I installed these POSIX-conformance fixes for unexpand.
They're fairly subtle, but basically "unexpand" was converted
some blanks that it should have left alone. I added test cases
for the problem areas.
2004-08-24 Paul Eggert <[EMAIL PROTECTED]>
POSIX-conformance fixes for "expand" and "unexpand".
Also, consistently use "tab stop" rather than "tabstop".
* NEWS: Document fixes.
* src/expand.c: Revamp to resemble the new unexpand.c better.
(usage): -i does not convert tabs after non-tabs.
(add_tab_stop): Renamed from add_tabstop. All uses changed.
(parse_tab_stop): Renamed from parse_tabstop. All uses changed.
(validate_tab_stop): Renamed from validate_tabstop. All uses changed.
(next_file, main): Check fclose against 0, not EOF.
(expand): Remove unnecessary casts.
Add another loop nesting level, for lines, so that per-line variables
are initialized cleanly.
Revamp tab checking. Check for write error immediately, rather
than just once at the end of the program.
* src/unexpand.c: Lkewise (for the expand.c changes).
(TAB_STOP_SENTINEL): Remove.
(tab_size): Now size_t, not uintmax_t, since we need to store
the sequences of blanks.
(max_column_width): New var.
(usage): Say "blank" where POSIX requires this.
(add_tab_stop): Calculate maximum column width.
(unexpand): Store the pending blanks, instead of merely counting them.
Follow POSIX's rules about -a requiring two blanks before a tab stop.
Get rid of internal label and goto.
* tests/unexpand/basic-1: Fix infloop-3 to match POSIX.
Add blanks-1 through blanks-13.
* doc/coreutils.texi: Standardize on "tab stop" (the POSIX usage)
rather than "tabstop".
(unexpand invocation): Use "blank" rather than "space" when
POSIX requires "blank". Define "blank". Initial blanks are
converted even if there's just one. For -a, convert two or
more blanks only if they occur just before a tab stop.
Index: NEWS
===================================================================
RCS file: /home/eggert/coreutils/cu/NEWS,v
retrieving revision 1.229
diff -p -u -r1.229 NEWS
--- NEWS 19 Aug 2004 20:02:07 -0000 1.229
+++ NEWS 24 Aug 2004 07:27:46 -0000
@@ -85,6 +85,11 @@ GNU coreutils NEWS
POSIXLY_CORRECT is set and the first argument is not "-n", echo now
outputs all option-like arguments instead of treating them as options.
+ expand and unexpand now conform to POSIX better. They check for
+ blanks (which can include characters other than space and tab in
+ non-POSIX locales) instead of spaces and tabs. Unexpand now
+ preserves some blanks instead of converting them to tabs or spaces.
+
printf has several changes:
It now uses 'intmax_t' (not 'long int') to format integers, so it
Index: src/expand.c
===================================================================
RCS file: /home/eggert/coreutils/cu/src/expand.c,v
retrieving revision 1.76
diff -p -u -r1.76 expand.c
--- src/expand.c 2 Aug 2004 23:49:31 -0000 1.76
+++ src/expand.c 24 Aug 2004 07:12:14 -0000
@@ -24,9 +24,9 @@
--tabs=tab1[,tab2[,...]]
-t tab1[,tab2[,...]]
-tab1[,tab2[,...]] If only one tab stop is given, set the tabs tab1
- spaces apart instead of the default 8. Otherwise,
+ columns apart instead of the default 8. Otherwise,
set the tabs at columns tab1, tab2, etc. (numbered from
- 0); replace any tabs beyond the tabstops given with
+ 0); replace any tabs beyond the tab stops given with
single spaces.
--initial
-i Only convert initial tabs on each line to spaces.
