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
@@ -1,69 +0,0 @@
1
- # THIS FILE IS AUTOMATICALLY GENERATED BY CARGO
2
- #
3
- # When uploading crates to the registry Cargo will automatically
4
- # "normalize" Cargo.toml files for maximal compatibility
5
- # with all versions of Cargo and also rewrite `path` dependencies
6
- # to registry (e.g., crates.io) dependencies.
7
- #
8
- # If you are reading this file be aware that the original Cargo.toml
9
- # will likely look very different (and much more reasonable).
10
- # See Cargo.toml.orig for the original contents.
11
-
12
- [package]
13
- edition = "2021"
14
- rust-version = "1.71.0"
15
- name = "xml5ever"
16
- version = "0.36.1"
17
- authors = ["The xml5ever project developers"]
18
- build = false
19
- exclude = ["xml5lib-tests/*"]
20
- autolib = false
21
- autobins = false
22
- autoexamples = false
23
- autotests = false
24
- autobenches = false
25
- description = "Push based streaming parser for XML."
26
- homepage = "https://github.com/servo/html5ever/blob/main/xml5ever/README.md"
27
- documentation = "https://docs.rs/xml5ever"
28
- readme = "README.md"
29
- keywords = [
30
- "xml",
31
- "xml5",
32
- "parser",
33
- "parsing",
34
- ]
35
- categories = [
36
- "parser-implementations",
37
- "web-programming",
38
- ]
39
- license = "MIT OR Apache-2.0"
40
- repository = "https://github.com/servo/html5ever"
41
-
42
- [features]
43
- trace_tokenizer = []
44
-
45
- [lib]
46
- name = "xml5ever"
47
- path = "src/lib.rs"
48
-
49
- [[example]]
50
- name = "simple_xml_tokenizer"
51
- path = "examples/simple_xml_tokenizer.rs"
52
-
53
- [[example]]
54
- name = "xml_tokenizer"
55
- path = "examples/xml_tokenizer.rs"
56
-
57
- [[bench]]
58
- name = "xml5ever"
59
- path = "benches/xml5ever.rs"
60
- harness = false
61
-
62
- [dependencies.log]
63
- version = "0.4"
64
-
65
- [dependencies.markup5ever]
66
- version = "0.36.1"
67
-
68
- [dev-dependencies.criterion]
69
- version = "0.7"
@@ -1,29 +0,0 @@
1
- [package]
2
- name = "xml5ever"
3
- authors = ["The xml5ever project developers"]
4
- description = "Push based streaming parser for XML."
5
- documentation = "https://docs.rs/xml5ever"
6
- homepage = "https://github.com/servo/html5ever/blob/main/xml5ever/README.md"
7
- readme = "README.md"
8
- keywords = ["xml", "xml5", "parser", "parsing"]
9
- exclude = ["xml5lib-tests/*"]
10
- categories = ["parser-implementations", "web-programming"]
11
- version.workspace = true
12
- license.workspace = true
13
- repository.workspace = true
14
- edition.workspace = true
15
- rust-version.workspace = true
16
-
17
- [features]
18
- trace_tokenizer = []
19
-
20
- [dependencies]
21
- markup5ever = { workspace = true }
22
- log = { workspace = true }
23
-
24
- [dev-dependencies]
25
- criterion = { workspace = true }
26
-
27
- [[bench]]
28
- name = "xml5ever"
29
- harness = false
@@ -1,201 +0,0 @@
1
- Apache License
2
- Version 2.0, January 2004
3
- http://www.apache.org/licenses/
4
-
5
- TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
6
-
7
- 1. Definitions.
8
-
9
- "License" shall mean the terms and conditions for use, reproduction,
10
- and distribution as defined by Sections 1 through 9 of this document.
11
-
12
- "Licensor" shall mean the copyright owner or entity authorized by
13
- the copyright owner that is granting the License.
14
-
15
- "Legal Entity" shall mean the union of the acting entity and all
16
- other entities that control, are controlled by, or are under common
17
- control with that entity. For the purposes of this definition,
18
- "control" means (i) the power, direct or indirect, to cause the
19
- direction or management of such entity, whether by contract or
20
- otherwise, or (ii) ownership of fifty percent (50%) or more of the
21
- outstanding shares, or (iii) beneficial ownership of such entity.
