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
@@ -1,554 +0,0 @@
1
- #data
2
- <foo bar=qux/>
3
- #errors
4
- (1,14): expected-doctype-but-got-start-tag
5
- (1,14): expected-closing-tag-but-got-eof
6
- #document
7
- | <html>
8
- | <head>
9
- | <body>
10
- | <foo>
11
- | bar="qux/"
12
-
13
- #data
14
- <p id="status"><noscript><strong>A</strong></noscript><span>B</span></p>
15
- #errors
16
- (1,15): expected-doctype-but-got-start-tag
17
- #script-on
18
- #document
19
- | <html>
20
- | <head>
21
- | <body>
22
- | <p>
23
- | id="status"
24
- | <noscript>
25
- | "<strong>A</strong>"
26
- | <span>
27
- | "B"
28
-
29
- #data
30
- <p id="status"><noscript><strong>A</strong></noscript><span>B</span></p>
31
- #errors
32
- (1,15): expected-doctype-but-got-start-tag
33
- #script-off
34
- #document
35
- | <html>
36
- | <head>
37
- | <body>
38
- | <p>
39
- | id="status"
40
- | <noscript>
41
- | <strong>
42
- | "A"
43
- | <span>
44
- | "B"
45
-
46
- #data
47
- <div><sarcasm><div></div></sarcasm></div>
48
- #errors
49
- (1,5): expected-doctype-but-got-start-tag
50
- #document
51
- | <html>
52
- | <head>
53
- | <body>
54
- | <div>
55
- | <sarcasm>
56
- | <div>
57
-
58
- #data
59
- <html><body><img src="" border="0" alt="><div>A</div></body></html>
60
- #errors
61
- (1,6): expected-doctype-but-got-start-tag
62
- (1,67): eof-in-attribute-value-double-quote
63
- #new-errors
64
- (1:68) eof-in-tag
65
- #document
66
- | <html>
67
- | <head>
68
- | <body>
69
-
70
- #data
71
- <table><td></tbody>A
72
- #errors
73
- (1,7): expected-doctype-but-got-start-tag
74
- (1,11): unexpected-cell-in-table-body
75
- (1,20): foster-parenting-character
76
- (1,20): eof-in-table
77
- #document
78
- | <html>
79
- | <head>
80
- | <body>
81
- | "A"
82
- | <table>
83
- | <tbody>
84
- | <tr>
85
- | <td>
86
-
87
- #data
88
- <table><td></thead>A
89
- #errors
90
- (1,7): expected-doctype-but-got-start-tag
91
- (1,11): unexpected-cell-in-table-body
92
- (1,19): XXX-undefined-error
93
- (1,20): expected-closing-tag-but-got-eof
94
- #document
95
- | <html>
96
- | <head>
97
- | <body>
98
- | <table>
99
- | <tbody>
100
- | <tr>
101
- | <td>
102
- | "A"
103
-
104
- #data
105
- <table><td></tfoot>A
106
- #errors
107
- (1,7): expected-doctype-but-got-start-tag
108
- (1,11): unexpected-cell-in-table-body
109
- (1,19): XXX-undefined-error
110
- (1,20): expected-closing-tag-but-got-eof
111
- #document
112
- | <html>
113
- | <head>
114
- | <body>
115
- | <table>
116
- | <tbody>
117
- | <tr>
118
- | <td>
119
- | "A"
120
-
121
- #data
122
- <table><thead><td></tbody>A
123
- #errors
124
- (1,7): expected-doctype-but-got-start-tag
125
- (1,18): unexpected-cell-in-table-body
126
- (1,26): XXX-undefined-error
127
- (1,27): expected-closing-tag-but-got-eof
128
- #document
129
- | <html>
130
- | <head>
131
- | <body>
132
- | <table>
133
- | <thead>
134
- | <tr>
135
- | <td>
136
- | "A"
137
-
138
- #data
139
- <legend>test</legend>
140
- #errors
141
- (1,7): expected-doctype-but-got-start-tag
142
- #document
143
- | <html>
144
- | <head>
145
- | <body>
146
- | <legend>
147
- | "test"
148
-
149
- #data
150
- <table><input>
151
- #errors
152
- (1,7): expected-doctype-but-got-start-tag
153
- (1,14): foster-parenting-start-tag
154
- (1,15): expected-closing-tag-but-got-eof
155
- #document
156
- | <html>
157
- | <head>
158
- | <body>
159
- | <input>
160
- | <table>
161
-
162
- #data
163
- <b><em><dcell><postfield><postfield><postfield><postfield><missing_glyph><missing_glyph><missing_glyph><missing_glyph><hkern><aside></b></em>
