-
Notifications
You must be signed in to change notification settings - Fork 138
Expand file tree
/
Copy pathlinenoise.c
More file actions
3083 lines (2779 loc) · 86.7 KB
/
Copy pathlinenoise.c
File metadata and controls
3083 lines (2779 loc) · 86.7 KB
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
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
#line 1 "utf8.h"
#ifndef UTF8_UTIL_H
#define UTF8_UTIL_H
#ifdef __cplusplus
extern "C" {
#endif
/**
* UTF-8 utility functions
*
* (c) 2010-2019 Steve Bennett <steveb@workware.net.au>
*
* See utf8.c for licence details.
*/
#ifndef USE_UTF8
#include <ctype.h>
#define MAX_UTF8_LEN 1
/* No utf-8 support. 1 byte = 1 char */
#define utf8_charcount(S, B) ((B) < 0 ? (int)strlen(S) : (B))
#define utf8_strwidth(S, B) utf8_strlen((S), (B))
#define utf8_tounicode(S, CP) (*(CP) = (unsigned char)*(S), 1)
#define utf8_index(C, I) (I)
#define utf8_dispwidth(C) 1
#define utf8_str_dispwidth(S) (int)strlen(S)
#define utf8_char_bytes(S, B) 1
#define utf8_inspect(S, CP, DW) (*(CP) = (unsigned char)*(S), *(DW) = 1, 1)
#else
/* Note that below the term "character" is used to refer to a grapheme cluster,
* which may consist of multiple unicode code points.
* The term "codepoint" refers to a single unicode codepoint
* that may have a byte length of 1 or more
*/
#define MAX_UTF8_LEN 4
/* If you don't want to use the amalgamation, define UTF8_STATIC to empty
* to make these functions non-static and put them in a separate .c file.
*/
#ifndef UTF8_STATIC
#define UTF8_STATIC static
#endif
/**
* Converts the given unicode codepoint (0 - 0x1fffff) to utf-8
* and stores the result at 'p'.
*
* Returns the number of bytes used to store the codepoint.
*/
UTF8_STATIC int utf8_fromunicode(char p[MAX_UTF8_LEN], unsigned uc);
/**
* Returns the unicode codepoint corresponding to the
* utf-8 sequence 'str'.
*
* Stores the result in *uc and returns the number of bytes
* consumed.
*
* If 'str' is null terminated, then an invalid utf-8 sequence
* at the end of the string will be returned as individual bytes.
*
* If it is not null terminated, the length *must* be checked first.
*
* Does not support unicode code points > \u1fffff
*/
UTF8_STATIC int utf8_tounicode(const char *str, int *uc);
/**
* Returns the byte length of the utf-8 sequence starting with byte 'c'.
*
* Returns 1-4, or -1 if this is not a valid start byte.
*/
UTF8_STATIC int utf8_bytelen(int c);
/**
* Returns the number of characters in the string of the given byte length.
* If bytelen is -1, the string is assumed to be null terminated.
*
* Any bytes which are not part of an valid utf-8
* sequence are treated as individual characters.
*
* Does not support unicode code points > \u1fffff
*/
UTF8_STATIC int utf8_charcount(const char *str, int bytelen);
/**
* Returns the display width of the given unicode codepoint.
* This is 1 for normal letters and 0 for combining codepoints and 2 for wide codepoints.
*
* In general, use utf8_str_dispwidth() instead of this function as
* by itself it does not take into account combining characters,
* which may be part of a grapheme cluster.
*/
UTF8_STATIC int utf8_dispwidth(int cp);
/**
* Calculates the display width of the null terminates string, 'str'.
*/
UTF8_STATIC int utf8_str_dispwidth(const char *str);
/**
* Returns the byte index of the given character in the utf-8 string
* of the given length.
*
* This will return the byte length of a utf-8 string
* if given the char length.
*/
UTF8_STATIC int utf8_index(const char *str, int charindex);
/**
* Returns the number of bytes used to represent the first character at 'str'
* of length 'len' bytes. (len < 0 means null-terminated string)
*
* A character is a utf-8 encoded base codepoint followed by any number of combining characters,
* and possibly ZJW-joined characters.
*
* If the first character isn't valid UTF-8, it will be treated as a single byte character.
