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
@@ -1,831 +0,0 @@
1
- #data
2
- <!DOCTYPE html>Test
3
- #errors
4
- #document
5
- | <!DOCTYPE html>
6
- | <html>
7
- | <head>
8
- | <body>
9
- | "Test"
10
-
11
- #data
12
- <textarea>test</div>test
13
- #errors
14
- (1,10): expected-doctype-but-got-start-tag
15
- (1,24): expected-closing-tag-but-got-eof
16
- #document
17
- | <html>
18
- | <head>
19
- | <body>
20
- | <textarea>
21
- | "test</div>test"
22
-
23
- #data
24
- <table><td>
25
- #errors
26
- (1,7): expected-doctype-but-got-start-tag
27
- (1,11): unexpected-cell-in-table-body
28
- (1,11): expected-closing-tag-but-got-eof
29
- #document
30
- | <html>
31
- | <head>
32
- | <body>
33
- | <table>
34
- | <tbody>
35
- | <tr>
36
- | <td>
37
-
38
- #data
39
- <table><td>test</tbody></table>
40
- #errors
41
- (1,7): expected-doctype-but-got-start-tag
42
- (1,11): unexpected-cell-in-table-body
43
- #document
44
- | <html>
45
- | <head>
46
- | <body>
47
- | <table>
48
- | <tbody>
49
- | <tr>
50
- | <td>
51
- | "test"
52
-
53
- #data
54
- <frame>test
55
- #errors
56
- (1,7): expected-doctype-but-got-start-tag
57
- (1,7): unexpected-start-tag-ignored
58
- #document
59
- | <html>
60
- | <head>
61
- | <body>
62
- | "test"
63
-
64
- #data
65
- <!DOCTYPE html><frameset>test
66
- #errors
67
- (1,29): unexpected-char-in-frameset
68
- (1,29): unexpected-char-in-frameset
69
- (1,29): unexpected-char-in-frameset
70
- (1,29): unexpected-char-in-frameset
71
- (1,29): eof-in-frameset
72
- #document
73
- | <!DOCTYPE html>
74
- | <html>
75
- | <head>
76
- | <frameset>
77
-
78
- #data
79
- <!DOCTYPE html><frameset> te st
80
- #errors
81
- (1,29): unexpected-char-in-frameset
82
- (1,29): unexpected-char-in-frameset
83
- (1,29): unexpected-char-in-frameset
84
- (1,29): unexpected-char-in-frameset
85
- (1,29): eof-in-frameset
86
- #document
87
- | <!DOCTYPE html>
88
- | <html>
89
- | <head>
90
- | <frameset>
91
- | " "
92
-
93
- #data
94
- <!DOCTYPE html><frameset></frameset> te st
95
- #errors
96
- (1,29): unexpected-char-after-frameset
97
- (1,29): unexpected-char-after-frameset
98
- (1,29): unexpected-char-after-frameset
99
- (1,29): unexpected-char-after-frameset
100
- #document
101
- | <!DOCTYPE html>
102
- | <html>
103
- | <head>
104
- | <frameset>
105
- | " "
106
-
107
- #data
108
- <!DOCTYPE html><frameset><!DOCTYPE html>
109
- #errors
110
- (1,40): unexpected-doctype
111
- (1,40): eof-in-frameset
112
- #document
113
- | <!DOCTYPE html>
114
- | <html>
115
- | <head>
116
- | <frameset>
117
-
118
- #data
119
- <!DOCTYPE html><font><p><b>test</font>
120
- #errors
121
- (1,38): adoption-agency-1.3
122
- (1,38): adoption-agency-1.3
123
- #document
124
- | <!DOCTYPE html>
125
- | <html>
126
- | <head>
127
- | <body>
128
- | <font>
129
- | <p>
130
- | <font>
131
- | <b>
132
- | "test"
133
-
134
- #data
135
- <!DOCTYPE html><dt><div><dd>
136
- #errors
137
- (1,28): end-tag-too-early
138
- #document
139
- | <!DOCTYPE html>
140
- | <html>
141
- | <head>
142
- | <body>
143
- | <dt>
144
- | <div>
145
- | <dd>
146
-
147
- #data
148
- <script></x
149
- #errors
150
- (1,8): expected-doctype-but-got-start-tag
151
- (1,11): expected-named-closing-tag-but-got-eof
152
- #document
153
- | <html>
154
- | <head>
155
- | <script>
156
- | "</x"
157
- | <body>
158
-
159
- #data
160
- <table><plaintext><td>
161
- #errors
162
- (1,7): expected-doctype-but-got-start-tag
163
