1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
|
# cache.py - functions for metadata cache
#
# Copyright (C) 2015 Arthur de Jong
#
# 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 2 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, write to the Free Software
# Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA
#
# The files produced as output from the software do not automatically fall
# under the copyright of the software, unless explicitly stated otherwise.
import json
import os
import sqlite3
class MetaData(object):
def __init__(self, cache_dir, uuid):
# set a default cache directory
if not cache_dir:
import xdg.BaseDirectory
cache_dir = os.path.join(
xdg.BaseDirectory.xdg_cache_home, 'sloth')
# create cache directory if needed
if not os.path.isdir(cache_dir):
os.makedirs(cache_dir)
# set up SQLite connection
self.connection = sqlite3.connect(
'%s/%s-v2.sqlite' % (cache_dir, uuid))
# create database tables
self.connection.executescript('''
PRAGMA secure_delete = false;
PRAGMA temp_store = MEMORY;
PRAGMA cache_size = 20000;
PRAGMA synchronous = OFF;
PRAGMA journal_mode = MEMORY;
CREATE TABLE IF NOT EXISTS `archive_contents`
( `id` INTEGER PRIMARY KEY,
`archive` TEXT NOT NULL,
`path` TEXT NOT NULL,
`size` INTEGER NOT NULL,
`meta` TEXT NOT NULL,
`used` INTEGER NOT NULL DEFAULT 0 );
CREATE INDEX IF NOT EXISTS `archive_contents_archive_idx`
ON `archive_contents` (`archive`);
CREATE INDEX IF NOT EXISTS `archive_contents_path_idx`
ON `archive_contents` (`path`);
CREATE INDEX IF NOT EXISTS `archive_contents_meta_idx`
ON `archive_contents` (`meta`);
CREATE TABLE IF NOT EXISTS `backups`
( `backup` TEXT PRIMARY KEY,
`json` TEXT NOT NULL );
CREATE INDEX IF NOT EXISTS `backups_backup_idx`
ON `backups` (`backup`);
''')
def is_crawled(self, path):
cursor = self.connection.execute('''
SELECT 1
FROM `crawled`
WHERE `path` = ?
''', (path, ))
return bool(list(cursor))
def resync_archives(self, repo):
"""Update metadata cache with the information from the repository."""
# set up temporary table to hold list of archives found in repository
self.connection.executescript('''
CREATE TEMPORARY TABLE `tmp_archives`
( `archive` TEXT NOT NULL );
CREATE INDEX IF NOT EXISTS `tmp_archives_archive_idx`
ON `tmp_archives` (`archive`);
''')
# get list of archives in the repository
with self.connection:
self.connection.executemany('''
INSERT INTO `tmp_archives`
(`archive`)
VALUES
(?)
''', ((archive, ) for archive in repo.list_archives()))
# remove archives from database that are not in the repository
with self.connection:
self.connection.execute('''
DELETE FROM `archive_contents`
WHERE `archive` NOT IN (
SELECT `archive` FROM `tmp_archives`)
''')
# read archive metadata that is missing from the database
cursor = self.connection.execute('''
SELECT `archive`
FROM `tmp_archives`
WHERE `archive` NOT IN (
SELECT DISTINCT `archive` FROM `archive_contents`)
''')
# use fetchall because SQLite cannot handle partial reads from a cursor
# if the database is being modified in another cursor
for archive, in cursor.fetchall():
print('Importing archive %s file list' % archive)
try:
fileslist = repo.read_fileslist('archives/%s.json' % archive)
with self.connection:
self.connection.executemany('''
INSERT INTO `archive_contents`
(`archive`, `path`, `size`, `meta`)
VALUES
(?, ?, ?, ?)
''', ((
archive, meta['path'], meta['size'],
json.dumps(meta, sort_keys=True))
for meta in fileslist))
except (EnvironmentError, ValueError):
import traceback
print(traceback.format_exc())
# clean up
self.connection.executescript('''
DROP TABLE `tmp_archives`;
''')
def _check_backups(self, repo, table, backup=None):
"""Return the list of backups that need to be synced, checking the
specified table."""
if backup is not None:
# if we already have data for the backup, we're done
cursor = self.connection.execute('''
SELECT 1
FROM `%s`
WHERE `backup` = ?
''' % table, (backup, ))
if bool(list(cursor)):
return []
return [backup]
# get list of backups in the repository
self.connection.executescript('''
CREATE TEMPORARY TABLE `tmp_backups`
( `backup` TEXT NOT NULL );
CREATE INDEX IF NOT EXISTS `tmp_backups_backup_idx`
ON `tmp_backups` (`backup`);
''')
with self.connection:
self.connection.executemany('''
INSERT INTO `tmp_backups`
(`backup`)
VALUES
(?)
''', ((backup, ) for backup in repo.list_backups()))
# remove backups from database that are not in the repository
with self.connection:
self.connection.execute('''
DELETE FROM `%s`
WHERE `backup` NOT IN (
SELECT `backup` FROM `tmp_backups`)
''' % table)
# read backup metadata that is missing from the database
backups = [
row[0] for row in self.connection.execute('''
SELECT `backup`
FROM `tmp_backups`
WHERE `backup` NOT IN (
SELECT `backup` FROM `%s`)
''' % table)]
# clean up
self.connection.executescript('''
DROP TABLE IF EXISTS `tmp_backups`;
''')
return backups
def resync_backups(self, repo):
"""Update metadata cache with the information from the repository."""
for backup in self._check_backups(repo, 'backups'):
print('Importing backup %s metadata' % backup)
try:
with repo.read_file('backups/%s/info.json' % backup) as f:
info = json.load(f)
with self.connection:
self.connection.execute('''
INSERT OR REPLACE INTO `backups`
(`backup`, `json`)
VALUES
(?, ?)
''', (
backup, json.dumps(info, sort_keys=True)))
except (EnvironmentError, ValueError):
import traceback
print(traceback.format_exc())
|