Submitted by: DJ Lucas (dj_AT_linuxfromscratch_DOT_org)
-Date: 2016-02-09
-Initial Package Version: 8.25
+Date: 2017-03-12
+Initial Package Version: 8.27
Upstream Status: Rejected
-Origin: Based on Suse's i18n patches at https://build.opensuse.org/package/view_file/Base:System/coreutils/coreutils-i18n.patch
-Description: Fixes several i18n issues with various Coreutils programs
+Origin: Based on Fedora's i18n patches at
+ http://pkgs.fedoraproject.org/cgit/rpms/coreutils.git/tree/
+Description: Fixes i18n issues with various Coreutils programs
-diff -Naurp coreutils-8.25-orig/lib/linebuffer.h coreutils-8.25/lib/linebuffer.h
---- coreutils-8.25-orig/lib/linebuffer.h 2016-01-01 07:45:55.000000000 -0600
-+++ coreutils-8.25/lib/linebuffer.h 2016-02-08 19:07:10.298944609 -0600
+diff -Naurp coreutils-8.27-orig/bootstrap.conf coreutils-8.27/bootstrap.conf
+--- coreutils-8.27-orig/bootstrap.conf 2017-03-07 23:34:06.000000000 -0600
++++ coreutils-8.27/bootstrap.conf 2017-03-11 23:47:38.068058445 -0600
+@@ -152,6 +152,7 @@ gnulib_modules="
+ maintainer-makefile
+ malloc-gnu
+ manywarnings
++ mbfile
+ mbrlen
+ mbrtowc
+ mbsalign
+diff -Naurp coreutils-8.27-orig/configure.ac coreutils-8.27/configure.ac
+--- coreutils-8.27-orig/configure.ac 2017-02-26 08:52:29.000000000 -0600
++++ coreutils-8.27/configure.ac 2017-03-11 23:47:38.068058445 -0600
+@@ -429,6 +429,8 @@ fi
+ # I'm leaving it here for now. This whole thing needs to be modernized...
+ gl_WINSIZE_IN_PTEM
+
++gl_MBFILE
++
+ gl_HEADER_TIOCGWINSZ_IN_TERMIOS_H
+
+ if test $gl_cv_sys_tiocgwinsz_needs_termios_h = no && \
+diff -Naurp coreutils-8.27-orig/lib/linebuffer.h coreutils-8.27/lib/linebuffer.h
+--- coreutils-8.27-orig/lib/linebuffer.h 2017-01-01 16:35:38.000000000 -0600
++++ coreutils-8.27/lib/linebuffer.h 2017-03-11 23:47:13.089286391 -0600
@@ -21,6 +21,11 @@
# include <stdio.h>
};
/* Initialize linebuffer LINEBUFFER for use. */
-diff -Naurp coreutils-8.25-orig/src/cut.c coreutils-8.25/src/cut.c
---- coreutils-8.25-orig/src/cut.c 2016-01-13 05:08:59.000000000 -0600
-+++ coreutils-8.25/src/cut.c 2016-02-08 19:07:10.300944616 -0600
+diff -Naurp coreutils-8.27-orig/lib/mbfile.c coreutils-8.27/lib/mbfile.c
+--- coreutils-8.27-orig/lib/mbfile.c 1969-12-31 18:00:00.000000000 -0600
++++ coreutils-8.27/lib/mbfile.c 2017-03-11 23:47:38.069058397 -0600
+@@ -0,0 +1,3 @@
++#include <config.h>
++#define MBFILE_INLINE _GL_EXTERN_INLINE
++#include "mbfile.h"
+diff -Naurp coreutils-8.27-orig/lib/mbfile.h coreutils-8.27/lib/mbfile.h
+--- coreutils-8.27-orig/lib/mbfile.h 1969-12-31 18:00:00.000000000 -0600
++++ coreutils-8.27/lib/mbfile.h 2017-03-11 23:47:38.069058397 -0600
+@@ -0,0 +1,255 @@
++/* Multibyte character I/O: macros for multi-byte encodings.
++ Copyright (C) 2001, 2005, 2009-2017 Free Software Foundation, Inc.
++
++ This program is free software: you can redistribute it and/or modify
++ it under the terms of the GNU General Public License as published by
++ the Free Software Foundation; either version 3 of the License, or
++ (at your option) any later version.
++
++ This program is distributed in the hope that it will be useful,
++ but WITHOUT ANY WARRANTY; without even the implied warranty of
++ MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
++ GNU General Public License for more details.
++
++ You should have received a copy of the GNU General Public License
++ along with this program. If not, see <http://www.gnu.org/licenses/>. */
++
++/* Written by Mitsuru Chinen <mchinen@yamato.ibm.com>
++ and Bruno Haible <bruno@clisp.org>. */
++
++/* The macros in this file implement multi-byte character input from a
++ stream.
++
++ mb_file_t
++ is the type for multibyte character input stream, usable for variable
++ declarations.
++
++ mbf_char_t
++ is the type for multibyte character or EOF, usable for variable
++ declarations.
++
++ mbf_init (mbf, stream)
++ initializes the MB_FILE for reading from stream.
++
++ mbf_getc (mbc, mbf)
++ reads the next multibyte character from mbf and stores it in mbc.
++
++ mb_iseof (mbc)
++ returns true if mbc represents the EOF value.
++
++ Here are the function prototypes of the macros.
++
++ extern void mbf_init (mb_file_t mbf, FILE *stream);
++ extern void mbf_getc (mbf_char_t mbc, mb_file_t mbf);
++ extern bool mb_iseof (const mbf_char_t mbc);
++ */
++
++#ifndef _MBFILE_H
++#define _MBFILE_H 1
++
++#include <assert.h>
++#include <stdbool.h>
++#include <stdio.h>
++#include <string.h>
++
++/* Tru64 with Desktop Toolkit C has a bug: <stdio.h> must be included before
++ <wchar.h>.
++ BSD/OS 4.1 has a bug: <stdio.h> and <time.h> must be included before
++ <wchar.h>. */
++#include <stdio.h>
++#include <time.h>
++#include <wchar.h>
++
++#include "mbchar.h"
++
++#ifndef _GL_INLINE_HEADER_BEGIN
++ #error "Please include config.h first."
++#endif
++_GL_INLINE_HEADER_BEGIN
++#ifndef MBFILE_INLINE
++# define MBFILE_INLINE _GL_INLINE
++#endif
++
++struct mbfile_multi {
++ FILE *fp;
++ bool eof_seen;
++ bool have_pushback;
++ mbstate_t state;
++ unsigned int bufcount;
++ char buf[MBCHAR_BUF_SIZE];
++ struct mbchar pushback;
++};
++
++MBFILE_INLINE void
++mbfile_multi_getc (struct mbchar *mbc, struct mbfile_multi *mbf)
++{
++ size_t bytes;
++
++ /* If EOF has already been seen, don't use getc. This matters if
++ mbf->fp is connected to an interactive tty. */
++ if (mbf->eof_seen)
++ goto eof;
++
++ /* Return character pushed back, if there is one. */
++ if (mbf->have_pushback)
++ {
++ mb_copy (mbc, &mbf->pushback);
++ mbf->have_pushback = false;
++ return;
++ }
++
++ /* Before using mbrtowc, we need at least one byte. */
++ if (mbf->bufcount == 0)
++ {
++ int c = getc (mbf->fp);
++ if (c == EOF)
++ {
++ mbf->eof_seen = true;
++ goto eof;
++ }
++ mbf->buf[0] = (unsigned char) c;
++ mbf->bufcount++;
++ }
++
++ /* Handle most ASCII characters quickly, without calling mbrtowc(). */
++ if (mbf->bufcount == 1 && mbsinit (&mbf->state) && is_basic (mbf->buf[0]))
++ {
++ /* These characters are part of the basic character set. ISO C 99
++ guarantees that their wide character code is identical to their
++ char code. */
++ mbc->wc = mbc->buf[0] = mbf->buf[0];
++ mbc->wc_valid = true;
++ mbc->ptr = &mbc->buf[0];
++ mbc->bytes = 1;
++ mbf->bufcount = 0;
++ return;
++ }
++
++ /* Use mbrtowc on an increasing number of bytes. Read only as many bytes
++ from mbf->fp as needed. This is needed to give reasonable interactive
++ behaviour when mbf->fp is connected to an interactive tty. */
++ for (;;)
++ {
++ /* We don't know whether the 'mbrtowc' function updates the state when
++ it returns -2, - this is the ISO C 99 and glibc-2.2 behaviour - or
++ not - amended ANSI C, glibc-2.1 and Solaris 2.7 behaviour. We
++ don't have an autoconf test for this, yet.
++ The new behaviour would allow us to feed the bytes one by one into
++ mbrtowc. But the old behaviour forces us to feed all bytes since
++ the end of the last character into mbrtowc. Since we want to retry
++ with more bytes when mbrtowc returns -2, we must backup the state
++ before calling mbrtowc, because implementations with the new
++ behaviour will clobber it. */
++ mbstate_t backup_state = mbf->state;
++
++ bytes = mbrtowc (&mbc->wc, &mbf->buf[0], mbf->bufcount, &mbf->state);
++
++ if (bytes == (size_t) -1)
++ {
++ /* An invalid multibyte sequence was encountered. */
++ /* Return a single byte. */
++ bytes = 1;
++ mbc->wc_valid = false;
++ break;
++ }
++ else if (bytes == (size_t) -2)
++ {
++ /* An incomplete multibyte character. */
++ mbf->state = backup_state;
++ if (mbf->bufcount == MBCHAR_BUF_SIZE)
++ {
++ /* An overlong incomplete multibyte sequence was encountered. */
++ /* Return a single byte. */
++ bytes = 1;
++ mbc->wc_valid = false;
++ break;
++ }
++ else
++ {
++ /* Read one more byte and retry mbrtowc. */
++ int c = getc (mbf->fp);
++ if (c == EOF)
++ {
++ /* An incomplete multibyte character at the end. */
++ mbf->eof_seen = true;
++ bytes = mbf->bufcount;
++ mbc->wc_valid = false;
++ break;
++ }
++ mbf->buf[mbf->bufcount] = (unsigned char) c;
++ mbf->bufcount++;
++ }
++ }
++ else
++ {
++ if (bytes == 0)
++ {
++ /* A null wide character was encountered. */
++ bytes = 1;
++ assert (mbf->buf[0] == '\0');
++ assert (mbc->wc == 0);
++ }
++ mbc->wc_valid = true;
++ break;
++ }
++ }
++
++ /* Return the multibyte sequence mbf->buf[0..bytes-1]. */
++ mbc->ptr = &mbc->buf[0];
++ memcpy (&mbc->buf[0], &mbf->buf[0], bytes);
++ mbc->bytes = bytes;
++
++ mbf->bufcount -= bytes;
++ if (mbf->bufcount > 0)
++ {
++ /* It's not worth calling memmove() for so few bytes. */
++ unsigned int count = mbf->bufcount;
++ char *p = &mbf->buf[0];
++
++ do
++ {
++ *p = *(p + bytes);
++ p++;
++ }
++ while (--count > 0);
++ }
++ return;
++
++eof:
++ /* An mbchar_t with bytes == 0 is used to indicate EOF. */
++ mbc->ptr = NULL;
++ mbc->bytes = 0;
++ mbc->wc_valid = false;
++ return;
++}
++
++MBFILE_INLINE void
++mbfile_multi_ungetc (const struct mbchar *mbc, struct mbfile_multi *mbf)
++{
++ mb_copy (&mbf->pushback, mbc);
++ mbf->have_pushback = true;
++}
++
++typedef struct mbfile_multi mb_file_t;
++
++typedef mbchar_t mbf_char_t;
++
++#define mbf_init(mbf, stream) \
++ ((mbf).fp = (stream), \
++ (mbf).eof_seen = false, \
++ (mbf).have_pushback = false, \
++ memset (&(mbf).state, '\0', sizeof (mbstate_t)), \
++ (mbf).bufcount = 0)
++
++#define mbf_getc(mbc, mbf) mbfile_multi_getc (&(mbc), &(mbf))
++
++#define mbf_ungetc(mbc, mbf) mbfile_multi_ungetc (&(mbc), &(mbf))
++
++#define mb_iseof(mbc) ((mbc).bytes == 0)
++
++#ifndef _GL_INLINE_HEADER_BEGIN
++ #error "Please include config.h first."
++#endif
++_GL_INLINE_HEADER_BEGIN
++
++#endif /* _MBFILE_H */
+diff -Naurp coreutils-8.27-orig/m4/mbfile.m4 coreutils-8.27/m4/mbfile.m4
+--- coreutils-8.27-orig/m4/mbfile.m4 1969-12-31 18:00:00.000000000 -0600
++++ coreutils-8.27/m4/mbfile.m4 2017-03-11 23:47:38.070058349 -0600
+@@ -0,0 +1,14 @@
++# mbfile.m4 serial 7
++dnl Copyright (C) 2005, 2008-2017 Free Software Foundation, Inc.
++dnl This file is free software; the Free Software Foundation
++dnl gives unlimited permission to copy and/or distribute it,
++dnl with or without modifications, as long as this notice is preserved.
++
++dnl autoconf tests required for use of mbfile.h
++dnl From Bruno Haible.
