devel/coreutils/coreutils-i18n.patch

diff -urNp coreutils-8.0-orig/lib/linebuffer.h coreutils-8.0/lib/linebuffer.h
--- coreutils-8.0-orig/lib/linebuffer.h	2009-10-06 10:59:48.000000000 +0200
+++ coreutils-8.0/lib/linebuffer.h	2009-10-07 10:07:16.000000000 +0200
@@ -21,6 +21,11 @@
 
 # include <stdio.h>
 
+/* Get mbstate_t.  */
+# if HAVE_WCHAR_H
+#  include <wchar.h>
+# endif
+
 /* A `struct linebuffer' holds a line of text. */
 
 struct linebuffer
@@ -28,6 +33,9 @@ struct linebuffer
   size_t size;			/* Allocated. */
   size_t length;		/* Used. */
   char *buffer;
+# if HAVE_WCHAR_H
+  mbstate_t state;
+# endif
 };
 
 /* Initialize linebuffer LINEBUFFER for use. */
diff -urNp coreutils-8.0-orig/lib/linebuffer.h.orig coreutils-8.0/lib/linebuffer.h.orig
--- coreutils-8.0-orig/lib/linebuffer.h.orig	1970-01-01 01:00:00.000000000 +0100
+++ coreutils-8.0/lib/linebuffer.h.orig	2009-10-06 10:59:48.000000000 +0200
@@ -0,0 +1,53 @@
+/* linebuffer.h -- declarations for reading arbitrarily long lines
+
+   Copyright (C) 1986, 1991, 1998, 1999, 2002, 2003, 2007 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/>.  */
+
+#if !defined LINEBUFFER_H
+# define LINEBUFFER_H
+
+# include <stdio.h>
+
+/* A `struct linebuffer' holds a line of text. */
+
+struct linebuffer
+{
+  size_t size;			/* Allocated. */
+  size_t length;		/* Used. */
+  char *buffer;
+};
+
+/* Initialize linebuffer LINEBUFFER for use. */
+void initbuffer (struct linebuffer *linebuffer);
+
+/* Read an arbitrarily long line of text from STREAM into LINEBUFFER.
+   Consider lines to be terminated by DELIMITER.
+   Keep the delimiter; append DELIMITER if we reach EOF and it wasn't
+   the last character in the file.  Do not NUL-terminate.
+   Return LINEBUFFER, except at end of file return NULL.  */
+struct linebuffer *readlinebuffer_delim (struct linebuffer *linebuffer,
+					 FILE *stream, char delimiter);
+
+/* Read an arbitrarily long line of text from STREAM into LINEBUFFER.
+   Keep the newline; append a newline if it's the last line of a file
+   that ends in a non-newline character.  Do not NUL-terminate.
+   Return LINEBUFFER, except at end of file return NULL.  */
+struct linebuffer *readlinebuffer (struct linebuffer *linebuffer, FILE *stream);
+
+/* Free linebuffer LINEBUFFER and its data, all allocated with malloc. */
+void freebuffer (struct linebuffer *);
+
+#endif /* LINEBUFFER_H */
diff -urNp coreutils-8.0-orig/src/cut.c coreutils-8.0/src/cut.c
--- coreutils-8.0-orig/src/cut.c	2009-09-23 10:25:44.000000000 +0200
+++ coreutils-8.0/src/cut.c	2009-10-07 10:07:16.000000000 +0200
@@ -28,6 +28,11 @@
 #include <assert.h>
 #include <getopt.h>
 #include <sys/types.h>
+
+/* Get mbstate_t, mbrtowc().  */
+#if HAVE_WCHAR_H
+# include <wchar.h>
+#endif
 #include "system.h"
 
 #include "error.h"
@@ -36,6 +41,18 @@
 #include "quote.h"
 #include "xstrndup.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
+# undef MB_LEN_MAX
+# 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 "cut"
 
@@ -71,6 +88,52 @@
     }							\
   while (0)
 
+/* Refill the buffer BUF to get a multibyte character. */
+#define REFILL_BUFFER(BUF, BUFPOS, BUFLEN, STREAM)                        \
+  do                                                                        \
+    {                                                                        \
+      if (BUFLEN < MB_LEN_MAX && !feof (STREAM) && !ferror (STREAM))        \
+        {                                                                \
+          memmove (BUF, BUFPOS, BUFLEN);                                \
+          BUFLEN += fread (BUF + BUFLEN, sizeof(char), BUFSIZ, STREAM); \
+          BUFPOS = BUF;                                                        \
+        }                                                                \
+    }                                                                        \
+  while (0)
+
+/* Get wide character on BUFPOS. BUFPOS is not included after that.
+   If byte sequence is not valid as a character, CONVFAIL is 1. Otherwise 0. */ 
+#define GET_NEXT_WC_FROM_BUFFER(WC, BUFPOS, BUFLEN, MBLENGTH, STATE, CONVFAIL) \
+  do                                                                        \
+    {                                                                        \
+      mbstate_t state_bak;                                                \
+                                                                        \
+      if (BUFLEN < 1)                                                        \
+        {                                                                \
+          WC = WEOF;                                                        \
+          break;                                                        \
+        }                                                                \
+                                                                        \
+      /* Get a wide character. */                                        \
+      CONVFAIL = 0;                                                        \
+      state_bak = STATE;                                                \
+      MBLENGTH = mbrtowc ((wchar_t *)&WC, BUFPOS, BUFLEN, &STATE);        \
+                                                                        \
+      switch (MBLENGTH)                                                        \
+        {                                                                \
+        case (size_t)-1:                                                \
+        case (size_t)-2:                                                \
+          CONVFAIL++;                                                        \
+          STATE = state_bak;                                                \
+          /* Fall througn. */                                                \
+                                                                        \
+        case 0:                                                                \
+          MBLENGTH = 1;                                                        \
+          break;                                                        \
+        }                                                                \
+    }                                                                        \
+  while (0)
+
 struct range_pair
   {
     size_t lo;
@@ -89,7 +152,7 @@ static char *field_1_buffer;
 /* The number of bytes allocated for FIELD_1_BUFFER.  */
 static size_t field_1_bufsize;
 
-/* The largest field or byte index used as an endpoint of a closed
+/* The largest byte, character or field index used as an endpoint of a closed
    or degenerate range specification;  this doesn't include the starting
    index of right-open-ended ranges.  For example, with either range spec
    `2-5,9-', `2-3,5,9-' this variable would be set to 5.  */
@@ -101,10 +164,11 @@ static size_t eol_range_start;
 
 /* This is a bit vector.
    In byte mode, which bytes to output.
+   In character mode, which characters to output.
    In field mode, which DELIM-separated fields to output.
-   Both bytes and fields are numbered starting with 1,
+   Bytes, characters and fields are numbered starting with 1,
    so the zeroth bit of this array is unused.
-   A field or byte K has been selected if
+   A byte, character or field K has been selected if
    (K <= MAX_RANGE_ENDPOINT and is_printable_field(K))
     || (EOL_RANGE_START > 0 && K >= EOL_RANGE_START).  */
 static unsigned char *printable_field;
@@ -113,15 +177,25 @@ enum operating_mode
   {
     undefined_mode,
 
-    /* Output characters that are in the given bytes. */
+    /* Output bytes that are at the given positions. */
     byte_mode,
 
+    /* Output characters that are at the given positions. */
+    character_mode,
+
     /* Output the given delimeter-separated fields. */
     field_mode
   };
 
 static enum operating_mode operating_mode;
 
