forked from pola-rs/polars
-
Notifications
You must be signed in to change notification settings - Fork 0
/
dfa.rs.html
733 lines (705 loc) · 47.1 KB
/
dfa.rs.html
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
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
<!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-automata-0.1.9/src/dfa.rs`."><meta name="keywords" content="rust, rustlang, rust-lang"><title>dfa.rs - source</title><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="../../light.css" id="themeStyle"><link rel="stylesheet" type="text/css" href="../../dark.css" disabled ><link rel="stylesheet" type="text/css" href="../../ayu.css" disabled ><script id="default-settings"></script><script src="../../storage.js"></script><script src="../../crates.js"></script><noscript><link rel="stylesheet" href="../../noscript.css"></noscript><link rel="icon" type="image/svg+xml" href="../../favicon.svg">
<link rel="alternate icon" type="image/png" href="../../favicon-16x16.png">
<link rel="alternate icon" type="image/png" href="../../favicon-32x32.png"><style type="text/css">#crate-search{background-image:url("../../down-arrow.svg");}</style></head><body class="rustdoc source"><!--[if lte IE 8]><div class="warning">This old browser is unsupported and will most likely display funky things.</div><![endif]--><nav class="sidebar"><div class="sidebar-menu" role="button">☰</div><a href='../../regex_automata/index.html'><div class='logo-container rust-logo'><img src='../../rust-logo.png' alt='logo'></div></a></nav><div class="theme-picker"><button id="theme-picker" aria-label="Pick another theme!" aria-haspopup="menu"><img src="../../brush.svg" width="18" height="18" alt="Pick another theme!"></button><div id="theme-choices" role="menu"></div></div><nav class="sub"><form class="search-form"><div class="search-container"><div><select id="crate-search"><option value="All crates">All crates</option></select><input class="search-input" name="search" disabled autocomplete="off" spellcheck="false" placeholder="Click or press ‘S’ to search, ‘?’ for more options…" type="search"></div><button type="button" class="help-button">?</button>
<a id="settings-menu" href="../../settings.html"><img src="../../wheel.svg" width="18" height="18" alt="Change settings"></a></div></form></nav><section id="main" class="content"><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>
<span id="313">313</span>
<span id="314">314</span>
<span id="315">315</span>
<span id="316">316</span>
<span id="317">317</span>
<span id="318">318</span>
<span id="319">319</span>
<span id="320">320</span>
<span id="321">321</span>
<span id="322">322</span>
<span id="323">323</span>
<span id="324">324</span>
<span id="325">325</span>
<span id="326">326</span>
<span id="327">327</span>
<span id="328">328</span>
<span id="329">329</span>
<span id="330">330</span>
<span id="331">331</span>
<span id="332">332</span>
<span id="333">333</span>
<span id="334">334</span>
<span id="335">335</span>
<span id="336">336</span>
<span id="337">337</span>
<span id="338">338</span>
<span id="339">339</span>
<span id="340">340</span>
<span id="341">341</span>
<span id="342">342</span>
<span id="343">343</span>
<span id="344">344</span>
<span id="345">345</span>
<span id="346">346</span>
<span id="347">347</span>
<span id="348">348</span>
<span id="349">349</span>
<span id="350">350</span>
<span id="351">351</span>
<span id="352">352</span>
<span id="353">353</span>
<span id="354">354</span>
<span id="355">355</span>
<span id="356">356</span>
<span id="357">357</span>
<span id="358">358</span>
<span id="359">359</span>
<span id="360">360</span>
<span id="361">361</span>
<span id="362">362</span>
<span id="363">363</span>
</pre><div class="example-wrap"><pre class="rust ">
<span class="kw">use</span> <span class="ident">state_id</span>::<span class="ident">StateID</span>;
<span class="doccomment">/// A trait describing the interface of a deterministic finite automaton (DFA).</span>
<span class="doccomment">///</span>
<span class="doccomment">/// Every DFA has exactly one start state and at least one dead state (which</span>
<span class="doccomment">/// may be the same, as in the case of an empty DFA). In all cases, a state</span>
<span class="doccomment">/// identifier of `0` must be a dead state such that `DFA::is_dead_state(0)`</span>
<span class="doccomment">/// always returns `true`.</span>
<span class="doccomment">///</span>
<span class="doccomment">/// Every DFA also has zero or more match states, such that</span>
<span class="doccomment">/// `DFA::is_match_state(id)` returns `true` if and only if `id` corresponds to</span>
<span class="doccomment">/// a match state.</span>
