hexapdf 0.17.1 → 0.17.2
Sign up to get free protection for your applications and to get access to all the features.
- checksums.yaml +4 -4
- data/CHANGELOG.md +1024 -0
- data/LICENSE +29 -0
- data/README.md +129 -0
- data/Rakefile +109 -0
- data/agpl-3.0.txt +661 -0
- data/examples/001-hello_world.rb +16 -0
- data/examples/002-graphics.rb +275 -0
- data/examples/003-arcs.rb +50 -0
- data/examples/004-optimizing.rb +23 -0
- data/examples/005-merging.rb +27 -0
- data/examples/006-standard_pdf_fonts.rb +73 -0
- data/examples/007-truetype.rb +42 -0
- data/examples/008-show_char_bboxes.rb +55 -0
- data/examples/009-text_layouter_alignment.rb +47 -0
- data/examples/010-text_layouter_inline_boxes.rb +64 -0
- data/examples/011-text_layouter_line_wrapping.rb +57 -0
- data/examples/012-text_layouter_styling.rb +122 -0
- data/examples/013-text_layouter_shapes.rb +176 -0
- data/examples/014-text_in_polygon.rb +60 -0
- data/examples/015-boxes.rb +76 -0
- data/examples/016-frame_automatic_box_placement.rb +90 -0
- data/examples/017-frame_text_flow.rb +60 -0
- data/examples/018-composer.rb +44 -0
- data/examples/019-acro_form.rb +88 -0
- data/examples/emoji-smile.png +0 -0
- data/examples/emoji-wink.png +0 -0
- data/examples/machupicchu.jpg +0 -0
- data/lib/hexapdf/content/graphic_object/endpoint_arc.rb +66 -0
- data/lib/hexapdf/content/graphic_object/geom2d.rb +13 -0
- data/lib/hexapdf/version.rb +1 -1
- data/test/data/aes-test-vectors/CBCGFSbox-128-decrypt.data.gz +0 -0
- data/test/data/aes-test-vectors/CBCGFSbox-128-encrypt.data.gz +0 -0
- data/test/data/aes-test-vectors/CBCGFSbox-192-decrypt.data.gz +0 -0
- data/test/data/aes-test-vectors/CBCGFSbox-192-encrypt.data.gz +0 -0
- data/test/data/aes-test-vectors/CBCGFSbox-256-decrypt.data.gz +0 -0
- data/test/data/aes-test-vectors/CBCGFSbox-256-encrypt.data.gz +0 -0
- data/test/data/aes-test-vectors/CBCKeySbox-128-decrypt.data.gz +0 -0
- data/test/data/aes-test-vectors/CBCKeySbox-128-encrypt.data.gz +0 -0
- data/test/data/aes-test-vectors/CBCKeySbox-192-decrypt.data.gz +0 -0
- data/test/data/aes-test-vectors/CBCKeySbox-192-encrypt.data.gz +0 -0
- data/test/data/aes-test-vectors/CBCKeySbox-256-decrypt.data.gz +0 -0
- data/test/data/aes-test-vectors/CBCKeySbox-256-encrypt.data.gz +0 -0
- data/test/data/aes-test-vectors/CBCVarKey-128-decrypt.data.gz +0 -0
- data/test/data/aes-test-vectors/CBCVarKey-128-encrypt.data.gz +0 -0
- data/test/data/aes-test-vectors/CBCVarKey-192-decrypt.data.gz +0 -0
- data/test/data/aes-test-vectors/CBCVarKey-192-encrypt.data.gz +0 -0
- data/test/data/aes-test-vectors/CBCVarKey-256-decrypt.data.gz +0 -0
- data/test/data/aes-test-vectors/CBCVarKey-256-encrypt.data.gz +0 -0
- data/test/data/aes-test-vectors/CBCVarTxt-128-decrypt.data.gz +0 -0
- data/test/data/aes-test-vectors/CBCVarTxt-128-encrypt.data.gz +0 -0
- data/test/data/aes-test-vectors/CBCVarTxt-192-decrypt.data.gz +0 -0
- data/test/data/aes-test-vectors/CBCVarTxt-192-encrypt.data.gz +0 -0
- data/test/data/aes-test-vectors/CBCVarTxt-256-decrypt.data.gz +0 -0
- data/test/data/aes-test-vectors/CBCVarTxt-256-encrypt.data.gz +0 -0
- data/test/data/fonts/Ubuntu-Title.ttf +0 -0
- data/test/data/images/cmyk.jpg +0 -0
- data/test/data/images/fillbytes.jpg +0 -0
- data/test/data/images/gray.jpg +0 -0
- data/test/data/images/greyscale-1bit.png +0 -0
- data/test/data/images/greyscale-2bit.png +0 -0
- data/test/data/images/greyscale-4bit.png +0 -0
- data/test/data/images/greyscale-8bit.png +0 -0
- data/test/data/images/greyscale-alpha-8bit.png +0 -0
- data/test/data/images/greyscale-trns-8bit.png +0 -0
- data/test/data/images/greyscale-with-gamma1.0.png +0 -0
- data/test/data/images/greyscale-with-gamma1.5.png +0 -0
- data/test/data/images/indexed-1bit.png +0 -0
- data/test/data/images/indexed-2bit.png +0 -0
- data/test/data/images/indexed-4bit.png +0 -0
- data/test/data/images/indexed-8bit.png +0 -0
- data/test/data/images/indexed-alpha-4bit.png +0 -0
- data/test/data/images/indexed-alpha-8bit.png +0 -0
- data/test/data/images/rgb.jpg +0 -0
- data/test/data/images/truecolour-8bit.png +0 -0
- data/test/data/images/truecolour-alpha-8bit.png +0 -0
- data/test/data/images/truecolour-gama-chrm-8bit.png +0 -0
- data/test/data/images/truecolour-srgb-8bit.png +0 -0
- data/test/data/images/ycck.jpg +0 -0
- data/test/data/minimal.pdf +44 -0
- data/test/data/standard-security-handler/README +9 -0
- data/test/data/standard-security-handler/bothpwd-aes-128bit-V4.pdf +44 -0
- data/test/data/standard-security-handler/bothpwd-aes-256bit-V5.pdf +0 -0
- data/test/data/standard-security-handler/bothpwd-arc4-128bit-V2.pdf +43 -0
- data/test/data/standard-security-handler/bothpwd-arc4-128bit-V4.pdf +43 -0
- data/test/data/standard-security-handler/bothpwd-arc4-40bit-V1.pdf +0 -0
- data/test/data/standard-security-handler/nopwd-aes-128bit-V4.pdf +43 -0
- data/test/data/standard-security-handler/nopwd-aes-256bit-V5.pdf +0 -0
- data/test/data/standard-security-handler/nopwd-arc4-128bit-V2.pdf +43 -0
- data/test/data/standard-security-handler/nopwd-arc4-128bit-V4.pdf +43 -0
- data/test/data/standard-security-handler/nopwd-arc4-40bit-V1.pdf +43 -0
