html-to-markdown 2.24.6 → 2.25.1

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.
Files changed (231) hide show
  1. checksums.yaml +4 -4
  2. data/Gemfile.lock +2 -2
  3. data/README.md +1 -1
  4. data/ext/html-to-markdown-rb/native/Cargo.lock +9 -32
  5. data/ext/html-to-markdown-rb/native/Cargo.toml +1 -1
  6. data/lib/html_to_markdown/version.rb +1 -1
  7. data/rust-vendor/html-to-markdown-rs/Cargo.toml +0 -1
  8. data/rust-vendor/html-to-markdown-rs/src/converter/main_helpers.rs +1 -1
  9. data/rust-vendor/html-to-markdown-rs/src/hocr/converter/hierarchy.rs +20 -5
  10. data/rust-vendor/html-to-markdown-rs/src/lib.rs +1 -0
  11. data/rust-vendor/{markup5ever_rcdom/lib.rs → html-to-markdown-rs/src/rcdom.rs} +56 -91
  12. data/rust-vendor/html-to-markdown-rs/tests/hocr_compliance_test.rs +157 -0
  13. data/rust-vendor/memmap2/.cargo-checksum.json +1 -1
  14. data/rust-vendor/memmap2/.cargo_vcs_info.json +1 -1
  15. data/rust-vendor/memmap2/CHANGELOG.md +8 -0
  16. data/rust-vendor/memmap2/Cargo.lock +1 -1
  17. data/rust-vendor/memmap2/Cargo.toml +2 -1
  18. data/rust-vendor/memmap2/Cargo.toml.orig +2 -1
  19. data/rust-vendor/memmap2/src/lib.rs +25 -1
  20. data/rust-vendor/memmap2/src/stub.rs +1 -4
  21. data/rust-vendor/memmap2/src/unix.rs +14 -1
  22. data/rust-vendor/png/.cargo-checksum.json +1 -1
  23. data/rust-vendor/png/.cargo_vcs_info.json +1 -1
  24. data/rust-vendor/png/CHANGES.md +44 -0
  25. data/rust-vendor/png/Cargo.lock +124 -171
  26. data/rust-vendor/png/Cargo.toml +1 -1
  27. data/rust-vendor/png/Cargo.toml.orig +1 -1
  28. data/rust-vendor/png/benches/expand_paletted.rs +5 -5
  29. data/rust-vendor/png/benches/unfilter.rs +3 -3
  30. data/rust-vendor/png/src/adam7.rs +17 -10
  31. data/rust-vendor/png/src/common.rs +8 -8
  32. data/rust-vendor/png/src/decoder/mod.rs +53 -20
  33. data/rust-vendor/png/src/decoder/stream.rs +263 -78
  34. data/rust-vendor/png/src/decoder/unfiltering_buffer.rs +210 -53
  35. data/rust-vendor/png/src/decoder/zlib.rs +130 -90
  36. data/rust-vendor/png/src/encoder.rs +4 -2
  37. data/rust-vendor/png/src/{filter.rs → filter/mod.rs} +100 -367
  38. data/rust-vendor/png/src/filter/optimization-notes.md +104 -0
  39. data/rust-vendor/png/src/filter/paeth.rs +398 -0
  40. data/rust-vendor/png/src/filter/simd.rs +308 -0
  41. data/rust-vendor/png/src/lib.rs +1 -0
  42. data/rust-vendor/syn/.cargo-checksum.json +1 -1
  43. data/rust-vendor/syn/.cargo_vcs_info.json +1 -1
  44. data/rust-vendor/syn/Cargo.lock +40 -41
  45. data/rust-vendor/syn/Cargo.toml +1 -1
  46. data/rust-vendor/syn/Cargo.toml.orig +1 -1
  47. data/rust-vendor/syn/src/item.rs +61 -40
  48. data/rust-vendor/syn/src/lib.rs +2 -1
  49. data/rust-vendor/syn/tests/test_item.rs +54 -0
  50. data/rust-vendor/unicode-ident/.cargo-checksum.json +1 -1
  51. data/rust-vendor/unicode-ident/.cargo_vcs_info.json +1 -1
  52. data/rust-vendor/unicode-ident/Cargo.lock +21 -21
  53. data/rust-vendor/unicode-ident/Cargo.toml +1 -1
  54. data/rust-vendor/unicode-ident/Cargo.toml.orig +1 -1
  55. data/rust-vendor/unicode-ident/src/lib.rs +1 -1
  56. data/rust-vendor/unicode-ident/src/tables.rs +87 -97
