pdftdx 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/.idea/.rakeTasks +7 -0
- data/.idea/inspectionProfiles/Project_Default.xml +10 -0
- data/.idea/inspectionProfiles/profiles_settings.xml +7 -0
- data/.idea/misc.xml +14 -0
- data/.idea/modules.xml +8 -0
- data/.idea/pdftdx.iml +11 -0
- data/.idea/vcs.xml +6 -0
- data/Gemfile +2 -0
- data/Gemfile.lock +22 -0
- data/LICENSE.txt +21 -0
- data/README.md +7 -0
- data/Rakefile +2 -0
- data/bin/pdftdx +26 -0
- data/lib/pdftdx/parser.rb +80 -0
- data/lib/pdftdx/version.rb +9 -0
- data/lib/pdftdx.rb +25 -0
- data/pdftdx.gemspec +25 -0
- metadata +104 -0
checksums.yaml
ADDED
@@ -0,0 +1,7 @@
|
|
1
|
+
---
|
2
|
+
SHA1:
|
3
|
+
metadata.gz: 87f8818e7d617b36b12f835b98aa2b93acf47a1d
|
4
|
+
data.tar.gz: 743387ff99d01c64d164c864ebef401802529c63
|
5
|
+
SHA512:
|
6
|
+
metadata.gz: 0742c4e3b4ccc06926a1ff2a71721ed5c545078f54b67b0554364d8c405970ea45788c37f33c1d6426700099feedd4ab7bc8dd6a67f5383c136ffefc3ae59a2c
|
7
|
+
data.tar.gz: 4f85e5f1bcb20146fc1223afa80c6993e2fc379193e246bcf7b34c2422620ce9e8674e4262a55e9edfe2afb59cdc572685b351a091f64056450570e1b4ffe5d7
|
data/.gitignore
ADDED
data/.idea/.rakeTasks
ADDED
@@ -0,0 +1,7 @@
|
|
1
|
+
<?xml version="1.0" encoding="UTF-8"?>
|
2
|
+
<Settings><!--This file was automatically generated by Ruby plugin.
|
3
|
+
You are allowed to:
|
4
|
+
1. Remove rake task
|
5
|
+
2. Add existing rake tasks
|
6
|
+
To add existing rake tasks automatically delete this file and reload the project.
|
7
|
+
--><RakeGroup description="" fullCmd="" taksId="rake"><RakeTask description="Build pdftdx-0.1.0.gem into the pkg directory" fullCmd="build" taksId="build" /><RakeTask description="Remove any temporary products" fullCmd="clean" taksId="clean" /><RakeTask description="Remove any generated files" fullCmd="clobber" taksId="clobber" /><RakeTask description="Build and install pdftdx-0.1.0.gem into system gems" fullCmd="install" taksId="install" /><RakeGroup description="" fullCmd="" taksId="install"><RakeTask description="Build and install pdftdx-0.1.0.gem into system gems without network access" fullCmd="install:local" taksId="local" /></RakeGroup><RakeTask description="Create tag v0.1.0 and build and push pdftdx-0.1.0.gem to Rubygems" fullCmd="release[remote]" taksId="release[remote]" /><RakeTask description="" fullCmd="default" taksId="default" /><RakeTask description="" fullCmd="release" taksId="release" /><RakeGroup description="" fullCmd="" taksId="release"><RakeTask description="" fullCmd="release:guard_clean" taksId="guard_clean" /><RakeTask description="" fullCmd="release:rubygem_push" taksId="rubygem_push" /><RakeTask description="" fullCmd="release:source_control_push" taksId="source_control_push" /></RakeGroup></RakeGroup></Settings>
|
@@ -0,0 +1,10 @@
|
|
1
|
+
<component name="InspectionProjectProfileManager">
|
2
|
+
<profile version="1.0">
|
3
|
+
<option name="myName" value="Project Default" />
|
4
|
+
<inspection_tool class="SpellCheckingInspection" enabled="false" level="TYPO" enabled_by_default="false">
|
5
|
+
