X-Git-Url: https://git.notmuchmail.org/git?p=notmuch;a=blobdiff_plain;f=lib%2Fdatabase.cc;h=380bbe3daa66e9a878c084b6f1e7fc2b1ace1470;hp=2b5b64dffd9bf0499a0ca70534eba115366610b3;hb=bb74e9dff80e64734308d5997c756fd96d041235;hpb=e0a8dee8bcf0785325c07fff5a11e8ec494826db diff --git a/lib/database.cc b/lib/database.cc index 2b5b64df..380bbe3d 100644 --- a/lib/database.cc +++ b/lib/database.cc @@ -24,7 +24,6 @@ #include #include -#include #include /* g_free, GPtrArray, GHashTable */ @@ -44,7 +43,8 @@ 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 * ------------- @@ -56,8 +56,12 @@ typedef struct { * * type: mail * - * id: Unique ID of mail, (from Message-ID header or generated - * as "notmuch-sha1-. + * id: Unique ID of mail. This is from the Message-ID header + * if present and not too long (see NOTMUCH_MESSAGE_ID_MAX). + * If it's present and too long, then we use + * "notmuch-sha1-". + * If this header is not present, we use + * "notmuch-sha1-". * * thread: The ID of the thread to which the mail belongs * @@ -118,6 +122,51 @@ 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 (or the SHA1 sum of a message ID if it is very + * long---see description of 'id' in the mail + * document). 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: @@ -135,7 +184,7 @@ typedef struct { * nearly universal to all mail messages). */ -prefix_t BOOLEAN_PREFIX_INTERNAL[] = { +static prefix_t BOOLEAN_PREFIX_INTERNAL[] = { { "type", "T" }, { "reference", "XREFERENCE" }, { "replyto", "XREPLYTO" }, @@ -144,13 +193,14 @@ prefix_t BOOLEAN_PREFIX_INTERNAL[] = { { "directory-direntry", "XDDIRENTRY" }, }; -prefix_t BOOLEAN_PREFIX_EXTERNAL[] = { +static prefix_t BOOLEAN_PREFIX_EXTERNAL[] = { { "thread", "G" }, { "tag", "K" }, + { "is", "K" }, { "id", "Q" } }; -prefix_t PROBABILISTIC_PREFIX[]= { +static prefix_t PROBABILISTIC_PREFIX[]= { { "from", "XFROM" }, { "to", "XTO" }, { "attachment", "XATTACHMENT" }, @@ -289,6 +339,23 @@ find_document_for_doc_id (notmuch_database_t *notmuch, unsigned doc_id) return notmuch->xapian_db->get_document (doc_id); } +/* Generate a compressed version of 'message_id' of the form: + * + * notmuch-sha1- + */ +static char * +_message_id_compressed (void *ctx, const char *message_id) +{ + char *sha1, *compressed; + + sha1 = notmuch_sha1_of_string (message_id); + + compressed = talloc_asprintf (ctx, "notmuch-sha1-%s", sha1); + free (sha1); + + return compressed; +} + notmuch_message_t * notmuch_database_find_message (notmuch_database_t *notmuch, const char *message_id) @@ -296,13 +363,23 @@ notmuch_database_find_message (notmuch_database_t *notmuch, notmuch_private_status_t status; unsigned int doc_id; - status = _notmuch_database_find_unique_doc_id (notmuch, "id", - message_id, &doc_id); + if (strlen (message_id) > NOTMUCH_MESSAGE_ID_MAX) + message_id = _message_id_compressed (notmuch, message_id); - if (status == NOTMUCH_PRIVATE_STATUS_NO_DOCUMENT_FOUND) - return NULL; + try { + status = _notmuch_database_find_unique_doc_id (notmuch, "id", + message_id, &doc_id); + + if (status == NOTMUCH_PRIVATE_STATUS_NO_DOCUMENT_FOUND) + return NULL; - return _notmuch_message_create (notmuch, notmuch, doc_id, NULL); + return _notmuch_message_create (notmuch, notmuch, doc_id, NULL); + } catch (const Xapian::Error &error) { + fprintf (stderr, "A Xapian exception occurred finding message: %s.\n", + error.get_msg().c_str()); + notmuch->exception_reported = TRUE; + return NULL; + } } /* Advance 'str' past any whitespace or RFC 822 comments. A comment is @@ -570,6 +647,7 @@ notmuch_database_open (const char *path, } } + notmuch->last_doc_id = notmuch->xapian_db->get_lastdocid (); last_thread_id = notmuch->xapian_db->get_metadata ("last_thread_id"); if (last_thread_id.empty ()) { notmuch->last_thread_id = 0; @@ -751,8 +829,8 @@ notmuch_database_upgrade (notmuch_database_t *notmuch, 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, (double) count / total); @@ -827,8 +905,8 @@ notmuch_database_upgrade (notmuch_database_t *notmuch, char *filename; 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, (double) count / total); @@ -1107,15 +1185,79 @@ notmuch_database_get_directory (notmuch_database_t *notmuch, { notmuch_status_t status; - return _notmuch_directory_create (notmuch, path, &status); + try { + return _notmuch_directory_create (notmuch, path, &status); + } catch (const Xapian::Error &error) { + fprintf (stderr, "A Xapian exception occurred getting directory: %s.