  57. data/rust-vendor/unicode-ident/tests/static_size.rs +1 -1
  58. metadata +7 -177
  59. data/rust-vendor/markup5ever_rcdom/.cargo-checksum.json +0 -1
  60. data/rust-vendor/markup5ever_rcdom/.cargo_vcs_info.json +0 -7
  61. data/rust-vendor/markup5ever_rcdom/Cargo.lock +0 -658
  62. data/rust-vendor/markup5ever_rcdom/Cargo.toml +0 -109
  63. data/rust-vendor/markup5ever_rcdom/Cargo.toml.orig +0 -42
  64. data/rust-vendor/markup5ever_rcdom/LICENSE-APACHE +0 -201
  65. data/rust-vendor/markup5ever_rcdom/LICENSE-MIT +0 -25
  66. data/rust-vendor/markup5ever_rcdom/README.md +0 -7
  67. data/rust-vendor/markup5ever_rcdom/custom-html5lib-tokenizer-tests/regression.test +0 -69
  68. data/rust-vendor/markup5ever_rcdom/data/test/ignore +0 -1
  69. data/rust-vendor/markup5ever_rcdom/examples/hello_xml.rs +0 -39
  70. data/rust-vendor/markup5ever_rcdom/examples/html2html.rs +0 -51
  71. data/rust-vendor/markup5ever_rcdom/examples/print-rcdom.rs +0 -78
  72. data/rust-vendor/markup5ever_rcdom/examples/xml_tree_printer.rs +0 -67
  73. data/rust-vendor/markup5ever_rcdom/html5lib-tests/.gitattributes +0 -2
  74. data/rust-vendor/markup5ever_rcdom/html5lib-tests/.github/workflows/downstream.yml +0 -76
  75. data/rust-vendor/markup5ever_rcdom/html5lib-tests/.github/workflows/lint.yml +0 -25
  76. data/rust-vendor/markup5ever_rcdom/html5lib-tests/.gitignore +0 -79
  77. data/rust-vendor/markup5ever_rcdom/html5lib-tests/AUTHORS.rst +0 -34
  78. data/rust-vendor/markup5ever_rcdom/html5lib-tests/LICENSE +0 -21
  79. data/rust-vendor/markup5ever_rcdom/html5lib-tests/encoding/chardet/test_big5.txt +0 -51
  80. data/rust-vendor/markup5ever_rcdom/html5lib-tests/encoding/scripted/tests1.dat +0 -5
  81. data/rust-vendor/markup5ever_rcdom/html5lib-tests/encoding/test-yahoo-jp.dat +0 -10
  82. data/rust-vendor/markup5ever_rcdom/html5lib-tests/encoding/tests1.dat +0 -388
  83. data/rust-vendor/markup5ever_rcdom/html5lib-tests/encoding/tests2.dat +0 -115
  84. data/rust-vendor/markup5ever_rcdom/html5lib-tests/lint +0 -6
  85. data/rust-vendor/markup5ever_rcdom/html5lib-tests/lint_lib/__init__.py +0 -0
  86. data/rust-vendor/markup5ever_rcdom/html5lib-tests/lint_lib/_vendor/__init__.py +0 -0
  87. data/rust-vendor/markup5ever_rcdom/html5lib-tests/lint_lib/_vendor/funcparserlib/LICENSE +0 -18
  88. data/rust-vendor/markup5ever_rcdom/html5lib-tests/lint_lib/_vendor/funcparserlib/__init__.py +0 -0
  89. data/rust-vendor/markup5ever_rcdom/html5lib-tests/lint_lib/_vendor/funcparserlib/lexer.py +0 -211
  90. data/rust-vendor/markup5ever_rcdom/html5lib-tests/lint_lib/_vendor/funcparserlib/lexer.pyi +0 -34
  91. data/rust-vendor/markup5ever_rcdom/html5lib-tests/lint_lib/_vendor/funcparserlib/parser.py +0 -872
  92. data/rust-vendor/markup5ever_rcdom/html5lib-tests/lint_lib/_vendor/funcparserlib/parser.pyi +0 -83
  93. data/rust-vendor/markup5ever_rcdom/html5lib-tests/lint_lib/_vendor/funcparserlib/py.typed +0 -0
  94. data/rust-vendor/markup5ever_rcdom/html5lib-tests/lint_lib/_vendor/funcparserlib/util.py +0 -72
  95. data/rust-vendor/markup5ever_rcdom/html5lib-tests/lint_lib/_vendor/funcparserlib/util.pyi +0 -7
  96. data/rust-vendor/markup5ever_rcdom/html5lib-tests/lint_lib/_vendor/vendor.txt +0 -1
