#include <unistd.h>
-static volatile sig_atomic_t do_add_files_print_progress = 0;
+typedef struct _filename_node {
+ char *filename;
+ time_t mtime;
+ struct _filename_node *next;
+} _filename_node_t;
+
+typedef struct _filename_list {
+ unsigned count;
+ _filename_node_t *head;
+ _filename_node_t **tail;
+} _filename_list_t;
+
+typedef struct {
+ int output_is_a_tty;
+ notmuch_bool_t verbose;
+ notmuch_bool_t debug;
+ const char **new_tags;
+ size_t new_tags_length;
+ const char **new_ignore;
+ size_t new_ignore_length;
+
+ int total_files;
+ int processed_files;
+ int added_messages, removed_messages, renamed_messages;
+ struct timeval tv_start;
+
+ _filename_list_t *removed_files;
+ _filename_list_t *removed_directories;
+ _filename_list_t *directory_mtimes;
+
+ notmuch_bool_t synchronize_flags;
+} add_files_state_t;
+
+static volatile sig_atomic_t do_print_progress = 0;
static void
handle_sigalrm (unused (int signal))
{
- do_add_files_print_progress = 1;
+ do_print_progress = 1;
}
static volatile sig_atomic_t interrupted;
static void
handle_sigint (unused (int sig))
{
- ssize_t ignored;
static char msg[] = "Stopping... \n";
- ignored = write(2, msg, sizeof(msg)-1);
+ /* This write is "opportunistic", so it's okay to ignore the
+ * result. It is not required for correctness, and if it does
+ * fail or produce a short write, we want to get out of the signal
+ * handler as quickly as possible, not retry it. */
+ IGNORE_RESULT (write (2, msg, sizeof(msg)-1));
interrupted = 1;
}
-static void
-tag_inbox_and_unread (notmuch_message_t *message)
+static _filename_list_t *
+_filename_list_create (const void *ctx)
{
- notmuch_message_add_tag (message, "inbox");
- notmuch_message_add_tag (message, "unread");
+ _filename_list_t *list;
+
+ list = talloc (ctx, _filename_list_t);
+ if (list == NULL)
+ return NULL;
+
+ list->head = NULL;
+ list->tail = &list->head;
+ list->count = 0;
+
+ return list;
+}
+
+static _filename_node_t *
+_filename_list_add (_filename_list_t *list,
+ const char *filename)
+{
+ _filename_node_t *node = talloc (list, _filename_node_t);
+
+ list->count++;
+
+ node->filename = talloc_strdup (list, filename);
+ node->next = NULL;
+
+ *(list->tail) = node;
+ list->tail = &node->next;
+
+ return node;
}
static void
-add_files_print_progress (add_files_state_t *state)
+generic_print_progress (const char *action, const char *object,
+ struct timeval tv_start, unsigned processed, unsigned total)
{
struct timeval tv_now;
double elapsed_overall, rate_overall;
gettimeofday (&tv_now, NULL);
- elapsed_overall = notmuch_time_elapsed (state->tv_start, tv_now);
- rate_overall = (state->processed_files) / elapsed_overall;
+ elapsed_overall = notmuch_time_elapsed (tv_start, tv_now);
+ rate_overall = processed / elapsed_overall;
- printf ("Processed %d", state->processed_files);
+ printf ("%s %d ", action, processed);
- if (state->total_files) {
- double time_remaining;
-
- time_remaining = ((state->total_files - state->processed_files) /
- rate_overall);
- printf (" of %d files (", state->total_files);
- notmuch_time_print_formatted_seconds (time_remaining);
- printf (" remaining). \r");
+ if (total) {
+ printf ("of %d %s", total, object);
+ if (processed > 0 && elapsed_overall > 0.5) {
+ double time_remaining = ((total - processed) / rate_overall);
+ printf (" (");
+ notmuch_time_print_formatted_seconds (time_remaining);
+ printf (" remaining)");
+ }
} else {
- printf (" files (%d files/sec.) \r", (int) rate_overall);
+ printf ("%s", object);
+ if (elapsed_overall > 0.5)
+ printf (" (%d %s/sec.)", (int) rate_overall, object);
}
+ printf (".\033[K\r");
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);
+}
+
+/* Return the type of a directory entry relative to path as a stat(2)
+ * mode. Like stat, this follows symlinks. Returns -1 and sets errno
+ * if the file's type cannot be determined (which includes dangling
+ * symlinks).
