Add C interface for Unicode character property table.

19 files changed, 59 insertions, 59 deletions

diff --git a/lisp/ChangeLog b/lisp/ChangeLog
index 89b33dc7a62..b85a1680286 100644
--- a/lisp/ChangeLog
+++ b/lisp/ChangeLog
@@ -1,3 +1,39 @@
+2011-07-06  Kenichi Handa  <handa@m17n.org>
+
+        * international/characters.el (build-unicode-category-table):
+        Delete it.
+        (unicode-category-table): Set it by
+        unicode-prroperty-table-internal.
+
+        * international/mule-cmds.el (char-code-property-alist): Moved to
+        to src/chartab.c.
+        (get-char-code-property): Call unicode-property-table-internal to
+        load a file.  Call get-unicode-property-internal where necessary.
+        (put-char-code-property): Call unicode-property-table-internal to
+        load a file.  Call put-unicode-property-internal where necessary.
+        put-unicode-property-internal where necessary.
+        (char-code-property-description): Call
+        unicode-property-table-internal to load a file.
+
+        * international/charprop.el:
+        * international/uni-bidi.el:
+        * international/uni-category.el:
+        * international/uni-combining.el:
+        * international/uni-comment.el:
+        * international/uni-decimal.el:
+        * international/uni-decomposition.el:
+        * international/uni-digit.el:
+        * international/uni-lowercase.el:
+        * international/uni-mirrored.el:
+        * international/uni-name.el:
+        * international/uni-numeric.el:
+        * international/uni-old-name.el:
+        * international/uni-titlecase.el:
+        * international/uni-uppercase.el: Regenerate.
+
+        * loadup.el: Load international/charprop.el before
+        international/characters.
+
 2011-06-22  Richard Stallman  <rms@gnu.org>
 
         * mail/sendmail.el (mail-bury): If Rmail is in use, return nicely
diff --git a/lisp/international/characters.el b/lisp/international/characters.el
index 455cbe697d6..a9657c17b9f 100644
--- a/lisp/international/characters.el
+++ b/lisp/international/characters.el
@@ -1206,22 +1206,8 @@ Setup char-width-table appropriate for non-CJK language environment."
 
 ;;; Setting unicode-category-table.
 
-;; This macro is to build unicode-category-table at compile time so
-;; that C code can access the table efficiently.
-(defmacro build-unicode-category-table ()
-  (let ((table (make-char-table 'unicode-category-table nil)))
-    (dotimes (i #x110000)
-      (if (or (< i #xD800)
-              (and (>= i #xF900) (< i #x30000))
-              (and (>= i #xE0000) (< i #xE0200)))
-          (aset table i (get-char-code-property i 'general-category))))
-    (set-char-table-range table '(#xE000 . #xF8FF) 'Co)
-    (set-char-table-range table '(#xF0000 . #xFFFFD) 'Co)
-    (set-char-table-range table '(#x100000 . #x10FFFD) 'Co)
-    (optimize-char-table table 'eq)
-    table))
-
-(setq unicode-category-table (build-unicode-category-table))
+(setq unicode-category-table
+      (unicode-property-table-internal 'general-category))
 (map-char-table #'(lambda (key val)
                     (if (and val
                              (or (and (/= (aref (symbol-name val) 0) ?M)
diff --git a/lisp/international/charprop.el b/lisp/international/charprop.el
index 5c3efcc9d07..919666010b1 100644
--- a/lisp/international/charprop.el
+++ b/lisp/international/charprop.el
@@ -1,8 +1,4 @@
-;; Copyright (C) 1991-2010 Unicode, Inc.
-;; This file was generated from the Unicode data file at
-;; http://www.unicode.org/Public/UNIDATA/UnicodeData.txt.
-;; See lisp/international/README for the copyright and permission notice.
-
+;; Automatically generated by unidata-gen.el.
 ;; FILE: uni-name.el
 (define-char-code-property 'name "uni-name.el"
   "Unicode character name.
@@ -45,7 +41,7 @@ Property value is an integer or a floating point.")
 ;; FILE: uni-mirrored.el
 (define-char-code-property 'mirrored "uni-mirrored.el"
   "Unicode bidi mirrored flag.
-Property value is a symbol `Y' or `N'.")
+Property value is a symbol `Y' or `N'.  See also the property `mirroring'.")
 ;; FILE: uni-old-name.el
 (define-char-code-property 'old-name "uni-old-name.el"
   "Unicode old names as published in Unicode 1.0.
@@ -66,6 +62,11 @@ Property value is a character.")
 (define-char-code-property 'titlecase "uni-titlecase.el"
   "Unicode simple titlecase mapping.
 Property value is a character.")
+;; FILE: uni-mirrored.el
+(define-char-code-property 'mirroring "uni-mirrored.el"
+  "Unicode bidi-mirroring characters.
+Property value is a character that has the corresponding mirroring image,
+or nil for non-mirrored character.")
 ;; Local Variables:
 ;; coding: utf-8
 ;; no-byte-compile: t
diff --git a/lisp/international/mule-cmds.el b/lisp/international/mule-cmds.el
index b3f17bb3fcf..e75a22d6415 100644
--- a/lisp/international/mule-cmds.el
+++ b/lisp/international/mule-cmds.el
@@ -2709,16 +2709,6 @@ See also `locale-charset-language-names', `locale-language-names',
 