  97. data/rust-vendor/markup5ever_rcdom/html5lib-tests/lint_lib/_vendor-patches/funcparserlib.patch +0 -24
  98. data/rust-vendor/markup5ever_rcdom/html5lib-tests/lint_lib/lint.py +0 -280
  99. data/rust-vendor/markup5ever_rcdom/html5lib-tests/lint_lib/parser.py +0 -177
  100. data/rust-vendor/markup5ever_rcdom/html5lib-tests/pyproject.toml +0 -7
  101. data/rust-vendor/markup5ever_rcdom/html5lib-tests/serializer/core.test +0 -125
  102. data/rust-vendor/markup5ever_rcdom/html5lib-tests/serializer/injectmeta.test +0 -66
  103. data/rust-vendor/markup5ever_rcdom/html5lib-tests/serializer/optionaltags.test +0 -965
  104. data/rust-vendor/markup5ever_rcdom/html5lib-tests/serializer/options.test +0 -60
  105. data/rust-vendor/markup5ever_rcdom/html5lib-tests/serializer/whitespace.test +0 -51
  106. data/rust-vendor/markup5ever_rcdom/html5lib-tests/tokenizer/README.md +0 -107
  107. data/rust-vendor/markup5ever_rcdom/html5lib-tests/tokenizer/contentModelFlags.test +0 -93
  108. data/rust-vendor/markup5ever_rcdom/html5lib-tests/tokenizer/domjs.test +0 -335
  109. data/rust-vendor/markup5ever_rcdom/html5lib-tests/tokenizer/entities.test +0 -542
  110. data/rust-vendor/markup5ever_rcdom/html5lib-tests/tokenizer/escapeFlag.test +0 -36
  111. data/rust-vendor/markup5ever_rcdom/html5lib-tests/tokenizer/namedEntities.test +0 -42422
  112. data/rust-vendor/markup5ever_rcdom/html5lib-tests/tokenizer/numericEntities.test +0 -1677
  113. data/rust-vendor/markup5ever_rcdom/html5lib-tests/tokenizer/pendingSpecChanges.test +0 -9
  114. data/rust-vendor/markup5ever_rcdom/html5lib-tests/tokenizer/test1.test +0 -353
  115. data/rust-vendor/markup5ever_rcdom/html5lib-tests/tokenizer/test2.test +0 -275
  116. data/rust-vendor/markup5ever_rcdom/html5lib-tests/tokenizer/test3.test +0 -11233
  117. data/rust-vendor/markup5ever_rcdom/html5lib-tests/tokenizer/test4.test +0 -532
  118. data/rust-vendor/markup5ever_rcdom/html5lib-tests/tokenizer/unicodeChars.test +0 -1577
  119. data/rust-vendor/markup5ever_rcdom/html5lib-tests/tokenizer/unicodeCharsProblematic.test +0 -41
  120. data/rust-vendor/markup5ever_rcdom/html5lib-tests/tokenizer/xmlViolation.test +0 -20
  121. data/rust-vendor/markup5ever_rcdom/html5lib-tests/tree-construction/README.md +0 -108
  122. data/rust-vendor/markup5ever_rcdom/html5lib-tests/tree-construction/adoption01.dat +0 -354
  123. data/rust-vendor/markup5ever_rcdom/html5lib-tests/tree-construction/adoption02.dat +0 -39
  124. data/rust-vendor/markup5ever_rcdom/html5lib-tests/tree-construction/blocks.dat +0 -695
  125. data/rust-vendor/markup5ever_rcdom/html5lib-tests/tree-construction/comments01.dat +0 -217
  126. data/rust-vendor/markup5ever_rcdom/html5lib-tests/tree-construction/doctype01.dat +0 -474
  127. data/rust-vendor/markup5ever_rcdom/html5lib-tests/tree-construction/domjs-unsafe.dat +0 -0
  128. data/rust-vendor/markup5ever_rcdom/html5lib-tests/tree-construction/entities01.dat +0 -943
  129. data/rust-vendor/markup5ever_rcdom/html5lib-tests/tree-construction/entities02.dat +0 -309
  130. data/rust-vendor/markup5ever_rcdom/html5lib-tests/tree-construction/foreign-fragment.dat +0 -645
