Hi,
I got no comments/enquiries on my previous descriptions?
Anyway here's the patch for uniq to implement the following
functionality:
>echo -ne "1\n2\n2\n3\n3\n" | uniq -Dl
2
2
3
3
>
The patch is against the 2.0 release.
To apply: cd textutils-2.0; patch -p1 <uniq_delim.patch
3 files will be patched (uniq.c, Test.pm & Textutils.texi).
The only thing I didn't update were the various language files.
Padraig.
diff -arc textutils-2.0/doc/textutils.texi textutils-pb/doc/textutils.texi
*** textutils-2.0/doc/textutils.texi Sat Jul 31 10:03:30 1999
--- textutils-pb/doc/textutils.texi Sun Apr 22 00:07:39 2001
***************
*** 2508,2513 ****
--- 2508,2524 ----
This is a GNU extension.
@c FIXME: give an example showing *how* it's useful
+ @item -l
+ @itemx --delim-repeated
+ @opindex -l
+ @opindex --delim-repeated
+ @cindex delimit duplicate lines, outputting
+ Print a blank line between groups of duplicate lines.
+ This option is only valid in conjunction with -D (--all-repeated).
+ It's main use is to simplify automated processing of uniq output,
+ but it is a useful aid to people using uniq interactively also.
+ This is a GNU extension.
+
@item -u
@itemx --unique
@opindex -u
diff -arc textutils-2.0/src/uniq.c textutils-pb/src/uniq.c
*** textutils-2.0/src/uniq.c Sun Jul 4 11:02:54 1999
--- textutils-pb/src/uniq.c Sat Apr 21 23:47:15 2001
***************
*** 74,84 ****
--- 74,88 ----
/* If nonzero, ignore case when comparing. */
static int ignore_case;
+ /* If nonzero, delimit groups of duplicate lines with \n */
+ static int delim_repeated;
+
static struct option const longopts[] =
{
{"count", no_argument, NULL, 'c'},
{"repeated", no_argument, NULL, 'd'},
{"all-repeated", no_argument, NULL, 'D'},
+ {"delim-repeated", no_argument, NULL, 'l'},
{"ignore-case", no_argument, NULL, 'i'},
{"unique", no_argument, NULL, 'u'},
{"skip-fields", required_argument, NULL, 'f'},
***************
*** 108,113 ****
--- 112,118 ----
-c, --count prefix lines by the number of occurrences\n\
-d, --repeated only print duplicate lines\n\
-D, --all-repeated print all duplicate lines\n\
+ -l, --delim-repeated delimit \"--all-repeated\" groups with blank lines\n\
-f, --skip-fields=N avoid comparing the first N fields\n\
-i, --ignore-case ignore differences in case when comparing\n\
-s, --skip-chars=N avoid comparing the first N characters\n\
***************
*** 214,219 ****
--- 219,225 ----
char *prevfield, *thisfield;
size_t prevlen, thislen;
int match_count = 0;
+ int first_delimiter = 1;
if (STREQ (infile, "-"))
istream = stdin;
***************
*** 251,256 ****
--- 257,271 ----
if (match)
++match_count;
+
+ if (delim_repeated)
+ if (!match && mode == output_all_repeated)
+ {
+ if (match_count) /* a previous match */
+ first_delimiter = 0;
+ }
+ else if (match_count == 1 && !first_delimiter)
+ fwrite ("\n", sizeof (char), 1, ostream);
if (!match || mode == output_all_repeated)
{
***************
*** 295,301 ****
mode = output_all;
countmode = count_none;
! while ((optc = getopt_long (argc, argv, "0123456789cdDf:is:uw:", longopts,
NULL)) != -1)
{
switch (optc)
--- 310,316 ----
mode = output_all;
countmode = count_none;
! while ((optc = getopt_long (argc, argv, "0123456789cdDlf:is:uw:", longopts,
NULL)) != -1)
{
switch (optc)
***************
*** 328,333 ****
--- 343,352 ----
mode = output_all_repeated;
break;
+ case 'l':
+ delim_repeated = 1;
+ break;
+
case 'f': /* Like '-#'. */
{
long int tmp_long;
***************
*** 414,419 ****
--- 433,445 ----
{
error (0, 0,
_("printing all duplicated lines and repeat counts is meaningless"));
+ usage (1);
+ }
+
+ if (delim_repeated && mode != output_all_repeated)
+ {
+ error (0, 0,
+ _("Grouping lines while not printing all duplicated lines is meaningless"));
usage (1);
}
diff -arc textutils-2.0/tests/uniq/Test.pm textutils-pb/tests/uniq/Test.pm
*** textutils-2.0/tests/uniq/Test.pm Sat Jan 9 16:14:38 1999
--- textutils-pb/tests/uniq/Test.pm Sat Apr 21 23:46:44 2001
***************
*** 70,75 ****
--- 70,80 ----
['110', '-D', "a\na\n", "a\na\n", 0],
['111', '-D -w1',"a a\na b\n", "a a\na b\n", 0],
['112', '-D -c', "a a\na b\n", "", 1],
+ # Check the local -l (--delim-repeated) option
+ ['113', '-Dl', "a\na\n", "a\na\n", 0],
+ ['114', '-Dl',"a\na\nb\nc\nc\n", "a\na\n\nc\nc\n", 0],
+ ['115', '-Dl',"a\na\nb\nb\nc\n", "a\na\n\nb\nb\n", 0],
+ ['116', '-l', "a\na\n", "", 1],
);
sub test_vector