+/* If nonzero, when in byte mode, don't split multibyte characters.  */
+static int byte_mode_character_aware;
+
+/* If nonzero, the function for single byte locale is work
+   if this program runs on multibyte locale. */
+static int force_singlebyte_mode;
+
 /* If true do not output lines containing no delimeter characters.
    Otherwise, all such lines are printed.  This option is valid only
    with field mode.  */
@@ -133,6 +207,9 @@ static bool complement;
 
 /* The delimeter character for field mode. */
 static unsigned char delim;
+#if HAVE_WCHAR_H
+static wchar_t wcdelim;
+#endif
 
 /* True if the --output-delimiter=STRING option was specified.  */
 static bool output_delimiter_specified;
@@ -206,7 +283,7 @@ Mandatory arguments to long options are 
   -f, --fields=LIST       select only these fields;  also print any line\n\
                             that contains no delimiter character, unless\n\
                             the -s option is specified\n\
-  -n                      (ignored)\n\
+  -n                      with -b: don't split multibyte characters\n\
 "), stdout);
       fputs (_("\
       --complement        complement the set of selected bytes, characters\n\
@@ -365,7 +442,7 @@ set_fields (const char *fieldstr)
           in_digits = false;
           /* Starting a range. */
           if (dash_found)
-            FATAL_ERROR (_("invalid byte or field list"));
+            FATAL_ERROR (_("invalid byte, character or field list"));
           dash_found = true;
           fieldstr++;
 
@@ -389,14 +466,16 @@ set_fields (const char *fieldstr)
               if (!rhs_specified)
                 {
                   /* `n-'.  From `initial' to end of line. */
-                  eol_range_start = initial;
+                  if (eol_range_start == 0 ||
+                      (eol_range_start != 0 && eol_range_start > initial))
+                    eol_range_start = initial;
                   field_found = true;
                 }
               else
                 {
                   /* `m-n' or `-n' (1-n). */
                   if (value < initial)
-                    FATAL_ERROR (_("invalid decreasing range"));
+                    FATAL_ERROR (_("invalid byte, character or field list"));
 
                   /* Is there already a range going to end of line? */
                   if (eol_range_start != 0)
@@ -476,6 +555,9 @@ set_fields (const char *fieldstr)
               if (operating_mode == byte_mode)
                 error (0, 0,
                        _("byte offset %s is too large"), quote (bad_num));
+              else if (operating_mode == character_mode)
+                error (0, 0,
+                       _("character offset %s is too large"), quote (bad_num));
               else
                 error (0, 0,
                        _("field number %s is too large"), quote (bad_num));
@@ -486,7 +568,7 @@ set_fields (const char *fieldstr)
           fieldstr++;
         }
       else
-        FATAL_ERROR (_("invalid byte or field list"));
+        FATAL_ERROR (_("invalid byte, character or field list"));
     }
 
   max_range_endpoint = 0;
@@ -579,6 +661,63 @@ cut_bytes (FILE *stream)
     }
 }
 
+#if HAVE_MBRTOWC
+/* This function is in use for the following case.
+
+   1. Read from the stream STREAM, printing to standard output any selected
+   characters. 
+
+   2. Read from stream STREAM, printing to standard output any selected bytes,
+   without splitting multibyte characters.  */
+ 
+static void
+cut_characters_or_cut_bytes_no_split (FILE *stream)
+{
+  int idx;                /* number of bytes or characters in the line so far. */
+  char buf[MB_LEN_MAX + BUFSIZ];  /* For spooling a read byte sequence. */
+  char *bufpos;                /* Next read position of BUF. */
+  size_t buflen;        /* 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. */
+  mbstate_t state;        /* State of the stream. */
+  int convfail;                /* 1, when conversion is failed. Otherwise 0. */
+
+  idx = 0;
+  buflen = 0;
+  bufpos = buf;
+  memset (&state, '\0', sizeof(mbstate_t));
+
+  while (1)
+    {
+      REFILL_BUFFER (buf, bufpos, buflen, stream);
+
+      GET_NEXT_WC_FROM_BUFFER (wc, bufpos, buflen, mblength, state, convfail);
+
+      if (wc == WEOF)
+        {
+          if (idx > 0)
+            putchar ('\n');
+          break;
+        }
+      else if (wc == L'\n')
+        {
+          putchar ('\n');
+          idx = 0;
+        }
+      else
+        {
+          idx += (operating_mode == byte_mode) ? mblength : 1;
+          if (print_kth (idx, NULL))
+            fwrite (bufpos, mblength, sizeof(char), stdout);
+        }
+
+      buflen -= mblength;
+      bufpos += mblength;
+    }
+}
+#endif
+                   
 /* Read from stream STREAM, printing to standard output any selected fields.  */
 
