[PATCH] add '--whole-pkg' to match (eregex) on whole package names

[Stefano Zacchiroli]

Using this flag given extended regex will not match substring of
package names in fields expressing inter-package relationships (e.g.,
Depends, Recommends, ...).

Passing '--whole-pkg' implies '-e'.

(Closes: #476861) actually, proposed fix for ...
---
 grep-dctrl/grep-dctrl.c |   13 ++++++++++++-
 lib/predicate.c         |   17 +++++++++++++++--
 lib/predicate.h         |    2 ++
 3 files changed, 29 insertions(+), 3 deletions(-)

diff --git a/grep-dctrl/grep-dctrl.c b/grep-dctrl/grep-dctrl.c
index 70a1fd1..d5fb5f5 100644
--- a/grep-dctrl/grep-dctrl.c
+++ b/grep-dctrl/grep-dctrl.c
@@ -59,7 +59,8 @@ enum {
         OPT_GE,
         OPT_MMAP,
         OPT_IGN_ERRS,
-        OPT_PATTERN
+        OPT_PATTERN,
+        OPT_WHOLE_PKG
 };
 
 #undef BANNER
@@ -139,6 +140,7 @@ static struct argp_option options[] = {
 	{ "mmap",           OPT_MMAP, 0,            0, N_("Attempt mmapping input files") },
 	{ "ignore-parse-errors", OPT_IGN_ERRS, 0,   0, N_("Ignore parse errors") },
         { "pattern",        OPT_PATTERN, N_("PATTERN"), 0, N_("Specify the pattern to search for") },
+	{ "whole-pkg",	    OPT_WHOLE_PKG, 0,	    0, N_("Do (eregex) matching on whole package names") },
 	{ 0 }
 };
 
@@ -235,6 +237,7 @@ struct atom * clone_atom(struct arguments * args)
 	rv->field_inx = atom->field_inx;
 	rv->mode = atom->mode;
 	rv->ignore_case = atom->ignore_case;
+	rv->whole_pkg = atom->whole_pkg;
 	rv->pat = atom->pat;
 	rv->patlen = atom->patlen;
 	struct atom_code * ac = args->atom_code[oa];
@@ -357,6 +360,7 @@ static struct atom * enter_atom(struct arguments * args)
 	rv->field_inx = -1;
 	rv->mode = M_SUBSTR;
 	rv->ignore_case = 0;
+	rv->whole_pkg = 0;
 	rv->pat = 0;
 	rv->patlen = 0;
 	return rv;
@@ -551,6 +555,12 @@ static error_t parse_opt (int key, char * arg, struct argp_state * state)
 		if (atom->pat == 0) fatal_enomem(0);
 		strcpy((char*)atom->pat, arg);
 		break;
+	case OPT_WHOLE_PKG:
+		debug_message("parse_opt: whole-pkg", 0);
+		atom = ENTER_ATOM;
+		atom->whole_pkg = 1;
+		set_mode(M_EREGEX);
+		break;
 	case ARGP_KEY_ARG:
 		debug_message("parse_opt: argument", 0);
 	redo:
@@ -620,6 +630,7 @@ static void dump_args(struct arguments * args)
 		printf("atoms[%zi].field_name = %s\n", i, args->p.atoms[i].field_name);
 		printf("atoms[%zi].mode = %i\n", i, args->p.atoms[i].mode);
 		printf("atoms[%zi].ignore_case = %i\n", i, args->p.atoms[i].ignore_case);
+		printf("atoms[%zi].whole_pkg = %i\n", i, args->p.atoms[i].whole_pkg);
 		printf("atoms[%zi].pat = %s\n", i, args->p.atoms[i].pat);
 	}
 	printf("proglen = %zi\n", args->p.proglen);
diff --git a/lib/predicate.c b/lib/predicate.c
index 2657457..14f8500 100644
--- a/lib/predicate.c
+++ b/lib/predicate.c
@@ -27,6 +27,9 @@
 #include "strutil.h"
 #include "version.h"
 
+#define RE_PKG_BEGIN	"(^| )"
+#define RE_PKG_END	"([, \\(]|$)"
+
 void init_predicate(struct predicate * p)
 {
 	p->num_atoms = 0;
@@ -46,6 +49,8 @@ void addinsn(struct predicate * p, int insn)
 void predicate_finish_atom(struct predicate * p)
 {
 	struct atom * atom =  get_current_atom(p);
+	char * regex_pat = NULL;
+	int regex_patlen = atom->patlen + 30;
 	debug_message("predicate_finish_atom", 0);
 	if (atom->field_name != 0) {
                 char * repl = strchr(atom->field_name, ':');
@@ -59,12 +64,20 @@ void predicate_finish_atom(struct predicate * p)
 	}
 
 	if (atom->mode == M_REGEX || atom->mode == M_EREGEX) {
+		regex_pat = calloc(1, regex_patlen);
+		if (regex_pat == 0)  fatal_enomem(0);
+		if (atom->whole_pkg)
+			strncat(regex_pat, RE_PKG_BEGIN, strlen(RE_PKG_BEGIN));
+		strncat(regex_pat, atom->pat, atom->patlen);
+		if (atom->whole_pkg)
+			strncat(regex_pat, RE_PKG_END, strlen(RE_PKG_END));
 		debug_message("compiling:", 0);
-		debug_message(atom->pat, 0);
-		int rerr = regcomp(&atom->regex, atom->pat,
+		debug_message(regex_pat, 0);
+		int rerr = regcomp(&atom->regex, regex_pat,
 				   (atom->mode == M_EREGEX ? REG_EXTENDED : 0)
 				   | REG_NOSUB
 				   | (atom->ignore_case ? REG_ICASE : 0));
+		free(regex_pat);
 		if (rerr != 0) {
 			char * s;
 			s = get_regerror(rerr, &atom->regex);
diff --git a/lib/predicate.h b/lib/predicate.h
index 6720ed7..d58b71f 100644
--- a/lib/predicate.h
+++ b/lib/predicate.h
@@ -66,6 +66,8 @@ struct atom {
 	/* A compiled version of pat; valid only when mode is M_REGEX
 	 * or M_EREGEX.  */
 	regex_t regex;
+	/* Flag: (extended) regex should match whole package names */
+	unsigned whole_pkg;
 };
 
 /* A predicate is represented as a set of atomic predicates and a
-- 
1.5.6.5


--pWyiEgJYm5f9v55/
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment; filename="0002-document-whole-pkg-in-grep-dctrl-manpage.patch"