thai-orthographic-segmenter 0.1.0__tar.gz
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.
- thai_orthographic_segmenter-0.1.0/Cargo.lock +6749 -0
- thai_orthographic_segmenter-0.1.0/Cargo.toml +42 -0
- thai_orthographic_segmenter-0.1.0/LICENSE-APACHE +176 -0
- thai_orthographic_segmenter-0.1.0/LICENSE-MIT +21 -0
- thai_orthographic_segmenter-0.1.0/LICENSE-UNICODE +55 -0
- thai_orthographic_segmenter-0.1.0/PKG-INFO +88 -0
- thai_orthographic_segmenter-0.1.0/README.md +68 -0
- thai_orthographic_segmenter-0.1.0/pyproject.toml +44 -0
- thai_orthographic_segmenter-0.1.0/python/thai_orthographic_segmenter/__init__.py +145 -0
- thai_orthographic_segmenter-0.1.0/python/thai_orthographic_segmenter/_native.pyi +27 -0
- thai_orthographic_segmenter-0.1.0/python/thai_orthographic_segmenter/py.typed +0 -0
- thai_orthographic_segmenter-0.1.0/thai-line-segmenter/Cargo.toml +28 -0
- thai_orthographic_segmenter-0.1.0/thai-line-segmenter/LICENSE-APACHE +176 -0
- thai_orthographic_segmenter-0.1.0/thai-line-segmenter/LICENSE-MIT +21 -0
- thai_orthographic_segmenter-0.1.0/thai-line-segmenter/README.md +71 -0
- thai_orthographic_segmenter-0.1.0/thai-line-segmenter/data/icu/LICENSE +55 -0
- thai_orthographic_segmenter-0.1.0/thai-line-segmenter/data/icu/th-icu.txt +26390 -0
- thai_orthographic_segmenter-0.1.0/thai-line-segmenter/src/error.rs +26 -0
- thai_orthographic_segmenter-0.1.0/thai-line-segmenter/src/icu_dictionary.rs +164 -0
- thai_orthographic_segmenter-0.1.0/thai-line-segmenter/src/line_segmenter.rs +455 -0
- thai_orthographic_segmenter-0.1.0/thai-line-segmenter/src/thai-line-segmenter.rs +85 -0
- thai_orthographic_segmenter-0.1.0/thai-line-segmenter/tests/auto_traits.rs +18 -0
- thai_orthographic_segmenter-0.1.0/thai-line-segmenter/tests/contracts.rs +79 -0
- thai_orthographic_segmenter-0.1.0/thai-line-segmenter/tests/properties.rs +40 -0
- thai_orthographic_segmenter-0.1.0/thai-segmenter-python/Cargo.toml +28 -0
- thai_orthographic_segmenter-0.1.0/thai-segmenter-python/LICENSE-APACHE +176 -0
- thai_orthographic_segmenter-0.1.0/thai-segmenter-python/LICENSE-MIT +21 -0
- thai_orthographic_segmenter-0.1.0/thai-segmenter-python/LICENSE-UNICODE +55 -0
- thai_orthographic_segmenter-0.1.0/thai-segmenter-python/README.md +68 -0
- thai_orthographic_segmenter-0.1.0/thai-segmenter-python/src/error.rs +30 -0
- thai_orthographic_segmenter-0.1.0/thai-segmenter-python/src/lines.rs +46 -0
- thai_orthographic_segmenter-0.1.0/thai-segmenter-python/src/parts.rs +36 -0
- thai_orthographic_segmenter-0.1.0/thai-segmenter-python/src/spans.rs +40 -0
- thai_orthographic_segmenter-0.1.0/thai-segmenter-python/src/syllables.rs +49 -0
- thai_orthographic_segmenter-0.1.0/thai-segmenter-python/src/thai-segmenter-python.rs +30 -0
- thai_orthographic_segmenter-0.1.0/thai-segmenter-python/src/words.rs +156 -0
- thai_orthographic_segmenter-0.1.0/thai-segmenter-python/tests/test_segmenters.py +126 -0
- thai_orthographic_segmenter-0.1.0/thai-syllable-rules/Cargo.toml +44 -0
- thai_orthographic_segmenter-0.1.0/thai-syllable-rules/LICENSE-APACHE +176 -0
