file-digests 0.0.20 → 0.0.25
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- checksums.yaml +4 -4
- data/bin/file-digests +1 -1
- data/lib/file-digests.rb +402 -166
- metadata +23 -13
- data/bin/file-digests-auto +0 -7
- data/bin/file-digests-test +0 -7
checksums.yaml
CHANGED
|
@@ -1,7 +1,7 @@
|
|
|
1
1
|
---
|
|
2
2
|
SHA256:
|
|
3
|
-
metadata.gz:
|
|
4
|
-
data.tar.gz:
|
|
3
|
+
metadata.gz: 3bae6b10fe6496192c178f9139003b8d5a19774c70d957fd83f83ee91540cff9
|
|
4
|
+
data.tar.gz: 15d2965cb47eaeedec5dd56a0fe0a30e2f686e72d80f823416a351326d034ba8
|
|
5
5
|
SHA512:
|
|
6
|
-
metadata.gz:
|
|
7
|
-
data.tar.gz:
|
|
6
|
+
metadata.gz: 89b7fc7eea7a5b87f2cc23ea794ac1b2f85e9b367825694876afd91c9206c438a8df91487aaa4872e7b24480e0e5eb25b2750237318fc63305c605aa7fa372a4
|
|
7
|
+
data.tar.gz: 8fedea5e7034824276ea1f315543d5248e09a06e2fb97cf714f242181012701209383ab6416fcc0bfa206ce5b278abcdef216e4d3e41bbb9463a265b537091f2
|
data/bin/file-digests
CHANGED
data/lib/file-digests.rb
CHANGED
|
@@ -1,120 +1,255 @@
|
|
|
1
1
|
require 'date'
|
|
2
|
-
require 'set'
|
|
3
2
|
require 'digest'
|
|
4
3
|
require 'fileutils'
|
|
4
|
+
require 'openssl'
|
|
5
|
+
require 'optparse'
|
|
5
6
|
require 'pathname'
|
|
7
|
+
require 'set'
|
|
6
8
|
require 'sqlite3'
|
|
7
9
|
|
|
8
10
|
class FileDigests
|
|
11
|
+
DIGEST_ALGORITHMS=["BLAKE2b512", "SHA3-256", "SHA512-256"]
|
|
12
|
+
LEGACY_DIGEST_ALGORITHMS = ["SHA512", "SHA256"]
|
|
13
|
+
|
|
14
|
+
def self.canonical_digest_algorithm_name(string)
|
|
15
|
+
if string
|
|
16
|
+
algorithms = DIGEST_ALGORITHMS + LEGACY_DIGEST_ALGORITHMS
|
|
17
|
+
index = algorithms.map(&:downcase).index(string.downcase)
|
|
18
|
+
index && algorithms[index]
|
|
19
|
+
end
|
|
20
|
+
end
|
|
9
21
|
|
|
10
|
-
def
|
|
11
|
-
|
|
12
|
-
auto: (ENV["AUTO"] == "true"),
|
|
13
|
-
quiet: (ENV["QUIET"] == "true"),
|
|
14
|
-
test_only: (ENV["TEST_ONLY"] == "true")
|
|
15
|
-
}
|
|
16
|
-
file_digests = self.new ARGV[0], ARGV[1], options
|
|
17
|
-
file_digests.perform_check
|
|
22
|
+
def canonical_digest_algorithm_name string
|
|
23
|
+
self.class.canonical_digest_algorithm_name string
|
|
18
24
|
end
|
|
19
25
|
|
|
20
|
-
def self.
|
|
21
|
-
|
|
22
|
-
|
|
26
|
+
def self.digest_algorithms_list_text
|
|
27
|
+
"Digest algorithm should be one of the following: #{DIGEST_ALGORITHMS.join ", "}"
|
|
28
|
+
end
|
|
29
|
+
|
|
30
|
+
def self.parse_cli_options
|
|
31
|
+
options = {}
|
|
32
|
+
|
|
33
|
+
OptionParser.new do |opts|
|
|
34
|
+
opts.banner = [
|
|
35
|
+
"Usage: file-digests [options] [path/to/directory] [path/to/database_file]",
|
|
36
|
+
" By default the current directory will be operated upon, and the database file will be placed to the current directory as well.",
|
|
37
|
+
" Should you wish to check current directory but place the database elsewhere, you could provide \".\" as a first argument, and the path to a database_file as a second."
|
|
38
|
+
].join "\n"
|
|
39
|
+
|
|
40
|
+
opts.on("-a", "--auto", "Do not ask for any confirmation") do
|
|
41
|
+
options[:auto] = true
|
|
42
|
+
end
|
|
43
|
+
|
|
44
|
+
opts.on(
|
|
45
|
+
'--digest=DIGEST',
|
|
46
|
+
'Select a digest algorithm to use. Default is "BLAKE2b512".',
|
|
47
|
+
'You might also consider to use slower "SHA512-256" or even more slower "SHA3-256".',
|
|
48
|
+
"#{digest_algorithms_list_text}.",
|
|
49
|
+
'You only need to specify an algorithm on the first run, your choice will be saved to a database.',
|
|
50
|
+
'Any time later you could specify a new algorithm to change the current one.',
|
|
51
|
+
'Transition to a new algorithm will only occur if all files pass the check by digests which were stored using the old one.'