<option name="processCode" value="true" />
|
6
|
+
<option name="processLiterals" value="true" />
|
7
|
+
<option name="processComments" value="true" />
|
8
|
+
</inspection_tool>
|
9
|
+
</profile>
|
10
|
+
</component>
|
data/.idea/misc.xml
ADDED
@@ -0,0 +1,14 @@
|
|
1
|
+
<?xml version="1.0" encoding="UTF-8"?>
|
2
|
+
<project version="4">
|
3
|
+
<component name="ProjectLevelVcsManager" settingsEditedManually="false">
|
4
|
+
<OptionsSetting value="true" id="Add" />
|
5
|
+
<OptionsSetting value="true" id="Remove" />
|
6
|
+
<OptionsSetting value="true" id="Checkout" />
|
7
|
+
<OptionsSetting value="true" id="Update" />
|
8
|
+
<OptionsSetting value="true" id="Status" />
|
9
|
+
<OptionsSetting value="true" id="Edit" />
|
10
|
+
<ConfirmationsSetting value="0" id="Add" />
|
11
|
+
<ConfirmationsSetting value="0" id="Remove" />
|
12
|
+
</component>
|
13
|
+
<component name="ProjectRootManager" version="2" project-jdk-name="RVM: ruby-2.3.0 [global]" project-jdk-type="RUBY_SDK" />
|
14
|
+
</project>
|
data/.idea/modules.xml
ADDED
data/.idea/pdftdx.iml
ADDED
@@ -0,0 +1,11 @@
|
|
1
|
+
<?xml version="1.0" encoding="UTF-8"?>
|
2
|
+
<module type="RUBY_MODULE" version="4">
|
3
|
+
<component name="NewModuleRootManager">
|
4
|
+
<content url="file://$MODULE_DIR$" />
|
5
|
+
<orderEntry type="inheritedJdk" />
|
6
|
+
<orderEntry type="sourceFolder" forTests="false" />
|
7
|
+
<orderEntry type="library" scope="PROVIDED" name="bundler (v1.12.5, RVM: ruby-2.3.0 [global]) [gem]" level="application" />
|
8
|
+
<orderEntry type="library" scope="PROVIDED" name="pdftohtml (v0.2.1, RVM: ruby-2.3.0 [global]) [gem]" level="application" />
|
9
|
+
<orderEntry type="library" scope="PROVIDED" name="rake (v10.5.0, RVM: ruby-2.3.0 [global]) [gem]" level="application" />
|
10
|
+
</component>
|
11
|
+
</module>
|
data/.idea/vcs.xml
ADDED
data/Gemfile
ADDED
data/Gemfile.lock
ADDED
@@ -0,0 +1,22 @@
|
|
1
|
+
PATH
|
2
|
+
remote: .
|
3
|
+
specs:
|
4
|
+
pdftdx (0.1.0)
|
5
|
+
pdftohtml
|
6
|
+
|
7
|
+
GEM
|
8
|
+
remote: https://rubygems.org/
|
9
|
+
specs:
|
10
|
+
pdftohtml (0.2.1)
|
11
|
+
rake (10.5.0)
|
12
|
+
|
13
|
+
PLATFORMS
|
14
|
+
ruby
|
15
|
+
|
16
|
+
DEPENDENCIES
|
17
|
+
bundler (~> 1.12)
|
18
|
+
pdftdx!
|
19
|
+
rake (~> 10.0)
|
20
|
+
|
21
|
+
BUNDLED WITH
|
22
|
+
1.12.5
|
data/LICENSE.txt
ADDED
@@ -0,0 +1,21 @@
|
|
1
|
+
The MIT License (MIT)
|
2
|
+
|
3
|
+
Copyright (c) 2016 Paul Duncan
|
4
|
+
|
5
|
+
Permission is hereby granted, free of charge, to any person obtaining a copy
|
6
|
+
of this software and associated documentation files (the "Software"), to deal
|
7
|
+
in the Software without restriction, including without limitation the rights
|
8
|
+
to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
|
9
|
+
copies of the Software, and to permit persons to whom the Software is
|
10
|
+
furnished to do so, subject to the following conditions:
|
11
|
+
|
12
|
+
The above copyright notice and this permission notice shall be included in
|
13
|
+
all copies or substantial portions of the Software.
