pdf-reader 0.8.6 → 0.9.0
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.
- data/CHANGELOG +17 -0
- data/README.rdoc +7 -15
- data/Rakefile +10 -63
- data/TODO +6 -8
- data/bin/pdf_object +3 -0
- data/bin/pdf_text +4 -2
- data/examples/extract_images.rb +108 -0
- data/examples/hash.rb +1 -1
- data/examples/text.rb +3 -0
- data/lib/pdf/hash.rb +8 -225
- data/lib/pdf/reader.rb +79 -55
- data/lib/pdf/reader/abstract_strategy.rb +77 -0
- data/lib/pdf/reader/buffer.rb +61 -40
- data/lib/pdf/reader/cmap.rb +11 -10
- data/lib/pdf/reader/encoding.rb +85 -79
- data/lib/pdf/reader/error.rb +1 -2
- data/lib/pdf/reader/filter.rb +109 -6
- data/lib/pdf/reader/font.rb +11 -11
- data/lib/pdf/reader/lzw.rb +123 -0
- data/lib/pdf/reader/metadata_strategy.rb +53 -0
- data/lib/pdf/reader/object_hash.rb +275 -0
- data/lib/pdf/reader/object_stream.rb +51 -0
- data/lib/pdf/reader/{content.rb → pages_strategy.rb} +63 -100
- data/lib/pdf/reader/parser.rb +74 -37
- data/lib/pdf/reader/print_receiver.rb +0 -1
- data/lib/pdf/reader/register_receiver.rb +21 -0
- data/lib/pdf/reader/stream.rb +5 -1
- data/lib/pdf/reader/text_receiver.rb +3 -1
- data/lib/pdf/reader/token.rb +1 -1
- data/lib/pdf/reader/xref.rb +126 -64
- metadata +61 -13
- data/lib/pdf/reader/explore.rb +0 -116
metadata
CHANGED
@@ -1,13 +1,13 @@
|
|
1
1
|
--- !ruby/object:Gem::Specification
|
2
2
|
name: pdf-reader
|
3
3
|
version: !ruby/object:Gem::Version
|
4
|
-
hash:
|
4
|
+
hash: 59
|
5
5
|
prerelease: false
|
6
6
|
segments:
|
7
7
|
- 0
|
8
|
-
-
|
9
|
-
-
|
10
|
-
version: 0.
|
8
|
+
- 9
|
9
|
+
- 0
|
10
|
+
version: 0.9.0
|
11
11
|
platform: ruby
|
12
12
|
authors:
|
13
13
|
- James Healy
|
@@ -15,13 +15,56 @@ autorequire:
|
|
15
15
|
bindir: bin
|
16
16
|
cert_chain: []
|
17
17
|
|
18
|
-
date: 2010-
|
18
|
+
date: 2010-11-19 00:00:00 -05:00
|
19
19
|
default_executable:
|
20
20
|
dependencies:
|
21
21
|
- !ruby/object:Gem::Dependency
|
22
|
-
name:
|
22
|
+
name: rake
|
23
23
|
prerelease: false
|
24
24
|
requirement: &id001 !ruby/object:Gem::Requirement
|
25
|
+
none: false
|
26
|
+
requirements:
|
27
|
+
- - ">="
|
28
|
+
- !ruby/object:Gem::Version
|
29
|
+
hash: 3
|
30
|
+
segments:
|
31
|
+
- 0
|
32
|
+
version: "0"
|
33
|
+
type: :development
|
34
|
+
version_requirements: *id001
|
35
|
+
- !ruby/object:Gem::Dependency
|
36
|
+
name: roodi
|
37
|
+
prerelease: false
|
38
|
+
requirement: &id002 !ruby/object:Gem::Requirement
|
39
|
+
none: false
|
40
|
+
requirements:
|
41
|
+
- - ">="
|
42
|
+
- !ruby/object:Gem::Version
|
43
|
+
hash: 3
|
44
|
+
segments:
|
45
|
+
- 0
|
46
|
+
version: "0"
|
47
|
+
type: :development
|
48
|
+
version_requirements: *id002
|
49
|
+
- !ruby/object:Gem::Dependency
|
50
|
+
name: rspec
|
51
|
+
prerelease: false
|
52
|
+
requirement: &id003 !ruby/object:Gem::Requirement
|
53
|
+
none: false
|
54
|
+
requirements:
|
55
|
+
- - ~>
|
56
|
+
- !ruby/object:Gem::Version
|
57
|
+
hash: 1
|
58
|
+
segments:
|
59
|
+
- 2
|
60
|
+
- 1