- thai_orthographic_segmenter-0.1.0/thai-syllable-rules/LICENSE-MIT +21 -0
- thai_orthographic_segmenter-0.1.0/thai-syllable-rules/README.md +83 -0
- thai_orthographic_segmenter-0.1.0/thai-syllable-rules/src/alternative_sites.rs +127 -0
- thai_orthographic_segmenter-0.1.0/thai-syllable-rules/src/atom.rs +307 -0
- thai_orthographic_segmenter-0.1.0/thai-syllable-rules/src/atom_sequence.rs +5 -0
- thai_orthographic_segmenter-0.1.0/thai-syllable-rules/src/atomization.rs +24 -0
- thai_orthographic_segmenter-0.1.0/thai-syllable-rules/src/atomization_completion.rs +400 -0
- thai_orthographic_segmenter-0.1.0/thai-syllable-rules/src/atomization_leading_vowel.rs +286 -0
- thai_orthographic_segmenter-0.1.0/thai-syllable-rules/src/atomization_onset.rs +297 -0
- thai_orthographic_segmenter-0.1.0/thai-syllable-rules/src/atomization_rime.rs +180 -0
- thai_orthographic_segmenter-0.1.0/thai-syllable-rules/src/atomization_silent_mark.rs +197 -0
- thai_orthographic_segmenter-0.1.0/thai-syllable-rules/src/attachment_evidence.rs +130 -0
- thai_orthographic_segmenter-0.1.0/thai-syllable-rules/src/character.rs +483 -0
- thai_orthographic_segmenter-0.1.0/thai-syllable-rules/src/character_sequence.rs +9 -0
- thai_orthographic_segmenter-0.1.0/thai-syllable-rules/src/completeness.rs +73 -0
- thai_orthographic_segmenter-0.1.0/thai-syllable-rules/src/construction_scan.rs +44 -0
- thai_orthographic_segmenter-0.1.0/thai-syllable-rules/src/ending.rs +64 -0
- thai_orthographic_segmenter-0.1.0/thai-syllable-rules/src/ending_closure.rs +107 -0
- thai_orthographic_segmenter-0.1.0/thai-syllable-rules/src/ending_extension.rs +147 -0
- thai_orthographic_segmenter-0.1.0/thai-syllable-rules/src/ending_finals.rs +500 -0
- thai_orthographic_segmenter-0.1.0/thai-syllable-rules/src/ending_lookahead.rs +253 -0
- thai_orthographic_segmenter-0.1.0/thai-syllable-rules/src/implicit.rs +139 -0
- thai_orthographic_segmenter-0.1.0/thai-syllable-rules/src/ownership_plan.rs +135 -0
- thai_orthographic_segmenter-0.1.0/thai-syllable-rules/src/part.rs +119 -0
- thai_orthographic_segmenter-0.1.0/thai-syllable-rules/src/r_han.rs +95 -0
- thai_orthographic_segmenter-0.1.0/thai-syllable-rules/src/reading_alternative.rs +71 -0
- thai_orthographic_segmenter-0.1.0/thai-syllable-rules/src/resolution.rs +87 -0
- thai_orthographic_segmenter-0.1.0/thai-syllable-rules/src/resolution_bare_run.rs +265 -0
- thai_orthographic_segmenter-0.1.0/thai-syllable-rules/src/resolution_candidates.rs +316 -0
- thai_orthographic_segmenter-0.1.0/thai-syllable-rules/src/resolution_hard_ending.rs +475 -0
- thai_orthographic_segmenter-0.1.0/thai-syllable-rules/src/resolution_input.rs +226 -0
- thai_orthographic_segmenter-0.1.0/thai-syllable-rules/src/resolution_nucleus.rs +220 -0
- thai_orthographic_segmenter-0.1.0/thai-syllable-rules/src/resolution_ordinary_run.rs +254 -0
- thai_orthographic_segmenter-0.1.0/thai-syllable-rules/src/rule_analysis.rs +185 -0
- thai_orthographic_segmenter-0.1.0/thai-syllable-rules/src/source.rs +257 -0
- thai_orthographic_segmenter-0.1.0/thai-syllable-rules/src/syllable_pattern.rs +250 -0
