Cargo.lock
Cargo.toml
LICENSE.md
MANIFEST.in
README.md
THIRD_PARTY_NOTICES.md
pyproject.toml
setup.cfg
setup.py
.github/scripts/check_pypi_version.py
.github/workflows/ci.yml
.github/workflows/publish.yml
.github/workflows/wheels.yml
benchmarks/splitter-benchmark.json
documentation/HANDOFF.md
documentation/avagraha-normalization.md
documentation/database-location.md
documentation/dictionary-results.md
documentation/local-cache.md
documentation/pre-split-compounds.md
documentation/prefix-rejoin.md
documentation/prefix-segmentation.md
documentation/publishing.md
documentation/rust-splitter-benchmark.md
documentation/rust-splitter.md
documentation/sandhi-splitter.md
documentation/taddhita-derivation.md
documentation/word-list-index.md
process_sanskrit/__init__.py
process_sanskrit.egg-info/PKG-INFO
process_sanskrit.egg-info/SOURCES.txt
process_sanskrit.egg-info/dependency_links.txt
process_sanskrit.egg-info/entry_points.txt
process_sanskrit.egg-info/requires.txt
process_sanskrit.egg-info/top_level.txt
process_sanskrit/functions/SQLiteFind.py
process_sanskrit/functions/__init__.py
process_sanskrit/functions/cleanResults.py
process_sanskrit/functions/compoundAnalysis.py
process_sanskrit/functions/dictionaryLookup.py
process_sanskrit/functions/hybridSplitter.py
process_sanskrit/functions/inflect.py
process_sanskrit/functions/model_inference.py
process_sanskrit/functions/process.py
process_sanskrit/functions/processBYT5.py
process_sanskrit/functions/rootAnyWord.py
process_sanskrit/functions/sandhiSplitScorer.py
process_sanskrit/functions/sandhiSplitter.py
process_sanskrit/functions/taddhitaDerivation.py
process_sanskrit/resources/MWKeysOnly.json
process_sanskrit/resources/__init__.py
process_sanskrit/resources/stopwords.csv
process_sanskrit/resources/type_map.tsv
process_sanskrit/setup/updateDB.py
process_sanskrit/splitter/LICENSE.darts-clone
process_sanskrit/splitter/LICENSE.protobuf-lite
process_sanskrit/splitter/LICENSE.sentencepiece
process_sanskrit/splitter/LICENSE.upstream
process_sanskrit/splitter/NOTICE.md
process_sanskrit/splitter/__init__.py
process_sanskrit/splitter/api.py
process_sanskrit/splitter/backends.py
process_sanskrit/splitter/data_manager.py
process_sanskrit/splitter/datastructures.py
process_sanskrit/splitter/lookup.py
process_sanskrit/splitter/normalization.py
process_sanskrit/splitter/sandhi.py
process_sanskrit/splitter/sandhi_analyzer.py
process_sanskrit/splitter/sanskrit_base.py
process_sanskrit/splitter/scorer.py
process_sanskrit/splitter/scorer_model.py
process_sanskrit/splitter/data/README.md
process_sanskrit/splitter/data/forms.trie
process_sanskrit/splitter/data/log-table.npy
process_sanskrit/splitter/data/sandhi_rules.zip
process_sanskrit/splitter/data/sentencepiece.model
process_sanskrit/splitter/data/w2v.npz
process_sanskrit/splitter/data/native/README.md
process_sanskrit/splitter/data/native/forms.fst
process_sanskrit/splitter/data/native/native-assets.json
process_sanskrit/splitter/data/native/sandhi_after.fst
process_sanskrit/splitter/data/native/sandhi_variants.bin
process_sanskrit/splitter/data/native/scorer.bin
process_sanskrit/splitter/data/native/scorer_vocab.fst
process_sanskrit/splitter/data/native/sentencepiece.model
process_sanskrit/utils/__init__.py
process_sanskrit/utils/analysisCache.py
process_sanskrit/utils/databaseSetup.py
process_sanskrit/utils/detectTransliteration.py
process_sanskrit/utils/dictionary_references.py
process_sanskrit/utils/lexicalResources.py
process_sanskrit/utils/loadResources.py
process_sanskrit/utils/paradigm.py
process_sanskrit/utils/processAPI.py
process_sanskrit/utils/resourcePaths.py
process_sanskrit/utils/stopwordsRemoval.py
