all messages for Emacs-related lists mirrored at yhetil.org
 help / color / mirror / code / Atom feed
* xml.el patches for better spec compliance
@ 2003-03-12 21:04 Mark A. Hershberger
  2003-03-13 10:31 ` Juanma Barranquero
       [not found] ` <mailman.3159.1047551561.21513.bug-gnu-emacs@gnu.org>
  0 siblings, 2 replies; 7+ messages in thread
From: Mark A. Hershberger @ 2003-03-12 21:04 UTC (permalink / raw)



[This patch replaces the one sent earlier.]

The following patch contains the following changes to xml.el:

* All instances of "[:space:]" changed to " \t\n\r".  This is
  because the whitespace class does not include \r, but the XML
  spec includes \r as whitespace.  (I had previously submitted
  the patch to change " \t\n" to "[:space:]", but I was wrong.) 
  See
  <http://www.w3.org/TR/2000/REC-xml-20001006#sec-common-syn>.

* Replace "\r\n" and "\r" with "\n".  See
  <http://www.w3.org/TR/2000/REC-xml-20001006#sec-line-ends>.

* Added attribute normalization.  See
  <http://www.w3.org/TR/2000/REC-xml-20001006#AVNormalize>.

* Added character references.  See
  <http://www.w3.org/TR/2000/REC-xml-20001006#sec-references>.

diff -c -r1.16 xml.el
*** xml.el	11 Mar 2003 21:57:46 -0000	1.16
--- xml.el	12 Mar 2003 21:02:24 -0000
***************
*** 184,190 ****
     ;; beginning of a document)
     ((looking-at "<\\?")
      (search-forward "?>" end)
!     (goto-char (- (re-search-forward "[^[:space:]]") 1))
      (xml-parse-tag end))
     ;;  Character data (CDATA) sections, in which no tag should be interpreted
     ((looking-at "<!\\[CDATA\\[")
--- 184,190 ----
     ;; beginning of a document)
     ((looking-at "<\\?")
      (search-forward "?>" end)
!     (goto-char (- (re-search-forward "[^ \t\n\r]") 1))
      (xml-parse-tag end))
     ;;  Character data (CDATA) sections, in which no tag should be interpreted
     ((looking-at "<!\\[CDATA\\[")
***************
*** 198,204 ****
        (if parse-dtd
  	  (setq dtd (xml-parse-dtd end))
  	(xml-skip-dtd end))
!       (goto-char (- (re-search-forward "[^[:space:]]") 1))
        (if dtd
  	  (cons dtd (xml-parse-tag end))
  	(xml-parse-tag end))))
--- 198,204 ----
        (if parse-dtd
  	  (setq dtd (xml-parse-dtd end))
  	(xml-skip-dtd end))
!       (goto-char (- (re-search-forward "[^ \t\n\r]") 1))
        (if dtd
  	  (cons dtd (xml-parse-tag end))
  	(xml-parse-tag end))))
***************
*** 210,216 ****
     ((looking-at "</")
      '())
     ;;  opening tag
!    ((looking-at "<\\([^/>[:space:]]+\\)")
      (goto-char (match-end 1))
      (let* ((case-fold-search nil) ;; XML is case-sensitive.
  	   (node-name (match-string 1))
--- 210,216 ----
     ((looking-at "</")
      '())
     ;;  opening tag
!    ((looking-at "<\\([^/> \t\n\r]+\\)")
      (goto-char (match-end 1))
      (let* ((case-fold-search nil) ;; XML is case-sensitive.
  	   (node-name (match-string 1))
***************
*** 219,225 ****
  	   pos)
  
        ;; is this an empty element ?
!       (if (looking-at "/[[:space:]]*>")
  	  (progn
  	    (forward-char 2)
  	    (nreverse (cons '("") children)))
--- 219,225 ----
  	   pos)
  