++
++AC_DEFUN([gl_MBFILE],
++[
++ AC_REQUIRE([AC_TYPE_MBSTATE_T])
++ :
++])
+diff -Naurp coreutils-8.27-orig/src/cut.c coreutils-8.27/src/cut.c
+--- coreutils-8.27-orig/src/cut.c 2017-01-01 16:34:24.000000000 -0600
++++ coreutils-8.27/src/cut.c 2017-03-11 23:47:59.526048471 -0600
@@ -28,6 +28,11 @@
#include <assert.h>
#include <getopt.h>
}
if (optind == argc)
-diff -Naurp coreutils-8.25-orig/src/expand.c coreutils-8.25/src/expand.c
---- coreutils-8.25-orig/src/expand.c 2016-01-01 07:48:50.000000000 -0600
-+++ coreutils-8.25/src/expand.c 2016-02-08 19:07:10.301944619 -0600
-@@ -37,12 +37,34 @@
+diff -Naurp coreutils-8.27-orig/src/expand.c coreutils-8.27/src/expand.c
+--- coreutils-8.27-orig/src/expand.c 2017-02-26 15:42:25.000000000 -0600
++++ coreutils-8.27/src/expand.c 2017-03-11 23:49:06.758133530 -0600
+@@ -37,6 +37,9 @@
#include <stdio.h>
#include <getopt.h>
#include <sys/types.h>
+
-+/* Get mbstate_t, mbrtowc(), wcwidth(). */
-+#if HAVE_WCHAR_H
-+# include <wchar.h>
-+#endif
-+
-+/* Get iswblank(). */
-+#if HAVE_WCTYPE_H
-+# include <wctype.h>
-+#endif
++#include <mbfile.h>
+
#include "system.h"
- #include "error.h"
- #include "fadvise.h"
- #include "quote.h"
+ #include "die.h"
#include "xstrndup.h"
+@@ -100,19 +103,41 @@ expand (void)
+ {
+ /* Input stream. */
+ FILE *fp = next_file (NULL);
++ mb_file_t mbf;
++ mbf_char_t c;
++ /* True if the starting locale is utf8. */
++ bool using_utf_locale;
++
++ /* True if the first file contains BOM header. */
++ bool found_bom;
++ using_utf_locale=check_utf_locale();
+
+ if (!fp)
+ return;
++ mbf_init (mbf, fp);
++ found_bom=check_bom(fp,&mbf);
-+/* MB_LEN_MAX is incorrectly defined to be 1 in at least one GCC
-+ installation; work around this configuration error. */
-+#if !defined MB_LEN_MAX || MB_LEN_MAX < 2
-+# define MB_LEN_MAX 16
-+#endif
+- while (true)
++ if (using_utf_locale == false && found_bom == true)
++ {
++ /*try using some predefined locale */
+
-+/* Some systems, like BeOS, have multibyte encodings but lack mbstate_t. */
-+#if HAVE_MBRTOWC && defined mbstate_t
-+# define mbrtowc(pwc, s, n, ps) (mbrtowc) (pwc, s, n, 0)
-+#endif
++ if (set_utf_locale () != 0)
+ {
+- /* Input character, or EOF. */
+- int c;
++ error (EXIT_FAILURE, errno, _("cannot set UTF-8 locale"));
++ }
++ }
+
- /* The official name of this program (e.g., no 'g' prefix). */
- #define PROGRAM_NAME "expand"
-@@ -357,6 +379,142 @@ expand (void)
++ if (found_bom == true)
++ {
++ print_bom();
++ }
++
++ while (true)
++ {
+ /* If true, perform translations. */
+ bool convert = true;
+
+-
+ /* The following variables have valid values only when CONVERT
+ is true: */
+
+@@ -122,17 +147,48 @@ expand (void)
+ /* 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)))
+- continue;
++ while (true) {
++ mbf_getc (c, mbf);
++ if ((mb_iseof (c)) && (fp = next_file (fp)))
++ {
++ mbf_init (mbf, fp);
++ if (fp!=NULL)
++ {
++ if (check_bom(fp,&mbf)==true)
++ {
++ /*Not the first file - check BOM header*/
++ if (using_utf_locale==false && found_bom==false)
++ {
++ /*BOM header in subsequent file but not in the first one. */
++ error (EXIT_FAILURE, errno, _("combination of files with and without BOM header"));
++ }
++ }
++ else
++ {
++ if(using_utf_locale==false && found_bom==true)
++ {
++ /*First file conatined BOM header - locale was switched to UTF
++ /*all subsequent files should contain BOM. */
++ error (EXIT_FAILURE, errno, _("combination of files with and without BOM header"));
++ }
++ }
++ }
++ continue;
++ }
++ else
++ {
++ break;
++ }
++ }
++
+
+ if (convert)
+ {
+- if (c == '\t')
++ if (mb_iseq (c, '\t'))
+ {
+ /* Column the next input tab stop is on. */
+ uintmax_t next_tab_column;
+@@ -151,32 +207,34 @@ expand (void)
+ if (putchar (' ') < 0)
+ die (EXIT_FAILURE, errno, _("write error"));
+
+- c = ' ';
++ mb_setascii (&c, ' ');
+ }
+- else if (c == '\b')
++ else if (mb_iseq (c, '\b'))
+ {
+ /* Go back one column, and force recalculation of the
+ next tab stop. */
+ column -= !!column;
+ tab_index -= !!tab_index;
+ }
+- else
++ /* A leading control character could make us trip over. */
++ else if (!mb_iscntrl (c))
+ {
+- column++;
++ column += mb_width (c);
+ if (!column)
+ die (EXIT_FAILURE, 0, _("input line is too long"));
+ }
+
+- convert &= convert_entire_line || !! isblank (c);
++ convert &= convert_entire_line || mb_isblank (c);
+ }
+
+- if (c < 0)
++ if (mb_iseof (c))
+ return;
+
+- if (putchar (c) < 0)
++ mb_putc (c, stdout);
++ if (ferror (stdout))
+ die (EXIT_FAILURE, errno, _("write error"));
+ }
+- while (c != '\n');
++ while (!mb_iseq (c, '\n'));
}
}
-+#if HAVE_MBRTOWC
-+static void
-+expand_multibyte (void)
+diff -Naurp coreutils-8.27-orig/src/expand-common.c coreutils-8.27/src/expand-common.c
+--- coreutils-8.27-orig/src/expand-common.c 2017-03-01 11:22:55.000000000 -0600
++++ coreutils-8.27/src/expand-common.c 2017-03-11 23:49:06.757133570 -0600
+@@ -18,6 +18,7 @@
+
+ #include <stdio.h>
+ #include <sys/types.h>
++#include <mbfile.h>
+ #include "system.h"
+ #include "die.h"
+ #include "error.h"
+@@ -105,6 +106,119 @@ set_extend_size (uintmax_t tabval)
+ return ok;
+ }
+
++extern int
++set_utf_locale (void)
+{
-+ FILE *fp; /* Input strem. */
-+ mbstate_t i_state; /* Current shift state of the input stream. */
-+ mbstate_t i_state_bak; /* Back up the I_STATE. */
-+ mbstate_t o_state; /* Current shift state of the output stream. */
-+ char buf[MB_LEN_MAX + BUFSIZ]; /* For spooling a read byte sequence. */
-+ char *bufpos = buf; /* Next read position of BUF. */
-+ size_t buflen = 0; /* The length of the byte sequence in buf. */
-+ wchar_t wc; /* A gotten wide character. */
-+ size_t mblength; /* The byte size of a multibyte character
-+ which shows as same character as WC. */
-+ int tab_index = 0; /* Index in `tab_list' of next tabstop. */
-+ int column = 0; /* Column on screen of the next char. */
-+ int next_tab_column; /* Column the next tab stop is on. */
-+ int convert = 1; /* If nonzero, perform translations. */
-+
-+ fp = next_file ((FILE *) NULL);
-+ if (fp == NULL)
-+ return;
++ /*try using some predefined locale */
++ const char* predef_locales[] = {"C.UTF8","en_US.UTF8","en_GB.UTF8"};
+
-+ memset (&o_state, '\0', sizeof(mbstate_t));
-+ memset (&i_state, '\0', sizeof(mbstate_t));
++ const int predef_locales_count=3;
++ for (int i=0;i<predef_locales_count;i++)
++ {
++ if (setlocale(LC_ALL,predef_locales[i])!=NULL)
++ {
++ break;
++ }
++ else if (i==predef_locales_count-1)
++ {
++ return 1;
++ error (EXIT_FAILURE, errno, _("cannot set UTF-8 locale"));
++ }
++ }
++ return 0;
++}
+
-+ for (;;)
-+ {
-+ /* Refill the buffer BUF. */
-+ if (buflen < MB_LEN_MAX && !feof(fp) && !ferror(fp))
-+ {
-+ memmove (buf, bufpos, buflen);
-+ buflen += fread (buf + buflen, sizeof(char), BUFSIZ, fp);
-+ bufpos = buf;
-+ }
++extern bool
++check_utf_locale(void)
++{
++ char* locale = setlocale (LC_CTYPE , NULL);
++ if (locale == NULL)
++ {
++ return false;
++ }
++ else if (strcasestr(locale, "utf8") == NULL && strcasestr(locale, "utf-8") == NULL)
++ {
++ return false;
++ }
++ return true;
++}
+
-+ /* No character is left in BUF. */
-+ if (buflen < 1)
-+ {
-+ fp = next_file (fp);
++extern bool
++check_bom(FILE* fp, mb_file_t *mbf)
++{
++ int c;
+
-+ if (fp == NULL)
-+ break; /* No more files. */
-+ else
-+ {
-+ memset (&i_state, '\0', sizeof(mbstate_t));
-+ continue;
-+ }
-+ }
+
-+ /* Get a wide character. */
-+ i_state_bak = i_state;
-+ mblength = mbrtowc (&wc, bufpos, buflen, &i_state);
++ c=fgetc(fp);
+
-+ switch (mblength)
-+ {
-+ case (size_t)-1: /* illegal byte sequence. */
-+ case (size_t)-2:
-+ mblength = 1;
-+ i_state = i_state_bak;
-+ if (convert)
-+ {
-+ ++column;
-+ if (convert_entire_line == 0 && !isblank(*bufpos))
-+ convert = 0;
-+ }
-+ putchar (*bufpos);
-+ break;
-+
-+ case 0: /* null. */
-+ mblength = 1;
-+ if (convert && convert_entire_line == 0)
-+ convert = 0;
-+ putchar ('\0');
-+ break;
-+
-+ default:
-+ if (wc == L'\n') /* LF. */
-+ {
-+ tab_index = 0;
-+ column = 0;
-+ convert = 1;
-+ putchar ('\n');
-+ }
-+ else if (wc == L'\t' && convert) /* Tab. */
-+ {
-+ 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;
-+ }
-+ else
-+ next_tab_column = column + tab_size - column % tab_size;
++ /*test BOM header of the first file */
++ mbf->bufcount=0;
++ if (c == 0xEF)
++ {
++ c=fgetc(fp);
++ }
++ else
++ {
++ if (c != EOF)
++ {
++ ungetc(c,fp);
++ }
++ return false;
++ }
+
-+ while (column < next_tab_column)
-+ {
-+ putchar (' ');
-+ ++column;
-+ }
-+ }
-+ else /* Others. */
-+ {
-+ if (convert)
-+ {
-+ if (wc == L'\b')
-+ {
-+ if (column > 0)
-+ --column;
-+ }
-+ else
-+ {
-+ int width; /* The width of WC. */
-+
-+ width = wcwidth (wc);
-+ column += (width > 0) ? width : 0;
-+ if (convert_entire_line == 0 && !iswblank(wc))
-+ convert = 0;
-+ }
-+ }
-+ fwrite (bufpos, sizeof(char), mblength, stdout);
-+ }
-+ }
-+ buflen -= mblength;
-+ bufpos += mblength;
++ if (c == 0xBB)
++ {
++ c=fgetc(fp);
++ }
++ else
++ {
++ if ( c!= EOF )
++ {
++ mbf->buf[0]=(unsigned char) 0xEF;
++ mbf->bufcount=1;
++ ungetc(c,fp);
++ return false;
++ }
++ else
++ {
++ ungetc(0xEF,fp);
++ return false;
+ }
++ }
++ if (c == 0xBF)
++ {
++ mbf->bufcount=0;
++ return true;
++ }
++ else
++ {
++ if (c != EOF)
++ {
++ mbf->buf[0]=(unsigned char) 0xEF;
++ mbf->buf[1]=(unsigned char) 0xBB;
++ mbf->bufcount=2;
++ ungetc(c,fp);
++ return false;
++ }
++ else
++ {
++ mbf->buf[0]=(unsigned char) 0xEF;
++ mbf->bufcount=1;
++ ungetc(0xBB,fp);
++ return false;
++ }
++ }
++ return false;
+}
-+#endif
+
- int
- main (int argc, char **argv)
- {
-@@ -421,7 +579,12 @@ main (int argc, char **argv)
-
- file_list = (optind < argc ? &argv[optind] : stdin_argv);
-
-- expand ();
-+#if HAVE_MBRTOWC
-+ if (MB_CUR_MAX > 1)
-+ expand_multibyte ();
-+ else
-+#endif
-+ expand ();
-
- if (have_read_stdin && fclose (stdin) != 0)
- error (EXIT_FAILURE, errno, "-");
-diff -Naurp coreutils-8.25-orig/src/fold.c coreutils-8.25/src/fold.c
---- coreutils-8.25-orig/src/fold.c 2016-01-01 07:48:50.000000000 -0600
-+++ coreutils-8.25/src/fold.c 2016-02-08 19:07:10.302944622 -0600
-@@ -22,11 +22,33 @@
++extern void
++print_bom(void)
++{
++ putc (0xEF, stdout);
++ putc (0xBB, stdout);
++ putc (0xBF, stdout);
++}
++
+ /* Add the comma or blank separated list of tab stops STOPS
+ to the list of tab stops. */
+ extern void
+diff -Naurp coreutils-8.27-orig/src/expand-common.h coreutils-8.27/src/expand-common.h
+--- coreutils-8.27-orig/src/expand-common.h 2017-01-01 16:34:24.000000000 -0600
++++ coreutils-8.27/src/expand-common.h 2017-03-11 23:49:06.758133530 -0600
+@@ -34,6 +34,18 @@ extern size_t max_column_width;
+ /* The desired exit status. */
+ extern int exit_status;
+
++extern int
++set_utf_locale (void);
++
++extern bool
++check_utf_locale(void);
++
++extern bool
++check_bom(FILE* fp, mb_file_t *mbf);
++
++extern void
++print_bom(void);
++
+ /* Add tab stop TABVAL to the end of 'tab_list'. */
+ extern void
+ add_tab_stop (uintmax_t tabval);
+diff -Naurp coreutils-8.27-orig/src/fold.c coreutils-8.27/src/fold.c
+--- coreutils-8.27-orig/src/fold.c 2017-01-01 16:34:24.000000000 -0600
++++ coreutils-8.27/src/fold.c 2017-03-11 23:49:30.982169404 -0600
+@@ -22,12 +22,34 @@
#include <getopt.h>
#include <sys/types.h>
+#endif
+
#include "system.h"
+ #include "die.h"
#include "error.h"
#include "fadvise.h"
#include "xdectoint.h"
#define TAB_WIDTH 8
/* The official name of this program (e.g., no 'g' prefix). */
-@@ -34,20 +56,41 @@
+@@ -35,20 +57,41 @@
#define AUTHORS proper_name ("David MacKenzie")
{"spaces", no_argument, NULL, 's'},
{"width", required_argument, NULL, 'w'},
{GETOPT_HELP_OPTION_DECL},
-@@ -75,6 +118,7 @@ Wrap input lines in each FILE, writing t
+@@ -76,6 +119,7 @@ Wrap input lines in each FILE, writing t
fputs (_("\
-b, --bytes count bytes rather than columns\n\
-s, --spaces break at spaces\n\
-w, --width=WIDTH use WIDTH columns instead of 80\n\
"), stdout);
-@@ -92,7 +136,7 @@ Wrap input lines in each FILE, writing t
+@@ -93,7 +137,7 @@ Wrap input lines in each FILE, writing t
static size_t
adjust_column (size_t column, char c)
{
{
if (c == '\b')
{
-@@ -115,30 +159,14 @@ adjust_column (size_t column, char c)
+@@ -116,30 +160,14 @@ adjust_column (size_t column, char c)
to stdout, with maximum line length WIDTH.