*/
UTF8_STATIC int utf8_char_bytes(const char *str, int len);
/**
* Like utf8_char_bytes(), but also returns the codepoint in *c and the display width of the character
* in *dispwidth.
*/
UTF8_STATIC int utf8_inspect(const char *str, int *c, int *dispwidth);
#endif
#ifdef __cplusplus
}
#endif
#endif
#line 1 "utf8.c"
/**
* UTF-8 utility functions
*
* (c) 2010-2026 Steve Bennett <steveb@workware.net.au>
*
* All rights reserved.
*
* Redistribution and use in source and binary forms, with or without
* modification, are permitted provided that the following conditions are met:
*
* * Redistributions of source code must retain the above copyright notice,
* this list of conditions and the following disclaimer.
*
* * Redistributions in binary form must reproduce the above copyright notice,
* this list of conditions and the following disclaimer in the documentation
* and/or other materials provided with the distribution.
*
* THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" AND
* ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED
* WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE
* DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE LIABLE FOR
* ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES
* (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES;
* LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON
* ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
* (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS
* SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
*/
#include <ctype.h>
#include <stdlib.h>
#include <string.h>
#include <stdio.h>
#include <assert.h>
#ifndef UTF8_UTIL_H
#include "utf8.h"
#endif
#ifdef USE_UTF8
UTF8_STATIC int utf8_fromunicode(char p[MAX_UTF8_LEN], unsigned uc)
{
if (uc <= 0x7f) {
*p = uc;
return 1;
}
else if (uc <= 0x7ff) {
*p++ = 0xc0 | ((uc & 0x7c0) >> 6);
*p = 0x80 | (uc & 0x3f);
return 2;
}
else if (uc <= 0xffff) {
*p++ = 0xe0 | ((uc & 0xf000) >> 12);
*p++ = 0x80 | ((uc & 0xfc0) >> 6);
*p = 0x80 | (uc & 0x3f);
return 3;
}
/* Note: We silently truncate to 21 bits here: 0x1fffff */
else {
*p++ = 0xf0 | ((uc & 0x1c0000) >> 18);
*p++ = 0x80 | ((uc & 0x3f000) >> 12);
*p++ = 0x80 | ((uc & 0xfc0) >> 6);
*p = 0x80 | (uc & 0x3f);
return 4;
}
}
UTF8_STATIC int utf8_bytelen(int c)
{
if ((c & 0x80) == 0) {
return 1;
}
if ((c & 0xe0) == 0xc0) {
return 2;
}
if ((c & 0xf0) == 0xe0) {
return 3;
}
if ((c & 0xf8) == 0xf0) {
return 4;
}
/* Invalid sequence */
return -1;
}
UTF8_STATIC int utf8_charcount(const char *str, int bytelen)
{
int chars = 0;
if (bytelen < 0) {
bytelen = strlen(str);
}
while (bytelen > 0) {
int n = utf8_char_bytes(str, bytelen);
if (n > bytelen) {
/* This is an invalid sequence, so consume what is remaining */
n = bytelen;
}
bytelen -= n;
str += n;
chars++;
}
return chars;
}
UTF8_STATIC int utf8_index(const char *str, int index)
{
const char *s = str;
while (index--) {
s += utf8_char_bytes(s, -1);
}
return s - str;
}
UTF8_STATIC int utf8_tounicode(const char *str, int *uc)
{
unsigned const char *s = (unsigned const char *)str;
if (s[0] < 0xc0) {
*uc = s[0];
return 1;
}
if (s[0] < 0xe0) {
if ((s[1] & 0xc0) == 0x80) {
*uc = ((s[0] & ~0xc0) << 6) | (s[1] & ~0x80);
if (*uc >= 0x80) {
return 2;
}
/* Otherwise this is an invalid sequence */
}
}
else if (s[0] < 0xf0) {
if (((str[1] & 0xc0) == 0x80) && ((str[2] & 0xc0) == 0x80)) {
*uc = ((s[0] & ~0xe0) << 12) | ((s[1] & ~0x80) << 6) | (s[2] & ~0x80);
if (*uc >= 0x800) {
return 3;
}
/* Otherwise this is an invalid sequence */
}
}
else if (s[0] < 0xf8) {
if (((str[1] & 0xc0) == 0x80) && ((str[2] & 0xc0) == 0x80) && ((str[3] & 0xc0) == 0x80)) {
*uc = ((s[0] & ~0xf0) << 18) | ((s[1] & ~0x80) << 12) | ((s[2] & ~0x80) << 6) | (s[3] & ~0x80);
if (*uc >= 0x10000) {
return 4;
}
/* Otherwise this is an invalid sequence */
}
}