        ;; is this an empty element ?
!       (if (looking-at "/[ \t\n\r]*>")
  	  (progn
  	    (forward-char 2)
  	    (nreverse (cons '("") children)))
***************
*** 230,236 ****
  	      (forward-char 1)
  	      ;;  Now check that we have the right end-tag. Note that this
  	      ;;  one might contain spaces after the tag name
! 	      (while (not (looking-at (concat "</" node-name "[[:space:]]*>")))
  		(cond
  		 ((looking-at "</")
  		  (error (concat
--- 230,236 ----
  	      (forward-char 1)
  	      ;;  Now check that we have the right end-tag. Note that this
  	      ;;  one might contain spaces after the tag name
! 	      (while (not (looking-at (concat "</" node-name "[ \t\n\r]*>")))
  		(cond
  		 ((looking-at "</")
  		  (error (concat
***************
*** 248,259 ****
  		  (let ((string (buffer-substring-no-properties pos (point)))
  			(pos 0))
  
! 		    ;; Clean up the string (no newline characters)
! 		    ;; Not done, since as per XML specifications, the XML processor
! 		    ;; should always pass the whole string to the application.
! 		    ;; 	    (while (string-match "\\s +" string pos)
! 		    ;; 	      (setq string (replace-match " " t t string))
! 		    ;; 	      (setq pos (1+ (match-beginning 0))))
  
  		    (setq string (xml-substitute-special string))
  		    (setq children
--- 248,261 ----
  		  (let ((string (buffer-substring-no-properties pos (point)))
  			(pos 0))
  
! 		    ;; Clean up the string.  As per XML
! 		    ;; specifications, the XML processor should
! 		    ;; always pass the whole string to the
! 		    ;; application.  But \r's should be replaced:
! 		    ;; http://www.w3.org/TR/2000/REC-xml-20001006#sec-line-ends
! 		    (while (string-match "\r\n?" string pos)
! 		      (setq string (replace-match "\n" t t string))
! 		      (setq pos (1+ (match-beginning 0))))
  
  		    (setq string (xml-substitute-special string))
  		    (setq children
***************
*** 280,307 ****
  The search for attributes end at the position END in the current buffer.
  Leaves the point on the first non-blank character after the tag."
    (let ((attlist ())
! 	name)
!     (goto-char (- (re-search-forward "[^[:space:]]") 1))
!     (while (looking-at "\\([a-zA-Z_:][-a-zA-Z0-9._:]*\\)[[:space:]]*=[[:space:]]*")
        (setq name (intern (match-string 1)))
        (goto-char (match-end 0))
  
        ;; Do we have a string between quotes (or double-quotes),
        ;;  or a simple word ?
!       (unless (looking-at "\"\\([^\"]*\\)\"")
! 	(unless (looking-at "'\\([^']*\\)'")
  	  (error "XML: Attribute values must be given between quotes")))
  
        ;; Each attribute must be unique within a given element
        (if (assoc name attlist)
  	  (error "XML: each attribute must be unique within an element"))
  
!       (push (cons name (match-string-no-properties 1)) attlist)
!       (goto-char (match-end 0))
!       (goto-char (- (re-search-forward "[^[:space:]]") 1))
        (if (> (point) end)
! 	  (error "XML: end of attribute list not found before end of region"))
!       )
      (nreverse attlist)))
  
  ;;*******************************************************************
--- 282,325 ----
  The search for attributes end at the position END in the current buffer.
  Leaves the point on the first non-blank character after the tag."
    (let ((attlist ())
! 	start-pos name)
!     (goto-char (- (re-search-forward "[^ \t\n\r]") 1))
!     (while (looking-at "\\([a-zA-Z_:][-a-zA-Z0-9._:]*\\)[ \t\n\r]*=[ \t\n\r]*")
        (setq name (intern (match-string 1)))
        (goto-char (match-end 0))
  
+       ;; See also: http://www.w3.org/TR/2000/REC-xml-20001006#AVNormalize
+ 
        ;; Do we have a string between quotes (or double-quotes),
        ;;  or a simple word ?
!       (if (looking-at "\"\\([^\"]*\\)\"")
! 	  (setq start-pos (match-beginning 0))
! 	(if (looking-at "'\\([^']*\\)")
! 	    (setq start-pos (match-beginning 0))
  	  (error "XML: Attribute values must be given between quotes")))
  
        ;; Each attribute must be unique within a given element
        (if (assoc name attlist)
  	  (error "XML: each attribute must be unique within an element"))
  