- thai_orthographic_segmenter-0.1.0/thai-syllable-rules/src/test_support.rs +318 -0
- thai_orthographic_segmenter-0.1.0/thai-syllable-rules/src/thai-syllable-rules.rs +117 -0
- thai_orthographic_segmenter-0.1.0/thai-syllable-rules/src/thai_legality.rs +118 -0
- thai_orthographic_segmenter-0.1.0/thai-syllable-rules/tests/architecture_contracts.rs +176 -0
- thai_orthographic_segmenter-0.1.0/thai-syllable-rules/tests/atomization.rs +295 -0
- thai_orthographic_segmenter-0.1.0/thai-syllable-rules/tests/attachment_evidence.rs +133 -0
- thai_orthographic_segmenter-0.1.0/thai-syllable-rules/tests/auto_traits.rs +27 -0
- thai_orthographic_segmenter-0.1.0/thai-syllable-rules/tests/carrier_and_cluster_atomization.rs +256 -0
- thai_orthographic_segmenter-0.1.0/thai-syllable-rules/tests/carrier_boundaries.rs +417 -0
- thai_orthographic_segmenter-0.1.0/thai-syllable-rules/tests/completeness.rs +155 -0
- thai_orthographic_segmenter-0.1.0/thai-syllable-rules/tests/construction_alternatives.rs +61 -0
- thai_orthographic_segmenter-0.1.0/thai-syllable-rules/tests/endings.rs +254 -0
- thai_orthographic_segmenter-0.1.0/thai-syllable-rules/tests/final_and_cluster_boundaries.rs +274 -0
- thai_orthographic_segmenter-0.1.0/thai-syllable-rules/tests/fixtures.rs +218 -0
- thai_orthographic_segmenter-0.1.0/thai-syllable-rules/tests/han_solo_expected/records_001_to_020.rs +470 -0
- thai_orthographic_segmenter-0.1.0/thai-syllable-rules/tests/han_solo_expected/records_021_to_030.rs +451 -0
- thai_orthographic_segmenter-0.1.0/thai-syllable-rules/tests/han_solo_expected/records_031_to_047.rs +449 -0
- thai_orthographic_segmenter-0.1.0/thai-syllable-rules/tests/han_solo_expected/records_048_to_067.rs +442 -0
- thai_orthographic_segmenter-0.1.0/thai-syllable-rules/tests/han_solo_expected/records_068_to_080.rs +439 -0
- thai_orthographic_segmenter-0.1.0/thai-syllable-rules/tests/han_solo_expected/records_081_to_096.rs +469 -0
- thai_orthographic_segmenter-0.1.0/thai-syllable-rules/tests/han_solo_expected/records_097_to_113.rs +467 -0
- thai_orthographic_segmenter-0.1.0/thai-syllable-rules/tests/han_solo_expected/records_114_to_134.rs +463 -0
- thai_orthographic_segmenter-0.1.0/thai-syllable-rules/tests/han_solo_expected/records_135_to_149.rs +457 -0
- thai_orthographic_segmenter-0.1.0/thai-syllable-rules/tests/han_solo_expected/records_150_to_160.rs +419 -0
- thai_orthographic_segmenter-0.1.0/thai-syllable-rules/tests/han_solo_expected/records_161_to_173.rs +473 -0
- thai_orthographic_segmenter-0.1.0/thai-syllable-rules/tests/han_solo_expected/records_174_to_189.rs +299 -0
- thai_orthographic_segmenter-0.1.0/thai-syllable-rules/tests/han_solo_expected/records_190_to_191.rs +374 -0
- thai_orthographic_segmenter-0.1.0/thai-syllable-rules/tests/han_solo_expected/records_192_to_199.rs +401 -0
- thai_orthographic_segmenter-0.1.0/thai-syllable-rules/tests/han_solo_test.rs +262 -0
- thai_orthographic_segmenter-0.1.0/thai-syllable-rules/tests/hard_ending_fixture.rs +168 -0
- thai_orthographic_segmenter-0.1.0/thai-syllable-rules/tests/implicit_attachment.rs +262 -0