<span class="doccomment">///</span>
<span class="doccomment">/// In general, users of this trait likely will only need to use the search</span>
<span class="doccomment">/// routines such as `is_match`, `shortest_match`, `find` or `rfind`. The other</span>
<span class="doccomment">/// methods are lower level and are used for walking the transitions of a DFA</span>
<span class="doccomment">/// manually. In particular, the aforementioned search routines are implemented</span>
<span class="doccomment">/// generically in terms of the lower level transition walking routines.</span>
<span class="kw">pub</span> <span class="kw">trait</span> <span class="ident">DFA</span> {
<span class="doccomment">/// The representation used for state identifiers in this DFA.</span>
<span class="doccomment">///</span>
<span class="doccomment">/// Typically, this is one of `u8`, `u16`, `u32`, `u64` or `usize`.</span>
<span class="kw">type</span> <span class="ident">ID</span>: <span class="ident">StateID</span>;
<span class="doccomment">/// Return the identifier of this DFA's start state.</span>
<span class="kw">fn</span> <span class="ident">start_state</span>(<span class="kw-2">&</span><span class="self">self</span>) <span class="op">-</span><span class="op">></span> <span class="self">Self</span>::<span class="ident">ID</span>;
<span class="doccomment">/// Returns true if and only if the given identifier corresponds to a match</span>
<span class="doccomment">/// state.</span>
<span class="kw">fn</span> <span class="ident">is_match_state</span>(<span class="kw-2">&</span><span class="self">self</span>, <span class="ident">id</span>: <span class="self">Self</span>::<span class="ident">ID</span>) <span class="op">-</span><span class="op">></span> <span class="ident">bool</span>;
<span class="doccomment">/// Returns true if and only if the given identifier corresponds to a dead</span>
<span class="doccomment">/// state. When a DFA enters a dead state, it is impossible to leave and</span>
<span class="doccomment">/// thus can never lead to a match.</span>
<span class="kw">fn</span> <span class="ident">is_dead_state</span>(<span class="kw-2">&</span><span class="self">self</span>, <span class="ident">id</span>: <span class="self">Self</span>::<span class="ident">ID</span>) <span class="op">-</span><span class="op">></span> <span class="ident">bool</span>;
<span class="doccomment">/// Returns true if and only if the given identifier corresponds to either</span>
<span class="doccomment">/// a dead state or a match state, such that one of `is_match_state(id)`</span>
<span class="doccomment">/// or `is_dead_state(id)` must return true.</span>
<span class="doccomment">///</span>
<span class="doccomment">/// Depending on the implementation of the DFA, this routine can be used</span>
<span class="doccomment">/// to save a branch in the core matching loop. Nevertheless,</span>
<span class="doccomment">/// `is_match_state(id) || is_dead_state(id)` is always a valid</span>
<span class="doccomment">/// implementation.</span>
<span class="kw">fn</span> <span class="ident">is_match_or_dead_state</span>(<span class="kw-2">&</span><span class="self">self</span>, <span class="ident">id</span>: <span class="self">Self</span>::<span class="ident">ID</span>) <span class="op">-</span><span class="op">></span> <span class="ident">bool</span>;
<span class="doccomment">/// Returns true if and only if this DFA is anchored.</span>
<span class="doccomment">///</span>
<span class="doccomment">/// When a DFA is anchored, it is only allowed to report matches that</span>
<span class="doccomment">/// start at index `0`.</span>
<span class="kw">fn</span> <span class="ident">is_anchored</span>(<span class="kw-2">&</span><span class="self">self</span>) <span class="op">-</span><span class="op">></span> <span class="ident">bool</span>;
<span class="doccomment">/// Given the current state that this DFA is in and the next input byte,</span>
<span class="doccomment">/// this method returns the identifier of the next state. The identifier</span>
<span class="doccomment">/// returned is always valid, but it may correspond to a dead state.</span>
<span class="kw">fn</span> <span class="ident">next_state</span>(<span class="kw-2">&</span><span class="self">self</span>, <span class="ident">current</span>: <span class="self">Self</span>::<span class="ident">ID</span>, <span class="ident">input</span>: <span class="ident">u8</span>) <span class="op">-</span><span class="op">></span> <span class="self">Self</span>::<span class="ident">ID</span>;
<span class="doccomment">/// Like `next_state`, but its implementation may look up the next state</span>
<span class="doccomment">/// without memory safety checks such as bounds checks. As such, callers</span>
