either of the `Alphabetic` or</span>
<span class="doccomment">/// `Join_Control` properties, or is in one of the `Decimal_Number`, `Mark`</span>
<span class="doccomment">/// or `Connector_Punctuation` general categories.</span>
<span class="doccomment">///</span>
<span class="doccomment">/// # Errors</span>
<span class="doccomment">///</span>
<span class="doccomment">/// If the `unicode-perl` feature is not enabled, then this function always</span>
<span class="doccomment">/// returns an error.</span>
<span class="kw">pub</span> <span class="kw">fn</span> <span class="ident">try_is_word_character</span>(
<span class="ident">c</span>: <span class="ident">char</span>,
) -> <span class="ident">std::result::Result</span><span class="op"><</span><span class="ident">bool</span>, <span class="ident">UnicodeWordError</span><span class="op">></span> {
<span class="ident">unicode::is_word_character</span>(<span class="ident">c</span>)
}
<span class="doccomment">/// Returns true if and only if the given character is an ASCII word character.</span>
<span class="doccomment">///</span>
<span class="doccomment">/// An ASCII word character is defined by the following character class:</span>
<span class="doccomment">/// `[_0-9a-zA-Z]'.</span>
<span class="kw">pub</span> <span class="kw">fn</span> <span class="ident">is_word_byte</span>(<span class="ident">c</span>: <span class="ident">u8</span>) -> <span class="ident">bool</span> {
<span class="kw">match</span> <span class="ident">c</span> {
<span class="string">b'_'</span> <span class="op">|</span> <span class="string">b'0'</span>..<span class="op">=</span><span class="string">b'9'</span> <span class="op">|</span> <span class="string">b'a'</span>..<span class="op">=</span><span class="string">b'z'</span> <span class="op">|</span> <span class="string">b'A'</span>..<span class="op">=</span><span class="string">b'Z'</span> => <span class="bool-val">true</span>,
<span class="kw">_</span> => <span class="bool-val">false</span>,
}
}
<span class="attribute">#[<span class="ident">cfg</span>(<span class="ident">test</span>)]</span>
<span class="kw">mod</span> <span class="ident">tests</span> {
<span class="kw">use</span> <span class="kw">super</span>::<span class="kw-2">*</span>;
<span class="attribute">#[<span class="ident">test</span>]</span>
<span class="kw">fn</span> <span class="ident">escape_meta</span>() {
<span class="macro">assert_eq!</span>(
<span class="ident">escape</span>(<span class="string">r"\.+*?()|[]{}^$#&-~"</span>),
<span class="string">r"\\\.\+\*\?\(\)\|\[\]\{\}\^\$\#\&\-\~"</span>.<span class="ident">to_string</span>()
);
}
<span class="attribute">#[<span class="ident">test</span>]</span>
<span class="kw">fn</span> <span class="ident">word_byte</span>() {
<span class="macro">assert!</span>(<span class="ident">is_word_byte</span>(<span class="string">b'a'</span>));
<span class="macro">assert!</span>(<span class="op">!</span><span class="ident">is_word_byte</span>(<span class="string">b'-'</span>));
}
<span class="attribute">#[<span class="ident">test</span>]</span>
<span class="attribute">#[<span class="ident">cfg</span>(<span class="ident">feature</span> <span class="op">=</span> <span class="string">"unicode-perl"</span>)]</span>
<span class="kw">fn</span> <span class="ident">word_char</span>() {
<span class="macro">assert!</span>(<span class="ident">is_word_character</span>(<span class="string">'a'</span>), <span class="string">"ASCII"</span>);
<span class="macro">assert!</span>(<span class="ident">is_word_character</span>(<span class="string">'à'</span>), <span class="string">"Latin-1"</span>);
<span class="macro">assert!</span>(<span class="ident">is_word_character</span>(<span class="string">'β'</span>), <span class="string">"Greek"</span>);
<span class="macro">assert!</span>(<span class="ident">is_word_character</span>(<span class="string">'\u{11011}'</span>), <span class="string">"Brahmi (Unicode 6.0)"</span>);
<span class="macro">assert!</span>(<span class="ident">is_word_character</span>(<span class="string">'\u{11611}'</span>), <span class="string">"Modi (Unicode 7.0)"</span>);
<span class="macro">assert!</span>(<span class="ident">is_word_character</span>(<span class="string">'\u{11711}'</span>), <span class="string">"Ahom (Unicode 8.0)"</span>);
<span class="macro">assert!</span>(<span class="ident">is_word_character</span>(<span class="string">'\u{17828}'</span>), <span class="string">"Tangut (Unicode 9.0)"</span>);
<span class="macro">assert!</span>(<span class="ident">is_word_character</span>(<span class="string">'\u{1B1B1}'</span>), <span class="string">"Nushu (Unicode 10.0)"</span>);
<span class="macro">assert!</span>(<span class="ident">is_word_character</span>(<span class="string">'\u{16E40}'</span>), <span class="string">"Medefaidrin (Unicode 11.0)"</span>);
<span class="macro">assert!</span>(<span class="op">!</span><span class="ident">is_word_character</span>(<span class="string">'-'</span>));
<span class="macro">assert!</span>(<span class="op">!</span><span class="ident">is_word_character</span>(<span class="string">'☃'</span>));
}
<span class="attribute">#[<span class="ident">test</span>]</span>
<span class="attribute">#[<span class="ident">should_panic</span>]</span>
<span class="attribute">#[<span class="ident">cfg</span>(<span class="ident">not</span>(<span class="ident">feature</span> <span class="op">=</span> <span class="string">"unicode-perl"</span>))]</span>
<span class="kw">fn</span> <span class="ident">word_char_disabled_panic</span>() {
<span class="macro">assert!</span>(<span class="ident">is_word_character</span>(<span class="string">'a'</span>));
}
<span class="attribute">#[<span class="ident">test</span>]</span>
<span class="attribute">#[<span class="ident">cfg</span>(<span class="ident">not</span>(<span class="ident">feature</span> <span class="op">=</span> <span class="string">"unicode-perl"</span>))]</span>
<span class="kw">fn</span> <span class="ident">word_char_disabled_error</span>() {
<span class="macro">assert!</span>(<span class="ident">try_is_word_character</span>(<span class="string">'a'</span>).<span class="ident">is_err</span>());
}
}
</code></pre></div>
</section></div></main><div id="rustdoc-vars" data-root-path="../../" data-current-crate="regex_syntax" data-themes="ayu,dark,light" data-resource-suffix="" data-rustdoc-version="1.64.0-nightly (495b21669 2022-07-03)" ></div>
</body></html>