omnizip 0.4.7-aarch64-linux

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 (632) hide show
  1. checksums.yaml +7 -0
  2. data/.rspec +3 -0
  3. data/.rubocop.yml +32 -0
  4. data/.rubocop_todo.yml +293 -0
  5. data/CHANGELOG.md +1647 -0
  6. data/CONTEXT.md +68 -0
  7. data/COPYING +502 -0
  8. data/Gemfile +19 -0
  9. data/LICENSE +12 -0
  10. data/README.adoc +1327 -0
  11. data/Rakefile +15 -0
  12. data/TODO.refactor/00-overview.md +67 -0
  13. data/TODO.refactor/01-registry-base-class.md +81 -0
  14. data/TODO.refactor/02-error-hierarchy.md +57 -0
  15. data/TODO.refactor/03-autoload-entry-point.md +69 -0
  16. data/TODO.refactor/04-filter-base-consolidation.md +49 -0
  17. data/TODO.refactor/05-send-private-methods.md +64 -0
  18. data/TODO.refactor/06-instance-variable-access.md +69 -0
  19. data/TODO.refactor/07-respond-to-replacement.md +237 -0
  20. data/TODO.refactor/08-spec-doubles.md +27 -0
  21. data/TODO.refactor/09-cli-shared-module.md +35 -0
  22. data/TODO.refactor/10-format-detector-ocp.md +34 -0
  23. data/TODO.refactor/11-convenience-decoupling.md +38 -0
  24. data/TODO.refactor/12-thread-safety.md +8 -0
  25. data/TODO.refactor/13-lutaml-model-migration.md +158 -0
  26. data/TODO.refactor/14-add-missing-specs.md +25 -0
  27. data/benchmark/README.md +260 -0
  28. data/benchmark/benchmark_suite.rb +125 -0
  29. data/benchmark/compression_bench.rb +181 -0
  30. data/benchmark/filter_bench.rb +180 -0
  31. data/benchmark/models/benchmark_result.rb +59 -0
  32. data/benchmark/models/comparison_result.rb +69 -0
  33. data/benchmark/profile_suite.rb +167 -0
  34. data/benchmark/reporter.rb +150 -0
  35. data/benchmark/run_benchmarks.rb +66 -0
  36. data/benchmark/test_data.rb +137 -0
  37. data/config/formats/rar3_spec.yml +92 -0
  38. data/config/formats/rar5_spec.yml +102 -0
  39. data/docs/.github/workflows/docs.yml +142 -0
  40. data/docs/.gitignore +21 -0
  41. data/docs/.lychee.toml +67 -0
  42. data/docs/Gemfile +13 -0
  43. data/docs/RAR_WRITE_SUPPORT.md +26 -0
  44. data/docs/README.md +101 -0
  45. data/docs/_config.yml +112 -0
  46. data/docs/assets/logo.svg +1 -0
  47. data/docs/assets/omnizip-logo.pdf +1540 -11
  48. data/docs/comparison/feature-matrix.adoc +694 -0
  49. data/docs/comparison/index.adoc +113 -0
  50. data/docs/comparison/vs-7zip.adoc +309 -0
  51. data/docs/comparison/vs-peazip.adoc +77 -0
  52. data/docs/comparison/vs-rubyzip.adoc +342 -0
  53. data/docs/comparison/vs-winrar.adoc +100 -0
  54. data/docs/compatibility.adoc +579 -0
  55. data/docs/concepts/index.adoc +129 -0
  56. data/docs/developer/architecture.adoc +256 -0
  57. data/docs/developer/contributing.adoc +158 -0
  58. data/docs/developer/index.adoc +25 -0
  59. data/docs/developer/testing.adoc +212 -0
  60. data/docs/getting-started/basic-usage.adoc +263 -0
  61. data/docs/getting-started/index.adoc +42 -0
  62. data/docs/getting-started/installation.adoc +138 -0
  63. data/docs/getting-started/quick-start.adoc +183 -0
  64. data/docs/getting-started/your-first-archive.adoc +219 -0
  65. data/docs/guides/advanced-features/encryption.adoc +277 -0
  66. data/docs/guides/advanced-features/index.adoc +59 -0
  67. data/docs/guides/advanced-features/parallel-processing.adoc +144 -0
  68. data/docs/guides/advanced-features/progress-tracking.adoc +124 -0
  69. data/docs/guides/advanced-features/streaming.adoc +142 -0
  70. data/docs/guides/archive-formats/gzip-format.adoc +105 -0
  71. data/docs/guides/archive-formats/index.adoc +160 -0
  72. data/docs/guides/archive-formats/ole-format.adoc +151 -0
  73. data/docs/guides/archive-formats/rar-format.adoc +104 -0
  74. data/docs/guides/archive-formats/rar5.adoc +521 -0
  75. data/docs/guides/archive-formats/rpm-format.adoc +108 -0
  76. data/docs/guides/archive-formats/seven-zip-format.adoc +35 -0
  77. data/docs/guides/archive-formats/tar-format.adoc +106 -0
  78. data/docs/guides/archive-formats/xz-format.adoc +118 -0
  79. data/docs/guides/archive-formats/zip-format.adoc +35 -0
  80. data/docs/guides/compression-algorithms/bzip2.adoc +114 -0
  81. data/docs/guides/compression-algorithms/deflate.adoc +313 -0
  82. data/docs/guides/compression-algorithms/index.adoc +190 -0
  83. data/docs/guides/compression-algorithms/lzma.adoc +394 -0
  84. data/docs/guides/compression-algorithms/lzma2.adoc +244 -0
  85. data/docs/guides/compression-algorithms/ppmd.adoc +313 -0
  86. data/docs/guides/compression-algorithms/zstandard.adoc +296 -0
  87. data/docs/guides/creating-archives.adoc +348 -0
  88. data/docs/guides/extracting-archives.adoc +53 -0
  89. data/docs/guides/format-conversion.adoc +64 -0
  90. data/docs/guides/index.adoc +49 -0
  91. data/docs/guides/migration-rubyzip.adoc +217 -0
  92. data/docs/guides/parity-archives.adoc +605 -0
  93. data/docs/guides/performance-tuning.adoc +88 -0
  94. data/docs/index.adoc +228 -0
  95. data/docs/lychee.toml +67 -0
  96. data/docs/reference/api/overview.adoc +187 -0
  97. data/docs/reference/cli/compress-command.adoc +114 -0
  98. data/docs/reference/cli/overview.adoc +140 -0
  99. data/docs/reference/index.adoc +26 -0
  100. data/docs/resources/faq.adoc +185 -0
  101. data/docs/resources/quick-reference.adoc +222 -0
  102. data/docs/rust-backend.md +0 -0
  103. data/docs/troubleshooting/index.adoc +207 -0
  104. data/docs/xar_format.md +216 -0
  105. data/examples/api_comparison.rb +205 -0
  106. data/examples/deflate64_example.rb +96 -0
  107. data/examples/par2_demo.rb +121 -0
  108. data/examples/quick_start_native.rb +150 -0
  109. data/examples/quick_start_rubyzip.rb +115 -0
  110. data/examples/rubyzip_compatibility_demo.rb +194 -0
  111. data/exe/omnizip +27 -0
  112. data/lib/omnizip/algorithm.rb +176 -0
  113. data/lib/omnizip/algorithm_registry.rb +65 -0
  114. data/lib/omnizip/algorithms/.keep +0 -0
  115. data/lib/omnizip/algorithms/bzip2/bwt.rb +236 -0
  116. data/lib/omnizip/algorithms/bzip2/bz2.rb +687 -0
  117. data/lib/omnizip/algorithms/bzip2/rle.rb +146 -0
  118. data/lib/omnizip/algorithms/bzip2.rb +108 -0
  119. data/lib/omnizip/algorithms/deflate/constants.rb +28 -0
  120. data/lib/omnizip/algorithms/deflate/decoder.rb +37 -0
  121. data/lib/omnizip/algorithms/deflate/encoder.rb +45 -0
  122. data/lib/omnizip/algorithms/deflate.rb +135 -0
  123. data/lib/omnizip/algorithms/deflate64/constants.rb +45 -0
  124. data/lib/omnizip/algorithms/deflate64/decoder.rb +151 -0
  125. data/lib/omnizip/algorithms/deflate64/encoder.rb +95 -0
  126. data/lib/omnizip/algorithms/deflate64/huffman_coder.rb +352 -0
  127. data/lib/omnizip/algorithms/deflate64/lz77_encoder.rb +140 -0
  128. data/lib/omnizip/algorithms/deflate64.rb +118 -0
  129. data/lib/omnizip/algorithms/lzma/bit_model.rb +120 -0
  130. data/lib/omnizip/algorithms/lzma/constants.rb +112 -0
  131. data/lib/omnizip/algorithms/lzma/decoder.rb +146 -0
  132. data/lib/omnizip/algorithms/lzma/dictionary.rb +70 -0
