[Patch v4 06/12] lib: index message files with duplicate message-ids

[David Bremner]

The corresponding xapian document just gets more terms added to it,
but this doesn't seem to break anything. Values on the other hand get
overwritten, which is a bit annoying, but arguably it is not worse to
take the values (from, subject, date) from the last file indexed
rather than the first.
---
 lib/add-message.cc         | 19 +++++++++++--------
 test/T160-json.sh          |  4 ++--
 test/T670-duplicate-mid.sh |  9 +++++++--
 3 files changed, 20 insertions(+), 12 deletions(-)

diff --git a/lib/add-message.cc b/lib/add-message.cc
index 2922eaa9..f0a80c4f 100644
--- a/lib/add-message.cc
+++ b/lib/add-message.cc
@@ -529,19 +529,22 @@ notmuch_database_add_message (notmuch_database_t *notmuch,
 	    if (is_ghost)
 		/* Convert ghost message to a regular message */
 		_notmuch_message_remove_term (message, "type", "ghost");
-	    ret = _notmuch_database_link_message (notmuch, message,
+	}
+
+	ret = _notmuch_database_link_message (notmuch, message,
 						  message_file, is_ghost);
-	    if (ret)
-		goto DONE;
+	if (ret)
+	    goto DONE;
 
+	if (is_new || is_ghost)
 	    _notmuch_message_set_header_values (message, date, from, subject);
 
-	    ret = _notmuch_message_index_file (message, message_file);
-	    if (ret)
-		goto DONE;
-	} else {
+	ret = _notmuch_message_index_file (message, message_file);
+	if (ret)
+	    goto DONE;
+
+	if (! is_new && !is_ghost)
 	    ret = NOTMUCH_STATUS_DUPLICATE_MESSAGE_ID;
-	}
 
 	_notmuch_message_sync (message);
     } catch (const Xapian::Error &error) {
diff --git a/test/T160-json.sh b/test/T160-json.sh
index ac51895e..07955a2b 100755
--- a/test/T160-json.sh
+++ b/test/T160-json.sh
@@ -71,8 +71,8 @@ test_begin_subtest "Format version: too high"
 test_expect_code 21 "notmuch search --format-version=999 \\*"
 
 test_begin_subtest "Show message: multiple filenames"
-add_message "[id]=message-id at example.com [filename]=copy1"
-add_message "[id]=message-id at example.com [filename]=copy2"
+add_message '[id]=message-id at example.com [filename]=copy1 [date]="Fri, 05 Jan 2001 15:43:52 +0000"'
+add_message '[id]=message-id at example.com [filename]=copy2 [date]="Fri, 05 Jan 2001 15:43:52 +0000"'
 cat <<EOF > EXPECTED
 [
     [
diff --git a/test/T670-duplicate-mid.sh b/test/T670-duplicate-mid.sh
index ced28a21..137cb6a5 100755
--- a/test/T670-duplicate-mid.sh
+++ b/test/T670-duplicate-mid.sh
@@ -5,8 +5,14 @@ test_description="duplicate message ids"
 add_message '[id]="duplicate"' '[subject]="message 1" [filename]=copy1'
 add_message '[id]="duplicate"' '[subject]="message 2" [filename]=copy2'
 
+test_begin_subtest 'First subject preserved'
+cat <<EOF > EXPECTED
+thread:XXX   2001-01-05 [1/1] Notmuch Test Suite; message 1 (inbox unread)
+EOF
+notmuch search id:duplicate | notmuch_search_sanitize > OUTPUT
+test_expect_equal_file EXPECTED OUTPUT
+
 test_begin_subtest 'Search for second subject'
-test_subtest_known_broken
 cat <<EOF >EXPECTED
 MAIL_DIR/copy1
 MAIL_DIR/copy2
@@ -16,7 +22,6 @@ test_expect_equal_file EXPECTED OUTPUT
 
 add_message '[id]="duplicate"' '[body]="sekrit" [filename]=copy3'
 test_begin_subtest 'search for body in duplicate file'
-test_subtest_known_broken
 cat <<EOF >EXPECTED
 MAIL_DIR/copy1
 MAIL_DIR/copy2
-- 
2.13.2