forked from yob/pdf-reader
/
parser.rb
246 lines (223 loc) · 8.17 KB
/
parser.rb
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
################################################################################
#
# Copyright (C) 2006 Peter J Jones (pjones@pmade.com)
#
# Permission is hereby granted, free of charge, to any person obtaining
# a copy of this software and associated documentation files (the
# "Software"), to deal in the Software without restriction, including
# without limitation the rights to use, copy, modify, merge, publish,
# distribute, sublicense, and/or sell copies of the Software, and to
# permit persons to whom the Software is furnished to do so, subject to
# the following conditions:
#
# The above copyright notice and this permission notice shall be
# included in all copies or substantial portions of the Software.
#
# THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
# EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
# MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
# NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE
# LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION
# OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION
# WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE.
#
################################################################################
class PDF::Reader
################################################################################
# An internal PDF::Reader class that reads objects from the PDF file and converts
# them into useable ruby objects (hash's, arrays, true, false, etc)
class Parser
TOKEN_STRATEGY = proc { |parser, token| Token.new(token) }
STRATEGIES = {
"/" => proc { |parser, token| parser.send(:pdf_name) },
"<<" => proc { |parser, token| parser.send(:dictionary) },
"[" => proc { |parser, token| parser.send(:array) },
"(" => proc { |parser, token| parser.send(:string) },
"<" => proc { |parser, token| parser.send(:hex_string) },
nil => proc { nil },
"true" => proc { true },
"false" => proc { false },
"null" => proc { nil },
"obj" => TOKEN_STRATEGY,
"endobj" => TOKEN_STRATEGY,
"stream" => TOKEN_STRATEGY,
"endstream" => TOKEN_STRATEGY,
">>" => TOKEN_STRATEGY,
"]" => TOKEN_STRATEGY,
">" => TOKEN_STRATEGY,
")" => TOKEN_STRATEGY
}
################################################################################
# Create a new parser around a PDF::Reader::Buffer object
#
# buffer - a PDF::Reader::Buffer object that contains PDF data
# objects - a PDF::Reader::ObjectHash object that can return objects from the PDF file
def initialize (buffer, objects=nil)
@buffer = buffer
@objects = objects
end
################################################################################
# Reads the next token from the underlying buffer and convets it to an appropriate
# object
#
# operators - a hash of supported operators to read from the underlying buffer.
def parse_token (operators={})
token = @buffer.token
if STRATEGIES.has_key? token
STRATEGIES[token].call(self, token)
elsif token.is_a? PDF::Reader::Reference
token
elsif token.is_a? Token
token
elsif operators.has_key? token
Token.new(token)
elsif token.respond_to?(:to_token)
token.to_token
elsif token =~ /\d*\.\d/
token.to_f
else
token.to_i
end
end
################################################################################
# Reads an entire PDF object from the buffer and returns it as a Ruby String.
# If the object is a content stream, returns both the stream and the dictionary
# that describes it
#
# id - the object ID to return
# gen - the object revision number to return
def object (id, gen)
Error.assert_equal(parse_token, id)
Error.assert_equal(parse_token, gen)
Error.str_assert(parse_token, "obj")
obj = parse_token
post_obj = parse_token
if post_obj == "stream"
stream(obj)
else
obj
end
end
private
################################################################################
# reads a PDF dict from the buffer and converts it to a Ruby Hash.
def dictionary
dict = {}
loop do
key = parse_token
break if key.kind_of?(Token) and key == ">>"
raise MalformedPDFError, "Dictionary key (#{key.inspect}) is not a name" unless key.kind_of?(Symbol)
value = parse_token
value.kind_of?(Token) and Error.str_assert_not(value, ">>")
dict[key] = value
end
dict
end
################################################################################
# reads a PDF name from the buffer and converts it to a Ruby Symbol
def pdf_name
tok = @buffer.token
tok = " " if tok == "" && RUBY_VERSION < "1.9"
tok.gsub!(/#([A-Fa-f0-9]{2})/) do |match|
match[1, 2].hex.chr
end
tok.to_sym
end
################################################################################
# reads a PDF array from the buffer and converts it to a Ruby Array.
def array
a = []
loop do
item = parse_token
break if item.kind_of?(Token) and item == "]"
a << item
end
a
end
################################################################################
# Reads a PDF hex string from the buffer and converts it to a Ruby String
def hex_string
str = ""
loop do
token = @buffer.token
break if token == ">"
str << token
end
# add a missing digit if required, as required by the spec
str << "0" unless str.size % 2 == 0
str.scan(/../).map {|i| i.hex.chr}.join
end
################################################################################
# Reads a PDF String from the buffer and converts it to a Ruby String
def string
str = @buffer.token
return "" if str == ")"
Error.assert_equal(parse_token, ")")
ret = ""
idx = 0
while idx < str.size
chr = str[idx,1]
jump = 1
if chr == "\\"
jump = 2
case str[idx+1, 1]
when "" then jump = 1
when "n" then chr = "\n"
when "r" then chr = "\r"
when "t" then chr = "\t"
when "b" then chr = "\b"
when "f" then chr = "\f"
when "(" then chr = "("
when ")" then chr = ")"
when "\\" then chr = "\\"
when "\n" then
chr = ""
jump = 2
else
if str[idx+1,3].match(/\d{3}/)
jump = 4
chr = str[idx+1,3].oct.chr
elsif str[idx+1,2].match(/\d{2}/)
jump = 3
chr = ("0"+str[idx+1,2]).oct.chr
elsif str[idx+1,1].match(/\d/)
jump = 2
chr = ("00"+str[idx+1,1]).oct.chr
else
jump = 1
chr = ""
end
end
elsif chr == "\r" && str[idx+1,1] == "\n"
chr = "\n"
jump = 2
elsif chr == "\n" && str[idx+1,1] == "\r"
chr = "\n"
jump = 2
elsif chr == "\r"
chr = "\n"
end
ret << chr
idx += jump
end
ret
end
################################################################################
# Decodes the contents of a PDF Stream and returns it as a Ruby String.
def stream (dict)
raise MalformedPDFError, "PDF malformed, missing stream length" unless dict.has_key?(:Length)
if @objects
length = @objects.deref(dict[:Length])
else
length = dict[:Length] || 0
end
data = @buffer.read(length, :skip_eol => true)
Error.str_assert(parse_token, "endstream")
Error.str_assert(parse_token, "endobj")
PDF::Reader::Stream.new(dict, data)
end
################################################################################
end
################################################################################
end
################################################################################