summaryrefslogtreecommitdiffstats
path: root/generic/tclScan.c
blob: 229f3faa13615c578789ffd47061266706b2342c (plain)
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
1001
1002
1003
1004
1005
1006
1007
1008
1009
1010
1011
1012
1013
1014
1015
1016
1017
1018
1019
1020
1021
1022
1023
1024
1025
1026
1027
1028
1029
1030
1031
1032
1033
1034
1035
1036
1037
1038
1039
1040
1041
1042
1043
1044
1045
1046
1047
1048
1049
1050
1051
/*
 * tclScan.c --
 *
 *	This file contains the implementation of the "scan" command.
 *
 * Copyright (c) 1998 by Scriptics Corporation.
 *
 * See the file "license.terms" for information on usage and redistribution of
 * this file, and for a DISCLAIMER OF ALL WARRANTIES.
 */

#include "tclInt.h"

/*
 * Flag values used by Tcl_ScanObjCmd.
 */

#define SCAN_NOSKIP	0x1		/* Don't skip blanks. */
#define SCAN_SUPPRESS	0x2		/* Suppress assignment. */
#define SCAN_UNSIGNED	0x4		/* Read an unsigned value. */
#define SCAN_WIDTH	0x8		/* A width value was supplied. */

#define SCAN_LONGER	0x400		/* Asked for a wide value. */
#define SCAN_BIG	0x800		/* Asked for a bignum value. */

/*
 * The following structure contains the information associated with a
 * character set.
 */

typedef struct CharSet {
    int exclude;		/* 1 if this is an exclusion set. */
    int nchars;
    Tcl_UniChar *chars;
    int nranges;
    struct Range {
	Tcl_UniChar start;
	Tcl_UniChar end;
    } *ranges;
} CharSet;

/*
 * Declarations for functions used only in this file.
 */

static char *		BuildCharSet(CharSet *cset, char *format);
static int		CharInSet(CharSet *cset, int ch);
static void		ReleaseCharSet(CharSet *cset);
static int		ValidateFormat(Tcl_Interp *interp, char *format,
			    int numVars, int *totalVars);

/*
 *----------------------------------------------------------------------
 *
 * BuildCharSet --
 *
 *	This function examines a character set format specification and builds
 *	a CharSet containing the individual characters and character ranges
 *	specified.
 *
 * Results:
 *	Returns the next format position.
 *
 * Side effects:
 *	Initializes the charset.
 *
 *----------------------------------------------------------------------
 */

static char *
BuildCharSet(
    CharSet *cset,
    char *format)		/* Points to first char of set. */
{
    Tcl_UniChar ch, start;
    int offset, nranges;
    char *end;

    memset(cset, 0, sizeof(CharSet));

    offset = Tcl_UtfToUniChar(format, &ch);
    if (ch == '^') {
	cset->exclude = 1;
	format += offset;
	offset = Tcl_UtfToUniChar(format, &ch);
    }
    end = format + offset;

    /*
     * Find the close bracket so we can overallocate the set.
     */

    if (ch == ']') {
	end += Tcl_UtfToUniChar(end, &ch);
    }
    nranges = 0;
    while (ch != ']') {
	if (ch == '-') {
	    nranges++;
	}
	end += Tcl_UtfToUniChar(end, &ch);
    }

    cset->chars = (Tcl_UniChar *)
	    ckalloc(sizeof(Tcl_UniChar) * (end - format - 1));
    if (nranges > 0) {
	cset->ranges = (struct Range *) ckalloc(sizeof(struct Range)*nranges);
    } else {
	cset->ranges = NULL;
    }

    /*
     * Now build the character set.
     */

    cset->nchars = cset->nranges = 0;
    format += Tcl_UtfToUniChar(format, &ch);
    start = ch;
    if (ch == ']' || ch == '-') {
	cset->chars[cset->nchars++] = ch;
	format += Tcl_UtfToUniChar(format, &ch);
    }
    while (ch != ']') {
	if (*format == '-') {
	    /*
	     * This may be the first character of a range, so don't add it
	     * yet.
	     */

	    start = ch;
	} else if (ch == '-') {
	    /*
	     * Check to see if this is the last character in the set, in which
	     * case it is not a range and we should add the previous character
	     * as well as the dash.
	     */

	    if (*format == ']') {
		cset->chars[cset->nchars++] = start;
		cset->chars[cset->nchars++] = ch;
	    } else {
		format += Tcl_UtfToUniChar(format, &ch);

		/*
		 * Check to see if the range is in reverse order.
		 */

		if (start < ch) {
		    cset->ranges[cset->nranges].start = start;
		    cset->ranges[cset->nranges].end = ch;
		} else {
		    cset->ranges[cset->nranges].start = ch;
		    cset->ranges[cset->nranges].end = start;
		}
		cset->nranges++;
	    }
	} else {
	    cset->chars[cset->nchars++] = ch;
	}
	format += Tcl_UtfToUniChar(format, &ch);
    }
    return format;
}

/*
 *----------------------------------------------------------------------
 *
 * CharInSet --
 *
 *	Check to see if a character matches the given set.
 *
 * Results:
 *	Returns non-zero if the character matches the given set.
 *
 * Side effects:
 *	None.
 *
 *----------------------------------------------------------------------
 */

static int
CharInSet(
    CharSet *cset,
    int c)			/* Character to test, passed as int because of
				 * non-ANSI prototypes. */
{
    Tcl_UniChar ch = (Tcl_UniChar) c;
    int i, match = 0;

    for (i = 0; i < cset->nchars; i++) {
	if (cset->chars[i] == ch) {
	    match = 1;
	    break;
	}
    }
    if (!match) {
	for (i = 0; i < cset->nranges; i++) {
	    if ((cset->ranges[i].start <= ch) && (ch <= cset->ranges[i].end)) {
		match = 1;
		break;
	    }
	}
    }
    return (cset->exclude ? !match : match);
}

/*
 *----------------------------------------------------------------------
 *
 * ReleaseCharSet --
 *
 *	Free the storage associated with a character set.
 *
 * Results:
 *	None.
 *
 * Side effects:
 *	None.
 *
 *----------------------------------------------------------------------
 */

static void
ReleaseCharSet(
    CharSet *cset)
{
    ckfree((char *)cset->chars);
    if (cset->ranges) {
	ckfree((char *)cset->ranges);
    }
}

/*
 *----------------------------------------------------------------------
 *
 * ValidateFormat --
 *
 *	Parse the format string and verify that it is properly formed and that
 *	there are exactly enough variables on the command line.
 *
 * Results:
 *	A standard Tcl result.
 *
 * Side effects:
 *	May place an error in the interpreter result.
 *
 *----------------------------------------------------------------------
 */

static int
ValidateFormat(
    Tcl_Interp *interp,		/* Current interpreter. */
    char *format,		/* The format string. */
    int numVars,		/* The number of variables passed to the scan
				 * command. */
    int *totalSubs)		/* The number of variables that will be
				 * required. */
{
    int gotXpg, gotSequential, value, i, flags;
    char *end;
    Tcl_UniChar ch;
    int objIndex, xpgSize, nspace = numVars;
    int *nassign = (int *) TclStackAlloc(interp, nspace * sizeof(int));
    char buf[TCL_UTF_MAX+1];