164
- #errors
165
- unexpected-b-end-tag
166
- unexpected-em-end-tag
167
- eof-in-aside
168
- #document-fragment
169
- div
170
- #document
171
- | <b>
172
- | <em>
173
- | <dcell>
174
- | <postfield>
175
- | <postfield>
176
- | <postfield>
177
- | <postfield>
178
- | <missing_glyph>
179
- | <missing_glyph>
180
- | <missing_glyph>
181
- | <missing_glyph>
182
- | <hkern>
183
- | <aside>
184
- | <b>
185
-
186
- #data
187
- <b><em><foo><foo><aside></b>
188
- #errors
189
- (1,3): expected-doctype-but-got-start-tag
190
- (1,28): adoption-agency-9
191
- (1,29): expected-closing-tag-but-got-eof
192
- #document
193
- | <html>
194
- | <head>
195
- | <body>
196
- | <b>
197
- | <em>
198
- | <foo>
199
- | <foo>
200
- | <em>
201
- | <aside>
202
- | <b>
203
-
204
- #data
205
- <b><em><foo><foo><aside></b></em>
206
- #errors
207
- (1,3): expected-doctype-but-got-start-tag
208
- (1,28): adoption-agency-9
209
- (1,33): adoption-agency-9
210
- (1,34): expected-closing-tag-but-got-eof
211
- #document
212
- | <html>
213
- | <head>
214
- | <body>
215
- | <b>
216
- | <em>
217
- | <foo>
218
- | <foo>
219
- | <em>
220
- | <aside>
221
- | <em>
222
- | <b>
223
-
224
- #data
225
- <b><em><foo><foo><foo><aside></b>
226
- #errors
227
- (1,3): expected-doctype-but-got-start-tag
228
- (1,33): adoption-agency-9
229
- (1,34): expected-closing-tag-but-got-eof
230
- #document
231
- | <html>
232
- | <head>
233
- | <body>
234
- | <b>
235
- | <em>
236
- | <foo>
237
- | <foo>
238
- | <foo>
239
- | <aside>
240
- | <b>
241
-
242
- #data
243
- <b><em><foo><foo><foo><aside></b></em>
244
- #errors
245
- (1,3): expected-doctype-but-got-start-tag
246
- (1,33): adoption-agency-9
247
- (1,38): adoption-agency-9
248
- (1,39): expected-closing-tag-but-got-eof
249
- #document
250
- | <html>
251
- | <head>
252
- | <body>
253
- | <b>
254
- | <em>
255
- | <foo>
256
- | <foo>
257
- | <foo>
258
- | <aside>
259
- | <b>
260
-
261
- #data
262
- <b><em><foo><foo><foo><foo><foo><foo><foo><foo><foo><foo><aside></b></em>
263
- #errors
264
- (1,68): adoption-agency-9
265
- (1,73): adoption-agency-9
266
- (1,74): expected-closing-tag-but-got-eof
267
- #document-fragment
268
- div
269
- #document
270
- | <b>
271
- | <em>
272
- | <foo>
273
- | <foo>
274
- | <foo>
275
- | <foo>
276
- | <foo>
277
- | <foo>
278
- | <foo>
279
- | <foo>
280
- | <foo>
281
- | <foo>
282
- | <aside>
283
- | <b>
284
-
285
- #data
286
- <b><em><foo><foob><foob><foob><foob><fooc><fooc><fooc><fooc><food><aside></b></em>
287
- #errors
288
- (1,77): adoption-agency-9
289
- (1,82): adoption-agency-9
290
- (1,83): expected-closing-tag-but-got-eof
291
- #document-fragment
292
- div
293
- #document
294
- | <b>
295
- | <em>
296
- | <foo>
297
- | <foob>
298
- | <foob>
299
- | <foob>
300
- | <foob>
301
- | <fooc>
302
- | <fooc>
303
- | <fooc>
304
- | <fooc>
305
- | <food>
306
- | <aside>
307
- | <b>
308
-
309
- #data
310
- <option><XH<optgroup></optgroup>
311
- #errors
312
- (1,21): unexpected-start-tag-in-select
313
- (1,32): unexpected-end-tag-in-select
314
- #document-fragment
315
- select
316
- #document
317
- | <option>
318
-
319
- #data
320
- <svg><foreignObject><div>foo</div><plaintext></foreignObject></svg><div>bar</div>
321
- #errors
322
- (1,5): expected-doctype-but-got-start-tag
323
- (1,82): expected-closing-tag-but-got-eof
324
- #document
325
- | <html>
326
- | <head>
327
- | <body>
328
- | <svg svg>
329
- | <svg foreignObject>
330
- | <div>
331
- | "foo"
332
- | <plaintext>
333
- | "</foreignObject></svg><div>bar</div>"
334
-
335