/* Invalid sequence, so just return the byte */
*uc = *s;
return 1;
}
UTF8_STATIC int utf8_inspect(const char *str, int *c, int *dispwidth)
{
int n = utf8_tounicode(str, c);
/* Should this be utf8_str_dispwidth(str, n) instead? */
*dispwidth = utf8_dispwidth(*c);
return utf8_char_bytes(str, n);
}
UTF8_STATIC int utf8_str_dispwidth(const char *str)
{
int width = 0;
while (*str) {
int w;
int c;
int n = utf8_inspect(str, &c, &w);
width += w;
str += n;
}
return width;
}
/* Note: The following functions were taken largely as-is from
* https://github.com/antirez/linenoise.git
*/
static int utf8_is_variation_selector(int cp)
{
return cp == 0xFE0E || cp == 0xFE0F; /* Text/emoji style */
}
/* Check if codepoint is a skin tone modifier. */
static int isSkinToneModifier(int cp)
{
return cp >= 0x1F3FB && cp <= 0x1F3FF;
}
/* Check if codepoint is Zero Width Joiner. */
static int utf8_is_zero_width_joiner(int cp)
{
return cp == 0x200D;
}
/* Check if codepoint is a Regional Indicator (for flag emoji). */
static int utf8_is_regional_indicator(int cp)
{
return cp >= 0x1F1E6 && cp <= 0x1F1FF;
}
/* Check if codepoint is a combining mark or other zero-width character. */
static int utf8_is_combining_mark(int cp)
{
return (cp >= 0x0300 && cp <= 0x036F) || /* Combining Diacriticals */
(cp >= 0x1AB0 && cp <= 0x1AFF) || /* Combining Diacriticals Extended */
(cp >= 0x1DC0 && cp <= 0x1DFF) || /* Combining Diacriticals Supplement */
(cp >= 0x20D0 && cp <= 0x20FF) || /* Combining Diacriticals for Symbols */
(cp >= 0xFE20 && cp <= 0xFE2F); /* Combining Half Marks */
}
/* Check if codepoint extends the previous character (doesn't start a new grapheme). */
static int utf8_is_grapheme_extend(int cp)
{
return utf8_is_variation_selector(cp) || isSkinToneModifier(cp) ||
utf8_is_zero_width_joiner(cp) || utf8_is_combining_mark(cp);
}
/* Note: The following functions are based on code from
* https://github.com/antirez/linenoise.git
*/
UTF8_STATIC int utf8_char_bytes(const char *str, int len)
{
/* First we get the current character. Then we look ahead
* to see if there are any combining characters that follow it, and if so we
* treat them as part of the same "character".
*/
int total = 0;
int c;
int n = utf8_tounicode(str, &c);
total += n;
str += n;
if (len < 0) {
len = strlen(str);
}
const char *end = str + len;
int is_ri = utf8_is_regional_indicator(c);
/* Consume any extending characters that follow. */
while (str < end) {
/* Check the next character. */
n = utf8_tounicode(str, &c);
if (utf8_is_zero_width_joiner(c) && str + n < end) {
/* ZWJ: include it and the following character. */
total += n;
str += n;
/* Get the character after ZWJ. */
n = utf8_tounicode(str, &c);
total += n;
str += n;
continue; /* Check for more extending after the joined char. */
} else if (utf8_is_grapheme_extend(c)) {
/* Variation selector, skin tone, combining mark, etc. */
total += n;
str += n;
continue;
} else if (is_ri && utf8_is_regional_indicator(c)) {
/* Second regional indicator for a flag pair. */
total += n;
str += n;
is_ri = 0; /* Only pair once. */
continue;
} else {
break;
}
}
return total;
}
/* Return the display width of a Unicode codepoint. This is a heuristic
* that works for most common cases:
* - Control chars and zero-width: 0 columns
* - Grapheme-extending chars (VS, skin tone, ZWJ): 0 columns
* - ASCII printable: 1 column
* - Wide chars (CJK, emoji, fullwidth): 2 columns
* - Everything else: 1 column
*
* This is not a full wcwidth() implementation, but a minimal heuristic
* that handles emoji and CJK characters reasonably well. */
UTF8_STATIC int utf8_dispwidth(int cp)
{
/* Control characters and combining marks: zero width. */
if (cp < 32 || (cp >= 0x7F && cp < 0xA0)) {
return 0;
}
if (utf8_is_combining_mark(cp)) {
return 0;
}
/* Grapheme-extending characters: zero width.