    /*
     * Initialize an array that records the number of times a variable is
     * assigned to by the format string. We use this to detect if a variable
     * is multiply assigned or left unassigned.
     */

    for (i = 0; i < nspace; i++) {
	nassign[i] = 0;
    }

    xpgSize = objIndex = gotXpg = gotSequential = 0;

    while (*format != '\0') {
	format += Tcl_UtfToUniChar(format, &ch);

	flags = 0;

	if (ch != '%') {
	    continue;
	}
	format += Tcl_UtfToUniChar(format, &ch);
	if (ch == '%') {
	    continue;
	}
	if (ch == '*') {
	    flags |= SCAN_SUPPRESS;
	    format += Tcl_UtfToUniChar(format, &ch);
	    goto xpgCheckDone;
	}

	if ((ch < 0x80) && isdigit(UCHAR(ch))) {	/* INTL: "C" locale. */
	    /*
	     * Check for an XPG3-style %n$ specification. Note: there must
	     * not be a mixture of XPG3 specs and non-XPG3 specs in the same
	     * format string.
	     */

	    value = strtoul(format-1, &end, 10);	/* INTL: "C" locale. */
	    if (*end != '$') {
		goto notXpg;
	    }
	    format = end+1;
	    format += Tcl_UtfToUniChar(format, &ch);
	    gotXpg = 1;
	    if (gotSequential) {
		goto mixedXPG;
	    }
	    objIndex = value - 1;
	    if ((objIndex < 0) || (numVars && (objIndex >= numVars))) {
		goto badIndex;
	    } else if (numVars == 0) {
		/*
		 * In the case where no vars are specified, the user can
		 * specify %9999$ legally, so we have to consider special
		 * rules for growing the assign array. 'value' is guaranteed
		 * to be > 0.
		 */
		xpgSize = (xpgSize > value) ? xpgSize : value;
	    }
	    goto xpgCheckDone;
	}

    notXpg:
	gotSequential = 1;
	if (gotXpg) {
	mixedXPG:
	    Tcl_SetResult(interp,
		    "cannot mix \"%\" and \"%n$\" conversion specifiers",
		    TCL_STATIC);
	    goto error;
	}

    xpgCheckDone:
	/*
	 * Parse any width specifier.
	 */

	if ((ch < 0x80) && isdigit(UCHAR(ch))) {	/* INTL: "C" locale. */
	    value = strtoul(format-1, &format, 10);	/* INTL: "C" locale. */
	    flags |= SCAN_WIDTH;
	    format += Tcl_UtfToUniChar(format, &ch);
	}

	/*
	 * Handle any size specifier.
	 */

	switch (ch) {
	case 'l':
	    if (*format == 'l') {
		flags |= SCAN_BIG;
		format += 1;
		format += Tcl_UtfToUniChar(format, &ch);
		break;
	    }
	case 'L':
	    flags |= SCAN_LONGER;
	case 'h':
	    format += Tcl_UtfToUniChar(format, &ch);
	}

	if (!(flags & SCAN_SUPPRESS) && numVars && (objIndex >= numVars)) {
	    goto badIndex;
	}

	/*
	 * Handle the various field types.
	 */

	switch (ch) {
	case 'c':
	    if (flags & SCAN_WIDTH) {
		Tcl_SetResult(interp,
			"field width may not be specified in %c conversion",
			TCL_STATIC);
		goto error;
	    }
	    /*
	     * Fall through!
	     */
	case 'n':
	case 's':
	    if (flags & (SCAN_LONGER|SCAN_BIG)) {
	    invalidFieldSize:
		buf[Tcl_UniCharToUtf(ch, buf)] = '\0';
		Tcl_AppendResult(interp,
			"field size modifier may not be specified in %", buf,
			" conversion", NULL);
		goto error;
	    }
	    /*
	     * Fall through!
	     */
	case 'd':
	case 'e':
	case 'E':
	case 'f':
	case 'g':
	case 'G':
	case 'i':
	case 'o':
	case 'x':
	case 'X':
	    break;
	case 'u':
	    if (flags & SCAN_BIG) {
		Tcl_SetResult(interp,
			"unsigned bignum scans are invalid", TCL_STATIC);
		goto error;
	    }
	    break;
	    /*
	     * Bracket terms need special checking
	     */
	case '[':
	    if (flags & (SCAN_LONGER|SCAN_BIG)) {
		goto invalidFieldSize;
	    }
	    if (*format == '\0') {
		goto badSet;
	    }
	    format += Tcl_UtfToUniChar(format, &ch);
	    if (ch == '^') {
		if (*format == '\0') {
		    goto badSet;
		}
		format += Tcl_UtfToUniChar(format, &ch);
	    }
	    if (ch == ']') {
		if (*format == '\0') {
		    goto badSet;
		}
		format += Tcl_UtfToUniChar(format, &ch);
	    }
	    while (ch != ']') {
		if (*format == '\0') {
		    goto badSet;
		}
		format += Tcl_UtfToUniChar(format, &ch);
	    }
	    break;
	badSet:
	    Tcl_SetResult(interp, "unmatched [ in format string",
		    TCL_STATIC);
	    goto error;
	default:
	    {
		char buf[TCL_UTF_MAX+1];

		buf[Tcl_UniCharToUtf(ch, buf)] = '\0';
		Tcl_AppendResult(interp, "bad scan conversion character \"",
			buf, "\"", NULL);
		goto error;
	    }
	}
	if (!(flags & SCAN_SUPPRESS)) {
	    if (objIndex >= nspace) {
		/*
		 * Expand the nassign buffer. If we are using XPG specifiers,
		 * make sure that we grow to a large enough size. xpgSize is
		 * guaranteed to be at least one larger than objIndex.
		 */

		value = nspace;
		if (xpgSize) {
		    nspace = xpgSize;
		} else {
		    nspace += 16;	/* formerly STATIC_LIST_SIZE */
		}
		nassign = (int *) TclStackRealloc(interp, nassign,
			nspace * sizeof(int));
		for (i = value; i < nspace; i++) {
		    nassign[i] = 0;
		}
	    }
	    nassign[objIndex]++;
	    objIndex++;
	}
    }

    /*
     * Verify that all of the variable were assigned exactly once.
     */

    if (numVars == 0) {
	if (xpgSize) {
	    numVars = xpgSize;
	} else {
	    numVars = objIndex;
	}
    }
    if (totalSubs) {
	*totalSubs = numVars;
    }
    for (i = 0; i < numVars; i++) {
	if (nassign[i] > 1) {
	    Tcl_SetResult(interp,
		    "variable is assigned by multiple \"%n$\" conversion specifiers",
		    TCL_STATIC);
	    goto error;
	} else if (!xpgSize && (nassign[i] == 0)) {
	    /*
	     * If the space is empty, and xpgSize is 0 (means XPG wasn't used,
	     * and/or numVars != 0), then too many vars were given
	     */

	    Tcl_SetResult(interp,
		    "variable is not assigned by any conversion specifiers",
		    TCL_STATIC);
	    goto error;
	}
    }

    TclStackFree(interp, nassign);
    return TCL_OK;

  badIndex:
    if (gotXpg) {
	Tcl_SetResult(interp, "\"%n$\" argument index out of range",
		TCL_STATIC);
    } else {
	Tcl_SetResult(interp,
		"different numbers of variable names and field specifiers",
		TCL_STATIC);
    }

  error:
    TclStackFree(interp, nassign);
    return TCL_ERROR;
}

/*
 *----------------------------------------------------------------------
 *
 * Tcl_ScanObjCmd --
 *
 *	This function is invoked to process the "scan" Tcl command. See the
 *	user documentation for details on what it does.
 *
 * Results:
 *	A standard Tcl result.
 *
 * Side effects:
 *	See the user documentation.
 *
 *----------------------------------------------------------------------
 */

	/* ARGSUSED */
int
Tcl_ScanObjCmd(
    ClientData dummy,    	/* Not used. */
    Tcl_Interp *interp,		/* Current interpreter. */
    int objc,			/* Number of arguments. */
    Tcl_Obj *CONST objv[])	/* Argument objects. */
{
    char *format;
    int numVars, nconversions, totalVars = -1;
    int objIndex, offset, i, result, code;
    long value;
    CONST char *string, *end, *baseString;
    char op = 0;
    int width, underflow = 0;
    Tcl_WideInt wideValue;
    Tcl_UniChar ch, sch;
    Tcl_Obj **objs = NULL, *objPtr = NULL;
    int flags;
    char buf[513];		/* Temporary buffer to hold scanned number
				 * strings before they are passed to
				 * strtoul. */

    if (objc < 3) {
	Tcl_WrongNumArgs(interp, 1, objv,
		"string format ?varName varName ...?");
	return TCL_ERROR;
    }

    format = Tcl_GetStringFromObj(objv[2], NULL);
    numVars = objc-3;