+ */
+static int
+dirent_type (const char *path, const struct dirent *entry)
+{
+ struct stat statbuf;
+ char *abspath;
+ int err, saved_errno;
+
+#ifdef _DIRENT_HAVE_D_TYPE
+ /* Mapping from d_type to stat mode_t. We omit DT_LNK so that
+ * we'll fall through to stat and get the real file type. */
+ static const mode_t modes[] = {
+ [DT_BLK] = S_IFBLK,
+ [DT_CHR] = S_IFCHR,
+ [DT_DIR] = S_IFDIR,
+ [DT_FIFO] = S_IFIFO,
+ [DT_REG] = S_IFREG,
+ [DT_SOCK] = S_IFSOCK
+ };
+ if (entry->d_type < ARRAY_SIZE(modes) && modes[entry->d_type])
+ return modes[entry->d_type];
+#endif
+
+ abspath = talloc_asprintf (NULL, "%s/%s", path, entry->d_name);
+ if (!abspath) {
+ errno = ENOMEM;
+ return -1;
+ }
+ err = stat(abspath, &statbuf);
+ saved_errno = errno;
+ talloc_free (abspath);
+ if (err < 0) {
+ errno = saved_errno;
+ return -1;
+ }
+ return statbuf.st_mode & S_IFMT;
+}
+
/* Test if the directory looks like a Maildir directory.
*
* Search through the array of directory entries to see if we can find all
* Return 1 if the directory looks like a Maildir and 0 otherwise.
*/
static int
-is_maildir (struct dirent **entries, int count)
+_entries_resemble_maildir (const char *path, struct dirent **entries, int count)
{
int i, found = 0;
for (i = 0; i < count; i++) {
- if (entries[i]->d_type != DT_DIR) continue;
+ if (dirent_type (path, entries[i]) != S_IFDIR)
+ continue;
+
if (strcmp(entries[i]->d_name, "new") == 0 ||
strcmp(entries[i]->d_name, "cur") == 0 ||
strcmp(entries[i]->d_name, "tmp") == 0)
return 0;
}
+/* Test if the file/directory is to be ignored.
+ */
+static notmuch_bool_t
+_entry_in_ignore_list (const char *entry, add_files_state_t *state)
+{
+ size_t i;
+
+ for (i = 0; i < state->new_ignore_length; i++)
+ if (strcmp (entry, state->new_ignore[i]) == 0)
+ return TRUE;
+
+ return FALSE;
+}
+
+/* Add a single file to the database. */
+static notmuch_status_t
+add_file (notmuch_database_t *notmuch, const char *filename,
+ add_files_state_t *state)
+{
+ notmuch_message_t *message = NULL;
+ const char **tag;
+ notmuch_status_t status;
+
+ status = notmuch_database_begin_atomic (notmuch);
+ if (status)
+ goto DONE;
+
+ status = notmuch_database_add_message (notmuch, filename, &message);
+ switch (status) {
+ /* Success. */
+ case NOTMUCH_STATUS_SUCCESS:
+ state->added_messages++;
+ notmuch_message_freeze (message);
+ for (tag = state->new_tags; *tag != NULL; tag++)
+ notmuch_message_add_tag (message, *tag);
+ if (state->synchronize_flags)
+ notmuch_message_maildir_flags_to_tags (message);
+ notmuch_message_thaw (message);
+ break;
+ /* Non-fatal issues (go on to next file). */
+ case NOTMUCH_STATUS_DUPLICATE_MESSAGE_ID:
+ if (state->synchronize_flags)
+ notmuch_message_maildir_flags_to_tags (message);
+ break;
+ case NOTMUCH_STATUS_FILE_NOT_EMAIL:
+ fprintf (stderr, "Note: Ignoring non-mail file: %s\n", filename);
+ break;
+ /* Fatal issues. Don't process anymore. */
+ case NOTMUCH_STATUS_READ_ONLY_DATABASE:
+ case NOTMUCH_STATUS_XAPIAN_EXCEPTION:
+ case NOTMUCH_STATUS_OUT_OF_MEMORY:
+ fprintf (stderr, "Error: %s. Halting processing.\n",
+ notmuch_status_to_string (status));
+ goto DONE;
+ default:
+ INTERNAL_ERROR ("add_message returned unexpected value: %d", status);
+ goto DONE;
+ }
+
+ status = notmuch_database_end_atomic (notmuch);
+
+ DONE:
+ if (message)
+ notmuch_message_destroy (message);
+
+ return status;
+}
+
/* Examine 'path' recursively as follows:
*
- * o Ask the filesystem for the mtime of 'path' (path_mtime)
+ * o Ask the filesystem for the mtime of 'path' (fs_mtime)
+ * o Ask the database for its timestamp of 'path' (db_mtime)
*
- * o Ask the database for its timestamp of 'path' (path_dbtime)
+ * o Ask the filesystem for files and directories within 'path'
+ * (via scandir and stored in fs_entries)
*
- * o If 'path_mtime' > 'path_dbtime'
+ * o Pass 1: For each directory in fs_entries, recursively call into
+ * this same function.
