emacs-unicode-2: miscellaneous addendum for coding system gbk and gb18030

[Zhang Wei]

The gbk and gb18030 coding system support is added in emacs-unicode-2,
Emacs 22 doesn't support them, so miscellaneous code must be added here
and there, I gathered some patches and hope them useful.

* local directory is at address@hidden/emacs--unicode--0--patch-135
* comparing to address@hidden/emacs--unicode--0--patch-135
A  gbk-gb18030-patch
M  lisp/faces.el
M  lisp/international/characters.el
M  lisp/gnus/mm-util.el
M  lisp/gnus/rfc2047.el
M  lisp/international/mule-cmds.el
M  lisp/language/chinese.el
M  lisp/international/fontset.el

* modified files

--- orig/lisp/faces.el
+++ mod/lisp/faces.el
@@ -81,11 +81,11 @@
 (defcustom face-font-registry-alternatives
   (if (eq system-type 'windows-nt)
       '(("iso8859-1" "ms-oemlatin")
-       ("gb2312.1980" "gb2312")
+       ("gb2312.1980" "gb2312" "gbk" "gb18030")
        ("jisx0208.1990" "jisx0208.1983" "jisx0208.1978")
        ("ksc5601.1989" "ksx1001.1992" "ksc5601.1987")
        ("muletibetan-2" "muletibetan-0"))
-    '(("gb2312.1980" "gb2312.80&gb8565.88" "gbk*")
+    '(("gb2312.1980" "gb2312.80&gb8565.88" "gbk" "gb18030")
       ("jisx0208.1990" "jisx0208.1983" "jisx0208.1978")
       ("ksc5601.1989" "ksx1001.1992" "ksc5601.1987")
       ("muletibetan-2" "muletibetan-0")))


--- orig/lisp/gnus/mm-util.el
+++ mod/lisp/gnus/mm-util.el
@@ -443,6 +443,10 @@
     (iso-2022-jp latin-jisx0201 japanese-jisx0208 japanese-jisx0208-1978)
     (euc-kr korean-ksc5601)
     (gb2312 chinese-gb2312)
+    (gbk chinese-gbk)
+    (gb18030 gb18030-2-byte
+            gb18030-4-byte-bmp gb18030-4-byte-smp
+            gb18030-4-byte-ext-1 gb18030-4-byte-ext-2)
     (big5 chinese-big5-1 chinese-big5-2)
     (tibetan tibetan)
     (thai-tis620 thai-tis620)


--- orig/lisp/gnus/rfc2047.el
+++ mod/lisp/gnus/rfc2047.el
@@ -107,6 +107,8 @@
     (iso-2022-jp . B)
     (iso-2022-kr . B)
     (gb2312 . B)
+    (gbk . B)
+    (gb18030 . B)
     (big5 . B)
     (cn-big5 . B)
     (cn-gb . B)


--- orig/lisp/international/characters.el
+++ mod/lisp/international/characters.el
@@ -834,12 +834,16 @@
           (cyrillic-iso8859-5  . cyrillic-iso-8bit)
           (latin-iso8859-9     . iso-latin-5)
           (japanese-jisx0208-1978 . iso-2022-jp)
-          (chinese-gb2312      . cn-gb-2312)
+          (chinese-gb2312      . chinese-iso-8bit)
+          (chinese-gbk         . chinese-gbk)
+          (gb18030-2-byte      . chinese-gb18030)
+          (gb18030-4-byte-bmp  . chinese-gb18030)
+          (gb18030-4-byte-smp  . chinese-gb18030)
+          (gb18030-4-byte-ext-1 . chinese-gb18030)
+          (gb18030-4-byte-ext-2 . chinese-gb18030)
           (japanese-jisx0208   . iso-2022-jp)
           (korean-ksc5601      . iso-2022-kr)
           (japanese-jisx0212   . iso-2022-jp)
-          (chinese-cns11643-1  . iso-2022-cn)
-          (chinese-cns11643-2  . iso-2022-cn)
           (chinese-big5-1      . chinese-big5)
           (chinese-big5-2      . chinese-big5)
           (chinese-sisheng     . iso-2022-7bit)
@@ -854,6 +858,8 @@
           (indian-glyph        . devanagari)
           (tibetan-1-column    . tibetan)
           (ethiopic            . iso-2022-7bit)
+          (chinese-cns11643-1  . iso-2022-cn)
+          (chinese-cns11643-2  . iso-2022-cn)
           (chinese-cns11643-3  . iso-2022-cn)
           (chinese-cns11643-4  . iso-2022-cn)
           (chinese-cns11643-5  . iso-2022-cn)


--- orig/lisp/international/fontset.el
+++ mod/lisp/international/fontset.el
@@ -50,6 +50,7 @@
        ("iso8859-15$" . iso-8859-15)
        ("gb2312.1980" . chinese-gb2312)
        ("gbk" . chinese-gbk)
+       ("gb18030" . gb18030)
        ("jisx0208.1978" . japanese-jisx0208-1978)
        ("jisx0208" . japanese-jisx0208)
        ("jisx0201" . jisx0201)
@@ -306,6 +307,7 @@
          (nil . "CNS11643.1992-6")
          (nil . "CNS11643.1992-7")
          (nil . "gbk-0")
+         (nil . "gb18030")
          (nil . "JISX0213.2000-1")
          (nil . "JISX0213.2000-2")
          (nil . "JISX0213.2004-1"))
@@ -323,6 +325,7 @@
               (nil . "CNS11643.1992-6")
               (nil . "CNS11643.1992-7")
               (nil . "gbk-0")
+              (nil . "gb18030")
               (nil . "JISX0213.2000-1")
               (nil . "JISX0213.2000-2"))
 