    /*
     * Check for errors in the format string.
     */

    if (ValidateFormat(interp, format, numVars, &totalVars) == TCL_ERROR) {
	return TCL_ERROR;
    }

    /*
     * Allocate space for the result objects.
     */

    if (totalVars > 0) {
	objs = (Tcl_Obj **) ckalloc(sizeof(Tcl_Obj*) * totalVars);
	for (i = 0; i < totalVars; i++) {
	    objs[i] = NULL;
	}
    }

    string = Tcl_GetStringFromObj(objv[1], NULL);
    baseString = string;

    /*
     * Iterate over the format string filling in the result objects until we
     * reach the end of input, the end of the format string, or there is a
     * mismatch.
     */

    objIndex = 0;
    nconversions = 0;
    while (*format != '\0') {
	int parseFlag = TCL_PARSE_NO_WHITESPACE;
	format += Tcl_UtfToUniChar(format, &ch);

	flags = 0;

	/*
	 * If we see whitespace in the format, skip whitespace in the string.
	 */

	if (Tcl_UniCharIsSpace(ch)) {
	    offset = Tcl_UtfToUniChar(string, &sch);
	    while (Tcl_UniCharIsSpace(sch)) {
		if (*string == '\0') {
		    goto done;
		}
		string += offset;
		offset = Tcl_UtfToUniChar(string, &sch);
	    }
	    continue;
	}

	if (ch != '%') {
	literal:
	    if (*string == '\0') {
		underflow = 1;
		goto done;
	    }
	    string += Tcl_UtfToUniChar(string, &sch);
	    if (ch != sch) {
		goto done;
	    }
	    continue;
	}

	format += Tcl_UtfToUniChar(format, &ch);
	if (ch == '%') {
	    goto literal;
	}

	/*
	 * Check for assignment suppression ('*') or an XPG3-style assignment
	 * ('%n$').
	 */

	if (ch == '*') {
	    flags |= SCAN_SUPPRESS;
	    format += Tcl_UtfToUniChar(format, &ch);
	} else if ((ch < 0x80) && isdigit(UCHAR(ch))) {	/* INTL: "C" locale. */
	    char *formatEnd;
	    value = strtoul(format-1, &formatEnd, 10);/* INTL: "C" locale. */
	    if (*formatEnd == '$') {
		format = formatEnd+1;
		format += Tcl_UtfToUniChar(format, &ch);
		objIndex = (int) value - 1;
	    }
	}

	/*
	 * Parse any width specifier.
	 */

	if ((ch < 0x80) && isdigit(UCHAR(ch))) {	/* INTL: "C" locale. */
	    width = (int) strtoul(format-1, &format, 10);/* INTL: "C" locale. */
	    format += Tcl_UtfToUniChar(format, &ch);
	} else {
	    width = 0;
	}

	/*
	 * Handle any size specifier.
	 */

	switch (ch) {
	case 'l':
	    if (*format == 'l') {
		flags |= SCAN_BIG;
		format += 1;
		format += Tcl_UtfToUniChar(format, &ch);
		break;
	    }
	case 'L':
	    flags |= SCAN_LONGER;
	    /*
	     * Fall through so we skip to the next character.
	     */
	case 'h':
	    format += Tcl_UtfToUniChar(format, &ch);
	}

	/*
	 * Handle the various field types.
	 */

	switch (ch) {
	case 'n':
	    if (!(flags & SCAN_SUPPRESS)) {
		objPtr = Tcl_NewIntObj(string - baseString);
		Tcl_IncrRefCount(objPtr);
		objs[objIndex++] = objPtr;
	    }
	    nconversions++;
	    continue;

	case 'd':
	    op = 'i';
	    parseFlag |= TCL_PARSE_DECIMAL_ONLY;
	    break;
	case 'i':
	    op = 'i';
	    parseFlag |= TCL_PARSE_SCAN_PREFIXES;
	    break;
	case 'o':
	    op = 'i';
	    parseFlag |= TCL_PARSE_OCTAL_ONLY | TCL_PARSE_SCAN_PREFIXES;
	    break;
	case 'x':
	case 'X':
	    op = 'i';
	    parseFlag |= TCL_PARSE_HEXADECIMAL_ONLY;
	    break;
	case 'u':
	    op = 'i';
	    parseFlag |= TCL_PARSE_DECIMAL_ONLY;
	    flags |= SCAN_UNSIGNED;
	    break;

	case 'f':
	case 'e':
	case 'E':
	case 'g':
	case 'G':
	    op = 'f';
	    break;

	case 's':
	    op = 's';
	    break;

	case 'c':
	    op = 'c';
	    flags |= SCAN_NOSKIP;
	    break;
	case '[':
	    op = '[';
	    flags |= SCAN_NOSKIP;
	    break;
	}

	/*
	 * At this point, we will need additional characters from the string
	 * to proceed.
	 */

	if (*string == '\0') {
	    underflow = 1;
	    goto done;
	}

	/*
	 * Skip any leading whitespace at the beginning of a field unless the
	 * format suppresses this behavior.
	 */

	if (!(flags & SCAN_NOSKIP)) {
	    while (*string != '\0') {
		offset = Tcl_UtfToUniChar(string, &sch);
		if (!Tcl_UniCharIsSpace(sch)) {
		    break;
		}
		string += offset;
	    }
	    if (*string == '\0') {
		underflow = 1;
		goto done;
	    }
	}

	/*
	 * Perform the requested scanning operation.
	 */

	switch (op) {
	case 's':
	    /*
	     * Scan a string up to width characters or whitespace.
	     */

	    if (width == 0) {
		width = ~0;
	    }
	    end = string;
	    while (*end != '\0') {
		offset = Tcl_UtfToUniChar(end, &sch);
		if (Tcl_UniCharIsSpace(sch)) {
		    break;
		}
		end += offset;
		if (--width == 0) {
		    break;
		}
	    }
	    if (!(flags & SCAN_SUPPRESS)) {
		objPtr = Tcl_NewStringObj(string, end-string);
		Tcl_IncrRefCount(objPtr);
		objs[objIndex++] = objPtr;
	    }
	    string = end;
	    break;

	case '[': {
	    CharSet cset;

	    if (width == 0) {
		width = ~0;
	    }
	    end = string;

	    format = BuildCharSet(&cset, format);
	    while (*end != '\0') {
		offset = Tcl_UtfToUniChar(end, &sch);
		if (!CharInSet(&cset, (int)sch)) {
		    break;
		}
		end += offset;
		if (--width == 0) {
		    break;
		}
	    }
	    ReleaseCharSet(&cset);

	    if (string == end) {
		/*
		 * Nothing matched the range, stop processing.
		 */
		goto done;
	    }
	    if (!(flags & SCAN_SUPPRESS)) {
		objPtr = Tcl_NewStringObj(string, end-string);
		Tcl_IncrRefCount(objPtr);
		objs[objIndex++] = objPtr;
	    }
	    string = end;

	    break;
	}
	case 'c':
	    /*
	     * Scan a single Unicode character.
	     */

	    string += Tcl_UtfToUniChar(string, &sch);
	    if (!(flags & SCAN_SUPPRESS)) {
		objPtr = Tcl_NewIntObj((int)sch);
		Tcl_IncrRefCount(objPtr);
		objs[objIndex++] = objPtr;
	    }
	    break;

