Training courses

Kernel and Embedded Linux

Bootlin training courses

Embedded Linux, kernel,
Yocto Project, Buildroot, real-time,
graphics, boot time, debugging...

Bootlin logo

Elixir Cross Referencer

  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
/*	$NetBSD: v_word.c,v 1.4 2017/11/21 07:43:47 rin Exp $ */
/*-
 * Copyright (c) 1992, 1993, 1994
 *	The Regents of the University of California.  All rights reserved.
 * Copyright (c) 1992, 1993, 1994, 1995, 1996
 *	Keith Bostic.  All rights reserved.
 *
 * See the LICENSE file for redistribution information.
 */

#include "config.h"

#include <sys/cdefs.h>
#if 0
#ifndef lint
static const char sccsid[] = "Id: v_word.c,v 10.6 2001/06/25 15:19:36 skimo Exp  (Berkeley) Date: 2001/06/25 15:19:36 ";
#endif /* not lint */
#else
__RCSID("$NetBSD: v_word.c,v 1.4 2017/11/21 07:43:47 rin Exp $");
#endif

#include <sys/types.h>
#include <sys/queue.h>
#include <sys/time.h>

#include <bitstring.h>
#include <ctype.h>
#include <limits.h>
#include <stdio.h>

#include "../common/common.h"
#include "vi.h"

/*
 * There are two types of "words".  Bigwords are easy -- groups of anything
 * delimited by whitespace.  Normal words are trickier.  They are either a
 * group of characters, numbers and underscores, or a group of anything but,
 * delimited by whitespace.  When for a word, if you're in whitespace, it's
 * easy, just remove the whitespace and go to the beginning or end of the
 * word.  Otherwise, figure out if the next character is in a different group.
 * If it is, go to the beginning or end of that group, otherwise, go to the
 * beginning or end of the current group.  The historic version of vi didn't
 * get this right, so, for example, there were cases where "4e" was not the
 * same as "eeee" -- in particular, single character words, and commands that
 * began in whitespace were almost always handled incorrectly.  To get it right
 * you have to resolve the cursor after each search so that the look-ahead to
 * figure out what type of "word" the cursor is in will be correct.
 *
 * Empty lines, and lines that consist of only white-space characters count
 * as a single word, and the beginning and end of the file counts as an
 * infinite number of words.
 *
 * Movements associated with commands are different than movement commands.
 * For example, in "abc  def", with the cursor on the 'a', "cw" is from
 * 'a' to 'c', while "w" is from 'a' to 'd'.  In general, trailing white
 * space is discarded from the change movement.  Another example is that,
 * in the same string, a "cw" on any white space character replaces that
 * single character, and nothing else.  Ain't nothin' in here that's easy.
 *
 * One historic note -- in the original vi, the 'w', 'W' and 'B' commands
 * would treat groups of empty lines as individual words, i.e. the command
 * would move the cursor to each new empty line.  The 'e' and 'E' commands
 * would treat groups of empty lines as a single word, i.e. the first use
 * would move past the group of lines.  The 'b' command would just beep at
 * you, or, if you did it from the start of the line as part of a motion
 * command, go absolutely nuts.  If the lines contained only white-space
 * characters, the 'w' and 'W' commands would just beep at you, and the 'B',
 * 'b', 'E' and 'e' commands would treat the group as a single word, and
 * the 'B' and 'b' commands will treat the lines as individual words.  This
 * implementation treats all of these cases as a single white-space word.
 *
 * We regard a boundary between single- and multi-width characters as
 * a word boundary.
 */

enum which {BIGWORD, LITTLEWORD};

static int bword __P((SCR *, VICMD *, enum which));
static int eword __P((SCR *, VICMD *, enum which));
static int fword __P((SCR *, VICMD *, enum which));

/*
 * v_wordW -- [count]W
 *	Move forward a bigword at a time.
 *
 * PUBLIC: int v_wordW __P((SCR *, VICMD *));
 */
int
v_wordW(SCR *sp, VICMD *vp)
{
	return (fword(sp, vp, BIGWORD));
}

/*
 * v_wordw -- [count]w
 *	Move forward a word at a time.
 *
 * PUBLIC: int v_wordw __P((SCR *, VICMD *));
 */
int
v_wordw(SCR *sp, VICMD *vp)
{
	return (fword(sp, vp, LITTLEWORD));
}

/*
 * fword --
 *	Move forward by words.
 */
static int
fword(SCR *sp, VICMD *vp, enum which type)
{
	enum { INWORD, NOTWORD } state;
	VCS cs;
	u_long cnt;
	int nmw, omw;

	cnt = F_ISSET(vp, VC_C1SET) ? vp->count : 1;
	cs.cs_lno = vp->m_start.lno;
	cs.cs_cno = vp->m_start.cno;
	if (cs_init(sp, &cs))
		return (1);

