archive_io 0.1.0
Sign up to get free protection for your applications and to get access to all the features.
- checksums.yaml +7 -0
- data/.gitignore +10 -0
- data/.rspec +2 -0
- data/Gemfile +4 -0
- data/README.md +57 -0
- data/Rakefile +2 -0
- data/archive_io.gemspec +28 -0
- data/bin/console +10 -0
- data/lib/archive_io.rb +10 -0
- data/lib/archive_io/archive_reader.rb +70 -0
- data/lib/archive_io/file_reader.rb +23 -0
- data/lib/archive_io/header.rb +21 -0
- data/lib/archive_io/lib_archive.rb +35 -0
- data/lib/archive_io/version.rb +3 -0
- data/lib/archive_io/wildcard_pattern.rb +12 -0
- metadata +143 -0
checksums.yaml
ADDED
@@ -0,0 +1,7 @@
|
|
1
|
+
---
|
2
|
+
SHA1:
|
3
|
+
metadata.gz: 85be778c44e05a1acce8d7da11e8b8d59e3959f7
|
4
|
+
data.tar.gz: eeda3b05ca916422564bed68c861f2c28c3f75d9
|
5
|
+
SHA512:
|
6
|
+
metadata.gz: 93ebdc5b74f7aee6183b7645b71a2985cbc43e7946b7a1467032f420a20a1e708ed35b1bade51ca2459bbb80a9d395859eb568be2d2ff6065109004c97667b56
|
7
|
+
data.tar.gz: bf0cc25bc5054e8cbe70bd5d35c41b03e3a9c82202c5edf4d197e920187755120781492421ccec98ab035afae7e9f9ac63f7f18282bfee1af510b9fbd67014dc
|
data/.gitignore
ADDED
data/.rspec
ADDED
data/Gemfile
ADDED
data/README.md
ADDED
@@ -0,0 +1,57 @@
|
|
1
|
+
# ArchiveIo
|
2
|
+
|
3
|
+
Library which can traverse archived file (using [libarchive](http://www.libarchive.org/) under the hood) and yields IO like object on each file entry inside it for further streamline processing.
|
4
|
+
|
5
|
+
**Note:** [libarchive](http://www.libarchive.org/) have to be pre-installed and available on the host system
|
6
|
+
|
7
|
+
## Installation
|
8
|
+
|
9
|
+
Add this line to your application's Gemfile:
|
10
|
+
|
11
|
+
```ruby
|
12
|
+
gem 'archive_io'
|
13
|
+
```
|
14
|
+
|
15
|
+
And then execute:
|
16
|
+
|
17
|
+
$ bundle
|
18
|
+
|
19
|
+
Or install it yourself as:
|
20
|
+
|
21
|
+
$ gem install archive_io
|
22
|
+
|
23
|
+
## Usage
|
24
|
+
|
25
|
+
Simple usage:
|
26
|
+
|
27
|
+
```ruby
|
28
|
+
archive = ArchiveIO.open("archive.7z")
|
29
|
+
archive.each do |cursor|
|
30
|
+
puts cursor.pathname # prints out pathname inside archive
|
31
|
+
puts cursor.read(10) # prints out beginning of each file
|
32
|
+
end
|
33
|
+
archive.close
|
34
|
+
```
|
35
|
+
|
36
|
+
This library can come in handy if you want to process huge xml files reading straight from the archive without uncompressing it and works nicely together with `Nokogiri::XML::Reader` and can be used as follows:
|
37
|
+
|
38
|
+
```ruby
|
39
|
+
archive = ArchiveIO.open("archive.7z")
|
40
|
+
archive.select("*.xml") do |cursor|
|
41
|
+
Nokogiri::XML::Reader(cursor).each do |xml_node|
|
42
|
+
# your custom xml processing logic goes here
|
43
|
+
end
|
44
|
+
end
|
45
|
+
archive.close
|
46
|
+
```
|
47
|
+
|
48
|
+
## Development
|
49
|
+
|
50
|
+
After checking out the repo, run `bundle install` to install dependencies. You can also run `bin/console` for an interactive prompt that will allow you to experiment.
