Andrew's git / gitweb.git / diff
?
grep: teach --debug option to dump the parse tree
authorJunio C Hamano <gitster@pobox.com>
Thu, 13 Sep 2012 21:21:44 +0000 (14:21 -0700)
committerJunio C Hamano <gitster@pobox.com>
Fri, 14 Sep 2012 17:10:35 +0000 (10:10 -0700)
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>
builtin/grep.c patch | blob | history
grep.c patch | blob | history
grep.h patch | blob | history
revision.c patch | blob | history
diff --git a/builtin/grep.c b/builtin/grep.c
index fe1726f5ef60d054938eaa849f2ae6020a95f805..8aea00c04840552d8d9912195609883ed0dc6bb2 100644 (file)
--- a/builtin/grep.c
+++ b/builtin/grep.c
@@ -772,6 +772,9 @@ int cmd_grep(int argc, const char **argv, const char *prefix)
                           "indicate hit with exit status without output"),
                OPT_BOOLEAN(0, "all-match", &opt.all_match,
                        "show only matches from files that match all patterns"),
                           "indicate hit with exit status without output"),
                OPT_BOOLEAN(0, "all-match", &opt.all_match,
                        "show only matches from files that match all patterns"),
+               { OPTION_SET_INT, 0, "debug", &opt.debug, NULL,
+                 "show parse tree for grep expression",
+                 PARSE_OPT_NOARG | PARSE_OPT_HIDDEN, NULL, 1 },
                OPT_GROUP(""),
                { OPTION_STRING, 'O', "open-files-in-pager", &show_in_pager,
                        "pager", "show matching files in the pager",
                OPT_GROUP(""),
                { OPTION_STRING, 'O', "open-files-in-pager", &show_in_pager,
                        "pager", "show matching files in the pager",
diff --git a/grep.c b/grep.c
index 04e3ec6c6e90e8bd96495c7b40bcb014384b07d8..be15c4753d9768820dc47e107b54f41523c13caf 100644 (file)
--- a/grep.c
+++ b/grep.c
@@ -332,6 +332,87 @@ static struct grep_expr *compile_pattern_expr(struct grep_pat **list)
        return compile_pattern_or(list);
 }
 
        return compile_pattern_or(list);
 }
 
+static void indent(int in)
+{
+       while (in-- > 0)
+               fputc(' ', stderr);
+}
+
+static void dump_grep_pat(struct grep_pat *p)
+{
+       switch (p->token) {
+       case GREP_AND: fprintf(stderr, "*and*"); break;
+       case GREP_OPEN_PAREN: fprintf(stderr, "*(*"); break;
+       case GREP_CLOSE_PAREN: fprintf(stderr, "*)*"); break;
+       case GREP_NOT: fprintf(stderr, "*not*"); break;
+       case GREP_OR: fprintf(stderr, "*or*"); break;
+
+       case GREP_PATTERN: fprintf(stderr, "pattern"); break;
+       case GREP_PATTERN_HEAD: fprintf(stderr, "pattern_head"); break;
+       case GREP_PATTERN_BODY: fprintf(stderr, "pattern_body"); break;
+       }
+
+       switch (p->token) {
+       default: break;
+       case GREP_PATTERN_HEAD:
+               fprintf(stderr, "<head %d>", p->field); break;
+       case GREP_PATTERN_BODY:
+               fprintf(stderr, "<body>"); break;
+       }
+       switch (p->token) {
+       default: break;
+       case GREP_PATTERN_HEAD:
+       case GREP_PATTERN_BODY:
+       case GREP_PATTERN:
+               fprintf(stderr, "%.*s", (int)p->patternlen, p->pattern);
+               break;
+       }
+       fputc('\n', stderr);
+}
+
+static void dump_grep_expression_1(struct grep_expr *x, int in)
+{
+       indent(in);
+       switch (x->node) {
+       case GREP_NODE_TRUE:
+               fprintf(stderr, "true\n");
+               break;
+       case GREP_NODE_ATOM:
+               dump_grep_pat(x->u.atom);
+               break;
+       case GREP_NODE_NOT:
+               fprintf(stderr, "(not\n");
+               dump_grep_expression_1(x->u.unary, in+1);
+               indent(in);
+               fprintf(stderr, ")\n");
+               break;
+       case GREP_NODE_AND:
+               fprintf(stderr, "(and\n");
+               dump_grep_expression_1(x->u.binary.left, in+1);
+               dump_grep_expression_1(x->u.binary.right, in+1);
+               indent(in);
+               fprintf(stderr, ")\n");
+               break;
+       case GREP_NODE_OR:
+               fprintf(stderr, "(or\n");
+               dump_grep_expression_1(x->u.binary.left, in+1);
+               dump_grep_expression_1(x->u.binary.right, in+1);
+               indent(in);
+               fprintf(stderr, ")\n");
+               break;
+       }
+}
+
+void dump_grep_expression(struct grep_opt *opt)
+{
+       struct grep_expr *x = opt->pattern_expression;
+
+       if (opt->all_match)
+               fprintf(stderr, "[all-match]\n");
+       dump_grep_expression_1(x, 0);
+       fflush(NULL);
+}
+
 static struct grep_expr *grep_true_expr(void)
 {
        struct grep_expr *z = xcalloc(1, sizeof(*z));
 static struct grep_expr *grep_true_expr(void)
 {
        struct grep_expr *z = xcalloc(1, sizeof(*z));
@@ -395,7 +476,7 @@ static struct grep_expr *prep_header_patterns(struct grep_opt *opt)
        return header_expr;
 }
 