- (1,18): unexpected-start-tag-implies-table-voodoo
164
- (1,22): foster-parenting-character-in-table
165
- (1,22): foster-parenting-character-in-table
166
- (1,22): foster-parenting-character-in-table
167
- (1,22): foster-parenting-character-in-table
168
- (1,22): eof-in-table
169
- #document
170
- | <html>
171
- | <head>
172
- | <body>
173
- | <plaintext>
174
- | "<td>"
175
- | <table>
176
-
177
- #data
178
- <plaintext></plaintext>
179
- #errors
180
- (1,11): expected-doctype-but-got-start-tag
181
- (1,23): expected-closing-tag-but-got-eof
182
- #document
183
- | <html>
184
- | <head>
185
- | <body>
186
- | <plaintext>
187
- | "</plaintext>"
188
-
189
- #data
190
- <!DOCTYPE html><table><tr>TEST
191
- #errors
192
- (1,30): foster-parenting-character-in-table
193
- (1,30): foster-parenting-character-in-table
194
- (1,30): foster-parenting-character-in-table
195
- (1,30): foster-parenting-character-in-table
196
- (1,30): eof-in-table
197
- #document
198
- | <!DOCTYPE html>
199
- | <html>
200
- | <head>
201
- | <body>
202
- | "TEST"
203
- | <table>
204
- | <tbody>
205
- | <tr>
206
-
207
- #data
208
- <!DOCTYPE html><body t1=1><body t2=2><body t3=3 t4=4>
209
- #errors
210
- (1,37): unexpected-start-tag
211
- (1,53): unexpected-start-tag
212
- #document
213
- | <!DOCTYPE html>
214
- | <html>
215
- | <head>
216
- | <body>
217
- | t1="1"
218
- | t2="2"
219
- | t3="3"
220
- | t4="4"
221
-
222
- #data
223
- </b test
224
- #errors
225
- (1,8): eof-in-attribute-name
226
- (1,8): expected-doctype-but-got-eof
227
- #new-errors
228
- (1:9) eof-in-tag
229
- #document
230
- | <html>
231
- | <head>
232
- | <body>
233
-
234
- #data
235
- <!DOCTYPE html></b test<b &=&amp>X
236
- #errors
237
- (1,24): invalid-character-in-attribute-name
238
- (1,32): named-entity-without-semicolon
239
- (1,33): attributes-in-end-tag
240
- (1,33): unexpected-end-tag-before-html
241
- #new-errors
242
- (1:24) unexpected-character-in-attribute-name
243
- (1:33) missing-semicolon-after-character-reference
244
- (1:33) end-tag-with-attributes
245
- #document
246
- | <!DOCTYPE html>
247
- | <html>
248
- | <head>
249
- | <body>
250
- | "X"
251
-
252
- #data
253
- <!doctypehtml><scrIPt type=text/x-foobar;baz>X</SCRipt
254
- #errors
255
- (1,9): need-space-after-doctype
256
- (1,54): expected-named-closing-tag-but-got-eof
257
- #new-errors
258
- (1:10) missing-whitespace-before-doctype-name
259
- #document
260
- | <!DOCTYPE html>
261
- | <html>
262
- | <head>
263
- | <script>
264
- | type="text/x-foobar;baz"
265
- | "X</SCRipt"
266
- | <body>
267
-
268
- #data
269
- &
270
- #errors
271
- (1,1): expected-doctype-but-got-chars
272
- #document
273
- | <html>
274
- | <head>
275
- | <body>
276
- | "&"
277
-
278
- #data
279
- &#
280
- #errors
281
- (1,2): expected-numeric-entity
282
- (1,2): expected-doctype-but-got-chars
283
- #new-errors
284
- (1:3) absence-of-digits-in-numeric-character-reference
285
- #document
286
- | <html>
287
- | <head>
288
- | <body>
289
- | "&#"
290
-
291
- #data
292
- &#X
293
- #errors
294
- (1,3): expected-numeric-entity
295
- (1,3): expected-doctype-but-got-chars
296
- #new-errors
297
- (1:4) absence-of-digits-in-numeric-character-reference
298
- #document
299
- | <html>
300
- | <head>
301
- | <body>
302
- | "&#X"
303
-
304
- #data
305
- &#x
306
- #errors
307
- (1,3): expected-numeric-entity
308
- (1,3): expected-doctype-but-got-chars
309
- #new-errors
310