@@ -120,7 +120,7 @@ With no FILE, or when FILE is -, read st
Mandatory arguments to long options are mandatory for short options too.\n\
"), stdout);
fputs (_("\
- -i, --initial do not convert TABs after non whitespace\n\
+ -i, --initial do not convert tabs after non blanks\n\
-t, --tabs=NUMBER have tabs NUMBER characters apart, not 8\n\
"), stdout);
fputs (_("\
@@ -136,18 +136,18 @@ Mandatory arguments to long options are
/* Add tab stop TABVAL to the end of `tab_list'. */
static void
-add_tabstop (uintmax_t tabval)
+add_tab_stop (uintmax_t tabval)
{
if (first_free_tab == n_tabs_allocated)
tab_list = x2nrealloc (tab_list, &n_tabs_allocated, sizeof *tab_list);
tab_list[first_free_tab++] = tabval;
}
-/* Add the comma or blank separated list of tabstops STOPS
- to the list of tabstops. */
+/* Add the comma or blank separated list of tab stops STOPS
+ to the list of tab stops. */
static void
-parse_tabstops (char const *stops)
+parse_tab_stops (char const *stops)
{
bool have_tabval = false;
uintmax_t tabval IF_LINT (= 0);
@@ -159,7 +159,7 @@ parse_tabstops (char const *stops)
if (*stops == ',' || ISBLANK (to_uchar (*stops)))
{
if (have_tabval)
- add_tabstop (tabval);
+ add_tab_stop (tabval);
have_tabval = false;
}
else if (ISDIGIT (*stops))
@@ -198,14 +198,14 @@ parse_tabstops (char const *stops)
exit (EXIT_FAILURE);
if (have_tabval)
- add_tabstop (tabval);
+ add_tab_stop (tabval);
}
-/* Check that the list of tabstops TABS, with ENTRIES entries,
+/* Check that the list of tab stops TABS, with ENTRIES entries,
contains only nonzero, ascending values. */
static void
-validate_tabstops (uintmax_t const *tabs, size_t entries)
+validate_tab_stops (uintmax_t const *tabs, size_t entries)
{
uintmax_t prev_tab = 0;
size_t i;
@@ -240,7 +240,7 @@ next_file (FILE *fp)
}
if (fp == stdin)
clearerr (fp); /* Also clear EOF. */
- else if (fclose (fp) == EOF)
+ else if (fclose (fp) != 0)
{
error (0, errno, "%s", prev_file);
exit_status = EXIT_FAILURE;
@@ -273,14 +273,10 @@ next_file (FILE *fp)
static void
expand (void)
{
- FILE *fp; /* Input stream. */
- size_t tab_index = 0; /* Index in `tab_list' of next tabstop. */
- uintmax_t column = 0; /* Column of next char. */
- uintmax_t next_tab_column; /* Column the next tab stop is on. */
- bool convert = true; /* If true, perform translations. */
+ /* Input stream. */
+ FILE *fp = next_file (NULL);
- fp = next_file ((FILE *) NULL);
- if (fp == NULL)
+ if (!fp)
return;
/* Binary I/O will preserve the original EOL style (DOS/Unix) of files. */
@@ -288,74 +284,89 @@ expand (void)
for (;;)
{
- int c = getc (fp);
- if (c == EOF)
- {
- fp = next_file (fp);
- if (fp)
- {
- SET_BINARY2 (fileno (fp), STDOUT_FILENO);
- continue;
- }
- break;
- }
+ /* Input character, or EOF. */
+ int c;
- if (c == '\n')
- {
- putchar (c);
- tab_index = 0;
- column = 0;
- convert = true;
- }
- else if (c == '\t' && convert)
- {
- if (tab_size == 0)
- {
- /* Do not let tab_index == first_free_tab;
- stop when it is 1 less. */
- while (tab_index < first_free_tab - 1
- && column >= tab_list[tab_index])
- tab_index++;
- next_tab_column = tab_list[tab_index];
- if (tab_index < first_free_tab - 1)
- tab_index++;
- if (column >= next_tab_column)
- next_tab_column = column + 1; /* Ran out of tab stops. */
- }
- else
- {
- next_tab_column = column + tab_size - column % tab_size;
- }
- if (next_tab_column < column)
- error (EXIT_FAILURE, 0, _("input line is too long"));
- while (column < next_tab_column)
- {
- putchar (' ');
- ++column;
- }
- }
- else
+ /* If true, perform translations. */
+ bool convert = true;
+
+
+ /* The following variables have valid values only when CONVERT
+ is true: */
+
