Make notmuch-mutt script more portable

[notmuch] / contrib / notmuch-mutt / notmuch-mutt

diff --git a/contrib/notmuch-mutt/notmuch-mutt b/contrib/notmuch-mutt/notmuch-mutt
index 00c5ef82d50d67d0fcac7c43794dcf6958ac3cb1..d33223bdd88e776acf79ae8b4ba2703ff1e6cc58 100755 (executable)
--- a/contrib/notmuch-mutt/notmuch-mutt
+++ b/contrib/notmuch-mutt/notmuch-mutt
@@ -1,8 +1,8 @@
-#!/usr/bin/perl -w
+#!/usr/bin/env perl
 #
 # notmuch-mutt - notmuch (of a) helper for Mutt
 #
-# Copyright: © 2011-2012 Stefano Zacchiroli <zack@upsilon.cc> 
+# Copyright: © 2011-2015 Stefano Zacchiroli <zack@upsilon.cc>
 # License: GNU General Public License (GPL), version 3 or above
 #
 # See the bottom of this file for more documentation.
@@ -13,13 +13,12 @@ use warnings;
 
 use File::Path;
 use Getopt::Long qw(:config no_getopt_compat);
-use Mail::Internet;
+use Mail::Header;
 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 +35,22 @@ 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);
+          . " | while IFS= read -r searchoutput; do ln -s \$searchoutput $maildir/cur/; done");
 }
 
 sub prompt($$) {
@@ -120,10 +76,29 @@ sub prompt($$) {
 }
 
 sub get_message_id() {
-    my $mail = Mail::Internet->new(\*STDIN);
-    my $mid = $mail->head->get("message-id") or return undef;
-    $mid =~ /^<(.*)>$/;        # get message-id value
-    return $1;
+    my $mid = undef;
+    my @headers = ();
+
+    while (<STDIN>) {  # collect header lines in @headers
+       push(@headers, $_);
+       last if $_ =~ /^$/;
+    }
+    my $head = Mail::Header->new(\@headers);
+    $mid = $head->get("message-id") or undef;
+
+    if ($mid) {  # Message-ID header found
+       $mid =~ /^<(.*)>$/;  # extract message id
+       $mid = $1;
+    } else {  # Message-ID header not found, synthesize a message id
+             # based on SHA1, as notmuch would do.  See:
+             # https://git.notmuchmail.org/git/notmuch/blob/HEAD:/lib/sha1.c
+       my $sha = Digest::SHA->new(1);
+       $sha->add($_) foreach(@headers);
+       $sha->addfile(\*STDIN);
+       $mid = 'notmuch-sha1-' . $sha->hexdigest;
+    }
+
+    return $mid;
 }
 
 sub search_action($$$@) {
@@ -158,9 +133,7 @@ sub tag_action(@) {
     my $mid = get_message_id();
     defined $mid or die "notmuch-mutt: cannot find Message-Id, abort.\n";
 
-    system("notmuch tag "
-          . shell_quote(join(' ', @_))
-          . " id:$mid");
+    system("notmuch", "tag", @_, "--", "id:$mid");
 }
 
 sub die_usage() {
@@ -252,7 +225,10 @@ 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