X-Git-Url: https://git.notmuchmail.org/git?p=notmuch;a=blobdiff_plain;f=notmuch-new.c;h=44b50aaa2c49ceea06825abea39256790f2c1a5d;hp=f34d4676cbc95c724fbbe93901b80012ff172f2c;hb=9ddde6eb14c126e314d90e2e08f213fb81f0457f;hpb=28ce73848d98d8ee2b661733402e2c10b13418d5 diff --git a/notmuch-new.c b/notmuch-new.c index f34d4676..44b50aaa 100644 --- a/notmuch-new.c +++ b/notmuch-new.c @@ -22,6 +22,16 @@ #include +typedef struct _filename_node { + char *filename; + struct _filename_node *next; +} _filename_node_t; + +typedef struct _filename_list { + _filename_node_t *head; + _filename_node_t **tail; +} _filename_list_t; + typedef struct { int output_is_a_tty; int verbose; @@ -30,6 +40,9 @@ typedef struct { int processed_files; int added_messages; struct timeval tv_start; + + _filename_list_t *removed_files; + _filename_list_t *removed_directories; } add_files_state_t; static volatile sig_atomic_t do_add_files_print_progress = 0; @@ -52,6 +65,34 @@ handle_sigint (unused (int sig)) interrupted = 1; } +static _filename_list_t * +_filename_list_create (const void *ctx) +{ + _filename_list_t *list; + + list = talloc (ctx, _filename_list_t); + if (list == NULL) + return NULL; + + list->head = NULL; + list->tail = &list->head; + + return list; +} + +static void +_filename_list_add (_filename_list_t *list, + const char *filename) +{ + _filename_node_t *node = talloc (list, _filename_node_t); + + node->filename = talloc_strdup (list, filename); + node->next = NULL; + + *(list->tail) = node; + list->tail = &node->next; +} + static void tag_inbox_and_unread (notmuch_message_t *message) { @@ -87,11 +128,18 @@ add_files_print_progress (add_files_state_t *state) fflush (stdout); } -static int ino_cmp(const struct dirent **a, const struct dirent **b) +static int +dirent_sort_inode (const struct dirent **a, const struct dirent **b) { return ((*a)->d_ino < (*b)->d_ino) ? -1 : 1; } +static int +dirent_sort_strcmp_name (const struct dirent **a, const struct dirent **b) +{ + return strcmp ((*a)->d_name, (*b)->d_name); +} + /* Test if the directory looks like a Maildir directory. * * Search through the array of directory entries to see if we can find all @@ -100,12 +148,14 @@ static int ino_cmp(const struct dirent **a, const struct dirent **b) * Return 1 if the directory looks like a Maildir and 0 otherwise. */ static int -is_maildir (struct dirent **entries, int count) +_entries_resemble_maildir (struct dirent **entries, int count) { int i, found = 0; for (i = 0; i < count; i++) { - if (entries[i]->d_type != DT_DIR) continue; + if (entries[i]->d_type != DT_DIR && entries[i]->d_type != DT_UNKNOWN) + continue; + if (strcmp(entries[i]->d_name, "new") == 0 || strcmp(entries[i]->d_name, "cur") == 0 || strcmp(entries[i]->d_name, "tmp") == 0) @@ -122,21 +172,37 @@ is_maildir (struct dirent **entries, int count) /* Examine 'path' recursively as follows: * * o Ask the filesystem for the mtime of 'path' (fs_mtime) - * * o Ask the database for its timestamp of 'path' (db_mtime) * - * o For each sub-directory of path, recursively call into this - * same function. + * o Ask the filesystem for files and directories within 'path' + * (via scandir and stored in fs_entries) + * o Ask the database for files and directories within 'path' + * (db_files and db_subdirs) * - * o If 'fs_mtime' > 'db_mtime' + * o Pass 1: For each directory in fs_entries, recursively call into + * this same function. * - * o For each regular file directly within 'path', call - * add_message to add the file to the database. + * o Pass 2: If 'fs_mtime' > 'db_mtime', then walk fs_entries + * simultaneously with db_files and db_subdirs. Look for one of + * three interesting cases: * - * o Tell the database to update its time of 'path' to 'fs_mtime' + * 