+ /* Column of next input character. */
+ uintmax_t column = 0;
+
+ /* Index in TAB_LIST of next tab stop to examine. */
+ size_t tab_index = 0;
+
+
+ /* Convert a line of text. */
+
+ do
{
+ while ((c = getc (fp)) < 0 && (fp = next_file (fp)))
+ SET_BINARY2 (fileno (fp), STDOUT_FILENO);
+
if (convert)
{
- if (c == '\b')
+ if (c == '\t')
+ {
+ /* Column the next input tab stop is on. */
+ uintmax_t next_tab_column;
+
+ if (tab_size)
+ next_tab_column = column + (tab_size - column % tab_size);
+ else
+ for (;;)
+ if (tab_index == first_free_tab)
+ {
+ next_tab_column = column + 1;
+ break;
+ }
+ else
+ {
+ uintmax_t tab = tab_list[tab_index++];
+ if (column < tab)
+ {
+ next_tab_column = tab;
+ break;
+ }
+ }
+
+ if (next_tab_column < column)
+ error (EXIT_FAILURE, 0, _("input line is too long"));
+
+ while (++column < next_tab_column)
+ if (putchar (' ') < 0)
+ error (EXIT_FAILURE, errno, _("write error"));
+
+ c = ' ';
+ }
+ else if (c == '\b')
{
- if (column > 0)
- {
- column--;
- tab_index -= (tab_index != 0);
- }
+ /* Go back one column, and force recalculation of the
+ next tab stop. */
+ column -= !!column;
+ tab_index -= !!tab_index;
}
else
{
- ++column;
- if (column == 0)
+ column++;
+ if (!column)
error (EXIT_FAILURE, 0, _("input line is too long"));
- convert &= convert_entire_line;
}
+
+ convert &= convert_entire_line | ISBLANK (c);
}
- putchar (c);
+
+ if (c < 0)
+ return;
+
+ if (putchar (c) < 0)
+ error (EXIT_FAILURE, errno, _("write error"));
}
+ while (c != '\n');
}
}
@@ -396,11 +407,11 @@ main (int argc, char **argv)
convert_entire_line = false;
break;
case 't':
- parse_tabstops (optarg);
+ parse_tab_stops (optarg);
break;
case ',':
if (have_tabval)
- add_tabstop (tabval);
+ add_tab_stop (tabval);
have_tabval = false;
obsolete_tablist = true;
break;
@@ -425,9 +436,9 @@ main (int argc, char **argv)
}
if (have_tabval)
- add_tabstop (tabval);
+ add_tab_stop (tabval);
- validate_tabstops (tab_list, first_free_tab);
+ validate_tab_stops (tab_list, first_free_tab);
if (first_free_tab == 0)
tab_size = 8;
@@ -440,7 +451,7 @@ main (int argc, char **argv)
expand ();
- if (have_read_stdin && fclose (stdin) == EOF)
+ if (have_read_stdin && fclose (stdin) != 0)
error (EXIT_FAILURE, errno, "-");
exit (exit_status);
Index: src/unexpand.c
===================================================================
RCS file: /home/eggert/coreutils/cu/src/unexpand.c,v
retrieving revision 1.81
diff -p -u -r1.81 unexpand.c
--- src/unexpand.c 3 Aug 2004 23:27:20 -0000 1.81
+++ src/unexpand.c 24 Aug 2004 06:58:38 -0000
@@ -1,4 +1,4 @@
-/* unexpand - convert spaces to tabs
+/* unexpand - convert blanks to tabs
Copyright (C) 89, 91, 1995-2004 Free Software Foundation, Inc.
This program is free software; you can redistribute it and/or modify
@@ -25,12 +25,11 @@
--tabs=tab1[,tab2[,...]]
-t tab1[,tab2[,...]]
-tab1[,tab2[,...]] If only one tab stop is given, set the tabs tab1
- spaces apart instead of the default 8. Otherwise,
+ columns apart instead of the default 8. Otherwise,
set the tabs at columns tab1, tab2, etc. (numbered from
- 0); replace any tabs beyond the tabstops given with
- single spaces.
+ 0); preserve any blanks beyond the tab stops given.
--all
- -a Use tabs wherever they would replace 2 or more spaces,
+ -a Use tabs wherever they would replace 2 or more blanks,
not just at the beginnings of lines.
David MacKenzie <[EMAIL PROTECTED]> */
@@ -55,13 +54,6 @@
allocated for the output line. */
#define OUTPUT_BLOCK 256
-/* A sentinel value that's placed at the end of the list of tab stops.
- This value must be a large number, but not so large that adding the
- length of a line to it would cause the column variable to overflow.
