lib: Separate all phrases indexed by _notmuch_message_gen_terms

This adds a 100 termpos gap between all phrases indexed by
_notmuch_message_gen_terms.  This fixes a bug where terms from the end
of one header and the beginning of another header could match together
in a single phrase and a separate bug where term positions of
un-prefixed terms overlapped.

This fix only affects newly indexed messages.  Messages that are
already indexed won't benefit from this fix without re-indexing, but
the fix won't make things any worse for existing messages.

diff --git a/lib/message.cc b/lib/message.cc
index 9243b769d2b0b77ffae9858b22e5af8cccf3774d..d0b7351e71796ad2e288a018cbc5ef00ff4fcb67 100644 (file)
--- a/lib/message.cc
+++ b/lib/message.cc
@@ -1023,16 +1023,21 @@ _notmuch_message_gen_terms (notmuch_message_t *message,
        return NOTMUCH_PRIVATE_STATUS_NULL_POINTER;
 
     term_gen->set_document (message->doc);
-    term_gen->set_termpos (message->termpos);
 
     if (prefix_name) {
        const char *prefix = _find_prefix (prefix_name);
 
+       term_gen->set_termpos (message->termpos);
        term_gen->index_text (text, 1, prefix);
-       message->termpos = term_gen->get_termpos ();
+       /* Create a gap between this an the next terms so they don't
+        * appear to be a phrase. */
+       message->termpos = term_gen->get_termpos () + 100;
     }
 
+    term_gen->set_termpos (message->termpos);
     term_gen->index_text (text);
+    /* Create a term gap, as above. */
+    message->termpos = term_gen->get_termpos () + 100;
 
     return NOTMUCH_PRIVATE_STATUS_SUCCESS;
 }

diff --git a/test/T080-search.sh b/test/T080-search.sh
index 3f6b565fe622b753cd18e7fed72fdea713e61154..05027fb0fee0bfbc7b1548421220e860bef1144d 100755 (executable)
--- a/test/T080-search.sh
+++ b/test/T080-search.sh
@@ -170,14 +170,12 @@ EOF
 notmuch new > /dev/null
 
 test_begin_subtest "headers do not have adjacent term positions"
-test_subtest_known_broken
 # Regression test for a bug where term positions for non-prefixed
 # terms weren't updated
 output=$(notmuch search id:termpos and '"com dest"')
 test_expect_equal "$output" ""
 
 test_begin_subtest "parts have non-overlapping term positions"
-test_subtest_known_broken
 output=$(notmuch search id:termpos and '"a y c"')
 test_expect_equal "$output" ""