kreuzberg 4.0.0.pre.rc.13 → 4.0.0.pre.rc.15

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 (369) hide show
  1. checksums.yaml +4 -4
  2. data/.gitignore +14 -14
  3. data/.rspec +3 -3
  4. data/.rubocop.yaml +1 -1
  5. data/.rubocop.yml +538 -538
  6. data/Gemfile +8 -8
  7. data/Gemfile.lock +104 -2
  8. data/README.md +454 -454
  9. data/Rakefile +33 -25
  10. data/Steepfile +47 -47
  11. data/examples/async_patterns.rb +341 -341
  12. data/ext/kreuzberg_rb/extconf.rb +45 -45
  13. data/ext/kreuzberg_rb/native/.cargo/config.toml +2 -2
  14. data/ext/kreuzberg_rb/native/Cargo.lock +6750 -6941
  15. data/ext/kreuzberg_rb/native/Cargo.toml +53 -54
  16. data/ext/kreuzberg_rb/native/README.md +425 -425
  17. data/ext/kreuzberg_rb/native/build.rs +52 -15
  18. data/ext/kreuzberg_rb/native/include/ieeefp.h +11 -11
  19. data/ext/kreuzberg_rb/native/include/msvc_compat/strings.h +14 -14
  20. data/ext/kreuzberg_rb/native/include/strings.h +20 -20
  21. data/ext/kreuzberg_rb/native/include/unistd.h +47 -47
  22. data/ext/kreuzberg_rb/native/src/lib.rs +3158 -3158
  23. data/extconf.rb +28 -28
  24. data/kreuzberg.gemspec +214 -214
  25. data/lib/kreuzberg/api_proxy.rb +142 -142
  26. data/lib/kreuzberg/cache_api.rb +81 -81
  27. data/lib/kreuzberg/cli.rb +55 -55
  28. data/lib/kreuzberg/cli_proxy.rb +127 -127
  29. data/lib/kreuzberg/config.rb +724 -724
  30. data/lib/kreuzberg/error_context.rb +80 -80
  31. data/lib/kreuzberg/errors.rb +118 -118
  32. data/lib/kreuzberg/extraction_api.rb +340 -340
  33. data/lib/kreuzberg/mcp_proxy.rb +186 -186
  34. data/lib/kreuzberg/ocr_backend_protocol.rb +113 -113
  35. data/lib/kreuzberg/post_processor_protocol.rb +86 -86
  36. data/lib/kreuzberg/result.rb +279 -279
  37. data/lib/kreuzberg/setup_lib_path.rb +80 -80
  38. data/lib/kreuzberg/validator_protocol.rb +89 -89
  39. data/lib/kreuzberg/version.rb +5 -5
  40. data/lib/kreuzberg.rb +109 -109
  41. data/lib/{pdfium.dll → libpdfium.so} +0 -0
  42. data/sig/kreuzberg/internal.rbs +184 -184
  43. data/sig/kreuzberg.rbs +546 -546
  44. data/spec/binding/cache_spec.rb +227 -227
  45. data/spec/binding/cli_proxy_spec.rb +85 -85
  46. data/spec/binding/cli_spec.rb +55 -55
  47. data/spec/binding/config_spec.rb +345 -345
  48. data/spec/binding/config_validation_spec.rb +283 -283
  49. data/spec/binding/error_handling_spec.rb +213 -213
  50. data/spec/binding/errors_spec.rb +66 -66
  51. data/spec/binding/plugins/ocr_backend_spec.rb +307 -307
  52. data/spec/binding/plugins/postprocessor_spec.rb +269 -269
  53. data/spec/binding/plugins/validator_spec.rb +274 -274
  54. data/spec/fixtures/config.toml +39 -39
  55. data/spec/fixtures/config.yaml +41 -41
  56. data/spec/fixtures/invalid_config.toml +4 -4
  57. data/spec/smoke/package_spec.rb +178 -178
  58. data/spec/spec_helper.rb +42 -42
  59. data/vendor/Cargo.toml +2 -2
  60. data/vendor/kreuzberg/Cargo.toml +5 -5
  61. data/vendor/kreuzberg/README.md +230 -230
  62. data/vendor/kreuzberg/benches/otel_overhead.rs +48 -48
  63. data/vendor/kreuzberg/build.rs +887 -843
  64. data/vendor/kreuzberg/src/api/error.rs +81 -81
  65. data/vendor/kreuzberg/src/api/handlers.rs +199 -199
  66. data/vendor/kreuzberg/src/api/mod.rs +87 -79
  67. data/vendor/kreuzberg/src/api/server.rs +353 -353
  68. data/vendor/kreuzberg/src/api/types.rs +170 -170
  69. data/vendor/kreuzberg/src/cache/mod.rs +1167 -1167
  70. data/vendor/kreuzberg/src/chunking/mod.rs +1877 -1877
  71. data/vendor/kreuzberg/src/chunking/processor.rs +220 -220
  72. data/vendor/kreuzberg/src/core/batch_mode.rs +95 -95
  73. data/vendor/kreuzberg/src/core/config.rs +1080 -1080
  74. data/vendor/kreuzberg/src/core/extractor.rs +1156 -1156
  75. data/vendor/kreuzberg/src/core/io.rs +329 -329
  76. data/vendor/kreuzberg/src/core/mime.rs +605 -605
  77. data/vendor/kreuzberg/src/core/mod.rs +47 -47
  78. data/vendor/kreuzberg/src/core/pipeline.rs +1184 -1184
  79. data/vendor/kreuzberg/src/embeddings.rs +500 -500
  80. data/vendor/kreuzberg/src/error.rs +431 -431
  81. data/vendor/kreuzberg/src/extraction/archive.rs +954 -954
  82. data/vendor/kreuzberg/src/extraction/docx.rs +398 -398
  83. data/vendor/kreuzberg/src/extraction/email.rs +854 -854
  84. data/vendor/kreuzberg/src/extraction/excel.rs +688 -688
  85. data/vendor/kreuzberg/src/extraction/html.rs +634 -601
  86. data/vendor/kreuzberg/src/extraction/image.rs +491 -491
  87. data/vendor/kreuzberg/src/extraction/libreoffice.rs +574 -574
  88. data/vendor/kreuzberg/src/extraction/markdown.rs +213 -213
  89. data/vendor/kreuzberg/src/extraction/mod.rs +81 -81
  90. data/vendor/kreuzberg/src/extraction/office_metadata/app_properties.rs +398 -398
  91. data/vendor/kreuzberg/src/extraction/office_metadata/core_properties.rs +247 -247
  92. data/vendor/kreuzberg/src/extraction/office_metadata/custom_properties.rs +240 -240
  93. data/vendor/kreuzberg/src/extraction/office_metadata/mod.rs +130 -130
  94. data/vendor/kreuzberg/src/extraction/office_metadata/odt_properties.rs +284 -284
  95. data/vendor/kreuzberg/src/extraction/pptx.rs +3100 -3100
  96. data/vendor/kreuzberg/src/extraction/structured.rs +490 -490
  97. data/vendor/kreuzberg/src/extraction/table.rs +328 -328
  98. data/vendor/kreuzberg/src/extraction/text.rs +269 -269
  99. data/vendor/kreuzberg/src/extraction/xml.rs +333 -333
  100. data/vendor/kreuzberg/src/extractors/archive.rs +447 -447
  101. data/vendor/kreuzberg/src/extractors/bibtex.rs +470 -470
  102. data/vendor/kreuzberg/src/extractors/docbook.rs +504 -504
  103. data/vendor/kreuzberg/src/extractors/docx.rs +400 -400
  104. data/vendor/kreuzberg/src/extractors/email.rs +157 -157
  105. data/vendor/kreuzberg/src/extractors/epub.rs +708 -708
  106. data/vendor/kreuzberg/src/extractors/excel.rs +345 -345
  107. data/vendor/kreuzberg/src/extractors/fictionbook.rs +492 -492
  108. data/vendor/kreuzberg/src/extractors/html.rs +407 -407
  109. data/vendor/kreuzberg/src/extractors/image.rs +219 -219
  110. data/vendor/kreuzberg/src/extractors/jats.rs +1054 -1054
  111. data/vendor/kreuzberg/src/extractors/jupyter.rs +368 -368
  112. data/vendor/kreuzberg/src/extractors/latex.rs +653 -653
  113. data/vendor/kreuzberg/src/extractors/markdown.rs +701 -701
  114. data/vendor/kreuzberg/src/extractors/mod.rs +429 -429
  115. data/vendor/kreuzberg/src/extractors/odt.rs +628 -628
  116. data/vendor/kreuzberg/src/extractors/opml.rs +635 -635
  117. data/vendor/kreuzberg/src/extractors/orgmode.rs +529 -529
  118. data/vendor/kreuzberg/src/extractors/pdf.rs +749 -749
  119. data/vendor/kreuzberg/src/extractors/pptx.rs +267 -267
  120. data/vendor/kreuzberg/src/extractors/rst.rs +577 -577
  121. data/vendor/kreuzberg/src/extractors/rtf.rs +809 -809
  122. data/vendor/kreuzberg/src/extractors/security.rs +484 -484
  123. data/vendor/kreuzberg/src/extractors/security_tests.rs +367 -367
  124. data/vendor/kreuzberg/src/extractors/structured.rs +142 -142
  125. data/vendor/kreuzberg/src/extractors/text.rs +265 -265
  126. data/vendor/kreuzberg/src/extractors/typst.rs +651 -651
  127. data/vendor/kreuzberg/src/extractors/xml.rs +147 -147
  128. data/vendor/kreuzberg/src/image/dpi.rs +164 -164
  129. data/vendor/kreuzberg/src/image/mod.rs +6 -6
  130. data/vendor/kreuzberg/src/image/preprocessing.rs +417 -417
  131. data/vendor/kreuzberg/src/image/resize.rs +89 -89
  132. data/vendor/kreuzberg/src/keywords/config.rs +154 -154
  133. data/vendor/kreuzberg/src/keywords/mod.rs +237 -237
  134. data/vendor/kreuzberg/src/keywords/processor.rs +275 -275
