-
Notifications
You must be signed in to change notification settings - Fork 47
/
regexp.html
1609 lines (1336 loc) · 157 KB
/
regexp.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
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
993
994
995
996
997
998
999
1000
<!DOCTYPE html>
<head>
<meta charset="utf-8">
<meta name="viewport" content="width=device-width, initial-scale=1.0">
<meta name="theme-color" content="#2D2D2D" />
<title>NLTK :: nltk.chunk.regexp</title>
<link rel="stylesheet" href="../../../_static/css/nltk_theme.css"/>
<link rel="stylesheet" href="../../../_static/css/custom.css"/>
<script type="text/javascript" id="documentation_options" data-url_root="../../../" src="../../../_static/documentation_options.js"></script>
<script type="text/javascript" src="../../../_static/documentation_options.js"></script>
<script type="text/javascript" src="../../../_static/jquery.js"></script>
<script type="text/javascript" src="../../../_static/underscore.js"></script>
<script type="text/javascript" src="../../../_static/doctools.js"></script>
<script src="https://email.tl.fortawesome.com/c/eJxNjUEOgyAQAF8jR7Kw6wIHDh7sP1Cw2mgxgmn6-3JsMqc5zEQfE8dkxOY1KKMUOI3ACFKRJpSW2AAp7ontYIaxI6i7XPJVwyeVfCQ550Os3jLrGSNOLgbdAy6s0PBk2TFNjEbsfq31LB0OnX407pJa5v2faRadwSW63mn5KuLyR9j2tgx3zecanl-55R_-jjPs"></script>
</head>
<body>
<div id="nltk-theme-container">
<header>
<div id="logo-container">
<h1>
<a href="../../../index.html">NLTK</a>
</h1>
</div>
<div id="project-container">
<h1>Documentation</h1>
</div>
<a id="menu-toggle" class="fa fa-bars" aria-hidden="true"></a>
<script type="text/javascript">
$("#menu-toggle").click(function() {
$("#menu-toggle").toggleClass("toggled");
$("#side-menu-container").slideToggle(300);
});
</script>
</header>
<div id="content-container">
<div id="side-menu-container">
<div id="search" role="search">
<form id="rtd-search-form" class="wy-form" action="../../../search.html" method="get">
<input type="text" name="q" placeholder="Search" />
<input type="hidden" name="check_keywords" value="yes" />
<input type="hidden" name="area" value="default" />
</form>
</div>
<div id="side-menu" role="navigation">
<p class="caption" role="heading"><span class="caption-text">NLTK Documentation</span></p>
<ul>
<li class="toctree-l1"><a class="reference internal" href="../../../api/nltk.html">API Reference</a></li>
<li class="toctree-l1"><a class="reference external" href="http://www.nltk.org/howto">Example Usage</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../py-modindex.html">Module Index</a></li>
<li class="toctree-l1"><a class="reference external" href="https://github.com/nltk/nltk/wiki">Wiki</a></li>
<li class="toctree-l1"><a class="reference external" href="https://github.com/nltk/nltk/wiki/FAQ">FAQ</a></li>
</ul>
<p class="caption" role="heading"><span class="caption-text">Installation</span></p>
<ul>
<li class="toctree-l1"><a class="reference internal" href="../../../install.html">Installing NLTK</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../data.html">Installing NLTK Data</a></li>
</ul>
<p class="caption" role="heading"><span class="caption-text">More</span></p>
<ul>
<li class="toctree-l1"><a class="reference internal" href="../../../news.html">Release Notes</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../contribute.html">Contributing to NLTK</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../team.html">NLTK Team</a></li>
</ul>
</div>
</div>
<div id="main-content-container">
<div id="main-content" role="main">
<h1>Source code for nltk.chunk.regexp</h1><div class="highlight"><pre>
<span></span><span class="c1"># Natural Language Toolkit: Regular Expression Chunkers</span>
<span class="c1">#</span>
<span class="c1"># Copyright (C) 2001-2021 NLTK Project</span>
<span class="c1"># Author: Edward Loper <edloper@gmail.com></span>
<span class="c1"># Steven Bird <stevenbird1@gmail.com> (minor additions)</span>
<span class="c1"># URL: <http://nltk.org/></span>
<span class="c1"># For license information, see LICENSE.TXT</span>
<span class="kn">import</span> <span class="nn">re</span>
<span class="kn">from</span> <span class="nn">nltk.chunk.api</span> <span class="kn">import</span> <span class="n">ChunkParserI</span>
<span class="kn">from</span> <span class="nn">nltk.tree</span> <span class="kn">import</span> <span class="n">Tree</span>
<span class="c1"># //////////////////////////////////////////////////////</span>
<span class="c1"># ChunkString</span>
<span class="c1"># //////////////////////////////////////////////////////</span>
<div class="viewcode-block" id="ChunkString"><a class="viewcode-back" href="../../../api/nltk.chunk.regexp.html#nltk.chunk.regexp.ChunkString">[docs]</a><span class="k">class</span> <span class="nc">ChunkString</span><span class="p">:</span>
<span class="sd">"""</span>
<span class="sd"> A string-based encoding of a particular chunking of a text.</span>
<span class="sd"> Internally, the ``ChunkString`` class uses a single string to</span>
<span class="sd"> encode the chunking of the input text. This string contains a</span>
<span class="sd"> sequence of angle-bracket delimited tags, with chunking indicated</span>
<span class="sd"> by braces. An example of this encoding is::</span>
<span class="sd"> {<DT><JJ><NN>}<VBN><IN>{<DT><NN>}<.>{<DT><NN>}<VBD><.></span>
<span class="sd"> ``ChunkString`` are created from tagged texts (i.e., lists of</span>
<span class="sd"> ``tokens`` whose type is ``TaggedType``). Initially, nothing is</span>
<span class="sd"> chunked.</span>
<span class="sd"> The chunking of a ``ChunkString`` can be modified with the ``xform()``</span>
<span class="sd"> method, which uses a regular expression to transform the string</span>
<span class="sd"> representation. These transformations should only add and remove</span>
<span class="sd"> braces; they should *not* modify the sequence of angle-bracket</span>
<span class="sd"> delimited tags.</span>
<span class="sd"> :type _str: str</span>
<span class="sd"> :ivar _str: The internal string representation of the text's</span>
<span class="sd"> encoding. This string representation contains a sequence of</span>
<span class="sd"> angle-bracket delimited tags, with chunking indicated by</span>
<span class="sd"> braces. An example of this encoding is::</span>
<span class="sd"> {<DT><JJ><NN>}<VBN><IN>{<DT><NN>}<.>{<DT><NN>}<VBD><.></span>
<span class="sd"> :type _pieces: list(tagged tokens and chunks)</span>
<span class="sd"> :ivar _pieces: The tagged tokens and chunks encoded by this ``ChunkString``.</span>
<span class="sd"> :ivar _debug: The debug level. See the constructor docs.</span>
<span class="sd"> :cvar IN_CHUNK_PATTERN: A zero-width regexp pattern string that</span>
<span class="sd"> will only match positions that are in chunks.</span>
<span class="sd"> :cvar IN_STRIP_PATTERN: A zero-width regexp pattern string that</span>
<span class="sd"> will only match positions that are in strips.</span>
<span class="sd"> """</span>
<span class="n">CHUNK_TAG_CHAR</span> <span class="o">=</span> <span class="sa">r</span><span class="s2">"[^\{\}<>]"</span>
<span class="n">CHUNK_TAG</span> <span class="o">=</span> <span class="sa">r</span><span class="s2">"(<</span><span class="si">%s</span><span class="s2">+?>)"</span> <span class="o">%</span> <span class="n">CHUNK_TAG_CHAR</span>
<span class="n">IN_CHUNK_PATTERN</span> <span class="o">=</span> <span class="sa">r</span><span class="s2">"(?=[^\{]*\})"</span>
<span class="n">IN_STRIP_PATTERN</span> <span class="o">=</span> <span class="sa">r</span><span class="s2">"(?=[^\}]*(\{|$))"</span>
<span class="c1"># These are used by _verify</span>
<span class="n">_CHUNK</span> <span class="o">=</span> <span class="sa">r</span><span class="s2">"(\{</span><span class="si">%s</span><span class="s2">+?\})+?"</span> <span class="o">%</span> <span class="n">CHUNK_TAG</span>
<span class="n">_STRIP</span> <span class="o">=</span> <span class="sa">r</span><span class="s2">"(</span><span class="si">%s</span><span class="s2">+?)+?"</span> <span class="o">%</span> <span class="n">CHUNK_TAG</span>
<span class="n">_VALID</span> <span class="o">=</span> <span class="n">re</span><span class="o">.</span><span class="n">compile</span><span class="p">(</span><span class="sa">r</span><span class="s2">"^(\{?</span><span class="si">%s</span><span class="s2">\}?)*?$"</span> <span class="o">%</span> <span class="n">CHUNK_TAG</span><span class="p">)</span>
<span class="n">_BRACKETS</span> <span class="o">=</span> <span class="n">re</span><span class="o">.</span><span class="n">compile</span><span class="p">(</span><span class="sa">r</span><span class="s2">"[^\{\}]+"</span><span class="p">)</span>
<span class="n">_BALANCED_BRACKETS</span> <span class="o">=</span> <span class="n">re</span><span class="o">.</span><span class="n">compile</span><span class="p">(</span><span class="sa">r</span><span class="s2">"(\{\})*$"</span><span class="p">)</span>
<div class="viewcode-block" id="ChunkString.__init__"><a class="viewcode-back" href="../../../api/nltk.chunk.regexp.html#nltk.chunk.regexp.ChunkString.__init__">[docs]</a> <span class="k">def</span> <span class="fm">__init__</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">chunk_struct</span><span class="p">,</span> <span class="n">debug_level</span><span class="o">=</span><span class="mi">1</span><span class="p">):</span>
<span class="sd">"""</span>
<span class="sd"> Construct a new ``ChunkString`` that encodes the chunking of</span>
<span class="sd"> the text ``tagged_tokens``.</span>
<span class="sd"> :type chunk_struct: Tree</span>
<span class="sd"> :param chunk_struct: The chunk structure to be further chunked.</span>
<span class="sd"> :type debug_level: int</span>
<span class="sd"> :param debug_level: The level of debugging which should be</span>
<span class="sd"> applied to transformations on the ``ChunkString``. The</span>
<span class="sd"> valid levels are:</span>
<span class="sd"> - 0: no checks</span>
<span class="sd"> - 1: full check on to_chunkstruct</span>
<span class="sd"> - 2: full check on to_chunkstruct and cursory check after</span>
<span class="sd"> each transformation.</span>
<span class="sd"> - 3: full check on to_chunkstruct and full check after</span>
<span class="sd"> each transformation.</span>
<span class="sd"> We recommend you use at least level 1. You should</span>
<span class="sd"> probably use level 3 if you use any non-standard</span>
<span class="sd"> subclasses of ``RegexpChunkRule``.</span>