- FIXME: The algorithm isn't correct once the numbers get large;
- also, no error is reported if overflow occurs. */
-#define TAB_STOP_SENTINEL INTMAX_MAX
-
/* The name this program was run with. */
char *program_name;
@@ -70,7 +62,10 @@ char *program_name;
static bool convert_entire_line;
/* If nonzero, the size of all tab stops. If zero, use `tab_list' instead. */
-static uintmax_t tab_size;
+static size_t tab_size;
+
+/* The maximum distance between tab stops. */
+static size_t max_column_width;
/* Array of the explicit column numbers of the tab stops;
after `tab_list' is exhausted, the rest of the line is printed
@@ -129,7 +124,7 @@ Usage: %s [OPTION]... [FILE]...\n\
"),
program_name);
fputs (_("\
-Convert spaces in each FILE to tabs, writing to standard output.\n\
+Convert blanks in each FILE to tabs, writing to standard output.\n\
With no FILE, or when FILE is -, read standard input.\n\
\n\
"), stdout);
@@ -137,8 +132,8 @@ With no FILE, or when FILE is -, read st
Mandatory arguments to long options are mandatory for short options too.\n\
"), stdout);
fputs (_("\
- -a, --all convert all whitespace, instead of just initial whitespace\n\
- --first-only convert only leading sequences of whitespace (overrides -a)\n\
+ -a, --all convert all blanks, instead of just initial blanks\n\
+ --first-only convert only leading sequences of blanks (overrides -a)\n\
-t, --tabs=N have tabs N characters apart instead of 8 (enables -a)\n\
-t, --tabs=LIST use comma separated LIST of tab positions (enables -a)\n\
"), stdout);
@@ -152,18 +147,28 @@ Mandatory arguments to long options are
/* Add tab stop TABVAL to the end of `tab_list'. */
static void
-add_tabstop (uintmax_t tabval)
+add_tab_stop (uintmax_t tabval)
{
+ uintmax_t column_width =
+ tabval - (first_free_tab ? tab_list[first_free_tab - 1] : 0);
+
if (first_free_tab == n_tabs_allocated)
tab_list = x2nrealloc (tab_list, &n_tabs_allocated, sizeof *tab_list);
tab_list[first_free_tab++] = tabval;
+
+ if (max_column_width < column_width)
+ {
+ if (SIZE_MAX < column_width)
+ error (EXIT_FAILURE, 0, _("tabs are too far apart"));
+ max_column_width = column_width;
+ }
}
-/* Add the comma or blank separated list of tabstops STOPS
- to the list of tabstops. */
+/* Add the comma or blank separated list of tab stops STOPS
+ to the list of tab stops. */
static void
-parse_tabstops (char const *stops)
+parse_tab_stops (char const *stops)
{
bool have_tabval = false;
uintmax_t tabval IF_LINT (= 0);
@@ -175,7 +180,7 @@ parse_tabstops (char const *stops)
if (*stops == ',' || ISBLANK (to_uchar (*stops)))
{
if (have_tabval)
- add_tabstop (tabval);
+ add_tab_stop (tabval);
have_tabval = false;
}
else if (ISDIGIT (*stops))
@@ -214,14 +219,14 @@ parse_tabstops (char const *stops)
exit (EXIT_FAILURE);
if (have_tabval)
- add_tabstop (tabval);
+ add_tab_stop (tabval);
}
-/* Check that the list of tabstops TABS, with ENTRIES entries,
+/* Check that the list of tab stops TABS, with ENTRIES entries,
contains only nonzero, ascending values. */
static void
-validate_tabstops (uintmax_t const *tabs, size_t entries)
+validate_tab_stops (uintmax_t const *tabs, size_t entries)
{
uintmax_t prev_tab = 0;
size_t i;
@@ -256,7 +261,7 @@ next_file (FILE *fp)
}
if (fp == stdin)
clearerr (fp); /* Also clear EOF. */
- else if (fclose (fp) == EOF)
+ else if (fclose (fp) != 0)
{
error (0, errno, "%s", prev_file);
exit_status = EXIT_FAILURE;
@@ -283,147 +288,175 @@ next_file (FILE *fp)
return NULL;
}
-/* Change spaces to tabs, writing to stdout.
+/* Change blanks to tabs, writing to stdout.