Return true if successful. */
fadvise (istream, FADVISE_SEQUENTIAL);
-@@ -168,6 +196,15 @@ fold_file (char const *filename, size_t
+@@ -169,6 +197,15 @@ fold_file (char const *filename, size_t
bool found_blank = false;
size_t logical_end = offset_out;
/* Look for the last blank. */
while (logical_end)
{
-@@ -214,11 +251,221 @@ fold_file (char const *filename, size_t
+@@ -215,11 +252,220 @@ fold_file (char const *filename, size_t
line_out[offset_out++] = c;
}
+ }
+
+rescan:
-+ if (operating_mode == byte_mode) /* byte mode */
++ if (convfail)
++ increment = 1;
++ else if (wc == L'\n')
++ {
++ /* preserve newline */
++ fwrite (line_out, sizeof(char), offset_out, stdout);
++ START_NEW_LINE;
++ continue;
++ }
++ else if (operating_mode == byte_mode) /* byte mode */
+ increment = mblength;
+ else if (operating_mode == character_mode) /* character mode */
+ increment = 1;
-+ else /* column mode */
++ else /* column mode */
+ {
-+ if (convfail)
-+ increment = 1;
-+ else
++ switch (wc)
+ {
-+ switch (wc)
-+ {
-+ case L'\n':
-+ fwrite (line_out, sizeof(char), offset_out, stdout);
-+ START_NEW_LINE;
-+ continue;
-+
-+ case L'\b':
-+ increment = (column > 0) ? -1 : 0;
-+ break;
++ case L'\b':
++ increment = (column > 0) ? -1 : 0;
++ break;
+
-+ case L'\r':
-+ increment = -1 * column;
-+ break;
++ case L'\r':
++ increment = -1 * column;
++ break;
+
-+ case L'\t':
-+ increment = 8 - column % 8;
-+ break;
++ case L'\t':
++ increment = 8 - column % 8;
++ break;
+
-+ default:
-+ increment = wcwidth (wc);
-+ increment = (increment < 0) ? 0 : increment;
-+ }
++ default:
++ increment = wcwidth (wc);
++ increment = (increment < 0) ? 0 : increment;
+ }
+ }
+
+
+ if (istream == NULL)
+ {
-+ error (0, errno, "%s", quotef (filename));
++ error (0, errno, "%s", filename);
+ return 1;
+ }
+
if (ferror (istream))
{
error (0, saved_errno, "%s", quotef (filename));
-@@ -251,7 +498,8 @@ main (int argc, char **argv)
+@@ -252,7 +498,8 @@ main (int argc, char **argv)
atexit (close_stdout);
while ((optc = getopt_long (argc, argv, shortopts, longopts, NULL)) != -1)
{
-@@ -260,7 +508,15 @@ main (int argc, char **argv)
+@@ -261,7 +508,15 @@ main (int argc, char **argv)
switch (optc)
{
case 'b': /* Count bytes rather than columns. */
break;
case 's': /* Break at word boundaries. */
-diff -Naurp coreutils-8.25-orig/src/join.c coreutils-8.25/src/join.c
---- coreutils-8.25-orig/src/join.c 2016-01-13 05:08:59.000000000 -0600
-+++ coreutils-8.25/src/join.c 2016-02-08 19:07:10.303944625 -0600
-@@ -22,18 +22,32 @@
+diff -Naurp coreutils-8.27-orig/src/join.c coreutils-8.27/src/join.c
+--- coreutils-8.27-orig/src/join.c 2017-01-01 16:34:24.000000000 -0600
++++ coreutils-8.27/src/join.c 2017-03-11 23:47:13.091286290 -0600
+@@ -22,19 +22,33 @@
#include <sys/types.h>
#include <getopt.h>
+#endif
+
#include "system.h"
+ #include "die.h"
#include "error.h"
#include "fadvise.h"
#include "hard-locale.h"
/* The official name of this program (e.g., no 'g' prefix). */
#define PROGRAM_NAME "join"
-@@ -135,10 +149,12 @@ static struct outlist outlist_head;
+@@ -136,10 +150,12 @@ static struct outlist outlist_head;
/* Last element in 'outlist', where a new element can be added. */
static struct outlist *outlist_end = &outlist_head;
/* If nonzero, check that the input is correctly ordered. */
static enum
-@@ -275,13 +291,14 @@ xfields (struct line *line)
+@@ -276,13 +292,14 @@ xfields (struct line *line)
if (ptr == lim)
return;
{
/* Skip leading blanks before the first field. */
while (field_sep (*ptr))
-@@ -305,6 +322,147 @@ xfields (struct line *line)
+@@ -306,6 +323,147 @@ xfields (struct line *line)
extract_field (line, ptr, lim - ptr);
}
static void
freeline (struct line *line)
{
-@@ -326,56 +484,133 @@ keycmp (struct line const *line1, struct
+@@ -327,56 +485,133 @@ keycmp (struct line const *line1, struct
size_t jf_1, size_t jf_2)
{
/* Start of field to compare in each file. */
- diff = memcmp (beg1, beg2, MIN (len1, len2));
+ copy[0] = beg[0];
+ copy[1] = beg[1];
-+ }
-+
+ }
+
+ if (hard_LC_COLLATE)
+ {
+ diff = xmemcoll ((char *) copy[0], len[0], (char *) copy[1], len[1]);
+ free (copy[i]);
+
+ return diff;
- }
++ }
+ diff = memcmp (copy[0], copy[1], MIN (len[0], len[1]));
+
+ if (mallocd)
+ for (i = 0; i < 2; i++)
+ free (copy[i]);
+
-
++
if (diff)
return diff;
- return len1 < len2 ? -1 : len1 != len2;
}
/* Check that successive input lines PREV and CURRENT from input file
-@@ -467,6 +702,11 @@ get_line (FILE *fp, struct line **linep,
+@@ -468,6 +703,11 @@ get_line (FILE *fp, struct line **linep,
}
++line_no[which - 1];
xfields (line);
if (prevline[which - 1])
-@@ -566,21 +806,28 @@ prfield (size_t n, struct line const *li
+@@ -567,21 +807,28 @@ prfield (size_t n, struct line const *li
/* Output all the fields in line, other than the join field. */
prfield (i, line);
}
}
-@@ -591,7 +838,6 @@ static void
+@@ -592,7 +839,6 @@ static void
prjoin (struct line const *line1, struct line const *line2)
{
const struct outlist *outlist;
size_t field;
struct line const *line;
-@@ -625,7 +871,7 @@ prjoin (struct line const *line1, struct
+@@ -626,7 +872,7 @@ prjoin (struct line const *line1, struct
o = o->next;
if (o == NULL)
break;
}
putchar (eolchar);
}
-@@ -1103,21 +1349,46 @@ main (int argc, char **argv)
+@@ -1104,20 +1350,43 @@ main (int argc, char **argv)
case 't':
{
+ newtablen = 1;
if (! newtab)
- newtab = '\n'; /* '' => process the whole line. */
-+ {
+ newtab = (char*)"\n"; /* '' => process the whole line. */
-+ }
else if (optarg[1])
{
- if (STREQ (optarg, "\\0"))
- newtab = '\0';
- else
-- error (EXIT_FAILURE, 0, _("multi-character tab %s"),
-- quote (optarg));
+- die (EXIT_FAILURE, 0, _("multi-character tab %s"),
+- quote (optarg));
+ if (newtablen == 1 && newtab[1])
+ {
+ if (STREQ (newtab, "\\0"))
+ if (tab != NULL && strcmp (tab, newtab))
+ {
+ free (newtab);
-+ error (EXIT_FAILURE, 0, _("incompatible tabs"));
++ die (EXIT_FAILURE, 0, _("incompatible tabs"));
}
- if (0 <= tab && tab != newtab)
-- error (EXIT_FAILURE, 0, _("incompatible tabs"));
+- die (EXIT_FAILURE, 0, _("incompatible tabs"));
tab = newtab;
-- }
+ tablen = newtablen;
-+ }
+ }
break;
- case 'z':
-diff -Naurp coreutils-8.25-orig/src/pr.c coreutils-8.25/src/pr.c
---- coreutils-8.25-orig/src/pr.c 2016-01-01 07:48:50.000000000 -0600
-+++ coreutils-8.25/src/pr.c 2016-02-08 19:07:10.306944635 -0600
+diff -Naurp coreutils-8.27-orig/src/pr.c coreutils-8.27/src/pr.c
+--- coreutils-8.27-orig/src/pr.c 2017-01-01 16:34:24.000000000 -0600
++++ coreutils-8.27/src/pr.c 2017-03-11 23:47:13.094286139 -0600
@@ -311,6 +311,24 @@
#include <getopt.h>
+#endif
+
#include "system.h"
+ #include "die.h"
#include "error.h"
- #include "fadvise.h"
-@@ -323,6 +341,18 @@
+@@ -324,6 +342,18 @@
#include "xstrtol.h"
#include "xdectoint.h"
/* The official name of this program (e.g., no 'g' prefix). */
#define PROGRAM_NAME "pr"
-@@ -415,7 +445,20 @@ struct COLUMN
+@@ -416,7 +446,20 @@ struct COLUMN
typedef struct COLUMN COLUMN;
static bool read_line (COLUMN *p);
static bool print_page (void);
static bool print_stored (COLUMN *p);
-@@ -427,6 +470,7 @@ static void add_line_number (COLUMN *p);
+@@ -428,6 +471,7 @@ static void add_line_number (COLUMN *p);
static void getoptnum (const char *n_str, int min, int *num,
const char *errfmt);
static void getoptarg (char *arg, char switch_char, char *character,
int *number);
static void print_files (int number_of_files, char **av);
static void init_parameters (int number_of_files);
-@@ -440,7 +484,6 @@ static void store_char (char c);
+@@ -441,7 +485,6 @@ static void store_char (char c);
static void pad_down (unsigned int lines);
static void read_rest_of_line (COLUMN *p);
static void skip_read (COLUMN *p, int column_number);
static void cleanup (void);
static void print_sep_string (void);
static void separator_string (const char *optarg_S);
-@@ -452,7 +495,7 @@ static COLUMN *column_vector;
+@@ -453,7 +496,7 @@ static COLUMN *column_vector;
we store the leftmost columns contiguously in buff.
