X-Git-Url: https://git.notmuchmail.org/git?p=notmuch;a=blobdiff_plain;f=lib%2Fdatabase.cc;h=dd1fc6378c48c8b435eab97a0cede52ebc975f0a;hp=acd06de8b4ff89ea2757b4d21c65bb1262a809eb;hb=98845fdbb2a4acaa0036f8e2e998e726b18e6b13;hpb=e890b0cf4011fd9fd77ebd87343379e4a778888b diff --git a/lib/database.cc b/lib/database.cc index acd06de8..dd1fc637 100644 --- a/lib/database.cc +++ b/lib/database.cc @@ -22,6 +22,8 @@ #include +#include +#include #include #include /* g_free, GPtrArray, GHashTable */ @@ -35,9 +37,15 @@ 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 * ------------- @@ -63,6 +71,12 @@ typedef struct { * * tag: Any tags associated with this message by the user. * + * file-direntry: A colon-separated pair of values + * (INTEGER:STRING), where INTEGER is the + * document ID of a directory document, and + * STRING is the name of a file within that + * directory for this mail message. + * * A mail document also has two values: * * TIMESTAMP: The time_t value corresponding to the message's @@ -75,8 +89,7 @@ typedef struct { * user in searching. But the database doesn't really care itself * about any of these. * - * Finally, the data portion of a mail document contains the path name - * of the mail message (relative to the database path). + * The data portion of a mail document is empty. * * Directory document * ------------------ @@ -84,15 +97,71 @@ typedef struct { * maintain data necessary to allow for efficient polling of mail * directories. * - * The directory document contains the following terms: + * All directory documents contain one term: * * directory: The directory path (relative to the database path) - * parent: The document ID of the parent directory document. - * Top-level directories will have a parent value of 0. + * Or the SHA1 sum of the directory path (if the + * path itself is too long to fit in a Xapian + * term). * - * and has a single value: + * And all directory documents for directories other than top-level + * directories also contain the following term: + * + * directory-direntry: A colon-separated pair of values + * (INTEGER:STRING), where INTEGER is the + * document ID of the parent directory + * document, and STRING is the name of this + * directory within that parent. + * + * All directory documents have a single value: * * TIMESTAMP: The mtime of the directory (at last scan) + * + * 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: @@ -111,24 +180,26 @@ typedef struct { */ prefix_t BOOLEAN_PREFIX_INTERNAL[] = { - { "type", "T" }, - { "reference", "XREFERENCE" }, - { "replyto", "XREPLYTO" }, - { "directory", "XDIRECTORY" }, - { "parent", "XPARENT" }, + { "type", "T" }, + { "reference", "XREFERENCE" }, + { "replyto", "XREPLYTO" }, + { "directory", "XDIRECTORY" }, + { "file-direntry", "XFDIRENTRY" }, + { "directory-direntry", "XDDIRENTRY" }, }; prefix_t BOOLEAN_PREFIX_EXTERNAL[] = { - { "thread", "G" }, - { "tag", "K" }, - { "id", "Q" } + { "thread", "G" }, + { "tag", "K" }, + { "is", "K" }, + { "id", "Q" } }; prefix_t PROBABILISTIC_PREFIX[]= { - { "from", "XFROM" }, - { "to", "XTO" }, - { "attachment", "XATTACHMENT" }, - { "subject", "XSUBJECT"} + { "from", "XFROM" }, + { "to", "XTO" }, + { "attachment", "XATTACHMENT" }, + { "subject", "XSUBJECT"} }; int @@ -179,8 +250,8 @@ 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: - return "The database is read-only"; + 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"; case NOTMUCH_STATUS_FILE_ERROR: @@ -201,6 +272,17 @@ notmuch_status_to_string (notmuch_status_t status) } } +static void +find_doc_ids_for_term (notmuch_database_t *notmuch, + const char *term, + Xapian::PostingIterator *begin, + Xapian::PostingIterator *end) +{ + *begin = notmuch->xapian_db->postlist_begin (term); + + *end = notmuch->xapian_db->postlist_end (term); +} + static void find_doc_ids (notmuch_database_t *notmuch, const char *prefix_name, @@ -208,24 +290,21 @@ find_doc_ids (notmuch_database_t *notmuch, Xapian::PostingIterator *begin, Xapian::PostingIterator *end) { - Xapian::PostingIterator i; char *term; term = talloc_asprintf (notmuch, "%s%s", _find_prefix (prefix_name), value); - *begin = notmuch->xapian_db->postlist_begin (term); - - *end = notmuch->xapian_db->postlist_end (term); + find_doc_ids_for_term (notmuch, term, begin, end); talloc_free (term); } -static notmuch_private_status_t -find_unique_doc_id (notmuch_database_t *notmuch, - const char *prefix_name, - const char *value, - unsigned int *doc_id) +notmuch_private_status_t +_notmuch_database_find_unique_doc_id (notmuch_database_t *notmuch, + const char *prefix_name, + const char *value, + unsigned int *doc_id) { Xapian::PostingIterator i, end; @@ -234,10 +313,19 @@ find_unique_doc_id (notmuch_database_t *notmuch, if (i == end) { *doc_id = 0; return NOTMUCH_PRIVATE_STATUS_NO_DOCUMENT_FOUND; - } else { - *doc_id = *i; - return NOTMUCH_PRIVATE_STATUS_SUCCESS; } + + *doc_id = *i; + +#if DEBUG_DATABASE_SANITY + i++; + + if (i != end) + INTERNAL_ERROR ("Term %s:%s is not unique as expected.\n", + prefix_name, value); +#endif + + return NOTMUCH_PRIVATE_STATUS_SUCCESS; } static Xapian::Document @@ -246,26 +334,6 @@ find_document_for_doc_id (notmuch_database_t *notmuch, unsigned doc_id) return notmuch->xapian_db->get_document (doc_id); } -static notmuch_private_status_t -find_unique_document (notmuch_database_t *notmuch, - const char *prefix_name, - const char *value, - Xapian::Document *document, - unsigned int *doc_id) -{ - notmuch_private_status_t status; - - status = find_unique_doc_id (notmuch, prefix_name, value, doc_id); - - if (status) { - *document = Xapian::Document (); - return status; - } - - *document = find_document_for_doc_id (notmuch, *doc_id); - return NOTMUCH_PRIVATE_STATUS_SUCCESS; -} - notmuch_message_t * notmuch_database_find_message (notmuch_database_t *notmuch, const char *message_id) @@ -273,12 +341,20 @@ notmuch_database_find_message (notmuch_database_t *notmuch, notmuch_private_status_t status; unsigned int doc_id; - status = find_unique_doc_id (notmuch, "id", message_id, &doc_id); + try { + status = _notmuch_database_find_unique_doc_id (notmuch, "id", + message_id, &doc_id); - if (status == NOTMUCH_PRIVATE_STATUS_NO_DOCUMENT_FOUND) - return NULL; + 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 @@ -450,6 +526,7 @@ 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) @@ -458,6 +535,17 @@ 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) @@ -466,7 +554,7 @@ notmuch_database_open (const char *path, char *notmuch_path = NULL, *xapian_path = NULL; struct stat st; int err; - unsigned int i; + unsigned int i, version; if (asprintf (¬much_path, "%s/%s", path, ".notmuch") == -1) { notmuch_path = NULL; @@ -494,14 +582,60 @@ notmuch_database_open (const char *path, if (notmuch->path[strlen (notmuch->path) - 1] == '/') notmuch->path[strlen (notmuch->path) - 1] = '\0'; + 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); + 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")); @@ -564,11 +698,253 @@ notmuch_database_get_path (notmuch_database_t *notmuch) return notmuch->path; } -static notmuch_private_status_t -find_directory_document (notmuch_database_t *notmuch, const char *db_path, - Xapian::Document *doc, unsigned int *doc_id) +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 find_unique_document (notmuch, "directory", db_path, doc, doc_id); + 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; } /* We allow the user to use arbitrarily long paths for directories. But @@ -579,8 +955,8 @@ find_directory_document (notmuch_database_t *notmuch, const char *db_path, * does