Class: Podoff::Document

Inherits:
Object
  • Object
show all
Defined in:
lib/podoff.rb

Instance Attribute Summary collapse

Class Method Summary collapse

Instance Method Summary collapse

Constructor Details

#initialize(s, encoding) ⇒ Document

Returns a new instance of Document.



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
 
# File 'lib/podoff.rb', line 70

def initialize(s, encoding)

  fail ArgumentError.new('not a PDF file') \
    unless s.match(/\A%PDF-\d+\.\d+\s/)

  @encoding = encoding

  @scanner = ::StringScanner.new(s)
  @version = nil
  @xref = nil
  @objs = {}
  @obj_counters = {}
  @root = nil

  @additions = {}

  @version = @scanner.scan(/%PDF-\d+\.\d+/)

  loop do

    i = @scanner.skip_until(
      /(startxref\s+\d+|\d+\s+\d+\s+obj|\/Root\s+\d+\s+\d+\s+R)/)

    m = @scanner.matched
    break unless m

    if m[0] == 's'
      @xref = m.split(' ').last.to_i
    elsif m[0] == '/'
      @root = extract_ref(m)
    else
      obj = Podoff::Obj.extract(self)
      @objs[obj.ref] = obj
      @obj_counters[obj.ref] = (@obj_counters[obj.ref] || 0) + 1
    end
  end

  if @root == nil
    @scanner.pos = 0
    loop do
      i = @scanner.skip_until(/\/Root\s+\d+\s+\d+\s+R/)
      break unless @scanner.matched
      @root = extract_ref(@scanner.matched)
    end
  end
end

Instance Attribute Details

#additions ⇒ Object (readonly)

Returns the value of attribute additions.



68
69
70
 
# File 'lib/podoff.rb', line 68

def additions
  @additions
end

#encoding ⇒ Object (readonly)

Returns the value of attribute encoding.



59
60
61
 
# File 'lib/podoff.rb', line 59

def encoding
  @encoding
end

#obj_counters ⇒ Object (readonly)

Returns the value of attribute obj_counters.



65
66
67
 
# File 'lib/podoff.rb', line 65

def obj_counters
  @obj_counters
end

#objs ⇒ Object (readonly)

Returns the value of attribute objs.



64
65
66
 
# File 'lib/podoff.rb', line 64

def objs
  @objs
end

#root ⇒ Object (readonly)

Returns the value of attribute root.



66
67
68
 
# File 'lib/podoff.rb', line 66

def root
  @root
end

#scanner ⇒ Object (readonly)

Returns the value of attribute scanner.



61
62
63
 
# File 'lib/podoff.rb', line 61

def scanner
  @scanner
end

#version ⇒ Object (readonly)

Returns the value of attribute version.



62
63
64
 
# File 'lib/podoff.rb', line 62

def version
  @version
end

#xref ⇒ Object (readonly)

Returns the value of attribute xref.



63
64
65
 
# File 'lib/podoff.rb', line 63

def xref
  @xref
end

Class Method Details

.load(path, encoding) ⇒ Object 



46
47
48
49
50
51
52
 
# File 'lib/podoff.rb', line 46

def self.load(path, encoding)

  Podoff::Document.new(
    File.open(path, 'rb:' + encoding) { |f| f.read },
    encoding
  )
end

.parse(s) ⇒ Object 



54
55
56
57
 
# File 'lib/podoff.rb', line 54

def self.parse(s)

  Podoff::Document.new(s)
end

Instance Method Details

#add(obj) ⇒ Object 



183
184
185
186
187
188
189
 
# File 'lib/podoff.rb', line 183

def add(obj)

  @objs[obj.ref] = obj
  @additions[obj.ref] = obj

  obj
end

#add_base_font(name) ⇒ Object 



191
192
193
194
195
196
197
198
199
 
# File 'lib/podoff.rb', line 191

def add_base_font(name)

  name = name[1..-1] if name[0] == '/'

  r = new_ref
  s = "#{r} obj <</Type /Font /Subtype /Type1 /BaseFont /#{name}>> endobj"

  add(Obj.new(self, r, source: s))
end

#add_stream(src = nil, &block) ⇒ Object 



201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
 
# File 'lib/podoff.rb', line 201

def add_stream(src=nil, &block)

  ref = new_ref

  src =
    src &&
    [
      "#{ref} obj",
      "<< /Length #{src.size} >>\nstream\n#{src}\nendstream",
      "endobj"
    ].join("\n")

  str =
    src ?
    nil :
    make_stream(&block)

  obj = add(Obj.new(self, ref, source: src, stream: str))

  str || obj
end

#dup ⇒ Object 



127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
 
# File 'lib/podoff.rb', line 127

def dup

  o = self

  self.class.allocate.instance_eval do

    @encoding = o.encoding

    @scanner = ::StringScanner.new(o.source)
    @xref = o.xref

    @objs = o.objs.inject({}) { |h, (k, v)| h[k] = v.dup(self); h }
    @obj_counters = o.obj_counters.dup