|
61
|
+
version: "2.1"
|
62
|
+
type: :development
|
63
|
+
version_requirements: *id003
|
64
|
+
- !ruby/object:Gem::Dependency
|
65
|
+
name: Ascii85
|
66
|
+
prerelease: false
|
67
|
+
requirement: &id004 !ruby/object:Gem::Requirement
|
25
68
|
none: false
|
26
69
|
requirements:
|
27
70
|
- - ">="
|
@@ -32,7 +75,7 @@ dependencies:
|
|
32
75
|
- 9
|
33
76
|
version: "0.9"
|
34
77
|
type: :runtime
|
35
|
-
version_requirements: *
|
78
|
+
version_requirements: *id004
|
36
79
|
description: The PDF::Reader library implements a PDF parser conforming as much as possible to the PDF specification from Adobe
|
37
80
|
email: jimmy@deefa.com
|
38
81
|
executables:
|
@@ -56,22 +99,27 @@ files:
|
|
56
99
|
- examples/text.rb
|
57
100
|
- examples/version.rb
|
58
101
|
- examples/page_counter_improved.rb
|
102
|
+
- examples/extract_images.rb
|
59
103
|
- lib/pdf/reader/glyphlist.txt
|
60
|
-
- lib/pdf/reader/content.rb
|
61
104
|
- lib/pdf/reader/error.rb
|
62
105
|
- lib/pdf/reader/font.rb
|
106
|
+
- lib/pdf/reader/lzw.rb
|
63
107
|
- lib/pdf/reader/print_receiver.rb
|
64
108
|
- lib/pdf/reader/reference.rb
|
65
109
|
- lib/pdf/reader/filter.rb
|
66
110
|
- lib/pdf/reader/text_receiver.rb
|
111
|
+
- lib/pdf/reader/pages_strategy.rb
|
112
|
+
- lib/pdf/reader/abstract_strategy.rb
|
67
113
|
- lib/pdf/reader/encoding.rb
|
68
114
|
- lib/pdf/reader/stream.rb
|
69
115
|
- lib/pdf/reader/register_receiver.rb
|
116
|
+
- lib/pdf/reader/object_hash.rb
|
70
117
|
- lib/pdf/reader/token.rb
|
71
118
|
- lib/pdf/reader/xref.rb
|
72
119
|
- lib/pdf/reader/cmap.rb
|
120
|
+
- lib/pdf/reader/object_stream.rb
|
121
|
+
- lib/pdf/reader/metadata_strategy.rb
|
73
122
|
- lib/pdf/reader/buffer.rb
|
74
|
-
- lib/pdf/reader/explore.rb
|
75
123
|
- lib/pdf/reader/encodings/zapf_dingbats.txt
|
76
124
|
- lib/pdf/reader/encodings/standard.txt
|
77
125
|
- lib/pdf/reader/encodings/mac_roman.txt
|
@@ -84,13 +132,13 @@ files:
|
|
84
132
|
- lib/pdf/reader.rb
|
85
133
|
- lib/pdf-reader.rb
|
86
134
|
- Rakefile
|
87
|
-
- bin/pdf_object
|
88
|
-
- bin/pdf_text
|
89
|
-
- bin/pdf_list_callbacks
|
90
135
|
- README.rdoc
|
91
136
|
- TODO
|
92
137
|
- CHANGELOG
|
93
138
|
- MIT-LICENSE
|
139
|
+
- bin/pdf_object
|
140
|
+
- bin/pdf_text
|
141
|
+
- bin/pdf_list_callbacks
|
94
142
|
has_rdoc: true
|
95
143
|
homepage: http://github.com/yob/pdf-reader
|
96
144
|
licenses: []
|
@@ -124,7 +172,7 @@ required_rubygems_version: !ruby/object:Gem::Requirement
|
|
124
172
|
version: "0"
|
125
173
|
requirements: []
|
126
174
|
|
127
|
-
rubyforge_project:
|
175
|
+
rubyforge_project:
|
128
176
|
rubygems_version: 1.3.7
|
129
177
|
signing_key:
|
130
178
|
specification_version: 3
|
data/lib/pdf/reader/explore.rb
DELETED
@@ -1,116 +0,0 @@
|
|
1
|
-
################################################################################
|
2
|
-
#
|
3
|
-
# Copyright (C) 2006 Peter J Jones (pjones@pmade.com)
|
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.