<span class="sd"> """</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_root_label</span> <span class="o">=</span> <span class="n">chunk_struct</span><span class="o">.</span><span class="n">label</span><span class="p">()</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_pieces</span> <span class="o">=</span> <span class="n">chunk_struct</span><span class="p">[:]</span>
<span class="n">tags</span> <span class="o">=</span> <span class="p">[</span><span class="bp">self</span><span class="o">.</span><span class="n">_tag</span><span class="p">(</span><span class="n">tok</span><span class="p">)</span> <span class="k">for</span> <span class="n">tok</span> <span class="ow">in</span> <span class="bp">self</span><span class="o">.</span><span class="n">_pieces</span><span class="p">]</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_str</span> <span class="o">=</span> <span class="s2">"<"</span> <span class="o">+</span> <span class="s2">"><"</span><span class="o">.</span><span class="n">join</span><span class="p">(</span><span class="n">tags</span><span class="p">)</span> <span class="o">+</span> <span class="s2">">"</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_debug</span> <span class="o">=</span> <span class="n">debug_level</span></div>
<span class="k">def</span> <span class="nf">_tag</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">tok</span><span class="p">):</span>
<span class="k">if</span> <span class="nb">isinstance</span><span class="p">(</span><span class="n">tok</span><span class="p">,</span> <span class="nb">tuple</span><span class="p">):</span>
<span class="k">return</span> <span class="n">tok</span><span class="p">[</span><span class="mi">1</span><span class="p">]</span>
<span class="k">elif</span> <span class="nb">isinstance</span><span class="p">(</span><span class="n">tok</span><span class="p">,</span> <span class="n">Tree</span><span class="p">):</span>
<span class="k">return</span> <span class="n">tok</span><span class="o">.</span><span class="n">label</span><span class="p">()</span>
<span class="k">else</span><span class="p">:</span>
<span class="k">raise</span> <span class="ne">ValueError</span><span class="p">(</span><span class="s2">"chunk structures must contain tagged "</span> <span class="s2">"tokens or trees"</span><span class="p">)</span>
<span class="k">def</span> <span class="nf">_verify</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">s</span><span class="p">,</span> <span class="n">verify_tags</span><span class="p">):</span>
<span class="sd">"""</span>
<span class="sd"> Check to make sure that ``s`` still corresponds to some chunked</span>
<span class="sd"> version of ``_pieces``.</span>
<span class="sd"> :type verify_tags: bool</span>
<span class="sd"> :param verify_tags: Whether the individual tags should be</span>
<span class="sd"> checked. If this is false, ``_verify`` will check to make</span>
<span class="sd"> sure that ``_str`` encodes a chunked version of *some*</span>
<span class="sd"> list of tokens. If this is true, then ``_verify`` will</span>
<span class="sd"> check to make sure that the tags in ``_str`` match those in</span>
<span class="sd"> ``_pieces``.</span>
<span class="sd"> :raise ValueError: if the internal string representation of</span>
<span class="sd"> this ``ChunkString`` is invalid or not consistent with _pieces.</span>
<span class="sd"> """</span>
<span class="c1"># Check overall form</span>
<span class="k">if</span> <span class="ow">not</span> <span class="n">ChunkString</span><span class="o">.</span><span class="n">_VALID</span><span class="o">.</span><span class="n">match</span><span class="p">(</span><span class="n">s</span><span class="p">):</span>
<span class="k">raise</span> <span class="ne">ValueError</span><span class="p">(</span>
<span class="s2">"Transformation generated invalid "</span> <span class="s2">"chunkstring:</span><span class="se">\n</span><span class="s2"> </span><span class="si">%s</span><span class="s2">"</span> <span class="o">%</span> <span class="n">s</span>
<span class="p">)</span>
<span class="c1"># Check that parens are balanced. If the string is long, we</span>
<span class="c1"># have to do this in pieces, to avoid a maximum recursion</span>
<span class="c1"># depth limit for regular expressions.</span>
<span class="n">brackets</span> <span class="o">=</span> <span class="n">ChunkString</span><span class="o">.</span><span class="n">_BRACKETS</span><span class="o">.</span><span class="n">sub</span><span class="p">(</span><span class="s2">""</span><span class="p">,</span> <span class="n">s</span><span class="p">)</span>
<span class="k">for</span> <span class="n">i</span> <span class="ow">in</span> <span class="nb">range</span><span class="p">(</span><span class="mi">1</span> <span class="o">+</span> <span class="nb">len</span><span class="p">(</span><span class="n">brackets</span><span class="p">)</span> <span class="o">//</span> <span class="mi">5000</span><span class="p">):</span>
<span class="n">substr</span> <span class="o">=</span> <span class="n">brackets</span><span class="p">[</span><span class="n">i</span> <span class="o">*</span> <span class="mi">5000</span> <span class="p">:</span> <span class="n">i</span> <span class="o">*</span> <span class="mi">5000</span> <span class="o">+</span> <span class="mi">5000</span><span class="p">]</span>
<span class="k">if</span> <span class="ow">not</span> <span class="n">ChunkString</span><span class="o">.</span><span class="n">_BALANCED_BRACKETS</span><span class="o">.</span><span class="n">match</span><span class="p">(</span><span class="n">substr</span><span class="p">):</span>
<span class="k">raise</span> <span class="ne">ValueError</span><span class="p">(</span>
<span class="s2">"Transformation generated invalid "</span> <span class="s2">"chunkstring:</span><span class="se">\n</span><span class="s2"> </span><span class="si">%s</span><span class="s2">"</span> <span class="o">%</span> <span class="n">s</span>
<span class="p">)</span>
<span class="k">if</span> <span class="n">verify_tags</span> <span class="o"><=</span> <span class="mi">0</span><span class="p">:</span>
<span class="k">return</span>
<span class="n">tags1</span> <span class="o">=</span> <span class="p">(</span><span class="n">re</span><span class="o">.</span><span class="n">split</span><span class="p">(</span><span class="sa">r</span><span class="s2">"[\{\}<>]+"</span><span class="p">,</span> <span class="n">s</span><span class="p">))[</span><span class="mi">1</span><span class="p">:</span><span class="o">-</span><span class="mi">1</span><span class="p">]</span>
<span class="n">tags2</span> <span class="o">=</span> <span class="p">[</span><span class="bp">self</span><span class="o">.</span><span class="n">_tag</span><span class="p">(</span><span class="n">piece</span><span class="p">)</span> <span class="k">for</span> <span class="n">piece</span> <span class="ow">in</span> <span class="bp">self</span><span class="o">.</span><span class="n">_pieces</span><span class="p">]</span>
<span class="k">if</span> <span class="n">tags1</span> <span class="o">!=</span> <span class="n">tags2</span><span class="p">:</span>
<span class="k">raise</span> <span class="ne">ValueError</span><span class="p">(</span>
<span class="s2">"Transformation generated invalid "</span> <span class="s2">"chunkstring: tag changed"</span>
<span class="p">)</span>
<div class="viewcode-block" id="ChunkString.to_chunkstruct"><a class="viewcode-back" href="../../../api/nltk.chunk.regexp.html#nltk.chunk.regexp.ChunkString.to_chunkstruct">[docs]</a> <span class="k">def</span> <span class="nf">to_chunkstruct</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">chunk_label</span><span class="o">=</span><span class="s2">"CHUNK"</span><span class="p">):</span>
<span class="sd">"""</span>
<span class="sd"> Return the chunk structure encoded by this ``ChunkString``.</span>
<span class="sd"> :rtype: Tree</span>
<span class="sd"> :raise ValueError: If a transformation has generated an</span>
<span class="sd"> invalid chunkstring.</span>
<span class="sd"> """</span>
<span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">_debug</span> <span class="o">></span> <span class="mi">0</span><span class="p">:</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_verify</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">_str</span><span class="p">,</span> <span class="mi">1</span><span class="p">)</span>
<span class="c1"># Use this alternating list to create the chunkstruct.</span>
<span class="n">pieces</span> <span class="o">=</span> <span class="p">[]</span>
<span class="n">index</span> <span class="o">=</span> <span class="mi">0</span>
<span class="n">piece_in_chunk</span> <span class="o">=</span> <span class="mi">0</span>
<span class="k">for</span> <span class="n">piece</span> <span class="ow">in</span> <span class="n">re</span><span class="o">.</span><span class="n">split</span><span class="p">(</span><span class="s2">"[</span><span class="si">{}</span><span class="s2">]"</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">_str</span><span class="p">):</span>
<span class="c1"># Find the list of tokens contained in this piece.</span>
<span class="n">length</span> <span class="o">=</span> <span class="n">piece</span><span class="o">.</span><span class="n">count</span><span class="p">(</span><span class="s2">"<"</span><span class="p">)</span>
<span class="n">subsequence</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">_pieces</span><span class="p">[</span><span class="n">index</span> <span class="p">:</span> <span class="n">index</span> <span class="o">+</span> <span class="n">length</span><span class="p">]</span>
<span class="c1"># Add this list of tokens to our pieces.</span>
<span class="k">if</span> <span class="n">piece_in_chunk</span><span class="p">:</span>
<span class="n">pieces</span><span class="o">.</span><span class="n">append</span><span class="p">(</span><span class="n">Tree</span><span class="p">(</span><span class="n">chunk_label</span><span class="p">,</span> <span class="n">subsequence</span><span class="p">))</span>
<span class="k">else</span><span class="p">:</span>
<span class="n">pieces</span> <span class="o">+=</span> <span class="n">subsequence</span>
<span class="c1"># Update index, piece_in_chunk</span>
<span class="n">index</span> <span class="o">+=</span> <span class="n">length</span>
<span class="n">piece_in_chunk</span> <span class="o">=</span> <span class="ow">not</span> <span class="n">piece_in_chunk</span>