	case 'i':
	    /*
	     * Scan an unsigned or signed integer.
	     */
	    objPtr = Tcl_NewLongObj(0);
	    Tcl_IncrRefCount(objPtr);
	    if (width == 0) {
		width = ~0;
	    }
	    if (TCL_OK != TclParseNumber(NULL, objPtr, NULL, string, width,
		    &end, TCL_PARSE_INTEGER_ONLY | parseFlag)) {
		Tcl_DecrRefCount(objPtr);
		if (width < 0) {
		    if (*end == '\0') {
			underflow = 1;
		    }
		} else {
		    if (end == string + width) {
			underflow = 1;
		    }
		}
		goto done;
	    }
	    string = end;
	    if (flags & SCAN_SUPPRESS) {
		Tcl_DecrRefCount(objPtr);
		break;
	    }
	    if (flags & SCAN_LONGER) {
		if (Tcl_GetWideIntFromObj(NULL, objPtr, &wideValue) != TCL_OK) {
		    wideValue = ~(Tcl_WideUInt)0 >> 1;	/* WIDE_MAX */
		    if (TclGetString(objPtr)[0] == '-') {
			wideValue++;	/* WIDE_MAX + 1 = WIDE_MIN */
		    }
		}
		if ((flags & SCAN_UNSIGNED) && (wideValue < 0)) {
		    sprintf(buf, "%" TCL_LL_MODIFIER "u",
			    (Tcl_WideUInt)wideValue);
		    Tcl_SetStringObj(objPtr, buf, -1);
		} else {
		    Tcl_SetWideIntObj(objPtr, wideValue);
		}
	    } else if (!(flags & SCAN_BIG)) {
		if (TclGetLongFromObj(NULL, objPtr, &value) != TCL_OK) {
		    if (TclGetString(objPtr)[0] == '-') {
			value = LONG_MIN;
		    } else {
			value = LONG_MAX;
		    }
		}
		if ((flags & SCAN_UNSIGNED) && (value < 0)) {
		    sprintf(buf, "%lu", value);	/* INTL: ISO digit */
		    Tcl_SetStringObj(objPtr, buf, -1);
		} else {
		    Tcl_SetLongObj(objPtr, value);
		}
	    }
	    objs[objIndex++] = objPtr;
	    break;

	case 'f':
	    /*
	     * Scan a floating point number
	     */

	    objPtr = Tcl_NewDoubleObj(0.0);
	    Tcl_IncrRefCount(objPtr);
	    if (width == 0) {
		width = ~0;
	    }
	    if (TCL_OK != TclParseNumber(NULL, objPtr, NULL, string, width,
		    &end, TCL_PARSE_DECIMAL_ONLY | TCL_PARSE_NO_WHITESPACE)) {
		Tcl_DecrRefCount(objPtr);
		if (width < 0) {
		    if (*end == '\0') {
			underflow = 1;
		    }
		} else {
		    if (end == string + width) {
			underflow = 1;
		    }
		}
		goto done;
	    } else if (flags & SCAN_SUPPRESS) {
		Tcl_DecrRefCount(objPtr);
		string = end;
	    } else {
		double dvalue;
		if (Tcl_GetDoubleFromObj(NULL, objPtr, &dvalue) != TCL_OK) {
#ifdef ACCEPT_NAN
		    if (objPtr->typePtr == &tclDoubleType) {
			dvalue = objPtr->internalRep.doubleValue;
		    } else
#endif
		    {
			Tcl_DecrRefCount(objPtr);
			goto done;
		    }
		}
		Tcl_SetDoubleObj(objPtr, dvalue);
		objs[objIndex++] = objPtr;
		string = end;
	    }
	}
	nconversions++;
    }

  done:
    result = 0;
    code = TCL_OK;

    if (numVars) {
	/*
	 * In this case, variables were specified (classic scan).
	 */

	for (i = 0; i < totalVars; i++) {
	    if (objs[i] == NULL) {
		continue;
	    }
	    result++;
	    if (Tcl_ObjSetVar2(interp, objv[i+3], NULL, objs[i], 0) == NULL) {
		Tcl_AppendResult(interp, "couldn't set variable \"",
			TclGetString(objv[i+3]), "\"", NULL);
		code = TCL_ERROR;
	    }
	    Tcl_DecrRefCount(objs[i]);
	}
    } else {
	/*
	 * Here no vars were specified, we want a list returned (inline scan)
	 */

	objPtr = Tcl_NewObj();
	for (i = 0; i < totalVars; i++) {
	    if (objs[i] != NULL) {
		Tcl_ListObjAppendElement(NULL, objPtr, objs[i]);
		Tcl_DecrRefCount(objs[i]);
	    } else {
		/*
		 * More %-specifiers than matching chars, so we just spit out
		 * empty strings for these.
		 */

		Tcl_ListObjAppendElement(NULL, objPtr, Tcl_NewObj());
	    }
	}
    }
    if (objs != NULL) {
	ckfree((char*) objs);
    }
    if (code == TCL_OK) {
	if (underflow && (nconversions == 0)) {
	    if (numVars) {
		objPtr = Tcl_NewIntObj(-1);
	    } else {
		if (objPtr) {
		    Tcl_SetListObj(objPtr, 0, NULL);
		} else {
		    objPtr = Tcl_NewObj();
		}
	    }
	} else if (numVars) {
	    objPtr = Tcl_NewIntObj(result);
	}
	Tcl_SetObjResult(interp, objPtr);
    }
    return code;
}