|
51
|
+
|
52
|
+
To release a new version, update the version number in `version.rb`, and then run `bundle exec rake release`, which will create a git tag for the version, push git commits and tags, and push the `.gem` file to [rubygems.org](https://rubygems.org).
|
53
|
+
|
54
|
+
## Contributing
|
55
|
+
|
56
|
+
Bug reports and pull requests are welcome on GitHub at https://github.com/AMekss/archive_io.
|
57
|
+
|
data/Rakefile
ADDED
data/archive_io.gemspec
ADDED
@@ -0,0 +1,28 @@
|
|
1
|
+
# coding: utf-8
|
2
|
+
lib = File.expand_path('../lib', __FILE__)
|
3
|
+
$LOAD_PATH.unshift(lib) unless $LOAD_PATH.include?(lib)
|
4
|
+
require 'archive_io/version'
|
5
|
+
|
6
|
+
Gem::Specification.new do |spec|
|
7
|
+
spec.name = "archive_io"
|
8
|
+
spec.version = ArchiveIO::VERSION
|
9
|
+
spec.authors = ["Artūrs Mekšs"]
|
10
|
+
spec.email = ["arturs.mekss@gmail.com"]
|
11
|
+
|
12
|
+
spec.summary = %q{Library which can traverse archived file and yields io like object on each file in it.}
|
13
|
+
spec.description = %q{Library which can traverse archived file (using `libarchive` under the hood) and yield io like object on each file entry inside it for further processing.}
|
14
|
+
spec.homepage = "https://github.com/AMekss/archive_io"
|
15
|
+
|
16
|
+
spec.files = `git ls-files -z`.split("\x0").reject { |f| f.match(%r{^(test|spec|features)/}) }
|
17
|
+
spec.bindir = "exe"
|
18
|
+
spec.executables = spec.files.grep(%r{^exe/}) { |f| File.basename(f) }
|
19
|
+
spec.require_paths = ["lib"]
|
20
|
+
|
21
|
+
spec.add_dependency "ffi", "~> 1.9"
|
22
|
+
|
23
|
+
spec.add_development_dependency "bundler", "~> 1.11"
|
24
|
+
spec.add_development_dependency "rake", "~> 10.0"
|
25
|
+
spec.add_development_dependency "rspec", "~> 3.5"
|
26
|
+
spec.add_development_dependency "pry"
|
27
|
+
spec.add_development_dependency "nokogiri"
|
28
|
+
end
|
data/bin/console
ADDED
data/lib/archive_io.rb
ADDED
@@ -0,0 +1,70 @@
|
|
1
|
+
require "archive_io/lib_archive"
|
2
|
+
require "archive_io/header"
|
3
|
+
require "archive_io/file_reader"
|
4
|
+
require "archive_io/wildcard_pattern"
|
5
|
+
|
6
|
+
module ArchiveIO
|
7
|
+
class ArchiveReader
|
8
|
+
HEADER_HANDLING_STRATEGIES = {
|
9
|
+
LibArchive::OK => -> (pointer) { Header.new(pointer) },
|
10
|
+
LibArchive::EOF => -> (_) { nil },
|
11
|
+
}.freeze
|
12
|
+
|
13
|
+
def initialize
|
14
|
+
ObjectSpace.define_finalizer(self, &method(:close))
|
15
|
+
end
|
16
|
+
|
17
|
+
def open(filename)
|
18
|
+
close
|
19
|
+
|
20
|
+
@archive = LibArchive::archive_read_new
|
21
|
+
@filename = filename
|
22
|
+
|
23
|
+
assert_operation_valid(LibArchive::archive_read_support_compression_all(archive))
|
24
|
+
assert_operation_valid(LibArchive::archive_read_support_format_all(archive))
|
25
|
+
assert_operation_valid(LibArchive::archive_read_open_filename(archive, filename, 10240))
|
26
|
+
end
|
27
|
+
|
28
|
+
def each
|
29
|
+
raise LibArchive::NoArchiveError, "Archive is not open, call open with filename on archive before this operation" unless archive
|
30
|
+
|
31
|
+
while header = next_header
|
32
|
+
yield FileReader.new(header.pathname, archive) if header.file?