<span class="doccomment">/// must ensure that the given identifier corresponds to a valid DFA</span>
<span class="doccomment">/// state. Implementors must, in turn, ensure that this routine is safe</span>
<span class="doccomment">/// for all valid state identifiers and for all possible `u8` values.</span>
<span class="kw">unsafe</span> <span class="kw">fn</span> <span class="ident">next_state_unchecked</span>(
<span class="kw-2">&</span><span class="self">self</span>,
<span class="ident">current</span>: <span class="self">Self</span>::<span class="ident">ID</span>,
<span class="ident">input</span>: <span class="ident">u8</span>,
) <span class="op">-</span><span class="op">></span> <span class="self">Self</span>::<span class="ident">ID</span>;
<span class="doccomment">/// Returns true if and only if the given bytes match this DFA.</span>
<span class="doccomment">///</span>
<span class="doccomment">/// This routine may short circuit if it knows that scanning future input</span>
<span class="doccomment">/// will never lead to a different result. In particular, if a DFA enters</span>
<span class="doccomment">/// a match state or a dead state, then this routine will return `true` or</span>
<span class="doccomment">/// `false`, respectively, without inspecting any future input.</span>
<span class="doccomment">///</span>
<span class="doccomment">/// # Example</span>
<span class="doccomment">///</span>
<span class="doccomment">/// This example shows how to use this method with a</span>
<span class="doccomment">/// [`DenseDFA`](enum.DenseDFA.html).</span>
<span class="doccomment">///</span>
<span class="doccomment">/// ```</span>
<span class="doccomment">/// use regex_automata::{DFA, DenseDFA};</span>
<span class="doccomment">///</span>
<span class="doccomment">/// # fn example() -> Result<(), regex_automata::Error> {</span>
<span class="doccomment">/// let dfa = DenseDFA::new("foo[0-9]+bar")?;</span>
<span class="doccomment">/// assert_eq!(true, dfa.is_match(b"foo12345bar"));</span>
<span class="doccomment">/// assert_eq!(false, dfa.is_match(b"foobar"));</span>
<span class="doccomment">/// # Ok(()) }; example().unwrap()</span>
<span class="doccomment">/// ```</span>
<span class="attribute">#[<span class="ident">inline</span>]</span>
<span class="kw">fn</span> <span class="ident">is_match</span>(<span class="kw-2">&</span><span class="self">self</span>, <span class="ident">bytes</span>: <span class="kw-2">&</span>[<span class="ident">u8</span>]) <span class="op">-</span><span class="op">></span> <span class="ident">bool</span> {
<span class="self">self</span>.<span class="ident">is_match_at</span>(<span class="ident">bytes</span>, <span class="number">0</span>)
}
<span class="doccomment">/// Returns the first position at which a match is found.</span>
<span class="doccomment">///</span>
<span class="doccomment">/// This routine stops scanning input in precisely the same circumstances</span>
<span class="doccomment">/// as `is_match`. The key difference is that this routine returns the</span>
<span class="doccomment">/// position at which it stopped scanning input if and only if a match</span>
<span class="doccomment">/// was found. If no match is found, then `None` is returned.</span>
<span class="doccomment">///</span>
<span class="doccomment">/// # Example</span>
<span class="doccomment">///</span>
<span class="doccomment">/// This example shows how to use this method with a</span>
<span class="doccomment">/// [`DenseDFA`](enum.DenseDFA.html).</span>
<span class="doccomment">///</span>
<span class="doccomment">/// ```</span>
<span class="doccomment">/// use regex_automata::{DFA, DenseDFA};</span>
<span class="doccomment">///</span>
<span class="doccomment">/// # fn example() -> Result<(), regex_automata::Error> {</span>
<span class="doccomment">/// let dfa = DenseDFA::new("foo[0-9]+")?;</span>
<span class="doccomment">/// assert_eq!(Some(4), dfa.shortest_match(b"foo12345"));</span>
<span class="doccomment">///</span>
<span class="doccomment">/// // Normally, the end of the leftmost first match here would be 3,</span>
<span class="doccomment">/// // but the shortest match semantics detect a match earlier.</span>
<span class="doccomment">/// let dfa = DenseDFA::new("abc|a")?;</span>
<span class="doccomment">/// assert_eq!(Some(1), dfa.shortest_match(b"abc"));</span>
<span class="doccomment">/// # Ok(()) }; example().unwrap()</span>
<span class="doccomment">/// ```</span>
<span class="attribute">#[<span class="ident">inline</span>]</span>