/*
 * Local Variables:
 * mode: c
 * c-basic-offset: 4
 * fill-column: 78
 * End:
 */
>, ahi, b, blo, bhi) return # no close pair, but an identical pair -- synch up on that best_i, best_j, best_ratio = eqi, eqj, 1.0 else: # there's a close pair, so forget the identical pair (if any) eqi = None # a[best_i] very similar to b[best_j]; eqi is None iff they're not # identical # pump out diffs from before the synch point yield from self._fancy_helper(a, alo, best_i, b, blo, best_j) # do intraline marking on the synch pair aelt, belt = a[best_i], b[best_j] if eqi is None: # pump out a '-', '?', '+', '?' quad for the synched lines atags = btags = "" cruncher.set_seqs(aelt, belt) for tag, ai1, ai2, bj1, bj2 in cruncher.get_opcodes(): la, lb = ai2 - ai1, bj2 - bj1 if tag == 'replace': atags += '^' * la btags += '^' * lb elif tag == 'delete': atags += '-' * la elif tag == 'insert': btags += '+' * lb elif tag == 'equal': atags += ' ' * la btags += ' ' * lb else: raise ValueError('unknown tag %r' % (tag,)) yield from self._qformat(aelt, belt, atags, btags) else: # the synch pair is identical yield ' ' + aelt # pump out diffs from after the synch point yield from self._fancy_helper(a, best_i+1, ahi, b, best_j+1, bhi) def _fancy_helper(self, a, alo, ahi, b, blo, bhi): g = [] if alo < ahi: if blo < bhi: g = self._fancy_replace(a, alo, ahi, b, blo, bhi) else: g = self._dump('-', a, alo, ahi) elif blo < bhi: g = self._dump('+', b, blo, bhi) yield from g def _qformat(self, aline, bline, atags, btags): r""" Format "?" output and deal with tabs. Example: >>> d = Differ() >>> results = d._qformat('\tabcDefghiJkl\n', '\tabcdefGhijkl\n', ... ' ^ ^ ^ ', ' ^ ^ ^ ') >>> for line in results: print(repr(line)) ... '- \tabcDefghiJkl\n' '? \t ^ ^ ^\n' '+ \tabcdefGhijkl\n' '? \t ^ ^ ^\n' """ atags = _keep_original_ws(aline, atags).rstrip() btags = _keep_original_ws(bline, btags).rstrip() yield "- " + aline if atags: yield f"? {atags}\n" yield "+ " + bline if btags: yield f"? {btags}\n" # With respect to junk, an earlier version of ndiff simply refused to # *start* a match with a junk element. The result was cases like this: # before: private Thread currentThread; # after: private volatile Thread currentThread; # If you consider whitespace to be junk, the longest contiguous match # not starting with junk is "e Thread currentThread". So ndiff reported # that "e volatil" was inserted between the 't' and the 'e' in "private". # While an accurate view, to people that's absurd. The current version # looks for matching blocks that are entirely junk-free, then extends the # longest one of those as far as possible but only with matching junk. # So now "currentThread" is matched, then extended to suck up the # preceding blank; then "private" is matched, and extended to suck up the # following blank; then "Thread" is matched; and finally ndiff reports # that "volatile " was inserted before "Thread". The only quibble # remaining is that perhaps it was really the case that " volatile" # was inserted after "private". I can live with that <wink>. import re def IS_LINE_JUNK(line, pat=re.compile(r"\s*(?:#\s*)?$").match): r""" Return True for ignorable line: iff `line` is blank or contains a single '#'. Examples: >>> IS_LINE_JUNK('\n') True >>> IS_LINE_JUNK(' # \n') True >>> IS_LINE_JUNK('hello\n') False """ return pat(line) is not None def IS_CHARACTER_JUNK(ch, ws=" \t"): r""" Return True for ignorable character: iff `ch` is a space or tab. Examples: >>> IS_CHARACTER_JUNK(' ') True >>> IS_CHARACTER_JUNK('\t') True >>> IS_CHARACTER_JUNK('\n') False >>> IS_CHARACTER_JUNK('x') False """ return ch in ws ######################################################################## ### Unified Diff ######################################################################## def _format_range_unified(start, stop): 'Convert range to the "ed" format' # Per the diff spec at http://www.unix.org/single_unix_specification/ beginning = start + 1 # lines start numbering with one length = stop - start if length == 1: return '{}'.format(beginning) if not length: beginning -= 1 # empty ranges begin at line just before the range return '{},{}'.format(beginning, length) def unified_diff(a, b, fromfile='', tofile='', fromfiledate='', tofiledate='', n=3, lineterm='\n'): r""" Compare two sequences of lines; generate the delta as a unified diff. Unified diffs are a compact way of showing line changes and a few lines of context. The number of context lines is set by 'n' which defaults to three. By default, the diff control lines (those with ---, +++, or @@) are created with a trailing newline. This is helpful so that inputs created from file.readlines() result in diffs that are suitable for file.writelines() since both the inputs and outputs have trailing newlines. For inputs that do not have trailing newlines, set the lineterm argument to "" so that the output will be uniformly newline free. The unidiff format normally has a header for filenames and modification times. Any or all of these may be specified using strings for 'fromfile', 'tofile', 'fromfiledate', and 'tofiledate'. The modification times are normally expressed in the ISO 8601 format. Example: >>> for line in unified_diff('one two three four'.split(), ... 'zero one tree four'.split(), 'Original', 'Current', ... '2005-01-26 23:30:50', '2010-04-02 10:20:52', ... lineterm=''): ... print(line) # doctest: +NORMALIZE_WHITESPACE --- Original 2005-01-26 23:30:50 +++ Current 2010-04-02 10:20:52 @@ -1,4 +1,4 @@ +zero one -two -three +tree four """ _check_types(a, b, fromfile, tofile, fromfiledate, tofiledate, lineterm) started = False for group in SequenceMatcher(None,a,b).get_grouped_opcodes(n): if not started: started = True fromdate = '\t{}'.format(fromfiledate) if fromfiledate else '' todate = '\t{}'.format(tofiledate) if tofiledate else '' yield '--- {}{}{}'.format(fromfile, fromdate, lineterm) yield '+++ {}{}{}'.format(tofile, todate, lineterm) first, last = group[0], group[-1] file1_range = _format_range_unified(first[1], last[2]) file2_range = _format_range_unified(first[3], last[4]) yield '@@ -{} +{} @@{}'.format(file1_range, file2_range, lineterm) for tag, i1, i2, j1, j2 in group: if tag == 'equal': for line in a[i1:i2]: yield ' ' + line continue if tag in {'replace', 'delete'}: for line in a[i1:i2]: yield '-' + line if tag in {'replace', 'insert'}: for line in b[j1:j2]: yield '+' + line ######################################################################## ### Context Diff ######################################################################## def _format_range_context(start, stop): 'Convert range to the "ed" format' # Per the diff spec at http://www.unix.org/single_unix_specification/ beginning = start + 1 # lines start numbering with one length = stop - start if not length: beginning -= 1 # empty ranges begin at line just before the range if length <= 1: return '{}'.format(beginning) return '{},{}'.format(beginning, beginning + length - 1) # See http://www.unix.org/single_unix_specification/ def context_diff(a, b, fromfile='', tofile='', fromfiledate='', tofiledate='', n=3, lineterm='\n'): r""" Compare two sequences of lines; generate the delta as a context diff. Context diffs are a compact way of showing line changes and a few lines of context. The number of context lines is set by 'n' which defaults to three. By default, the diff control lines (those with *** or ---) are created with a trailing newline. This is helpful so that inputs created from file.readlines() result in diffs that are suitable for file.writelines() since both the inputs and outputs have trailing newlines. For inputs that do not have trailing newlines, set the lineterm argument to "" so that the output will be uniformly newline free. The context diff format normally has a header for filenames and modification times. Any or all of these may be specified using strings for 'fromfile', 'tofile', 'fromfiledate', and 'tofiledate'. The modification times are normally expressed in the ISO 8601 format. If not specified, the strings default to blanks. Example: >>> print(''.join(context_diff('one\ntwo\nthree\nfour\n'.splitlines(True), ... 