- thai_orthographic_segmenter-0.1.0/thai-syllable-rules/tests/leading_candidates.rs +280 -0
- thai_orthographic_segmenter-0.1.0/thai-syllable-rules/tests/legality.rs +127 -0
- thai_orthographic_segmenter-0.1.0/thai-syllable-rules/tests/linguistic_audit.rs +218 -0
- thai_orthographic_segmenter-0.1.0/thai-syllable-rules/tests/linguistic_roles.rs +90 -0
- thai_orthographic_segmenter-0.1.0/thai-syllable-rules/tests/ownership_ambiguity.rs +16 -0
- thai_orthographic_segmenter-0.1.0/thai-syllable-rules/tests/ownership_ranges.rs +48 -0
- thai_orthographic_segmenter-0.1.0/thai-syllable-rules/tests/pass_contracts.rs +84 -0
- thai_orthographic_segmenter-0.1.0/thai-syllable-rules/tests/properties.rs +68 -0
- thai_orthographic_segmenter-0.1.0/thai-syllable-rules/tests/ranges.rs +47 -0
- thai_orthographic_segmenter-0.1.0/thai-syllable-rules/tests/reading_alternatives.rs +152 -0
- thai_orthographic_segmenter-0.1.0/thai-syllable-rules/tests/sara_am.rs +52 -0
- thai_orthographic_segmenter-0.1.0/thai-syllable-rules/tests/serde_round_trip.rs +25 -0
- thai_orthographic_segmenter-0.1.0/thai-syllable-rules/tests/source_alphabet.rs +30 -0
- thai_orthographic_segmenter-0.1.0/thai-syllable-rules/tests/syllable_pattern.rs +97 -0
- thai_orthographic_segmenter-0.1.0/thai-syllable-rules/tests/text_part.rs +24 -0
- thai_orthographic_segmenter-0.1.0/thai-syllable-rules/tests/vowel_boundaries.rs +449 -0
- thai_orthographic_segmenter-0.1.0/thai-syllable-segmenter/Cargo.toml +31 -0
- thai_orthographic_segmenter-0.1.0/thai-syllable-segmenter/LICENSE-APACHE +176 -0
- thai_orthographic_segmenter-0.1.0/thai-syllable-segmenter/LICENSE-MIT +21 -0
- thai_orthographic_segmenter-0.1.0/thai-syllable-segmenter/README.md +90 -0
- thai_orthographic_segmenter-0.1.0/thai-syllable-segmenter/examples/convert-checkpoint.rs +223 -0
- thai_orthographic_segmenter-0.1.0/thai-syllable-segmenter/examples/syllable-boundaries.rs +33 -0
- thai_orthographic_segmenter-0.1.0/thai-syllable-segmenter/model/characters.txt +71 -0
- thai_orthographic_segmenter-0.1.0/thai-syllable-segmenter/model/ngrams.txt +41164 -0
- thai_orthographic_segmenter-0.1.0/thai-syllable-segmenter/model/weights.safetensors +0 -0
- thai_orthographic_segmenter-0.1.0/thai-syllable-segmenter/src/checkpoint.rs +50 -0
- thai_orthographic_segmenter-0.1.0/thai-syllable-segmenter/src/contextual_model.rs +292 -0
- thai_orthographic_segmenter-0.1.0/thai-syllable-segmenter/src/error.rs +44 -0
- thai_orthographic_segmenter-0.1.0/thai-syllable-segmenter/src/inference/checkpoint.rs +500 -0
- thai_orthographic_segmenter-0.1.0/thai-syllable-segmenter/src/inference/cpu.rs +45 -0
- thai_orthographic_segmenter-0.1.0/thai-syllable-segmenter/src/inference/encoder_layer.rs +606 -0
- thai_orthographic_segmenter-0.1.0/thai-syllable-segmenter/src/inference/numerics.rs +294 -0
- thai_orthographic_segmenter-0.1.0/thai-syllable-segmenter/src/inference/packed_matrix.rs +446 -0
- thai_orthographic_segmenter-0.1.0/thai-syllable-segmenter/src/inference/weights.rs +476 -0
- thai_orthographic_segmenter-0.1.0/thai-syllable-segmenter/src/inference.rs +19 -0
