grep: teach --debug option to dump the parse tree
Our "grep" allows complex boolean expressions to be formed to match each individual line with operators like --and, '(', ')' and --not. Introduce the "--debug" option to show the parse tree to help people who want to debug and enhance it. Also "log" learns "--grep-debug" option to do the same. The command line parser to the log family is a lot more limited than the general "git grep" parser, but it has special handling for header matching (e.g. "--author"), and a parse tree is valuable when working on it. Note that "--all-match" is *not* any individual node in the parse tree. It is an instruction to the evaluator to check all the nodes in the top-level backbone have matched and reject a document as non-matching otherwise. Signed-off-by: Junio C Hamano <gitster@pobox.com>
Junio C Hamano committed
Sep 13, 2012 at 14:21 UTC
17bf35a3c7b46df7131681bcc5bee5f12e1caec4
4 files changed
+96
-2
builtin/grep.c
+3
@@ -772,6 +772,9 @@ int cmd_grep(int argc, const char **argv, const char *prefix)
772
"indicate hit with exit status without output"),
773
OPT_BOOLEAN(0, "all-match", &opt.all_match,
774
"show only matches from files that match all patterns"),
775
+ { OPTION_SET_INT, 0, "debug", &opt.debug, NULL,
776
+ "show parse tree for grep expression",
777
+ PARSE_OPT_NOARG | PARSE_OPT_HIDDEN, NULL, 1 },
778
OPT_GROUP(""),
779
{ OPTION_STRING, 'O', "open-files-in-pager", &show_in_pager,
780
"pager", "show matching files in the pager",
grep.c
+90
-2
@@ -332,6 +332,87 @@ static struct grep_expr *compile_pattern_expr(struct grep_pat **list)
332
return compile_pattern_or(list);
333
}
334
335
+static void indent(int in)
336
+{
337
+ while (in-- > 0)
338
+ fputc(' ', stderr);
339
+}
340
+
341
+static void dump_grep_pat(struct grep_pat *p)
342
+{
343
+ switch (p->token) {
344
+ case GREP_AND: fprintf(stderr, "*and*"); break;
345
+ case GREP_OPEN_PAREN: fprintf(stderr, "*(*"); break;
346
+ case GREP_CLOSE_PAREN: fprintf(stderr, "*)*"); break;
347
+ case GREP_NOT: fprintf(stderr, "*not*"); break;
348
+ case GREP_OR: fprintf(stderr, "*or*"); break;
349
+
350
+ case GREP_PATTERN: fprintf(stderr, "pattern"); break;
351
+ case GREP_PATTERN_HEAD: fprintf(stderr, "pattern_head"); break;
352
+ case GREP_PATTERN_BODY: fprintf(stderr, "pattern_body"); break;
353
+ }
354
+
355
+ switch (p->token) {
356
+ default: break;
357
+ case GREP_PATTERN_HEAD:
358
+ fprintf(stderr, "<head %d>", p->field); break;
359
+ case GREP_PATTERN_BODY:
360
+ fprintf(stderr, "<body>"); break;
361
+ }
362
+ switch (p->token) {
363
+ default: break;
364
+ case GREP_PATTERN_HEAD:
365
+ case GREP_PATTERN_BODY:
366
+ case GREP_PATTERN:
367
+ fprintf(stderr, "%.*s", (int)p->patternlen, p->pattern);
368
+ break;
369
+ }
370
+ fputc('\n', stderr);
371
+}
372
+
373
+static void dump_grep_expression_1(struct grep_expr *x, int in)
374
+{
375
+ indent(in);
376
+ switch (x->node) {
377
+ case GREP_NODE_TRUE:
378
+ fprintf(stderr, "true\n");
379
+ break;
380
+ case GREP_NODE_ATOM:
381
+ dump_grep_pat(x->u.atom);
382
+ break;
383
+ case GREP_NODE_NOT:
384
+ fprintf(stderr, "(not\n");
385
+ dump_grep_expression_1(x->u.unary, in+1);
386
+ indent(in);
387
+ fprintf(stderr, ")\n");
388
+ break;
389
+ case GREP_NODE_AND:
390
+ fprintf(stderr, "(and\n");
391
+ dump_grep_expression_1(x->u.binary.left, in+1);
392
+ dump_grep_expression_1(x->u.binary.right, in+1);
393
+ indent(in);
394
+ fprintf(stderr, ")\n");
395
+ break;
396
+ case GREP_NODE_OR:
397
+ fprintf(stderr, "(or\n");
398
+ dump_grep_expression_1(x->u.binary.left, in+1);
399
+ dump_grep_expression_1(x->u.binary.right, in+1);
400
+ indent(in);
401
+ fprintf(stderr, ")\n");
402
+ break;
403
+ }
404
+}
405
+
406
+void dump_grep_expression(struct grep_opt *opt)
407
+{
408
+ struct grep_expr *x = opt->pattern_expression;
409
+
410
+ if (opt->all_match)
411
+ fprintf(stderr, "[all-match]\n");
412
+ dump_grep_expression_1(x, 0);
413
+ fflush(NULL);
414
+}
415
+
416
static struct grep_expr *grep_true_expr(void)
417
{
418
struct grep_expr *z = xcalloc(1, sizeof(*z));
@@ -395,7 +476,7 @@ static struct grep_expr *prep_header_patterns(struct grep_opt *opt)
476
return header_expr;
477
}
478
398
-void compile_grep_patterns(struct grep_opt *opt)
479
+static void compile_grep_patterns_real(struct grep_opt *opt)
480
{
481
struct grep_pat *p;
482
struct grep_expr *header_expr = prep_header_patterns(opt);
@@ -415,7 +496,7 @@ void compile_grep_patterns(struct grep_opt *opt)
496
497
if (opt->all_match || header_expr)
498
opt->extended = 1;
418
- else if (!opt->extended)
499
+ else if (!opt->extended && !opt->debug)
500
return;
501
502
p = opt->pattern_list;
@@ -435,6 +516,13 @@ void compile_grep_patterns(struct grep_opt *opt)
516
opt->all_match = 1;
517
}
518
519
+void compile_grep_patterns(struct grep_opt *opt)
520
+{
521
+ compile_grep_patterns_real(opt);
522
+ if (opt->debug)
523
+ dump_grep_expression(opt);
524
+}
525
+
526
static void free_pattern_expr(struct grep_expr *x)
527
{
528
switch (x->node) {
grep.h
+1
@@ -90,6 +90,7 @@ struct grep_opt {
90
int word_regexp;
91
int fixed;
92
int all_match;
93
+ int debug;
94
#define GREP_BINARY_DEFAULT 0
95
#define GREP_BINARY_NOMATCH 1
96
#define GREP_BINARY_TEXT 2
revision.c
+2
@@ -1578,6 +1578,8 @@ static int handle_revision_opt(struct rev_info *revs, int argc, const char **arg
1578
} else if ((argcount = parse_long_opt("grep", argv, &optarg))) {
1579
add_message_grep(revs, optarg);
1580
return argcount;
1581
+ } else if (!strcmp(arg, "--grep-debug")) {
1582
+ revs->grep_filter.debug = 1;
1583
} else if (!strcmp(arg, "--extended-regexp") || !strcmp(arg, "-E")) {
1584
revs->grep_filter.regflags |= REG_EXTENDED;
1585
} else if (!strcmp(arg, "--regexp-ignore-case") || !strcmp(arg, "-i")) {