22
-
23
- "You" (or "Your") shall mean an individual or Legal Entity
24
- exercising permissions granted by this License.
25
-
26
- "Source" form shall mean the preferred form for making modifications,
27
- including but not limited to software source code, documentation
28
- source, and configuration files.
29
-
30
- "Object" form shall mean any form resulting from mechanical
31
- transformation or translation of a Source form, including but
32
- not limited to compiled object code, generated documentation,
33
- and conversions to other media types.
34
-
35
- "Work" shall mean the work of authorship, whether in Source or
36
- Object form, made available under the License, as indicated by a
37
- copyright notice that is included in or attached to the work
38
- (an example is provided in the Appendix below).
39
-
40
- "Derivative Works" shall mean any work, whether in Source or Object
41
- form, that is based on (or derived from) the Work and for which the
42
- editorial revisions, annotations, elaborations, or other modifications
43
- represent, as a whole, an original work of authorship. For the purposes
44
- of this License, Derivative Works shall not include works that remain
45
- separable from, or merely link (or bind by name) to the interfaces of,
46
- the Work and Derivative Works thereof.
47
-
48
- "Contribution" shall mean any work of authorship, including
49
- the original version of the Work and any modifications or additions
50
- to that Work or Derivative Works thereof, that is intentionally
51
- submitted to Licensor for inclusion in the Work by the copyright owner
52
- or by an individual or Legal Entity authorized to submit on behalf of
53
- the copyright owner. For the purposes of this definition, "submitted"
54
- means any form of electronic, verbal, or written communication sent
55
- to the Licensor or its representatives, including but not limited to
56
- communication on electronic mailing lists, source code control systems,
57
- and issue tracking systems that are managed by, or on behalf of, the
58
- Licensor for the purpose of discussing and improving the Work, but
59
- excluding communication that is conspicuously marked or otherwise
60
- designated in writing by the copyright owner as "Not a Contribution."
61
-
62
- "Contributor" shall mean Licensor and any individual or Legal Entity
63
- on behalf of whom a Contribution has been received by Licensor and
64
- subsequently incorporated within the Work.
65
-
66
- 2. Grant of Copyright License. Subject to the terms and conditions of
67
- this License, each Contributor hereby grants to You a perpetual,
68
- worldwide, non-exclusive, no-charge, royalty-free, irrevocable
69
- copyright license to reproduce, prepare Derivative Works of,
70
- publicly display, publicly perform, sublicense, and distribute the
71
- Work and such Derivative Works in Source or Object form.
72
-
73
- 3. Grant of Patent License. Subject to the terms and conditions of
74
- this License, each Contributor hereby grants to You a perpetual,
75
- worldwide, non-exclusive, no-charge, royalty-free, irrevocable
76
- (except as stated in this section) patent license to make, have made,
77
- use, offer to sell, sell, import, and otherwise transfer the Work,
78
- where such license applies only to those patent claims licensable
79
- by such Contributor that are necessarily infringed by their
80
- Contribution(s) alone or by combination of their Contribution(s)
81
- with the Work to which such Contribution(s) was submitted. If You
82
- institute patent litigation against any entity (including a
83
- cross-claim or counterclaim in a lawsuit) alleging that the Work
84
- or a Contribution incorporated within the Work constitutes direct
85
- or contributory patent infringement, then any patent licenses
86
- granted to You under this License for that Work shall terminate
87
- as of the date such litigation is filed.
