(encode_coding_raw_text): Fix last change.

[gnu-emacs] / src / coding.c

diff --git a/src/coding.c b/src/coding.c
index 01a678e2eaf50c1515d6b1771733a2cfad620ae6..91e8dd890b22f5f2aa65a3b66caa6dde07446a3d 100644 (file)
--- a/src/coding.c
+++ b/src/coding.c
@@ -11,10 +11,10 @@
 
 This file is part of GNU Emacs.
 
 
 This file is part of GNU Emacs.
 

-GNU Emacs is free software; you can redistribute it and/or modify
+GNU Emacs is free software: you can redistribute it and/or modify

 it under the terms of the GNU General Public License as published by
 it under the terms of the GNU General Public License as published by

-the Free Software Foundation; either version 3, or (at your option)
-any later version.
+the Free Software Foundation, either version 3 of the License, or
+(at your option) any later version.

 
 GNU Emacs is distributed in the hope that it will be useful,
 but WITHOUT ANY WARRANTY; without even the implied warranty of
 
 GNU Emacs is distributed in the hope that it will be useful,
 but WITHOUT ANY WARRANTY; without even the implied warranty of


@@ -22,9 +22,7 @@ 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
 GNU General Public License for more details.
 
 You should have received a copy of the GNU General Public License

-along with GNU Emacs; see the file COPYING.  If not, write to
-the Free Software Foundation, Inc., 51 Franklin Street, Fifth Floor,
-Boston, MA 02110-1301, USA.  */
+along with GNU Emacs.  If not, see <http://www.gnu.org/licenses/>.  */

 
 /*** TABLE OF CONTENTS ***
 
 
 /*** TABLE OF CONTENTS ***
 


@@ -625,6 +623,7 @@ enum coding_category
    | CATEGORY_MASK_ISO_7_ELSE          \
    | CATEGORY_MASK_ISO_8_ELSE          \
    | CATEGORY_MASK_UTF_8               \
    | CATEGORY_MASK_ISO_7_ELSE          \
    | CATEGORY_MASK_ISO_8_ELSE          \
    | CATEGORY_MASK_UTF_8               \

+   | CATEGORY_MASK_UTF_16_AUTO         \

    | CATEGORY_MASK_UTF_16_BE           \
    | CATEGORY_MASK_UTF_16_LE           \
    | CATEGORY_MASK_UTF_16_BE_NOSIG     \
    | CATEGORY_MASK_UTF_16_BE           \
    | CATEGORY_MASK_UTF_16_LE           \
    | CATEGORY_MASK_UTF_16_BE_NOSIG     \


@@ -657,7 +656,8 @@ enum coding_category
      | CATEGORY_MASK_ISO_ELSE)
 
 #define CATEGORY_MASK_UTF_16           \
      | CATEGORY_MASK_ISO_ELSE)
 
 #define CATEGORY_MASK_UTF_16           \

-  (CATEGORY_MASK_UTF_16_BE             \
+  (CATEGORY_MASK_UTF_16_AUTO           \
+   | CATEGORY_MASK_UTF_16_BE           \

    | CATEGORY_MASK_UTF_16_LE           \
    | CATEGORY_MASK_UTF_16_BE_NOSIG     \
    | CATEGORY_MASK_UTF_16_LE_NOSIG)
    | CATEGORY_MASK_UTF_16_LE           \
    | CATEGORY_MASK_UTF_16_BE_NOSIG     \
    | CATEGORY_MASK_UTF_16_LE_NOSIG)


@@ -898,7 +898,7 @@ static INLINE void produce_charset P_ ((struct coding_system *, int *,
 static void produce_annotation P_ ((struct coding_system *, EMACS_INT));
 static int decode_coding P_ ((struct coding_system *));
 static INLINE int *handle_composition_annotation P_ ((EMACS_INT, EMACS_INT,
 static void produce_annotation P_ ((struct coding_system *, EMACS_INT));
 static int decode_coding P_ ((struct coding_system *));
 static INLINE int *handle_composition_annotation P_ ((EMACS_INT, EMACS_INT,

-                                                     struct coding_system *, 
+                                                     struct coding_system *,

                                                      int *, EMACS_INT *));
 static INLINE int *handle_charset_annotation P_ ((EMACS_INT, EMACS_INT,
                                                  struct coding_system *,
                                                      int *, EMACS_INT *));
 static INLINE int *handle_charset_annotation P_ ((EMACS_INT, EMACS_INT,
                                                  struct coding_system *,


@@ -1513,11 +1513,44 @@ detect_coding_utf_16 (coding, detect_info)
                                | CATEGORY_MASK_UTF_16_BE_NOSIG
                                | CATEGORY_MASK_UTF_16_LE_NOSIG);
     }
                                | CATEGORY_MASK_UTF_16_BE_NOSIG
                                | CATEGORY_MASK_UTF_16_LE_NOSIG);
     }