 ;;; Character property
 
-;; Each element has the form (PROP . TABLE).
-;; PROP is a symbol representing a character property.
-;; TABLE is a char-table containing the property value for each character.
-;; TABLE may be a name of file to load to build a char-table.
-;; Don't modify this variable directly but use `define-char-code-property'.
-
-(defvar char-code-property-alist nil
-  "Alist of character property name vs char-table containing property values.
-Internal use only.")
-
 (put 'char-code-property-table 'char-table-extra-slots 5)
 
 (defun define-char-code-property (name table &optional docstring)
@@ -2770,32 +2760,23 @@ See also the documentation of `get-char-code-property' and
 
 (defun get-char-code-property (char propname)
   "Return the value of CHAR's PROPNAME property."
-  (let ((slot (assq propname char-code-property-alist)))
-    (if slot
-        (let (table value func)
-          (if (stringp (cdr slot))
-              (load (cdr slot) nil t))
-          (setq table (cdr slot)
-                value (aref table char)
-                func (char-table-extra-slot table 1))
+  (let ((table (unicode-property-table-internal propname)))
+    (if table
+        (let ((func (char-table-extra-slot table 1)))
           (if (functionp func)
-              (setq value (funcall func char value table)))
-          value)
+              (funcall func char (aref table char) table)
+            (get-unicode-property-internal table char)))
       (plist-get (aref char-code-property-table char) propname))))
 
 (defun put-char-code-property (char propname value)
   "Store CHAR's PROPNAME property with VALUE.
 It can be retrieved with `(get-char-code-property CHAR PROPNAME)'."
-  (let ((slot (assq propname char-code-property-alist)))
-    (if slot
-        (let (table func)
-          (if (stringp (cdr slot))
-              (load (cdr slot) nil t))
-          (setq table (cdr slot)
-                func (char-table-extra-slot table 2))
+  (let ((table (unicode-property-table-internal propname)))
+    (if table
+        (let ((func (char-table-extra-slot table 2)))
           (if (functionp func)
               (funcall func char value table)
-            (aset table char value)))
+            (put-unicode-property-internal table char value)))
       (let* ((plist (aref char-code-property-table char))
              (x (plist-put plist propname value)))
         (or (eq x plist)
@@ -2805,13 +2786,9 @@ It can be retrieved with `(get-char-code-property CHAR PROPNAME)'."
 (defun char-code-property-description (prop value)
   "Return a description string of character property PROP's value VALUE.
 If there's no description string for VALUE, return nil."
-  (let ((slot (assq prop char-code-property-alist)))
-    (if slot
-        (let (table func)
-          (if (stringp (cdr slot))
-              (load (cdr slot) nil t))
-          (setq table (cdr slot)
-                func (char-table-extra-slot table 3))
+  (let ((table (unicode-property-table-internal prop)))
+    (if table
+        (let ((func (char-table-extra-slot table 3)))
           (if (functionp func)
               (funcall func value))))))
 
