[PATCH] Index Content-Type of attachments with a contenttype prefix

[Todd]

I wanted to tag messages with calendar invitations, but couldn't as
the information wasn't indexed.

This patch allows for queries for like:

Find calendar invites
- contenttype:text/calendar or contenttype:applicaton/ics

Find any image attachments
- contenttype:image

Find all patches
- contenttype:text/x-patch


- Todd

---
 NEWS                               |  6 ++++++
 completion/notmuch-completion.bash |  2 +-
 doc/man7/notmuch-search-terms.rst  |  6 ++++++
 emacs/notmuch.el                   |  2 +-
 lib/database.cc                    |  1 +
 lib/index.cc                       |  5 +++++
 test/T190-multipart.sh             | 32 ++++++++++++++++++++++++++++++++
 7 files changed, 52 insertions(+), 2 deletions(-)

diff --git a/NEWS b/NEWS
index 44e8d05..5f4622c 100644
--- a/NEWS
+++ b/NEWS
@@ -15,6 +15,12 @@ keyboard shortcuts to saved searches.
 Command-Line Interface
 ----------------------

+There is a new `contenttype:` search prefix
+
+  The new `contenttype:` search prefix allows searching for the
+  content-type of attachments, which is now indexed by `notmuch
+  insert`. See the `notmuch-search-terms` manual page for details.
+
 Stopped `notmuch dump` failing if someone writes to the database

   The dump command now takes the write lock when running. This
diff --git a/completion/notmuch-completion.bash b/completion/notmuch-completion.bash
index d58dc8b..05b5969 100644
--- a/completion/notmuch-completion.bash
+++ b/completion/notmuch-completion.bash
@@ -61,7 +61,7 @@ _notmuch_search_terms()
 		sed "s|^$path/||" | grep -v "\(^\|/\)\(cur\|new\|tmp\)$" ) )
 	    ;;
 	*)
-	    local search_terms="from: to: subject: attachment: tag: id: thread: folder: path: date:"
+	    local search_terms="from: to: subject: attachment: contenttype: tag: id: thread: folder: path: date:"
 	    compopt -o nospace
 	    COMPREPLY=( $(compgen -W "${search_terms}" -- ${cur}) )
 	    ;;
diff --git a/doc/man7/notmuch-search-terms.rst b/doc/man7/notmuch-search-terms.rst
index 1acdaa0..d126ce6 100644
--- a/doc/man7/notmuch-search-terms.rst
+++ b/doc/man7/notmuch-search-terms.rst
@@ -40,6 +40,8 @@ indicate user-supplied values):

 -  attachment:<word>

+-  contenttype:<word>
+
 -  tag:<tag> (or is:<tag>)

 -  id:<message-id>
@@ -66,6 +68,10 @@ by including quotation marks around the phrase, immediately following
 The **attachment:** prefix can be used to search for specific filenames
 (or extensions) of attachments to email messages.

+The **contenttype:** prefix can be used to search for specific
+content-types of attachments to email messages (as specified by the
+sender).
+
 For **tag:** and **is:** valid tag values include **inbox** and
 **unread** by default for new messages added by **notmuch new** as well
 as any other tag values added manually with **notmuch tag**.
diff --git a/emacs/notmuch.el b/emacs/notmuch.el
index 218486a..702700c 100644
--- a/emacs/notmuch.el
+++ b/emacs/notmuch.el
@@ -858,7 +858,7 @@ PROMPT is the string to prompt with."
   (lexical-let
       ((completions
 	(append (list "folder:" "path:" "thread:" "id:" "date:" "from:" "to:"
-		      "subject:" "attachment:")
+		      "subject:" "attachment:" "contenttype:")
 		(mapcar (lambda (tag)
 			  (concat "tag:" (notmuch-escape-boolean-term tag)))
 			(process-lines notmuch-command "search" "--output=tags" "*")))))
diff --git a/lib/database.cc b/lib/database.cc
index 3601f9d..a7a64c9 100644
--- a/lib/database.cc
+++ b/lib/database.cc
@@ -254,6 +254,7 @@ static prefix_t PROBABILISTIC_PREFIX[]= {
     { "from",			"XFROM" },
     { "to",			"XTO" },
     { "attachment",		"XATTACHMENT" },
+    { "contenttype",		"XCONTENTTYPE"},
     { "subject",		"XSUBJECT"},
 };

diff --git a/lib/index.cc b/lib/index.cc
index 1a2e63d..c3f7c6b 100644
--- a/lib/index.cc
+++ b/lib/index.cc
@@ -346,6 +346,11 @@ _index_mime_part (notmuch_message_t *message,
 	return;
     }

+    GMimeContentType*  content_type = g_mime_object_get_content_type(part);
+    if (content_type) {
+	_notmuch_message_gen_terms (message, "contenttype", g_mime_content_type_to_string(content_type));
+    }
+
     if (GMIME_IS_MESSAGE_PART (part)) {
 	GMimeMessage *mime_message;

diff --git a/test/T190-multipart.sh b/test/T190-multipart.sh
index 85cbf67..e3270a7 100755
--- a/test/T190-multipart.sh
+++ b/test/T190-multipart.sh
@@ -104,6 +104,30 @@ Content-Transfer-Encoding: base64
 7w0K
 --==-=-=--
 EOF
+
+cat <<EOF > content_types
+From: Todd <todd at electricoding.com>
+To: todd at electricoding.com
+Subject: odd content types
+Date: Fri, 05 Jan 2001 15:42:57 +0000
+User-Agent: Notmuch/0.5 (http://notmuchmail.org) Emacs/23.3.1 (i486-pc-linux-gnu)
+Message-ID: <87liy5ap01.fsf at yoom.home.cworth.org>
+MIME-Version: 1.0
+Content-Type: multipart/alternative; boundary="==-=-=="
+
+--==-=-==
+Content-Type: application/unique_identifier
+
+<p>This is an embedded message, with a multipart/alternative part.</p>
+
+--==-=-==
+Content-Type: text/some_other_identifier
+
+This is an embedded message, with a multipart/alternative part.
+
+--==-=-==--
+EOF
+cat content_types >> ${MAIL_DIR}/odd_content_type
 notmuch new > /dev/null

 test_begin_subtest "--format=text --part=0, full message"
@@ -727,4 +751,12 @@ test_begin_subtest "html parts included"
 notmuch show --format=json --include-html id:htmlmessage > OUTPUT
 test_expect_equal_json "$(cat OUTPUT)" "$(cat EXPECTED.withhtml)"

+test_begin_subtest "indexes content-type"
+output=$(notmuch search contenttype:application/unique_identifier | notmuch_search_sanitize)
+test_expect_equal "$output" "thread:XXX   2001-01-05 [1/1] Todd; odd content types (inbox unread)"
+
+output=$(notmuch search contenttype:text/some_other_identifier | notmuch_search_sanitize)
+test_expect_equal "$output" "thread:XXX   2001-01-05 [1/1] Todd; odd content types (inbox unread)"
+
+
 test_done
--
1.9.1