!       ;; Multiple whitespace characters should be replaced with a single one
!       ;; in the attributes
!       (let ((string (match-string-no-properties 1))
! 	    (pos 0))
! 	(while (string-match "[ \t\n\r]+" string pos)
! 	  (setq string (replace-match " " t nil string))
! 	  (setq pos (1+ (match-beginning 0))))
! 	(push (cons name (xml-substitute-special string)) attlist))
! 
!       (goto-char start-pos)
!       (if (looking-at "\"\\([^\"]*\\)\"")
! 	  (goto-char (match-end 0))
! 	(if (looking-at "'\\([^']*\\)")
! 	    (goto-char (match-end 0))))
! 
!       (goto-char (- (re-search-forward "[^ \t\n\r]") 1)) 
        (if (> (point) end)
!           (error "XML: end of attribute list not found before end of region")))
      (nreverse attlist)))
  
  ;;*******************************************************************
***************
*** 318,332 ****
  The point must be just before the starting tag of the DTD.
  This follows the rule [28] in the XML specifications."
    (forward-char (length "<!DOCTYPE"))
!   (if (looking-at "[[:space:]]*>")
        (error "XML: invalid DTD (excepting name of the document)"))
    (condition-case nil
        (progn
! 	(forward-word 1)  ;; name of the document
! 	(goto-char (- (re-search-forward "[[:space:]]") 1))
! 	(goto-char (- (re-search-forward "[^[:space:]]") 1))
  	(if (looking-at "\\[")
! 	    (re-search-forward "\\][[:space:]]*>" end)
  	  (search-forward ">" end)))
      (error (error "XML: No end to the DTD"))))
  
--- 336,350 ----
  The point must be just before the starting tag of the DTD.
  This follows the rule [28] in the XML specifications."
    (forward-char (length "<!DOCTYPE"))
!   (if (looking-at "[ \t\n\r]*>")
        (error "XML: invalid DTD (excepting name of the document)"))
    (condition-case nil
        (progn
! 	(forward-word 1)
! 	(goto-char (- (re-search-forward "[ \t\n\r]") 1))
! 	(goto-char (- (re-search-forward "[^ \t\n\r]") 1))
  	(if (looking-at "\\[")
! 	    (re-search-forward "\\][ \t\n\r]*>" end)
  	  (search-forward ">" end)))
      (error (error "XML: No end to the DTD"))))
  
***************
*** 334,340 ****
    "Parse the DTD that point is looking at.
  The DTD must end before the position END in the current buffer."
    (forward-char (length "<!DOCTYPE"))
!   (goto-char (- (re-search-forward "[^[:space:]]") 1))
    (if (looking-at ">")
        (error "XML: invalid DTD (excepting name of the document)"))
  
--- 352,358 ----
    "Parse the DTD that point is looking at.
  The DTD must end before the position END in the current buffer."
    (forward-char (length "<!DOCTYPE"))
!   (goto-char (- (re-search-forward "[^ \t\n\r]") 1))
    (if (looking-at ">")
        (error "XML: invalid DTD (excepting name of the document)"))
  
***************
*** 344,350 ****
  	type element end-pos)
      (goto-char (match-end 0))
  
!     (goto-char (- (re-search-forward "[^[:space:]]") 1))
  
      ;;  External DTDs => don't know how to handle them yet
      (if (looking-at "SYSTEM")
--- 362,368 ----
  	type element end-pos)
      (goto-char (match-end 0))
  
!     (goto-char (- (re-search-forward "[^ \t\n\r]") 1))
  
      ;;  External DTDs => don't know how to handle them yet
      (if (looking-at "SYSTEM")
***************
*** 355,367 ****
  
      ;;  Parse the rest of the DTD
      (forward-char 1)
!     (while (and (not (looking-at "[[:space:]]*\\]"))
  		(<= (point) end))
        (cond
  
         ;;  Translation of rule [45] of XML specifications
         ((looking-at
! 	 "[[:space:]]*<!ELEMENT[[:space:]]+\\([a-zA-Z0-9.%;]+\\)[[:space:]]+\\([^>]+\\)>")
  