- data/test/data/standard-security-handler/ownerpwd-aes-128bit-V4.pdf +0 -0
- data/test/data/standard-security-handler/ownerpwd-aes-256bit-V5.pdf +43 -0
- data/test/data/standard-security-handler/ownerpwd-arc4-128bit-V2.pdf +43 -0
- data/test/data/standard-security-handler/ownerpwd-arc4-128bit-V4.pdf +43 -0
- data/test/data/standard-security-handler/ownerpwd-arc4-40bit-V1.pdf +43 -0
- data/test/data/standard-security-handler/userpwd-aes-128bit-V4.pdf +43 -0
- data/test/data/standard-security-handler/userpwd-aes-256bit-V5.pdf +43 -0
- data/test/data/standard-security-handler/userpwd-arc4-128bit-V2.pdf +0 -0
- data/test/data/standard-security-handler/userpwd-arc4-128bit-V4.pdf +0 -0
- data/test/data/standard-security-handler/userpwd-arc4-40bit-V1.pdf +43 -0
- data/test/hexapdf/common_tokenizer_tests.rb +236 -0
- data/test/hexapdf/content/common.rb +39 -0
- data/test/hexapdf/content/graphic_object/test_arc.rb +102 -0
- data/test/hexapdf/content/graphic_object/test_endpoint_arc.rb +90 -0
- data/test/hexapdf/content/graphic_object/test_geom2d.rb +79 -0
- data/test/hexapdf/content/graphic_object/test_solid_arc.rb +86 -0
- data/test/hexapdf/content/test_canvas.rb +1279 -0
- data/test/hexapdf/content/test_color_space.rb +176 -0
- data/test/hexapdf/content/test_graphics_state.rb +151 -0
- data/test/hexapdf/content/test_operator.rb +619 -0
- data/test/hexapdf/content/test_parser.rb +99 -0
- data/test/hexapdf/content/test_processor.rb +163 -0
- data/test/hexapdf/content/test_transformation_matrix.rb +64 -0
- data/test/hexapdf/document/test_files.rb +72 -0
- data/test/hexapdf/document/test_fonts.rb +60 -0
- data/test/hexapdf/document/test_images.rb +72 -0
- data/test/hexapdf/document/test_pages.rb +130 -0
- data/test/hexapdf/encryption/common.rb +87 -0
- data/test/hexapdf/encryption/test_aes.rb +129 -0
- data/test/hexapdf/encryption/test_arc4.rb +39 -0
- data/test/hexapdf/encryption/test_fast_aes.rb +17 -0
- data/test/hexapdf/encryption/test_fast_arc4.rb +12 -0
- data/test/hexapdf/encryption/test_identity.rb +21 -0
- data/test/hexapdf/encryption/test_ruby_aes.rb +23 -0
- data/test/hexapdf/encryption/test_ruby_arc4.rb +20 -0
- data/test/hexapdf/encryption/test_security_handler.rb +380 -0
- data/test/hexapdf/encryption/test_standard_security_handler.rb +322 -0
- data/test/hexapdf/filter/common.rb +53 -0
- data/test/hexapdf/filter/test_ascii85_decode.rb +59 -0
- data/test/hexapdf/filter/test_ascii_hex_decode.rb +38 -0
- data/test/hexapdf/filter/test_crypt.rb +21 -0
- data/test/hexapdf/filter/test_encryption.rb +24 -0
- data/test/hexapdf/filter/test_flate_decode.rb +44 -0
- data/test/hexapdf/filter/test_lzw_decode.rb +52 -0
- data/test/hexapdf/filter/test_predictor.rb +219 -0
- data/test/hexapdf/filter/test_run_length_decode.rb +32 -0
- data/test/hexapdf/font/cmap/test_parser.rb +102 -0
- data/test/hexapdf/font/cmap/test_writer.rb +66 -0
- data/test/hexapdf/font/encoding/test_base.rb +45 -0
- data/test/hexapdf/font/encoding/test_difference_encoding.rb +29 -0
- data/test/hexapdf/font/encoding/test_glyph_list.rb +59 -0
- data/test/hexapdf/font/encoding/test_zapf_dingbats_encoding.rb +16 -0
- data/test/hexapdf/font/test_cmap.rb +104 -0
- data/test/hexapdf/font/test_encoding.rb +27 -0
- data/test/hexapdf/font/test_invalid_glyph.rb +34 -0
- data/test/hexapdf/font/test_true_type_wrapper.rb +186 -0
- data/test/hexapdf/font/test_type1_wrapper.rb +107 -0
- data/test/hexapdf/font/true_type/common.rb +17 -0
- data/test/hexapdf/font/true_type/table/common.rb +27 -0
- data/test/hexapdf/font/true_type/table/test_cmap.rb +47 -0
- data/test/hexapdf/font/true_type/table/test_cmap_subtable.rb +141 -0
- data/test/hexapdf/font/true_type/table/test_directory.rb +30 -0
- data/test/hexapdf/font/true_type/table/test_glyf.rb +58 -0
- data/test/hexapdf/font/true_type/table/test_head.rb +56 -0
- data/test/hexapdf/font/true_type/table/test_hhea.rb +26 -0
- data/test/hexapdf/font/true_type/table/test_hmtx.rb +30 -0
- data/test/hexapdf/font/true_type/table/test_kern.rb +61 -0
- data/test/hexapdf/font/true_type/table/test_loca.rb +33 -0
- data/test/hexapdf/font/true_type/table/test_maxp.rb +50 -0
- data/test/hexapdf/font/true_type/table/test_name.rb +76 -0
- data/test/hexapdf/font/true_type/table/test_os2.rb +55 -0
- data/test/hexapdf/font/true_type/table/test_post.rb +78 -0
- data/test/hexapdf/font/true_type/test_builder.rb +42 -0
- data/test/hexapdf/font/true_type/test_font.rb +116 -0
- data/test/hexapdf/font/true_type/test_optimizer.rb +26 -0
- data/test/hexapdf/font/true_type/test_subsetter.rb +73 -0
- data/test/hexapdf/font/true_type/test_table.rb +48 -0
- data/test/hexapdf/font/type1/common.rb +6 -0
- data/test/hexapdf/font/type1/test_afm_parser.rb +65 -0
- data/test/hexapdf/font/type1/test_font.rb +104 -0
- data/test/hexapdf/font/type1/test_font_metrics.rb +22 -0
- data/test/hexapdf/font/type1/test_pfb_parser.rb +37 -0
- data/test/hexapdf/font_loader/test_from_configuration.rb +43 -0
- data/test/hexapdf/font_loader/test_from_file.rb +36 -0
- data/test/hexapdf/font_loader/test_standard14.rb +33 -0