*
- * o For each regular file in 'path' with mtime newer than the
- * 'path_dbtime' call add_message to add the file to the
- * database.
+ * o Compare fs_mtime to db_mtime. If they are equivalent, terminate
+ * the algorithm at this point, (this directory has not been
+ * updated in the filesystem since the last database scan of PASS
+ * 2).
*
- * o For each sub-directory of path, recursively call into this
- * same function.
+ * o Ask the database for files and directories within 'path'
+ * (db_files and db_subdirs)
*
- * o Tell the database to update its time of 'path' to 'path_mtime'
+ * o Pass 2: Walk fs_entries simultaneously with db_files and
+ * db_subdirs. Look for one of three interesting cases:
*
- * The 'struct stat *st' must point to a structure that has already
- * been initialized for 'path' by calling stat().
+ * 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).
+ *
+ * o Tell the database to update its time of 'path' to 'fs_mtime'
+ * if fs_mtime isn't the current wall-clock time.
*/
static notmuch_status_t
-add_files_recursive (notmuch_database_t *notmuch,
- const char *path,
- struct stat *st,
- add_files_state_t *state)
+add_files (notmuch_database_t *notmuch,
+ const char *path,
+ add_files_state_t *state)
{
DIR *dir = NULL;
struct dirent *entry = NULL;
char *next = NULL;
- time_t path_mtime, path_dbtime;
+ time_t fs_mtime, db_mtime;
notmuch_status_t status, ret = NOTMUCH_STATUS_SUCCESS;
- notmuch_message_t *message = NULL;
- struct dirent **namelist = NULL;
- int num_entries;
+ struct dirent **fs_entries = NULL;
+ int i, num_fs_entries = 0, entry_type;
notmuch_directory_t *directory;
+ notmuch_filenames_t *db_files = NULL;
+ notmuch_filenames_t *db_subdirs = NULL;
+ time_t stat_time;
+ struct stat st;
+ notmuch_bool_t is_maildir;
+
+ if (stat (path, &st)) {
+ fprintf (stderr, "Error reading directory %s: %s\n",
+ path, strerror (errno));
+ return NOTMUCH_STATUS_FILE_ERROR;
+ }
+ stat_time = time (NULL);
+
+ if (! S_ISDIR (st.st_mode)) {
+ fprintf (stderr, "Error: %s is not a directory.\n", path);
+ return NOTMUCH_STATUS_FILE_ERROR;
+ }
- path_mtime = st->st_mtime;
+ fs_mtime = st.st_mtime;
- directory = notmuch_database_get_directory (notmuch, path);
- path_dbtime = notmuch_directory_get_mtime (directory);
+ status = notmuch_database_get_directory (notmuch, path, &directory);
+ if (status) {
+ ret = status;
+ goto DONE;
+ }
+ db_mtime = directory ? notmuch_directory_get_mtime (directory) : 0;
+
+ /* If the directory is unchanged from our last scan and has no
+ * sub-directories, then return without scanning it at all. In
+ * some situations, skipping the scan can substantially reduce the
+ * cost of notmuch new, especially since the huge numbers of files
+ * in Maildirs make scans expensive, but all files live in leaf
+ * directories.
+ *
+ * To check for sub-directories, we borrow a trick from find,
+ * kpathsea, and many other UNIX tools: since a directory's link
+ * count is the number of sub-directories (specifically, their
+ * '..' entries) plus 2 (the link from the parent and the link for
+ * '.'). This check is safe even on weird file systems, since
+ * file systems that can't compute this will return 0 or 1. This
+ * is safe even on *really* weird file systems like HFS+ that
+ * mistakenly return the total number of directory entries, since
+ * that only inflates the count beyond 2.
+ */
+ if (directory && fs_mtime == db_mtime && st.st_nlink == 2) {
+ /* There's one catch: pass 1 below considers symlinks to
+ * directories to be directories, but these don't increase the
+ * file system link count. So, only bail early if the
+ * database agrees that there are no sub-directories. */
+ db_subdirs = notmuch_directory_get_child_directories (directory);
+ if (!notmuch_filenames_valid (db_subdirs))
+ goto DONE;
+ notmuch_filenames_destroy (db_subdirs);
+ db_subdirs = NULL;
+ }
- num_entries = scandir (path, &namelist, 0, ino_cmp);
+ /* 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,
+ directory ?
