X-Git-Url: https://git.notmuchmail.org/git?p=notmuch;a=blobdiff_plain;f=lib%2Fdatabase.cc;h=8f8df1a1434ed604ca2fe1a7bdf5f87b7084a28d;hp=125b37ebb6b5538d4d4d07cf2d6c3eaef2df7ee2;hb=cfc5f1059aa16753cba610c41601cacc97260e08;hpb=6ed606c19edfe06d2dfd48854fc97f8502eaaf7c diff --git a/lib/database.cc b/lib/database.cc index 125b37eb..8f8df1a1 100644 --- a/lib/database.cc +++ b/lib/database.cc @@ -22,9 +22,13 @@ #include -#include +#include +#include #include /* g_free, GPtrArray, GHashTable */ +#include /* g_type_init */ + +#include /* g_mime_init */ using namespace std; @@ -35,9 +39,15 @@ typedef struct { const char *prefix; } prefix_t; -/* Here's the current schema for our database: +#define NOTMUCH_DATABASE_VERSION 1 + +#define STRINGIFY(s) _SUB_STRINGIFY(s) +#define _SUB_STRINGIFY(s) #s + +/* 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 * ------------- @@ -49,8 +59,12 @@ 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 * @@ -58,7 +72,7 @@ typedef struct { * * Multiple terms of given prefix: * - * reference: All message IDs from In-Reply-To and Re ferences + * reference: All message IDs from In-Reply-To and References * headers in the message. * * tag: Any tags associated with this message by the user. @@ -69,17 +83,22 @@ typedef struct { * STRING is the name of a file within that * directory for this mail message. * - * A mail document also has two values: + * A mail document also has four values: * * TIMESTAMP: The time_t value corresponding to the message's * Date header. * * MESSAGE_ID: The unique ID of the mail mess (see "id" above) * + * FROM: The value of the "From" header + * + * SUBJECT: The value of the "Subject" header + * * 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. + * user in searching. Similarly, terms from the path of the mail + * message are added with a "folder" prefix. But the database doesn't + * really care itself about any of these. * * The data portion of a mail document is empty. * @@ -111,6 +130,51 @@ 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). Successive 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 arbitrarily 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: @@ -128,7 +192,7 @@ 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" }, @@ -137,34 +201,21 @@ 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" }, - { "subject", "XSUBJECT"} + { "subject", "XSUBJECT"}, + { "folder", "XFOLDER"} }; -int -_internal_error (const char *format, ...) -{ - va_list va_args; - - va_start (va_args, format); - - fprintf (stderr, "Internal error: "); - vfprintf (stderr, format, va_args); - - exit (1); - - return 1; -} - const char * _find_prefix (const char *name) { @@ -198,7 +249,7 @@ notmuch_status_to_string (notmuch_status_t status) return "No error occurred"; case NOTMUCH_STATUS_OUT_OF_MEMORY: return "Out of memory"; - case NOTMUCH_STATUS_READONLY_DATABASE: + case NOTMUCH_STATUS_READ_ONLY_DATABASE: return "Attempt to write to a read-only database"; case NOTMUCH_STATUS_XAPIAN_EXCEPTION: return "A Xapian exception occurred"; @@ -214,6 +265,8 @@ notmuch_status_to_string (notmuch_status_t status) return "Tag value is too long (exceeds NOTMUCH_TAG_MAX)"; case NOTMUCH_STATUS_UNBALANCED_FREEZE_THAW: return "Unbalanced number of calls to notmuch_message_freeze/thaw"; + case NOTMUCH_STATUS_UNBALANCED_ATOMIC: + return "Unbalanced number of calls to notmuch_database_begin_atomic/end_atomic"; default: case NOTMUCH_STATUS_LAST_STATUS: return "Unknown error status value"; @@ -282,20 +335,58 @@ find_document_for_doc_id (notmuch_database_t *notmuch, unsigned doc_id) return notmuch->xapian_db->get_document (doc_id); } -notmuch_message_t * +/* 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_status_t notmuch_database_find_message (notmuch_database_t *notmuch, - const char *message_id) + const char *message_id, + notmuch_message_t **message_ret) { notmuch_private_status_t status; unsigned int doc_id; - status = _notmuch_database_find_unique_doc_id (notmuch, "id", - message_id, &doc_id); + if (message_ret == NULL) + return NOTMUCH_STATUS_NULL_POINTER; - if (status == NOTMUCH_PRIVATE_STATUS_NO_DOCUMENT_FOUND) - return