1. Regular file in fs_entries and not in db_files + * This is a new file to add_message into the database. + * + * 2. Filename in db_files not in fs_entries. + * This is a file that has been removed from the mail store. + * + * 3. Directory in db_subdirs not in fs_entries + * This is a directory that has been removed from the mail store. + * + * Note that the addition of a directory is not interesting here, + * since that will have been taken care of in pass 1. Also, we + * don't immediately act on file/directory removal since we must + * ensure that in the case of a rename that the new filename is + * added before the old filename is removed, (so that no + * information is lost from the database). * - * The 'struct stat *st' must point to a structure that has already - * been initialized for 'path' by calling stat(). + * o Tell the database to update its time of 'path' to 'fs_mtime' */ static notmuch_status_t add_files_recursive (notmuch_database_t *notmuch, @@ -152,7 +218,10 @@ add_files_recursive (notmuch_database_t *notmuch, struct dirent **fs_entries = NULL; int i, num_fs_entries; notmuch_directory_t *directory; + notmuch_filenames_t *db_files = NULL; + notmuch_filenames_t *db_subdirs = NULL; struct stat st; + notmuch_bool_t is_maildir, new_directory; if (stat (path, &st)) { fprintf (stderr, "Error reading directory %s: %s\n", @@ -160,17 +229,33 @@ add_files_recursive (notmuch_database_t *notmuch, return NOTMUCH_STATUS_FILE_ERROR; } - if (! S_ISDIR (st.st_mode)) { - fprintf (stderr, "Error: %s is not a directory.\n", path); - return NOTMUCH_STATUS_FILE_ERROR; - } + /* This is not an error since we may have recursed based on a + * symlink to a regular file, not a directory, and we don't know + * that until this stat. */ + if (! S_ISDIR (st.st_mode)) + return NOTMUCH_STATUS_SUCCESS; fs_mtime = st.st_mtime; directory = notmuch_database_get_directory (notmuch, path); db_mtime = notmuch_directory_get_mtime (directory); - num_fs_entries = scandir (path, &fs_entries, 0, ino_cmp); + if (db_mtime == 0) { + new_directory = TRUE; + db_files = NULL; + db_subdirs = NULL; + } else { + new_directory = FALSE; + db_files = notmuch_directory_get_child_files (directory); + db_subdirs = notmuch_directory_get_child_directories (directory); + } + + /* If the database knows about this directory, then we sort based + * on strcmp to match the database sorting. Otherwise, we can do + * inode-based sorting for faster filesystem operation. */ + num_fs_entries = scandir (path, &fs_entries, 0, + new_directory ? + dirent_sort_inode : dirent_sort_strcmp_name); if (num_fs_entries == -1) { fprintf (stderr, "Error opening directory %s: %s\n", @@ -179,26 +264,38 @@ add_files_recursive (notmuch_database_t *notmuch, goto DONE; } - /* First, recurse into all sub-directories. */ + /* Pass 1: Recurse into all sub-directories. */ + is_maildir = _entries_resemble_maildir (fs_entries, num_fs_entries); + for (i = 0; i < num_fs_entries; i++) { if (interrupted) break; entry = fs_entries[i]; - if (entry->d_type != DT_DIR) + /* We only want to descend into directories. + * But symlinks can be to directories too, of course. + * + * And if the filesystem doesn't tell us the file type in the + * scandir results, then it might be a directory (and if not, + * then we'll stat and return immediately in the next level of + * recursion). */ + if (entry->d_type != DT_DIR && + entry->d_type != DT_LNK && + entry->d_type != DT_UNKNOWN) + { continue; + } /* Ignore special directories to avoid infinite recursion. - * Also ignore the .notmuch directory. + * Also ignore the .notmuch directory and any "tmp" directory + * that appears within a maildir. */ /* XXX: Eventually we'll want more sophistication to let the * user specify files