-
Notifications
You must be signed in to change notification settings - Fork 1
/
Copy pathtextnorm.js
1345 lines (1167 loc) · 51.7 KB
/
textnorm.js
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
//******************************************************************************
//
// 2020 text normalisation JavaScript Lib,
// Prof. Charlotte Schubert Alte Geschichte, Leipzig
//
//******************************************************************************
/*
DEF: A text normalization is everything done to equalize encoding, appearance
and composition of a sequence of signs called a text. There are two goals of
normalization. The first is a common ground of signs and the second is a
reduction of differences between two sequences of signs. Not every
normalization step is useful for every comparison task! Remember:
Sometimes it is important to not equalize word forms and
sometimes it is important.
*/
/*
GPLv3 copyrigth
This program is free software: you can redistribute it and/or modify
it under the terms of the GNU General Public License as published by
the Free Software Foundation, either version 3 of the License, or
(at your option) any later version.
This program is distributed in the hope that it will be useful,
but WITHOUT ANY WARRANTY; without even the implied warranty of
MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
GNU General Public License for more details.
You should have received a copy of the GNU General Public License
along with this program. If not, see <http://www.gnu.org/licenses/>.
*/
//
"use strict";
//GLOBALS
let doUVlatin = false;
const analysisNormalform = "NFKD";
const dispnormalform = "NFC";
//
let notprivalpha = [];//["ἀΐω"];
//letters and words arrays
let buchstGRI = {"Α":"A", "α":"a", "Β":"B", "β":"b", "Γ":"G", "γ":"g", "Δ":"D", "δ":"d", "Ε":"E", "ε":"e", "Ζ":"Z", "ζ":"z", "Η":"H", "η":"h", "Θ":"Th", "θ":"th", "Ι":"I", "ι":"i", "Κ": "K", "κ":"k", "Λ":"L", "λ":"l", "Μ":"M", "μ":"m", "Ν":"N", "ν":"n", "Ξ":"Xi", "ξ":"xi", "Ο":"O", "ο":"o", "Π":"P", "π":"p", "Ρ":"R", "ρ":"r", "Σ":"S", "σ":"s", "ς":"s", "Τ":"T", "τ":"t", "Υ":"U", "υ":"u", "Φ":"Ph", "φ":"ph", "Χ":"X", "χ":"x", "Ψ":"Ps", "ψ":"ps", "Ω":"O", "ω":"o"}
let LAGRI = {"A":"Α", "a":"α", "B":"Β", "b":"β", "G":"Γ", "g":"γ", "D":"Δ", "d":"δ", "E":"Ε", "e":"ε", "Z":"Ζ", "z":"ζ", "H":"Η", "h":"η", "Th":"Θ", "th":"θ", "I":"Ι", "i":"ι", "K":"Κ", "k":"κ","C":"Κ", "c":"κ", "Q":"Κ", "q":"κ", "L":"Λ", "l":"λ", "M":"Μ", "m":"μ", "N":"Ν", "n":"ν", "Xi":"Ξ", "xi":"ξ", "O":"Ο", "o":"ο", "P":"Π", "p":"π", "R":"Ρ", "r":"ρ", "S":"Σ", "s":"σ", "s":"ς", "T":"Τ", "t":"τ", "U":"Υ", "u":"υ", "Ph":"Φ", "ph":"φ", "F":"Φ", "f":"φ", "V":"Φ", "v":"φ", "X":"Χ", "x":"χ", "Ps":"Ψ", "ps":"ψ", "O":"Ω", "o":"ω"}
const groups = {"γγ":["n", "g"], "γκ":["n", "c"], "γξ":["n","x"], "γχ":["n", "ch"], "ηυ":["ē", "u"]}; //only small letters?
const behauchung = { "῾":"h" }; //missing other Hauch?
const buchsCoptic = {"ϐ": "B", "ϑ":"Th", "ϱ":"r", "ϰ":"k", "ϒ":"y", "ϕ":"ph", "ϖ":"p", "Ϝ":"W", "ϝ":"w", "Ϙ":"Q","ϙ":"q", "Ϟ":"ḳ", "ϟ":"ḳ", "Ϲ":"S", "Ⲥ":"S", "ⲥ":"s", "ϲ":"s", "Ͻ":"S", "ͻ":"s","Ϳ ":"j","ϳ":"j","Ͱ":"h","ͱ":"h","Ⲁ":"A","ⲁ":"a",
"ϴ":"t","Ⲑ":"t","ⲑ":"t","ϵ":"e","϶":"e","Ϸ":"Sh","ϸ":"sh", "ϼ":"P","Ϡ":"S","ϡ":"S","Ⳁ":"S","ⳁ":"s",
"Ͳ":"Ss", "ͳ":"ss", "Ϻ":"S","ϻ":"s", "Ϣ":"š","ϣ":"š", "Ϥ":"F","ϥ":"f", "Ϧ":"X", "Ⳉ":"X",
"ϧ":"x","ⳉ":"x", "Ϩ":"H", "ϩ":"h", "Ϫ":"J", "ϫ":"j", "Ϭ":"C","ϭ":"c","Ϯ":"Di","ϯ":"di",
"Ͼ":"S", "Ͽ":"S", "ͼ":"s", "ͽ":"s", "Ⲃ":"B","ⲃ":"b","Ⲅ":"G","ⲅ":"g", "Ⲇ":"D", "ⲇ":"d", "Ⲉ":"E", "ⲉ":"e",
"Ⲋ":"St", "ⲋ":"st", "Ⲍ":"Z", "ⲍ":"z", "Ⲏ":"ê", "ⲏ":"ê", "Ⲓ":"I", "ⲓ":"i", "Ⲕ":"K", "ⲕ":"k",
"Ⲗ":"L", "ⲗ":"l", "Ⲙ":"M", "ⲙ":"m", "Ⲛ":"N","ⲛ":"n", "Ⲝ":"ks", "ⲝ":"ks", "Ⲟ ":"O", "ⲟ":"o",
"Ⲡ":"B", "ⲡ":"b", "Ⲣ":"R","ⲣ":"r", "Ⲧ":"T", "ⲧ":"t", "Ⲩ":"U", "ⲩ":"u", "Ⲫ":"F","ⲫ":"f","Ⲭ":"Kh", "ⲭ":"kh",
"Ⲯ":"Ps", "ⲯ":"ps", "Ⲱ":"ô", "ⲱ":"ô", "Ͷ":"W", "ͷ":"w"}; //
//"de" Akzente richtig, oder falsch????