-  else if (c1 >= 0 && c2 >= 0)
+  else

     {
     {

+      /* We check the dispersion of Eth and Oth bytes where E is even and
+        O is odd.  If both are high, we assume binary data.*/
+      unsigned char e[256], o[256];
+      unsigned e_num = 1, o_num = 1;
+
+      memset (e, 0, 256);
+      memset (o, 0, 256);
+      e[c1] = 1;
+      o[c2] = 1;
+

       detect_info->rejected
        |= (CATEGORY_MASK_UTF_16_BE | CATEGORY_MASK_UTF_16_LE);
       detect_info->rejected
        |= (CATEGORY_MASK_UTF_16_BE | CATEGORY_MASK_UTF_16_LE);

+
+      while (1)
+       {
+         ONE_MORE_BYTE (c1);
+         ONE_MORE_BYTE (c2);
+         if (! e[c1])
+           {
+             e[c1] = 1;
+             e_num++;
+             if (e_num >= 128)
+               break;
+           }
+         if (! o[c2])
+           {
+             o[c1] = 1;
+             o_num++;
+             if (o_num >= 128)
+               break;
+           }
+       }
+      detect_info->rejected |= CATEGORY_MASK_UTF_16;
+      return 0;

     }
     }

+

  no_more_source:
   return 1;
 }
  no_more_source:
   return 1;
 }


@@ -1926,7 +1959,7 @@ detect_coding_emacs_mule (coding, detect_info)
          /* Perhaps the start of composite character.  We simple skip
             it because analyzing it is too heavy for detecting.  But,
             at least, we check that the composite character
          /* Perhaps the start of composite character.  We simple skip
             it because analyzing it is too heavy for detecting.  But,
             at least, we check that the composite character

-            constitues of more than 4 bytes.  */
+            constitutes of more than 4 bytes.  */

          const unsigned char *src_base;
 
        repeat:
          const unsigned char *src_base;
 
        repeat:


@@ -2660,6 +2693,8 @@ detect_coding_iso_2022 (coding, detect_info)
       struct coding_system *this = &(coding_categories[i]);
       Lisp_Object attrs, val;
 
       struct coding_system *this = &(coding_categories[i]);
       Lisp_Object attrs, val;
 

+      if (this->id < 0)
+       continue;

       attrs = CODING_ID_ATTRS (this->id);
       if (CODING_ISO_FLAGS (this) & CODING_ISO_FLAG_FULL_SUPPORT
          && ! EQ (CODING_ATTR_SAFE_CHARSETS (attrs), Viso_2022_charset_list))
       attrs = CODING_ID_ATTRS (this->id);
       if (CODING_ISO_FLAGS (this) & CODING_ISO_FLAG_FULL_SUPPORT
          && ! EQ (CODING_ATTR_SAFE_CHARSETS (attrs), Viso_2022_charset_list))


@@ -4717,7 +4752,7 @@ encode_coding_ccl (coding)
       else
        {
          ASSURE_DESTINATION (ccl.produced);
       else
        {
          ASSURE_DESTINATION (ccl.produced);

-         for (i = 0; i < ccl.produced; i++)    
+         for (i = 0; i < ccl.produced; i++)

            *dst++ = destination_charbuf[i] & 0xFF;
          produced_chars += ccl.produced;
        }
            *dst++ = destination_charbuf[i] & 0xFF;
          produced_chars += ccl.produced;
        }


@@ -4838,7 +4873,6 @@ encode_coding_raw_text (coding)
                *dst++ = CHAR_TO_BYTE8 (c);
              else
                CHAR_STRING_ADVANCE (c, dst);
                *dst++ = CHAR_TO_BYTE8 (c);
              else
                CHAR_STRING_ADVANCE (c, dst);

-             produced_chars++;

            }
        }
       else
            }
        }
       else


@@ -4846,8 +4880,8 @@ encode_coding_raw_text (coding)
          ASSURE_DESTINATION (charbuf_end - charbuf);
          while (charbuf < charbuf_end && dst < dst_end)
            *dst++ = *charbuf++;
          ASSURE_DESTINATION (charbuf_end - charbuf);
          while (charbuf < charbuf_end && dst < dst_end)
            *dst++ = *charbuf++;

-         produced_chars = dst - (coding->destination + coding->dst_bytes);

        }
        }

+      produced_chars = charbuf - coding->charbuf;

     }
   record_conversion_result (coding, CODING_RESULT_SUCCESS);
   coding->produced_char += produced_chars;
     }
   record_conversion_result (coding, CODING_RESULT_SUCCESS);
   coding->produced_char += produced_chars;


@@ -4906,7 +4940,7 @@ detect_coding_charset (coding, detect_info)
              if (src == src_end)
                goto too_short;
              ONE_MORE_BYTE (c);
              if (src == src_end)
                goto too_short;
              ONE_MORE_BYTE (c);