  133. data/lib/omnizip/algorithms/lzma/distance_coder.rb +326 -0
  134. data/lib/omnizip/algorithms/lzma/encoder.rb +139 -0
  135. data/lib/omnizip/algorithms/lzma/length_coder.rb +172 -0
  136. data/lib/omnizip/algorithms/lzma/literal_decoder.rb +204 -0
  137. data/lib/omnizip/algorithms/lzma/literal_encoder.rb +208 -0
  138. data/lib/omnizip/algorithms/lzma/lzip_decoder.rb +368 -0
  139. data/lib/omnizip/algorithms/lzma/lzma1_encoder.rb +105 -0
  140. data/lib/omnizip/algorithms/lzma/lzma_alone_decoder.rb +194 -0
  141. data/lib/omnizip/algorithms/lzma/lzma_state.rb +128 -0
  142. data/lib/omnizip/algorithms/lzma/match.rb +32 -0
  143. data/lib/omnizip/algorithms/lzma/match_finder.rb +233 -0
  144. data/lib/omnizip/algorithms/lzma/match_finder_config.rb +142 -0
  145. data/lib/omnizip/algorithms/lzma/match_finder_factory.rb +84 -0
  146. data/lib/omnizip/algorithms/lzma/optimal_encoder.rb +159 -0
  147. data/lib/omnizip/algorithms/lzma/probability_models.rb +72 -0
  148. data/lib/omnizip/algorithms/lzma/range_coder.rb +82 -0
  149. data/lib/omnizip/algorithms/lzma/range_decoder.rb +274 -0
  150. data/lib/omnizip/algorithms/lzma/range_encoder.rb +202 -0
  151. data/lib/omnizip/algorithms/lzma/state.rb +127 -0
  152. data/lib/omnizip/algorithms/lzma/xz_buffered_range_encoder.rb +323 -0
  153. data/lib/omnizip/algorithms/lzma/xz_encoder.rb +420 -0
  154. data/lib/omnizip/algorithms/lzma/xz_encoder_fast.rb +640 -0
  155. data/lib/omnizip/algorithms/lzma/xz_match_finder_adapter.rb +224 -0
  156. data/lib/omnizip/algorithms/lzma/xz_price_calculator.rb +167 -0
  157. data/lib/omnizip/algorithms/lzma/xz_probability_models.rb +258 -0
  158. data/lib/omnizip/algorithms/lzma/xz_range_encoder.rb +223 -0
  159. data/lib/omnizip/algorithms/lzma/xz_range_encoder_exact.rb +314 -0
  160. data/lib/omnizip/algorithms/lzma/xz_state.rb +108 -0
  161. data/lib/omnizip/algorithms/lzma/xz_utils_decoder.rb +1311 -0
  162. data/lib/omnizip/algorithms/lzma.rb +266 -0
  163. data/lib/omnizip/algorithms/lzma2/chunk_manager.rb +180 -0
  164. data/lib/omnizip/algorithms/lzma2/constants.rb +38 -0
  165. data/lib/omnizip/algorithms/lzma2/encoder.rb +145 -0
  166. data/lib/omnizip/algorithms/lzma2/lzma2_chunk.rb +165 -0
  167. data/lib/omnizip/algorithms/lzma2/properties.rb +179 -0
  168. data/lib/omnizip/algorithms/lzma2/simple_lzma2_encoder.rb +122 -0
  169. data/lib/omnizip/algorithms/lzma2/xz_encoder_adapter.rb +85 -0
  170. data/lib/omnizip/algorithms/lzma2.rb +133 -0
  171. data/lib/omnizip/algorithms/ppmd7/constants.rb +74 -0
  172. data/lib/omnizip/algorithms/ppmd7/context.rb +151 -0
  173. data/lib/omnizip/algorithms/ppmd7/decoder.rb +127 -0
  174. data/lib/omnizip/algorithms/ppmd7/encoder.rb +153 -0
  175. data/lib/omnizip/algorithms/ppmd7/model.rb +245 -0
  176. data/lib/omnizip/algorithms/ppmd7/symbol_state.rb +57 -0
  177. data/lib/omnizip/algorithms/ppmd7.rb +146 -0
  178. data/lib/omnizip/algorithms/ppmd8/constants.rb +61 -0
  179. data/lib/omnizip/algorithms/ppmd8/context.rb +32 -0
  180. data/lib/omnizip/algorithms/ppmd8/decoder.rb +104 -0
  181. data/lib/omnizip/algorithms/ppmd8/encoder.rb +135 -0
  182. data/lib/omnizip/algorithms/ppmd8/model.rb +246 -0
  183. data/lib/omnizip/algorithms/ppmd8/restoration_method.rb +78 -0
  184. data/lib/omnizip/algorithms/ppmd8.rb +122 -0
  185. data/lib/omnizip/algorithms/ppmd_base.rb +142 -0
  186. data/lib/omnizip/algorithms/registration.rb +28 -0
  187. data/lib/omnizip/algorithms/zstandard/constants.rb +158 -0
  188. data/lib/omnizip/algorithms/zstandard/decoder.rb +249 -0
  189. data/lib/omnizip/algorithms/zstandard/dictionary.rb +73 -0
  190. data/lib/omnizip/algorithms/zstandard/encoder.rb +294 -0
  191. data/lib/omnizip/algorithms/zstandard/frame/block.rb +143 -0
  192. data/lib/omnizip/algorithms/zstandard/frame/header.rb +233 -0
  193. data/lib/omnizip/algorithms/zstandard/frame.rb +33 -0
  194. data/lib/omnizip/algorithms/zstandard/fse/bitstream.rb +183 -0
  195. data/lib/omnizip/algorithms/zstandard/fse/encoder.rb +534 -0
  196. data/lib/omnizip/algorithms/zstandard/fse/interleaved.rb +92 -0
  197. data/lib/omnizip/algorithms/zstandard/fse/table.rb +188 -0
  198. data/lib/omnizip/algorithms/zstandard/fse/table_description.rb +203 -0
  199. data/lib/omnizip/algorithms/zstandard/fse.rb +53 -0
  200. data/lib/omnizip/algorithms/zstandard/huffman.rb +276 -0
  201. data/lib/omnizip/algorithms/zstandard/huffman_encoder.rb +327 -0
  202. data/lib/omnizip/algorithms/zstandard/ldm.rb +121 -0
  203. data/lib/omnizip/algorithms/zstandard/literals.rb +241 -0
  204. data/lib/omnizip/algorithms/zstandard/literals_encoder.rb +96 -0
  205. data/lib/omnizip/algorithms/zstandard/match_finder.rb +483 -0
  206. data/lib/omnizip/algorithms/zstandard/sequences.rb +350 -0
  207. data/lib/omnizip/algorithms/zstandard/sequences_encoder.rb +333 -0
  208. data/lib/omnizip/algorithms/zstandard/xxhash.rb +159 -0
  209. data/lib/omnizip/algorithms/zstandard.rb +210 -0
  210. data/lib/omnizip/algorithms.rb +35 -0
  211. data/lib/omnizip/archive/builder.rb +48 -0
  212. data/lib/omnizip/archive/reader_session.rb +67 -0
  213. data/lib/omnizip/archive.rb +86 -0
  214. data/lib/omnizip/archive_handler.rb +82 -0
  215. data/lib/omnizip/archive_handlers/cpio_handler.rb +47 -0
  216. data/lib/omnizip/archive_handlers/iso_handler.rb +54 -0
  217. data/lib/omnizip/archive_handlers/ole_handler.rb +37 -0
  218. data/lib/omnizip/archive_handlers/rar_handler.rb +96 -0
  219. data/lib/omnizip/archive_handlers/rpm_handler.rb +45 -0
  220. data/lib/omnizip/archive_handlers/seven_zip_handler.rb +89 -0
  221. data/lib/omnizip/archive_handlers/tar_handler.rb +75 -0
  222. data/lib/omnizip/archive_handlers/xar_handler.rb +49 -0
  223. data/lib/omnizip/archive_handlers/zip_handler.rb +115 -0
  224. data/lib/omnizip/archive_handlers.rb +18 -0
  225. data/lib/omnizip/backends.rb +160 -0
  226. data/lib/omnizip/buffer/memory_archive.rb +246 -0
  227. data/lib/omnizip/buffer/memory_extractor.rb +234 -0
  228. data/lib/omnizip/buffer/seven_zip_bridge.rb +171 -0
  229. data/lib/omnizip/buffer.rb +187 -0
  230. data/lib/omnizip/checksum_registry.rb +41 -0
  231. data/lib/omnizip/checksums/crc32.rb +101 -0
  232. data/lib/omnizip/checksums/crc64.rb +102 -0
  233. data/lib/omnizip/checksums/crc_base.rb +158 -0
  234. data/lib/omnizip/checksums/registration.rb +16 -0
  235. data/lib/omnizip/checksums/verifier.rb +130 -0
  236. data/lib/omnizip/checksums.rb +11 -0
  237. data/lib/omnizip/chunked/memory_manager.rb +194 -0
  238. data/lib/omnizip/chunked/reader.rb +78 -0
  239. data/lib/omnizip/chunked/writer.rb +123 -0
  240. data/lib/omnizip/chunked.rb +123 -0
  241. data/lib/omnizip/cli/output_formatter.rb +112 -0
  242. data/lib/omnizip/cli.rb +604 -0
  243. data/lib/omnizip/commands/.keep +0 -0
  244. data/lib/omnizip/commands/archive_create_command.rb +245 -0