- data/test/hexapdf/image_loader/test_jpeg.rb +93 -0
- data/test/hexapdf/image_loader/test_pdf.rb +47 -0
- data/test/hexapdf/image_loader/test_png.rb +259 -0
- data/test/hexapdf/layout/test_box.rb +154 -0
- data/test/hexapdf/layout/test_frame.rb +350 -0
- data/test/hexapdf/layout/test_image_box.rb +73 -0
- data/test/hexapdf/layout/test_inline_box.rb +71 -0
- data/test/hexapdf/layout/test_line.rb +206 -0
- data/test/hexapdf/layout/test_style.rb +790 -0
- data/test/hexapdf/layout/test_text_box.rb +140 -0
- data/test/hexapdf/layout/test_text_fragment.rb +375 -0
- data/test/hexapdf/layout/test_text_layouter.rb +758 -0
- data/test/hexapdf/layout/test_text_shaper.rb +62 -0
- data/test/hexapdf/layout/test_width_from_polygon.rb +109 -0
- data/test/hexapdf/task/test_dereference.rb +51 -0
- data/test/hexapdf/task/test_optimize.rb +162 -0
- data/test/hexapdf/test_composer.rb +258 -0
- data/test/hexapdf/test_configuration.rb +93 -0
- data/test/hexapdf/test_data_dir.rb +32 -0
- data/test/hexapdf/test_dictionary.rb +340 -0
- data/test/hexapdf/test_dictionary_fields.rb +269 -0
- data/test/hexapdf/test_document.rb +641 -0
- data/test/hexapdf/test_filter.rb +100 -0
- data/test/hexapdf/test_importer.rb +106 -0
- data/test/hexapdf/test_object.rb +258 -0
- data/test/hexapdf/test_parser.rb +645 -0
- data/test/hexapdf/test_pdf_array.rb +169 -0
- data/test/hexapdf/test_rectangle.rb +73 -0
- data/test/hexapdf/test_reference.rb +50 -0
- data/test/hexapdf/test_revision.rb +188 -0
- data/test/hexapdf/test_revisions.rb +196 -0
- data/test/hexapdf/test_serializer.rb +195 -0
- data/test/hexapdf/test_stream.rb +274 -0
- data/test/hexapdf/test_tokenizer.rb +80 -0
- data/test/hexapdf/test_type.rb +18 -0
- data/test/hexapdf/test_writer.rb +140 -0
- data/test/hexapdf/test_xref_section.rb +61 -0
- data/test/hexapdf/type/acro_form/test_appearance_generator.rb +795 -0
- data/test/hexapdf/type/acro_form/test_button_field.rb +308 -0
- data/test/hexapdf/type/acro_form/test_choice_field.rb +220 -0
- data/test/hexapdf/type/acro_form/test_field.rb +259 -0
- data/test/hexapdf/type/acro_form/test_form.rb +357 -0
- data/test/hexapdf/type/acro_form/test_signature_field.rb +38 -0
- data/test/hexapdf/type/acro_form/test_text_field.rb +201 -0
- data/test/hexapdf/type/acro_form/test_variable_text_field.rb +88 -0
- data/test/hexapdf/type/actions/test_launch.rb +24 -0
- data/test/hexapdf/type/actions/test_uri.rb +23 -0
- data/test/hexapdf/type/annotations/test_markup_annotation.rb +22 -0
- data/test/hexapdf/type/annotations/test_text.rb +34 -0
- data/test/hexapdf/type/annotations/test_widget.rb +225 -0
- data/test/hexapdf/type/test_annotation.rb +97 -0
- data/test/hexapdf/type/test_catalog.rb +48 -0
- data/test/hexapdf/type/test_cid_font.rb +61 -0
- data/test/hexapdf/type/test_file_specification.rb +141 -0
- data/test/hexapdf/type/test_font.rb +67 -0
- data/test/hexapdf/type/test_font_descriptor.rb +61 -0
- data/test/hexapdf/type/test_font_simple.rb +176 -0
- data/test/hexapdf/type/test_font_true_type.rb +31 -0
- data/test/hexapdf/type/test_font_type0.rb +120 -0
- data/test/hexapdf/type/test_font_type1.rb +142 -0
- data/test/hexapdf/type/test_font_type3.rb +26 -0
- data/test/hexapdf/type/test_form.rb +120 -0
- data/test/hexapdf/type/test_image.rb +261 -0
- data/test/hexapdf/type/test_info.rb +9 -0
- data/test/hexapdf/type/test_object_stream.rb +117 -0
- data/test/hexapdf/type/test_page.rb +598 -0
- data/test/hexapdf/type/test_page_tree_node.rb +315 -0
- data/test/hexapdf/type/test_resources.rb +209 -0
- data/test/hexapdf/type/test_trailer.rb +116 -0
- data/test/hexapdf/type/test_xref_stream.rb +143 -0
- data/test/hexapdf/utils/test_bit_field.rb +63 -0
- data/test/hexapdf/utils/test_bit_stream.rb +69 -0
- data/test/hexapdf/utils/test_graphics_helpers.rb +37 -0
- data/test/hexapdf/utils/test_lru_cache.rb +22 -0
- data/test/hexapdf/utils/test_object_hash.rb +120 -0
- data/test/hexapdf/utils/test_pdf_doc_encoding.rb +18 -0
- data/test/hexapdf/utils/test_sorted_tree_node.rb +239 -0
- data/test/test_helper.rb +58 -0
- metadata +263 -3
@@ -0,0 +1,645 @@
|
|
1
|
+
# -*- encoding: utf-8 -*-
|
2
|
+
|
3
|
+
require 'test_helper'
|
4
|
+
require 'hexapdf/document'
|
5
|
+
require 'hexapdf/parser'
|
6
|
+
require 'stringio'
|
7
|
+
|
8
|
+
describe HexaPDF::Parser do
|
9
|
+
before do
|
10
|
+
@document = HexaPDF::Document.new
|
11
|
+
@document.config['parser.try_xref_reconstruction'] = false
|
12
|
+
@document.add(@document.wrap(10, oid: 1, gen: 0))
|
13
|
+
|
14
|
+
create_parser(<<~EOF)
|
15
|
+
%PDF-1.7
|
16
|
+
|
17
|
+
1 0 obj
|
18
|
+
10
|
19
|
+
endobj
|
20
|
+
|
21
|
+
2 0 obj
|
22
|
+
[ 5 6 <</Length 10 >> (name) <4E6F762073 686D6F7A20 6B612070
|
23
|
+
6F702E>]
|
24
|
+
endobj
|
25
|
+
|
26
|
+
3 15 obj<< /Length 1 0 R/Hallo 6/Filter /Fl/DecodeParms<<>> >>stream
|
27
|
+
Hallo PDF!endstream
|
28
|
+
endobj
|
29
|
+
|
30
|
+
4 0 obj
|
31
|
+
<</Type /XRef /Length 3 /W [1 1 1] /Index [1 1] /Size 2 >> stream
|
32
|
+
\x01\x0A\x00
|
33
|
+
endstream
|
34
|
+
endobj
|
35
|
+
|
36
|
+
xref
|
37
|
+
0 4
|
38
|
+
0000000000 65535 f
|
39
|
+
0000000010 00000 n
|
40
|
+