|
|
52
|
+
) do |value|
|
|
53
|
+
digest_algorithm = canonical_digest_algorithm_name(value)
|
|
54
|
+
unless DIGEST_ALGORITHMS.include?(digest_algorithm)
|
|
55
|
+
STDERR.puts "ERROR: #{digest_algorithms_list_text}"
|
|
56
|
+
exit 1
|
|
57
|
+
end
|
|
58
|
+
options[:digest_algorithm] = digest_algorithm
|
|
59
|
+
end
|
|
60
|
+
|
|
61
|
+
opts.on("-d", "--duplicates", "Show the list of duplicate files, based on the information out of the database") do
|
|
62
|
+
options[:action] = :show_duplicates
|
|
63
|
+
end
|
|
64
|
+
|
|
65
|
+
opts.on("-t", "--test", "Perform only the test, do not modify the digest database") do
|
|
66
|
+
options[:test_only] = true
|
|
67
|
+
end
|
|
68
|
+
|
|
69
|
+
opts.on("-q", "--quiet", "Less verbose output, stil report any found issues") do
|
|
70
|
+
options[:quiet] = true
|
|
71
|
+
end
|
|
72
|
+
|
|
73
|
+
opts.on("-v", "--verbose", "More verbose output") do
|
|
74
|
+
options[:verbose] = true
|
|
75
|
+
end
|
|
76
|
+
|
|
77
|
+
opts.on("-h", "--help", "Prints this help") do
|
|
78
|
+
puts opts
|
|
79
|
+
exit
|
|
80
|
+
end
|
|
81
|
+
end.parse!
|
|
82
|
+
options
|
|
83
|
+
end
|
|
84
|
+
|
|
85
|
+
def self.run_cli_utility
|
|
86
|
+
options = parse_cli_options
|
|
87
|
+
|
|
88
|
+
file_digests = self.new ARGV[0], ARGV[1], options
|
|
89
|
+
file_digests.send(options[:action] || :perform_check)
|
|
23
90
|
end
|
|
24
91
|
|
|
25
92
|
def initialize files_path, digest_database_path, options = {}
|
|
26
93
|
@options = options
|
|
27
94
|
|
|
28
|
-
|
|
29
|
-
|
|
30
|
-
|
|
31
|
-
raise "Files path must be a readable directory" unless (File.directory?(@files_path) && File.readable?(@files_path))
|
|
95
|
+
initialize_paths files_path, digest_database_path
|
|
96
|
+
initialize_database
|
|
32
97
|
|
|
33
|
-
@
|
|
34
|
-
|
|
98
|
+
if @digest_algorithm = canonical_digest_algorithm_name(get_metadata("digest_algorithm"))
|
|
99
|
+
if @options[:digest_algorithm] && @options[:digest_algorithm] != @digest_algorithm
|
|
100
|
+
@new_digest_algorithm = @options[:digest_algorithm]
|
|
101
|
+
end
|
|
35
102
|
else
|
|
36
|
-
@
|
|
103
|
+
@digest_algorithm = (@options[:digest_algorithm] || "BLAKE2b512")
|
|
104
|
+
set_metadata "digest_algorithm", @digest_algorithm
|
|
37
105
|
end
|
|
38
106
|
|
|
39
|
-
if
|
|
40
|
-
|
|
41
|
-
end
|
|
107
|
+
puts "Using #{@digest_algorithm} digest algorithm" if @options[:verbose]
|
|
108
|
+
end
|
|
42
109
|
|
|
43
|
-
|
|
44
|
-
|
|
45
|
-
|
|
110
|
+
def initialize_paths files_path, digest_database_path
|
|
111
|
+
@files_path = cleanup_path(files_path || ".")