    @root = o.root

    @additions =
      o.additions.inject({}) { |h, (k, v)| h[k] = v.dup(self); h }

    self
  end
end

#new_ref ⇒ Object 



176
177
178
179
180
181
 
# File 'lib/podoff.rb', line 176

def new_ref

  "#{
    @objs.keys.inject(-1) { |i, r| [ i, r.split(' ').first.to_i ].max } + 1
  } 0"
end

#page(index) ⇒ Object 



165
166
167
168
169
170
171
172
173
174
 
# File 'lib/podoff.rb', line 165

def page(index)

  if index < 0
    pages[index]
  elsif index == 0
    nil
  else
    pages[index - 1]
  end
end

#pages ⇒ Object 



150
151
152
153
154
155
156
157
158
159
160
161
162
163
 
# File 'lib/podoff.rb', line 150

def pages

  #@objs.values.select { |o| o.type == '/Page' }

  ps = @objs.values.find { |o| o.type == '/Pages' }

  fail ArgumentError.new(
    "no /Pages, the PDF is not usable by Podoff as is, you have to do " +
    "`qpdf --object-streams=disable original.pdf unpacked.pdf` " +
    "and use unpacked.pdf instead of original.pdf"
  ) unless ps

  extract_refs(ps.attributes[:kids]).collect { |r| @objs[r] }
end

#re_add(obj_or_ref) ⇒ Object 



223
224
225
226
227
228
229
230
 
# File 'lib/podoff.rb', line 223

def re_add(obj_or_ref)

  obj = obj_or_ref.is_a?(String) ? @objs[obj_or_ref] : obj_or_ref

  obj = obj.replicate unless obj.replica?

  add(obj)
end

#rewrite(path = :string, encoding = nil) ⇒ Object 



277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
 
# File 'lib/podoff.rb', line 277

def rewrite(path=:string, encoding=nil)

  encoding ||= @encoding

  f =
    case path
      when :string, '-' then StringIO.new
      when String then File.open(path, 'wb')
      else path
    end
  f.set_encoding(encoding)

  v = source.match(/%PDF-\d+\.\d+/)[0]
  f.write(v)
  f.write("\n")

  pointers = {}

  objs.keys.sort.each do |k|
    pointers[k.split(' ').first.to_i] = f.pos
    f.write(objs[k].source.force_encoding(encoding))
    f.write("\n")
  end

  xref = f.pos

  write_xref(f, pointers)

  f.write("trailer\n")
  f.write("<<\n")
  f.write("/Size #{objs.size + 1}\n")
  f.write("/Root #{root} R\n")
  f.write(">>\n")
  f.write("startxref #{xref}\n")
  f.write("%%EOF\n")

  f.close if path.is_a?(String) || path.is_a?(Symbol)

  f.is_a?(StringIO) ? f.string : nil
end

#source ⇒ Object 



117
118
119
120
 
# File 'lib/podoff.rb', line 117

def source

  @scanner.string
end

#updated? ⇒ Boolean

Returns:

  • (Boolean) 


122
123
124
125
 
# File 'lib/podoff.rb', line 122

def updated?

  @additions.any?
end

#write(path = :string, encoding = nil) ⇒ Object 



232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
 
# File 'lib/podoff.rb', line 232

def write(path=:string, encoding=nil)

  encoding ||= @encoding

  f =
    case path
      when :string, '-' then StringIO.new
      when String then File.open(path, 'wb')
      else path
    end
  f.set_encoding(encoding) # internal encoding: nil
  #f.set_encoding(encoding, encoding)

  f.write(source)

  if @additions.any?

    pointers = {}

    @additions.values.each do |o|
      f.write("\n")
      pointers[o.ref.split(' ').first.to_i] = f.pos
      f.write(o.to_s.force_encoding(encoding))
    end
    f.write("\n\n")

    xref = f.pos

    write_xref(f, pointers)

    f.write("trailer\n")
    f.write("<<\n")
    f.write("/Prev #{self.xref}\n")
    f.write("/Size #{objs.size + 1}\n")
    f.write("/Root #{root} R\n")
    f.write(">>\n")
    f.write("startxref #{xref}\n")
    f.write("%%EOF\n")
  end

  f.close if path.is_a?(String) || path.is_a?(Symbol)

  f.is_a?(StringIO) ? f.string : nil
end