'zero\none\ntree\nfour\n'.splitlines(True), 'Original', 'Current')), ... end="") *** Original --- Current *************** *** 1,4 **** one ! two ! three four --- 1,4 ---- + zero one ! tree four """ _check_types(a, b, fromfile, tofile, fromfiledate, tofiledate, lineterm) prefix = dict(insert='+ ', delete='- ', replace='! ', equal=' ') started = False for group in SequenceMatcher(None,a,b).get_grouped_opcodes(n): if not started: started = True fromdate = '\t{}'.format(fromfiledate) if fromfiledate else '' todate = '\t{}'.format(tofiledate) if tofiledate else '' yield '*** {}{}{}'.format(fromfile, fromdate, lineterm) yield '--- {}{}{}'.format(tofile, todate, lineterm) first, last = group[0], group[-1] yield '***************' + lineterm file1_range = _format_range_context(first[1], last[2]) yield '*** {} ****{}'.format(file1_range, lineterm) if any(tag in {'replace', 'delete'} for tag, _, _, _, _ in group): for tag, i1, i2, _, _ in group: if tag != 'insert': for line in a[i1:i2]: yield prefix[tag] + line file2_range = _format_range_context(first[3], last[4]) yield '--- {} ----{}'.format(file2_range, lineterm) if any(tag in {'replace', 'insert'} for tag, _, _, _, _ in group): for tag, _, _, j1, j2 in group: if tag != 'delete': for line in b[j1:j2]: yield prefix[tag] + line def _check_types(a, b, *args): # Checking types is weird, but the alternative is garbled output when # someone passes mixed bytes and str to {unified,context}_diff(). E.g. # without this check, passing filenames as bytes results in output like # --- b'oldfile.txt' # +++ b'newfile.txt' # because of how str.format() incorporates bytes objects. if a and not isinstance(a[0], str): raise TypeError('lines to compare must be str, not %s (%r)' % (type(a[0]).__name__, a[0])) if b and not isinstance(b[0], str): raise TypeError('lines to compare must be str, not %s (%r)' % (type(b[0]).__name__, b[0])) for arg in args: if not isinstance(arg, str): raise TypeError('all arguments must be str, not: %r' % (arg,)) def diff_bytes(dfunc, a, b, fromfile=b'', tofile=b'', fromfiledate=b'', tofiledate=b'', n=3, lineterm=b'\n'): r""" Compare `a` and `b`, two sequences of lines represented as bytes rather than str. This is a wrapper for `dfunc`, which is typically either unified_diff() or context_diff(). Inputs are losslessly converted to strings so that `dfunc` only has to worry about strings, and encoded back to bytes on return. This is necessary to compare files with unknown or inconsistent encoding. All other inputs (except `n`) must be bytes rather than str. """ def decode(s): try: return s.decode('ascii', 'surrogateescape') except AttributeError as err: msg = ('all arguments must be bytes, not %s (%r)' % (type(s).__name__, s)) raise TypeError(msg) from err a = list(map(decode, a)) b = list(map(decode, b)) fromfile = decode(fromfile) tofile = decode(tofile) fromfiledate = decode(fromfiledate) tofiledate = decode(tofiledate) lineterm = decode(lineterm) lines = dfunc(a, b, fromfile, tofile, fromfiledate, tofiledate, n, lineterm) for line in lines: yield line.encode('ascii', 'surrogateescape') def ndiff(a, b, linejunk=None, charjunk=IS_CHARACTER_JUNK): r""" Compare `a` and `b` (lists of strings); return a `Differ`-style delta. Optional keyword parameters `linejunk` and `charjunk` are for filter functions, or can be None: - linejunk: A function that should accept a single string argument and return true iff the string is junk. The default is None, and is recommended; the underlying SequenceMatcher class has an adaptive notion of "noise" lines. - charjunk: A function that accepts a character (string of length 1), and returns true iff the character is junk. The default is the module-level function IS_CHARACTER_JUNK, which filters out whitespace characters (a blank or tab; note: it's a bad idea to include newline in this!). Tools/scripts/ndiff.py is a command-line front-end to this function. Example: >>> diff = ndiff('one\ntwo\nthree\n'.splitlines(keepends=True), ... 'ore\ntree\nemu\n'.splitlines(keepends=True)) >>> print(''.join(diff), end="") - one ? ^ + ore ? ^ - two - three ? - + tree + emu """ return Differ(linejunk, charjunk).compare(a, b) def _mdiff(fromlines, tolines, context=None, linejunk=None, charjunk=IS_CHARACTER_JUNK): r"""Returns generator yielding marked up from/to side by side differences. Arguments: fromlines -- list of text lines to compared to tolines tolines -- list of text lines to be compared to fromlines context -- number of context lines to display on each side of difference, if None, all from/to text lines will be generated. linejunk -- passed on to ndiff (see ndiff documentation) charjunk -- passed on to ndiff (see ndiff documentation) This function returns an iterator which returns a tuple: (from line tuple, to line tuple, boolean flag) from/to line tuple -- (line num, line text) line num -- integer or None (to indicate a context separation) line text -- original line text with following markers inserted: '\0+' -- marks start of added text '\0-' -- marks start of deleted text '\0^' -- marks start of changed text '\1' -- marks end of added/deleted/changed text boolean flag -- None indicates context separation, True indicates either "from" or "to" line contains a change, otherwise False. This function/iterator was originally developed to generate side by side file difference for making HTML pages (see HtmlDiff class for example usage). Note, this function utilizes the ndiff function to generate the side by side difference markup. Optional ndiff arguments may be passed to this function and they in turn will be passed to ndiff. """ import re # regular expression for finding intraline change indices change_re = re.compile(r'(\++|\-+|\^+)') # create the difference iterator to generate the differences diff_lines_iterator = ndiff(fromlines,tolines,linejunk,charjunk) def _make_line(lines, format_key, side, num_lines=[0,0]): """Returns line of text with user's change markup and line formatting. lines -- list of lines from the ndiff generator to produce a line of text from. When producing the line of text to return, the lines used are removed from this list. format_key -- '+' return first line in list with "add" markup around the entire line. '-' return first line in list with "delete" markup around the entire line. '?' return first line in list with add/delete/change intraline markup (indices obtained from second line) None return first line in list with no markup side -- indice into the num_lines list (0=from,1=to) num_lines -- from/to current line number. This is NOT intended to be a passed parameter. It is present as a keyword argument to maintain memory of the current line numbers between calls of this function. Note, this function is purposefully not defined at the module scope so that data it needs from its parent function (within whose context it is defined) does not need to be of module scope. """ num_lines[side] += 1 # Handle case where no user markup is to be added, just return line of # text with user's line format to allow for usage of the line number. if format_key is None: return (num_lines[side],lines.pop(0)[2:]) # Handle case of intraline changes if format_key == '?': text, markers = lines.pop(0), lines.pop(0) # find intraline changes (store change type and indices in tuples) sub_info = [] def record_sub_info(match_object,sub_info=sub_info): sub_info.append([match_object.group(1)[0],match_object.span()]) return match_object.group(1) change_re.sub(record_sub_info,markers) # process each tuple inserting our special marks that won't be # noticed by an xml/html escaper. for key,(begin,end) in reversed(sub_info): text = text[0:begin]+'\0'+key+text[begin:end]+'\1'+text[end:] text = text[2:] # Handle case of add/delete entire line else: text = lines.pop(0)[2:] # if line of text is just a newline, insert a space so there is # something for the user to highlight and see. if not text: text = ' ' # insert marks that won't be noticed by an xml/html escaper. text = '\0' + format_key + text + '\1' # Return line of text, first allow user's line formatter to do its # thing (such as adding the line number) then replace the special # marks with what the user's change markup. return (num_lines[side],text) def _line_iterator(): """Yields from/to lines of text with a change indication. This function is an iterator. It itself pulls lines from a differencing iterator, processes them and yields them. When it can it yields both a "from" and a "to" line, otherwise it will yield one or the other. In addition to yielding the lines of from/to text, a boolean flag is yielded to indicate if the text line(s) have differences in them. Note, this function is purposefully not defined at the module scope so that data it needs from its parent function (within whose context it is defined) does not need to be of module scope. """ lines = [] num_blanks_pending, num_blanks_to_yield = 0, 0 while True: # Load up next 4 lines so we can look ahead, create strings which # are a concatenation of the first character of each of the 4 lines # so we can do some very readable comparisons. while len(lines) < 4: lines.append(next(diff_lines_iterator, 'X')) s = ''.join([line[0] for line in lines]) if s.startswith('X'): # When no more lines, pump out any remaining blank lines so the # corresponding add/delete lines get a matching blank line so # all line pairs get yielded at the next level. num_blanks_to_yield = num_blanks_pending elif s.startswith('-?+?'): # simple intraline change yield _make_line(lines,'?',0), _make_line(lines,'?',1), True continue elif s.startswith('--++'): # in delete block, add block coming: we do NOT want to get # caught up on blank lines yet, just process the delete line num_blanks_pending -= 1 yield _make_line(lines,'-',0), None, True continue elif s.startswith(('--?