 static void
@@ -701,13 +840,192 @@ cut_fields (FILE *stream)
     }
 }
 
+#if HAVE_MBRTOWC
+static void
+cut_fields_mb (FILE *stream)
+{
+  int c;
+  unsigned int field_idx;
+  int found_any_selected_field;
+  int buffer_first_field;
+  int empty_input;
+  char buf[MB_LEN_MAX + BUFSIZ];  /* For spooling a read byte sequence. */
+  char *bufpos;                /* Next read position of BUF. */
+  size_t buflen;        /* The length of the byte sequence in buf. */
+  wint_t wc = 0;        /* A gotten wide character. */
+  size_t mblength;        /* The byte size of a multibyte character which shows
+                           as same character as WC. */
+  mbstate_t state;        /* State of the stream. */
+  int convfail;                /* 1, when conversion is failed. Otherwise 0. */
+
+  found_any_selected_field = 0;
+  field_idx = 1;
+  bufpos = buf;
+  buflen = 0;
+  memset (&state, '\0', sizeof(mbstate_t));
+
+  c = getc (stream);
+  empty_input = (c == EOF);
+  if (c != EOF)
+    ungetc (c, stream);
+  else
+    wc = WEOF;
+
+  /* To support the semantics of the -s flag, we may have to buffer
+     all of the first field to determine whether it is `delimited.'
+     But that is unnecessary if all non-delimited lines must be printed
+     and the first field has been selected, or if non-delimited lines
+     must be suppressed and the first field has *not* been selected.
+     That is because a non-delimited line has exactly one field.  */
+  buffer_first_field = (suppress_non_delimited ^ !print_kth (1, NULL));
+
+  while (1)
+    {
+      if (field_idx == 1 && buffer_first_field)
+        {
+          int len = 0;
+
+          while (1)
+            {
+              REFILL_BUFFER (buf, bufpos, buflen, stream);
+
+              GET_NEXT_WC_FROM_BUFFER
+                (wc, bufpos, buflen, mblength, state, convfail);
+
+              if (wc == WEOF)
+                break;
+
+              field_1_buffer = xrealloc (field_1_buffer, len + mblength);
+              memcpy (field_1_buffer + len, bufpos, mblength);
+              len += mblength;
+              buflen -= mblength;
+              bufpos += mblength;
+
+              if (!convfail && (wc == L'\n' || wc == wcdelim))
+                break;
+            }
+
+          if (wc == WEOF)
+            break;
+
+          /* If the first field extends to the end of line (it is not
+             delimited) and we are printing all non-delimited lines,
+             print this one.  */
+          if (convfail || (!convfail && wc != wcdelim))
+            {
+              if (suppress_non_delimited)
+                {
+                  /* Empty.        */
+                }
+              else
+                {
+                  fwrite (field_1_buffer, sizeof (char), len, stdout);
+                  /* Make sure the output line is newline terminated.  */
+                  if (convfail || (!convfail && wc != L'\n'))
+                    putchar ('\n');
+                }
+              continue;
+            }
+
+          if (print_kth (1, NULL))
+            {
+              /* Print the field, but not the trailing delimiter.  */
+              fwrite (field_1_buffer, sizeof (char), len - 1, stdout);
+              found_any_selected_field = 1;
+            }
+          ++field_idx;
+        }
+
+      if (wc != WEOF)
+        {
+          if (print_kth (field_idx, NULL))
+            {
+              if (found_any_selected_field)
+                {
+                  fwrite (output_delimiter_string, sizeof (char),
+                          output_delimiter_length, stdout);
+                }
+              found_any_selected_field = 1;
+            }
+
+          while (1)
+            {
+              REFILL_BUFFER (buf, bufpos, buflen, stream);
+
+              GET_NEXT_WC_FROM_BUFFER
+                (wc, bufpos, buflen, mblength, state, convfail);
+
+              if (wc == WEOF)
+                break;
+              else if (!convfail && (wc == wcdelim || wc == L'\n'))
+                {
+                  buflen -= mblength;
+                  bufpos += mblength;
+                  break;
+                }
+
+              if (print_kth (field_idx, NULL))
+                fwrite (bufpos, mblength, sizeof(char), stdout);
+
+              buflen -= mblength;
+              bufpos += mblength;
+            }
+        }
+
+      if ((!convfail || wc == L'\n') && buflen < 1)
+        wc = WEOF;
+
+      if (!convfail && wc == wcdelim)
+        ++field_idx;
+      else if (wc == WEOF || (!convfail && wc == L'\n'))
+        {
+          if (found_any_selected_field
+              || (!empty_input && !(suppress_non_delimited && field_idx == 1)))
+            putchar ('\n');
+          if (wc == WEOF)
+            break;
+          field_idx = 1;
+          found_any_selected_field = 0;
+        }
+    }
+}
+#endif
+
 static void
 cut_stream (FILE *stream)
 {
-  if (operating_mode == byte_mode)
-    cut_bytes (stream);
+#if HAVE_MBRTOWC
+  if (MB_CUR_MAX > 1 && !force_singlebyte_mode)
+    {
+      switch (operating_mode)
+        {
+        case byte_mode:
+          if (byte_mode_character_aware)
+            cut_characters_or_cut_bytes_no_split (stream);
+          else
+            cut_bytes (stream);
+          break;
+
+        case character_mode:
+          cut_characters_or_cut_bytes_no_split (stream);
+          break;
+
+        case field_mode:
+          cut_fields_mb (stream);
+          break;
+
+        default:
+          abort ();
+        }
+    }
   else
-    cut_fields (stream);
+#endif
+    {
+      if (operating_mode == field_mode)
+        cut_fields (stream);
+      else
+        cut_bytes (stream);
+    }
 }
 
 /* Process file FILE to standard output.
@@ -757,6 +1075,8 @@ main (int argc, char **argv)
   bool ok;
   bool delim_specified = false;
   char *spec_list_string IF_LINT(= NULL);
+  char mbdelim[MB_LEN_MAX + 1];
+  size_t delimlen = 0;
 
   initialize_main (&argc, &argv);
   set_program_name (argv[0]);
@@ -779,7 +1099,6 @@ main (int argc, char **argv)
       switch (optc)
         {
         case 'b':
-        case 'c':
           /* Build the byte list. */
           if (operating_mode != undefined_mode)
             FATAL_ERROR (_("only one type of list may be specified"));
@@ -787,6 +1106,14 @@ main (int argc, char **argv)
           spec_list_string = optarg;
           break;
 
+        case 'c':
+          /* Build the character list. */
+          if (operating_mode != undefined_mode)
+            FATAL_ERROR (_("only one type of list may be specified"));
+          operating_mode = character_mode;
+          spec_list_string = optarg;
+          break;
+
         case 'f':
           /* Build the field list. */
           if (operating_mode != undefined_mode)
@@ -798,10 +1125,35 @@ main (int argc, char **argv)
         case 'd':
           /* New delimiter. */
           /* Interpret -d '' to mean `use the NUL byte as the delimiter.'  */
-          if (optarg[0] != '\0' && optarg[1] != '\0')
-            FATAL_ERROR (_("the delimiter must be a single character"));
-          delim = optarg[0];
-          delim_specified = true;
+            {
+#if HAVE_MBRTOWC
+              if(MB_CUR_MAX > 1)
+                {
+                  mbstate_t state;
+
+                  memset (&state, '\0', sizeof(mbstate_t));
+                  delimlen = mbrtowc (&wcdelim, optarg, strnlen(optarg, MB_LEN_MAX), &state);
+
+                  if (delimlen == (size_t)-1 || delimlen == (size_t)-2)
+                    ++force_singlebyte_mode;
+                  else
+                    {
+                      delimlen = (delimlen < 1) ? 1 : delimlen;
+                      if (wcdelim != L'\0' && *(optarg + delimlen) != '\0')
+                        FATAL_ERROR (_("the delimiter must be a single character"));
+                      memcpy (mbdelim, optarg, delimlen);
+                    }
+                }
+
+              if (MB_CUR_MAX <= 1 || force_singlebyte_mode)
+#endif
+                {
+                  if (optarg[0] != '\0' && optarg[1] != '\0')
+                    FATAL_ERROR (_("the delimiter must be a single character"));
+                  delim = (unsigned char) optarg[0];
+                }
+            delim_specified = true;
+          }
           break;
 
         case OUTPUT_DELIMITER_OPTION:
@@ -814,6 +1166,7 @@ main (int argc, char **argv)
           break;
 
         case 'n':
+          byte_mode_character_aware = 1;
           break;
 
         case 's':
@@ -836,7 +1189,7 @@ main (int argc, char **argv)
   if (operating_mode == undefined_mode)
     FATAL_ERROR (_("you must specify a list of bytes, characters, or fields"));
 
-  if (delim != '\0' && operating_mode != field_mode)
+  if (delim_specified && operating_mode != field_mode)
     FATAL_ERROR (_("an input delimiter may be specified only\
  when operating on fields"));
 
@@ -863,15 +1216,34 @@ main (int argc, char **argv)
     }
 
   if (!delim_specified)
-    delim = '\t';
+    {
+      delim = '\t';
+#ifdef HAVE_MBRTOWC
+      wcdelim = L'\t';
+      mbdelim[0] = '\t';
+      mbdelim[1] = '\0';
+      delimlen = 1;
+#endif
+    }
 
   if (output_delimiter_string == NULL)
     {
-      static char dummy[2];
-      dummy[0] = delim;
-      dummy[1] = '\0';
-      output_delimiter_string = dummy;
-      output_delimiter_length = 1;
+#ifdef HAVE_MBRTOWC
+      if (MB_CUR_MAX > 1 && !force_singlebyte_mode)
+        {
+          output_delimiter_string = xstrdup(mbdelim);
+          output_delimiter_length = delimlen;
+        }
+
+      if (MB_CUR_MAX <= 1 || force_singlebyte_mode)
+#endif
+        {
+          static char dummy[2]; 
+          dummy[0] = delim;
+          dummy[1] = '\0';
+          output_delimiter_string = dummy;
+          output_delimiter_length = 1;
+        }
     }
 