process_sanskrit/utils/transliterationUtils.py
process_sanskrit/utils/wordListBuilder.py
rust/README.md
rust/resources.toml
rust/python/Cargo.toml
rust/python/build.rs
rust/python/cpp/ps_sentencepiece.cc
rust/python/cpp/ps_sentencepiece.h
rust/python/src/lib.rs
rust/resource-builder/Cargo.toml
rust/resource-builder/README.md
rust/resource-builder/src/config.rs
rust/resource-builder/src/lib.rs
rust/resource-builder/src/main.rs
rust/splitter-core/Cargo.toml
rust/splitter-core/src/error.rs
rust/splitter-core/src/lib.rs
rust/splitter-core/src/resources.rs
rust/splitter-core/src/rules.rs
rust/splitter-core/src/scorer.rs
rust/splitter-core/src/splitter.rs
rust/splitter-core/tests/core_contract.rs
rust/splitter-core/tests/scorer_contract.rs
rust/vendor/sentencepiece/LICENSE
rust/vendor/sentencepiece/README.md
rust/vendor/sentencepiece/VERSION.txt
rust/vendor/sentencepiece/src/CMakeLists.txt
rust/vendor/sentencepiece/src/bpe_model.cc
rust/vendor/sentencepiece/src/bpe_model.h
rust/vendor/sentencepiece/src/bpe_model_test.cc
rust/vendor/sentencepiece/src/bpe_model_trainer.cc
rust/vendor/sentencepiece/src/bpe_model_trainer.h
rust/vendor/sentencepiece/src/bpe_model_trainer_test.cc
rust/vendor/sentencepiece/src/builder.cc
rust/vendor/sentencepiece/src/builder.h
rust/vendor/sentencepiece/src/builder_test.cc
rust/vendor/sentencepiece/src/char_model.cc
rust/vendor/sentencepiece/src/char_model.h
rust/vendor/sentencepiece/src/char_model_test.cc
rust/vendor/sentencepiece/src/char_model_trainer.cc
rust/vendor/sentencepiece/src/char_model_trainer.h
rust/vendor/sentencepiece/src/char_model_trainer_test.cc
rust/vendor/sentencepiece/src/common.h
rust/vendor/sentencepiece/src/compile_charsmap_main.cc
rust/vendor/sentencepiece/src/error.cc
rust/vendor/sentencepiece/src/filesystem.cc
rust/vendor/sentencepiece/src/filesystem.h
rust/vendor/sentencepiece/src/filesystem_test.cc
rust/vendor/sentencepiece/src/freelist.h
rust/vendor/sentencepiece/src/freelist_test.cc
rust/vendor/sentencepiece/src/init.h
rust/vendor/sentencepiece/src/init_test.cc
rust/vendor/sentencepiece/src/model_factory.cc
rust/vendor/sentencepiece/src/model_factory.h
rust/vendor/sentencepiece/src/model_factory_test.cc
rust/vendor/sentencepiece/src/model_interface.cc
rust/vendor/sentencepiece/src/model_interface.h
rust/vendor/sentencepiece/src/model_interface_test.cc
rust/vendor/sentencepiece/src/normalization_rule.h
rust/vendor/sentencepiece/src/normalizer.cc
rust/vendor/sentencepiece/src/normalizer.h
rust/vendor/sentencepiece/src/normalizer_test.cc
rust/vendor/sentencepiece/src/pretokenizer_for_training.cc
rust/vendor/sentencepiece/src/pretokenizer_for_training.h
rust/vendor/sentencepiece/src/pretokenizer_for_training_test.cc
rust/vendor/sentencepiece/src/sentencepiece.proto
rust/vendor/sentencepiece/src/sentencepiece_model.proto
rust/vendor/sentencepiece/src/sentencepiece_processor.cc
rust/vendor/sentencepiece/src/sentencepiece_processor.h
rust/vendor/sentencepiece/src/sentencepiece_processor_test.cc
rust/vendor/sentencepiece/src/sentencepiece_trainer.cc
rust/vendor/sentencepiece/src/sentencepiece_trainer.h
rust/vendor/sentencepiece/src/sentencepiece_trainer_test.cc
rust/vendor/sentencepiece/src/spec_parser.h
rust/vendor/sentencepiece/src/spm_decode_main.cc
rust/vendor/sentencepiece/src/spm_encode_main.cc
rust/vendor/sentencepiece/src/spm_export_vocab_main.cc
rust/vendor/sentencepiece/src/spm_normalize_main.cc
rust/vendor/sentencepiece/src/spm_train_main.cc
rust/vendor/sentencepiece/src/test_main.cc
rust/vendor/sentencepiece/src/testharness.cc
rust/vendor/sentencepiece/src/testharness.h
rust/vendor/sentencepiece/src/trainer_factory.cc