|
33
|
+
end
|
34
|
+
|
35
|
+
open(@filename) #reopen file for the next call
|
36
|
+
end
|
37
|
+
|
38
|
+
def select(pattern)
|
39
|
+
wildcard = WildcardPattern.new(pattern)
|
40
|
+
|
41
|
+
each do |file|
|
42
|
+
yield file if wildcard.match?(file.pathname)
|
43
|
+
end
|
44
|
+
end
|
45
|
+
|
46
|
+
def close
|
47
|
+
LibArchive::archive_read_finish(archive) if archive
|
48
|
+
ensure
|
49
|
+
@archive = nil
|
50
|
+
@filename = nil
|
51
|
+
end
|
52
|
+
|
53
|
+
private
|
54
|
+
|
55
|
+
attr_reader :archive
|
56
|
+
|
57
|
+
def header_handler(code)
|
58
|
+
HEADER_HANDLING_STRATEGIES.fetch(code) { raise LibArchive::Error, archive }
|
59
|
+
end
|
60
|
+
|
61
|
+
def next_header
|
62
|
+
header = LibArchive::archive_entry_new
|
63
|
+
header_handler(LibArchive::archive_read_next_header(archive, header)).call(header.read_pointer)
|
64
|
+
end
|
65
|
+
|
66
|
+
def assert_operation_valid(operation_result_code)
|
67
|
+
raise LibArchive::Error, archive if operation_result_code != LibArchive::OK
|
68
|
+
end
|
69
|
+
end
|
70
|
+
end
|
@@ -0,0 +1,23 @@
|
|
1
|
+
require "archive_io/lib_archive"
|
2
|
+
|
3
|
+
module ArchiveIO
|
4
|
+
class FileReader
|
5
|
+
attr_reader :pathname
|
6
|
+
|
7
|
+
def initialize(pathname, archive)
|
8
|
+
@pathname = pathname
|
9
|
+
@archive = archive
|
10
|
+
end
|
11
|
+
|
12
|
+
def read(size)
|
13
|
+
buffer = FFI::MemoryPointer.new(:char, size)
|
14
|
+
return nil if LibArchive::archive_read_data(@archive, buffer, size) < 0
|
15
|
+
buffer.get_string(0)
|
16
|
+
end
|
17
|
+
|
18
|
+
def close
|
19
|
+
# does nothing, purpose of having it is to support IO like interface
|
20
|
+
end
|
21
|
+
end
|
22
|
+
private_constant :FileReader
|
23
|
+
end
|
@@ -0,0 +1,21 @@
|
|
1
|
+
require "archive_io/lib_archive"
|
2
|
+
|
3
|
+
module ArchiveIO
|
4
|
+
class Header
|
5
|
+
S_IFMT = 0170000
|
6
|
+
S_IFREG = 0100000 # regular file
|
7
|
+
|
8
|
+
def initialize(pointer)
|
9
|
+
@pointer = pointer
|
10
|
+
end
|
11
|
+
|
12
|
+
def file?