NULL; + if (strlen (message_id) > NOTMUCH_MESSAGE_ID_MAX) + message_id = _message_id_compressed (notmuch, message_id); - return _notmuch_message_create (notmuch, notmuch, doc_id, NULL); + try { + status = _notmuch_database_find_unique_doc_id (notmuch, "id", + message_id, &doc_id); + + if (status == NOTMUCH_PRIVATE_STATUS_NO_DOCUMENT_FOUND) + *message_ret = NULL; + else { + *message_ret = _notmuch_message_create (notmuch, notmuch, doc_id, + NULL); + if (*message_ret == NULL) + return NOTMUCH_STATUS_OUT_OF_MEMORY; + } + + return NOTMUCH_STATUS_SUCCESS; + } catch (const Xapian::Error &error) { + fprintf (stderr, "A Xapian exception occurred finding message: %s.\n", + error.get_msg().c_str()); + notmuch->exception_reported = TRUE; + *message_ret = NULL; + return NOTMUCH_STATUS_XAPIAN_EXCEPTION; + } } /* Advance 'str' past any whitespace or RFC 822 comments. A comment is @@ -336,7 +427,7 @@ skip_space_and_comments (const char **str) } /* Parse an RFC 822 message-id, discarding whitespace, any RFC 822 - * comments, and the '<' and '>' delimeters. + * comments, and the '<' and '>' delimiters. * * If not NULL, then *next will be made to point to the first character * not parsed, (possibly pointing to the final '\0' terminator. @@ -467,6 +558,7 @@ notmuch_database_create (const char *path) notmuch = notmuch_database_open (path, NOTMUCH_DATABASE_MODE_READ_WRITE); + notmuch_database_upgrade (notmuch, NULL, NULL); DONE: if (notmuch_path) @@ -475,18 +567,30 @@ notmuch_database_create (const char *path) return notmuch; } +notmuch_status_t +_notmuch_database_ensure_writable (notmuch_database_t *notmuch) +{ + if (notmuch->mode == NOTMUCH_DATABASE_MODE_READ_ONLY) { + fprintf (stderr, "Cannot write to a read-only database.\n"); + return NOTMUCH_STATUS_READ_ONLY_DATABASE; + } + + return NOTMUCH_STATUS_SUCCESS; +} + notmuch_database_t * notmuch_database_open (const char *path, notmuch_database_mode_t mode) { + void *local = talloc_new (NULL); notmuch_database_t *notmuch = NULL; - char *notmuch_path = NULL, *xapian_path = NULL; + char *notmuch_path, *xapian_path; struct stat st; int err; - unsigned int i; + unsigned int i, version; + static int initialized = 0; - if (asprintf (¬much_path, "%s/%s", path, ".notmuch") == -1) { - notmuch_path = NULL; + if (! (notmuch_path = talloc_asprintf (local, "%s/%s", path, ".notmuch"))) { fprintf (stderr, "Out of memory\n"); goto DONE; } @@ -498,27 +602,82 @@ notmuch_database_open (const char *path, goto DONE; } - if (asprintf (&xapian_path, "%s/%s", notmuch_path, "xapian") == -1) { - xapian_path = NULL; + if (! (xapian_path = talloc_asprintf (local, "%s/%s", notmuch_path, "xapian"))) { fprintf (stderr, "Out of memory\n"); goto DONE; } - notmuch = talloc (NULL, notmuch_database_t); + /* Initialize the GLib type system and threads */ + g_type_init (); + + /* Initialize gmime */ + if (! initialized) { + g_mime_init (0); + initialized = 1; + } + + notmuch = talloc_zero (NULL, notmuch_database_t); notmuch->exception_reported = FALSE; notmuch->path = talloc_strdup (notmuch, path); if (notmuch->path[strlen (notmuch->path) - 1] == '/') notmuch->path[strlen (notmuch->path) - 1] = '\0'; + notmuch->needs_upgrade = FALSE; notmuch->mode = mode; + notmuch->atomic_nesting = 0; 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); + version = notmuch_database_get_version (notmuch); + + if (version > NOTMUCH_DATABASE_VERSION) { + fprintf (stderr, + "Error: Notmuch database at %s\n" + " has a newer database format version (%u) than supported by this\n" + " version of notmuch (%u). Refusing to open this database in\n" + " read-write mode.\n", + notmuch_path, version, NOTMUCH_DATABASE_VERSION); + notmuch->mode = NOTMUCH_DATABASE_MODE_READ_ONLY; + notmuch_database_close (notmuch); + notmuch = NULL; + goto DONE; + } + + if (version < NOTMUCH_DATABASE_VERSION) + notmuch->needs_upgrade = TRUE; } else { notmuch->xapian_db = new Xapian::Database (xapian_path); + version = notmuch_database_get_version (notmuch); + if (version > NOTMUCH_DATABASE_VERSION) + { + fprintf (stderr, + "Warning: Notmuch database at %s\n" + " has a newer database format version (%u) than supported by this\n" + " version of notmuch (%u). Some operations may behave incorrectly,\n" + " (but the database will not be harmed since it is being opened\n" + " in read-only mode).