- thai_orthographic_segmenter-0.1.0/thai-syllable-segmenter/src/lattice.rs +295 -0
- thai_orthographic_segmenter-0.1.0/thai-syllable-segmenter/src/lattice_config.rs +51 -0
- thai_orthographic_segmenter-0.1.0/thai-syllable-segmenter/src/model_config.rs +39 -0
- thai_orthographic_segmenter-0.1.0/thai-syllable-segmenter/src/thai-syllable-segmenter.rs +210 -0
- thai_orthographic_segmenter-0.1.0/thai-syllable-segmenter/src/vocabulary.rs +131 -0
- thai_orthographic_segmenter-0.1.0/thai-syllable-segmenter/tests/auto_traits.rs +49 -0
- thai_orthographic_segmenter-0.1.0/thai-syllable-segmenter/tests/checkpoint.rs +187 -0
- thai_orthographic_segmenter-0.1.0/thai-syllable-segmenter/tests/inference.rs +143 -0
- thai_orthographic_segmenter-0.1.0/thai-syllable-segmenter/tests/properties.rs +84 -0
- thai_orthographic_segmenter-0.1.0/thai-syllable-segmenter/tests/segment.rs +90 -0
- thai_orthographic_segmenter-0.1.0/thai-word-segmenter/Cargo.toml +52 -0
- thai_orthographic_segmenter-0.1.0/thai-word-segmenter/LICENSE-APACHE +176 -0
- thai_orthographic_segmenter-0.1.0/thai-word-segmenter/LICENSE-MIT +21 -0
- thai_orthographic_segmenter-0.1.0/thai-word-segmenter/README.md +170 -0
- thai_orthographic_segmenter-0.1.0/thai-word-segmenter/examples/compare_bible.rs +209 -0
- thai_orthographic_segmenter-0.1.0/thai-word-segmenter/examples/throughput.rs +67 -0
- thai_orthographic_segmenter-0.1.0/thai-word-segmenter/model/config.json +13 -0
- thai_orthographic_segmenter-0.1.0/thai-word-segmenter/model/dictionary.txt +43276 -0
- thai_orthographic_segmenter-0.1.0/thai-word-segmenter/model/model.safetensors +0 -0
- thai_orthographic_segmenter-0.1.0/thai-word-segmenter/src/decoding.rs +241 -0
- thai_orthographic_segmenter-0.1.0/thai-word-segmenter/src/dictionary.rs +185 -0
- thai_orthographic_segmenter-0.1.0/thai-word-segmenter/src/encoding.rs +228 -0
- thai_orthographic_segmenter-0.1.0/thai-word-segmenter/src/error.rs +65 -0
- thai_orthographic_segmenter-0.1.0/thai-word-segmenter/src/inference.rs +547 -0
- thai_orthographic_segmenter-0.1.0/thai-word-segmenter/src/model.rs +501 -0
- thai_orthographic_segmenter-0.1.0/thai-word-segmenter/src/network.rs +365 -0
- thai_orthographic_segmenter-0.1.0/thai-word-segmenter/src/text_groups.rs +45 -0
- thai_orthographic_segmenter-0.1.0/thai-word-segmenter/src/text_runs.rs +87 -0
- thai_orthographic_segmenter-0.1.0/thai-word-segmenter/src/thai-word-segmenter.rs +86 -0
- thai_orthographic_segmenter-0.1.0/thai-word-segmenter/src/word_segmenter.rs +438 -0
- thai_orthographic_segmenter-0.1.0/thai-word-segmenter/tests/auto_traits.rs +44 -0
- thai_orthographic_segmenter-0.1.0/thai-word-segmenter/tests/cluster_contracts.rs +148 -0
- thai_orthographic_segmenter-0.1.0/thai-word-segmenter/tests/contracts.rs +121 -0
- thai_orthographic_segmenter-0.1.0/thai-word-segmenter/tests/inference.rs +129 -0
- thai_orthographic_segmenter-0.1.0/thai-word-segmenter/tests/properties.rs +113 -0
There are too many changes on this page to be displayed.
The amount of changes on this page would crash your brower.
You can still verify the content by downloading the package file manually.