|
|
112
|
+
|
|
113
|
+
raise "Files path must be a readable directory" unless (File.directory?(@files_path) && File.readable?(@files_path))
|
|
46
114
|
|
|
115
|
+
@digest_database_path = digest_database_path ? cleanup_path(digest_database_path) : @files_path
|
|
116
|
+
@digest_database_path += '.file-digests.sqlite' if File.directory?(@digest_database_path)
|
|
47
117
|
ensure_dir_exists @digest_database_path.dirname
|
|
48
118
|
|
|
49
|
-
|
|
50
|
-
|
|
51
|
-
|
|
119
|
+
if @options[:verbose]
|
|
120
|
+
puts "Target directory: #{@files_path}"
|
|
121
|
+
puts "Database location: #{@digest_database_path}"
|
|
52
122
|
end
|
|
53
|
-
|
|
54
|
-
initialize_database @digest_database_path
|
|
55
123
|
end
|
|
56
124
|
|
|
57
|
-
def initialize_database
|
|
58
|
-
@db = SQLite3::Database.new
|
|
125
|
+
def initialize_database
|
|
126
|
+
@db = SQLite3::Database.new @digest_database_path.to_s
|
|
59
127
|
@db.results_as_hash = true
|
|
60
128
|
|
|
129
|
+
file_digests_gem_version = Gem.loaded_specs["file-digests"]&.version&.to_s
|
|
130
|
+
|
|
131
|
+
execute 'PRAGMA encoding = "UTF-8"'
|
|
61
132
|
execute 'PRAGMA journal_mode = "WAL"'
|
|
62
133
|
execute 'PRAGMA synchronous = "NORMAL"'
|
|
63
134
|
execute 'PRAGMA locking_mode = "EXCLUSIVE"'
|
|
64
135
|
execute 'PRAGMA cache_size = "5000"'
|
|
65
136
|
|
|
66
|
-
|
|
67
|
-
|
|
68
|
-
|
|
69
|
-
|
|
70
|
-
|
|
71
|
-
|
|
72
|
-
|
|
73
|
-
|
|
74
|
-
|
|
75
|
-
end
|
|
137
|
+
@db.transaction(:exclusive) do
|
|
138
|
+
metadata_table_was_created = false
|
|
139
|
+
unless table_exist?("metadata")
|
|
140
|
+
execute "CREATE TABLE metadata (
|
|
141
|
+
key TEXT NOT NULL PRIMARY KEY,
|
|
142
|
+
value TEXT)"
|
|
143
|
+
execute "CREATE UNIQUE INDEX metadata_key ON metadata(key)"
|
|
144
|
+
metadata_table_was_created = true
|
|
145
|
+
end
|
|
76
146
|
|
|
77
|
-
|
|
78
|
-
|
|
79
|
-
|
|
80
|
-
|
|
81
|
-
|
|
82
|
-
|
|
83
|
-
|
|
147
|
+
prepare_method :set_metadata_query, "INSERT INTO metadata (key, value) VALUES (?, ?) ON CONFLICT (key) DO UPDATE SET value=excluded.value"
|
|
148
|
+
prepare_method :get_metadata_query, "SELECT value FROM metadata WHERE key = ?"
|
|
149
|
+
|
|
150
|
+
set_metadata("metadata_table_created_by_gem_version", file_digests_gem_version) if file_digests_gem_version && metadata_table_was_created
|
|
151
|
+
|
|
152
|
+
# Heuristic to detect database version 1 (metadata was not stored back then)
|
|
153
|
+
unless get_metadata("database_version")
|
|
154
|
+
if table_exist?("digests")
|
|
155
|
+
set_metadata "database_version", "1"
|
|
156
|
+
end
|
|
157
|
+
end
|
|
158
|
+
|
|
159
|
+
unless table_exist?("digests")
|
|
160
|
+
execute "CREATE TABLE digests (
|
|
161
|
+
id INTEGER NOT NULL PRIMARY KEY,
|
|
162
|
+
filename TEXT NOT NULL,
|
|
163
|
+
mtime TEXT,
|
|
164
|
+
digest TEXT NOT NULL,
|
|
165
|
+
digest_check_time TEXT NOT NULL)"
|
|
166
|
+
execute "CREATE UNIQUE INDEX digests_filename ON digests(filename)"
|
|
167
|
+
set_metadata("digests_table_created_by_gem_version", file_digests_gem_version) if file_digests_gem_version
|
|
168
|
+
end
|
|
169
|
+
|
|
170
|
+
prepare_method :insert, "INSERT INTO digests (filename, mtime, digest, digest_check_time) VALUES (?, ?, ?, datetime('now'))"
|
|
171
|
+
prepare_method :find_by_filename_query, "SELECT id, mtime, digest FROM digests WHERE filename = ?"
|
|
172
|
+
prepare_method :touch_digest_check_time, "UPDATE digests SET digest_check_time = datetime('now') WHERE id = ?"
|
|
173
|
+
prepare_method :update_mtime_and_digest, "UPDATE digests SET mtime = ?, digest = ?, digest_check_time = datetime('now') WHERE id = ?"
|
|
174
|
+
prepare_method :update_mtime, "UPDATE digests SET mtime = ?, digest_check_time = datetime('now') WHERE id = ?"
|
|
175
|
+
prepare_method :delete_by_filename, "DELETE FROM digests WHERE filename = ?"
|
|
176
|
+
prepare_method :query_duplicates, "SELECT digest, filename FROM digests WHERE digest IN (SELECT digest FROM digests GROUP BY digest HAVING count(*) > 1) ORDER BY digest, filename;"
|
|
177
|
+
prepare_method :update_digest_to_new_digest, "UPDATE digests SET digest = ? WHERE digest = ?"
|
|
178
|
+
|
|
179
|
+
unless get_metadata("database_version")
|
|
180
|
+
set_metadata "database_version", "2"
|
|
181
|
+
end
|
|
182
|
+
|
|
183
|
+
# Convert database from 1st to 2nd version
|
|
184
|
+
unless get_metadata("digest_algorithm")
|
|
185
|
+
if get_metadata("database_version") == "1"
|
|
186
|
+
if File.exist?(@digest_database_path.dirname + '.file-digests.sha512')
|
|
187
|
+
set_metadata("digest_algorithm", "SHA512")
|
|
188
|
+
else
|
|
189
|
+
set_metadata("digest_algorithm", "SHA256")
|
|
190
|
+
end
|
|
191
|
+
set_metadata "database_version", "2"
|
|
192
|
+
end
|
|
193
|
+
end
|
|
194
|
+
|
|
195
|
+
if get_metadata("database_version") != "2"
|
|
196
|
+
STDERR.puts "This version of file-digests is only compartible with the database version 2. Current database version is #{get_metadata("database_version")}. To use this database, please install appropriate version if file-digest."