  	(setq element (intern (match-string-no-properties 1))
  	      type    (match-string-no-properties 2))
--- 373,385 ----
  
      ;;  Parse the rest of the DTD
      (forward-char 1)
!     (while (and (not (looking-at "[ \t\n\r]*\\]"))
  		(<= (point) end))
        (cond
  
         ;;  Translation of rule [45] of XML specifications
         ((looking-at
! 	 "[ \t\n\r]*<!ELEMENT[ \t\n\r]+\\([a-zA-Z0-9.%;]+\\)[ \t\n\r]+\\([^>]+\\)>")
  
  	(setq element (intern (match-string-no-properties 1))
  	      type    (match-string-no-properties 2))
***************
*** 369,381 ****
  
  	;;  Translation of rule [46] of XML specifications
  	(cond
! 	 ((string-match "^EMPTY[[:space:]]*$" type)     ;; empty declaration
  	  (setq type 'empty))
! 	 ((string-match "^ANY[[:space:]]*$" type)       ;; any type of contents
  	  (setq type 'any))
! 	 ((string-match "^(\\(.*\\))[[:space:]]*$" type) ;; children ([47])
  	  (setq type (xml-parse-elem-type (match-string-no-properties 1 type))))
! 	 ((string-match "^%[^;]+;[[:space:]]*$" type)   ;; substitution
  	  nil)
  	 (t
  	  (error "XML: Invalid element type in the DTD")))
--- 387,399 ----
  
  	;;  Translation of rule [46] of XML specifications
  	(cond
! 	 ((string-match "^EMPTY[ \t\n\r]*$" type)     ;; empty declaration
  	  (setq type 'empty))
! 	 ((string-match "^ANY[ \t\n\r]*$" type)       ;; any type of contents
  	  (setq type 'any))
! 	 ((string-match "^(\\(.*\\))[ \t\n\r]*$" type) ;; children ([47])
  	  (setq type (xml-parse-elem-type (match-string-no-properties 1 type))))
! 	 ((string-match "^%[^;]+;[ \t\n\r]*$" type)   ;; substitution
  	  nil)
  	 (t
  	  (error "XML: Invalid element type in the DTD")))
***************
*** 417,423 ****
  				 (mapcar 'xml-parse-elem-type
  					 (split-string elem ","))))
  	      )))
!       (if (string-match "[[:space:]]*\\([^+*?]+\\)\\([+*?]?\\)" string)
  	  (setq elem     (match-string 1 string)
  		modifier (match-string 2 string))))
  
--- 435,441 ----
  				 (mapcar 'xml-parse-elem-type
  					 (split-string elem ","))))
  	      )))
!       (if (string-match "[ \t\n\r]*\\([^+*?]+\\)\\([+*?]?\\)" string)
  	  (setq elem     (match-string 1 string)
  		modifier (match-string 2 string))))
  
***************
*** 451,456 ****
--- 469,485 ----
      (setq string (replace-match "'"  t nil string)))
    (while (string-match "&quot;" string)
      (setq string (replace-match "\"" t nil string)))
+   (while (string-match "&#\\([0-9]+\\);" string)
+     (setq string (replace-match (char-to-ucs
+ 				 (string-to-int
+ 				  (match-string-no-properties 1 string)))
+ 				t nil string)))
+   (while (string-match "&#x\\([0-9a-fA-F]+\\);" string)
+     (setq string (replace-match (char-to-ucs
+ 				 (hex-string-to-number
+ 				  (match-string-no-properties 1 string)))
+ 				t nil string)))
+ 
    ;; This goes last so it doesn't confuse the matches above.
    (while (string-match "&amp;" string)
      (setq string (replace-match "&"  t nil string)))

^ permalink raw reply	[flat|nested] 7+ messages in thread
[parent not found: <mailman.3142.1047498362.21513.bug-gnu-emacs@gnu.org>]
* xml.el patches for better spec compliance
@ 2003-03-12 19:42 Mark A. Hershberger
  0 siblings, 0 replies; 7+ messages in thread
From: Mark A. Hershberger @ 2003-03-12 19:42 UTC (permalink / raw)



The following patch contains the following changes to xml.el:

* All instances of "[:space:]" changed to " \t\n\r".  This is
  because the whitespace class does not include \r, but the XML
  spec includes \r as whitespace.  (I had previously submitted
  the patch to change " \t\n" to "[:space:]", but I was wrong.) 
  See
  <http://www.w3.org/TR/2000/REC-xml-20001006#sec-common-syn>.

