mirror of
https://git.savannah.gnu.org/git/coreutils.git
synced 2026-11-19 03:33:43 +03:00
join,sort,uniq: with -z, treat '\n' as a field separator
* NEWS: Mention the change in behavior.
* doc/coreutils.texi (newlineFieldSeparator): A new description,
referenced from ({join,sort,uniq} invocation).
* src/system.h (field_sep): A new inline function to determine
if a character is a field separator.
* src/join.c (usage): s/whitespace/blank/ to be more accurate
wrt which characters are field separators.
(xfields): s/isblank/field_sep/.
* src/sort.c (inittables): Likewise.
* src/uniq.c (find_field): Likewise.
* tests/misc/join.pl: Adjust -z test, and add a test/example
for processing the whole record with field processing.
* tests/misc/sort.pl: Add -z test cases, including case with '\n'.
* tests/misc/uniq.pl: Add -z -f test case with \n.
This commit is contained in:
1 parent
d44ae88199
commit
b2eadd109c
9 files changed
+34
-11
No files matched your search
@@ -64,6 +64,8 @@ GNU coreutils NEWS -*- outline -*-
|
||||
ls now quotes file names unambiguously and appropriate for use in a shell,
|
||||
when outputting to a terminal.
|
||||
|
||||
join, sort, uniq with --zero-terminated, now treat '\n' as a field delimiter.
|
||||
|
||||
** Improvements
|
||||
|
||||
All utilities now quote user supplied arguments in error strings,
|
||||
|
||||
@@ -4493,6 +4493,9 @@ numeric string when checking for uniqueness, whereas @code{sort -n |
|
||||
uniq} inspects the entire line. @xref{uniq invocation}.
|
||||
|
||||
@optZeroTerminated
|
||||
@macro newlineFieldSeparator
|
||||
Note with @option{-z} the newline character is treated as a field separator.
|
||||
@end macro
|
||||
|
||||
@end table
|
||||
|
||||
@@ -5034,6 +5037,7 @@ fields and characters). By default the entire rest of the lines are
|
||||
compared.
|
||||
|
||||
@optZeroTerminated
|
||||
@newlineFieldSeparator
|
||||
|
||||
@end table
|
||||
|
||||
@@ -6157,6 +6161,7 @@ Print a line for each unpairable line in file @var{file-number}
|
||||
(either @samp{1} or @samp{2}), instead of the normal output.
|
||||
|
||||
@optZeroTerminated
|
||||
@newlineFieldSeparator
|
||||
|
||||
@end table
|
||||
|
||||
|
||||
+4
-4
@@ -194,7 +194,7 @@ Usage: %s [OPTION]... FILE1 FILE2\n\
|
||||
program_name);
|
||||
fputs (_("\
|
||||
For each pair of input lines with identical join fields, write a line to\n\
|
||||
standard output. The default join field is the first, delimited by whitespace.\
|
||||
standard output. The default join field is the first, delimited by blanks.\
|
||||
\n\
|
||||
"), stdout);
|
||||
fputs (_("\
|
||||
@@ -284,19 +284,19 @@ xfields (struct line *line)
|
||||
else if (tab < 0)
|
||||
{
|
||||
/* Skip leading blanks before the first field. */
|
||||
while (isblank (to_uchar (*ptr)))
|
||||
while (field_sep (*ptr))
|
||||
if (++ptr == lim)
|
||||
return;
|
||||
|
||||
do
|
||||
{
|
||||
char *sep;
|
||||
for (sep = ptr + 1; sep != lim && ! isblank (to_uchar (*sep)); sep++)
|
||||
for (sep = ptr + 1; sep != lim && ! field_sep (*sep); sep++)
|
||||
continue;
|
||||
extract_field (line, ptr, sep - ptr);
|
||||
if (sep == lim)
|
||||