  135. data/vendor/kreuzberg/src/keywords/rake.rs +293 -293
  136. data/vendor/kreuzberg/src/keywords/types.rs +68 -68
  137. data/vendor/kreuzberg/src/keywords/yake.rs +163 -163
  138. data/vendor/kreuzberg/src/language_detection/mod.rs +985 -985
  139. data/vendor/kreuzberg/src/language_detection/processor.rs +219 -219
  140. data/vendor/kreuzberg/src/lib.rs +113 -113
  141. data/vendor/kreuzberg/src/mcp/mod.rs +35 -35
  142. data/vendor/kreuzberg/src/mcp/server.rs +2076 -2076
  143. data/vendor/kreuzberg/src/ocr/cache.rs +469 -469
  144. data/vendor/kreuzberg/src/ocr/error.rs +37 -37
  145. data/vendor/kreuzberg/src/ocr/hocr.rs +216 -216
  146. data/vendor/kreuzberg/src/ocr/mod.rs +58 -58
  147. data/vendor/kreuzberg/src/ocr/processor.rs +863 -863
  148. data/vendor/kreuzberg/src/ocr/table/mod.rs +4 -4
  149. data/vendor/kreuzberg/src/ocr/table/tsv_parser.rs +144 -144
  150. data/vendor/kreuzberg/src/ocr/tesseract_backend.rs +452 -452
  151. data/vendor/kreuzberg/src/ocr/types.rs +393 -393
  152. data/vendor/kreuzberg/src/ocr/utils.rs +47 -47
  153. data/vendor/kreuzberg/src/ocr/validation.rs +206 -206
  154. data/vendor/kreuzberg/src/panic_context.rs +154 -154
  155. data/vendor/kreuzberg/src/pdf/bindings.rs +44 -44
  156. data/vendor/kreuzberg/src/pdf/bundled.rs +452 -346
  157. data/vendor/kreuzberg/src/pdf/error.rs +130 -130
  158. data/vendor/kreuzberg/src/pdf/images.rs +139 -139
  159. data/vendor/kreuzberg/src/pdf/metadata.rs +489 -489
  160. data/vendor/kreuzberg/src/pdf/mod.rs +68 -68
  161. data/vendor/kreuzberg/src/pdf/rendering.rs +368 -368
  162. data/vendor/kreuzberg/src/pdf/table.rs +420 -420
  163. data/vendor/kreuzberg/src/pdf/text.rs +240 -240
  164. data/vendor/kreuzberg/src/plugins/extractor.rs +1044 -1044
  165. data/vendor/kreuzberg/src/plugins/mod.rs +212 -212
  166. data/vendor/kreuzberg/src/plugins/ocr.rs +639 -639
  167. data/vendor/kreuzberg/src/plugins/processor.rs +650 -650
  168. data/vendor/kreuzberg/src/plugins/registry.rs +1339 -1339
  169. data/vendor/kreuzberg/src/plugins/traits.rs +258 -258
  170. data/vendor/kreuzberg/src/plugins/validator.rs +967 -967
  171. data/vendor/kreuzberg/src/stopwords/mod.rs +1470 -1470
  172. data/vendor/kreuzberg/src/text/mod.rs +25 -25
  173. data/vendor/kreuzberg/src/text/quality.rs +697 -697
  174. data/vendor/kreuzberg/src/text/quality_processor.rs +219 -219
  175. data/vendor/kreuzberg/src/text/string_utils.rs +217 -217
  176. data/vendor/kreuzberg/src/text/token_reduction/cjk_utils.rs +164 -164
  177. data/vendor/kreuzberg/src/text/token_reduction/config.rs +100 -100
  178. data/vendor/kreuzberg/src/text/token_reduction/core.rs +796 -796
  179. data/vendor/kreuzberg/src/text/token_reduction/filters.rs +902 -902
  180. data/vendor/kreuzberg/src/text/token_reduction/mod.rs +160 -160
  181. data/vendor/kreuzberg/src/text/token_reduction/semantic.rs +619 -619
  182. data/vendor/kreuzberg/src/text/token_reduction/simd_text.rs +147 -147
  183. data/vendor/kreuzberg/src/types.rs +1055 -1055
  184. data/vendor/kreuzberg/src/utils/mod.rs +17 -17
  185. data/vendor/kreuzberg/src/utils/quality.rs +959 -959
  186. data/vendor/kreuzberg/src/utils/string_utils.rs +381 -381
  187. data/vendor/kreuzberg/stopwords/af_stopwords.json +53 -53
  188. data/vendor/kreuzberg/stopwords/ar_stopwords.json +482 -482
  189. data/vendor/kreuzberg/stopwords/bg_stopwords.json +261 -261
  190. data/vendor/kreuzberg/stopwords/bn_stopwords.json +400 -400
  191. data/vendor/kreuzberg/stopwords/br_stopwords.json +1205 -1205
  192. data/vendor/kreuzberg/stopwords/ca_stopwords.json +280 -280
  193. data/vendor/kreuzberg/stopwords/cs_stopwords.json +425 -425
  194. data/vendor/kreuzberg/stopwords/da_stopwords.json +172 -172
  195. data/vendor/kreuzberg/stopwords/de_stopwords.json +622 -622
  196. data/vendor/kreuzberg/stopwords/el_stopwords.json +849 -849
  197. data/vendor/kreuzberg/stopwords/en_stopwords.json +1300 -1300
  198. data/vendor/kreuzberg/stopwords/eo_stopwords.json +175 -175
  199. data/vendor/kreuzberg/stopwords/es_stopwords.json +734 -734
  200. data/vendor/kreuzberg/stopwords/et_stopwords.json +37 -37
  201. data/vendor/kreuzberg/stopwords/eu_stopwords.json +100 -100
  202. data/vendor/kreuzberg/stopwords/fa_stopwords.json +801 -801
  203. data/vendor/kreuzberg/stopwords/fi_stopwords.json +849 -849
  204. data/vendor/kreuzberg/stopwords/fr_stopwords.json +693 -693
  205. data/vendor/kreuzberg/stopwords/ga_stopwords.json +111 -111
  206. data/vendor/kreuzberg/stopwords/gl_stopwords.json +162 -162
  207. data/vendor/kreuzberg/stopwords/gu_stopwords.json +226 -226
  208. data/vendor/kreuzberg/stopwords/ha_stopwords.json +41 -41
  209. data/vendor/kreuzberg/stopwords/he_stopwords.json +196 -196
  210. data/vendor/kreuzberg/stopwords/hi_stopwords.json +227 -227
  211. data/vendor/kreuzberg/stopwords/hr_stopwords.json +181 -181
  212. data/vendor/kreuzberg/stopwords/hu_stopwords.json +791 -791
  213. data/vendor/kreuzberg/stopwords/hy_stopwords.json +47 -47
  214. data/vendor/kreuzberg/stopwords/id_stopwords.json +760 -760
  215. data/vendor/kreuzberg/stopwords/it_stopwords.json +634 -634
  216. data/vendor/kreuzberg/stopwords/ja_stopwords.json +136 -136
  217. data/vendor/kreuzberg/stopwords/kn_stopwords.json +84 -84
  218. data/vendor/kreuzberg/stopwords/ko_stopwords.json +681 -681
  219. data/vendor/kreuzberg/stopwords/ku_stopwords.json +64 -64
  220. data/vendor/kreuzberg/stopwords/la_stopwords.json +51 -51
  221. data/vendor/kreuzberg/stopwords/lt_stopwords.json +476 -476
  222. data/vendor/kreuzberg/stopwords/lv_stopwords.json +163 -163
  223. data/vendor/kreuzberg/stopwords/ml_stopwords.json +1 -1
  224. data/vendor/kreuzberg/stopwords/mr_stopwords.json +101 -101
  225. data/vendor/kreuzberg/stopwords/ms_stopwords.json +477 -477
  226. data/vendor/kreuzberg/stopwords/ne_stopwords.json +490 -490
  227. data/vendor/kreuzberg/stopwords/nl_stopwords.json +415 -415
  228. data/vendor/kreuzberg/stopwords/no_stopwords.json +223 -223
  229. data/vendor/kreuzberg/stopwords/pl_stopwords.json +331 -331
  230. data/vendor/kreuzberg/stopwords/pt_stopwords.json +562 -562
  231. data/vendor/kreuzberg/stopwords/ro_stopwords.json +436 -436
  232. data/vendor/kreuzberg/stopwords/ru_stopwords.json +561 -561
  233. data/vendor/kreuzberg/stopwords/si_stopwords.json +193 -193
  234. data/vendor/kreuzberg/stopwords/sk_stopwords.json +420 -420
  235. data/vendor/kreuzberg/stopwords/sl_stopwords.json +448 -448
  236. data/vendor/kreuzberg/stopwords/so_stopwords.json +32 -32
  237. data/vendor/kreuzberg/stopwords/st_stopwords.json +33 -33
  238. data/vendor/kreuzberg/stopwords/sv_stopwords.json +420 -420
  239. data/vendor/kreuzberg/stopwords/sw_stopwords.json +76 -76
  240. data/vendor/kreuzberg/stopwords/ta_stopwords.json +129 -129
  241. data/vendor/kreuzberg/stopwords/te_stopwords.json +54 -54
  242. data/vendor/kreuzberg/stopwords/th_stopwords.json +118 -118
  243. data/vendor/kreuzberg/stopwords/tl_stopwords.json +149 -149
  244. data/vendor/kreuzberg/stopwords/tr_stopwords.json +506 -506
  245. data/vendor/kreuzberg/stopwords/uk_stopwords.json +75 -75
  246. data/vendor/kreuzberg/stopwords/ur_stopwords.json +519 -519
  247. data/vendor/kreuzberg/stopwords/vi_stopwords.json +647 -647
  248. data/vendor/kreuzberg/stopwords/yo_stopwords.json +62 -62
  249. data/vendor/kreuzberg/stopwords/zh_stopwords.json +796 -796
  250. data/vendor/kreuzberg/stopwords/zu_stopwords.json +31 -31
  251. data/vendor/kreuzberg/tests/api_extract_multipart.rs +52 -52
