onlyoffice_pdf_parser 0.1.2 → 0.4.0
Sign up to get free protection for your applications and to get access to all the features.
- checksums.yaml +4 -4
- data/lib/onlyoffice_pdf_parser/bmp_image.rb +17 -5
- data/lib/onlyoffice_pdf_parser/helpers/cursor_point.rb +10 -0
- data/lib/onlyoffice_pdf_parser/name.rb +10 -0
- data/lib/onlyoffice_pdf_parser/pdf_structure.rb +8 -0
- data/lib/onlyoffice_pdf_parser/version.rb +3 -1
- data/lib/onlyoffice_pdf_parser.rb +2 -2
- metadata +150 -22
checksums.yaml
CHANGED
@@ -1,7 +1,7 @@
|
|
1
1
|
---
|
2
2
|
SHA256:
|
3
|
-
metadata.gz:
|
4
|
-
data.tar.gz:
|
3
|
+
metadata.gz: aa1e4904848f330f9e50f850cfdcab6e4b0e170e2478491a94c1e6ca5172bea2
|
4
|
+
data.tar.gz: afc8fcd96b544e8d7ec8dd5cab7db1d7225359a0d2e5423b706243fa24252654
|
5
5
|
SHA512:
|
6
|
-
metadata.gz:
|
7
|
-
data.tar.gz:
|
6
|
+
metadata.gz: '05112925b5f8dfb5abd423435e96410344e421e1cf1705733b2c142cf2225bee45dc1611e89915d70233ac548ae131edf6711d91500c3bf85b76a6562b3a493f'
|
7
|
+
data.tar.gz: 45e19650bd51a9bffca33598e45831389eb4caa6a732651a901cedd1fce41813c7ffe3dc2dfcbfc19f08532289da43c01a8f33e30c4fda0dcba3bb015cd6a603
|
@@ -13,7 +13,9 @@ module OnlyofficePdfParser
|
|
13
13
|
# @return [String] binary dat of file
|
14
14
|
attr_reader :data
|
15
15
|
|
16
|
-
def initialize(param = nil)
|
16
|
+
def initialize(param = nil, width: nil, height: nil)
|
17
|
+
@width = width
|
18
|
+
@height = height
|
17
19
|
return unless param
|
18
20
|
|
19
21
|
init_data(param)
|
@@ -24,10 +26,14 @@ module OnlyofficePdfParser
|
|
24
26
|
fetch_pixels
|
25
27
|
end
|
26
28
|
|
29
|
+
# @return [String] convert object to string
|
27
30
|
def to_s
|
28
31
|
path_to_image
|
29
32
|
end
|
30
33
|
|
34
|
+
# Compare object with other
|
35
|
+
# @param other [Object] object to compare
|
36
|
+
# @return [True, False] result of comparison
|
31
37
|
def ==(other)
|
32
38
|
return false unless other.width == width && other.height == height
|
33
39
|
|
@@ -41,8 +47,13 @@ module OnlyofficePdfParser
|
|
41
47
|
true
|
42
48
|
end
|
43
49
|
|
50
|
+
# Get sub image from coordinates
|
51
|
+
# @param start_point [CursorPoint] top left coordinates to get
|
52
|
+
# @param width [Integer] width to get
|
53
|
+
# @param height [Integer] height to get
|
54
|
+
# @return [BmpImage] result
|
44
55
|
def get_sub_image(start_point = CursorPoint.new(0, 0), width = 0, height = 0)
|
45
|
-
sub_image = BmpImage.new
|
56
|
+
sub_image = BmpImage.new(nil, width: width, height: height)
|
46
57
|
pixels_array = []
|
47
58
|
height.times do |current_height|
|
48
59
|
line_array = []
|
@@ -56,11 +67,12 @@ module OnlyofficePdfParser
|
|
56
67
|
pixels_array << line_array
|
57
68
|
end
|
58
69
|
sub_image.pixels = pixels_array
|
59
|
-
sub_image.width = width
|
60
|
-
sub_image.height = height
|
61
70
|
sub_image
|
62
71
|
end
|
63
72
|
|
73
|
+
# Get sub image from file pattern coordinates
|
74
|
+
# @param path_to_sub_image [String] path to pattern to find
|
75
|
+
# @return [Array<CursorPoint>] result
|
64
76
|
def get_sub_image_array(path_to_sub_image)
|
65
77
|
coordinates_array = []
|
66
78
|
sub_image = BmpImage.new(path_to_sub_image)
|
@@ -95,7 +107,7 @@ module OnlyofficePdfParser
|
|
95
107
|
# @return [Void] Fill @pixel with data
|
96
108
|
def fetch_pixels
|
97
109
|
tmp_file = Tempfile.new('onlyoffice_pdf_parser')
|
98
|
-
File.