To print a line from buff, get the index of the first character
from line_vector[i], and print up to line_vector[i + 1]. */
/* Index of the position in buff where the next character
will be stored. */
-@@ -556,7 +599,7 @@ static int chars_per_column;
+@@ -557,7 +600,7 @@ static int chars_per_column;
static bool untabify_input = false;
/* (-e) The input tab character. */
/* (-e) Tabstops are at chars_per_tab, 2*chars_per_tab, 3*chars_per_tab, ...
where the leftmost column is 1. */
-@@ -566,7 +609,10 @@ static int chars_per_input_tab = 8;
+@@ -567,7 +610,10 @@ static int chars_per_input_tab = 8;
static bool tabify_output = false;
/* (-i) The output tab character. */
/* (-i) The width of the output tab. */
static int chars_per_output_tab = 8;
-@@ -636,7 +682,13 @@ static int line_number;
+@@ -637,7 +683,13 @@ static int line_number;
static bool numbered_lines = false;
/* (-n) Character which follows each line number. */
/* (-n) line counting starts with 1st line of input file (not with 1st
line of 1st page printed). */
-@@ -689,6 +741,7 @@ static bool use_col_separator = false;
+@@ -690,6 +742,7 @@ static bool use_col_separator = false;
-a|COLUMN|-m is a 'space' and with the -J option a 'tab'. */
- static char *col_sep_string = (char *) "";
+ static char const *col_sep_string = "";
static int col_sep_length = 0;
+static int col_sep_width = 0;
static char *column_separator = (char *) " ";
static char *line_separator = (char *) "\t";
-@@ -839,6 +892,13 @@ separator_string (const char *optarg_S)
- col_sep_length = (int) strlen (optarg_S);
- col_sep_string = xmalloc (col_sep_length + 1);
- strcpy (col_sep_string, optarg_S);
+@@ -851,6 +904,13 @@ separator_string (const char *optarg_S)
+ integer_overflow ();
+ col_sep_length = len;
+ col_sep_string = optarg_S;
+
+#if HAVE_MBRTOWC
+ if (MB_CUR_MAX > 1)
}
int
-@@ -863,6 +923,21 @@ main (int argc, char **argv)
+@@ -875,6 +935,21 @@ main (int argc, char **argv)
atexit (close_stdout);
+
n_files = 0;
file_names = (argc > 1
- ? xmalloc ((argc - 1) * sizeof (char *))
-@@ -939,8 +1014,12 @@ main (int argc, char **argv)
+ ? xnmalloc (argc - 1, sizeof (char *))
+@@ -951,8 +1026,12 @@ main (int argc, char **argv)
break;
case 'e':
if (optarg)
/* Could check tab width > 0. */
untabify_input = true;
break;
-@@ -953,8 +1032,12 @@ main (int argc, char **argv)
+@@ -965,8 +1044,12 @@ main (int argc, char **argv)
break;
case 'i':
if (optarg)
/* Could check tab width > 0. */
tabify_output = true;
break;
-@@ -972,8 +1055,8 @@ main (int argc, char **argv)
+@@ -984,8 +1067,8 @@ main (int argc, char **argv)
case 'n':
numbered_lines = true;
if (optarg)
break;
case 'N':
skip_count = false;
-@@ -997,7 +1080,7 @@ main (int argc, char **argv)
- old_s = false;
+@@ -1010,6 +1093,7 @@ main (int argc, char **argv)
/* Reset an additional input of -s, -S dominates -s */
- col_sep_string = bad_cast ("");
-- col_sep_length = 0;
-+ col_sep_length = col_sep_width = 0;
+ col_sep_string = "";
+ col_sep_length = 0;
++ col_sep_width = 0;
use_col_separator = true;
if (optarg)
separator_string (optarg);
-@@ -1152,10 +1235,45 @@ getoptnum (const char *n_str, int min, i
+@@ -1166,10 +1250,45 @@ getoptnum (const char *n_str, int min, i
a number. */
static void
if (*arg)
{
long int tmp_long;
-@@ -1177,6 +1295,11 @@ static void
+@@ -1191,6 +1310,11 @@ static void
init_parameters (int number_of_files)
{
int chars_used_by_number = 0;
lines_per_body = lines_per_page - lines_per_header - lines_per_footer;
if (lines_per_body <= 0)
-@@ -1214,7 +1337,7 @@ init_parameters (int number_of_files)
+@@ -1228,7 +1352,7 @@ init_parameters (int number_of_files)
else
col_sep_string = column_separator;
use_col_separator = true;
}
/* It's rather pointless to define a TAB separator with column
-@@ -1244,11 +1367,11 @@ init_parameters (int number_of_files)
+@@ -1258,11 +1382,11 @@ init_parameters (int number_of_files)
+ TAB_WIDTH (chars_per_input_tab, chars_per_number); */
/* Estimate chars_per_text without any margin and keep it constant. */
/* The number is part of the column width unless we are
printing files in parallel. */
-@@ -1257,7 +1380,7 @@ init_parameters (int number_of_files)
+@@ -1271,7 +1395,7 @@ init_parameters (int number_of_files)
}
- chars_per_column = (chars_per_line - chars_used_by_number
-- - (columns - 1) * col_sep_length) / columns;
-+ - (columns - 1) * col_sep_width) / columns;
-
- if (chars_per_column < 1)
- error (EXIT_FAILURE, 0, _("page width too narrow"));
-@@ -1275,7 +1398,7 @@ init_parameters (int number_of_files)
+ int sep_chars, useful_chars;
+- if (INT_MULTIPLY_WRAPV (columns - 1, col_sep_length, &sep_chars))
++ if (INT_MULTIPLY_WRAPV (columns - 1, col_sep_width, &sep_chars))
+ sep_chars = INT_MAX;
+ if (INT_SUBTRACT_WRAPV (chars_per_line - chars_used_by_number, sep_chars,
+ &useful_chars))
+@@ -1294,7 +1418,7 @@ init_parameters (int number_of_files)
We've to use 8 as the lower limit, if we use chars_per_default_tab = 8
to expand a tab which is not an input_tab-char. */
free (clump_buff);
}
/* Open the necessary files,
-@@ -1383,7 +1506,7 @@ init_funcs (void)
+@@ -1402,7 +1526,7 @@ init_funcs (void)
/* Enlarge p->start_position of first column to use the same form of
padding_not_printed with all columns. */
/* This loop takes care of all but the rightmost column. */
-@@ -1417,7 +1540,7 @@ init_funcs (void)
+@@ -1436,7 +1560,7 @@ init_funcs (void)
}
else
{
h_next = h + chars_per_column;
}
}
-@@ -1708,9 +1831,9 @@ static void
+@@ -1727,9 +1851,9 @@ static void
align_column (COLUMN *p)
{
padding_not_printed = p->start_position;
-- if (padding_not_printed - col_sep_length > 0)
-+ if (padding_not_printed - col_sep_width > 0)
+- if (col_sep_length < padding_not_printed)
++ if (col_sep_width < padding_not_printed)
{
- pad_across_to (padding_not_printed - col_sep_length);
+ pad_across_to (padding_not_printed - col_sep_width);
padding_not_printed = ANYWHERE;
}
-@@ -1981,13 +2104,13 @@ store_char (char c)
+@@ -2004,13 +2128,13 @@ store_char (char c)
/* May be too generous. */
buff = X2REALLOC (buff, &buff_allocated);
}
char *s;
int num_width;
-@@ -2004,22 +2127,24 @@ add_line_number (COLUMN *p)
+@@ -2027,22 +2151,24 @@ add_line_number (COLUMN *p)
/* Tabification is assumed for multiple columns, also for n-separators,
but 'default n-separator = TAB' hasn't been given priority over
equal column_width also specified by POSIX. */
output_position = POS_AFTER_TAB (chars_per_output_tab,
output_position);
}
-@@ -2180,7 +2305,7 @@ print_white_space (void)
+@@ -2203,7 +2329,7 @@ print_white_space (void)
while (goal - h_old > 1
&& (h_new = POS_AFTER_TAB (chars_per_output_tab, h_old)) <= goal)
{
h_old = h_new;
}
while (++h_old <= goal)
-@@ -2200,6 +2325,7 @@ print_sep_string (void)
+@@ -2223,6 +2349,7 @@ print_sep_string (void)
{
- char *s;
+ char const *s = col_sep_string;
int l = col_sep_length;
+ int not_space_flag;
- s = col_sep_string;
-
-@@ -2213,6 +2339,7 @@ print_sep_string (void)
+ if (separators_not_printed <= 0)
+ {
+@@ -2234,6 +2361,7 @@ print_sep_string (void)
{
for (; separators_not_printed > 0; --separators_not_printed)
{
while (l-- > 0)
{
/* 3 types of sep_strings: spaces only, spaces and chars,
-@@ -2226,12 +2353,15 @@ print_sep_string (void)
+@@ -2247,12 +2375,15 @@ print_sep_string (void)
}
else
{
/* sep_string ends with some spaces */
if (spaces_not_printed > 0)
print_white_space ();
-@@ -2259,7 +2389,7 @@ print_clump (COLUMN *p, int n, char *clu
+@@ -2280,7 +2411,7 @@ print_clump (COLUMN *p, int n, char *clu
required number of tabs and spaces. */
static void
{
if (tabify_output)
{
-@@ -2283,6 +2413,74 @@ print_char (char c)
+@@ -2304,6 +2435,74 @@ print_char (char c)
putchar (c);
}
/* Skip to page PAGE before printing.
PAGE may be larger than total number of pages. */
-@@ -2462,9 +2660,9 @@ read_line (COLUMN *p)
+@@ -2483,9 +2682,9 @@ read_line (COLUMN *p)
align_empty_cols = false;
}
-- if (padding_not_printed - col_sep_length > 0)
-+ if (padding_not_printed - col_sep_width > 0)
+- if (col_sep_length < padding_not_printed)
++ if (col_sep_width < padding_not_printed)
{
- pad_across_to (padding_not_printed - col_sep_length);
+ pad_across_to (padding_not_printed - col_sep_width);
padding_not_printed = ANYWHERE;
}
-@@ -2534,7 +2732,7 @@ print_stored (COLUMN *p)
+@@ -2555,7 +2754,7 @@ print_stored (COLUMN *p)
int i;
int line = p->current_line++;
/* FIXME
UMR: Uninitialized memory read:
* This is occurring while in:
-@@ -2546,7 +2744,7 @@ print_stored (COLUMN *p)
+@@ -2567,7 +2766,7 @@ print_stored (COLUMN *p)
xmalloc [xmalloc.c:94]
init_store_cols [pr.c:1648]
*/
pad_vertically = true;
-@@ -2565,9 +2763,9 @@ print_stored (COLUMN *p)
+@@ -2586,9 +2785,9 @@ print_stored (COLUMN *p)
}
}
-- if (padding_not_printed - col_sep_length > 0)
-+ if (padding_not_printed - col_sep_width > 0)
+- if (col_sep_length < padding_not_printed)
++ if (col_sep_width < padding_not_printed)
{
- pad_across_to (padding_not_printed - col_sep_length);
+ pad_across_to (padding_not_printed - col_sep_width);
padding_not_printed = ANYWHERE;
}
-@@ -2580,8 +2778,8 @@ print_stored (COLUMN *p)
+@@ -2601,8 +2800,8 @@ print_stored (COLUMN *p)
if (spaces_not_printed == 0)
{
output_position = p->start_position + end_vector[line];
}
return true;
-@@ -2600,7 +2798,7 @@ print_stored (COLUMN *p)
+@@ -2621,7 +2820,7 @@ print_stored (COLUMN *p)
number of characters is 1.) */
static int
{
unsigned char uc = c;
char *s = clump_buff;
-@@ -2610,10 +2808,10 @@ char_to_clump (char c)
+@@ -2631,10 +2830,10 @@ char_to_clump (char c)
int chars;
int chars_per_c = 8;
{
width = TAB_WIDTH (chars_per_c, input_position);
-@@ -2694,6 +2892,164 @@ char_to_clump (char c)
+@@ -2715,6 +2914,164 @@ char_to_clump (char c)
return chars;
}
/* We've just printed some files and need to clean up things before
looking for more options and printing the next batch of files.
-diff -Naurp coreutils-8.25-orig/src/sort.c coreutils-8.25/src/sort.c
---- coreutils-8.25-orig/src/sort.c 2016-01-16 13:09:33.000000000 -0600
-+++ coreutils-8.25/src/sort.c 2016-02-08 19:07:10.310944648 -0600
+diff -Naurp coreutils-8.27-orig/src/sort.c coreutils-8.27/src/sort.c
+--- coreutils-8.27-orig/src/sort.c 2017-01-01 16:34:24.000000000 -0600
++++ coreutils-8.27/src/sort.c 2017-03-11 23:49:22.416505389 -0600
@@ -29,6 +29,14 @@
#include <sys/wait.h>
#include <signal.h>
+
#include "system.h"
#include "argmatch.h"
- #include "error.h"
-@@ -163,14 +171,39 @@ static int decimal_point;
+ #include "die.h"
+@@ -165,14 +173,39 @@ static int decimal_point;
/* Thousands separator; if -1, then there isn't one. */
static int thousands_sep;
/* The kind of blanks for '-b' to skip in various options. */
enum blanktype { bl_start, bl_end, bl_both };
-@@ -344,13 +377,11 @@ static bool reverse;
+@@ -346,13 +379,11 @@ static bool reverse;
they were read if all keys compare equal. */
static bool stable;
/* Flag to remove consecutive duplicate lines from the output.
Only the last of a sequence of equal lines will be output. */
-@@ -810,6 +841,46 @@ reap_all (void)
+@@ -811,6 +842,46 @@ reap_all (void)
reap (-1);
}
/* Clean up any remaining temporary files. */
static void
-@@ -1254,7 +1325,7 @@ zaptemp (char const *name)
+@@ -1255,7 +1326,7 @@ zaptemp (char const *name)
free (node);
}
static int
struct_month_cmp (void const *m1, void const *m2)
-@@ -1269,7 +1340,7 @@ struct_month_cmp (void const *m1, void c
+@@ -1270,7 +1341,7 @@ struct_month_cmp (void const *m1, void c
/* Initialize the character class tables. */
static void
{
size_t i;
-@@ -1281,7 +1352,7 @@ inittables (void)
+@@ -1282,7 +1353,7 @@ inittables (void)
fold_toupper[i] = toupper (i);
}
/* If we're not in the "C" locale, read different names for months. */
if (hard_LC_TIME)
{
-@@ -1363,6 +1434,84 @@ specify_nmerge (int oi, char c, char con
+@@ -1364,6 +1435,84 @@ specify_nmerge (int oi, char c, char con
xstrtol_fatal (e, oi, c, long_options, s);
}
/* Specify the amount of main memory to use when sorting. */
static void
specify_sort_size (int oi, char c, char const *s)
-@@ -1596,7 +1745,7 @@ buffer_linelim (struct buffer const *buf
+@@ -1597,7 +1746,7 @@ buffer_linelim (struct buffer const *buf
by KEY in LINE. */
static char *
{
char *ptr = line->text, *lim = ptr + line->length - 1;
size_t sword = key->sword;
-@@ -1605,10 +1754,10 @@ begfield (struct line const *line, struc
+@@ -1606,10 +1755,10 @@ begfield (struct line const *line, struc
/* The leading field separator itself is included in a field when -t
is absent. */
++ptr;
if (ptr < lim)
++ptr;
-@@ -1634,11 +1783,70 @@ begfield (struct line const *line, struc
+@@ -1635,11 +1784,70 @@ begfield (struct line const *line, struc
return ptr;
}
{
char *ptr = line->text, *lim = ptr + line->length - 1;
size_t eword = key->eword, echar = key->echar;
-@@ -1653,10 +1861,10 @@ limfield (struct line const *line, struc
+@@ -1654,10 +1862,10 @@ limfield (struct line const *line, struc
'beginning' is the first character following the delimiting TAB.