  252. data/vendor/kreuzberg/tests/api_tests.rs +966 -966
  253. data/vendor/kreuzberg/tests/archive_integration.rs +545 -545
  254. data/vendor/kreuzberg/tests/batch_orchestration.rs +556 -556
  255. data/vendor/kreuzberg/tests/batch_processing.rs +318 -318
  256. data/vendor/kreuzberg/tests/bibtex_parity_test.rs +421 -421
  257. data/vendor/kreuzberg/tests/concurrency_stress.rs +533 -533
  258. data/vendor/kreuzberg/tests/config_features.rs +612 -612
  259. data/vendor/kreuzberg/tests/config_loading_tests.rs +416 -416
  260. data/vendor/kreuzberg/tests/core_integration.rs +510 -510
  261. data/vendor/kreuzberg/tests/csv_integration.rs +414 -414
  262. data/vendor/kreuzberg/tests/docbook_extractor_tests.rs +500 -500
  263. data/vendor/kreuzberg/tests/docx_metadata_extraction_test.rs +122 -122
  264. data/vendor/kreuzberg/tests/docx_vs_pandoc_comparison.rs +370 -370
  265. data/vendor/kreuzberg/tests/email_integration.rs +327 -327
  266. data/vendor/kreuzberg/tests/epub_native_extractor_tests.rs +275 -275
  267. data/vendor/kreuzberg/tests/error_handling.rs +402 -402
  268. data/vendor/kreuzberg/tests/fictionbook_extractor_tests.rs +228 -228
  269. data/vendor/kreuzberg/tests/format_integration.rs +165 -164
  270. data/vendor/kreuzberg/tests/helpers/mod.rs +142 -142
  271. data/vendor/kreuzberg/tests/html_table_test.rs +551 -551
  272. data/vendor/kreuzberg/tests/image_integration.rs +255 -255
  273. data/vendor/kreuzberg/tests/instrumentation_test.rs +139 -139
  274. data/vendor/kreuzberg/tests/jats_extractor_tests.rs +639 -639
  275. data/vendor/kreuzberg/tests/jupyter_extractor_tests.rs +704 -704
  276. data/vendor/kreuzberg/tests/keywords_integration.rs +479 -479
  277. data/vendor/kreuzberg/tests/keywords_quality.rs +509 -509
  278. data/vendor/kreuzberg/tests/latex_extractor_tests.rs +496 -496
  279. data/vendor/kreuzberg/tests/markdown_extractor_tests.rs +490 -490
  280. data/vendor/kreuzberg/tests/mime_detection.rs +429 -429
  281. data/vendor/kreuzberg/tests/ocr_configuration.rs +514 -514
  282. data/vendor/kreuzberg/tests/ocr_errors.rs +698 -698
  283. data/vendor/kreuzberg/tests/ocr_quality.rs +629 -629
  284. data/vendor/kreuzberg/tests/ocr_stress.rs +469 -469
  285. data/vendor/kreuzberg/tests/odt_extractor_tests.rs +674 -674
  286. data/vendor/kreuzberg/tests/opml_extractor_tests.rs +616 -616
  287. data/vendor/kreuzberg/tests/orgmode_extractor_tests.rs +822 -822
  288. data/vendor/kreuzberg/tests/pdf_integration.rs +45 -45
  289. data/vendor/kreuzberg/tests/pdfium_linking.rs +374 -374
  290. data/vendor/kreuzberg/tests/pipeline_integration.rs +1436 -1436
  291. data/vendor/kreuzberg/tests/plugin_ocr_backend_test.rs +776 -776
  292. data/vendor/kreuzberg/tests/plugin_postprocessor_test.rs +560 -560
  293. data/vendor/kreuzberg/tests/plugin_system.rs +927 -927
  294. data/vendor/kreuzberg/tests/plugin_validator_test.rs +783 -783
  295. data/vendor/kreuzberg/tests/registry_integration_tests.rs +587 -587
  296. data/vendor/kreuzberg/tests/rst_extractor_tests.rs +694 -694
  297. data/vendor/kreuzberg/tests/rtf_extractor_tests.rs +775 -775
  298. data/vendor/kreuzberg/tests/security_validation.rs +416 -416
  299. data/vendor/kreuzberg/tests/stopwords_integration_test.rs +888 -888
  300. data/vendor/kreuzberg/tests/test_fastembed.rs +631 -631
  301. data/vendor/kreuzberg/tests/typst_behavioral_tests.rs +1260 -1260
  302. data/vendor/kreuzberg/tests/typst_extractor_tests.rs +648 -648
  303. data/vendor/kreuzberg/tests/xlsx_metadata_extraction_test.rs +87 -87
  304. data/vendor/kreuzberg-tesseract/.commitlintrc.json +13 -13
  305. data/vendor/kreuzberg-tesseract/.crate-ignore +2 -2
  306. data/vendor/kreuzberg-tesseract/Cargo.lock +2933 -2933
  307. data/vendor/kreuzberg-tesseract/Cargo.toml +2 -2
  308. data/vendor/kreuzberg-tesseract/LICENSE +22 -22
  309. data/vendor/kreuzberg-tesseract/README.md +399 -399
  310. data/vendor/kreuzberg-tesseract/build.rs +1354 -1354
  311. data/vendor/kreuzberg-tesseract/patches/README.md +71 -71
  312. data/vendor/kreuzberg-tesseract/patches/tesseract.diff +199 -199
  313. data/vendor/kreuzberg-tesseract/src/api.rs +1371 -1371
  314. data/vendor/kreuzberg-tesseract/src/choice_iterator.rs +77 -77
  315. data/vendor/kreuzberg-tesseract/src/enums.rs +297 -297
  316. data/vendor/kreuzberg-tesseract/src/error.rs +81 -81
  317. data/vendor/kreuzberg-tesseract/src/lib.rs +145 -145
  318. data/vendor/kreuzberg-tesseract/src/monitor.rs +57 -57
  319. data/vendor/kreuzberg-tesseract/src/mutable_iterator.rs +197 -197
  320. data/vendor/kreuzberg-tesseract/src/page_iterator.rs +253 -253
  321. data/vendor/kreuzberg-tesseract/src/result_iterator.rs +286 -286
  322. data/vendor/kreuzberg-tesseract/src/result_renderer.rs +183 -183
  323. data/vendor/kreuzberg-tesseract/tests/integration_test.rs +211 -211
  324. data/vendor/rb-sys/.cargo_vcs_info.json +5 -5
  325. data/vendor/rb-sys/Cargo.lock +393 -393
  326. data/vendor/rb-sys/Cargo.toml +70 -70
  327. data/vendor/rb-sys/Cargo.toml.orig +57 -57
  328. data/vendor/rb-sys/LICENSE-APACHE +190 -190
  329. data/vendor/rb-sys/LICENSE-MIT +21 -21
  330. data/vendor/rb-sys/build/features.rs +111 -111
  331. data/vendor/rb-sys/build/main.rs +286 -286
  332. data/vendor/rb-sys/build/stable_api_config.rs +155 -155
  333. data/vendor/rb-sys/build/version.rs +50 -50
  334. data/vendor/rb-sys/readme.md +36 -36
  335. data/vendor/rb-sys/src/bindings.rs +21 -21
  336. data/vendor/rb-sys/src/hidden.rs +11 -11
  337. data/vendor/rb-sys/src/lib.rs +35 -35
  338. data/vendor/rb-sys/src/macros.rs +371 -371
  339. data/vendor/rb-sys/src/memory.rs +53 -53
  340. data/vendor/rb-sys/src/ruby_abi_version.rs +38 -38
  341. data/vendor/rb-sys/src/special_consts.rs +31 -31
  342. data/vendor/rb-sys/src/stable_api/compiled.c +179 -179
  343. data/vendor/rb-sys/src/stable_api/compiled.rs +257 -257
  344. data/vendor/rb-sys/src/stable_api/ruby_2_7.rs +324 -324
  345. data/vendor/rb-sys/src/stable_api/ruby_3_0.rs +332 -332
  346. data/vendor/rb-sys/src/stable_api/ruby_3_1.rs +325 -325
  347. data/vendor/rb-sys/src/stable_api/ruby_3_2.rs +323 -323
  348. data/vendor/rb-sys/src/stable_api/ruby_3_3.rs +339 -339
  349. data/vendor/rb-sys/src/stable_api/ruby_3_4.rs +339 -339
  350. data/vendor/rb-sys/src/stable_api.rs +260 -260
  351. data/vendor/rb-sys/src/symbol.rs +31 -31
  352. data/vendor/rb-sys/src/tracking_allocator.rs +330 -330
  353. data/vendor/rb-sys/src/utils.rs +89 -89
  354. data/vendor/rb-sys/src/value_type.rs +7 -7
  355. metadata +81 -22
  356. data/vendor/kreuzberg-ffi/Cargo.toml +0 -63
  357. data/vendor/kreuzberg-ffi/README.md +0 -851
  358. data/vendor/kreuzberg-ffi/build.rs +0 -176
  359. data/vendor/kreuzberg-ffi/cbindgen.toml +0 -27
  360. data/vendor/kreuzberg-ffi/kreuzberg-ffi-install.pc +0 -12
  361. data/vendor/kreuzberg-ffi/kreuzberg-ffi.pc.in +0 -12
  362. data/vendor/kreuzberg-ffi/kreuzberg.h +0 -1087
  363. data/vendor/kreuzberg-ffi/src/lib.rs +0 -3616
  364. data/vendor/kreuzberg-ffi/src/panic_shield.rs +0 -247
  365. data/vendor/kreuzberg-ffi/tests.disabled/README.md +0 -48
  366. data/vendor/kreuzberg-ffi/tests.disabled/config_loading_tests.rs +0 -299
  367. data/vendor/kreuzberg-ffi/tests.disabled/config_tests.rs +0 -346
  368. data/vendor/kreuzberg-ffi/tests.disabled/extractor_tests.rs +0 -232
  369. data/vendor/kreuzberg-ffi/tests.disabled/plugin_registration_tests.rs +0 -470
data/vendor/kreuzberg/src/extractors/opml.rs CHANGED
@@ -1,635 +1,635 @@
1
- //! Native OPML (Outline Processor Markup Language) extractor using the `roxmltree` library.