88
-
89
- 4. Redistribution. You may reproduce and distribute copies of the
90
- Work or Derivative Works thereof in any medium, with or without
91
- modifications, and in Source or Object form, provided that You
92
- meet the following conditions:
93
-
94
- (a) You must give any other recipients of the Work or
95
- Derivative Works a copy of this License; and
96
-
97
- (b) You must cause any modified files to carry prominent notices
98
- stating that You changed the files; and
99
-
100
- (c) You must retain, in the Source form of any Derivative Works
101
- that You distribute, all copyright, patent, trademark, and
102
- attribution notices from the Source form of the Work,
103
- excluding those notices that do not pertain to any part of
104
- the Derivative Works; and
105
-
106
- (d) If the Work includes a "NOTICE" text file as part of its
107
- distribution, then any Derivative Works that You distribute must
108
- include a readable copy of the attribution notices contained
109
- within such NOTICE file, excluding those notices that do not
110
- pertain to any part of the Derivative Works, in at least one
111
- of the following places: within a NOTICE text file distributed
112
- as part of the Derivative Works; within the Source form or
113
- documentation, if provided along with the Derivative Works; or,
114
- within a display generated by the Derivative Works, if and
115
- wherever such third-party notices normally appear. The contents
116
- of the NOTICE file are for informational purposes only and
117
- do not modify the License. You may add Your own attribution
118
- notices within Derivative Works that You distribute, alongside
119
- or as an addendum to the NOTICE text from the Work, provided
120
- that such additional attribution notices cannot be construed
121
- as modifying the License.
122
-
123
- You may add Your own copyright statement to Your modifications and
124
- may provide additional or different license terms and conditions
125
- for use, reproduction, or distribution of Your modifications, or
126
- for any such Derivative Works as a whole, provided Your use,
127
- reproduction, and distribution of the Work otherwise complies with
128
- the conditions stated in this License.
129
-
130
- 5. Submission of Contributions. Unless You explicitly state otherwise,
131
- any Contribution intentionally submitted for inclusion in the Work
132
- by You to the Licensor shall be under the terms and conditions of
133
- this License, without any additional terms or conditions.
134
- Notwithstanding the above, nothing herein shall supersede or modify
135
- the terms of any separate license agreement you may have executed
136
- with Licensor regarding such Contributions.
137
-
138
- 6. Trademarks. This License does not grant permission to use the trade
139
- names, trademarks, service marks, or product names of the Licensor,
140
- except as required for reasonable and customary use in describing the
141
- origin of the Work and reproducing the content of the NOTICE file.
142
-
143
- 7. Disclaimer of Warranty. Unless required by applicable law or
144
- agreed to in writing, Licensor provides the Work (and each
145
- Contributor provides its Contributions) on an "AS IS" BASIS,
146
- WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
147
- implied, including, without limitation, any warranties or conditions
148
- of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
149
- PARTICULAR PURPOSE. You are solely responsible for determining the
150
- appropriateness of using or redistributing the Work and assume any
151
- risks associated with Your exercise of permissions under this License.
152
-
153
- 8. Limitation of Liability. In no event and under no legal theory,
154
- whether in tort (including negligence), contract, or otherwise,
155
- unless required by applicable law (such as deliberate and grossly
156
- negligent acts) or agreed to in writing, shall any Contributor be
157
- liable to You for damages, including any direct, indirect, special,
158
- incidental, or consequential damages of any character arising as a
159
- result of this License or out of the use or inability to use the
160
- Work (including but not limited to damages for loss of goodwill,
161
- work stoppage, computer failure or malfunction, or any and all
162
- other commercial damages or losses), even if such Contributor
163
- has been advised of the possibility of such damages.
164
-
165
- 9. Accepting Warranty or Additional Liability. While redistributing
166
- the Work or Derivative Works thereof, You may choose to offer,
167
- and charge a fee for, acceptance of support, warranty, indemnity,
168
- or other liability obligations and/or rights consistent with this
169
- License. However, in accepting such obligations, You may act only
170
- on Your own behalf and on Your sole responsibility, not on behalf
171
- of any other Contributor, and only if You agree to indemnify,
172
- defend, and hold each Contributor harmless for any liability
173
- incurred by, or claims asserted against, such Contributor by reason
174
- of your accepting any such warranty or additional liability.
175
-
176
- END OF TERMS AND CONDITIONS
177
-
178
- APPENDIX: How to apply the Apache License to your work.
179
-
180
- To apply the Apache License to your work, attach the following
181
- boilerplate notice, with the fields enclosed by brackets "[]"
182
- replaced with your own identifying information. (Don't include
183
- the brackets!) The text should be enclosed in the appropriate
184
- comment syntax for the file format. We also recommend that a
185
- file or class name and description of purpose be included on the
186
- same "printed page" as the copyright notice for easier
187
- identification within third-party archives.