Read each file in `file_list', in order. */
static void
unexpand (void)
{
- FILE *fp; /* Input stream. */
- size_t tab_index = 0; /* Index in `tab_list' of next tabstop. */
- size_t print_tab_index = 0; /* For printing as many tabs as possible. */
- uintmax_t column = 0; /* Column of next char. */
- uintmax_t next_tab_column; /* Column the next tab stop is on. */
- bool convert = true; /* If true, perform translations. */
- uintmax_t pending = 0; /* Pending columns of blanks. */
- int saved_errno IF_LINT (= 0);
+ /* Input stream. */
+ FILE *fp = next_file (NULL);
- fp = next_file ((FILE *) NULL);
- if (fp == NULL)
+ /* The array of pending blanks. In non-POSIX locales, blanks can
+ include characters other than spaces, so the blanks must be
+ stored, not merely counted. */
+ char *pending_blank;
+
+ if (!fp)
return;
/* Binary I/O will preserve the original EOL style (DOS/Unix) of files. */
SET_BINARY2 (fileno (fp), STDOUT_FILENO);
+ /* The worst case is a non-blank character, then one blank, then a
+ tab stop, then MAX_COLUMN_WIDTH - 1 blanks, then a non-blank; so
+ allocate MAX_COLUMN_WIDTH bytes to store the blanks. */
+ pending_blank = xmalloc (max_column_width);
+
for (;;)
{
- int c = getc (fp);
- if (c == EOF)
- {
- fp = next_file (fp);
- if (fp)
- {
- SET_BINARY2 (fileno (fp), STDOUT_FILENO);
- continue;
- }
- saved_errno = errno;
- }
+ /* Input character, or EOF. */
+ int c;
- if (c == ' ' && convert && column < TAB_STOP_SENTINEL)
- {
- ++pending;
- ++column;
- }
- else if (c == '\t' && convert)
- {
- if (tab_size == 0)
- {
- /* Do not let tab_index == first_free_tab;
- stop when it is 1 less. */
- while (tab_index < first_free_tab - 1
- && column >= tab_list[tab_index])
- tab_index++;
- next_tab_column = tab_list[tab_index];
- if (tab_index < first_free_tab - 1)
- tab_index++;
- if (column >= next_tab_column)
- {
- convert = false; /* Ran out of tab stops. */
- goto flush_pend;
- }
- }
- else
- {
- next_tab_column = column + tab_size - column % tab_size;
- }
- pending += next_tab_column - column;
- column = next_tab_column;
- }
- else
+ /* If true, perform translations. */
+ bool convert = true;
+
+
+ /* The following variables have valid values only when CONVERT
+ is true: */
+
+ /* Column of next input character. */
+ uintmax_t column = 0;
+
+ /* Column the next input tab stop is on. */
+ uintmax_t next_tab_column = 0;
+
+ /* Index in TAB_LIST of next tab stop to examine. */
+ size_t tab_index = 0;
+
+ /* If true, the first pending blank came just before a tab stop. */
+ bool one_blank_before_tab_stop = false;
+
+ /* If true, the previous input character was a blank. This is
+ initially true, since initial strings of blanks are treated
+ as if the line was preceded by a blank. */
+ bool prev_blank = true;
+
+ /* Number of pending columns of blanks. */
+ size_t pending = 0;
+
+
+ /* Convert a line of text. */
+
+ do
{
- flush_pend:
- /* Flush pending spaces. Print as many tabs as possible,
- then print the rest as spaces. */
- if (pending == 1)
- {
- putchar (' ');
- pending = 0;
- }
- column -= pending;
- while (pending > 0)
+ while ((c = getc (fp)) < 0 && (fp = next_file (fp)))
+ SET_BINARY2 (fileno (fp), STDOUT_FILENO);
+
+ if (convert)
{
- if (tab_size == 0)
- {
- /* Do not let print_tab_index == first_free_tab;
- stop when it is 1 less. */
- while (print_tab_index < first_free_tab - 1
- && column >= tab_list[print_tab_index])
- print_tab_index++;
- next_tab_column = tab_list[print_tab_index];
- if (print_tab_index < first_free_tab - 1)
- print_tab_index++;
- }
- else
- {
- next_tab_column = column + tab_size - column % tab_size;
- }
- if (next_tab_column - column <= pending)
- {
- putchar ('\t');