	/*
	 * If in white-space:
	 *	If the count is 1, and it's a change command, we're done.
	 *	Else, move to the first non-white-space character, which
	 *	counts as a single word move.  If it's a motion command,
	 *	don't move off the end of the line.
	 */
	if (cs.cs_flags == CS_EMP || (cs.cs_flags == 0 && ISBLANK2(cs.cs_ch))) {
		if (ISMOTION(vp) && cs.cs_flags != CS_EMP && cnt == 1) {
			if (ISCMD(vp->rkp, 'c'))
				return (0);
			if (ISCMD(vp->rkp, 'd') || ISCMD(vp->rkp, 'y')) {
				if (cs_fspace(sp, &cs))
					return (1);
				goto ret;
			}
		}
		if (cs_fblank(sp, &cs))
			return (1);
		--cnt;
	}

	/*
	 * Cyclically move to the next word -- this involves skipping
	 * over word characters and then any trailing non-word characters.
	 * Note, for the 'w' command, the definition of a word keeps
	 * switching.
	 */
	if (type == BIGWORD)
		while (cnt--) {
			nmw = ISMULTIWIDTH(sp, cs.cs_ch);
			for (;;) {
				omw = nmw;
				if (cs_next(sp, &cs))
					return (1);
				if (cs.cs_flags == CS_EOF)
					goto ret;
				if (cs.cs_flags != 0 || ISBLANK2(cs.cs_ch) ||
				    (nmw = ISMULTIWIDTH(sp, cs.cs_ch)) != omw)
					break;
			}
			/*
			 * If a motion command and we're at the end of the
			 * last word, we're done.  Delete and yank eat any
			 * trailing blanks, but we don't move off the end
			 * of the line regardless.
			 */
			if (cnt == 0 && ISMOTION(vp)) {
				if ((ISCMD(vp->rkp, 'd') ||
				    ISCMD(vp->rkp, 'y')) &&
				    cs_fspace(sp, &cs))
					return (1);
				break;
			}

			/* Eat whitespace characters. */
			if (nmw == omw && cs_fblank(sp, &cs))
				return (1);
			if (cs.cs_flags == CS_EOF)
				goto ret;
		}
	else
		while (cnt--) {
			state = cs.cs_flags == 0 &&
			    inword(cs.cs_ch) ? INWORD : NOTWORD;
			nmw = ISMULTIWIDTH(sp, cs.cs_ch);
			for (;;) {
				omw = nmw;
				if (cs_next(sp, &cs))
					return (1);
				if (cs.cs_flags == CS_EOF)
					goto ret;
				if (cs.cs_flags != 0 || ISBLANK2(cs.cs_ch) ||
				    (nmw = ISMULTIWIDTH(sp, cs.cs_ch)) != omw)
					break;
				if (state == INWORD) {
					if (!inword(cs.cs_ch))
						break;
				} else
					if (inword(cs.cs_ch))
						break;
			}
			/* See comment above. */
			if (cnt == 0 && ISMOTION(vp)) {
				if ((ISCMD(vp->rkp, 'd') ||
				    ISCMD(vp->rkp, 'y')) &&
				    cs_fspace(sp, &cs))
					return (1);
				break;
			}

			/* Eat whitespace characters. */
			if (cs.cs_flags != 0 || ISBLANK2(cs.cs_ch))
				if (cs_fblank(sp, &cs))
					return (1);
			if (cs.cs_flags == CS_EOF)
				goto ret;
		}

	/*
	 * If we didn't move, we must be at EOF.
	 *
	 * !!!
	 * That's okay for motion commands, however.
	 */
ret:	if (!ISMOTION(vp) &&
	    cs.cs_lno == vp->m_start.lno && cs.cs_cno == vp->m_start.cno) {
		v_eof(sp, &vp->m_start);
		return (1);
	}

	/* Adjust the end of the range for motion commands. */
	vp->m_stop.lno = cs.cs_lno;
	vp->m_stop.cno = cs.cs_cno;
	if (ISMOTION(vp) && cs.cs_flags == 0)
		--vp->m_stop.cno;

	/*
	 * Non-motion commands move to the end of the range.  Delete
	 * and yank stay at the start, ignore others.
	 */
	vp->m_final = ISMOTION(vp) ? vp->m_start : vp->m_stop;
	return (0);
}

/*
 * v_wordE -- [count]E
 *	Move forward to the end of the bigword.
 *
 * PUBLIC: int v_wordE __P((SCR *, VICMD *));
 */
int
v_wordE(SCR *sp, VICMD *vp)
{
	return (eword(sp, vp, BIGWORD));
}