+', '--+', '- ')): # in delete block and see an intraline change or unchanged line # coming: yield the delete line and then blanks from_line,to_line = _make_line(lines,'-',0), None num_blanks_to_yield,num_blanks_pending = num_blanks_pending-1,0 elif s.startswith('-+?'): # intraline change yield _make_line(lines,None,0), _make_line(lines,'?',1), True continue elif s.startswith('-?+'): # intraline change yield _make_line(lines,'?',0), _make_line(lines,None,1), True continue elif s.startswith('-'): # delete FROM line num_blanks_pending -= 1 yield _make_line(lines,'-',0), None, True continue elif s.startswith('+--'): # in add block, delete block coming: we do NOT want to get # caught up on blank lines yet, just process the add line num_blanks_pending += 1 yield None, _make_line(lines,'+',1), True continue elif s.startswith(('+ ', '+-')): # will be leaving an add block: yield blanks then add line from_line, to_line = None, _make_line(lines,'+',1) num_blanks_to_yield,num_blanks_pending = num_blanks_pending+1,0 elif s.startswith('+'): # inside an add block, yield the add line num_blanks_pending += 1 yield None, _make_line(lines,'+',1), True continue elif s.startswith(' '): # unchanged text, yield it to both sides yield _make_line(lines[:],None,0),_make_line(lines,None,1),False continue # Catch up on the blank lines so when we yield the next from/to # pair, they are lined up. while(num_blanks_to_yield < 0): num_blanks_to_yield += 1 yield None,('','\n'),True while(num_blanks_to_yield > 0): num_blanks_to_yield -= 1 yield ('','\n'),None,True if s.startswith('X'): return else: yield from_line,to_line,True def _line_pair_iterator(): """Yields from/to lines of text with a change indication. This function is an iterator. It itself pulls lines from the line iterator. Its difference from that iterator is that this function always yields a pair of from/to text lines (with the change indication). If necessary it will collect single from/to lines until it has a matching pair from/to pair to yield. Note, this function is purposefully not defined at the module scope so that data it needs from its parent function (within whose context it is defined) does not need to be of module scope. """ line_iterator = _line_iterator() fromlines,tolines=[],[] while True: # Collecting lines of text until we have a from/to pair while (len(fromlines)==0 or len(tolines)==0): try: from_line, to_line, found_diff = next(line_iterator) except StopIteration: return if from_line is not None: fromlines.append((from_line,found_diff)) if to_line is not None: tolines.append((to_line,found_diff)) # Once we have a pair, remove them from the collection and yield it from_line, fromDiff = fromlines.pop(0) to_line, to_diff = tolines.pop(0) yield (from_line,to_line,fromDiff or to_diff) # Handle case where user does not want context differencing, just yield # them up without doing anything else with them. line_pair_iterator = _line_pair_iterator() if context is None: yield from line_pair_iterator # Handle case where user wants context differencing. We must do some # storage of lines until we know for sure that they are to be yielded. else: context += 1 lines_to_write = 0 while True: # Store lines up until we find a difference, note use of a # circular queue because we only need to keep around what # we need for context. index, contextLines = 0, [None]*(context) found_diff = False while(found_diff is False): try: from_line, to_line, found_diff = next(line_pair_iterator) except StopIteration: return i = index % context contextLines[i] = (from_line, to_line, found_diff) index += 1 # Yield lines that we have collected so far, but first yield # the user's separator. if index > context: yield None, None, None lines_to_write = context else: lines_to_write = index index = 0 while(lines_to_write): i = index % context index += 1 yield contextLines[i] lines_to_write -= 1 # Now yield the context lines after the change lines_to_write = context-1 try: while(lines_to_write): from_line, to_line, found_diff = next(line_pair_iterator) # If another change within the context, extend the context if found_diff: lines_to_write = context-1 else: lines_to_write -= 1 yield from_line, to_line, found_diff except StopIteration: # Catch exception from next() and return normally return _file_template = """ <!DOCTYPE html PUBLIC "-//W3C//DTD XHTML 1.0 Transitional//EN" "http://www.w3.org/TR/xhtml1/DTD/xhtml1-transitional.dtd"> <html> <head> <meta http-equiv="Content-Type" content="text/html; charset=%(charset)s" /> <title></title> <style type="text/css">%(styles)s </style> </head> <body> %(table)s%(legend)s </body> </html>""" _styles = """ table.diff {font-family:Courier; border:medium;} .diff_header {background-color:#e0e0e0} td.diff_header {text-align:right} .diff_next {background-color:#c0c0c0} .diff_add {background-color:#aaffaa} .diff_chg {background-color:#ffff77} .diff_sub {background-color:#ffaaaa}""" _table_template = """ <table class="diff" id="difflib_chg_%(prefix)s_top" cellspacing="0" cellpadding="0" rules="groups" > <colgroup></colgroup> <colgroup></colgroup> <colgroup></colgroup> <colgroup></colgroup> <colgroup></colgroup> <colgroup></colgroup> %(header_row)s <tbody> %(data_rows)s </tbody> </table>""" _legend = """ <table class="diff" summary="Legends"> <tr> <th colspan="2"> Legends </th> </tr> <tr> <td> <table border="" summary="Colors"> <tr><th> Colors </th> </tr> <tr><td class="diff_add">&nbsp;Added&nbsp;</td></tr> <tr><td class="diff_chg">Changed</td> </tr> <tr><td class="diff_sub">Deleted</td> </tr> </table></td> <td> <table border="" summary="Links"> <tr><th colspan="2"> Links </th> </tr> <tr><td>(f)irst change</td> </tr> <tr><td>(n)ext change</td> </tr> <tr><td>(t)op</td> </tr> </table></td> </tr> </table>""" class HtmlDiff(object): """For producing HTML side by side comparison with change highlights. This class can be used to create an HTML table (or a complete HTML file containing the table) showing a side by side, line by line comparison of text with inter-line and intra-line change highlights. The table can be generated in either full or contextual difference mode. The following methods are provided for HTML generation: make_table -- generates HTML for a single side by side table make_file -- generates complete HTML file with a single side by side table See tools/scripts/diff.py for an example usage of this class. """ _file_template = _file_template _styles = _styles _table_template = _table_template _legend = _legend _default_prefix = 0 def __init__(self,tabsize=8,wrapcolumn=None,linejunk=None, charjunk=IS_CHARACTER_JUNK): """HtmlDiff instance initializer Arguments: tabsize -- tab stop spacing, defaults to 8. wrapcolumn -- column number where lines are broken and wrapped, defaults to None where lines are not wrapped. linejunk,charjunk -- keyword arguments passed into ndiff() (used by HtmlDiff() to generate the side by side HTML differences). See ndiff() documentation for argument default values and descriptions. """ self._tabsize = tabsize self._wrapcolumn = wrapcolumn self._linejunk = linejunk self._charjunk = charjunk def make_file(self, fromlines, tolines, fromdesc='', todesc='', context=False, numlines=5, *, charset='utf-8'): """Returns HTML file of side by side comparison with change highlights Arguments: fromlines -- list of "from" lines tolines -- list of "to" lines fromdesc -- "from" file column header string todesc -- "to" file column header string context -- set to True for contextual differences (defaults to False which shows full differences). numlines -- number of context lines. When context is set True, controls number of lines displayed before and after the change. When context is False, controls the number of lines to place the "next" link anchors before the next change (so click of "next" link jumps to just before the change). charset -- charset of the HTML document """ return (self._file_template % dict( styles=self._styles, legend=self._legend, table=self.make_table(fromlines, tolines, fromdesc, todesc, context=context, numlines=numlines), charset=charset )).encode(charset, 'xmlcharrefreplace').decode(charset) def _tab_newline_replace(self,fromlines,tolines): """Returns from/to line lists with tabs expanded and newlines removed. Instead of tab characters being replaced by the number of spaces needed to fill in to the next tab stop, this function will fill the space with tab characters. This is done so that the difference algorithms can identify changes in a file when tabs are replaced by spaces and vice versa. At the end of the HTML generation, the tab characters will be replaced with a nonbreakable space. """ def expand_tabs(line): # hide real spaces line = line.replace(' ','\0') # expand tabs into spaces line = line.expandtabs(self._tabsize) # replace spaces from expanded tabs back into tab characters # (we'll replace them with markup after we do differencing) line = line.replace(' ','\t') return line.replace('\0',' ').rstrip('\n') fromlines = [expand_tabs(line) for line in fromlines] tolines = [expand_tabs(line) for line in tolines] return