Failed attempt to improve program(s)

bc-dupe-checker.pl

@@ -3,12 +3,15 @@
 # given a file with the (unsorted) output of sha1sum, list duplicate files
 # fairly trivial to write
 
-require "bclib.pl";
+# "bc-dupe-checker.pl sha1file | xargs ls -l | sort -k5nr" helpful in
+# finding large duplicates
 
-chdir(tmpdir());
+push(@INC, "/usr/local/lib");
+require "bclib.pl";
+$dir = tmpdir();
 
-system("sort $ARGV[0] > sha1sorted.txt");
-$sha1s = read_file("sha1sorted.txt");
+system("sort $ARGV[0] > $dir/sha1sorted.txt");
+$sha1s = read_file("$dir/sha1sorted.txt");
 
 for $i (split(/\n/, $sha1s)) {
   # confirm the line is really sha1 or md5 followed by filename
@@ -22,7 +25,8 @@
 
   # are we seeing the same sha1 again?
   if ($sha1 eq $cur) {
-    print "'$file'\n";
+#    print qq%"$file";: $cur\n%;
+    print qq%"$file"\n%;
     next;
   }
 

bc-extract-attachments.pl

@@ -4,6 +4,7 @@
 # consistent "sha1" format. Recreates mailbox with pointers to
 # attachment files
 
+push(@INC,"/usr/local/lib");
 require "bclib.pl";
 
 # list of types we can handle (excl image/jpeg and octet-stream, which
@@ -23,6 +24,7 @@
     handle_attachment($msg);
     $msg=$_;
   } else {
+    debug("READ: $_");
     $msg = "$msg$_";
   }
 }
@@ -32,6 +34,7 @@
 
 sub handle_attachment {
   my($a)=@_;
+  debug("handle_attachment length:". length($a));
   my($fname, $ctype, $bound);
   # need a global to preserve uniqueness
   $attachnum++;
@@ -45,6 +48,7 @@ sub handle_attachment {
   }
 
   my($head,$body)=($1,$2);
+  debug("HEAD: $head");
 
   # if multipart, get content-type and boundary (if not, just get content-type)
   if ($head=~/Content-[Tt]ype: (.*?); boundary="(.*?)"/m) {
@@ -57,6 +61,7 @@ sub handle_attachment {
   }
 
   my($ctype)=$1;
+  debug("CTYPE: $ctype");
 
   # is this a multipart msg? if so, recurse
   if ($ctype=~m!multipart/(.*?)!i) {