188
-
189
- Copyright [yyyy] [name of copyright owner]
190
-
191
- Licensed under the Apache License, Version 2.0 (the "License");
192
- you may not use this file except in compliance with the License.
193
- You may obtain a copy of the License at
194
-
195
- http://www.apache.org/licenses/LICENSE-2.0
196
-
197
- Unless required by applicable law or agreed to in writing, software
198
- distributed under the License is distributed on an "AS IS" BASIS,
199
- WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
200
- See the License for the specific language governing permissions and
201
- limitations under the License.
@@ -1,25 +0,0 @@
1
- Copyright (c) 2014 The html5ever Project Developers
2
-
3
- Permission is hereby granted, free of charge, to any
4
- person obtaining a copy of this software and associated
5
- documentation files (the "Software"), to deal in the
6
- Software without restriction, including without
7
- limitation the rights to use, copy, modify, merge,
8
- publish, distribute, sublicense, and/or sell copies of
9
- the Software, and to permit persons to whom the Software
10
- is furnished to do so, subject to the following
11
- conditions:
12
-
13
- The above copyright notice and this permission notice
14
- shall be included in all copies or substantial portions
15
- of the Software.
16
-
17
- THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF
18
- ANY KIND, EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED
19
- TO THE WARRANTIES OF MERCHANTABILITY, FITNESS FOR A
20
- PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT
21
- SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY
22
- CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION
23
- OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR
24
- IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER
25
- DEALINGS IN THE SOFTWARE.
@@ -1,72 +0,0 @@
1
- # xml5ever
2
-
3
- ![http://www.apache.org/licenses/LICENSE-2.0](https://img.shields.io/badge/license-Apache-blue.svg) ![https://opensource.org/licenses/MIT](https://img.shields.io/badge/license-MIT-blue.svg)
4
- [![Docs.rs](https://docs.rs/xml5ever/badge.svg)](https://docs.rs/xml5ever)
5
- [![](https://img.shields.io/crates/v/xml5ever.svg)](https://crates.io/crates/xml5ever)
6
-
7
- [API documentation](https://docs.rs/xml5ever)
8
-
9
- **Warning:** This library is alpha quality, so no guarantees are given.
10
-
11
- This crate provides a push based XML parser library that trades well-formedness for error recovery.
12
-
13
- xml5ever is based largely on [html5ever](https://github.com/servo/html5ever) parser, so if you have experience with html5ever you will be familiar with xml5ever.
14
-
15
- The library is dual licensed under MIT and Apache license.
16
-
17
- # Why you should use xml5ever
18
-
19
- Main use case for this library is when XML is badly formatted, usually from bad XML
20
- templates. XML5 tries to handle most common errors, in a manner similar to HTML5.
21
-
22
- ## When you should use it?
23
-
24
- - You aren't interested in well-formed documents.
25
- - You need to get some info from your data even if it has errors (although not all possible errors are handled).
26
- - You want to features like character references or XML namespaces.
27
-
28
- ## When you shouldn't use it
29
-
30
- - You need to have your document validated.
31
- - You require DTD support.
32
- - You require an easy to use parser, with lots of extensions (e.g. XPath, XQuery).
33
- - You require a battle tested, industry proven solution.
34
-
35
- # Installation
36
-
37
- Add xml5ever as a dependency:
38
-
39
- ```bash
40
- cargo add xml5ever
41
- ```
42
-
43
- # Getting started
44
-
45
- Here is a very simple RcDom backed parser:
46
-
47
- ```rust
48
-
49
- let input = "<xml></xml>".to_tendril();
50
-
51
- // To parse XML into a tree form, we need a TreeSink
52
- // luckily xml5ever comes with a static RC backed tree represetation.
53
- let dom: RcDom = parse(std::iter::once(input), Default::default());
54
-
55
- // Do something with dom
56
-
57
- ```
58
- The thing that does actual parsing is the `parse` function. It expects an iterator that can be converted into `StrTendril`, so you can use `std::iter::once(input)` or `Some(input).into_iter()` (where `input` is `StrTendril` like structure).