<span class="kw">fn</span> <span class="ident">shortest_match</span>(<span class="kw-2">&</span><span class="self">self</span>, <span class="ident">bytes</span>: <span class="kw-2">&</span>[<span class="ident">u8</span>]) <span class="op">-</span><span class="op">></span> <span class="prelude-ty">Option</span><span class="op"><</span><span class="ident">usize</span><span class="op">></span> {
<span class="self">self</span>.<span class="ident">shortest_match_at</span>(<span class="ident">bytes</span>, <span class="number">0</span>)
}
<span class="doccomment">/// Returns the end offset of the longest match. If no match exists,</span>
<span class="doccomment">/// then `None` is returned.</span>
<span class="doccomment">///</span>
<span class="doccomment">/// Implementors of this trait are not required to implement any particular</span>
<span class="doccomment">/// match semantics (such as leftmost-first), which are instead manifest in</span>
<span class="doccomment">/// the DFA's topology itself.</span>
<span class="doccomment">///</span>
<span class="doccomment">/// In particular, this method must continue searching even after it</span>
<span class="doccomment">/// enters a match state. The search should only terminate once it has</span>
<span class="doccomment">/// reached the end of the input or when it has entered a dead state. Upon</span>
<span class="doccomment">/// termination, the position of the last byte seen while still in a match</span>
<span class="doccomment">/// state is returned.</span>
<span class="doccomment">///</span>
<span class="doccomment">/// # Example</span>
<span class="doccomment">///</span>
<span class="doccomment">/// This example shows how to use this method with a</span>
<span class="doccomment">/// [`DenseDFA`](enum.DenseDFA.html). By default, a dense DFA uses</span>
<span class="doccomment">/// "leftmost first" match semantics.</span>
<span class="doccomment">///</span>
<span class="doccomment">/// Leftmost first match semantics corresponds to the match with the</span>
<span class="doccomment">/// smallest starting offset, but where the end offset is determined by</span>
<span class="doccomment">/// preferring earlier branches in the original regular expression. For</span>
<span class="doccomment">/// example, `Sam|Samwise` will match `Sam` in `Samwise`, but `Samwise|Sam`</span>
<span class="doccomment">/// will match `Samwise` in `Samwise`.</span>
<span class="doccomment">///</span>
<span class="doccomment">/// Generally speaking, the "leftmost first" match is how most backtracking</span>
<span class="doccomment">/// regular expressions tend to work. This is in contrast to POSIX-style</span>
<span class="doccomment">/// regular expressions that yield "leftmost longest" matches. Namely,</span>
<span class="doccomment">/// both `Sam|Samwise` and `Samwise|Sam` match `Samwise` when using</span>
<span class="doccomment">/// leftmost longest semantics.</span>
<span class="doccomment">///</span>
<span class="doccomment">/// ```</span>
<span class="doccomment">/// use regex_automata::{DFA, DenseDFA};</span>
<span class="doccomment">///</span>
<span class="doccomment">/// # fn example() -> Result<(), regex_automata::Error> {</span>
<span class="doccomment">/// let dfa = DenseDFA::new("foo[0-9]+")?;</span>
<span class="doccomment">/// assert_eq!(Some(8), dfa.find(b"foo12345"));</span>
<span class="doccomment">///</span>
<span class="doccomment">/// // Even though a match is found after reading the first byte (`a`),</span>
<span class="doccomment">/// // the leftmost first match semantics demand that we find the earliest</span>
<span class="doccomment">/// // match that prefers earlier parts of the pattern over latter parts.</span>
<span class="doccomment">/// let dfa = DenseDFA::new("abc|a")?;</span>
<span class="doccomment">/// assert_eq!(Some(3), dfa.find(b"abc"));</span>
<span class="doccomment">/// # Ok(()) }; example().unwrap()</span>
<span class="doccomment">/// ```</span>
<span class="attribute">#[<span class="ident">inline</span>]</span>
<span class="kw">fn</span> <span class="ident">find</span>(<span class="kw-2">&</span><span class="self">self</span>, <span class="ident">bytes</span>: <span class="kw-2">&</span>[<span class="ident">u8</span>]) <span class="op">-</span><span class="op">></span> <span class="prelude-ty">Option</span><span class="op"><</span><span class="ident">usize</span><span class="op">></span> {
<span class="self">self</span>.<span class="ident">find_at</span>(<span class="ident">bytes</span>, <span class="number">0</span>)
}
<span class="doccomment">/// Returns the start offset of the longest match in reverse, by searching</span>
<span class="doccomment">/// from the end of the input towards the start of the input. If no match</span>
<span class="doccomment">/// exists, then `None` is returned. In other words, this has the same</span>