|
|
197
|
+
raise "Incompatible database version"
|
|
198
|
+
end
|
|
199
|
+
end
|
|
84
200
|
end
|
|
85
201
|
|
|
86
202
|
def perform_check
|
|
87
|
-
@
|
|
88
|
-
|
|
89
|
-
|
|
203
|
+
perhaps_transaction(@new_digest_algorithm, :exclusive) do
|
|
204
|
+
@counters = {good: 0, updated: 0, new: 0, renamed: 0, likely_damaged: 0, exceptions: 0}
|
|
205
|
+
@new_files = {}
|
|
206
|
+
@new_digests = {}
|
|
207
|
+
|
|
208
|
+
@missing_files = Hash[@db.prepare("SELECT filename, digest FROM digests").execute!]
|
|
90
209
|
|
|
91
|
-
|
|
92
|
-
|
|
93
|
-
|
|
210
|
+
measure_time do
|
|
211
|
+
walk_files do |filename|
|
|
212
|
+
process_file filename
|
|
213
|
+
end
|
|
94
214
|
end
|
|
95
|
-
end
|
|
96
215
|
|
|
97
|
-
|
|
216
|
+
track_renames
|
|
98
217
|
|
|
99
|
-
|
|
100
|
-
|
|
101
|
-
|
|
102
|
-
|
|
218
|
+
if any_missing_files?
|
|
219
|
+
if any_exceptions?
|
|
220
|
+
STDERR.puts "Due to previously occurred errors, database cleanup from missing files will be skipped this time."
|
|
221
|
+
else
|
|
222
|
+
print_missing_files
|
|
223
|
+
if !@options[:test_only] && (@options[:auto] || confirm("Remove missing files from the database"))
|
|
224
|
+
remove_missing_files
|
|
225
|
+
end
|
|
226
|
+
end
|
|
103
227
|
end
|
|
104
|
-
end
|
|
105
228
|
|
|
106
|
-
|
|
107
|
-
|
|
108
|
-
|
|
229
|
+
if @new_digest_algorithm && !@options[:test_only]
|
|
230
|
+
if any_missing_files? || any_likely_damaged? || any_exceptions?
|
|
231
|
+
STDERR.puts "ERROR: New digest algorithm will not be in effect until there are files that are missing, likely damaged, or processed with an exception."
|
|
232
|
+
else
|
|
233
|
+
@new_digests.each do |old_digest, new_digest|
|
|
234
|
+
update_digest_to_new_digest new_digest, old_digest
|
|
235
|
+
end
|
|
236
|
+
set_metadata "digest_algorithm", @new_digest_algorithm
|
|
237
|
+
end
|
|
238
|
+
end
|
|
109
239
|
|
|
110
|
-
|
|
240
|
+
if any_likely_damaged? || any_exceptions?
|
|
241
|
+
STDERR.puts "PLEASE REVIEW ERRORS THAT WERE OCCURRED!"
|
|
242
|
+
end
|
|
243
|
+
|
|
244
|
+
set_metadata(@options[:test_only] ? "latest_test_only_check_time" : "latest_complete_check_time", time_to_database(Time.now))
|
|
245
|
+
|
|
246
|
+
print_counters
|
|
247
|
+
end
|
|
111
248
|
end
|
|
112
249
|
|
|
113
250
|
def show_duplicates
|
|
114
251
|
current_digest = nil
|
|
115
|
-
|
|
116
|
-
|
|
117
|
-
while found = result.next_hash do
|
|
252
|
+
query_duplicates.each do |found|
|
|
118
253
|
if current_digest != found['digest']
|
|
119
254
|
puts "" if current_digest
|
|
120
255
|
current_digest = found['digest']
|
|
@@ -135,117 +270,72 @@ class FileDigests
|
|
|
135
270
|
return if stat.chardev?
|
|
136
271
|
return if stat.directory?
|
|
137
272
|
return if stat.pipe?
|
|
138
|
-
unless stat.readable?
|
|
139
|
-
raise "File is not readable"
|
|
140
|
-
end
|
|
141
273
|
return if stat.socket?
|
|
142
274
|
|
|
143
|
-
|
|
144
|
-
|
|
145
|
-
|
|
146
|
-
|
|
147
|
-
|
|
148
|
-
|
|
275
|
+
raise "File is not readable" unless stat.readable?