let listofelusion = { "δ᾽":"δὲ","δ'":"δὲ", "ἀλλ’": "ἀλλά", "ἀνθ’": "ἀντί", "ἀπ’": "ἀπό", "ἀφ’": "ἀπό","γ’": "γε","γένοιτ’": "γένοιτο","δ’": "δέ","δι’": "διά","δύναιτ’": "δύναιτο","εἶτ’": "εἶτα","ἐπ’": "ἐπί","ἔτ’": "ἔτι","ἐφ’": "ἐπί","ἡγοῖντ’": "ἡγοῖντο","ἵν’": "ἵνα","καθ’": "κατά","κατ’": "κατά","μ’": "με","μεθ’": "μετά","μετ’": "μετά","μηδ’": "μηδέ","μήδ’": "μηδέ","ὅτ’": "ὅτε","οὐδ’": "οὐδέ","πάνθ’": "πάντα","πάντ’": "πάντα","παρ’": "παρά","ποτ’": "ποτε","σ’": "σε","ταῦθ’": "ταῦτα","ταῦτ’": "ταῦτα","τοῦτ’": "τοῦτο","ὑπ’": "ὑπό","ὑφ’": "ὑπό"};
//numbers
const ronum = {//not perfect
"i" :1,
"ii" :1,
"iii" :1,
"iiii" :1,
"iv" :1,
"v" :1,
"vii" :1,
"viii" :1,
"ix" :1,
"x" :1,
"xi" :1,
"xii" :1,
"xiii" :1,
"xiv" :1,
"xv" :1,
"xvi" :1,
"xvii" :1,
"xviii" :1,
"xix" :1,
"xx" :1,
"xxi" :1,
"xxii" :1,
"xxiii" :1,
"xxiv" :1,
"xxv" :1,
"xxvi" :1,
"xxvii" :1,
"xxviii" :1,
"xxix" :1,
"xxx" :1,
"xxxi" :1,
"xxxii" :1,
"xxxiii" :1,
"xxxiv" :1,
"xxxv" :1,
"xxxvi" :1,
"xxxvii" :1,
"xxxviii" :1,
"xxxix" :1,
"xl" :1,
"xli" :1,
"xlii" :1,
"xliii" :1,
"xliv" :1,
"xlv" :1,
"xlvi" :1,
"xlvii" :1,
"xlviii" :1,
"xlix" :1,
"l" :1,
"li" :1,
"lii" :1,
"liii" :1,
"liv" :1,
"lv" :1,
"lvi" :1,
"lvii" :1,
"lviii" :1,
"lix" :1,
"lx" :1,
"lxi" :1,
"lxii" :1,
"lxiii" :1,
"lxiv" :1,
"lxv" :1,
"lxvi" :1,
"lxvii" :1,
"lxviii" :1,
"lxix" :1,
"lxx" :1,
"lxxi" :1,
"lxxii" :1,
"lxxiii" :1,
"lxxiv" :1,
"lxxv" :1,
"lxxvi" :1,
"lxxvii" :1,
"lxxviii" :1,
"lxxix" :1,
"lxxx" :1,
"lxxxi" :1,
"lxxxii" :1,
"lxxxiii" :1,
"lxxxiv" :1,
"lxxxv" :1,
"lxxxvi" :1,
"lxxxvii" :1,
"lxxxviii" :1,
"lxxxix" :1,
"xc" :1,
"xci" :1,
"xcii" :1,
"xciii" :1,
"xciv" :1,
"xcv" :1,
"xcvi" :1,
"xcvii" :1,
"xcviii" :1,
"xcix" :1,
"c":1
};
const grnum = {//not perfect
"α" :1,
"β" :1,
"γ" :1,
"δ" :1,
"ε" :1,
"ϛ" :1,
"ζ" :1,
"η" :1,
"θ" :1,
"ι" :1,
"ια" :1,
"ιβ" :1,
"ιγ" :1,
"ιδ" :1,
"ιε" :1,
"ιϛ" :1,
"ιζ" :1,
"ιη" :1,
"ιθ" :1,
"κ" :1,
"κα" :1,
"κβ" :1,
"κγ" :1,
"κδ" :1,
"κε" :1,
"κϛ" :1,
"κζ" :1,
"κη" :1,
"κθ" :1,
"λ" :1,
"λα" :1,
"λβ" :1,
"λγ" :1,
"λδ" :1,
"λε" :1,
"λϛ" :1,
"λζ" :1,
"λη" :1,
"λθ" :1,
"μ" :1,
"μα" :1,
"μβ" :1,
"μγ" :1,
"μδ" :1,
"με" :1,
"μϛ" :1,
"μζ" :1,
"μη" :1,
"μθ" :1,
"ν" :1,
"να" :1,
"νβ" :1,
"νγ" :1,
"νδ" :1,
"νε" :1,
"νϛ" :1,
"νζ" :1,
"νη" :1,
"νθ" :1,
"ξ" :1,
"ξα" :1,
"ξβ" :1,
"ξγ" :1,
"ξδ" :1,
"ξε" :1,
"ξϛ" :1,
"ξζ" :1,
"ξη" :1,
"ξθ" :1,
"ο" :1,
"οα" :1,
"οβ" :1,
"ογ" :1,
"οδ" :1,
"οε" :1,
"οϛ" :1,
"οζ" :1,
"οη" :1,
"οθ" :1,
"π" :1,
"πα" :1,
"πβ" :1,
"πγ" :1,
"πδ" :1,
"πε" :1,
"πϛ" :1,
"πζ" :1,
"πη" :1,
"πθ" :1,
"ϟ" :1,
"ϟα" :1,
"ϟβ" :1,
"ϟγ" :1,
"ϟδ" :1,
"ϟε" :1,
"ϟϛ" :1,
"ϟζ" :1,
"ϟη" :1,
"ϟθ" :1,
"ρ" : 1
};
//regexp section
//const cleanhtmltags = new RegExp( '<(?:.|[\n\s\t\.\:])*?>', 'g' );
const cleanhtmltags = new RegExp('<[^>]*>', 'g' );
const cleanhtmlformat1 = new RegExp( ' ', 'g' );
const regEbr1 = new RegExp( '<br/>', 'g' );
const regEbr2 = new RegExp( '<br>', 'g' );
const reglb = new RegExp( '<lb.*?>', 'g' );
const cleanNEWL = new RegExp( '\n', 'g' );
const cleanRETL = new RegExp( '\r', 'g' );
const cleanTAB = new RegExp( '\t', 'g' );
