X-Git-Url: http://repo.macrolet.net/gitweb/?a=blobdiff_plain;f=src%2Fcode%2Ftarget-char.lisp;h=ad0f9ee0df697108ee81b981d8a53f08368f94d9;hb=d10b036b1d20e6cff820f72b69af2a06dc362327;hp=4be9e8376bc3485de4a4570d2f4c4fb111c358fc;hpb=0a535fd0f5db046624b05aa956395d3b502ec927;p=sbcl.git diff --git a/src/code/target-char.lisp b/src/code/target-char.lisp index 4be9e83..ad0f9ee 100644 --- a/src/code/target-char.lisp +++ b/src/code/target-char.lisp @@ -25,68 +25,187 @@ ;;; We compile some trivial character operations via inline expansion. #!-sb-fluid (declaim (inline standard-char-p graphic-char-p alpha-char-p - upper-case-p lower-case-p both-case-p alphanumericp - char-int)) + upper-case-p lower-case-p both-case-p alphanumericp + char-int)) (declaim (maybe-inline digit-char-p digit-weight)) (deftype char-code () `(integer 0 (,char-code-limit))) -;;; 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. -(macrolet ((frob (char-names-list) - (collect ((results)) - (dolist (code char-names-list) - (destructuring-bind (ccode names) code - (dolist (name names) - (results (cons name (code-char ccode)))))) - `(defparameter *char-name-alist* ',(results))))) +(defvar *character-database*) +(declaim (type (simple-array (unsigned-byte 8) (*)) *character-database*)) + +#!+sb-unicode +(progn + (defvar *unicode-character-name-database*) + (defvar *unicode-character-name-huffman-tree*)) + +(macrolet ((frob () + (flet ((file (name type) + (merge-pathnames (make-pathname + :directory + '(:relative :up :up "output") + :name name :type type) + sb!xc:*compile-file-truename*))) + `(progn + ,(with-open-file (stream (file "ucd" "dat") + :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)))) + ,(with-open-file (stream (file "ucd-names" "lisp-expr") + :direction :input + :element-type 'character) + (let ((names (make-hash-table))) + #!+sb-unicode + (loop + for code-point = (read stream nil nil) + for char-name = (string-upcase (read stream nil nil)) + while code-point + do (setf (gethash code-point names) char-name)) + (let ((tree + #!+sb-unicode + (make-huffman-tree + (let (list) + (maphash (lambda (code name) + (declare (ignore code)) + (push name list)) + names) + list))) + (code->name + (make-array (hash-table-count names) + :fill-pointer 0)) + (name->code nil)) + (maphash (lambda (code name) + (vector-push + (cons code (huffman-encode name tree)) + code->name)) + names) + (setf name->code + (sort (copy-seq code->name) #'< :key #'cdr)) + (setf code->name + (sort (copy-seq name->code) #'< :key #'car)) + (setf names nil) + `(defun !character-name-database-cold-init () + #!+sb-unicode + (setq *unicode-character-name-database* + (cons ',code->name ',name->code) + *unicode-character-name-huffman-tree* ',tree))))))))) + (frob)) +#+sb-xc-host (!character-database-cold-init) +#+sb-xc-host (!character-name-database-cold-init) + +(defparameter *base-char-name-alist* ;; 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. - (frob ((#x00 ("Nul" "Null" "^@")) - (#x01 ("Soh" "^a")) - (#x02 ("Stx" "^b")) - (#x03 ("Etx" "^c")) - (#x04 ("Eot" "^d")) - (#x05 ("Enq" "^e")) - (#x06 ("Ack" "^f")) - (#x07 ("Bel" "Bell" "^g")) - (#x08 ("Backspace" "^h" "Bs")) ; *** See Note above. - (#x09 ("Tab" "^i" "Ht")) ; *** See Note above. - (#x0A ("Newline" "Linefeed" "^j" "Lf" "Nl" )) ; *** See Note above. - (#x0B ("Vt" "^k")) - (#x0C ("Page" "^l" "Form" "Formfeed" "Ff" "Np")) ; *** See Note above. - (#x0D ("Return" "^m" "Cr")) ; *** See Note above. - (#x0E ("So" "^n")) - (#x0F ("Si" "^o")) - (#x10 ("Dle" "^p")) - (#x11 ("Dc1" "^q")) - (#x12 ("Dc2" "^r")) - (#x13 ("Dc3" "^s")) - (#x14 ("Dc4" "^t")) - (#x15 ("Nak" "^u")) - (#x16 ("Syn" "^v")) - (#x17 ("Etb" "^w")) - (#x18 ("Can" "^x")) - (#x19 ("Em" "^y")) - (#x1A ("Sub" "^z")) - (#x1B ("Esc" "Escape" "^[" "Altmode" "Alt")) - (#x1C ("Fs" "^\\")) - (#x1D ("Gs" "^]")) - (#x1E ("Rs" "^^")) - (#x1F ("Us" "^_")) - (#x20 ("Space" "Sp")) ; *** See Note above. - (#x7f ("Rubout" "Delete" "Del"))))) ; *** See Note above. + '((#x00 "Nul" "Null" "^@") + (#x01 "Soh" "^a") + (#x02 "Stx" "^b") + (#x03 "Etx" "^c") + (#x04 "Eot" "^d") + (#x05 "Enq" "^e") + (#x06 "Ack" "^f") + (#x07 "Bel" "Bell" "^g") + (#x08 "Backspace" "^h" "Bs") ; *** See Note above + (#x09 "Tab" "^i" "Ht") ; *** See Note above + (#x0A "Newline" "Linefeed" "^j" "Lf" "Nl") ; *** See Note above + (#x0B "Vt" "^k") + (#x0C "Page" "^l" "Form" "Formfeed" "Ff" "Np") ; *** See Note above + (#x0D "Return" "^m" "Cr") ; *** See Note above + (#x0E "So" "^n") + (#x0F "Si" "^o") + (#x10 "Dle" "^p") + (#x11 "Dc1" "^q") + (#x12 "Dc2" "^r") + (#x13 "Dc3" "^s") + (#x14 "Dc4" "^t") + (#x15 "Nak" "^u") + (#x16 "Syn" "^v") + (#x17 "Etb" "^w") + (#x18 "Can" "^x") + (#x19 "Em" "^y") + (#x1A "Sub" "^z") + (#x1B "Esc" "Escape" "^[" "Altmode" "Alt") + (#x1C "Fs" "^\\") + (#x1D "Gs" "^]") + (#x1E "Rs" "^^") + (#x1F "Us" "^_") + (#x20 "Space" "Sp") ; *** 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 ;;;; 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 @@ -101,37 +220,74 @@ (defun character (object) #!+sb-doc - "Coerce OBJECT into a CHARACTER if possible. Legal inputs are + "Coerce OBJECT into a CHARACTER if possible. Legal inputs are characters, strings and symbols of length 1." (flet ((do-error (control args) - (error 'simple-type-error - :datum object - ;;?? how to express "symbol with name of length 1"? - :expected-type '(or character (string 1)) - :format-control control - :format-arguments args))) + (error 'simple-type-error + :datum object + ;;?? how to express "symbol with name of length 1"? + :expected-type '(or character (string 1)) + :format-control control + :format-arguments args))) (typecase object (character object) (string (if (= 1 (length (the string object))) - (char object 0) - (do-error - "String is not of length one: ~S" (list object)))) + (char object 0) + (do-error + "String is not of length one: ~S" (list object)))) (symbol (if (= 1 (length (symbol-name object))) - (schar (symbol-name object) 0) - (do-error - "Symbol name is not of length one: ~S" (list object)))) + (schar (symbol-name object) 0) + (do-error + "Symbol name is not of length one: ~S" (list object)))) (t (do-error "~S cannot be coerced to a character." (list object)))))) (defun char-name (char) #!+sb-doc "Return the name (a STRING) for a CHARACTER object." - (car (rassoc char *char-name-alist*))) + (let ((char-code (char-code char))) + (or (second (assoc char-code *base-char-name-alist*)) + #!+sb-unicode + (let ((h-code (cdr (binary-search char-code + (car *unicode-character-name-database*) + :key #'car)))) + (cond + (h-code + (huffman-decode h-code *unicode-character-name-huffman-tree*)) + ((< char-code #x10000) + (format nil "U~4,'0X" char-code)) + (t + (format nil "U~8,'0X" char-code))))))) (defun name-char (name) #!+sb-doc "Given an argument acceptable to STRING, NAME-CHAR returns a character whose name is that string, if one exists. Otherwise, NIL is returned." - (cdr (assoc (string name) *char-name-alist* :test #'string-equal))) + (or (let ((char-code (car (rassoc-if (lambda (names) + (member name names :test #'string-equal)) + *base-char-name-alist*)))) + (when char-code + (code-char char-code))) + #!