* These modify the preceding character rather than taking space. */
if (utf8_is_variation_selector(cp) || utf8_is_combining_mark(cp) || utf8_is_grapheme_extend(cp)) {
return 0;
}
/* Wide character ranges - these display as 2 columns:
* - CJK Unified Ideographs and Extensions
* - Fullwidth forms
* - Various emoji ranges */
if (cp >= 0x1100 &&
(cp <= 0x115F || /* Hangul Jamo */
cp == 0x2329 || cp == 0x232A || /* Angle brackets */
(cp >= 0x231A && cp <= 0x231B) || /* Watch, Hourglass */
(cp >= 0x23E9 && cp <= 0x23F3) || /* Various symbols */
(cp >= 0x23F8 && cp <= 0x23FA) || /* Various symbols */
(cp >= 0x25AA && cp <= 0x25AB) || /* Small squares */
(cp >= 0x25B6 && cp <= 0x25C0) || /* Play/reverse buttons */
(cp >= 0x25FB && cp <= 0x25FE) || /* Squares */
(cp >= 0x2600 && cp <= 0x26FF) || /* Misc Symbols (sun, cloud, etc) */
(cp >= 0x2700 && cp <= 0x27BF) || /* Dingbats (❤, ✂, etc) */
(cp >= 0x2934 && cp <= 0x2935) || /* Arrows */
(cp >= 0x2B05 && cp <= 0x2B07) || /* Arrows */
(cp >= 0x2B1B && cp <= 0x2B1C) || /* Squares */
cp == 0x2B50 || cp == 0x2B55 || /* Star, circle */
(cp >= 0x2E80 && cp <= 0xA4CF &&
cp != 0x303F) || /* CJK ... Yi */
(cp >= 0xAC00 && cp <= 0xD7A3) || /* Hangul Syllables */
(cp >= 0xF900 && cp <= 0xFAFF) || /* CJK Compatibility Ideographs */
(cp >= 0xFE10 && cp <= 0xFE1F) || /* Vertical forms */
(cp >= 0xFE30 && cp <= 0xFE6F) || /* CJK Compatibility Forms */
(cp >= 0xFF00 && cp <= 0xFF60) || /* Fullwidth Forms */
(cp >= 0xFFE0 && cp <= 0xFFE6) || /* Fullwidth Signs */
(cp >= 0x1F1E6 && cp <= 0x1F1FF) || /* Regional Indicators (flags) */
(cp >= 0x1F300 && cp <= 0x1F64F) || /* Misc Symbols and Emoticons */
(cp >= 0x1F680 && cp <= 0x1F6FF) || /* Transport and Map Symbols */
(cp >= 0x1F900 && cp <= 0x1F9FF) || /* Supplemental Symbols */
(cp >= 0x1FA00 && cp <= 0x1FAFF) || /* Chess, Extended-A */
(cp >= 0x20000 && cp <= 0x2FFFF))) /* CJK Extension B and beyond */
return 2;
return 1; /* Default: single width */
}
#endif
#line 1 "stringbuf.h"
#ifndef STRINGBUF_H
#define STRINGBUF_H
/**
* resizable string buffer supporting utf8 "characters" if USE_UTF8 is defined.
*
* Note that here "characters" means utf8 graphemes, which may
* correspond to more than one codepoint.
*
* (c) 2017-2026 Steve Bennett <steveb@workware.net.au>
*
* See utf8.c for licence details.
*/
#ifdef __cplusplus
extern "C" {
#endif
/** @file
* A stringbuf is a resizing, null terminated string buffer.
*
* The buffer is reallocated as necessary.
*
* In general it is *not* OK to call these functions with a NULL pointer
* unless stated otherwise.
*
* If USE_UTF8 is defined, supports utf8.
*/
/**
* The stringbuf structure should not be accessed directly.
* Use the functions below.