- pending -= next_tab_column - column;
- column = next_tab_column;
- }
- else
+ bool blank = ISBLANK (c);
+
+ if (blank)
{
- --print_tab_index;
- column += pending;
- while (pending != 0)
+ if (next_tab_column <= column)
{
- putchar (' ');
- pending--;
+ if (tab_size)
+ next_tab_column =
+ column + (tab_size - column % tab_size);
+ else
+ for (;;)
+ if (tab_index == first_free_tab)
+ {
+ convert = false;
+ break;
+ }
+ else
+ {
+ uintmax_t tab = tab_list[tab_index++];
+ if (column < tab)
+ {
+ next_tab_column = tab;
+ break;
+ }
+ }
}
- }
- }
- if (c == EOF)
- {
- errno = saved_errno;
- break;
- }
+ if (convert)
+ {
+ if (next_tab_column < column)
+ error (EXIT_FAILURE, 0, _("input line is too long"));
- if (convert)
- {
- if (c == '\b')
+ if (c == '\t')
+ {
+ column = next_tab_column;
+
+ /* Discard pending blanks, unless it was a single
+ blank just before the previous tab stop. */
+ if (! (pending == 1 && one_blank_before_tab_stop))
+ {
+ pending = 0;
+ one_blank_before_tab_stop = false;
+ }
+ }
+ else
+ {
+ column++;
+
+ if (! (prev_blank && column == next_tab_column))
+ {
+ /* It is not yet known whether the pending blanks
+ will be replaced by tabs. */
+ if (column == next_tab_column)
+ one_blank_before_tab_stop = true;
+ pending_blank[pending++] = c;
+ prev_blank = true;
+ continue;
+ }
+
+ /* Replace the pending blanks by a tab or two. */
+ pending_blank[0] = c = '\t';
+ pending = one_blank_before_tab_stop;
+ }
+ }
+ }
+ else if (c == '\b')
{
- if (column > 0)
- --column;
+ /* Go back one column, and force recalculation of the
+ next tab stop. */
+ column -= !!column;
+ next_tab_column = column;
+ tab_index -= !!tab_index;
}
else
{
- ++column;
- convert &= convert_entire_line;
+ column++;
+ if (!column)
+ error (EXIT_FAILURE, 0, _("input line is too long"));
}
- }
- putchar (c);
+ if (pending)
+ {
+ if (fwrite (pending_blank, 1, pending, stdout) != pending)
+ error (EXIT_FAILURE, errno, _("write error"));
+ pending = 0;
+ one_blank_before_tab_stop = false;
+ }
+
+ prev_blank = blank;
+ convert &= convert_entire_line | blank;
+ }
- if (c == '\n')
+ if (c < 0)
{
- tab_index = print_tab_index = 0;
- column = pending = 0;
- convert = true;
+ free (pending_blank);
+ return;
}
+
+ if (putchar (c) < 0)
+ error (EXIT_FAILURE, errno, _("write error"));
}
+ while (c != '\n');
}
}
@@ -435,7 +468,7 @@ main (int argc, char **argv)
int c;
/* If true, cancel the effect of any -a (explicit or implicit in -t),
- so that only leading white space will be considered. */
+ so that only leading blanks will be considered. */
bool convert_first_only = false;
bool obsolete_tablist = false;
@@ -469,14 +502,14 @@ main (int argc, char **argv)
break;
case 't':
convert_entire_line = true;
- parse_tabstops (optarg);
+ parse_tab_stops (optarg);
break;
case CONVERT_FIRST_ONLY_OPTION:
convert_first_only = true;
break;
case ',':
if (have_tabval)
- add_tabstop (tabval);
+ add_tab_stop (tabval);
have_tabval = false;
obsolete_tablist = true;
break;
@@ -505,26 +538,22 @@ main (int argc, char **argv)
convert_entire_line = false;
if (have_tabval)
- add_tabstop (tabval);
+ add_tab_stop (tabval);
- validate_tabstops (tab_list, first_free_tab);
+ validate_tab_stops (tab_list, first_free_tab);
if (first_free_tab == 0)
- tab_size = 8;
+ tab_size = max_column_width = 8;
else if (first_free_tab == 1)
tab_size = tab_list[0];
else
- {
- /* Append a sentinel to the list of tab stop indices. */
- add_tabstop (TAB_STOP_SENTINEL);
- tab_size = 0;
- }
+ tab_size = 0;
file_list = (optind < argc ? &argv[optind] : stdin_argv);
unexpand ();
- if (have_read_stdin && fclose (stdin) == EOF)
+ if (have_read_stdin && fclose (stdin) != 0)
error (EXIT_FAILURE, errno, "-");
exit (exit_status);
