File: integration_invalid_spec.rb

package info (click to toggle)
ruby-pdf-reader 2.15.0-1
  • links: PTS, VCS
  • area: main
  • in suites: forky, sid
  • size: 33,512 kB
  • sloc: ruby: 11,959; sh: 46; makefile: 11
file content (375 lines) | stat: -rw-r--r-- 9,707 bytes parent folder | download
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
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
276
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
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
# typed: false
# coding: utf-8

# A set of integration specs that assert we raise expected errors when trying to parse PDFs that
# are invalid. Usually they have some form of corruption that we're unable to compensate for

describe PDF::Reader, "integration specs with invalid PDF files" do

  context "Empty file" do
    it "raises an exception" do
      expect {
        PDF::Reader.new(StringIO.new(""))
      }.to raise_error(PDF::Reader::MalformedPDFError)
    end
  end

  context "PDF has a content stream refers to a non-existant font" do
    let(:filename) { pdf_spec_file("content_stream_refers_to_invalid_font") }

    it "raises an exception" do
      expect {
        reader = PDF::Reader.new(filename)
        reader.page(1).text
      }.to raise_error(PDF::Reader::MalformedPDFError)
    end
  end

  context "Malformed PDF" do
    let(:filename) { pdf_spec_file("trailer_root_is_not_a_dict") }

    it "raises an exception if trailer Root is not a dict" do
      PDF::Reader.open(filename) do |reader|
        expect { reader.page(1) }.to raise_error(PDF::Reader::MalformedPDFError)
      end
    end
  end

  context "PDF with missing page data" do
    let(:filename) { pdf_spec_file("invalid_pages") }

    it "raises a MalformedPDFError when an InvalidPageError is raised internally" do
      PDF::Reader.open(filename) do |reader|
        expect { reader.pages }.to raise_error(PDF::Reader::MalformedPDFError)
      end
    end
  end

  context "PDF that has a content stream with a broken string" do
    let(:filename) { pdf_spec_file("broken_string") }

    # this file used to get us into a hard, endless loop. Make sure that doesn't still happen
    it "doesn't hang when extracting doc info" do
      Timeout::timeout(3) do
        expect {
          reader = PDF::Reader.new(filename)
          reader.info
        }.to raise_error(PDF::Reader::MalformedPDFError)
      end
    end
  end

  context "gh-217" do
    let(:filename) { pdf_spec_file("gh-217") }

    it "raises MalformedPDFError when parsed" do
      expect {
        parse_pdf(filename)
      }.to raise_error(PDF::Reader::MalformedPDFError)
    end
  end

  context "gh-222" do
    let(:filename) { pdf_spec_file("gh-222") }

    it "raises MalformedPDFError when parsed" do
      expect {
        parse_pdf(filename)
      }.to raise_error(PDF::Reader::MalformedPDFError)
    end
  end

  # The top level Pages object is corrupted and has no Count or Type key
  context "gh-223" do
    let(:filename) { pdf_spec_file("gh-223") }

    it "parses without error" do
      expect {
        parse_pdf(filename)
      }.to_not raise_error
    end

    it "has zero pages" do
      PDF::Reader.open(filename) do |reader|
        expect(reader.page_count).to eq 0
        expect(reader.pages).to eq []
      end
    end
  end

  context "gh-224" do
    let(:filename) { pdf_spec_file("gh-224") }

    it "raises MalformedPDFError when parsed" do
      expect {
        parse_pdf(filename)
      }.to raise_error(PDF::Reader::MalformedPDFError)
    end
  end

  context "gh-227" do
    let(:filename) { pdf_spec_file("gh-227") }

    it "raises MalformedPDFError when parsed" do
      expect {
        parse_pdf(filename)
      }.to raise_error(PDF::Reader::MalformedPDFError)
    end
  end

  context "gh-228" do
    let(:filename) { pdf_spec_file("gh-228") }

    it "raises MalformedPDFError when parsed" do
      expect {
        parse_pdf(filename)
      }.to raise_error(PDF::Reader::MalformedPDFError)
    end
  end

  context "gh-229" do
    let(:filename) { pdf_spec_file("gh-229") }

    it "raises MalformedPDFError when parsed" do
      expect {
        parse_pdf(filename)
      }.to raise_error(PDF::Reader::MalformedPDFError)
    end
  end

  context "gh-230" do
    let(:filename) { pdf_spec_file("gh-230") }

    it "raises MalformedPDFError when parsed" do
      expect {
        parse_pdf(filename)
      }.to raise_error(PDF::Reader::MalformedPDFError)
    end
  end

  context "gh-231" do
    let(:filename) { pdf_spec_file("gh-231") }

    it "raises MalformedPDFError when parsed" do
      expect {
        parse_pdf(filename)
      }.to raise_error(PDF::Reader::MalformedPDFError)
    end
  end

  context "gh-232" do
    let(:filename) { pdf_spec_file("gh-232") }

    it "raises MalformedPDFError when parsed" do
      expect {
        parse_pdf(filename)
      }.to raise_error(PDF::Reader::MalformedPDFError)
    end
  end

  context "gh-234" do
    let(:filename) { pdf_spec_file("gh-234") }

    it "raises MalformedPDFError when parsed" do
      expect {
        parse_pdf(filename)
      }.to raise_error(PDF::Reader::MalformedPDFError)
    end
  end

