W3C home > Mailing lists > Public > html-tidy@w3.org > October to December 2000

Re: Patch to add rudimentary custom entity capability

From: Matej Vela <vela@debian.org>
Date: Sat, 23 Dec 2000 15:13:03 +0100
To: html-tidy@w3.org
Cc: "Gregor N. Purdy" <gregor@focusresearch.com>, Joey Hess <joey@kitenet.net>, 67685-forwarded@bugs.debian.org
Message-ID: <20001223151303.A7291@om>
On Tue, Nov 28, 2000 at 03:23:51PM -0500, Gregor N. Purdy wrote:
> I was using tidy to process an XML file that used some custom entities.
> Since tidy wasn't aware of those entities, it refused to generate a
> tidied file. I did a little rooting around and modified the code just
> enough to produce the desired effect. There are some TODO comments in
> the code to point out where it is suboptimal. Nonetheless, I'm posting
> it here in case anyone else wants to make use of it or in case someone
> wants to tidy (ahem) it up for inclusion in the next release.

Here's a cleaned up version.  (It doesn't expand custom entities
because I feel that's beyond Tidy's scope.)

--- tidy4aug00.orig/Overview.html	Fri Aug  4 18:21:05 2000
+++ tidy4aug00/Overview.html	Sat Dec 23 15:07:13 2000
@@ -422,6 +422,13 @@
 this feature is to allow Tidy to be applied to Cold Fusion
 files.</p>
 
+<p>You can also teach Tidy about new entities by declaring them
+in the configuration file, the syntax is:</p>
+
+<pre>
+  new-entities: <em>entity1, entity2, entity3</em>
+</pre>
+
 <p class="c7">I am working on ways to make it easy to customize
 the permitted document syntax using <a
 href="http://www.w3.org/People/Raggett/dtdgen/Docs/">assertion
@@ -1088,6 +1095,14 @@
 CDATA elements (similar to script).</dd>
 </dl>
 
+<dt>new-entities: <em>entity1, entity2, entity3</em></dt>
+
+<dd>Use this to declare new entities. The option takes a space
+or comma separated list of entity names. There is no mechanism
+for specifying the values of the entities. Note that tidy still
+does not read custom entities from any internal document subset.
+</dd>
+
 <h4>Sample Config File</h4>
 
 <p>This is just an example to get you started.</p>
@@ -1115,6 +1130,7 @@
   mprescripts, mtable, mtr, mtd, mth
 new-blocklevel-tags: cfoutput, cfquery
 new-empty-tags: cfelse
+new-entities: disclaimer
 </pre>
 
 <h3><a id="scripts" name="scripts">Using Tidy from
--- tidy4aug00.orig/config.c	Fri Aug  4 18:21:05 2000
+++ tidy4aug00/config.c	Sat Dec 23 15:07:13 2000
@@ -105,6 +105,7 @@
 static char *block_tags;
 static char *empty_tags;
 static char *pre_tags;
+static char *entities;
 
 
 typedef struct _plist PList;
@@ -182,6 +183,7 @@
     {"new-blocklevel-tags", {(int *)&block_tags},   ParseTagNames},
     {"new-empty-tags",  {(int *)&empty_tags},       ParseTagNames},
     {"new-pre-tags",    {(int *)&pre_tags},         ParseTagNames},
+    {"new-entities",    {(int *)&entities},         ParseTagNames},
     {"char-encoding",   {(int *)&CharEncoding},     ParseCharEncoding},
     {"doctype",         {(int *)&doctype_str},      ParseDocType},
     {"fix-backslash",   {(int *)&FixBackslash},     ParseBool},
@@ -665,6 +667,8 @@
             DefineEmptyTag(buf);
         else if (location.string == &pre_tags)
             DefinePreTag(buf);
+        else if (location.string == &entities)
+            DefineEntity(buf);
 
         i = 0;
     }
--- tidy4aug00.orig/entities.c	Fri Aug  4 18:21:05 2000
+++ tidy4aug00/entities.c	Sat Dec 23 15:07:13 2000
@@ -349,6 +349,11 @@
     return 0;   /* zero signifies unknown entity name */
 }
 
