Mercurial > hg > xemacs-beta
changeset 3948:adecfd791c9b
[xemacs-hg @ 2007-05-12 10:17:00 by aidan]
Non-Latin-1 escapes can lead to corrupted ELC code.
| author | aidan |
|---|---|
| date | Sat, 12 May 2007 10:17:09 +0000 |
| parents | 67e8a09db7ed |
| children | 33b9323388c5 |
| files | lisp/ChangeLog lisp/bytecomp.el tests/ChangeLog tests/automated/mule-tests.el |
| diffstat | 4 files changed, 135 insertions(+), 5 deletions(-) [+] |
line wrap: on
line diff
--- a/lisp/ChangeLog Fri May 11 21:51:38 2007 +0000 +++ b/lisp/ChangeLog Sat May 12 10:17:09 2007 +0000 @@ -1,9 +1,17 @@ +2007-05-12 Aidan Kehoe <kehoea@parhasard.net> + + * bytecomp.el (byte-compile-insert-header): + Check for any Unicode escapes in the source file text when + deciding whether Mule support is necessary for it, and whether to + use escape-quoted as the .elc coding system. Thanks to Stephen for + the suggestion as to how to ignore appearances in comments. + 2007-05-01 Stephen J. Turnbull <stephen@xemacs.org> * dumped-lisp.el (preloaded-file-list): Move resize-minibuffer before simple. - * resize-minibuffer.el: Remove CVS $Id: ChangeLog,v 1.793 2007/05/01 14:32:50 stephent Exp $ cookie.. + * resize-minibuffer.el: Remove CVS $Id: ChangeLog,v 1.794 2007/05/12 10:17:00 aidan Exp $ cookie.. * resize-minibuffer.el (resize-minibuffer-mode): Remove autoload.
--- a/lisp/bytecomp.el Fri May 11 21:51:38 2007 +0000 +++ b/lisp/bytecomp.el Sat May 12 10:17:09 2007 +0000 @@ -1842,10 +1842,20 @@ (save-excursion (set-buffer byte-compile-inbuffer) (goto-char (point-min)) - ;; mrb- There must be a better way than skip-chars-forward - (skip-chars-forward (concat (char-to-string 0) "-" - (char-to-string 255))) - (eq (point) (point-max)))) + ;; Look for any non-Latin-1 literals or Unicode character + ;; escapes. Any such occurrences in a @#COUNT comment will lead + ;; to an escape-quoted coding cookie being inserted, but this is + ;; not true of ordinary comments. + (let ((non-latin-1-re + (concat "[^\000-\377]" + #r"\|\\u[0-9a-fA-F]\{4,4\}\|\\U[0-9a-fA-F]\{8,8\}")) + (case-fold-search nil)) + (catch 'need-to-escape-quote + (while (re-search-forward non-latin-1-re nil t) + (skip-chars-backward "^;" (point-at-bol)) + (if (bolp) (throw 'need-to-escape-quote nil)) + (forward-line 1)) + t)))) (setq buffer-file-coding-system 'raw-text-unix) (insert "(or (featurep 'mule) (error \"Loading this file requires Mule support\")) ;;;###coding system: escape-quoted\n")
--- a/tests/ChangeLog Fri May 11 21:51:38 2007 +0000 +++ b/tests/ChangeLog Sat May 12 10:17:09 2007 +0000 @@ -1,3 +1,12 @@ +2007-05-12 Aidan Kehoe <kehoea@parhasard.net> + + * automated/mule-tests.el: + * automated/mule-tests.el (bytecomp): + Require it, since we're testing its Unicode support. + * automated/mule-tests.el (featurep): + Assert that the escape-quoted coding cookie is added when needed, + and ignored when not. + 2007-04-29 Aidan Kehoe <kehoea@parhasard.net> * automated/mule-tests.el (featurep):