2
- //!
3
- //! This extractor provides native Rust-based OPML extraction, parsing outline structures
4
- //! commonly used for RSS feed lists, podcast directories, and general outlines.
5
- //!
6
- //! Extracts:
7
- //! - Metadata from `<head>`: title, dateCreated, dateModified, ownerName, ownerEmail
8
- //! - Content from `<body><outline>` hierarchy using text attributes
9
- //! - Outline hierarchy structure preserved in plain text format with indentation
10
- //! - Note: URLs (xmlUrl, htmlUrl) are extracted from attributes but not included in main content
11
- //!
12
- //! Example OPML structure:
13
- //! ```xml
14
- //! <opml version="2.0">
15
- //! <head>
16
- //! <title>My Feeds</title>
17
- //! <ownerName>John</ownerName>
18
- //! </head>
19
- //! <body>
20
- //! <outline text="Tech" type="folder">
21
- //! <outline text="Hacker News" type="rss" xmlUrl="https://..." />
22
- //! </outline>
23
- //! </body>
24
- //! </opml>
25
- //! ```
26
-
27
- use crate::Result;
28
- use crate::core::config::ExtractionConfig;
29
- use crate::plugins::{DocumentExtractor, Plugin};
30
- use crate::types::{ExtractionResult, Metadata};
31
- use async_trait::async_trait;
32
- use std::collections::HashMap;
33
-
34
- #[cfg(feature = "office")]
35
- use roxmltree::Node;
36
-
37
- /// OPML format extractor.
38
- ///
39
- /// Extracts outline structure and metadata from OPML documents using native Rust parsing.
40
- pub struct OpmlExtractor;
41
-
42
- impl OpmlExtractor {
43
- /// Create a new OPML extractor.
44
- pub fn new() -> Self {
45
- Self
46
- }
47
-
48
- /// Extract OPML content and structure
49
- #[cfg(feature = "office")]
50
- fn extract_content_and_metadata(content: &[u8]) -> Result<(String, HashMap<String, serde_json::Value>)> {
51
- let doc = roxmltree::Document::parse(
52
- std::str::from_utf8(content)
53
- .map_err(|e| crate::KreuzbergError::Other(format!("Invalid UTF-8 in OPML: {}", e)))?,
54
- )
55
- .map_err(|e| crate::KreuzbergError::Other(format!("Failed to parse OPML: {}", e)))?;
56
-
57
- let mut extracted_content = String::new();
58
- let mut metadata = HashMap::new();
59
-
60
- if let Some(opml) = doc.root().children().find(|n| n.tag_name().name() == "opml") {
61
- if let Some(head) = opml.children().find(|n| n.tag_name().name() == "head") {
62
- for child in head.children().filter(|n| n.is_element()) {
63
- let tag = child.tag_name().name();
64
- let text = child.text().unwrap_or("").trim();
65
-
66
- match tag {
67
- "title" => {
68
- if !text.is_empty() {
69
- metadata.insert("title".to_string(), serde_json::json!(text));
70
- }
71
- }
72
- "dateCreated" => {
73
- if !text.is_empty() {
74
- metadata.insert("dateCreated".to_string(), serde_json::json!(text));
75
- }
76
- }
77
- "dateModified" => {
78
- if !text.is_empty() {
79
- metadata.insert("dateModified".to_string(), serde_json::json!(text));
80
- }
81
- }
82
- "ownerName" => {
83
- if !text.is_empty() {
84
- metadata.insert("ownerName".to_string(), serde_json::json!(text));
85
- }
86
- }
87
- "ownerEmail" => {
88
- if !text.is_empty() {
89
- metadata.insert("ownerEmail".to_string(), serde_json::json!(text));
90
- }
91
- }
92
- _ => {}
93
- }
94
- }
95
- }
96
-
97
- if let Some(body) = opml.children().find(|n| n.tag_name().name() == "body") {
98
- if let Some(title) = metadata.get("title").and_then(|v| v.as_str()) {
99
- extracted_content.push_str(title);
100
- extracted_content.push('\n');
101
- extracted_content.push('\n');
102
- }
103
-
104
- for outline in body.children().filter(|n| n.tag_name().name() == "outline") {
105
- Self::process_outline(outline, 0, &mut extracted_content);
106
- }
107
- }
108
- }
109
-
110
- Ok((extracted_content.trim().to_string(), metadata))
111
- }
112
-
113
- /// Process outline elements recursively
114
- ///
115
- /// Extracts text content from outline hierarchy while preserving nesting depth
116
- /// through indentation. URL attributes are excluded from the main content.
117
- #[cfg(feature = "office")]
118
- fn process_outline(node: Node, depth: usize, output: &mut String) {
119
- let text = node.attribute("text").unwrap_or("").trim();
120
-
121
- if !text.is_empty() {
122
- let indent = " ".repeat(depth);
123
- output.push_str(&indent);
124
- output.push_str(text);
125
- output.push('\n');
126
- }
127
-
128
- for child in node.children().filter(|n| n.tag_name().name() == "outline") {
129
- Self::process_outline(child, depth + 1, output);
130
- }
131
- }
132
- }
133
-
134
- impl Default for OpmlExtractor {
135
- fn default() -> Self {
136
- Self::new()
137
- }
138
- }
139
-
140
- impl Plugin for OpmlExtractor {
141
- fn name(&self) -> &str {
142
- "opml-extractor"
143
- }
144
-
145
- fn version(&self) -> String {
146
- env!("CARGO_PKG_VERSION").to_string()
147
- }
148
-
149
- fn initialize(&self) -> Result<()> {
150
- Ok(())
151
- }
152
-
153
- fn shutdown(&self) -> Result<()> {
154
- Ok(())
155
- }
156
-
157
- fn description(&self) -> &str {
158
- "Extracts content and metadata from OPML (Outline Processor Markup Language) documents"
159
- }
160
-
161
- fn author(&self) -> &str {
162
- "Kreuzberg Team"
163
- }
164
- }
165
-
166
- #[cfg(feature = "office")]
167
- #[async_trait]
168
- impl DocumentExtractor for OpmlExtractor {
169
- #[cfg_attr(
170
- feature = "otel",
171
- tracing::instrument(
172
- skip(self, content, _config),
173
- fields(
174
- extractor.name = self.name(),
175
- content.size_bytes = content.len(),
176
- )
177
- )
178
- )]
179
- async fn extract_bytes(
180
- &self,
181
- content: &[u8],
182
- mime_type: &str,
183
- _config: &ExtractionConfig,
184
- ) -> Result<ExtractionResult> {
185
- let (extracted_content, metadata_map) = Self::extract_content_and_metadata(content)?;
186
-
187
- Ok(ExtractionResult {
188
- content: extracted_content,
189
- mime_type: mime_type.to_string(),
190
- metadata: Metadata {
191
- additional: metadata_map,
192
- ..Default::default()
193
- },
194
- pages: None,
195
- tables: vec![],
196
- detected_languages: None,
197
- chunks: None,
198
- images: None,
199
- })
200
- }
201
-
202
- fn supported_mime_types(&self) -> &[&str] {
203
- &["text/x-opml", "application/xml+opml"]
204
- }
205
-
206
- fn priority(&self) -> i32 {
207
- 55
208
- }
209
- }
210
-
211
- #[cfg(all(test, feature = "office"))]
212
- mod tests {
213
- use super::*;
214
-
215
- #[test]
216
- fn test_opml_extractor_plugin_interface() {
217
- let extractor = OpmlExtractor::new();
218
- assert_eq!(extractor.name(), "opml-extractor");
219
- assert_eq!(extractor.version(), env!("CARGO_PKG_VERSION"));
220
- assert_eq!(extractor.priority(), 55);
221
- assert!(!extractor.supported_mime_types().is_empty());
222
- }
223
-
224
- #[test]
225
- fn test_opml_extractor_default() {
226
- let extractor = OpmlExtractor;
227
- assert_eq!(extractor.name(), "opml-extractor");
228
- }
229
-
230
- #[tokio::test]
231
- async fn test_opml_extractor_initialize_shutdown() {
232
- let extractor = OpmlExtractor::new();
233
- assert!(extractor.initialize().is_ok());
234
- assert!(extractor.shutdown().is_ok());
235
- }
236
-
237
- #[test]
238
- fn test_opml_simple_outline_parsing() {
239
- let opml = br#"<?xml version="1.0"?>
240
- <opml version="2.0">
241
- <head>
242
- <title>Test</title>
243
- </head>
244
- <body>
245
- <outline text="Item 1" />
246
- <outline text="Item 2" />
247
- </body>
248
- </opml>"#;
249
-
250
- let (content, metadata) = OpmlExtractor::extract_content_and_metadata(opml).expect("Should parse simple OPML");
251
-
252
- assert!(content.contains("Item 1"), "Should extract first item");
253
- assert!(content.contains("Item 2"), "Should extract second item");
254
- assert_eq!(
255
- metadata.get("title").and_then(|v| v.as_str()),
256
- Some("Test"),
257
- "Should extract title"
258
- );
259
- }
260
-
261
- #[test]
262
- fn test_opml_nested_hierarchy() {
263
- let opml = br#"<?xml version="1.0"?>
264
- <opml version="2.0">
265
- <head>
266