|
13
|
+
LibArchive::archive_entry_filetype(@pointer) & S_IFMT == S_IFREG
|
14
|
+
end
|
15
|
+
|
16
|
+
def pathname
|
17
|
+
LibArchive::archive_entry_pathname(@pointer)
|
18
|
+
end
|
19
|
+
end
|
20
|
+
private_constant :Header
|
21
|
+
end
|
@@ -0,0 +1,35 @@
|
|
1
|
+
require "ffi"
|
2
|
+
|
3
|
+
module ArchiveIO
|
4
|
+
module LibArchive
|
5
|
+
extend FFI::Library
|
6
|
+
|
7
|
+
OK = 0
|
8
|
+
EOF = 1
|
9
|
+
|
10
|
+
ffi_lib ["archive", "libarchive.so.2"]
|
11
|
+
|
12
|
+
attach_function :archive_version_string, [], :string
|
13
|
+
attach_function :archive_read_open_filename, [:pointer, :string, :size_t], :int
|
14
|
+
attach_function :archive_read_support_compression_all, [:pointer], :int
|
15
|
+
attach_function :archive_read_support_format_all, [:pointer], :int
|
16
|
+
attach_function :archive_error_string, [:pointer], :string
|
17
|
+
attach_function :archive_read_new, [], :pointer
|
18
|
+
attach_function :archive_read_finish, [:pointer], :int
|
19
|
+
attach_function :archive_read_header_position, [:pointer], :int
|
20
|
+
attach_function :archive_read_next_header, [:pointer, :pointer], :int
|
21
|
+
attach_function :archive_read_data, [:pointer, :pointer, :size_t], :size_t
|
22
|
+
|
23
|
+
# entry
|
24
|
+
attach_function :archive_entry_new, [], :pointer
|
25
|
+
attach_function :archive_entry_filetype, [:pointer], :mode_t
|
26
|
+
attach_function :archive_entry_pathname, [:pointer], :string
|
27
|
+
|
28
|
+
class NoArchiveError < StandardError; end
|
29
|
+
class Error < StandardError
|
30
|
+
def initialize(archive)
|
31
|
+
super "#{LibArchive::archive_error_string(archive)}"
|
32
|
+
end
|
33
|
+
end
|
34
|
+
end
|
35
|
+
end
|
metadata
ADDED
@@ -0,0 +1,143 @@
|
|
1
|
+
--- !ruby/object:Gem::Specification
|
2
|
+
name: archive_io
|
3
|
+
version: !ruby/object:Gem::Version
|
4
|
+
version: 0.1.0
|
5
|
+
platform: ruby
|
6
|
+
authors:
|
7
|
+
- Artūrs Mekšs
|
8
|
+
autorequire:
|
9
|
+
bindir: exe
|
10
|
+
cert_chain: []
|
11
|
+
date: 2016-08-29 00:00:00.000000000 Z
|
12
|
+
dependencies:
|
13
|
+
- !ruby/object:Gem::Dependency
|
14
|
+
name: ffi
|
15
|
+
requirement: !ruby/object:Gem::Requirement
|
16
|
+
requirements:
|
17
|
+
- - "~>"
|
18
|
+
- !ruby/object:Gem::Version
|
19
|
+
version: '1.9'
|
20
|
+
type: :runtime
|
21
|
+
prerelease: false
|
22
|
+
version_requirements: !ruby/object:Gem::Requirement
|
23
|
+
requirements:
|
24
|
+
- - "~>"
|
25
|
+
- !ruby/object:Gem::Version
|
26
|
+
version: '1.9'
|
27
|
+
- !ruby/object:Gem::Dependency
|
28
|
+
name: bundler
|
29
|
+
requirement: !ruby/object:Gem::Requirement
|
30
|
+
requirements:
|
31
|
+
- - "~>"
|
32
|
+
- !ruby/object:Gem::Version
|
33
|
+
version: '1.11'
|
34
|
+
type: :development
|
35
|
+
prerelease: false
|
36
|
+
version_requirements: !ruby/object:Gem::Requirement
|
37
|
+
requirements:
|
38
|
+
- - "~>"
|
39
|
+
- !ruby/object:Gem::Version
|
40
|
+
version: '1.11'
|
41
|
+
- !ruby/object:Gem::Dependency
|
42
|
+
name: rake
|
43
|
+
requirement: !ruby/object:Gem::Requirement
|
44
|
+
requirements:
|
45
|
+
- - "~>"
|
46
|
+
- !ruby/object:Gem::Version
|
47
|
+
version: '10.0'