  245. data/lib/omnizip/commands/archive_extract_command.rb +231 -0
  246. data/lib/omnizip/commands/archive_list_command.rb +204 -0
  247. data/lib/omnizip/commands/archive_repair_command.rb +129 -0
  248. data/lib/omnizip/commands/archive_verify_command.rb +115 -0
  249. data/lib/omnizip/commands/compress_command.rb +115 -0
  250. data/lib/omnizip/commands/decompress_command.rb +149 -0
  251. data/lib/omnizip/commands/list_command.rb +51 -0
  252. data/lib/omnizip/commands/metadata_command.rb +215 -0
  253. data/lib/omnizip/commands/parity_create_command.rb +114 -0
  254. data/lib/omnizip/commands/parity_repair_command.rb +120 -0
  255. data/lib/omnizip/commands/parity_verify_command.rb +122 -0
  256. data/lib/omnizip/commands/profile_list_command.rb +54 -0
  257. data/lib/omnizip/commands/profile_show_command.rb +44 -0
  258. data/lib/omnizip/commands.rb +21 -0
  259. data/lib/omnizip/convenience.rb +389 -0
  260. data/lib/omnizip/converter/conversion_registry.rb +50 -0
  261. data/lib/omnizip/converter/conversion_strategy.rb +108 -0
  262. data/lib/omnizip/converter/extract_repack_strategy.rb +51 -0
  263. data/lib/omnizip/converter/seven_zip_to_zip_strategy.rb +43 -0
  264. data/lib/omnizip/converter/zip_to_seven_zip_strategy.rb +54 -0
  265. data/lib/omnizip/converter.rb +124 -0
  266. data/lib/omnizip/crypto/aes256/cipher.rb +104 -0
  267. data/lib/omnizip/crypto/aes256/constants.rb +28 -0
  268. data/lib/omnizip/crypto/aes256/key_derivation.rb +100 -0
  269. data/lib/omnizip/crypto/aes256.rb +102 -0
  270. data/lib/omnizip/crypto.rb +11 -0
  271. data/lib/omnizip/entry.rb +44 -0
  272. data/lib/omnizip/error.rb +110 -0
  273. data/lib/omnizip/eta/exponential_smoothing_estimator.rb +95 -0
  274. data/lib/omnizip/eta/moving_average_estimator.rb +96 -0
  275. data/lib/omnizip/eta/rate_calculator.rb +104 -0
  276. data/lib/omnizip/eta/sample_history.rb +143 -0
  277. data/lib/omnizip/eta/time_estimator.rb +106 -0
  278. data/lib/omnizip/eta.rb +68 -0
  279. data/lib/omnizip/extraction/filter_chain.rb +179 -0
  280. data/lib/omnizip/extraction/glob_pattern.rb +140 -0
  281. data/lib/omnizip/extraction/pattern_matcher.rb +66 -0
  282. data/lib/omnizip/extraction/predicate_pattern.rb +52 -0
  283. data/lib/omnizip/extraction/regex_pattern.rb +50 -0
  284. data/lib/omnizip/extraction/selective_extractor.rb +247 -0
  285. data/lib/omnizip/extraction.rb +115 -0
  286. data/lib/omnizip/file_type/mime_classifier.rb +144 -0
  287. data/lib/omnizip/file_type.rb +117 -0
  288. data/lib/omnizip/filter.rb +141 -0
  289. data/lib/omnizip/filter_pipeline.rb +108 -0
  290. data/lib/omnizip/filter_registry.rb +113 -0
  291. data/lib/omnizip/filters/bcj.rb +277 -0
  292. data/lib/omnizip/filters/bcj2/constants.rb +53 -0
  293. data/lib/omnizip/filters/bcj2/decoder.rb +263 -0
  294. data/lib/omnizip/filters/bcj2/encoder.rb +58 -0
  295. data/lib/omnizip/filters/bcj2/stream_data.rb +91 -0
  296. data/lib/omnizip/filters/bcj2.rb +93 -0
  297. data/lib/omnizip/filters/bcj_arm.rb +174 -0
  298. data/lib/omnizip/filters/bcj_arm64.rb +242 -0
  299. data/lib/omnizip/filters/bcj_ia64.rb +194 -0
  300. data/lib/omnizip/filters/bcj_ppc.rb +188 -0
  301. data/lib/omnizip/filters/bcj_sparc.rb +174 -0
  302. data/lib/omnizip/filters/bcj_x86.rb +191 -0
  303. data/lib/omnizip/filters/delta.rb +195 -0
  304. data/lib/omnizip/filters/xz_delta.rb +258 -0
  305. data/lib/omnizip/filters.rb +20 -0
  306. data/lib/omnizip/format_detector.rb +166 -0
  307. data/lib/omnizip/formats/.keep +0 -0
  308. data/lib/omnizip/formats/bzip2_file.rb +159 -0
  309. data/lib/omnizip/formats/cpio/bounded_io.rb +66 -0
  310. data/lib/omnizip/formats/cpio/constants.rb +55 -0
  311. data/lib/omnizip/formats/cpio/entry.rb +389 -0
  312. data/lib/omnizip/formats/cpio/reader.rb +194 -0
  313. data/lib/omnizip/formats/cpio/writer.rb +232 -0
  314. data/lib/omnizip/formats/cpio.rb +132 -0
  315. data/lib/omnizip/formats/format_spec_loader.rb +228 -0
  316. data/lib/omnizip/formats/gzip.rb +236 -0
  317. data/lib/omnizip/formats/iso/directory_builder.rb +321 -0
  318. data/lib/omnizip/formats/iso/directory_record.rb +162 -0
  319. data/lib/omnizip/formats/iso/joliet.rb +204 -0
  320. data/lib/omnizip/formats/iso/path_table.rb +125 -0
  321. data/lib/omnizip/formats/iso/reader.rb +194 -0
  322. data/lib/omnizip/formats/iso/rock_ridge.rb +349 -0
  323. data/lib/omnizip/formats/iso/volume_builder.rb +319 -0
  324. data/lib/omnizip/formats/iso/volume_descriptor.rb +168 -0
  325. data/lib/omnizip/formats/iso/writer.rb +543 -0
  326. data/lib/omnizip/formats/iso.rb +133 -0
  327. data/lib/omnizip/formats/lzip.rb +161 -0
  328. data/lib/omnizip/formats/lzma_alone.rb +149 -0
  329. data/lib/omnizip/formats/msi/cab_extractor.rb +181 -0
  330. data/lib/omnizip/formats/msi/constants.rb +157 -0
  331. data/lib/omnizip/formats/msi/directory_resolver.rb +188 -0
  332. data/lib/omnizip/formats/msi/entry.rb +134 -0
  333. data/lib/omnizip/formats/msi/reader.rb +301 -0
  334. data/lib/omnizip/formats/msi/string_pool.rb +246 -0
  335. data/lib/omnizip/formats/msi/table_parser.rb +244 -0
  336. data/lib/omnizip/formats/msi.rb +73 -0
  337. data/lib/omnizip/formats/ole/allocation_table.rb +263 -0
  338. data/lib/omnizip/formats/ole/constants.rb +61 -0
  339. data/lib/omnizip/formats/ole/dirent.rb +439 -0
  340. data/lib/omnizip/formats/ole/header.rb +199 -0
  341. data/lib/omnizip/formats/ole/ranges_io.rb +347 -0
  342. data/lib/omnizip/formats/ole/storage.rb +482 -0
  343. data/lib/omnizip/formats/ole/types/variant.rb +338 -0
  344. data/lib/omnizip/formats/ole.rb +143 -0
  345. data/lib/omnizip/formats/rar/archive_repairer.rb +240 -0
  346. data/lib/omnizip/formats/rar/archive_verifier.rb +192 -0
  347. data/lib/omnizip/formats/rar/block_parser.rb +282 -0
  348. data/lib/omnizip/formats/rar/compression/bit_stream.rb +180 -0
  349. data/lib/omnizip/formats/rar/compression/dispatcher.rb +210 -0
  350. data/lib/omnizip/formats/rar/compression/lz77_huffman/decoder.rb +212 -0
  351. data/lib/omnizip/formats/rar/compression/lz77_huffman/encoder.rb +154 -0
  352. data/lib/omnizip/formats/rar/compression/lz77_huffman/huffman_builder.rb +217 -0
  353. data/lib/omnizip/formats/rar/compression/lz77_huffman/huffman_coder.rb +189 -0
  354. data/lib/omnizip/formats/rar/compression/lz77_huffman/match_finder.rb +135 -0
  355. data/lib/omnizip/formats/rar/compression/lz77_huffman/sliding_window.rb +165 -0
  356. data/lib/omnizip/formats/rar/compression/lz77_huffman.rb +25 -0
  357. data/lib/omnizip/formats/rar/compression/ppmd/context.rb +103 -0
  358. data/lib/omnizip/formats/rar/compression/ppmd/decoder.rb +238 -0
  359. data/lib/omnizip/formats/rar/compression/ppmd/encoder.rb +250 -0
  360. data/lib/omnizip/formats/rar/compression/ppmd.rb +16 -0
  361. data/lib/omnizip/formats/rar/compression.rb +17 -0
  362. data/lib/omnizip/formats/rar/compression_method_registry.rb +106 -0