* Replace "\r\n" and "\r" with "\n".  See
  <http://www.w3.org/TR/2000/REC-xml-20001006#sec-line-ends>.

* Added attribute normalization.  See
  <http://www.w3.org/TR/2000/REC-xml-20001006#AVNormalize>.

* Added character references.  See
  <http://www.w3.org/TR/2000/REC-xml-20001006#sec-references>.

diff -c -r1.16 xml.el
*** xml.el	11 Mar 2003 21:57:46 -0000	1.16
--- xml.el	12 Mar 2003 19:36:01 -0000
***************
*** 184,190 ****
     ;; beginning of a document)
     ((looking-at "<\\?")
      (search-forward "?>" end)
!     (goto-char (- (re-search-forward "[^[:space:]]") 1))
      (xml-parse-tag end))
     ;;  Character data (CDATA) sections, in which no tag should be interpreted
     ((looking-at "<!\\[CDATA\\[")
--- 184,190 ----
     ;; beginning of a document)
     ((looking-at "<\\?")
      (search-forward "?>" end)
!     (goto-char (- (re-search-forward "[^ \t\n\r]") 1))
      (xml-parse-tag end))
     ;;  Character data (CDATA) sections, in which no tag should be interpreted
     ((looking-at "<!\\[CDATA\\[")
***************
*** 198,204 ****
        (if parse-dtd
  	  (setq dtd (xml-parse-dtd end))
  	(xml-skip-dtd end))
!       (goto-char (- (re-search-forward "[^[:space:]]") 1))
        (if dtd
  	  (cons dtd (xml-parse-tag end))
  	(xml-parse-tag end))))
--- 198,204 ----
        (if parse-dtd
  	  (setq dtd (xml-parse-dtd end))
  	(xml-skip-dtd end))
!       (goto-char (- (re-search-forward "[^ \t\n\r]") 1))
        (if dtd
  	  (cons dtd (xml-parse-tag end))
  	(xml-parse-tag end))))
***************
*** 210,216 ****
     ((looking-at "</")
      '())
     ;;  opening tag
!    ((looking-at "<\\([^/>[:space:]]+\\)")
      (goto-char (match-end 1))
      (let* ((case-fold-search nil) ;; XML is case-sensitive.
  	   (node-name (match-string 1))
--- 210,216 ----
     ((looking-at "</")
      '())
     ;;  opening tag
!    ((looking-at "<\\([^/> \t\n\r]+\\)")
      (goto-char (match-end 1))
      (let* ((case-fold-search nil) ;; XML is case-sensitive.
  	   (node-name (match-string 1))
***************
*** 219,225 ****
  	   pos)
  
        ;; is this an empty element ?
!       (if (looking-at "/[[:space:]]*>")
  	  (progn
  	    (forward-char 2)
  	    (nreverse (cons '("") children)))
--- 219,225 ----
  	   pos)
  
        ;; is this an empty element ?
!       (if (looking-at "/[ \t\n\r]*>")
  	  (progn
  	    (forward-char 2)
  	    (nreverse (cons '("") children)))
***************
*** 230,236 ****
  	      (forward-char 1)
  	      ;;  Now check that we have the right end-tag. Note that this
  	      ;;  one might contain spaces after the tag name
! 	      (while (not (looking-at (concat "</" node-name "[[:space:]]*>")))
  		(cond
  		 ((looking-at "</")
  		  (error (concat
--- 230,236 ----
  	      (forward-char 1)
  	      ;;  Now check that we have the right end-tag. Note that this
  	      ;;  one might contain spaces after the tag name
! 	      (while (not (looking-at (concat "</" node-name "[ \t\n\r]*>")))
  		(cond
  		 ((looking-at "</")
  		  (error (concat
***************
*** 248,259 ****
  		  (let ((string (buffer-substring-no-properties pos (point)))
  			(pos 0))
  