   if (optind == argc)
diff -urNp coreutils-8.0-orig/src/cut.c.orig coreutils-8.0/src/cut.c.orig
--- coreutils-8.0-orig/src/cut.c.orig	1970-01-01 01:00:00.000000000 +0100
+++ coreutils-8.0/src/cut.c.orig	2009-09-23 10:25:44.000000000 +0200
@@ -0,0 +1,893 @@
+/* cut - remove parts of lines of files
+   Copyright (C) 1997-2009 Free Software Foundation, Inc.
+   Copyright (C) 1984 David M. Ihnat
+
+   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 David Ihnat.  */
+
+/* POSIX changes, bug fixes, long-named options, and cleanup
+   by David MacKenzie <djm@gnu.ai.mit.edu>.
+
+   Rewrite cut_fields and cut_bytes -- Jim Meyering.  */
+
+#include <config.h>
+
+#include <stdio.h>
+#include <assert.h>
+#include <getopt.h>
+#include <sys/types.h>
+#include "system.h"
+
+#include "error.h"
+#include "getndelim2.h"
+#include "hash.h"
+#include "quote.h"
+#include "xstrndup.h"
+
+/* The official name of this program (e.g., no `g' prefix).  */
+#define PROGRAM_NAME "cut"
+
+#define AUTHORS \
+  proper_name ("David M. Ihnat"), \
+  proper_name ("David MacKenzie"), \
+  proper_name ("Jim Meyering")
+
+#define FATAL_ERROR(Message)						\
+  do									\
+    {									\
+      error (0, 0, (Message));						\
+      usage (EXIT_FAILURE);						\
+    }									\
+  while (0)
+
+/* Append LOW, HIGH to the list RP of range pairs, allocating additional
+   space if necessary.  Update local variable N_RP.  When allocating,
+   update global variable N_RP_ALLOCATED.  */
+
+#define ADD_RANGE_PAIR(rp, low, high)			\
+  do							\
+    {							\
+      if (low == 0 || high == 0)			\
+        FATAL_ERROR (_("fields and positions are numbered from 1")); \
+      if (n_rp >= n_rp_allocated)			\
+        {						\
+          (rp) = X2NREALLOC (rp, &n_rp_allocated);	\
+        }						\
+      rp[n_rp].lo = (low);				\
+      rp[n_rp].hi = (high);				\
+      ++n_rp;						\
+    }							\
+  while (0)
+
+struct range_pair
+  {
+    size_t lo;
+    size_t hi;
+  };
+
+/* This buffer is used to support the semantics of the -s option
+   (or lack of same) when the specified field list includes (does
+   not include) the first field.  In both of those cases, the entire
+   first field must be read into this buffer to determine whether it
+   is followed by a delimiter or a newline before any of it may be
+   output.  Otherwise, cut_fields can do the job without using this
+   buffer.  */
+static char *field_1_buffer;
+
+/* The number of bytes allocated for FIELD_1_BUFFER.  */
+static size_t field_1_bufsize;
+
+/* The largest field or byte index used as an endpoint of a closed
+   or degenerate range specification;  this doesn't include the starting
+   index of right-open-ended ranges.  For example, with either range spec
+   `2-5,9-', `2-3,5,9-' this variable would be set to 5.  */
+static size_t max_range_endpoint;
+
+/* If nonzero, this is the index of the first field in a range that goes
+   to end of line. */
+static size_t eol_range_start;
+
+/* This is a bit vector.
+   In byte mode, which bytes to output.
+   In field mode, which DELIM-separated fields to output.
+   Both bytes and fields are numbered starting with 1,
+   so the zeroth bit of this array is unused.
+   A field or byte K has been selected if
+   (K <= MAX_RANGE_ENDPOINT and is_printable_field(K))
+    || (EOL_RANGE_START > 0 && K >= EOL_RANGE_START).  */
+static unsigned char *printable_field;
+
+enum operating_mode
+  {
+    undefined_mode,
+
+    /* Output characters that are in the given bytes. */
+    byte_mode,
+
+    /* Output the given delimeter-separated fields. */
+    field_mode
+  };
+
+static enum operating_mode operating_mode;
+
+/* If true do not output lines containing no delimeter characters.
+   Otherwise, all such lines are printed.  This option is valid only
+   with field mode.  */
+static bool suppress_non_delimited;
+
+/* If nonzero, print all bytes, characters, or fields _except_
+   those that were specified.  */
+static bool complement;
+
+/* The delimeter character for field mode. */
+static unsigned char delim;
+
+/* True if the --output-delimiter=STRING option was specified.  */
+static bool output_delimiter_specified;
+
+/* The length of output_delimiter_string.  */
+static size_t output_delimiter_length;
+
+/* The output field separator string.  Defaults to the 1-character
+   string consisting of the input delimiter.  */
+static char *output_delimiter_string;
+
+/* True if we have ever read standard input. */
+static bool have_read_stdin;
+
+#define HT_RANGE_START_INDEX_INITIAL_CAPACITY 31
+
+/* The set of range-start indices.  For example, given a range-spec list like
+   `-b1,3-5,4-9,15-', the following indices will be recorded here: 1, 3, 15.
+   Note that although `4' looks like a range-start index, it is in the middle
+   of the `3-5' range, so it doesn't count.
+   This table is created/used IFF output_delimiter_specified is set.  */
+static Hash_table *range_start_ht;
+
+/* For long options that have no equivalent short option, use a
+   non-character as a pseudo short option, starting with CHAR_MAX + 1.  */
+enum
+{
+  OUTPUT_DELIMITER_OPTION = CHAR_MAX + 1,
+  COMPLEMENT_OPTION
+};
+
+static struct option const longopts[] =
+{
+  {"bytes", required_argument, NULL, 'b'},
+  {"characters", required_argument, NULL, 'c'},
+  {"fields", required_argument, NULL, 'f'},
+  {"delimiter", required_argument, NULL, 'd'},
+  {"only-delimited", no_argument, NULL, 's'},
+  {"output-delimiter", required_argument, NULL, OUTPUT_DELIMITER_OPTION},
+  {"complement", no_argument, NULL, COMPLEMENT_OPTION},
+  {GETOPT_HELP_OPTION_DECL},
+  {GETOPT_VERSION_OPTION_DECL},
+  {NULL, 0, NULL, 0}
+};
+
+void
+usage (int status)
+{
+  if (status != EXIT_SUCCESS)
+    fprintf (stderr, _("Try `%s --help' for more information.\n"),
+             program_name);
+  else
+    {
+      printf (_("\
+Usage: %s OPTION... [FILE]...\n\
+"),
+              program_name);
+      fputs (_("\
+Print selected parts of lines from each FILE to standard output.\n\
+\n\
+"), stdout);
+      fputs (_("\
+Mandatory arguments to long options are mandatory for short options too.\n\
+"), stdout);
+      fputs (_("\
+  -b, --bytes=LIST        select only these bytes\n\
+  -c, --characters=LIST   select only these characters\n\
+  -d, --delimiter=DELIM   use DELIM instead of TAB for field delimiter\n\
+"), stdout);
+      fputs (_("\
+  -f, --fields=LIST       select only these fields;  also print any line\n\
+                            that contains no delimiter character, unless\n\
+                            the -s option is specified\n\
+  -n                      (ignored)\n\
+"), stdout);
+      fputs (_("\
+      --complement        complement the set of selected bytes, characters\n\
+                            or fields\n\
+"), stdout);
+      fputs (_("\
+  -s, --only-delimited    do not print lines not containing delimiters\n\
+      --output-delimiter=STRING  use STRING as the output delimiter\n\
