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
This commit is contained in:
Todd 2015-01-22 17:43:38 -06:00 committed by David Bremner
parent 0de999aab5
commit b04bc967f9
3 changed files with 11 additions and 3 deletions

View file

@ -254,6 +254,7 @@ static prefix_t PROBABILISTIC_PREFIX[]= {
{ "from", "XFROM" }, { "from", "XFROM" },
{ "to", "XTO" }, { "to", "XTO" },
{ "attachment", "XATTACHMENT" }, { "attachment", "XATTACHMENT" },
{ "mimetype", "XMIMETYPE"},
{ "subject", "XSUBJECT"}, { "subject", "XSUBJECT"},
}; };

View file

@ -318,6 +318,16 @@ _index_mime_part (notmuch_message_t *message,
return; 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)) { if (GMIME_IS_MULTIPART (part)) {
GMimeMultipart *multipart = GMIME_MULTIPART (part); GMimeMultipart *multipart = GMIME_MULTIPART (part);
int i; int i;

View file

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