return;
|
||||
for (ptr = sep + 1; ptr != lim && isblank (to_uchar (*ptr)); ptr++)
|
||||
for (ptr = sep + 1; ptr != lim && field_sep (*ptr); ptr++)
|
||||
continue;
|
||||
}
|
||||
while (ptr != lim);
|
||||
|
||||
+2
-2
@@ -1275,9 +1275,9 @@ inittables (void)
|
||||
|
||||
for (i = 0; i < UCHAR_LIM; ++i)
|
||||
{
|
||||
blanks[i] = !! isblank (i);
|
||||
blanks[i] = field_sep (i);
|
||||
nonprinting[i] = ! isprint (i);
|
||||
nondictionary[i] = ! isalnum (i) && ! isblank (i);
|
||||
nondictionary[i] = ! isalnum (i) && ! field_sep (i);
|
||||
fold_toupper[i] = toupper (i);
|
||||
}
|
||||
|
||||
|
||||
@@ -155,6 +155,13 @@ enum
|
||||
errors that the cast doesn't. */
|
||||
static inline unsigned char to_uchar (char ch) { return ch; }
|
||||
|
||||
/* '\n' is considered a field separator with --zero-terminated. */
|
||||
static inline bool
|
||||
field_sep (unsigned char ch)
|
||||
{
|
||||
return isblank (ch) || ch == '\n';
|
||||
}
|
||||
|
||||
#include <locale.h>
|
||||
|
||||
/* Take care of NLS matters. */
|
||||
|
||||
+2
-2
@@ -261,9 +261,9 @@ find_field (struct linebuffer const *line)
|
||||
|
||||
for (count = 0; count < skip_fields && i < size; count++)
|
||||
{
|
||||
while (i < size && isblank (to_uchar (lp[i])))
|
||||
while (i < size && field_sep (lp[i]))
|
||||
i++;
|
||||
while (i < size && !isblank (to_uchar (lp[i])))
|
||||
while (i < size && !field_sep (lp[i]))
|
||||
i++;
|
||||
}
|
||||
|
||||
|
||||
+6
-3
@@ -290,10 +290,13 @@ my @tv = (
|
||||
# missing last NUL at the end of the last line (=end of file)
|
||||
['z4', '-z',
|
||||
["a\0c\0e", "a\0b\0c"], "a\0c\0", 0],
|
||||
# edge-case: the embedded newlines should treated as
|
||||
# part of the nul-terminated line
|
||||
# With -z, embedded newlines are treated as field separators.
|
||||
# Note '\n' are converted to ' ' in this case.
|
||||
['z5', '-z -a1 -a2',
|
||||
["a\n1\0c 3\0","b\n8\0c 9\0"], "a\n1\0b\n8\0c 3 9\0"],
|
||||
["a\n\n1\0c 3\0", "a 2\0b\n8\0c 9\0"], "a 1 2\0b 8\0c 3 9\0"],
|
||||
# One can avoid field processing like:
|
||||
['z6', '-z -t ""',
|
||||
["a\n1\n\0", "a\n1\n\0"], "a\n1\n\0"],
|
||||
|
||||
);
|
||||
|
||||
|
||||
@@ -406,6 +406,11 @@ my @Tests =
|
||||
["output-is-input-3", '-m -o f', {OUT=>''},
|
||||
{IN=> {g=> "a\n"}}, {IN=> {h=> "b\n"}}, {IN=> {f=> "c\n"}},
|
||||
{CMP=> ["a\nb\nc\n", {'f'=> undef}]} ],
|
||||
|
||||
# --zero-terminated
|
||||
['zero-1', '-z', {IN=>"2\0001\000"}, {OUT=>"1\0002\000"}],
|
||||
['zero-2', '-z -k2,2', {IN=>"1\n2\0002\n1\000"}, {OUT=>"2\n1\0001\n2\000"}],
|
||||
['zero-3', '-zb -k2,2', {IN=>"1\n\n2\0002\n1\0"}, {OUT=>"2\n1\0001\n\n2\0"}],
|
||||
);
|
||||
|
||||
# Add _POSIX2_VERSION=199209 to the environment of each test
|
||||
|
||||
@@ -95,6 +95,7 @@ my @Tests =
|
||||
['3z', '-z', {IN=>"a\na"}, {OUT=>"a\na\0"}],
|
||||
['4z', '-z', {IN=>"a\nb"}, {OUT=>"a\nb\0"}],
|
||||
['5z', '-z', {IN=>"a\na\nb"}, {OUT=>"a\na\nb\0"}],
|
||||
['10z', '-z -f1', {IN=>"a\nb\n\0c\nb\n\0"}, {OUT=>"a\nb\n\0"}],
|
||||
['20z', '-dz', {IN=>"a\na\n"}, {OUT=>""}],
|
||||
|
||||
# Make sure that eight bit characters work
|
||||
|
||||
Reference in new issue
Block a user