- <title>Hierarchy Test</title>
267
- </head>
268
- <body>
269
- <outline text="Category">
270
- <outline text="Subcategory">
271
- <outline text="Item" />
272
- </outline>
273
- </outline>
274
- </body>
275
- </opml>"#;
276
-
277
- let (content, _) = OpmlExtractor::extract_content_and_metadata(opml).expect("Should parse nested OPML");
278
-
279
- assert!(content.contains("Category"), "Should contain top level");
280
- assert!(content.contains("Subcategory"), "Should contain nested level");
281
- assert!(content.contains("Item"), "Should contain deep item");
282
- assert!(content.contains(" "), "Should have indentation for nested items");
283
- }
284
-
285
- #[test]
286
- fn test_opml_rss_feeds() {
287
- let opml = br#"<?xml version="1.0"?>
288
- <opml version="2.0">
289
- <head>
290
- <title>Feeds</title>
291
- </head>
292
- <body>
293
- <outline text="Tech">
294
- <outline text="Hacker News" type="rss" xmlUrl="https://news.ycombinator.com/rss" htmlUrl="https://news.ycombinator.com/" />
295
- <outline text="TechCrunch" type="rss" xmlUrl="https://techcrunch.com/feed/" />
296
- </outline>
297
- </body>
298
- </opml>"#;
299
-
300
- let (content, _) = OpmlExtractor::extract_content_and_metadata(opml).expect("Should parse RSS OPML");
301
-
302
- assert!(content.contains("Hacker News"), "Should extract feed title");
303
- assert!(
304
- !content.contains("https://"),
305
- "Should NOT extract feed URLs (text-only extraction)"
306
- );
307
- assert!(content.contains("TechCrunch"), "Should extract multiple feeds");
308
- }
309
-
310
- #[test]
311
- fn test_opml_metadata_extraction() {
312
- let opml = br#"<?xml version="1.0"?>
313
- <opml version="2.0">
314
- <head>
315
- <title>My Feeds</title>
316
- <dateCreated>Mon, 06 Nov 2023 00:00:00 GMT</dateCreated>
317
- <dateModified>Fri, 01 Dec 2023 12:00:00 GMT</dateModified>
318
- <ownerName>John Doe</ownerName>
319
- <ownerEmail>john@example.com</ownerEmail>
320
- </head>
321
- <body>
322
- <outline text="Item" />
323
- </body>
324
- </opml>"#;
325
-
326
- let (_content, metadata) = OpmlExtractor::extract_content_and_metadata(opml).expect("Should extract metadata");
327
-
328
- assert_eq!(metadata.get("title").and_then(|v| v.as_str()), Some("My Feeds"));
329
- assert_eq!(metadata.get("ownerName").and_then(|v| v.as_str()), Some("John Doe"));
330
- assert_eq!(
331
- metadata.get("ownerEmail").and_then(|v| v.as_str()),
332
- Some("john@example.com")
333
- );
334
- assert!(metadata.contains_key("dateCreated"));
335
- assert!(metadata.contains_key("dateModified"));
336
- }
337
-
338
- #[test]
339
- fn test_opml_supported_mime_types() {
340
- let extractor = OpmlExtractor::new();
341
- let supported = extractor.supported_mime_types();
342
- assert!(supported.contains(&"text/x-opml"));
343
- assert!(supported.contains(&"application/xml+opml"));
344
- }
345
-
346
- #[test]
347
- fn test_opml_with_special_characters() {
348
- let opml = br#"<?xml version="1.0"?>
349
- <opml version="2.0">
350
- <head>
351
- <title>Test &amp; Special</title>
352
- </head>
353
- <body>
354
- <outline text="Business &amp; Startups" />
355
- <outline text="Science &lt;Advanced&gt;" />
356
- </body>
357
- </opml>"#;
358
-
359
- let (content, metadata) =
360
- OpmlExtractor::extract_content_and_metadata(opml).expect("Should handle special characters");
361
-
362
- assert!(
363
- content.contains("Business") && content.contains("Startups"),
364
- "Should decode HTML entities"
365
- );
366
- let title = metadata.get("title").and_then(|v| v.as_str()).unwrap_or("");
367
- assert!(!title.is_empty(), "Should extract title");
368
- }
369
-
370
- #[test]
371
- fn test_opml_empty_body() {
372
- let opml = br#"<?xml version="1.0"?>
373
- <opml version="2.0">
374
- <head>
375
- <title>Empty</title>
376
- </head>
377
- <body>
378
- </body>
379
- </opml>"#;
380
-
381
- let (_content, metadata) = OpmlExtractor::extract_content_and_metadata(opml).expect("Should handle empty body");
382
-
383
- assert_eq!(metadata.get("title").and_then(|v| v.as_str()), Some("Empty"));
384
- }
385
-
386
- #[tokio::test]
387
- async fn test_opml_extractor_async_extraction() {
388
- let extractor = OpmlExtractor::new();
389
- let opml = br#"<?xml version="1.0"?>
390
- <opml version="2.0">
391
- <head>
392
- <title>Async Test</title>
393
- </head>
394
- <body>
395
- <outline text="Item" />
396
- </body>
397
- </opml>"#;
398
-
399
- let result = extractor
400
- .extract_bytes(opml, "text/x-opml", &ExtractionConfig::default())
401
- .await
402
- .expect("Should extract OPML asynchronously");
403
-
404
- assert_eq!(result.mime_type, "text/x-opml");
405
- assert!(result.content.contains("Item"));
406
- assert_eq!(
407
- result.metadata.additional.get("title").and_then(|v| v.as_str()),
408
- Some("Async Test")
409
- );
410
- }
411
-
412
- #[test]
413
- fn test_opml_malformed_missing_closing_tag() {
414
- let opml = br#"<?xml version="1.0"?>
415
- <opml version="2.0">
416
- <head>
417
- <title>Broken</title>
418
- </head>
419
- <body>
420
- <outline text="Unclosed"
421
- </body>
422
- </opml>"#;
423
-
424
- let result = OpmlExtractor::extract_content_and_metadata(opml);
425
- assert!(result.is_err(), "Should fail to parse OPML with missing closing tags");
426
- }
427
-
428
- #[test]
429
- fn test_opml_malformed_invalid_nesting() {
430
- let opml = br#"<?xml version="1.0"?>
431
- <opml version="2.0">
432
- <head>
433
- <title>Invalid Nesting</title>
434
- <body>
435
- <outline text="Item" />
436
- </body>
437
- </opml>"#;
438
-
439
- let result = OpmlExtractor::extract_content_and_metadata(opml);
440
- assert!(result.is_err(), "Should fail to parse OPML with invalid nesting");
441
- }
442
-
443
- #[test]
444
- fn test_opml_empty_outline_elements() {
445
- let opml = br#"<?xml version="1.0"?>
446
- <opml version="2.0">
447
- <head>
448
- <title>Empty Outlines</title>
449
- </head>
450
- <body>
451
- <outline text="" />
452
- <outline />
453
- <outline text="Valid Item">
454
- <outline text="" />
455
- <outline text="Another Valid" />
456
- </outline>
457
- </body>
458
- </opml>"#;
459
-
460
- let (content, metadata) =
461
- OpmlExtractor::extract_content_and_metadata(opml).expect("Should handle empty outline elements");
462
-
463
- assert!(content.contains("Valid Item"), "Should extract valid items");
464
- assert!(content.contains("Another Valid"), "Should extract nested valid items");
465
- let empty_count = content.matches("\n\n").count();
466
- assert!(empty_count < 3, "Should skip empty outline elements");
467
-
468
- assert_eq!(metadata.get("title").and_then(|v| v.as_str()), Some("Empty Outlines"));
469
- }
470
-
471
- #[test]
472
- fn test_opml_deeply_nested_empty_nodes() {
473
- let opml = br#"<?xml version="1.0"?>
474
- <opml version="2.0">
475
- <head>
476
- <title>Deep Nesting</title>
477
- </head>
478
- <body>
479
- <outline text="Level 1">
480
- <outline text="">
481
- <outline text="">
482
- <outline text="Deep Item">
483
- <outline text="" />
484
- </outline>
485
- </outline>
486
- </outline>
487
- <outline text="Level 1 Sibling" />
488
- </outline>
489
- </body>
490
- </opml>"#;
491
-
492
- let (content, _) =
493
- OpmlExtractor::extract_content_and_metadata(opml).expect("Should handle deeply nested structures");
494
-
495
- assert!(content.contains("Level 1"), "Should extract top-level item");
496
- assert!(content.contains("Deep Item"), "Should extract deeply nested item");
497
- assert!(content.contains("Level 1 Sibling"), "Should extract sibling items");
498
- }
499
-
500
- #[test]
501
- fn test_opml_outline_with_missing_text_attribute() {
502
- let opml = br#"<?xml version="1.0"?>
503
- <opml version="2.0">
504
- <head>
505
- <title>Missing Attributes</title>
506
- </head>
507
- <body>
508
- <outline type="folder" />
509
- <outline text="Valid Item" type="rss" />
510
- <outline type="rss" xmlUrl="https://example.com/feed" />
511
- </body>
512
- </opml>"#;
513
-