\n", + error.get_msg().c_str()); + notmuch->exception_reported = TRUE; + return NULL; + } +} + +/* Allocate a document ID that satisfies the following criteria: + * + * 1. The ID does not exist for any document in the Xapian database + * + * 2. The ID was not previously returned from this function + * + * 3. The ID is the smallest integer satisfying (1) and (2) + * + * This function will trigger an internal error if these constraints + * cannot all be satisfied, (that is, the pool of available document + * IDs has been exhausted). + */ +unsigned int +_notmuch_database_generate_doc_id (notmuch_database_t *notmuch) +{ + assert (notmuch->last_doc_id >= notmuch->xapian_db->get_lastdocid ()); + + notmuch->last_doc_id++; + + if (notmuch->last_doc_id == 0) + INTERNAL_ERROR ("Xapian document IDs are exhausted.\n"); + + return notmuch->last_doc_id; +} + +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) +{ + if (strlen (message_id) > NOTMUCH_MESSAGE_ID_MAX) + message_id = _message_id_compressed (ctx, message_id); + + return talloc_asprintf (ctx, NOTMUCH_METADATA_THREAD_ID_PREFIX "%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, @@ -1123,19 +1265,41 @@ _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 talloc_strdup (ctx, thread_id); } static notmuch_status_t @@ -1218,22 +1382,21 @@ _notmuch_database_link_message_to_parents (notmuch_database_t *notmuch, const char *parent_thread_id; parent_message_id = (char *) l->data; + + _notmuch_message_add_term (message, "reference", + parent_message_id); + parent_thread_id = _resolve_message_id_to_thread_id (notmuch, message, parent_message_id); - if (parent_thread_id == NULL) { - _notmuch_message_add_term (message, "reference", - parent_message_id); - } else { - if (*thread_id == NULL) { - *thread_id = talloc_strdup (message, parent_thread_id); - _notmuch_message_add_term (message, "thread", *thread_id); - } else if (strcmp (*thread_id, parent_thread_id)) { - ret = _merge_threads (notmuch, *thread_id, parent_thread_id); - if (ret) - goto DONE; - } + if (*thread_id == NULL) { + *thread_id = talloc_strdup (message, parent_thread_id); + _notmuch_message_add_term (message, "thread", *thread_id); + } else if (strcmp (*thread_id, parent_thread_id)) { + ret = _merge_threads (notmuch, *thread_id, parent_thread_id); + if (ret) + goto DONE; } } @@ -1294,40 +1457,30 @@ _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 (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, @@ -1335,7 +1488,30 @@ _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, @@ -1423,10 +1599,12 @@ notmuch_database_add_message (notmuch_database_t *notmuch, if (message_id == NULL) message_id = talloc_strdup (message_file, header); - /* Reject a Message ID that's too long. */ - if (message_id && strlen (message_id) + 1 > NOTMUCH_TERM_MAX) { + /* If a message ID is too long, substitute its sha1 instead. */ + if (message_id && strlen (message_id) > NOTMUCH_MESSAGE_ID_MAX) { + char *compressed = _message_id_compressed (message_file, + message_id); talloc_free (message_id); - message_id = NULL; + message_id = compressed; } } @@ -1464,6 +1642,13 @@ notmuch_database_add_message (notmuch_database_t *notmuch, _notmuch_message_add_filename (message, filename); + /* This is a new message or it has a new filename and as such, + * its tags in database either do not exists or might be out + * of date. We assign the tags later in notmuch new, but until + * then we should not synchronize the tags back to the maildir + * flags (if notmuch is configured to do so). */ + notmuch_message_set_flag(message, NOTMUCH_MESSAGE_FLAG_TAGS_INVALID, TRUE); + /* Is this a newly created message object? */ if (private_status == NOTMUCH_PRIVATE_STATUS_NO_DOCUMENT_FOUND) { _notmuch_message_add_term (message, "type", "mail"); @@ -1484,7 +1669,7 @@ notmuch_database_add_message (notmuch_database_t *notmuch, _notmuch_message_sync (message); } catch (const Xapian::Error &error) { fprintf (stderr, "A Xapian exception occurred adding message: %s.