X-Git-Url: https://git.notmuchmail.org/git?p=notmuch;a=blobdiff_plain;f=lib%2Fdatabase.cc;h=415b0d77c3439abb9165d8236c5106d3f1cfffee;hp=c91e97c125940b384a3bd24963df6cbeedd88acb;hb=328626d0fd17910eec5d8b5b51dda46f4bbd8189;hpb=e3046c688be7a28e7dcfbce5fa54074917fd9904

diff --git a/lib/database.cc b/lib/database.cc
index c91e97c1..415b0d77 100644
--- a/lib/database.cc
+++ b/lib/database.cc
@@ -44,7 +44,8 @@ typedef struct {
 
 /* Here's the current schema for our database (for NOTMUCH_DATABASE_VERSION):
  *
- * We currently have two different types of documents: mail and directory.
+ * We currently have two different types of documents (mail and
+ * directory) and also some metadata.
  *
  * Mail document
  * -------------
@@ -118,6 +119,49 @@ typedef struct {
  *
  * The data portion of a directory document contains the path of the
  * directory (relative to the database path).
+ *
+ * Database metadata
+ * -----------------
+ * Xapian allows us to store arbitrary name-value pairs as
+ * "metadata". We currently use the following metadata names with the
+ * given meanings:
+ *
+ *	version		The database schema version, (which is distinct
+ *			from both the notmuch package version (see
+ *			notmuch --version) and the libnotmuch library
+ *			version. The version is stored as an base-10
+ *			ASCII integer. The initial database version
+ *			was 1, (though a schema existed before that
+ *			were no "version" database value existed at
+ *			all). Succesive versions are allocated as
+ *			changes are made to the database (such as by
+ *			indexing new fields).
+ *
+ *	last_thread_id	The last thread ID generated. This is stored
+ *			as a 16-byte hexadecimal ASCII representation
+ *			of a 64-bit unsigned integer. The first ID
+ *			generated is 1 and the value will be
+ *			incremented for each thread ID.
+ *
+ *	thread_id_*	A pre-allocated thread ID for a particular
+ *			message. This is actually an arbitarily large
+ *			family of metadata name. Any particular name
+ *			is formed by concatenating "thread_id_" with a
+ *			message ID. The value stored is a thread ID.
+ *
+ *			These thread ID metadata values are stored
+ *			whenever a message references a parent message
+ *			that does not yet exist in the database. A
+ *			thread ID will be allocated and stored, and if
+ *			the message is later added, the stored thread
+ *			ID will be used (and the metadata value will
+ *			be cleared).
+ *
+ *			Even before a message is added, it's
+ *			pre-allocated thread ID is useful so that all
+ *			descendant messages that reference this common
+ *			parent can be recognized as belonging to the
+ *			same thread.
  */
 
 /* With these prefix values we follow the conventions published here:
@@ -1111,12 +1155,40 @@ notmuch_database_get_directory (notmuch_database_t *notmuch,
     return _notmuch_directory_create (notmuch, path, &status);
 }
 
+static const char *
+_notmuch_database_generate_thread_id (notmuch_database_t *notmuch)
+{
+    /* 16 bytes (+ terminator) for hexadecimal representation of
+     * a 64-bit integer. */
+    static char thread_id[17];
+    Xapian::WritableDatabase *db;
+
+    db = static_cast <Xapian::WritableDatabase *> (notmuch->xapian_db);
+
+    notmuch->last_thread_id++;
+
+    sprintf (thread_id, "%016" PRIx64, notmuch->last_thread_id);
+
+    db->set_metadata ("last_thread_id", thread_id);
+
+    return thread_id;
+}
+
+static char *
+_get_metadata_thread_id_key (void *ctx, const char *message_id)
+{
+    return talloc_asprintf (ctx, "thread_id_%s", message_id);
+}
+
 /* Find the thread ID to which the message with 'message_id' belongs.
  *
- * Returns NULL if no message with message ID 'message_id' is in the
- * database.
+ * Always returns a newly talloced string belonging to 'ctx'.
  *
- * Otherwise, returns a newly talloced string belonging to 'ctx'.
+ * Note: If there is no message in the database with the given
+ * 'message_id' then a new thread_id will be allocated for this
+ * message and stored in the database metadata, (where this same
+ * thread ID can be looked up if the message is added to the database
+ * later).
  */
 static const char *
 _resolve_message_id_to_thread_id (notmuch_database_t *notmuch,
@@ -1124,19 +1196,41 @@ _resolve_message_id_to_thread_id (notmuch_database_t *notmuch,
 				  const char *message_id)
 {
     notmuch_message_t *message;
-    const char *ret = NULL;
+    string thread_id_string;
+    const char *thread_id;
+    char *metadata_key;
+    Xapian::WritableDatabase *db;
 
     message = notmuch_database_find_message (notmuch, message_id);
-    if (message == NULL)
-	goto DONE;
 