  131. data/rust-vendor/markup5ever_rcdom/html5lib-tests/tree-construction/html5test-com.dat +0 -301
  132. data/rust-vendor/markup5ever_rcdom/html5lib-tests/tree-construction/inbody01.dat +0 -54
  133. data/rust-vendor/markup5ever_rcdom/html5lib-tests/tree-construction/isindex.dat +0 -49
  134. data/rust-vendor/markup5ever_rcdom/html5lib-tests/tree-construction/main-element.dat +0 -46
  135. data/rust-vendor/markup5ever_rcdom/html5lib-tests/tree-construction/math.dat +0 -104
  136. data/rust-vendor/markup5ever_rcdom/html5lib-tests/tree-construction/menuitem-element.dat +0 -240
  137. data/rust-vendor/markup5ever_rcdom/html5lib-tests/tree-construction/namespace-sensitivity.dat +0 -22
  138. data/rust-vendor/markup5ever_rcdom/html5lib-tests/tree-construction/noscript01.dat +0 -237
  139. data/rust-vendor/markup5ever_rcdom/html5lib-tests/tree-construction/pending-spec-changes-plain-text-unsafe.dat +0 -0
  140. data/rust-vendor/markup5ever_rcdom/html5lib-tests/tree-construction/pending-spec-changes.dat +0 -46
  141. data/rust-vendor/markup5ever_rcdom/html5lib-tests/tree-construction/plain-text-unsafe.dat +0 -0
  142. data/rust-vendor/markup5ever_rcdom/html5lib-tests/tree-construction/quirks01.dat +0 -53
  143. data/rust-vendor/markup5ever_rcdom/html5lib-tests/tree-construction/ruby.dat +0 -302
  144. data/rust-vendor/markup5ever_rcdom/html5lib-tests/tree-construction/scriptdata01.dat +0 -372
  145. data/rust-vendor/markup5ever_rcdom/html5lib-tests/tree-construction/scripted/adoption01.dat +0 -16
  146. data/rust-vendor/markup5ever_rcdom/html5lib-tests/tree-construction/scripted/ark.dat +0 -27
  147. data/rust-vendor/markup5ever_rcdom/html5lib-tests/tree-construction/scripted/webkit01.dat +0 -30
  148. data/rust-vendor/markup5ever_rcdom/html5lib-tests/tree-construction/search-element.dat +0 -46
  149. data/rust-vendor/markup5ever_rcdom/html5lib-tests/tree-construction/svg.dat +0 -104
  150. data/rust-vendor/markup5ever_rcdom/html5lib-tests/tree-construction/tables01.dat +0 -322
  151. data/rust-vendor/markup5ever_rcdom/html5lib-tests/tree-construction/template.dat +0 -1673
  152. data/rust-vendor/markup5ever_rcdom/html5lib-tests/tree-construction/tests1.dat +0 -1956
  153. data/rust-vendor/markup5ever_rcdom/html5lib-tests/tree-construction/tests10.dat +0 -849
  154. data/rust-vendor/markup5ever_rcdom/html5lib-tests/tree-construction/tests11.dat +0 -523
  155. data/rust-vendor/markup5ever_rcdom/html5lib-tests/tree-construction/tests12.dat +0 -62
  156. data/rust-vendor/markup5ever_rcdom/html5lib-tests/tree-construction/tests14.dat +0 -75
  157. data/rust-vendor/markup5ever_rcdom/html5lib-tests/tree-construction/tests15.dat +0 -216
  158. data/rust-vendor/markup5ever_rcdom/html5lib-tests/tree-construction/tests16.dat +0 -2602
  159. data/rust-vendor/markup5ever_rcdom/html5lib-tests/tree-construction/tests17.dat +0 -179
  160. data/rust-vendor/markup5ever_rcdom/html5lib-tests/tree-construction/tests18.dat +0 -558
  161. data/rust-vendor/markup5ever_rcdom/html5lib-tests/tree-construction/tests19.dat +0 -1398
  162. data/rust-vendor/markup5ever_rcdom/html5lib-tests/tree-construction/tests2.dat +0 -831
  163. data/rust-vendor/markup5ever_rcdom/html5lib-tests/tree-construction/tests20.dat +0 -842