Index: tests/unexpand/basic-1
===================================================================
RCS file: /home/eggert/coreutils/cu/tests/unexpand/basic-1,v
retrieving revision 1.14
diff -p -u -r1.14 basic-1
--- tests/unexpand/basic-1 8 Apr 2003 10:55:02 -0000 1.14
+++ tests/unexpand/basic-1 24 Aug 2004 06:42:47 -0000
@@ -41,13 +41,9 @@ my @Tests =
['b-1', '-t', '2,4', {IN=> " ."}, {OUT=>"\t\t ."}],
# These would infloop prior to textutils-2.0d.
- # Solaris' /bin/unexpand does this:
- # ['infloop-1', '-t', '1,2', {IN=> " \t\t .\n"}, {OUT=>" \t\t .\n"}],
- # FIXME: find out which is required
-
['infloop-1', '-t', '1,2', {IN=> " \t\t .\n"}, {OUT=>"\t\t\t .\n"}],
['infloop-2', '-t', '4,5', {IN=> ' 'x4 . "\t\t \n"}, {OUT=>"\t\t\t \n"}],
- ['infloop-3', '-t', '2,3', {IN=> "x \t\t \n"}, {OUT=>"x\t\t\t \n"}],
+ ['infloop-3', '-t', '2,3', {IN=> "x \t\t \n"}, {OUT=>"x \t\t \n"}],
['infloop-4', '-t', '1,2', {IN=> " \t\t \n"}, {OUT=>"\t\t\t \n"}],
['c-1', '-t', '1,2', {IN=> "x\t\t .\n"}, {OUT=>"x\t\t .\n"}],
@@ -55,6 +51,21 @@ my @Tests =
# Feature addition (--first-only) prompted by a report from Jie Xu.
['tabs-1', qw(-t 3), {IN=> " a b\n"}, {OUT=>"\ta\tb\n"}],
['tabs-2', qw(-t 3 --first-only), {IN=> " a b\n"}, {OUT=>"\ta b\n"}],
+
+ # blanks
+ ['blanks-1', qw(-t 1), {IN=> " b c d\n"}, {OUT=> "\tb\t\tc\t\t\td\n"}],
+ ['blanks-2', qw(-t 1), {IN=> "a \n"}, {OUT=> "a \n"}],
+ ['blanks-3', qw(-t 1), {IN=> "a \n"}, {OUT=> "a\t\t\n"}],
+ ['blanks-4', qw(-t 1), {IN=> "a \n"}, {OUT=> "a\t\t\t\n"}],
+ ['blanks-5', qw(-t 1), {IN=> "a "}, {OUT=> "a "}],
+ ['blanks-6', qw(-t 1), {IN=> "a "}, {OUT=> "a\t\t"}],
+ ['blanks-7', qw(-t 1), {IN=> "a "}, {OUT=> "a\t\t\t"}],
+ ['blanks-8', qw(-t 1), {IN=> " a a a\n"}, {OUT=> "\ta a\t\ta\n"}],
+ ['blanks-9', qw(-t 2), {IN=> " a a a\n"}, {OUT=> "\t a\ta a\n"}],
+ ['blanks-10', '-t', '3,4', {IN=> "0 2 4 6\t8\n"}, {OUT=> "0 2 4 6\t8\n"}],
+ ['blanks-11', '-t', '3,4', {IN=> " 4\n"}, {OUT=> "\t\t4\n"}],
+ ['blanks-12', '-t', '3,4', {IN=> "01 4\n"}, {OUT=> "01\t\t4\n"}],
+ ['blanks-13', '-t', '3,4', {IN=> "0 4\n"}, {OUT=> "0\t\t4\n"}],
);
my $save_temps = $ENV{DEBUG};
Index: doc/coreutils.texi
===================================================================
RCS file: /home/eggert/coreutils/cu/doc/coreutils.texi,v
retrieving revision 1.201
diff -p -u -r1.201 coreutils.texi
--- doc/coreutils.texi 19 Aug 2004 20:05:52 -0000 1.201
+++ doc/coreutils.texi 24 Aug 2004 06:56:26 -0000
@@ -5090,15 +5090,15 @@ The program accepts the following option
@itemx [EMAIL PROTECTED],@[EMAIL PROTECTED]
@opindex -t
@opindex --tabs
[EMAIL PROTECTED] tabstops, setting
[EMAIL PROTECTED] tab stops, setting
If only one tab stop is given, set the tabs @var{tab1} spaces apart
(default is 8). Otherwise, set the tabs at columns @var{tab1},
@var{tab2}, @dots{} (numbered from 0), and replace any tabs beyond the
-last tabstop given with single spaces. Tabstops can be separated by
+last tab stop given with single spaces. Tab stops can be separated by
blanks as well as by commas.
