roffit: detect RFC better by a leading non-word or start of line

Amend the test accordingly Ref: curl/curl#11381
bagder · Jun 24, 2023 · 26d34eb · 26d34eb
1 parent 9f030f3
commit 26d34eb
Show file tree

Hide file tree

Showing 3 changed files with 6 additions and 3 deletions.
diff --git a/roffit b/roffit
@@ -254,7 +254,7 @@ sub linkfile {
             $field =~ s/(^|\W)((https|http|ftp):\/\/[a-z0-9\-._~%:\/?\#\[\]\@!\$&'()*+,;=]+)/$1<a href=\"$2\">$2<\/a>/gi;
 
             # convert (uppercase only) "RFC [number]" to a link
-            $field =~ s/(^|[\"\s])RFC ?(\d+)/$1<a href=\"http:\/\/www.ietf.org\/rfc\/rfc$2.txt\">RFC $2<\/a>/g;
+            $field =~ s/(^|\W)RFC ?(\d+)/$1<a href=\"http:\/\/www.ietf.org\/rfc\/rfc$2.txt\">RFC $2<\/a>/g;
 
             $processed .= $field . $tail;
         }

diff --git a/testpage.1 b/testpage.1
@@ -13,7 +13,9 @@ converts the \fIinputfile\fP to \fIoutputfile\fP. The \fIinputfile\fP must be
 an nroff formatted man page, and the \fIoutputfile\fP will be an HTML
 document.
 
-RFC 959 is FTP
+(RFC 959) is FTP
+
+but ARFC 959 is a fake
 
 RFC3986 is URI syntax
 

diff --git a/testpage.output b/testpage.output
@@ -4,7 +4,8 @@
 <p class="level0">testpage - test input nroff man page for roffit testing <a name="SYNOPSIS"></a><h2 class="nroffsh">Synopsis</h2>
 <p class="level0"><span Class="bold">roffit</span> [<span Class="emphasis">options</span>] &lt; inputfile &gt; outputfile <a name="DESCRIPTION"></a><h2 class="nroffsh">Description</h2>
 <p class="level0"><span Class="bold">roffit</span> converts the <span Class="emphasis">inputfile</span> to <span Class="emphasis">outputfile</span>. The <span Class="emphasis">inputfile</span> must be an nroff formatted man page, and the <span Class="emphasis">outputfile</span> will be an HTML document. 
-<p class="level0"><a href="http://www.ietf.org/rfc/rfc959.txt">RFC 959</a> is FTP 
+<p class="level0">(<a href="http://www.ietf.org/rfc/rfc959.txt">RFC 959</a>) is FTP 
+<p class="level0">but ARFC 959 is a fake 
 <p class="level0"><a href="http://www.ietf.org/rfc/rfc3986.txt">RFC 3986</a> is URI syntax 
 <p class="level0">Also, we must support <span class="emphasis">style staring on one line and ending on another that may</span> be multiple lines off. <a name="OPTIONS"></a><h2 class="nroffsh">Options</h2>
 <p class="level0">