<span class="k">return</span> <span class="n">Tree</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">_root_label</span><span class="p">,</span> <span class="n">pieces</span><span class="p">)</span></div>
<div class="viewcode-block" id="ChunkString.xform"><a class="viewcode-back" href="../../../api/nltk.chunk.regexp.html#nltk.chunk.regexp.ChunkString.xform">[docs]</a> <span class="k">def</span> <span class="nf">xform</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">regexp</span><span class="p">,</span> <span class="n">repl</span><span class="p">):</span>
<span class="sd">"""</span>
<span class="sd"> Apply the given transformation to the string encoding of this</span>
<span class="sd"> ``ChunkString``. In particular, find all occurrences that match</span>
<span class="sd"> ``regexp``, and replace them using ``repl`` (as done by</span>
<span class="sd"> ``re.sub``).</span>
<span class="sd"> This transformation should only add and remove braces; it</span>
<span class="sd"> should *not* modify the sequence of angle-bracket delimited</span>
<span class="sd"> tags. Furthermore, this transformation may not result in</span>
<span class="sd"> improper bracketing. Note, in particular, that bracketing may</span>
<span class="sd"> not be nested.</span>
<span class="sd"> :type regexp: str or regexp</span>
<span class="sd"> :param regexp: A regular expression matching the substring</span>
<span class="sd"> that should be replaced. This will typically include a</span>
<span class="sd"> named group, which can be used by ``repl``.</span>
<span class="sd"> :type repl: str</span>
<span class="sd"> :param repl: An expression specifying what should replace the</span>
<span class="sd"> matched substring. Typically, this will include a named</span>
<span class="sd"> replacement group, specified by ``regexp``.</span>
<span class="sd"> :rtype: None</span>
<span class="sd"> :raise ValueError: If this transformation generated an</span>
<span class="sd"> invalid chunkstring.</span>
<span class="sd"> """</span>
<span class="c1"># Do the actual substitution</span>
<span class="n">s</span> <span class="o">=</span> <span class="n">re</span><span class="o">.</span><span class="n">sub</span><span class="p">(</span><span class="n">regexp</span><span class="p">,</span> <span class="n">repl</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">_str</span><span class="p">)</span>
<span class="c1"># The substitution might have generated "empty chunks"</span>
<span class="c1"># (substrings of the form "{}"). Remove them, so they don't</span>
<span class="c1"># interfere with other transformations.</span>
<span class="n">s</span> <span class="o">=</span> <span class="n">re</span><span class="o">.</span><span class="n">sub</span><span class="p">(</span><span class="sa">r</span><span class="s2">"\{\}"</span><span class="p">,</span> <span class="s2">""</span><span class="p">,</span> <span class="n">s</span><span class="p">)</span>
<span class="c1"># Make sure that the transformation was legal.</span>
<span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">_debug</span> <span class="o">></span> <span class="mi">1</span><span class="p">:</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_verify</span><span class="p">(</span><span class="n">s</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">_debug</span> <span class="o">-</span> <span class="mi">2</span><span class="p">)</span>
<span class="c1"># Commit the transformation.</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_str</span> <span class="o">=</span> <span class="n">s</span></div>
<span class="k">def</span> <span class="fm">__repr__</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span>
<span class="sd">"""</span>
<span class="sd"> Return a string representation of this ``ChunkString``.</span>
<span class="sd"> It has the form::</span>
<span class="sd"> <ChunkString: '{<DT><JJ><NN>}<VBN><IN>{<DT><NN>}'></span>
<span class="sd"> :rtype: str</span>
<span class="sd"> """</span>
<span class="k">return</span> <span class="s2">"<ChunkString: </span><span class="si">%s</span><span class="s2">>"</span> <span class="o">%</span> <span class="nb">repr</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">_str</span><span class="p">)</span>
<span class="k">def</span> <span class="fm">__str__</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span>
<span class="sd">"""</span>
<span class="sd"> Return a formatted representation of this ``ChunkString``.</span>
<span class="sd"> This representation will include extra spaces to ensure that</span>
<span class="sd"> tags will line up with the representation of other</span>
<span class="sd"> ``ChunkStrings`` for the same text, regardless of the chunking.</span>
<span class="sd"> :rtype: str</span>
<span class="sd"> """</span>
<span class="c1"># Add spaces to make everything line up.</span>
<span class="nb">str</span> <span class="o">=</span> <span class="n">re</span><span class="o">.</span><span class="n">sub</span><span class="p">(</span><span class="sa">r</span><span class="s2">">(?!\})"</span><span class="p">,</span> <span class="sa">r</span><span class="s2">"> "</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">_str</span><span class="p">)</span>
<span class="nb">str</span> <span class="o">=</span> <span class="n">re</span><span class="o">.</span><span class="n">sub</span><span class="p">(</span><span class="sa">r</span><span class="s2">"([^\{])<"</span><span class="p">,</span> <span class="sa">r</span><span class="s2">"\1 <"</span><span class="p">,</span> <span class="nb">str</span><span class="p">)</span>
<span class="k">if</span> <span class="nb">str</span><span class="p">[</span><span class="mi">0</span><span class="p">]</span> <span class="o">==</span> <span class="s2">"<"</span><span class="p">:</span>
<span class="nb">str</span> <span class="o">=</span> <span class="s2">" "</span> <span class="o">+</span> <span class="nb">str</span>
<span class="k">return</span> <span class="nb">str</span></div>
<span class="c1"># //////////////////////////////////////////////////////</span>
<span class="c1"># Chunking Rules</span>
<span class="c1"># //////////////////////////////////////////////////////</span>
<div class="viewcode-block" id="RegexpChunkRule"><a class="viewcode-back" href="../../../api/nltk.chunk.regexp.html#nltk.chunk.regexp.RegexpChunkRule">[docs]</a><span class="k">class</span> <span class="nc">RegexpChunkRule</span><span class="p">:</span>
<span class="sd">"""</span>
<span class="sd"> A rule specifying how to modify the chunking in a ``ChunkString``,</span>
<span class="sd"> using a transformational regular expression. The</span>
<span class="sd"> ``RegexpChunkRule`` class itself can be used to implement any</span>
<span class="sd"> transformational rule based on regular expressions. There are</span>
<span class="sd"> also a number of subclasses, which can be used to implement</span>
<span class="sd"> simpler types of rules, based on matching regular expressions.</span>
<span class="sd"> Each ``RegexpChunkRule`` has a regular expression and a</span>
<span class="sd"> replacement expression. When a ``RegexpChunkRule`` is "applied"</span>
<span class="sd"> to a ``ChunkString``, it searches the ``ChunkString`` for any</span>
<span class="sd"> substring that matches the regular expression, and replaces it</span>
<span class="sd"> using the replacement expression. This search/replace operation</span>
<span class="sd"> has the same semantics as ``re.sub``.</span>
<span class="sd"> Each ``RegexpChunkRule`` also has a description string, which</span>
<span class="sd"> gives a short (typically less than 75 characters) description of</span>
<span class="sd"> the purpose of the rule.</span>
<span class="sd"> This transformation defined by this ``RegexpChunkRule`` should</span>
<span class="sd"> only add and remove braces; it should *not* modify the sequence</span>
<span class="sd"> of angle-bracket delimited tags. Furthermore, this transformation</span>
<span class="sd"> may not result in nested or mismatched bracketing.</span>
<span class="sd"> """</span>
<div class="viewcode-block" id="RegexpChunkRule.__init__"><a class="viewcode-back" href="../../../api/nltk.chunk.regexp.html#nltk.chunk.regexp.RegexpChunkRule.__init__">[docs]</a> <span class="k">def</span> <span class="fm">__init__</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">regexp</span><span class="p">,</span> <span class="n">repl</span><span class="p">,</span> <span class="n">descr</span><span class="p">):</span>
<span class="sd">"""</span>
<span class="sd"> Construct a new RegexpChunkRule.</span>
<span class="sd"> :type regexp: regexp or str</span>
<span class="sd"> :param regexp: The regular expression for this ``RegexpChunkRule``.</span>
<span class="sd"> When this rule is applied to a ``ChunkString``, any</span>
<span class="sd"> substring that matches ``regexp`` will be replaced using</span>
<span class="sd"> the replacement string ``repl``. Note that this must be a</span>
<span class="sd"> normal regular expression, not a tag pattern.</span>
<span class="sd"> :type repl: str</span>
<span class="sd"> :param repl: The replacement expression for this ``RegexpChunkRule``.</span>
<span class="sd"> When this rule is applied to a ``ChunkString``, any substring</span>
<span class="sd"> that matches ``regexp`` will be replaced using ``repl``.</span>
<span class="sd"> :type descr: str</span>
<span class="sd"> :param descr: A short description of the purpose and/or effect</span>
<span class="sd"> of this rule.</span>
<span class="sd"> """</span>
<span class="k">if</span> <span class="nb">isinstance</span><span class="p">(</span><span class="n">regexp</span><span class="p">,</span> <span class="nb">str</span><span class="p">):</span>
<span class="n">regexp</span> <span class="o">=</span> <span class="n">re</span><span class="o">.</span><span class="n">compile</span><span class="p">(</span><span class="n">regexp</span><span class="p">)</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_repl</span> <span class="o">=</span> <span class="n">repl</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_descr</span> <span class="o">=</span> <span class="n">descr</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_regexp</span> <span class="o">=</span> <span class="n">regexp</span></div>
<div class="viewcode-block" id="RegexpChunkRule.apply"><a class="viewcode-back" href="../../../api/nltk.chunk.regexp.html#nltk.chunk.regexp.RegexpChunkRule.apply">[docs]</a> <span class="k">def</span> <span class="nf">apply</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">chunkstr</span><span class="p">):</span>