|
48
|
+
type: :development
|
49
|
+
prerelease: false
|
50
|
+
version_requirements: !ruby/object:Gem::Requirement
|
51
|
+
requirements:
|
52
|
+
- - "~>"
|
53
|
+
- !ruby/object:Gem::Version
|
54
|
+
version: '10.0'
|
55
|
+
- !ruby/object:Gem::Dependency
|
56
|
+
name: rspec
|
57
|
+
requirement: !ruby/object:Gem::Requirement
|
58
|
+
requirements:
|
59
|
+
- - "~>"
|
60
|
+
- !ruby/object:Gem::Version
|
61
|
+
version: '3.5'
|
62
|
+
type: :development
|
63
|
+
prerelease: false
|
64
|
+
version_requirements: !ruby/object:Gem::Requirement
|
65
|
+
requirements:
|
66
|
+
- - "~>"
|
67
|
+
- !ruby/object:Gem::Version
|
68
|
+
version: '3.5'
|
69
|
+
- !ruby/object:Gem::Dependency
|
70
|
+
name: pry
|
71
|
+
requirement: !ruby/object:Gem::Requirement
|
72
|
+
requirements:
|
73
|
+
- - ">="
|
74
|
+
- !ruby/object:Gem::Version
|
75
|
+
version: '0'
|
76
|
+
type: :development
|
77
|
+
prerelease: false
|
78
|
+
version_requirements: !ruby/object:Gem::Requirement
|
79
|
+
requirements:
|
80
|
+
- - ">="
|
81
|
+
- !ruby/object:Gem::Version
|
82
|
+
version: '0'
|
83
|
+
- !ruby/object:Gem::Dependency
|
84
|
+
name: nokogiri
|
85
|
+
requirement: !ruby/object:Gem::Requirement
|
86
|
+
requirements:
|
87
|
+
- - ">="
|
88
|
+
- !ruby/object:Gem::Version
|
89
|
+
version: '0'
|
90
|
+
type: :development
|
91
|
+
prerelease: false
|
92
|
+
version_requirements: !ruby/object:Gem::Requirement
|
93
|
+
requirements:
|
94
|
+
- - ">="
|
95
|
+
- !ruby/object:Gem::Version
|
96
|
+
version: '0'
|
97
|
+
description: Library which can traverse archived file (using `libarchive` under the
|
98
|
+
hood) and yield io like object on each file entry inside it for further processing.
|
99
|
+
email:
|
100
|
+
- arturs.mekss@gmail.com
|
101
|
+
executables: []
|
102
|
+
extensions: []
|
103
|
+
extra_rdoc_files: []
|
104
|
+
files:
|
105
|
+
- ".gitignore"
|
106
|
+
- ".rspec"
|
107
|
+
- Gemfile
|
108
|
+
- README.md
|
109
|
+
- Rakefile
|
110
|
+
- archive_io.gemspec
|
111
|
+
- bin/console
|
112
|
+
- lib/archive_io.rb
|
113
|
+
- lib/archive_io/archive_reader.rb
|
114
|
+
- lib/archive_io/file_reader.rb
|
115
|
+
- lib/archive_io/header.rb
|
116
|
+
- lib/archive_io/lib_archive.rb
|
117
|
+
- lib/archive_io/version.rb
|
118
|
+
- lib/archive_io/wildcard_pattern.rb
|
119
|
+
homepage: https://github.com/AMekss/archive_io
|
120
|
+
licenses: []
|
121
|
+
metadata: {}
|
122
|
+
post_install_message:
|
123
|
+
rdoc_options: []
|
124
|
+
require_paths:
|
125
|
+
- lib
|
126
|
+
required_ruby_version: !ruby/object:Gem::Requirement
|
127
|
+
requirements:
|
128
|
+
- - ">="
|
129
|
+
- !ruby/object:Gem::Version
|
130
|
+
version: '0'
|
131
|
+
required_rubygems_version: !ruby/object:Gem::Requirement
|
132
|
+
requirements:
|
133
|
+
- - ">="
|
134
|
+
- !ruby/object:Gem::Version
|
135
|
+
version: '0'
|
136
|
+
requirements: []
|
137
|
+
rubyforge_project:
|
138
|
+
rubygems_version: 2.5.1
|
139
|
+
signing_key:
|
140
|
+
specification_version: 4
|
141
|
+
summary: Library which can traverse archived file and yields io like object on each
|
142
|
+
file in it.
|
143
|
+
test_files: []
|