doc_ripper 0.0.4
Sign up to get free protection for your applications and to get access to all the features.
- checksums.yaml +15 -0
- data/.gitignore +14 -0
- data/Gemfile +4 -0
- data/LICENSE.txt +22 -0
- data/README.md +37 -0
- data/Rakefile +2 -0
- data/doc_ripper.gemspec +26 -0
- data/lib/doc_ripper.rb +11 -0
- data/lib/doc_ripper/docx_ripper.rb +9 -0
- data/lib/doc_ripper/ms_doc_ripper.rb +9 -0
- data/lib/doc_ripper/pdf_ripper.rb +9 -0
- data/lib/doc_ripper/ripper/base.rb +20 -0
- data/lib/doc_ripper/text_ripper.rb +29 -0
- data/lib/doc_ripper/version.rb +5 -0
- metadata +88 -0
checksums.yaml
ADDED
@@ -0,0 +1,15 @@
|
|
1
|
+
---
|
2
|
+
!binary "U0hBMQ==":
|
3
|
+
metadata.gz: !binary |-
|
4
|
+
OTJjZmJlZjQwMzQ2ZDFlMWQwMzIyY2UyNGJmYTA1NWQxNGJmODEyZA==
|
5
|
+
data.tar.gz: !binary |-
|
6
|
+
MWIxZWYzZmIwZWE5Yjk5MTg0N2RkNWVjNTA1ODYxYzg4NWM5NTkzYw==
|
7
|
+
!binary "U0hBNTEy":
|
8
|
+
metadata.gz: !binary |-
|
9
|
+
MDczOTMxNDI1ZWFlYmQzM2JlMTU0YjJlYjEwNGQ5ZjM4M2I0ZmYxMWRhOTNl
|
10
|
+
YTkxN2UyY2ZhZWVhYmE3ZWYyNmZlODA3MWJjN2M1ZDI1MjZjMjdhZmQ3ODE0
|
11
|
+
NDIxYzA0ZTA4MWFhOTRhNjcxY2U0NmVhMDM3MGZkN2NiOWY0OTg=
|
12
|
+
data.tar.gz: !binary |-
|
13
|
+
OTA0NmU4ZDliOWY1MjVjYmYzMTJjNjJhZmI4YzUyZWQyYTg1ZDNhMzM0Y2Zm
|
14
|
+
MTZhNGI2NDMzMjE0MGVjN2EwMDE2YWRjNjYzNTAxYWVlZmU3ZGNhZjYzNWE3
|
15
|
+
Y2M5NzU2ZTliNjIwNDI4MzNlN2ZkNjYxM2I3YTRhMzA3Y2FlNjk=
|
data/.gitignore
ADDED
data/Gemfile
ADDED
data/LICENSE.txt
ADDED
@@ -0,0 +1,22 @@
|
|
1
|
+
Copyright (c) 2014 Paul Zaich
|
2
|
+
|
3
|
+
MIT License
|
4
|
+
|
5
|
+
Permission is hereby granted, free of charge, to any person obtaining
|
6
|
+
a copy of this software and associated documentation files (the
|
7
|
+
"Software"), to deal in the Software without restriction, including
|
8
|
+
without limitation the rights to use, copy, modify, merge, publish,
|
9
|
+
distribute, sublicense, and/or sell copies of the Software, and to
|
10
|
+
permit persons to whom the Software is furnished to do so, subject to
|
11
|
+
the following conditions:
|
12
|
+
|
13
|
+
The above copyright notice and this permission notice shall be
|
14
|
+
included in all copies or substantial portions of the Software.
|
15
|
+
|
16
|
+
THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
|
17
|
+
EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
|
18
|
+
MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
|
19
|
+
NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE
|
20
|
+
LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION
|
21
|
+
OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION
|
22
|
+
WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE.
|
data/README.md
ADDED
@@ -0,0 +1,37 @@
|
|
1
|
+
DocRipper is an extremely lightweight Ruby wrapper that can be used to parse text contents from common file formats (currently .doc, .docx and .pdf) without the need for a large number of dependencies like an OCR library or OpenOffice/LibreOffice.
|
2
|
+
|
3
|
+
For simple parsing, you'll likely see a large performance improvement with DocRipper over solutions that rely on OpenOffice/LibreOffice for .doc/.docx conversion. I found
|
4
|
+
|
5
|
+
Need OCR support or in-image text parsing? Take a look at [Docsplit](https://github.com/documentcloud/docsplit).
