X-Git-Url: https://git.notmuchmail.org/git?p=notmuch;a=blobdiff_plain;f=lib%2Fdatabase.cc;h=415b0d77c3439abb9165d8236c5106d3f1cfffee;hp=6b8c9989ea4f9c75ada9df3ae0591fca1b65c20f;hb=328626d0fd17910eec5d8b5b51dda46f4bbd8189;hpb=909f52bd8c4bdfa11cd3e75e3d0959e0293689bd diff --git a/lib/database.cc b/lib/database.cc index 6b8c9989..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: @@ -147,6 +191,7 @@ prefix_t BOOLEAN_PREFIX_INTERNAL[] = { prefix_t BOOLEAN_PREFIX_EXTERNAL[] = { { "thread", "G" }, { "tag", "K" }, + { "is", "K" }, { "id", "Q" } }; @@ -533,6 +578,8 @@ notmuch_database_open (const char *path, notmuch->needs_upgrade = FALSE; notmuch->mode = mode; try { + string last_thread_id; + if (mode == NOTMUCH_DATABASE_MODE_READ_WRITE) { notmuch->xapian_db = new Xapian::WritableDatabase (xapian_path, Xapian::DB_CREATE_OR_OPEN); @@ -567,6 +614,20 @@ notmuch_database_open (const char *path, notmuch_path, version, NOTMUCH_DATABASE_VERSION); } } + + last_thread_id = notmuch->xapian_db->get_metadata ("last_thread_id"); + if (last_thread_id.empty ()) { + notmuch->last_thread_id = 0; + } else { + const char *str; + char *end; + + str = last_thread_id.c_str (); + notmuch->last_thread_id = strtoull (str, &end, 16); + if (*end != '\0') + INTERNAL_ERROR ("Malformed database last_thread_id: %s", str); + } + notmuch->query_parser = new Xapian::QueryParser; notmuch->term_gen = new Xapian::TermGenerator; notmuch->term_gen->set_stemmer (Xapian::Stem ("english")); @@ -681,8 +742,7 @@ handle_sigalrm (unused (int signal)) notmuch_status_t notmuch_database_upgrade (notmuch_database_t *notmuch, void (*progress_notify) (void *closure, - unsigned int count, - unsigned int total), + double progress), void *closure) { Xapian::WritableDatabase *db; @@ -691,6 +751,7 @@ notmuch_database_upgrade (notmuch_database_t *notmuch, notmuch_bool_t timer_is_active = FALSE; unsigned int version; notmuch_status_t status; + unsigned int count = 0, total = 0; status = _notmuch_database_ensure_writable (notmuch); if (status) @@ -722,37 +783,46 @@ notmuch_database_upgrade (notmuch_database_t *notmuch, } /* Before version 1, each message document had its filename in the - * data field. Move that into the new format by calling + * data field. Copy that into the new format by calling * notmuch_message_add_filename. */ if (version < 1) { - unsigned int count = 0, total; notmuch_query_t *query = notmuch_query_create (notmuch, ""); notmuch_messages_t *messages; notmuch_message_t *message; + char *filename; + Xapian::TermIterator t, t_end; total = notmuch_query_count_messages (query); for (messages = notmuch_query_search_messages (query); - notmuch_messages_has_more (messages); - notmuch_messages_advance (messages)) + notmuch_messages_valid (messages); + notmuch_messages_move_to_next (messages)) { - if (do_progress_notify) - progress_notify (closure, count, total); + if (do_progress_notify) { + progress_notify (closure, (double) count / total); + do_progress_notify = 0; + } message = notmuch_messages_get (messages); - _notmuch_message_upgrade_filename_storage (message); + filename = _notmuch_message_talloc_copy_data (message); + if (filename && *filename != '\0') { + _notmuch_message_add_filename (message, filename); + _notmuch_message_sync (message); + } + talloc_free (filename); + + notmuch_message_destroy (message); count++; } - } - /* Also, before version 1 we stored directory timestamps in - * XTIMESTAMP documents instead of the current XDIRECTORY - * documents. So convert those as well. */ - if (version < 1) { - Xapian::TermIterator t, t_end; + notmuch_query_destroy (query); + + /* Also, before version 1 we stored directory timestamps in + * XTIMESTAMP documents instead of the current XDIRECTORY + * documents. So copy those as well. */ t_end = notmuch->xapian_db->allterms_end ("XTIMESTAMP"); @@ -773,6 +843,11 @@ notmuch_database_upgrade (notmuch_database_t *notmuch, time_t mtime; notmuch_directory_t *directory; + if (do_progress_notify) { + progress_notify (closure, (double) count / total); + do_progress_notify = 0; + } + document = find_document_for_doc_id (notmuch, *p); mtime = Xapian::sortable_unserialise ( document.get_value (NOTMUCH_VALUE_TIMESTAMP)); @@ -788,6 +863,66 @@ notmuch_database_upgrade (notmuch_database_t *notmuch, db->set_metadata ("version", STRINGIFY (NOTMUCH_DATABASE_VERSION)); db->flush (); + /* Now that the upgrade is complete we can remove the old data + * and documents that are no longer needed. */ + if (version < 1) { + notmuch_query_t *query = notmuch_query_create (notmuch, ""); + notmuch_messages_t *messages; + notmuch_message_t *message; + char *filename; + + for (messages = notmuch_query_search_messages (query); + notmuch_messages_valid (messages); + notmuch_messages_move_to_next (messages)) + { + if (do_progress_notify) { + progress_notify (closure, (double) count / total); + do_progress_notify = 0; + } + + message = notmuch_messages_get (messages); + + filename = _notmuch_message_talloc_copy_data (message); + if (filename && *filename != '\0') { + _notmuch_message_clear_data (message); + _notmuch_message_sync (message); + } + talloc_free (filename); + + notmuch_message_destroy (message); + } + + notmuch_query_destroy (query); + } + + if (version < 1) { + Xapian::TermIterator t, t_end; + + t_end = notmuch->xapian_db->allterms_end ("XTIMESTAMP"); + + for (t = notmuch->xapian_db->allterms_begin ("XTIMESTAMP"); + t != t_end; + t++) + { + Xapian::PostingIterator p, p_end; + std::string term = *t; + + p_end = notmuch->xapian_db->postlist_end (term); + + for (p = notmuch->xapian_db->postlist_begin (term); + p != p_end; + p++) + { + if (do_progress_notify) { + progress_notify (closure, (double) count / total); + do_progress_notify = 0; + } + + db->delete_document (*p); + } + } + } + if (timer_is_active) { /* Now stop the timer. */ timerval.it_interval.tv_sec = 0; @@ -1020,12 +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 (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, @@ -1033,19 +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 (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 @@ -1207,13 +1392,27 @@ _notmuch_database_link_message_to_children (notmuch_database_t *notmuch, /* 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'. + * 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). * - * The end result is to call _notmuch_message_ensure_thread_id which - * 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, @@ -1221,7 +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 (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, @@ -1234,8 +1456,12 @@ _notmuch_database_link_message (notmuch_database_t *notmuch, if (status) return status; - if (thread_id == NULL) - _notmuch_message_ensure_thread_id (message); + /* If not part of any existing thread, generate a new thread ID. */ + if (thread_id == NULL) { + thread_id = _notmuch_database_generate_thread_id (notmuch); + + _notmuch_message_add_term (message, "thread", thread_id); + } return NOTMUCH_STATUS_SUCCESS; }