From 4114c93af398d7aecb5eb253f90d9b4cc0785643 Mon Sep 17 00:00:00 2001
From: Assaf Gordon <assafgordon@gmail.com>
Date: Wed, 6 Mar 2013 15:53:16 -0500
Subject: csplit: add the --suppress-matched option

With --suppress-matched, the lines that match the pattern will not be
printed in the output files.  I.E. the first line from the second
and subsequent splits will be suppressed.

* src/csplit.c: process_regexp(),process_line_count(): Don't output the
matched lines.  Since csplit includes "up to but not including" matched
lines in each split, the first line (in the next group) is the matched
line - so just skip it.
main(): Handle new option.
usage(): Mention new option.
* doc/coreutils.texi (csplit invocation): Mention new option, examples.
* tests/misc/csplit-suppress-matched.pl: New test script.
* tests/local.mk: Reference the new test.
* NEWS: Mention new feature.
---
 src/csplit.c | 34 ++++++++++++++++++++++++++++++++--
 1 file changed, 32 insertions(+), 2 deletions(-)

(limited to 'src')

diff --git a/src/csplit.c b/src/csplit.c
index 22f3ad4b1..7a36e6736 100644
--- a/src/csplit.c
+++ b/src/csplit.c
@@ -166,6 +166,9 @@ static bool volatile remove_files;
 /* If true, remove all output files which have a zero length. */
 static bool elide_empty_files;
 
+/* If true, suppress the lines that match the PATTERN */
+static bool suppress_matched;
+
 /* The compiled pattern arguments, which determine how to split
    the input file. */
 static struct control *controls;
@@ -176,6 +179,13 @@ static size_t control_used;
 /* The set of signals that are caught.  */
 static sigset_t caught_signals;
 
+/* For long options that have no equivalent short option, use a
+   non-character as a pseudo short option, starting with CHAR_MAX + 1.  */
+enum
+{
+  SUPPRESS_MATCHED_OPTION = CHAR_MAX + 1
+};
+
 static struct option const longopts[] =
 {
   {"digits", required_argument, NULL, 'n'},
@@ -185,6 +195,7 @@ static struct option const longopts[] =
   {"elide-empty-files", no_argument, NULL, 'z'},
   {"prefix", required_argument, NULL, 'f'},
   {"suffix-format", required_argument, NULL, 'b'},
+  {"suppress-matched", no_argument, NULL, SUPPRESS_MATCHED_OPTION},
   {GETOPT_HELP_OPTION_DECL},
   {GETOPT_VERSION_OPTION_DECL},
   {NULL, 0, NULL, 0}
@@ -721,8 +732,13 @@ process_line_count (const struct control *p, uintmax_t repetition)
 
   create_output_file ();
 
-  linenum = get_first_line_in_buffer ();
+  /* Ensure that the line number specified is not 1 greater than
+     the number of lines in the file.
+     When suppressing matched lines, check before the loop. */
+  if (no_more_lines () && suppress_matched)
+    handle_line_error (p, repetition);
 
+  linenum = get_first_line_in_buffer ();
   while (linenum++ < last_line_to_save)
     {
       line = remove_line ();
@@ -733,9 +749,12 @@ process_line_count (const struct control *p, uintmax_t repetition)
 
   close_output_file ();
 
+  if (suppress_matched)
+    line = remove_line ();
+
   /* Ensure that the line number specified is not 1 greater than
      the number of lines in the file. */
-  if (no_more_lines ())
+  if (no_more_lines () && !suppress_matched)
     handle_line_error (p, repetition);
 }
 
@@ -778,6 +797,9 @@ process_regexp (struct control *p, uintmax_t repetition)
   if (!ignore)
     create_output_file ();
 
+  if (suppress_matched && current_line > 0)
+    line = remove_line ();
+
   /* If there is no offset for the regular expression, or
      it is positive, then it is not necessary to buffer the lines. */
 
@@ -1324,6 +1346,7 @@ main (int argc, char **argv)
   control_used = 0;
   suppress_count = false;
   remove_files = true;
+  suppress_matched = false;
   prefix = DEFAULT_PREFIX;
 
   while ((optc = getopt_long (argc, argv, "f:b:kn:sqz", longopts, NULL)) != -1)
@@ -1357,6 +1380,10 @@ main (int argc, char **argv)
         elide_empty_files = true;
         break;
 
+      case SUPPRESS_MATCHED_OPTION:
+        suppress_matched = true;
+        break;
+
       case_GETOPT_HELP_CHAR;
 
       case_GETOPT_VERSION_CHAR (PROGRAM_NAME, AUTHORS);
@@ -1463,6 +1490,9 @@ and output byte counts of each piece to standard output.\n\
   -b, --suffix-format=FORMAT  use sprintf FORMAT instead of %02d\n\
   -f, --prefix=PREFIX        use PREFIX instead of 'xx'\n\
   -k, --keep-files           do not remove output files on errors\n\
+"), stdout);
+      fputs (_("\
+  -m, --suppress-matched     suppress the lines matching PATTERN\n\
 "), stdout);
       fputs (_("\
   -n, --digits=DIGITS        use specified number of digits instead of 2\n\
-- 
cgit v1.2.3-54-g00ecf