(deftype char-code ()
`(integer 0 (,char-code-limit)))
+(defvar *character-database*)
+(declaim (type (simple-array (unsigned-byte 8) (*)) *character-database*))
+
+(macrolet ((frob ()
+ (with-open-file (stream (merge-pathnames
+ (make-pathname
+ :directory
+ '(:relative :up :up "output")
+ :name "ucd"
+ :type "dat")
+ sb!xc:*compile-file-truename*)
+ :direction :input
+ :element-type '(unsigned-byte 8))
+ (let* ((length (file-length stream))
+ (array (make-array length
+ :element-type '(unsigned-byte 8))))
+ (read-sequence array stream)
+ `(defun !character-database-cold-init ()
+ (setq *character-database* ',array))))))
+ (frob))
+#+sb-xc-host (!character-database-cold-init)
+
;;; This is the alist of (character-name . character) for characters
;;; with long names. The first name in this list for a given character
;;; is used on typeout and is the preferred form for input.
(dolist (code char-names-list)
(destructuring-bind (ccode names) code
(dolist (name names)
- (results (cons name (code-char ccode))))))
- `(defparameter *char-name-alist* ',(results)))))
+ (results (cons name ccode)))))
+ `(defparameter *char-name-alist*
+ (mapcar (lambda (x) (cons (car x) (code-char (cdr x))))
+ ',(results))))))
;; Note: The *** markers here indicate character names which are
;; required by the ANSI specification of #'CHAR-NAME. For the others,
;; we prefer the ASCII standard name.
(#x1E ("Rs" "^^"))
(#x1F ("Us" "^_"))
(#x20 ("Space" "Sp")) ; *** See Note above.
- (#x7f ("Rubout" "Delete" "Del"))))) ; *** See Note above.
+ (#x7f ("Rubout" "Delete" "Del"))
+ (#x80 ("C80"))
+ (#x81 ("C81"))
+ (#x82 ("Break-Permitted"))
+ (#x83 ("No-Break-Permitted"))
+ (#x84 ("C84"))
+ (#x85 ("Next-Line"))
+ (#x86 ("Start-Selected-Area"))
+ (#x87 ("End-Selected-Area"))
+ (#x88 ("Character-Tabulation-Set"))
+ (#x89 ("Character-Tabulation-With-Justification"))
+ (#x8A ("Line-Tabulation-Set"))
+ (#x8B ("Partial-Line-Forward"))
+ (#x8C ("Partial-Line-Backward"))
+ (#x8D ("Reverse-Linefeed"))
+ (#x8E ("Single-Shift-Two"))
+ (#x8F ("Single-Shift-Three"))
+ (#x90 ("Device-Control-String"))
+ (#x91 ("Private-Use-One"))
+ (#x92 ("Private-Use-Two"))
+ (#x93 ("Set-Transmit-State"))
+ (#x94 ("Cancel-Character"))
+ (#x95 ("Message-Waiting"))
+ (#x96 ("Start-Guarded-Area"))
+ (#x97 ("End-Guarded-Area"))
+ (#x98 ("Start-String"))
+ (#x99 ("C99"))
+ (#x9A ("Single-Character-Introducer"))
+ (#x9B ("Control-Sequence-Introducer"))
+ (#x9C ("String-Terminator"))
+ (#x9D ("Operating-System-Command"))
+ (#x9E ("Privacy-Message"))
+ (#x9F ("Application-Program-Command"))))) ; *** See Note above.
\f
;;;; accessor functions
+;; (* 8 186) => 1488
+;; (+ 1488 (ash #x110000 -8)) => 5840
+(defun ucd-index (char)
+ (let* ((cp (char-code char))
+ (cp-high (ash cp -8))
+ (page (aref *character-database* (+ 1488 cp-high))))
+ (+ 5840 (ash page 10) (ash (ldb (byte 8 0) cp) 2))))
+
+(defun ucd-value-0 (char)
+ (aref *character-database* (ucd-index char)))
+
+(defun ucd-value-1 (char)
+ (let ((index (ucd-index char)))
+ (dpb (aref *character-database* (+ index 3))
+ (byte 8 16)
+ (dpb (aref *character-database* (+ index 2))
+ (byte 8 8)
+ (aref *character-database* (1+ index))))))
+
+(defun ucd-general-category (char)
+ (aref *character-database* (* 8 (ucd-value-0 char))))
+
+(defun ucd-decimal-digit (char)
+ (let ((decimal-digit (aref *character-database*
+ (+ 3 (* 8 (ucd-value-0 char))))))
+ (when (< decimal-digit 10)
+ decimal-digit)))
+
(defun char-code (char)
#!+sb-doc
"Return the integer code of CHAR."
+ ;; FIXME: do we actually need this?
(etypecase char
- (base-char (char-code (truly-the base-char char)))))
+ (character (char-code (truly-the character char)))))
(defun char-int (char)
#!+sb-doc
(defun code-char (code)
#!+sb-doc
"Return the character with the code CODE."