! 		    ;; Clean up the string (no newline characters)
! 		    ;; Not done, since as per XML specifications, the XML processor
! 		    ;; should always pass the whole string to the application.
! 		    ;; 	    (while (string-match "\\s +" string pos)
! 		    ;; 	      (setq string (replace-match " " t t string))
! 		    ;; 	      (setq pos (1+ (match-beginning 0))))
  
  		    (setq string (xml-substitute-special string))
  		    (setq children
--- 248,261 ----
  		  (let ((string (buffer-substring-no-properties pos (point)))
  			(pos 0))
  
! 		    ;; Clean up the string.  As per XML
! 		    ;; specifications, the XML processor should
! 		    ;; always pass the whole string to the
! 		    ;; application.  But \r's should be replaced:
! 		    ;; http://www.w3.org/TR/2000/REC-xml-20001006#sec-line-ends
! 		    (while (string-match "\r\n?" string pos)
! 		      (setq string (replace-match "\n" t t string))
! 		      (setq pos (1+ (match-beginning 0))))
  
  		    (setq string (xml-substitute-special string))
  		    (setq children
***************
*** 280,307 ****
  The search for attributes end at the position END in the current buffer.
  Leaves the point on the first non-blank character after the tag."
    (let ((attlist ())
! 	name)
!     (goto-char (- (re-search-forward "[^[:space:]]") 1))
!     (while (looking-at "\\([a-zA-Z_:][-a-zA-Z0-9._:]*\\)[[:space:]]*=[[:space:]]*")
        (setq name (intern (match-string 1)))
        (goto-char (match-end 0))
  
        ;; Do we have a string between quotes (or double-quotes),
        ;;  or a simple word ?
!       (unless (looking-at "\"\\([^\"]*\\)\"")
! 	(unless (looking-at "'\\([^']*\\)'")
  	  (error "XML: Attribute values must be given between quotes")))
  
        ;; Each attribute must be unique within a given element
        (if (assoc name attlist)
  	  (error "XML: each attribute must be unique within an element"))
  
!       (push (cons name (match-string-no-properties 1)) attlist)
!       (goto-char (match-end 0))
!       (goto-char (- (re-search-forward "[^[:space:]]") 1))
        (if (> (point) end)
! 	  (error "XML: end of attribute list not found before end of region"))
!       )
      (nreverse attlist)))
  
  ;;*******************************************************************
--- 282,324 ----
  The search for attributes end at the position END in the current buffer.
  Leaves the point on the first non-blank character after the tag."
    (let ((attlist ())
! 	start-pos name)
!     (goto-char (- (re-search-forward "[^ \t\n\r]") 1))
!     (while (looking-at "\\([a-zA-Z_:][-a-zA-Z0-9._:]*\\)[ \t\n\r]*=[ \t\n\r]*")
        (setq name (intern (match-string 1)))
        (goto-char (match-end 0))
  
+       ;; See also: http://www.w3.org/TR/2000/REC-xml-20001006#AVNormalize
+ 
        ;; Do we have a string between quotes (or double-quotes),
        ;;  or a simple word ?
!       (if (looking-at "\"\\([^\"]*\\)\"")
! 	  (setq start-pos (match-beginning 0))
! 	(if (looking-at "'\\([^']*\\)")
! 	    (setq start-pos (match-beginning 0))
  	  (error "XML: Attribute values must be given between quotes")))
  
        ;; Each attribute must be unique within a given element
        (if (assoc name attlist)
  	  (error "XML: each attribute must be unique within an element"))
  
!       ;; Multiple whitespace characters should be replaced with a single one
!       ;; in the attributes
!       (let ((string (match-string-no-properties 1))
! 	    (pos 0))
! 	(while (string-match "[ \t\n\r]+" string pos)
! 	  (setq string (replace-match " " t nil string))
! 	  (setq pos (1+ (match-beginning 0))))
! 	(push (cons name (xml-substitute-special string)) attlist))
! 
!       (goto-char start-pos)
!       (if (looking-at "\"\\([^\"]*\\)\"")
! 	  (goto-char (match-end 0))
! 	(if (looking-at "'\\([^']*\\)")
! 	    (goto-char (match-end 0))))
! 
        (if (> (point) end)
!           (error "XML: end of attribute list not found before end of region")))
      (nreverse attlist)))
  
