database: Add "replyto" to the database schema documentation.

[notmuch] / lib / database.cc

diff --git a/lib/database.cc b/lib/database.cc
index 3c8d626e93d66aeabc2715a4889aacfe7bffd88a..5b677d42007fcae27e2632701d2c4073a664e44b 100644 (file)
--- a/lib/database.cc
+++ b/lib/database.cc
@@ -42,7 +42,8 @@ typedef struct {
  * Mail document
  * -------------
  * A mail document is associated with a particular email message file
- * on disk. It is indexed with the following prefixed terms:
+ * on disk. It is indexed with the following prefixed terms which the
+ * database uses to construct threads, etc.:
  *
  *    Single terms of given prefix:
  *
@@ -53,15 +54,14 @@ typedef struct {
  *
  *     thread: The ID of the thread to which the mail belongs
  *
+ *     replyto: The ID from the In-Reply-To header of the mail (if any).
+ *
  *    Multiple terms of given prefix:
  *
- *     ref:    All unresolved message IDs from In-Reply-To and
- *             References headers in the message. (Once a referenced
- *             message is added to the database and the thread IDs
- *             are linked the corresponding "ref" term is dropped
- *             from the message document.)
+ *     reference: All message IDs from In-Reply-To and Re ferences
+ *                headers in the message.
  *
- *     tag:    Any tags associated with this message by the user.
+ *     tag:       Any tags associated with this message by the user.
  *
  *    A mail document also has two values:
  *
@@ -70,6 +70,11 @@ typedef struct {
  *
  *     MESSAGE_ID:     The unique ID of the mail mess (see "id" above)
  *
+ * In addition, terms from the content of the message are added with
+ * "from", "to", "attachment", and "subject" prefixes for use by the
+ * user in searching. But the database doesn't really care itself
+ * about any of these.
+ *
  * Timestamp document
  * ------------------
  * A timestamp document is used by a client of the notmuch library to
@@ -104,7 +109,7 @@ typedef struct {
 
 prefix_t BOOLEAN_PREFIX_INTERNAL[] = {
     { "type", "T" },
-    { "ref", "XREFERENCE" },
+    { "reference", "XREFERENCE" },
     { "replyto", "XREPLYTO" },
     { "timestamp", "XTIMESTAMP" },
 };
@@ -371,9 +376,16 @@ _parse_message_id (void *ctx, const char *message_id, const char **next)
 }
 
 /* Parse a References header value, putting a (talloc'ed under 'ctx')
- * copy of each referenced message-id into 'hash'. */
+ * copy of each referenced message-id into 'hash'.
+ *
+ * We explicitly avoid including any reference identical to
+ * 'message_id' in the result (to avoid mass confusion when a single
+ * message references itself cyclically---and yes, mail messages are
+ * not infrequent in the wild that do this---don't ask me why).
+*/
 static void
 parse_references (void *ctx,
+                 const char *message_id,
                  GHashTable *hash,
                  const char *refs)
 {
@@ -385,7 +397,7 @@ parse_references (void *ctx,
     while (*refs) {
        ref = _parse_message_id (ctx, refs, &refs);
 
-       if (ref)
+       if (ref && strcmp (ref, message_id))
            g_hash_table_insert (hash, ref, NULL);
     }
 }
@@ -697,7 +709,7 @@ _notmuch_database_link_message_to_parents (notmuch_database_t *notmuch,
                                           const char **thread_id)
 {
     GHashTable *parents = NULL;
-    const char *refs, *in_reply_to;
+    const char *refs, *in_reply_to, *in_reply_to_message_id;
     GList *l, *keys = NULL;
     notmuch_status_t ret = NOTMUCH_STATUS_SUCCESS;
 
@@ -705,12 +717,21 @@ _notmuch_database_link_message_to_parents (notmuch_database_t *notmuch,
                                     _my_talloc_free_for_g_hash, NULL);
 
     refs = notmuch_message_file_get_header (message_file, "references");
-    parse_references (message, parents, refs);
+    parse_references (message, notmuch_message_get_message_id (message),
+                     parents, refs);
 
     in_reply_to = notmuch_message_file_get_header (message_file, "in-reply-to");
-    parse_references (message, parents, in_reply_to);
-    _notmuch_message_add_term (message, "replyto",
-                              _parse_message_id (message, in_reply_to, NULL));
+    parse_references (message, notmuch_message_get_message_id (message),
+                     parents, in_reply_to);
+
+    /* Carefully avoid adding any self-referential in-reply-to term. */
+    in_reply_to_message_id = _parse_message_id (message, in_reply_to, NULL);
+    if (strcmp (in_reply_to_message_id,
+               notmuch_message_get_message_id (message)))
+    {
+       _notmuch_message_add_term (message, "replyto",
+                            _parse_message_id (message, in_reply_to, NULL));
+    }
 
     keys = g_hash_table_get_keys (parents);
     for (l = keys; l; l = l->next) {
@@ -723,7 +744,8 @@ _notmuch_database_link_message_to_parents (notmuch_database_t *notmuch,
                                                             parent_message_id);
 
        if (parent_thread_id == NULL) {
-           _notmuch_message_add_term (message, "ref", parent_message_id);
+           _notmuch_message_add_term (message, "reference",
+                                      parent_message_id);
        } else {
            if (*thread_id == NULL) {
                *thread_id = talloc_strdup (message, parent_thread_id);
@@ -757,7 +779,7 @@ _notmuch_database_link_message_to_children (notmuch_database_t *notmuch,
     notmuch_status_t ret = NOTMUCH_STATUS_SUCCESS;
     notmuch_private_status_t private_status;
 
-    find_doc_ids (notmuch, "ref", message_id, &child, &children_end);
+    find_doc_ids (notmuch, "reference", message_id, &child, &children_end);
 
     for ( ; child != children_end; child++) {
 
@@ -774,7 +796,7 @@ _notmuch_database_link_message_to_children (notmuch_database_t *notmuch,
            *thread_id = talloc_strdup (message, child_thread_id);
            _notmuch_message_add_term (message, "thread", *thread_id);
        } else if (strcmp (*thread_id, child_thread_id)) {
-           _notmuch_message_remove_term (child_message, "ref",
+           _notmuch_message_remove_term (child_message, "reference",
                                          message_id);
            _notmuch_message_sync (child_message);
            ret = _merge_threads (notmuch, *thread_id, child_thread_id);
@@ -912,7 +934,6 @@ notmuch_database_add_message (notmuch_database_t *notmuch,
         * database). */
 
        message = _notmuch_message_create_for_message_id (notmuch,
-                                                         notmuch,
                                                          message_id,
                                                          &private_status);