;; unidata-gen.el -- Create files containing character property data.
+
+;; Copyright 2008-2013 (C) Free Software Foundation, Inc.
+
;; Copyright (C) 2005, 2006, 2007, 2008, 2009, 2010, 2011
;; National Institute of Advanced Industrial Science and Technology (AIST)
;; Registration Number H13PRO009
;; SPECIAL NOTICE
;;
;; This file must be byte-compilable/loadable by `temacs' and also
-;; the entry function `unidata-gen-files' must be runnable by
-;; `temacs'.
+;; the entry function `unidata-gen-files' must be runnable by `temacs'.
;; FILES TO BE GENERATED
;;
;; The entry function `unidata-gen-files' generates these files in
-;; the current directory.
+;; in directory specified by its dest-dir argument.
;;
;; charprop.el
;; It contains a series of forms of this format:
(defvar unidata-list nil)
-;; Name of the directory containing files of Unicode Character
-;; Database.
+;; Name of the directory containing files of Unicode Character Database.
+;; Dynamically bound in unidata-gen-files.
(defvar unidata-dir nil)
(defun unidata-setup-list (unidata-text-file)
(setq unidata-list (cdr table))))
;; Alist of this form:
-;; (PROP INDEX GENERATOR FILENAME DOCSTRING DESCRIBER VAL-LIST)
+;; (PROP INDEX GENERATOR FILENAME DOCSTRING DESCRIBER DEFAULT VAL-LIST)
;; PROP: character property
;; INDEX: index to each element of unidata-list for PROP.
;; It may be a function that generates an alist of character codes
;; FILENAME: filename to store the char-table
;; DOCSTRING: docstring for the property
;; DESCRIBER: function to call to get a description string of property value
-;; DEFAULT: the default value of the property
+;; DEFAULT: the default value of the property. It may have the form
+;; (VAL0 (FROM1 TO1 VAL1) ...) which indicates that the default
+;; value is VAL0 except for characters in the ranges specified by
+;; FROMn and TOn (inclusive). The default value of characters
+;; between FROMn and TOn is VALn.
;; VAL-LIST: list of specially ordered property values
(defconst unidata-prop-alist
'((name
1 unidata-gen-table-name "uni-name.el"
"Unicode character name.
-Property value is a string.")
+Property value is a string or nil.
+The value nil stands for the default value \"null string\")."
+ nil
+ nil)
(general-category
2 unidata-gen-table-symbol "uni-category.el"
"Unicode general category.
Lu, Ll, Lt, Lm, Lo, Mn, Mc, Me, Nd, Nl, No, Pc, Pd, Ps, Pe, Pi, Pf, Po,
Sm, Sc, Sk, So, Zs, Zl, Zp, Cc, Cf, Cs, Co, Cn"
unidata-describe-general-category
- nil
+ Cn
;; The order of elements must be in sync with unicode_category_t
;; in src/character.h.
(Lu Ll Lt Lm Lo Mn Mc Me Nd Nl No Pc Pd Ps Pe Pi Pf Po
3 unidata-gen-table-integer "uni-combining.el"
"Unicode canonical combining class.
Property value is an integer."
- unidata-describe-canonical-combining-class)
+ unidata-describe-canonical-combining-class
+ 0)
(bidi-class
4 unidata-gen-table-symbol "uni-bidi.el"
"Unicode bidi class.
L, LRE, LRO, R, AL, RLE, RLO, PDF, EN, ES, ET,
AN, CS, NSM, BN, B, S, WS, ON"
unidata-describe-bidi-class
- L
+ ;; The assignment of default values to blocks of code points
+ ;; follows the file DerivedBidiClass.txt from the Unicode
+ ;; Character Database (UCD).
+ (L (#x0600 #x06FF AL) (#xFB50 #xFDFF AL) (#xFE70 #xFEFF AL)
+ (#x0590 #x05FF R) (#x07C0 #x08FF R)
+ (#xFB1D #xFB4F R) (#x10800 #x10FFF R) (#x1E800 #x1EFFF R))
;; The order of elements must be in sync with bidi_type_t in
;; src/dispextern.h.
(L R EN AN BN B AL LRE LRO RLE RLO PDF ES ET CS NSM S WS ON))
(decimal-digit-value
6 unidata-gen-table-integer "uni-decimal.el"
"Unicode numeric value (decimal digit).
-Property value is an integer.")
+Property value is an integer 0..9, or nil.
+The value nil stands for NaN \"Numeric_Value\".")
(digit-value
7 unidata-gen-table-integer "uni-digit.el"
"Unicode numeric value (digit).
-Property value is an integer.")
+Property value is an integer 0..9, or nil.
+The value nil stands for NaN \"Numeric_Value\".")