<span class="doccomment">/// match semantics as `find`, but in reverse.</span>
<span class="doccomment">///</span>
<span class="doccomment">/// # Example</span>
<span class="doccomment">///</span>
<span class="doccomment">/// This example shows how to use this method with a</span>
<span class="doccomment">/// [`DenseDFA`](enum.DenseDFA.html). In particular, this routine</span>
<span class="doccomment">/// is principally useful when used in conjunction with the</span>
<span class="doccomment">/// [`dense::Builder::reverse`](dense/struct.Builder.html#method.reverse)</span>
<span class="doccomment">/// configuration knob. In general, it's unlikely to be correct to use both</span>
<span class="doccomment">/// `find` and `rfind` with the same DFA since any particular DFA will only</span>
<span class="doccomment">/// support searching in one direction.</span>
<span class="doccomment">///</span>
<span class="doccomment">/// ```</span>
<span class="doccomment">/// use regex_automata::{dense, DFA};</span>
<span class="doccomment">///</span>
<span class="doccomment">/// # fn example() -> Result<(), regex_automata::Error> {</span>
<span class="doccomment">/// let dfa = dense::Builder::new().reverse(true).build("foo[0-9]+")?;</span>
<span class="doccomment">/// assert_eq!(Some(0), dfa.rfind(b"foo12345"));</span>
<span class="doccomment">/// # Ok(()) }; example().unwrap()</span>
<span class="doccomment">/// ```</span>
<span class="attribute">#[<span class="ident">inline</span>]</span>
<span class="kw">fn</span> <span class="ident">rfind</span>(<span class="kw-2">&</span><span class="self">self</span>, <span class="ident">bytes</span>: <span class="kw-2">&</span>[<span class="ident">u8</span>]) <span class="op">-</span><span class="op">></span> <span class="prelude-ty">Option</span><span class="op"><</span><span class="ident">usize</span><span class="op">></span> {
<span class="self">self</span>.<span class="ident">rfind_at</span>(<span class="ident">bytes</span>, <span class="ident">bytes</span>.<span class="ident">len</span>())
}
<span class="doccomment">/// Returns the same as `is_match`, but starts the search at the given</span>
<span class="doccomment">/// offset.</span>
<span class="doccomment">///</span>
<span class="doccomment">/// The significance of the starting point is that it takes the surrounding</span>
<span class="doccomment">/// context into consideration. For example, if the DFA is anchored, then</span>
<span class="doccomment">/// a match can only occur when `start == 0`.</span>
<span class="attribute">#[<span class="ident">inline</span>]</span>
<span class="kw">fn</span> <span class="ident">is_match_at</span>(<span class="kw-2">&</span><span class="self">self</span>, <span class="ident">bytes</span>: <span class="kw-2">&</span>[<span class="ident">u8</span>], <span class="ident">start</span>: <span class="ident">usize</span>) <span class="op">-</span><span class="op">></span> <span class="ident">bool</span> {
<span class="kw">if</span> <span class="self">self</span>.<span class="ident">is_anchored</span>() <span class="op">&&</span> <span class="ident">start</span> <span class="op">></span> <span class="number">0</span> {
<span class="kw">return</span> <span class="bool-val">false</span>;
}
<span class="kw">let</span> <span class="kw-2">mut</span> <span class="ident">state</span> <span class="op">=</span> <span class="self">self</span>.<span class="ident">start_state</span>();
<span class="kw">if</span> <span class="self">self</span>.<span class="ident">is_match_or_dead_state</span>(<span class="ident">state</span>) {
<span class="kw">return</span> <span class="self">self</span>.<span class="ident">is_match_state</span>(<span class="ident">state</span>);
}
<span class="kw">for</span> <span class="kw-2">&</span><span class="ident">b</span> <span class="kw">in</span> <span class="ident">bytes</span>[<span class="ident">start</span>..].<span class="ident">iter</span>() {
<span class="ident">state</span> <span class="op">=</span> <span class="kw">unsafe</span> { <span class="self">self</span>.<span class="ident">next_state_unchecked</span>(<span class="ident">state</span>, <span class="ident">b</span>) };
<span class="kw">if</span> <span class="self">self</span>.<span class="ident">is_match_or_dead_state</span>(<span class="ident">state</span>) {
<span class="kw">return</span> <span class="self">self</span>.<span class="ident">is_match_state</span>(<span class="ident">state</span>);
}
}
<span class="bool-val">false</span>
}
<span class="doccomment">/// Returns the same as `shortest_match`, but starts the search at the</span>
<span class="doccomment">/// given offset.</span>
<span class="doccomment">///</span>
