emacs: src/coding.c comparison

comparison src/coding.c @ 89420:c3e67ce6ee0f

(Qsignature, Qendian): Delete these variables. (syms_of_coding): Don't initialize them. (CATEGORY_MASK_UTF_16_AUTO): New macro. (detect_coding_utf_16): Add CATEGORY_MASK_UTF_16_AUTO in detect_info->found. (decode_coding_utf_16): Don't detect BOM here. (encode_coding_utf_16): Produce BOM if CODING_UTF_16_BOM (coding) is NOT utf_16_without_bom. (setup_coding_system): For a coding system of type utf-16, check if the attribute :endian is Qbig or not (not nil or not), and set CODING_REQUIRE_DETECTION_MASK if BOM detection is required. (detect_coding): If coding type is utf-16 and BOM detection is required, detect it. (Fdefine_coding_system_internal): For a coding system of type utf-16, check if the attribute :endian is Qbig or not (not nil or not).

author	Kenichi Handa <handa@m17n.org>
date	Tue, 06 May 2003 12:28:11 +0000
parents	a9c2b3712863
children	3c978149859b

comparison

equal deleted inserted replaced

-:18e57407a82b
+:c3e67ce6ee0f
 Lisp_Object Qbuffer_file_coding_system;
 Lisp_Object Qpost_read_conversion, Qpre_write_conversion;
 Lisp_Object Qdefault_char;
 Lisp_Object Qno_conversion, Qundecided;
 Lisp_Object Qcharset, Qiso_2022, Qutf_8, Qutf_16, Qshift_jis, Qbig5;
-Lisp_Object Qsignature, Qendian, Qbig, Qlittle;
+Lisp_Object Qbig, Qlittle;
 Lisp_Object Qcoding_system_history;
 Lisp_Object Qvalid_codes;
 extern Lisp_Object Qinsert_file_contents, Qwrite_region;
 Lisp_Object Qcall_process, Qcall_process_region, Qprocess_argument;
 #define CATEGORY_MASK_ISO_8_1		(1 << coding_category_iso_8_1)
 #define CATEGORY_MASK_ISO_8_2		(1 << coding_category_iso_8_2)
 #define CATEGORY_MASK_ISO_7_ELSE	(1 << coding_category_iso_7_else)
 #define CATEGORY_MASK_ISO_8_ELSE	(1 << coding_category_iso_8_else)
 #define CATEGORY_MASK_UTF_8		(1 << coding_category_utf_8)
+#define CATEGORY_MASK_UTF_16_AUTO	(1 << coding_category_utf_16_auto)
 #define CATEGORY_MASK_UTF_16_BE		(1 << coding_category_utf_16_be)
 #define CATEGORY_MASK_UTF_16_LE		(1 << coding_category_utf_16_le)
 #define CATEGORY_MASK_UTF_16_BE_NOSIG	(1 << coding_category_utf_16_be_nosig)
 #define CATEGORY_MASK_UTF_16_LE_NOSIG	(1 << coding_category_utf_16_le_nosig)
 #define CATEGORY_MASK_CHARSET		(1 << coding_category_charset)
 ONE_MORE_BYTE (c1);
 ONE_MORE_BYTE (c2);
 if ((c1 == 0xFF) && (c2 == 0xFE))
 {
-detect_info->found |= CATEGORY_MASK_UTF_16_LE;
+detect_info->found |= (CATEGORY_MASK_UTF_16_LE
+			     | CATEGORY_MASK_UTF_16_AUTO);
 detect_info->rejected |= CATEGORY_MASK_UTF_16_BE;
 }
 else if ((c1 == 0xFE) && (c2 == 0xFF))
 {
-detect_info->found |= CATEGORY_MASK_UTF_16_BE;
+detect_info->found |= (CATEGORY_MASK_UTF_16_BE
+			     | CATEGORY_MASK_UTF_16_AUTO);
 detect_info->rejected |= CATEGORY_MASK_UTF_16_LE;
 }
 no_more_source:
 return 1;
 }
 int surrogate = CODING_UTF_16_SURROGATE (coding);
 Lisp_Object attr, eol_type, charset_list;
 CODING_GET_INFO (coding, attr, eol_type, charset_list);
-if (bom != utf_16_without_bom)
+if (bom == utf_16_with_bom)
 {
 int c, c1, c2;
 src_base = src;
 ONE_MORE_BYTE (c1);
 ONE_MORE_BYTE (c2);
 c = (c1 << 8) | c2;
-if (bom == utf_16_with_bom)
-	{
+if (endian == utf_16_big_endian
-	  if (endian == utf_16_big_endian
+	  ? c != 0xFEFF : c != 0xFFFE)
-	      ? c != 0xFEFF : c != 0xFFFE)
+	{
-	    {
+	  /* The first two bytes are not BOM.  Treat them as bytes
-	      /* We are sure that there's enouph room at CHARBUF.  */
+	     for a normal character.  */
-	      *charbuf++ = c1;
+	  src = src_base;
-	      *charbuf++ = c2;
+	  coding->errors++;
-	      coding->errors++;
+	}
-	    }
+CODING_UTF_16_BOM (coding) = utf_16_without_bom;
-	}
+}