514
- let (content, metadata) = OpmlExtractor::extract_content_and_metadata(opml)
515
- .expect("Should handle outline with missing text attribute");
516
-
517
- assert!(content.contains("Valid Item"), "Should extract item with text");
518
- assert!(!content.contains("https://"), "Should not extract URLs");
519
-
520
- assert_eq!(
521
- metadata.get("title").and_then(|v| v.as_str()),
522
- Some("Missing Attributes")
523
- );
524
- }
525
-
526
- #[test]
527
- fn test_opml_whitespace_only_text_attribute() {
528
- let opml = br#"<?xml version="1.0"?>
529
- <opml version="2.0">
530
- <head>
531
- <title>Whitespace Test</title>
532
- </head>
533
- <body>
534
- <outline text=" " />
535
- <outline text="
536
- " />
537
- <outline text="Real Content" />
538
- </body>
539
- </opml>"#;
540
-
541
- let (content, _) =
542
- OpmlExtractor::extract_content_and_metadata(opml).expect("Should handle whitespace-only text");
543
-
544
- assert!(
545
- content.contains("Real Content"),
546
- "Should extract non-whitespace content"
547
- );
548
- let trimmed = content.trim();
549
- assert!(trimmed.contains("Whitespace Test"), "Should have title");
550
- assert!(trimmed.contains("Real Content"), "Should have real content");
551
- }
552
-
553
- #[test]
554
- fn test_opml_html_entity_in_nested_structure() {
555
- let opml = br#"<?xml version="1.0"?>
556
- <opml version="2.0">
557
- <head>
558
- <title>Entities &amp; Nesting</title>
559
- </head>
560
- <body>
561
- <outline text="News &amp; Updates">
562
- <outline text="Tech &lt; Science" />
563
- <outline text="Health &gt; Wealth" />
564
- </outline>
565
- </body>
566
- </opml>"#;
567
-
568
- let (content, metadata) =
569
- OpmlExtractor::extract_content_and_metadata(opml).expect("Should handle HTML entities");
570
-
571
- assert!(
572
- content.contains("News") && content.contains("Updates"),
573
- "Should decode &amp; entity"
574
- );
575
- assert!(content.contains("Tech"), "Should handle &lt; entity");
576
- assert!(content.contains("Science"), "Should decode entity properly");
577
-
578
- let title = metadata.get("title").and_then(|v| v.as_str()).unwrap_or("");
579
- assert!(
580
- title.contains("&") && title.contains("Nesting"),
581
- "Title should have decoded entity"
582
- );
583
- }
584
-
585
- #[test]
586
- fn test_opml_single_outline_no_children() {
587
- let opml = br#"<?xml version="1.0"?>
588
- <opml version="2.0">
589
- <head>
590
- <title>Single</title>
591
- </head>
592
- <body>
593
- <outline text="Only Item" />
594
- </body>
595
- </opml>"#;
596
-
597
- let (content, metadata) =
598
- OpmlExtractor::extract_content_and_metadata(opml).expect("Should handle single outline");
599
-
600
- assert!(content.contains("Only Item"), "Should extract single item");
601
- assert_eq!(metadata.get("title").and_then(|v| v.as_str()), Some("Single"));
602
- }
603
-
604
- #[test]
605
- fn test_opml_head_without_body() {
606
- let opml = br#"<?xml version="1.0"?>
607
- <opml version="2.0">
608
- <head>
609
- <title>No Body</title>
610
- </head>
611
- </opml>"#;
612
-
613
- let (content, metadata) =
614
- OpmlExtractor::extract_content_and_metadata(opml).expect("Should handle OPML without body");
615
-
616
- assert_eq!(metadata.get("title").and_then(|v| v.as_str()), Some("No Body"));
617
- assert!(content.is_empty() || content.trim() == "No Body");
618
- }
619
-
620
- #[test]
621
- fn test_opml_body_without_head() {
622
- let opml = br#"<?xml version="1.0"?>
623
- <opml version="2.0">
624
- <body>
625
- <outline text="Item" />
626
- </body>
627
- </opml>"#;
628
-
629
- let (content, metadata) =
630
- OpmlExtractor::extract_content_and_metadata(opml).expect("Should handle OPML without head");
631
-
632
- assert!(content.contains("Item"), "Should extract body content");
633
- assert!(metadata.is_empty(), "Should have no metadata without head");
634
- }
635
- }
1
+ //! Native OPML (Outline Processor Markup Language) extractor using the `roxmltree` library.
2
+ //!
3
+ //! This extractor provides native Rust-based OPML extraction, parsing outline structures
4
+ //! commonly used for RSS feed lists, podcast directories, and general outlines.
5
+ //!
6
+ //! Extracts:
7
+ //! - Metadata from `<head>`: title, dateCreated, dateModified, ownerName, ownerEmail
8
+ //! - Content from `<body><outline>` hierarchy using text attributes
9
+ //! - Outline hierarchy structure preserved in plain text format with indentation
10
+ //! - Note: URLs (xmlUrl, htmlUrl) are extracted from attributes but not included in main content
11
+ //!
12
+ //! Example OPML structure:
13
+ //! ```xml
14
+ //! <opml version="2.0">
15
+ //! <head>
16
+ //! <title>My Feeds</title>
17
+ //! <ownerName>John</ownerName>
18
+ //! </head>
19
+ //! <body>
20
+ //! <outline text="Tech" type="folder">
21
+ //! <outline text="Hacker News" type="rss" xmlUrl="https://..." />
22
+ //! </outline>
23
+ //! </body>
24
+ //! </opml>
25
+ //! ```
26
+
27
+ use crate::Result;
28
+ use crate::core::config::ExtractionConfig;
29
+ use crate::plugins::{DocumentExtractor, Plugin};
30
+ use crate::types::{ExtractionResult, Metadata};
31
+ use async_trait::async_trait;
32
+ use std::collections::HashMap;
33
+
34
+ #[cfg(feature = "office")]
35
+ use roxmltree::Node;
36
+
37
+ /// OPML format extractor.
38
+ ///
39
+ /// Extracts outline structure and metadata from OPML documents using native Rust parsing.
40
+ pub struct OpmlExtractor;
41
+
42
+ impl OpmlExtractor {
43
+ /// Create a new OPML extractor.
44
+ pub fn new() -> Self {
45
+ Self
46
+ }
47
+
48
+ /// Extract OPML content and structure
49
+ #[cfg(feature = "office")]
50
+ fn extract_content_and_metadata(content: &[u8]) -> Result<(String, HashMap<String, serde_json::Value>)> {
51
+ let doc = roxmltree::Document::parse(
52
+ std::str::from_utf8(content)
53
+ .map_err(|e| crate::KreuzbergError::Other(format!("Invalid UTF-8 in OPML: {}", e)))?,
54
+ )
55
+ .map_err(|e| crate::KreuzbergError::Other(format!("Failed to parse OPML: {}", e)))?;
56
+
57
+ let mut extracted_content = String::new();
58
+ let mut metadata = HashMap::new();
59
+
60
+ if let Some(opml) = doc.root().children().find(|n| n.tag_name().name() == "opml") {
61
+ if let Some(head) = opml.children().find(|n| n.tag_name().name() == "head") {
62
+ for child in head.children().filter(|n| n.is_element()) {
63
+ let tag = child.tag_name().name();
64
+ let text = child.text().unwrap_or("").trim();
65
+
66
+ match tag {
67
+ "title" => {
68
+ if !text.is_empty() {
69
+ metadata.insert("title".to_string(), serde_json::json!(text));
70
+ }
71
+ }
72
+ "dateCreated" => {
73
+ if !text.is_empty() {
74
+ metadata.insert("dateCreated".to_string(), serde_json::json!(text));
75
+ }
76
+ }
77
+ "dateModified" => {
78
+ if !text.is_empty() {
79
+ metadata.insert("dateModified".to_string(), serde_json::json!(text));
80
+ }
81
+ }
82
+ "ownerName" => {
83
+ if !text.is_empty() {
84
+ metadata.insert("ownerName".to_string(), serde_json::json!(text));
85
+ }
86
+ }
87
+ "ownerEmail" => {
88
+ if !text.is_empty() {
89
+ metadata.insert("ownerEmail".to_string(), serde_json::json!(text));
90
+ }
91
+ }
92
+ _ => {}
93
+ }
94
+ }
95
+ }
96
+
97
+ if let Some(body) = opml.children().find(|n| n.tag_name().name() == "body") {
98
+ if let Some(title) = metadata.get("title").and_then(|v| v.as_str()) {
99
+ extracted_content.push_str(title);
100
+ extracted_content.push('\n');
101
+ extracted_content.push('\n');
102
+ }
103
+
104
+ for outline in body.children().filter(|n| n.tag_name().name() == "outline") {
105
+ Self::process_outline(outline, 0, &mut extracted_content);
106
+ }
107
+ }
108
+ }
109
+
110
+ Ok((extracted_content.trim().to_string(), metadata))
111
+ }
112
+
113
+ /// Process outline elements recursively
114
+ ///
115
+ /// Extracts text content from outline hierarchy while preserving nesting depth
116
+ /// through indentation. URL attributes are excluded from the main content.