- (declare (type char-code code))
(code-char code))
(defun character (object)
(defun standard-char-p (char)
#!+sb-doc
- "The argument must be a character object. Standard-char-p returns T if the
+ "The argument must be a character object. STANDARD-CHAR-P returns T if the
argument is a standard character -- one of the 95 ASCII printing characters
or <return>."
- (declare (character char))
(and (typep char 'base-char)
(let ((n (char-code (the base-char char))))
(or (< 31 n 127)
(defun %standard-char-p (thing)
#!+sb-doc
"Return T if and only if THING is a standard-char. Differs from
- standard-char-p in that THING doesn't have to be a character."
+ STANDARD-CHAR-P in that THING doesn't have to be a character."
(and (characterp thing) (standard-char-p thing)))
(defun graphic-char-p (char)
#!+sb-doc
- "The argument must be a character object. Graphic-char-p returns T if the
+ "The argument must be a character object. GRAPHIC-CHAR-P returns T if the
argument is a printing character (space through ~ in ASCII), otherwise
- returns ()."
- (declare (character char))
- (and (typep char 'base-char)
- (< 31
- (char-code (the base-char char))
- 127)))
+ returns NIL."
+ (let ((n (char-code char)))
+ (or (< 31 n 127)
+ (< 159 n))))
(defun alpha-char-p (char)
#!+sb-doc
- "The argument must be a character object. Alpha-char-p returns T if the
- argument is an alphabetic character, A-Z or a-z; otherwise ()."
- (declare (character char))
- (let ((m (char-code char)))
- (or (< 64 m 91) (< 96 m 123))))
+ "The argument must be a character object. ALPHA-CHAR-P returns T if the
+ argument is an alphabetic character, A-Z or a-z; otherwise NIL."
+ (< (ucd-general-category char) 5))
(defun upper-case-p (char)
#!+sb-doc
- "The argument must be a character object; upper-case-p returns T if the
- argument is an upper-case character, () otherwise."
- (declare (character char))
- (< 64
- (char-code char)
- 91))
+ "The argument must be a character object; UPPER-CASE-P returns T if the
+ argument is an upper-case character, NIL otherwise."
+ (= (ucd-value-0 char) 0))
(defun lower-case-p (char)
#!+sb-doc
- "The argument must be a character object; lower-case-p returns T if the
- argument is a lower-case character, () otherwise."
- (declare (character char))
- (< 96
- (char-code char)
- 123))
+ "The argument must be a character object; LOWER-CASE-P returns T if the
+ argument is a lower-case character, NIL otherwise."
+ (= (ucd-value-0 char) 1))
(defun both-case-p (char)
#!+sb-doc
- "The argument must be a character object. Both-case-p returns T if the
+ "The argument must be a character object. BOTH-CASE-P returns T if the
argument is an alphabetic character and if the character exists in
- both upper and lower case. For ASCII, this is the same as Alpha-char-p."
- (declare (character char))
- (let ((m (char-code char)))
- (or (< 64 m 91) (< 96 m 123))))
+ both upper and lower case. For ASCII, this is the same as ALPHA-CHAR-P."
+ (< (ucd-value-0 char) 2))
(defun digit-char-p (char &optional (radix 10.))
#!+sb-doc
"If char is a digit in the specified radix, returns the fixnum for
- which that digit stands, else returns NIL. Radix defaults to 10
- (decimal)."
- (declare (character char) (type (integer 2 36) radix))
+ which that digit stands, else returns NIL."
(let ((m (- (char-code char) 48)))
(declare (fixnum m))
(cond ((<= radix 10.)
;; Also check lower case a - z.
((and (>= (setq m (- m 32)) 10) (< m radix)) m)
;; Else, fail.
- (t nil))))
-
-(defun whitespace-char-p (x)
- (and (characterp x)
- (or (char= x #\space)
- (char= x (code-char tab-char-code))
- (char= x (code-char return-char-code))
- (char= x #\linefeed))))
+ (t (let ((number (ucd-decimal-digit char)))
+ (when (and number (< number radix))
+ number))))))
(defun alphanumericp (char)
#!+sb-doc
- "Given a character-object argument, alphanumericp returns T if the
+ "Given a character-object argument, ALPHANUMERICP returns T if the
argument is either numeric or alphabetic."
- (declare (character char))
- (let ((m (char-code char)))
- (or (< 47 m 58) (< 64 m 91) (< 96 m 123))))
+ (let ((gc (ucd-general-category char)))
+ (or (< gc 5)
+ (= gc 12))))
(defun char= (character &rest more-characters)
#!+sb-doc
"Return T if all of the arguments are the same character."
- (do ((clist more-characters (cdr clist)))
- ((atom clist) T)
- (unless (eq (car clist) character) (return nil))))
+ (dolist (c more-characters t)
+ (declare (type character c))
+ (unless (eq c character) (return nil))))
(defun char/= (character &rest more-characters)
#!+sb-doc
"Return T if no two of the arguments are the same character."
