bugfixes and README update

LDP/txt2db/README

@@ -10,13 +10,18 @@ or feedback@linuxdoc.org if you're not.
 
 Or just add it in the cvs. :-)
 
+Foo			<para>Foo</para>
+
 =Title=			<sect1><title>Title</title>
-			<sect1>
+			</sect1>
 
 =Title|id=		<sect1 id='id'><title>Title</title>
-			<sect1>
+			</sect1>
 
-(works for other sect levels as well)
+			works for other sect levels as well, and many other
+			tags. It is either the "id" value, or the "title"
+			value, depending on the semantics of the particular
+			tag. Usage should be obvious in context.
 
 ==Title==		<sect2><title>Title</title>
 			</sect2>
@@ -24,18 +29,17 @@ Or just add it in the cvs. :-)
 ===Title===		<sect3><title>Title</title>
 			</sect3>
 
-Foo			<para>Foo</para>
 
 #Foo			<orderedlist>
 #Bar			<listitem><para>Foo</para></listitem>
 #Baz			<listitem><para>Bar</para></listitem>
-			<listitem><para>Baz</para></listitem>
+/#			<listitem><para>Baz</para></listitem>
 			</orderedlist>
 
 *Foo			<simplelist>
 *Bar			<listitem><para>Foo</para></listitem>
 *Baz			<listitem><para>Bar</para></listitem>
-			<listitem><para>Baz</para></listitem>
+/*			<listitem><para>Baz</para></listitem>
 			</simplelist>
 
 [[http://foo.org]]	<ulink url='http://foo.org'>
@@ -46,7 +50,10 @@ Foo			<para>Foo</para>
 			  <citetitle>Foo</citetitle>
 			</ulink>
 
-[Foo]			<filename>Foo</filename>
+[http://foo.org|Foo]]	You can also delimit with the pipe character "|".
+			This works on any of these [[]] tags.
+
+[[file:Foo]]		<filename>Foo</filename>
 
 '''Foo'''		<emphasis>Foo</emphasis>
 
@@ -54,3 +61,9 @@ A few DocBook structures do not have <para> tags wrapped around them. They
 are <para> itself (duh!), <sect?> and <programlisting>. If you insert anything
 using these tags, no <para> tags will be wrapped around it or inserted into it.
 So if you want fine control over your <para> tags, insert them yourself.
+
+These tags include:
+
+<programlisting/>
+<screen/>
+

LDP/txt2db/txt2db.pl

@@ -10,6 +10,7 @@
 # 
 
 use File::Basename;
+use HTML::Entities;
 
 my($txtfile, $dbfile) = '';
 
@@ -118,6 +119,13 @@ sub proc_txt {
 		$line =~ s/^q:/Q:/;
 		$line =~ s/^a:/A:/;
 
+		# encode entities
+		#
+#		while ($line =~ //) {
+#		}
+#		decode_entities($line);
+		encode_entities($line);
+		
 		# inline docbook
 		#
 		# ulink
@@ -140,7 +148,11 @@ sub proc_txt {
 			} else {
 				$linkname = $link;
 			}
-			
+
+			# kill quotes, they mess us up
+			# 
+			$link =~ s/'/%27/g;
+
 			# namespaces are handled differently
 			#
 			print "$link\n" if ($verbose);
@@ -191,13 +203,6 @@ sub proc_txt {
 			$line =~ s/'''/<\/emphasis>/;
 		}
 
-		# filename
-		# 
-#		while ($line =~ /\[.*?\]/) {
-#			$line =~ s/\[/<filename>/;
-#			$line =~ s/\]/<\/filename>/;
-#		}
-
 		# this block defines DocBook structures that won't be broken up with 
 		# paragraphs when we hit empty lines:
 		#
@@ -367,6 +372,9 @@ sub proc_txt {
 			$answer = 1;
 			$para = 1;
 
+		} elsif ($line =~ /^\s*----\s*$/) {
+			$line = '';
+
 		# para
 		#
 		} else {