|
6
|
+
|
7
|
+
## Quickstart
|
8
|
+
|
9
|
+
```
|
10
|
+
gem install doc_ripper
|
11
|
+
```
|
12
|
+
### Specify a file to parse
|
13
|
+
|
14
|
+
```
|
15
|
+
DocRipper::TextRipper.new('/path/to/file')
|
16
|
+
```
|
17
|
+
|
18
|
+
### Return the file's text
|
19
|
+
```
|
20
|
+
dr = DocRipper::TextRipper.new('/path/to/file')
|
21
|
+
dr.text
|
22
|
+
=> "Document's text"
|
23
|
+
```
|
24
|
+
|
25
|
+
If the file cannot be read, nil will be returned.
|
26
|
+
|
27
|
+
```
|
28
|
+
dr = DocRipper::TextRipper.new('/path/to/missing/file')
|
29
|
+
dr.text
|
30
|
+
=> nil
|
31
|
+
```
|
32
|
+
|
33
|
+
|
34
|
+
## Dependencies
|
35
|
+
- Ruby version >= 1.9.2
|
36
|
+
- [Poppler-utils/(pdftotext)](http://poppler.freedesktop.org/) (PDF)
|
37
|
+
- [Antiword](http://www.winfield.demon.nl/) (docx) more info: http://linux.die.net/man/1/antiword
|
data/Rakefile
ADDED
data/doc_ripper.gemspec
ADDED
@@ -0,0 +1,26 @@
|
|
1
|
+
# coding: utf-8
|
2
|
+
lib = File.expand_path('../lib', __FILE__)
|
3
|
+
$LOAD_PATH.unshift(lib) unless $LOAD_PATH.include?(lib)
|
4
|
+
require 'doc_ripper/version'
|
5
|
+
|
6
|
+
Gem::Specification.new do |spec|
|
7
|
+
spec.name = "doc_ripper"
|
8
|
+
spec.version = DocRipper::VERSION
|
9
|
+
spec.authors = ["Paul Zaich"]
|
10
|
+
spec.email = ["pzaich@gmail.com"]
|
11
|
+
spec.summary = %q{Rip out text from pdf, doc and docx formats}
|
12
|
+
spec.description = %q{Provides a lean, convenient ruby wrapper to poppler, and antiword command line tools to quickly rip out text from common text formats.}
|
13
|
+
spec.homepage = "https://github.com/pzaich/doc_ripper"
|
14
|
+
spec.license = "MIT"
|
15
|
+
|
16
|
+
spec.files = `git ls-files -z`.split("\x0")
|
17
|
+
spec.executables = spec.files.grep(%r{^bin/}) { |f| File.basename(f) }
|
18
|
+
spec.test_files = spec.files.grep(%r{^(test|spec|features)/})
|
19
|
+
spec.require_paths = ["lib"]
|
20
|
+
|
21
|
+
spec.requirements << 'Antiword'
|
22
|
+
spec.requirements << "pdftotext/poppler"
|
23
|
+
|
24
|
+
spec.add_development_dependency "bundler", "~> 1.6"
|
25
|
+
spec.add_development_dependency "rake", "~> 10.0"
|
26
|
+
end
|
data/lib/doc_ripper.rb
ADDED
@@ -0,0 +1,20 @@
|
|
1
|
+
module DocRipper
|
2
|
+
module Ripper
|
3
|
+
|
4
|
+
class Base
|
5
|
+
attr_reader :text
|
6
|
+
|
7
|
+
def initialize(file_path)
|
8
|
+
@file_path = file_path
|
9
|
+
@text_file_path = "#{file_path.split('.').first}.txt"
|
10
|
+
end
|
11
|
+
|
12
|
+
private
|
13
|
+
|
14
|
+
def to_shell(file_path)
|
15
|
+
Shellwords.escape(file_path)
|
16
|
+
end
|
17
|
+
end
|
18
|
+
|
19
|
+
end
|
20
|
+
end
|
@@ -0,0 +1,29 @@
|
|
1
|
+
#encoding: UTF-8
|
2
|
+
|
3
|
+
module DocRipper
|
4
|
+
class TextRipper < Ripper::Base
|
5
|
+
attr_reader :text_file_path, :file_path
|
6
|
+
|
7
|
+
def rip
|
8
|
+
@is_ripped ||=choose_ripper
|
9
|
+
end
|
10
|
+
|
11
|
+
def text
|
12
|
+
@text ||= IO.read(@text_file_path).force_encoding("ISO-8859-1").encode("utf-8", replace: nil) if rip
|
13
|
+
end
|
14
|
+
|
15
|
+
private
|
16
|
+
|
17
|
+
def choose_ripper
|
18
|
+
case
|
19
|
+