<span class="c1"># Keep docstring generic so we can inherit it.</span>
<span class="sd">"""</span>
<span class="sd"> Apply this rule to the given ``ChunkString``. See the</span>
<span class="sd"> class reference documentation for a description of what it</span>
<span class="sd"> means to apply a rule.</span>
<span class="sd"> :type chunkstr: ChunkString</span>
<span class="sd"> :param chunkstr: The chunkstring to which this rule is applied.</span>
<span class="sd"> :rtype: None</span>
<span class="sd"> :raise ValueError: If this transformation generated an</span>
<span class="sd"> invalid chunkstring.</span>
<span class="sd"> """</span>
<span class="n">chunkstr</span><span class="o">.</span><span class="n">xform</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">_regexp</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">_repl</span><span class="p">)</span></div>
<div class="viewcode-block" id="RegexpChunkRule.descr"><a class="viewcode-back" href="../../../api/nltk.chunk.regexp.html#nltk.chunk.regexp.RegexpChunkRule.descr">[docs]</a> <span class="k">def</span> <span class="nf">descr</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span>
<span class="sd">"""</span>
<span class="sd"> Return a short description of the purpose and/or effect of</span>
<span class="sd"> this rule.</span>
<span class="sd"> :rtype: str</span>
<span class="sd"> """</span>
<span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">_descr</span></div>
<span class="k">def</span> <span class="fm">__repr__</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span>
<span class="sd">"""</span>
<span class="sd"> Return a string representation of this rule. It has the form::</span>
<span class="sd"> <RegexpChunkRule: '{<IN|VB.*>}'->'<IN>'></span>
<span class="sd"> Note that this representation does not include the</span>
<span class="sd"> description string; that string can be accessed</span>
<span class="sd"> separately with the ``descr()`` method.</span>
<span class="sd"> :rtype: str</span>
<span class="sd"> """</span>
<span class="k">return</span> <span class="p">(</span>
<span class="s2">"<RegexpChunkRule: "</span>
<span class="o">+</span> <span class="nb">repr</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">_regexp</span><span class="o">.</span><span class="n">pattern</span><span class="p">)</span>
<span class="o">+</span> <span class="s2">"->"</span>
<span class="o">+</span> <span class="nb">repr</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">_repl</span><span class="p">)</span>
<span class="o">+</span> <span class="s2">">"</span>
<span class="p">)</span>
<div class="viewcode-block" id="RegexpChunkRule.fromstring"><a class="viewcode-back" href="../../../api/nltk.chunk.regexp.html#nltk.chunk.regexp.RegexpChunkRule.fromstring">[docs]</a> <span class="nd">@staticmethod</span>
<span class="k">def</span> <span class="nf">fromstring</span><span class="p">(</span><span class="n">s</span><span class="p">):</span>
<span class="sd">"""</span>
<span class="sd"> Create a RegexpChunkRule from a string description.</span>
<span class="sd"> Currently, the following formats are supported::</span>
<span class="sd"> {regexp} # chunk rule</span>
<span class="sd"> }regexp{ # strip rule</span>
<span class="sd"> regexp}{regexp # split rule</span>
<span class="sd"> regexp{}regexp # merge rule</span>
<span class="sd"> Where ``regexp`` is a regular expression for the rule. Any</span>
<span class="sd"> text following the comment marker (``#``) will be used as</span>
<span class="sd"> the rule's description:</span>
<span class="sd"> >>> from nltk.chunk.regexp import RegexpChunkRule</span>
<span class="sd"> >>> RegexpChunkRule.fromstring('{<DT>?<NN.*>+}')</span>
<span class="sd"> <ChunkRule: '<DT>?<NN.*>+'></span>
<span class="sd"> """</span>
<span class="c1"># Split off the comment (but don't split on '\#')</span>
<span class="n">m</span> <span class="o">=</span> <span class="n">re</span><span class="o">.</span><span class="n">match</span><span class="p">(</span><span class="sa">r</span><span class="s2">"(?P<rule>(</span><span class="se">\\</span><span class="s2">.|[^#])*)(?P<comment>#.*)?"</span><span class="p">,</span> <span class="n">s</span><span class="p">)</span>
<span class="n">rule</span> <span class="o">=</span> <span class="n">m</span><span class="o">.</span><span class="n">group</span><span class="p">(</span><span class="s2">"rule"</span><span class="p">)</span><span class="o">.</span><span class="n">strip</span><span class="p">()</span>
<span class="n">comment</span> <span class="o">=</span> <span class="p">(</span><span class="n">m</span><span class="o">.</span><span class="n">group</span><span class="p">(</span><span class="s2">"comment"</span><span class="p">)</span> <span class="ow">or</span> <span class="s2">""</span><span class="p">)[</span><span class="mi">1</span><span class="p">:]</span><span class="o">.</span><span class="n">strip</span><span class="p">()</span>
<span class="c1"># Pattern bodies: chunk, strip, split, merge</span>
<span class="k">try</span><span class="p">:</span>
<span class="k">if</span> <span class="ow">not</span> <span class="n">rule</span><span class="p">:</span>
<span class="k">raise</span> <span class="ne">ValueError</span><span class="p">(</span><span class="s2">"Empty chunk pattern"</span><span class="p">)</span>
<span class="k">if</span> <span class="n">rule</span><span class="p">[</span><span class="mi">0</span><span class="p">]</span> <span class="o">==</span> <span class="s2">"{"</span> <span class="ow">and</span> <span class="n">rule</span><span class="p">[</span><span class="o">-</span><span class="mi">1</span><span class="p">]</span> <span class="o">==</span> <span class="s2">"}"</span><span class="p">:</span>
<span class="k">return</span> <span class="n">ChunkRule</span><span class="p">(</span><span class="n">rule</span><span class="p">[</span><span class="mi">1</span><span class="p">:</span><span class="o">-</span><span class="mi">1</span><span class="p">],</span> <span class="n">comment</span><span class="p">)</span>
<span class="k">elif</span> <span class="n">rule</span><span class="p">[</span><span class="mi">0</span><span class="p">]</span> <span class="o">==</span> <span class="s2">"}"</span> <span class="ow">and</span> <span class="n">rule</span><span class="p">[</span><span class="o">-</span><span class="mi">1</span><span class="p">]</span> <span class="o">==</span> <span class="s2">"{"</span><span class="p">:</span>
<span class="k">return</span> <span class="n">StripRule</span><span class="p">(</span><span class="n">rule</span><span class="p">[</span><span class="mi">1</span><span class="p">:</span><span class="o">-</span><span class="mi">1</span><span class="p">],</span> <span class="n">comment</span><span class="p">)</span>
<span class="k">elif</span> <span class="s2">"}{"</span> <span class="ow">in</span> <span class="n">rule</span><span class="p">:</span>
<span class="n">left</span><span class="p">,</span> <span class="n">right</span> <span class="o">=</span> <span class="n">rule</span><span class="o">.</span><span class="n">split</span><span class="p">(</span><span class="s2">"}{"</span><span class="p">)</span>
<span class="k">return</span> <span class="n">SplitRule</span><span class="p">(</span><span class="n">left</span><span class="p">,</span> <span class="n">right</span><span class="p">,</span> <span class="n">comment</span><span class="p">)</span>
<span class="k">elif</span> <span class="s2">"</span><span class="si">{}</span><span class="s2">"</span> <span class="ow">in</span> <span class="n">rule</span><span class="p">:</span>
<span class="n">left</span><span class="p">,</span> <span class="n">right</span> <span class="o">=</span> <span class="n">rule</span><span class="o">.</span><span class="n">split</span><span class="p">(</span><span class="s2">"</span><span class="si">{}</span><span class="s2">"</span><span class="p">)</span>
<span class="k">return</span> <span class="n">MergeRule</span><span class="p">(</span><span class="n">left</span><span class="p">,</span> <span class="n">right</span><span class="p">,</span> <span class="n">comment</span><span class="p">)</span>
<span class="k">elif</span> <span class="n">re</span><span class="o">.</span><span class="n">match</span><span class="p">(</span><span class="s2">"[^</span><span class="si">{}</span><span class="s2">]*{[^</span><span class="si">{}</span><span class="s2">]*}[^</span><span class="si">{}</span><span class="s2">]*"</span><span class="p">,</span> <span class="n">rule</span><span class="p">):</span>
<span class="n">left</span><span class="p">,</span> <span class="n">chunk</span><span class="p">,</span> <span class="n">right</span> <span class="o">=</span> <span class="n">re</span><span class="o">.</span><span class="n">split</span><span class="p">(</span><span class="s2">"[</span><span class="si">{}</span><span class="s2">]"</span><span class="p">,</span> <span class="n">rule</span><span class="p">)</span>
<span class="k">return</span> <span class="n">ChunkRuleWithContext</span><span class="p">(</span><span class="n">left</span><span class="p">,</span> <span class="n">chunk</span><span class="p">,</span> <span class="n">right</span><span class="p">,</span> <span class="n">comment</span><span class="p">)</span>
<span class="k">else</span><span class="p">:</span>
<span class="k">raise</span> <span class="ne">ValueError</span><span class="p">(</span><span class="s2">"Illegal chunk pattern: </span><span class="si">%s</span><span class="s2">"</span> <span class="o">%</span> <span class="n">rule</span><span class="p">)</span>
<span class="k">except</span> <span class="p">(</span><span class="ne">ValueError</span><span class="p">,</span> <span class="n">re</span><span class="o">.</span><span class="n">error</span><span class="p">)</span> <span class="k">as</span> <span class="n">e</span><span class="p">:</span>
<span class="k">raise</span> <span class="ne">ValueError</span><span class="p">(</span><span class="s2">"Illegal chunk pattern: </span><span class="si">%s</span><span class="s2">"</span> <span class="o">%</span> <span class="n">rule</span><span class="p">)</span> <span class="kn">from</span> <span class="nn">e</span></div></div>
