X-Git-Url: https://git.notmuchmail.org/git?p=notmuch;a=blobdiff_plain;f=lib%2Fdatabase.cc;h=2b5b64dffd9bf0499a0ca70534eba115366610b3;hp=726c5a98a02b1e153358c0daff820dac8cac3cc3;hb=e0a8dee8bcf0785325c07fff5a11e8ec494826db;hpb=2ce25b93a72b4a8d6daa5321f9ef7df0772a789f diff --git a/lib/database.cc b/lib/database.cc index 726c5a98..2b5b64df 100644 --- a/lib/database.cc +++ b/lib/database.cc @@ -22,6 +22,8 @@ #include +#include +#include #include #include /* g_free, GPtrArray, GHashTable */ @@ -35,9 +37,14 @@ 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 timestamps. + * We currently have two different types of documents: mail and directory. * * Mail document * ------------- @@ -63,6 +70,12 @@ 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 @@ -75,21 +88,36 @@ typedef struct { * user in searching. But the database doesn't really care itself * about any of these. * - * Timestamp document + * The data portion of a mail document is empty. + * + * Directory document * ------------------ - * A timestamp document is used by a client of the notmuch library to + * A directory document is used by a client of the notmuch library to * maintain data necessary to allow for efficient polling of mail - * directories. The notmuch library does no interpretation of - * timestamps, but merely allows the user to store and retrieve - * timestamps as name/value pairs. + * directories. + * + * All directory documents contain one term: * - * The timestamp document is indexed with a single prefixed term: + * directory: The directory path (relative to the database path) + * Or the SHA1 sum of the directory path (if the + * path itself is too long to fit in a Xapian + * term). * - * timestamp: The user's key value (likely a directory name) + * And all directory documents for directories other than top-level + * directories also contain the following term: * - * and has a single value: + * 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. * - * TIMESTAMP: The time_t value from the user. + * 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). */ /* With these prefix values we follow the conventions published here: @@ -108,23 +136,25 @@ typedef struct { */ prefix_t BOOLEAN_PREFIX_INTERNAL[] = { - { "type", "T" }, - { "reference", "XREFERENCE" }, - { "replyto", "XREPLYTO" }, - { "timestamp", "XTIMESTAMP" }, + { "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" }, + { "id", "Q" } }; prefix_t PROBABILISTIC_PREFIX[]= { - { "from", "XFROM" }, - { "to", "XTO" }, - { "attachment", "XATTACHMENT" }, - { "subject", "XSUBJECT"} + { "from", "XFROM" }, + { "to", "XTO" }, + { "attachment", "XATTACHMENT" }, + { "subject", "XSUBJECT"} }; int @@ -147,17 +177,20 @@ _find_prefix (const char *name) { unsigned int i; - for (i = 0; i < ARRAY_SIZE (BOOLEAN_PREFIX_INTERNAL); i++) + for (i = 0; i < ARRAY_SIZE (BOOLEAN_PREFIX_INTERNAL); i++) { if (strcmp (name, BOOLEAN_PREFIX_INTERNAL[i].name) == 0) return BOOLEAN_PREFIX_INTERNAL[i].prefix; + } - for (i = 0; i < ARRAY_SIZE (BOOLEAN_PREFIX_EXTERNAL); i++) + for (i = 0; i < ARRAY_SIZE (BOOLEAN_PREFIX_EXTERNAL); i++) { if (strcmp (name, BOOLEAN_PREFIX_EXTERNAL[i].name) == 0) return BOOLEAN_PREFIX_EXTERNAL[i].prefix; + } - for (i = 0; i < ARRAY_SIZE (PROBABILISTIC_PREFIX); i++) + for (i = 0; i < ARRAY_SIZE (PROBABILISTIC_PREFIX); i++) { if (strcmp (name, PROBABILISTIC_PREFIX[i].name) == 0) return PROBABILISTIC_PREFIX[i].prefix; + } INTERNAL_ERROR ("No prefix exists for '%s'\n", name); @@ -172,6 +205,8 @@ 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_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: @@ -192,6 +227,17 @@ 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, @@ -199,24 +245,21 @@ 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; @@ -225,10 +268,19 @@ 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 @@ -237,26 +289,6 @@ 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) @@ -264,7 +296,8 @@ 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); + status = _notmuch_database_find_unique_doc_id (notmuch, "id", + message_id, &doc_id); if (status == NOTMUCH_PRIVATE_STATUS_NO_DOCUMENT_FOUND) return NULL; @@ -293,13 +326,14 @@ skip_space_and_comments (const char **str) int nesting = 1; s++; while (*s && nesting) { - if (*s == '(') + if (*s == '(') { nesting++; - else if (*s == ')') + } else if (*s == ')') { nesting--; - else if (*s == '\\') + } else if (*s == '\\') { if (*(s+1)) s++; + } s++; } } @@ -323,7 +357,7 @@ _parse_message_id (void *ctx, const char *message_id, const char **next) const char *s, *end; char *result; - if (message_id == NULL) + if (message_id == NULL || *message_id == '\0') return NULL; s = message_id; @@ -391,7 +425,7 @@ parse_references (void *ctx, { char *ref; - if (refs == NULL) + if (refs == NULL || *refs == '\0') return; while (*refs) { @@ -438,7 +472,9 @@ notmuch_database_create (const char *path) goto DONE; } - notmuch = notmuch_database_open (path); + notmuch = notmuch_database_open (path, + NOTMUCH_DATABASE_MODE_READ_WRITE); + notmuch_database_upgrade (notmuch, NULL, NULL); DONE: if (notmuch_path) @@ -447,14 +483,26 @@ 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_open (const char *path, + notmuch_database_mode_t mode) { notmuch_database_t *notmuch = NULL; 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; @@ -476,22 +524,75 @@ notmuch_database_open (const char *path) } notmuch = talloc (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; try { - notmuch->xapian_db = new Xapian::WritableDatabase (xapian_path, - Xapian::DB_CREATE_OR_OPEN); + 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); + } + } + + 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")); + notmuch->value_range_processor = new Xapian::NumberValueRangeProcessor (NOTMUCH_VALUE_TIMESTAMP); notmuch->query_parser->set_default_op (Xapian::Query::OP_AND); notmuch->query_parser->set_database (*notmuch->xapian_db); notmuch->query_parser->set_stemmer (Xapian::Stem ("english")); notmuch->query_parser->set_stemming_strategy (Xapian::QueryParser::STEM_SOME); + notmuch->query_parser->add_valuerangeprocessor (notmuch->value_range_processor); for (i = 0; i < ARRAY_SIZE (BOOLEAN_PREFIX_EXTERNAL); i++) { prefix_t *prefix = &BOOLEAN_PREFIX_EXTERNAL[i]; @@ -504,11 +605,11 @@ notmuch_database_open (const char *path) notmuch->query_parser->add_prefix (prefix->name, prefix->prefix); } } catch (const Xapian::Error &error) { - fprintf (stderr, "A Xapian exception occurred: %s\n", + fprintf (stderr, "A Xapian exception occurred opening database: %s\n", error.get_msg().c_str()); notmuch = NULL; } - + DONE: if (notmuch_path) free (notmuch_path); @@ -521,11 +622,20 @@ notmuch_database_open (const char *path) void notmuch_database_close (notmuch_database_t *notmuch) { - notmuch->xapian_db->flush (); + try { + if (notmuch->mode == NOTMUCH_DATABASE_MODE_READ_WRITE) + (static_cast (notmuch->xapian_db))->flush (); + } catch (const Xapian::Error &error) { + if (! notmuch->exception_reported) { + fprintf (stderr, "Error: A Xapian exception occurred flushing database: %s\n", + error.get_msg().c_str()); + } + } delete notmuch->term_gen; delete notmuch->query_parser; delete notmuch->xapian_db; + delete notmuch->value_range_processor; talloc_free (notmuch); } @@ -535,101 +645,469 @@ notmuch_database_get_path (notmuch_database_t *notmuch) return notmuch->path; } -static notmuch_private_status_t -find_timestamp_document (notmuch_database_t *notmuch, const char *db_key, - 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, "timestamp", db_key, doc, doc_id); + return notmuch->needs_upgrade; } -/* We allow the user to use arbitrarily long keys for timestamps, - * (they're for filesystem paths after all, which have no limit we - * know about). But we have a term-length limit. So if we exceed that, - * we'll use the SHA-1 of the user's key as the actual key for - * constructing a database term. +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. * - * Caution: This function returns a newly allocated string which the - * caller should free() when finished. + * 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. */ -static char * -timestamp_db_key (const char *key) +notmuch_status_t +notmuch_database_upgrade (notmuch_database_t *notmuch, + void (*progress_notify) (void *closure, + double progress), + void *closure) { - int term_len = strlen (_find_prefix ("timestamp")) + strlen (key); + 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_has_more (messages); + notmuch_messages_advance (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_has_more (messages); + notmuch_messages_advance (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 + * we have a term-length limit. So if we exceed that, we'll use the + * SHA-1 of the path for the database term. + * + * Note: This function may return the original value of 'path'. If it + * does not, then the caller is responsible to free() the returned + * value. + */ +const char * +_notmuch_database_get_directory_db_path (const char *path) +{ + int term_len = strlen (_find_prefix ("directory")) + strlen (path); if (term_len > NOTMUCH_TERM_MAX) - return notmuch_sha1_of_string (key); + return notmuch_sha1_of_string (path); else - return strdup (key); + 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 -notmuch_database_set_timestamp (notmuch_database_t *notmuch, - const char *key, time_t timestamp) +_notmuch_database_split_path (void *ctx, + const char *path, + const char **directory, + const char **basename) { - Xapian::Document doc; - unsigned int doc_id; - notmuch_private_status_t status; - notmuch_status_t ret = NOTMUCH_STATUS_SUCCESS; - char *db_key = NULL; + const char *slash; + + if (path == NULL || *path == '\0') { + if (directory) + *directory = NULL; + if (basename) + *basename = NULL; + return NOTMUCH_STATUS_SUCCESS; + } - db_key = timestamp_db_key (key); + /* Find the last slash (not counting a trailing slash), if any. */ - try { - status = find_timestamp_document (notmuch, db_key, &doc, &doc_id); + slash = path + strlen (path) - 1; - doc.add_value (NOTMUCH_VALUE_TIMESTAMP, - Xapian::sortable_serialise (timestamp)); + /* First, skip trailing slashes. */ + while (slash != path) { + if (*slash != '/') + break; - if (status == NOTMUCH_PRIVATE_STATUS_NO_DOCUMENT_FOUND) { - char *term = talloc_asprintf (NULL, "%s%s", - _find_prefix ("timestamp"), db_key); - doc.add_term (term); - talloc_free (term); + --slash; + } - notmuch->xapian_db->add_document (doc); - } else { - notmuch->xapian_db->replace_document (doc_id, doc); - } + /* Then, find a slash. */ + while (slash != path) { + if (*slash == '/') + break; - } catch (Xapian::Error &error) { - fprintf (stderr, "A Xapian exception occurred: %s.\n", - error.get_msg().c_str()); - ret = NOTMUCH_STATUS_XAPIAN_EXCEPTION; + if (basename) + *basename = slash; + + --slash; } - if (db_key) - free (db_key); + /* Finally, skip multiple slashes. */ + while (slash != path) { + if (*slash != '/') + break; - return ret; + --slash; + } + + if (slash == path) { + if (directory) + *directory = talloc_strdup (ctx, ""); + if (basename) + *basename = path; + } else { + if (directory) + *directory = talloc_strndup (ctx, path, slash - path + 1); + } + + return NOTMUCH_STATUS_SUCCESS; } -time_t -notmuch_database_get_timestamp (notmuch_database_t *notmuch, const char *key) +notmuch_status_t +_notmuch_database_find_directory_id (notmuch_database_t *notmuch, + const char *path, + unsigned int *directory_id) { - Xapian::Document doc; - unsigned int doc_id; - notmuch_private_status_t status; - char *db_key = NULL; - time_t ret = 0; + notmuch_directory_t *directory; + notmuch_status_t status; - db_key = timestamp_db_key (key); + if (path == NULL) { + *directory_id = 0; + return NOTMUCH_STATUS_SUCCESS; + } - try { - status = find_timestamp_document (notmuch, db_key, &doc, &doc_id); + directory = _notmuch_directory_create (notmuch, path, &status); + if (status) { + *directory_id = -1; + return status; + } - if (status == NOTMUCH_PRIVATE_STATUS_NO_DOCUMENT_FOUND) - goto DONE; + *directory_id = _notmuch_directory_get_document_id (directory); - ret = Xapian::sortable_unserialise (doc.get_value (NOTMUCH_VALUE_TIMESTAMP)); - } catch (Xapian::Error &error) { - goto DONE; + 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. + * + * The return value will be a pointer to the originl 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). + */ +const char * +_notmuch_database_relative_path (notmuch_database_t *notmuch, + const char *path) +{ + const char *db_path, *relative; + unsigned int db_path_len; + + db_path = notmuch_database_get_path (notmuch); + db_path_len = strlen (db_path); + + relative = path; + + if (*relative == '/') { + while (*relative == '/' && *(relative+1) == '/') + relative++; + + if (strncmp (relative, db_path, db_path_len) == 0) + { + relative += db_path_len; + while (*relative == '/') + relative++; + } } - DONE: - if (db_key) - free (db_key); + return relative; +} - return ret; +notmuch_directory_t * +notmuch_database_get_directory (notmuch_database_t *notmuch, + const char *path) +{ + notmuch_status_t status; + + return _notmuch_directory_create (notmuch, path, &status); } /* Find the thread ID to which the message with 'message_id' belongs. @@ -816,17 +1294,40 @@ _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'.p + * database for existing message that reference 'message'. In either + * case, we will assign to the current message the first thread_id + * found (through either parent or child). We will also merge any + * existing, distinct threads where this message belongs to both, + * (which is not uncommon when mesages are processed out of order). * - * The end result is to call _notmuch_message_add_thread_id with one - * or more thread IDs to which this message belongs, (including - * generating a new thread ID if necessary if the message doesn't - * connect to any existing threads). + * 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. */ static notmuch_status_t _notmuch_database_link_message (notmuch_database_t *notmuch, @@ -847,8 +1348,12 @@ _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; } @@ -865,16 +1370,18 @@ notmuch_database_add_message (notmuch_database_t *notmuch, const char *date, *header; const char *from, *to, *subject; - char *message_id; + char *message_id = NULL; 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", @@ -896,9 +1403,9 @@ notmuch_database_add_message (notmuch_database_t *notmuch, subject = notmuch_message_file_get_header (message_file, "subject"); to = notmuch_message_file_get_header (message_file, "to"); - if (from == NULL && - subject == NULL && - to == NULL) + if ((from == NULL || *from == '\0') && + (subject == NULL || *subject == '\0') && + (to == NULL || *to == '\0')) { ret = NOTMUCH_STATUS_FILE_NOT_EMAIL; goto DONE; @@ -908,13 +1415,22 @@ notmuch_database_add_message (notmuch_database_t *notmuch, * is to find a message ID (or else create one ourselves). */ header = notmuch_message_file_get_header (message_file, "message-id"); - if (header) { + if (header && *header != '\0') { message_id = _parse_message_id (message_file, header, NULL); + /* So the header value isn't RFC-compliant, but it's * better than no message-id at all. */ if (message_id == NULL) message_id = talloc_strdup (message_file, header); - } else { + + /* Reject a Message ID that's too long. */ + if (message_id && strlen (message_id) + 1 > NOTMUCH_TERM_MAX) { + talloc_free (message_id); + message_id = NULL; + } + } + + if (message_id == NULL ) { /* No message-id at all, let's generate one by taking a * hash over the file's contents. */ char *sha1 = notmuch_sha1_of_file (filename); @@ -940,31 +1456,36 @@ notmuch_database_add_message (notmuch_database_t *notmuch, talloc_free (message_id); - if (message == NULL) + if (message == NULL) { + ret = COERCE_STATUS (private_status, + "Unexpected status value from _notmuch_message_create_for_message_id"); 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: %s.\n", - error.get_msg().c_str()); + fprintf (stderr, "A Xapian exception occurred adding message: %s.\n", + error.get_description().c_str()); + notmuch->exception_reported = TRUE; ret = NOTMUCH_STATUS_XAPIAN_EXCEPTION; goto DONE; } @@ -982,3 +1503,100 @@ 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 = talloc_new (notmuch); + 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; + + db = static_cast (notmuch->xapian_db); + + 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; + } + } + + talloc_free (local); + + return status; +} + +notmuch_tags_t * +_notmuch_convert_tags (void *ctx, Xapian::TermIterator &i, + Xapian::TermIterator &end) +{ + const char *prefix = _find_prefix ("tag"); + notmuch_tags_t *tags; + std::string tag; + + /* 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)) + return NULL; + + i.skip_to (prefix); + + while (i != end) { + tag = *i; + + if (tag.empty () || tag[0] != *prefix) + break; + + _notmuch_tags_add_tag (tags, tag.c_str () + 1); + + i++; + } + + _notmuch_tags_prepare_iterator (tags); + + return tags; +} + +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); +}