  164. data/rust-vendor/markup5ever_rcdom/html5lib-tests/tree-construction/tests21.dat +0 -306
  165. data/rust-vendor/markup5ever_rcdom/html5lib-tests/tree-construction/tests22.dat +0 -190
  166. data/rust-vendor/markup5ever_rcdom/html5lib-tests/tree-construction/tests23.dat +0 -168
  167. data/rust-vendor/markup5ever_rcdom/html5lib-tests/tree-construction/tests24.dat +0 -79
  168. data/rust-vendor/markup5ever_rcdom/html5lib-tests/tree-construction/tests25.dat +0 -288
  169. data/rust-vendor/markup5ever_rcdom/html5lib-tests/tree-construction/tests26.dat +0 -453
  170. data/rust-vendor/markup5ever_rcdom/html5lib-tests/tree-construction/tests3.dat +0 -305
  171. data/rust-vendor/markup5ever_rcdom/html5lib-tests/tree-construction/tests4.dat +0 -74
  172. data/rust-vendor/markup5ever_rcdom/html5lib-tests/tree-construction/tests5.dat +0 -210
  173. data/rust-vendor/markup5ever_rcdom/html5lib-tests/tree-construction/tests6.dat +0 -663
  174. data/rust-vendor/markup5ever_rcdom/html5lib-tests/tree-construction/tests7.dat +0 -453
  175. data/rust-vendor/markup5ever_rcdom/html5lib-tests/tree-construction/tests8.dat +0 -165
  176. data/rust-vendor/markup5ever_rcdom/html5lib-tests/tree-construction/tests9.dat +0 -472
  177. data/rust-vendor/markup5ever_rcdom/html5lib-tests/tree-construction/tests_innerHTML_1.dat +0 -843
  178. data/rust-vendor/markup5ever_rcdom/html5lib-tests/tree-construction/tricky01.dat +0 -336
  179. data/rust-vendor/markup5ever_rcdom/html5lib-tests/tree-construction/webkit01.dat +0 -785
  180. data/rust-vendor/markup5ever_rcdom/html5lib-tests/tree-construction/webkit02.dat +0 -554
  181. data/rust-vendor/markup5ever_rcdom/tests/foreach_html5lib_test/mod.rs +0 -41
  182. data/rust-vendor/markup5ever_rcdom/tests/html-driver.rs +0 -29
  183. data/rust-vendor/markup5ever_rcdom/tests/html-serializer.rs +0 -265
  184. data/rust-vendor/markup5ever_rcdom/tests/html-tokenizer.rs +0 -487
  185. data/rust-vendor/markup5ever_rcdom/tests/html-tree-builder.rs +0 -298
  186. data/rust-vendor/markup5ever_rcdom/tests/html-tree-sink.rs +0 -141
  187. data/rust-vendor/markup5ever_rcdom/tests/util/find_tests.rs +0 -34
  188. data/rust-vendor/markup5ever_rcdom/tests/util/runner.rs +0 -48
  189. data/rust-vendor/markup5ever_rcdom/tests/xml-driver.rs +0 -101
  190. data/rust-vendor/markup5ever_rcdom/tests/xml-tokenizer.rs +0 -374
  191. data/rust-vendor/markup5ever_rcdom/tests/xml-tree-builder.rs +0 -237
  192. data/rust-vendor/markup5ever_rcdom/xml5lib-tests/AUTHORS.rst +0 -9
  193. data/rust-vendor/markup5ever_rcdom/xml5lib-tests/LICENSE +0 -21
  194. data/rust-vendor/markup5ever_rcdom/xml5lib-tests/tokenizer/README.md +0 -92
  195. data/rust-vendor/markup5ever_rcdom/xml5lib-tests/tokenizer/comments.test +0 -274
  196. data/rust-vendor/markup5ever_rcdom/xml5lib-tests/tokenizer/doctype.test +0 -3232
  197. data/rust-vendor/markup5ever_rcdom/xml5lib-tests/tokenizer/entities.test +0 -283
  198. data/rust-vendor/markup5ever_rcdom/xml5lib-tests/tokenizer/eof.test +0 -113
  199. data/rust-vendor/markup5ever_rcdom/xml5lib-tests/tokenizer/namedEntities.test +0 -42210
  200. data/rust-vendor/markup5ever_rcdom/xml5lib-tests/tokenizer/numericEntities.test +0 -1349