@@ -363,6 +366,8 @@
 
      ;; Fallback fonts
      (nil (nil . "gb2312.1980")
+         (nil . "gbk-0")
+         (nil . "gb18030")
          (nil . "jisx0208")
          (nil . "ksc5601.1987")
          (nil . "CNS11643.1992-1")
@@ -515,11 +520,11 @@
 
 ;; Setting for suppressing XLoadQueryFont on big fonts.
 (setq x-pixel-size-width-font-regexp
-      "gb2312\\|jisx0208\\|ksc5601\\|cns11643\\|big5")
+      "gb2312\\|gbk\\|gb18030\\|jisx0208\\|ksc5601\\|cns11643\\|big5")
 
 ;; These fonts require vertical centering.
 (setq vertical-centering-font-regexp
-      "gb2312\\|jisx0208\\|jisx0212\\|ksc5601\\|cns11643\\|big5")
+      
"gb2312\\|gbk\\|gb18030\\|jisx0208\\|jisx0212\\|ksc5601\\|cns11643\\|big5")
 
 ;; CDAC fonts are actually smaller than their design sizes.
 (setq face-font-rescale-alist
@@ -723,6 +728,11 @@
     (katakana-jisx0201 . kana)
     (chinese-gb2312 . han)
     (chinese-gbk . han)
+    (gb18030-2-byte . han)
+    (gb18030-4-byte-bmp . han)
+    (gb18030-4-byte-ext-1 . han)
+    (gb18030-4-byte-ext-2 . han)
+    (gb18030-4-byte-smp . han)
     (chinese-big5-1 . han)
     (chinese-big5-2 . han)
     (chinese-cns11643-1 . han)


--- orig/lisp/international/mule-cmds.el
+++ mod/lisp/international/mule-cmds.el
@@ -2262,8 +2262,8 @@
     ("zh_CN.GB2312" "Chinese-GB")
     ("zh_CN.GBK" "Chinese-GBK")
     ("zh_CN.GB18030" "Chinese-GB18030")
-    ("zh_CN" . "Chinese-GB")
-    ("zh" . "Chinese-GB")
+    ("zh_CN" . "Chinese-GBK")
+    ("zh" . "Chinese-GBK")
     ("zu" . "Latin-1") ; Zulu
 
     ;; ISO standard locales
@@ -2281,7 +2281,7 @@
     ("sp" . "Cyrillic-ISO") ; Serbian (Cyrillic alphabet), e.g. X11R6.4
     ("su" . "Latin-1") ; Finnish, e.g. Solaris 2.6
     ("jp" . "Japanese") ; e.g. MS Windows
-    ("chs" . "Chinese-GB") ; MS Windows Chinese Simplified
+    ("chs" . "Chinese-GBK") ; MS Windows Chinese Simplified
     ("cht" . "Chinese-BIG5") ; MS Windows Chinese Traditional
     ("gbz" . "UTF-8") ; MS Windows Dari Persian
     ("div" . "UTF-8") ; MS Windows Divehi (Maldives)


--- orig/lisp/language/chinese.el
+++ mod/lisp/language/chinese.el
@@ -91,7 +91,6 @@
 (define-coding-system-alias 'euc-cn 'chinese-iso-8bit)
 (define-coding-system-alias 'cn-gb 'chinese-iso-8bit)
 (define-coding-system-alias 'gb2312 'chinese-iso-8bit)
-(define-coding-system-alias 'cp936 'chinese-iso-8bit)
 
 (define-coding-system 'chinese-hz
   "Hz/ZW 7-bit encoding for Chinese GB2312 (MIME:HZ-GB-2312)."
@@ -233,7 +232,8 @@
                 (input-method . "chinese-py-punct") ; fixme?
                 (sample-text . "Chinese (中文,普通话,汉语) 妳好")
                 (features china-util)
-                (documentation . "Support for Chinese GBK character set."))
+                (documentation . "Support for Chinese GBK character set.")
+                (tutorial . "TUTORIAL.cn"))
  '("Chinese"))
 
 ;;; Chinese GB18030
@@ -255,9 +255,11 @@
                     (coding-priority gb18030 gbk iso-2022-cn chinese-big5
                                      chinese-iso-8bit) ; fixme?
                     (input-method . "chinese-py-punct") ; fixme?
+                    (sample-text . "Chinese (中文,普通话,汉语) 你好")
                     (features china-util)
-                    (documentation
-                     . "Support for Chinese GB18030 character set."))
+                    (documentation 
+                     . "Support for Chinese GB18030 character set.")
+                    (tutorial . "TUTORIAL.cn"))
  '("Chinese"))
 
 ;; Fixme: add HKSCS