to be ignored. */ if (strcmp (entry->d_name, ".") == 0 || strcmp (entry->d_name, "..") == 0 || - (entry->d_type == DT_DIR && - (strcmp (entry->d_name, "tmp") == 0) && - is_maildir (fs_entries, num_fs_entries)) || + (is_maildir && strcmp (entry->d_name, "tmp") == 0) || strcmp (entry->d_name, ".notmuch") ==0) { continue; @@ -213,21 +310,86 @@ add_files_recursive (notmuch_database_t *notmuch, } /* If this directory hasn't been modified since the last - * add_files, then we can skip the second pass where we look for - * new files in this directory. */ + * "notmuch new", then we can skip the second pass entirely. */ if (fs_mtime <= db_mtime) goto DONE; - /* Second, scan the regular files in this directory. */ - for (i = 0; i < num_fs_entries; i++) { + /* Pass 2: Scan for new files, removed files, and removed directories. */ + for (i = 0; i < num_fs_entries; i++) + { if (interrupted) break; entry = fs_entries[i]; - if (entry->d_type != DT_REG) + /* Check if we've walked past any names in db_files or + * db_subdirs. If so, these have been deleted. */ + while (notmuch_filenames_valid (db_files) && + strcmp (notmuch_filenames_get (db_files), entry->d_name) < 0) + { + char *absolute = talloc_asprintf (state->removed_files, + "%s/%s", path, + notmuch_filenames_get (db_files)); + + _filename_list_add (state->removed_files, absolute); + + notmuch_filenames_move_to_next (db_files); + } + + while (notmuch_filenames_valid (db_subdirs) && + strcmp (notmuch_filenames_get (db_subdirs), entry->d_name) <= 0) + { + const char *filename = notmuch_filenames_get (db_subdirs); + + if (strcmp (filename, entry->d_name) < 0) + { + char *absolute = talloc_asprintf (state->removed_directories, + "%s/%s", path, filename); + + _filename_list_add (state->removed_directories, absolute); + } + + notmuch_filenames_move_to_next (db_subdirs); + } + + /* If we're looking at a symlink, we only want to add it if it + * links to a regular file, (and not to a directory, say). + * + * Similarly, if the file is of unknown type (due to filesytem + * limitations), then we also need to look closer. + * + * In either case, a stat does the trick. + */ + if (entry->d_type == DT_LNK || entry->d_type == DT_UNKNOWN) { + int err; + + next = talloc_asprintf (notmuch, "%s/%s", path, entry->d_name); + err = stat (next, &st); + talloc_free (next); + next = NULL; + + /* Don't emit an error for a link pointing nowhere, since + * the directory-traversal pass will have already done + * that. */ + if (err) + continue; + + if (! S_ISREG (st.st_mode)) + continue; + } else if (entry->d_type != DT_REG) { continue; + } + /* Don't add a file that we've added before. */ + if (notmuch_filenames_valid (db_files) && + strcmp (notmuch_filenames_get (db_files), entry->d_name) == 0) + { + notmuch_filenames_move_to_next (db_files); + continue; + } + + /* We're now looking at a regular file that doesn't yet exist + * in the database, so add it. */ next = talloc_asprintf (notmuch, "%s/%s", path, entry->d_name); state->processed_files++; @@ -261,7 +423,7 @@ add_files_recursive (notmuch_database_t *notmuch, next); break; /* Fatal issues. Don't process anymore. */ - case NOTMUCH_STATUS_READONLY_DATABASE: + case NOTMUCH_STATUS_READ_ONLY_DATABASE: case NOTMUCH_STATUS_XAPIAN_EXCEPTION: case NOTMUCH_STATUS_OUT_OF_MEMORY: fprintf (stderr, "Error: %s. Halting processing.