- #data
336
- <svg><foreignObject></foreignObject><title></svg>foo
337
- #errors
338
- (1,5): expected-doctype-but-got-start-tag
339
- (1,49): expected-one-end-tag-but-got-another
340
- #document
341
- | <html>
342
- | <head>
343
- | <body>
344
- | <svg svg>
345
- | <svg foreignObject>
346
- | <svg title>
347
- | "foo"
348
-
349
- #data
350
- </foreignObject><plaintext><div>foo</div>
351
- #errors
352
- (1,16): expected-doctype-but-got-end-tag
353
- (1,16): unexpected-end-tag-before-html
354
- (1,42): expected-closing-tag-but-got-eof
355
- #document
356
- | <html>
357
- | <head>
358
- | <body>
359
- | <plaintext>
360
- | "<div>foo</div>"
361
-
362
- #data
363
- <svg xml:base xml:lang xml:space xml:baaah definitionurl>
364
- #errors
365
- no-doctype
366
- eof-in-svg
367
- #document
368
- | <html>
369
- | <head>
370
- | <body>
371
- | <svg svg>
372
- | definitionurl=""
373
- | xml lang=""
374
- | xml space=""
375
- | xml:baaah=""
376
- | xml:base=""
377
-
378
- #data
379
- <math definitionurl xlink:title xlink:show>
380
- #errors
381
- no-doctype
382
- eof-in-math
383
- #document
384
- | <html>
385
- | <head>
386
- | <body>
387
- | <math math>
388
- | definitionURL=""
389
- | xlink show=""
390
- | xlink title=""
391
-
392
- #data
393
- <math DEFINITIONURL>
394
- #errors
395
- no-doctype
396
- eof-in-math
397
- #document
398
- | <html>
399
- | <head>
400
- | <body>
401
- | <math math>
402
- | definitionURL=""
403
-
404
- #data
405
- <select><hr>
406
- #errors
407
- 1:1: ERROR: Expected a doctype token
408
- 1:13: ERROR: Premature end of file. Currently open tags: html, body, select.
409
- #document
410
- | <html>
411
- | <head>
412
- | <body>
413
- | <select>
414
- | <hr>
415
-
416
- #data
417
- <select><option><hr>
418
- #errors
419
- 1:1: ERROR: Expected a doctype token
420
- 1:21: ERROR: Premature end of file. Currently open tags: html, body, select.
421
- #document
422
- | <html>
423
- | <head>
424
- | <body>
425
- | <select>
426
- | <option>
427
- | <hr>
428
-
429
- #data
430
- <select><optgroup><option><hr>
431
- #errors
432
- 1:1: ERROR: Expected a doctype token
433
- 1:31: ERROR: Premature end of file. Currently open tags: html, body, select.
434
- #document
435
- | <html>
436
- | <head>
437
- | <body>
438
- | <select>
439
- | <optgroup>
440
- | <option>
441
- | <hr>
442
-
443
- #data
444
- <select><optgroup><hr>
445
- #errors
446
- 1:1: ERROR: Expected a doctype token
447
- 1:23: ERROR: Premature end of file. Currently open tags: html, body, select.
448
- #document
449
- | <html>
450
- | <head>
451
- | <body>
452
- | <select>
453
- | <optgroup>
454
- | <hr>
455
-
456
- #data
457
- <select><option><optgroup><hr>
458
- #errors
459
- 1:1: ERROR: Expected a doctype token
460
- 1:31: ERROR: Premature end of file. Currently open tags: html, body, select.
461
- #document
462
- | <html>
463
- | <head>
464
- | <body>
465
- | <select>
466
- | <option>
467
- | <optgroup>
468
- | <hr>
469
-
470
- #data
471
- <table><tr><td><select><hr>
472
- #errors
473
- 1:1: ERROR: Expected a doctype token
474
- 1:28: ERROR: Premature end of file. Currently open tags: html, body, table, tbody, tr, td, select.
475
- #document
476
- | <html>
477
- | <head>
478
- | <body>
479
- | <table>
480
- | <tbody>
481
- | <tr>
482
- | <td>
483
- | <select>
484
- | <hr>
485
-
486
- #data
487
- <table><tr><td><select><option><hr>
488
- #errors
489
- 1:1: ERROR: Expected a doctype token
490
- 1:36: ERROR: Premature end of file. Currently open tags: html, body, table, tbody, tr, td, select.