-else
+else if (bom == utf_16_detect_bom)
-	{
+{
-	  if (c == 0xFEFF)
+/* We have already tried to detect BOM and failed in
-	    CODING_UTF_16_ENDIAN (coding)
+	 detect_coding.  */
-	      = endian = utf_16_big_endian;
+CODING_UTF_16_BOM (coding) = utf_16_without_bom;
-	  else if (c == 0xFFFE)
-	    CODING_UTF_16_ENDIAN (coding)
-	      = endian = utf_16_little_endian;
-	  else
-	    {
-	      CODING_UTF_16_ENDIAN (coding)
-		= endian = utf_16_big_endian;
-	      src = src_base;
-	    }
-	}
-CODING_UTF_16_BOM (coding) = utf_16_with_bom;
 }
 while (1)
 {
 int c, c1, c2;
 Lisp_Object attrs, eol_type, charset_list;
 int c;
 CODING_GET_INFO (coding, attrs, eol_type, charset_list);
-if (bom == utf_16_with_bom)
+if (bom != utf_16_without_bom)
 {
 ASSURE_DESTINATION (safe_room);
 if (big_endian)
 	EMIT_TWO_BYTES (0xFE, 0xFF);
 else
 val = AREF (attrs, coding_attr_utf_16_bom);
 CODING_UTF_16_BOM (coding) = (CONSP (val) ? utf_16_detect_bom
 				    : EQ (val, Qt) ? utf_16_with_bom
 				    : utf_16_without_bom);
 val = AREF (attrs, coding_attr_utf_16_endian);
-CODING_UTF_16_ENDIAN (coding) = (NILP (val) ? utf_16_big_endian
+CODING_UTF_16_ENDIAN (coding) = (EQ (val, Qbig) ? utf_16_big_endian
 				       : utf_16_little_endian);
 CODING_UTF_16_SURROGATE (coding) = 0;
 coding->detector = detect_coding_utf_16;
 coding->decoder = decode_coding_utf_16;
 coding->encoder = encode_coding_utf_16;
 coding->common_flags
 	|= (CODING_REQUIRE_DECODING_MASK | CODING_REQUIRE_ENCODING_MASK);
+if (CODING_UTF_16_BOM (coding) == utf_16_detect_bom)
+	coding->common_flags |= CODING_REQUIRE_DETECTION_MASK;
 }
 else if (EQ (coding_type, Qccl))
 {
 coding->detector = detect_coding_ccl;
 coding->decoder = decode_coding_ccl;
 		  setup_coding_system (CODING_ID_NAME (this->id), coding);
 		  break;
 		}
 	}
 }
+else if (EQ (CODING_ATTR_TYPE (CODING_ID_ATTRS (coding->id)), Qutf_16))
+{
+Lisp_Object coding_systems;
+struct coding_detection_info detect_info;
+coding_systems
+	= AREF (CODING_ID_ATTRS (coding->id), coding_attr_utf_16_bom);
+detect_info.found = detect_info.rejected = 0;
+if (CONSP (coding_systems)
+	  && detect_coding_utf_16 (coding, &detect_info)
+	  && (detect_info.found & (CATEGORY_MASK_UTF_16_LE
+				   | CATEGORY_MASK_UTF_16_BE)))
+	{
+	  if (detect_info.found & CATEGORY_MASK_UTF_16_LE)
+	    setup_coding_system (XCAR (coding_systems), coding);
+	  else
+	    setup_coding_system (XCDR (coding_systems), coding);
+	}
+}
 attrs = CODING_ID_ATTRS (coding->id);
 coding_type = CODING_ATTR_TYPE (attrs);
 /* If we have not yet decided the EOL type, detect it now.  But, the
 	  CHECK_CODING_SYSTEM (XCDR (bom));
 	}
 ASET (attrs, coding_attr_utf_16_bom, bom);
 endian = args[coding_arg_utf16_endian];
+CHECK_SYMBOL (endian);
+if (NILP (endian))
+	endian = Qbig;
+else if (! EQ (endian, Qbig) && ! EQ (endian, Qlittle))
+	error ("Invalid endian: %s", XSYMBOL (endian)->name->data);
 ASET (attrs, coding_attr_utf_16_endian, endian);
 category = (CONSP (bom)
 		  ? coding_category_utf_16_auto
 		  : NILP (bom)
-		  ? (NILP (endian)
+		  ? (EQ (endian, Qbig)
 		     ? coding_category_utf_16_be_nosig
 		     : coding_category_utf_16_le_nosig)
-		  : (NILP (endian)
+		  : (EQ (endian, Qbig)
 		     ? coding_category_utf_16_be
 		     : coding_category_utf_16_le));
 }
 else if (EQ (coding_type, Qiso_2022))
 {
 DEFSYM (Qiso_2022, "iso-2022");
 DEFSYM (Qutf_8, "utf-8");
 DEFSYM (Qutf_16, "utf-16");
-DEFSYM (Qsignature, "signature");
-DEFSYM (Qendian, "endian");
 DEFSYM (Qbig, "big");
 DEFSYM (Qlittle, "little");
 DEFSYM (Qshift_jis, "shift-jis");
 DEFSYM (Qbig5, "big5");

Mercurial > emacs

comparison src/coding.c @ 89420:c3e67ce6ee0f