+ dirent_sort_strcmp_name : dirent_sort_inode);
- if (num_entries == -1) {
+ if (num_fs_entries == -1) {
fprintf (stderr, "Error opening directory %s: %s\n",
path, strerror (errno));
+ /* We consider this a fatal error because, if a user moved a
+ * message from another directory that we were able to scan
+ * into this directory, skipping this directory will cause
+ * that message to be lost. */
ret = NOTMUCH_STATUS_FILE_ERROR;
goto DONE;
}
- int i=0;
+ /* Pass 1: Recurse into all sub-directories. */
+ is_maildir = _entries_resemble_maildir (path, fs_entries, num_fs_entries);
- while (!interrupted) {
- if (i == num_entries)
+ for (i = 0; i < num_fs_entries; i++) {
+ if (interrupted)
break;
- entry= namelist[i++];
+ entry = fs_entries[i];
+
+ /* Ignore any files/directories the user has configured to
+ * ignore. We do this before dirent_type both for performance
+ * and because we don't care if dirent_type fails on entries
+ * that are explicitly ignored.
+ */
+ if (_entry_in_ignore_list (entry->d_name, state)) {
+ if (state->debug)
+ printf ("(D) add_files_recursive, pass 1: explicitly ignoring %s/%s\n",
+ path, entry->d_name);
+ continue;
+ }
- /* If this directory hasn't been modified since the last
- * add_files, then we only need to look further for
- * sub-directories. */
- if (path_mtime <= path_dbtime && entry->d_type == DT_REG)
+ /* We only want to descend into directories (and symlinks to
+ * directories). */
+ entry_type = dirent_type (path, entry);
+ if (entry_type == -1) {
+ /* Be pessimistic, e.g. so we don't lose lots of mail just
+ * because a user broke a symlink. */
+ fprintf (stderr, "Error reading file %s/%s: %s\n",
+ path, entry->d_name, strerror (errno));
+ return NOTMUCH_STATUS_FILE_ERROR;
+ } else if (entry_type != S_IFDIR) {
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 (namelist, num_entries)) ||
- strcmp (entry->d_name, ".notmuch") ==0)
+ (is_maildir && strcmp (entry->d_name, "tmp") == 0) ||
+ strcmp (entry->d_name, ".notmuch") == 0)
+ continue;
+
+ next = talloc_asprintf (notmuch, "%s/%s", path, entry->d_name);
+ status = add_files (notmuch, next, state);
+ if (status) {
+ ret = status;
+ goto DONE;
+ }
+ talloc_free (next);
+ next = NULL;
+ }
+
+ /* If the directory's modification time in the filesystem is the
+ * same as what we recorded in the database the last time we
+ * scanned it, then we can skip the second pass entirely.
+ *
+ * We test for strict equality here to avoid a bug that can happen
+ * if the system clock jumps backward, (preventing new mail from
+ * being discovered until the clock catches up and the directory
+ * is modified again).
+ */
+ if (directory && fs_mtime == db_mtime)
+ goto DONE;
+
+ /* If the database has never seen this directory before, we can
+ * simply leave db_files and db_subdirs NULL. */
+ if (directory) {
+ db_files = notmuch_directory_get_child_files (directory);
+ db_subdirs = notmuch_directory_get_child_directories (directory);
+ }
+
+ /* 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];
+
+ /* Ignore files & directories user has configured to be ignored */
+ if (_entry_in_ignore_list (entry->d_name, state)) {
+ if (state->debug)
+ printf ("(D) add_files_recursive, pass 2: explicitly ignoring %s/%s\n",
+ path,
+ entry->d_name);
+ continue;
+ }
+
+ /* 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);
+ }
+
+ /* Only add regular files (and symlinks to regular files). */
+ entry_type = dirent_type (path, entry);
+ if (entry_type == -1) {
+ fprintf (stderr, "Error reading file %s/%s: %s\n",
+ path, entry->d_name, strerror (errno));
+ return NOTMUCH_STATUS_FILE_ERROR;
+ } else if (entry_type != S_IFREG) {
+ 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);
- if (stat (next, st)) {
- int err = errno;
+ state->processed_files++;
- switch (err) {
- case ENOENT:
- /* The file was removed between scandir and now... */
- case EPERM:
- case EACCES:
- /* We can't read this file so don't add it to the cache. */
- continue;
- }
+ if (state->verbose) {
+ if (state->output_is_a_tty)
+ printf("\r\033[K");
+
+ printf ("%i/%i: %s",
+ state->processed_files,
+ state->total_files,
+ next);
+
+ putchar((state->output_is_a_tty) ? '\r' : '\n');
+ fflush (stdout);
+ }
- fprintf (stderr, "Error reading %s: %s\n",
- next, strerror (errno));
- ret = NOTMUCH_STATUS_FILE_ERROR;
+ status = add_file (notmuch, next, state);
+ if (status) {
+ ret = status;
goto DONE;
}
- if (S_ISREG (st->st_mode)) {
- /* If the file hasn't been modified since the last
- * add_files, then we need not look at it. */
- if (path_dbtime == 0 || st->st_mtime > path_dbtime) {
- state->processed_files++;
-
- if (state->verbose) {
- if (state->output_is_a_tty)
- printf("\r\033[K");
-
- printf ("%i/%i: %s",
- state->processed_files,
- state->total_files,
- next);
-
- putchar((state->output_is_a_tty) ? '\r' : '\n');
- fflush (stdout);
- }
-
- status = notmuch_database_add_message (notmuch, next, &message);
- switch (status) {
- /* success */
- case NOTMUCH_STATUS_SUCCESS:
- state->added_messages++;
- tag_inbox_and_unread (message);
- break;
- /* Non-fatal issues (go on to next file) */
- case NOTMUCH_STATUS_DUPLICATE_MESSAGE_ID:
- /* Stay silent on this one. */
- break;
- case NOTMUCH_STATUS_FILE_NOT_EMAIL:
- fprintf (stderr, "Note: Ignoring non-mail file: %s\n",
- next);
- break;
- /* Fatal issues. Don't process anymore. */
- case NOTMUCH_STATUS_READONLY_DATABASE:
- case NOTMUCH_STATUS_XAPIAN_EXCEPTION:
- case NOTMUCH_STATUS_OUT_OF_MEMORY:
- fprintf (stderr, "Error: %s. Halting processing.\n",
- notmuch_status_to_string (status));
- ret = status;
- goto DONE;
- default:
- case NOTMUCH_STATUS_FILE_ERROR:
- case NOTMUCH_STATUS_NULL_POINTER:
- case NOTMUCH_STATUS_TAG_TOO_LONG:
- case NOTMUCH_STATUS_UNBALANCED_FREEZE_THAW:
- case NOTMUCH_STATUS_LAST_STATUS:
- INTERNAL_ERROR ("add_message returned unexpected value: %d", status);
- goto DONE;
- }
-
- if (message) {
- notmuch_message_destroy (message);
- message = NULL;
- }
-
- if (do_add_files_print_progress) {
- do_add_files_print_progress = 0;
- add_files_print_progress (state);
- }
- }
- } else if (S_ISDIR (st->st_mode)) {
- status = add_files_recursive (notmuch, next, st, state);
- if (status && ret == NOTMUCH_STATUS_SUCCESS)
- ret = status;
+ if (do_print_progress) {
+ do_print_progress = 0;
+ generic_print_progress ("Processed", "files", state->tv_start,
+ state->processed_files, state->total_files);
}
talloc_free (next);
next = NULL;
}
- status = notmuch_directory_set_mtime (directory, path_mtime);
- if (status && ret == NOTMUCH_STATUS_SUCCESS)
- ret = status;
+ if (interrupted)
+ goto DONE;
+
+ /* 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 the directory's mtime is the same as the wall-clock time
+ * when we stat'ed the directory, we skip updating the mtime in
+ * the database because a message could be delivered later in this
+ * same second. This may lead to unnecessary re-scans, but it
+ * avoids overlooking messages. */
+ if (fs_mtime != stat_time)
+ _filename_list_add (state->directory_mtimes, path)->mtime = fs_mtime;
DONE:
if (next)
talloc_free (next);
- if (entry)
- free (entry);
if (dir)
closedir (dir);
- if (namelist)
- free (namelist);
+ if (fs_entries) {
+ for (i = 0; i < num_fs_entries; i++)
+ free (fs_entries[i]);
+
+ 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;
}
-/* This is the top-level entry point for add_files. It does a couple
- * of error checks, sets up the progress-printing timer and then calls
- * into the recursive function. */
-notmuch_status_t
-add_files (notmuch_database_t *notmuch,
- const char *path,
- add_files_state_t *state)
+static void
+setup_progress_printing_timer (void)
{
- struct stat st;
- notmuch_status_t status;
struct sigaction action;
struct itimerval timerval;
- notmuch_bool_t timer_is_active = FALSE;
-