        return header_expr;
 }
 
-void compile_grep_patterns(struct grep_opt *opt)
+static void compile_grep_patterns_real(struct grep_opt *opt)
 {
        struct grep_pat *p;
        struct grep_expr *header_expr = prep_header_patterns(opt);
 {
        struct grep_pat *p;
        struct grep_expr *header_expr = prep_header_patterns(opt);
@@ -415,7 +496,7 @@ void compile_grep_patterns(struct grep_opt *opt)
 
        if (opt->all_match || header_expr)
                opt->extended = 1;
 
        if (opt->all_match || header_expr)
                opt->extended = 1;
-       else if (!opt->extended)
+       else if (!opt->extended && !opt->debug)
                return;
 
        p = opt->pattern_list;
                return;
 
        p = opt->pattern_list;
@@ -435,6 +516,13 @@ void compile_grep_patterns(struct grep_opt *opt)
        opt->all_match = 1;
 }
 
        opt->all_match = 1;
 }
 
+void compile_grep_patterns(struct grep_opt *opt)
+{
+       compile_grep_patterns_real(opt);
+       if (opt->debug)
+               dump_grep_expression(opt);
+}
+
 static void free_pattern_expr(struct grep_expr *x)
 {
        switch (x->node) {
 static void free_pattern_expr(struct grep_expr *x)
 {
        switch (x->node) {
diff --git a/grep.h b/grep.h
index ed7de6bec8e604a7b3dcb9f9a19053696b7c3fdf..bf5be5ada4bc84a814cf0fe41b613bebd6ac7ce4 100644 (file)
--- a/grep.h
+++ b/grep.h
@@ -90,6 +90,7 @@ struct grep_opt {
        int word_regexp;
        int fixed;
        int all_match;
        int word_regexp;
        int fixed;
        int all_match;
+       int debug;
 #define GREP_BINARY_DEFAULT    0
 #define GREP_BINARY_NOMATCH    1
 #define GREP_BINARY_TEXT       2
 #define GREP_BINARY_DEFAULT    0
 #define GREP_BINARY_NOMATCH    1
 #define GREP_BINARY_TEXT       2
diff --git a/revision.c b/revision.c
index 9a0d9c7de2af43c7ae082a892a2a9cfd6f4b4761..90376e8e19878b8cc67c2f18a92cf05615b90bd8 100644 (file)
--- a/revision.c
+++ b/revision.c
@@ -1578,6 +1578,8 @@ static int handle_revision_opt(struct rev_info *revs, int argc, const char **arg
        } else if ((argcount = parse_long_opt("grep", argv, &optarg))) {
                add_message_grep(revs, optarg);
                return argcount;
        } else if ((argcount = parse_long_opt("grep", argv, &optarg))) {
                add_message_grep(revs, optarg);
                return argcount;
+       } else if (!strcmp(arg, "--grep-debug")) {
+               revs->grep_filter.debug = 1;
        } else if (!strcmp(arg, "--extended-regexp") || !strcmp(arg, "-E")) {
                revs->grep_filter.regflags |= REG_EXTENDED;
        } else if (!strcmp(arg, "--regexp-ignore-case") || !strcmp(arg, "-i")) {
        } else if (!strcmp(arg, "--extended-regexp") || !strcmp(arg, "-E")) {
                revs->grep_filter.regflags |= REG_EXTENDED;
        } else if (!strcmp(arg, "--regexp-ignore-case") || !strcmp(arg, "-i")) {