|
110
|
+
File.binwrite(tmp_file, data)
|
99
111
|
@pixels = ImageList.new(tmp_file.path).get_pixels(0, 0, width, height).each_slice(width).to_a
|
100
112
|
tmp_file.unlink
|
101
113
|
end
|
@@ -15,14 +15,20 @@ module OnlyofficePdfParser
|
|
15
15
|
alias x left
|
16
16
|
alias y top
|
17
17
|
|
18
|
+
# Make a copy of object
|
19
|
+
# @return [CursorPoint] another object
|
18
20
|
def dup
|
19
21
|
CursorPoint.new(@left, @top)
|
20
22
|
end
|
21
23
|
|
24
|
+
# @return [String] convert object to string
|
22
25
|
def to_s
|
23
26
|
"[#{@left}, #{@top}]"
|
24
27
|
end
|
25
28
|
|
29
|
+
# Compare object with other
|
30
|
+
# @param other [Object] object to compare
|
31
|
+
# @return [True, False] result of comparison
|
26
32
|
def ==(other)
|
27
33
|
if other.respond_to?(:left) && other.respond_to?(:top)
|
28
34
|
@left == other.left && @top == other.top
|
@@ -31,6 +37,9 @@ module OnlyofficePdfParser
|
|
31
37
|
end
|
32
38
|
end
|
33
39
|
|
40
|
+
# Accessor of attributes like hash
|
41
|
+
# @param name [Symbol] attribute name
|
42
|
+
# @return [Object] value of attribute
|
34
43
|
def [](name)
|
35
44
|
case name
|
36
45
|
when :width
|
@@ -43,5 +52,6 @@ module OnlyofficePdfParser
|
|
43
52
|
end
|
44
53
|
end
|
45
54
|
|
55
|
+
# Alias for this object
|
46
56
|
Dimensions = CursorPoint
|
47
57
|
end
|
@@ -24,6 +24,9 @@ module OnlyofficePdfParser
|
|
24
24
|
@pages_in_bmp = []
|
25
25
|
end
|
26
26
|
|
27
|
+
# Accessor of attributes like hash
|
28
|
+
# @param parameter [Symbol] attribute name
|
29
|
+
# @return [Object] value of attribute
|
27
30
|
def [](parameter)
|
28
31
|
case parameter
|
29
32
|
when :pages
|
@@ -70,6 +73,7 @@ module OnlyofficePdfParser
|
|
70
73
|
@page_size ||= "Landscape #{PAGE_SIZE_FOR_PDF.key(page_size_points.reverse)}"
|
71
74
|
end
|
72
75
|
|
76
|
+
# @return [Hash] list of default page size and names
|
73
77
|
PAGE_SIZE_FOR_PDF = { 'US Letter' => [612, 792],
|
74
78
|
'US Legal' => [612, 1008],
|
75
79
|
'A4' => [595, 842],
|
@@ -84,6 +88,9 @@ module OnlyofficePdfParser
|
|
84
88
|
'Envelope Choukei 3' => [340, 666],
|
85
89
|
'Super B/A3' => [936, 1368] }.freeze
|
86
90
|
|
91
|
+
# Parse file
|
92
|
+
# @param filename [String] path to file
|
93
|
+
# @return [PdfStructure] result of parse
|
87
94
|
def self.parse(filename)
|
88
95
|
file = PdfStructure.new(pages: [], file_path: filename)
|
89
96
|
file.pdf_reader_parse
|
@@ -93,5 +100,6 @@ module OnlyofficePdfParser
|
|
93
100
|
end
|
94
101
|
end
|
95
102
|
|
103
|
+
# Alias for object
|
96
104
|
PdfParser = PdfStructure
|
97
105
|
end
|
metadata
CHANGED
@@ -1,7 +1,7 @@
|
|
1
1
|
--- !ruby/object:Gem::Specification
|
2
2
|
name: onlyoffice_pdf_parser
|
3
3
|
version: !ruby/object:Gem::Version
|
4
|
-
version: 0.