const cleanstrangehochpunkt = new RegExp( '‧', 'g' );
const cleanthisbinde = new RegExp( '—', 'g' );
const cleanthisleer = new RegExp( '\xa0', 'g' );
const cleanleerpunkt = new RegExp( ' \\.', 'g' );
const cleanleerdoppelpunkt = new RegExp( ' :', 'g' );
const cleanleerkoma = new RegExp( ' ,', 'g' );
const cleanleersemik = new RegExp( ' ;', 'g' );
const cleanleerausrufe = new RegExp( ' !', 'g' );
const cleanleerfrege = new RegExp( ' \\?', 'g' );
//breakdown typographic letiances "Bindestriche und Geviertstriche"
const cleanklbindstrichvollbreit = new RegExp( '－', 'g' );
const cleanklbindstrichkurz = new RegExp( '﹣', 'g' );
const cleanklgeviert = new RegExp( '﹘', 'g' );
const cleanviertelgeviert = new RegExp( '‐', 'g' );
const cleanziffbreitergeviert = new RegExp( '‒', 'g' );
const cleanhalbgeviert = new RegExp( '–', 'g' );
const cleangeviert = new RegExp( '—', 'g' );
const escspitzeL = new RegExp( '<', 'g' );
const escspitzeR = new RegExp( '>', 'g' );
// array of unicode diacritics (relevant for polytonic greek)
const diacriticsunicodeRegExp = new Array(
new RegExp( '\u{0313}', 'g' ),
new RegExp( "\u{0314}", 'g' ),
new RegExp( "\u{0300}", 'g' ),
new RegExp( "\u{0301}", 'g' ),
new RegExp( "\u{00B4}", 'g' ),
new RegExp( "\u{02CA}", 'g' ),
new RegExp( "\u{02B9}", 'g' ),
new RegExp( "\u{0342}", 'g' ),
new RegExp( "\u{0308}", 'g' ),
new RegExp( "\u{0304}", 'g' ),
new RegExp( "\u{0306}", 'g' ),
new RegExp( '’', 'g' ),
new RegExp( '\'', 'g' ),
new RegExp( '᾽', 'g' ),
new RegExp( '´', 'g' ),
new RegExp( "‘", 'g' )
);
const alldiamodern = new RegExp( '[\u0300-\u036f]', 'g' );
const alldiamodern2 = new RegExp( '\p{Diacritic}', 'g' );
const regJotaSub = new RegExp( '\u{0345}', 'g' );
// precompiled regular expressions
/*const strClean1 = new RegExp( '’', 'g' );
const strClean2 = new RegExp( '\'', 'g' );
const strClean3 = new RegExp( '᾽', 'g' );
const strClean4 = new RegExp( '´', 'g' );
const strClean5 = new RegExp( "‘", 'g' );*/
const numeringReg1 = new RegExp( '\[[0-9]+\]', 'g' );
const numeringReg2 = new RegExp( /\[[M{0,4}(CM|CD|D?C{0,3})(XC|XL|L?X{0,3})(IX|IV|V?I{0,3})]+\]/, 'g' );
// precompiled regular expressions of the relevant ligatures
const regEstigma = new RegExp( '\u{03DA}', 'g' );
const regEstigmakl = new RegExp( '\u{03DB}', 'g' );
const regEomikonyplsi = new RegExp( 'ȣ', 'g' );
const regEomikonyplsiK = new RegExp( 'Ȣ', 'g' );
const regEUk = new RegExp( 'Ꙋ', 'g' );
const regEuk = new RegExp( 'ꙋ', 'g' );
const regEkai = new RegExp( 'ϗ', 'g' );
const regEKai = new RegExp( 'Ϗ', 'g' );
const regEl1 = new RegExp( '\u{0223}', 'g' );
const regEl2 = new RegExp( '\u{0222}', 'g' );
const regEdoppelP = new RegExp( ':', 'g' );
const regEeinfahP = new RegExp( '\\.', 'g' );
const regEkomma = new RegExp( ',', 'g' );
const regEsemiK = new RegExp( ';', 'g' );
const regEhochP = new RegExp( '·', 'g' );
const regEausr = new RegExp( '!', 'g' );
const regEfarge = new RegExp( '\\?', 'g' );
const regEan1 = new RegExp( '“', 'g' );
const regEan5 = new RegExp( '„', 'g' );
const regEan2 = new RegExp( '”', 'g' );
const regEan3 = new RegExp( '"', 'g' );