  ;;*******************************************************************
***************
*** 318,332 ****
  The point must be just before the starting tag of the DTD.
  This follows the rule [28] in the XML specifications."
    (forward-char (length "<!DOCTYPE"))
!   (if (looking-at "[[:space:]]*>")
        (error "XML: invalid DTD (excepting name of the document)"))
    (condition-case nil
        (progn
  	(forward-word 1)  ;; name of the document
! 	(goto-char (- (re-search-forward "[[:space:]]") 1))
! 	(goto-char (- (re-search-forward "[^[:space:]]") 1))
  	(if (looking-at "\\[")
! 	    (re-search-forward "\\][[:space:]]*>" end)
  	  (search-forward ">" end)))
      (error (error "XML: No end to the DTD"))))
  
--- 335,349 ----
  The point must be just before the starting tag of the DTD.
  This follows the rule [28] in the XML specifications."
    (forward-char (length "<!DOCTYPE"))
!   (if (looking-at "[ \t\n\r]*>")
        (error "XML: invalid DTD (excepting name of the document)"))
    (condition-case nil
        (progn
  	(forward-word 1)  ;; name of the document
! 	(goto-char (- (re-search-forward "[ \t\n\r]") 1))
! 	(goto-char (- (re-search-forward "[^\t\n\r]") 1))
  	(if (looking-at "\\[")
! 	    (re-search-forward "\\][ \t\n\r]*>" end)
  	  (search-forward ">" end)))
      (error (error "XML: No end to the DTD"))))
  
***************
*** 334,340 ****
    "Parse the DTD that point is looking at.
  The DTD must end before the position END in the current buffer."
    (forward-char (length "<!DOCTYPE"))
!   (goto-char (- (re-search-forward "[^[:space:]]") 1))
    (if (looking-at ">")
        (error "XML: invalid DTD (excepting name of the document)"))
  
--- 351,357 ----
    "Parse the DTD that point is looking at.
  The DTD must end before the position END in the current buffer."
    (forward-char (length "<!DOCTYPE"))
!   (goto-char (- (re-search-forward "[^ \t\n\r]") 1))
    (if (looking-at ">")
        (error "XML: invalid DTD (excepting name of the document)"))
  
***************
*** 344,350 ****
  	type element end-pos)
      (goto-char (match-end 0))
  
!     (goto-char (- (re-search-forward "[^[:space:]]") 1))
  
      ;;  External DTDs => don't know how to handle them yet
      (if (looking-at "SYSTEM")
--- 361,367 ----
  	type element end-pos)
      (goto-char (match-end 0))
  
!     (goto-char (- (re-search-forward "[^ \t\n\r]") 1))
  
      ;;  External DTDs => don't know how to handle them yet
      (if (looking-at "SYSTEM")
***************
*** 355,367 ****
  
      ;;  Parse the rest of the DTD
      (forward-char 1)
!     (while (and (not (looking-at "[[:space:]]*\\]"))
  		(<= (point) end))
        (cond
  
         ;;  Translation of rule [45] of XML specifications
         ((looking-at
! 	 "[[:space:]]*<!ELEMENT[[:space:]]+\\([a-zA-Z0-9.%;]+\\)[[:space:]]+\\([^>]+\\)>")
  
  	(setq element (intern (match-string-no-properties 1))
  	      type    (match-string-no-properties 2))
--- 372,384 ----
  
      ;;  Parse the rest of the DTD
      (forward-char 1)
!     (while (and (not (looking-at "[ \t\n\r]*\\]"))
  		(<= (point) end))
        (cond
  
         ;;  Translation of rule [45] of XML specifications
         ((looking-at
! 	 "[ \t\n\r]*<!ELEMENT[ \t\n\r]+\\([a-zA-Z0-9.%;]+\\)[ \t\n\r]+\\([^>]+\\)>")
  
  	(setq element (intern (match-string-no-properties 1))
  	      type    (match-string-no-properties 2))
***************
*** 369,381 ****
  