0000000029 00000 n
|
41
|
+
0000000000 65535 f
|
42
|
+
3 1
|
43
|
+
0000000556 00000 n
|
44
|
+
trailer
|
45
|
+
<< /Test (now) >>
|
46
|
+
startxref
|
47
|
+
308
|
48
|
+
%%EOF
|
49
|
+
EOF
|
50
|
+
end
|
51
|
+
|
52
|
+
def create_parser(str)
|
53
|
+
@parse_io = StringIO.new(str)
|
54
|
+
@parser = HexaPDF::Parser.new(@parse_io, @document)
|
55
|
+
end
|
56
|
+
|
57
|
+
describe "parse_indirect_object" do
|
58
|
+
it "reads indirect objects sequentially" do
|
59
|
+
object, oid, gen, stream = @parser.parse_indirect_object
|
60
|
+
assert_equal(1, oid)
|
61
|
+
assert_equal(0, gen)
|
62
|
+
assert_equal(10, object)
|
63
|
+
assert_nil(stream)
|
64
|
+
|
65
|
+
object, oid, gen, stream = @parser.parse_indirect_object
|
66
|
+
assert_equal(2, oid)
|
67
|
+
assert_equal(0, gen)
|
68
|
+
assert_equal([5, 6, {Length: 10}, "name", "Nov shmoz ka pop."], object)
|
69
|
+
assert_nil(stream)
|
70
|
+
|
71
|
+
object, oid, gen, stream = @parser.parse_indirect_object
|
72
|
+
assert_equal(3, oid)
|
73
|
+
assert_equal(15, gen)
|
74
|
+
assert_kind_of(HexaPDF::StreamData, stream)
|
75
|
+
assert_equal([:Fl], stream.filter)
|
76
|
+
assert_equal([{}], stream.decode_parms)
|
77
|
+
assert_equal({Length: 10, Hallo: 6, Filter: :Fl, DecodeParms: {}}, object)
|
78
|
+
end
|
79
|
+
|
80
|
+
it "handles empty indirect objects by using PDF null for them" do
|
81
|
+
create_parser("1 0 obj\nendobj")
|
82
|
+
object, * = @parser.parse_indirect_object
|
83
|
+
assert_nil(object)
|
84
|
+
end
|
85
|
+
|
86
|
+
it "handles keyword stream followed only by CR without LF" do
|
87
|
+
create_parser("1 0 obj<</Length 2>> stream\r12\nendstream endobj")
|
88
|
+
*, stream = @parser.parse_indirect_object
|
89
|
+
assert_equal('12', TestHelper.collector(stream.fiber))
|
90
|
+
end
|
91
|
+
|
92
|
+
it "handles keyword stream followed by space and CR or LF" do
|
93
|
+
create_parser("1 0 obj<</Length 2>> stream \n12\nendstream endobj")
|
94
|
+
*, stream = @parser.parse_indirect_object
|
95
|
+
assert_equal('12', TestHelper.collector(stream.fiber))
|
96
|
+
end
|
97
|
+
|
98
|
+
it "handles keyword stream followed by space and CR LF" do
|
99
|
+
create_parser("1 0 obj<</Length 2>> stream \r\n12\nendstream endobj")
|
100
|
+
*, stream = @parser.parse_indirect_object
|
101
|
+
assert_equal('12', TestHelper.collector(stream.fiber))
|
102
|
+
end
|
103
|
+
|
104
|
+
it "handles invalid indirect object value consisting of number followed by endobj without space" do
|
105
|
+
create_parser("1 0 obj 749endobj")
|
106
|
+
object, * = @parser.parse_indirect_object
|
107
|
+
assert_equal(749, object)
|
108
|
+
end
|
109
|
+
|
110
|
+
it "treats indirect objects with invalid values as null objects" do
|
111
|
+
create_parser("1 0 obj <</test ( /other (end)>> endobj")
|
112
|
+
object, * = @parser.parse_indirect_object
|
113
|
+
assert_nil(object)
|
114
|
+
end
|
115
|
+
|
116
|
+
it "recovers from a stream length value that doesn't reflect the correct length" do
|
117
|
+
create_parser("1 0 obj<</Length 4>> stream\n12endstream endobj")
|
118
|
+
obj, _, _, stream = @parser.parse_indirect_object
|
119
|
+
assert_equal(2, obj[:Length])
|
120
|
+
assert_equal('12', TestHelper.collector(stream.fiber))
|
121
|
+
end
|
122
|
+
|
123
|
+
it "recovers from an invalid stream length value" do
|
124
|
+
create_parser("1 0 obj<</Length 2 0 R>> stream\n12endstream endobj")
|
125
|
+
@document.add([5], oid: 2)
|
126
|
+
obj, _, _, stream = @parser.parse_indirect_object
|
127
|
+
assert_equal(2, obj[:Length])
|
128
|
+
assert_equal('12', TestHelper.collector(stream.fiber))
|
129
|
+
end
|
130
|
+
|
131
|
+
it "works even if the keyword endobj is missing or mangled" do
|
132
|
+
create_parser("1 0 obj<</Length 4>>5")
|
133
|
+
object, * = @parser.parse_indirect_object
|
134
|
+
assert_equal({Length: 4}, object)
|
135
|
+
create_parser("1 0 obj<</Length 4>>endobjk")
|
136
|
+
object, * = @parser.parse_indirect_object
|
137
|
+
assert_equal({Length: 4}, object)
|
138
|
+
end
|
139
|
+
|
140
|
+
it "fails if the oid, gen or 'obj' keyword is invalid" do
|
141
|
+
create_parser("a 0 obj\n5\nendobj")
|
142
|
+
exp = assert_raises(HexaPDF::MalformedPDFError) { @parser.parse_indirect_object }
|
143
|
+
assert_match(/No valid object/, exp.message)
|
144
|
+
create_parser("1 a obj\n5\nendobj")
|
145
|
+
exp = assert_raises(HexaPDF::MalformedPDFError) { @parser.parse_indirect_object }
|
146
|
+
assert_match(/No valid object/, exp.message)
|
147
|
+
create_parser("1 0 dobj\n5\nendobj")
|
148
|
+
exp = assert_raises(HexaPDF::MalformedPDFError) { @parser.parse_indirect_object }
|
149
|
+
assert_match(/No valid object/, exp.message)
|
150
|
+
end
|
151
|
+
|
152
|
+
it "fails if the value of a stream is not a dictionary" do
|
153
|
+
create_parser("1 0 obj\n(fail)\nstream\nendstream\nendobj\n")
|
154
|
+
exp = assert_raises(HexaPDF::MalformedPDFError) { @parser.parse_indirect_object }
|
155
|
+
assert_match(/stream.*dictionary/, exp.message)
|
156
|
+
end
|
157
|
+
|
158
|
+
it "fails if the 'stream' keyword isn't followed by EOL" do
|
159
|
+