const regEan4 = new RegExp( "'", 'g' );
const regEan6 = new RegExp( '(\s*)[\∶|\⋮|\·|\⁙|;]+(\s*)', 'g' );
const regU1 = new RegExp( "†", 'g' );
const regU2 = new RegExp( "\\*", 'g' );
const regU3 = new RegExp( "⋖", 'g' );
const regU4 = new RegExp( "#", 'g' );
const regU5 = new RegExp( "§", 'g');
const regU6 = new RegExp( "⁑", 'g');
const regEtailingsig = new RegExp( "ς", 'g' );
const regEuv = new RegExp( "u", 'g' );
const regEvu = new RegExp( "v", 'g' );
const regEji = new RegExp( "j", 'g' );
const regEkla1 = new RegExp( /\(/, 'g' );
const regEkla2 = new RegExp( /\)/, 'g' );
const regEkla3 = new RegExp( /\{/, 'g' );
const regEkla4 = new RegExp( /\}/, 'g' );
const regEkla5 = new RegExp( /\[/, 'g' );
const regEkla6 = new RegExp( /\]/, 'g' );
const regEkla7 = new RegExp( '\u{003C}', 'g' ); //less than, THAT SEEM NOT TO WORK
const regEkla8 = new RegExp( /\>/, 'g' ); //THAT SEEM NOT TO WORK, without escape same same ????
const regEkla9 = new RegExp( "⌈", 'g' );
const regEkla10 = new RegExp( "⌉", 'g' );
const regEkla11 = new RegExp( "‹", 'g' );
const regEkla12 = new RegExp( "›", 'g' );
const regEkla13 = new RegExp( "«", 'g' );
const regEkla14 = new RegExp( "»", 'g' );
const regEkla15 = new RegExp( "⟦", 'g' );
const regEkla16 = new RegExp( "⟧", 'g' );
const regEkla17 = new RegExp( '\u{3008}', 'g' );
const regEkla18 = new RegExp( '\u{3009}', 'g' );
const regEkla19 = new RegExp( '\u{2329}', 'g' );
const regEkla20 = new RegExp( '\u{232A}', 'g' );
const regEkla21 = new RegExp( '\u{27E8}', 'g' );
const regEkla22 = new RegExp( '\u{27E9}', 'g' );
const spai1 = new RegExp( '\u{2002}', 'g' );//enspacing
const spai2 = new RegExp( '\u{2000}', 'g' );//enquad
let satzzeichen = new Array(".", ";", ",", ":", "!", "?", "·");
//**************************************************
// Section 0000
// helper
//**************************************************
function isnumber( maybe ){
//do romannumbers
const maymay = parseInt(maybe);
if( !isNaN( maymay ) ){
return true;
} else if( maybe in ronum ){
return true;
} else if( maybe in grnum ){
return true;
}
return false;
}
//******************************************************************************
// Section 000
// basic UNICODE NORMAL FORM / TRANSLITERATION
//******************************************************************************
function setAnaFormTO( fnew ){
analysisNormalform = fnew;
}
function setDisplFormTO( fnew ){
dispnormalform = fnew;
}
function normarrayk( aarray ){
let replacearray = new Object( );
for( let p in aarray ){
replacearray[ disambiguDIAkritika( p.normalize( analysisNormalform ) ) ] = aarray[ p ];
}
return replacearray;
}
function normarrayksiguv( aarray ){
let replacearray = new Object( );
for( let p in aarray ){
replacearray[ sigmaistgleich(delji(deluv( disambiguDIAkritika( p.normalize( analysisNormalform ) ) ) ) )] = aarray[ p ];
}
return replacearray;
}
function normarrayval( aarray ){ // by reference ????
for( let p in aarray ){
aarray[ p ] = disambiguDIAkritika( aarray[ p ].normalize( analysisNormalform ));
}
}
function normarrayvalsiguv( aarray ){ // by reference ????