(numeric-value
8 unidata-gen-table-numeric "uni-numeric.el"
"Unicode numeric value (numeric).
-Property value is an integer or a floating point.")
+Property value is an integer, a floating point, or nil.
+The value nil stands for NaN \"Numeric_Value\".")
(mirrored
9 unidata-gen-table-symbol "uni-mirrored.el"
"Unicode bidi mirrored flag.
-Property value is a symbol `Y' or `N'. See also the property `mirroring'.")
+Property value is a symbol `Y' or `N'. See also the property `mirroring'."
+ nil
+ N)
(old-name
10 unidata-gen-table-name "uni-old-name.el"
"Unicode old names as published in Unicode 1.0.
-Property value is a string.")
+Property value is a string or nil.
+The value nil stands for the default value \"null string\").")
(iso-10646-comment
11 unidata-gen-table-name "uni-comment.el"
"Unicode ISO 10646 comment.
(uppercase
12 unidata-gen-table-character "uni-uppercase.el"
"Unicode simple uppercase mapping.
-Property value is a character."
+Property value is a character or nil.
+The value nil means that the actual property value of a character
+is the character itself."
string)
(lowercase
13 unidata-gen-table-character "uni-lowercase.el"
"Unicode simple lowercase mapping.
-Property value is a character."
+Property value is a character or nil.
+The value nil means that the actual property value of a character
+is the character itself."
string)
(titlecase
14 unidata-gen-table-character "uni-titlecase.el"
"Unicode simple titlecase mapping.
-Property value is a character."
+Property value is a character or nil.
+The value nil means that the actual property value of a character
+is the character itself."
string)
(mirroring
unidata-gen-mirroring-list unidata-gen-table-character "uni-mirrored.el"
"Unicode bidi-mirroring characters.
-Property value is a character that has the corresponding mirroring image,
-or nil for non-mirrored character.")))
+Property value is a character that has the corresponding mirroring image or nil.
+The value nil means that the actual property value of a character
+is the character itself.")))
;; Functions to access the above data.
(defsubst unidata-prop-index (prop) (nth 1 (assq prop unidata-prop-alist)))
(while tail
(setcar tail (cons (car tail) val-code))
(setq tail (cdr tail) val-code (1+ val-code)))
- (setq default-value (unidata-encode-val val-list default-value))
- (set-char-table-range table t default-value)
- (set-char-table-range table nil default-value)
+ (if (consp default-value)
+ (setq default-value (copy-sequence default-value))
+ (setq default-value (list default-value)))
+ (setcar default-value
+ (unidata-encode-val val-list (car default-value)))
+ (set-char-table-range table t (car default-value))
+ (set-char-table-range table nil (car default-value))
+ (dolist (elm (cdr default-value))
+ (setcar (nthcdr 2 elm)
+ (unidata-encode-val val-list (nth 2 elm)))
+ (set-char-table-range table (cons (car elm) (nth 1 elm)) (nth 2 elm)))
+
(setq tail unidata-list)
(while tail
(setq elt (car tail) tail (cdr tail))
(setq prev-range-data (cons (cons from to) val-code)))))
(let* ((start (lsh (lsh range -7) 7))
(limit (+ start 127))
- str count new-val)
- (fillarray vec 0)
- ;; See the comment above.
- (when (and prev-range-data
- (>= (cdr (car prev-range-data)) start))
- (let ((from (car (car prev-range-data)))
- (to (cdr (car prev-range-data)))
- (vcode (cdr prev-range-data)))
+ str count new-val from to vcode)
+ (fillarray vec (car default-value))
+ (dolist (elm (cdr default-value))
+ (setq from (car elm) to (nth 1 elm))
+ (when (and (<= from limit)
+ (or (>= from start) (>= to start)))
+ (setq from (max from start)
+ to (min to limit)
+ vcode (nth 2 elm))
(while (<= from to)
(aset vec (- from start) vcode)
(setq from (1+ from)))))
+ ;; See the comment above.
