[PATCH] grep-dctrl: add new mode for exact package name matching
Stefano Zacchiroli
zack at upsilon.cc
Thu Apr 16 11:20:08 UTC 2009
Add to grep-dctrl the new matching mode --whole-pkg / -w. It behaves
as -e (extended regexp matching), but matches over exact package
names, thus avoiding sub-package name matching.
Closes: #383921
Signed-off-by: Stefano Zacchiroli <zack at debian.org>
---
debian/changelog | 5 +++++
grep-dctrl/grep-dctrl.c | 10 ++++++++++
lib/predicate.c | 18 ++++++++++++++++--
lib/predicate.h | 2 ++
man/grep-dctrl.1.cp | 6 ++++++
5 files changed, 39 insertions(+), 2 deletions(-)
diff --git a/debian/changelog b/debian/changelog
index bc607f2..a549164 100644
--- a/debian/changelog
+++ b/debian/changelog
@@ -16,6 +16,11 @@ dctrl-tools (2.14) UNRELEASED; urgency=3Dlow
Closes: #506138 (Segfault when calling with wrong order of parameter=
s)
Reported by Marco T=FAlio Gontijo e Silva <marcot at holoscopio.com>.
=20
+ [ Stefano Zacchiroli ]
+ * grep-dctrl: add new matching mode --whole-pkg/-w: it is an improved =
-e
+ matching exact package names, i.e., no sub-string matching on packag=
e
+ names. Closes: #383921
+
-- Antti-Juhani Kaijanaho <ajk at debian.org> Tue, 06 Jan 2009 20:20:17 +=
0200
=20
dctrl-tools (2.13.0) unstable; urgency=3Dlow
diff --git a/grep-dctrl/grep-dctrl.c b/grep-dctrl/grep-dctrl.c
index 70a1fd1..7eab847 100644
--- a/grep-dctrl/grep-dctrl.c
+++ b/grep-dctrl/grep-dctrl.c
@@ -139,6 +139,7 @@ static struct argp_option options[] =3D {
{ "mmap", OPT_MMAP, 0, 0, N_("Attempt mmapping inp=
ut files") },
{ "ignore-parse-errors", OPT_IGN_ERRS, 0, 0, N_("Ignore parse errors"=
) },
{ "pattern", OPT_PATTERN, N_("PATTERN"), 0, N_("Specify t=
he pattern to search for") },
+ { "whole-pkg", 'w', 0, 0, N_("Do (eregex) matching =
on whole package names") },
{ 0 }
};
=20
@@ -235,6 +236,7 @@ struct atom * clone_atom(struct arguments * args)
rv->field_inx =3D atom->field_inx;
rv->mode =3D atom->mode;
rv->ignore_case =3D atom->ignore_case;
+ rv->whole_pkg =3D atom->whole_pkg;
rv->pat =3D atom->pat;
rv->patlen =3D atom->patlen;
struct atom_code * ac =3D args->atom_code[oa];
@@ -357,6 +359,7 @@ static struct atom * enter_atom(struct arguments * ar=
gs)
rv->field_inx =3D -1;
rv->mode =3D M_SUBSTR;
rv->ignore_case =3D 0;
+ rv->whole_pkg =3D 0;
rv->pat =3D 0;
rv->patlen =3D 0;
return rv;
@@ -551,6 +554,12 @@ static error_t parse_opt (int key, char * arg, struc=
t argp_state * state)
if (atom->pat =3D=3D 0) fatal_enomem(0);
strcpy((char*)atom->pat, arg);
break;
+ case 'w':
+ debug_message("parse_opt: whole-pkg", 0);
+ atom =3D ENTER_ATOM;
+ atom->whole_pkg =3D 1;
+ set_mode(M_EREGEX);
+ break;
case ARGP_KEY_ARG:
debug_message("parse_opt: argument", 0);
redo:
@@ -620,6 +629,7 @@ static void dump_args(struct arguments * args)
printf("atoms[%zi].field_name =3D %s\n", i, args->p.atoms[i].field_nam=
e);
printf("atoms[%zi].mode =3D %i\n", i, args->p.atoms[i].mode);
printf("atoms[%zi].ignore_case =3D %i\n", i, args->p.atoms[i].ignore_c=
ase);
+ printf("atoms[%zi].whole_pkg =3D %i\n", i, args->p.atoms[i].whole_pkg)=
;
printf("atoms[%zi].pat =3D %s\n", i, args->p.atoms[i].pat);
}
printf("proglen =3D %zi\n", args->p.proglen);
diff --git a/lib/predicate.c b/lib/predicate.c
index 2657457..02617d4 100644
--- a/lib/predicate.c
+++ b/lib/predicate.c
@@ -27,6 +27,9 @@
#include "strutil.h"
#include "version.h"
=20
+#define RE_PKG_BEGIN "(^| )"
+#define RE_PKG_END "([, \\(]|$)"
+
void init_predicate(struct predicate * p)
{
p->num_atoms =3D 0;
@@ -46,6 +49,9 @@ void addinsn(struct predicate * p, int insn)
void predicate_finish_atom(struct predicate * p)
{
struct atom * atom =3D get_current_atom(p);
+ char * regex_pat =3D NULL;
+ int regex_patlen =3D atom->patlen + strlen(RE_PKG_BEGIN)
+ + strlen(RE_PKG_END) + 1;
debug_message("predicate_finish_atom", 0);
if (atom->field_name !=3D 0) {
char * repl =3D strchr(atom->field_name, ':');
@@ -59,12 +65,20 @@ void predicate_finish_atom(struct predicate * p)
}
=20
if (atom->mode =3D=3D M_REGEX || atom->mode =3D=3D M_EREGEX) {
+ regex_pat =3D calloc(1, regex_patlen); /* rely on mem 0-ing */
+ if (regex_pat =3D=3D 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 =3D regcomp(&atom->regex, atom->pat,
+ debug_message(regex_pat, 0);
+ int rerr =3D regcomp(&atom->regex, regex_pat,
(atom->mode =3D=3D M_EREGEX ? REG_EXTENDED : 0)
| REG_NOSUB
| (atom->ignore_case ? REG_ICASE : 0));
+ free(regex_pat);
if (rerr !=3D 0) {
char * s;
s =3D 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;
};
=20
/* A predicate is represented as a set of atomic predicates and a
diff --git a/man/grep-dctrl.1.cp b/man/grep-dctrl.1.cp
index 36741e7..6b47c71 100644
--- a/man/grep-dctrl.1.cp
+++ b/man/grep-dctrl.1.cp
@@ -137,6 +137,12 @@ Ignore case when looking for a match in the current =
simple filter.
.IP "\-X, \-\-exact\-match"
Do an exact match (as opposed to a substring match) in the current
simple filter.
+.IP "\-w, \-\-whole\-pkg"
+Do an extended regular expression match on whole package names,
+assuming the syntax of inter-package relationship fields such as
+Depends, Recommends, ... When this flag is given you should not worry
+about sub-package names such as "libpcre3" also matching
+"libpcre3-dev". This flag implies (and is incompatible with) \-e.
.IP "\-\-eq"
Do an equality comparison under the Debian version number system. If
the pattern or the field to be searched in is not a valid Debian
--=20
1.6.2.3
--DocE+STaALJfprDB--
More information about the Dctrl-tools-devel
mailing list