*/
typedef struct {
int remaining; /**< Allocated, but unused space */
int last; /**< Index of the null terminator (and thus the length of the string) */
#ifdef USE_UTF8
int chars; /**< Count of characters */
#endif
char *data; /**< Allocated memory containing the string or NULL for empty */
} stringbuf;
/**
* Allocates and returns a new stringbuf with no elements.
*/
stringbuf *sb_alloc(void);
/**
* Frees a stringbuf.
* It is OK to call this with NULL.
*/
void sb_free(stringbuf *sb);
/**
* Returns an allocated copy of the stringbuf
*/
stringbuf *sb_copy(stringbuf *sb);
/**
* Returns the byte length of the buffer.
*
* Returns 0 for both a NULL buffer and an empty buffer.
*/
static inline int sb_len(stringbuf *sb) {
return sb->last;
}
/**
* Returns the utf8 character length of the buffer.
*
* Returns 0 for both a NULL buffer and an empty buffer.
*/
int sb_chars(stringbuf *sb);
/**
* Appends a null terminated string to the stringbuf
*/
void sb_append(stringbuf *sb, const char *str);
/**
* Like sb_append() except does not require a null terminated string.
* The length of 'str' is given as 'len'
*/
void sb_append_len(stringbuf *sb, const char *str, int len);
/**
* Returns a pointer to the null terminated string in the buffer.
*
* Note this pointer only remains valid until the next modification to the
* string buffer.
*
* The returned pointer can be used to update the buffer in-place
* as long as care is taken to not overwrite the end of the buffer.
*/
static inline char *sb_str(const stringbuf *sb)
{
return sb->data;
}
/**
* Inserts the given string *before* (zero-based) byte 'index' in the stringbuf.
* If index is past the end of the buffer, the string is appended,
* just like sb_append()
* len is the length of 'str' in bytes, or -1 to indicate a null terminated string.
*
* In utf8 mode, be careful to only insert at the start of a char.
*/
void sb_insert_len(stringbuf *sb, int index, const char *str, int len);
/**
* Like sb_insert_len() except 'str' is null terminated.
*/
#define sb_insert(SB, I, STR) sb_insert_len(SB, I, STR, -1)
/**
* Like sb_insert_len() except position is given as a character index instead of a byte index.
*/
void sb_insert_chars(stringbuf *sb, int charindex, const char *str, int len);
/**
* Delete 'len' bytes in the string at the given byte index.
*
* Any bytes past the end of the buffer are ignored.
* The buffer remains null terminated.
*
* If len is -1, deletes to the end of the buffer.
*
* In utf8 mode, be careful to only delete whole chars.
*/
void sb_delete(stringbuf *sb, int index, int len);
/**
* Like sb_delete(), except position and length are given
* as characters instead of bytes.
*/
void sb_delete_chars(stringbuf *sb, int charindex, int nchars);
/**
* Clear to an empty buffer.
*/
void sb_clear(stringbuf *sb);
/**
* Return an allocated copy of buffer and frees 'sb'.
*
* If 'sb' is empty, returns an allocated copy of "".
*/
char *sb_to_string(stringbuf *sb);
#ifdef __cplusplus
}
#endif
#endif
#line 1 "stringbuf.c"
/**
* resizable string buffer
*
* (c) 2017-2020 Steve Bennett <steveb@workware.net.au>
*
* See utf8.c for licence details.
*/
#include <stdlib.h>
#include <string.h>
#include <stdio.h>
#include <ctype.h>
#include <assert.h>
#ifndef STRINGBUF_H
#include "stringbuf.h"
#endif
#ifdef USE_UTF8
#ifndef UTF8_UTIL_H
#include "utf8.h"
#endif
#endif
#define SB_INCREMENT 200
stringbuf *sb_alloc(void)
{
stringbuf *sb = (stringbuf *)malloc(sizeof(*sb));
sb->remaining = 0;
sb->last = 0;
#ifdef USE_UTF8
sb->chars = 0;
#endif
sb->data = NULL;
return(sb);
}
void sb_free(stringbuf *sb)
{
if (sb) {
free(sb->data);
}
free(sb);
}
static void sb_realloc(stringbuf *sb, int newlen)
{
sb->data = (char *)realloc(sb->data, newlen);
sb->remaining = newlen - sb->last;
}
/* Returns the character count, recalculating it if necessary.
