From 898ced2a4d1f2503f3447f6408ddf5b05a906261 Mon Sep 17 00:00:00 2001 From: William Harold Newman Date: Wed, 12 Dec 2001 19:18:38 +0000 Subject: [PATCH] 0.pre7.89: (gave in to the temptation to check in a version which had only been "rebuilt" with slam.sh, not full make.sh) changed default CHAR-NAME of unprintable ASCII characters not specified in the ANSI standard to #\Nul, #\Soh, etc. --- NEWS | 9 +++-- TODO | 6 +-- src/code/target-char.lisp | 91 +++++++++++++++++++++++---------------------- tests/character.pure.lisp | 37 ++++++++++++++++++ version.lisp-expr | 2 +- 5 files changed, 92 insertions(+), 53 deletions(-) create mode 100644 tests/character.pure.lisp diff --git a/NEWS b/NEWS index 0336a7a..7ecaf9e 100644 --- a/NEWS +++ b/NEWS @@ -914,10 +914,11 @@ changes in sbcl-0.7.0 relative to sbcl-0.6.13: ILISP and SBCL left me very deeply nested in the debugger. In the short term, this change will probably provoke more ILISP/SBCL squabbles, but hopefully it will be an improvement in the long run.) -?? minor incompatible change: The default output representation for - unprintable ASCII characters which, unlike e.g. #\Newline, don't - have names defined in the ANSI Common Lisp standard, is now based - on their ASCII symbolic names: #\Nul, #\Soh, #\Stx, etc. +* minor incompatible change: The CHAR-NAME of unprintable ASCII + characters which, unlike e.g. #\Newline and #\Tab, don't have names + specified in the ANSI Common Lisp standard, is now based on their + ASCII symbolic names (#\Nul, #\Soh, #\Stx, etc.) The old CMU CL + names (#\Null, #\^a, #\^b, etc.) are still accepted by NAME-CHAR. ?? Old operator names in the style DEF-FOO are now deprecated in favor of new corresponding names DEFINE-FOO, for consistency with the naming convention used in the ANSI standard (DEFSTRUCT, DEFVAR, diff --git a/TODO b/TODO index 303b744..31dac18 100644 --- a/TODO +++ b/TODO @@ -5,9 +5,9 @@ for 0.7.0: leaving some filing for later:-) from the monster EVAL/EVAL-WHEN/%COMPILE/DEFUN/DEFSTRUCT cleanup: ** made inlining DEFUN inside MACROLET work again -* incompatible changes listed in NEWS: - ** changed default output representation of *PRINT-ESCAPE*-ed - unprintable ASCII characters to #\Nul, #\Soh, etc. + ** (SB-DEBUG:BACKTRACE) output should start with something + including the name BACKTRACE, not (as in 0.pre7.88) + just "0: (\"hairy arg processor\" ...)" * more renaming in global external names: ** used DEFINE-THE-FOO-THING and DEFFOO style consistently (and deprecated supported extensions named in the DEF-FOO diff --git a/src/code/target-char.lisp b/src/code/target-char.lisp index 0437cc3..68f3948 100644 --- a/src/code/target-char.lisp +++ b/src/code/target-char.lisp @@ -32,51 +32,53 @@ (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) - #!+sb-doc - "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.")))) - (frob ((#x00 ("Null" "^@" "Nul")) - (#x01 ("^a" "Soh")) - (#x02 ("^b" "Stx")) - (#x03 ("^c" "Etx")) - (#x04 ("^d" "Eot")) - (#x05 ("^e" "Enq")) - (#x06 ("^f" "Ack")) - (#x07 ("Bell" "^g" "Bel")) - (#x08 ("Backspace" "^h" "Bs")) - (#x09 ("Tab" "^i" "Ht")) - (#x0A ("Newline" "Linefeed" "^j" "Lf" "Nl" )) + `(defparameter *char-name-alist* ',(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. + (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")) - (#x0D ("Return" "^m" "Cr")) - (#x0E ("^n" "So")) - (#x0F ("^o" "Si")) - (#x10 ("^p" "Dle")) - (#x11 ("^q" "Dc1")) - (#x12 ("^r" "Dc2")) - (#x13 ("^s" "Dc3")) - (#x14 ("^t" "Dc4")) - (#x15 ("^u" "Nak")) - (#x16 ("^v" "Syn")) - (#x17 ("^w" "Etb")) - (#x18 ("^x" "Can")) - (#x19 ("^y" "Em")) - (#x1A ("^z" "Sub")) - (#x1B ("Escape" "^[" "Altmode" "Esc" "Alt")) - (#x1C ("^\\" "Fs")) - (#x1D ("^]" "Gs")) - (#x1E ("^^" "Rs")) - (#x1F ("^_" "Us")) - (#x20 ("Space" "Sp")) - (#x7f ("Rubout" "Delete" "Del"))))) + (#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. ;;;; accessor functions @@ -88,8 +90,8 @@ (defun char-int (char) #!+sb-doc - "Return the integer code of CHAR. This is the same as char-code, as - CMU Common Lisp does not implement character bits or fonts." + "Return the integer code of CHAR. (In SBCL this is the same as CHAR-CODE, as + there are no character bits or fonts.)" (char-code char)) (defun code-char (code) @@ -100,7 +102,7 @@ (defun character (object) #!+sb-doc - "Coerces its argument into a character object if possible. Accepts + "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 @@ -123,14 +125,13 @@ (defun char-name (char) #!+sb-doc - "Given a character object, char-name returns the name for that - object (a symbol)." + "Return the name (a STRING) for a CHARACTER object." (car (rassoc char *char-name-alist*))) (defun name-char (name) #!+sb-doc - "Given an argument acceptable to string, name-char returns a character - object whose name is that symbol, if one exists. Otherwise, () 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." (cdr (assoc (string name) *char-name-alist* :test #'string-equal))) ;;;; predicates diff --git a/tests/character.pure.lisp b/tests/character.pure.lisp new file mode 100644 index 0000000..cc6f397 --- /dev/null +++ b/tests/character.pure.lisp @@ -0,0 +1,37 @@ +;;;; various CHARACTER tests without side-effects + +;;;; This software is part of the SBCL system. See the README file for +;;;; more information. +;;;; +;;;; While most of SBCL is derived from the CMU CL system, the test +;;;; files (like this one) were written from scratch after the fork +;;;; from CMU CL. +;;;; +;;;; This software is in the public domain and is provided with +;;;; absolutely no warranty. See the COPYING and CREDITS files for +;;;; more information. + +(cl:in-package :cl-user) + +;;; ANSI's specification of #'CHAR-NAME imposes these constraints. +;;; +;;; (Obviously, the numeric values in this test implicitly assume +;;; we're using an ASCII-based character set.) +(dolist (i '(("Newline" 10) + ;; (ANSI also imposes a constraint on the "semi-standard + ;; character" "Linefeed", but in ASCII as interpreted by + ;; Unix it's shadowed by "Newline" and so doesn't exist + ;; as a separate character.) + ("Space" 32) + ("Tab" 9) + ("Page" 12) + ("Rubout" 127) + ("Return" 13) + ("Backspace" 8))) + (destructuring-bind (name code) i + (let ((named-char (name-char name)) + (coded-char (code-char code))) + (assert (eql named-char coded-char)) + (assert (characterp named-char)) + (let ((coded-char-name (char-name coded-char))) + (assert (string= name coded-char-name)))))) diff --git a/version.lisp-expr b/version.lisp-expr index 18dcf15..6798103 100644 --- a/version.lisp-expr +++ b/version.lisp-expr @@ -18,4 +18,4 @@ ;;; for internal versions, especially for internal versions off the ;;; main CVS branch, it gets hairier, e.g. "0.pre7.14.flaky4.13".) -"0.pre7.88" +"0.pre7.89" -- 1.7.10.4