rust/vendor/sentencepiece/src/trainer_factory.h
rust/vendor/sentencepiece/src/trainer_factory_test.cc
rust/vendor/sentencepiece/src/trainer_interface.cc
rust/vendor/sentencepiece/src/trainer_interface.h
rust/vendor/sentencepiece/src/trainer_interface_test.cc
rust/vendor/sentencepiece/src/unicode_script.cc
rust/vendor/sentencepiece/src/unicode_script.h
rust/vendor/sentencepiece/src/unicode_script_map.h
rust/vendor/sentencepiece/src/unicode_script_test.cc
rust/vendor/sentencepiece/src/unigram_model.cc
rust/vendor/sentencepiece/src/unigram_model.h
rust/vendor/sentencepiece/src/unigram_model_test.cc
rust/vendor/sentencepiece/src/unigram_model_trainer.cc
rust/vendor/sentencepiece/src/unigram_model_trainer.h
rust/vendor/sentencepiece/src/unigram_model_trainer_test.cc
rust/vendor/sentencepiece/src/util.cc
rust/vendor/sentencepiece/src/util.h
rust/vendor/sentencepiece/src/util_test.cc
rust/vendor/sentencepiece/src/word_model.cc
rust/vendor/sentencepiece/src/word_model.h
rust/vendor/sentencepiece/src/word_model_test.cc
rust/vendor/sentencepiece/src/word_model_trainer.cc
rust/vendor/sentencepiece/src/word_model_trainer.h
rust/vendor/sentencepiece/src/word_model_trainer_test.cc
rust/vendor/sentencepiece/src/builtin_pb/sentencepiece.pb.cc
rust/vendor/sentencepiece/src/builtin_pb/sentencepiece.pb.h
rust/vendor/sentencepiece/src/builtin_pb/sentencepiece_model.pb.cc
rust/vendor/sentencepiece/src/builtin_pb/sentencepiece_model.pb.h
rust/vendor/sentencepiece/third_party/CMakeLists.txt
rust/vendor/sentencepiece/third_party/absl/LICENSE
rust/vendor/sentencepiece/third_party/absl/container/btree_set.h
rust/vendor/sentencepiece/third_party/absl/container/flat_hash_map.h
rust/vendor/sentencepiece/third_party/absl/container/flat_hash_set.h
rust/vendor/sentencepiece/third_party/absl/flags/flag.cc
rust/vendor/sentencepiece/third_party/absl/flags/flag.h
rust/vendor/sentencepiece/third_party/absl/flags/parse.h
rust/vendor/sentencepiece/third_party/absl/flags/usage.h
rust/vendor/sentencepiece/third_party/absl/strings/ascii.h
rust/vendor/sentencepiece/third_party/absl/strings/match.h
rust/vendor/sentencepiece/third_party/absl/strings/numbers.h
rust/vendor/sentencepiece/third_party/absl/strings/str_cat.h
rust/vendor/sentencepiece/third_party/absl/strings/str_format.h
rust/vendor/sentencepiece/third_party/absl/strings/str_join.h
rust/vendor/sentencepiece/third_party/absl/strings/str_replace.h
rust/vendor/sentencepiece/third_party/absl/strings/str_split.h
rust/vendor/sentencepiece/third_party/absl/strings/string_view.h
rust/vendor/sentencepiece/third_party/absl/strings/strip.h
rust/vendor/sentencepiece/third_party/darts_clone/LICENSE
rust/vendor/sentencepiece/third_party/darts_clone/darts.h
rust/vendor/sentencepiece/third_party/esaxx/LICENSE
rust/vendor/sentencepiece/third_party/esaxx/esa.hxx
rust/vendor/sentencepiece/third_party/esaxx/sais.hxx
rust/vendor/sentencepiece/third_party/protobuf-lite/LICENSE
rust/vendor/sentencepiece/third_party/protobuf-lite/arena.cc
rust/vendor/sentencepiece/third_party/protobuf-lite/arenastring.cc
rust/vendor/sentencepiece/third_party/protobuf-lite/bytestream.cc
rust/vendor/sentencepiece/third_party/protobuf-lite/coded_stream.cc
rust/vendor/sentencepiece/third_party/protobuf-lite/common.cc
rust/vendor/sentencepiece/third_party/protobuf-lite/extension_set.cc
rust/vendor/sentencepiece/third_party/protobuf-lite/generated_enum_util.cc
rust/vendor/sentencepiece/third_party/protobuf-lite/generated_message_table_driven_lite.cc
rust/vendor/sentencepiece/third_party/protobuf-lite/generated_message_util.cc
rust/vendor/sentencepiece/third_party/protobuf-lite/implicit_weak_message.cc
rust/vendor/sentencepiece/third_party/protobuf-lite/int128.cc