+                            the default is to use the input delimiter\n\
+"), stdout);
+      fputs (HELP_OPTION_DESCRIPTION, stdout);
+      fputs (VERSION_OPTION_DESCRIPTION, stdout);
+      fputs (_("\
+\n\
+Use one, and only one of -b, -c or -f.  Each LIST is made up of one\n\
+range, or many ranges separated by commas.  Selected input is written\n\
+in the same order that it is read, and is written exactly once.\n\
+"), stdout);
+      fputs (_("\
+Each range is one of:\n\
+\n\
+  N     N'th byte, character or field, counted from 1\n\
+  N-    from N'th byte, character or field, to end of line\n\
+  N-M   from N'th to M'th (included) byte, character or field\n\
+  -M    from first to M'th (included) byte, character or field\n\
+\n\
+With no FILE, or when FILE is -, read standard input.\n\
+"), stdout);
+      emit_ancillary_info ();
+    }
+  exit (status);
+}
+
+static inline void
+mark_range_start (size_t i)
+{
+  /* Record the fact that `i' is a range-start index.  */
+  void *ent_from_table = hash_insert (range_start_ht, (void*) i);
+  if (ent_from_table == NULL)
+    {
+      /* Insertion failed due to lack of memory.  */
+      xalloc_die ();
+    }
+  assert ((size_t) ent_from_table == i);
+}
+
+static inline void
+mark_printable_field (size_t i)
+{
+  size_t n = i / CHAR_BIT;
+  printable_field[n] |= (1 << (i % CHAR_BIT));
+}
+
+static inline bool
+is_printable_field (size_t i)
+{
+  size_t n = i / CHAR_BIT;
+  return (printable_field[n] >> (i % CHAR_BIT)) & 1;
+}
+
+static size_t
+hash_int (const void *x, size_t tablesize)
+{
+#ifdef UINTPTR_MAX
+  uintptr_t y = (uintptr_t) x;
+#else
+  size_t y = (size_t) x;
+#endif
+  return y % tablesize;
+}
+
+static bool
+hash_compare_ints (void const *x, void const *y)
+{
+  return (x == y) ? true : false;
+}
+
+static bool
+is_range_start_index (size_t i)
+{
+  return hash_lookup (range_start_ht, (void *) i) ? true : false;
+}
+
+/* Return nonzero if the K'th field or byte is printable.
+   When returning nonzero, if RANGE_START is non-NULL,
+   set *RANGE_START to true if K is the beginning of a range, and to
+   false otherwise.  */
+
+static bool
+print_kth (size_t k, bool *range_start)
+{
+  bool k_selected
+    = ((0 < eol_range_start && eol_range_start <= k)
+       || (k <= max_range_endpoint && is_printable_field (k)));
+
+  bool is_selected = k_selected ^ complement;
+  if (range_start && is_selected)
+    *range_start = is_range_start_index (k);
+
+  return is_selected;
+}
+
+/* Comparison function for qsort to order the list of
+   struct range_pairs.  */
+static int
+compare_ranges (const void *a, const void *b)
+{
+  int a_start = ((const struct range_pair *) a)->lo;
+  int b_start = ((const struct range_pair *) b)->lo;
+  return a_start < b_start ? -1 : a_start > b_start;
+}
+
+/* Given the list of field or byte range specifications FIELDSTR, set
+   MAX_RANGE_ENDPOINT and allocate and initialize the PRINTABLE_FIELD
+   array.  If there is a right-open-ended range, set EOL_RANGE_START
+   to its starting index.  FIELDSTR should be composed of one or more
+   numbers or ranges of numbers, separated by blanks or commas.
+   Incomplete ranges may be given: `-m' means `1-m'; `n-' means `n'
+   through end of line.  Return true if FIELDSTR contains at least
+   one field specification, false otherwise.  */
+
+/* FIXME-someday:  What if the user wants to cut out the 1,000,000-th
+   field of some huge input file?  This function shouldn't have to
+   allocate a table of a million bits just so we can test every
+   field < 10^6 with an array dereference.  Instead, consider using
+   an adaptive approach: if the range of selected fields is too large,
+   but only a few fields/byte-offsets are actually selected, use a
+   hash table.  If the range of selected fields is too large, and
+   too many are selected, then resort to using the range-pairs (the
+   `rp' array) directly.  */
+
+static bool
+set_fields (const char *fieldstr)
+{
+  size_t initial = 1;		/* Value of first number in a range.  */
+  size_t value = 0;		/* If nonzero, a number being accumulated.  */
+  bool lhs_specified = false;
+  bool rhs_specified = false;
+  bool dash_found = false;	/* True if a '-' is found in this field.  */
+  bool field_found = false;	/* True if at least one field spec
+                                   has been processed.  */
+
+  struct range_pair *rp = NULL;
+  size_t n_rp = 0;
+  size_t n_rp_allocated = 0;
+  size_t i;
+  bool in_digits = false;
+
+  /* Collect and store in RP the range end points.
+     It also sets EOL_RANGE_START if appropriate.  */
+
+  for (;;)
+    {
+      if (*fieldstr == '-')
+        {
+          in_digits = false;
+          /* Starting a range. */
+          if (dash_found)
+            FATAL_ERROR (_("invalid byte or field list"));
+          dash_found = true;
+          fieldstr++;
+
+          initial = (lhs_specified ? value : 1);
+          value = 0;
+        }
+      else if (*fieldstr == ',' ||
+               isblank (to_uchar (*fieldstr)) || *fieldstr == '\0')
+        {
+          in_digits = false;
+          /* Ending the string, or this field/byte sublist. */
+          if (dash_found)
+            {
+              dash_found = false;
+
+              if (!lhs_specified && !rhs_specified)
+                FATAL_ERROR (_("invalid range with no endpoint: -"));
+
+              /* A range.  Possibilities: -n, m-n, n-.
+                 In any case, `initial' contains the start of the range. */
+              if (!rhs_specified)
+                {
+                  /* `n-'.  From `initial' to end of line. */
+                  eol_range_start = initial;
+                  field_found = true;
+                }
+              else
+                {
+                  /* `m-n' or `-n' (1-n). */
+                  if (value < initial)
+                    FATAL_ERROR (_("invalid decreasing range"));
+
+                  /* Is there already a range going to end of line? */
+                  if (eol_range_start != 0)
+                    {
+                      /* Yes.  Is the new sequence already contained
+                         in the old one?  If so, no processing is
+                         necessary. */
+                      if (initial < eol_range_start)
+                        {
+                          /* No, the new sequence starts before the
+                             old.  Does the old range going to end of line
+                             extend into the new range?  */
+                          if (eol_range_start <= value)
+                            {
+                              /* Yes.  Simply move the end of line marker. */
+                              eol_range_start = initial;
+                            }
+                          else
+                            {
+                              /* No.  A simple range, before and disjoint from
+                                 the range going to end of line.  Fill it. */