create_parser("1 0 obj\n<< >>\nstream endstream\nendobj\n")
|
160
|
+
exp = assert_raises(HexaPDF::MalformedPDFError) { @parser.parse_indirect_object(0) }
|
161
|
+
assert_match(/stream.*followed by LF/, exp.message)
|
162
|
+
end
|
163
|
+
|
164
|
+
it "fails if the 'endstream' keyword is missing" do
|
165
|
+
create_parser("1 0 obj\n<< >>\nstream\nendobj\n")
|
166
|
+
exp = assert_raises(HexaPDF::MalformedPDFError) { @parser.parse_indirect_object(0) }
|
167
|
+
assert_match(/stream.*followed by.*endstream/i, exp.message)
|
168
|
+
end
|
169
|
+
|
170
|
+
describe "with strict parsing" do
|
171
|
+
before do
|
172
|
+
@document.config['parser.on_correctable_error'] = proc { true }
|
173
|
+
end
|
174
|
+
|
175
|
+
it "fails if an empty indirect object is found" do
|
176
|
+
create_parser("1 0 obj\nendobj")
|
177
|
+
exp = assert_raises(HexaPDF::MalformedPDFError) { @parser.parse_indirect_object }
|
178
|
+
assert_match(/no indirect object value/i, exp.message)
|
179
|
+
end
|
180
|
+
|
181
|
+
it "fails if keyword stream is followed only by CR without LF" do
|
182
|
+
create_parser("1 0 obj<</Length 2>> stream\r12\nendstream endobj")
|
183
|
+
exp = assert_raises(HexaPDF::MalformedPDFError) { @parser.parse_indirect_object }
|
184
|
+
assert_match(/not CR alone/, exp.message)
|
185
|
+
end
|
186
|
+
|
187
|
+
it "fails if keyword stream is followed by space and CR or LF instead of LF or CR/LF" do
|
188
|
+
create_parser("1 0 obj<</Length 2>> stream \n12\nendstream endobj")
|
189
|
+
exp = assert_raises(HexaPDF::MalformedPDFError) { @parser.parse_indirect_object }
|
190
|
+
assert_match(/followed by space instead/, exp.message)
|
191
|
+
end
|
192
|
+
|
193
|
+
it "fails if keyword stream is followed by space and CR LF instead of LF or CR/LF" do
|
194
|
+
create_parser("1 0 obj<</Length 2>> stream \r\n12\nendstream endobj")
|
195
|
+
exp = assert_raises(HexaPDF::MalformedPDFError) { @parser.parse_indirect_object }
|
196
|
+
assert_match(/followed by space instead/, exp.message)
|
197
|
+
end
|
198
|
+
|
199
|
+
it "fails for numbers followed by endobj without space" do
|
200
|
+
create_parser("1 0 obj 749endobj")
|
201
|
+
exp = assert_raises(HexaPDF::MalformedPDFError) { @parser.parse_indirect_object }
|
202
|
+
assert_match(/Missing whitespace after number/, exp.message)
|
203
|
+
end
|
204
|
+
|
205
|
+
it "fails for invalid values" do
|
206
|
+
create_parser("1 0 obj <</test ( /other (end)>> endobj")
|
207
|
+
exp = assert_raises(HexaPDF::MalformedPDFError) { @parser.parse_indirect_object }
|
208
|
+
assert_match(/Invalid value after '1 0 obj'/, exp.message)
|
209
|
+
end
|
210
|
+
|
211
|
+
it "fails if the stream length value is invalid" do
|
212
|
+
create_parser("1 0 obj<</Length 4>> stream\n12endstream endobj")
|
213
|
+
exp = assert_raises(HexaPDF::MalformedPDFError) { @parser.parse_indirect_object }
|
214
|
+
assert_match(/invalid stream length/i, exp.message)
|
215
|
+
end
|
216
|
+
|
217
|
+
it "fails if the keyword endobj is mangled" do
|
218
|
+
create_parser("1 0 obj\n<< >>\nendobjd\n")
|
219
|
+
exp = assert_raises(HexaPDF::MalformedPDFError) { @parser.parse_indirect_object }
|
220
|
+
assert_match(/keyword endobj/, exp.message)
|
221
|
+
end
|
222
|
+
|
223
|
+
it "fails if the keyword endobj is missing" do
|
224
|
+
create_parser("1 0 obj\n<< >>")
|
225
|
+
exp = assert_raises(HexaPDF::MalformedPDFError) { @parser.parse_indirect_object }
|
226
|
+
assert_match(/keyword endobj/, exp.message)
|
227
|
+
end
|
228
|
+
|
229
|
+
it "fails if there is data between 'endstream' and 'endobj'" do
|
230
|
+
create_parser("1 0 obj\n<< >>\nstream\nendstream\ntest\nendobj\n")
|
231
|
+
exp = assert_raises(HexaPDF::MalformedPDFError) { @parser.parse_indirect_object(0) }
|
232
|
+
assert_match(/keyword endobj/, exp.message)
|
233
|
+
end
|
234
|
+
end
|
235
|
+
end
|
236
|
+
|
237
|
+
describe "load_object" do
|
238
|
+
before do
|
239
|
+
@entry = HexaPDF::XRefSection.in_use_entry(2, 0, 29)
|
240
|
+
end
|
241
|
+
|
242
|
+
it "can load an indirect object" do
|
243
|
+
obj = @parser.load_object(@entry)
|
244
|
+
assert_kind_of(HexaPDF::Object, obj)
|
245
|
+
assert_equal(5, obj.value[0])
|
246
|
+
assert_equal(2, obj.oid)
|
247
|
+
assert_equal(0, obj.gen)
|
248
|
+
end
|
249
|
+
|
250
|
+
it "can load a free object" do
|
251
|
+
obj = @parser.load_object(HexaPDF::XRefSection.free_entry(0, 0))
|
252
|
+
assert_kind_of(HexaPDF::Object, obj)
|
253
|
+
assert_nil(obj.value)
|
254
|
+
end
|
255
|
+
|
256
|
+
it "can load a compressed object" do
|
257
|
+
def (@document).object(_oid)
|
258
|
+
obj = Object.new
|
259
|
+
def obj.parse_stream
|
260
|
+
HexaPDF::Type::ObjectStream::Data.new("5 [1 2]", [1, 2], [0, 2])
|
261
|
+
end
|
262
|
+
obj
|
263
|
+
end
|
264
|
+
|
265
|
+
obj = @parser.load_object(HexaPDF::XRefSection.compressed_entry(2, 3, 1))
|
266
|
+
assert_kind_of(HexaPDF::Object, obj)
|
267
|
+
assert_equal([1, 2], obj.value)
|
268
|
+
end
|
269
|
+
|
270
|
+
it "handles an invalid indirect object offset of 0" do
|
271
|
+
obj = @parser.load_object(HexaPDF::XRefSection.in_use_entry(2, 0, 0))
|
272
|
+
assert(obj.null?)