rust/vendor/sentencepiece/third_party/protobuf-lite/io_win32.cc
rust/vendor/sentencepiece/third_party/protobuf-lite/message_lite.cc
rust/vendor/sentencepiece/third_party/protobuf-lite/parse_context.cc
rust/vendor/sentencepiece/third_party/protobuf-lite/repeated_field.cc
rust/vendor/sentencepiece/third_party/protobuf-lite/status.cc
rust/vendor/sentencepiece/third_party/protobuf-lite/statusor.cc
rust/vendor/sentencepiece/third_party/protobuf-lite/stringpiece.cc
rust/vendor/sentencepiece/third_party/protobuf-lite/stringprintf.cc
rust/vendor/sentencepiece/third_party/protobuf-lite/structurally_valid.cc
rust/vendor/sentencepiece/third_party/protobuf-lite/strutil.cc
rust/vendor/sentencepiece/third_party/protobuf-lite/time.cc
rust/vendor/sentencepiece/third_party/protobuf-lite/wire_format_lite.cc
rust/vendor/sentencepiece/third_party/protobuf-lite/zero_copy_stream.cc
rust/vendor/sentencepiece/third_party/protobuf-lite/zero_copy_stream_impl.cc
rust/vendor/sentencepiece/third_party/protobuf-lite/zero_copy_stream_impl_lite.cc
rust/vendor/sentencepiece/third_party/protobuf-lite/google/protobuf/any.h
rust/vendor/sentencepiece/third_party/protobuf-lite/google/protobuf/arena.h
rust/vendor/sentencepiece/third_party/protobuf-lite/google/protobuf/arena_impl.h
rust/vendor/sentencepiece/third_party/protobuf-lite/google/protobuf/arenastring.h
rust/vendor/sentencepiece/third_party/protobuf-lite/google/protobuf/descriptor.h
rust/vendor/sentencepiece/third_party/protobuf-lite/google/protobuf/extension_set.h
rust/vendor/sentencepiece/third_party/protobuf-lite/google/protobuf/extension_set_inl.h
rust/vendor/sentencepiece/third_party/protobuf-lite/google/protobuf/generated_enum_reflection.h
rust/vendor/sentencepiece/third_party/protobuf-lite/google/protobuf/generated_enum_util.h
rust/vendor/sentencepiece/third_party/protobuf-lite/google/protobuf/generated_message_table_driven.h
rust/vendor/sentencepiece/third_party/protobuf-lite/google/protobuf/generated_message_table_driven_lite.h
rust/vendor/sentencepiece/third_party/protobuf-lite/google/protobuf/generated_message_util.h
rust/vendor/sentencepiece/third_party/protobuf-lite/google/protobuf/has_bits.h
rust/vendor/sentencepiece/third_party/protobuf-lite/google/protobuf/implicit_weak_message.h
rust/vendor/sentencepiece/third_party/protobuf-lite/google/protobuf/map.h
rust/vendor/sentencepiece/third_party/protobuf-lite/google/protobuf/map_entry_lite.h
rust/vendor/sentencepiece/third_party/protobuf-lite/google/protobuf/map_field_lite.h
rust/vendor/sentencepiece/third_party/protobuf-lite/google/protobuf/map_type_handler.h
rust/vendor/sentencepiece/third_party/protobuf-lite/google/protobuf/message_lite.h
rust/vendor/sentencepiece/third_party/protobuf-lite/google/protobuf/metadata_lite.h
rust/vendor/sentencepiece/third_party/protobuf-lite/google/protobuf/parse_context.h
rust/vendor/sentencepiece/third_party/protobuf-lite/google/protobuf/port.h
rust/vendor/sentencepiece/third_party/protobuf-lite/google/protobuf/port_def.inc
rust/vendor/sentencepiece/third_party/protobuf-lite/google/protobuf/port_undef.inc
rust/vendor/sentencepiece/third_party/protobuf-lite/google/protobuf/repeated_field.h
rust/vendor/sentencepiece/third_party/protobuf-lite/google/protobuf/unknown_field_set.h
rust/vendor/sentencepiece/third_party/protobuf-lite/google/protobuf/wire_format_lite.h
rust/vendor/sentencepiece/third_party/protobuf-lite/google/protobuf/io/coded_stream.h
rust/vendor/sentencepiece/third_party/protobuf-lite/google/protobuf/io/io_win32.h
rust/vendor/sentencepiece/third_party/protobuf-lite/google/protobuf/io/zero_copy_stream.h
rust/vendor/sentencepiece/third_party/protobuf-lite/google/protobuf/io/zero_copy_stream_impl.h