  201. data/rust-vendor/markup5ever_rcdom/xml5lib-tests/tokenizer/test1.test +0 -162
  202. data/rust-vendor/markup5ever_rcdom/xml5lib-tests/tokenizer/test2.test +0 -64
  203. data/rust-vendor/markup5ever_rcdom/xml5lib-tests/tokenizer/unicodeChars.test +0 -1295
  204. data/rust-vendor/markup5ever_rcdom/xml5lib-tests/tree-construction/README.md +0 -104
  205. data/rust-vendor/markup5ever_rcdom/xml5lib-tests/tree-construction/namespace.dat +0 -119
  206. data/rust-vendor/markup5ever_rcdom/xml5lib-tests/tree-construction/test1.dat +0 -124
  207. data/rust-vendor/xml5ever/.cargo-checksum.json +0 -1
  208. data/rust-vendor/xml5ever/.cargo_vcs_info.json +0 -6
  209. data/rust-vendor/xml5ever/Cargo.lock +0 -752
  210. data/rust-vendor/xml5ever/Cargo.toml +0 -69
  211. data/rust-vendor/xml5ever/Cargo.toml.orig +0 -29
  212. data/rust-vendor/xml5ever/LICENSE-APACHE +0 -201
  213. data/rust-vendor/xml5ever/LICENSE-MIT +0 -25
  214. data/rust-vendor/xml5ever/README.md +0 -72
  215. data/rust-vendor/xml5ever/benches/xml5ever.rs +0 -77
  216. data/rust-vendor/xml5ever/data/bench/strong.xml +0 -1
  217. data/rust-vendor/xml5ever/examples/README.md +0 -223
  218. data/rust-vendor/xml5ever/examples/example.xml +0 -3
  219. data/rust-vendor/xml5ever/examples/simple_xml_tokenizer.rs +0 -81
  220. data/rust-vendor/xml5ever/examples/xml_tokenizer.rs +0 -115
  221. data/rust-vendor/xml5ever/src/driver.rs +0 -90
  222. data/rust-vendor/xml5ever/src/lib.rs +0 -47
  223. data/rust-vendor/xml5ever/src/macros.rs +0 -18
  224. data/rust-vendor/xml5ever/src/serialize/mod.rs +0 -216
  225. data/rust-vendor/xml5ever/src/tokenizer/char_ref/mod.rs +0 -456
  226. data/rust-vendor/xml5ever/src/tokenizer/interface.rs +0 -116
  227. data/rust-vendor/xml5ever/src/tokenizer/mod.rs +0 -1344
  228. data/rust-vendor/xml5ever/src/tokenizer/qname.rs +0 -84
  229. data/rust-vendor/xml5ever/src/tokenizer/states.rs +0 -167
  230. data/rust-vendor/xml5ever/src/tree_builder/mod.rs +0 -774
  231. data/rust-vendor/xml5ever/src/tree_builder/types.rs +0 -37
@@ -1,336 +0,0 @@
1
- #data
2
- <b><p>Bold </b> Not bold</p>
3
- Also not bold.
4
- #errors
5
- (1,3): expected-doctype-but-got-start-tag
6
- (1,15): adoption-agency-1.3
7
- #document
8
- | <html>
9
- | <head>
10
- | <body>
11
- | <b>
12
- | <p>
13
- | <b>
14
- | "Bold "
15
- | " Not bold"
16
- | "
17
- Also not bold."
18
-
19
- #data
20
- <html>
21
- <font color=red><i>Italic and Red<p>Italic and Red </font> Just italic.</p> Italic only.</i> Plain
22
- <p>I should not be red. <font color=red>Red. <i>Italic and red.</p>
23
- <p>Italic and red. </i> Red.</font> I should not be red.</p>
24
- <b>Bold <i>Bold and italic</b> Only Italic </i> Plain
25
- #errors
26
- (1,6): expected-doctype-but-got-start-tag
27
- (2,58): adoption-agency-1.3
28
- (3,67): unexpected-end-tag
29
- (4,23): adoption-agency-1.3
30
- (4,35): adoption-agency-1.3
31
- (5,30): adoption-agency-1.3
32
- #document
33
- | <html>
34
- | <head>
35
- | <body>
36
- | <font>
37
- | color="red"
38
- | <i>
39
- | "Italic and Red"
40
- | <i>
41
- | <p>
42
- | <font>
43
- | color="red"
44
- | "Italic and Red "
45
- | " Just italic."