  363. data/lib/omnizip/formats/rar/constants.rb +88 -0
  364. data/lib/omnizip/formats/rar/decompressor.rb +316 -0
  365. data/lib/omnizip/formats/rar/external_writer.rb +311 -0
  366. data/lib/omnizip/formats/rar/header.rb +209 -0
  367. data/lib/omnizip/formats/rar/license_validator.rb +111 -0
  368. data/lib/omnizip/formats/rar/models/rar_archive.rb +77 -0
  369. data/lib/omnizip/formats/rar/models/rar_entry.rb +65 -0
  370. data/lib/omnizip/formats/rar/models/rar_volume.rb +56 -0
  371. data/lib/omnizip/formats/rar/models.rb +14 -0
  372. data/lib/omnizip/formats/rar/parity_handler.rb +299 -0
  373. data/lib/omnizip/formats/rar/rar5/compression/lzma.rb +200 -0
  374. data/lib/omnizip/formats/rar/rar5/compression/lzss.rb +584 -0
  375. data/lib/omnizip/formats/rar/rar5/compression/store.rb +60 -0
  376. data/lib/omnizip/formats/rar/rar5/crc32.rb +39 -0
  377. data/lib/omnizip/formats/rar/rar5/encryption/aes256_cbc.rb +96 -0
  378. data/lib/omnizip/formats/rar/rar5/encryption/encryption_header.rb +114 -0
  379. data/lib/omnizip/formats/rar/rar5/encryption/encryption_manager.rb +162 -0
  380. data/lib/omnizip/formats/rar/rar5/encryption/key_derivation.rb +97 -0
  381. data/lib/omnizip/formats/rar/rar5/header.rb +208 -0
  382. data/lib/omnizip/formats/rar/rar5/models/encryption_options.rb +74 -0
  383. data/lib/omnizip/formats/rar/rar5/models/recovery_options.rb +63 -0
  384. data/lib/omnizip/formats/rar/rar5/models/solid_options.rb +63 -0
  385. data/lib/omnizip/formats/rar/rar5/models/volume_options.rb +74 -0
  386. data/lib/omnizip/formats/rar/rar5/multi_volume/ARCHITECTURE.md +290 -0
  387. data/lib/omnizip/formats/rar/rar5/multi_volume/volume_manager.rb +260 -0
  388. data/lib/omnizip/formats/rar/rar5/multi_volume/volume_splitter.rb +155 -0
  389. data/lib/omnizip/formats/rar/rar5/multi_volume/volume_writer.rb +176 -0
  390. data/lib/omnizip/formats/rar/rar5/solid/solid_encoder.rb +108 -0
  391. data/lib/omnizip/formats/rar/rar5/solid/solid_manager.rb +139 -0
  392. data/lib/omnizip/formats/rar/rar5/solid/solid_stream.rb +121 -0
  393. data/lib/omnizip/formats/rar/rar5/vint.rb +53 -0
  394. data/lib/omnizip/formats/rar/rar5/writer.rb +540 -0
  395. data/lib/omnizip/formats/rar/rar_format_base.rb +239 -0
  396. data/lib/omnizip/formats/rar/reader.rb +377 -0
  397. data/lib/omnizip/formats/rar/recovery_record.rb +245 -0
  398. data/lib/omnizip/formats/rar/volume_manager.rb +166 -0
  399. data/lib/omnizip/formats/rar/writer.rb +437 -0
  400. data/lib/omnizip/formats/rar.rb +193 -0
  401. data/lib/omnizip/formats/rar3/compressor.rb +71 -0
  402. data/lib/omnizip/formats/rar3/decompressor.rb +64 -0
  403. data/lib/omnizip/formats/rar3/reader.rb +107 -0
  404. data/lib/omnizip/formats/rar3/writer.rb +220 -0
  405. data/lib/omnizip/formats/rar3.rb +15 -0
  406. data/lib/omnizip/formats/rar5/compressor.rb +71 -0
  407. data/lib/omnizip/formats/rar5/decompressor.rb +64 -0
  408. data/lib/omnizip/formats/rar5/reader.rb +130 -0
  409. data/lib/omnizip/formats/rar5/writer.rb +65 -0
  410. data/lib/omnizip/formats/rar5.rb +15 -0
  411. data/lib/omnizip/formats/rpm/constants.rb +58 -0
  412. data/lib/omnizip/formats/rpm/entry.rb +106 -0
  413. data/lib/omnizip/formats/rpm/header.rb +106 -0
  414. data/lib/omnizip/formats/rpm/lead.rb +132 -0
  415. data/lib/omnizip/formats/rpm/tag.rb +228 -0
  416. data/lib/omnizip/formats/rpm/writer.rb +652 -0
  417. data/lib/omnizip/formats/rpm.rb +458 -0
  418. data/lib/omnizip/formats/seven_zip/bcj2_stream_decompressor.rb +274 -0
  419. data/lib/omnizip/formats/seven_zip/coder_chain.rb +169 -0
  420. data/lib/omnizip/formats/seven_zip/constants.rb +126 -0
  421. data/lib/omnizip/formats/seven_zip/encoded_header.rb +110 -0
  422. data/lib/omnizip/formats/seven_zip/encrypted_header.rb +139 -0
  423. data/lib/omnizip/formats/seven_zip/file_collector.rb +143 -0
  424. data/lib/omnizip/formats/seven_zip/header.rb +102 -0
  425. data/lib/omnizip/formats/seven_zip/header_encryptor.rb +132 -0
  426. data/lib/omnizip/formats/seven_zip/header_writer.rb +425 -0
  427. data/lib/omnizip/formats/seven_zip/models/coder_info.rb +30 -0
  428. data/lib/omnizip/formats/seven_zip/models/file_entry.rb +65 -0
  429. data/lib/omnizip/formats/seven_zip/models/folder.rb +67 -0
  430. data/lib/omnizip/formats/seven_zip/models/stream_info.rb +42 -0
  431. data/lib/omnizip/formats/seven_zip/models.rb +20 -0
  432. data/lib/omnizip/formats/seven_zip/parser.rb +671 -0
  433. data/lib/omnizip/formats/seven_zip/reader.rb +626 -0
  434. data/lib/omnizip/formats/seven_zip/split_archive_reader.rb +611 -0
  435. data/lib/omnizip/formats/seven_zip/split_archive_writer.rb +308 -0
  436. data/lib/omnizip/formats/seven_zip/stream_compressor.rb +151 -0
  437. data/lib/omnizip/formats/seven_zip/stream_decompressor.rb +166 -0
  438. data/lib/omnizip/formats/seven_zip/writer.rb +801 -0
  439. data/lib/omnizip/formats/seven_zip.rb +179 -0
  440. data/lib/omnizip/formats/tar/constants.rb +73 -0
  441. data/lib/omnizip/formats/tar/entry.rb +98 -0
  442. data/lib/omnizip/formats/tar/header.rb +206 -0
  443. data/lib/omnizip/formats/tar/reader.rb +119 -0
  444. data/lib/omnizip/formats/tar/writer.rb +212 -0
  445. data/lib/omnizip/formats/tar.rb +74 -0
  446. data/lib/omnizip/formats/xar/constants.rb +119 -0
  447. data/lib/omnizip/formats/xar/entry.rb +268 -0
  448. data/lib/omnizip/formats/xar/header.rb +223 -0
  449. data/lib/omnizip/formats/xar/reader.rb +400 -0
  450. data/lib/omnizip/formats/xar/toc.rb +570 -0
  451. data/lib/omnizip/formats/xar/writer.rb +461 -0
  452. data/lib/omnizip/formats/xar.rb +145 -0
  453. data/lib/omnizip/formats/xz/reader.rb +121 -0
  454. data/lib/omnizip/formats/xz/writer.rb +416 -0
  455. data/lib/omnizip/formats/xz.rb +210 -0
  456. data/lib/omnizip/formats/xz_const.rb +49 -0
  457. data/lib/omnizip/formats/xz_impl/block_decoder.rb +761 -0
  458. data/lib/omnizip/formats/xz_impl/block_encoder.rb +304 -0
  459. data/lib/omnizip/formats/xz_impl/block_header.rb +210 -0
  460. data/lib/omnizip/formats/xz_impl/block_header_parser.rb +182 -0
  461. data/lib/omnizip/formats/xz_impl/index_decoder.rb +174 -0
  462. data/lib/omnizip/formats/xz_impl/index_encoder.rb +120 -0
  463. data/lib/omnizip/formats/xz_impl/stream_decoder.rb +470 -0
  464. data/lib/omnizip/formats/xz_impl/stream_encoder.rb +95 -0
  465. data/lib/omnizip/formats/xz_impl/stream_footer.rb +79 -0
  466. data/lib/omnizip/formats/xz_impl/stream_footer_parser.rb +115 -0
  467. data/lib/omnizip/formats/xz_impl/stream_header.rb +53 -0
  468. data/lib/omnizip/formats/xz_impl/stream_header_parser.rb +106 -0
  469. data/lib/omnizip/formats/xz_impl/vli.rb +128 -0
  470. data/lib/omnizip/formats/xz_impl.rb +52 -0
  471. data/lib/omnizip/formats/zip/central_directory_header.rb +223 -0
  472. data/lib/omnizip/formats/zip/constants.rb +69 -0
  473. data/lib/omnizip/formats/zip/end_of_central_directory.rb +132 -0