for( let p in aarray ){
aarray[ p ] = sigmaistgleich(delji(deluv(disambiguDIAkritika( aarray[ p ].normalize( analysisNormalform )))));
}
}
// function takes sting and normalform string (for example "NFD")
/*function normatextwordbyword( text, wichnorm ){
let spt = text.split( " " );
const lele = spt.length;
for( let w = 0; w < lele; w++ ){
let nw = normatext( spt[ w ], wichnorm );
spt[ w ] = nw;
}
return spt.join( " " )
}*/
function normatext( text, wichnorm ){
return text.normalize( wichnorm );
}
function sameallspacing( astr ){
astr = astr.replace( spai1, ' ' );
astr = astr.replace( spai2, ' ' );
return astr;
}
function disambiguDIAkritika( astr ){
astr = astr.split( "\u0027" ).join( "\u2019" ); //typogra korrektes apostroph;
astr = astr.split( "'" ).join( "\u2019" );
astr = astr.split( "\u1FBD" ).join( "\u2019" );
//console.log(astr);
return astr;
}
function disambiguadashes( astring ){
astring = astring.replace( cleangeviert, '-' );
astring = astring.replace( cleanhalbgeviert, '-' );
astring = astring.replace( cleanziffbreitergeviert, '-' );
astring = astring.replace( cleanviertelgeviert, '-' );
astring = astring.replace( cleanklgeviert, '-' );
astring = astring.replace( cleanklbindstrichkurz, '-' );
astring = astring.replace( cleanklbindstrichvollbreit, '-' );
return astring;
}
function ExtractDiafromBuchst( buchst ){ //input as string
let toitter = buchst.normalize( "NFKD" ).split( "" );
let b = [];
let d = [];
for( let t in toitter ){
let co = toitter[t].toLowerCase( );
if( buchstGRI[ co ] || buchsCoptic[ co ] || buchstLAT[ co ] ){
b.push( toitter[t] );
} else {
d.push( toitter[t] );
}
}
return [d.join(""), b.join("")];
}
function ExtractDiafromBuchstText( atext ){
let t = "";
let spli = atext.split( " " );
for( let i in spli ){
t += JSON.stringify( ExtractDiafromBuchst( spli[ i ] ) );
}
return t;
}
function replaceBehauchung( adiakstring ){
if( adiakstring.indexOf( "῾" ) !== -1 ){
return "h"+adiakstring.replace( "῾","" );
} else {
return adiakstring;
}
}
//replace a elision
function Expandelision( aword ){
//if word in listofelusion
let t = listofelusion[ aword ];
if( t ){
return t;
} else {
return aword;
}
}
function ExpandelisionText( atext ){
let t = "";
let wds = atext.split( " " );
for( let w in wds ){
t += " "+ Expandelision( wds[ w ] );
}
return t;
}
function TranslitLatinGreekLetters( astring ){
//
let wordlevel = delligaturen( astring.trim().normalize( "NFC" ) ).split(" ");
let greekenized = [ ];
for( let w in wordlevel ){
let buchstlevel = Expandelision( wordlevel[ w ] ).split("");
const lele = len( buchstlevel );
let perword = [];
let extractedida2 = "";
let extracteBUCHST2 = "";
for( let b = 1; b < lele; b+=1 ){
let zwischenerg1 = ExtractDiafromBuchst( buchstlevel[ b-1 ] );
let zwischenerg2 = ExtractDiafromBuchst( buchstlevel[ b ] );
//console.log(zwischenerg1, zwischenerg2);
let extractedida1 = zwischenerg1[0];
extractedida2 = zwischenerg2[0];
let extracteBUCHST1 = zwischenerg1[1];
extracteBUCHST2 = zwischenerg2[1];
//console.log("o1", buchstlevel[ b-1 ], "o2", buchstlevel[ b ], "e1", extracteBUCHST1, "d1", extractedida1, "e2", extracteBUCHST2, "d2", extractedida2);
if( LAGRI[ extracteBUCHST1+extracteBUCHST2 ] && extracteBUCHST1 !== "" && extracteBUCHST2 !== "" ){
perword.push( LAGRI[ extracteBUCHST1+extracteBUCHST2 ]+extractedida1+extractedida2 );
} else {
if( LAGRI[extracteBUCHST1] ){
perword.push( LAGRI[ extracteBUCHST1 ]+extractedida1 );
} else {
perword.push( buchstlevel[ b-1 ] );
}
}
}
if( LAGRI[ extracteBUCHST2 ] ){
perword.push( LAGRI[ extracteBUCHST2 ]+extractedida2 );
} else {
perword.push( buchstlevel[ lele-1 ] );
}
greekenized.push( perword.join( "" ) );
}
//return astring;
return greekenized.join( " " );
}
function TraslitAncientGreekLatin( astring ){
//if( notgreek ){
// return astring;
//}
//console.log(astring);
let wordlevel = delligaturen( iotasubiotoad( astring.trim().normalize( "NFD" ) ).normalize( "NFC" ) ).split(" "); //care for iotasubscriptum, Ligature
//console.log(wordlevel);
//de !!!