|
273
|
+
assert_equal(2, obj.oid)
|
274
|
+
assert_equal(0, obj.gen)
|
275
|
+
end
|
276
|
+
|
277
|
+
describe "with strict parsing" do
|
278
|
+
it "raises an error if an indirect object has an offset of 0" do
|
279
|
+
@document.config['parser.on_correctable_error'] = proc { true }
|
280
|
+
exp = assert_raises(HexaPDF::MalformedPDFError) do
|
281
|
+
@parser.load_object(HexaPDF::XRefSection.in_use_entry(2, 0, 0))
|
282
|
+
end
|
283
|
+
assert_match(/has offset 0/, exp.message)
|
284
|
+
end
|
285
|
+
end
|
286
|
+
|
287
|
+
it "fails if another object is found instead of an object stream" do
|
288
|
+
def (@document).object(_oid)
|
289
|
+
:invalid
|
290
|
+
end
|
291
|
+
exp = assert_raises(HexaPDF::MalformedPDFError) do
|
292
|
+
@parser.load_object(HexaPDF::XRefSection.compressed_entry(2, 1, 1))
|
293
|
+
end
|
294
|
+
assert_match(/not an object stream/, exp.message)
|
295
|
+
end
|
296
|
+
|
297
|
+
it "fails if the xref entry type is invalid" do
|
298
|
+
exp = assert_raises(HexaPDF::MalformedPDFError) do
|
299
|
+
@parser.load_object(HexaPDF::XRefSection::Entry.new(:invalid))
|
300
|
+
end
|
301
|
+
assert_match(/invalid cross-reference type/i, exp.message)
|
302
|
+
end
|
303
|
+
|
304
|
+
it "fails if the object/generation numbers don't match" do
|
305
|
+
exp = assert_raises(HexaPDF::MalformedPDFError) do
|
306
|
+
@entry.gen = 2
|
307
|
+
@parser.load_object(@entry)
|
308
|
+
end
|
309
|
+
assert_match(/oid,gen.*don't match/, exp.message)
|
310
|
+
end
|
311
|
+
end
|
312
|
+
|
313
|
+
describe "startxref_offset" do
|
314
|
+
it "caches the offset value" do
|
315
|
+
assert_equal(308, @parser.startxref_offset)
|
316
|
+
@parser.instance_eval { @io }.string.sub!(/308\n/, "309\n")
|
317
|
+
assert_equal(308, @parser.startxref_offset)
|
318
|
+
end
|
319
|
+
|
320
|
+
it "returns the correct offset" do
|
321
|
+
assert_equal(308, @parser.startxref_offset)
|
322
|
+
end
|
323
|
+
|
324
|
+
it "ignores garbage at the end of the file" do
|
325
|
+
create_parser("startxref\n5\n%%EOF" << "\nhallo" * 150)
|
326
|
+
assert_equal(5, @parser.startxref_offset)
|
327
|
+
end
|
328
|
+
|
329
|
+
it "uses the last startxref if there are more than one" do
|
330
|
+
create_parser("startxref\n5\n%%EOF\n\nsome garbage\n\nstartxref\n555\n%%EOF\n")
|
331
|
+
assert_equal(555, @parser.startxref_offset)
|
332
|
+
end
|
333
|
+
|
334
|
+
it "finds the startxref anywhere in file" do
|
335
|
+
create_parser("startxref\n5\n%%EOF" << "\nhallo" * 5000)
|
336
|
+
assert_equal(5, @parser.startxref_offset)
|
337
|
+
create_parser("startxref\n5\n%%EOF\n" << "h" * 1017)
|
338
|
+
assert_equal(5, @parser.startxref_offset)
|
339
|
+
end
|
340
|
+
|
341
|
+
it "fails even in big files when nothing is found" do
|
342
|
+
create_parser("\nhallo" * 5000)
|
343
|
+
exp = assert_raises(HexaPDF::MalformedPDFError) { @parser.startxref_offset }
|
344
|
+
assert_match(/end-of-file marker not found/, exp.message)
|
345
|
+
end
|
346
|
+
|
347
|
+
it "fails if the %%EOF marker is missing" do
|
348
|
+
create_parser("startxref\n5")
|
349
|
+
exp = assert_raises(HexaPDF::MalformedPDFError) { @parser.startxref_offset }
|
350
|
+
assert_match(/end-of-file marker not found/, exp.message)
|
351
|
+
|
352
|
+
create_parser("")
|
353
|
+
exp = assert_raises(HexaPDF::MalformedPDFError) { @parser.startxref_offset }
|
354
|
+
assert_match(/end-of-file marker not found/, exp.message)
|
355
|
+
end
|
356
|
+
|
357
|
+
it "fails if the startxref keyword is missing" do
|
358
|
+
create_parser("somexref\n5\n%%EOF")
|
359
|
+
exp = assert_raises(HexaPDF::MalformedPDFError) { @parser.startxref_offset }
|
360
|
+
assert_match(/missing startxref/, exp.message)
|
361
|
+
end
|
362
|
+
|
363
|
+
it "fails on strict parsing if the startxref is not in the last part of the file" do
|
364
|
+
@document.config['parser.on_correctable_error'] = proc { true }
|
365
|
+
create_parser("startxref\n5\n%%EOF" << "\nhallo" * 5000)
|
366
|
+
exp = assert_raises(HexaPDF::MalformedPDFError) { @parser.startxref_offset }
|
367
|
+
assert_match(/end-of-file marker not found/, exp.message)
|
368
|
+
end
|
369
|
+
end
|
370
|
+
|
371
|
+
describe "file_header_version" do
|
372
|
+
it "returns the correct version" do
|
373
|
+
assert_equal('1.7', @parser.file_header_version)
|
374
|
+
end
|
375
|
+
|
376
|
+
it "fails if the header is mangled" do
|
377
|
+
create_parser("%PDF-1\n")
|
378
|
+
exp = assert_raises(HexaPDF::MalformedPDFError) { @parser.file_header_version }
|
379
|
+
assert_match(/file header/, exp.message)
|
380
|
+
end
|
381
|
+
|
382
|
+
it "fails if the header is missing" do
|
383
|
+
create_parser("no header")
|
384
|
+
exp = assert_raises(HexaPDF::MalformedPDFError) { @parser.file_header_version }
|
385
|
+
assert_match(/file header/, exp.message)
|
386
|
+
end
|
387
|
+
|
388
|
+
it "ignores junk at the beginning of the file and correctly calculates offset" do
|
389
|
+
create_parser("junk" * 200 << "\n%PDF-1.4\n")
|
390
|
+
assert_equal('1.4', @parser.file_header_version)
|
391
|
+
assert_equal(801, @parser.instance_variable_get(:@header_offset))
|
392
|
+
end
|
393
|
+
end
|
394
|
+
|
395
|
+
it "xref_section?" do
|
396
|
+
assert(@parser.xref_section?(@parser.startxref_offset))
|
397
|
+
refute(@parser.xref_section?(53))
|
398
|
+
end
|
399
|
+
|
400
|
+
describe "parse_xref_section_and_trailer" do
|
401
|
+
it "works on a section with multiple sub sections" do
|
402
|
+
section, trailer = @parser.parse_xref_section_and_trailer(@parser.startxref_offset)
|
403
|
+
assert_equal({Test: 'now'}, trailer)
|
404
|
+
assert_equal(HexaPDF::XRefSection.free_entry(0, 65535), section[0, 65535])
|
405
|
+
assert_equal(HexaPDF::XRefSection.free_entry(3, 65535), section[3, 65535])
|
406
|
+
assert_equal(HexaPDF::XRefSection.in_use_entry(1, 0, 10), section[1])
|
407
|
+
end
|
408
|
+
|
409
|
+
it "works for an empty section" do
|
410
|
+
create_parser("xref\n0 0\ntrailer\n<</Name /Value >>\n")
|
411
|
+
_, trailer = @parser.parse_xref_section_and_trailer(0)
|
412
|
+
assert_equal({Name: :Value}, trailer)
|
413
|
+
end
|
414
|
+
|
415
|
+
it "handles xref type=n with offset=0" do
|
416
|
+
create_parser("xref\n0 2\n0000000000 00000 n \n0000000000 00000 n \ntrailer\n<<>>\n")
|
417
