From 9ddafb2f99208c19df468190188486d608f802a5 Mon Sep 17 00:00:00 2001
From: "Eric S. Raymond" <esr@thyrsus.com>
Date: Wed, 10 Sep 2003 17:22:16 +0000
Subject: [PATCH] We can now ignore shell comments.

---
 comparator.xml | 21 ++++++++++++++-------
 shredtree.c    | 39 ++++++++++++++++++++++++---------------
 2 files changed, 38 insertions(+), 22 deletions(-)

diff --git a/comparator.xml b/comparator.xml
index 054a26c..8eb58e9 100644
--- a/comparator.xml
+++ b/comparator.xml
@@ -29,6 +29,8 @@
   <command>filterator</command>
   <arg choice='opt'>-d <replaceable>dir</replaceable></arg>
   <arg choice='opt'>-n</arg>
+  <arg choice='opt'>-s <replaceable>minsize</replaceable></arg>
+  <arg choice='opt'>-x</arg>
 </cmdsynopsis>
 
 </refsynopsisdiv>
@@ -101,10 +103,11 @@ removed.  This is recommended for comparing C code; it prevents the
 comparison from being fooled by differences in indent style.</para>
 
 <para>The <option>-r</option> option removes comments.  This is only
-effective in conjunction with <option>-C</option>. All // comments,
+effective in conjunction with <option>-C</option>. In C files, ll // comments,
 but only "winged" /* comments with the start and end of comment on the
-same line are ignored.  Block /* comments are retained, but the
-beginning /* and ending */ are ignored, </para>
+same line are ignored; also, block /* comments are retained, but the
+beginning /* and ending */ are ignored, In other files, all #
+comments are removed.</para>
 
 <para>The <option>-x</option> enables some debugging output.  It
 is for developers; if you need to understand it, read the code.</para>
@@ -121,14 +124,18 @@ percentage of printable characters near the front of the file is above
 <para><application>filterator</application> is a postprocessor for the
 SCF-B output of <application>comparator</application> that produces an
 actual code listing.  By default, it throws away ranges that appear to
-be noise.  The noise test is to throw away whitespace, C syntax,
+be noise.  The noise test for C files is to throw away whitespace, C syntax,
 #include lines and a few common macros and see if anything is left.
-The <option>-n</option> suppresses noise filtering.  The
+The noise test for shell files throws away Bourne-shell keywords</para>
+
+<para>The <option>-n</option> suppresses noise filtering.  The
 <option>-d</option> acts as it does for
 <application>comparator</application>.  The <option>-s</option> option
 sets the minimum size of overlap to be reported; setting this to a
-slightly larger number than the <application>comparator</application> shred
-size may be a useful way to filter out spurious matches.</para>
+slightly larger number than the <application>comparator</application>
+shred size may be a useful way to filter out spurious matches. The
+<option>-x</option> enables some debugging output.  It is for
+developers; if you need to understand it, read the code.</para>
 
 <para>Occasionally the <application>filterator</application> output
 looks as through the code has failed to properly merge two or more
diff --git a/shredtree.c b/shredtree.c
index 951d28a..b361eb7 100644
--- a/shredtree.c
+++ b/shredtree.c
@@ -70,24 +70,33 @@ static int eligible(const char *file)
 static int normalize(char *buf)
 /* normalize a buffer in place, return 0 if it should be skipped */
 {
-    if (remove_comments && remove_braces)	/* remove_c_comments */
-    {
-	char	*ss = strstr(buf, "//");
-
-	if (ss)
-	    *ss = '\0';
+    if (remove_comments)
+	if (remove_braces)	/* remove C comments */
+	{
+	    char	*ss = strstr(buf, "//");
+
+	    if (ss)
+		*ss = '\0';
+	    else
+	    {
+		char *start = strstr(buf, "/*"), *end = strstr(buf, "*/");
+
+		if (start && end && start < end)
+		    strcpy(start, end+2);
+		else if (start && !end)
+		    *start = '\0';
+		else if (end && !start)
+		    *end = '\0';
+	    }
+	}
 	else
 	{
-	    char *start = strstr(buf, "/*"), *end = strstr(buf, "*/");
-
-	    if (start && end && start < end)
-		strcpy(start, end+2);
-	    else if (start && !end)
-		*start = '\0';
-	    else if (end && !start)
-		*end = '\0';
+	    char	*ss = strchr(buf, '#');
+
+	    if (ss)
+		*ss = '\0';
 	}
-    }
+
     if (remove_whitespace)	/* strip whitespace, ignore blank lines */
     {
 	char *tp, *sp;
-- 
2.43.0