\n", - error.get_description().c_str()); + error.get_msg().c_str()); notmuch->exception_reported = TRUE; ret = NOTMUCH_STATUS_XAPIAN_EXCEPTION; goto DONE; @@ -1492,7 +1677,8 @@ notmuch_database_add_message (notmuch_database_t *notmuch, DONE: if (message) { - if (ret == NOTMUCH_STATUS_SUCCESS && message_ret) + if ((ret == NOTMUCH_STATUS_SUCCESS || + ret == NOTMUCH_STATUS_DUPLICATE_MESSAGE_ID) && message_ret) *message_ret = message; else notmuch_message_destroy (message); @@ -1509,7 +1695,7 @@ notmuch_database_remove_message (notmuch_database_t *notmuch, const char *filename) { Xapian::WritableDatabase *db; - void *local = talloc_new (notmuch); + void *local; const char *prefix = _find_prefix ("file-direntry"); char *direntry, *term; Xapian::PostingIterator i, end; @@ -1520,37 +1706,47 @@ notmuch_database_remove_message (notmuch_database_t *notmuch, if (status) return status; + local = talloc_new (notmuch); + db = static_cast (notmuch->xapian_db); - status = _notmuch_database_filename_to_direntry (local, notmuch, - filename, &direntry); - if (status) - return status; + try { - term = talloc_asprintf (notmuch, "%s%s", prefix, direntry); + status = _notmuch_database_filename_to_direntry (local, notmuch, + filename, &direntry); + if (status) + return status; - find_doc_ids_for_term (notmuch, term, &i, &end); + term = talloc_asprintf (notmuch, "%s%s", prefix, direntry); - for ( ; i != end; i++) { - Xapian::TermIterator j; + find_doc_ids_for_term (notmuch, term, &i, &end); - document = find_document_for_doc_id (notmuch, *i); + for ( ; i != end; i++) { + Xapian::TermIterator j; - document.remove_term (term); + document = find_document_for_doc_id (notmuch, *i); - j = document.termlist_begin (); - j.skip_to (prefix); + document.remove_term (term); - /* Was this the last file-direntry in the message? */ - if (j == document.termlist_end () || - strncmp ((*j).c_str (), prefix, strlen (prefix))) - { - db->delete_document (document.get_docid ()); - status = NOTMUCH_STATUS_SUCCESS; - } else { - db->replace_document (document.get_docid (), document); - status = NOTMUCH_STATUS_DUPLICATE_MESSAGE_ID; + j = document.termlist_begin (); + j.skip_to (prefix); + + /* Was this the last file-direntry in the message? */ + if (j == document.termlist_end () || + strncmp ((*j).c_str (), prefix, strlen (prefix))) + { + db->delete_document (document.get_docid ()); + status = NOTMUCH_STATUS_SUCCESS; + } else { + db->replace_document (document.get_docid (), document); + status = NOTMUCH_STATUS_DUPLICATE_MESSAGE_ID; + } } + } catch (const Xapian::Error &error) { + fprintf (stderr, "Error: A Xapian exception occurred removing message: %s\n", + error.get_msg().c_str()); + notmuch->exception_reported = TRUE; + status = NOTMUCH_STATUS_XAPIAN_EXCEPTION; } talloc_free (local); @@ -1596,7 +1792,15 @@ notmuch_tags_t * notmuch_database_get_all_tags (notmuch_database_t *db) { Xapian::TermIterator i, end; - i = db->xapian_db->allterms_begin(); - end = db->xapian_db->allterms_end(); - return _notmuch_convert_tags(db, i, end); + + try { + i = db->xapian_db->allterms_begin(); + end = db->xapian_db->allterms_end(); + return _notmuch_convert_tags(db, i, end); + } catch (const Xapian::Error &error) { + fprintf (stderr, "A Xapian exception occurred getting tags: %s.\n", + error.get_msg().c_str()); + db->exception_reported = TRUE; + return NULL; + } }