|
+
section, _trailer = @parser.parse_xref_section_and_trailer(0)
|
418
|
+
assert_equal(HexaPDF::XRefSection.free_entry(1, 0), section[1])
|
419
|
+
end
|
420
|
+
|
421
|
+
it "handles xref type=n with gen>65535" do
|
422
|
+
create_parser("xref\n0 2\n0000000000 00000 n \n0000000000 65536 n \ntrailer\n<<>>\n")
|
423
|
+
section, _trailer = @parser.parse_xref_section_and_trailer(0)
|
424
|
+
assert_equal(HexaPDF::XRefSection.free_entry(1, 65536), section[1])
|
425
|
+
end
|
426
|
+
|
427
|
+
it "handles xref with missing whitespace at end" do
|
428
|
+
create_parser("xref\n0 2\n0000000000 00000 n\n0000000000 65536 n\ntrailer\n<<>>\n")
|
429
|
+
section, _trailer = @parser.parse_xref_section_and_trailer(0)
|
430
|
+
assert_equal(HexaPDF::XRefSection.free_entry(1, 65536), section[1])
|
431
|
+
end
|
432
|
+
|
433
|
+
it "fails if the xref keyword is missing/mangled" do
|
434
|
+
create_parser("xTEf\n0 d\n0000000000 00000 n \ntrailer\n<< >>\n")
|
435
|
+
exp = assert_raises(HexaPDF::MalformedPDFError) { @parser.parse_xref_section_and_trailer(0) }
|
436
|
+
assert_match(/keyword xref/, exp.message)
|
437
|
+
end
|
438
|
+
|
439
|
+
it "fails if a sub section header is mangled" do
|
440
|
+
create_parser("xref\n0 d\n0000000000 00000 n \ntrailer\n<< >>\n")
|
441
|
+
exp = assert_raises(HexaPDF::MalformedPDFError) { @parser.parse_xref_section_and_trailer(0) }
|
442
|
+
assert_match(/invalid cross-reference subsection/i, exp.message)
|
443
|
+
end
|
444
|
+
|
445
|
+
it "fails if a sub section entry is mangled" do
|
446
|
+
create_parser("xref\n0 2\n000a000000 00000 n\n0000000000 65535 n\ntrailer\n<<>>\n")
|
447
|
+
exp = assert_raises(HexaPDF::MalformedPDFError) { @parser.parse_xref_section_and_trailer(0) }
|
448
|
+
assert_match(/invalid cross-reference entry/i, exp.message)
|
449
|
+
end
|
450
|
+
|
451
|
+
it "fails if there is no trailer" do
|
452
|
+
create_parser("xref\n0 1\n0000000000 00000 n \n")
|
453
|
+
exp = assert_raises(HexaPDF::MalformedPDFError) { @parser.parse_xref_section_and_trailer(0) }
|
454
|
+
assert_match(/keyword trailer/i, exp.message)
|
455
|
+
end
|
456
|
+
|
457
|
+
it "fails if the trailer is not a PDF dictionary" do
|
458
|
+
create_parser("xref\n0 1\n0000000000 00000 n \ntrailer\n(base)")
|
459
|
+
exp = assert_raises(HexaPDF::MalformedPDFError) { @parser.parse_xref_section_and_trailer(0) }
|
460
|
+
assert_match(/dictionary/, exp.message)
|
461
|
+
end
|
462
|
+
|
463
|
+
describe "invalid numbering of main xref section" do
|
464
|
+
it "handles the xref if the numbering is off by N" do
|
465
|
+
create_parser(" 1 0 obj 1 endobj\n" \
|
466
|
+
"xref\n1 2\n0000000000 65535 f \n0000000001 00000 n \ntrailer\n<<>>\n")
|
467
|
+
section, _trailer = @parser.parse_xref_section_and_trailer(17)
|
468
|
+
assert_equal(HexaPDF::XRefSection.in_use_entry(1, 0, 1), section[1])
|
469
|
+
end
|
470
|
+
|
471
|
+
it "fails if the first entry is not the one for oid=0" do
|
472
|
+
create_parser(" 1 0 obj 1 endobj\n" \
|
473
|
+
"xref\n1 2\n0000000000 00005 f \n0000000001 00000 n \ntrailer\n<<>>\n")
|
474
|
+
exp = assert_raises(HexaPDF::MalformedPDFError) { @parser.parse_xref_section_and_trailer(17) }
|
475
|
+
assert_match(/Main.*invalid numbering/i, exp.message)
|
476
|
+
|
477
|
+
create_parser(" 1 0 obj 1 endobj\n" \
|
478
|
+
"xref\n1 2\n0000000001 00000 n \n0000000001 00000 n \ntrailer\n<<>>\n")
|
479
|
+
exp = assert_raises(HexaPDF::MalformedPDFError) { @parser.parse_xref_section_and_trailer(17) }
|
480
|
+
assert_match(/Main.*invalid numbering/i, exp.message)
|
481
|
+
end
|
482
|
+
|
483
|
+
it "fails if the tested entry position is invalid" do
|
484
|
+
create_parser(" 1 0 obj 1 endobj\n" \
|
485
|
+
"xref\n1 2\n0000000000 65535 f \n0000000005 00000 n \ntrailer\n<<>>\n")
|
486
|
+
exp = assert_raises(HexaPDF::MalformedPDFError) { @parser.parse_xref_section_and_trailer(17) }
|
487
|
+
assert_match(/Main.*invalid numbering/i, exp.message)
|
488
|
+
end
|
489
|
+
|
490
|
+
it "fails if the tested entry position's oid doesn't match the corrected entry oid" do
|
491
|
+
create_parser(" 2 0 obj 1 endobj\n" \
|
492
|
+
"xref\n1 2\n0000000000 65535 f \n0000000001 00000 n \ntrailer\n<<>>\n")
|
493
|
+
exp = assert_raises(HexaPDF::MalformedPDFError) { @parser.parse_xref_section_and_trailer(17) }
|
494
|
+
assert_match(/Main.*invalid numbering/i, exp.message)
|
495
|
+
end
|
496
|
+
end
|
497
|
+
|
498
|
+
describe "with strict parsing" do
|
499
|
+
before do
|
500
|
+
@document.config['parser.on_correctable_error'] = proc { true }
|
501
|
+
end
|
502
|
+
|
503
|
+
it "fails if xref type=n with offset=0" do
|
504
|
+
create_parser("xref\n0 2\n0000000000 00000 n \n0000000000 00000 n \ntrailer\n<<>>\n")
|
505
|
+
exp = assert_raises(HexaPDF::MalformedPDFError) { @parser.parse_xref_section_and_trailer(0) }
|
506
|
+
assert_match(/invalid.*cross-reference entry/i, exp.message)
|
507
|
+
end
|
508
|
+
|
509
|
+
it " fails xref type=n with gen>65535" do
|
510
|
+
create_parser("xref\n0 2\n0000000000 00000 n \n0000000000 65536 n \ntrailer\n<<>>\n")
|
511
|
+
exp = assert_raises(HexaPDF::MalformedPDFError) { @parser.parse_xref_section_and_trailer(0) }
|
512
|
+
assert_match(/invalid.*cross-reference entry/i, exp.message)
|
513
|
+
end
|
514
|
+
|
515
|
+
it "fails if trailing second whitespace is missing" do
|
516
|
+
create_parser("xref\n0 1\n0000000000 00000 n\ntrailer\n<<>>\n")
|
517
|
+
exp = assert_raises(HexaPDF::MalformedPDFError) { @parser.parse_xref_section_and_trailer(0) }
|
518
|
+
assert_match(/invalid.*cross-reference entry/i, exp.message)
|
519
|
+
end
|
520
|
+
|
521
|
+
it "fails if the main cross-reference section has invalid numbering" do
|
522
|
+
create_parser("xref\n1 1\n0000000001 00000 n \ntrailer\n<<>>\n")
|
523
|
+
exp = assert_raises(HexaPDF::MalformedPDFError) { @parser.parse_xref_section_and_trailer(0) }
|
524
|
+
assert_match(/Main.*invalid numbering/i, exp.message)
|
525
|
+
end
|
526
|
+
end
|
527
|
+
end
|
528
|
+
|
529
|
+
describe "load_revision" do
|
530
|
+
it "works for a simple cross-reference section" do
|
531
|
+
xref_section, trailer = @parser.load_revision(@parser.startxref_offset)
|
532
|
+
assert_equal({Test: 'now'}, trailer)
|
533
|
+
assert(xref_section[1].in_use?)