  	;;  Translation of rule [46] of XML specifications
  	(cond
! 	 ((string-match "^EMPTY[[:space:]]*$" type)     ;; empty declaration
  	  (setq type 'empty))
! 	 ((string-match "^ANY[[:space:]]*$" type)       ;; any type of contents
  	  (setq type 'any))
! 	 ((string-match "^(\\(.*\\))[[:space:]]*$" type) ;; children ([47])
  	  (setq type (xml-parse-elem-type (match-string-no-properties 1 type))))
! 	 ((string-match "^%[^;]+;[[:space:]]*$" type)   ;; substitution
  	  nil)
  	 (t
  	  (error "XML: Invalid element type in the DTD")))
--- 386,398 ----
  
  	;;  Translation of rule [46] of XML specifications
  	(cond
! 	 ((string-match "^EMPTY[ \t\n\r]*$" type)     ;; empty declaration
  	  (setq type 'empty))
! 	 ((string-match "^ANY[ \t\n\r]*$" type)       ;; any type of contents
  	  (setq type 'any))
! 	 ((string-match "^(\\(.*\\))[ \t\n\r]*$" type) ;; children ([47])
  	  (setq type (xml-parse-elem-type (match-string-no-properties 1 type))))
! 	 ((string-match "^%[^;]+;[ \t\n\r]*$" type)   ;; substitution
  	  nil)
  	 (t
  	  (error "XML: Invalid element type in the DTD")))
***************
*** 417,423 ****
  				 (mapcar 'xml-parse-elem-type
  					 (split-string elem ","))))
  	      )))
!       (if (string-match "[[:space:]]*\\([^+*?]+\\)\\([+*?]?\\)" string)
  	  (setq elem     (match-string 1 string)
  		modifier (match-string 2 string))))
  
--- 434,440 ----
  				 (mapcar 'xml-parse-elem-type
  					 (split-string elem ","))))
  	      )))
!       (if (string-match "[ \t\n\r]*\\([^+*?]+\\)\\([+*?]?\\)" string)
  	  (setq elem     (match-string 1 string)
  		modifier (match-string 2 string))))
  
***************
*** 451,456 ****
--- 468,484 ----
      (setq string (replace-match "'"  t nil string)))
    (while (string-match "&quot;" string)
      (setq string (replace-match "\"" t nil string)))
+   (while (string-match "&#\\([0-9]+\\);" string)
+     (setq string (replace-match (char-to-string 
+ 				 (string-to-int
+ 				  (match-string-no-properties 1 string)))
+ 				t nil string)))
+   (while (string-match "&#x\\([0-9a-fA-F]+\\);" string)
+     (setq string (replace-match (char-to-string 
+ 				 (hex-string-to-number
+ 				  (match-string-no-properties 1 string)))
+ 				t nil string)))
+ 
    ;; This goes last so it doesn't confuse the matches above.
    (while (string-match "&amp;" string)
      (setq string (replace-match "&"  t nil string)))

^ permalink raw reply	[flat|nested] 7+ messages in thread

end of thread, other threads:[~2003-03-14 23:51 UTC | newest]

Thread overview: 7+ messages (download: mbox.gz follow: Atom feed
-- links below jump to the message on this page --
2003-03-12 21:04 xml.el patches for better spec compliance Mark A. Hershberger
2003-03-13 10:31 ` Juanma Barranquero
     [not found] ` <mailman.3159.1047551561.21513.bug-gnu-emacs@gnu.org>
2003-03-13 17:03   ` Mark A. Hershberger
2003-03-14 17:03     ` Mark A. Hershberger
     [not found] <mailman.3142.1047498362.21513.bug-gnu-emacs@gnu.org>
2003-03-14 17:56 ` Mark A. Hershberger
2003-03-14 23:51   ` Juanma Barranquero
  -- strict thread matches above, loose matches on Subject: below --
2003-03-12 19:42 Mark A. Hershberger

Code repositories for project(s) associated with this external index

	https://git.savannah.gnu.org/cgit/emacs.git
	https://git.savannah.gnu.org/cgit/emacs/org-mode.git

This is an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.