@loaders.gl/parquet 4.5.3 → 5.0.0-alpha.10
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.
- package/LICENSE +14 -3
- package/dist/bundled.d.ts +9 -0
- package/dist/bundled.d.ts.map +1 -0
- package/dist/bundled.js +10 -0
- package/dist/bundled.js.map +1 -0
- package/dist/delta-format.d.ts +9 -0
- package/dist/delta-format.d.ts.map +1 -0
- package/dist/delta-format.js +12 -0
- package/dist/delta-format.js.map +1 -0
- package/dist/delta-source-loader-types.d.ts +27 -0
- package/dist/delta-source-loader-types.d.ts.map +1 -0
- package/dist/delta-source-loader-types.js +28 -0
- package/dist/delta-source-loader-types.js.map +1 -0
- package/dist/delta-source.d.ts +48 -0
- package/dist/delta-source.d.ts.map +1 -0
- package/dist/delta-source.js +222 -0
- package/dist/delta-source.js.map +1 -0
- package/dist/delta-types.d.ts +38 -0
- package/dist/delta-types.d.ts.map +1 -0
- package/dist/delta-types.js +5 -0
- package/dist/delta-types.js.map +1 -0
- package/dist/geoparquet-loader-with-parser.d.ts +33 -0
- package/dist/geoparquet-loader-with-parser.d.ts.map +1 -0
- package/dist/geoparquet-loader-with-parser.js +52 -0
- package/dist/geoparquet-loader-with-parser.js.map +1 -0
- package/dist/geoparquet-loader.d.ts +59 -0
- package/dist/geoparquet-loader.d.ts.map +1 -0
- package/dist/geoparquet-loader.js +30 -0
- package/dist/geoparquet-loader.js.map +1 -0
- package/dist/iceberg-rest-catalog.d.ts +49 -0
- package/dist/iceberg-rest-catalog.d.ts.map +1 -0
- package/dist/iceberg-rest-catalog.js +78 -0
- package/dist/iceberg-rest-catalog.js.map +1 -0
- package/dist/iceberg-table-source.d.ts +63 -0
- package/dist/iceberg-table-source.d.ts.map +1 -0
- package/dist/iceberg-table-source.js +797 -0
- package/dist/iceberg-table-source.js.map +1 -0
- package/dist/iceberg-types.d.ts +150 -0
- package/dist/iceberg-types.d.ts.map +1 -0
- package/dist/iceberg-types.js +5 -0
- package/dist/iceberg-types.js.map +1 -0
- package/dist/index.cjs +41568 -6781
- package/dist/index.cjs.map +3 -4
- package/dist/index.d.ts +15 -9
- package/dist/index.d.ts.map +1 -1
- package/dist/index.js +11 -12
- package/dist/index.js.map +1 -1
- package/dist/lib/arrow/convert-columns-to-row-group.js +3 -0
- package/dist/lib/arrow/convert-columns-to-row-group.js.map +1 -1
- package/dist/lib/arrow/convert-schema-from-parquet.d.ts +3 -1
- package/dist/lib/arrow/convert-schema-from-parquet.d.ts.map +1 -1
- package/dist/lib/arrow/convert-schema-from-parquet.js +164 -29
- package/dist/lib/arrow/convert-schema-from-parquet.js.map +1 -1
- package/dist/lib/arrow/convert-schema-to-parquet.d.ts.map +1 -1
- package/dist/lib/arrow/convert-schema-to-parquet.js +16 -7
- package/dist/lib/arrow/convert-schema-to-parquet.js.map +1 -1
- package/dist/lib/arrow/create-nested-arrow-vector.d.ts +8 -0
- package/dist/lib/arrow/create-nested-arrow-vector.d.ts.map +1 -0
- package/dist/lib/arrow/create-nested-arrow-vector.js +485 -0
- package/dist/lib/arrow/create-nested-arrow-vector.js.map +1 -0
- package/dist/lib/constants.d.ts +0 -1
- package/dist/lib/constants.d.ts.map +1 -1