not, then the caller is responsible to free() the returned * value. */ -static const char * -directory_db_path (const char *path) +const char * +_notmuch_database_get_directory_db_path (const char *path) { int term_len = strlen (_find_prefix ("directory")) + strlen (path); @@ -590,18 +966,40 @@ directory_db_path (const char *path) return path; } +/* Given a path, split it into two parts: the directory part is all + * components except for the last, and the basename is that last + * component. Getting the return-value for either part is optional + * (the caller can pass NULL). + * + * The original 'path' can represent either a regular file or a + * directory---the splitting will be carried out in the same way in + * either case. Trailing slashes on 'path' will be ignored, and any + * cases of multiple '/' characters appearing in series will be + * treated as a single '/'. + * + * Allocation (if any) will have 'ctx' as the talloc owner. But + * pointers will be returned within the original path string whenever + * possible. + * + * Note: If 'path' is non-empty and contains no non-trailing slash, + * (that is, consists of a filename with no parent directory), then + * the directory returned will be an empty string. However, if 'path' + * is an empty string, then both directory and basename will be + * returned as NULL. + */ notmuch_status_t -_find_parent_id (notmuch_database_t *notmuch, - const char *path, - Xapian::docid *parent_id) +_notmuch_database_split_path (void *ctx, + const char *path, + const char **directory, + const char **basename) { - const char *slash, *parent_db_path; - char *parent_path; - notmuch_private_status_t private_status; - notmuch_status_t status = NOTMUCH_STATUS_SUCCESS; + const char *slash; if (path == NULL || *path == '\0') { - *parent_id = 0; + if (directory) + *directory = NULL; + if (basename) + *basename = NULL; return NOTMUCH_STATUS_SUCCESS; } @@ -622,6 +1020,9 @@ _find_parent_id (notmuch_database_t *notmuch, if (*slash == '/') break; + if (basename) + *basename = slash; + --slash; } @@ -633,31 +1034,90 @@ _find_parent_id (notmuch_database_t *notmuch, --slash; } - if (slash == path) - parent_path = talloc_strdup (notmuch, ""); - else - parent_path = talloc_strndup (notmuch, path, slash - path + 1); + if (slash == path) { + if (directory) + *directory = talloc_strdup (ctx, ""); + if (basename) + *basename = path; + } else { + if (directory) + *directory = talloc_strndup (ctx, path, slash - path + 1); + } - parent_db_path = directory_db_path (parent_path); + return NOTMUCH_STATUS_SUCCESS; +} - private_status = find_unique_doc_id (notmuch, "directory", - parent_db_path, parent_id); - if (private_status == NOTMUCH_PRIVATE_STATUS_NO_DOCUMENT_FOUND) { - status = notmuch_database_set_directory_mtime (notmuch, - parent_path, 0); - if (status) - return status; - private_status = find_unique_doc_id (notmuch, "directory", - parent_db_path, parent_id); - status = COERCE_STATUS (private_status, "_find_parent_id"); +notmuch_status_t +_notmuch_database_find_directory_id (notmuch_database_t *notmuch, + const char *path, + unsigned int *directory_id) +{ + notmuch_directory_t *directory; + notmuch_status_t status; + + if (path == NULL) { + *directory_id = 0; + return NOTMUCH_STATUS_SUCCESS; } - if (parent_db_path != parent_path) - free ((char *) parent_db_path); + directory = _notmuch_directory_create (notmuch, path, &status); + if (status) { + *directory_id = -1; + return status; + } - talloc_free (parent_path); + *directory_id = _notmuch_directory_get_document_id (directory); - return status; + notmuch_directory_destroy (directory); + + return NOTMUCH_STATUS_SUCCESS; +} + +const char * +_notmuch_database_get_directory_path (void *ctx, + notmuch_database_t *notmuch, + unsigned int doc_id) +{ + Xapian::Document document; + + document = find_document_for_doc_id (notmuch, doc_id); + + return talloc_strdup (ctx, document.get_data ().c_str ()); +} + +/* Given a legal 'filename' for the database, (either relative to + * database path or absolute with initial components identical to + * database path), return a new string (with 'ctx' as the talloc + * owner) suitable for use as a direntry term value. + * + * The necessary directory documents will be created in the database + * as needed. + */ +notmuch_status_t +_notmuch_database_filename_to_direntry (void *ctx, + notmuch_database_t *notmuch, + const char *filename, + char **direntry) +{ + const char *relative, *directory, *basename; + Xapian::docid directory_id; + notmuch_status_t status; + + relative = _notmuch_database_relative_path (notmuch, filename); + + status = _notmuch_database_split_path (ctx, relative, + &directory, &basename); + if (status) + return status; + + status = _notmuch_database_find_directory_id (notmuch, directory, + &directory_id); + if (status) + return status; + + *direntry = talloc_asprintf (ctx, "%u:%s", directory_id, basename); + + return NOTMUCH_STATUS_SUCCESS; } /* Given a legal 'path' for the database, return the relative path. @@ -694,106 +1154,81 @@ _notmuch_database_relative_path (notmuch_database_t *notmuch, return relative; } -notmuch_status_t -notmuch_database_set_directory_mtime (notmuch_database_t *notmuch, - const char *path, - time_t mtime) +notmuch_directory_t * +notmuch_database_get_directory (notmuch_database_t *notmuch, + const char *path) { - Xapian::Document doc; - Xapian::WritableDatabase *db; - unsigned int doc_id; - notmuch_private_status_t status; - notmuch_status_t ret = NOTMUCH_STATUS_SUCCESS; - const char *db_path = NULL; - Xapian::docid parent_id; - - if (notmuch->mode == NOTMUCH_DATABASE_MODE_READ_ONLY) { - fprintf (stderr, "Attempted to update a read-only database.\n"); - return NOTMUCH_STATUS_READONLY_DATABASE; - } - - path = _notmuch_database_relative_path (notmuch, path); - - db = static_cast (notmuch->xapian_db); - db_path = directory_db_path (path); + notmuch_status_t status; try { - status = find_directory_document (notmuch, db_path, &doc, &doc_id); - - doc.add_value (NOTMUCH_VALUE_TIMESTAMP, - Xapian::sortable_serialise (mtime)); - - if (status == NOTMUCH_PRIVATE_STATUS_NO_DOCUMENT_FOUND) { - char *term = talloc_asprintf (NULL, "%s%s", - _find_prefix ("directory"), db_path); - doc.add_term (term); - talloc_free (term); - - status = _find_parent_id (notmuch, path, &parent_id); - if (status) - return status; - - term = talloc_asprintf (NULL, "%s%u", - _find_prefix ("parent"), - parent_id); - doc.add_term (term); - talloc_free (term); - - db->add_document (doc); - } else { - db->replace_document (doc_id, doc); - } - + return _notmuch_directory_create (notmuch, path, &status); } catch (const Xapian::Error &error) { - fprintf (stderr, "A Xapian exception occurred setting directory mtime: %s.\n", + fprintf (stderr, "A Xapian exception occurred getting directory: %s.\n", error.get_msg().c_str()); notmuch->exception_reported = TRUE; - ret = NOTMUCH_STATUS_XAPIAN_EXCEPTION; + return NULL; } +} - if (db_path != path) - free ((char *) db_path); +/* 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 ()); - return ret; + notmuch->last_doc_id++; + + if (notmuch->last_doc_id == 0) + INTERNAL_ERROR ("Xapian document IDs are exhausted.