-             if (c < charset->code_space[(dim - 1 - idx) * 2] 
+             if (c < charset->code_space[(dim - 1 - idx) * 2]

                  || c > charset->code_space[(dim - 1 - idx) * 2 + 1])
                break;
            }
                  || c > charset->code_space[(dim - 1 - idx) * 2 + 1])
                break;
            }


@@ -5677,32 +5711,53 @@ detect_coding (coding)
     {
       int c, i;
       struct coding_detection_info detect_info;
     {
       int c, i;
       struct coding_detection_info detect_info;

+      int null_byte_found = 0, eight_bit_found = 0;

 
       detect_info.checked = detect_info.found = detect_info.rejected = 0;
 
       detect_info.checked = detect_info.found = detect_info.rejected = 0;

-      for (i = 0, src = coding->source; src < src_end; i++, src++)
+      coding->head_ascii = -1;
+      for (src = coding->source; src < src_end; src++)

        {
          c = *src;
          if (c & 0x80)
        {
          c = *src;
          if (c & 0x80)

-           break;
-         if (c < 0x20
-             && (c == ISO_CODE_ESC || c == ISO_CODE_SI || c == ISO_CODE_SO)
-             && ! inhibit_iso_escape_detection
-             && ! detect_info.checked)

            {
            {

-             coding->head_ascii = src - (coding->source + coding->consumed);
-             if (detect_coding_iso_2022 (coding, &detect_info))
+             eight_bit_found = 1;
+             if (coding->head_ascii < 0)
+               coding->head_ascii = src - coding->source;
+             if (null_byte_found)
+               break;
+           }
+         else if (c < 0x20)
+           {
+             if ((c == ISO_CODE_ESC || c == ISO_CODE_SI || c == ISO_CODE_SO)
+                 && ! inhibit_iso_escape_detection
+                 && ! detect_info.checked)

                {
                {

-                 /* We have scanned the whole data.  */
-                 if (! (detect_info.rejected & CATEGORY_MASK_ISO_7_ELSE))
-                   /* We didn't find an 8-bit code.  */
-                   src = src_end;
-                 break;
+                 if (coding->head_ascii < 0)
+                   coding->head_ascii = src - coding->source;
+                 if (detect_coding_iso_2022 (coding, &detect_info))
+                   {
+                     /* We have scanned the whole data.  */
+                     if (! (detect_info.rejected & CATEGORY_MASK_ISO_7_ELSE))
+                       /* We didn't find an 8-bit code.  We may have
+                          found a null-byte, but it's very rare that
+                          a binary file confirm to ISO-2022.  */
+                       src = src_end;
+                     break;
+                   }
+               }
+             else if (! c)
+               {
+                 null_byte_found = 1;
+                 if (eight_bit_found)
+                   break;

                }
            }
        }
                }
            }
        }

-      coding->head_ascii = src - (coding->source + coding->consumed);
+      if (coding->head_ascii < 0)
+       coding->head_ascii = src - coding->source;

 
 

-      if (coding->head_ascii < coding->src_bytes
+      if (null_byte_found || eight_bit_found
+         || coding->head_ascii < coding->src_bytes

          || detect_info.found)
        {
          enum coding_category category;
          || detect_info.found)
        {
          enum coding_category category;


@@ -5718,48 +5773,58 @@ detect_coding (coding)
                  break;
              }
          else
                  break;
              }
          else

-           for (i = 0; i < coding_category_raw_text; i++)
-             {
-               category = coding_priorities[i];
-               this = coding_categories + category;
-               if (this->id < 0)
-                 {
-                   /* No coding system of this category is defined.  */
-                   detect_info.rejected |= (1 << category);
-                 }
-               else if (category >= coding_category_raw_text)
-                 continue;
-               else if (detect_info.checked & (1 << category))
-                 {
-                   if (detect_info.found & (1 << category))
-                     break;
-                 }
-               else if ((*(this->detector)) (coding, &detect_info)
-                        && detect_info.found & (1 << category))
-                 {
-                   if (category == coding_category_utf_16_auto)
-                     {
-                       if (detect_info.found & CATEGORY_MASK_UTF_16_LE)
-                         category = coding_category_utf_16_le;
-                       else
-                         category = coding_category_utf_16_be;
-                     }
-                   break;
-                 }
-             }
-         
-         if (i < coding_category_raw_text)
-           setup_coding_system (CODING_ID_NAME (this->id), coding);
-         else if (detect_info.rejected == CATEGORY_MASK_ANY)
-           setup_coding_system (Qraw_text, coding);
-         else if (detect_info.rejected)
-           for (i = 0; i < coding_category_raw_text; i++)
-             if (! (detect_info.rejected & (1 << coding_priorities[i])))
+           {
+             if (null_byte_found)