- (1:4) absence-of-digits-in-numeric-character-reference
311
- #document
312
- | <html>
313
- | <head>
314
- | <body>
315
- | "&#x"
316
-
317
- #data
318
- &#45
319
- #errors
320
- (1,4): numeric-entity-without-semicolon
321
- (1,4): expected-doctype-but-got-chars
322
- #new-errors
323
- (1:5) missing-semicolon-after-character-reference
324
- #document
325
- | <html>
326
- | <head>
327
- | <body>
328
- | "-"
329
-
330
- #data
331
- &x-test
332
- #errors
333
- (1,2): expected-doctype-but-got-chars
334
- #document
335
- | <html>
336
- | <head>
337
- | <body>
338
- | "&x-test"
339
-
340
- #data
341
- <!doctypehtml><p><li>
342
- #errors
343
- (1,9): need-space-after-doctype
344
- #new-errors
345
- (1:10) missing-whitespace-before-doctype-name
346
- #document
347
- | <!DOCTYPE html>
348
- | <html>
349
- | <head>
350
- | <body>
351
- | <p>
352
- | <li>
353
-
354
- #data
355
- <!doctypehtml><p><dt>
356
- #errors
357
- (1,9): need-space-after-doctype
358
- #new-errors
359
- (1:10) missing-whitespace-before-doctype-name
360
- #document
361
- | <!DOCTYPE html>
362
- | <html>
363
- | <head>
364
- | <body>
365
- | <p>
366
- | <dt>
367
-
368
- #data
369
- <!doctypehtml><p><dd>
370
- #errors
371
- (1,9): need-space-after-doctype
372
- #new-errors
373
- (1:10) missing-whitespace-before-doctype-name
374
- #document
375
- | <!DOCTYPE html>
376
- | <html>
377
- | <head>
378
- | <body>
379
- | <p>
380
- | <dd>
381
-
382
- #data
383
- <!doctypehtml><p><form>
384
- #errors
385
- (1,9): need-space-after-doctype
386
- (1,23): expected-closing-tag-but-got-eof
387
- #new-errors
388
- (1:10) missing-whitespace-before-doctype-name
389
- #document
390
- | <!DOCTYPE html>
391
- | <html>
392
- | <head>
393
- | <body>
394
- | <p>
395
- | <form>
396
-
397
- #data
398
- <!DOCTYPE html><p></P>X
399
- #errors
400
- #document
401
- | <!DOCTYPE html>
402
- | <html>
403
- | <head>
404
- | <body>
405
- | <p>
406
- | "X"
407
-
408
- #data
409
- &AMP
410
- #errors
411
- (1,4): named-entity-without-semicolon
412
- (1,4): expected-doctype-but-got-chars
413
- #new-errors
414
- (1:5) missing-semicolon-after-character-reference
415
- #document
416
- | <html>
417
- | <head>
418
- | <body>
419
- | "&"
420
-
421
- #data
422
- &AMp;
423
- #errors
424
- (1,3): expected-named-entity
425
- (1,3): expected-doctype-but-got-chars
426
- #new-errors
427
- (1:5) unknown-named-character-reference
428
- #document
429
- | <html>
430
- | <head>
431
- | <body>
432
- | "&AMp;"
433
-
434
- #data
435
- <!DOCTYPE html><html><head></head><body><thisISasillyTESTelementNameToMakeSureCrazyTagNamesArePARSEDcorrectLY>
436
- #errors
437
- (1,110): expected-closing-tag-but-got-eof
438
- #document
439
- | <!DOCTYPE html>
440
- | <html>
441
- | <head>
442
- | <body>
443
- | <thisisasillytestelementnametomakesurecrazytagnamesareparsedcorrectly>
444
-
445
- #data
446
- <!DOCTYPE html>X</body>X
447
- #errors
448
- (1,24): unexpected-char-after-body
449
- #document
450
- | <!DOCTYPE html>
451
- | <html>
452
- | <head>
453
- | <body>
454
- | "XX"
455
-
456
- #data
457
- <!DOCTYPE html><!-- X
458
- #errors
459
- (1,21): eof-in-comment
460
- #new-errors
461
- (1:22) eof-in-comment
462
- #document
463
- | <!DOCTYPE html>
464
- | <!-- X -->
465
- | <html>
466
- | <head>
467
- | <body>
468
-
469
- #data
470
- <!DOCTYPE html><table><caption>test TEST</caption><td>test
471
- #errors
472
- (1,54): unexpected-cell-in-table-body
473
- (1,58): expected-closing-tag-but-got-eof