(do* ((head character (car list))
(list more-characters (cdr list)))
- ((atom list) T)
- (unless (do* ((l list (cdr l))) ;inner loop returns T
- ((atom l) T) ; iff head /= rest.
- (if (eq head (car l)) (return nil)))
- (return nil))))
+ ((null list) t)
+ (declare (type character head))
+ (dolist (c list)
+ (declare (type character c))
+ (when (eq head c) (return-from char/= nil)))))
(defun char< (character &rest more-characters)
#!+sb-doc
"Return T if the arguments are in strictly increasing alphabetic order."
(do* ((c character (car list))
(list more-characters (cdr list)))
- ((atom list) T)
+ ((null list) t)
(unless (< (char-int c)
(char-int (car list)))
(return nil))))
"Return T if the arguments are in strictly decreasing alphabetic order."
(do* ((c character (car list))
(list more-characters (cdr list)))
- ((atom list) T)
+ ((null list) t)
(unless (> (char-int c)
(char-int (car list)))
(return nil))))
"Return T if the arguments are in strictly non-decreasing alphabetic order."
(do* ((c character (car list))
(list more-characters (cdr list)))
- ((atom list) T)
+ ((null list) t)
(unless (<= (char-int c)
(char-int (car list)))
(return nil))))
"Return T if the arguments are in strictly non-increasing alphabetic order."
(do* ((c character (car list))
(list more-characters (cdr list)))
- ((atom list) T)
+ ((null list) t)
(unless (>= (char-int c)
(char-int (car list)))
(return nil))))
-;;; Equal-Char-Code is used by the following functions as a version of char-int
+;;; EQUAL-CHAR-CODE is used by the following functions as a version of CHAR-INT
;;; which loses font, bits, and case info.
(defmacro equal-char-code (character)
- `(let ((ch (char-code ,character)))
- (if (< 96 ch 123) (- ch 32) ch)))
+ (let ((ch (gensym)))
+ `(let ((,ch ,character))
+ (if (= (ucd-value-0 ,ch) 0)
+ (ucd-value-1 ,ch)
+ (char-code ,ch)))))
(defun char-equal (character &rest more-characters)
#!+sb-doc
"Return T if all of the arguments are the same character.
Font, bits, and case are ignored."
(do ((clist more-characters (cdr clist)))
- ((atom clist) T)
+ ((null clist) t)
(unless (= (equal-char-code (car clist))
(equal-char-code character))
(return nil))))
Font, bits, and case are ignored."
(do* ((head character (car list))
(list more-characters (cdr list)))
- ((atom list) T)
+ ((null list) t)
(unless (do* ((l list (cdr l)))
- ((atom l) T)
+ ((null l) t)
(if (= (equal-char-code head)
(equal-char-code (car l)))
(return nil)))
Font, bits, and case are ignored."
(do* ((c character (car list))
(list more-characters (cdr list)))
- ((atom list) T)
+ ((null list) t)
(unless (< (equal-char-code c)
(equal-char-code (car list)))
(return nil))))
Font, bits, and case are ignored."
(do* ((c character (car list))
(list more-characters (cdr list)))
- ((atom list) T)
+ ((null list) t)
(unless (> (equal-char-code c)
(equal-char-code (car list)))
(return nil))))
Font, bits, and case are ignored."
(do* ((c character (car list))
(list more-characters (cdr list)))
- ((atom list) T)
+ ((null list) t)
(unless (<= (equal-char-code c)
(equal-char-code (car list)))
(return nil))))
Font, bits, and case are ignored."
(do* ((c character (car list))
(list more-characters (cdr list)))
- ((atom list) T)
+ ((null list) t)
(unless (>= (equal-char-code c)
(equal-char-code (car list)))
(return nil))))
(defun char-upcase (char)
#!+sb-doc
- "Return CHAR converted to upper-case if that is possible."
- (declare (character char))
- (if (lower-case-p char)
- (code-char (- (char-code char) 32))
+ "Return CHAR converted to upper-case if that is possible. Don't convert
+ lowercase eszet (U+DF)."
+ (if (= (ucd-value-0 char) 1)
+ (code-char (ucd-value-1 char))
char))
(defun char-downcase (char)
#!+sb-doc
"Return CHAR converted to lower-case if that is possible."
- (declare (character char))
- (if (upper-case-p char)
- (code-char (+ (char-code char) 32))
+ (if (= (ucd-value-0 char) 0)
+ (code-char (ucd-value-1 char))
char))
(defun digit-char (weight &optional (radix 10))
#!+sb-doc
"All arguments must be integers. Returns a character object that
represents a digit of the given weight in the specified radix. Returns
- NIL if no such character exists. The character will have the specified
- font attributes."
- (declare (type (integer 2 36) radix) (type unsigned-byte weight))
+ NIL if no such character exists."
(and (typep weight 'fixnum)
(>= weight 0) (< weight radix) (< weight 36)
(code-char (if (< weight 10) (+ 48 weight) (+ 55 weight)))))