diff --git a/lisp/international/uni-bidi.el b/lisp/international/uni-bidi.el
index 9e571ef9d0d..e7682c6d8ff 100644
--- a/lisp/international/uni-bidi.el
+++ b/lisp/international/uni-bidi.el
diff --git a/lisp/international/uni-category.el b/lisp/international/uni-category.el
index 80538f7b416..a4455decc52 100644
--- a/lisp/international/uni-category.el
+++ b/lisp/international/uni-category.el
diff --git a/lisp/international/uni-combining.el b/lisp/international/uni-combining.el
index 2ee74d8b818..227b9d0af79 100644
--- a/lisp/international/uni-combining.el
+++ b/lisp/international/uni-combining.el
diff --git a/lisp/international/uni-comment.el b/lisp/international/uni-comment.el
index dcc717977c7..c9743064bd4 100644
--- a/lisp/international/uni-comment.el
+++ b/lisp/international/uni-comment.el
diff --git a/lisp/international/uni-decimal.el b/lisp/international/uni-decimal.el
index 22207a224b0..2c424ffb5de 100644
--- a/lisp/international/uni-decimal.el
+++ b/lisp/international/uni-decimal.el
diff --git a/lisp/international/uni-decomposition.el b/lisp/international/uni-decomposition.el
index f35bcebfed8..b0bf07bbe85 100644
--- a/lisp/international/uni-decomposition.el
+++ b/lisp/international/uni-decomposition.el
diff --git a/lisp/international/uni-digit.el b/lisp/international/uni-digit.el
index 692dea1edc8..fc52fd8c28c 100644
--- a/lisp/international/uni-digit.el
+++ b/lisp/international/uni-digit.el
diff --git a/lisp/international/uni-lowercase.el b/lisp/international/uni-lowercase.el
index 7cc601159f0..41890018204 100644
--- a/lisp/international/uni-lowercase.el
+++ b/lisp/international/uni-lowercase.el
diff --git a/lisp/international/uni-mirrored.el b/lisp/international/uni-mirrored.el
index 5129a93396d..006cf575591 100644
--- a/lisp/international/uni-mirrored.el
+++ b/lisp/international/uni-mirrored.el
diff --git a/lisp/international/uni-name.el b/lisp/international/uni-name.el
index 5b9e8323d21..7fac18b278d 100644
--- a/lisp/international/uni-name.el
+++ b/lisp/international/uni-name.el
diff --git a/lisp/international/uni-numeric.el b/lisp/international/uni-numeric.el
index 278ad683fe4..d16e8c00870 100644
--- a/lisp/international/uni-numeric.el
+++ b/lisp/international/uni-numeric.el
diff --git a/lisp/international/uni-old-name.el b/lisp/international/uni-old-name.el
index 2e283492408..4e704e5cdd0 100644
--- a/lisp/international/uni-old-name.el
+++ b/lisp/international/uni-old-name.el
diff --git a/lisp/international/uni-titlecase.el b/lisp/international/uni-titlecase.el
index 729a469d103..b8098c81876 100644
--- a/lisp/international/uni-titlecase.el
+++ b/lisp/international/uni-titlecase.el
diff --git a/lisp/international/uni-uppercase.el b/lisp/international/uni-uppercase.el
index 0714b14794f..899276eb725 100644
--- a/lisp/international/uni-uppercase.el
+++ b/lisp/international/uni-uppercase.el
diff --git a/lisp/loadup.el b/lisp/loadup.el
index 4c677523689..792827dd913 100644
--- a/lisp/loadup.el
+++ b/lisp/loadup.el
@@ -123,11 +123,11 @@
 ;; multilingual text.
 (load "international/mule-cmds")
 (load "case-table")
-(load "international/characters")
-(load "composite")
 ;; This file doesn't exist when building a development version of Emacs
 ;; from the repository.  It is generated just after temacs is built.
 (load "international/charprop.el" t)
+(load "international/characters")
+(load "composite")
 
 ;; Load language-specific files.
 (load "language/chinese")