- 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;
- }
- if (state->output_is_a_tty && ! debugger_is_active () && ! state->verbose) {
- /* 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;
- }
-
- status = add_files_recursive (notmuch, path, &st, state);
+ /* 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);
+}
- 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);
+static void
+stop_progress_printing_timer (void)
+{
+ struct sigaction action;
+ struct itimerval timerval;
- /* And disable the signal handler. */
- action.sa_handler = SIG_IGN;
- sigaction (SIGALRM, &action, NULL);
- }
+ /* 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);
- return status;
+ /* And disable the signal handler. */
+ action.sa_handler = SIG_IGN;
+ sigaction (SIGALRM, &action, NULL);
}
+
/* XXX: This should be merged with the add_files function since it
* shares a lot of logic with it. */
/* Recursively count all regular files in path and all sub-directories
* initialized to zero by the top-level caller before calling
* count_files). */
static void
-count_files (const char *path, int *count)
+count_files (const char *path, int *count, add_files_state_t *state)
{
struct dirent *entry = NULL;
char *next;
- struct stat st;
- struct dirent **namelist = NULL;
- int n_entries = scandir (path, &namelist, 0, ino_cmp);
- int i = 0;
+ struct dirent **fs_entries = NULL;
+ int num_fs_entries = scandir (path, &fs_entries, 0, dirent_sort_inode);
+ int entry_type, i;
- if (n_entries == -1) {
+ if (num_fs_entries == -1) {
fprintf (stderr, "Warning: failed to open directory %s: %s\n",
path, strerror (errno));
goto DONE;
}
- while (!interrupted) {
- if (i == n_entries)
- break;
-
- entry= namelist[i++];
+ for (i = 0; i < num_fs_entries && ! interrupted; i++) {
+ entry = fs_entries[i];
/* Ignore special directories to avoid infinite recursion.
- * Also ignore the .notmuch directory.
+ * Also ignore the .notmuch directory and files/directories
+ * the user has configured to be ignored.
*/
- /* 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 ||
- strcmp (entry->d_name, ".notmuch") == 0)
+ strcmp (entry->d_name, ".notmuch") == 0 ||
+ _entry_in_ignore_list (entry->d_name, state))
{
+ if (state->debug && _entry_in_ignore_list (entry->d_name, state))
+ printf ("(D) count_files: explicitly ignoring %s/%s\n",
+ path,
+ entry->d_name);
continue;
}
continue;
}
- stat (next, &st);
-
- if (S_ISREG (st.st_mode)) {
+ entry_type = dirent_type (path, entry);
+ if (entry_type == S_IFREG) {
*count = *count + 1;
if (*count % 1000 == 0) {
printf ("Found %d files so far.\r", *count);
fflush (stdout);
}
- } else if (S_ISDIR (st.st_mode)) {
- count_files (next, count);
+ } else if (entry_type == S_IFDIR) {
+ count_files (next, count, state);
}
free (next);
}
DONE:
- if (entry)
- free (entry);
- if (namelist)
- free (namelist);
+ if (fs_entries) {
+ for (i = 0; i < num_fs_entries; i++)
+ free (fs_entries[i]);
+
+ 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);
+}
+
+/* Remove one message filename from the database. */
+static notmuch_status_t
+remove_filename (notmuch_database_t *notmuch,
+ const char *path,
+ add_files_state_t *add_files_state)
+{
+ notmuch_status_t status;
+ notmuch_message_t *message;
+ status = notmuch_database_begin_atomic (notmuch);
+ if (status)
+ return status;
+ status = notmuch_database_find_message_by_filename (notmuch, path, &message);
+ if (status || message == NULL)
+ goto DONE;
+
+ status = notmuch_database_remove_message (notmuch, path);
+ if (status == NOTMUCH_STATUS_DUPLICATE_MESSAGE_ID) {
+ add_files_state->renamed_messages++;
+ if (add_files_state->synchronize_flags == TRUE)
+ notmuch_message_maildir_flags_to_tags (message);
+ status = NOTMUCH_STATUS_SUCCESS;
+ } else if (status == NOTMUCH_STATUS_SUCCESS) {
+ add_files_state->removed_messages++;
+ }
+ notmuch_message_destroy (message);
+
+ DONE:
+ notmuch_database_end_atomic (notmuch);
+ return status;
+}
+