|
|
276
|
+
|
|
277
|
+
if filename == "#{@digest_database_path}" ||
|
|
278
|
+
filename == "#{@digest_database_path}-wal" ||
|
|
279
|
+
filename == "#{@digest_database_path}-shm"
|
|
280
|
+
puts "SKIPPING DATABASE FILE: #{filename}" if @options[:verbose]
|
|
281
|
+
return
|
|
149
282
|
end
|
|
150
283
|
|
|
151
|
-
|
|
152
|
-
|
|
153
|
-
stat.mtime.utc.strftime('%Y-%m-%d %H:%M:%S'),
|
|
154
|
-
get_file_digest(filename)
|
|
155
|
-
)
|
|
156
|
-
rescue => exception
|
|
157
|
-
@counters[:exceptions] += 1
|
|
158
|
-
STDERR.puts "EXCEPTION: #{filename.encode('utf-8', universal_newline: true)}: #{exception.message}"
|
|
159
|
-
end
|
|
284
|
+
normalized_filename = filename.delete_prefix("#{@files_path.to_s}/").encode('utf-8', universal_newline: true).unicode_normalize(:nfkc)
|
|
285
|
+
mtime_string = time_to_database stat.mtime
|
|
160
286
|
|
|
161
|
-
|
|
162
|
-
Gem.win_platform? ? path.gsub(/\\/, '/') : path
|
|
163
|
-
end
|
|
287
|
+
process_file_indeed normalized_filename, mtime_string, get_file_digest(filename)
|
|
164
288
|
|
|
165
|
-
|
|
166
|
-
|
|
289
|
+
rescue => exception
|
|
290
|
+
@counters[:exceptions] += 1
|
|
291
|
+
print_file_exception exception, filename
|
|
167
292
|
end
|
|
168
293
|
|
|
169
|
-
def
|
|
170
|
-
if
|
|
171
|
-
|
|
172
|
-
raise "#{path} is not a directory"
|
|
173
|
-
end
|
|
294
|
+
def process_file_indeed filename, mtime, digest
|
|
295
|
+
if found = find_by_filename(filename)
|
|
296
|
+
process_previously_seen_file found, filename, mtime, digest
|
|
174
297
|
else
|
|
175
|
-
|
|
176
|
-
end
|
|
177
|
-
end
|
|
178
|
-
|
|
179
|
-
def walk_files
|
|
180
|
-
Dir.glob(@files_path + '**' + '*', File::FNM_DOTMATCH) do |filename|
|
|
181
|
-
yield filename
|
|
298
|
+
process_new_file filename, mtime, digest
|
|
182
299
|
end
|
|
183
300
|
end
|
|
184
301
|
|
|
185
|
-
def
|
|
186
|
-
|
|
187
|
-
|
|
188
|
-
|
|
189
|
-
|
|
190
|
-
|
|
302
|
+
def process_previously_seen_file found, filename, mtime, digest
|
|
303
|
+
@missing_files.delete(filename)
|
|
304
|
+
if found['digest'] == digest
|
|
305
|
+
@counters[:good] += 1
|
|
306
|
+
puts "GOOD: #{filename}" if @options[:verbose]
|
|
307
|
+
unless @options[:test_only]
|
|
308
|
+
if found['mtime'] == mtime
|
|
309
|
+
touch_digest_check_time found['id']
|
|
310
|
+
else
|
|
311
|
+
update_mtime mtime, found['id']
|
|
312
|
+
end
|
|
313
|
+
end
|
|
314
|
+
else
|
|
315
|
+
if found['mtime'] == mtime # Digest is different and mtime is the same
|
|
316
|
+
@counters[:likely_damaged] += 1
|
|
317
|
+
STDERR.puts "LIKELY DAMAGED: #{filename}"
|
|
318
|
+
else
|
|
319
|
+
@counters[:updated] += 1
|
|
320
|
+
puts "UPDATED: #{filename}" unless @options[:quiet]
|
|
321
|
+
unless @options[:test_only]
|
|
322
|
+
update_mtime_and_digest mtime, digest, found['id']
|
|
323
|
+
end
|
|
191
324
|
end
|
|
192
|
-
return digest.hexdigest
|
|
193
325
|
end
|
|
194
326
|
end
|
|
195
327
|
|
|
196
|
-
def
|
|
197
|
-
|
|
198
|
-
|
|
199
|
-
|
|
328
|
+
def process_new_file filename, mtime, digest
|
|
329
|
+
@counters[:new] += 1
|
|
330
|
+
puts "NEW: #{filename}" unless @options[:quiet]
|
|
331
|
+
unless @options[:test_only]
|
|
332
|
+
@new_files[filename] = digest
|
|
333
|
+
insert filename, mtime, digest
