;;;; character functions
-;;;;
-;;;; This implementation assumes the use of ASCII codes and the
-;;;; specific character formats used in SBCL (and its ancestor, CMU
-;;;; CL). It is optimized for performance rather than for portability
-;;;; and elegance, and may have to be rewritten if the character
-;;;; representation is changed.
-;;;;
-;;;; KLUDGE: As of sbcl-0.6.11.25, at least, the ASCII-dependence is
-;;;; not confined to this file. E.g. there are DEFTRANSFORMs in
-;;;; srctran.lisp for CHAR-UPCASE, CHAR-EQUAL, and CHAR-DOWNCASE, and
-;;;; they assume ASCII. -- WHN 2001-03-25
;;;; This software is part of the SBCL system. See the README file for
;;;; more information.
(deftype char-code ()
`(integer 0 (,char-code-limit)))
-(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)))))))))
+(macrolet
+ ((frob ()
+ (flet ((file (name type)
+ (merge-pathnames (make-pathname
+ :directory
+ '(:relative :up :up "output")
+ :name name :type type)
+ sb!xc:*compile-file-truename*))
+ (read-ub8-vector (pathname)
+ (with-open-file (stream pathname
+ :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)
+ array))))
+ (let ((character-database (read-ub8-vector (file "ucd" "dat")))
+ (decompositions (read-ub8-vector (file "decomp" "dat")))
+ (long-decompositions (read-ub8-vector (file "ldecomp" "dat"))))
+ `(progn
+ (declaim (type (simple-array (unsigned-byte 8) (*)) **character-database** **character-decompositions** **character-long-decompositions**))
+ (defglobal **character-database** ,character-database)
+ (defglobal **character-decompositions** ,decompositions)
+ (defglobal **character-long-decompositions** ,long-decompositions)
+ (defun !character-database-cold-init ()
+ (setf **character-database** ,character-database))
+ ,(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*
(#x9E "Privacy-Message")
(#x9F "Application-Program-Command"))) ; *** See Note above
\f
-;;;; accessor functions
-
-;; (* 8 186) => 1488
-;; (+ 1488 (ash #x110000 -8)) => 5840
+;;;; UCD accessor functions
+
+;;; The first (* 8 395) => 3160 entries in **CHARACTER-DATABASE**
+;;; contain entries for the distinct character attributes:
+;;; specifically, indexes into the GC kinds, Bidi kinds, CCC kinds,
+;;; the decimal digit property, the digit property and the
+;;; bidi-mirrored boolean property. (There are two spare bytes for
+;;; other information, should that become necessary)
+;;;
+;;; the next (ash #x110000 -8) entries contain single-byte indexes
+;;; into a table of 256-element 4-byte-sized entries. These entries
+;;; follow directly on, and are of the form
+;;; {attribute-index[11b],transformed-code-point[21b]}x256, where the
+;;; attribute index is an index into the miscellaneous information
+;;; table, and the transformed code point is the code point of the
+;;; simple mapping of the character to its lowercase or uppercase
+;;; equivalent, as appropriate and if any.
+;;;
+;;; I feel the opacity of the above suggests the need for a diagram:
+;;;
+;;; C _______________________________________
+;;; / \
+;;; L \
+;;; [***************|=============================|--------...]
+;;; (a) \ _
+;;; A \______________________/| B
+;;;
+;;; To look up information about a character, take the high 13 bits of
+;;; its code point, and index the character database with that and a
+;;; base of 3160 (going past the miscellaneous information[*], so
+;;; treating (a) as the start of the array). This, labelled A, gives
+;;; us another index into the detailed pages[-], which we can use to
+;;; look up the details for the character in question: we add the low
+;;; 8 bits of the character, shifted twice (because we have four-byte
+;;; table entries) to 1024 times the `page' index, with a base of 6088
+;;; to skip over everything else. This gets us to point B. If we're
+;;; after a transformed code point (i.e. an upcase or downcase
+;;; operation), we can simply read it off now, beginning with an
+;;; offset of 11 bits from point B in some endianness; if we're
+;;; looking for miscellaneous information, we take the 11-bit value at
+;;; B, and index the character database once more to get to the
+;;; relevant miscellaneous information.
+;;;
+;;; As an optimization to the common case (pun intended) of looking up
+;;; case information for a character, the entries in C above are
+;;; sorted such that the characters which are UPPER-CASE-P in CL terms
+;;; have index values lower than all others, followed by those which
+;;; are LOWER-CASE-P in CL terms; this permits implementation of
+;;; character case tests without actually going to the trouble of
+;;; looking up the value associated with the index. (Actually, this
+;;; isn't just a speed optimization; the information about whether a
+;;; character is BOTH-CASE-P is used just in the ordering and not
+;;; explicitly recorded in the database).