|
4
|
+
version: 0.4.0
|
5
5
|
platform: ruby
|
6
6
|
authors:
|
7
7
|
- Pavel Lobashov
|
@@ -9,22 +9,28 @@ authors:
|
|
9
9
|
autorequire:
|
10
10
|
bindir: bin
|
11
11
|
cert_chain: []
|
12
|
-
date:
|
12
|
+
date: 2022-01-21 00:00:00.000000000 Z
|
13
13
|
dependencies:
|
14
14
|
- !ruby/object:Gem::Dependency
|
15
15
|
name: image_size
|
16
16
|
requirement: !ruby/object:Gem::Requirement
|
17
17
|
requirements:
|
18
|
-
- - "
|
18
|
+
- - ">="
|
19
19
|
- !ruby/object:Gem::Version
|
20
20
|
version: '2'
|
21
|
+
- - "<"
|
22
|
+
- !ruby/object:Gem::Version
|
23
|
+
version: '4'
|
21
24
|
type: :runtime
|
22
25
|
prerelease: false
|
23
26
|
version_requirements: !ruby/object:Gem::Requirement
|
24
27
|
requirements:
|
25
|
-
- - "
|
28
|
+
- - ">="
|
26
29
|
- !ruby/object:Gem::Version
|
27
30
|
version: '2'
|
31
|
+
- - "<"
|
32
|
+
- !ruby/object:Gem::Version
|
33
|
+
version: '4'
|
28
34
|
- !ruby/object:Gem::Dependency
|
29
35
|
name: pdf-reader
|
30
36
|
requirement: !ruby/object:Gem::Requirement
|
@@ -43,36 +49,156 @@ dependencies:
|
|
43
49
|
name: rmagick
|
44
50
|
requirement: !ruby/object:Gem::Requirement
|
45
51
|
requirements:
|
46
|
-
- - "
|
47
|
-
- !ruby/object:Gem::Version
|
48
|
-
version: '2'
|
49
|
-
- - "<"
|
52
|
+
- - "~>"
|
50
53
|
- !ruby/object:Gem::Version
|
51
|
-
version: '
|
54
|
+
version: '4'
|
52
55
|
type: :runtime
|
53
56
|
prerelease: false
|
54
57
|
version_requirements: !ruby/object:Gem::Requirement
|
55
58
|
requirements:
|
56
|
-
- - "
|
59
|
+
- - "~>"
|
57
60
|
- !ruby/object:Gem::Version
|
58
|
-
version: '
|
59
|
-
|
61
|
+
version: '4'
|
62
|
+
- !ruby/object:Gem::Dependency
|
63
|
+
name: overcommit
|
64
|
+
requirement: !ruby/object:Gem::Requirement
|
65
|
+
requirements:
|
66
|
+
- - "~>"
|
60
67
|
- !ruby/object:Gem::Version
|
61
|
-
version: '
|
68
|
+
version: '0'
|
69
|
+
type: :development
|
70
|
+
prerelease: false
|
71
|
+
version_requirements: !ruby/object:Gem::Requirement
|
72
|
+
requirements:
|
73
|
+
- - "~>"
|
74
|
+
- !ruby/object:Gem::Version
|
75
|
+
version: '0'
|
76
|
+
- !ruby/object:Gem::Dependency
|
77
|
+
name: parallel_tests
|
78
|
+
requirement: !ruby/object:Gem::Requirement
|
79
|
+
requirements:
|
80
|
+
- - "~>"
|
81
|
+
- !ruby/object:Gem::Version
|
82
|
+
version: '3'
|
83
|
+
type: :development
|
84
|
+
prerelease: false
|
85
|
+
version_requirements: !ruby/object:Gem::Requirement
|
86
|
+
requirements:
|
87
|
+
- - "~>"
|
88
|
+
- !ruby/object:Gem::Version
|
89
|
+
version: '3'
|
62
90
|
- !ruby/object:Gem::Dependency
|
63
91
|
name: rake
|
64
92
|
requirement: !ruby/object:Gem::Requirement
|
65
93
|
requirements:
|
66
94
|
- - "~>"
|
67
95
|
- !ruby/object:Gem::Version
|
68
|
-
version: '13
|
96
|
+
version: '13'
|
97
|
+
type: :development
|