|
|
200
334
|
end
|
|
201
335
|
end
|
|
202
336
|
|
|
203
|
-
def measure_time
|
|
204
|
-
start = Process.clock_gettime(Process::CLOCK_MONOTONIC)
|
|
205
|
-
yield
|
|
206
|
-
elapsed = (Process.clock_gettime(Process::CLOCK_MONOTONIC) - start).to_i
|
|
207
|
-
puts "Elapsed time: #{elapsed / 3600}h #{(elapsed % 3600) / 60}m #{elapsed % 60}s" unless @options[:quiet]
|
|
208
|
-
end
|
|
209
337
|
|
|
210
|
-
|
|
211
|
-
result = find_by_filename file_path
|
|
212
|
-
|
|
213
|
-
if found = result.next_hash
|
|
214
|
-
raise "Multiple records found" if result.next
|
|
215
|
-
|
|
216
|
-
@missing_files.delete(file_path)
|
|
217
|
-
|
|
218
|
-
if found['digest'] == digest
|
|
219
|
-
@counters[:good] += 1
|
|
220
|
-
# puts "GOOD: #{file_path}" unless @options[:quiet]
|
|
221
|
-
unless @options[:test_only]
|
|
222
|
-
if found['mtime'] == mtime
|
|
223
|
-
touch_digest_check_time found['id']
|
|
224
|
-
else
|
|
225
|
-
update_mtime mtime, found['id']
|
|
226
|
-
end
|
|
227
|
-
end
|
|
228
|
-
else
|
|
229
|
-
if found['mtime'] == mtime # Digest is different and mtime is the same
|
|
230
|
-
@counters[:likely_damaged] += 1
|
|
231
|
-
STDERR.puts "LIKELY DAMAGED: #{file_path}"
|
|
232
|
-
else
|
|
233
|
-
@counters[:updated] += 1
|
|
234
|
-
puts "UPDATED: #{file_path}" unless @options[:quiet]
|
|
235
|
-
unless @options[:test_only]
|
|
236
|
-
update_mtime_and_digest mtime, digest, found['id']
|
|
237
|
-
end
|
|
238
|
-
end
|
|
239
|
-
end
|
|
240
|
-
else
|
|
241
|
-
@counters[:new] += 1
|
|
242
|
-
puts "NEW: #{file_path}" unless @options[:quiet]
|
|
243
|
-
unless @options[:test_only]
|
|
244
|
-
@new_files[file_path] = digest
|
|
245
|
-
insert file_path, mtime, digest
|
|
246
|
-
end
|
|
247
|
-
end
|
|
248
|
-
end
|
|
338
|
+
# Renames and missing files
|
|
249
339
|
|
|
250
340
|
def track_renames
|
|
251
341
|
@missing_files.delete_if do |filename, digest|
|
|
@@ -257,11 +347,6 @@ class FileDigests
|
|
|
257
347
|
true
|
|
258
348
|
end
|
|
259
349
|
end
|
|
260
|
-
@counters[:missing] = @missing_files.length
|
|
261
|
-
end
|
|
262
|
-
|
|
263
|
-
def any_missing_files?
|
|
264
|
-
@missing_files.length > 0
|
|
265
350
|
end
|
|
266
351
|
|
|
267
352
|
def print_missing_files
|
|
@@ -272,22 +357,173 @@ class FileDigests
|
|
|
272
357
|
end
|
|
273
358
|
|
|
274
359
|
def remove_missing_files
|
|
275
|
-
|
|
360
|
+
nested_transaction do
|
|
276
361
|
@missing_files.each do |filename, digest|
|
|
277
362
|
delete_by_filename filename
|
|
278
363
|
end
|
|
364
|
+
@missing_files = {}
|
|
279
365
|
end
|
|
280
366
|
end
|
|
281
367
|
|
|
368
|
+
|
|
369
|
+
# Database helpers
|
|
370
|
+
|
|
282
371
|
def execute *args, &block
|
|
283
372
|
@db.execute *args, &block
|
|
284
373
|
end
|
|
285
374
|
|
|
375
|
+
def nested_transaction(mode = :deferred)
|
|
376
|
+
if @db.transaction_active?
|
|
377
|
+
yield
|
|
378
|
+
else
|
|
379
|
+
@db.transaction(mode) do
|
|
380
|
+
yield
|
|
381
|
+
end
|
|
382
|
+
end
|
|
383
|
+
end
|
|
384
|
+
|
|
385
|
+
def perhaps_transaction(condition, mode = :deferred)
|
|
386
|
+
if condition
|
|
387
|
+
nested_transaction(mode) do
|
|
388
|
+
yield
|
|
389
|
+
end
|
|
390
|
+
else
|
|
391
|
+
yield
|
|
392
|
+
end
|
|
393
|
+
end
|
|
394
|
+
|