474
- #document
475
- | <!DOCTYPE html>
476
- | <html>
477
- | <head>
478
- | <body>
479
- | <table>
480
- | <caption>
481
- | "test TEST"
482
- | <tbody>
483
- | <tr>
484
- | <td>
485
- | "test"
486
-
487
- #data
488
- <!DOCTYPE html><select><option><optgroup>
489
- #errors
490
- (1,41): eof-in-select
491
- #document
492
- | <!DOCTYPE html>
493
- | <html>
494
- | <head>
495
- | <body>
496
- | <select>
497
- | <option>
498
- | <optgroup>
499
-
500
- #data
501
- <!DOCTYPE html><select><optgroup><option></optgroup><option><select><option>
502
- #errors
503
- (1,68): unexpected-select-in-select
504
- #document
505
- | <!DOCTYPE html>
506
- | <html>
507
- | <head>
508
- | <body>
509
- | <select>
510
- | <optgroup>
511
- | <option>
512
- | <option>
513
- | <option>
514
-
515
- #data
516
- <!DOCTYPE html><select><optgroup><option><optgroup>
517
- #errors
518
- (1,51): eof-in-select
519
- #document
520
- | <!DOCTYPE html>
521
- | <html>
522
- | <head>
523
- | <body>
524
- | <select>
525
- | <optgroup>
526
- | <option>
527
- | <optgroup>
528
-
529
- #data
530
- <!DOCTYPE html><datalist><option>foo</datalist>bar
531
- #errors
532
- #document
533
- | <!DOCTYPE html>
534
- | <html>
535
- | <head>
536
- | <body>
537
- | <datalist>
538
- | <option>
539
- | "foo"
540
- | "bar"
541
-
542
- #data
543
- <!DOCTYPE html><font><input><input></font>
544
- #errors
545
- #document
546
- | <!DOCTYPE html>
547
- | <html>
548
- | <head>
549
- | <body>
550
- | <font>
551
- | <input>
552
- | <input>
553
-
554
- #data
555
- <!DOCTYPE html><!-- XXX - XXX -->
556
- #errors
557
- #document
558
- | <!DOCTYPE html>
559
- | <!-- XXX - XXX -->
560
- | <html>
561
- | <head>
562
- | <body>
563
-
564
- #data
565
- <!DOCTYPE html><!-- XXX - XXX
566
- #errors
567
- (1,29): eof-in-comment
568
- #new-errors
569
- (1:30) eof-in-comment
570
- #document
571
- | <!DOCTYPE html>
572
- | <!-- XXX - XXX -->
573
- | <html>
574
- | <head>
575
- | <body>
576
-
577
- #data
578
- <!DOCTYPE html><!-- XXX - XXX - XXX -->
579
- #errors
580
- #document
581
- | <!DOCTYPE html>
582
- | <!-- XXX - XXX - XXX -->
583
- | <html>
584
- | <head>
585
- | <body>
586
-
587
- #data
588
- <!DOCTYPE html> <!DOCTYPE html>
589
- #errors
590
- Line: 1 Col: 31 Unexpected DOCTYPE. Ignored.
591
- #document
592
- | <!DOCTYPE html>
593
- | <html>
594
- | <head>
595
- | <body>
596
-
597
- #data
598
- test
599
- test
600
- #errors
601
- (2,4): expected-doctype-but-got-chars
602
- #document
603
- | <html>
604
- | <head>
605
- | <body>
606
- | "test
607
- test"
608
-
609
- #data
610
- <!DOCTYPE html><body><title>test</body></title>
611
- #errors
612
- #document
613
- | <!DOCTYPE html>
614
- | <html>
615
- | <head>
616
- | <body>
617
- | <title>
618
- | "test</body>"
619
-
620
- #data
621
- <!DOCTYPE html><body><title>X</title><meta name=z><link rel=foo><style>
622
- x { content:"</style" } </style>
623
- #errors
624
- #document
625
- | <!DOCTYPE html>
626
- | <html>
627
- | <head>
628
- | <body>
629
- | <title>
630
- | "X"
631
- | <meta>
632
- | name="z"
633
- | <link>
634
- | rel="foo"
635
- | <style>
636
- | "
637
- x { content:"</style" } "
638
-
639
- #data
640
- <!DOCTYPE html><select><optgroup></optgroup></select>
641
- #errors
642
- #document
643
- | <!DOCTYPE html>
644
- | <html>
645
- | <head>
646
- | <body>
647
- | <select>
648
- | <optgroup>
649
-
650
- #data
651
-
652
-
653
- #errors
654
- (2,1): expected-doctype-but-got-eof