98
|
+
prerelease: false
|
99
|
+
version_requirements: !ruby/object:Gem::Requirement
|
100
|
+
requirements:
|
101
|
+
- - "~>"
|
102
|
+
- !ruby/object:Gem::Version
|
103
|
+
version: '13'
|
104
|
+
- !ruby/object:Gem::Dependency
|
105
|
+
name: rspec
|
106
|
+
requirement: !ruby/object:Gem::Requirement
|
107
|
+
requirements:
|
108
|
+
- - "~>"
|
109
|
+
- !ruby/object:Gem::Version
|
110
|
+
version: '3'
|
111
|
+
type: :development
|
112
|
+
prerelease: false
|
113
|
+
version_requirements: !ruby/object:Gem::Requirement
|
114
|
+
requirements:
|
115
|
+
- - "~>"
|
116
|
+
- !ruby/object:Gem::Version
|
117
|
+
version: '3'
|
118
|
+
- !ruby/object:Gem::Dependency
|
119
|
+
name: rubocop
|
120
|
+
requirement: !ruby/object:Gem::Requirement
|
121
|
+
requirements:
|
122
|
+
- - "~>"
|
123
|
+
- !ruby/object:Gem::Version
|
124
|
+
version: '1'
|
125
|
+
type: :development
|
126
|
+
prerelease: false
|
127
|
+
version_requirements: !ruby/object:Gem::Requirement
|
128
|
+
requirements:
|
129
|
+
- - "~>"
|
130
|
+
- !ruby/object:Gem::Version
|
131
|
+
version: '1'
|
132
|
+
- !ruby/object:Gem::Dependency
|
133
|
+
name: rubocop-performance
|
134
|
+
requirement: !ruby/object:Gem::Requirement
|
135
|
+
requirements:
|
136
|
+
- - "~>"
|
137
|
+
- !ruby/object:Gem::Version
|
138
|
+
version: '1'
|
139
|
+
type: :development
|
140
|
+
prerelease: false
|
141
|
+
version_requirements: !ruby/object:Gem::Requirement
|
142
|
+
requirements:
|
143
|
+
- - "~>"
|
144
|
+
- !ruby/object:Gem::Version
|
145
|
+
version: '1'
|
146
|
+
- !ruby/object:Gem::Dependency
|
147
|
+
name: rubocop-rake
|
148
|
+
requirement: !ruby/object:Gem::Requirement
|
149
|
+
requirements:
|
150
|
+
- - "~>"
|
151
|
+
- !ruby/object:Gem::Version
|
152
|
+
version: '0'
|
69
153
|
type: :development
|
70
154
|
prerelease: false
|
71
155
|
version_requirements: !ruby/object:Gem::Requirement
|
72
156
|
requirements:
|
73
157
|
- - "~>"
|
74
158
|
- !ruby/object:Gem::Version
|
75
|
-
version: '
|
159
|
+
version: '0'
|
160
|
+
- !ruby/object:Gem::Dependency
|
161
|
+
name: rubocop-rspec
|
162
|
+
requirement: !ruby/object:Gem::Requirement
|
163
|
+
requirements:
|
164
|
+
- - "~>"
|
165
|
+
- !ruby/object:Gem::Version
|
166
|
+
version: '2'
|
167
|
+
type: :development
|
168
|
+
prerelease: false
|
169
|
+
version_requirements: !ruby/object:Gem::Requirement
|
170
|
+
requirements:
|
171
|
+
- - "~>"
|
172
|
+
- !ruby/object:Gem::Version
|
173
|
+
version: '2'
|
174
|
+
- !ruby/object:Gem::Dependency
|
175
|
+
name: simplecov
|
176
|
+
requirement: !ruby/object:Gem::Requirement
|
177
|
+
requirements:
|
178
|
+
- - "~>"
|
179
|
+
- !ruby/object:Gem::Version
|
180
|
+
version: '0'
|
181
|
+
type: :development
|
182
|
+
prerelease: false
|
183
|
+