<div class="viewcode-block" id="ChunkRule"><a class="viewcode-back" href="../../../api/nltk.chunk.regexp.html#nltk.chunk.regexp.ChunkRule">[docs]</a><span class="k">class</span> <span class="nc">ChunkRule</span><span class="p">(</span><span class="n">RegexpChunkRule</span><span class="p">):</span>
<span class="sd">"""</span>
<span class="sd"> A rule specifying how to add chunks to a ``ChunkString``, using a</span>
<span class="sd"> matching tag pattern. When applied to a ``ChunkString``, it will</span>
<span class="sd"> find any substring that matches this tag pattern and that is not</span>
<span class="sd"> already part of a chunk, and create a new chunk containing that</span>
<span class="sd"> substring.</span>
<span class="sd"> """</span>
<div class="viewcode-block" id="ChunkRule.__init__"><a class="viewcode-back" href="../../../api/nltk.chunk.regexp.html#nltk.chunk.regexp.ChunkRule.__init__">[docs]</a> <span class="k">def</span> <span class="fm">__init__</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">tag_pattern</span><span class="p">,</span> <span class="n">descr</span><span class="p">):</span>
<span class="sd">"""</span>
<span class="sd"> Construct a new ``ChunkRule``.</span>
<span class="sd"> :type tag_pattern: str</span>
<span class="sd"> :param tag_pattern: This rule's tag pattern. When</span>
<span class="sd"> applied to a ``ChunkString``, this rule will</span>
<span class="sd"> chunk any substring that matches this tag pattern and that</span>
<span class="sd"> is not already part of a chunk.</span>
<span class="sd"> :type descr: str</span>
<span class="sd"> :param descr: A short description of the purpose and/or effect</span>
<span class="sd"> of this rule.</span>
<span class="sd"> """</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_pattern</span> <span class="o">=</span> <span class="n">tag_pattern</span>
<span class="n">regexp</span> <span class="o">=</span> <span class="n">re</span><span class="o">.</span><span class="n">compile</span><span class="p">(</span>
<span class="s2">"(?P<chunk></span><span class="si">%s</span><span class="s2">)</span><span class="si">%s</span><span class="s2">"</span>
<span class="o">%</span> <span class="p">(</span><span class="n">tag_pattern2re_pattern</span><span class="p">(</span><span class="n">tag_pattern</span><span class="p">),</span> <span class="n">ChunkString</span><span class="o">.</span><span class="n">IN_STRIP_PATTERN</span><span class="p">)</span>
<span class="p">)</span>
<span class="n">RegexpChunkRule</span><span class="o">.</span><span class="fm">__init__</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">regexp</span><span class="p">,</span> <span class="sa">r</span><span class="s2">"{\g<chunk>}"</span><span class="p">,</span> <span class="n">descr</span><span class="p">)</span></div>
<span class="k">def</span> <span class="fm">__repr__</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span>
<span class="sd">"""</span>
<span class="sd"> Return a string representation of this rule. It has the form::</span>
<span class="sd"> <ChunkRule: '<IN|VB.*>'></span>
<span class="sd"> Note that this representation does not include the</span>
<span class="sd"> description string; that string can be accessed</span>
<span class="sd"> separately with the ``descr()`` method.</span>
<span class="sd"> :rtype: str</span>
<span class="sd"> """</span>
<span class="k">return</span> <span class="s2">"<ChunkRule: "</span> <span class="o">+</span> <span class="nb">repr</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">_pattern</span><span class="p">)</span> <span class="o">+</span> <span class="s2">">"</span></div>
<div class="viewcode-block" id="StripRule"><a class="viewcode-back" href="../../../api/nltk.chunk.regexp.html#nltk.chunk.regexp.StripRule">[docs]</a><span class="k">class</span> <span class="nc">StripRule</span><span class="p">(</span><span class="n">RegexpChunkRule</span><span class="p">):</span>
<span class="sd">"""</span>
<span class="sd"> A rule specifying how to remove strips to a ``ChunkString``,</span>
<span class="sd"> using a matching tag pattern. When applied to a</span>
<span class="sd"> ``ChunkString``, it will find any substring that matches this</span>
<span class="sd"> tag pattern and that is contained in a chunk, and remove it</span>
<span class="sd"> from that chunk, thus creating two new chunks.</span>
<span class="sd"> """</span>
<div class="viewcode-block" id="StripRule.__init__"><a class="viewcode-back" href="../../../api/nltk.chunk.regexp.html#nltk.chunk.regexp.StripRule.__init__">[docs]</a> <span class="k">def</span> <span class="fm">__init__</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">tag_pattern</span><span class="p">,</span> <span class="n">descr</span><span class="p">):</span>
<span class="sd">"""</span>
<span class="sd"> Construct a new ``StripRule``.</span>
<span class="sd"> :type tag_pattern: str</span>
<span class="sd"> :param tag_pattern: This rule's tag pattern. When</span>
<span class="sd"> applied to a ``ChunkString``, this rule will</span>
<span class="sd"> find any substring that matches this tag pattern and that</span>
<span class="sd"> is contained in a chunk, and remove it from that chunk,</span>
<span class="sd"> thus creating two new chunks.</span>
<span class="sd"> :type descr: str</span>
<span class="sd"> :param descr: A short description of the purpose and/or effect</span>
<span class="sd"> of this rule.</span>
<span class="sd"> """</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_pattern</span> <span class="o">=</span> <span class="n">tag_pattern</span>
<span class="n">regexp</span> <span class="o">=</span> <span class="n">re</span><span class="o">.</span><span class="n">compile</span><span class="p">(</span>
<span class="s2">"(?P<strip></span><span class="si">%s</span><span class="s2">)</span><span class="si">%s</span><span class="s2">"</span>
<span class="o">%</span> <span class="p">(</span><span class="n">tag_pattern2re_pattern</span><span class="p">(</span><span class="n">tag_pattern</span><span class="p">),</span> <span class="n">ChunkString</span><span class="o">.</span><span class="n">IN_CHUNK_PATTERN</span><span class="p">)</span>
<span class="p">)</span>
<span class="n">RegexpChunkRule</span><span class="o">.</span><span class="fm">__init__</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">regexp</span><span class="p">,</span> <span class="sa">r</span><span class="s2">"}\g<strip>{"</span><span class="p">,</span> <span class="n">descr</span><span class="p">)</span></div>
<span class="k">def</span> <span class="fm">__repr__</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span>
<span class="sd">"""</span>
<span class="sd"> Return a string representation of this rule. It has the form::</span>
<span class="sd"> <StripRule: '<IN|VB.*>'></span>
<span class="sd"> Note that this representation does not include the</span>
<span class="sd"> description string; that string can be accessed</span>
<span class="sd"> separately with the ``descr()`` method.</span>
<span class="sd"> :rtype: str</span>
<span class="sd"> """</span>
<span class="k">return</span> <span class="s2">"<StripRule: "</span> <span class="o">+</span> <span class="nb">repr</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">_pattern</span><span class="p">)</span> <span class="o">+</span> <span class="s2">">"</span></div>
<div class="viewcode-block" id="UnChunkRule"><a class="viewcode-back" href="../../../api/nltk.chunk.regexp.html#nltk.chunk.regexp.UnChunkRule">[docs]</a><span class="k">class</span> <span class="nc">UnChunkRule</span><span class="p">(</span><span class="n">RegexpChunkRule</span><span class="p">):</span>
<span class="sd">"""</span>
<span class="sd"> A rule specifying how to remove chunks to a ``ChunkString``,</span>
<span class="sd"> using a matching tag pattern. When applied to a</span>
<span class="sd"> ``ChunkString``, it will find any complete chunk that matches this</span>
<span class="sd"> tag pattern, and un-chunk it.</span>
<span class="sd"> """</span>
<div class="viewcode-block" id="UnChunkRule.__init__"><a class="viewcode-back" href="../../../api/nltk.chunk.regexp.html#nltk.chunk.regexp.UnChunkRule.__init__">[docs]</a> <span class="k">def</span> <span class="fm">__init__</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">tag_pattern</span><span class="p">,</span> <span class="n">descr</span><span class="p">):</span>
<span class="sd">"""</span>
<span class="sd"> Construct a new ``UnChunkRule``.</span>
<span class="sd"> :type tag_pattern: str</span>
<span class="sd"> :param tag_pattern: This rule's tag pattern. When</span>
<span class="sd"> applied to a ``ChunkString``, this rule will</span>
<span class="sd"> find any complete chunk that matches this tag pattern,</span>
<span class="sd"> and un-chunk it.</span>
<span class="sd"> :type descr: str</span>
<span class="sd"> :param descr: A short description of the purpose and/or effect</span>
<span class="sd"> of this rule.</span>
<span class="sd"> """</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_pattern</span> <span class="o">=</span> <span class="n">tag_pattern</span>
<span class="n">regexp</span> <span class="o">=</span> <span class="n">re</span><span class="o">.</span><span class="n">compile</span><span class="p">(</span><span class="sa">r</span><span class="s2">"\{(?P<chunk></span><span class="si">%s</span><span class="s2">)\}"</span> <span class="o">%</span> <span class="n">tag_pattern2re_pattern</span><span class="p">(</span><span class="n">tag_pattern</span><span class="p">))</span>
<span class="n">RegexpChunkRule</span><span class="o">.</span><span class="fm">__init__</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">regexp</span><span class="p">,</span> <span class="sa">r</span><span class="s2">"\g<chunk>"</span><span class="p">,</span> <span class="n">descr</span><span class="p">)</span></div>
<span class="k">def</span> <span class="fm">__repr__</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span>
<span class="sd">"""</span>
<span class="sd"> Return a string representation of this rule. It has the form::</span>
<span class="sd"> <UnChunkRule: '<IN|VB.*>'></span>
<span class="sd"> Note that this representation does not include the</span>
<span class="sd"> description string; that string can be accessed</span>
<span class="sd"> separately with the ``descr()`` method.</span>
<span class="sd"> :rtype: str</span>
<span class="sd"> """</span>
<span class="k">return</span> <span class="s2">"<UnChunkRule: "</span> <span class="o">+</span> <span class="nb">repr</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">_pattern</span><span class="p">)</span> <span class="o">+</span> <span class="s2">">"</span></div>