fromlines,tolines def _split_line(self,data_list,line_num,text): """Builds list of text lines by splitting text lines at wrap point This function will determine if the input text line needs to be wrapped (split) into separate lines. If so, the first wrap point will be determined and the first line appended to the output text line list. This function is used recursively to handle the second part of the split line to further split it. """ # if blank line or context separator, just add it to the output list if not line_num: data_list.append((line_num,text)) return # if line text doesn't need wrapping, just add it to the output list size = len(text) max = self._wrapcolumn if (size <= max) or ((size -(text.count('\0')*3)) <= max): data_list.append((line_num,text)) return # scan text looking for the wrap point, keeping track if the wrap # point is inside markers i = 0 n = 0 mark = '' while n < max and i < size: if text[i] == '\0': i += 1 mark = text[i] i += 1 elif text[i] == '\1': i += 1 mark = '' else: i += 1 n += 1 # wrap point is inside text, break it up into separate lines line1 = text[:i] line2 = text[i:] # if wrap point is inside markers, place end marker at end of first # line and start marker at beginning of second line because each # line will have its own table tag markup around it. if mark: line1 = line1 + '\1' line2 = '\0' + mark + line2 # tack on first line onto the output list data_list.append((line_num,line1)) # use this routine again to wrap the remaining text self._split_line(data_list,'>',line2) def _line_wrapper(self,diffs): """Returns iterator that splits (wraps) mdiff text lines""" # pull from/to data and flags from mdiff iterator for fromdata,todata,flag in diffs: # check for context separators and pass them through if flag is None: yield fromdata,todata,flag continue (fromline,fromtext),(toline,totext) = fromdata,todata # for each from/to line split it at the wrap column to form # list of text lines. fromlist,tolist = [],[] self._split_line(fromlist,fromline,fromtext) self._split_line(tolist,toline,totext) # yield from/to line in pairs inserting blank lines as # necessary when one side has more wrapped lines while fromlist or tolist: if fromlist: fromdata = fromlist.pop(0) else: fromdata = ('',' ') if tolist: todata = tolist.pop(0) else: todata = ('',' ') yield fromdata,todata,flag def _collect_lines(self,diffs): """Collects mdiff output into separate lists Before storing the mdiff from/to data into a list, it is converted into a single line of text with HTML markup. """ fromlist,tolist,flaglist = [],[],[] # pull from/to data and flags from mdiff style iterator for fromdata,todata,flag in diffs: try: # store HTML markup of the lines into the lists fromlist.append(self._format_line(0,flag,*fromdata)) tolist.append(self._format_line(1,flag,*todata)) except TypeError: # exceptions occur for lines where context separators go fromlist.append(None) tolist.append(None) flaglist.append(flag) return fromlist,tolist,flaglist def _format_line(self,side,flag,linenum,text): """Returns HTML markup of "from" / "to" text lines side -- 0 or 1 indicating "from" or "to" text flag -- indicates if difference on line linenum -- line number (used for line number column) text -- line text to be marked up """ try: linenum = '%d' % linenum id = ' id="%s%s"' % (self._prefix[side],linenum) except TypeError: # handle blank lines where linenum is '>' or '' id = '' # replace those things that would get confused with HTML symbols text=text.replace("&","&amp;").replace(">","&gt;").replace("<","&lt;") # make space non-breakable so they don't get compressed or line wrapped text = text.replace(' ','&nbsp;').rstrip() return '<td class="diff_header"%s>%s</td><td nowrap="nowrap">%s</td>' \ % (id,linenum,text) def _make_prefix(self): """Create unique anchor prefixes""" # Generate a unique anchor prefix so multiple tables # can exist on the same HTML page without conflicts. fromprefix = "from%d_" % HtmlDiff._default_prefix toprefix = "to%d_" % HtmlDiff._default_prefix HtmlDiff._default_prefix += 1 # store prefixes so line format method has access self._prefix = [fromprefix,toprefix] def _convert_flags(self,fromlist,tolist,flaglist,context,numlines): """Makes list of "next" links""" # all anchor names will be generated using the unique "to" prefix toprefix = self._prefix[1] # process change flags, generating middle column of next anchors/links next_id = ['']*len(flaglist) next_href = ['']*len(flaglist) num_chg, in_change = 0, False last = 0 for i,flag in enumerate(flaglist): if flag: if not in_change: in_change = True last = i # at the beginning of a change, drop an anchor a few lines # (the context lines) before the change for the previous # link i = max([0,i-numlines]) next_id[i] = ' id="difflib_chg_%s_%d"' % (toprefix,num_chg) # at the beginning of a change, drop a link to the next # change num_chg += 1 next_href[last] = '<a href="#difflib_chg_%s_%d">n</a>' % ( toprefix,num_chg) else: in_change = False # check for cases where there is no content to avoid exceptions if not flaglist: flaglist = [False] next_id = [''] next_href = [''] last = 0 if context: fromlist = ['<td></td><td>&nbsp;No Differences Found&nbsp;</td>'] tolist = fromlist else: fromlist = tolist = ['<td></td><td>&nbsp;Empty File&nbsp;</td>'] # if not a change on first line, drop a link if not flaglist[0]: next_href[0] = '<a href="#difflib_chg_%s_0">f</a>' % toprefix # redo the last link to link to the top next_href[last] = '<a href="#difflib_chg_%s_top">t</a>' % (toprefix) return fromlist,tolist,flaglist,next_href,next_id def make_table(self,fromlines,tolines,fromdesc='',todesc='',context=False, numlines=5): """Returns HTML table of side by side comparison with change highlights Arguments: fromlines -- list of "from" lines tolines -- list of "to" lines fromdesc -- "from" file column header string todesc -- "to" file column header string context -- set to True for contextual differences (defaults to False which shows full differences). numlines -- number of context lines. When context is set True, controls number of lines displayed before and after the change. When context is False, controls the number of lines to place the "next" link anchors before the next change (so click of "next" link jumps to just before the change). """ # make unique anchor prefixes so that multiple tables may exist # on the same page without conflict. self._make_prefix() # change tabs to spaces before it gets more difficult after we insert # markup fromlines,tolines = self._tab_newline_replace(fromlines,tolines) # create diffs iterator which generates side by side from/to data if context: context_lines = numlines else: context_lines = None diffs = _mdiff(fromlines,tolines,context_lines,linejunk=self._linejunk, charjunk=self._charjunk) # set up iterator to wrap lines that exceed desired width if self._wrapcolumn: diffs = self._line_wrapper(diffs) # collect up from/to lines and flags into lists (also format the lines) fromlist,tolist,flaglist = self._collect_lines(diffs) # process change flags, generating middle column of next anchors/links fromlist,tolist,flaglist,next_href,next_id = self._convert_flags( fromlist,tolist,flaglist,context,numlines) s = [] fmt = ' <tr><td class="diff_next"%s>%s</td>%s' + \ '<td class="diff_next">%s</td>%s</tr>\n' for i in range(len(flaglist)): if flaglist[i] is None: # mdiff yields None on separator lines skip the bogus ones # generated for the first line if i > 0: s.append(' </tbody> \n <tbody>\n') else: s.append( fmt % (next_id[i],next_href[i],fromlist[i], next_href[i],tolist[i])) if fromdesc or todesc: header_row = '<thead><tr>%s%s%s%s</tr></thead>' % ( '<th class="diff_next"><br /></th>', '<th colspan="2" class="diff_header">%s</th>' % fromdesc, '<th class="diff_next"><br /></th>', '<th colspan="2" class="diff_header">%s</th>' % todesc) else: header_row = '' table = self._table_template % dict( data_rows=''.join(s), header_row=header_row, prefix=self._prefix[1]) return table.replace('\0+','<span class="diff_add">'). \ replace('\0-','<span class="diff_sub">'). \ replace('\0^','<span class="diff_chg">'). \ replace('\1','</span>'). \ replace('\t','&nbsp;') del re def restore(delta, which): r""" Generate one of the two sequences that generated a delta. Given a `delta` produced by `Differ.compare()` or `ndiff()`, extract lines originating from file 1 or 2 (parameter `which`), stripping off line prefixes. Examples: >>> diff = ndiff('one\ntwo\nthree\n'.splitlines(keepends=True), ... 'ore\ntree\nemu\n'.splitlines(keepends=True)) >>> diff = list(diff) >>> print(''.join(restore(diff, 1)), end="") one two three >>> print(''.join(restore(diff, 2)), end="") ore tree emu """ try: tag = {1: "- ", 2: "+ "}[int(which)] except KeyError: raise ValueError('unknown delta choice (must be 1 or 2): %r' % which) from None prefixes = (" ", tag) for line in delta: if line[:2] in prefixes: yield line[2:] def _test(): import doctest, difflib return doctest.testmod(difflib) if __name__ == "__main__": _test()