[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]
[PATCH 2/2] cut: fix -f to work with the -d$'\n' edge case
From: |
Pádraig Brady |
Subject: |
[PATCH 2/2] cut: fix -f to work with the -d$'\n' edge case |
Date: |
Tue, 22 Jan 2013 01:47:51 +0000 |
* src/cut.c (cut_fields): Handle the edge case where '\n' is
the delimiter, which could be used for example to suppress
the last line if it doesn't contain a '\n'.
* test/misc/cut.pl: Add tests for this edge case.
---
src/cut.c | 14 ++++++++------
tests/misc/cut.pl | 10 ++++++++++
2 files changed, 18 insertions(+), 6 deletions(-)
diff --git a/src/cut.c b/src/cut.c
index 88a2f1b..c48eef7 100644
--- a/src/cut.c
+++ b/src/cut.c
@@ -618,6 +618,7 @@ cut_fields (FILE *stream)
{
ssize_t len;
size_t n_bytes;
+ bool got_line;
len = getndelim2 (&field_1_buffer, &field_1_bufsize, 0,
GETNLINE_NO_LIMIT, delim, '\n', stream);
@@ -634,13 +635,14 @@ cut_fields (FILE *stream)
assert (n_bytes != 0);
c = 0;
+ got_line = field_1_buffer[n_bytes - 1] == '\n';
/* If the first field extends to the end of line (it is not
delimited) and we are printing all non-delimited lines,
print this one. */
- if (to_uchar (field_1_buffer[n_bytes - 1]) != delim)
+ if (to_uchar (field_1_buffer[n_bytes - 1]) != delim || got_line)
{
- if (suppress_non_delimited)
+ if (suppress_non_delimited && !(got_line && delim == '\n'))
{
/* Empty. */
}
@@ -648,7 +650,7 @@ cut_fields (FILE *stream)
{
fwrite (field_1_buffer, sizeof (char), n_bytes, stdout);
/* Make sure the output line is newline terminated. */
- if (field_1_buffer[n_bytes - 1] != '\n')
+ if (! got_line)
putchar ('\n');
c = '\n';
}
@@ -688,9 +690,7 @@ cut_fields (FILE *stream)
}
}
- if (c == delim)
- ++field_idx;
- else if (c == '\n' || c == EOF)
+ if (c == '\n' || c == EOF)
{
if (found_any_selected_field
|| !(suppress_non_delimited && field_idx == 1))
@@ -703,6 +703,8 @@ cut_fields (FILE *stream)
field_idx = 1;
found_any_selected_field = false;
}
+ else if (c == delim)
+ field_idx++;
}
}
diff --git a/tests/misc/cut.pl b/tests/misc/cut.pl
index 3ce09bb..874c169 100755
--- a/tests/misc/cut.pl
+++ b/tests/misc/cut.pl
@@ -143,6 +143,16 @@ my @Tests =
['newline-11', '-s', '-d:', '-f1,2', {IN=>"a:1\nb:2\n"},
{OUT=>"a:1\nb:2\n"}],
['newline-12', '-s', '-d:', '-f1', {IN=>"a:1\nb:"}, {OUT=>"a\nb\n"}],
['newline-13', '-d:', '-f1-', {IN=>"a1:\n:"}, {OUT=>"a1:\n:\n"}],
+ # newline processing for fields when -d == '\n'
+ ['newline-14', "-d'\n'", '-f1', {IN=>"a:1\nb:"}, {OUT=>"a:1\nb:\n"}],
+ ['newline-15', '-s', "-d'\n'", '-f1', {IN=>"a:1\nb:"}, {OUT=>"a:1\n"}],
+ ['newline-16', '-s', "-d'\n'", '-f2', {IN=>"\nb"}, {OUT=>""}],
+ ['newline-17', '-s', "-d'\n'", '-f1', {IN=>"\nb"}, {OUT=>"\n"}],
+ ['newline-18', "-d'\n'", '-f2', {IN=>"\nb"}, {OUT=>"\nb\n"}],
+ ['newline-19', "-d'\n'", '-f1', {IN=>"\nb"}, {OUT=>"\nb\n"}],
+ ['newline-20', '-s', "-d'\n'", '-f1-', {IN=>"\n"}, {OUT=>"\n"}],
+ ['newline-21', '-s', "-d'\n'", '-f1-', {IN=>"\nb"}, {OUT=>"\n"}],
+ ['newline-22', "-d'\n'", '-f1-', {IN=>"\nb"}, {OUT=>"\nb\n"}],
# New functionality:
['out-delim1', '-c1-3,5-', '--output-d=:', {IN=>"abcdefg\n"},
--
1.7.6.4