Add indexing for the mimetype term

This adds the indexing support for the "mimetype:" term and removes
the broken test flag.  The indexing is probablistic in Xapian terms,
which gives a better experience to end users.  Standard content-types
of the form "foo/bar" are automatically interpreted as phrases in
Xapian due to the embedded slash.

Assume, separate messages with application/pdf and application/x-pdf
are indexed, then:

- mimetype:application/x-pdf will find only the application/x-pdf
- mimetype:application/pdf will find only the application/pdf
- mimetype:pdf will find both of the messages

diff --git a/lib/database.cc b/lib/database.cc
index 0d2c417214e87e79c7daf26301d33555b591775d..3974e2ed3a35c1278443095d452dbd1243b7fef2 100644 (file)
--- a/lib/database.cc
+++ b/lib/database.cc
@@ -254,6 +254,7 @@ static prefix_t PROBABILISTIC_PREFIX[]= {
     { "from",                  "XFROM" },
     { "to",                    "XTO" },
     { "attachment",            "XATTACHMENT" },
+    { "mimetype",              "XMIMETYPE"},
     { "subject",               "XSUBJECT"},
 };
 

diff --git a/lib/index.cc b/lib/index.cc
index 1a2e63df58e45a2f163f7ca61ab6a7740032314a..c88ed8d744334ba2f1e7acaf02e9c812ff14ed91 100644 (file)
--- a/lib/index.cc
+++ b/lib/index.cc
@@ -318,6 +318,16 @@ _index_mime_part (notmuch_message_t *message,
        return;
     }
 
+    GMimeContentType *content_type = g_mime_object_get_content_type(part);
+    if (content_type) {
+       char *mime_string = g_mime_content_type_to_string(content_type);
+       if (mime_string)
+       {
+           _notmuch_message_gen_terms (message, "mimetype", mime_string);
+           g_free(mime_string);
+       }
+    }
+
     if (GMIME_IS_MULTIPART (part)) {
        GMimeMultipart *multipart = GMIME_MULTIPART (part);
        int i;

diff --git a/test/T190-multipart.sh b/test/T190-multipart.sh
index a97dc282f10659c1dfd605a2249eeb1f7bf88287..ad8d29eafcc69802f6226fa60be5860da056d887 100755 (executable)
--- a/test/T190-multipart.sh
+++ b/test/T190-multipart.sh
@@ -752,17 +752,14 @@ notmuch show --format=json --include-html id:htmlmessage > OUTPUT
 test_expect_equal_json "$(cat OUTPUT)" "$(cat EXPECTED.withhtml)"
 
 test_begin_subtest "indexes mime-type #1"
-test_subtest_known_broken
 output=$(notmuch search mimetype:application/unique_identifier | notmuch_search_sanitize)
 test_expect_equal "$output" "thread:XXX   2014-01-12 [1/1] Todd; odd content types (inbox unread)"
 
 test_begin_subtest "indexes mime-type #2"
-test_subtest_known_broken
 output=$(notmuch search mimetype:text/some_other_identifier | notmuch_search_sanitize)
 test_expect_equal "$output" "thread:XXX   2014-01-12 [1/1] Todd; odd content types (inbox unread)"
 
 test_begin_subtest "indexes mime-type #3"
-test_subtest_known_broken
 output=$(notmuch search from:todd and mimetype:multipart/alternative | notmuch_search_sanitize)
 test_expect_equal "$output" "thread:XXX   2014-01-12 [1/1] Todd; odd content types (inbox unread)"