+ (when (and prev-range-data
+ (>= (cdr (car prev-range-data)) start))
+ (setq from (car (car prev-range-data))
+ to (cdr (car prev-range-data))
+ vcode (cdr prev-range-data))
+ (while (<= from to)
+ (aset vec (- from start) vcode)
+ (setq from (1+ from))))
(setq prev-range-data nil)
(if val-code
(aset vec (- range start) val-code))
(defun unidata-get-decomposition (char val table)
(cond
+ ((not val)
+ (list char))
+
((consp val)
val)
(aset vec idx (nconc word-list tail-list)))
(dotimes (i 128)
(aset table (+ first-char i) (aref vec i)))
- (aref vec (- char first-char)))))
+ (setq val (aref vec (- char first-char)))
+ (or val (list char)))))
;; Hangul syllable
((and (eq val 0) (>= char #xAC00) (<= char #xD7A3))
idx (1+ i)))))
(nreverse (cons (intern (substring str idx)) l))))))
+(defun unidata--ensure-compiled (&rest funcs)
+ (dolist (fun funcs)
+ (or (byte-code-function-p (symbol-function fun))
+ (byte-compile fun))))
+
(defun unidata-gen-table-name (prop &rest ignore)
(let* ((table (unidata-gen-table-word-list prop 'unidata-split-name))
(word-tables (char-table-extra-slot table 4)))
- (byte-compile 'unidata-get-name)
- (byte-compile 'unidata-put-name)
+ (unidata--ensure-compiled 'unidata-get-name 'unidata-put-name)
(set-char-table-extra-slot table 1 (symbol-function 'unidata-get-name))
(set-char-table-extra-slot table 2 (symbol-function 'unidata-put-name))
(defun unidata-gen-table-decomposition (prop &rest ignore)
(let* ((table (unidata-gen-table-word-list prop 'unidata-split-decomposition))
(word-tables (char-table-extra-slot table 4)))
- (byte-compile 'unidata-get-decomposition)
- (byte-compile 'unidata-put-decomposition)
+ (unidata--ensure-compiled 'unidata-get-decomposition
+ 'unidata-put-decomposition)
(set-char-table-extra-slot table 1
(symbol-function 'unidata-get-decomposition))
(set-char-table-extra-slot table 2
;; The entry function. It generates files described in the header
;; comment of this file.
-(defun unidata-gen-files (&optional data-dir unidata-text-file)
+;; Write files (charprop.el, uni-*.el) to dest-dir (default PWD),
+;; using as input files from data-dir, and
+;; unidata-text-file (default "unidata.txt" in PWD).
+(defun unidata-gen-files (&optional data-dir dest-dir unidata-text-file)
(or data-dir
- (setq data-dir (car command-line-args-left)
- command-line-args-left (cdr command-line-args-left)
- unidata-text-file (car command-line-args-left)
- command-line-args-left (cdr command-line-args-left)))
+ (setq data-dir (pop command-line-args-left)
+ dest-dir (or (pop command-line-args-left) default-directory)
+ unidata-text-file (or (pop command-line-args-left)
+ (expand-file-name "unidata.txt"))))
(let ((coding-system-for-write 'utf-8-unix)
- (charprop-file "charprop.el")
+ (charprop-file (expand-file-name "charprop.el" dest-dir))
(unidata-dir data-dir))
(dolist (elt unidata-prop-alist)
(let* ((prop (car elt))
(dolist (elt unidata-prop-alist)
(let* ((prop (car elt))
(generator (unidata-prop-generator prop))
- (file (unidata-prop-file prop))
+ (file (expand-file-name (unidata-prop-file prop) dest-dir))
+ (basename (file-name-nondirectory file))
(docstring (unidata-prop-docstring prop))
(describer (unidata-prop-describer prop))
(default-value (unidata-prop-default prop))
table)
;; Filename in this comment line is extracted by sed in
;; Makefile.
- (insert (format ";; FILE: %s\n" file))
+ (insert (format ";; FILE: %s\n" basename))
(insert (format "(define-char-code-property '%S %S\n %S)\n"
- prop file docstring))
+ prop basename docstring))
(with-temp-buffer
(message "Generating %s..." file)
(when (file-exists-p file)
(setq table (funcall generator prop default-value val-list))
(when describer
(unless (subrp (symbol-function describer))
- (byte-compile describer)
+ (unidata--ensure-compiled describer)
(setq describer (symbol-function describer)))
(set-char-table-extra-slot table 3 describer))
(if (bobp)
- (insert ";; Copyright (C) 1991-2009 Unicode, Inc.
+ (insert ";; Copyright (C) 1991-2013 Unicode, Inc.
;; This file was generated from the Unicode data files at
;; http://www.unicode.org/Public/UNIDATA/.
;; See lisp/international/README for the copyright and permission notice.\n"))
(if (eobp)
(insert ";; Local Variables:\n"
";; coding: utf-8\n"
+ ";; version-control: never\n"
";; no-byte-compile: t\n"
";; End:\n\n"
- (format ";; %s ends here\n" file)))
+ (format ";; %s ends here\n" basename)))
(write-file file)
(message "Generating %s...done" file))))
(message "Writing %s..." charprop-file)
(insert ";; Local Variables:\n"
";; coding: utf-8\n"
+ ";; version-control: never\n"
";; no-byte-compile: t\n"
";; End:\n\n"
- (format ";; %s ends here\n" charprop-file)))))
+ (format ";; %s ends here\n"
+ (file-name-nondirectory charprop-file))))))
\f
HCoop / bpt / emacs.git / blobdiff