Otherwise, leave PTR pointing at the first 'blank' character after
the preceding field. */
++ptr;
if (ptr < lim && (eword || echar))
++ptr;
-@@ -1702,10 +1910,10 @@ limfield (struct line const *line, struc
+@@ -1703,10 +1911,10 @@ limfield (struct line const *line, struc
*/
/* Make LIM point to the end of (one byte past) the current field. */
if (newlim)
lim = newlim;
}
-@@ -1736,6 +1944,130 @@ limfield (struct line const *line, struc
+@@ -1737,6 +1945,130 @@ limfield (struct line const *line, struc
return ptr;
}
/* Fill BUF reading from FP, moving buf->left bytes from the end
of buf->buf to the beginning first. If EOF is reached and the
file wasn't terminated by a newline, supply one. Set up BUF's line
-@@ -1822,8 +2154,22 @@ fillbuf (struct buffer *buf, FILE *fp, c
+@@ -1823,8 +2155,22 @@ fillbuf (struct buffer *buf, FILE *fp, c
else
{
if (key->skipsblanks)
line->keybeg = line_start;
}
}
-@@ -1944,7 +2290,7 @@ human_numcompare (char const *a, char co
+@@ -1958,12 +2304,10 @@ find_unit_order (char const *number)
+ <none/unknown> < K/k < M < G < T < P < E < Z < Y */
+
+ static int
+-human_numcompare (char const *a, char const *b)
++human_numcompare (char *a, char *b)
+ {
+- while (blanks[to_uchar (*a)])
+- a++;
+- while (blanks[to_uchar (*b)])
+- b++;
++ skipblanks(&a, a + strlen(a));
++ skipblanks(&b, b + strlen(b));
+
+ int diff = find_unit_order (a) - find_unit_order (b);
+ return (diff ? diff : strnumcmp (a, b, decimal_point, thousands_sep));
+@@ -1974,7 +2318,7 @@ human_numcompare (char const *a, char co
hideously fast. */
static int
{
while (blanks[to_uchar (*a)])
a++;
-@@ -1954,6 +2300,25 @@ numcompare (char const *a, char const *b
+@@ -1984,6 +2328,25 @@ numcompare (char const *a, char const *b
return strnumcmp (a, b, decimal_point, thousands_sep);
}
/* Work around a problem whereby the long double value returned by glibc's
strtold ("NaN", ...) contains uninitialized bits: clear all bytes of
A and B before calling strtold. FIXME: remove this function once
-@@ -2004,7 +2369,7 @@ general_numcompare (char const *sa, char
+@@ -2034,7 +2397,7 @@ general_numcompare (char const *sa, char
Return 0 if the name in S is not recognized. */
static int
{
size_t lo = 0;
size_t hi = MONTHS_PER_YEAR;
-@@ -2280,15 +2645,14 @@ debug_key (struct line const *line, stru
+@@ -2310,15 +2673,14 @@ debug_key (struct line const *line, stru
char saved = *lim;
*lim = '\0';
else if (key->general_numeric)
ignore_value (strtold (beg, &tighter_lim));
else if (key->numeric || key->human_numeric)
-@@ -2432,7 +2796,7 @@ key_warnings (struct keyfield const *gke
- bool maybe_space_aligned = !hard_LC_COLLATE && default_key_compare (key)
- && !(key->schar || key->echar);
+@@ -2452,7 +2814,7 @@ key_warnings (struct keyfield const *gke
+ /* Warn about significant leading blanks. */
+ bool implicit_skip = key_numeric (key) || key->month;
bool line_offset = key->eword == 0 && key->echar != 0; /* -k1.x,1.y */
-- if (!gkey_only && tab == TAB_DEFAULT && !line_offset
-+ if (!gkey_only && !tab_length && !line_offset
- && ((!key->skipsblanks && !(implicit_skip || maybe_space_aligned))
+- if (!zero_width && !gkey_only && tab == TAB_DEFAULT && !line_offset
++ if (!zero_width && !gkey_only && !tab_length && !line_offset
+ && ((!key->skipsblanks && !implicit_skip)
|| (!key->skipsblanks && key->schar)
|| (!key->skipeblanks && key->echar)))
-@@ -2490,11 +2854,87 @@ key_warnings (struct keyfield const *gke
+@@ -2510,11 +2872,87 @@ key_warnings (struct keyfield const *gke
error (0, 0, _("option '-r' only applies to last-resort comparison"));
}
{
struct keyfield *key = keylist;
-@@ -2579,7 +3019,7 @@ keycompare (struct line const *a, struct
+@@ -2599,7 +3037,7 @@ keycompare (struct line const *a, struct
else if (key->human_numeric)
diff = human_numcompare (ta, tb);
else if (key->month)
else if (key->random)
diff = compare_random (ta, tlena, tb, tlenb);
else if (key->version)
-@@ -2695,6 +3135,211 @@ keycompare (struct line const *a, struct
+@@ -2715,6 +3153,211 @@ keycompare (struct line const *a, struct
return key->reverse ? -diff : diff;
}
/* Compare two lines A and B, returning negative, zero, or positive
depending on whether A compares less than, equal to, or greater than B. */
-@@ -2722,7 +3367,7 @@ compare (struct line const *a, struct li
+@@ -2742,7 +3385,7 @@ compare (struct line const *a, struct li
diff = - NONZERO (blen);
else if (blen == 0)
diff = 1;
{
/* Note xmemcoll0 is a performance enhancement as
it will not unconditionally write '\0' after the
-@@ -4121,6 +4766,7 @@ set_ordering (char const *s, struct keyf
+@@ -4139,6 +4782,7 @@ set_ordering (char const *s, struct keyf
break;
case 'f':
key->translate = fold_toupper;
break;
case 'g':
key->general_numeric = true;
-@@ -4199,7 +4845,7 @@ main (int argc, char **argv)
+@@ -4218,7 +4862,7 @@ main (int argc, char **argv)
initialize_exit_failure (SORT_FAILURE);
hard_LC_COLLATE = hard_locale (LC_COLLATE);
hard_LC_TIME = hard_locale (LC_TIME);
#endif
-@@ -4220,6 +4866,29 @@ main (int argc, char **argv)
+@@ -4239,6 +4883,29 @@ main (int argc, char **argv)
thousands_sep = -1;
}
have_read_stdin = false;
inittables ();
-@@ -4494,13 +5163,34 @@ main (int argc, char **argv)
+@@ -4513,13 +5180,34 @@ main (int argc, char **argv)
case 't':
{
+ size_t newtab_length = 1;
+ strncpy (newtab, optarg, MB_LEN_MAX);
+ if (! newtab[0])
- error (SORT_FAILURE, 0, _("empty tab"));
+ die (SORT_FAILURE, 0, _("empty tab"));
- if (optarg[1])
+#if HAVE_MBRTOWC
+ if (MB_CUR_MAX > 1)
else
{
/* Provoke with 'sort -txx'. Complain about
-@@ -4511,9 +5201,12 @@ main (int argc, char **argv)
- quote (optarg));
+@@ -4530,9 +5218,11 @@ main (int argc, char **argv)
+ quote (optarg));
}
}
- if (tab != TAB_DEFAULT && tab != newtab)
-+ if (tab_length
-+ && (tab_length != newtab_length
-+ || memcmp (tab, newtab, tab_length) != 0))
- error (SORT_FAILURE, 0, _("incompatible tabs"));
++ if (tab_length && (tab_length != newtab_length
++ || memcmp (tab, newtab, tab_length) != 0))
+ die (SORT_FAILURE, 0, _("incompatible tabs"));
- tab = newtab;
+ memcpy (tab, newtab, newtab_length);
+ tab_length = newtab_length;
}
break;
-@@ -4751,12 +5444,10 @@ main (int argc, char **argv)
+@@ -4770,12 +5460,10 @@ main (int argc, char **argv)
sort (files, nfiles, outfile, nthreads);
}
-#endif
if (have_read_stdin && fclose (stdin) == EOF)
- die (_("close failed"), "-");
-diff -Naurp coreutils-8.25-orig/src/unexpand.c coreutils-8.25/src/unexpand.c
---- coreutils-8.25-orig/src/unexpand.c 2016-01-01 07:48:50.000000000 -0600
-+++ coreutils-8.25/src/unexpand.c 2016-02-08 19:07:10.311944651 -0600
-@@ -38,12 +38,29 @@
+ sort_die (_("close failed"), "-");
+diff -Naurp coreutils-8.27-orig/src/unexpand.c coreutils-8.27/src/unexpand.c
+--- coreutils-8.27-orig/src/unexpand.c 2017-01-01 16:34:24.000000000 -0600
++++ coreutils-8.27/src/unexpand.c 2017-03-11 23:49:06.758133530 -0600
+@@ -38,6 +38,9 @@
#include <stdio.h>
#include <getopt.h>
#include <sys/types.h>
+
-+/* Get mbstate_t, mbrtowc(), wcwidth(). */
-+#if HAVE_WCHAR_H
-+# include <wchar.h>
-+#endif
++#include <mbfile.h>
+
#include "system.h"
- #include "error.h"
- #include "fadvise.h"
- #include "quote.h"
+ #include "die.h"
#include "xstrndup.h"
+@@ -107,24 +110,47 @@ unexpand (void)
+ {
+ /* Input stream. */
+ FILE *fp = next_file (NULL);
++ mb_file_t mbf;
+
+ /* 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;
++ mbf_char_t *pending_blank;
++ /* True if the starting locale is utf8. */
++ bool using_utf_locale;
++
++ /* True if the first file contains BOM header. */
++ bool found_bom;
++ using_utf_locale=check_utf_locale();
+
+ if (!fp)
+ return;
++ mbf_init (mbf, fp);
++ found_bom=check_bom(fp,&mbf);
-+/* MB_LEN_MAX is incorrectly defined to be 1 in at least one GCC
-+ installation; work around this configuration error. */
-+#if !defined MB_LEN_MAX || MB_LEN_MAX < 2
-+# define MB_LEN_MAX 16
-+#endif
-+
-+/* Some systems, like BeOS, have multibyte encodings but lack mbstate_t. */
-+#if HAVE_MBRTOWC && defined mbstate_t
-+# define mbrtowc(pwc, s, n, ps) (mbrtowc) (pwc, s, n, 0)
-+#endif
-+
- /* The official name of this program (e.g., no 'g' prefix). */
- #define PROGRAM_NAME "unexpand"
-
-@@ -103,6 +120,210 @@ static struct option const longopts[] =
- {NULL, 0, NULL, 0}
- };
-
-+static FILE *next_file (FILE *fp);
-+
-+#if HAVE_MBRTOWC
-+static void
-+unexpand_multibyte (void)
-+{
-+ FILE *fp; /* Input stream. */
-+ mbstate_t i_state; /* Current shift state of the input stream. */
-+ mbstate_t i_state_bak; /* Back up the I_STATE. */
-+ mbstate_t o_state; /* Current shift state of the output stream. */
-+ char buf[MB_LEN_MAX + BUFSIZ]; /* For spooling a read byte sequence. */
-+ char *bufpos = buf; /* Next read position of BUF. */
-+ size_t buflen = 0; /* The length of the byte sequence in buf. */
-+ wint_t wc; /* A gotten wide character. */
-+ size_t mblength; /* The byte size of a multibyte character
-+ which shows as same character as WC. */
-+ bool prev_tab = false;
-+
-+ /* Index in `tab_list' of next tabstop: */
-+ int tab_index = 0; /* For calculating width of pending tabs. */
-+ int print_tab_index = 0; /* For printing as many tabs as possible. */
-+ unsigned int column = 0; /* Column on screen of next char. */
-+ int next_tab_column; /* Column the next tab stop is on. */
-+ int convert = 1; /* If nonzero, perform translations. */
-+ unsigned int pending = 0; /* Pending columns of blanks. */
-+
-+ fp = next_file ((FILE *) NULL);
-+ if (fp == NULL)
-+ return;
-+
-+ memset (&o_state, '\0', sizeof(mbstate_t));
-+ memset (&i_state, '\0', sizeof(mbstate_t));
++ if (using_utf_locale == false && found_bom == true)
++ {
++ /*try using some predefined locale */
+
-+ for (;;)
++ if (set_utf_locale () != 0)
+ {
-+ if (buflen < MB_LEN_MAX && !feof(fp) && !ferror(fp))
-+ {
-+ memmove (buf, bufpos, buflen);
-+ buflen += fread (buf + buflen, sizeof(char), BUFSIZ, fp);
-+ bufpos = buf;
-+ }
-+
-+ /* Get a wide character. */
-+ if (buflen < 1)
-+ {
-+ mblength = 1;
-+ wc = WEOF;
-+ }
-+ else
-+ {
-+ i_state_bak = i_state;
-+ mblength = mbrtowc ((wchar_t *)&wc, bufpos, buflen, &i_state);
-+ }
-+
-+ if (mblength == (size_t)-1 || mblength == (size_t)-2)
-+ {
-+ i_state = i_state_bak;
-+ wc = L'\0';
-+ }
-+
-+ if (wc == L' ' && convert && column < INT_MAX)
-+ {
-+ ++pending;
-+ ++column;
-+ }
-+ else if (wc == L'\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 = 0; /* Ran out of tab stops. */
-+ goto flush_pend_mb;
-+ }
-+ }
-+ else
-+ {
-+ next_tab_column = column + tab_size - column % tab_size;
-+ }