655
- #document
656
- | <html>
657
- | <head>
658
- | <body>
659
-
660
- #data
661
- <!DOCTYPE html> <html>
662
- #errors
663
- #document
664
- | <!DOCTYPE html>
665
- | <html>
666
- | <head>
667
- | <body>
668
-
669
- #data
670
- <!DOCTYPE html><script>
671
- </script> <title>x</title> </head>
672
- #errors
673
- #document
674
- | <!DOCTYPE html>
675
- | <html>
676
- | <head>
677
- | <script>
678
- | "
679
- "
680
- | " "
681
- | <title>
682
- | "x"
683
- | " "
684
- | <body>
685
-
686
- #data
687
- <!DOCTYPE html><html><body><html id=x>
688
- #errors
689
- (1,38): non-html-root
690
- #document
691
- | <!DOCTYPE html>
692
- | <html>
693
- | id="x"
694
- | <head>
695
- | <body>
696
-
697
- #data
698
- <!DOCTYPE html>X</body><html id="x">
699
- #errors
700
- (1,36): non-html-root
701
- #document
702
- | <!DOCTYPE html>
703
- | <html>
704
- | id="x"
705
- | <head>
706
- | <body>
707
- | "X"
708
-
709
- #data
710
- <!DOCTYPE html><head><html id=x>
711
- #errors
712
- (1,32): non-html-root
713
- #document
714
- | <!DOCTYPE html>
715
- | <html>
716
- | id="x"
717
- | <head>
718
- | <body>
719
-
720
- #data
721
- <!DOCTYPE html>X</html>X
722
- #errors
723
- (1,24): expected-eof-but-got-char
724
- #document
725
- | <!DOCTYPE html>
726
- | <html>
727
- | <head>
728
- | <body>
729
- | "XX"
730
-
731
- #data
732
- <!DOCTYPE html>X</html>
733
- #errors
734
- #document
735
- | <!DOCTYPE html>
736
- | <html>
737
- | <head>
738
- | <body>
739
- | "X "
740
-
741
- #data
742
- <!DOCTYPE html>X</html><p>X
743
- #errors
744
- (1,26): expected-eof-but-got-start-tag
745
- #document
746
- | <!DOCTYPE html>
747
- | <html>
748
- | <head>
749
- | <body>
750
- | "X"
751
- | <p>
752
- | "X"
753
-
754
- #data
755
- <!DOCTYPE html>X<p/x/y/z>
756
- #errors
757
- (1,19): unexpected-character-after-solidus-in-tag
758
- (1,21): unexpected-character-after-solidus-in-tag
759
- (1,23): unexpected-character-after-solidus-in-tag
760
- #new-errors
761
- (1:20) unexpected-solidus-in-tag
762
- (1:22) unexpected-solidus-in-tag
763
- (1:24) unexpected-solidus-in-tag
764
- #document
765
- | <!DOCTYPE html>
766
- | <html>
767
- | <head>
768
- | <body>
769
- | "X"
770
- | <p>
771
- | x=""
772
- | y=""
773
- | z=""
774
-
775
- #data
776
- <!DOCTYPE html><!--x--
777
- #errors
778
- (1,22): eof-in-comment-double-dash
779
- #new-errors
780
- (1:23) eof-in-comment
781
- #document
782
- | <!DOCTYPE html>
783
- | <!-- x -->
784
- | <html>
785
- | <head>
786
- | <body>
787
-
788
- #data
789
- <!DOCTYPE html><table><tr><td></p></table>
790
- #errors
791
- (1,34): unexpected-end-tag
792
- #document
793
- | <!DOCTYPE html>
794
- | <html>
795
- | <head>
796
- | <body>
797
- | <table>
798
- | <tbody>
799
- | <tr>
800
- | <td>
801
- | <p>
802
-
803
- #data
804
- <!DOCTYPE <!DOCTYPE HTML>><!--<!--x-->-->
805
- #errors
806
- (1,20): expected-space-or-right-bracket-in-doctype
807
- (1,25): unknown-doctype
808
- (1,35): unexpected-char-in-comment
809
- #new-errors
810
- (1:21) invalid-character-sequence-after-doctype-name
811
- (1:35) nested-comment
812
- #document
813
- | <!DOCTYPE <!doctype>
814
- | <html>
815
- | <head>
816
- | <body>
817
- | ">"
818
- | <!-- <!--x -->
819
- | "-->"
820
-
821
- #data
822
- <!doctype html><div><form></form><div></div></div>
823
- #errors
824
- #document
825
- | <!DOCTYPE html>
826
- | <html>
827
- | <head>
828
- | <body>
829
- | <div>
830
- | <form>
831
- | <div>