when !!(@file_path[-5.. -1] =~ /.docx/i)
|
20
|
+
DocxRipper.new(@file_path).rip
|
21
|
+
when !!(@file_path[-4.. -1] =~ /.doc/i)
|
22
|
+
MsDocRipper.new(@file_path).rip
|
23
|
+
when !!(@file_path[-4..-1] =~ /.pdf/i)
|
24
|
+
PdfRipper.new(@file_path).rip
|
25
|
+
end
|
26
|
+
end
|
27
|
+
|
28
|
+
end
|
29
|
+
end
|
metadata
ADDED
@@ -0,0 +1,88 @@
|
|
1
|
+
--- !ruby/object:Gem::Specification
|
2
|
+
name: doc_ripper
|
3
|
+
version: !ruby/object:Gem::Version
|
4
|
+
version: 0.0.4
|
5
|
+
platform: ruby
|
6
|
+
authors:
|
7
|
+
- Paul Zaich
|
8
|
+
autorequire:
|
9
|
+
bindir: bin
|
10
|
+
cert_chain: []
|
11
|
+
date: 2014-07-22 00:00:00.000000000 Z
|
12
|
+
dependencies:
|
13
|
+
- !ruby/object:Gem::Dependency
|
14
|
+
name: bundler
|
15
|
+
requirement: !ruby/object:Gem::Requirement
|
16
|
+
requirements:
|
17
|
+
- - ~>
|
18
|
+
- !ruby/object:Gem::Version
|
19
|
+
version: '1.6'
|
20
|
+
type: :development
|
21
|
+
prerelease: false
|
22
|
+
version_requirements: !ruby/object:Gem::Requirement
|
23
|
+
requirements:
|
24
|
+
- - ~>
|
25
|
+
- !ruby/object:Gem::Version
|
26
|
+
version: '1.6'
|
27
|
+
- !ruby/object:Gem::Dependency
|
28
|
+
name: rake
|
29
|
+
requirement: !ruby/object:Gem::Requirement
|
30
|
+
requirements:
|
31
|
+
- - ~>
|
32
|
+
- !ruby/object:Gem::Version
|
33
|
+
version: '10.0'
|
34
|
+
type: :development
|
35
|
+
prerelease: false
|
36
|
+
version_requirements: !ruby/object:Gem::Requirement
|
37
|
+
requirements:
|
38
|
+
- - ~>
|
39
|
+
- !ruby/object:Gem::Version
|
40
|
+
version: '10.0'
|
41
|
+
description: Provides a lean, convenient ruby wrapper to poppler, and antiword command
|
42
|
+
line tools to quickly rip out text from common text formats.
|
43
|
+
email:
|
44
|
+
- pzaich@gmail.com
|
45
|
+
executables: []
|
46
|
+
extensions: []
|
47
|
+
extra_rdoc_files: []
|
48
|
+
files:
|
49
|
+
- .gitignore
|
50
|
+
- Gemfile
|
51
|
+
- LICENSE.txt
|
52
|
+
- README.md
|
53
|
+
- Rakefile
|
54
|
+
- doc_ripper.gemspec
|
55
|
+
- lib/doc_ripper.rb
|
56
|
+
- lib/doc_ripper/docx_ripper.rb
|
57
|
+
- lib/doc_ripper/ms_doc_ripper.rb
|
58
|
+
- lib/doc_ripper/pdf_ripper.rb
|
59
|
+
- lib/doc_ripper/ripper/base.rb
|
60
|
+
- lib/doc_ripper/text_ripper.rb
|
61
|
+
- lib/doc_ripper/version.rb
|
62
|
+
homepage: https://github.com/pzaich/doc_ripper
|
63
|
+
licenses:
|
64
|
+
- MIT
|
65
|
+
metadata: {}
|
66
|
+
post_install_message:
|
67
|
+
rdoc_options: []
|
68
|
+
require_paths:
|
69
|
+
- lib
|
70
|
+
required_ruby_version: !ruby/object:Gem::Requirement
|
71
|
+
requirements:
|
72
|
+
- - ! '>='
|
73
|
+
- !ruby/object:Gem::Version
|
74
|
+
version: '0'
|
75
|
+
required_rubygems_version: !ruby/object:Gem::Requirement
|
76
|
+
requirements:
|
77
|
+
- - ! '>='
|
78
|
+
- !ruby/object:Gem::Version
|
79
|
+
version: '0'
|
80
|
+
requirements:
|
81
|
+
- Antiword
|
82
|
+
- pdftotext/poppler
|
83
|
+
rubyforge_project:
|
84
|
+
rubygems_version: 2.0.3
|
85
|
+
signing_key:
|
86
|
+
specification_version: 4
|
87
|
+
summary: Rip out text from pdf, doc and docx formats
|
88
|
+
test_files: []
|