-+ pending += next_tab_column - column;
-+ column = next_tab_column;
-+ }
-+ else
-+ {
-+flush_pend_mb:
-+ /* Flush pending spaces. Print as many tabs as possible,
-+ then print the rest as spaces. */
-+ if (pending == 1 && column != 1 && !prev_tab)
-+ {
-+ putchar (' ');
-+ pending = 0;
-+ }
-+ column -= pending;
-+ while (pending > 0)
-+ {
-+ 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
-+ {
-+ --print_tab_index;
-+ column += pending;
-+ while (pending != 0)
-+ {
-+ putchar (' ');
-+ pending--;
-+ }
-+ }
-+ }
-+
-+ if (wc == WEOF)
-+ {
-+ fp = next_file (fp);
-+ if (fp == NULL)
-+ break; /* No more files. */
-+ else
-+ {
-+ memset (&i_state, '\0', sizeof(mbstate_t));
-+ continue;
-+ }
-+ }
-+
-+ if (mblength == (size_t)-1 || mblength == (size_t)-2)
-+ {
-+ if (convert)
-+ {
-+ ++column;
-+ if (convert_entire_line == 0)
-+ convert = 0;
-+ }
-+ mblength = 1;
-+ putchar (buf[0]);
-+ }
-+ else if (mblength == 0)
-+ {
-+ if (convert && convert_entire_line == 0)
-+ convert = 0;
-+ mblength = 1;
-+ putchar ('\0');
-+ }
-+ else
-+ {
-+ if (convert)
-+ {
-+ if (wc == L'\b')
-+ {
-+ if (column > 0)
-+ --column;
-+ }
-+ else
-+ {
-+ int width; /* The width of WC. */
-+
-+ width = wcwidth (wc);
-+ column += (width > 0) ? width : 0;
-+ if (convert_entire_line == 0)
-+ convert = 0;
-+ }
-+ }
-+
-+ if (wc == L'\n')
-+ {
-+ tab_index = print_tab_index = 0;
-+ column = pending = 0;
-+ convert = 1;
-+ }
-+ fwrite (bufpos, sizeof(char), mblength, stdout);
-+ }
-+ }
-+ prev_tab = wc == L'\t';
-+ buflen -= mblength;
-+ bufpos += mblength;
++ error (EXIT_FAILURE, errno, _("cannot set UTF-8 locale"));
+ }
-+}
-+#endif
++ }
+ /* 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);
++ pending_blank = xmalloc (max_column_width * sizeof (mbf_char_t));
+
++ if (found_bom == true)
++ {
++ print_bom();
++ }
+
+ while (true)
+ {
+ /* Input character, or EOF. */
+- int c;
++ mbf_char_t c;
+
+ /* If true, perform translations. */
+ bool convert = true;
+@@ -158,12 +184,44 @@ unexpand (void)
+
+ do
+ {
+- while ((c = getc (fp)) < 0 && (fp = next_file (fp)))
+- continue;
++ while (true) {
++ mbf_getc (c, mbf);
++ if ((mb_iseof (c)) && (fp = next_file (fp)))
++ {
++ mbf_init (mbf, fp);
++ if (fp!=NULL)
++ {
++ if (check_bom(fp,&mbf)==true)
++ {
++ /*Not the first file - check BOM header*/
++ if (using_utf_locale==false && found_bom==false)
++ {
++ /*BOM header in subsequent file but not in the first one. */
++ error (EXIT_FAILURE, errno, _("combination of files with and without BOM header"));
++ }
++ }
++ else
++ {
++ if(using_utf_locale==false && found_bom==true)
++ {
++ /*First file conatined BOM header - locale was switched to UTF
++ /*all subsequent files should contain BOM. */
++ error (EXIT_FAILURE, errno, _("combination of files with and without BOM header"));
++ }
++ }
++ }
++ continue;
++ }
++ else
++ {
++ break;
++ }
++ }
+
- void
- usage (int status)
- {
-@@ -523,7 +744,12 @@ main (int argc, char **argv)
- file_list = (optind < argc ? &argv[optind] : stdin_argv);
+ if (convert)
+ {
+- bool blank = !! isblank (c);
++ bool blank = mb_isblank (c);
-- unexpand ();
-+#if HAVE_MBRTOWC
-+ if (MB_CUR_MAX > 1)
-+ unexpand_multibyte ();
-+ else
-+#endif
-+ unexpand ();
+ if (blank)
+ {
+@@ -180,16 +238,16 @@ unexpand (void)
+ if (next_tab_column < column)
+ die (EXIT_FAILURE, 0, _("input line is too long"));
+
+- if (c == '\t')
++ if (mb_iseq (c, '\t'))
+ {
+ column = next_tab_column;
+
+ if (pending)
+- pending_blank[0] = '\t';
++ mb_setascii (&pending_blank[0], '\t');
+ }
+ else
+ {
+- column++;
++ column += mb_width (c);
+
+ if (! (prev_blank && column == next_tab_column))
+ {
+@@ -197,13 +255,14 @@ unexpand (void)
+ will be replaced by tabs. */
+ if (column == next_tab_column)
+ one_blank_before_tab_stop = true;
+- pending_blank[pending++] = c;
++ mb_copy (&pending_blank[pending++], &c);
+ prev_blank = true;
+ continue;
+ }
+
+ /* Replace the pending blanks by a tab or two. */
+- pending_blank[0] = c = '\t';
++ mb_setascii (&c, '\t');
++ mb_setascii (&pending_blank[0], '\t');
+ }
+
+ /* Discard pending blanks, unless it was a single
+@@ -211,7 +270,7 @@ unexpand (void)
+ pending = one_blank_before_tab_stop;
+ }
+ }
+- else if (c == '\b')
++ else if (mb_iseq (c, '\b'))
+ {
+ /* Go back one column, and force recalculation of the
+ next tab stop. */
+@@ -219,9 +278,9 @@ unexpand (void)
+ next_tab_column = column;
+ tab_index -= !!tab_index;
+ }
+- else
++ else if (!mb_iseq (c, '\n'))
+ {
+- column++;
++ column += mb_width (c);
+ if (!column)
+ die (EXIT_FAILURE, 0, _("input line is too long"));
+ }
+@@ -229,8 +288,11 @@ unexpand (void)
+ if (pending)
+ {
+ if (pending > 1 && one_blank_before_tab_stop)
+- pending_blank[0] = '\t';
+- if (fwrite (pending_blank, 1, pending, stdout) != pending)
++ mb_setascii (&pending_blank[0], '\t');
++
++ for (int n = 0; n < pending; ++n)
++ mb_putc (pending_blank[n], stdout);
++ if (ferror (stdout))
+ die (EXIT_FAILURE, errno, _("write error"));
+ pending = 0;
+ one_blank_before_tab_stop = false;
+@@ -240,16 +302,17 @@ unexpand (void)
+ convert &= convert_entire_line || blank;
+ }
+
+- if (c < 0)
++ if (mb_iseof (c))
+ {
+ free (pending_blank);
+ return;
+ }
+
+- if (putchar (c) < 0)
++ mb_putc (c, stdout);
++ if (ferror (stdout))
+ die (EXIT_FAILURE, errno, _("write error"));
+ }
+- while (c != '\n');
++ while (!mb_iseq (c, '\n'));
+ }
+ }
- if (have_read_stdin && fclose (stdin) != 0)
- error (EXIT_FAILURE, errno, "-");
-diff -Naurp coreutils-8.25-orig/src/uniq.c coreutils-8.25/src/uniq.c
---- coreutils-8.25-orig/src/uniq.c 2016-01-13 05:08:59.000000000 -0600
-+++ coreutils-8.25/src/uniq.c 2016-02-08 19:07:10.312944654 -0600
+diff -Naurp coreutils-8.27-orig/src/uniq.c coreutils-8.27/src/uniq.c
+--- coreutils-8.27-orig/src/uniq.c 2017-01-01 16:34:24.000000000 -0600
++++ coreutils-8.27/src/uniq.c 2017-03-11 23:47:13.098285938 -0600
@@ -21,6 +21,17 @@
#include <getopt.h>
#include <sys/types.h>
#include "system.h"
#include "argmatch.h"
#include "linebuffer.h"
-@@ -33,6 +44,18 @@
+@@ -32,9 +43,21 @@
+ #include "stdio--.h"
+ #include "xmemcoll.h"
#include "xstrtol.h"
- #include "memcasecmp.h"
- #include "quote.h"
+-#include "memcasecmp.h"
+#include "xmemcoll.h"
-+
+ #include "quote.h"
+
+/* MB_LEN_MAX is incorrectly defined to be 1 in at least one GCC
+ installation; work around this configuration error. */
+#if !defined MB_LEN_MAX || MB_LEN_MAX < 2
+#if HAVE_MBRTOWC && defined mbstate_t
+# define mbrtowc(pwc, s, n, ps) (mbrtowc) (pwc, s, n, 0)
+#endif
-
++
++
/* The official name of this program (e.g., no 'g' prefix). */
#define PROGRAM_NAME "uniq"
-@@ -143,6 +166,10 @@ enum
+
+@@ -144,6 +167,10 @@ enum
GROUP_OPTION = CHAR_MAX + 1
};
static struct option const longopts[] =
{
{"count", no_argument, NULL, 'c'},
-@@ -252,7 +279,7 @@ size_opt (char const *opt, char const *m
+@@ -260,7 +287,7 @@ size_opt (char const *opt, char const *m
return a pointer to the beginning of the line's field to be compared. */
static char * _GL_ATTRIBUTE_PURE
{
size_t count;
char const *lp = line->buffer;
-@@ -272,6 +299,83 @@ find_field (struct linebuffer const *lin
+@@ -280,6 +307,83 @@ find_field (struct linebuffer const *lin
return line->buffer + i;
}
/* Return false if two strings OLD and NEW match, true if not.
OLD and NEW point not to the beginnings of the lines
but rather to the beginnings of the fields to compare.
-@@ -280,6 +384,8 @@ find_field (struct linebuffer const *lin
+@@ -288,6 +392,8 @@ find_field (struct linebuffer const *lin
static bool
different (char *old, char *new, size_t oldlen, size_t newlen)
{
if (check_chars < oldlen)
oldlen = check_chars;
if (check_chars < newlen)
-@@ -287,15 +393,104 @@ different (char *old, char *new, size_t
+@@ -295,14 +401,103 @@ different (char *old, char *new, size_t
if (ignore_case)
{
+
+ return xmemcoll (copy_old, oldlen, copy_new, newlen);
+
- }
-
++}
++
+#if HAVE_MBRTOWC
+static int
+different_multi (const char *old, const char *new, size_t oldlen, size_t newlen, mbstate_t oldstate, mbstate_t newstate)
+ free (copy[1]);
+ return rc;
+
-+}
+ }
+#endif
-+
+
/* Output the line in linebuffer LINE to standard output
provided that the switches say it should be output.
- MATCH is true if the line matches the previous line.
-@@ -359,19 +554,38 @@ check_file (const char *infile, const ch
+@@ -367,19 +562,38 @@ check_file (const char *infile, const ch
char *prevfield IF_LINT ( = NULL);
size_t prevlen IF_LINT ( = 0);
bool first_group_printed = false;
new_group = (prevline->length == 0
|| different (thisfield, prevfield, thislen, prevlen));
-@@ -389,6 +603,10 @@ check_file (const char *infile, const ch
+@@ -397,6 +611,10 @@ check_file (const char *infile, const ch
SWAP_LINES (prevline, thisline);
prevfield = thisfield;
prevlen = thislen;
first_group_printed = true;
}
}
-@@ -401,17 +619,26 @@ check_file (const char *infile, const ch
+@@ -409,17 +627,26 @@ check_file (const char *infile, const ch
size_t prevlen;
uintmax_t match_count = 0;
bool first_delimiter = true;
if (readlinebuffer_delim (thisline, stdin, delimiter) == 0)
{
if (ferror (stdin))
-@@ -420,6 +647,14 @@ check_file (const char *infile, const ch
+@@ -428,6 +655,14 @@ check_file (const char *infile, const ch
}
thisfield = find_field (thisline);
thislen = thisline->length - 1 - (thisfield - thisline->buffer);
match = !different (thisfield, prevfield, thislen, prevlen);
match_count += match;
-@@ -452,6 +687,9 @@ check_file (const char *infile, const ch
+@@ -460,6 +695,9 @@ check_file (const char *infile, const ch
SWAP_LINES (prevline, thisline);
prevfield = thisfield;
prevlen = thislen;
if (!match)
match_count = 0;
}
-@@ -498,6 +736,19 @@ main (int argc, char **argv)
+@@ -506,6 +744,19 @@ main (int argc, char **argv)
atexit (close_stdout);
skip_chars = 0;
skip_fields = 0;
check_chars = SIZE_MAX;
-diff -Naurp coreutils-8.25-orig/tests/i18n/sort-month.sh coreutils-8.25/tests/i18n/sort-month.sh
---- coreutils-8.25-orig/tests/i18n/sort-month.sh 1969-12-31 18:00:00.000000000 -0600
-+++ coreutils-8.25/tests/i18n/sort-month.sh 2016-02-08 19:07:10.312944654 -0600
-@@ -0,0 +1,34 @@
+diff -Naurp coreutils-8.27-orig/tests/expand/mb.sh coreutils-8.27/tests/expand/mb.sh
+--- coreutils-8.27-orig/tests/expand/mb.sh 1969-12-31 18:00:00.000000000 -0600
++++ coreutils-8.27/tests/expand/mb.sh 2017-03-11 23:49:06.759133489 -0600
+@@ -0,0 +1,183 @@
+#!/bin/sh
-+# Verify sort -M multi-byte support.
+
-+. "${srcdir=.}/tests/init.sh"; path_prepend_ ./src
-+print_ver_ sort
-+require_valgrind_
++# Copyright (C) 2012-2017 Free Software Foundation, Inc.