  474. data/lib/omnizip/formats/zip/local_file_header.rb +136 -0
  475. data/lib/omnizip/formats/zip/reader.rb +376 -0
  476. data/lib/omnizip/formats/zip/unix_extra_field.rb +153 -0
  477. data/lib/omnizip/formats/zip/writer.rb +489 -0
  478. data/lib/omnizip/formats/zip/zip64_end_of_central_directory.rb +102 -0
  479. data/lib/omnizip/formats/zip/zip64_end_of_central_directory_locator.rb +64 -0
  480. data/lib/omnizip/formats/zip/zip64_extra_field.rb +112 -0
  481. data/lib/omnizip/formats/zip.rb +50 -0
  482. data/lib/omnizip/formats.rb +29 -0
  483. data/lib/omnizip/implementations/base/lzma2_decoder_base.rb +75 -0
  484. data/lib/omnizip/implementations/base/lzma2_encoder_base.rb +128 -0
  485. data/lib/omnizip/implementations/base/lzma_decoder_base.rb +83 -0
  486. data/lib/omnizip/implementations/base/lzma_encoder_base.rb +108 -0
  487. data/lib/omnizip/implementations/base/state_machine_base.rb +182 -0
  488. data/lib/omnizip/implementations/base.rb +19 -0
  489. data/lib/omnizip/implementations/rust/archive.rb +93 -0
  490. data/lib/omnizip/implementations/rust/library.rb +221 -0
  491. data/lib/omnizip/implementations/rust.rb +26 -0
  492. data/lib/omnizip/implementations/seven_zip/lzma/decoder.rb +428 -0
  493. data/lib/omnizip/implementations/seven_zip/lzma/encoder.rb +456 -0
  494. data/lib/omnizip/implementations/seven_zip/lzma/match_finder.rb +285 -0
  495. data/lib/omnizip/implementations/seven_zip/lzma/range_decoder.rb +197 -0
  496. data/lib/omnizip/implementations/seven_zip/lzma/range_encoder.rb +194 -0
  497. data/lib/omnizip/implementations/seven_zip/lzma/state_machine.rb +139 -0
  498. data/lib/omnizip/implementations/seven_zip/lzma.rb +21 -0
  499. data/lib/omnizip/implementations/seven_zip/lzma2/encoder.rb +56 -0
  500. data/lib/omnizip/implementations/seven_zip/lzma2.rb +12 -0
  501. data/lib/omnizip/implementations/seven_zip.rb +11 -0
  502. data/lib/omnizip/implementations/xz_utils/lzma2/decoder.rb +547 -0
  503. data/lib/omnizip/implementations/xz_utils/lzma2/encoder.rb +748 -0
  504. data/lib/omnizip/implementations/xz_utils/lzma2.rb +13 -0
  505. data/lib/omnizip/implementations/xz_utils.rb +10 -0
  506. data/lib/omnizip/implementations.rb +25 -0
  507. data/lib/omnizip/io/buffered_input.rb +147 -0
  508. data/lib/omnizip/io/buffered_output.rb +106 -0
  509. data/lib/omnizip/io/source.rb +143 -0
  510. data/lib/omnizip/io/stream_manager.rb +117 -0
  511. data/lib/omnizip/io.rb +15 -0
  512. data/lib/omnizip/link_handler/hard_link.rb +79 -0
  513. data/lib/omnizip/link_handler/symbolic_link.rb +74 -0
  514. data/lib/omnizip/link_handler.rb +129 -0
  515. data/lib/omnizip/metadata/archive_metadata.rb +114 -0
  516. data/lib/omnizip/metadata/entry_metadata.rb +153 -0
  517. data/lib/omnizip/metadata/metadata_editor.rb +169 -0
  518. data/lib/omnizip/metadata/metadata_registry.rb +71 -0
  519. data/lib/omnizip/metadata/metadata_validator.rb +101 -0
  520. data/lib/omnizip/metadata.rb +58 -0
  521. data/lib/omnizip/models/.keep +0 -0
  522. data/lib/omnizip/models/algorithm_metadata.rb +41 -0
  523. data/lib/omnizip/models/attribute_apply.rb +40 -0
  524. data/lib/omnizip/models/compression_options.rb +53 -0
  525. data/lib/omnizip/models/conversion_options.rb +79 -0
  526. data/lib/omnizip/models/conversion_result.rb +141 -0
  527. data/lib/omnizip/models/eta_result.rb +45 -0
  528. data/lib/omnizip/models/extraction_rule.rb +115 -0
  529. data/lib/omnizip/models/filter_chain.rb +142 -0
  530. data/lib/omnizip/models/filter_config.rb +148 -0
  531. data/lib/omnizip/models/match_result.rb +141 -0
  532. data/lib/omnizip/models/optimization_suggestion.rb +95 -0
  533. data/lib/omnizip/models/parallel_options.rb +116 -0
  534. data/lib/omnizip/models/performance_result.rb +85 -0
  535. data/lib/omnizip/models/profile_report.rb +116 -0
  536. data/lib/omnizip/models/progress_options.rb +39 -0
  537. data/lib/omnizip/models/split_options.rb +116 -0
  538. data/lib/omnizip/optimization_registry.rb +45 -0
  539. data/lib/omnizip/parallel/engine.rb +52 -0
  540. data/lib/omnizip/parallel/job_queue.rb +209 -0
  541. data/lib/omnizip/parallel/job_scheduler.rb +225 -0
  542. data/lib/omnizip/parallel/parallel_compressor.rb +326 -0
  543. data/lib/omnizip/parallel/parallel_extractor.rb +238 -0
  544. data/lib/omnizip/parallel/thread_pool.rb +60 -0
  545. data/lib/omnizip/parallel/worker_pool.rb +227 -0
  546. data/lib/omnizip/parallel.rb +156 -0
  547. data/lib/omnizip/parity/chunked_block_processor.rb +194 -0
  548. data/lib/omnizip/parity/galois16.rb +145 -0
  549. data/lib/omnizip/parity/models/creator_packet.rb +71 -0
  550. data/lib/omnizip/parity/models/file_description_packet.rb +131 -0
  551. data/lib/omnizip/parity/models/ifsc_packet.rb +111 -0
  552. data/lib/omnizip/parity/models/main_packet.rb +126 -0
  553. data/lib/omnizip/parity/models/packet.rb +156 -0
  554. data/lib/omnizip/parity/models/packet_registry.rb +102 -0
  555. data/lib/omnizip/parity/models/recovery_slice_packet.rb +76 -0
  556. data/lib/omnizip/parity/models.rb +27 -0
  557. data/lib/omnizip/parity/par2_creator.rb +496 -0
  558. data/lib/omnizip/parity/par2_repairer.rb +409 -0
  559. data/lib/omnizip/parity/par2_verifier.rb +373 -0
  560. data/lib/omnizip/parity/par2cmdline_algorithm.rb +108 -0
  561. data/lib/omnizip/parity/par2cmdline_coefficients.rb +78 -0
  562. data/lib/omnizip/parity/reed_solomon_decoder.rb +263 -0
  563. data/lib/omnizip/parity/reed_solomon_encoder.rb +108 -0
  564. data/lib/omnizip/parity/reed_solomon_matrix.rb +339 -0
  565. data/lib/omnizip/parity.rb +207 -0
  566. data/lib/omnizip/password/encryption_registry.rb +26 -0
  567. data/lib/omnizip/password/encryption_strategy.rb +96 -0
  568. data/lib/omnizip/password/password_validator.rb +129 -0
  569. data/lib/omnizip/password/winzip_aes_strategy.rb +190 -0
  570. data/lib/omnizip/password/zip_crypto_strategy.rb +135 -0
  571. data/lib/omnizip/password.rb +88 -0
  572. data/lib/omnizip/pipe/stream_compressor.rb +124 -0
  573. data/lib/omnizip/pipe/stream_decompressor.rb +173 -0
  574. data/lib/omnizip/pipe.rb +120 -0
  575. data/lib/omnizip/platform/ntfs_streams.rb +200 -0
  576. data/lib/omnizip/platform.rb +189 -0
  577. data/lib/omnizip/profile/archive_profile.rb +36 -0
  578. data/lib/omnizip/profile/balanced_profile.rb +31 -0
  579. data/lib/omnizip/profile/binary_profile.rb +33 -0
  580. data/lib/omnizip/profile/compression_profile.rb +157 -0
  581. data/lib/omnizip/profile/custom_profile.rb +155 -0
  582. data/lib/omnizip/profile/fast_profile.rb +31 -0
  583. data/lib/omnizip/profile/maximum_profile.rb +31 -0
  584. data/lib/omnizip/profile/profile_detector.rb +108 -0
  585. data/lib/omnizip/profile/profile_registry.rb +160 -0
  586. data/lib/omnizip/profile/text_profile.rb +33 -0
  587. data/lib/omnizip/profile.rb +261 -0
  588. data/lib/omnizip/profiler/memory_profiler.rb +66 -0