<div class="viewcode-block" id="MergeRule"><a class="viewcode-back" href="../../../api/nltk.chunk.regexp.html#nltk.chunk.regexp.MergeRule">[docs]</a><span class="k">class</span> <span class="nc">MergeRule</span><span class="p">(</span><span class="n">RegexpChunkRule</span><span class="p">):</span>
<span class="sd">"""</span>
<span class="sd"> A rule specifying how to merge chunks in a ``ChunkString``, using</span>
<span class="sd"> two matching tag patterns: a left pattern, and a right pattern.</span>
<span class="sd"> When applied to a ``ChunkString``, it will find any chunk whose end</span>
<span class="sd"> matches left pattern, and immediately followed by a chunk whose</span>
<span class="sd"> beginning matches right pattern. It will then merge those two</span>
<span class="sd"> chunks into a single chunk.</span>
<span class="sd"> """</span>
<div class="viewcode-block" id="MergeRule.__init__"><a class="viewcode-back" href="../../../api/nltk.chunk.regexp.html#nltk.chunk.regexp.MergeRule.__init__">[docs]</a> <span class="k">def</span> <span class="fm">__init__</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">left_tag_pattern</span><span class="p">,</span> <span class="n">right_tag_pattern</span><span class="p">,</span> <span class="n">descr</span><span class="p">):</span>
<span class="sd">"""</span>
<span class="sd"> Construct a new ``MergeRule``.</span>
<span class="sd"> :type right_tag_pattern: str</span>
<span class="sd"> :param right_tag_pattern: This rule's right tag</span>
<span class="sd"> pattern. When applied to a ``ChunkString``, this</span>
<span class="sd"> rule will find any chunk whose end matches</span>
<span class="sd"> ``left_tag_pattern``, and immediately followed by a chunk</span>
<span class="sd"> whose beginning matches this pattern. It will</span>
<span class="sd"> then merge those two chunks into a single chunk.</span>
<span class="sd"> :type left_tag_pattern: str</span>
<span class="sd"> :param left_tag_pattern: This rule's left tag</span>
<span class="sd"> pattern. When applied to a ``ChunkString``, this</span>
<span class="sd"> rule will find any chunk whose end matches</span>
<span class="sd"> this pattern, and immediately followed by a chunk</span>
<span class="sd"> whose beginning matches ``right_tag_pattern``. It will</span>
<span class="sd"> then merge those two chunks into a single chunk.</span>
<span class="sd"> :type descr: str</span>
<span class="sd"> :param descr: A short description of the purpose and/or effect</span>
<span class="sd"> of this rule.</span>
<span class="sd"> """</span>
<span class="c1"># Ensure that the individual patterns are coherent. E.g., if</span>
<span class="c1"># left='(' and right=')', then this will raise an exception:</span>
<span class="n">re</span><span class="o">.</span><span class="n">compile</span><span class="p">(</span><span class="n">tag_pattern2re_pattern</span><span class="p">(</span><span class="n">left_tag_pattern</span><span class="p">))</span>
<span class="n">re</span><span class="o">.</span><span class="n">compile</span><span class="p">(</span><span class="n">tag_pattern2re_pattern</span><span class="p">(</span><span class="n">right_tag_pattern</span><span class="p">))</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_left_tag_pattern</span> <span class="o">=</span> <span class="n">left_tag_pattern</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_right_tag_pattern</span> <span class="o">=</span> <span class="n">right_tag_pattern</span>
<span class="n">regexp</span> <span class="o">=</span> <span class="n">re</span><span class="o">.</span><span class="n">compile</span><span class="p">(</span>
<span class="s2">"(?P<left></span><span class="si">%s</span><span class="s2">)}{(?=</span><span class="si">%s</span><span class="s2">)"</span>
<span class="o">%</span> <span class="p">(</span>
<span class="n">tag_pattern2re_pattern</span><span class="p">(</span><span class="n">left_tag_pattern</span><span class="p">),</span>
<span class="n">tag_pattern2re_pattern</span><span class="p">(</span><span class="n">right_tag_pattern</span><span class="p">),</span>
<span class="p">)</span>
<span class="p">)</span>
<span class="n">RegexpChunkRule</span><span class="o">.</span><span class="fm">__init__</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">regexp</span><span class="p">,</span> <span class="sa">r</span><span class="s2">"\g<left>"</span><span class="p">,</span> <span class="n">descr</span><span class="p">)</span></div>
<span class="k">def</span> <span class="fm">__repr__</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span>
<span class="sd">"""</span>
<span class="sd"> Return a string representation of this rule. It has the form::</span>
<span class="sd"> <MergeRule: '<NN|DT|JJ>', '<NN|JJ>'></span>
<span class="sd"> Note that this representation does not include the</span>
<span class="sd"> description string; that string can be accessed</span>
<span class="sd"> separately with the ``descr()`` method.</span>
<span class="sd"> :rtype: str</span>
<span class="sd"> """</span>
<span class="k">return</span> <span class="p">(</span>
<span class="s2">"<MergeRule: "</span>
<span class="o">+</span> <span class="nb">repr</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">_left_tag_pattern</span><span class="p">)</span>
<span class="o">+</span> <span class="s2">", "</span>
<span class="o">+</span> <span class="nb">repr</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">_right_tag_pattern</span><span class="p">)</span>
<span class="o">+</span> <span class="s2">">"</span>
<span class="p">)</span></div>
<div class="viewcode-block" id="SplitRule"><a class="viewcode-back" href="../../../api/nltk.chunk.regexp.html#nltk.chunk.regexp.SplitRule">[docs]</a><span class="k">class</span> <span class="nc">SplitRule</span><span class="p">(</span><span class="n">RegexpChunkRule</span><span class="p">):</span>
<span class="sd">"""</span>
<span class="sd"> A rule specifying how to split chunks in a ``ChunkString``, using</span>
<span class="sd"> two matching tag patterns: a left pattern, and a right pattern.</span>
<span class="sd"> When applied to a ``ChunkString``, it will find any chunk that</span>
<span class="sd"> matches the left pattern followed by the right pattern. It will</span>
<span class="sd"> then split the chunk into two new chunks, at the point between the</span>
<span class="sd"> two pattern matches.</span>
<span class="sd"> """</span>
<div class="viewcode-block" id="SplitRule.__init__"><a class="viewcode-back" href="../../../api/nltk.chunk.regexp.html#nltk.chunk.regexp.SplitRule.__init__">[docs]</a> <span class="k">def</span> <span class="fm">__init__</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">left_tag_pattern</span><span class="p">,</span> <span class="n">right_tag_pattern</span><span class="p">,</span> <span class="n">descr</span><span class="p">):</span>
<span class="sd">"""</span>
<span class="sd"> Construct a new ``SplitRule``.</span>
<span class="sd"> :type right_tag_pattern: str</span>
<span class="sd"> :param right_tag_pattern: This rule's right tag</span>
<span class="sd"> pattern. When applied to a ``ChunkString``, this rule will</span>
<span class="sd"> find any chunk containing a substring that matches</span>
<span class="sd"> ``left_tag_pattern`` followed by this pattern. It will</span>
<span class="sd"> then split the chunk into two new chunks at the point</span>
<span class="sd"> between these two matching patterns.</span>
<span class="sd"> :type left_tag_pattern: str</span>
<span class="sd"> :param left_tag_pattern: This rule's left tag</span>
<span class="sd"> pattern. When applied to a ``ChunkString``, this rule will</span>
<span class="sd"> find any chunk containing a substring that matches this</span>
<span class="sd"> pattern followed by ``right_tag_pattern``. It will then</span>
<span class="sd"> split the chunk into two new chunks at the point between</span>
<span class="sd"> these two matching patterns.</span>
<span class="sd"> :type descr: str</span>
<span class="sd"> :param descr: A short description of the purpose and/or effect</span>
<span class="sd"> of this rule.</span>
<span class="sd"> """</span>
<span class="c1"># Ensure that the individual patterns are coherent. E.g., if</span>
<span class="c1"># left='(' and right=')', then this will raise an exception:</span>
<span class="n">re</span><span class="o">.</span><span class="n">compile</span><span class="p">(</span><span class="n">tag_pattern2re_pattern</span><span class="p">(</span><span class="n">left_tag_pattern</span><span class="p">))</span>
<span class="n">re</span><span class="o">.</span><span class="n">compile</span><span class="p">(</span><span class="n">tag_pattern2re_pattern</span><span class="p">(</span><span class="n">right_tag_pattern</span><span class="p">))</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_left_tag_pattern</span> <span class="o">=</span> <span class="n">left_tag_pattern</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_right_tag_pattern</span> <span class="o">=</span> <span class="n">right_tag_pattern</span>
<span class="n">regexp</span> <span class="o">=</span> <span class="n">re</span><span class="o">.</span><span class="n">compile</span><span class="p">(</span>
<span class="s2">"(?P<left></span><span class="si">%s</span><span class="s2">)(?=</span><span class="si">%s</span><span class="s2">)"</span>
<span class="o">%</span> <span class="p">(</span>
<span class="n">tag_pattern2re_pattern</span><span class="p">(</span><span class="n">left_tag_pattern</span><span class="p">),</span>
<span class="n">tag_pattern2re_pattern</span><span class="p">(</span><span class="n">right_tag_pattern</span><span class="p">),</span>
<span class="p">)</span>
<span class="p">)</span>
<span class="n">RegexpChunkRule</span><span class="o">.</span><span class="fm">__init__</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">regexp</span><span class="p">,</span> <span class="sa">r</span><span class="s2">"\g<left>}{"</span><span class="p">,</span> <span class="n">descr</span><span class="p">)</span></div>
<span class="k">def</span> <span class="fm">__repr__</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span>
<span class="sd">"""</span>
<span class="sd"> Return a string representation of this rule. It has the form::</span>
<span class="sd"> <SplitRule: '<NN>', '<DT>'></span>
<span class="sd"> Note that this representation does not include the</span>