/*
 * v_worde -- [count]e
 *	Move forward to the end of the word.
 *
 * PUBLIC: int v_worde __P((SCR *, VICMD *));
 */
int
v_worde(SCR *sp, VICMD *vp)
{
	return (eword(sp, vp, LITTLEWORD));
}

/*
 * eword --
 *	Move forward to the end of the word.
 */
static int
eword(SCR *sp, VICMD *vp, enum which type)
{
	enum { INWORD, NOTWORD } state;
	VCS cs;
	u_long cnt;
	int nmw, omw;

	cnt = F_ISSET(vp, VC_C1SET) ? vp->count : 1;
	cs.cs_lno = vp->m_start.lno;
	cs.cs_cno = vp->m_start.cno;
	if (cs_init(sp, &cs))
		return (1);

	/*
	 * !!!
	 * If in whitespace, or the next character is whitespace, move past
	 * it.  (This doesn't count as a word move.)  Stay at the character
	 * past the current one, it sets word "state" for the 'e' command.
	 */
	if (cs.cs_flags == 0 && !ISBLANK2(cs.cs_ch)) {
		if (cs_next(sp, &cs))
			return (1);
		if (cs.cs_flags == 0 && !ISBLANK2(cs.cs_ch))
			goto start;
	}
	if (cs_fblank(sp, &cs))
		return (1);

	/*
	 * Cyclically move to the next word -- this involves skipping
	 * over word characters and then any trailing non-word characters.
	 * Note, for the 'e' command, the definition of a word keeps
	 * switching.
	 */
start:	if (type == BIGWORD)
		while (cnt--) {
			nmw = ISMULTIWIDTH(sp, cs.cs_ch);
			for (;;) {
				omw = nmw;
				if (cs_next(sp, &cs))
					return (1);
				if (cs.cs_flags == CS_EOF)
					goto ret;
				if (cs.cs_flags != 0 || ISBLANK2(cs.cs_ch) ||
				    (nmw = ISMULTIWIDTH(sp, cs.cs_ch)) != omw)
					break;
			}
			/*
			 * When we reach the start of the word after the last
			 * word, we're done.  If we changed state, back up one
			 * to the end of the previous word.
			 */
			if (cnt == 0) {
				if (cs.cs_flags == 0 && cs_prev(sp, &cs))
					return (1);
				break;
			}

			/* Eat whitespace characters. */
			if (nmw == omw && cs_fblank(sp, &cs))
				return (1);
			if (cs.cs_flags == CS_EOF)
				goto ret;
		}
	else
		while (cnt--) {
			state = cs.cs_flags == 0 &&
			    inword(cs.cs_ch) ? INWORD : NOTWORD;
			nmw = ISMULTIWIDTH(sp, cs.cs_ch);
			for (;;) {
				omw = nmw;
				if (cs_next(sp, &cs))
					return (1);
				if (cs.cs_flags == CS_EOF)
					goto ret;
				if (cs.cs_flags != 0 || ISBLANK2(cs.cs_ch) ||
				    (nmw = ISMULTIWIDTH(sp, cs.cs_ch)) != omw)
					break;
				if (state == INWORD) {
					if (!inword(cs.cs_ch))
						break;
				} else
					if (inword(cs.cs_ch))
						break;
			}
			/* See comment above. */
			if (cnt == 0) {
				if (cs.cs_flags == 0 && cs_prev(sp, &cs))
					return (1);
				break;
			}

			/* Eat whitespace characters. */
			if (cs.cs_flags != 0 || ISBLANK2(cs.cs_ch))
				if (cs_fblank(sp, &cs))
					return (1);
			if (cs.cs_flags == CS_EOF)
				goto ret;
		}

	/*
	 * If we didn't move, we must be at EOF.
	 *
	 * !!!
	 * That's okay for motion commands, however.
	 */
ret:	if (!ISMOTION(vp) &&
	    cs.cs_lno == vp->m_start.lno && cs.cs_cno == vp->m_start.cno) {
		v_eof(sp, &vp->m_start);
		return (1);
	}

	/* Set the end of the range for motion commands. */
	vp->m_stop.lno = cs.cs_lno;
	vp->m_stop.cno = cs.cs_cno;

	/*
	 * Non-motion commands move to the end of the range.
	 * Delete and yank stay at the start, ignore others.
	 */
	vp->m_final = ISMOTION(vp) ? vp->m_start : vp->m_stop;
	return (0);
}

/*
 * v_WordB -- [count]B
 *	Move backward a bigword at a time.
 *
 * PUBLIC: int v_wordB __P((SCR *, VICMD *));
 */
int
v_wordB(SCR *sp, VICMD *vp)
{
	return (bword(sp, vp, BIGWORD));
}