|
14
|
+
|
15
|
+
THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
|
16
|
+
IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
|
17
|
+
FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
|
18
|
+
AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
|
19
|
+
LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
|
20
|
+
OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
|
21
|
+
THE SOFTWARE.
|
data/README.md
ADDED
data/Rakefile
ADDED
data/bin/pdftdx
ADDED
@@ -0,0 +1,26 @@
|
|
1
|
+
#!/usr/bin/env ruby
|
2
|
+
|
3
|
+
# PDF Table Data Extractor
|
4
|
+
# by Eresse <eresse@eresse.net>
|
5
|
+
|
6
|
+
# Internal Includes
|
7
|
+
require 'pdftdx'
|
8
|
+
|
9
|
+
# Usage
|
10
|
+
def usage
|
11
|
+
puts "Usage: #{$0} <PDF_FILE>"
|
12
|
+
exit 1
|
13
|
+
end
|
14
|
+
|
15
|
+
# Main
|
16
|
+
def main args
|
17
|
+
|
18
|
+
# Check Args
|
19
|
+
usage unless args.length == 1
|
20
|
+
|
21
|
+
# Extract Data from provided PDF File\
|
22
|
+
PDFTDX.extract_data args[0]
|
23
|
+
end
|
24
|
+
|
25
|
+
# Call Main
|
26
|
+
main ARGV
|
@@ -0,0 +1,80 @@
|
|
1
|
+
# PDF Table Data Extractor
|
2
|
+
# by Eresse <eresse@eresse.net>
|
3
|
+
|
4
|
+
# External Includes
|
5
|
+
require 'htmlentities'
|
6
|
+
|
7
|
+
# Internal Includes
|
8
|
+
require 'pdftdx/version'
|
9
|
+
|
10
|
+
# PDF TDX Module
|
11
|
+
module PDFTDX
|
12
|
+
|
13
|
+
# Parser Module
|
14
|
+
module Parser
|
15
|
+
|
16
|
+
# Line Regex
|
17
|
+
LINE_REGEX = /^<p style[^>]+top:([0-9]+)px[^>]+left:([0-9]+)px[^>]+>(.*)<\/p>/
|
18
|
+
|
19
|
+
# Maximum Cell Length (to be considered usable data)
|
20
|
+
MAX_CELL_LEN = 100
|
21
|
+
|
22
|
+
# Page Offset
|
23
|
+
PAGE_OFF = 10000
|
24
|
+
|
25
|
+
# Title Cell Regex
|
26
|
+
TITLE_CELL_REGEX = /<bbb>/
|
27
|
+
|
28
|
+
# Check Same Line
|
29
|
+
def self.same_line data, idx_a, idx_b
|
30
|
+
data[idx_a][:top] == data[idx_b][:top]
|
31
|
+
end
|
32
|
+
|
33
|
+
# Is All Same Data
|
34
|
+
def self.is_all_same row_data
|
35
|
+
n = row_data[row_data.keys[0]]
|
36
|
+
row_data.inject(true) { |b, e| b && (e[1] == n) }
|
37
|
+
end
|
38
|
+
|
39
|
+
# Contains Unusable Data (Empty / Long Strings)
|
40
|
+
def self.contains_unusable row_data
|
41
|
+
row_data.inject(false) { |b, e| b || (e[1].length == 0) || (e[1].length > MAX_CELL_LEN) }
|
42
|
+
end
|
43
|
+
|
44
|
+
# Process Data
|
45
|
+
def self.process_data data
|
46
|
+
|
47
|
+
# Build Data Table
|
48
|
+
table = {}
|
49
|
+
data.each { |d| table[d[:top]] ||= {}; table[d[:top]][d[:left]] = d[:data] }
|
50
|
+
|
51
|
+
# Filter Table Rows (Remove Lone Elements & Footers)
|
52
|
+
table.reject! { |top, row| row.size < 2 || (top % PAGE_OFF) >= 1110 || is_all_same(row) || contains_unusable(row) }
