notmuch/notmuch-reindex.c

135 lines
4 KiB
C
Raw Normal View History

/* notmuch - Not much of an email program, (just index and search)
*
* Copyright © 2016 Daniel Kahn Gillmor
*
* This program is free software: you can redistribute it and/or modify
* it under the terms of the GNU General Public License as published by
* the Free Software Foundation, either version 3 of the License, or
* (at your option) any later version.
*
* This program is distributed in the hope that it will be useful,
* but WITHOUT ANY WARRANTY; without even the implied warranty of
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
* GNU General Public License for more details.
*
* You should have received a copy of the GNU General Public License
* along with this program. If not, see http://www.gnu.org/licenses/ .
*
* Author: Daniel Kahn Gillmor <dkg@fifthhorseman.net>
*/
#include "notmuch-client.h"
#include "string-util.h"
static volatile sig_atomic_t interrupted;
static void
handle_sigint (unused (int sig))
{
static char msg[] = "Stopping... \n";
/* 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;
}
/* reindex all messages matching 'query_string' using the passed-in indexopts
*/
static int
reindex_query (notmuch_database_t *notmuch, const char *query_string,
reindex: drop notmuch_param_t, use notmuch_indexopts_t instead There are at least three places in notmuch that can trigger an indexing action: * notmuch new * notmuch insert * notmuch reindex I have plans to add some indexing options (e.g. indexing the cleartext of encrypted parts, external filters, automated property injection) that should properly be available in all places where indexing happens. I also want those indexing options to be exposed by (and constrained by) the libnotmuch C API. This isn't yet an API break because we've never made a release with notmuch_param_t. These indexing options are relevant in the listed places (and in the libnotmuch analogues), but they aren't relevant in the other kinds of functionality that notmuch offers (e.g. dump/restore, tagging, search, show, reply). So i think a generic "param" object isn't well-suited for this case. In particular: * a param object sounds like it could contain parameters for some other (non-indexing) operation. This sounds confusing -- why would i pass non-indexing parameters to a function that only does indexing? * bremner suggests online a generic param object would actually be passed as a list of param objects, argv-style. In this case (at least in the obvious argv implementation), the params might be some sort of generic string. This introduces a problem where the API of the library doesn't grow as new options are added, which means that when code outside the library tries to use a feature, it first has to test for it, and have code to handle it not being available. The indexopts approach proposed here instead makes it clear at compile time and at dynamic link time that there is an explicit dependency on that feature, which allows automated tools to keep track of what's needed and keeps the actual code simple. My proposal adds the notmuch_indexopts_t as an opaque struct, so that we can extend the list of options without causing ABI breakage. The cost of this proposal appears to be that the "boilerplate" API increases a little bit, with a generic constructor and destructor function for the indexopts struct. More patches will follow that make use of this indexopts approach.
2017-08-18 01:14:26 +02:00
notmuch_indexopts_t *indexopts)
{
notmuch_query_t *query;
notmuch_messages_t *messages;
notmuch_message_t *message;
notmuch_status_t status;
notmuch_status_t ret = NOTMUCH_STATUS_SUCCESS;
query = notmuch_query_create (notmuch, query_string);
if (query == NULL) {
fprintf (stderr, "Out of memory.\n");
return 1;
}
/* reindexing is not interested in any special sort order */
notmuch_query_set_sort (query, NOTMUCH_SORT_UNSORTED);
status = notmuch_query_search_messages (query, &messages);
if (print_status_query ("notmuch reindex", query, status))
return status;
ret = notmuch_database_begin_atomic (notmuch);
for (;
notmuch_messages_valid (messages) && ! interrupted;
notmuch_messages_move_to_next (messages)) {
message = notmuch_messages_get (messages);
ret = notmuch_message_reindex(message, indexopts);
if (ret != NOTMUCH_STATUS_SUCCESS)
break;
}
if (!ret)
ret = notmuch_database_end_atomic (notmuch);
notmuch_query_destroy (query);
return ret || interrupted;
}
int
notmuch_reindex_command (notmuch_config_t *config, int argc, char *argv[])
{
char *query_string = NULL;
notmuch_database_t *notmuch;
struct sigaction action;
int opt_index;
int ret;
reindex: drop notmuch_param_t, use notmuch_indexopts_t instead There are at least three places in notmuch that can trigger an indexing action: * notmuch new * notmuch insert * notmuch reindex I have plans to add some indexing options (e.g. indexing the cleartext of encrypted parts, external filters, automated property injection) that should properly be available in all places where indexing happens. I also want those indexing options to be exposed by (and constrained by) the libnotmuch C API. This isn't yet an API break because we've never made a release with notmuch_param_t. These indexing options are relevant in the listed places (and in the libnotmuch analogues), but they aren't relevant in the other kinds of functionality that notmuch offers (e.g. dump/restore, tagging, search, show, reply). So i think a generic "param" object isn't well-suited for this case. In particular: * a param object sounds like it could contain parameters for some other (non-indexing) operation. This sounds confusing -- why would i pass non-indexing parameters to a function that only does indexing? * bremner suggests online a generic param object would actually be passed as a list of param objects, argv-style. In this case (at least in the obvious argv implementation), the params might be some sort of generic string. This introduces a problem where the API of the library doesn't grow as new options are added, which means that when code outside the library tries to use a feature, it first has to test for it, and have code to handle it not being available. The indexopts approach proposed here instead makes it clear at compile time and at dynamic link time that there is an explicit dependency on that feature, which allows automated tools to keep track of what's needed and keeps the actual code simple. My proposal adds the notmuch_indexopts_t as an opaque struct, so that we can extend the list of options without causing ABI breakage. The cost of this proposal appears to be that the "boilerplate" API increases a little bit, with a generic constructor and destructor function for the indexopts struct. More patches will follow that make use of this indexopts approach.
2017-08-18 01:14:26 +02:00
notmuch_indexopts_t *indexopts = NULL;
/* Set up 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);
notmuch_opt_desc_t options[] = {
{ NOTMUCH_OPT_INHERIT, (void *) &notmuch_shared_options, NULL, 0, 0 },
{ 0, 0, 0, 0, 0 }
};
opt_index = parse_arguments (argc, argv, options, 1);
if (opt_index < 0)
return EXIT_FAILURE;
notmuch_process_shared_options (argv[0]);
if (notmuch_database_open (notmuch_config_get_database_path (config),
NOTMUCH_DATABASE_MODE_READ_WRITE, &notmuch))
return EXIT_FAILURE;
notmuch_exit_if_unmatched_db_uuid (notmuch);
query_string = query_string_from_args (config, argc-opt_index, argv+opt_index);
if (query_string == NULL) {
fprintf (stderr, "Out of memory\n");
return EXIT_FAILURE;
}
if (*query_string == '\0') {
fprintf (stderr, "Error: notmuch reindex requires at least one search term.\n");
return EXIT_FAILURE;
}
ret = reindex_query (notmuch, query_string, indexopts);
notmuch_database_destroy (notmuch);
return ret || interrupted ? EXIT_FAILURE : EXIT_SUCCESS;
}