\n", @@ -292,6 +454,30 @@ add_files_recursive (notmuch_database_t *notmuch, next = NULL; } + /* Now that we've walked the whole filesystem list, anything left + * over in the database lists has been deleted. */ + while (notmuch_filenames_valid (db_files)) + { + char *absolute = talloc_asprintf (state->removed_files, + "%s/%s", path, + notmuch_filenames_get (db_files)); + + _filename_list_add (state->removed_files, absolute); + + notmuch_filenames_move_to_next (db_files); + } + + while (notmuch_filenames_valid (db_subdirs)) + { + char *absolute = talloc_asprintf (state->removed_directories, + "%s/%s", path, + notmuch_filenames_get (db_subdirs)); + + _filename_list_add (state->removed_directories, absolute); + + notmuch_filenames_move_to_next (db_subdirs); + } + if (! interrupted) { status = notmuch_directory_set_mtime (directory, fs_mtime); if (status && ret == NOTMUCH_STATUS_SUCCESS) @@ -307,6 +493,12 @@ add_files_recursive (notmuch_database_t *notmuch, closedir (dir); if (fs_entries) free (fs_entries); + if (db_subdirs) + notmuch_filenames_destroy (db_subdirs); + if (db_files) + notmuch_filenames_destroy (db_files); + if (directory) + notmuch_directory_destroy (directory); return ret; } @@ -323,6 +515,7 @@ add_files (notmuch_database_t *notmuch, struct sigaction action; struct itimerval timerval; notmuch_bool_t timer_is_active = FALSE; + struct stat st; if (state->output_is_a_tty && ! debugger_is_active () && ! state->verbose) { /* Setup our handler for SIGALRM */ @@ -342,6 +535,17 @@ add_files (notmuch_database_t *notmuch, timer_is_active = TRUE; } + if (stat (path, &st)) { + fprintf (stderr, "Error reading directory %s: %s\n", + path, strerror (errno)); + return NOTMUCH_STATUS_FILE_ERROR; + } + + if (! S_ISDIR (st.st_mode)) { + fprintf (stderr, "Error: %s is not a directory.\n", path); + return NOTMUCH_STATUS_FILE_ERROR; + } + status = add_files_recursive (notmuch, path, state); if (timer_is_active) { @@ -373,7 +577,7 @@ count_files (const char *path, int *count) char *next; struct stat st; struct dirent **fs_entries = NULL; - int num_fs_entries = scandir (path, &fs_entries, 0, ino_cmp); + int num_fs_entries = scandir (path, &fs_entries, 0, dirent_sort_inode); int i = 0; if (num_fs_entries == -1) { @@ -429,6 +633,75 @@ count_files (const char *path, int *count) free (fs_entries); } +static void +upgrade_print_progress (void *closure, + double progress) +{ + add_files_state_t *state = closure; + + printf ("Upgrading database: %.2f%% complete", progress * 100.0); + + if (progress > 0) { + struct timeval tv_now; + double elapsed, time_remaining; + + gettimeofday (&tv_now, NULL); + + elapsed = notmuch_time_elapsed (state->tv_start, tv_now); + time_remaining = (elapsed / progress) * (1.0 - progress); + printf (" ("); + notmuch_time_print_formatted_seconds (time_remaining); + printf (" remaining)"); + } + + printf (". \r"); + + fflush (stdout); +} + +/* Recursively remove all filenames from the database referring to + * 'path' (or to any of its children). */ +static void +_remove_directory (void *ctx, + notmuch_database_t *notmuch, + const char *path, + int *renamed_files, + int *removed_files) +{ + notmuch_directory_t *directory; + notmuch_filenames_t *files, *subdirs; + notmuch_status_t status; + char *absolute; + + directory = notmuch_database_get_directory (notmuch, path); + + for (files = notmuch_directory_get_child_files (directory); + notmuch_filenames_valid (files); + notmuch_filenames_move_to_next (files)) + { + absolute = talloc_asprintf (ctx, "%s/%s", path, + notmuch_filenames_get (files)); + status = notmuch_database_remove_message (notmuch, absolute); + if (status == NOTMUCH_STATUS_DUPLICATE_MESSAGE_ID) + *renamed_files = *renamed_files + 1; + else + *removed_files = *removed_files + 1; + talloc_free (absolute); + } + + for (subdirs = notmuch_directory_get_child_directories (directory); + notmuch_filenames_valid (subdirs); + notmuch_filenames_move_to_next (subdirs)) + { + absolute = talloc_asprintf (ctx, "%s/%s", path, + notmuch_filenames_get (subdirs)); + _remove_directory (ctx, notmuch, absolute, renamed_files, removed_files); + talloc_free (absolute); + } + + notmuch_directory_destroy (directory); +} + int notmuch_new_command (void *ctx, int argc, char *argv[]) { @@ -442,6 +715,9 @@ notmuch_new_command (void *ctx, int argc, char *argv[]) const char *db_path; char *dot_notmuch_path; struct sigaction action; + _filename_node_t *f; + int renamed_files, removed_files; + notmuch_status_t status; int i; add_files_state.verbose = 0; @@ -456,13 +732,6 @@ notmuch_new_command (void *ctx, int argc, char *argv[]) } } - /* Setup our handler for SIGINT */ - memset (&action, 0, sizeof (struct sigaction)); - action.sa_handler = handle_sigint; - sigemptyset (&action.sa_mask); - action.sa_flags = SA_RESTART; - sigaction (SIGINT, &action, NULL); - config = notmuch_config_open (ctx, NULL, NULL); if (config == NULL) return 1; @@ -485,12 +754,33 @@ notmuch_new_command (void *ctx, int argc, char *argv[]) } else { notmuch = notmuch_database_open (db_path, NOTMUCH_DATABASE_MODE_READ_WRITE); + if (notmuch == NULL) + return 1; + + if (notmuch_database_needs_upgrade (notmuch)) { + printf ("Welcome to a new version of notmuch! Your database will now be upgraded.\n"); + gettimeofday (&add_files_state.tv_start, NULL); + notmuch_database_upgrade (notmuch, upgrade_print_progress, + &add_files_state); + printf ("Your notmuch database has now been upgraded to database format version %u.\n", + notmuch_database_get_version (notmuch)); + } + add_files_state.total_files = 0; } if (notmuch == NULL) return 1; + /* Setup our handler for SIGINT. We do this after having + * potentially done a database upgrade we this interrupt handler + * won't support. */ + memset (&action, 0, sizeof (struct sigaction)); + action.sa_handler = handle_sigint; + sigemptyset (&action.sa_mask); + action.sa_flags = SA_RESTART; + sigaction (SIGINT, &action, NULL); + talloc_free (dot_notmuch_path); dot_notmuch_path = NULL; @@ -498,11 +788,33 @@ notmuch_new_command (void *ctx, int argc, char *argv[]) add_files_state.added_messages = 0; gettimeofday (&add_files_state.tv_start, NULL); + add_files_state.removed_files = _filename_list_create (ctx); + add_files_state.removed_directories = _filename_list_create (ctx); + ret = add_files (notmuch, db_path, &add_files_state); + removed_files = 0; + renamed_files = 0; + for (f = add_files_state.removed_files->head; f; f = f->next) { + status = notmuch_database_remove_message (notmuch, f->filename); + if (status == NOTMUCH_STATUS_DUPLICATE_MESSAGE_ID) + renamed_files++; + else + removed_files++; + } + + for (f = add_files_state.removed_directories->head; f; f = f->next) { + _remove_directory (ctx, notmuch, f->filename, + &renamed_files, &removed_files); + } + + talloc_free (add_files_state.removed_files); + talloc_free (add_files_state.removed_directories); + gettimeofday (&tv_now, NULL); elapsed = notmuch_time_elapsed (add_files_state.tv_start, tv_now); + if (add_files_state.processed_files) { printf ("Processed %d %s in ", add_files_state.processed_files, add_files_state.processed_files == 1 ? @@ -515,15 +827,30 @@ notmuch_new_command (void *ctx, int argc, char *argv[]) printf (". \n"); } } + if (add_files_state.added_messages) { - printf ("Added %d new %s to the database.\n", + printf ("Added %d new %s to the database.", add_files_state.added_messages, add_files_state.added_messages == 1 ? "message" : "messages"); } else { - printf ("No new mail.\n"); + printf ("No new mail."); + } + + if (removed_files) { + printf (" Removed %d %s.", + removed_files, + removed_files == 1 ? "message" : "messages"); + } + + if (renamed_files) { + printf (" Detected %d file %s.", + renamed_files, + renamed_files == 1 ? "rename" : "renames"); } + printf ("\n"); + if (ret) { printf ("\nNote: At least one error was encountered: %s\n", notmuch_status_to_string (ret));