/*
 * v_wordb -- [count]b
 *	Move backward a word at a time.
 *
 * PUBLIC: int v_wordb __P((SCR *, VICMD *));
 */
int
v_wordb(SCR *sp, VICMD *vp)
{
	return (bword(sp, vp, LITTLEWORD));
}

/*
 * bword --
 *	Move backward by words.
 */
static int
bword(SCR *sp, VICMD *vp, enum which type)
{
	enum { INWORD, NOTWORD } state;
	VCS cs;
	u_long cnt;
	int nmw, omw;

	cnt = F_ISSET(vp, VC_C1SET) ? vp->count : 1;
	cs.cs_lno = vp->m_start.lno;
	cs.cs_cno = vp->m_start.cno;
	if (cs_init(sp, &cs))
		return (1);

	/*
	 * !!!
	 * If in whitespace, or the previous character is whitespace, move
	 * past it.  (This doesn't count as a word move.)  Stay at the
	 * character before the current one, it sets word "state" for the
	 * 'b' command.
	 */
	if (cs.cs_flags == 0 && !ISBLANK2(cs.cs_ch)) {
		if (cs_prev(sp, &cs))
			return (1);
		if (cs.cs_flags == 0 && !ISBLANK2(cs.cs_ch))
			goto start;
	}
	if (cs_bblank(sp, &cs))
		return (1);

	/*
	 * Cyclically move to the beginning of the previous word -- this
	 * involves skipping over word characters and then any trailing
	 * non-word characters.  Note, for the 'b' command, the definition
	 * of a word keeps switching.
	 */
start:	if (type == BIGWORD)
		while (cnt--) {
			nmw = ISMULTIWIDTH(sp, cs.cs_ch);
			for (;;) {
				omw = nmw;
				if (cs_prev(sp, &cs))
					return (1);
				if (cs.cs_flags == CS_SOF)
					goto ret;
				if (cs.cs_flags != 0 || ISBLANK2(cs.cs_ch) ||
				    (nmw = ISMULTIWIDTH(sp, cs.cs_ch)) != omw)
					break;
			}
			/*
			 * When we reach the end of the word before the last
			 * word, we're done.  If we changed state, move forward
			 * one to the end of the next word.
			 */
			if (cnt == 0) {
				if (cs.cs_flags == 0 && cs_next(sp, &cs))
					return (1);
				break;
			}

			/* Eat whitespace characters. */
			if (nmw == omw && cs_bblank(sp, &cs))
				return (1);
			if (cs.cs_flags == CS_SOF)
				goto ret;
		}
	else
		while (cnt--) {
			state = cs.cs_flags == 0 &&
			    inword(cs.cs_ch) ? INWORD : NOTWORD;
			nmw = ISMULTIWIDTH(sp, cs.cs_ch);
			for (;;) {
				omw = nmw;
				if (cs_prev(sp, &cs))
					return (1);
				if (cs.cs_flags == CS_SOF)
					goto ret;
				if (cs.cs_flags != 0 || ISBLANK2(cs.cs_ch) ||
				    (nmw = ISMULTIWIDTH(sp, cs.cs_ch)) != omw)
					break;
				if (state == INWORD) {
					if (!inword(cs.cs_ch))
						break;
				} else
					if (inword(cs.cs_ch))
						break;
			}
			/* See comment above. */
			if (cnt == 0) {
				if (cs.cs_flags == 0 && cs_next(sp, &cs))
					return (1);
				break;
			}

			/* Eat whitespace characters. */
			if (cs.cs_flags != 0 || ISBLANK2(cs.cs_ch))
				if (cs_bblank(sp, &cs))
					return (1);
			if (cs.cs_flags == CS_SOF)
				goto ret;
		}

	/* If we didn't move, we must be at SOF. */
ret:	if (cs.cs_lno == vp->m_start.lno && cs.cs_cno == vp->m_start.cno) {
		v_sof(sp, &vp->m_start);
		return (1);
	}

	/* Set the end of the range for motion commands. */
	vp->m_stop.lno = cs.cs_lno;
	vp->m_stop.cno = cs.cs_cno;

	/*
	 * All commands move to the end of the range.  Motion commands
	 * adjust the starting point to the character before the current
	 * one.
	 *
	 * !!!
	 * The historic vi didn't get this right -- the `yb' command yanked
	 * the right stuff and even updated the cursor value, but the cursor
	 * was not actually updated on the screen.
	 */
	vp->m_final = vp->m_stop;
	if (ISMOTION(vp))
		--vp->m_start.cno;
	return (0);
}