+;;;
+;;; The moral of all this? Next time, don't just say "FIXME: document
+;;; this"
(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))))
+ (page (aref **character-database** (+ 3160 cp-high))))
+ (+ 7512 (ash page 10) (ash (ldb (byte 8 0) cp) 2))))
+(declaim (ftype (sfunction (t) (unsigned-byte 11)) ucd-value-0))
(defun ucd-value-0 (char)
- (aref *character-database* (ucd-index char)))
+ (let ((index (ucd-index char))
+ (character-database **character-database**))
+ (dpb (aref character-database index)
+ (byte 8 3)
+ (ldb (byte 3 5) (aref character-database (+ index 1))))))
+(declaim (ftype (sfunction (t) (unsigned-byte 21)) ucd-value-1))
(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))
+ (let ((index (ucd-index char))
+ (character-database **character-database**))
+ (dpb (aref character-database (+ index 1))
+ (byte 5 16)
+ (dpb (aref character-database (+ index 2))
(byte 8 8)
- (aref *character-database* (1+ index))))))
+ (aref character-database (+ index 3))))))
+(declaim (ftype (sfunction (t) (unsigned-byte 8)) ucd-general-category))
(defun ucd-general-category (char)
- (aref *character-database* (* 8 (ucd-value-0 char))))
+ (aref **character-database** (* 8 (ucd-value-0 char))))
(defun ucd-decimal-digit (char)
- (let ((decimal-digit (aref *character-database*
+ (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
- (character (char-code (truly-the character char)))))
+ (char-code char))
(defun char-int (char)
#!+sb-doc
"Return the integer code of CHAR. (In SBCL this is the same as CHAR-CODE, as
- there are no character bits or fonts.)"
+there are no character bits or fonts.)"
(char-code char))
(defun code-char (code)
(defun character (object)
#!+sb-doc
- "Coerce OBJECT into a CHARACTER if possible. Legal inputs are
- characters, strings and symbols of length 1."
+ "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
(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."
+ "Given an argument acceptable to STRING, NAME-CHAR returns a character whose
+name is that string, if one exists. Otherwise, NIL is returned."
(or (let ((char-code (car (rassoc-if (lambda (names)
(member name names :test #'string-equal))
*base-char-name-alist*))))
(defun standard-char-p (char)
#!+sb-doc
"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>."
+argument is a standard character -- one of the 95 ASCII printing characters or
+<return>."
(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
- argument is a printing character (space through ~ in ASCII), otherwise
- returns NIL."
+argument is a printing character (space through ~ in ASCII), otherwise 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 NIL."
+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, NIL otherwise."
- (= (ucd-value-0 char) 0))
+argument is an upper-case character, NIL otherwise."
+ (< (ucd-value-0 char) 4))
(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."
- (= (ucd-value-0 char) 1))
+argument is a lower-case character, NIL otherwise."
+ (< 3 (ucd-value-0 char) 8))
(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."
- (< (ucd-value-0 char) 2))
+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."
+ (< (ucd-value-0 char) 8))
(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."
+ "If char is a digit in the specified radix, returns the fixnum for which
+that digit stands, else returns NIL."
(let ((m (- (char-code char) 48)))
(declare (fixnum m))
(cond ((<= radix 10.)
(defun alphanumericp (char)
#!+sb-doc
- "Given a character-object argument, ALPHANUMERICP returns T if the
- argument is either numeric or alphabetic."
+ "Given a character-object argument, ALPHANUMERICP returns T if the argument
+is either numeric or alphabetic."
(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."
- (declare (dynamic-extent more-characters))
+ (declare (truly-dynamic-extent more-characters))
(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."
- (declare (dynamic-extent more-characters))
+ (declare (truly-dynamic-extent more-characters))
(do* ((head character (car list))
(list more-characters (cdr list)))
((null list) t)
(defun char< (character &rest more-characters)
#!+sb-doc
"Return T if the arguments are in strictly increasing alphabetic order."
- (declare (dynamic-extent more-characters))
+ (declare (truly-dynamic-extent more-characters))
(do* ((c character (car list))
(list more-characters (cdr list)))
((null list) t)
(defun char> (character &rest more-characters)
#!+sb-doc
"Return T if the arguments are in strictly decreasing alphabetic order."