|
23
|
-
#
|
24
|
-
################################################################################
|
25
|
-
require 'pathname'
|
26
|
-
|
27
|
-
|
28
|
-
class PDF::Reader
|
29
|
-
################################################################################
|
30
|
-
class Explore
|
31
|
-
################################################################################
|
32
|
-
def self.file (name)
|
33
|
-
PDF::Reader.new.parse(File.open(name), self)
|
34
|
-
end
|
35
|
-
################################################################################
|
36
|
-
def initialize (receiver, xref)
|
37
|
-
@xref = xref
|
38
|
-
@pwd = '/'
|
39
|
-
end
|
40
|
-
################################################################################
|
41
|
-
def document (root)
|
42
|
-
@root = root
|
43
|
-
self
|
44
|
-
end
|
45
|
-
################################################################################
|
46
|
-
def output_parent (obj)
|
47
|
-
case obj
|
48
|
-
when Hash
|
49
|
-
obj.each do |k,v|
|
50
|
-
print "#{k}"; output_child(v); print "\n"
|
51
|
-
Explore::const_set(k, k) if !Explore.const_defined?(k)
|
52
|
-
end
|
53
|
-
when Array
|
54
|
-
obj.each_with_index {|o, i| print "#{i}: "; output_child(o); print "\n"}
|
55
|
-
else
|
56
|
-
output_child(obj)
|
57
|
-
print "\n"
|
58
|
-
end
|
59
|
-
end
|
60
|
-
################################################################################
|
61
|
-
def output_child (obj)
|
62
|
-
print ": #{obj.class}"
|
63
|
-
|
64
|
-
case obj
|
65
|
-
when Float
|
66
|
-
print ": #{obj}"
|
67
|
-
when String
|
68
|
-
print ": #{obj[0, 20].sub(/\n/, ' ')}"
|
69
|
-
end
|
70
|
-
end
|
71
|
-
################################################################################
|
72
|
-
def cd (path)
|
73
|
-
path = path.to_s
|
74
|
-
|
75
|
-
if path[0,1] == "/"
|
76
|
-
@pwd = path
|
77
|
-
else
|
78
|
-
@pwd = Pathname.new(@pwd + '/' + path).cleanpath.to_s
|
79
|
-
end
|
80
|
-
end
|
81
|
-
################################################################################
|
82
|
-
def pwd
|
83
|
-
@pwd
|
84
|
-
end
|
85
|
-
################################################################################
|
86
|
-
def ls (entry = nil)
|
87
|
-
parts = @pwd.split('/')
|
88
|
-
obj = @root
|
89
|
-
|
90
|
-
parts.shift if parts[0] == ""
|
91
|
-
parts.push(entry) if entry
|
92
|
-
|
93
|
-
parts.each do |p|
|
94
|
-
case obj
|
95
|
-
when Hash
|
96
|
-
unless obj.has_key?(p)
|
97
|
-
puts "invalid path at #{p}"
|
98
|
-
return
|
99
|
-
end
|
100
|
-
obj = obj[p]
|
101
|
-
|
102
|
-
when Array
|
103
|
-
obj = obj[p.to_i]
|
104
|
-
end
|
105
|
-
|
106
|
-
obj = @xref.object(obj)
|
107
|
-
end
|
108
|
-
|
109
|
-
output_parent(obj)
|
110
|
-
"#{@pwd}: #{obj.class}"
|
111
|
-
end
|
112
|
-
################################################################################
|
113
|
-
end
|
114
|
-
################################################################################
|
115
|
-
end
|
116
|
-
################################################################################
|