+
-+# Skip this test if some deallocations are
-+# avoided at process end.
-+grep '^#define lint 1' $CONFIG_HEADER > /dev/null ||
-+ skip_ 'Allocation checks only work reliably in "lint" mode'
++# This program is free software: you can redistribute it and/or modify
++# it under the terms of the GNU General Public License as published by
++# the Free Software Foundation, either version 3 of the License, or
++# (at your option) any later version.
++
++# This program is distributed in the hope that it will be useful,
++# but WITHOUT ANY WARRANTY; without even the implied warranty of
++# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
++# GNU General Public License for more details.
++
++# You should have received a copy of the GNU General Public License
++# along with this program. If not, see <http://www.gnu.org/licenses/>.
++
++. "${srcdir=.}/tests/init.sh"; path_prepend_ ./src
++print_ver_ expand
+
+export LC_ALL=en_US.UTF-8
-+locale -k LC_CTYPE | grep -q "charmap.*UTF-8" \
-+ || skip_ "No UTF-8 locale available"
+
-+# Note the use of ɑ here which expands to
-+# a wider representation upon case conversion
-+# which triggered an assertion in sort -M
-+cat <<EOF > exp
-+.
-+ɑ
++#input containing multibyte characters
++cat <<\EOF > in || framework_failure_
++1234567812345678123456781
++. . . .
++a b c d
++. . . .
++ä ö ü ß
++. . . .
++EOF
++env printf ' äöü\t. öüä. \tä xx\n' >> in || framework_failure_
++
++cat <<\EOF > exp || framework_failure_
++1234567812345678123456781
++. . . .
++a b c d
++. . . .
++ä ö ü ß
++. . . .
++ äöü . öüä. ä xx
+EOF
+
++expand < in > out || fail=1
++compare exp out > /dev/null 2>&1 || fail=1
++
++#multiple files as an input
++cat <<\EOF >> exp || framework_failure_
++1234567812345678123456781
++. . . .
++a b c d
++. . . .
++ä ö ü ß
++. . . .
++ äöü . öüä. ä xx
++EOF
+
-+# check large mem leak with --month-sort
-+# https://bugzilla.redhat.com/show_bug.cgi?id=1259942
-+valgrind --leak-check=full \
-+ --error-exitcode=1 --errors-for-leak-kinds=definite \
-+ sort -M < exp > out || fail=1
-+compare exp out || { fail=1; cat out; }
++expand ./in ./in > out || fail=1
++compare exp out > /dev/null 2>&1 || fail=1
++
++#test characters with display widths != 1
++env printf '12345678
++e\t|ascii(1)
++\u00E9\t|composed(1)
++e\u0301\t|decomposed(1)
++\u3000\t|ideo-space(2)
++\uFF0D\t|full-hypen(2)
++' > in || framework_failure_
++
++env printf '12345678
++e |ascii(1)
++\u00E9 |composed(1)
++e\u0301 |decomposed(1)
++\u3000 |ideo-space(2)
++\uFF0D |full-hypen(2)
++' > exp || framework_failure_
++
++expand < in > out || fail=1
++compare exp out > /dev/null 2>&1 || fail=1
++
++#shouldn't fail with "input line too long"
++#when a line starts with a control character
++env printf '\n' > in || framework_failure_
++
++expand < in > out || fail=1
++compare in out > /dev/null 2>&1 || fail=1
++
++#non-Unicode characters interspersed between Unicode ones
++env printf '12345678
++\t\xFF|
++\xFF\t|
++\t\xFFä|
++ä\xFF\t|
++\tä\xFF|
++\xFF\tä|
++äbcdef\xFF\t|
++' > in || framework_failure_
++
++env printf '12345678
++ \xFF|
++\xFF |
++ \xFFä|
++ä\xFF |
++ ä\xFF|
++\xFF ä|
++äbcdef\xFF |
++' > exp || framework_failure_
++
++expand < in > out || fail=1
++compare exp out > /dev/null 2>&1 || fail=1
++
++
++
++#BOM header test 1
++printf "\xEF\xBB\xBF" > in; cat <<\EOF >> in || framework_failure_
++1234567812345678123456781
++. . . .
++a b c d
++. . . .
++ä ö ü ß
++. . . .
++EOF
++env printf ' äöü\t. öüä. \tä xx\n' >> in || framework_failure_
++
++printf "\xEF\xBB\xBF" > exp; cat <<\EOF >> exp || framework_failure_
++1234567812345678123456781
++. . . .
++a b c d
++. . . .
++ä ö ü ß
++. . . .
++ äöü . öüä. ä xx
++EOF
+
+
-+Exit $fail
-diff -Naurp coreutils-8.25-orig/tests/i18n/sort.sh coreutils-8.25/tests/i18n/sort.sh
---- coreutils-8.25-orig/tests/i18n/sort.sh 1969-12-31 18:00:00.000000000 -0600
-+++ coreutils-8.25/tests/i18n/sort.sh 2016-02-08 19:07:10.312944654 -0600
++expand < in > out || fail=1
++compare exp out > /dev/null 2>&1 || fail=1
++
++LANG=C expand < in > out || fail=1
++compare exp out > /dev/null 2>&1 || fail=1
++
++LC_ALL=C expand < in > out || fail=1
++compare exp out > /dev/null 2>&1 || fail=1
++
++
++printf '\xEF\xBB\xBF' > in1; cat <<\EOF >> in1 || framework_failure_
++1234567812345678123456781
++. . . .
++a b c d
++. . . .
++ä ö ü ß
++. . . .
++EOF
++env printf ' äöü\t. öüä. \tä xx\n' >> in1 || framework_failure_
++
++
++printf '\xEF\xBB\xBF' > exp; cat <<\EOF >> exp || framework_failure_
++1234567812345678123456781
++. . . .
++a b c d
++. . . .
++ä ö ü ß
++. . . .
++ äöü . öüä. ä xx
++1234567812345678123456781
++. . . .
++a b c d
++. . . .
++ä ö ü ß
++. . . .
++ äöü . öüä. ä xx
++EOF
++
++expand in1 in1 > out || fail=1
++compare exp out > /dev/null 2>&1 || fail=1
++
++LANG=C expand in1 in1 > out || fail=1
++compare exp out > /dev/null 2>&1 || fail=1
++
++LC_ALL=C expand in1 in1 > out || fail=1
++compare exp out > /dev/null 2>&1 || fail=1
++
++exit $fail
+diff -Naurp coreutils-8.27-orig/tests/i18n/sort.sh coreutils-8.27/tests/i18n/sort.sh
+--- coreutils-8.27-orig/tests/i18n/sort.sh 1969-12-31 18:00:00.000000000 -0600
++++ coreutils-8.27/tests/i18n/sort.sh 2017-03-11 23:47:13.100285838 -0600
@@ -0,0 +1,29 @@
+#!/bin/sh
+# Verify sort's multi-byte support.
+
+
+Exit $fail
-diff -Naurp coreutils-8.25-orig/tests/local.mk coreutils-8.25/tests/local.mk
---- coreutils-8.25-orig/tests/local.mk 2016-01-16 12:18:13.000000000 -0600
-+++ coreutils-8.25/tests/local.mk 2016-02-08 19:07:10.313944658 -0600
-@@ -344,6 +344,9 @@ all_tests = \
+diff -Naurp coreutils-8.27-orig/tests/local.mk coreutils-8.27/tests/local.mk
+--- coreutils-8.27-orig/tests/local.mk 2017-02-28 22:25:37.000000000 -0600
++++ coreutils-8.27/tests/local.mk 2017-03-11 23:47:38.072058253 -0600
+@@ -352,6 +352,8 @@ all_tests = \
tests/misc/sort-discrim.sh \
tests/misc/sort-files0-from.pl \
tests/misc/sort-float.sh \
+ tests/misc/sort-mb-tests.sh \
+ tests/i18n/sort.sh \
-+ tests/i18n/sort-month.sh \
+ tests/misc/sort-h-thousands-sep.sh \
tests/misc/sort-merge.pl \
tests/misc/sort-merge-fdlimit.sh \
- tests/misc/sort-month.sh \
-diff -Naurp coreutils-8.25-orig/tests/misc/cut.pl coreutils-8.25/tests/misc/cut.pl
---- coreutils-8.25-orig/tests/misc/cut.pl 2016-01-16 12:18:13.000000000 -0600
-+++ coreutils-8.25/tests/misc/cut.pl 2016-02-08 19:07:10.314944661 -0600
+@@ -544,6 +546,7 @@ all_tests = \
+ tests/du/threshold.sh \
+ tests/du/trailing-slash.sh \
+ tests/du/two-args.sh \
++ tests/expand/mb.sh \
+ tests/id/gnu-zero-uids.sh \
+ tests/id/no-context.sh \
+ tests/id/context.sh \
+@@ -684,6 +687,7 @@ all_tests = \
+ tests/touch/read-only.sh \
+ tests/touch/relative.sh \
+ tests/touch/trailing-slash.sh \
++ tests/unexpand/mb.sh \
+ $(all_root_tests)
+
+ # See tests/factor/create-test.sh.
+diff -Naurp coreutils-8.27-orig/tests/misc/cut.pl coreutils-8.27/tests/misc/cut.pl
+--- coreutils-8.27-orig/tests/misc/cut.pl 2017-01-01 16:34:24.000000000 -0600
++++ coreutils-8.27/tests/misc/cut.pl 2017-03-11 23:47:13.100285838 -0600
@@ -23,9 +23,11 @@ use strict;
# Turn off localization of executable's output.
@ENV{qw(LANGUAGE LANG LC_ALL)} = ('C') x 3;
push @new, ["$test_name-mb", @new_t, {ENV => "LC_ALL=$mb_locale"}];
}
push @Tests, @new;
-diff -Naurp coreutils-8.25-orig/tests/misc/expand.pl coreutils-8.25/tests/misc/expand.pl
---- coreutils-8.25-orig/tests/misc/expand.pl 2016-01-16 12:18:13.000000000 -0600
-+++ coreutils-8.25/tests/misc/expand.pl 2016-02-08 19:07:10.314944661 -0600
-@@ -23,6 +23,15 @@ use strict;
+diff -Naurp coreutils-8.27-orig/tests/misc/expand.pl coreutils-8.27/tests/misc/expand.pl
+--- coreutils-8.27-orig/tests/misc/expand.pl 2017-03-01 11:16:46.000000000 -0600
++++ coreutils-8.27/tests/misc/expand.pl 2017-03-11 23:47:13.101285788 -0600
+@@ -27,6 +27,15 @@ my $prog = 'expand';
# Turn off localization of executable's output.
@ENV{qw(LANGUAGE LANG LC_ALL)} = ('C') x 3;
my @Tests =
(
['t1', '--tabs=3', {IN=>"a\tb"}, {OUT=>"a b"}],
-@@ -31,6 +40,37 @@ my @Tests =
- ['i2', '--tabs=3 -i', {IN=>" \ta\tb"}, {OUT=>" a\tb"}],
+@@ -152,6 +161,8 @@ my @Tests =
+ ['trail9', '--tab=1,2 -t/5',{IN=>"\ta\tb\tc"}, {OUT=>" a b c"}],
+
+ # Test errors
++ # FIXME: The following tests contain ‘quoting’ specific to LC_MESSAGES
++ # So we force LC_MESSAGES=C to make them pass.
+ ['e1', '--tabs="a"', {IN=>''}, {OUT=>''}, {EXIT=>1},
+ {ERR => "$prog: tab size contains invalid character(s): 'a'\n"}],
+ ['e2', "-t $UINTMAX_OFLOW", {IN=>''}, {OUT=>''}, {EXIT=>1},
+@@ -168,6 +179,37 @@ my @Tests =
+ {ERR => "$prog: '/' specifier not at start of number: '/'\n"}],
);
+if ($mb_locale ne 'C')
+ push @new_t, $sub;
+ push @$t, $sub;
+ }
-+ push @new, ["$test_name-mb", @new_t, {ENV => "LC_ALL=$mb_locale"}];
++ push @new, ["$test_name-mb", @new_t, {ENV => "LANG=$mb_locale LC_MESSAGES=C"}];
+ }
+ push @Tests, @new;
+ }
my $save_temps = $ENV{DEBUG};
my $verbose = $ENV{VERBOSE};
-diff -Naurp coreutils-8.25-orig/tests/misc/fold.pl coreutils-8.25/tests/misc/fold.pl
---- coreutils-8.25-orig/tests/misc/fold.pl 2016-01-16 12:18:13.000000000 -0600
-+++ coreutils-8.25/tests/misc/fold.pl 2016-02-08 19:07:10.314944661 -0600
+diff -Naurp coreutils-8.27-orig/tests/misc/fold.pl coreutils-8.27/tests/misc/fold.pl
+--- coreutils-8.27-orig/tests/misc/fold.pl 2017-01-01 16:34:24.000000000 -0600
++++ coreutils-8.27/tests/misc/fold.pl 2017-03-11 23:47:13.101285788 -0600
@@ -20,9 +20,18 @@ use strict;
(my $program_name = $0) =~ s|.*/||;
-my $prog = 'fold';
my $fail = run_tests ($program_name, $prog, \@Tests, $save_temps, $verbose);
exit $fail;
-diff -Naurp coreutils-8.25-orig/tests/misc/join.pl coreutils-8.25/tests/misc/join.pl
---- coreutils-8.25-orig/tests/misc/join.pl 2016-01-16 12:18:13.000000000 -0600
-+++ coreutils-8.25/tests/misc/join.pl 2016-02-08 19:07:10.315944664 -0600
+diff -Naurp coreutils-8.27-orig/tests/misc/join.pl coreutils-8.27/tests/misc/join.pl
+--- coreutils-8.27-orig/tests/misc/join.pl 2017-01-01 16:34:24.000000000 -0600
++++ coreutils-8.27/tests/misc/join.pl 2017-03-11 23:47:13.102285737 -0600
@@ -25,6 +25,15 @@ my $limits = getlimits ();
my $prog = 'join';
my $save_temps = $ENV{DEBUG};
my $verbose = $ENV{VERBOSE};
-diff -Naurp coreutils-8.25-orig/tests/misc/sort-mb-tests.sh coreutils-8.25/tests/misc/sort-mb-tests.sh
---- coreutils-8.25-orig/tests/misc/sort-mb-tests.sh 1969-12-31 18:00:00.000000000 -0600
-+++ coreutils-8.25/tests/misc/sort-mb-tests.sh 2016-02-08 19:07:10.315944664 -0600
+diff -Naurp coreutils-8.27-orig/tests/misc/sort-mb-tests.sh coreutils-8.27/tests/misc/sort-mb-tests.sh
+--- coreutils-8.27-orig/tests/misc/sort-mb-tests.sh 1969-12-31 18:00:00.000000000 -0600
++++ coreutils-8.27/tests/misc/sort-mb-tests.sh 2017-03-11 23:47:13.102285737 -0600
@@ -0,0 +1,45 @@
+#!/bin/sh
+# Verify sort's multi-byte support.