                {
                {

-                 this = coding_categories + coding_priorities[i];
-                 setup_coding_system (CODING_ID_NAME (this->id), coding);
-                 break;
+                 detect_info.checked |= ~CATEGORY_MASK_UTF_16;
+                 detect_info.rejected |= ~CATEGORY_MASK_UTF_16;

                }
                }

+             for (i = 0; i < coding_category_raw_text; i++)
+               {
+                 category = coding_priorities[i];
+                 this = coding_categories + category;
+                 if (this->id < 0)
+                   {
+                     /* No coding system of this category is defined.  */
+                     detect_info.rejected |= (1 << category);
+                   }
+                 else if (category >= coding_category_raw_text)
+                   continue;
+                 else if (detect_info.checked & (1 << category))
+                   {
+                     if (detect_info.found & (1 << category))
+                       break;
+                   }
+                 else if ((*(this->detector)) (coding, &detect_info)
+                          && detect_info.found & (1 << category))
+                   {
+                     if (category == coding_category_utf_16_auto)
+                       {
+                         if (detect_info.found & CATEGORY_MASK_UTF_16_LE)
+                           category = coding_category_utf_16_le;
+                         else
+                           category = coding_category_utf_16_be;
+                       }
+                     break;
+                   }
+               }
+
+             if (i < coding_category_raw_text)
+               setup_coding_system (CODING_ID_NAME (this->id), coding);
+             else if (null_byte_found)
+               setup_coding_system (Qno_conversion, coding);
+             else if ((detect_info.rejected & CATEGORY_MASK_ANY)
+                      == CATEGORY_MASK_ANY)
+               setup_coding_system (Qraw_text, coding);
+             else if (detect_info.rejected)
+               for (i = 0; i < coding_category_raw_text; i++)
+                 if (! (detect_info.rejected & (1 << coding_priorities[i])))
+                   {
+                     this = coding_categories + coding_priorities[i];
+                     setup_coding_system (CODING_ID_NAME (this->id), coding);
+                     break;
+                   }
+           }

        }
     }
   else if (XINT (CODING_ATTR_CATEGORY (CODING_ID_ATTRS (coding->id)))
        }
     }
   else if (XINT (CODING_ATTR_CATEGORY (CODING_ID_ATTRS (coding->id)))


@@ -5789,7 +5854,7 @@ decode_eol (coding)
 {
   Lisp_Object eol_type;
   unsigned char *p, *pbeg, *pend;
 {
   Lisp_Object eol_type;
   unsigned char *p, *pbeg, *pend;

-  
+

   eol_type = CODING_ID_EOL_TYPE (coding->id);
   if (EQ (eol_type, Qunix))
     return;
   eol_type = CODING_ID_EOL_TYPE (coding->id);
   if (EQ (eol_type, Qunix))
     return;


@@ -6812,7 +6877,7 @@ make_conversion_work_buffer (multibyte)
     }
   current = current_buffer;
   set_buffer_internal (XBUFFER (workbuf));
     }
   current = current_buffer;
   set_buffer_internal (XBUFFER (workbuf));

-  Ferase_buffer ();      
+  Ferase_buffer ();

   current_buffer->undo_list = Qt;
   current_buffer->enable_multibyte_characters = multibyte ? Qt : Qnil;
   set_buffer_internal (current);
   current_buffer->undo_list = Qt;
   current_buffer->enable_multibyte_characters = multibyte ? Qt : Qnil;
   set_buffer_internal (current);


@@ -7048,7 +7113,10 @@ decode_coding_object (coding, src_object, from, from_byte, to, to_byte,
     {
       code_conversion_save (0, 0);
       coding->dst_object = Qnil;
     {
       code_conversion_save (0, 0);
       coding->dst_object = Qnil;

-      coding->dst_multibyte = !CODING_FOR_UNIBYTE (coding);
+      /* Most callers presume this will return a multibyte result, and they
+        won't use `binary' or `raw-text' anyway, so let's not worry about
+        CODING_FOR_UNIBYTE.  */
+      coding->dst_multibyte = 1;

     }
 
   decode_coding (coding);
     }
 
   decode_coding (coding);


@@ -7365,14 +7433,14 @@ DEFUN ("coding-system-p", Fcoding_system_p, Scoding_system_p, 1, 1, 0,
        doc: /* Return t if OBJECT is nil or a coding-system.
 See the documentation of `define-coding-system' for information
 about coding-system objects.  */)
        doc: /* Return t if OBJECT is nil or a coding-system.
 See the documentation of `define-coding-system' for information
 about coding-system objects.  */)

-     (obj)
-     Lisp_Object obj;
+     (object)
+     Lisp_Object object;

 {
 {

-  if (NILP (obj)
-      || CODING_SYSTEM_ID (obj) >= 0)
+  if (NILP (object)
+      || CODING_SYSTEM_ID (object) >= 0)

     return Qt;
     return Qt;