46
- | " Italic only."
47
- | " Plain
48
- "
49
- | <p>
50
- | "I should not be red. "
51
- | <font>
52
- | color="red"
53
- | "Red. "
54
- | <i>
55
- | "Italic and red."
56
- | <font>
57
- | color="red"
58
- | <i>
59
- | "
60
- "
61
- | <p>
62
- | <font>
63
- | color="red"
64
- | <i>
65
- | "Italic and red. "
66
- | " Red."
67
- | " I should not be red."
68
- | "
69
- "
70
- | <b>
71
- | "Bold "
72
- | <i>
73
- | "Bold and italic"
74
- | <i>
75
- | " Only Italic "
76
- | " Plain"
77
-
78
- #data
79
- <html><body>
80
- <p><font size="7">First paragraph.</p>
81
- <p>Second paragraph.</p></font>
82
- <b><p><i>Bold and Italic</b> Italic</p>
83
- #errors
84
- (1,6): expected-doctype-but-got-start-tag
85
- (2,38): unexpected-end-tag
86
- (4,28): adoption-agency-1.3
87
- (4,28): adoption-agency-1.3
88
- (4,39): unexpected-end-tag
89
- #document
90
- | <html>
91
- | <head>
92
- | <body>
93
- | "
94
- "
95
- | <p>
96
- | <font>
97
- | size="7"
98
- | "First paragraph."
99
- | <font>
100
- | size="7"
101
- | "
102
- "
103
- | <p>
104
- | "Second paragraph."
105
- | "
106
- "
107
- | <b>
108
- | <p>
109
- | <b>
110
- | <i>
111
- | "Bold and Italic"
112
- | <i>
113
- | " Italic"
114
-
115
- #data
116
- <html>
117
- <dl>
118
- <dt><b>Boo
119
- <dd>Goo?
120
- </dl>
121
- </html>
122
- #errors
123
- (1,6): expected-doctype-but-got-start-tag
124
- (4,4): end-tag-too-early
125
- (5,5): end-tag-too-early
126
- (6,7): expected-one-end-tag-but-got-another
127
- #document
128
- | <html>
129
- | <head>
130
- | <body>
131
- | <dl>
132
- | "
133
- "
134
- | <dt>
135
- | <b>
136
- | "Boo
137
- "
138
- | <dd>
139
- | <b>
140
- | "Goo?
141
- "
142
- | <b>
143
- | "
144
- "
145
-
146
- #data
147
- <html><body>
148
- <label><a><div>Hello<div>World</div></a></label>
149
- </body></html>
150
- #errors
151
- (1,6): expected-doctype-but-got-start-tag
152
- (2,40): adoption-agency-1.3
153
- (2,48): unexpected-end-tag
154
- (3,7): expected-one-end-tag-but-got-another
155
- #document
156
- | <html>
157
- | <head>
158
- | <body>
159
- | "
160
- "
161
- | <label>
162
- | <a>
163
- | <div>
164
- | <a>
165
- | "Hello"
166
- | <div>
167
- | "World"
168
- | "
169
- "
170
-
171
- #data
172
- <table><center> <font>a</center> <img> <tr><td> </td> </tr> </table>
173
- #errors
174
- (1,7): expected-doctype-but-got-start-tag
175
- (1,15): foster-parenting-start-tag
176
- (1,16): foster-parenting-character
177
- (1,22): foster-parenting-start-tag
178
- (1,23): foster-parenting-character
179
- (1,32): foster-parenting-end-tag
180
- (1,32): end-tag-too-early
181
- (1,33): foster-parenting-character
182
- (1,38): foster-parenting-start-tag
183
- #document
184
- | <html>
185
- | <head>
186
- | <body>
187
- | <center>
188
- | " "
189
- | <font>
190
- | "a"
191
- | <font>
192
- | <img>
193
- | " "
194
- | <table>
195
- | " "
196
- | <tbody>
197
- | <tr>
198
- | <td>
199
- | " "
200
- | " "
201
- | " "
202
-
203
- #data
204
- <table><tr><p><a><p>You should see this text.