+sb-unicode + (let ((encoding (huffman-encode (string-upcase name) + *unicode-character-name-huffman-tree*))) + (when encoding + (let* ((char-code + (car (binary-search encoding + (cdr *unicode-character-name-database*) + :key #'cdr))) + (name-string (string name)) + (name-length (length name-string))) + (cond + (char-code + (code-char char-code)) + ((and (or (= name-length 9) + (= name-length 5)) + (char-equal (char name-string 0) #\U) + (loop for i from 1 below name-length + always (digit-char-p (char name-string i) 16))) + (code-char (parse-integer name-string :start 1 :radix 16))) + (t + nil))))))) ;;;; predicates @@ -142,8 +298,8 @@ or ." (and (typep char 'base-char) (let ((n (char-code (the base-char char)))) - (or (< 31 n 127) - (= n 10))))) + (or (< 31 n 127) + (= n 10))))) (defun %standard-char-p (thing) #!+sb-doc @@ -156,41 +312,34 @@ "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 NIL." - (and (typep char 'base-char) - (< 31 - (char-code (the base-char char)) - 127))) + (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 NIL." - (let ((m (char-code char))) - (or (< 64 m 91) (< 96 m 123)))) + (< (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, NIL otherwise." - (< 64 - (char-code char) - 91)) + (= (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, NIL otherwise." - (< 96 - (char-code char) - 123)) + (= (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 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." - (let ((m (char-code char))) - (or (< 64 m 91) (< 96 m 123)))) + (< (ucd-value-0 char) 2)) (defun digit-char-p (char &optional (radix 10.)) #!+sb-doc @@ -199,30 +348,26 @@ (let ((m (- (char-code char) 48))) (declare (fixnum m)) (cond ((<= radix 10.) - ;; Special-case decimal and smaller radices. - (if (and (>= m 0) (< m radix)) m nil)) - ;; Digits 0 - 9 are used as is, since radix is larger. - ((and (>= m 0) (< m 10)) m) - ;; Check for upper case A - Z. - ((and (>= (setq m (- m 7)) 10) (< m radix)) m) - ;; 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)))) + ;; Special-case decimal and smaller radices. + (if (and (>= m 0) (< m radix)) m nil)) + ;; Digits 0 - 9 are used as is, since radix is larger. + ((and (>= m 0) (< m 10)) m) + ;; Check for upper case A - Z. + ((and (>= (setq m (- m 7)) 10) (< m radix)) m) + ;; Also check lower case a - z. + ((and (>= (setq m (- m 32)) 10) (< m radix)) m) + ;; Else, fail. + (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 argument is either numeric or alphabetic." - (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 @@ -235,7 +380,7 @@ #!+sb-doc "Return T if no two of the arguments are the same character." (do* ((head character (car list)) - (list more-characters (cdr list))) + (list more-characters (cdr list))) ((null list) t) (declare (type character head)) (dolist (c list) @@ -246,48 +391,54 @@ #!+sb-doc "Return T if the arguments are in strictly increasing alphabetic order." (do* ((c character (car list)) - (list more-characters (cdr list))) + (list more-characters (cdr list))) ((null list) t) (unless (< (char-int c) - (char-int (car list))) + (char-int (car list))) (return nil)))) (defun char> (character &rest more-characters) #!+sb-doc "Return T if the arguments are in strictly decreasing alphabetic order." (do* ((c character (car list)) - (list more-characters (cdr list))) + (list more-characters (cdr list))) ((null list) t) (unless (> (char-int c) - (char-int (car list))) + (char-int (car list))) (return nil)))) (defun char<= (character &rest more-characters) #!+sb-doc "Return T if the arguments are in strictly non-decreasing alphabetic order." (do* ((c character (car list)) - (list more-characters (cdr list))) + (list more-characters (cdr list))) ((null list) t) (unless (<= (char-int c) - (char-int (car list))) + (char-int (car list))) (return nil)))) (defun char>= (character &rest more-characters) #!