-  if (! SYMBOLP (obj)
-      || NILP (Fget (obj, Qcoding_system_define_form)))
+  if (! SYMBOLP (object)
+      || NILP (Fget (object, Qcoding_system_define_form)))

     return Qnil;
   return Qt;
 }
     return Qnil;
   return Qt;
 }


@@ -7469,6 +7537,7 @@ detect_coding_system (src, src_chars, src_bytes, highest, multibytep,
   int id;
   struct coding_detection_info detect_info;
   enum coding_category base_category;
   int id;
   struct coding_detection_info detect_info;
   enum coding_category base_category;

+  int null_byte_found = 0, eight_bit_found = 0;

 
   if (NILP (coding_system))
     coding_system = Qundecided;
 
   if (NILP (coding_system))
     coding_system = Qundecided;


@@ -7494,33 +7563,54 @@ detect_coding_system (src, src_chars, src_bytes, highest, multibytep,
       struct coding_system *this;
       int c, i;
 
       struct coding_system *this;
       int c, i;
 

+      coding.head_ascii = -1;

       /* Skip all ASCII bytes except for a few ISO2022 controls.  */
       /* Skip all ASCII bytes except for a few ISO2022 controls.  */

-      for (i = 0; src < src_end; i++, src++)
+      for (; src < src_end; src++)

        {
          c = *src;
          if (c & 0x80)
        {
          c = *src;
          if (c & 0x80)

-           break;
-         if (c < 0x20
-             && (c == ISO_CODE_ESC || c == ISO_CODE_SI || c == ISO_CODE_SO)
-             && ! inhibit_iso_escape_detection)

            {
            {

-             coding.head_ascii = src - coding.source;
-             if (detect_coding_iso_2022 (&coding, &detect_info))
+             eight_bit_found = 1;
+             if (coding.head_ascii < 0)
+               coding.head_ascii = src - coding.source;
+             if (null_byte_found)
+               break;
+           }
+         if (c < 0x20)
+           {
+             if ((c == ISO_CODE_ESC || c == ISO_CODE_SI || c == ISO_CODE_SO)
+                 && ! inhibit_iso_escape_detection
+                 && ! detect_info.checked)

                {
                {

-                 /* We have scanned the whole data.  */
-                 if (! (detect_info.rejected & CATEGORY_MASK_ISO_7_ELSE))
-                   /* We didn't find an 8-bit code.  */
-                   src = src_end;
-                 break;
+                 if (coding.head_ascii < 0)
+                   coding.head_ascii = src - coding.source;
+                 if (detect_coding_iso_2022 (&coding, &detect_info))
+                   {
+                     /* We have scanned the whole data.  */
+                     if (! (detect_info.rejected & CATEGORY_MASK_ISO_7_ELSE))
+                       /* We didn't find an 8-bit code.  We may have
+                          found a null-byte, but it's very rare that
+                          a binary file confirm to ISO-2022.  */
+                       src = src_end;
+                     break;
+                   }
+               }
+             else if (! c)
+               {
+                 null_byte_found = 1;
+                 if (eight_bit_found)
+                   break;

                }
            }
        }
                }
            }
        }

-      coding.head_ascii = src - coding.source;
+      if (coding.head_ascii < 0)
+       coding.head_ascii = src - coding.source;

 
 

-      if (src < src_end
+      if (null_byte_found || eight_bit_found
+         || coding.head_ascii < coding.src_bytes

          || detect_info.found)
        {
          || detect_info.found)
        {

-         if (src == src_end)
+         if (coding.head_ascii == coding.src_bytes)

            /* As all bytes are 7-bit, we can ignore non-ISO-2022 codings.  */
            for (i = 0; i < coding_category_raw_text; i++)
              {
            /* As all bytes are 7-bit, we can ignore non-ISO-2022 codings.  */
            for (i = 0; i < coding_category_raw_text; i++)
              {


@@ -7530,44 +7620,48 @@ detect_coding_system (src, src_chars, src_bytes, highest, multibytep,
                  break;
              }
          else
                  break;
              }
          else

-           for (i = 0; i < coding_category_raw_text; i++)
-             {
-               category = coding_priorities[i];
-               this = coding_categories + category;
+           {
+             if (null_byte_found)
+               {
+                 detect_info.checked |= ~CATEGORY_MASK_UTF_16;
+                 detect_info.rejected |= ~CATEGORY_MASK_UTF_16;
+               }
+             for (i = 0; i < coding_category_raw_text; i++)
+               {
+                 category = coding_priorities[i];
+                 this = coding_categories + category;

 
 