117
+ #[cfg(feature = "office")]
118
+ fn process_outline(node: Node, depth: usize, output: &mut String) {
119
+ let text = node.attribute("text").unwrap_or("").trim();
120
+
121
+ if !text.is_empty() {
122
+ let indent = " ".repeat(depth);
123
+ output.push_str(&indent);
124
+ output.push_str(text);
125
+ output.push('\n');
126
+ }
127
+
128
+ for child in node.children().filter(|n| n.tag_name().name() == "outline") {
129
+ Self::process_outline(child, depth + 1, output);
130
+ }
131
+ }
132
+ }
133
+
134
+ impl Default for OpmlExtractor {
135
+ fn default() -> Self {
136
+ Self::new()
137
+ }
138
+ }
139
+
140
+ impl Plugin for OpmlExtractor {
141
+ fn name(&self) -> &str {
142
+ "opml-extractor"
143
+ }
144
+
145
+ fn version(&self) -> String {
146
+ env!("CARGO_PKG_VERSION").to_string()
147
+ }
148
+
149
+ fn initialize(&self) -> Result<()> {
150
+ Ok(())
151
+ }
152
+
153
+ fn shutdown(&self) -> Result<()> {
154
+ Ok(())
155
+ }
156
+
157
+ fn description(&self) -> &str {
158
+ "Extracts content and metadata from OPML (Outline Processor Markup Language) documents"
159
+ }
160
+
161
+ fn author(&self) -> &str {
162
+ "Kreuzberg Team"
163
+ }
164
+ }
165
+
166
+ #[cfg(feature = "office")]
167
+ #[async_trait]
168
+ impl DocumentExtractor for OpmlExtractor {
169
+ #[cfg_attr(
170
+ feature = "otel",
171
+ tracing::instrument(
172
+ skip(self, content, _config),
173
+ fields(
174
+ extractor.name = self.name(),
175
+ content.size_bytes = content.len(),
176
+ )
177
+ )
178
+ )]
179
+ async fn extract_bytes(
180
+ &self,
181
+ content: &[u8],
182
+ mime_type: &str,
183
+ _config: &ExtractionConfig,
184
+ ) -> Result<ExtractionResult> {
185
+ let (extracted_content, metadata_map) = Self::extract_content_and_metadata(content)?;
186
+
187
+ Ok(ExtractionResult {
188
+ content: extracted_content,
189
+ mime_type: mime_type.to_string(),
190
+ metadata: Metadata {
191
+ additional: metadata_map,
192
+ ..Default::default()
193
+ },
194
+ pages: None,
195
+ tables: vec![],
196
+ detected_languages: None,
197
+ chunks: None,
198
+ images: None,
199
+ })
200
+ }
201
+
202
+ fn supported_mime_types(&self) -> &[&str] {
203
+ &["text/x-opml", "application/xml+opml"]
204
+ }
205
+
206
+ fn priority(&self) -> i32 {
207
+ 55
208
+ }
209
+ }
210
+
211
+ #[cfg(all(test, feature = "office"))]
212
+ mod tests {
213
+ use super::*;
214
+
215
+ #[test]
216
+ fn test_opml_extractor_plugin_interface() {
217
+ let extractor = OpmlExtractor::new();
218
+ assert_eq!(extractor.name(), "opml-extractor");
219
+ assert_eq!(extractor.version(), env!("CARGO_PKG_VERSION"));
220
+ assert_eq!(extractor.priority(), 55);
221
+ assert!(!extractor.supported_mime_types().is_empty());
222
+ }
223
+
224
+ #[test]
225
+ fn test_opml_extractor_default() {
226
+ let extractor = OpmlExtractor;
227
+ assert_eq!(extractor.name(), "opml-extractor");
228
+ }
229
+
230
+ #[tokio::test]
231
+ async fn test_opml_extractor_initialize_shutdown() {
232
+ let extractor = OpmlExtractor::new();
233
+ assert!(extractor.initialize().is_ok());
234
+ assert!(extractor.shutdown().is_ok());
235
+ }
236
+
237
+ #[test]
238
+ fn test_opml_simple_outline_parsing() {
239
+ let opml = br#"<?xml version="1.0"?>
240
+ <opml version="2.0">
241
+ <head>
242
+ <title>Test</title>
243
+ </head>
244
+ <body>
245
+ <outline text="Item 1" />
246
+ <outline text="Item 2" />
247
+ </body>
248
+ </opml>"#;
249
+
250
+ let (content, metadata) = OpmlExtractor::extract_content_and_metadata(opml).expect("Should parse simple OPML");
251
+
252
+ assert!(content.contains("Item 1"), "Should extract first item");
253
+ assert!(content.contains("Item 2"), "Should extract second item");
254
+ assert_eq!(
255
+ metadata.get("title").and_then(|v| v.as_str()),
256
+ Some("Test"),
257
+ "Should extract title"
258
+ );
259
+ }
260
+
261
+ #[test]
262
+ fn test_opml_nested_hierarchy() {
263
+ let opml = br#"<?xml version="1.0"?>
264
+ <opml version="2.0">
265
+ <head>
266
+ <title>Hierarchy Test</title>
267
+ </head>
268
+ <body>
269
+ <outline text="Category">
270
+ <outline text="Subcategory">
271
+ <outline text="Item" />
272
+ </outline>
273
+ </outline>
274
+ </body>
275
+ </opml>"#;
276
+
277
+ let (content, _) = OpmlExtractor::extract_content_and_metadata(opml).expect("Should parse nested OPML");
278
+
279
+ assert!(content.contains("Category"), "Should contain top level");
280
+ assert!(content.contains("Subcategory"), "Should contain nested level");
281
+ assert!(content.contains("Item"), "Should contain deep item");
282
+ assert!(content.contains(" "), "Should have indentation for nested items");
283
+ }
284
+
285
+ #[test]
286
+ fn test_opml_rss_feeds() {
287
+ let opml = br#"<?xml version="1.0"?>
288
+ <opml version="2.0">
289
+ <head>
290
+ <title>Feeds</title>
291
+ </head>
292
+ <body>
293
+ <outline text="Tech">
294
+ <outline text="Hacker News" type="rss" xmlUrl="https://news.ycombinator.com/rss" htmlUrl="https://news.ycombinator.com/" />
295
+ <outline text="TechCrunch" type="rss" xmlUrl="https://techcrunch.com/feed/" />
296
+ </outline>
297
+ </body>
298
+ </opml>"#;
299
+
300
+ let (content, _) = OpmlExtractor::extract_content_and_metadata(opml).expect("Should parse RSS OPML");
301
+
302
+ assert!(content.contains("Hacker News"), "Should extract feed title");
303
+ assert!(
304
+ !content.contains("https://"),
305
+ "Should NOT extract feed URLs (text-only extraction)"
306
+ );
307
+ assert!(content.contains("TechCrunch"), "Should extract multiple feeds");
308
+ }
309
+
310
+ #[test]
311
+ fn test_opml_metadata_extraction() {
312
+ let opml = br#"<?xml version="1.0"?>
313
+ <opml version="2.0">
314
+ <head>
315
+ <title>My Feeds</title>
316
+ <dateCreated>Mon, 06 Nov 2023 00:00:00 GMT</dateCreated>
317
+ <dateModified>Fri, 01 Dec 2023 12:00:00 GMT</dateModified>
318
+ <ownerName>John Doe</ownerName>
319
+ <ownerEmail>john@example.com</ownerEmail>
320
+ </head>
321
+ <body>
322
+ <outline text="Item" />
323
+ </body>
324
+ </opml>"#;
325
+
326
+ let (_content, metadata) = OpmlExtractor::extract_content_and_metadata(opml).expect("Should extract metadata");
327
+
328
+ assert_eq!(metadata.get("title").and_then(|v| v.as_str()), Some("My Feeds"));
329
+ assert_eq!(metadata.get("ownerName").and_then(|v| v.as_str()), Some("John Doe"));
330
+ assert_eq!(
331
+ metadata.get("ownerEmail").and_then(|v| v.as_str()),
332
+ Some("john@example.com")
333
+ );
334
+ assert!(metadata.contains_key("dateCreated"));
335
+ assert!(metadata.contains_key("dateModified"));
336
+ }
337
+
338
+ #[test]
339
+ fn test_opml_supported_mime_types() {
340
+ let extractor = OpmlExtractor::new();
341
+ let supported = extractor.supported_mime_types();
342
+ assert!(supported.contains(&"text/x-opml"));
343
+ assert!(supported.contains(&"application/xml+opml"));
344
+ }
345
+
346
+ #[test]
347
+ fn test_opml_with_special_characters() {
348
+ let opml = br#"<?xml version="1.0"?>
349
+ <opml version="2.0">
350
+ <head>
351
+ <title>Test &amp; Special</title>
352
+ </head>
353
+ <body>
354
+ <outline text="Business &amp; Startups" />
355
+ <outline text="Science &lt;Advanced&gt;" />
356
+ </body>
357
+ </opml>"#;
358
+
359
+ let (content, metadata) =
360
+ OpmlExtractor::extract_content_and_metadata(opml).expect("Should handle special characters");
361
+
362
+ assert!(
363
+ content.contains("Business") && content.contains("Startups"),
364
+ "Should decode HTML entities"
365
+ );
366
+ let title = metadata.get("title").and_then(|v| v.as_str()).unwrap_or("");
367
+ assert!(!title.is_empty(), "Should extract title");
368
+ }
369
+
370
+ #[test]
371
+ fn test_opml_empty_body() {
372
+ let opml = br#"<?xml version="1.0"?>
373
+ <opml version="2.0">
374
+ <head>
375
+ <title>Empty</title>
376
+ </head>
377
+ <body>
378
+ </body>
379
+ </opml>"#;
380
+
381
+ let (_content, metadata) = OpmlExtractor::extract_content_and_metadata(opml).expect("Should handle empty body");