-    ret = talloc_steal (ctx, notmuch_message_get_thread_id (message));
+    if (message) {
+	thread_id = talloc_steal (ctx, notmuch_message_get_thread_id (message));
 
-  DONE:
-    if (message)
 	notmuch_message_destroy (message);
 
-    return ret;
+	return thread_id;
+    }
+
+    /* Message has not been seen yet.
+     *
+     * We may have seen a reference to it already, in which case, we
+     * can return the thread ID stored in the metadata. Otherwise, we
+     * generate a new thread ID and store it there.
+     */
+    db = static_cast <Xapian::WritableDatabase *> (notmuch->xapian_db);
+    metadata_key = _get_metadata_thread_id_key (ctx, message_id);
+    thread_id_string = notmuch->xapian_db->get_metadata (metadata_key);
+
+    if (thread_id_string.empty()) {
+	thread_id = _notmuch_database_generate_thread_id (notmuch);
+	db->set_metadata (metadata_key, thread_id);
+    } else {
+	thread_id = thread_id_string.c_str();
+    }
+
+    talloc_free (metadata_key);
+
+    return thread_id;
 }
 
 static notmuch_status_t
@@ -1295,40 +1389,30 @@ _notmuch_database_link_message_to_children (notmuch_database_t *notmuch,
     return ret;
 }
 
-static const char *
-_notmuch_database_generate_thread_id (notmuch_database_t *notmuch)
-{
-    /* 16 bytes (+ terminator) for hexadecimal representation of
-     * a 64-bit integer. */
-    static char thread_id[17];
-    Xapian::WritableDatabase *db;
-
-    db = static_cast <Xapian::WritableDatabase *> (notmuch->xapian_db);
-
-    notmuch->last_thread_id++;
-
-    sprintf (thread_id, "%016" PRIx64, notmuch->last_thread_id);
-
-    db->set_metadata ("last_thread_id", thread_id);
-
-    return thread_id;
-}
-
 /* Given a (mostly empty) 'message' and its corresponding
  * 'message_file' link it to existing threads in the database.
  *
- * We first look at 'message_file' and its link-relevant headers
- * (References and In-Reply-To) for message IDs. We also look in the
- * database for existing message that reference 'message'. In either
- * case, we will assign to the current message the first thread_id
+ * The first check is in the metadata of the database to see if we
+ * have pre-allocated a thread_id in advance for this message, (which
+ * would have happened if a message was previously added that
+ * referenced this one).
+ *
+ * Second, we look at 'message_file' and its link-relevant headers
+ * (References and In-Reply-To) for message IDs.
+ *
+ * Finally, we look in the database for existing message that
+ * reference 'message'.
+ *
+ * In all cases, we assign to the current message the first thread_id
  * found (through either parent or child). We will also merge any
  * existing, distinct threads where this message belongs to both,
  * (which is not uncommon when mesages are processed out of order).
  *
- * Finally, if not thread ID has been found through parent or child,
- * we call _notmuch_message_generate_thread_id to generate a new
- * generates a new thread ID if the message doesn't connect to any
- * existing threads.
+ * Finally, if no thread ID has been found through parent or child, we
+ * call _notmuch_message_generate_thread_id to generate a new thread
+ * ID. This should only happen for new, top-level messages, (no
+ * References or In-Reply-To header in this message, and no previously
+ * added message refers to this message).
  */
 static notmuch_status_t
 _notmuch_database_link_message (notmuch_database_t *notmuch,
@@ -1336,7 +1420,30 @@ _notmuch_database_link_message (notmuch_database_t *notmuch,
 				notmuch_message_file_t *message_file)
 {
     notmuch_status_t status;
-    const char *thread_id = NULL;
+    const char *message_id, *thread_id = NULL;
+    char *metadata_key;
+    string stored_id;
+
+    message_id = notmuch_message_get_message_id (message);
+    metadata_key = _get_metadata_thread_id_key (message, message_id);
+
+    /* Check if we have already seen related messages to this one.
+     * If we have then use the thread_id that we stored at that time.
+     */
+    stored_id = notmuch->xapian_db->get_metadata (metadata_key);
+    if (! stored_id.empty()) {
+        Xapian::WritableDatabase *db;
+
+	db = static_cast <Xapian::WritableDatabase *> (notmuch->xapian_db);
+
+	/* Clear the metadata for this message ID. We don't need it
+	 * anymore. */
+        db->set_metadata (metadata_key, "");
+        thread_id = stored_id.c_str();
+
+        _notmuch_message_add_term (message, "thread", thread_id);
+    }
+    talloc_free (metadata_key);
 
     status = _notmuch_database_link_message_to_parents (notmuch, message,
 							message_file,