--- a/tests/automated/mule-tests.el Fri May 11 21:51:38 2007 +0000 +++ b/tests/automated/mule-tests.el Sat May 12 10:17:09 2007 +0000 @@ -33,6 +33,8 @@ ;; This file will be (read)ed by a non-mule XEmacs, so don't use ;; literal non-Latin1 characters. Use (make-char) instead. +(require 'bytecomp) + ;;----------------------------------------------------------------- ;; Test whether all legal chars may be safely inserted to a buffer. ;;----------------------------------------------------------------- @@ -465,4 +467,105 @@ hebrew-iso8859-8 japanese-jisx0208 japanese-jisx0212 katakana-jisx0201 korean-ksc5601 latin-iso8859-1 latin-iso8859-2 thai-xtis vietnamese-viscii-lower)))) + + (with-temp-buffer + (flet + ((Assert-elc-is-escape-quoted () + "Assert the current buffer has an escape-quoted cookie if compiled." + (save-excursion + (let ((byte-compile-result (byte-compile-from-buffer + (current-buffer) nil nil)) + (temporary-file-name (make-temp-name + (expand-file-name "zjPQ2Pk" + (temp-directory))))) + (byte-compile-insert-header + temporary-file-name + (current-buffer) + byte-compile-result) + (Assert (string-match "^;;;###coding system: escape-quoted" + (buffer-substring nil nil + byte-compile-result)))))) + (Assert-elc-has-no-specified-encoding () + "Assert the current buffer has no coding cookie if compiled." + (save-excursion + (let ((byte-compile-result (byte-compile-from-buffer + (current-buffer) nil nil)) + (temporary-file-name (make-temp-name + (expand-file-name "zjPQ2Pk" + (temp-directory))))) + (byte-compile-insert-header + temporary-file-name + (current-buffer) + byte-compile-result) + (Assert (not (string-match + ";;;###coding system:" + (buffer-substring nil nil byte-compile-result)))))))) + (insert + ;; Create a buffer creating the Unicode escapes. + #r" (defvar testing-mule-compilation-handling + (string ?\u371E ;; kDefinition beautiful; pretty, used + ;; in girl's name + ?\U0002A6A9 ;; kDefinition (Cant.) sound of shouting + ?\U0002A65B ;; kDefinition (Cant.) decayed teeth; + ;; tongue-tied + ?\U00010400 ;; DESERET CAPITAL LETTER LONG I + ?\u3263)) ;; CIRCLED HANGUL RIEUL ") + + (Assert-elc-is-escape-quoted) + (delete-region (point-min) (point-max)) + + (insert + ;; This time, the buffer will contain the actual characters, because of + ;; u flag to the #r. + #ru" (defvar testing-mule-compilation-handling + (string ?\u371E ;; kDefinition beautiful; pretty, used + ;; in girl's name + ?\U0002A6A9 ;; kDefinition (Cant.) sound of shouting + ?\U0002A65B ;; kDefinition (Cant.) decayed teeth; + ;; tongue-tied + ?\U00010400 ;; DESERET CAPITAL LETTER LONG I + ?\u3263)) ;; CIRCLED HANGUL RIEUL ") + + (Assert-elc-is-escape-quoted) + (delete-region (point-min) (point-max)) + + (insert + ;; Just a single four character escape. + #r" (defvar testing-mule-compilation-handling + (string ?\u371E)) ;; kDefinition beautiful; pretty, used") + + (Assert-elc-is-escape-quoted) + (delete-region (point-min) (point-max)) + + (insert + ;; Just a single eight character escape. + #r" (defvar testing-mule-compilation-handling + (string ?\U0002A65B)) ;; kDefinition (Cant.) decayed teeth;") + + (Assert-elc-is-escape-quoted) + (delete-region (point-min) (point-max)) + + (insert + ;; A single latin-1 hex digit escape + #r" (defvar testing-mule-compilation-handling + (string ?\xab)) ;; LEFT-POINTING DOUBLE ANGLE QUOTATION MARK") + + (Assert-elc-has-no-specified-encoding) + (delete-region (point-min) (point-max)) + + (insert + ;; A single latin-1 character + #ru" (defvar testing-mule-compilation-handling + (string ?\u00AB)) ;; LEFT-POINTING DOUBLE ANGLE QUOTATION MARK") + + (Assert-elc-has-no-specified-encoding) + (delete-region (point-min) (point-max)) + + (insert + ;; Just ASCII. + #r" (defvar testing-mule-compilation-handling + (string ?A)) ;; LATIN CAPITAL LETTER A") + + (Assert-elc-has-no-specified-encoding) + (delete-region (point-min) (point-max)))) )