205
- #errors
206
- (1,7): expected-doctype-but-got-start-tag
207
- (1,14): unexpected-start-tag-implies-table-voodoo
208
- (1,17): unexpected-start-tag-implies-table-voodoo
209
- (1,20): unexpected-start-tag-implies-table-voodoo
210
- (1,20): closing-non-current-p-element
211
- (1,21): foster-parenting-character
212
- (1,22): foster-parenting-character
213
- (1,23): foster-parenting-character
214
- (1,24): foster-parenting-character
215
- (1,25): foster-parenting-character
216
- (1,26): foster-parenting-character
217
- (1,27): foster-parenting-character
218
- (1,28): foster-parenting-character
219
- (1,29): foster-parenting-character
220
- (1,30): foster-parenting-character
221
- (1,31): foster-parenting-character
222
- (1,32): foster-parenting-character
223
- (1,33): foster-parenting-character
224
- (1,34): foster-parenting-character
225
- (1,35): foster-parenting-character
226
- (1,36): foster-parenting-character
227
- (1,37): foster-parenting-character
228
- (1,38): foster-parenting-character
229
- (1,39): foster-parenting-character
230
- (1,40): foster-parenting-character
231
- (1,41): foster-parenting-character
232
- (1,42): foster-parenting-character
233
- (1,43): foster-parenting-character
234
- (1,44): foster-parenting-character
235
- (1,45): foster-parenting-character
236
- (1,45): eof-in-table
237
- #document
238
- | <html>
239
- | <head>
240
- | <body>
241
- | <p>
242
- | <a>
243
- | <p>
244
- | <a>
245
- | "You should see this text."
246
- | <table>
247
- | <tbody>
248
- | <tr>
249
-
250
- #data
251
- <TABLE>
252
- <TR>
253
- <CENTER><CENTER><TD></TD></TR><TR>
254
- <FONT>
255
- <TABLE><tr></tr></TABLE>
256
- </P>
257
- <a></font><font></a>
258
- This page contains an insanely badly-nested tag sequence.
259
- #errors
260
- (1,7): expected-doctype-but-got-start-tag
261
- (3,8): unexpected-start-tag-implies-table-voodoo
262
- (3,16): unexpected-start-tag-implies-table-voodoo
263
- (4,6): unexpected-start-tag-implies-table-voodoo
264
- (4,6): unexpected character token in table (the newline)
265
- (5,7): unexpected-start-tag-implies-end-tag
266
- (6,4): unexpected p end tag
267
- (7,10): adoption-agency-1.3
268
- (7,20): adoption-agency-1.3
269
- (8,57): expected-closing-tag-but-got-eof
270
- #document
271
- | <html>
272
- | <head>
273
- | <body>
274
- | <center>
275
- | <center>
276
- | <font>
277
- | "
278
- "
279
- | <table>
280
- | "
281
- "
282
- | <tbody>
283
- | <tr>
284
- | "
285
- "
286
- | <td>
287
- | <tr>
288
- | "
289
- "
290
- | <table>
291
- | <tbody>
292
- | <tr>
293
- | <font>
294
- | "
295
- "
296
- | <p>
297
- | "
298
- "
299
- | <a>
300
- | <a>
301
- | <font>
302
- | <font>
303
- | "
304
- This page contains an insanely badly-nested tag sequence."
305
-
306
- #data
307
- <html>
308
- <body>
309
- <b><nobr><div>This text is in a div inside a nobr</nobr>More text that should not be in the nobr, i.e., the
310
- nobr should have closed the div inside it implicitly. </b><pre>A pre tag outside everything else.</pre>
311
- </body>
312
- </html>
313
- #errors
314
- (1,6): expected-doctype-but-got-start-tag
315
- (3,56): adoption-agency-1.3
316
- (4,58): adoption-agency-1.3
317
- (5,7): expected-one-end-tag-but-got-another
318
- #document
319
- | <html>
320
- | <head>
321
- | <body>
322
- | "
323
- "
324
- | <b>
325
- | <nobr>
326
- | <div>
327
- | <b>
328
- | <nobr>
329
- | "This text is in a div inside a nobr"
330
- | "More text that should not be in the nobr, i.e., the
331
- nobr should have closed the div inside it implicitly. "
332
- | <pre>
333
- | "A pre tag outside everything else."
334
- | "
335
-
336
- "