*/
#ifdef USE_UTF8
static int sb_get_charlen(stringbuf *sb)
{
if (sb->chars < 0) {
sb->chars = utf8_charcount(sb->data, sb->last);
}
return sb->chars;
}
#endif
/* Mark the char count as invalid so it can be recalculated when needed. */
static void sb_invalidate_charlen(stringbuf *sb)
{
#ifdef USE_UTF8
sb->chars = -1;
#else
(void)sb;
#endif
}
/**
* Returns the utf8 character length of the buffer.
*
* Returns 0 for both a NULL buffer and an empty buffer.
*/
int sb_chars(stringbuf *sb)
{
#ifdef USE_UTF8
return sb_get_charlen(sb);
#else
return sb->last;
#endif
}
void sb_append(stringbuf *sb, const char *str)
{
sb_append_len(sb, str, strlen(str));
}
void sb_append_len(stringbuf *sb, const char *str, int len)
{
if (sb->remaining < len + 1) {
sb_realloc(sb, sb->last + len + 1 + SB_INCREMENT);
}
memcpy(sb->data + sb->last, str, len);
sb->data[sb->last + len] = 0;
sb->last += len;
sb->remaining -= len;
sb_invalidate_charlen(sb);
}
char *sb_to_string(stringbuf *sb)
{
if (sb->data == NULL) {
/* Return an allocated empty string, not null */
return strdup("");
}
else {
/* Just return the data and free the stringbuf structure */
char *pt = sb->data;
free(sb);
return pt;
}
}
/* Insert and delete operations */
/* Moves up all the data at position 'pos' and beyond by 'len' bytes
* to make room for new data
*
* Note: Does *not* recalc char count
*/
static void sb_insert_space(stringbuf *sb, int pos, int len)
{
assert(pos <= sb->last);
/* Make sure there is enough space */
if (sb->remaining < len) {
sb_realloc(sb, sb->last + len + SB_INCREMENT);
}
/* Now move it up */
memmove(sb->data + pos + len, sb->data + pos, sb->last - pos);
sb->last += len;
sb->remaining -= len;
/* And null terminate */
sb->data[sb->last] = 0;
}
/**
* Move down all the data from pos + len, effectively
* deleting the data at position 'pos' of length 'len'
*
* Note: Does *not* recalc char count
*/
static void sb_delete_space(stringbuf *sb, int pos, int len)
{
assert(pos < sb->last);
assert(pos + len <= sb->last);
/* Now move it up */
memmove(sb->data + pos, sb->data + pos + len, sb->last - pos - len);
sb->last -= len;
sb->remaining += len;
/* And null terminate */
sb->data[sb->last] = 0;
}
void sb_insert_len(stringbuf *sb, int index, const char *str, int len)
{
if (len < 0) {
len = strlen(str);
}
if (index >= sb->last) {
/* Inserting after the end of the list appends. */
sb_append_len(sb, str, len);
}
else {
sb_insert_space(sb, index, len);
memcpy(sb->data + index, str, len);
}
sb_invalidate_charlen(sb);
}
/**
* Like sb_insert_len() except position is given as a character index instead of a byte index.
*/
void sb_insert_chars(stringbuf *sb, int charindex, const char *str, int len)
{
/* Find the byte position of the char index */
#ifdef USE_UTF8
int pos = utf8_index(sb->data, charindex);
#else
int pos = charindex;
#endif
/* And insert the string at that position */
sb_insert_len(sb, pos, str, len);
}
/**
* Delete the bytes at index 'index' for length 'len'
* Has no effect if the index is past the end of the list.
*/
void sb_delete(stringbuf *sb, int index, int len)
{
if (index < sb->last) {
char *pos = sb->data + index;
if (len < 0) {
len = sb->last;
}
sb_delete_space(sb, pos - sb->data, len);
sb_invalidate_charlen(sb);
}
}
void sb_delete_chars(stringbuf *sb, int charpos, int nchars)
{
#ifdef USE_UTF8
if (charpos < sb_get_charlen(sb)) {
/* Find the byte position of the char index */
int pos = utf8_index(sb->data, charpos);
/* Now calculate the byte length of 'nchars' chars at this position */
int bytelen = utf8_index(sb->data + pos, nchars);
/* And delete them */
sb_delete(sb, pos, bytelen);
}
#else
/* If we don't have UTF-8 support then just delete the bytes */
sb_delete(sb, charpos, nchars);
#endif
}
void sb_clear(stringbuf *sb)
{
if (sb->data) {
/* Null terminate */
sb->data[0] = 0;
sb->last = 0;
#ifdef USE_UTF8
sb->chars = 0;
#endif
}
}
#line 1 "linenoise.c"
/* linenoise.c -- guerrilla line editing library against the idea that a
* line editing lib needs to be 20,000 lines of C code.