+                              ADD_RANGE_PAIR (rp, initial, value);
+                            }
+
+                          /* In any case, some fields were selected. */
+                          field_found = true;
+                        }
+                    }
+                  else
+                    {
+                      /* There is no range going to end of line. */
+                      ADD_RANGE_PAIR (rp, initial, value);
+                      field_found = true;
+                    }
+                  value = 0;
+                }
+            }
+          else
+            {
+              /* A simple field number, not a range. */
+              ADD_RANGE_PAIR (rp, value, value);
+              value = 0;
+              field_found = true;
+            }
+
+          if (*fieldstr == '\0')
+            {
+              break;
+            }
+
+          fieldstr++;
+          lhs_specified = false;
+          rhs_specified = false;
+        }
+      else if (ISDIGIT (*fieldstr))
+        {
+          /* Record beginning of digit string, in case we have to
+             complain about it.  */
+          static char const *num_start;
+          if (!in_digits || !num_start)
+            num_start = fieldstr;
+          in_digits = true;
+
+          if (dash_found)
+            rhs_specified = 1;
+          else
+            lhs_specified = 1;
+
+          /* Detect overflow.  */
+          if (!DECIMAL_DIGIT_ACCUMULATE (value, *fieldstr - '0', size_t))
+            {
+              /* In case the user specified -c$(echo 2^64|bc),22,
+                 complain only about the first number.  */
+              /* Determine the length of the offending number.  */
+              size_t len = strspn (num_start, "0123456789");
+              char *bad_num = xstrndup (num_start, len);
+              if (operating_mode == byte_mode)
+                error (0, 0,
+                       _("byte offset %s is too large"), quote (bad_num));
+              else
+                error (0, 0,
+                       _("field number %s is too large"), quote (bad_num));
+              free (bad_num);
+              exit (EXIT_FAILURE);
+            }
+
+          fieldstr++;
+        }
+      else
+        FATAL_ERROR (_("invalid byte or field list"));
+    }
+
+  max_range_endpoint = 0;
+  for (i = 0; i < n_rp; i++)
+    {
+      if (rp[i].hi > max_range_endpoint)
+        max_range_endpoint = rp[i].hi;
+    }
+
+  /* Allocate an array large enough so that it may be indexed by
+     the field numbers corresponding to all finite ranges
+     (i.e. `2-6' or `-4', but not `5-') in FIELDSTR.  */
+
+  printable_field = xzalloc (max_range_endpoint / CHAR_BIT + 1);
+
+  qsort (rp, n_rp, sizeof (rp[0]), compare_ranges);
+
+  /* Set the array entries corresponding to integers in the ranges of RP.  */
+  for (i = 0; i < n_rp; i++)
+    {
+      size_t j;
+      size_t rsi_candidate;
+
+      /* Record the range-start indices, i.e., record each start
+         index that is not part of any other (lo..hi] range.  */
+      rsi_candidate = complement ? rp[i].hi + 1 : rp[i].lo;
+      if (output_delimiter_specified
+          && !is_printable_field (rsi_candidate))
+        mark_range_start (rsi_candidate);
+
+      for (j = rp[i].lo; j <= rp[i].hi; j++)
+        mark_printable_field (j);
+    }
+
+  if (output_delimiter_specified
+      && !complement
+      && eol_range_start && !is_printable_field (eol_range_start))
+    mark_range_start (eol_range_start);
+
+  free (rp);
+
+  return field_found;
+}
+
+/* Read from stream STREAM, printing to standard output any selected bytes.  */
+
+static void
+cut_bytes (FILE *stream)
+{
+  size_t byte_idx;	/* Number of bytes in the line so far. */
+  /* Whether to begin printing delimiters between ranges for the current line.
+     Set after we've begun printing data corresponding to the first range.  */
+  bool print_delimiter;
+
+  byte_idx = 0;
+  print_delimiter = false;
+  while (1)
+    {
+      int c;		/* Each character from the file. */
+
+      c = getc (stream);
+
+      if (c == '\n')
+        {
+          putchar ('\n');
+          byte_idx = 0;
+          print_delimiter = false;
+        }
+      else if (c == EOF)
+        {
+          if (byte_idx > 0)
+            putchar ('\n');
+          break;
+        }
+      else
+        {
+          bool range_start;
+          bool *rs = output_delimiter_specified ? &range_start : NULL;
+          if (print_kth (++byte_idx, rs))
+            {
+              if (rs && *rs && print_delimiter)
+                {
+                  fwrite (output_delimiter_string, sizeof (char),
+                          output_delimiter_length, stdout);
+                }
+              print_delimiter = true;
+              putchar (c);
+            }
+        }
+    }
+}
+
+/* Read from stream STREAM, printing to standard output any selected fields.  */
+
+static void
+cut_fields (FILE *stream)
+{
+  int c;
+  size_t field_idx = 1;
+  bool found_any_selected_field = false;
+  bool buffer_first_field;
+
+  c = getc (stream);
+  if (c == EOF)
+    return;
+
+  ungetc (c, stream);
+
+  /* To support the semantics of the -s flag, we may have to buffer
+     all of the first field to determine whether it is `delimited.'
+     But that is unnecessary if all non-delimited lines must be printed
+     and the first field has been selected, or if non-delimited lines
+     must be suppressed and the first field has *not* been selected.
+     That is because a non-delimited line has exactly one field.  */
+  buffer_first_field = (suppress_non_delimited ^ !print_kth (1, NULL));
+
+  while (1)
+    {
+      if (field_idx == 1 && buffer_first_field)
+        {
+          ssize_t len;
+          size_t n_bytes;
+
+          len = getndelim2 (&field_1_buffer, &field_1_bufsize, 0,
+                            GETNLINE_NO_LIMIT, delim, '\n', stream);
+          if (len < 0)
+            {
+              free (field_1_buffer);
+              field_1_buffer = NULL;
+              if (ferror (stream) || feof (stream))
+                break;
+              xalloc_die ();
+            }
+
+          n_bytes = len;
+          assert (n_bytes != 0);
+
+          /* If the first field extends to the end of line (it is not
+             delimited) and we are printing all non-delimited lines,
+             print this one.  */
+          if (to_uchar (field_1_buffer[n_bytes - 1]) != delim)
+            {
+              if (suppress_non_delimited)
+                {
+                  /* Empty.  */
+                }
+              else
+                {
+                  fwrite (field_1_buffer, sizeof (char), n_bytes, stdout);
+                  /* Make sure the output line is newline terminated.  */
+                  if (field_1_buffer[n_bytes - 1] != '\n')
+                    putchar ('\n');
+                }
+              continue;