- (declare (dynamic-extent more-characters))
+ (declare (truly-dynamic-extent more-characters))
(do* ((c character (car list))
(list more-characters (cdr list)))
((null list) t)
(defun char<= (character &rest more-characters)
#!+sb-doc
"Return T if the arguments are in strictly non-decreasing alphabetic order."
- (declare (dynamic-extent more-characters))
+ (declare (truly-dynamic-extent more-characters))
(do* ((c character (car list))
(list more-characters (cdr list)))
((null list) t)
(defun char>= (character &rest more-characters)
#!+sb-doc
"Return T if the arguments are in strictly non-increasing alphabetic order."
- (declare (dynamic-extent more-characters))
+ (declare (truly-dynamic-extent more-characters))
(do* ((c character (car list))
(list more-characters (cdr list)))
((null list) t)
(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."
- (declare (dynamic-extent more-characters))
+Case is ignored."
+ (declare (truly-dynamic-extent more-characters))
(do ((clist more-characters (cdr clist)))
((null clist) t)
(unless (two-arg-char-equal (car clist) character)
(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."
- (declare (dynamic-extent more-characters))
+Case is ignored."
+ (declare (truly-dynamic-extent more-characters))
(do* ((head character (car list))
(list more-characters (cdr list)))
((null list) t)
(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."
- (declare (dynamic-extent more-characters))
+Case is ignored."
+ (declare (truly-dynamic-extent more-characters))
(do* ((c character (car list))
(list more-characters (cdr list)))
((null list) t)
(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."
- (declare (dynamic-extent more-characters))
+Case is ignored."
+ (declare (truly-dynamic-extent more-characters))
(do* ((c character (car list))
(list more-characters (cdr list)))
((null list) t)
(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."
- (declare (dynamic-extent more-characters))
+Case is ignored."
+ (declare (truly-dynamic-extent more-characters))
(do* ((c character (car list))
(list more-characters (cdr list)))
((null list) t)
(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."
- (declare (dynamic-extent more-characters))
+Case is ignored."
+ (declare (truly-dynamic-extent more-characters))
(do* ((c character (car list))
(list more-characters (cdr list)))
((null list) t)
(defun char-upcase (char)
#!+sb-doc
- "Return CHAR converted to upper-case if that is possible. Don't convert
- lowercase eszet (U+DF)."
- (if (= (ucd-value-0 char) 1)
+ "Return CHAR converted to upper-case if that is possible. Don't convert
+lowercase eszet (U+DF)."
+ (if (< 3 (ucd-value-0 char) 8)
(code-char (ucd-value-1 char))
char))
(defun char-downcase (char)
#!+sb-doc
"Return CHAR converted to lower-case if that is possible."
- (if (= (ucd-value-0 char) 0)
+ (if (< (ucd-value-0 char) 4)
(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."
+ "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."
(and (typep weight 'fixnum)
(>= weight 0) (< weight radix) (< weight 36)
(code-char (if (< weight 10) (+ 48 weight) (+ 55 weight)))))
+\f
+(defun char-decomposition-info (char)
+ (aref **character-database** (+ 6 (* 8 (ucd-value-0 char)))))
+
+(defun char-decomposition (char)
+ (let* ((cp (char-code char))
+ (cp-high (ash cp -8))
+ (decompositions **character-decompositions**)
+ (long-decompositions **character-long-decompositions**)
+ (index (+ #x1100
+ (ash (aref decompositions cp-high) 10)
+ (ash (ldb (byte 8 0) cp) 2)))
+ (v0 (aref decompositions index))
+ (v1 (aref decompositions (+ index 1)))
+ (v2 (aref decompositions (+ index 2)))
+ (v3 (aref decompositions (+ index 3)))
+ (length (dpb v0 (byte 8 3) (ldb (byte 3 5) v1)))
+ (entry (dpb (ldb (byte 5 0) v1) (byte 5 16)
+ (dpb v2 (byte 8 8) v3))))
+ (if (= length 1)
+ (string (code-char entry))
+ (let ((result (make-string length))
+ (e (* 4 entry)))
+ (dotimes (i length result)
+ (let ((code (dpb (aref long-decompositions (+ e 1))
+ (byte 8 16)
+ (dpb (aref long-decompositions (+ e 2))
+ (byte 8 8)
+ (aref long-decompositions (+ e 3))))))
+ (setf (char result i) (code-char code)))
+ (incf e 4))))))
+
+(defun decompose-char (char)
+ (if (= (char-decomposition-info char) 0)
+ (string char)
+ (char-decomposition char)))
projects / sbcl.git / blobdiff