382
+
383
+ assert_eq!(metadata.get("title").and_then(|v| v.as_str()), Some("Empty"));
384
+ }
385
+
386
+ #[tokio::test]
387
+ async fn test_opml_extractor_async_extraction() {
388
+ let extractor = OpmlExtractor::new();
389
+ let opml = br#"<?xml version="1.0"?>
390
+ <opml version="2.0">
391
+ <head>
392
+ <title>Async Test</title>
393
+ </head>
394
+ <body>
395
+ <outline text="Item" />
396
+ </body>
397
+ </opml>"#;
398
+
399
+ let result = extractor
400
+ .extract_bytes(opml, "text/x-opml", &ExtractionConfig::default())
401
+ .await
402
+ .expect("Should extract OPML asynchronously");
403
+
404
+ assert_eq!(result.mime_type, "text/x-opml");
405
+ assert!(result.content.contains("Item"));
406
+ assert_eq!(
407
+ result.metadata.additional.get("title").and_then(|v| v.as_str()),
408
+ Some("Async Test")
409
+ );
410
+ }
411
+
412
+ #[test]
413
+ fn test_opml_malformed_missing_closing_tag() {
414
+ let opml = br#"<?xml version="1.0"?>
415
+ <opml version="2.0">
416
+ <head>
417
+ <title>Broken</title>
418
+ </head>
419
+ <body>
420
+ <outline text="Unclosed"
421
+ </body>
422
+ </opml>"#;
423
+
424
+ let result = OpmlExtractor::extract_content_and_metadata(opml);
425
+ assert!(result.is_err(), "Should fail to parse OPML with missing closing tags");
426
+ }
427
+
428
+ #[test]
429
+ fn test_opml_malformed_invalid_nesting() {
430
+ let opml = br#"<?xml version="1.0"?>
431
+ <opml version="2.0">
432
+ <head>
433
+ <title>Invalid Nesting</title>
434
+ <body>
435
+ <outline text="Item" />
436
+ </body>
437
+ </opml>"#;
438
+
439
+ let result = OpmlExtractor::extract_content_and_metadata(opml);
440
+ assert!(result.is_err(), "Should fail to parse OPML with invalid nesting");
441
+ }
442
+
443
+ #[test]
444
+ fn test_opml_empty_outline_elements() {
445
+ let opml = br#"<?xml version="1.0"?>
446
+ <opml version="2.0">
447
+ <head>
448
+ <title>Empty Outlines</title>
449
+ </head>
450
+ <body>
451
+ <outline text="" />
452
+ <outline />
453
+ <outline text="Valid Item">
454
+ <outline text="" />
455
+ <outline text="Another Valid" />
456
+ </outline>
457
+ </body>
458
+ </opml>"#;
459
+
460
+ let (content, metadata) =
461
+ OpmlExtractor::extract_content_and_metadata(opml).expect("Should handle empty outline elements");
462
+
463
+ assert!(content.contains("Valid Item"), "Should extract valid items");
464
+ assert!(content.contains("Another Valid"), "Should extract nested valid items");
465
+ let empty_count = content.matches("\n\n").count();
466
+ assert!(empty_count < 3, "Should skip empty outline elements");
467
+
468
+ assert_eq!(metadata.get("title").and_then(|v| v.as_str()), Some("Empty Outlines"));
469
+ }
470
+
471
+ #[test]
472
+ fn test_opml_deeply_nested_empty_nodes() {
473
+ let opml = br#"<?xml version="1.0"?>
474
+ <opml version="2.0">
475
+ <head>
476
+ <title>Deep Nesting</title>
477
+ </head>
478
+ <body>
479
+ <outline text="Level 1">
480
+ <outline text="">
481
+ <outline text="">
482
+ <outline text="Deep Item">
483
+ <outline text="" />
484
+ </outline>
485
+ </outline>
486
+ </outline>
487
+ <outline text="Level 1 Sibling" />
488
+ </outline>
489
+ </body>
490
+ </opml>"#;
491
+
492
+ let (content, _) =
493
+ OpmlExtractor::extract_content_and_metadata(opml).expect("Should handle deeply nested structures");
494
+
495
+ assert!(content.contains("Level 1"), "Should extract top-level item");
496
+ assert!(content.contains("Deep Item"), "Should extract deeply nested item");
497
+ assert!(content.contains("Level 1 Sibling"), "Should extract sibling items");
498
+ }
499
+
500
+ #[test]
501
+ fn test_opml_outline_with_missing_text_attribute() {
502
+ let opml = br#"<?xml version="1.0"?>
503
+ <opml version="2.0">
504
+ <head>
505
+ <title>Missing Attributes</title>
506
+ </head>
507
+ <body>
508
+ <outline type="folder" />
509
+ <outline text="Valid Item" type="rss" />
510
+ <outline type="rss" xmlUrl="https://example.com/feed" />
511
+ </body>
512
+ </opml>"#;
513
+
514
+ let (content, metadata) = OpmlExtractor::extract_content_and_metadata(opml)
515
+ .expect("Should handle outline with missing text attribute");
516
+
517
+ assert!(content.contains("Valid Item"), "Should extract item with text");
518
+ assert!(!content.contains("https://"), "Should not extract URLs");
519
+
520
+ assert_eq!(
521
+ metadata.get("title").and_then(|v| v.as_str()),
522
+ Some("Missing Attributes")
523
+ );
524
+ }
525
+
526
+ #[test]
527
+ fn test_opml_whitespace_only_text_attribute() {
528
+ let opml = br#"<?xml version="1.0"?>
529
+ <opml version="2.0">
530
+ <head>
531
+ <title>Whitespace Test</title>
532
+ </head>
533
+ <body>
534
+ <outline text=" " />
535
+ <outline text="
536
+ " />
537
+ <outline text="Real Content" />
538
+ </body>
539
+ </opml>"#;
540
+
541
+ let (content, _) =
542
+ OpmlExtractor::extract_content_and_metadata(opml).expect("Should handle whitespace-only text");
543
+
544
+ assert!(
545
+ content.contains("Real Content"),
546
+ "Should extract non-whitespace content"
547
+ );
548
+ let trimmed = content.trim();
549
+ assert!(trimmed.contains("Whitespace Test"), "Should have title");
550
+ assert!(trimmed.contains("Real Content"), "Should have real content");
551
+ }
552
+
553
+ #[test]
554
+ fn test_opml_html_entity_in_nested_structure() {
555
+ let opml = br#"<?xml version="1.0"?>
556
+ <opml version="2.0">
557
+ <head>
558
+ <title>Entities &amp; Nesting</title>
559
+ </head>
560
+ <body>
561
+ <outline text="News &amp; Updates">
562
+ <outline text="Tech &lt; Science" />
563
+ <outline text="Health &gt; Wealth" />
564
+ </outline>
565
+ </body>
566
+ </opml>"#;
567
+
568
+ let (content, metadata) =
569
+ OpmlExtractor::extract_content_and_metadata(opml).expect("Should handle HTML entities");
570
+
571
+ assert!(
572
+ content.contains("News") && content.contains("Updates"),
573
+ "Should decode &amp; entity"
574
+ );
575
+ assert!(content.contains("Tech"), "Should handle &lt; entity");
576
+ assert!(content.contains("Science"), "Should decode entity properly");
577
+
578
+ let title = metadata.get("title").and_then(|v| v.as_str()).unwrap_or("");
579
+ assert!(
580
+ title.contains("&") && title.contains("Nesting"),
581
+ "Title should have decoded entity"
582
+ );
583
+ }
584
+
585
+ #[test]
586
+ fn test_opml_single_outline_no_children() {
587
+ let opml = br#"<?xml version="1.0"?>
588
+ <opml version="2.0">
589
+ <head>
590
+ <title>Single</title>
591
+ </head>
592
+ <body>
593
+ <outline text="Only Item" />
594
+ </body>
595
+ </opml>"#;
596
+
597
+ let (content, metadata) =
598
+ OpmlExtractor::extract_content_and_metadata(opml).expect("Should handle single outline");
599
+
600
+ assert!(content.contains("Only Item"), "Should extract single item");
601
+ assert_eq!(metadata.get("title").and_then(|v| v.as_str()), Some("Single"));
602
+ }
603
+
604
+ #[test]
605
+ fn test_opml_head_without_body() {
606
+ let opml = br#"<?xml version="1.0"?>
607
+ <opml version="2.0">
608
+ <head>
609
+ <title>No Body</title>
610
+ </head>
611
+ </opml>"#;
612
+
613
+ let (content, metadata) =
614
+ OpmlExtractor::extract_content_and_metadata(opml).expect("Should handle OPML without body");
615
+
616
+ assert_eq!(metadata.get("title").and_then(|v| v.as_str()), Some("No Body"));
617
+ assert!(content.is_empty() || content.trim() == "No Body");
618
+ }
619
+
620
+ #[test]
621
+ fn test_opml_body_without_head() {
622
+ let opml = br#"<?xml version="1.0"?>
623
+ <opml version="2.0">
624
+ <body>
625
+ <outline text="Item" />
626
+ </body>
627
+ </opml>"#;
628
+
629
+ let (content, metadata) =
630
+ OpmlExtractor::extract_content_and_metadata(opml).expect("Should handle OPML without head");
631
+
632
+ assert!(content.contains("Item"), "Should extract body content");
633
+ assert!(metadata.is_empty(), "Should have no metadata without head");
634
+ }
635
+ }