59
-
60
- # Working on xml5ever
61
-
62
- To build examples and tests you need to do something along the lines of:
63
-
64
- ```rust
65
- git submodule update --init # to fetch xml5lib-tests
66
- cargo build
67
- cargo test
68
- ```
69
-
70
- This will fetch tests from outside repository and it will invoke cargo to
71
- build and test the crate. If you need docs checkout either [API docs](https://docs.rs/xml5ever) or run `cargo docs`
72
- to generate documentation.
@@ -1,77 +0,0 @@
1
- #[macro_use]
2
- extern crate criterion;
3
- extern crate markup5ever;
4
- extern crate xml5ever;
5
-
6
- use std::fs;
7
- use std::path::PathBuf;
8
-
9
- use criterion::Criterion;
10
-
11
- use markup5ever::buffer_queue::BufferQueue;
12
- use xml5ever::tendril::*;
13
- use xml5ever::tokenizer::{ProcessResult, Token, TokenSink, XmlTokenizer};
14
-
15
- struct Sink;
16
-
17
- impl TokenSink for Sink {
18
- type Handle = ();
19
-
20
- fn process_token(&self, token: Token) -> ProcessResult<()> {
21
- // Don't use the token, but make sure we don't get
22
- // optimized out entirely.
23
- std::hint::black_box(token);
24
- ProcessResult::Continue
25
- }
26
- }
27
-
28
- fn run_bench(c: &mut Criterion, name: &str) {
29
- let mut path = PathBuf::from("./");
30
- path.push("data/bench/");
31
- path.push(name);
32
- let mut file = fs::File::open(&path).expect("can't open file");
33
-
34
- // Read the file and treat it as an infinitely repeating sequence of characters.
35
- let mut file_input = ByteTendril::new();
36
- file.read_to_tendril(&mut file_input)
37
- .expect("can't read file");
38
- let file_input: StrTendril = file_input.try_reinterpret().unwrap();
39
- let size = file_input.len();
40
- let mut stream = file_input.chars().cycle();
41
-
42
- // Break the input into chunks of 1024 chars (= a few kB).
43
- // This simulates reading from the network.
44
- let mut input = vec![];
45
- let mut total = 0usize;
46
- while total < size {
47
- // The by_ref() call is important, otherwise we get wrong results!
48
- // See rust-lang/rust#18045.
49
- let sz = std::cmp::min(1024, size - total);
50
- input.push(stream.by_ref().take(sz).collect::<String>().to_tendril());
51
- total += sz;
52
- }
53
-
54
- let test_name = format!("xml tokenizing {name}");
55
-
56
- c.bench_function(&test_name, move |b| {
57
- b.iter(|| {
58
- let tok = XmlTokenizer::new(Sink, Default::default());
59
- let buffer = BufferQueue::default();
60
- // We are doing clone inside the bench function, this is not ideal, but possibly
61
- // necessary since our iterator consumes the underlying buffer.
62
- for buf in input.clone().into_iter() {
63
- buffer.push_back(buf);
64
- let _ = tok.feed(&buffer);
65
- }
66
- let _ = tok.feed(&buffer);
67
- tok.end();
68
- })
69
- });
70
- }
71
-
72
- fn xml5ever_benchmarks(c: &mut Criterion) {
73
- run_bench(c, "strong.xml");
74
- }
75
-
76
- criterion_group!(benches, xml5ever_benchmarks);
77
- criterion_main!(benches);
@@ -1 +0,0 @@
1
- <strong><strong><strong><strong><strong><strong><strong><strong><strong><strong><strong><strong><strong><strong><strong><strong><strong><strong><strong><strong><strong><strong><strong><strong><strong><strong><strong><strong><strong><strong><strong><strong><strong><strong><strong><strong><strong><strong><strong><strong><strong><strong><strong><strong><strong><strong><strong><strong><strong><strong><strong><strong><strong><strong><strong><strong><strong><strong><strong><strong><strong><strong><strong><strong><strong><strong><strong><strong><strong><strong><strong><strong><strong><strong><strong><strong><strong><strong><strong><strong><strong><strong><strong><strong><strong><strong><strong><strong><strong><strong><strong><strong><strong><strong><strong><strong><strong><strong><strong><strong><strong><strong><strong><strong><strong><strong><strong><strong><strong><strong><strong><strong><strong><strong><strong><strong><strong><strong><strong><strong><strong><strong><strong><strong><strong><strong><strong><strong>