let romanized = [];
for( let w in wordlevel ){
let buchstlevel = Expandelision( wordlevel[ w ] ).split("");
//console.log(buchstlevel);
let grouped = [];
let notlastdone = true;
let extractedida2 = "";
let extracteBUCHST2 = "";
const lele = len( buchstlevel );
for( let b = 1; b < lele; b+=1 ){
if( buchstlevel[ b-1 ] === "" ){
continue;
}
let zwischenerg1 = ExtractDiafromBuchst( buchstlevel[ b-1 ] );
let zwischenerg2 = ExtractDiafromBuchst( buchstlevel[ b ] );
let extractedida1 = zwischenerg1[0];
extractedida2 = zwischenerg2[0];
let extracteBUCHST1 = zwischenerg1[1];
extracteBUCHST2 = zwischenerg2[1];
//console.log(zwischenerg1, zwischenerg2);
if( groups[extracteBUCHST1+extracteBUCHST2] && extractedida2.indexOf( "¨" ) === -1 ){ //wenn kein trema über dem zweiten buchstaben - diaresis keine Zusammenziehung (synresis)
let gou = groups[ extracteBUCHST1+extracteBUCHST2 ];
grouped.push( (gou[0]+replaceBehauchung(extractedida1)+gou[1]+replaceBehauchung(extractedida2)).normalize( "NFC" ) );
buchstlevel[ b ] = "";//delet alread in groupand revistible
notlastdone = false;
} else {
if( buchstGRI[extracteBUCHST1] ){
grouped.push( (buchstGRI[extracteBUCHST1]+replaceBehauchung(extractedida1)).normalize( "NFC" ) );
} else {
if( buchsCoptic[extracteBUCHST1] ){
grouped.push( (buchsCoptic[extracteBUCHST1]+replaceBehauchung(extractedida1)).normalize( "NFC" ) );
} else {
//realy not - leave IT
grouped.push( buchstlevel[ b-1 ] );
}
}
notlastdone = true;
}
}
if( notlastdone ){
if( buchstGRI[extracteBUCHST2] ){
grouped.push( (buchstGRI[extracteBUCHST2]+replaceBehauchung(extractedida2)).normalize( "NFC" ) );
} else {
if( buchsCoptic[extracteBUCHST2] ){
grouped.push( (buchsCoptic[extracteBUCHST2]+replaceBehauchung(extractedida2)).normalize( "NFC" ) );
} else {
//realy not - leave IT
grouped.push( buchstlevel[ buchstlevel.length-1 ] );
}
}
}
romanized.push( grouped.join("") );
}
return romanized.join( " " );
}
//******************************************************************************
// Section 00
// basic cleaning and string conversion via regexp
//******************************************************************************
function spitzeklammernHTML( astr ){
return astr.replace( escspitzeL, '<' ).replace( escspitzeR, '>' );
}
//basic equalisation and hypenation reversion
function basClean( astring ){
astring = disambiguadashes( astring.replace(cleanNEWL, " <br/>").replace(cleanRETL, " <br/>").replace(cleanstrangehochpunkt,"·").replace(cleanthisbinde," — ").replace( cleanthisleer, ' ').replace( cleanleerpunkt, '.').replace( cleanleerdoppelpunkt, ':').replace( cleanleerkoma, ',').replace( cleanleersemik, ';').replace( cleanleerausrufe, '!').replace( cleanleerfrege, '?').replace(cleangeviert, '-').replace(cleanhalbgeviert, '-').replace(cleanziffbreitergeviert, '-').replace(cleanviertelgeviert, '-').replace(cleanklgeviert, '-').replace(cleanklbindstrichkurz, '-').replace(cleanklbindstrichvollbreit, '-'));
// remove hyphens
let ws = astring.split(" ");
let ca = Trennstricheraus( ws );
/*
let halfw = "";
let secondhalf = "";
for( let w in ws ){
if( ws[w].indexOf( "-" ) !== -1 ){
let h = ws[w].split( "-" );
halfw = h[0].replace(" ", "");
secondhalf = h[1].replace(" ", "");
if( secondhalf.indexOf("]") !== -1 ){
let hh = h[1].split("]");
if( hh[1].length > 1 ){
ca.push( halfw + hh[1] + " " + hh[0] + "]<br/>" );
halfw = "";
secondhalf = "";
}
}
} else if ( "<br/>" !== ws[w] && ws[w] !== "" && ws[w] !== " " && halfw !== "" ){
if( ws[w].indexOf("]") !== -1 ){
secondhalf = ws[w].replace(" ", "");
} else {
ca.push( halfw + ws[w].replace("<br/>", "") + " " + secondhalf + "<br/>" ); //trennstriche
halfw = "";
secondhalf = "";
}
} else {
if( ws[w] !== "" ){ //remove mehrfache leerstellen
ca.push( ws[w] );
}
}
}
*/
return ca.join( " " );
}
function ohnesatzzeichen( wliste ){
for(let sa in satzzeichen ){
for( let w in wliste){
wliste[ w ] = wliste[ w ].split( satzzeichen[ sa ] ).join( "" );
}
}
return wliste;
}
//usage: replaceWordsfromarray( ["in", "cum", "et", "a", "ut"], " ", stringggg )
function replaceWordsfromarray( arr, replacement, strstr ){
for( let a in arr){
strstr = strstr.replace( arr[a], replacement );
}
return strstr
}
//******************************************************************************
// Section 0
// word leve conversions:
// alpha privativum
// alpha copulativum
//******************************************************************************
function AlphaPrivativumCopulativum( aword ){ //just works on NFC and NFKC
if( notprivalpha.includes( aword ) === false ){
let buchs = delall( aword ).split( "" );
if( buchs[0] === "α" ){ //erste Buchstabe alpha
if( hasKEY( vokaleGRI , buchs[1] ) ){ // zweiter ein Vokal
let b2dia = ExtractDiafromBuchst(aword[1])[0];
//let b1dia = ExtractDiafromBuchst(aword[0])[0];
//console.log( "zweiter vokal", ""b2dia, b2dia.indexOf( "\u0308" ))
//insert the https://de.wikipedia.org/wiki/Unicodeblock_Kombinierende_diakritische_Zeichen
if( b2dia.indexOf( "\u0308" ) !== -1 ){ //zweiter Buchstabe mit Trema, erste Buchstabe mit spiritus lenis
return aword[0] +" "+ aword.slice(1) ;
} else { //
return aword;
}
} else {
return aword;
}
} else {
return aword;
}
} else {
return aword;
}
}