+            }
+          if (print_kth (1, NULL))
+            {
+              /* Print the field, but not the trailing delimiter.  */
+              fwrite (field_1_buffer, sizeof (char), n_bytes - 1, stdout);
+              found_any_selected_field = true;
+            }
+          ++field_idx;
+        }
+
+      if (c != EOF)
+        {
+          if (print_kth (field_idx, NULL))
+            {
+              if (found_any_selected_field)
+                {
+                  fwrite (output_delimiter_string, sizeof (char),
+                          output_delimiter_length, stdout);
+                }
+              found_any_selected_field = true;
+
+              while ((c = getc (stream)) != delim && c != '\n' && c != EOF)
+                {
+                  putchar (c);
+                }
+            }
+          else
+            {
+              while ((c = getc (stream)) != delim && c != '\n' && c != EOF)
+                {
+                  /* Empty.  */
+                }
+            }
+        }
+
+      if (c == '\n')
+        {
+          c = getc (stream);
+          if (c != EOF)
+            {
+              ungetc (c, stream);
+              c = '\n';
+            }
+        }
+
+      if (c == delim)
+        ++field_idx;
+      else if (c == '\n' || c == EOF)
+        {
+          if (found_any_selected_field
+              || !(suppress_non_delimited && field_idx == 1))
+            putchar ('\n');
+          if (c == EOF)
+            break;
+          field_idx = 1;
+          found_any_selected_field = false;
+        }
+    }
+}
+
+static void
+cut_stream (FILE *stream)
+{
+  if (operating_mode == byte_mode)
+    cut_bytes (stream);
+  else
+    cut_fields (stream);
+}
+
+/* Process file FILE to standard output.
+   Return true if successful.  */
+
+static bool
+cut_file (char const *file)
+{
+  FILE *stream;
+
+  if (STREQ (file, "-"))
+    {
+      have_read_stdin = true;
+      stream = stdin;
+    }
+  else
+    {
+      stream = fopen (file, "r");
+      if (stream == NULL)
+        {
+          error (0, errno, "%s", file);
+          return false;
+        }
+    }
+
+  cut_stream (stream);
+
+  if (ferror (stream))
+    {
+      error (0, errno, "%s", file);
+      return false;
+    }
+  if (STREQ (file, "-"))
+    clearerr (stream);		/* Also clear EOF. */
+  else if (fclose (stream) == EOF)
+    {
+      error (0, errno, "%s", file);
+      return false;
+    }
+  return true;
+}
+
+int
+main (int argc, char **argv)
+{
+  int optc;
+  bool ok;
+  bool delim_specified = false;
+  char *spec_list_string IF_LINT(= NULL);
+
+  initialize_main (&argc, &argv);
+  set_program_name (argv[0]);
+  setlocale (LC_ALL, "");
+  bindtextdomain (PACKAGE, LOCALEDIR);
+  textdomain (PACKAGE);
+
+  atexit (close_stdout);
+
+  operating_mode = undefined_mode;
+
+  /* By default, all non-delimited lines are printed.  */
+  suppress_non_delimited = false;
+
+  delim = '\0';
+  have_read_stdin = false;
+
+  while ((optc = getopt_long (argc, argv, "b:c:d:f:ns", longopts, NULL)) != -1)
+    {
+      switch (optc)
+        {
+        case 'b':
+        case 'c':
+          /* Build the byte list. */
+          if (operating_mode != undefined_mode)
+            FATAL_ERROR (_("only one type of list may be specified"));
+          operating_mode = byte_mode;
+          spec_list_string = optarg;
+          break;
+
+        case 'f':
+          /* Build the field list. */
+          if (operating_mode != undefined_mode)
+            FATAL_ERROR (_("only one type of list may be specified"));
+          operating_mode = field_mode;
+          spec_list_string = optarg;
+          break;
+
+        case 'd':
+          /* New delimiter. */
+          /* Interpret -d '' to mean `use the NUL byte as the delimiter.'  */
+          if (optarg[0] != '\0' && optarg[1] != '\0')
+            FATAL_ERROR (_("the delimiter must be a single character"));
+          delim = optarg[0];
+          delim_specified = true;
+          break;
+
+        case OUTPUT_DELIMITER_OPTION:
+          output_delimiter_specified = true;
+          /* Interpret --output-delimiter='' to mean
+             `use the NUL byte as the delimiter.'  */
+          output_delimiter_length = (optarg[0] == '\0'
+                                     ? 1 : strlen (optarg));
+          output_delimiter_string = xstrdup (optarg);
+          break;
+
+        case 'n':
+          break;
+
+        case 's':
+          suppress_non_delimited = true;
+          break;
+
+        case COMPLEMENT_OPTION:
+          complement = true;
+          break;
+
+        case_GETOPT_HELP_CHAR;
+
+        case_GETOPT_VERSION_CHAR (PROGRAM_NAME, AUTHORS);
+
+        default:
+          usage (EXIT_FAILURE);
+        }
+    }
+
+  if (operating_mode == undefined_mode)
+    FATAL_ERROR (_("you must specify a list of bytes, characters, or fields"));
+
+  if (delim != '\0' && operating_mode != field_mode)
+    FATAL_ERROR (_("an input delimiter may be specified only\
+ when operating on fields"));
+
+  if (suppress_non_delimited && operating_mode != field_mode)
+    FATAL_ERROR (_("suppressing non-delimited lines makes sense\n\
+\tonly when operating on fields"));
+
+  if (output_delimiter_specified)
+    {
+      range_start_ht = hash_initialize (HT_RANGE_START_INDEX_INITIAL_CAPACITY,
+                                        NULL, hash_int,
+                                        hash_compare_ints, NULL);
+      if (range_start_ht == NULL)
+        xalloc_die ();
+
+    }
+
+  if (! set_fields (spec_list_string))
+    {
+      if (operating_mode == field_mode)
+        FATAL_ERROR (_("missing list of fields"));
+      else
+        FATAL_ERROR (_("missing list of positions"));
+    }
+
+  if (!delim_specified)
+    delim = '\t';
+
+  if (output_delimiter_string == NULL)
+    {
+      static char dummy[2];
+      dummy[0] = delim;
+      dummy[1] = '\0';
+      output_delimiter_string = dummy;
+      output_delimiter_length = 1;
+    }
+
+  if (optind == argc)
+    ok = cut_file ("-");
+  else
+    for (ok = true; optind < argc; optind++)
+      ok &= cut_file (argv[optind]);
+
+  if (range_start_ht)
+    hash_free (range_start_ht);
+
+  if (have_read_stdin && fclose (stdin) == EOF)
+    {
+      error (0, errno, "-");
+      ok = false;
+    }
+
+  exit (ok ? EXIT_SUCCESS : EXIT_FAILURE);
+}
diff -urNp coreutils-8.0-orig/src/expand.c coreutils-8.0/src/expand.c
--- coreutils-8.0-orig/src/expand.c	2009-09-29 15:27:54.000000000 +0200
+++ coreutils-8.0/src/expand.c	2009-10-07 10:07:16.000000000 +0200
@@ -37,11 +37,28 @@
 #include <stdio.h>
 #include <getopt.h>
 #include <sys/types.h>
+
+/* Get mbstate_t, mbrtowc(), wcwidth(). */
+#if HAVE_WCHAR_H
+# include <wchar.h>
+#endif
+
 #include "system.h"
 #include "error.h"
 #include "quote.h"
 #include "xstrndup.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
+# 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 "expand"
 