+void DefineEntity(char *name)
+{
+    install(name, '&');
+}
+
 void InitEntities(void)
 {
     struct entity *ep;
--- tidy4aug00.orig/html.h	Fri Aug  4 18:21:05 2000
+++ tidy4aug00/html.h	Sat Dec 23 15:07:13 2000
@@ -501,6 +501,8 @@
 Bool IsWord2000(Node *root);
 
 /* entities.c */
+void DefineEntity(char *name);
+
 void InitEntities(void);
 void FreeEntities(void);
 uint EntityCode(char *name);
--- tidy4aug00.orig/lexer.c	Fri Aug  4 18:21:05 2000
+++ tidy4aug00/lexer.c	Sat Dec 23 15:07:13 2000
@@ -296,7 +296,7 @@
 {
     uint start, map;
     Bool first = yes, semicolon = no;
-    int c, ch, startcol;
+    int c, ch, startcol, i;
 
     start = lexer->lexsize - 1;  /* to start at "&" */
     startcol = lexer->in->curcol - 1;
@@ -352,6 +352,15 @@
         }
         else /* naked & */
             ReportEntityError(lexer, UNESCAPED_AMPERSAND, lexer->lexbuf+start, ch);
+
+        if (QuoteAmpersand)
+        {
+            for (i = 0; i < 4; ++i)
+	        AddCharToLexer(lexer, '\0');
+            for (i = lexer->lexsize - 1; i > start + 4; --i)
+                lexer->lexbuf[i] = lexer->lexbuf[i - 4];
+            wstrncpy (lexer->lexbuf + start + 1, "amp;", 4);
+        }
     }
     else
     {
@@ -363,19 +372,16 @@
             ReportEntityError(lexer, MISSING_SEMICOLON, lexer->lexbuf+start, c);
         }
 
-        lexer->lexsize = start;
-
-        if (ch == 160 && (mode & Preformatted))
-            ch = ' ';
+        if (ch == '&')
+            AddCharToLexer(lexer, ';');
+        else
+        {
+            lexer->lexsize = start;
 
-        AddCharToLexer(lexer, ch);
+            if (ch == 160 && (mode & Preformatted))
+                ch = ' ';
 
-        if (ch == '&' && !QuoteAmpersand)
-        {
-            AddCharToLexer(lexer, 'a');
-            AddCharToLexer(lexer, 'm');
-            AddCharToLexer(lexer, 'p');
-            AddCharToLexer(lexer, ';');
+            AddCharToLexer(lexer, ch);
         }
     }
 }
--- tidy4aug00.orig/pprint.c	Fri Aug  4 18:21:05 2000
+++ tidy4aug00/pprint.c	Sat Dec 23 15:07:13 2000
@@ -362,21 +362,6 @@
             return;
         }
 
-        /*
-          naked '&' chars can be left alone or
-          quoted as &amp; The latter is required
-          for XML where naked '&' are illegal.
-        */
-        if (c == '&' && QuoteAmpersand)
-        {
-            AddC('&', linelen++);
-            AddC('a', linelen++);
-            AddC('m', linelen++);
-            AddC('p', linelen++);
-            AddC(';', linelen++);
-            return;
-        }
-
         if (c == '"' && QuoteMarks)
         {
             AddC('&', linelen++);
--- tidy4aug00.orig/release-notes.html	Fri Aug  4 18:21:05 2000
+++ tidy4aug00/release-notes.html	Sat Dec 23 15:07:13 2000
@@ -73,6 +73,14 @@
 current workload means that I don't get much time left to work on
 HTML Tidy.</p>
 
+<h2>December 2000</h2>
+
+<p>Gregor N. Purdy &lt;gregor@focusresearch.com&gt made a quick
+hack to permit the definition of custom entities in the config
+file via the new-entities option, and Matej Vela
+&lt;vela@debian.org&gt; cleaned it up. This is handy for tidying
+XML files.</p>
+
 <h2>August 2000</h2>
 
 <p>Ann Navarro comments that the "appears to" message is
Received on Saturday, 23 December 2000 12:23:34 GMT

This archive was generated by hypermail 2.2.0+W3C-0.50 : Tuesday, 3 April 2012 06:13:45 GMT