\n"); + + return notmuch->last_doc_id; } -time_t -notmuch_database_get_directory_mtime (notmuch_database_t *notmuch, - const char *path) +static const char * +_notmuch_database_generate_thread_id (notmuch_database_t *notmuch) { - Xapian::Document doc; - unsigned int doc_id; - notmuch_private_status_t status; - const char *db_path = NULL; - time_t ret = 0; + /* 16 bytes (+ terminator) for hexadecimal representation of + * a 64-bit integer. */ + static char thread_id[17]; + Xapian::WritableDatabase *db; - db_path = directory_db_path (path); + db = static_cast (notmuch->xapian_db); - try { - status = find_directory_document (notmuch, db_path, &doc, &doc_id); + notmuch->last_thread_id++; - if (status == NOTMUCH_PRIVATE_STATUS_NO_DOCUMENT_FOUND) - goto DONE; + sprintf (thread_id, "%016" PRIx64, notmuch->last_thread_id); - ret = Xapian::sortable_unserialise (doc.get_value (NOTMUCH_VALUE_TIMESTAMP)); - } catch (Xapian::Error &error) { - ret = 0; - goto DONE; - } + db->set_metadata ("last_thread_id", thread_id); - DONE: - if (db_path != path) - free ((char *) db_path); + return thread_id; +} - return ret; +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, @@ -801,19 +1236,41 @@ _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 @@ -896,22 +1353,21 @@ _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; } } @@ -975,13 +1431,27 @@ _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 mesages 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, @@ -989,7 +1459,30 @@ _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, @@ -1002,8 +1495,12 @@ _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; } @@ -1025,11 +1522,13 @@ 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; - goto DONE; - } + if (message_file == NULL) + return NOTMUCH_STATUS_FILE_ERROR; notmuch_message_file_restrict_headers (message_file, "date", @@ -1110,28 +1609,29 @@ notmuch_database_add_message (notmuch_database_t *notmuch, goto DONE; } + _notmuch_message_add_filename (message, filename); + /* Is this a newly created message object? */ if (private_status == NOTMUCH_PRIVATE_STATUS_NO_DOCUMENT_FOUND) { - _notmuch_message_set_filename (message, filename); _notmuch_message_add_term (message, "type", "mail"); - } else { - ret = NOTMUCH_STATUS_DUPLICATE_MESSAGE_ID; - goto DONE; - } - ret = _notmuch_database_link_message (notmuch, message, message_file); - if (ret) - goto DONE; + ret = _notmuch_database_link_message (notmuch, message, + message_file); + if (ret) + goto DONE; - date = notmuch_message_file_get_header (message_file, "date"); - _notmuch_message_set_date (message, date); + date = notmuch_message_file_get_header (message_file, "date"); + _notmuch_message_set_date (message, date); - _notmuch_message_index_file (message, filename); + _notmuch_message_index_file (message, filename); + } else { + ret = NOTMUCH_STATUS_DUPLICATE_MESSAGE_ID; + } _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; @@ -1151,6 +1651,70 @@ notmuch_database_add_message (notmuch_database_t *notmuch, return ret; } +notmuch_status_t +notmuch_database_remove_message (notmuch_database_t *notmuch, + const char *filename) +{ + Xapian::WritableDatabase *db; + void *local; + const char *prefix = _find_prefix ("file-direntry"); + char *direntry, *term; + Xapian::PostingIterator i, end; + Xapian::Document document; + notmuch_status_t status; + + status = _notmuch_database_ensure_writable (notmuch); + if (status) + return status; + + local = talloc_new (notmuch); + + db = static_cast (notmuch->xapian_db); + + try { + + status = _notmuch_database_filename_to_direntry (local, notmuch, + filename, &direntry); + if (status) + return status; + + term = talloc_asprintf (notmuch, "%s%s", prefix, direntry); + + find_doc_ids_for_term (notmuch, term, &i, &end); + + for ( ; i != end; i++) { + Xapian::TermIterator j; + + document = find_document_for_doc_id (notmuch, *i); + + document.remove_term (term); + + 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); + + return status; +} + notmuch_tags_t * _notmuch_convert_tags (void *ctx, Xapian::TermIterator &i, Xapian::TermIterator &end) @@ -1189,7 +1753,15 @@ 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; + } }