|
53
|
+
|
54
|
+
# Filter Table Cells
|
55
|
+
table = table.collect { |_top, r| r.reject { |_left, d| TITLE_CELL_REGEX =~ d } }.reject { |r| r.size < 1 }
|
56
|
+
|
57
|
+
# Cleanup Table ( IS THIS NECESSARY ? )
|
58
|
+
table.reject! { |r| r.size < 2 }
|
59
|
+
|
60
|
+
# DEBUG
|
61
|
+
puts "=============> #{table}"
|
62
|
+
end
|
63
|
+
|
64
|
+
# HTML Filter
|
65
|
+
def self.hfilter s
|
66
|
+
s.gsub '<br/>', "\n"
|
67
|
+
end
|
68
|
+
|
69
|
+
# Process Page Files
|
70
|
+
def self.process_page_files page_data
|
71
|
+
|
72
|
+
# Build HTML Entity Decoder
|
73
|
+
coder = HTMLEntities.new
|
74
|
+
|
75
|
+
# Collect & Process File Data
|
76
|
+
off = 0
|
77
|
+
process page_data.collect { |_idx, page| off = off + PAGE_OFF; page.select { |l| LINE_REGEX =~ l }.collect { |l| LINE_REGEX.match l }.collect { |d| { top: off + d[1].to_i, left: d[2].to_i, data: hfilter(coder.decode(d[3])) } } }.flatten
|
78
|
+
end
|
79
|
+
end
|
80
|
+
end
|
data/lib/pdftdx.rb
ADDED
@@ -0,0 +1,25 @@
|
|
1
|
+
# PDF Table Data Extractor
|
2
|
+
# by Eresse <eresse@eresse.net>
|
3
|
+
|
4
|
+
# External Includes
|
5
|
+
require 'htmlentities'
|
6
|
+
require 'pdftohtml'
|
7
|
+
|
8
|
+
# Internal Includes
|
9
|
+
require 'pdftdx/dumper'
|
10
|
+
require 'pdftdx/parser'
|
11
|
+
require 'pdftdx/version'
|
12
|
+
|
13
|
+
# PDF TDX Module
|
14
|
+
module PDFTDX
|
15
|
+
|
16
|
+
# Extract Data from PDF
|
17
|
+
def self.extract_data pdf_file
|
18
|
+
|
19
|
+
# Dump PDF Data
|
20
|
+
page_data = Pdftohtml.convert pdf_file
|
21
|
+
|
22
|
+
# Process Page Data
|
23
|
+
PDFTDX::Parser.process_page_files page_data
|
24
|
+
end
|
25
|
+
end
|
data/pdftdx.gemspec
ADDED
@@ -0,0 +1,25 @@
|
|
1
|
+
# coding: utf-8
|
2
|
+
lib = File.expand_path('../lib', __FILE__)
|
3
|
+
$LOAD_PATH.unshift(lib) unless $LOAD_PATH.include?(lib)
|
4
|
+
require 'pdftdx/version'
|
5
|
+
|
6
|
+
Gem::Specification.new do |spec|
|
7
|
+
spec.name = "pdftdx"
|
8
|
+
spec.version = PDFTDX::VERSION
|
9
|
+
spec.authors = ["Eresse"]
|
10
|
+
spec.email = ["eresse@eresse.net"]
|
11
|
+
|
12
|
+
spec.summary = "Simple PDF Table Data Extractor"
|
13
|
+
spec.description = "Simple tool to extract Table Data from PDFs"
|
14
|
+
spec.homepage = "http://redmine.eresse.net/projects/pdftdx"
|
15
|
+
spec.license = "MIT"
|
16
|
+
|
17
|
+
spec.files = `git ls-files -z`.split("\x0").reject { |f| f.match(%r{^(test|spec|features)/}) }
|
18
|
+
spec.bindir = "exe"
|
19
|
+
spec.executables = spec.files.grep(%r{^exe/}) { |f| File.basename(f) }
|
20
|
+
spec.require_paths = ["lib"]
|
21
|
+
|
22
|
+
spec.add_development_dependency "bundler", "~> 1.12"
|
23
|
+
