/*
* call-seq: DB.get_directory(path) => DIR
*
* Retrieve a directory object from the database for 'path'
*/
VALUE
notmuch_rb_database_get_directory (VALUE self, VALUE pathv)
{
const char *path;
notmuch_status_t ret;
notmuch_directory_t *dir;
notmuch_database_t *db;
Data_Get_Notmuch_Database (self, db);
SafeStringValue (pathv);
path = RSTRING_PTR (pathv);
ret = notmuch_database_get_directory (db, path, &dir);
notmuch_rb_status_raise (ret);
if (dir)
return Data_Wrap_Struct (notmuch_rb_cDirectory, NULL, NULL, dir);
return Qnil;
}
/* 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);
}
/*
* call-seq: DB.get_directory(path) => DIR
*
* Retrieve a directory object from the database for 'path'
*/
VALUE
notmuch_rb_database_get_directory(VALUE self, VALUE pathv)
{
const char *path;
notmuch_directory_t *dir;
notmuch_database_t *db;
Data_Get_Notmuch_Database(self, db);
#if !defined(RSTRING_PTR)
#define RSTRING_PTR(v) (RSTRING((v))->ptr)
#endif /* !defined(RSTRING_PTR) */
SafeStringValue(pathv);
path = RSTRING_PTR(pathv);
dir = notmuch_database_get_directory(db, path);
if (!dir)
rb_raise(notmuch_rb_eXapianError, "Xapian exception");
return Data_Wrap_Struct(notmuch_rb_cDirectory, NULL, NULL, dir);
}
/* 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 Ask the filesystem for files and directories within 'path'
* (via scandir and stored in fs_entries)
*
* o Pass 1: For each directory in fs_entries, recursively call into
* this same function.
*
* 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 Ask the database for files and directories within 'path'
* (db_files and db_subdirs)
*
* o Pass 2: Walk fs_entries simultaneously with db_files and
* db_subdirs. Look for one of three interesting cases:
*
* 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,
add_files_state_t *state)
{
DIR *dir = NULL;
struct dirent *entry = NULL;
char *next = NULL;
time_t fs_mtime, db_mtime;
notmuch_status_t status, ret = NOTMUCH_STATUS_SUCCESS;
notmuch_message_t *message = NULL;
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;
time_t stat_time;
struct stat st;
notmuch_bool_t is_maildir, new_directory;
const char **tag;
if (stat (path, &st)) {
fprintf (stderr, "Error reading directory %s: %s\n",
path, strerror (errno));
return NOTMUCH_STATUS_FILE_ERROR;
}
stat_time = time (NULL);
/* 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);
new_directory = db_mtime ? FALSE : TRUE;
/* XXX This is a temporary workaround. If we don't update the
* database mtime until after processing messages in this
* directory, then a 0 mtime is *not* sufficient to indicate that
* this directory has no messages or subdirs in the database (for
* example, if an earlier run skipped the mtime update because
* fs_mtime == stat_time, or was interrupted before updating the
* mtime at the end). To address this, we record a (bogus)
* non-zero value before processing any child messages so that a
* later run won't mistake this for a new directory (and, for
* example, fail to detect removed files and subdirs).
*
* A better solution would be for notmuch_database_get_directory
* to indicate if it really created a new directory or not, either
* by a new out-argument, or by recording this information and
* providing an accessor.
*/
if (new_directory)
notmuch_directory_set_mtime (directory, -1);
/* 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",
path, strerror (errno));
ret = NOTMUCH_STATUS_FILE_ERROR;
goto DONE;
}
/* 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];
/* 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 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 ||
(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_recursive (notmuch, next, state);
if (status && ret == NOTMUCH_STATUS_SUCCESS)
ret = status;
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 (fs_mtime == db_mtime)
goto DONE;
/* new_directory means a directory that the database has never
* seen before. In that case, we can simply leave db_files and
* db_subdirs NULL. */
if (!new_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];
/* 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 filesystem
* 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++;
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++;
notmuch_message_freeze (message);
for (tag=state->new_tags; *tag != NULL; tag++)
notmuch_message_add_tag (message, *tag);
if (state->synchronize_flags == TRUE)
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:
/* Defer sync of maildir flags until after old filenames
* are removed in the case of a rename. */
if (state->synchronize_flags == TRUE)
_filename_list_add (state->message_ids_to_sync,
notmuch_message_get_message_id (message));
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_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));
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_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;
}
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 (! interrupted && fs_mtime != stat_time) {
status = notmuch_directory_set_mtime (directory, fs_mtime);
if (status && ret == NOTMUCH_STATUS_SUCCESS)
ret = status;
}
DONE:
if (next)
talloc_free (next);
if (entry)
free (entry);
if (dir)
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;
}