<span class="doccomment">/// The significance of the starting point is that it takes the surrounding</span>
<span class="doccomment">/// context into consideration. For example, if the DFA is anchored, then</span>
<span class="doccomment">/// a match can only occur when `start == 0`.</span>
<span class="attribute">#[<span class="ident">inline</span>]</span>
<span class="kw">fn</span> <span class="ident">shortest_match_at</span>(<span class="kw-2">&</span><span class="self">self</span>, <span class="ident">bytes</span>: <span class="kw-2">&</span>[<span class="ident">u8</span>], <span class="ident">start</span>: <span class="ident">usize</span>) <span class="op">-</span><span class="op">></span> <span class="prelude-ty">Option</span><span class="op"><</span><span class="ident">usize</span><span class="op">></span> {
<span class="kw">if</span> <span class="self">self</span>.<span class="ident">is_anchored</span>() <span class="op">&&</span> <span class="ident">start</span> <span class="op">></span> <span class="number">0</span> {
<span class="kw">return</span> <span class="prelude-val">None</span>;
}
<span class="kw">let</span> <span class="kw-2">mut</span> <span class="ident">state</span> <span class="op">=</span> <span class="self">self</span>.<span class="ident">start_state</span>();
<span class="kw">if</span> <span class="self">self</span>.<span class="ident">is_match_or_dead_state</span>(<span class="ident">state</span>) {
<span class="kw">return</span> <span class="kw">if</span> <span class="self">self</span>.<span class="ident">is_dead_state</span>(<span class="ident">state</span>) { <span class="prelude-val">None</span> } <span class="kw">else</span> { <span class="prelude-val">Some</span>(<span class="ident">start</span>) };
}
<span class="kw">for</span> (<span class="ident">i</span>, <span class="kw-2">&</span><span class="ident">b</span>) <span class="kw">in</span> <span class="ident">bytes</span>[<span class="ident">start</span>..].<span class="ident">iter</span>().<span class="ident">enumerate</span>() {
<span class="ident">state</span> <span class="op">=</span> <span class="kw">unsafe</span> { <span class="self">self</span>.<span class="ident">next_state_unchecked</span>(<span class="ident">state</span>, <span class="ident">b</span>) };
<span class="kw">if</span> <span class="self">self</span>.<span class="ident">is_match_or_dead_state</span>(<span class="ident">state</span>) {
<span class="kw">return</span> <span class="kw">if</span> <span class="self">self</span>.<span class="ident">is_dead_state</span>(<span class="ident">state</span>) {
<span class="prelude-val">None</span>
} <span class="kw">else</span> {
<span class="prelude-val">Some</span>(<span class="ident">start</span> <span class="op">+</span> <span class="ident">i</span> <span class="op">+</span> <span class="number">1</span>)
};
}
}
<span class="prelude-val">None</span>
}
<span class="doccomment">/// Returns the same as `find`, but starts the search at the given</span>
<span class="doccomment">/// offset.</span>
<span class="doccomment">///</span>
<span class="doccomment">/// The significance of the starting point is that it takes the surrounding</span>
<span class="doccomment">/// context into consideration. For example, if the DFA is anchored, then</span>
<span class="doccomment">/// a match can only occur when `start == 0`.</span>
<span class="attribute">#[<span class="ident">inline</span>]</span>
<span class="kw">fn</span> <span class="ident">find_at</span>(<span class="kw-2">&</span><span class="self">self</span>, <span class="ident">bytes</span>: <span class="kw-2">&</span>[<span class="ident">u8</span>], <span class="ident">start</span>: <span class="ident">usize</span>) <span class="op">-</span><span class="op">></span> <span class="prelude-ty">Option</span><span class="op"><</span><span class="ident">usize</span><span class="op">></span> {
<span class="kw">if</span> <span class="self">self</span>.<span class="ident">is_anchored</span>() <span class="op">&&</span> <span class="ident">start</span> <span class="op">></span> <span class="number">0</span> {
<span class="kw">return</span> <span class="prelude-val">None</span>;
}
<span class="kw">let</span> <span class="kw-2">mut</span> <span class="ident">state</span> <span class="op">=</span> <span class="self">self</span>.<span class="ident">start_state</span>();
<span class="kw">let</span> <span class="kw-2">mut</span> <span class="ident">last_match</span> <span class="op">=</span> <span class="kw">if</span> <span class="self">self</span>.<span class="ident">is_dead_state</span>(<span class="ident">state</span>) {
<span class="kw">return</span> <span class="prelude-val">None</span>;
