Merge from emacs-24; up to 2012-12-11T18:52:31Z!monnier@iro.umontreal.ca

[bpt/emacs.git] / src / coding.c

diff --git a/src/coding.c b/src/coding.c
index 7628a9f..93da9db 100644 (file)
--- a/src/coding.c
+++ b/src/coding.c
@@ -1,5 +1,5 @@
 /* Coding system handler (conversion, detection, etc).
-   Copyright (C) 2001-2012 Free Software Foundation, Inc.
+   Copyright (C) 2001-2013 Free Software Foundation, Inc.
    Copyright (C) 1995, 1996, 1997, 1998, 1999, 2000, 2001, 2002, 2003, 2004,
      2005, 2006, 2007, 2008, 2009, 2010, 2011
      National Institute of Advanced Industrial Science and Technology (AIST)
@@ -302,6 +302,7 @@ Lisp_Object Vcoding_system_hash_table;
 static Lisp_Object Qcoding_system, Qeol_type;
 static Lisp_Object Qcoding_aliases;
 Lisp_Object Qunix, Qdos;
+static Lisp_Object Qmac;
 Lisp_Object Qbuffer_file_coding_system;
 static Lisp_Object Qpost_read_conversion, Qpre_write_conversion;
 static Lisp_Object Qdefault_char;
@@ -343,6 +344,10 @@ Lisp_Object Qcoding_system_p, Qcoding_system_error;
 Lisp_Object Qemacs_mule, Qraw_text;
 Lisp_Object Qutf_8_emacs;
 
+#if defined (WINDOWSNT) || defined (CYGWIN)
+static Lisp_Object Qutf_16le;
+#endif
+
 /* Coding-systems are handed between Emacs Lisp programs and C internal
    routines by the following three variables.  */
 /* Coding system to be used to encode text for terminal display when
@@ -1044,14 +1049,7 @@ coding_alloc_by_making_gap (struct coding_system *coding,
       GPT -= gap_head_used, GPT_BYTE -= gap_head_used;
     }
   else
-    {
-      Lisp_Object this_buffer;
-
-      this_buffer = Fcurrent_buffer ();
-      set_buffer_internal (XBUFFER (coding->dst_object));
-      make_gap (bytes);
-      set_buffer_internal (XBUFFER (this_buffer));
-    }
+    make_gap_1 (XBUFFER (coding->dst_object), bytes);
 }
 
 
@@ -3059,20 +3057,7 @@ detect_coding_iso_2022 (struct coding_system *coding,
            }
          if (single_shifting)
            break;
-       check_extra_latin:
-         if (! VECTORP (Vlatin_extra_code_table)
-             || NILP (AREF (Vlatin_extra_code_table, c)))
-           {
-             rejected = CATEGORY_MASK_ISO;
-             break;
-           }
-         if (CODING_ISO_FLAGS (&coding_categories[coding_category_iso_8_1])
-             & CODING_ISO_FLAG_LATIN_EXTRA)
-           found |= CATEGORY_MASK_ISO_8_1;
-         else
-           rejected |= CATEGORY_MASK_ISO_8_1;
-         rejected |= CATEGORY_MASK_ISO_8_2;
-         break;
+         goto check_extra_latin;
 
        default:
          if (c < 0)
@@ -3123,6 +3108,20 @@ detect_coding_iso_2022 (struct coding_system *coding,
                }
              break;
            }
+       check_extra_latin:
+         if (! VECTORP (Vlatin_extra_code_table)
+             || NILP (AREF (Vlatin_extra_code_table, c)))
+           {
+             rejected = CATEGORY_MASK_ISO;
+             break;
+           }
+         if (CODING_ISO_FLAGS (&coding_categories[coding_category_iso_8_1])
+             & CODING_ISO_FLAG_LATIN_EXTRA)
+           found |= CATEGORY_MASK_ISO_8_1;
+         else
+           rejected |= CATEGORY_MASK_ISO_8_1;
+         rejected |= CATEGORY_MASK_ISO_8_2;
+         break;
        }
     }
   detect_info->rejected |= CATEGORY_MASK_ISO;
@@ -7971,6 +7970,40 @@ preferred_coding_system (void)
   return CODING_ID_NAME (id);
 }
 
+#if defined (WINDOWSNT) || defined (CYGWIN)
+
+Lisp_Object
+from_unicode (Lisp_Object str)
+{
+  CHECK_STRING (str);
+  if (!STRING_MULTIBYTE (str) &&
+      SBYTES (str) & 1)
+    {
+      str = Fsubstring (str, make_number (0), make_number (-1));
+    }
+
+  return code_convert_string_norecord (str, Qutf_16le, 0);
+}
+
+wchar_t *
+to_unicode (Lisp_Object str, Lisp_Object *buf)
+{
+  *buf = code_convert_string_norecord (str, Qutf_16le, 1);
+  /* We need to make a another copy (in addition to the one made by
+     code_convert_string_norecord) to ensure that the final string is
+     _doubly_ zero terminated --- that is, that the string is
+     terminated by two zero bytes and one utf-16le null character.
+     Because strings are already terminated with a single zero byte,
+     we just add one additional zero. */
+  str = make_uninit_string (SBYTES (*buf) + 1);
+  memcpy (SDATA (str), SDATA (*buf), SBYTES (*buf));
+  SDATA (str) [SBYTES (*buf)] = '\0';
+  *buf = str;
+  return WCSDATA (*buf);
+}
+
+#endif /* WINDOWSNT || CYGWIN */
+
 \f
 #ifdef emacs
 /*** 8. Emacs Lisp library functions ***/
@@ -8388,9 +8421,6 @@ highest priority.  */)
   ptrdiff_t from, to;
   ptrdiff_t from_byte, to_byte;
 
-  CHECK_NUMBER_COERCE_MARKER (start);
-  CHECK_NUMBER_COERCE_MARKER (end);
-
   validate_region (&start, &end);
   from = XINT (start), to = XINT (end);
   from_byte = CHAR_TO_BYTE (from);
@@ -8834,8 +8864,6 @@ code_convert_region (Lisp_Object start, Lisp_Object end,
   ptrdiff_t from, from_byte, to, to_byte;
   Lisp_Object src_object;
 
-  CHECK_NUMBER_COERCE_MARKER (start);
-  CHECK_NUMBER_COERCE_MARKER (end);
   if (NILP (coding_system))
     coding_system = Qno_conversion;
   else
@@ -10270,6 +10298,7 @@ syms_of_coding (void)
   DEFSYM (Qeol_type, "eol-type");
   DEFSYM (Qunix, "unix");
   DEFSYM (Qdos, "dos");
+  DEFSYM (Qmac, "mac");
 
   DEFSYM (Qbuffer_file_coding_system, "buffer-file-coding-system");
   DEFSYM (Qpost_read_conversion, "post-read-conversion");
@@ -10284,6 +10313,11 @@ syms_of_coding (void)
   DEFSYM (Qutf_8, "utf-8");
   DEFSYM (Qutf_8_emacs, "utf-8-emacs");
 
+#if defined (WINDOWSNT) || defined (CYGWIN)
+  /* No, not utf-16-le: that one has a BOM.  */
+  DEFSYM (Qutf_16le, "utf-16le");
+#endif
+
   DEFSYM (Qutf_16, "utf-16");
   DEFSYM (Qbig, "big");
   DEFSYM (Qlittle, "little");