<span class="sd"> description string; that string can be accessed</span>
<span class="sd"> separately with the ``descr()`` method.</span>
<span class="sd"> :rtype: str</span>
<span class="sd"> """</span>
<span class="k">return</span> <span class="p">(</span>
<span class="s2">"<SplitRule: "</span>
<span class="o">+</span> <span class="nb">repr</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">_left_tag_pattern</span><span class="p">)</span>
<span class="o">+</span> <span class="s2">", "</span>
<span class="o">+</span> <span class="nb">repr</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">_right_tag_pattern</span><span class="p">)</span>
<span class="o">+</span> <span class="s2">">"</span>
<span class="p">)</span></div>
<div class="viewcode-block" id="ExpandLeftRule"><a class="viewcode-back" href="../../../api/nltk.chunk.regexp.html#nltk.chunk.regexp.ExpandLeftRule">[docs]</a><span class="k">class</span> <span class="nc">ExpandLeftRule</span><span class="p">(</span><span class="n">RegexpChunkRule</span><span class="p">):</span>
<span class="sd">"""</span>
<span class="sd"> A rule specifying how to expand chunks in a ``ChunkString`` to the left,</span>
<span class="sd"> using two matching tag patterns: a left pattern, and a right pattern.</span>
<span class="sd"> When applied to a ``ChunkString``, it will find any chunk whose beginning</span>
<span class="sd"> matches right pattern, and immediately preceded by a strip whose</span>
<span class="sd"> end matches left pattern. It will then expand the chunk to incorporate</span>
<span class="sd"> the new material on the left.</span>
<span class="sd"> """</span>
<div class="viewcode-block" id="ExpandLeftRule.__init__"><a class="viewcode-back" href="../../../api/nltk.chunk.regexp.html#nltk.chunk.regexp.ExpandLeftRule.__init__">[docs]</a> <span class="k">def</span> <span class="fm">__init__</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">left_tag_pattern</span><span class="p">,</span> <span class="n">right_tag_pattern</span><span class="p">,</span> <span class="n">descr</span><span class="p">):</span>
<span class="sd">"""</span>
<span class="sd"> Construct a new ``ExpandRightRule``.</span>
<span class="sd"> :type right_tag_pattern: str</span>
<span class="sd"> :param right_tag_pattern: This rule's right tag</span>
<span class="sd"> pattern. When applied to a ``ChunkString``, this</span>
<span class="sd"> rule will find any chunk whose beginning matches</span>
<span class="sd"> ``right_tag_pattern``, and immediately preceded by a strip</span>
<span class="sd"> whose end matches this pattern. It will</span>
<span class="sd"> then merge those two chunks into a single chunk.</span>
<span class="sd"> :type left_tag_pattern: str</span>
<span class="sd"> :param left_tag_pattern: This rule's left tag</span>
<span class="sd"> pattern. When applied to a ``ChunkString``, this</span>
<span class="sd"> rule will find any chunk whose beginning matches</span>
<span class="sd"> this pattern, and immediately preceded by a strip</span>
<span class="sd"> whose end matches ``left_tag_pattern``. It will</span>
<span class="sd"> then expand the chunk to incorporate the new material on the left.</span>
<span class="sd"> :type descr: str</span>
<span class="sd"> :param descr: A short description of the purpose and/or effect</span>
<span class="sd"> of this rule.</span>
<span class="sd"> """</span>
<span class="c1"># Ensure that the individual patterns are coherent. E.g., if</span>
<span class="c1"># left='(' and right=')', then this will raise an exception:</span>
<span class="n">re</span><span class="o">.</span><span class="n">compile</span><span class="p">(</span><span class="n">tag_pattern2re_pattern</span><span class="p">(</span><span class="n">left_tag_pattern</span><span class="p">))</span>
<span class="n">re</span><span class="o">.</span><span class="n">compile</span><span class="p">(</span><span class="n">tag_pattern2re_pattern</span><span class="p">(</span><span class="n">right_tag_pattern</span><span class="p">))</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_left_tag_pattern</span> <span class="o">=</span> <span class="n">left_tag_pattern</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_right_tag_pattern</span> <span class="o">=</span> <span class="n">right_tag_pattern</span>
<span class="n">regexp</span> <span class="o">=</span> <span class="n">re</span><span class="o">.</span><span class="n">compile</span><span class="p">(</span>
<span class="sa">r</span><span class="s2">"(?P<left></span><span class="si">%s</span><span class="s2">)\{(?P<right></span><span class="si">%s</span><span class="s2">)"</span>
<span class="o">%</span> <span class="p">(</span>
<span class="n">tag_pattern2re_pattern</span><span class="p">(</span><span class="n">left_tag_pattern</span><span class="p">),</span>
<span class="n">tag_pattern2re_pattern</span><span class="p">(</span><span class="n">right_tag_pattern</span><span class="p">),</span>
<span class="p">)</span>
<span class="p">)</span>
<span class="n">RegexpChunkRule</span><span class="o">.</span><span class="fm">__init__</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">regexp</span><span class="p">,</span> <span class="sa">r</span><span class="s2">"{\g<left>\g<right>"</span><span class="p">,</span> <span class="n">descr</span><span class="p">)</span></div>
<span class="k">def</span> <span class="fm">__repr__</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span>
<span class="sd">"""</span>
<span class="sd"> Return a string representation of this rule. It has the form::</span>
<span class="sd"> <ExpandLeftRule: '<NN|DT|JJ>', '<NN|JJ>'></span>
<span class="sd"> Note that this representation does not include the</span>
<span class="sd"> description string; that string can be accessed</span>
<span class="sd"> separately with the ``descr()`` method.</span>
<span class="sd"> :rtype: str</span>
<span class="sd"> """</span>
<span class="k">return</span> <span class="p">(</span>
<span class="s2">"<ExpandLeftRule: "</span>
<span class="o">+</span> <span class="nb">repr</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">_left_tag_pattern</span><span class="p">)</span>
<span class="o">+</span> <span class="s2">", "</span>
<span class="o">+</span> <span class="nb">repr</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">_right_tag_pattern</span><span class="p">)</span>
<span class="o">+</span> <span class="s2">">"</span>
<span class="p">)</span></div>
<div class="viewcode-block" id="ExpandRightRule"><a class="viewcode-back" href="../../../api/nltk.chunk.regexp.html#nltk.chunk.regexp.ExpandRightRule">[docs]</a><span class="k">class</span> <span class="nc">ExpandRightRule</span><span class="p">(</span><span class="n">RegexpChunkRule</span><span class="p">):</span>
<span class="sd">"""</span>
<span class="sd"> A rule specifying how to expand chunks in a ``ChunkString`` to the</span>
<span class="sd"> right, using two matching tag patterns: a left pattern, and a</span>
<span class="sd"> right pattern. When applied to a ``ChunkString``, it will find any</span>
<span class="sd"> chunk whose end matches left pattern, and immediately followed by</span>
<span class="sd"> a strip whose beginning matches right pattern. It will then</span>
<span class="sd"> expand the chunk to incorporate the new material on the right.</span>
<span class="sd"> """</span>
<div class="viewcode-block" id="ExpandRightRule.__init__"><a class="viewcode-back" href="../../../api/nltk.chunk.regexp.html#nltk.chunk.regexp.ExpandRightRule.__init__">[docs]</a> <span class="k">def</span> <span class="fm">__init__</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">left_tag_pattern</span><span class="p">,</span> <span class="n">right_tag_pattern</span><span class="p">,</span> <span class="n">descr</span><span class="p">):</span>
<span class="sd">"""</span>
<span class="sd"> Construct a new ``ExpandRightRule``.</span>
<span class="sd"> :type right_tag_pattern: str</span>
<span class="sd"> :param right_tag_pattern: This rule's right tag</span>
<span class="sd"> pattern. When applied to a ``ChunkString``, this</span>
<span class="sd"> rule will find any chunk whose end matches</span>
<span class="sd"> ``left_tag_pattern``, and immediately followed by a strip</span>
<span class="sd"> whose beginning matches this pattern. It will</span>
<span class="sd"> then merge those two chunks into a single chunk.</span>
<span class="sd"> :type left_tag_pattern: str</span>
<span class="sd"> :param left_tag_pattern: This rule's left tag</span>
<span class="sd"> pattern. When applied to a ``ChunkString``, this</span>
<span class="sd"> rule will find any chunk whose end matches</span>
<span class="sd"> this pattern, and immediately followed by a strip</span>
<span class="sd"> whose beginning matches ``right_tag_pattern``. It will</span>
<span class="sd"> then expand the chunk to incorporate the new material on the right.</span>
<span class="sd"> :type descr: str</span>
<span class="sd"> :param descr: A short description of the purpose and/or effect</span>
<span class="sd"> of this rule.</span>
<span class="sd"> """</span>
<span class="c1"># Ensure that the individual patterns are coherent. E.g., if</span>
<span class="c1"># left='(' and right=')', then this will raise an exception:</span>
<span class="n">re</span><span class="o">.</span><span class="n">compile</span><span class="p">(</span><span class="n">tag_pattern2re_pattern</span><span class="p">(</span><span class="n">left_tag_pattern</span><span class="p">))</span>
<span class="n">re</span><span class="o">.</span><span class="n">compile</span><span class="p">(</span><span class="n">tag_pattern2re_pattern</span><span class="p">(</span><span class="n">right_tag_pattern</span><span class="p">))</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_left_tag_pattern</span> <span class="o">=</span> <span class="n">left_tag_pattern</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_right_tag_pattern</span> <span class="o">=</span> <span class="n">right_tag_pattern</span>
<span class="n">regexp</span> <span class="o">=</span> <span class="n">re</span><span class="o">.</span><span class="n">compile</span><span class="p">(</span>
<span class="sa">r</span><span class="s2">"(?P<left></span><span class="si">%s</span><span class="s2">)\}(?P<right></span><span class="si">%s</span><span class="s2">)"</span>
<span class="o">%</span> <span class="p">(</span>