version_requirements: !ruby/object:Gem::Requirement
|
184
|
+
requirements:
|
185
|
+
- - "~>"
|
186
|
+
- !ruby/object:Gem::Version
|
187
|
+
version: '0'
|
188
|
+
- !ruby/object:Gem::Dependency
|
189
|
+
name: yard
|
190
|
+
requirement: !ruby/object:Gem::Requirement
|
191
|
+
requirements:
|
192
|
+
- - ">="
|
193
|
+
- !ruby/object:Gem::Version
|
194
|
+
version: 0.9.20
|
195
|
+
type: :development
|
196
|
+
prerelease: false
|
197
|
+
version_requirements: !ruby/object:Gem::Requirement
|
198
|
+
requirements:
|
199
|
+
- - ">="
|
200
|
+
- !ruby/object:Gem::Version
|
201
|
+
version: 0.9.20
|
76
202
|
description: Library for parsing, converting and extracting PDF data
|
77
203
|
email:
|
78
204
|
- shockwavenn@gmail.com
|
@@ -86,19 +212,21 @@ files:
|
|
86
212
|
- lib/onlyoffice_pdf_parser/helpers/array_helper.rb
|
87
213
|
- lib/onlyoffice_pdf_parser/helpers/cursor_point.rb
|
88
214
|
- lib/onlyoffice_pdf_parser/helpers/file_helper.rb
|
215
|
+
- lib/onlyoffice_pdf_parser/name.rb
|
89
216
|
- lib/onlyoffice_pdf_parser/pdf_structure.rb
|
90
217
|
- lib/onlyoffice_pdf_parser/pdf_structure/pdf_convert_to_bmp_helper.rb
|
91
218
|
- lib/onlyoffice_pdf_parser/pdf_structure/pdf_reader_helper.rb
|
92
219
|
- lib/onlyoffice_pdf_parser/version.rb
|
93
|
-
homepage: https://github.com/
|
220
|
+
homepage: https://github.com/ONLYOFFICE-QA/onlyoffice_pdf_parser
|
94
221
|
licenses:
|
95
222
|
- AGPL-3.0
|
96
223
|
metadata:
|
97
|
-
bug_tracker_uri: https://github.com/
|
98
|
-
changelog_uri: https://github.com/
|
224
|
+
bug_tracker_uri: https://github.com/ONLYOFFICE-QA/onlyoffice_pdf_parser/issues
|
225
|
+
changelog_uri: https://github.com/ONLYOFFICE-QA/onlyoffice_pdf_parser/blob/master/CHANGELOG.md
|
99
226
|
documentation_uri: https://www.rubydoc.info/gems/onlyoffice_pdf_parser
|
100
|
-
homepage_uri: https://github.com/
|
101
|
-
source_code_uri: https://github.com/
|
227
|
+
homepage_uri: https://github.com/ONLYOFFICE-QA/onlyoffice_pdf_parser
|
228
|
+
source_code_uri: https://github.com/ONLYOFFICE-QA/onlyoffice_pdf_parser
|
229
|
+
rubygems_mfa_required: 'true'
|
102
230
|
post_install_message:
|
103
231
|
rdoc_options: []
|
104
232
|
require_paths:
|
@@ -107,14 +235,14 @@ required_ruby_version: !ruby/object:Gem::Requirement
|
|
107
235
|
requirements:
|
108
236
|
- - ">="
|
109
237
|
- !ruby/object:Gem::Version
|
110
|
-
version: '
|
238
|
+
version: '2.5'
|
111
239
|
required_rubygems_version: !ruby/object:Gem::Requirement
|
112
240
|
requirements:
|
113
241
|
- - ">="
|
114
242
|
- !ruby/object:Gem::Version
|
115
243
|
version: '0'
|
116
244
|
requirements: []
|
117
|
-
rubygems_version: 3.
|
245
|
+
rubygems_version: 3.3.4
|
118
246
|
signing_key:
|
119
247
|
specification_version: 4
|
120
248
|
summary: ONLYOFFICE PDF Parser Gem
|