  589. data/lib/omnizip/profiler/method_profiler.rb +49 -0
  590. data/lib/omnizip/profiler/report_generator.rb +158 -0
  591. data/lib/omnizip/profiler.rb +192 -0
  592. data/lib/omnizip/progress/callback_reporter.rb +34 -0
  593. data/lib/omnizip/progress/console_reporter.rb +59 -0
  594. data/lib/omnizip/progress/log_reporter.rb +89 -0
  595. data/lib/omnizip/progress/operation_progress.rb +118 -0
  596. data/lib/omnizip/progress/progress_bar.rb +156 -0
  597. data/lib/omnizip/progress/progress_reporter.rb +40 -0
  598. data/lib/omnizip/progress/progress_tracker.rb +215 -0
  599. data/lib/omnizip/progress/silent_reporter.rb +22 -0
  600. data/lib/omnizip/progress.rb +131 -0
  601. data/lib/omnizip/registry.rb +111 -0
  602. data/lib/omnizip/rubyzip_compat.rb +61 -0
  603. data/lib/omnizip/temp/safe_extract.rb +124 -0
  604. data/lib/omnizip/temp/temp_file.rb +123 -0
  605. data/lib/omnizip/temp/temp_file_pool.rb +109 -0
  606. data/lib/omnizip/temp.rb +184 -0
  607. data/lib/omnizip/version.rb +5 -0
  608. data/lib/omnizip/zip/entry.rb +160 -0
  609. data/lib/omnizip/zip/file.rb +485 -0
  610. data/lib/omnizip/zip/input_stream.rb +270 -0
  611. data/lib/omnizip/zip/output_stream.rb +320 -0
  612. data/lib/omnizip/zip.rb +23 -0
  613. data/lib/omnizip.rb +157 -0
  614. data/lib/tasks/msi_test_files.rake +66 -0
  615. data/lib/tasks/platform_gems.rake +147 -0
  616. data/lib/tasks/rust_backend.rake +48 -0
  617. data/readme-docs/advanced-features.adoc +514 -0
  618. data/readme-docs/api-usage.adoc +445 -0
  619. data/readme-docs/architecture.adoc +450 -0
  620. data/readme-docs/archive-formats.adoc +479 -0
  621. data/readme-docs/cli-usage.adoc +222 -0
  622. data/readme-docs/compression-algorithms.adoc +446 -0
  623. data/readme-docs/compression-profiles.adoc +247 -0
  624. data/readme-docs/encryption-checksums.adoc +328 -0
  625. data/readme-docs/format-converter.adoc +316 -0
  626. data/readme-docs/installation.adoc +228 -0
  627. data/readme-docs/par2-archives.adoc +608 -0
  628. data/readme-docs/performance-profiler.adoc +389 -0
  629. data/readme-docs/preprocessing-filters.adoc +280 -0
  630. data/vendor/libomnizip_ffi.so +0 -0
  631. data/xz-file-format-1.2.1.txt +1174 -0
  632. metadata +768 -0
@@ -0,0 +1,534 @@
1
+ # frozen_string_literal: true
2
+
3
+ # Copyright (C) 2025 Ribose Inc.
4
+ #
5
+ # Permission is hereby granted, free of charge, to any person obtaining a
6
+ # copy of this software and associated documentation files (the "Software"),
7
+ # to deal in the Software without restriction, including without limitation
8
+ # the rights to use, copy, modify, merge, publish, distribute, sublicense,
9
+ # and/or sell copies of the Software, and to permit persons to whom the
10
+ # Software is furnished to do so, subject to the following conditions:
11
+ #
12
+ # The above copyright notice and this permission notice shall be included in
13
+ # all copies or substantial portions of the Software.
14
+ #
15
+ # THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
16
+ # IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
17
+ # FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
18
+ # AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
19
+ # LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING
20
+ # FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER
21
+ # DEALINGS IN THE SOFTWARE.
22
+
23
+ module Omnizip
24
+ module Algorithms
25
+ class Zstandard
26
+ module FSE
27
+ # FSE encoder (RFC 8878 §4.1): count normalization, NCount
28
+ # writing, CTable construction, and 2-state interleaved
29
+ # bitstream encoding. Mirrors the C reference FSE library.
30
+ class Encoder
31
+ include Constants
32
+
33
+ RTB_TABLE = [0, 473_195, 504_333, 520_860, 550_000, 700_000,
34
+ 750_000, 830_000].freeze
35
+ NOT_YET_ASSIGNED = -2
36
+
37
+ SymbolTT = Struct.new(:delta_nb_bits, :delta_find_state)
38
+
39
+ # @return [Array<Integer>] normalized distribution
40
+ attr_reader :distribution
41
+
42
+ # @return [Integer]
43
+ attr_reader :table_log
44
+
45
+ # @return [Integer]
46
+ attr_reader :max_symbol_value
47
+
48
+ # Normalize a raw histogram to sum to (1 << table_log).
49
+ #
50
+ # @param table_log [Integer]
51
+ # @param count [Array<Integer>] raw frequencies
52
+ # @param total [Integer] sum(count)
53
+ # @param max_symbol_value [Integer] highest symbol index
54
+ # @param use_low_prob [Boolean] emit -1 sentinels for rare
55
+ # symbols (the zstd default)
56
+ # @return [Array<Integer>] normalized distribution, or [] for
57
+ # an RLE stream
58
+ def self.normalize_count(table_log, count, total, max_symbol_value,
59
+ use_low_prob: true)
60
+ table_log = FSE_DEFAULT_TABLELOG if table_log.zero?
61
+
62
+ norm = Array.new(max_symbol_value + 1, 0)
63
+
64
+ # RLE: a single symbol accounts for everything.
65
+ (0..max_symbol_value).each do |s|
66
+ return [] if count[s] == total
67
+ end
68
+
69
+ low_prob_count = use_low_prob ? -1 : 1
70
+ scale = 62 - table_log
71
+ step = (1 << 62) / total
72
+ v_step = 1 << (scale - 20)
73
+ still_to_distribute = 1 << table_log
74
+ low_threshold = total >> table_log
75
+ largest = 0
76
+ largest_p = 0
77
+
78
+ (0..max_symbol_value).each do |s|
79
+ if count[s].zero?
80
+ norm[s] = 0
81
+ next
82
+ end
83
+
84
+ c64 = count[s]
85
+ if c64 <= low_threshold
86
+ norm[s] = low_prob_count
87
+ still_to_distribute -= 1
88
+ else
89
+ proba = (c64 * step) >> scale
90
+ if proba < 8
91
+ rest_to_beat = v_step * RTB_TABLE[proba]
92
+ diff = (c64 * step) - (proba << scale)
93
+ proba += 1 if diff > rest_to_beat
94
+ end
95
+ if proba > largest_p
96
+ largest_p = proba
97
+ largest = s
98
+ end
99
+ norm[s] = proba
100
+ still_to_distribute -= proba
101
+ end
102
+ end
103
+
104
+ if -still_to_distribute >= norm[largest] / 2
105
+ normalize_m2(norm, table_log, count, total, max_symbol_value,
106
+ low_prob_count)
107
+ else
108
+ norm[largest] += still_to_distribute
109
+ end
110
+
111
+ norm
112
+ end
113
+
114
+ # Secondary normalization (C FSE_normalizeM2), used when the
115
+ # primary method's largest-symbol correction would be too big.
116
+ # rubocop:disable Metrics/MethodLength
117
+ # rubocop:disable-next Metrics/AbcSize
118
+ def self.normalize_m2(norm, table_log, count, total, max_symbol_value,
119
+ low_prob_count)
120
+ table_size = 1 << table_log
121
+ low_threshold = total >> table_log
122
+ low_one = (total * 3) >> (table_log + 1)
123
+ distributed = 0
124
+ remaining = total
125
+
126
+ (0..max_symbol_value).each do |s|
127
+ if count[s].zero?
128
+ norm[s] = 0
129
+ elsif count[s] <= low_threshold
130
+ norm[s] = low_prob_count
131
+ distributed += 1
132
+ remaining -= count[s]
133
+ elsif count[s] <= low_one
134
+ norm[s] = 1
135
+ distributed += 1
136
+ remaining -= count[s]
137
+ else
138
+ norm[s] = NOT_YET_ASSIGNED
139
+ end
140
+ end
141
+
142
+ to_distribute = table_size - distributed
143
+ return if to_distribute.zero?