-               if (this->id < 0)
-                 {
-                   /* No coding system of this category is defined.  */
-                   detect_info.rejected |= (1 << category);
-                 }
-               else if (category >= coding_category_raw_text)
-                 continue;
-               else if (detect_info.checked & (1 << category))
-                 {
-                   if (highest
-                       && (detect_info.found & (1 << category)))
-                     break;
-                 }
-               else
-                 {
-                   if ((*(this->detector)) (&coding, &detect_info)
-                       && highest
-                       && (detect_info.found & (1 << category)))
-                     {
-                       if (category == coding_category_utf_16_auto)
-                         {
-                           if (detect_info.found & CATEGORY_MASK_UTF_16_LE)
-                             category = coding_category_utf_16_le;
-                           else
-                             category = coding_category_utf_16_be;
-                         }
+                 if (this->id < 0)
+                   {
+                     /* No coding system of this category is defined.  */
+                     detect_info.rejected |= (1 << category);
+                   }
+                 else if (category >= coding_category_raw_text)
+                   continue;
+                 else if (detect_info.checked & (1 << category))
+                   {
+                     if (highest
+                         && (detect_info.found & (1 << category)))

                        break;
                        break;

-                     }
-                 }
-             }
+                   }
+                 else if ((*(this->detector)) (&coding, &detect_info)
+                          && highest
+                          && (detect_info.found & (1 << category)))
+                   {
+                     if (category == coding_category_utf_16_auto)
+                       {
+                         if (detect_info.found & CATEGORY_MASK_UTF_16_LE)
+                           category = coding_category_utf_16_le;
+                         else
+                           category = coding_category_utf_16_be;
+                       }
+                     break;
+                   }
+               }
+           }

        }
 
        }
 

-      if (detect_info.rejected == CATEGORY_MASK_ANY)
+      if ((detect_info.rejected & CATEGORY_MASK_ANY) == CATEGORY_MASK_ANY)

        {
          detect_info.found = CATEGORY_MASK_RAW_TEXT;
          id = coding_categories[coding_category_raw_text].id;
        {
          detect_info.found = CATEGORY_MASK_RAW_TEXT;
          id = coding_categories[coding_category_raw_text].id;


@@ -7656,8 +7750,13 @@ detect_coding_system (src, src_chars, src_bytes, highest, multibytep,
     if (VECTORP (eol_type))
       {
        if (detect_info.found & ~CATEGORY_MASK_UTF_16)
     if (VECTORP (eol_type))
       {
        if (detect_info.found & ~CATEGORY_MASK_UTF_16)

-         normal_eol = detect_eol (coding.source, src_bytes,
-                                  coding_category_raw_text);
+         {
+           if (null_byte_found)
+             normal_eol = EOL_SEEN_LF;
+           else
+             normal_eol = detect_eol (coding.source, src_bytes,
+                                      coding_category_raw_text);
+         }

        if (detect_info.found & (CATEGORY_MASK_UTF_16_BE
                                 | CATEGORY_MASK_UTF_16_BE_NOSIG))
          utf_16_be_eol = detect_eol (coding.source, src_bytes,
        if (detect_info.found & (CATEGORY_MASK_UTF_16_BE
                                 | CATEGORY_MASK_UTF_16_BE_NOSIG))
          utf_16_be_eol = detect_eol (coding.source, src_bytes,


@@ -7721,9 +7820,9 @@ DEFUN ("detect-coding-region", Fdetect_coding_region, Sdetect_coding_region,
 Return a list of possible coding systems ordered by priority.
 
 If only ASCII characters are found (except for such ISO-2022 control
 Return a list of possible coding systems ordered by priority.
 
 If only ASCII characters are found (except for such ISO-2022 control

-characters ISO-2022 as ESC), it returns a list of single element
-`undecided' or its subsidiary coding system according to a detected
-end-of-line format.
+characters as ESC), it returns a list of single element `undecided'
+or its subsidiary coding system according to a detected end-of-line
+format.

 
 If optional argument HIGHEST is non-nil, return the coding system of
 highest priority.  */)
 
 If optional argument HIGHEST is non-nil, return the coding system of
 highest priority.  */)


@@ -7758,9 +7857,9 @@ DEFUN ("detect-coding-string", Fdetect_coding_string, Sdetect_coding_string,
 Return a list of possible coding systems ordered by priority.
 
 If only ASCII characters are found (except for such ISO-2022 control
 Return a list of possible coding systems ordered by priority.
 
 If only ASCII characters are found (except for such ISO-2022 control

-characters ISO-2022 as ESC), it returns a list of single element
-`undecided' or its subsidiary coding system according to a detected
-end-of-line format.
+characters as ESC), it returns a list of single element `undecided'
+or its subsidiary coding system according to a detected end-of-line
+format.

 
 If optional argument HIGHEST is non-nil, return the coding system of
 highest priority.  */)
 
 If optional argument HIGHEST is non-nil, return the coding system of
 highest priority.  */)


@@ -7928,7 +8027,7 @@ DEFUN ("unencodable-char-position", Funencodable_char_position,
        Sunencodable_char_position, 3, 5, 0,
        doc: /*
 Return position of first un-encodable character in a region.
        Sunencodable_char_position, 3, 5, 0,
        doc: /*
 Return position of first un-encodable character in a region.