+/* Recursively remove all filenames from the database referring to
+ * 'path' (or to any of its children). */
+static notmuch_status_t
+_remove_directory (void *ctx,
+ notmuch_database_t *notmuch,
+ const char *path,
+ add_files_state_t *add_files_state)
+{
+ notmuch_status_t status = NOTMUCH_STATUS_SUCCESS;
+ notmuch_directory_t *directory;
+ notmuch_filenames_t *files, *subdirs;
+ char *absolute;
+
+ status = notmuch_database_get_directory (notmuch, path, &directory);
+ if (status || !directory)
+ return status;
+
+ 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 = remove_filename (notmuch, absolute, add_files_state);
+ talloc_free (absolute);
+ if (status)
+ goto DONE;
+ }
+
+ 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));
+ status = _remove_directory (ctx, notmuch, absolute, add_files_state);
+ talloc_free (absolute);
+ if (status)
+ goto DONE;
+ }
+
+ DONE:
+ notmuch_directory_destroy (directory);
+ return status;
+}
+
+static void
+print_results (const add_files_state_t *state)
+{
+ double elapsed;
+ struct timeval tv_now;
+
+ gettimeofday (&tv_now, NULL);
+ elapsed = notmuch_time_elapsed (state->tv_start, tv_now);
+
+ if (state->processed_files) {
+ printf ("Processed %d %s in ", state->processed_files,
+ state->processed_files == 1 ? "file" : "total files");
+ notmuch_time_print_formatted_seconds (elapsed);
+ if (elapsed > 1)
+ printf (" (%d files/sec.).\033[K\n",
+ (int) (state->processed_files / elapsed));
+ else
+ printf (".\033[K\n");
+ }
+
+ if (state->added_messages)
+ printf ("Added %d new %s to the database.", state->added_messages,
+ state->added_messages == 1 ? "message" : "messages");
+ else
+ printf ("No new mail.");
+
+ if (state->removed_messages)
+ printf (" Removed %d %s.", state->removed_messages,
+ state->removed_messages == 1 ? "message" : "messages");
+
+ if (state->renamed_messages)
+ printf (" Detected %d file %s.", state->renamed_messages,
+ state->renamed_messages == 1 ? "rename" : "renames");
+
+ printf ("\n");
}
int
-notmuch_new_command (void *ctx, int argc, char *argv[])
+notmuch_new_command (notmuch_config_t *config, int argc, char *argv[])
{
- notmuch_config_t *config;
notmuch_database_t *notmuch;
add_files_state_t add_files_state;
- double elapsed;
- struct timeval tv_now;
+ struct timeval tv_start;
int ret = 0;
struct stat st;
const char *db_path;
char *dot_notmuch_path;
struct sigaction action;
+ _filename_node_t *f;
+ int opt_index;
int i;
+ notmuch_bool_t timer_is_active = FALSE;
+ notmuch_bool_t no_hooks = FALSE;
- add_files_state.verbose = 0;
+ add_files_state.verbose = FALSE;
+ add_files_state.debug = FALSE;
add_files_state.output_is_a_tty = isatty (fileno (stdout));
- for (i = 0; i < argc && argv[i][0] == '-'; i++) {
- if (STRNCMP_LITERAL (argv[i], "--verbose") == 0) {
- add_files_state.verbose = 1;
- } else {
- fprintf (stderr, "Unrecognized option: %s\n", argv[i]);
- return 1;
- }
- }
+ notmuch_opt_desc_t options[] = {
+ { NOTMUCH_OPT_BOOLEAN, &add_files_state.verbose, "verbose", 'v', 0 },
+ { NOTMUCH_OPT_BOOLEAN, &add_files_state.debug, "debug", 'd', 0 },
+ { NOTMUCH_OPT_BOOLEAN, &no_hooks, "no-hooks", 'n', 0 },
+ { 0, 0, 0, 0, 0 }
+ };
- /* 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;
+ opt_index = parse_arguments (argc, argv, options, 1);
+ if (opt_index < 0)
+ return EXIT_FAILURE;
+ add_files_state.new_tags = notmuch_config_get_new_tags (config, &add_files_state.new_tags_length);
+ add_files_state.new_ignore = notmuch_config_get_new_ignore (config, &add_files_state.new_ignore_length);
+ add_files_state.synchronize_flags = notmuch_config_get_maildir_synchronize_flags (config);
db_path = notmuch_config_get_database_path (config);
- dot_notmuch_path = talloc_asprintf (ctx, "%s/%s", db_path, ".notmuch");
+ if (!no_hooks) {
+ ret = notmuch_run_hook (db_path, "pre-new");
+ if (ret)
+ return EXIT_FAILURE;
+ }
+
+ dot_notmuch_path = talloc_asprintf (config, "%s/%s", db_path, ".notmuch");