} <span class="kw">else</span> <span class="kw">if</span> <span class="self">self</span>.<span class="ident">is_match_state</span>(<span class="ident">state</span>) {
<span class="prelude-val">Some</span>(<span class="ident">start</span>)
} <span class="kw">else</span> {
<span class="prelude-val">None</span>
};
<span class="kw">for</span> (<span class="ident">i</span>, <span class="kw-2">&</span><span class="ident">b</span>) <span class="kw">in</span> <span class="ident">bytes</span>[<span class="ident">start</span>..].<span class="ident">iter</span>().<span class="ident">enumerate</span>() {
<span class="ident">state</span> <span class="op">=</span> <span class="kw">unsafe</span> { <span class="self">self</span>.<span class="ident">next_state_unchecked</span>(<span class="ident">state</span>, <span class="ident">b</span>) };
<span class="kw">if</span> <span class="self">self</span>.<span class="ident">is_match_or_dead_state</span>(<span class="ident">state</span>) {
<span class="kw">if</span> <span class="self">self</span>.<span class="ident">is_dead_state</span>(<span class="ident">state</span>) {
<span class="kw">return</span> <span class="ident">last_match</span>;
}
<span class="ident">last_match</span> <span class="op">=</span> <span class="prelude-val">Some</span>(<span class="ident">start</span> <span class="op">+</span> <span class="ident">i</span> <span class="op">+</span> <span class="number">1</span>);
}
}
<span class="ident">last_match</span>
}
<span class="doccomment">/// Returns the same as `rfind`, but starts the search at the given</span>
<span class="doccomment">/// offset.</span>
<span class="doccomment">///</span>
<span class="doccomment">/// The significance of the starting point is that it takes the surrounding</span>
<span class="doccomment">/// context into consideration. For example, if the DFA is anchored, then</span>
<span class="doccomment">/// a match can only occur when `start == bytes.len()`.</span>
<span class="attribute">#[<span class="ident">inline</span>(<span class="ident">never</span>)]</span>
<span class="kw">fn</span> <span class="ident">rfind_at</span>(<span class="kw-2">&</span><span class="self">self</span>, <span class="ident">bytes</span>: <span class="kw-2">&</span>[<span class="ident">u8</span>], <span class="ident">start</span>: <span class="ident">usize</span>) <span class="op">-</span><span class="op">></span> <span class="prelude-ty">Option</span><span class="op"><</span><span class="ident">usize</span><span class="op">></span> {
<span class="kw">if</span> <span class="self">self</span>.<span class="ident">is_anchored</span>() <span class="op">&&</span> <span class="ident">start</span> <span class="op"><</span> <span class="ident">bytes</span>.<span class="ident">len</span>() {
<span class="kw">return</span> <span class="prelude-val">None</span>;
}
<span class="kw">let</span> <span class="kw-2">mut</span> <span class="ident">state</span> <span class="op">=</span> <span class="self">self</span>.<span class="ident">start_state</span>();
<span class="kw">let</span> <span class="kw-2">mut</span> <span class="ident">last_match</span> <span class="op">=</span> <span class="kw">if</span> <span class="self">self</span>.<span class="ident">is_dead_state</span>(<span class="ident">state</span>) {
<span class="kw">return</span> <span class="prelude-val">None</span>;
} <span class="kw">else</span> <span class="kw">if</span> <span class="self">self</span>.<span class="ident">is_match_state</span>(<span class="ident">state</span>) {
<span class="prelude-val">Some</span>(<span class="ident">start</span>)
} <span class="kw">else</span> {
<span class="prelude-val">None</span>
};
<span class="kw">for</span> (<span class="ident">i</span>, <span class="kw-2">&</span><span class="ident">b</span>) <span class="kw">in</span> <span class="ident">bytes</span>[..<span class="ident">start</span>].<span class="ident">iter</span>().<span class="ident">enumerate</span>().<span class="ident">rev</span>() {
<span class="ident">state</span> <span class="op">=</span> <span class="kw">unsafe</span> { <span class="self">self</span>.<span class="ident">next_state_unchecked</span>(<span class="ident">state</span>, <span class="ident">b</span>) };
<span class="kw">if</span> <span class="self">self</span>.<span class="ident">is_match_or_dead_state</span>(<span class="ident">state</span>) {
<span class="kw">if</span> <span class="self">self</span>.<span class="ident">is_dead_state</span>(<span class="ident">state</span>) {
<span class="kw">return</span> <span class="ident">last_match</span>;
}
<span class="ident">last_match</span> <span class="op">=</span> <span class="prelude-val">Some</span>(<span class="ident">i</span>);
}
}
<span class="ident">last_match</span>