function AlphaPrivativumCopulativumText( atext ){
let t = "";
let spli = atext.split( " " );
for( let l in spli ){
t += " "+AlphaPrivativumCopulativum( spli[ l ] );
}
return t;
}
//******************************************************************************
// Section 1
// unicode related comparing and norming, handling of diacritics
//******************************************************************************
// function takes string, splits it with jota subscriptum and joins the string again using jota adscriptum
function iotasubiotoad( aword ){
return aword.split( "\u0345" ).join( "ι" );
}
// function takes "one word"
function ohnediakritW( aword ){
for( let dia in diacriticsunicodeRegExp ){
aword = aword.replace( diacriticsunicodeRegExp[ dia ], "" );
}
return aword;
}
function capitali( astring ) {
return astring.charAt(0).toUpperCase() + astring.slice(1).toLowerCase();
}
// function takes a string replaces some signs with regexp and oth
function nodiakinword( aword ){
//let spt = ((aword.replace(strClean1, "").replace(strClean2, "").replace(strClean3, "").replace(strClean4, "")).normalize( analysisNormalform ));
//return iotasubiotoad( ohnediakritW( spt ) );
return iotasubiotoad( ohnediakritW( aword.normalize( analysisNormalform ) ) );
}
//******************************************************************************
// Section 2: deleting things that could be not same in two texts
//******************************************************************************
// function take a string and deletes diacritical signes, ligatures, remaining interpunction, line breaks, capital letters to small ones, equalizes sigma at the end of greek words, and removes brakets
function delall( text ){
if( doUVlatin ){ // convert u to v in classical latin text
text = delji( deluv( delklammern( sigmaistgleich( iotasubiotoad( delgrkl( delumbrbine( delligaturen( delinterp( delmakup( delnumbering( delunknown( deldiak( text)))))))))))));
} else {
text = delklammern( sigmaistgleich( iotasubiotoad( delgrkl( delumbrbine( delligaturen( delinterp( delmakup( delnumbering( delunknown( deldiak( text ) ) ) ) ) ) ) ) ) ) );
}
return text;
}
//run this before the klammern deletion
function delnumbering( text ){ //untested
return text.replace( numeringReg1,"" ).replace( numeringReg2,"" );
}
// function take a string and replaces all occorences of a regular expression
function delligaturen( text ){
return text.replace( regEstigma, "στ").replace( regEstigmakl, "στ").replace( regEUk, "Υκ").replace( regEuk, "υκ").replace(regEomikonyplsi, "ου").replace(regEomikonyplsiK, "ου").replace(regEkai, "καὶ").replace(regEKai, "Καὶ").replace(regEl1, "\u039F\u03C5" ).replace(regEl2, "\u03BF\u03C5" );
}
// function takes string and splits it into words, than normalizes each word, joins the string again
function deldiak( text ){
//console.log(text);
let spt = text.split( " " ); //seperate words
const lele = spt.length;
for( let wi = 0; wi < lele; wi++ ){
spt[ wi ] = nodiakinword( spt[ wi ] );
}
return spt.join( " " );
}
// function deleates EVERYTHING in the unicode Character class DIACRITICS
function unicodediacriticsremove( str ){ //on NFD and NFKD strings!!!
return str.replace( alldiamodern, "");
}
// function takes a string and replaces interpunction
function delinterp( text ){
return text.replace(regEdoppelP, "").replace(regEeinfahP, "").replace(regEkomma, "").replace(regEsemiK, "").replace(regEhochP, "").replace(regEausr, "").replace(regEfarge, "").replace(regEan1, "").replace(regEan2, "").replace(regEan3, "").replace(regEan4, "").replace(regEan5, "").replace(regEan6, "");
}
// function takes a string and replaces some unknown signs
function delunknown( text ){
return text.replace(regU1, "").replace(regU2, "").replace(regU3, "").replace(regU4, "").replace(regU5, "").replace(regU6, "");
}
// function takes string and replace html line breakes
function delumbrbine( text ){
return text.replace( " ", " " ).replace(cleanNEWL, " ").replace(cleanRETL, " ").replace(regEbr1, " ").replace(regEbr2, " ");
}
function umbrtospace( text ){
text = text.replace(cleanNEWL, " ");
text = text.replace(cleanRETL, " ");
text = text.replace(regEbr1, " ");
text = text.replace(regEbr2, " ");
return text;
}
//more to come
function delma(text){
if( text.indexOf( "<body>" ) != -1 ){
text = text.split( "<body>" )[1];
}
return text.replace(regEbr2,"\n").replace(regEbr1,"\n").replace(reglb,"\n").replace(cleanhtmltags, "").replace(cleanhtmlformat1, "");
}
function delmakup( text ){
try{
let parser = new DOMParser(); //if dom parser fails - mal formed xml/html, than use fallback
let doc = parser.parseFromString( text, "text/xml" ); //xml = html?
if( parser != undefined && doc.getElementsByTagName("body").length > 0 ){
//console.log("------xml parser", doc.getElementsByTagName("body").textContent);
const inneertext = doc.getElementsByTagName("body").item(0).textContent;
if( inneertext.indexOf("error") !== -1 || inneertext== "" ){ //error in parsed document
//console.log("parser but error")
return delma(text);
} else {
//console.log(inneertext)
return inneertext;
}
} else { // if parser is null
//console.log(text.replace(cleanhtmltags, ""))
return delma(text);
}
} catch( e ){ //fallback - needed???