144
+
145
+ if remaining / to_distribute > low_one
146
+ low_one = (remaining * 3) / (to_distribute * 2)
147
+ (0..max_symbol_value).each do |s|
148
+ if norm[s] == NOT_YET_ASSIGNED && count[s] <= low_one
149
+ norm[s] = 1
150
+ distributed += 1
151
+ remaining -= count[s]
152
+ end
153
+ end
154
+ to_distribute = table_size - distributed
155
+ end
156
+
157
+ if distributed == max_symbol_value + 1
158
+ max_v = 0
159
+ max_c = 0
160
+ (0..max_symbol_value).each do |s|
161
+ if count[s] > max_c
162
+ max_v = s
163
+ max_c = count[s]
164
+ end
165
+ end
166
+ norm[max_v] += to_distribute
167
+ return
168
+ end
169
+
170
+ if remaining.zero?
171
+ idx = 0
172
+ while to_distribute.positive? && idx <= max_symbol_value
173
+ if norm[idx]&.positive?
174
+ norm[idx] += 1
175
+ to_distribute -= 1
176
+ end
177
+ idx = (idx + 1) % (max_symbol_value + 1)
178
+ end
179
+ return
180
+ end
181
+
182
+ v_step_log = 62 - table_log
183
+ mid = (1 << (v_step_log - 1)) - 1
184
+ r_step = (((1 << v_step_log) * to_distribute) + mid) / remaining
185
+ tmp_total = mid
186
+ (0..max_symbol_value).each do |s|
187
+ next unless norm[s] == NOT_YET_ASSIGNED
188
+
189
+ end_v = tmp_total + (count[s] * r_step)
190
+ weight = (end_v >> v_step_log) - (tmp_total >> v_step_log)
191
+ norm[s] = weight
192
+ tmp_total = end_v
193
+ end
194
+ end
195
+ # rubocop:enable Metrics/MethodLength
196
+
197
+ # Choose an accuracy log for the given source size and alphabet.
198
+ #
199
+ # Direct port of C FSE_optimalTableLog; the branch ladder is
200
+ # inherent to the algorithm.
201
+ # rubocop:disable-next Metrics/AbcSize
202
+ def self.optimal_table_log(max_table_log, src_size, max_symbol_value)
203
+ return FSE_MIN_ACCURACY_LOG if src_size <= 1
204
+
205
+ max_bits_src = (src_size - 1).bit_length - 1 - 2
206
+ max_bits_src = 0 if max_bits_src.negative?
207
+ min_bits_src = src_size.bit_length + 1
208
+ min_bits_sym = [max_symbol_value, 1].max.bit_length + 2
209
+ min_bits = [min_bits_src, min_bits_sym].min
210
+
211
+ table_log = max_table_log
212
+ table_log = FSE_DEFAULT_TABLELOG if table_log.zero?
213
+ table_log = max_bits_src if max_bits_src < table_log
214
+ table_log = min_bits if min_bits > table_log
215
+ table_log.clamp(FSE_MIN_ACCURACY_LOG, FSE_MAX_ACCURACY_LOG)
216
+ end
217
+
218
+ # Build from raw symbols: normalize + store.
219
+ #
220
+ # @param symbols [Array<Integer>]
221
+ # @param max_symbol_value [Integer]
222
+ # @param max_table_log [Integer]
223
+ # @return [Encoder, nil] nil for an RLE stream (single symbol)
224
+ def self.build_from_symbols(symbols, max_symbol_value,
225
+ max_table_log = FSE_DEFAULT_TABLELOG)
226
+ counts = Array.new(max_symbol_value + 1, 0)
227
+ symbols.each { |s| counts[s] += 1 }
228
+ total = symbols.length
229
+
230
+ actual_max = max_symbol_value
231
+ actual_max -= 1 while actual_max.positive? && counts[actual_max].zero?
232
+
233
+ table_log = optimal_table_log(max_table_log, total, actual_max)
234
+ norm = normalize_count(table_log, counts, total, actual_max,
235
+ use_low_prob: true)
236
+ return nil if norm.empty?
237
+
238
+ new(norm, table_log, actual_max)
239
+ end
240
+
241
+ def initialize(distribution, table_log, max_symbol_value)
242
+ @distribution = distribution
243
+ @table_log = table_log
244
+ @max_symbol_value = max_symbol_value
245
+ build_encoding_tables
246
+ end
247
+
248
+ # Serialize the table description (NCount) per RFC 8878 §4.1.1.
249
+ #
250
+ # @return [String]
251
+ # rubocop:disable Metrics/MethodLength
252
+ # rubocop:disable-next Metrics/AbcSize
253
+ def write_ncount
254
+ out = []
255
+ table_size = 1 << @table_log
256
+ bit_stream = 0
257
+ bit_count = 0
258
+ symbol = 0
259
+ alphabet_size = @max_symbol_value + 1
260
+ previous_is_zero = false
261
+ remaining = table_size + 1
262
+ threshold = table_size
263
+ nb_bits = @table_log + 1
264
+
265
+ bit_stream |= (@table_log - FSE_MIN_ACCURACY_LOG) << bit_count
266
+ bit_count += 4
267
+
268
+ while symbol < alphabet_size && remaining > 1
269
+ if previous_is_zero
270
+ start = symbol
271
+ symbol += 1 while symbol < alphabet_size &&
272
+ @distribution[symbol].zero?
273
+ if symbol == alphabet_size
274
+ raise Omnizip::CompressionError, "bad FSE distribution"
275
+ end
276
+
277
+ while symbol >= start + 24
278
+ start += 24
279
+ bit_stream |= 0xFFFF << bit_count
280
+ out.push(bit_stream & 0xFF, (bit_stream >> 8) & 0xFF)
281
+ bit_stream >>= 16
282
+ end
283
+ while symbol >= start + 3
284
+ start += 3
285
+ bit_stream |= 3 << bit_count
286
+ bit_count += 2
287
+ end
288
+ bit_stream |= (symbol - start) << bit_count
289
+ bit_count += 2
290
+ if bit_count > 16
291
+ out.push(bit_stream & 0xFF, (bit_stream >> 8) & 0xFF)
292
+ bit_stream >>= 16
293
+ bit_count -= 16
294
+ end
295
+ end
296
+
297
+ count = @distribution[symbol]
298
+ symbol += 1
299
+ max = ((2 * threshold) - 1) - remaining
300
+ remaining -= count.negative? ? -count : count
301
+ count_val = count + 1
302
+ count_val += max if count_val >= threshold
303
+
304
+ bit_stream |= count_val << bit_count
305
+ bit_count += nb_bits
306
+ bit_count -= 1 if count_val < max
307
+
308
+ previous_is_zero = count_val == 1
309
+ raise Omnizip::CompressionError, "FSE NCount remaining < 1" if remaining < 1
310
+
311
+ while remaining < threshold
312
+ nb_bits -= 1
313
+ threshold >>= 1
314
+ end
315
+
316
+ if bit_count > 16
317
+ out.push(bit_stream & 0xFF, (bit_stream >> 8) & 0xFF)
318
+ bit_stream >>= 16
319
+ bit_count -= 16
320
+ end
321
+ end
322
+
323
+ unless remaining == 1
324
+ raise Omnizip::CompressionError,
325
+ "FSE NCount remaining != 1 (#{remaining})"
326
+ end
327
+
328
+ if bit_count.positive?
329
+ n_bytes = (bit_count + 7) / 8
330
+ out.push(*Array.new(n_bytes) { |i| (bit_stream >> (8 * i)) & 0xFF })
331
+ end
332
+
333
+ out.pack("C*")
334
+ end
335
+ # rubocop:enable Metrics/MethodLength
336
+
337
+ # Encode `symbols` into a 2-state interleaved reverse
338
+ # bitstream (C FSE_compress_usingCTable).
339
+ #
340
+ # @param symbols [Array<Integer>]
341
+ # @return [String] bitstream bytes ending with the 1-bit mark
342
+ # Direct port of C FSE_compress_usingCTable.
343
+ # rubocop:disable Metrics/AbcSize
344
+ def compress_symbols(symbols)
345
+ return "" if symbols.length <= 2
346
+
347
+ bitc = BitCStream.new
348
+ ip = symbols.length
349
+
350
+ ip -= 1
351
+ if symbols.length.odd?
352
+ s1 = CState.init2(self, symbols[ip])
353
+ ip -= 1
354
+ s2 = CState.init2(self, symbols[ip])
355
+ ip -= 1
356
+ s1.encode(bitc, self, symbols[ip])
357
+ bitc.flush
358
+ else
359
+ s2 = CState.init2(self, symbols[ip])
360
+ ip -= 1
361
+ s1 = CState.init2(self, symbols[ip])
362
+ end
363
+ # rubocop:enable Metrics/AbcSize
364
+
365
+ while ip.positive?
366
+ ip -= 1
367
+ s2.encode(bitc, self, symbols[ip])
368
+ break if ip.zero?
369
+
370
+ ip -= 1
371
+ s1.encode(bitc, self, symbols[ip])
372
+ bitc.flush
373
+ end
374
+
375
+ s2.flush(bitc)
376
+ s1.flush(bitc)
377
+ bitc.close
378
+ end
379
+
380
+ # Serialize table description + bitstream for `symbols`.