@@ -357,6 +374,142 @@ expand (void)
     }
 }
 
+#if HAVE_MBRTOWC
+static void
+expand_multibyte (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;			/* 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;
+
+  memset (&o_state, '\0', sizeof(mbstate_t));
+  memset (&i_state, '\0', sizeof(mbstate_t));
+
+  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;
+	}
+
+      /* No character is left in BUF. */
+      if (buflen < 1)
+	{
+	  fp = next_file (fp);
+
+	  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);
+
+      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)
+		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;
+
+	      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)
+			convert = 0;
+		    }
+		}
+	      fwrite (bufpos, sizeof(char), mblength, stdout);
+	    }
+	}
+      buflen -= mblength;
+      bufpos += mblength;
+    }
+}
+#endif
+
 int
 main (int argc, char **argv)
 {
@@ -421,7 +574,12 @@ 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 -urNp coreutils-8.0-orig/src/expand.c.orig coreutils-8.0/src/expand.c.orig
--- coreutils-8.0-orig/src/expand.c.orig	1970-01-01 01:00:00.000000000 +0100
+++ coreutils-8.0/src/expand.c.orig	2009-09-29 15:27:54.000000000 +0200
@@ -0,0 +1,430 @@
+/* expand - convert tabs to spaces
+   Copyright (C) 89, 91, 1995-2006, 2008-2009 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/>.  */
+
+/* By default, convert all tabs to spaces.
+   Preserves backspace characters in the output; they decrement the
+   column count for tab calculations.
+   The default action is equivalent to -8.
+
+   Options:
+   --tabs=tab1[,tab2[,...]]
+   -t tab1[,tab2[,...]]
+   -tab1[,tab2[,...]]	If only one tab stop is given, set the tabs tab1
+                        columns apart instead of the default 8.  Otherwise,
+                        set the tabs at columns tab1, tab2, etc. (numbered from
+                        0); replace any tabs beyond the tab stops given with
+                        single spaces.
+   --initial
+   -i			Only convert initial tabs on each line to spaces.
+
+   David MacKenzie <djm@gnu.ai.mit.edu> */
+
+#include <config.h>
+
+#include <stdio.h>
+#include <getopt.h>
+#include <sys/types.h>
+#include "system.h"
+#include "error.h"
+#include "quote.h"
+#include "xstrndup.h"
+
+/* The official name of this program (e.g., no `g' prefix).  */
+#define PROGRAM_NAME "expand"
+
+#define AUTHORS proper_name ("David MacKenzie")
+
+/* If true, convert blanks even after nonblank characters have been
+   read on the line.  */
+static bool convert_entire_line;
+
+/* If nonzero, the size of all tab stops.  If zero, use `tab_list' instead.  */
+static uintmax_t tab_size;
+
+/* Array of the explicit column numbers of the tab stops;
+   after `tab_list' is exhausted, each additional tab is replaced
+   by a space.  The first column is column 0.  */
+static uintmax_t *tab_list;
+
+/* The number of allocated entries in `tab_list'.  */
+static size_t n_tabs_allocated;
+
+/* The index of the first invalid element of `tab_list',
+   where the next element can be added.  */
+static size_t first_free_tab;
+
+/* Null-terminated array of input filenames.  */
+static char **file_list;
+
+/* Default for `file_list' if no files are given on the command line.  */
+static char *stdin_argv[] =
+{
+  (char *) "-", NULL
+};
+
+/* True if we have ever read standard input.  */
+static bool have_read_stdin;
+
+/* The desired exit status.  */
+static int exit_status;
+
+static char const shortopts[] = "it:0::1::2::3::4::5::6::7::8::9::";
+
+static struct option const longopts[] =
+{
+  {"tabs", required_argument, NULL, 't'},
+  {"initial", no_argument, NULL, 'i'},
+  {GETOPT_HELP_OPTION_DECL},
+  {GETOPT_VERSION_OPTION_DECL},
+  {NULL, 0, NULL, 0}
+};
+
+void
+usage (int status)
+{
+  if (status != EXIT_SUCCESS)
+    fprintf (stderr, _("Try `%s --help' for more information.\n"),
+             program_name);
+  else
+    {
+      printf (_("\
+Usage: %s [OPTION]... [FILE]...\n\
+"),
+              program_name);
+      fputs (_("\
+Convert tabs in each FILE to spaces, writing to standard output.\n\
+With no FILE, or when FILE is -, read standard input.\n\
+\n\
+"), stdout);
+      fputs (_("\
+Mandatory arguments to long options are mandatory for short options too.\n\
+"), stdout);
+      fputs (_("\
+  -i, --initial       do not convert tabs after non blanks\n\
+  -t, --tabs=NUMBER   have tabs NUMBER characters apart, not 8\n\
+"), stdout);
+      fputs (_("\
+  -t, --tabs=LIST     use comma separated list of explicit tab positions\n\
+"), stdout);
+      fputs (HELP_OPTION_DESCRIPTION, stdout);
+      fputs (VERSION_OPTION_DESCRIPTION, stdout);
+      emit_ancillary_info ();
+    }
+  exit (status);
+}
+
+/* Add tab stop TABVAL to the end of `tab_list'.  */
+
+static void
+add_tab_stop (uintmax_t tabval)
+{
+  if (first_free_tab == n_tabs_allocated)
+    tab_list = X2NREALLOC (tab_list, &n_tabs_allocated);
+  tab_list[first_free_tab++] = tabval;
+}
+
+/* Add the comma or blank separated list of tab stops STOPS
+   to the list of tab stops.  */
+
+static void
+parse_tab_stops (char const *stops)
+{
+  bool have_tabval = false;
+  uintmax_t tabval IF_LINT (= 0);
+  char const *num_start IF_LINT (= NULL);
+  bool ok = true;
+
+  for (; *stops; stops++)
+    {
+      if (*stops == ',' || isblank (to_uchar (*stops)))
+        {
+          if (have_tabval)
+            add_tab_stop (tabval);
+          have_tabval = false;
+        }
+      else if (ISDIGIT (*stops))
+        {
+          if (!have_tabval)
+            {
+              tabval = 0;
+              have_tabval = true;
+              num_start = stops;
+            }
+
+          /* Detect overflow.  */
+          if (!DECIMAL_DIGIT_ACCUMULATE (tabval, *stops - '0', uintmax_t))
+            {
+              size_t len = strspn (num_start, "0123456789");
+              char *bad_num = xstrndup (num_start, len);
+              error (0, 0, _("tab stop is too large %s"), quote (bad_num));
+              free (bad_num);
+              ok = false;
+              stops = num_start + len - 1;
+            }
+        }
+      else
+        {
+          error (0, 0, _("tab size contains invalid character(s): %s"),
+                 quote (stops));
+          ok = false;
+          break;
+        }
+    }
+
+  if (!ok)
+    exit (EXIT_FAILURE);
+
+  if (have_tabval)
+    add_tab_stop (tabval);
+}
+
+/* Check that the list of tab stops TABS, with ENTRIES entries,
+   contains only nonzero, ascending values.  */
+
+static void
+validate_tab_stops (uintmax_t const *tabs, size_t entries)
+{
+  uintmax_t prev_tab = 0;
+  size_t i;
+
+  for (i = 0; i < entries; i++)
+    {
+      if (tabs[i] == 0)
+        error (EXIT_FAILURE, 0, _("tab size cannot be 0"));
+      if (tabs[i] <= prev_tab)
+        error (EXIT_FAILURE, 0, _("tab sizes must be ascending"));
+      prev_tab = tabs[i];
+    }
+}
+
+/* Close the old stream pointer FP if it is non-NULL,
+   and return a new one opened to read the next input file.
+   Open a filename of `-' as the standard input.
+   Return NULL if there are no more input files.  */
+
+static FILE *
+next_file (FILE *fp)
+{
+  static char *prev_file;
+  char *file;
+
+  if (fp)
+    {
+      if (ferror (fp))
+        {
+          error (0, errno, "%s", prev_file);
+          exit_status = EXIT_FAILURE;
+        }
+      if (STREQ (prev_file, "-"))
+        clearerr (fp);		/* Also clear EOF.  */
+      else if (fclose (fp) != 0)
+        {
+          error (0, errno, "%s", prev_file);
+          exit_status = EXIT_FAILURE;
+        }
+    }
+
+  while ((file = *file_list++) != NULL)
+    {
+      if (STREQ (file, "-"))
+        {
+          have_read_stdin = true;
+          prev_file = file;
+          return stdin;
+        }
+      fp = fopen (file, "r");
+      if (fp)
+        {
+          prev_file = file;
+          return fp;
+        }
+      error (0, errno, "%s", file);
+      exit_status = EXIT_FAILURE;
+    }
+  return NULL;
+}
+
+/* Change tabs to spaces, writing to stdout.
+   Read each file in `file_list', in order.  */
+
+static void