|
534
|
+
end
|
535
|
+
|
536
|
+
it "works for a cross-reference stream" do
|
537
|
+
xref_section, trailer = @parser.load_revision(212)
|
538
|
+
assert_equal({Size: 2}, trailer)
|
539
|
+
assert(xref_section[1].in_use?)
|
540
|
+
end
|
541
|
+
|
542
|
+
it "fails if another object is found instead of a cross-reference stream" do
|
543
|
+
exp = assert_raises(HexaPDF::MalformedPDFError) { @parser.load_revision(10) }
|
544
|
+
assert_match(/not a cross-reference stream/, exp.message)
|
545
|
+
end
|
546
|
+
|
547
|
+
it "fails if the cross-reference stream is missing data" do
|
548
|
+
@parse_io.string[287..288] = ''
|
549
|
+
exp = assert_raises(HexaPDF::MalformedPDFError) { @parser.load_revision(212) }
|
550
|
+
assert_match(/missing data/, exp.message)
|
551
|
+
assert_equal(212, exp.pos)
|
552
|
+
end
|
553
|
+
|
554
|
+
it "fails on strict parsing if the cross-reference stream doesn't contain an entry for itself" do
|
555
|
+
@document.config['parser.on_correctable_error'] = proc { true }
|
556
|
+
create_parser("2 0 obj\n<</Type/XRef/Length 3/W [1 1 1]/Size 1>>" \
|
557
|
+
"stream\n\x01\x0A\x00\nendstream endobj")
|
558
|
+
exp = assert_raises(HexaPDF::MalformedPDFError) { @parser.load_revision(0) }
|
559
|
+
assert_match(/entry for itself/, exp.message)
|
560
|
+
end
|
561
|
+
end
|
562
|
+
|
563
|
+
describe "reconstruct_revision" do
|
564
|
+
before do
|
565
|
+
@document.config['parser.try_xref_reconstruction'] = true
|
566
|
+
@xref = HexaPDF::XRefSection.in_use_entry(1, 0, 100)
|
567
|
+
end
|
568
|
+
|
569
|
+
it "serially parses the contents" do
|
570
|
+
create_parser("1 0 obj\n5\nendobj\n1 0 obj\n6\nendobj\ntrailer\n<</Size 1>>")
|
571
|
+
assert_equal(6, @parser.load_object(@xref).value)
|
572
|
+
end
|
573
|
+
|
574
|
+
it "uses a security handler for decrypting indirect objects if necessary" do
|
575
|
+
handler = Minitest::Mock.new
|
576
|
+
handler.expect(:decrypt, HexaPDF::Object.new(:result, oid: 1), [HexaPDF::Object])
|
577
|
+
@document.instance_variable_set(:@security_handler, handler)
|
578
|
+
create_parser("1 0 obj\n6\nendobj\ntrailer\n<</Size 1>>")
|
579
|
+
assert_equal(:result, @parser.load_object(@xref).value)
|
580
|
+
assert(handler.verify)
|
581
|
+
end
|
582
|
+
|
583
|
+
it "ignores parts where the starting line is split across lines" do
|
584
|
+
create_parser("1 0 obj\n5\nendobj\n1 0\nobj\n6\nendobj\ntrailer\n<</Size 1>>")
|
585
|
+
assert_equal(5, @parser.load_object(@xref).value)
|
586
|
+
end
|
587
|
+
|
588
|
+
it "handles the case when the specified object had an xref entry but is not found" do
|
589
|
+
create_parser("3 0 obj\n5\nendobj\ntrailer\n<</Size 1>>")
|
590
|
+
assert(@parser.load_object(@xref).null?)
|
591
|
+
end
|
592
|
+
|
593
|
+
it "handles cases where the line contains an invalid string that exceeds the read buffer" do
|
594
|
+
create_parser("(1" << "(abc" * 32188 << "\n1 0 obj\n6\nendobj\ntrailer\n<</Size 1>>")
|
595
|
+
assert_equal(6, @parser.load_object(@xref).value)
|
596
|
+
end
|
597
|
+
|
598
|
+
it "handles pathalogical cases which contain many opened literal strings" do
|
599
|
+
time = Time.now
|
600
|
+
create_parser("(1" << "(abc\n" * 10000 << "\n1 0 obj\n6\nendobj\ntrailer\n<</Size 1>>")
|
601
|
+
assert_equal(6, @parser.load_object(@xref).value)
|
602
|
+
assert(Time.now - time < 0.5, "Xref reconstruction takes too long")
|
603
|
+
end
|
604
|
+
|
605
|
+
it "ignores invalid objects" do
|
606
|
+
create_parser("1 x obj\n5\nendobj\n1 0 xobj\n6\nendobj\n1 0 obj 4\nendobj\ntrailer\n<</Size 1>>")
|
607
|
+
assert_equal(4, @parser.load_object(@xref).value)
|
608
|
+
end
|
609
|
+
|
610
|
+
it "ignores invalid lines" do
|
611
|
+
create_parser("1 0 obj\n5\nendobj\nhello there\n1 0 obj\n6\nendobj\ntrailer\n<</Size 1>>")
|
612
|
+
assert_equal(6, @parser.load_object(@xref).value)
|
613
|
+
end
|
614
|
+
|
615
|
+
it "uses the last trailer" do
|
616
|
+
create_parser("trailer <</Size 1>>\ntrailer <</Size 2/Prev 342>>")
|
617
|
+
assert_equal({Size: 2}, @parser.reconstructed_revision.trailer.value)
|
618
|
+
end
|
619
|
+
|
620
|
+
it "uses the first trailer in case of a linearized file" do
|
621
|
+
create_parser("1 0 obj\n<</Linearized true>>\nendobj\ntrailer <</Size 1/Prev 342>>\ntrailer <</Size 2>>")
|
622
|
+
assert_equal({Size: 1}, @parser.reconstructed_revision.trailer.value)
|
623
|
+
end
|
624
|
+
|
625
|
+
it "tries the trailer specified at the startxref position if no other is found" do
|
626
|
+
create_parser("1 0 obj\n5\nendobj\nquack xref trailer <</Size 1/Prev 5>>\nstartxref\n22\n%%EOF")
|
627
|
+
assert_equal({Size: 1}, @parser.reconstructed_revision.trailer.value)
|
628
|
+
end
|
629
|
+
|
630
|
+
it "constructs a trailer with a /Root entry if no valid trailer was found" do
|
631
|
+
create_parser("1 0 obj\n<</Type /Catalog/Pages 2 0 R>>\nendobj\nxref trailer <</Size 1/Prev 5\n%%EOF")
|
632
|
+
assert_equal({Root: HexaPDF::Reference.new(1, 0)}, @parser.reconstructed_revision.trailer.value)
|
633
|
+
end
|
634
|
+
|
635
|
+
it "fails if no valid trailer is found and couldn't be constructed" do
|
636
|
+
create_parser("1 0 obj\n5\nendobj\nquack trailer <</Size 1>>\nstartxref\n22\n%%EOF")
|
637
|
+
assert_raises(HexaPDF::MalformedPDFError) { @parser.reconstructed_revision.trailer }
|
638
|
+
end
|
639
|
+
|
640
|
+
it "fails if no valid trailer is found" do
|
641
|
+
create_parser("1 0 obj\n5\nendobj")
|
642
|
+
assert_raises(HexaPDF::MalformedPDFError) { @parser.load_object(@xref) }
|
643
|
+
end
|
644
|
+
end
|
645
|
+
end
|