+compare exp out || { fail=1; cat out; }
+
+Exit $fail
-diff -Naurp coreutils-8.25-orig/tests/misc/sort-merge.pl coreutils-8.25/tests/misc/sort-merge.pl
---- coreutils-8.25-orig/tests/misc/sort-merge.pl 2016-01-16 12:18:14.000000000 -0600
-+++ coreutils-8.25/tests/misc/sort-merge.pl 2016-02-08 19:07:10.316944667 -0600
+diff -Naurp coreutils-8.27-orig/tests/misc/sort-merge.pl coreutils-8.27/tests/misc/sort-merge.pl
+--- coreutils-8.27-orig/tests/misc/sort-merge.pl 2017-01-01 16:34:24.000000000 -0600
++++ coreutils-8.27/tests/misc/sort-merge.pl 2017-03-11 23:47:13.102285737 -0600
@@ -26,6 +26,15 @@ my $prog = 'sort';
# Turn off localization of executable's output.
@ENV{qw(LANGUAGE LANG LC_ALL)} = ('C') x 3;
my $save_temps = $ENV{DEBUG};
my $verbose = $ENV{VERBOSE};
-diff -Naurp coreutils-8.25-orig/tests/misc/sort.pl coreutils-8.25/tests/misc/sort.pl
---- coreutils-8.25-orig/tests/misc/sort.pl 2016-01-16 12:18:14.000000000 -0600
-+++ coreutils-8.25/tests/misc/sort.pl 2016-02-08 19:07:10.316944667 -0600
+diff -Naurp coreutils-8.27-orig/tests/misc/sort.pl coreutils-8.27/tests/misc/sort.pl
+--- coreutils-8.27-orig/tests/misc/sort.pl 2017-01-21 08:53:43.000000000 -0600
++++ coreutils-8.27/tests/misc/sort.pl 2017-03-11 23:47:13.103285687 -0600
@@ -24,10 +24,15 @@ my $prog = 'sort';
# Turn off localization of executable's output.
@ENV{qw(LANGUAGE LANG LC_ALL)} = ('C') x 3;
# Since each test is run with a file name and with redirected stdin,
# the name in the diagnostic is either the file name or "-".
# Normalize each diagnostic to use '-'.
-@@ -424,6 +429,38 @@ foreach my $t (@Tests)
+@@ -423,6 +428,38 @@ foreach my $t (@Tests)
}
}
@Tests = triple_test \@Tests;
# Remember that triple_test creates from each test with exactly one "IN"
-@@ -433,6 +470,7 @@ foreach my $t (@Tests)
+@@ -432,6 +469,7 @@ foreach my $t (@Tests)
# Remove the IN_PIPE version of the "output-is-input" test above.
# The others aren't susceptible because they have three inputs each.
@Tests = grep {$_->[0] ne 'output-is-input.p'} @Tests;
my $save_temps = $ENV{DEBUG};
my $verbose = $ENV{VERBOSE};
-diff -Naurp coreutils-8.25-orig/tests/misc/unexpand.pl coreutils-8.25/tests/misc/unexpand.pl
---- coreutils-8.25-orig/tests/misc/unexpand.pl 2016-01-16 12:18:14.000000000 -0600
-+++ coreutils-8.25/tests/misc/unexpand.pl 2016-02-08 19:07:10.317944671 -0600
+diff -Naurp coreutils-8.27-orig/tests/misc/unexpand.pl coreutils-8.27/tests/misc/unexpand.pl
+--- coreutils-8.27-orig/tests/misc/unexpand.pl 2017-01-01 16:34:24.000000000 -0600
++++ coreutils-8.27/tests/misc/unexpand.pl 2017-03-11 23:47:13.103285687 -0600
@@ -27,6 +27,14 @@ my $limits = getlimits ();
my $prog = 'unexpand';
my @Tests =
(
['a1', {IN=> ' 'x 1 ."y\n"}, {OUT=> ' 'x 1 ."y\n"}],
-@@ -92,6 +100,37 @@ my @Tests =
- {EXIT => 1}, {ERR => "$prog: tab stop value is too large\n"}],
+@@ -128,6 +136,37 @@ my @Tests =
+ ['ts2', '-t5,8', {IN=>"x\t \t y\n"}, {OUT=>"x\t\t y\n"}],
);
+if ($mb_locale ne 'C')
my $save_temps = $ENV{DEBUG};
my $verbose = $ENV{VERBOSE};
-diff -Naurp coreutils-8.25-orig/tests/misc/uniq.pl coreutils-8.25/tests/misc/uniq.pl
---- coreutils-8.25-orig/tests/misc/uniq.pl 2016-01-16 12:18:14.000000000 -0600
-+++ coreutils-8.25/tests/misc/uniq.pl 2016-02-08 19:07:10.317944671 -0600
+diff -Naurp coreutils-8.27-orig/tests/misc/uniq.pl coreutils-8.27/tests/misc/uniq.pl
+--- coreutils-8.27-orig/tests/misc/uniq.pl 2017-01-01 16:34:24.000000000 -0600
++++ coreutils-8.27/tests/misc/uniq.pl 2017-03-11 23:47:13.103285687 -0600
@@ -23,9 +23,17 @@ my $limits = getlimits ();
my $prog = 'uniq';
my $try = "Try '$prog --help' for more information.\n";
@Tests = add_z_variants \@Tests;
@Tests = triple_test \@Tests;
-diff -Naurp coreutils-8.25-orig/tests/pr/pr-tests.pl coreutils-8.25/tests/pr/pr-tests.pl
---- coreutils-8.25-orig/tests/pr/pr-tests.pl 2016-01-16 12:18:14.000000000 -0600
-+++ coreutils-8.25/tests/pr/pr-tests.pl 2016-02-08 19:07:10.318944674 -0600
+diff -Naurp coreutils-8.27-orig/tests/pr/pr-tests.pl coreutils-8.27/tests/pr/pr-tests.pl
+--- coreutils-8.27-orig/tests/pr/pr-tests.pl 2017-01-01 16:34:24.000000000 -0600
++++ coreutils-8.27/tests/pr/pr-tests.pl 2017-03-11 23:47:13.103285687 -0600
@@ -24,6 +24,15 @@ use strict;
my $prog = 'pr';
my $normalize_strerror = "s/': .*/'/";
my @tv = (
# -b option is no longer an official option. But it's still working to
-@@ -467,8 +476,48 @@ push @Tests,
- {IN=>{3=>"x\ty\tz\n"}},
- {OUT=>join("\t", qw(a b c m n o x y z)) . "\n"} ];
+@@ -474,8 +483,48 @@ push @Tests,
+ {IN=>{2=>"a\n"}},
+ {OUT=>"a\t\t\t\t \t\t\ta\n"} ];
+# Add _POSIX2_VERSION=199209 to the environment of each test
+# that uses an old-style option like +1.
+ push @$t, $sub;
+ }
+ #temporarily skip some failing tests
-+ next if ($test_name =~ "col-0" or $test_name =~ "col-inval");
++ next if ($test_name =~ "col-0" or $test_name =~ "col-inval" or $test_name =~ "asan1");
+ push @new, ["$test_name-mb", @new_t, {ENV => "LC_ALL=$mb_locale"}];
+ }
+ push @Tests, @new;
my $save_temps = $ENV{DEBUG};
my $verbose = $ENV{VERBOSE};
+diff -Naurp coreutils-8.27-orig/tests/unexpand/mb.sh coreutils-8.27/tests/unexpand/mb.sh
+--- coreutils-8.27-orig/tests/unexpand/mb.sh 1969-12-31 18:00:00.000000000 -0600
++++ coreutils-8.27/tests/unexpand/mb.sh 2017-03-11 23:49:06.759133489 -0600
+@@ -0,0 +1,172 @@
++#!/bin/sh
++
++# Copyright (C) 2012-2017 Free Software Foundation, Inc.
++
++# This program is free software: you can redistribute it and/or modify
++# it under the terms of the GNU General Public License as published by
++# the Free Software Foundation, either version 3 of the License, or
++# (at your option) any later version.
++
++# This program is distributed in the hope that it will be useful,
++# but WITHOUT ANY WARRANTY; without even the implied warranty of
++# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
++# GNU General Public License for more details.
++
++# You should have received a copy of the GNU General Public License
++# along with this program. If not, see <http://www.gnu.org/licenses/>.
++
++. "${srcdir=.}/tests/init.sh"; path_prepend_ ./src
++print_ver_ unexpand
++
++export LC_ALL=en_US.UTF-8
++
++#input containing multibyte characters
++cat > in <<\EOF
++1234567812345678123456781
++. . . .
++a b c d
++. . . .
++ä ö ü ß
++. . . .
++ äöü . öüä. ä xx
++EOF
++
++cat > exp <<\EOF
++1234567812345678123456781
++. . . .
++a b c d
++. . . .
++ä ö ü ß
++. . . .
++ äöü . öüä. ä xx
++EOF
++
++unexpand -a < in > out || fail=1
++compare exp out > /dev/null 2>&1 || fail=1
++
++
++#multiple files as an input
++cat >> exp <<\EOF
++1234567812345678123456781
++. . . .
++a b c d
++. . . .
++ä ö ü ß
++. . . .
++ äöü . öüä. ä xx
++EOF
++
++
++unexpand -a ./in ./in > out || fail=1
++compare exp out > /dev/null 2>&1 || fail=1
++
++#test characters with a display width larger than 1
++
++env printf '12345678
++e |ascii(1)
++\u00E9 |composed(1)
++e\u0301 |decomposed(1)
++\u3000 |ideo-space(2)
++\uFF0D |full-hypen(2)
++' > in || framework_failure_
++
++env printf '12345678
++e\t|ascii(1)
++\u00E9\t|composed(1)
++e\u0301\t|decomposed(1)
++\u3000\t|ideo-space(2)
++\uFF0D\t|full-hypen(2)
++' > exp || framework_failure_
++
++unexpand -a < in > out || fail=1
++compare exp out > /dev/null 2>&1 || fail=1
++
++#test input where a blank of width > 1 is not being substituted
++in="$(LC_ALL=en_US.UTF-8 printf ' \u3000 ö ü ß')"
++exp=' ö ü ß'
++
++unexpand -a < in > out || fail=1
++compare exp out > /dev/null 2>&1 || fail=1
++
++#non-Unicode characters interspersed between Unicode ones
++env printf '12345678
++ \xFF|
++\xFF |
++ \xFFä|
++ä\xFF |
++ ä\xFF|
++\xFF ä|
++äbcdef\xFF |
++' > in || framework_failure_
++
++env printf '12345678
++\t\xFF|
++\xFF\t|
++\t\xFFä|
++ä\xFF\t|
++\tä\xFF|
++\xFF\tä|
++äbcdef\xFF\t|
++' > exp || framework_failure_
++
++unexpand -a < in > out || fail=1
++compare exp out > /dev/null 2>&1 || fail=1
++
++#BOM header test 1
++printf "\xEF\xBB\xBF" > in; cat <<\EOF >> in || framework_failure_
++1234567812345678123456781
++. . . .
++a b c d
++. . . .
++ä ö ü ß
++. . . .
++ äöü . öüä. ä xx
++EOF
++env printf ' äöü\t. öüä. \tä xx\n' >> in || framework_failure_
++
++printf "\xEF\xBB\xBF" > exp; cat <<\EOF >> exp || framework_failure_
++1234567812345678123456781
++. . . .
++a b c d
++. . . .
++ä ö ü ß
++. . . .
++ äöü . öüä. ä xx
++EOF
++
++unexpand < in > out || fail=1
++compare exp out > /dev/null 2>&1 || fail=1
++
++LANG=C unexpand < in > out || fail=1
++compare exp out > /dev/null 2>&1 || fail=1
++
++LC_ALL=C unexpand < in > out || fail=1
++compare exp out > /dev/null 2>&1 || fail=1
++
++
++printf "\xEF\xBB\xBF" > exp; cat <<\EOF >> exp || framework_failure_
++1234567812345678123456781
++. . . .
++a b c d
++. . . .
++ä ö ü ß
++. . . .
++ äöü . öüä. ä xx
++1234567812345678123456781
++. . . .
++a b c d
++. . . .
++ä ö ü ß
++. . . .
++ äöü . öüä. ä xx
++EOF
++
++
++unexpand in in > out || fail=1
++compare exp out > /dev/null 2>&1 || fail=1
++
++LANG=C unexpand in in > out || fail=1
++compare exp out > /dev/null 2>&1 || fail=1
++
++LC_ALL=C unexpand in in > out || fail=1
++compare exp out > /dev/null 2>&1 || fail=1
projects / ipfire-2.x.git / commitdiff