381
+ #
382
+ # @return [String]
383
+ def compress(symbols)
384
+ write_ncount + compress_symbols(symbols)
385
+ end
386
+
387
+ # @return [Array<Integer>] state transition table
388
+ attr_reader :state_table
389
+
390
+ # @return [Array<SymbolTT>]
391
+ attr_reader :symbol_tt
392
+
393
+ private
394
+
395
+ # Direct port of C FSE_buildCTable.
396
+ # rubocop:disable Metrics/AbcSize
397
+ def build_encoding_tables
398
+ table_size = 1 << @table_log
399
+ step = (table_size >> 1) + (table_size >> 3) + 3
400
+ mask = table_size - 1
401
+ max_sv1 = @max_symbol_value + 1
402
+
403
+ table_symbol = Array.new(table_size, 0xFFFF)
404
+ high_threshold = table_size - 1
405
+
406
+ cumul = Array.new(max_sv1 + 1, 0)
407
+ (1..max_sv1).each do |u|
408
+ if @distribution[u - 1] == -1
409
+ cumul[u] = cumul[u - 1] + 1
410
+ table_symbol[high_threshold] = u - 1
411
+ high_threshold -= 1
412
+ else
413
+ cumul[u] = cumul[u - 1] + @distribution[u - 1]
414
+ end
415
+ # rubocop:enable Metrics/AbcSize
416
+ end
417
+ cumul[max_sv1] = table_size + 1
418
+
419
+ position = 0
420
+ @distribution.each_with_index do |freq, symbol|
421
+ next unless freq.positive?
422
+
423
+ freq.times do
424
+ table_symbol[position] = symbol
425
+ position = (position + step) & mask
426
+ position = (position + step) & mask while position > high_threshold
427
+ end
428
+ end
429
+
430
+ @state_table = Array.new(table_size, 0)
431
+ table_size.times do |u|
432
+ s = table_symbol[u]
433
+ @state_table[cumul[s]] = table_size + u
434
+ cumul[s] += 1
435
+ end
436
+
437
+ @symbol_tt = Array.new(max_sv1) { SymbolTT.new(0, 0) }
438
+ total = 0
439
+ max_sv1.times do |s|
440
+ case @distribution[s]
441
+ when 0
442
+ @symbol_tt[s].delta_nb_bits = ((@table_log + 1) << 16) -
443
+ (1 << @table_log)
444
+ when -1, 1
445
+ @symbol_tt[s].delta_nb_bits = (@table_log << 16) -
446
+ (1 << @table_log)
447
+ @symbol_tt[s].delta_find_state = total - 1
448
+ total += 1
449
+ else
450
+ n = @distribution[s]
451
+ max_bits_out = @table_log - Constants.highbit32(n - 1)
452
+ min_state_plus = n << max_bits_out
453
+ @symbol_tt[s].delta_nb_bits = (max_bits_out << 16) - min_state_plus
454
+ @symbol_tt[s].delta_find_state = total - n
455
+ total += n
456
+ end
457
+ end
458
+ end
459
+
460
+ # Forward bit writer (C BIT_CStream): accumulates at the low
461
+ # end and flushes whole bytes.
462
+ class BitCStream
463
+ def initialize
464
+ @container = 0
465
+ @bit_pos = 0
466
+ end
467
+
468
+ # @param value [Integer] bits in the low end
469
+ # @param nb_bits [Integer] 0..31
470
+ def add_bits(value, nb_bits)
471
+ mask = (1 << nb_bits) - 1
472
+ @container |= (value & mask) << @bit_pos
473
+ @bit_pos += nb_bits
474
+ end
475
+
476
+ def flush
477
+ nb_bytes = @bit_pos >> 3
478
+ @bytes ||= []
479
+ nb_bytes.times do |i|
480
+ @bytes << ((@container >> (8 * i)) & 0xFF)
481
+ end
482
+ @container >>= nb_bytes * 8
483
+ @bit_pos &= 7
484
+ end
485
+
486
+ # Add the 1 end-mark bit and flush everything.
487
+ #
488
+ # @return [String]
489
+ def close
490
+ add_bits(1, 1)
491
+ flush
492
+ @bytes << (@container & 0xFF) if @bit_pos.positive?
493
+ @bytes.pack("C*")
494
+ end
495
+ end
496
+
497
+ # FSE encoder state (value in [table_size, 2*table_size)).
498
+ class CState
499
+ attr_reader :value
500
+
501
+ def initialize(value, state_log)
502
+ @value = value
503
+ @state_log = state_log
504
+ end
505
+
506
+ # Initialize to the baseline for the first symbol to encode
507
+ # (the last to decode); C FSE_initCState2.
508
+ # rubocop:disable-next Metrics/AbcSize
509
+ def self.init2(table, symbol)
510
+ s_tt = table.symbol_tt[symbol]
511
+ nb_bits_out = (s_tt.delta_nb_bits + (1 << 15)) >> 16
512
+ value = (nb_bits_out << 16) - s_tt.delta_nb_bits
513
+ idx = (value >> nb_bits_out) + s_tt.delta_find_state
514
+ new(table.state_table[idx], table.table_log)
515
+ end
516
+
517
+ def encode(bitc, table, symbol)
518
+ s_tt = table.symbol_tt[symbol]
519
+ nb_bits_out = (@value + s_tt.delta_nb_bits) >> 16
520
+ bitc.add_bits(@value, nb_bits_out)
521
+ idx = (@value >> nb_bits_out) + s_tt.delta_find_state
522
+ @value = table.state_table[idx]
523
+ end
524
+
525
+ def flush(bitc)
526
+ bitc.add_bits(@value, @state_log)
527
+ bitc.flush
528
+ end
529
+ end
530
+ end
531
+ end
532
+ end
533
+ end
534
+ end
@@ -0,0 +1,92 @@
1
+ # frozen_string_literal: true
2
+
3
+ # Copyright (C) 2025 Ribose Inc.
4
+ #
5
+ # Permission is hereby granted, free of charge, to any person obtaining a
6
+ # copy of this software and associated documentation files (the "Software"),
7
+ # to deal in the Software without restriction, including without limitation
8
+ # the rights to use, copy, modify, merge, publish, distribute, sublicense,
9
+ # and/or sell copies of the Software, and to permit persons to whom the
10
+ # Software is furnished to do so, subject to the following conditions:
11
+ #
12
+ # The above copyright notice and this permission notice shall be included in
13
+ # all copies or substantial portions of the Software.
14
+ #
15
+ # THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
16
+ # IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
17
+ # FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
18
+ # AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
19
+ # LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING
20
+ # FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER
21
+ # DEALINGS IN THE SOFTWARE.
22
+
23
+ module Omnizip
24
+ module Algorithms
25
+ class Zstandard
26
+ module FSE
27
+ # 2-state interleaved FSE stream decoder (RFC 8878 §4.2.1.2,
28
+ # "FSE compression of Huffman weights"; mirrors the C reference
29
+ # FSE_decompress_usingDTable).
30
+ #
31
+ # Symbols are produced until the bitstream overflows; after an
32
+ # overflow following one state's transition, one final symbol is
33
+ # decoded from the other state without transitioning.
34
+ module Interleaved
35
+ module_function
36
+
37
+ # Decode a 2-state interleaved FSE stream.
38
+ #
39
+ # @param table [Table]
40
+ # @param bitstream_bytes [String]
41
+ # @param max_output [Integer] cap on decoded length (corrupt
42
+ # input protection)
43
+ # @return [Array<Integer>] decoded symbols
44
+ def decode_stream(table, bitstream_bytes, max_output)
45
+ bs = BitStream.new(bitstream_bytes)
46
+ accuracy_log = table.accuracy_log
47
+
48
+ s1 = bs.read_bits(accuracy_log)
49
+ bs.reload
50
+ s2 = bs.read_bits(accuracy_log)
51
+ bs.reload
52
+
53
+ out = []
54
+
55
+ loop do
56
+ check_length!(out, max_output)
57
+ e1 = table[s1]
58
+ out << e1.symbol
59
+ s1 = e1.baseline + bs.read_bits(e1.num_bits)
60
+
61
+ if bs.reload_status == BitStream::OVERFLOW
62
+ check_length!(out, max_output)
63
+ out << table[s2].symbol
64
+ break
65
+ end
66
+
67
+ check_length!(out, max_output)
68
+ e2 = table[s2]
69
+ out << e2.symbol
70
+ s2 = e2.baseline + bs.read_bits(e2.num_bits)
71
+
72
+ if bs.reload_status == BitStream::OVERFLOW
73
+ check_length!(out, max_output)
74
+ out << table[s1].symbol
75
+ break
76
+ end
77
+ end
78
+
79
+ out
80
+ end
81
+
82
+ def check_length!(out, max_output)
83
+ return unless out.length >= max_output
84
+
85
+ raise Omnizip::DecompressionError,
86
+ "FSE decode exceeded max output #{max_output}"
87
+ end
88
+ end
89
+ end
90
+ end
91
+ end
92
+ end