<span class="n">tag_pattern2re_pattern</span><span class="p">(</span><span class="n">left_tag_pattern</span><span class="p">),</span>
<span class="n">tag_pattern2re_pattern</span><span class="p">(</span><span class="n">right_tag_pattern</span><span class="p">),</span>
<span class="p">)</span>
<span class="p">)</span>
<span class="n">RegexpChunkRule</span><span class="o">.</span><span class="fm">__init__</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">regexp</span><span class="p">,</span> <span class="sa">r</span><span class="s2">"\g<left>\g<right>}"</span><span class="p">,</span> <span class="n">descr</span><span class="p">)</span></div>
<span class="k">def</span> <span class="fm">__repr__</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span>
<span class="sd">"""</span>
<span class="sd"> Return a string representation of this rule. It has the form::</span>
<span class="sd"> <ExpandRightRule: '<NN|DT|JJ>', '<NN|JJ>'></span>
<span class="sd"> Note that this representation does not include the</span>
<span class="sd"> description string; that string can be accessed</span>
<span class="sd"> separately with the ``descr()`` method.</span>
<span class="sd"> :rtype: str</span>
<span class="sd"> """</span>
<span class="k">return</span> <span class="p">(</span>
<span class="s2">"<ExpandRightRule: "</span>
<span class="o">+</span> <span class="nb">repr</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">_left_tag_pattern</span><span class="p">)</span>
<span class="o">+</span> <span class="s2">", "</span>
<span class="o">+</span> <span class="nb">repr</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">_right_tag_pattern</span><span class="p">)</span>
<span class="o">+</span> <span class="s2">">"</span>
<span class="p">)</span></div>
<div class="viewcode-block" id="ChunkRuleWithContext"><a class="viewcode-back" href="../../../api/nltk.chunk.regexp.html#nltk.chunk.regexp.ChunkRuleWithContext">[docs]</a><span class="k">class</span> <span class="nc">ChunkRuleWithContext</span><span class="p">(</span><span class="n">RegexpChunkRule</span><span class="p">):</span>
<span class="sd">"""</span>
<span class="sd"> A rule specifying how to add chunks to a ``ChunkString``, using</span>
<span class="sd"> three matching tag patterns: one for the left context, one for the</span>
<span class="sd"> chunk, and one for the right context. When applied to a</span>
<span class="sd"> ``ChunkString``, it will find any substring that matches the chunk</span>
<span class="sd"> tag pattern, is surrounded by substrings that match the two</span>
<span class="sd"> context patterns, and is not already part of a chunk; and create a</span>
<span class="sd"> new chunk containing the substring that matched the chunk tag</span>
<span class="sd"> pattern.</span>
<span class="sd"> Caveat: Both the left and right context are consumed when this</span>
<span class="sd"> rule matches; therefore, if you need to find overlapping matches,</span>
<span class="sd"> you will need to apply your rule more than once.</span>
<span class="sd"> """</span>
<div class="viewcode-block" id="ChunkRuleWithContext.__init__"><a class="viewcode-back" href="../../../api/nltk.chunk.regexp.html#nltk.chunk.regexp.ChunkRuleWithContext.__init__">[docs]</a> <span class="k">def</span> <span class="fm">__init__</span><span class="p">(</span>
<span class="bp">self</span><span class="p">,</span>
<span class="n">left_context_tag_pattern</span><span class="p">,</span>
<span class="n">chunk_tag_pattern</span><span class="p">,</span>
<span class="n">right_context_tag_pattern</span><span class="p">,</span>
<span class="n">descr</span><span class="p">,</span>
<span class="p">):</span>
<span class="sd">"""</span>
<span class="sd"> Construct a new ``ChunkRuleWithContext``.</span>
<span class="sd"> :type left_context_tag_pattern: str</span>
<span class="sd"> :param left_context_tag_pattern: A tag pattern that must match</span>
<span class="sd"> the left context of ``chunk_tag_pattern`` for this rule to</span>
<span class="sd"> apply.</span>
<span class="sd"> :type chunk_tag_pattern: str</span>
<span class="sd"> :param chunk_tag_pattern: A tag pattern that must match for this</span>
<span class="sd"> rule to apply. If the rule does apply, then this pattern</span>
<span class="sd"> also identifies the substring that will be made into a chunk.</span>
<span class="sd"> :type right_context_tag_pattern: str</span>
<span class="sd"> :param right_context_tag_pattern: A tag pattern that must match</span>
<span class="sd"> the right context of ``chunk_tag_pattern`` for this rule to</span>
<span class="sd"> apply.</span>
<span class="sd"> :type descr: str</span>
<span class="sd"> :param descr: A short description of the purpose and/or effect</span>
<span class="sd"> of this rule.</span>
<span class="sd"> """</span>
<span class="c1"># Ensure that the individual patterns are coherent. E.g., if</span>
<span class="c1"># left='(' and right=')', then this will raise an exception:</span>
<span class="n">re</span><span class="o">.</span><span class="n">compile</span><span class="p">(</span><span class="n">tag_pattern2re_pattern</span><span class="p">(</span><span class="n">left_context_tag_pattern</span><span class="p">))</span>
<span class="n">re</span><span class="o">.</span><span class="n">compile</span><span class="p">(</span><span class="n">tag_pattern2re_pattern</span><span class="p">(</span><span class="n">chunk_tag_pattern</span><span class="p">))</span>
<span class="n">re</span><span class="o">.</span><span class="n">compile</span><span class="p">(</span><span class="n">tag_pattern2re_pattern</span><span class="p">(</span><span class="n">right_context_tag_pattern</span><span class="p">))</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_left_context_tag_pattern</span> <span class="o">=</span> <span class="n">left_context_tag_pattern</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_chunk_tag_pattern</span> <span class="o">=</span> <span class="n">chunk_tag_pattern</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_right_context_tag_pattern</span> <span class="o">=</span> <span class="n">right_context_tag_pattern</span>
<span class="n">regexp</span> <span class="o">=</span> <span class="n">re</span><span class="o">.</span><span class="n">compile</span><span class="p">(</span>
<span class="s2">"(?P<left></span><span class="si">%s</span><span class="s2">)(?P<chunk></span><span class="si">%s</span><span class="s2">)(?P<right></span><span class="si">%s</span><span class="s2">)</span><span class="si">%s</span><span class="s2">"</span>
<span class="o">%</span> <span class="p">(</span>
<span class="n">tag_pattern2re_pattern</span><span class="p">(</span><span class="n">left_context_tag_pattern</span><span class="p">),</span>
<span class="n">tag_pattern2re_pattern</span><span class="p">(</span><span class="n">chunk_tag_pattern</span><span class="p">),</span>
<span class="n">tag_pattern2re_pattern</span><span class="p">(</span><span class="n">right_context_tag_pattern</span><span class="p">),</span>
<span class="n">ChunkString</span><span class="o">.</span><span class="n">IN_STRIP_PATTERN</span><span class="p">,</span>
<span class="p">)</span>
<span class="p">)</span>
<span class="n">replacement</span> <span class="o">=</span> <span class="sa">r</span><span class="s2">"\g<left>{\g<chunk>}\g<right>"</span>
<span class="n">RegexpChunkRule</span><span class="o">.</span><span class="fm">__init__</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">regexp</span><span class="p">,</span> <span class="n">replacement</span><span class="p">,</span> <span class="n">descr</span><span class="p">)</span></div>
<span class="k">def</span> <span class="fm">__repr__</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span>
<span class="sd">"""</span>
<span class="sd"> Return a string representation of this rule. It has the form::</span>
<span class="sd"> <ChunkRuleWithContext: '<IN>', '<NN>', '<DT>'></span>
<span class="sd"> Note that this representation does not include the</span>
<span class="sd"> description string; that string can be accessed</span>
<span class="sd"> separately with the ``descr()`` method.</span>
<span class="sd"> :rtype: str</span>
<span class="sd"> """</span>
<span class="k">return</span> <span class="s2">"<ChunkRuleWithContext: </span><span class="si">{!r}</span><span class="s2">, </span><span class="si">{!r}</span><span class="s2">, </span><span class="si">{!r}</span><span class="s2">>"</span><span class="o">.</span><span class="n">format</span><span class="p">(</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_left_context_tag_pattern</span><span class="p">,</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_chunk_tag_pattern</span><span class="p">,</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_right_context_tag_pattern</span><span class="p">,</span>
<span class="p">)</span></div>
<span class="c1"># //////////////////////////////////////////////////////</span>
<span class="c1"># Tag Pattern Format Conversion</span>
<span class="c1"># //////////////////////////////////////////////////////</span>
<span class="c1"># this should probably be made more strict than it is -- e.g., it</span>
<span class="c1"># currently accepts 'foo'.</span>
<span class="n">CHUNK_TAG_PATTERN</span> <span class="o">=</span> <span class="n">re</span><span class="o">.</span><span class="n">compile</span><span class="p">(</span>
<span class="sa">r</span><span class="s2">"^((</span><span class="si">{}</span><span class="s2">|<</span><span class="si">{}</span><span class="s2">>)*)$"</span><span class="o">.</span><span class="n">format</span><span class="p">(</span><span class="sa">r</span><span class="s2">"([^\{\}<>]|\{\d+,?\}|\{\d*,\d+\})+"</span><span class="p">,</span> <span class="sa">r</span><span class="s2">"[^\{\}<>]+"</span><span class="p">)</span>
<span class="p">)</span>
<div class="viewcode-block" id="tag_pattern2re_pattern"><a class="viewcode-back" href="../../../api/nltk.chunk.regexp.html#nltk.chunk.regexp.tag_pattern2re_pattern">[docs]</a><span class="k">def</span> <span class="nf">tag_pattern2re_pattern</span><span class="p">(</span><span class="n">tag_pattern</span><span class="p">):</span>
<span class="sd">"""</span>
<span class="sd"> Convert a tag pattern to a regular expression pattern. A "tag</span>
<span class="sd"> pattern" is a modified version of a regular expression, designed</span>
<span class="sd"> for matching sequences of tags. The differences between regular</span>
<span class="sd"> expression patterns and tag patterns are:</span>