491
- #document
492
- | <html>
493
- | <head>
494
- | <body>
495
- | <table>
496
- | <tbody>
497
- | <tr>
498
- | <td>
499
- | <select>
500
- | <option>
501
- | <hr>
502
-
503
- #data
504
- <table><tr><td><select><optgroup><option><hr>
505
- #errors
506
- 1:1: ERROR: Expected a doctype token
507
- 1:46: ERROR: Premature end of file. Currently open tags: html, body, table, tbody, tr, td, select.
508
- #document
509
- | <html>
510
- | <head>
511
- | <body>
512
- | <table>
513
- | <tbody>
514
- | <tr>
515
- | <td>
516
- | <select>
517
- | <optgroup>
518
- | <option>
519
- | <hr>
520
-
521
- #data
522
- <table><tr><td><select><optgroup><hr>
523
- #errors
524
- 1:1: ERROR: Expected a doctype token
525
- 1:38: ERROR: Premature end of file. Currently open tags: html, body, table, tbody, tr, td, select.
526
- #document
527
- | <html>
528
- | <head>
529
- | <body>
530
- | <table>
531
- | <tbody>
532
- | <tr>
533
- | <td>
534
- | <select>
535
- | <optgroup>
536
- | <hr>
537
-
538
- #data
539
- <table><tr><td><select><option><optgroup><hr>
540
- #errors
541
- 1:1: ERROR: Expected a doctype token
542
- 1:46: ERROR: Premature end of file. Currently open tags: html, body, table, tbody, tr, td, select.
543
- #document
544
- | <html>
545
- | <head>
546
- | <body>
547
- | <table>
548
- | <tbody>
549
- | <tr>
550
- | <td>
551
- | <select>
552
- | <option>
553
- | <optgroup>
554
- | <hr>
@@ -1,41 +0,0 @@
1
- // Copyright 2014-2017 The html5ever Project Developers. See the
2
- // COPYRIGHT file at the top-level directory of this distribution.
3
- //
4
- // Licensed under the Apache License, Version 2.0 <LICENSE-APACHE or
5
- // http://www.apache.org/licenses/LICENSE-2.0> or the MIT license
6
- // <LICENSE-MIT or http://opensource.org/licenses/MIT>, at your
7
- // option. This file may not be copied, modified, or distributed
8
- // except according to those terms.
9
-
10
- use std::ffi::OsStr;
11
- use std::fs;
12
- use std::ops::FnMut;
13
- use std::path::Path;
14
-
15
- pub fn foreach_html5lib_test<Mk>(
16
- src_dir: &Path,
17
- subdir: &'static str,
18
- ext: &'static OsStr,
19
- mut mk: Mk,
20
- ) where
21
- Mk: FnMut(&Path, fs::File),
22
- {
23
- let mut test_dir_path = src_dir.to_path_buf();
24
- test_dir_path.push(subdir);
25
-
26
- let maybe_test_files = fs::read_dir(&test_dir_path);
27
- match maybe_test_files {
28
- Ok(test_files) => {
29
- for entry in test_files {
30
- let path = entry.unwrap().path();
31
- if path.extension() == Some(ext) {
32
- let file = fs::File::open(&path).unwrap();
33
- mk(&path, file);
34
- }
35
- }
36
- },
37
- Err(_) => {
38
- panic!("Before launching the tests, please run this command:\n\n\tgit submodule update --init\n\nto retrieve an html5lib-tests snapshot.");
39
- },
40
- }
41
- }
@@ -1,29 +0,0 @@
1
- use html5ever::driver;
2
- use html5ever::serialize;
3
- use html5ever::tendril::TendrilSink;
4
- use markup5ever_rcdom::{RcDom, SerializableHandle};
5
-
6
- #[test]
7
- fn from_utf8() {
8
- let dom = driver::parse_document(RcDom::default(), Default::default())
9
- .from_utf8()
10
- .one("<title>Test".as_bytes());
11
- let mut serialized = Vec::new();
12
- let document: SerializableHandle = dom.document.clone().into();
13
- serialize::serialize(&mut serialized, &document, Default::default()).unwrap();
14
- assert_eq!(
15
- String::from_utf8(serialized).unwrap().replace(' ', ""),
16
- "<html><head><title>Test</title></head><body></body></html>"
17
- );
18
- }
19
-
20
- #[test]
21
- fn many_templates() {
22
- let mut body = String::new();
23
- for _ in 1..10000 {
24
- body.push_str("<template>");
25
- }
26
- let _ = driver::parse_document(RcDom::default(), Default::default())
27
- .from_utf8()
28
- .one(body.as_bytes());
29
- }