spec.add_development_dependency "rake", "~> 10.0"
|
24
|
+
spec.add_runtime_dependency "pdftohtml"
|
25
|
+
end
|
metadata
ADDED
@@ -0,0 +1,104 @@
|
|
1
|
+
--- !ruby/object:Gem::Specification
|
2
|
+
name: pdftdx
|
3
|
+
version: !ruby/object:Gem::Version
|
4
|
+
version: 0.1.0
|
5
|
+
platform: ruby
|
6
|
+
authors:
|
7
|
+
- Eresse
|
8
|
+
autorequire:
|
9
|
+
bindir: exe
|
10
|
+
cert_chain: []
|
11
|
+
date: 2016-12-09 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: '1.12'
|
20
|
+
type: :development
|
21
|
+
prerelease: false
|
22
|
+
version_requirements: !ruby/object:Gem::Requirement
|
23
|
+
requirements:
|
24
|
+
- - "~>"
|
25
|
+
- !ruby/object:Gem::Version
|
26
|
+
version: '1.12'
|
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
|
+
- !ruby/object:Gem::Dependency
|
42
|
+
name: pdftohtml
|
43
|
+
requirement: !ruby/object:Gem::Requirement
|
44
|
+
requirements:
|
45
|
+
- - ">="
|
46
|
+
- !ruby/object:Gem::Version
|
47
|
+
version: '0'
|
48
|
+
type: :runtime
|
49
|
+
prerelease: false
|
50
|
+
version_requirements: !ruby/object:Gem::Requirement
|
51
|
+
requirements:
|
52
|
+
- - ">="
|
53
|
+
- !ruby/object:Gem::Version
|
54
|
+
version: '0'
|
55
|
+
description: Simple tool to extract Table Data from PDFs
|
56
|
+
email:
|
57
|
+
- eresse@eresse.net
|
58
|
+
executables: []
|
59
|
+
extensions: []
|
60
|
+
extra_rdoc_files: []
|
61
|
+
files:
|
62
|
+
- ".gitignore"
|
63
|
+
- ".idea/.rakeTasks"
|
64
|
+
- ".idea/inspectionProfiles/Project_Default.xml"
|
65
|
+
- ".idea/inspectionProfiles/profiles_settings.xml"
|
66
|
+
- ".idea/misc.xml"
|
67
|
+
- ".idea/modules.xml"
|
68
|
+
- ".idea/pdftdx.iml"
|
69
|
+
- ".idea/vcs.xml"
|
70
|
+
- Gemfile
|
71
|
+
- Gemfile.lock
|
72
|
+
- LICENSE.txt
|
73
|
+
- README.md
|
74
|
+
- Rakefile
|
75
|
+
- bin/pdftdx
|
76
|
+
- lib/pdftdx.rb
|
77
|
+
- lib/pdftdx/parser.rb
|
78
|
+
- lib/pdftdx/version.rb
|
79
|
+
- pdftdx.gemspec
|
80
|
+
homepage: http://redmine.eresse.net/projects/pdftdx
|
81
|
+
licenses:
|
82
|
+
- MIT
|
83
|
+
metadata: {}
|
84
|
+
post_install_message:
|
85
|
+
rdoc_options: []
|
86
|
+
require_paths:
|
87
|
+
- lib
|
88
|
+
required_ruby_version: !ruby/object:Gem::Requirement
|
89
|
+
requirements:
|
90
|
+
- - ">="
|
91
|
+
- !ruby/object:Gem::Version
|
92
|
+
version: '0'
|
93
|
+
required_rubygems_version: !ruby/object:Gem::Requirement
|
94
|
+
requirements:
|
95
|
+
- - ">="
|
96
|
+
- !ruby/object:Gem::Version
|
97
|
+
version: '0'
|
98
|
+
requirements: []
|
99
|
+
rubyforge_project:
|
100
|
+
rubygems_version: 2.5.1
|
101
|
+
signing_key:
|
102
|
+
specification_version: 4
|
103
|
+
summary: Simple PDF Table Data Extractor
|
104
|
+
test_files: []
|