-START and END specfiy the region and CODING-SYSTEM specifies the
+START and END specify the region and CODING-SYSTEM specifies the

 encoding to check.  Return nil if CODING-SYSTEM does encode the region.
 
 If optional 4th argument COUNT is non-nil, it specifies at most how
 encoding to check.  Return nil if CODING-SYSTEM does encode the region.
 
 If optional 4th argument COUNT is non-nil, it specifies at most how


@@ -8041,7 +8140,7 @@ START and END are buffer positions specifying the region.
 CODING-SYSTEM-LIST is a list of coding systems to check.
 
 The value is an alist ((CODING-SYSTEM POS0 POS1 ...) ...), where
 CODING-SYSTEM-LIST is a list of coding systems to check.
 
 The value is an alist ((CODING-SYSTEM POS0 POS1 ...) ...), where

-CODING-SYSTEM is a member of CODING-SYSTEM-LIst and can't encode the
+CODING-SYSTEM is a member of CODING-SYSTEM-LIST and can't encode the

 whole region, POS0, POS1, ... are buffer positions where non-encodable
 characters are found.
 
 whole region, POS0, POS1, ... are buffer positions where non-encodable
 characters are found.
 


@@ -8226,8 +8325,9 @@ It returns the length of the decoded text.  */)
 DEFUN ("encode-coding-region", Fencode_coding_region, Sencode_coding_region,
        3, 4, "r\nzCoding system: ",
        doc: /* Encode the current region by specified coding system.
 DEFUN ("encode-coding-region", Fencode_coding_region, Sencode_coding_region,
        3, 4, "r\nzCoding system: ",
        doc: /* Encode the current region by specified coding system.

-When called from a program, takes three arguments:
-START, END, and CODING-SYSTEM.  START and END are buffer positions.
+When called from a program, takes four arguments:
+        START, END, CODING-SYSTEM and DESTINATION.
+START and END are buffer positions.

 
 Optional 4th arguments DESTINATION specifies where the encoded text goes.
 If nil, the region between START and END is replace by the encoded text.
 
 Optional 4th arguments DESTINATION specifies where the encoded text goes.
 If nil, the region between START and END is replace by the encoded text.


@@ -8310,13 +8410,13 @@ DEFUN ("decode-coding-string", Fdecode_coding_string, Sdecode_coding_string,
 Optional third arg NOCOPY non-nil means it is OK to return STRING itself
 if the decoding operation is trivial.
 
 Optional third arg NOCOPY non-nil means it is OK to return STRING itself
 if the decoding operation is trivial.
 

-Optional fourth arg BUFFER non-nil meant that the decoded text is
+Optional fourth arg BUFFER non-nil means that the decoded text is

 inserted in BUFFER instead of returned as a string.  In this case,
 the return value is BUFFER.
 
 This function sets `last-coding-system-used' to the precise coding system
 used (which may be different from CODING-SYSTEM if CODING-SYSTEM is
 inserted in BUFFER instead of returned as a string.  In this case,
 the return value is BUFFER.
 
 This function sets `last-coding-system-used' to the precise coding system
 used (which may be different from CODING-SYSTEM if CODING-SYSTEM is

-not fully specified.  */)
+not fully specified.)  */)

   (string, coding_system, nocopy, buffer)
      Lisp_Object string, coding_system, nocopy, buffer;
 {
   (string, coding_system, nocopy, buffer)
      Lisp_Object string, coding_system, nocopy, buffer;
 {


@@ -8331,7 +8431,7 @@ DEFUN ("encode-coding-string", Fencode_coding_string, Sencode_coding_string,
 Optional third arg NOCOPY non-nil means it is OK to return STRING
 itself if the encoding operation is trivial.
 
 Optional third arg NOCOPY non-nil means it is OK to return STRING
 itself if the encoding operation is trivial.
 

-Optional fourth arg BUFFER non-nil meant that the encoded text is
+Optional fourth arg BUFFER non-nil means that the encoded text is

 inserted in BUFFER instead of returned as a string.  In this case,
 the return value is BUFFER.
 
 inserted in BUFFER instead of returned as a string.  In this case,
 the return value is BUFFER.
 


@@ -8591,9 +8691,9 @@ whichever argument specifies the file name is TARGET.
 TARGET has a meaning which depends on OPERATION:
   For file I/O, TARGET is a file name (except for the special case below).
   For process I/O, TARGET is a process name.
 TARGET has a meaning which depends on OPERATION:
   For file I/O, TARGET is a file name (except for the special case below).
   For process I/O, TARGET is a process name.

-  For network I/O, TARGET is a service name or a port number
+  For network I/O, TARGET is a service name or a port number.