}
}
<span class="kw">impl</span><span class="op"><</span><span class="lifetime">'a</span>, <span class="ident">T</span>: <span class="ident">DFA</span><span class="op">></span> <span class="ident">DFA</span> <span class="kw">for</span> <span class="kw-2">&</span><span class="lifetime">'a</span> <span class="ident">T</span> {
<span class="kw">type</span> <span class="ident">ID</span> <span class="op">=</span> <span class="ident">T</span>::<span class="ident">ID</span>;
<span class="attribute">#[<span class="ident">inline</span>]</span>
<span class="kw">fn</span> <span class="ident">start_state</span>(<span class="kw-2">&</span><span class="self">self</span>) <span class="op">-</span><span class="op">></span> <span class="self">Self</span>::<span class="ident">ID</span> {
(<span class="kw-2">*</span><span class="kw-2">*</span><span class="self">self</span>).<span class="ident">start_state</span>()
}
<span class="attribute">#[<span class="ident">inline</span>]</span>
<span class="kw">fn</span> <span class="ident">is_match_state</span>(<span class="kw-2">&</span><span class="self">self</span>, <span class="ident">id</span>: <span class="self">Self</span>::<span class="ident">ID</span>) <span class="op">-</span><span class="op">></span> <span class="ident">bool</span> {
(<span class="kw-2">*</span><span class="kw-2">*</span><span class="self">self</span>).<span class="ident">is_match_state</span>(<span class="ident">id</span>)
}
<span class="attribute">#[<span class="ident">inline</span>]</span>
<span class="kw">fn</span> <span class="ident">is_match_or_dead_state</span>(<span class="kw-2">&</span><span class="self">self</span>, <span class="ident">id</span>: <span class="self">Self</span>::<span class="ident">ID</span>) <span class="op">-</span><span class="op">></span> <span class="ident">bool</span> {
(<span class="kw-2">*</span><span class="kw-2">*</span><span class="self">self</span>).<span class="ident">is_match_or_dead_state</span>(<span class="ident">id</span>)
}
<span class="attribute">#[<span class="ident">inline</span>]</span>
<span class="kw">fn</span> <span class="ident">is_dead_state</span>(<span class="kw-2">&</span><span class="self">self</span>, <span class="ident">id</span>: <span class="self">Self</span>::<span class="ident">ID</span>) <span class="op">-</span><span class="op">></span> <span class="ident">bool</span> {
(<span class="kw-2">*</span><span class="kw-2">*</span><span class="self">self</span>).<span class="ident">is_dead_state</span>(<span class="ident">id</span>)
}
<span class="attribute">#[<span class="ident">inline</span>]</span>
<span class="kw">fn</span> <span class="ident">is_anchored</span>(<span class="kw-2">&</span><span class="self">self</span>) <span class="op">-</span><span class="op">></span> <span class="ident">bool</span> {
(<span class="kw-2">*</span><span class="kw-2">*</span><span class="self">self</span>).<span class="ident">is_anchored</span>()
}
<span class="attribute">#[<span class="ident">inline</span>]</span>
<span class="kw">fn</span> <span class="ident">next_state</span>(<span class="kw-2">&</span><span class="self">self</span>, <span class="ident">current</span>: <span class="self">Self</span>::<span class="ident">ID</span>, <span class="ident">input</span>: <span class="ident">u8</span>) <span class="op">-</span><span class="op">></span> <span class="self">Self</span>::<span class="ident">ID</span> {
(<span class="kw-2">*</span><span class="kw-2">*</span><span class="self">self</span>).<span class="ident">next_state</span>(<span class="ident">current</span>, <span class="ident">input</span>)
}
<span class="attribute">#[<span class="ident">inline</span>]</span>
<span class="kw">unsafe</span> <span class="kw">fn</span> <span class="ident">next_state_unchecked</span>(
<span class="kw-2">&</span><span class="self">self</span>,
<span class="ident">current</span>: <span class="self">Self</span>::<span class="ident">ID</span>,
<span class="ident">input</span>: <span class="ident">u8</span>,
) <span class="op">-</span><span class="op">></span> <span class="self">Self</span>::<span class="ident">ID</span> {
(<span class="kw-2">*</span><span class="kw-2">*</span><span class="self">self</span>).<span class="ident">next_state_unchecked</span>(<span class="ident">current</span>, <span class="ident">input</span>)
}
}
</pre></div>
</section><section id="search" class="content hidden"></section><section class="footer"></section><div id="rustdoc-vars" data-root-path="../../" data-current-crate="regex_automata" data-search-js="../../search-index.js"></div>
<script src="../../main.js"></script><script src="../../source-script.js"></script><script src="../../source-files.js"></script></body></html>