rust/vendor/sentencepiece/third_party/protobuf-lite/google/protobuf/io/zero_copy_stream_impl_lite.h
rust/vendor/sentencepiece/third_party/protobuf-lite/google/protobuf/stubs/bytestream.h
rust/vendor/sentencepiece/third_party/protobuf-lite/google/protobuf/stubs/callback.h
rust/vendor/sentencepiece/third_party/protobuf-lite/google/protobuf/stubs/casts.h
rust/vendor/sentencepiece/third_party/protobuf-lite/google/protobuf/stubs/common.h
rust/vendor/sentencepiece/third_party/protobuf-lite/google/protobuf/stubs/hash.h
rust/vendor/sentencepiece/third_party/protobuf-lite/google/protobuf/stubs/int128.h
rust/vendor/sentencepiece/third_party/protobuf-lite/google/protobuf/stubs/logging.h
rust/vendor/sentencepiece/third_party/protobuf-lite/google/protobuf/stubs/macros.h
rust/vendor/sentencepiece/third_party/protobuf-lite/google/protobuf/stubs/map_util.h
rust/vendor/sentencepiece/third_party/protobuf-lite/google/protobuf/stubs/mutex.h
rust/vendor/sentencepiece/third_party/protobuf-lite/google/protobuf/stubs/once.h
rust/vendor/sentencepiece/third_party/protobuf-lite/google/protobuf/stubs/platform_macros.h
rust/vendor/sentencepiece/third_party/protobuf-lite/google/protobuf/stubs/port.h
rust/vendor/sentencepiece/third_party/protobuf-lite/google/protobuf/stubs/status.h
rust/vendor/sentencepiece/third_party/protobuf-lite/google/protobuf/stubs/statusor.h
rust/vendor/sentencepiece/third_party/protobuf-lite/google/protobuf/stubs/stl_util.h
rust/vendor/sentencepiece/third_party/protobuf-lite/google/protobuf/stubs/stringpiece.h
rust/vendor/sentencepiece/third_party/protobuf-lite/google/protobuf/stubs/stringprintf.h
rust/vendor/sentencepiece/third_party/protobuf-lite/google/protobuf/stubs/strutil.h
rust/vendor/sentencepiece/third_party/protobuf-lite/google/protobuf/stubs/time.h
scripts/README.md
scripts/benchmark_optimizations.py
scripts/benchmark_splitter.py
tests/BYT5test.py
tests/__init__.py
tests/compound_processing_results.txt
tests/gretilTesting.py
tests/processCompounds.py
tests/runBenchmarks.py
tests/sanskrit_benchmark_results.txt
tests/test_analysis_cache.py
tests/test_avagraha.py
tests/test_compound_preference.py
tests/test_database_lifecycle.py
tests/test_database_path_configuration.py
tests/test_null_dictionary_components.py
tests/test_optimizations.py
tests/test_prefix_merge.py
tests/test_prefix_segmentation.py
tests/test_presplit_options.py
tests/test_publish_workflow.py
tests/test_reference_comparison.py
tests/test_rust_third_party_notices.py
tests/test_splitter_backends.py
tests/test_splitter_benchmark.py
tests/test_splitter_parity.py
tests/test_taddhita_derivation.py
tests/test_update_database.py
tests/test_word_list_integrity.py
tests/yoga_sutra_analysis.txt
tests/ysTest.py
tests/Removable/benchmarkTesting.py
tests/Removable/dbTest.py
tests/datasets/__init__.py
tests/datasets/sanskrit_compounds_benchmark.json
tests/datasets/sanskrit_compounds_benchmark2.json
tests/datasets/testCases.py
tests/datasets/yogaSutra.py
tests/results/compound_processing_results copy.txt
tests/results/compound_processing_results.txt
tests/results/compound_processing_resultsGrouped.txt
tests/results/performance_baseline_gensim.json
tests/results/performance_local_cache.json
tests/results/performance_optimized_gensim.json
tests/results/reference_comparison_report.txt
tests/results/reference_comparison_report_baseline.txt
tests/results/sanskrit_benchmark_results.txt
tests/results/standard_benchmark_results.txt
tests/results/yoga_sutra_analysis.txt
tests/results/~$mpound_processing_results.txt
tools/build_splitter_data.py
tools/build_word_list.py
tools/generate_rust_third_party_notices.py