\n", + notmuch_path, version, NOTMUCH_DATABASE_VERSION); + } } + + 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; + } 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")); @@ -543,14 +702,12 @@ notmuch_database_open (const char *path, } catch (const Xapian::Error &error) { fprintf (stderr, "A Xapian exception occurred opening database: %s\n", error.get_msg().c_str()); + notmuch_database_close (notmuch); notmuch = NULL; } DONE: - if (notmuch_path) - free (notmuch_path); - if (xapian_path) - free (xapian_path); + talloc_free (local); return notmuch; } @@ -559,7 +716,8 @@ void notmuch_database_close (notmuch_database_t *notmuch) { try { - if (notmuch->mode == NOTMUCH_DATABASE_MODE_READ_WRITE) + if (notmuch->xapian_db != NULL && + notmuch->mode == NOTMUCH_DATABASE_MODE_READ_WRITE) (static_cast (notmuch->xapian_db))->flush (); } catch (const Xapian::Error &error) { if (! notmuch->exception_reported) { @@ -568,6 +726,17 @@ notmuch_database_close (notmuch_database_t *notmuch) } } + /* Many Xapian objects (and thus notmuch objects) hold references to + * the database, so merely deleting the database may not suffice to + * close it. Thus, we explicitly close it here. */ + if (notmuch->xapian_db != NULL) { + try { + notmuch->xapian_db->close(); + } catch (const Xapian::Error &error) { + /* do nothing */ + } + } + delete notmuch->term_gen; delete notmuch->query_parser; delete notmuch->xapian_db; @@ -581,6 +750,310 @@ notmuch_database_get_path (notmuch_database_t *notmuch) return notmuch->path; } +unsigned int +notmuch_database_get_version (notmuch_database_t *notmuch) +{ + unsigned int version; + string version_string; + const char *str; + char *end; + + version_string = notmuch->xapian_db->get_metadata ("version"); + if (version_string.empty ()) + return 0; + + str = version_string.c_str (); + if (str == NULL || *str == '\0') + return 0; + + version = strtoul (str, &end, 10); + if (*end != '\0') + INTERNAL_ERROR ("Malformed database version: %s", str); + + return version; +} + +notmuch_bool_t +notmuch_database_needs_upgrade (notmuch_database_t *notmuch) +{ + return notmuch->needs_upgrade; +} + +static volatile sig_atomic_t do_progress_notify = 0; + +static void +handle_sigalrm (unused (int signal)) +{ + do_progress_notify = 1; +} + +/* Upgrade the current database. + * + * After opening a database in read-write mode, the client should + * check if an upgrade is needed (notmuch_database_needs_upgrade) and + * if so, upgrade with this function before making any modifications. + * + * The optional progress_notify callback can be used by the caller to + * provide progress indication to the user. If non-NULL it will be + * called periodically with 'count' as the number of messages upgraded + * so far and 'total' the overall number of messages that will be + * converted. + */ +notmuch_status_t +notmuch_database_upgrade (notmuch_database_t *notmuch, + void (*progress_notify) (void *closure, + double progress), + void *closure) +{ + Xapian::WritableDatabase *db; + struct sigaction action; + struct itimerval timerval; + 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) + return status; + + db = static_cast (notmuch->xapian_db); + + version = notmuch_database_get_version (notmuch); + + if (version >= NOTMUCH_DATABASE_VERSION) + return NOTMUCH_STATUS_SUCCESS; + + if (progress_notify) { + /* Setup our handler for SIGALRM */ + memset (&action, 0, sizeof (struct sigaction)); + action.sa_handler = handle_sigalrm; + sigemptyset (&action.sa_mask); + action.sa_flags = SA_RESTART; + sigaction (SIGALRM, &action, NULL); + + /* Then start a timer to send SIGALRM once per second. */ + timerval.it_interval.tv_sec = 1; + timerval.it_interval.tv_usec = 0; + timerval.it_value.tv_sec = 1; + timerval.it_value.tv_usec = 0; + setitimer (ITIMER_REAL, &timerval, NULL); + + timer_is_active = TRUE; + } + + /* Before version 1, each message document had its filename in the + * data field. Copy that into