//console.log("no parser solution");
return delma(text);
}
}
function makuptoleer( text ){
return text.replace(cleanhtmltags, " ").replace(cleanhtmlformat1, " ");
}
// ...
function delgrkl( text ){
return text.toLowerCase();
}
// function takes string and converts tailing sigma to inline sigma (greek lang)
function sigmaistgleich( text ){
return text.replace(regEtailingsig, "σ");
}
// function take sstring and replaces the brakets -- do not run this before the Klammersystem fkt
function delklammern( text ){
return text.replace(regEkla1, "").replace(regEkla2, "").replace(regEkla3, "").replace(regEkla4,"").replace(regEkla5,"").replace(regEkla6,"").replace(regEkla7,"").replace(regEkla8,"").replace(regEkla9,"").replace(regEkla10,"").replace(regEkla11,"").replace(regEkla12,"").replace(regEkla13,"").replace(regEkla14,"").replace(regEkla15,"").replace(regEkla16,"").replace(regEkla17,"").replace(regEkla18,"").replace(regEkla19,"").replace(regEkla20,"").replace(regEkla21,"").replace(regEkla22,"");
}
function deledklammern( text ){
return text.replace(regEkla1, "").replace(regEkla2, "").replace(regEkla3, "").replace(regEkla4,"").replace(regEkla5,"").replace(regEkla6,"").replace(regEkla9,"").replace(regEkla10,"").replace(regEkla11,"").replace(regEkla12,"").replace(regEkla13,"").replace(regEkla14,"").replace(regEkla15,"").replace(regEkla16,"").replace(regEkla17,"").replace(regEkla18,"").replace(regEkla19,"").replace(regEkla20,"").replace(regEkla21,"").replace(regEkla22,"");
}
// function takes string and replaces u by v, used in classical latin texts
function deluv( text ){
//console.log(text);
//return text.replace( regEuv, "v" );
return text.replace( regEvu, "u" );
}
function delji( text ){
return text.replace( regEji, "i" );
}
//some bundels
function Trennstricheraus( wliste ){
let ersterteil = "";
let zweiterteil = "";
let neueWLISTE = [];
const lele = wliste.length;
for(let w = 0; w < lele; w++){
if( ersterteil.length === 0 ){
if( wliste[ w ].indexOf( "-" ) !== -1 ){
let eUNDz = wliste[ w ].split( "-" );
if( eUNDz[1].length > 0 ){
let zweiohnenewline = eUNDz[1].split( "\n" );
neueWLISTE.push( eUNDz[0]+zweiohnenewline[ zweiohnenewline.length-1 ] );
} else {
ersterteil = eUNDz[0];
}
//console.log(eUNDz.length, eUNDz);
} else { //nix - normales wort
neueWLISTE.push( wliste[ w ] );
}
} else { // es gab eine Trennung und die ging über zwei Listenzellen
if( wliste[ w ].indexOf( "[" ) === -1 && wliste[ w ].indexOf( "]" ) === -1){
let zweiteralsliste = wliste[ w ].split( "\n" );
//console.log("split", zweiteralsliste, wliste[ w ], ersterteil+zweiteralsliste[ zweiteralsliste.length-1 ]);
neueWLISTE.push( ersterteil+zweiteralsliste[ zweiteralsliste.length-1 ] );
ersterteil = "";
} else { //klammern behandeln
//wenn ich hier kein push auf der neune Wortliste mache, dann lösche ich damit die geklammerten sachen
if( wliste[ w ].indexOf( "[" ) !== -1 && wliste[ w ].indexOf( "]" ) !== -1 ){ //klammern in einem Wort
let zweiteralsliste = wliste[ w ].split( "]" );
neueWLISTE.push( ersterteil+zweiteralsliste[1].substring(1, zweiteralsliste[1].length-1) );
//console.log("NO SPLIT", ersterteil+zweiteralsliste[1].substring(1, zweiteralsliste[1].length-1));
} else if( wliste[ w ].indexOf( "[" ) !== -1 ){
let zweiteralsliste = wliste[ w ].split( "[" );
neueWLISTE.push( ersterteil+zweiteralsliste.join("") );
} else { //nur schließende Klammer
let zweiteralsliste = wliste[ w ].split( "]" );
neueWLISTE.push( ersterteil+zweiteralsliste[1] );
//console.log("NO SPLIT", ersterteil+zweiteralsliste[1].substring(1, zweiteralsliste[1].length-1));
}
}
}
}
return neueWLISTE;
}
function UmbruchzuLeerzeichen( atext ){
atext = atext.split("\n").join( " " );
return atext;
}
function Interpunktiongetrennt( wliste ){
let neuewliste = [];
for( let sa in satzzeichen ){
for(let w in wliste ){
if( wliste[ w ].indexOf( satzzeichen[ sa ] ) !== -1 ){
neuewliste.push( wliste[ w ].split( satzzeichen[ sa ] ).join( "" ) );
neuewliste.push( satzzeichen[ sa ] );
} else {
neuewliste.push( wliste[ w ] );
}
}
wliste = neuewliste;
neuewliste = [];
}
return wliste;
}