+sb-doc "Return T if the arguments are in strictly non-increasing alphabetic order." (do* ((c character (car list)) - (list more-characters (cdr list))) + (list more-characters (cdr list))) ((null list) t) (unless (>= (char-int c) - (char-int (car list))) + (char-int (car list))) (return nil)))) ;;; 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 two-arg-char-equal (c1 c2) + (= (equal-char-code c1) (equal-char-code c2))) (defun char-equal (character &rest more-characters) #!+sb-doc @@ -295,82 +446,92 @@ Font, bits, and case are ignored." (do ((clist more-characters (cdr clist))) ((null clist) t) - (unless (= (equal-char-code (car clist)) - (equal-char-code character)) + (unless (two-arg-char-equal (car clist) character) (return nil)))) +(defun two-arg-char-not-equal (c1 c2) + (/= (equal-char-code c1) (equal-char-code c2))) + (defun char-not-equal (character &rest more-characters) #!+sb-doc "Return T if no two of the arguments are the same character. Font, bits, and case are ignored." (do* ((head character (car list)) - (list more-characters (cdr list))) + (list more-characters (cdr list))) ((null list) t) (unless (do* ((l list (cdr l))) - ((null l) t) - (if (= (equal-char-code head) - (equal-char-code (car l))) - (return nil))) + ((null l) t) + (if (two-arg-char-equal head (car l)) + (return nil))) (return nil)))) +(defun two-arg-char-lessp (c1 c2) + (< (equal-char-code c1) (equal-char-code c2))) + (defun char-lessp (character &rest more-characters) #!+sb-doc "Return T if the arguments are in strictly increasing alphabetic order. Font, bits, and case are ignored." (do* ((c character (car list)) - (list more-characters (cdr list))) + (list more-characters (cdr list))) ((null list) t) - (unless (< (equal-char-code c) - (equal-char-code (car list))) + (unless (two-arg-char-lessp c (car list)) (return nil)))) +(defun two-arg-char-greaterp (c1 c2) + (> (equal-char-code c1) (equal-char-code c2))) + (defun char-greaterp (character &rest more-characters) #!+sb-doc "Return T if the arguments are in strictly decreasing alphabetic order. Font, bits, and case are ignored." (do* ((c character (car list)) - (list more-characters (cdr list))) + (list more-characters (cdr list))) ((null list) t) - (unless (> (equal-char-code c) - (equal-char-code (car list))) + (unless (two-arg-char-greaterp c (car list)) (return nil)))) +(defun two-arg-char-not-greaterp (c1 c2) + (<= (equal-char-code c1) (equal-char-code c2))) + (defun char-not-greaterp (character &rest more-characters) #!+sb-doc "Return T if the arguments are in strictly non-decreasing alphabetic order. Font, bits, and case are ignored." (do* ((c character (car list)) - (list more-characters (cdr list))) + (list more-characters (cdr list))) ((null list) t) - (unless (<= (equal-char-code c) - (equal-char-code (car list))) + (unless (two-arg-char-not-greaterp c (car list)) (return nil)))) +(defun two-arg-char-not-lessp (c1 c2) + (>= (equal-char-code c1) (equal-char-code c2))) + (defun char-not-lessp (character &rest more-characters) #!+sb-doc "Return T if the arguments are in strictly non-increasing alphabetic order. Font, bits, and case are ignored." (do* ((c character (car list)) - (list more-characters (cdr list))) + (list more-characters (cdr list))) ((null list) t) - (unless (>= (equal-char-code c) - (equal-char-code (car list))) + (unless (two-arg-char-not-lessp c (car list)) (return nil)))) ;;;; miscellaneous functions (defun char-upcase (char) #!+sb-doc - "Return CHAR converted to upper-case if that is possible." - (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." - (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))