the new format by calling + * notmuch_message_add_filename. + */ + if (version < 1) { + 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_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_add_filename (message, filename); + _notmuch_message_sync (message); + } + talloc_free (filename); + + notmuch_message_destroy (message); + + count++; + } + + 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"); + + 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++) + { + Xapian::Document document; + 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)); + + directory = notmuch_database_get_directory (notmuch, + term.c_str() + 10); + notmuch_directory_set_mtime (directory, mtime); + notmuch_directory_destroy (directory); + } + } + } + + 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; + timerval.it_interval.tv_usec = 0; + timerval.it_value.tv_sec = 0; + timerval.it_value.tv_usec = 0; + setitimer (ITIMER_REAL, &timerval, NULL); + + /* And disable the signal handler. */ + action.sa_handler = SIG_IGN; + sigaction (SIGALRM, &action, NULL); + } + + return NOTMUCH_STATUS_SUCCESS; +} + +notmuch_status_t +notmuch_database_begin_atomic (notmuch_database_t *notmuch) +{ + if (notmuch->mode == NOTMUCH_DATABASE_MODE_READ_ONLY || + notmuch->atomic_nesting > 0) + goto DONE; + + try { + (static_cast (notmuch->xapian_db))->begin_transaction (false); + } catch (const Xapian::Error &error) { + fprintf (stderr, "A Xapian exception occurred beginning transaction: %s.\n", + error.get_msg().c_str()); + notmuch->exception_reported = TRUE; + return NOTMUCH_STATUS_XAPIAN_EXCEPTION; + } + +DONE: + notmuch->atomic_nesting++; + return NOTMUCH_STATUS_SUCCESS; +} + +notmuch_status_t +notmuch_database_end_atomic (notmuch_database_t *notmuch) +{ + Xapian::WritableDatabase *db; + + if (notmuch->atomic_nesting == 0) + return NOTMUCH_STATUS_UNBALANCED_ATOMIC; + + if (notmuch->mode == NOTMUCH_DATABASE_MODE_READ_ONLY || + notmuch->atomic_nesting > 1) + goto DONE; + + db = static_cast (notmuch->xapian_db); + try { + db->commit_transaction (); + + /* This is a hack for testing. Xapian never flushes on a + * non-flushed commit, even if the flush threshold is 1. + * However, we rely on flushing to test atomicity. */ + const char *thresh = getenv ("XAPIAN_FLUSH_THRESHOLD"); + if (thresh && atoi (thresh) == 1) + db->flush (); + } catch (const Xapian::Error &error) { + fprintf (stderr, "A Xapian exception occurred committing transaction: %s.\n", + error.get_msg().c_str()); + notmuch->exception_reported = TRUE; + return NOTMUCH_STATUS_XAPIAN_EXCEPTION; + } + +DONE: + notmuch->atomic_nesting--; + return NOTMUCH_STATUS_SUCCESS; +} + /* We allow the user to use arbitrarily long paths for directories. But * we have a term-length limit. So if we exceed that, we'll use the * SHA-1 of the path for the database term. @@ -756,7 +1229,7 @@ _notmuch_database_filename_to_direntry (void *ctx, /* Given a legal 'path' for the database, return the relative path. * - * The return value will be a pointer to the originl path contents, + * The return value will be a pointer to the original path contents, * and will be either the original string (if 'path' was relative) or * a portion of the string (if path was absolute and begins with the * database path). @@ -794,35 +1267,129 @@ 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; + } } -/* Find the thread ID to which the message with 'message_id' belongs. +/* Allocate a document ID that satisfies the following criteria: + * + * 1. The ID does not exist for any document in the Xapian database * - * Returns NULL if no message with message ID 'message_id' is in the - * database. + * 2. The ID was not previously returned from this function * - * Otherwise, returns a newly talloced string belonging to 'ctx'. + * 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. + * + * Note: 'thread_id_ret' must not be NULL! + * On success '*thread_id_ret' is set to 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 notmuch_status_t _resolve_message_id_to_thread_id (notmuch_database_t *notmuch, void *ctx, - const char *message_id) + const char *message_id, + const char **thread_id_ret) { + notmuch_status_t status; notmuch_message_t *message; - const char *ret = NULL; + string thread_id_string; + char *metadata_key; + Xapian::WritableDatabase *db; - message = notmuch_database_find_message (notmuch, message_id); - if (message == NULL) - goto DONE; + status = notmuch_database_find_message (notmuch, message_id, &message); + + if (status) + return status; - ret = talloc_steal (ctx, notmuch_message_get_thread_id (message)); + if (message) { + *thread_id_ret = talloc_steal (ctx, + notmuch_message_get_thread_id (message)); - DONE: - if (message) notmuch_message_destroy (message); - return ret; + return NOTMUCH_STATUS_SUCCESS; + } + + /* 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_ret = talloc_strdup (ctx, + _notmuch_database_generate_thread_id (notmuch)); + db->set_metadata (metadata_key, *thread_id_ret); + } else { + *thread_id_ret = talloc_strdup (ctx, thread_id_string.c_str()); + } + + talloc_free (metadata_key); + + return NOTMUCH_STATUS_SUCCESS; } static notmuch_status_t @@ -902,25 +1469,27 @@ _notmuch_database_link_message_to_parents (notmuch_database_t *notmuch, keys = g_hash_table_get_keys (parents); for (l = keys; l; l = l->next) { char *parent_message_id; - const char *parent_thread_id; + const char *parent_thread_id = NULL; parent_message_id = (char *) l->data; - 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; - } + _notmuch_message_add_term (message, "reference", + parent_message_id); + + ret = _resolve_message_id_to_thread_id (notmuch, + message, + parent_message_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; } } @@ -984,13 +1553,27 @@ _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). * - * 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. + * 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 messages are processed out of order). + * + * 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, @@ -998,7 +1581,30 @@ _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, @@ -1011,8 +1617,12 @@ _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; } @@ -1024,7 +1634,7 @@ notmuch_database_add_message (notmuch_database_t *notmuch, { notmuch_message_file_t *message_file; notmuch_message_t *message = NULL; - notmuch_status_t ret = NOTMUCH_STATUS_SUCCESS; + notmuch_status_t ret = NOTMUCH_STATUS_SUCCESS, ret2; notmuch_private_status_t private_status; const char *date, *header; @@ -1034,11 +1644,19 @@ notmuch_database_add_message (notmuch_database_t *notmuch, if (message_ret) *message_ret = NULL; + ret = _notmuch_database_ensure_writable (notmuch); + if (ret) + return ret; + message_file = notmuch_message_file_open (filename); - if (message_file == NULL) { - ret = NOTMUCH_STATUS_FILE_ERROR; + if (message_file == NULL) + return NOTMUCH_STATUS_FILE_ERROR; + + /* Adding a message may change many documents. Do this all + * atomically. */ + ret = notmuch_database_begin_atomic (notmuch); + if (ret) goto DONE; - } notmuch_message_file_restrict_headers (message_file, "date", @@ -1080,10 +1698,12 @@ 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; } } @@ -1131,7 +1751,7 @@ notmuch_database_add_message (notmuch_database_t *notmuch, goto DONE; date = notmuch_message_file_get_header (message_file, "date"); - _notmuch_message_set_date (message, date); + _notmuch_message_set_header_values (message, date, from, subject); _notmuch_message_index_file (message, filename); } else { @@ -1141,7 +1761,7 @@ 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; @@ -1149,7 +1769,8 @@ 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); @@ -1158,6 +1779,12 @@ notmuch_database_add_message (notmuch_database_t *notmuch, if (message_file) notmuch_message_file_close (message_file); + ret2 = notmuch_database_end_atomic (notmuch); + if ((ret == NOTMUCH_STATUS_SUCCESS || + ret == NOTMUCH_STATUS_DUPLICATE_MESSAGE_ID) && + ret2 != NOTMUCH_STATUS_SUCCESS) + ret = ret2; + return ret; } @@ -1165,96 +1792,116 @@ notmuch_status_t notmuch_database_remove_message (notmuch_database_t *notmuch, const char *filename) { - Xapian::WritableDatabase *db; - void *local = talloc_new (notmuch); - const char *prefix = _find_prefix ("file-direntry"); - char *direntry, *term; - Xapian::PostingIterator i, end; - Xapian::Document document; notmuch_status_t status; + notmuch_message_t *message; - if (notmuch->mode == NOTMUCH_DATABASE_MODE_READ_ONLY) { - fprintf (stderr, "Attempted to update a read-only database.