if (stat (dot_notmuch_path, &st)) {
int count;
count = 0;
- count_files (db_path, &count);
+ count_files (db_path, &count, &add_files_state);
if (interrupted)
- return 1;
+ return EXIT_FAILURE;
printf ("Found %d total files (that's not much mail).\n", count);
- notmuch = notmuch_database_create (db_path);
+ if (notmuch_database_create (db_path, ¬much))
+ return EXIT_FAILURE;
add_files_state.total_files = count;
} else {
- notmuch = notmuch_database_open (db_path,
- NOTMUCH_DATABASE_MODE_READ_WRITE);
+ if (notmuch_database_open (db_path, NOTMUCH_DATABASE_MODE_READ_WRITE,
+ ¬much))
+ return EXIT_FAILURE;
+
+ 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;
+ return EXIT_FAILURE;
+
+ /* 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;
add_files_state.processed_files = 0;
add_files_state.added_messages = 0;
+ add_files_state.removed_messages = add_files_state.renamed_messages = 0;
gettimeofday (&add_files_state.tv_start, NULL);
+ add_files_state.removed_files = _filename_list_create (config);
+ add_files_state.removed_directories = _filename_list_create (config);
+ add_files_state.directory_mtimes = _filename_list_create (config);
+
+ if (! debugger_is_active () && add_files_state.output_is_a_tty
+ && ! add_files_state.verbose) {
+ setup_progress_printing_timer ();
+ timer_is_active = TRUE;
+ }
+
ret = add_files (notmuch, db_path, &add_files_state);
+ if (ret)
+ goto DONE;
- 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 ?
- "file" : "total files");
- notmuch_time_print_formatted_seconds (elapsed);
- if (elapsed > 1) {
- printf (" (%d files/sec.). \n",
- (int) (add_files_state.processed_files / elapsed));
- } else {
- printf (". \n");
+ gettimeofday (&tv_start, NULL);
+ for (f = add_files_state.removed_files->head; f && !interrupted; f = f->next) {
+ ret = remove_filename (notmuch, f->filename, &add_files_state);
+ if (ret)
+ goto DONE;
+ if (do_print_progress) {
+ do_print_progress = 0;
+ generic_print_progress ("Cleaned up", "messages",
+ tv_start, add_files_state.removed_messages + add_files_state.renamed_messages,
+ add_files_state.removed_files->count);
}
}
- if (add_files_state.added_messages) {
- printf ("Added %d new %s to the database.\n",
- add_files_state.added_messages,
- add_files_state.added_messages == 1 ?
- "message" : "messages");
- } else {
- printf ("No new mail.\n");
+
+ gettimeofday (&tv_start, NULL);
+ for (f = add_files_state.removed_directories->head, i = 0; f && !interrupted; f = f->next, i++) {
+ ret = _remove_directory (config, notmuch, f->filename, &add_files_state);
+ if (ret)
+ goto DONE;
+ if (do_print_progress) {
+ do_print_progress = 0;
+ generic_print_progress ("Cleaned up", "directories",
+ tv_start, i,
+ add_files_state.removed_directories->count);
+ }
}
- if (ret) {
- printf ("\nNote: At least one error was encountered: %s\n",
- notmuch_status_to_string (ret));
+ for (f = add_files_state.directory_mtimes->head; f && !interrupted; f = f->next) {
+ notmuch_status_t status;
+ notmuch_directory_t *directory;
+ status = notmuch_database_get_directory (notmuch, f->filename, &directory);
+ if (status == NOTMUCH_STATUS_SUCCESS && directory) {
+ notmuch_directory_set_mtime (directory, f->mtime);
+ notmuch_directory_destroy (directory);
+ }
}
- notmuch_database_close (notmuch);
+ DONE:
+ talloc_free (add_files_state.removed_files);
+ talloc_free (add_files_state.removed_directories);
+ talloc_free (add_files_state.directory_mtimes);
+
+ if (timer_is_active)
+ stop_progress_printing_timer ();
+
+ print_results (&add_files_state);
+
+ if (ret)
+ fprintf (stderr, "Note: A fatal error was encountered: %s\n",
+ notmuch_status_to_string (ret));
+
+ notmuch_database_destroy (notmuch);
+
+ if (!no_hooks && !ret && !interrupted)
+ ret = notmuch_run_hook (db_path, "post-new");
- return ret || interrupted;
+ return ret || interrupted ? EXIT_FAILURE : EXIT_SUCCESS;
}
projects / notmuch / blobdiff