grep: option to use GNU regex matching instead of POSIX one.

 This fixes problems with NULs in files being scanned, but
 costs +800 bytes. The same can be done to sed (TODO).

2 files changed, 43 insertions, 2 deletions

diff --git a/libbb/get_line_from_file.c b/libbb/get_line_from_file.c
index 56761f941..968d7572d 100644
--- a/libbb/get_line_from_file.c
+++ b/libbb/get_line_from_file.c
@@ -9,6 +9,10 @@
  * Licensed under GPLv2 or later, see file LICENSE in this tarball for details.
  */
 
+/* for getline() [GNUism] */
+#ifndef _GNU_SOURCE
+#define _GNU_SOURCE 1
+#endif
 #include "libbb.h"
 
 /* This function reads an entire line from a text file, up to a newline
@@ -55,7 +59,6 @@ char* FAST_FUNC xmalloc_fgets(FILE *file)
 
         return bb_get_chunk_from_file(file, &i);
 }
-
 /* Get line.  Remove trailing \n */
 char* FAST_FUNC xmalloc_fgetline(FILE *file)
 {
@@ -69,6 +72,44 @@ char* FAST_FUNC xmalloc_fgetline(FILE *file)
 }
 
 #if 0
+
+/* GNUism getline() should be faster (not tested) than a loop with fgetc */
+
+/* Get line, including trailing \n if any */
+char* FAST_FUNC xmalloc_fgets(FILE *file)
+{
+        char *res_buf = NULL;
+        size_t res_sz;
+
+        if (getline(&res_buf, &res_sz, file) == -1) {
+                free(res_buf); /* uclibc allocates a buffer even on EOF. WTF? */
+                res_buf = NULL;
+        }
+//TODO: trimming to res_sz?
+        return res_buf;
+}
+/* Get line.  Remove trailing \n */
+char* FAST_FUNC xmalloc_fgetline(FILE *file)
+{
+        char *res_buf = NULL;
+        size_t res_sz;
+
+        res_sz = getline(&res_buf, &res_sz, file);
+
+        if ((ssize_t)res_sz != -1) {
+                if (res_buf[res_sz - 1] == '\n')
+                        res_buf[--res_sz] = '\0';
+//TODO: trimming to res_sz?
+        } else {
+                free(res_buf); /* uclibc allocates a buffer even on EOF. WTF? */
+                res_buf = NULL;
+        }
+        return res_buf;
+}
+
+#endif
+
+#if 0
 /* Faster routines (~twice as fast). +170 bytes. Unused as of 2008-07.
  *
  * NB: they stop at NUL byte too.
diff --git a/libbb/xregcomp.c b/libbb/xregcomp.c
index abfa35ff1..61efb5bc6 100644
--- a/libbb/xregcomp.c
+++ b/libbb/xregcomp.c
@@ -27,6 +27,6 @@ void FAST_FUNC xregcomp(regex_t *preg, const char *regex, int cflags)
 {
         char *errmsg = regcomp_or_errmsg(preg, regex, cflags);
         if (errmsg) {
-                bb_error_msg_and_die("xregcomp: %s", errmsg);
+                bb_error_msg_and_die("bad regex '%s': %s", regex, errmsg);
         }
 }