|
395
|
+
def table_exist? table_name
|
|
396
|
+
execute("SELECT name FROM sqlite_master WHERE type='table' AND name = '#{table_name}'").length == 1
|
|
397
|
+
end
|
|
398
|
+
|
|
286
399
|
def prepare_method name, query
|
|
287
400
|
variable = "@#{name}"
|
|
401
|
+
|
|
288
402
|
instance_variable_set(variable, @db.prepare(query))
|
|
403
|
+
|
|
289
404
|
define_singleton_method name do |*args, &block|
|
|
290
405
|
instance_variable_get(variable).execute(*args, &block)
|
|
291
406
|
end
|
|
407
|
+
|
|
408
|
+
define_singleton_method "#{name}!" do |*args, &block|
|
|
409
|
+
instance_variable_get(variable).execute!(*args, &block)
|
|
410
|
+
end
|
|
411
|
+
end
|
|
412
|
+
|
|
413
|
+
def set_metadata key, value
|
|
414
|
+
set_metadata_query key, value
|
|
415
|
+
puts "#{key} set to: #{value}" if @options[:verbose]
|
|
416
|
+
value
|
|
417
|
+
end
|
|
418
|
+
|
|
419
|
+
def get_metadata key
|
|
420
|
+
get_metadata_query!(key)&.first&.first
|
|
421
|
+
end
|
|
422
|
+
|
|
423
|
+
def find_by_filename filename
|
|
424
|
+
result = find_by_filename_query filename
|
|
425
|
+
found = result.next
|
|
426
|
+
raise "Multiple records found" if result.next
|
|
427
|
+
found
|
|
428
|
+
end
|
|
429
|
+
|
|
430
|
+
def time_to_database time
|
|
431
|
+
time.utc.strftime('%Y-%m-%d %H:%M:%S')
|
|
432
|
+
end
|
|
433
|
+
|
|
434
|
+
|
|
435
|
+
# Filesystem-related helpers
|
|
436
|
+
|
|
437
|
+
def patch_path_string path
|
|
438
|
+
Gem.win_platform? ? path.gsub(/\\/, '/') : path
|
|
439
|
+
end
|
|
440
|
+
|
|
441
|
+
def cleanup_path path
|
|
442
|
+
Pathname.new(patch_path_string(path)).cleanpath
|
|
443
|
+
end
|
|
444
|
+
|
|
445
|
+
def ensure_dir_exists path
|
|
446
|
+
if File.exist?(path)
|
|
447
|
+
unless File.directory?(path)
|
|
448
|
+
raise "#{path} is not a directory"
|
|
449
|
+
end
|
|
450
|
+
else
|
|
451
|
+
FileUtils.mkdir_p path
|
|
452
|
+
end
|
|
453
|
+
end
|
|
454
|
+
|
|
455
|
+
def walk_files
|
|
456
|
+
Dir.glob(@files_path + '**' + '*', File::FNM_DOTMATCH) do |filename|
|
|
457
|
+
yield filename
|
|
458
|
+
end
|
|
459
|
+
end
|
|
460
|
+
|
|
461
|
+
def get_file_digest filename
|
|
462
|
+
File.open(filename, 'rb') do |io|
|
|
463
|
+
digest = OpenSSL::Digest.new(@digest_algorithm)
|
|
464
|
+
new_digest = OpenSSL::Digest.new(@new_digest_algorithm) if @new_digest_algorithm
|
|
465
|
+
|
|
466
|
+
buffer = ""
|
|
467
|
+
while io.read(409600, buffer) # 409600 seems like a sweet spot
|
|
468
|
+
digest.update(buffer)
|
|
469
|
+
new_digest.update(buffer) if @new_digest_algorithm
|
|
470
|
+
end
|
|
471
|
+
@new_digests[digest.hexdigest] = new_digest.hexdigest if @new_digest_algorithm
|
|
472
|
+
return digest.hexdigest
|
|
473
|
+
end
|
|
474
|
+
end
|
|
475
|
+
|
|
476
|
+
|
|
477
|
+
# Runtime state helpers
|
|
478
|
+
|
|
479
|
+
def any_missing_files?
|
|
480
|
+
@missing_files.length > 0
|
|
481
|
+
end
|
|
482
|
+
|
|
483
|
+
def any_exceptions?
|
|
484
|
+
@counters[:exceptions] > 0
|
|
485
|
+
end
|
|
486
|
+
|
|
487
|
+
def any_likely_damaged?
|
|
488
|
+
@counters[:likely_damaged] > 0
|
|
489
|
+
end
|
|
490
|
+
|
|
491
|
+
# UI helpers
|
|
492
|
+
|
|
493
|
+
def confirm text
|
|
494
|
+
if STDIN.tty? && STDOUT.tty?
|
|
495
|
+
puts "#{text} (y/n)?"
