X-Git-Url: https://git.notmuchmail.org/git?p=notmuch;a=blobdiff_plain;f=lib%2Fdatabase.cc;h=aef748f75b5d61ca6f2f34c35a2af93d0bd81f70;hp=f8c4a7d121d0bdbcd2a631ee65ed9303ab9cd9fa;hb=3fed6736a7ef8b8b1f05d0fabb136bdd3b5917ee;hpb=7199d22f4394abdf72ab791fc0aba2c697bf1209 diff --git a/lib/database.cc b/lib/database.cc index f8c4a7d1..aef748f7 100644 --- a/lib/database.cc +++ b/lib/database.cc @@ -19,11 +19,14 @@ */ #include "database-private.h" +#include "parse-time-vrp.h" #include #include +#include #include +#include #include /* g_free, GPtrArray, GHashTable */ #include /* g_type_init */ @@ -39,7 +42,7 @@ typedef struct { const char *prefix; } prefix_t; -#define NOTMUCH_DATABASE_VERSION 1 +#define NOTMUCH_DATABASE_VERSION 2 #define STRINGIFY(s) _SUB_STRINGIFY(s) #define _SUB_STRINGIFY(s) #s @@ -97,8 +100,8 @@ typedef struct { * 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. 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. + * message are added with "folder" and "path" prefixes. But the + * database doesn't really care itself about any of these. * * The data portion of a mail document is empty. * @@ -205,7 +208,15 @@ static prefix_t BOOLEAN_PREFIX_EXTERNAL[] = { { "thread", "G" }, { "tag", "K" }, { "is", "K" }, - { "id", "Q" } + { "id", "Q" }, + { "path", "P" }, + /* + * Without the ":", since this is a multi-letter prefix, Xapian + * will add a colon itself if the first letter of the path is + * upper-case ASCII. Including the ":" forces there to always be a + * colon, which keeps our own logic simpler. + */ + { "folder", "XFOLDER:" }, }; static prefix_t PROBABILISTIC_PREFIX[]= { @@ -213,7 +224,6 @@ static prefix_t PROBABILISTIC_PREFIX[]= { { "to", "XTO" }, { "attachment", "XATTACHMENT" }, { "subject", "XSUBJECT"}, - { "folder", "XFOLDER"} }; const char * @@ -267,6 +277,8 @@ notmuch_status_to_string (notmuch_status_t status) 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"; + case NOTMUCH_STATUS_UNSUPPORTED_OPERATION: + return "Unsupported operation"; default: case NOTMUCH_STATUS_LAST_STATUS: return "Unknown error status value"; @@ -500,8 +512,10 @@ _parse_message_id (void *ctx, const char *message_id, const char **next) * 'message_id' in the result (to avoid mass confusion when a single * message references itself cyclically---and yes, mail messages are * not infrequent in the wild that do this---don't ask me why). -*/ -static void + * + * Return the last reference parsed, if it is not equal to message_id. + */ +static char * parse_references (void *ctx, const char *message_id, GHashTable *hash, @@ -510,7 +524,7 @@ parse_references (void *ctx, char *ref; if (refs == NULL || *refs == '\0') - return; + return NULL; while (*refs) { ref = _parse_message_id (ctx, refs, &refs); @@ -518,6 +532,17 @@ parse_references (void *ctx, if (ref && strcmp (ref, message_id)) g_hash_table_insert (hash, ref, NULL); } + + /* The return value of this function is used to add a parent + * reference to the database. We should avoid making a message + * its own parent, thus the following check. + */ + + if (ref && strcmp(ref, message_id)) { + return ref; + } else { + return NULL; + } } notmuch_status_t @@ -635,11 +660,13 @@ notmuch_database_open (const char *path, } /* Initialize the GLib type system and threads */ +#if !GLIB_CHECK_VERSION(2, 35, 1) g_type_init (); +#endif /* Initialize gmime */ if (! initialized) { - g_mime_init (0); + g_mime_init (GMIME_ENABLE_RFC2047_WORKAROUNDS); initialized = 1; } @@ -710,12 +737,14 @@ notmuch_database_open (const char *path, 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->date_range_processor = new ParseTimeValueRangeProcessor (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); + notmuch->query_parser->add_valuerangeprocessor (notmuch->date_range_processor); for (i = 0; i < ARRAY_SIZE (BOOLEAN_PREFIX_EXTERNAL); i++) { prefix_t *prefix = &BOOLEAN_PREFIX_EXTERNAL[i]; @@ -778,7 +807,189 @@ notmuch_database_close (notmuch_database_t *notmuch) notmuch->xapian_db = NULL; delete notmuch->value_range_processor; notmuch->value_range_processor = NULL; + delete notmuch->date_range_processor; + notmuch->date_range_processor = NULL; +} + +#if HAVE_XAPIAN_COMPACT +static int +unlink_cb (const char *path, + unused (const struct stat *sb), + unused (int type), + unused (struct FTW *ftw)) +{ + return remove (path); +} + +static int +rmtree (const char *path) +{ + return nftw (path, unlink_cb, 64, FTW_DEPTH | FTW_PHYS); +} + +class NotmuchCompactor : public Xapian::Compactor +{ + notmuch_compact_status_cb_t status_cb; + void *status_closure; + +public: + NotmuchCompactor(notmuch_compact_status_cb_t cb, void *closure) : + status_cb (cb), status_closure (closure) { } + + virtual void + set_status (const std::string &table, const std::string &status) + { + char *msg; + + if (status_cb == NULL) + return; + + if (status.length () == 0) + msg = talloc_asprintf (NULL, "compacting table %s", table.c_str()); + else + msg = talloc_asprintf (NULL, " %s", status.c_str()); + + if (msg == NULL) { + return; + } + + status_cb (msg, status_closure); + talloc_free (msg); + } +}; + +/* Compacts the given database, optionally saving the original database + * in backup_path. Additionally, a callback function can be provided to + * give the user feedback on the progress of the (likely long-lived) + * compaction process. + * + * The backup path must point to a directory on the same volume as the + * original database. Passing a NULL backup_path will result in the + * uncompacted database being deleted after compaction has finished. + * Note that the database write lock will be held during the + * compaction process to protect data integrity. + */ +notmuch_status_t +notmuch_database_compact (const char *path, + const char *backup_path, + notmuch_compact_status_cb_t status_cb, + void *closure) +{ + void *local; + char *notmuch_path, *xapian_path, *compact_xapian_path; + notmuch_status_t ret = NOTMUCH_STATUS_SUCCESS; + notmuch_database_t *notmuch = NULL; + struct stat statbuf; + notmuch_bool_t keep_backup; + + local = talloc_new (NULL); + if (! local) + return NOTMUCH_STATUS_OUT_OF_MEMORY; + + ret = notmuch_database_open (path, NOTMUCH_DATABASE_MODE_READ_WRITE, ¬much); + if (ret) { + goto DONE; + } + + if (! (notmuch_path = talloc_asprintf (local, "%s/%s", path, ".notmuch"))) { + ret = NOTMUCH_STATUS_OUT_OF_MEMORY; + goto DONE; + } + + if (! (xapian_path = talloc_asprintf (local, "%s/%s", notmuch_path, "xapian"))) { + ret = NOTMUCH_STATUS_OUT_OF_MEMORY; + goto DONE; + } + + if (! (compact_xapian_path = talloc_asprintf (local, "%s.compact", xapian_path))) { + ret = NOTMUCH_STATUS_OUT_OF_MEMORY; + goto DONE; + } + + if (backup_path == NULL) { + if (! (backup_path = talloc_asprintf (local, "%s.old", xapian_path))) { + ret = NOTMUCH_STATUS_OUT_OF_MEMORY; + goto DONE; + } + keep_backup = FALSE; + } + else { + keep_backup = TRUE; + } + + if (stat (backup_path, &statbuf) != -1) { + fprintf (stderr, "Path already exists: %s\n", backup_path); + ret = NOTMUCH_STATUS_FILE_ERROR; + goto DONE; + } + if (errno != ENOENT) { + fprintf (stderr, "Unknown error while stat()ing path: %s\n", + strerror (errno)); + ret = NOTMUCH_STATUS_FILE_ERROR; + goto DONE; + } + + /* Unconditionally attempt to remove old work-in-progress database (if + * any). This is "protected" by database lock. If this fails due to write + * errors (etc), the following code will fail and provide error message. + */ + (void) rmtree (compact_xapian_path); + + try { + NotmuchCompactor compactor (status_cb, closure); + + compactor.set_renumber (false); + compactor.add_source (xapian_path); + compactor.set_destdir (compact_xapian_path); + compactor.compact (); + } catch (const Xapian::Error &error) { + fprintf (stderr, "Error while compacting: %s\n", error.get_msg().c_str()); + ret = NOTMUCH_STATUS_XAPIAN_EXCEPTION; + goto DONE; + } + + if (rename (xapian_path, backup_path)) { + fprintf (stderr, "Error moving %s to %s: %s\n", + xapian_path, backup_path, strerror (errno)); + ret = NOTMUCH_STATUS_FILE_ERROR; + goto DONE; + } + + if (rename (compact_xapian_path, xapian_path)) { + fprintf (stderr, "Error moving %s to %s: %s\n", + compact_xapian_path, xapian_path, strerror (errno)); + ret = NOTMUCH_STATUS_FILE_ERROR; + goto DONE; + } + + if (! keep_backup) { + if (rmtree (backup_path)) { + fprintf (stderr, "Error removing old database %s: %s\n", + backup_path, strerror (errno)); + ret = NOTMUCH_STATUS_FILE_ERROR; + goto DONE; + } + } + + DONE: + if (notmuch) + notmuch_database_destroy (notmuch); + + talloc_free (local); + + return ret; +} +#else +notmuch_status_t +notmuch_database_compact (unused (const char *path), + unused (const char *backup_path), + unused (notmuch_compact_status_cb_t status_cb), + unused (void *closure)) +{ + fprintf (stderr, "notmuch was compiled against a xapian version lacking compaction support.\n"); + return NOTMUCH_STATUS_UNSUPPORTED_OPERATION; } +#endif void notmuch_database_destroy (notmuch_database_t *notmuch) @@ -956,13 +1167,47 @@ notmuch_database_upgrade (notmuch_database_t *notmuch, document.get_value (NOTMUCH_VALUE_TIMESTAMP)); directory = _notmuch_directory_create (notmuch, term.c_str() + 10, - &status); + NOTMUCH_FIND_CREATE, &status); notmuch_directory_set_mtime (directory, mtime); notmuch_directory_destroy (directory); } } } + /* + * Prior to version 2, the "folder:" prefix was probabilistic and + * stemmed. Change it to the current boolean prefix. Add "path:" + * prefixes while at it. + */ + if (version < 2) { + notmuch_query_t *query = notmuch_query_create (notmuch, ""); + notmuch_messages_t *messages; + notmuch_message_t *message; + + count = 0; + 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); + + _notmuch_message_upgrade_folder (message); + _notmuch_message_sync (message); + + notmuch_message_destroy (message); + + count++; + } + + notmuch_query_destroy (query); + } + db->set_metadata ("version", STRINGIFY (NOTMUCH_DATABASE_VERSION)); db->flush (); @@ -1197,9 +1442,17 @@ _notmuch_database_split_path (void *ctx, return NOTMUCH_STATUS_SUCCESS; } +/* Find the document ID of the specified directory. + * + * If (flags & NOTMUCH_FIND_CREATE), a new directory document will be + * created if one does not exist for 'path'. Otherwise, if the + * directory document does not exist, this sets *directory_id to + * ((unsigned int)-1) and returns NOTMUCH_STATUS_SUCCESS. + */ notmuch_status_t _notmuch_database_find_directory_id (notmuch_database_t *notmuch, const char *path, + notmuch_find_flags_t flags, unsigned int *directory_id) { notmuch_directory_t *directory; @@ -1210,8 +1463,8 @@ _notmuch_database_find_directory_id (notmuch_database_t *notmuch, return NOTMUCH_STATUS_SUCCESS; } - directory = _notmuch_directory_create (notmuch, path, &status); - if (status) { + directory = _notmuch_directory_create (notmuch, path, flags, &status); + if (status || !directory) { *directory_id = -1; return status; } @@ -1240,13 +1493,16 @@ _notmuch_database_get_directory_path (void *ctx, * 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. + * If (flags & NOTMUCH_FIND_CREATE), the necessary directory documents + * will be created in the database as needed. Otherwise, if the + * necessary directory documents do not exist, this sets + * *direntry to NULL and returns NOTMUCH_STATUS_SUCCESS. */ notmuch_status_t _notmuch_database_filename_to_direntry (void *ctx, notmuch_database_t *notmuch, const char *filename, + notmuch_find_flags_t flags, char **direntry) { const char *relative, *directory, *basename; @@ -1260,10 +1516,12 @@ _notmuch_database_filename_to_direntry (void *ctx, if (status) return status; - status = _notmuch_database_find_directory_id (notmuch, directory, + status = _notmuch_database_find_directory_id (notmuch, directory, flags, &directory_id); - if (status) + if (status || directory_id == (unsigned int)-1) { + *direntry = NULL; return status; + } *direntry = talloc_asprintf (ctx, "%u:%s", directory_id, basename); @@ -1315,12 +1573,9 @@ notmuch_database_get_directory (notmuch_database_t *notmuch, return NOTMUCH_STATUS_NULL_POINTER; *directory = NULL; - /* XXX Handle read-only databases properly */ - if (notmuch->mode == NOTMUCH_DATABASE_MODE_READ_ONLY) - return NOTMUCH_STATUS_READ_ONLY_DATABASE; - try { - *directory = _notmuch_directory_create (notmuch, path, &status); + *directory = _notmuch_directory_create (notmuch, path, + NOTMUCH_FIND_LOOKUP, &status); } catch (const Xapian::Error &error) { fprintf (stderr, "A Xapian exception occurred getting directory: %s.\n", error.get_msg().c_str()); @@ -1350,7 +1605,7 @@ _notmuch_database_generate_doc_id (notmuch_database_t *notmuch) notmuch->last_doc_id++; if (notmuch->last_doc_id == 0) - INTERNAL_ERROR ("Xapian document IDs are exhausted.\n"); + INTERNAL_ERROR ("Xapian document IDs are exhausted.\n"); return notmuch->last_doc_id; } @@ -1495,28 +1750,33 @@ _notmuch_database_link_message_to_parents (notmuch_database_t *notmuch, { GHashTable *parents = NULL; const char *refs, *in_reply_to, *in_reply_to_message_id; + const char *last_ref_message_id, *this_message_id; GList *l, *keys = NULL; notmuch_status_t ret = NOTMUCH_STATUS_SUCCESS; parents = g_hash_table_new_full (g_str_hash, g_str_equal, _my_talloc_free_for_g_hash, NULL); + this_message_id = notmuch_message_get_message_id (message); refs = notmuch_message_file_get_header (message_file, "references"); - parse_references (message, notmuch_message_get_message_id (message), - parents, refs); + last_ref_message_id = parse_references (message, + this_message_id, + parents, refs); in_reply_to = notmuch_message_file_get_header (message_file, "in-reply-to"); - parse_references (message, notmuch_message_get_message_id (message), - parents, in_reply_to); - - /* Carefully avoid adding any self-referential in-reply-to term. */ - in_reply_to_message_id = _parse_message_id (message, in_reply_to, NULL); - if (in_reply_to_message_id && - strcmp (in_reply_to_message_id, - notmuch_message_get_message_id (message))) - { + in_reply_to_message_id = parse_references (message, + this_message_id, + parents, in_reply_to); + + /* For the parent of this message, use the last message ID of the + * References header, if available. If not, fall back to the + * first message ID in the In-Reply-To header. */ + if (last_ref_message_id) { + _notmuch_message_add_term (message, "replyto", + last_ref_message_id); + } else if (in_reply_to_message_id) { _notmuch_message_add_term (message, "replyto", - _parse_message_id (message, in_reply_to, NULL)); + in_reply_to_message_id); } keys = g_hash_table_get_keys (parents); @@ -1806,7 +2066,9 @@ notmuch_database_add_message (notmuch_database_t *notmuch, date = notmuch_message_file_get_header (message_file, "date"); _notmuch_message_set_header_values (message, date, from, subject); - _notmuch_message_index_file (message, filename); + ret = _notmuch_message_index_file (message, filename); + if (ret) + goto DONE; } else { ret = NOTMUCH_STATUS_DUPLICATE_MESSAGE_ID; } @@ -1884,9 +2146,9 @@ notmuch_database_find_message_by_filename (notmuch_database_t *notmuch, local = talloc_new (notmuch); try { - status = _notmuch_database_filename_to_direntry (local, notmuch, - filename, &direntry); - if (status) + status = _notmuch_database_filename_to_direntry ( + local, notmuch, filename, NOTMUCH_FIND_LOOKUP, &direntry); + if (status || !direntry) goto DONE; term = talloc_asprintf (local, "%s%s", prefix, direntry);