From: Kevin McCarthy <kevin@8t8.us>
To: notmuch@notmuchmail.org
Subject: [PATCH 1/2] notmuch-mutt: use notmuch --duplicate flag
Date: Wed,  4 Sep 2013 19:05:50 -0700
Message-Id: <1378346751-25548-2-git-send-email-kevin@8t8.us>
In-Reply-To: <1378346751-25548-1-git-send-email-kevin@8t8.us>
References: <1378346751-25548-1-git-send-email-kevin@8t8.us>
Cc: zack@upsilon.cc
Precedence: list

Change notmuch-mutt to use the new --duplicate=1 flag for duplicate
removal.  This will remove duplicates based on message-id at the
notmuch level.  Previously we were using fdupes or generating sha sums
after the search.

This version will be faster, but will enable the possibility of hiding
search results due to accidental/malicious duplicate message-ids.
---
 contrib/notmuch-mutt/README       |  5 ---
 contrib/notmuch-mutt/notmuch-mutt | 64 +++++++--------------------------------
 2 files changed, 11 insertions(+), 58 deletions(-)

diff --git a/contrib/notmuch-mutt/README b/contrib/notmuch-mutt/README
index e00035c..382ac91 100644
--- a/contrib/notmuch-mutt/README
+++ b/contrib/notmuch-mutt/README
@@ -41,11 +41,6 @@ To *run* notmuch-mutt you will need Perl with the following libraries:
   (Debian package: libstring-shellquote-perl)
 - Term::ReadLine <http://search.cpan.org/~hayashi/Term-ReadLine-Gnu/>
   (Debian package: libterm-readline-gnu-perl)
-- File::Which <http://search.cpan.org/dist/File-Which/>
-  (Debian package: libfile-which-perl)
-
-The --remove-dups option will use fdupes <https://code.google.com/p/fdupes/>
-if it is installed.  Version fdupes-1.50-PR2 or higher is required.
 
 To *build* notmuch-mutt documentation you will need:
 
diff --git a/contrib/notmuch-mutt/notmuch-mutt b/contrib/notmuch-mutt/notmuch-mutt
index 00c5ef8..c69b35c 100755
--- a/contrib/notmuch-mutt/notmuch-mutt
+++ b/contrib/notmuch-mutt/notmuch-mutt
@@ -18,8 +18,6 @@ use Mail::Box::Maildir;
 use Pod::Usage;
 use String::ShellQuote;
 use Term::ReadLine;
-use Digest::SHA;
-use File::Which;
 
 
 my $xdg_cache_dir = "$ENV{HOME}/.cache";
@@ -36,65 +34,22 @@ sub empty_maildir($) {
     $folder->close();
 }
 
-# Match files by size and SHA-256; then delete duplicates
-sub builtin_remove_dups($) {
-    my ($maildir) = @_;
-    my (%size_to_files, %sha_to_files);
-
-    # Group files by matching sizes
-    foreach my $file (glob("$maildir/cur/*")) {
-        my $size = -s $file;
-        push(@{$size_to_files{$size}}, $file) if $size;
-    }
-
-    foreach my $same_size_files (values %size_to_files) {
-        # Don't run sha unless there is another file of the same size
-        next if scalar(@$same_size_files) < 2;
-        %sha_to_files = ();
-
-        # Group files with matching sizes by SHA-256
-        foreach my $file (@$same_size_files) {
-            open(my $fh, '<', $file) or next;
-            binmode($fh);
-            my $sha256hash = Digest::SHA->new(256)->addfile($fh)->hexdigest;
-            close($fh);
-
-            push(@{$sha_to_files{$sha256hash}}, $file);
-        }
-
-        # Remove duplicates
-        foreach my $same_sha_files (values %sha_to_files) {
-            next if scalar(@$same_sha_files) < 2;
-            unlink(@{$same_sha_files}[1..$#$same_sha_files]);
-        }
-    }
-}
-
-# Use either fdupes or the built-in scanner to detect and remove duplicate
-# search results in the maildir
-sub remove_duplicates($) {
-    my ($maildir) = @_;
-
-    my $fdupes = which("fdupes");
-    if ($fdupes) {
-      system("$fdupes --hardlinks --symlinks --delete --noprompt"
-             . " --quiet $maildir/cur/ > /dev/null");
-    } else {
-        builtin_remove_dups($maildir);
-    }
-}
-
 # search($maildir, $remove_dups, $query)
 # search mails according to $query with notmuch; store results in $maildir
 sub search($$$) {
     my ($maildir, $remove_dups, $query) = @_;
+    my $dup_option = "";
+
     $query = shell_quote($query);
 
+    if ($remove_dups) {
+      $dup_option = "--duplicate=1";
+    }
+
     empty_maildir($maildir);
-    system("notmuch search --output=files $query"
+    system("notmuch search --output=files $dup_option $query"
 	   . " | sed -e 's: :\\\\ :g'"
 	   . " | xargs --no-run-if-empty ln -s -t $maildir/cur/");
-    remove_duplicates($maildir) if ($remove_dups);
 }
 
 sub prompt($$) {
@@ -252,7 +207,10 @@ Instead of using command line search terms, prompt the user for them (only for
 
 =item --remove-dups
 
-Remove duplicates from search results.
+Remove emails with duplicate message-ids from search results.  (Passes
+--duplicate=1 to notmuch search command.)  Note this can hide search
+results if an email accidentally or maliciously uses the same message-id
+as a different email.
 
 =item -h
 
-- 
1.8.4.rc3