\n"); - return NOTMUCH_STATUS_READONLY_DATABASE; + status = notmuch_database_find_message_by_filename (notmuch, filename, + &message); + + if (status == NOTMUCH_STATUS_SUCCESS && message) { + status = _notmuch_message_remove_filename (message, filename); + if (status == NOTMUCH_STATUS_SUCCESS) + _notmuch_message_delete (message); + else if (status == NOTMUCH_STATUS_DUPLICATE_MESSAGE_ID) + _notmuch_message_sync (message); + + notmuch_message_destroy (message); } - db = static_cast (notmuch->xapian_db); + return status; +} - status = _notmuch_database_filename_to_direntry (local, notmuch, - filename, &direntry); - if (status) - return status; +notmuch_status_t +notmuch_database_find_message_by_filename (notmuch_database_t *notmuch, + const char *filename, + notmuch_message_t **message_ret) +{ + void *local; + const char *prefix = _find_prefix ("file-direntry"); + char *direntry, *term; + Xapian::PostingIterator i, end; + notmuch_status_t status; - term = talloc_asprintf (notmuch, "%s%s", prefix, direntry); + if (message_ret == NULL) + return NOTMUCH_STATUS_NULL_POINTER; - find_doc_ids_for_term (notmuch, term, &i, &end); + local = talloc_new (notmuch); - for ( ; i != end; i++) { - Xapian::TermIterator j; + try { + status = _notmuch_database_filename_to_direntry (local, notmuch, + filename, &direntry); + if (status) + goto DONE; - document = find_document_for_doc_id (notmuch, *i); + term = talloc_asprintf (local, "%s%s", prefix, direntry); - document.remove_term (term); + find_doc_ids_for_term (notmuch, term, &i, &end); - j = document.termlist_begin (); - j.skip_to (prefix); + if (i != end) { + notmuch_private_status_t private_status; - /* 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; + *message_ret = _notmuch_message_create (notmuch, notmuch, *i, + &private_status); + if (*message_ret == NULL) + status = NOTMUCH_STATUS_OUT_OF_MEMORY; } + } catch (const Xapian::Error &error) { + fprintf (stderr, "Error: A Xapian exception occurred finding message by filename: %s\n", + error.get_msg().c_str()); + notmuch->exception_reported = TRUE; + status = NOTMUCH_STATUS_XAPIAN_EXCEPTION; } + DONE: talloc_free (local); + if (status && *message_ret) { + notmuch_message_destroy (*message_ret); + *message_ret = NULL; + } return status; } -notmuch_tags_t * -_notmuch_convert_tags (void *ctx, Xapian::TermIterator &i, - Xapian::TermIterator &end) +notmuch_string_list_t * +_notmuch_database_get_terms_with_prefix (void *ctx, Xapian::TermIterator &i, + Xapian::TermIterator &end, + const char *prefix) { - const char *prefix = _find_prefix ("tag"); - notmuch_tags_t *tags; - std::string tag; + int prefix_len = strlen (prefix); + notmuch_string_list_t *list; - /* Currently this iteration is written with the assumption that - * "tag" has a single-character prefix. */ - assert (strlen (prefix) == 1); - - tags = _notmuch_tags_create (ctx); - if (unlikely (tags == NULL)) + list = _notmuch_string_list_create (ctx); + if (unlikely (list == NULL)) return NULL; - i.skip_to (prefix); - - while (i != end) { - tag = *i; - - if (tag.empty () || tag[0] != *prefix) + for (i.skip_to (prefix); i != end; i++) { + /* Terminate loop at first term without desired prefix. */ + if (strncmp ((*i).c_str (), prefix, prefix_len)) break; - _notmuch_tags_add_tag (tags, tag.c_str () + 1); - - i++; + _notmuch_string_list_append (list, (*i).c_str () + prefix_len); } - _notmuch_tags_prepare_iterator (tags); - - return tags; + return list; } 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); + notmuch_string_list_t *tags; + + try { + i = db->xapian_db->allterms_begin(); + end = db->xapian_db->allterms_end(); + tags = _notmuch_database_get_terms_with_prefix (db, i, end, + _find_prefix ("tag")); + _notmuch_string_list_sort (tags); + return _notmuch_tags_create (db, tags); + } 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; + } }