On older systems, @command{expand} supports an obsolete option
[EMAIL PROTECTED]@var{tab1}[,@[EMAIL PROTECTED], where tabstops must be
[EMAIL PROTECTED]@var{tab1}[,@[EMAIL PROTECTED], where tab stops must be
separated by commas. @acronym{POSIX} 1003.1-2001 (@pxref{Standards
conformance}) does not allow this; use @option{-t
@var{tab1}[,@[EMAIL PROTECTED] instead.
@@ -5123,16 +5123,17 @@ characters) on each line to spaces.
@command{unexpand} writes the contents of each given @var{file}, or
standard input if none are given or for a @var{file} of @samp{-}, to
-standard output, with strings of two or more space or tab characters
-converted to as many tabs as possible followed by as many spaces as are
-needed. Synopsis:
+standard output, converting blanks at the beginning of each line into
+as many tab characters as needed. In the default @acronym{POSIX}
+locale, a @dfn{blank} is a space or a tab; other locales may specify
+additional blank characters. Synopsis:
@example
unexpand [EMAIL PROTECTED]@dots{} [EMAIL PROTECTED]@dots{}
@end example
-By default, @command{unexpand} converts only initial spaces and tabs (those
-that precede all non space or tab characters) on each line. It
+By default, @command{unexpand} converts only initial blanks (those
+that precede all non-blank characters) on each line. It
preserves backspace characters in the output; they decrement the column
count for tab calculations. By default, tabs are set at every 8th
column.
@@ -5145,14 +5146,14 @@ The program accepts the following option
@itemx [EMAIL PROTECTED],@[EMAIL PROTECTED]
@opindex -t
@opindex --tabs
-If only one tab stop is given, set the tabs @var{tab1} spaces apart
+If only one tab stop is given, set the tabs @var{tab1} columns apart
instead of the default 8. Otherwise, set the tabs at columns
[EMAIL PROTECTED], @var{tab2}, @dots{} (numbered from 0), and leave spaces and
-tabs beyond the tabstops given unchanged. Tabstops can be separated by
[EMAIL PROTECTED], @var{tab2}, @dots{} (numbered from 0), and leave blanks
+beyond the tab stops given unchanged. Tab stops can be separated by
blanks as well as by commas. This option implies the @option{-a} option.
On older systems, @command{unexpand} supports an obsolete option
[EMAIL PROTECTED]@var{tab1}[,@[EMAIL PROTECTED], where tabstops must be
[EMAIL PROTECTED]@var{tab1}[,@[EMAIL PROTECTED], where tab stops must be
separated by commas. (Unlike @option{-t}, this obsolete option does
not imply @option{-a}.) @acronym{POSIX} 1003.1-2001 (@pxref{Standards
conformance}) does not allow this; use @option{--first-only -t
@@ -5162,8 +5163,8 @@ conformance}) does not allow this; use @
@itemx --all
@opindex -a
@opindex --all
-Convert all strings of two or more spaces or tabs, not just initial
-ones, to tabs.
+Also convert all sequences of two or more blanks just before a tab stop.
+even if they occur after non-blank characters in a line.
@end table
@@ -5832,7 +5833,7 @@ List the files in columns, sorted horizo
@itemx [EMAIL PROTECTED]
@opindex -T
@opindex --tabsize
-Assume that each tabstop is @var{cols} columns wide. The default is 8.
+Assume that each tab stop is @var{cols} columns wide. The default is 8.
@command{ls} uses tabs where possible in the output, for efficiency. If
@var{cols} is zero, do not use tabs at all.
_______________________________________________
Bug-coreutils mailing list
[EMAIL PROTECTED]
http://lists.gnu.org/mailman/listinfo/bug-coreutils