  context "gh-235" do
    let(:filename) { pdf_spec_file("gh-235") }

    it "raises MalformedPDFError when parsed" do
      expect {
        parse_pdf(filename)
      }.to raise_error(PDF::Reader::MalformedPDFError)
    end
  end

  context "gh-236" do
    let(:filename) { pdf_spec_file("gh-236") }

    it "raises MalformedPDFError when parsed" do
      expect {
        parse_pdf(filename)
      }.to raise_error(PDF::Reader::MalformedPDFError)
    end
  end

  context "gh-237" do
    let(:filename) { pdf_spec_file("gh-237") }

    it "raises MalformedPDFError when parsed" do
      expect {
        parse_pdf(filename)
      }.to raise_error(PDF::Reader::MalformedPDFError)
    end
  end

  context "gh-238" do
    let(:filename) { pdf_spec_file("gh-238") }

    it "raises MalformedPDFError when parsed" do
      expect {
        parse_pdf(filename)
      }.to raise_error(PDF::Reader::MalformedPDFError)
    end
  end

  context "gh-239" do
    let(:filename) { pdf_spec_file("gh-239") }

    it "raises MalformedPDFError when parsed" do
      expect {
        parse_pdf(filename)
      }.to raise_error(PDF::Reader::MalformedPDFError)
    end
  end

  context "gh-240" do
    let(:filename) { pdf_spec_file("gh-240") }

    it "raises MalformedPDFError when parsed" do
      expect {
        parse_pdf(filename)
      }.to raise_error(PDF::Reader::MalformedPDFError)
    end
  end

  context "gh-241" do
    let(:filename) { pdf_spec_file("gh-241") }

    it "raises MalformedPDFError when parsed" do
      expect {
        parse_pdf(filename)
      }.to raise_error(PDF::Reader::MalformedPDFError)
    end
  end

  context "gh-242" do
    let(:filename) { pdf_spec_file("gh-242") }

    it "raises MalformedPDFError when parsed" do
      expect {
        parse_pdf(filename)
      }.to raise_error(PDF::Reader::MalformedPDFError)
    end
  end

  # This one raised an unexpected exception in v2.0.0, but since v2.6.0 (and PR #372) it works
  # without error
  context "gh-243" do
    let(:filename) { pdf_spec_file("gh-243") }

    it "raises MalformedPDFError when parsed" do
      expect {
        parse_pdf(filename)
      }.to_not raise_error
    end
  end

  # This one raised an unexpected exception in v2.0.0, but since v2.4.0 (and PR #309) it works
  # without error
  context "gh-244" do
    let(:filename) { pdf_spec_file("gh-244") }

    it "raises MalformedPDFError when parsed" do
      expect {
        parse_pdf(filename)
      }.to_not raise_error
    end
  end

  # This encrypted PDF declares an invalid key length. It's not really that we don't support a
  # feature - we'll never support an invalid key length. We raise an unsupported fature error
  # anyway.
  context "gh-245" do
    let(:filename) { pdf_spec_file("gh-245") }

    it "raises MalformedPDFError when parsed" do
      expect {
        parse_pdf(filename)
      }.to raise_error(PDF::Reader::UnsupportedFeatureError)
    end
  end

  context "negative-xref-offset.pdf" do
    let(:filename) { pdf_spec_file("negative-xref-offset") }

    it "raises MalformedPDFError when parsed" do
      expect {
        parse_pdf(filename)
      }.to raise_error(PDF::Reader::MalformedPDFError)
    end
  end

  context "content_stream_wrong_args.pdf" do
    let(:filename) { pdf_spec_file("content_stream_wrong_args") }

    it "raises MalformedPDFError when parsed" do
      expect {
        parse_pdf(filename)
      }.to raise_error(PDF::Reader::MalformedPDFError)
    end
  end

  context "xref_offset_too_low.pdf" do
    let(:filename) { pdf_spec_file("xref_offset_too_low") }

    it "compensates for the error and can extract the paage text" do
      expect {
        parse_pdf(filename)
      }.to_not raise_error

      PDF::Reader.open(filename) do |pdf|
        expect(pdf.page(1).text).to eql(
          "The xref offset for the root object (obj 2) is a few bytes too low"
        )
      end
    end
  end

  context "stream_missing_endobj.pdf" do
    let(:filename) { pdf_spec_file("stream_missing_endobj") }

    it "compensates for the error and can extract the paage text" do
      expect {
        parse_pdf(filename)
      }.to_not raise_error

      PDF::Reader.open(filename) do |pdf|
        expect(pdf.page(1).text).to eql(
          "Object 4 (content stream) is missing the endobj token"
        )
      end
    end
  end

  context "loop-in-page-ancestors.pdf" do
    let(:filename) { pdf_spec_file("loop-in-page-ancestors") }

    it "detects the loop and raises an exception" do
      expect {
        parse_pdf(filename)
      }.to raise_error(PDF::Reader::MalformedPDFError, "loop found in ancestor path")
    end
  end

  # a very basic sanity check that we can open this file and extract interesting data
  def parse_pdf(filename)
    PDF::Reader.open(filename) do |reader|
      reader.pdf_version
      reader.info
      reader.metadata
      reader.objects
      reader.page_count

      reader.pages.each do |page|
        page.fonts.to_s
        page.text.to_s
        page.raw_content.to_s
      end
    end
  end
end