|
|
496
|
+
STDIN.gets.strip.downcase == "y"
|
|
497
|
+
end
|
|
498
|
+
end
|
|
499
|
+
|
|
500
|
+
def measure_time
|
|
501
|
+
start = Process.clock_gettime(Process::CLOCK_MONOTONIC)
|
|
502
|
+
yield
|
|
503
|
+
elapsed = (Process.clock_gettime(Process::CLOCK_MONOTONIC) - start)
|
|
504
|
+
puts "Elapsed time: #{elapsed.to_i / 3600}h #{(elapsed.to_i % 3600) / 60}m #{'%.3f' % (elapsed % 60)}s" unless @options[:quiet]
|
|
505
|
+
end
|
|
506
|
+
|
|
507
|
+
def print_file_exception exception, filename
|
|
508
|
+
STDERR.print "EXCEPTION: #{exception.message}, processing file: "
|
|
509
|
+
begin
|
|
510
|
+
STDERR.print filename.encode('utf-8', universal_newline: true)
|
|
511
|
+
rescue
|
|
512
|
+
STDERR.print "(Unable to encode file name to utf-8) "
|
|
513
|
+
STDERR.print filename
|
|
514
|
+
end
|
|
515
|
+
STDERR.print "\n"
|
|
516
|
+
STDERR.flush
|
|
517
|
+
exception.backtrace.each { |line| STDERR.puts " " + line }
|
|
518
|
+
end
|
|
519
|
+
|
|
520
|
+
def print_counters
|
|
521
|
+
puts "#{@counters[:good]} file(s) passes digest check" if @counters[:good] > 0
|
|
522
|
+
puts "#{@counters[:updated]} file(s) are updated" if @counters[:updated] > 0
|
|
523
|
+
puts "#{@counters[:new]} file(s) are new" if @counters[:new] > 0
|
|
524
|
+
puts "#{@counters[:renamed]} file(s) are renamed" if @counters[:renamed] > 0
|
|
525
|
+
puts "#{@missing_files.length} file(s) are missing" if @missing_files.length > 0
|
|
526
|
+
puts "#{@counters[:likely_damaged]} file(s) are likely damaged (!)" if @counters[:likely_damaged] > 0
|
|
527
|
+
puts "#{@counters[:exceptions]} file(s) had exceptions occured during processing (!)" if @counters[:exceptions] > 0
|
|
292
528
|
end
|
|
293
529
|
end
|
metadata
CHANGED
|
@@ -1,47 +1,57 @@
|
|
|
1
1
|
--- !ruby/object:Gem::Specification
|
|
2
2
|
name: file-digests
|
|
3
3
|
version: !ruby/object:Gem::Version
|
|
4
|
-
version: 0.0.
|
|
4
|
+
version: 0.0.25
|
|
5
5
|
platform: ruby
|
|
6
6
|
authors:
|
|
7
7
|
- Stanislav Senotrusov
|
|
8
|
-
autorequire:
|
|
8
|
+
autorequire:
|
|
9
9
|
bindir: bin
|
|
10
10
|
cert_chain: []
|
|
11
|
-
date: 2020-10-
|
|
11
|
+
date: 2020-10-12 00:00:00.000000000 Z
|
|
12
12
|
dependencies:
|
|
13
13
|
- !ruby/object:Gem::Dependency
|
|
14
14
|
name: sqlite3
|
|
15
15
|
requirement: !ruby/object:Gem::Requirement
|
|
16
16
|
requirements:
|
|
17
|
-
- - "
|
|
17
|
+
- - "~>"
|
|
18
18
|
- !ruby/object:Gem::Version
|
|
19
|
-
version: 1.3
|
|
19
|
+
version: '1.3'
|
|
20
20
|
type: :runtime
|
|
21
21
|
prerelease: false
|
|
22
22
|
version_requirements: !ruby/object:Gem::Requirement
|
|
23
23
|
requirements:
|
|
24
|
-
- - "
|
|
24
|
+
- - "~>"
|
|
25
25
|
- !ruby/object:Gem::Version
|
|
26
|
-
version: 1.3
|
|
26
|
+
version: '1.3'
|
|
27
|
+
- !ruby/object:Gem::Dependency
|
|
28
|
+
name: openssl
|
|
29
|
+
requirement: !ruby/object:Gem::Requirement
|
|
30
|
+
requirements:
|
|
31
|
+
- - "~>"
|
|
32
|
+
- !ruby/object:Gem::Version
|
|
33
|
+
version: '2.1'
|
|
34
|
+
type: :runtime
|
|
35
|
+
prerelease: false
|
|
36
|
+
version_requirements: !ruby/object:Gem::Requirement
|
|
37
|
+
requirements:
|
|
38
|
+
- - "~>"
|
|
39
|
+
- !ruby/object:Gem::Version
|
|
40
|
+
version: '2.1'
|
|
27
41
|
description: Calculate file digests and check for the possible file corruption
|
|
28
42
|
email: stan@senotrusov.com
|
|
29
43
|
executables:
|
|
30
44
|
- file-digests
|
|
31
|
-
- file-digests-auto
|
|
32
|
-
- file-digests-test
|
|
33
45
|
extensions: []
|
|
34
46
|
extra_rdoc_files: []
|
|
35
47
|
files:
|
|
36
48
|
- bin/file-digests
|
|
37
|
-
- bin/file-digests-auto
|
|
38
|
-
- bin/file-digests-test
|
|
39
49
|
- lib/file-digests.rb
|
|
40
50
|
homepage: https://github.com/senotrusov/file-digests
|
|
41
51
|
licenses:
|
|
42
52
|
- Apache-2.0
|
|
43
53
|
metadata: {}
|
|
44
|
-
post_install_message:
|
|
54
|
+
post_install_message:
|
|
45
55
|
rdoc_options: []
|
|
46
56
|
require_paths:
|
|
47
57
|
- lib
|
|
@@ -57,7 +67,7 @@ required_rubygems_version: !ruby/object:Gem::Requirement
|
|
|
57
67
|
version: '0'
|
|
58
68
|
requirements: []
|
|
59
69
|
rubygems_version: 3.1.2
|
|
60
|
-
signing_key:
|
|
70
|
+
signing_key:
|
|
61
71
|
specification_version: 4
|
|
62
72
|
summary: file-digests
|
|
63
73
|
test_files: []
|
data/bin/file-digests-auto
DELETED