 
 

-This function looks up what specified for TARGET in,
+This function looks up what is specified for TARGET in

 `file-coding-system-alist', `process-coding-system-alist',
 or `network-coding-system-alist' depending on OPERATION.
 They may specify a coding system, a cons of coding systems,
 `file-coding-system-alist', `process-coding-system-alist',
 or `network-coding-system-alist' depending on OPERATION.
 They may specify a coding system, a cons of coding systems,


@@ -8623,7 +8723,7 @@ usage: (find-operation-coding-system OPERATION ARGUMENTS...)  */)
   operation = args[0];
   if (!SYMBOLP (operation)
       || !INTEGERP (target_idx = Fget (operation, Qtarget_idx)))
   operation = args[0];
   if (!SYMBOLP (operation)
       || !INTEGERP (target_idx = Fget (operation, Qtarget_idx)))

-    error ("Invalid first arguement");
+    error ("Invalid first argument");

   if (nargs < 1 + XINT (target_idx))
     error ("Too few arguments for operation: %s",
           SDATA (SYMBOL_NAME (operation)));
   if (nargs < 1 + XINT (target_idx))
     error ("Too few arguments for operation: %s",
           SDATA (SYMBOL_NAME (operation)));


@@ -8685,10 +8785,10 @@ usage: (find-operation-coding-system OPERATION ARGUMENTS...)  */)
 DEFUN ("set-coding-system-priority", Fset_coding_system_priority,
        Sset_coding_system_priority, 0, MANY, 0,
        doc: /* Assign higher priority to the coding systems given as arguments.
 DEFUN ("set-coding-system-priority", Fset_coding_system_priority,
        Sset_coding_system_priority, 0, MANY, 0,
        doc: /* Assign higher priority to the coding systems given as arguments.

-If multiple coding systems belongs to the same category,
+If multiple coding systems belong to the same category,

 all but the first one are ignored.
 
 all but the first one are ignored.
 

-usage: (set-coding-system-priority ...)  */)
+usage: (set-coding-system-priority &rest coding-systems)  */)

      (nargs, args)
      int nargs;
      Lisp_Object *args;
      (nargs, args)
      int nargs;
      Lisp_Object *args;


@@ -9242,7 +9342,7 @@ usage: (define-coding-system-internal ...)  */)
     = Fcons (QCcategory, Fcons (AREF (Vcoding_category_table, category),
                                CODING_ATTR_PLIST (attrs)));
   CODING_ATTR_PLIST (attrs)
     = Fcons (QCcategory, Fcons (AREF (Vcoding_category_table, category),
                                CODING_ATTR_PLIST (attrs)));
   CODING_ATTR_PLIST (attrs)

-    = Fcons (QCascii_compatible_p, 
+    = Fcons (QCascii_compatible_p,

             Fcons (CODING_ATTR_ASCII_COMPAT (attrs),
                    CODING_ATTR_PLIST (attrs)));
 
             Fcons (CODING_ATTR_ASCII_COMPAT (attrs),
                    CODING_ATTR_PLIST (attrs)));
 


@@ -9373,7 +9473,7 @@ DEFUN ("define-coding-system-alias", Fdefine_coding_system_alias,
   CHECK_SYMBOL (alias);
   CHECK_CODING_SYSTEM_GET_SPEC (coding_system, spec);
   aliases = AREF (spec, 1);
   CHECK_SYMBOL (alias);
   CHECK_CODING_SYSTEM_GET_SPEC (coding_system, spec);
   aliases = AREF (spec, 1);

-  /* ALISES should be a list of length more than zero, and the first
+  /* ALIASES should be a list of length more than zero, and the first

      element is a base coding system.  Append ALIAS at the tail of the
      list.  */
   while (!NILP (XCDR (aliases)))
      element is a base coding system.  Append ALIAS at the tail of the
      list.  */
   while (!NILP (XCDR (aliases)))


@@ -9451,7 +9551,7 @@ DEFUN ("coding-system-aliases", Fcoding_system_aliases, Scoding_system_aliases,
 DEFUN ("coding-system-eol-type", Fcoding_system_eol_type,
        Scoding_system_eol_type, 1, 1, 0,
        doc: /* Return eol-type of CODING-SYSTEM.
 DEFUN ("coding-system-eol-type", Fcoding_system_eol_type,
        Scoding_system_eol_type, 1, 1, 0,
        doc: /* Return eol-type of CODING-SYSTEM.

-An eol-type is integer 0, 1, 2, or a vector of coding systems.
+An eol-type is an integer 0, 1, 2, or a vector of coding systems.

 
 Integer values 0, 1, and 2 indicate a format of end-of-line; LF, CRLF,
 and CR respectively.
 
 Integer values 0, 1, and 2 indicate a format of end-of-line; LF, CRLF,
 and CR respectively.