*
* You can find the latest source code at:
*
* http://github.com/msteveb/linenoise
* (forked from http://github.com/antirez/linenoise)
*
* Does a number of crazy assumptions that happen to be true in 99.9999% of
* the 2010 UNIX computers around.
*
* ------------------------------------------------------------------------
*
* Copyright (c) 2010, Salvatore Sanfilippo <antirez at gmail dot com>
* Copyright (c) 2010, Pieter Noordhuis <pcnoordhuis at gmail dot com>
* Copyright (c) 2011, Steve Bennett <steveb at workware dot net dot au>
*
* All rights reserved.
*
* Redistribution and use in source and binary forms, with or without
* modification, are permitted provided that the following conditions are
* met:
*
* * Redistributions of source code must retain the above copyright
* notice, this list of conditions and the following disclaimer.
*
* * Redistributions in binary form must reproduce the above copyright
* notice, this list of conditions and the following disclaimer in the
* documentation and/or other materials provided with the distribution.
*
* THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
* "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
* LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
* A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
* HOLDER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
* SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
* LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
* DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
* THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
* (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
* OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
*
* ------------------------------------------------------------------------
*
* References:
* - http://invisible-island.net/xterm/ctlseqs/ctlseqs.html
* - http://www.3waylabs.com/nw/WWW/products/wizcon/vt220.html
*
* Bloat:
* - Completion?
*
* Unix/termios
* ------------
* List of escape sequences used by this program, we do everything just
* a few sequences. In order to be so cheap we may have some
* flickering effect with some slow terminal, but the lesser sequences
* the more compatible.
*
* EL (Erase Line)
* Sequence: ESC [ 0 K
* Effect: clear from cursor to end of line
*
* CUF (CUrsor Forward)
* Sequence: ESC [ n C
* Effect: moves cursor forward n chars
*
* CR (Carriage Return)
* Sequence: \r
* Effect: moves cursor to column 1
*
* The following are used to clear the screen: ESC [ H ESC [ 2 J
* This is actually composed of two sequences:
*
* cursorhome
* Sequence: ESC [ H
* Effect: moves the cursor to upper left corner
*
* ED2 (Clear entire screen)
* Sequence: ESC [ 2 J
* Effect: clear the whole screen
*
* == For highlighting control characters, we also use the following two ==
* SO (enter StandOut)
* Sequence: ESC [ 7 m
* Effect: Uses some standout mode such as reverse video
*
* SE (Standout End)
* Sequence: ESC [ 0 m
* Effect: Exit standout mode
*
* == Only used if TIOCGWINSZ fails ==
* DSR/CPR (Report cursor position)
* Sequence: ESC [ 6 n
* Effect: reports current cursor position as ESC [ NNN ; MMM R
*
* == Only used in multiline mode ==
* CUU (Cursor Up)
* Sequence: ESC [ n A
* Effect: moves cursor up n chars.
*
* CUD (Cursor Down)
* Sequence: ESC [ n B
* Effect: moves cursor down n chars.
*
* win32/console
* -------------
* If __MINGW32__ is defined, the win32 console API is used.
* This could probably be made to work for the msvc compiler too.
* This support based in part on work by Jon Griffiths.
*/
#ifdef _WIN32 /* Windows platform, either MinGW or Visual Studio (MSVC) */
#include <windows.h>
#include <fcntl.h>
#define USE_WINCONSOLE
#ifdef __MINGW32__
#define HAVE_UNISTD_H
#endif
#else
#include <termios.h>
#include <sys/ioctl.h>
#include <poll.h>
#define USE_TERMIOS
#define HAVE_UNISTD_H
#endif
#ifdef HAVE_UNISTD_H
#include <unistd.h>
#endif
#include <stdlib.h>
#include <stdarg.h>