Mercurial > hg > xemacs-beta

changeset 3496:d08f0a2c8722

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
[xemacs-hg @ 2006-07-07 23:01:01 by aidan] Adjust the Mule charsets to support 500,000 unknown Unicode charsets.
author aidan
date Fri, 07 Jul 2006 23:01:11 +0000
parents 61954f295412
children 45671f160bd5
files man/ChangeLog man/internals/internals.texi src/ChangeLog src/charset.h
diffstat 4 files changed, 34 insertions(+), 19 deletions(-) [+]
line wrap: on
line diff
--- a/man/ChangeLog	Fri Jul 07 21:50:56 2006 +0000
+++ b/man/ChangeLog	Fri Jul 07 23:01:11 2006 +0000
@@ -1,3 +1,11 @@
+2006-07-08  Aidan Kehoe  <kehoea@parhasard.net>
+
+	* internals/internals.texi (Internal String Encoding):
+	Mention that UTF-8 would be a reasonable alternative encoding. 
+	* internals/internals.texi (Internal Character Encoding):
+	Re-arrange the description of characters to deal with 21-bit
+	characters. 
+
 2006-06-03  Aidan Kehoe  <kehoea@parhasard.net>
 
 	* lispref/mule.texi (CCL Syntax):
--- a/man/internals/internals.texi	Fri Jul 07 21:50:56 2006 +0000
+++ b/man/internals/internals.texi	Fri Jul 07 23:01:11 2006 +0000
@@ -11335,10 +11335,12 @@
 the actual multi-byte encoding.
 @end enumerate
 
-  None of the standard non-modal encodings meet all of these
+  None of the pre-Unciode standard non-modal encodings meet all of these
 conditions.  For example, EUC satisfies only (2) and (3), while
-Shift-JIS and Big5 (not yet described) satisfy only (2). (All
-non-modal encodings must satisfy (2), in order to be unambiguous.)
+Shift-JIS and Big5 (not yet described) satisfy only (2). (All non-modal
+encodings must satisfy (2), in order to be unambiguous.)  UTF-8,
+however, meets all three, and we are considering moving to it as an
+internal encoding.
 
 @node Internal Character Encoding,  , Internal String Encoding, Internal Mule Encodings
 @subsection Internal Character Encoding
@@ -11346,16 +11348,16 @@
 @cindex character encoding, internal
 @cindex encoding, internal character
 
-  One 19-bit word represents a single character.  The word is
+  One 21-bit word represents a single character.  The word is
 separated into three fields:
 
 @example
-Bit number:     18 17 16 15 14 13 12 11 10 09 08 07 06 05 04 03 02 01 00
-                <------------> <------------------> <------------------>
-Field:                1                  2                    3
-@end example
-
-  Note that fields 2 and 3 hold 7 bits each, while field 1 holds 5 bits.
+Bit number:     20 19 18 17 16 15 14 13 12 11 10 09 08 07 06 05 04 03 02 01 00
+                <------------------> <------------------> <------------------>
+Field:                    1                    2                    3
+@end example
+
+  Note that each field holds 7 bits. 
 
 @example
 Character set           Field 1         Field 2         Field 3
@@ -11370,12 +11372,12 @@
    range:                                    (20 - 6F)      (20 - 7F)
 Dimension-2 official    LB - 0x8F         PC1             PC2
    range:                    (01 - 0A)       (20 - 7F)      (20 - 7F)
-Dimension-2 private     LB - 0xE1         PC1             PC2
+Dimension-2 private     LB - 0x80         PC1             PC2
    range:                    (0F - 1E)       (20 - 7F)      (20 - 7F)
 Composite                 0x1F             ?               ?
 @end example
 
-Note that character codes 0 - 255 are the same as the ``binary
+Note also that character codes 0 - 255 are the same as the ``binary
 encoding'' described above.
 
 Most of the code in XEmacs knows nothing of the representation of a
@@ -11607,7 +11609,7 @@
 you cannot do the standard C trick of passing a pointer to a character
 to a function that expects a string.
 
-An Ichar takes up 19 bits of representation and (for code compatibility
+An Ichar takes up 21 bits of representation and (for code compatibility
 and such) is compatible with an int.  This representation is visible on
 the Lisp level.  The important characteristics of the Ichar
 representation are
--- a/src/ChangeLog	Fri Jul 07 21:50:56 2006 +0000
+++ b/src/ChangeLog	Fri Jul 07 23:01:11 2006 +0000
@@ -1,3 +1,8 @@
+2006-07-08  Aidan Kehoe  <kehoea@parhasard.net>
+
+	* charset.h:
+	Move to 7 bits instead of 5 for the first field of a character.
+
 2006-07-07  Aidan Kehoe  <kehoea@parhasard.net>
 
 	* config.h.in:
--- a/src/charset.h	Fri Jul 07 21:50:56 2006 +0000
+++ b/src/charset.h	Fri Jul 07 23:01:11 2006 +0000
@@ -140,8 +140,8 @@
 #define PRE_LEADING_BYTE_PRIVATE_2	0x9F	/* 2-byte char-set */
 
 #define MIN_LEADING_BYTE_PRIVATE_1	0xA0
-#define MAX_LEADING_BYTE_PRIVATE_1	0xEF
-#define MIN_LEADING_BYTE_PRIVATE_2	0xF0
+#define MAX_LEADING_BYTE_PRIVATE_1	0xC0
+#define MIN_LEADING_BYTE_PRIVATE_2	0xC1
 #define MAX_LEADING_BYTE_PRIVATE_2	0xFF
 
 #define NUM_LEADING_BYTES 129
@@ -354,9 +354,9 @@
 /************************************************************************/
 
 /* The bit fields of character are divided into 3 parts:
-   FIELD1(5bits):FIELD2(7bits):FIELD3(7bits) */
+   FIELD1(7bits):FIELD2(7bits):FIELD3(7bits) */
 
-#define ICHAR_FIELD1_MASK (0x1F << 14)
+#define ICHAR_FIELD1_MASK (0x7F << 14)
 #define ICHAR_FIELD2_MASK (0x7F << 7)
 #define ICHAR_FIELD3_MASK 0x7F
 
@@ -376,7 +376,7 @@
 #define FIELD2_TO_PRIVATE_LEADING_BYTE  0x80
 
 #define FIELD1_TO_OFFICIAL_LEADING_BYTE (MIN_LEADING_BYTE_OFFICIAL_2 - 1)
-#define FIELD1_TO_PRIVATE_LEADING_BYTE  0xE1
+#define FIELD1_TO_PRIVATE_LEADING_BYTE  0x80
 
 /* Minimum and maximum allowed values for the fields. */
 
@@ -406,7 +406,7 @@
 #define MIN_CHAR_PRIVATE_TYPE9N     (MIN_ICHAR_FIELD2_PRIVATE  <<  7)
 #define MIN_CHAR_OFFICIAL_TYPE9NX9N (MIN_ICHAR_FIELD1_OFFICIAL << 14)
 #define MIN_CHAR_PRIVATE_TYPE9NX9N  (MIN_ICHAR_FIELD1_PRIVATE  << 14)
-#define MIN_CHAR_COMPOSITION        (0x1F << 14)
+#define MIN_CHAR_COMPOSITION        (0x7F << 14)
 
 /* Leading byte of a character.