- package/dist/lib/constants.js +1 -2
- package/dist/lib/constants.js.map +1 -1
- package/dist/lib/encoders/encode-arrow-to-parquet.d.ts +2 -2
- package/dist/lib/encoders/encode-arrow-to-parquet.d.ts.map +1 -1
- package/dist/lib/encoders/encode-arrow-to-parquet.js +3 -10
- package/dist/lib/encoders/encode-arrow-to-parquet.js.map +1 -1
- package/dist/lib/encoders/encode-table-to-parquet-js.d.ts +5 -0
- package/dist/lib/encoders/encode-table-to-parquet-js.d.ts.map +1 -0
- package/dist/lib/encoders/encode-table-to-parquet-js.js +394 -0
- package/dist/lib/encoders/encode-table-to-parquet-js.js.map +1 -0
- package/dist/lib/geo/geoparquet-covering.d.ts +19 -0
- package/dist/lib/geo/geoparquet-covering.d.ts.map +1 -0
- package/dist/lib/geo/geoparquet-covering.js +137 -0
- package/dist/lib/geo/geoparquet-covering.js.map +1 -0
- package/dist/lib/geo/geospatial-metadata.d.ts +67 -0
- package/dist/lib/geo/geospatial-metadata.d.ts.map +1 -0
- package/dist/lib/geo/geospatial-metadata.js +412 -0
- package/dist/lib/geo/geospatial-metadata.js.map +1 -0
- package/dist/lib/parquet-bloom-filter-planner.d.ts +16 -0
- package/dist/lib/parquet-bloom-filter-planner.d.ts.map +1 -0
- package/dist/lib/parquet-bloom-filter-planner.js +57 -0
- package/dist/lib/parquet-bloom-filter-planner.js.map +1 -0
- package/dist/lib/parquet-bloom-filter.d.ts +30 -0
- package/dist/lib/parquet-bloom-filter.d.ts.map +1 -0
- package/dist/lib/parquet-bloom-filter.js +289 -0
- package/dist/lib/parquet-bloom-filter.js.map +1 -0
- package/dist/lib/parquet-encryption.d.ts +80 -0
- package/dist/lib/parquet-encryption.d.ts.map +1 -0
- package/dist/lib/parquet-encryption.js +190 -0
- package/dist/lib/parquet-encryption.js.map +1 -0
- package/dist/lib/parquet-page-index.d.ts +91 -0
- package/dist/lib/parquet-page-index.d.ts.map +1 -0
- package/dist/lib/parquet-page-index.js +463 -0
- package/dist/lib/parquet-page-index.js.map +1 -0
- package/dist/lib/parquet-predicate.d.ts +21 -0
- package/dist/lib/parquet-predicate.d.ts.map +1 -0
- package/dist/lib/parquet-predicate.js +328 -0
- package/dist/lib/parquet-predicate.js.map +1 -0
- package/dist/lib/parquet-source-worker-client.d.ts +6 -0
- package/dist/lib/parquet-source-worker-client.d.ts.map +1 -0
- package/dist/lib/parquet-source-worker-client.js +24 -0
- package/dist/lib/parquet-source-worker-client.js.map +1 -0
- package/dist/lib/parquet-source-worker-decoder.d.ts +7 -0
- package/dist/lib/parquet-source-worker-decoder.d.ts.map +1 -0
- package/dist/lib/parquet-source-worker-decoder.js +181 -0
- package/dist/lib/parquet-source-worker-decoder.js.map +1 -0
- package/dist/lib/parquet-source-worker-file.d.ts +24 -0
- package/dist/lib/parquet-source-worker-file.d.ts.map +1 -0
- package/dist/lib/parquet-source-worker-file.js +40 -0
- package/dist/lib/parquet-source-worker-file.js.map +1 -0
- package/dist/lib/parquet-source-worker-types.d.ts +121 -0
- package/dist/lib/parquet-source-worker-types.d.ts.map +1 -0
- package/dist/lib/parquet-source-worker-types.js +5 -0
- package/dist/lib/parquet-source-worker-types.js.map +1 -0
- package/dist/lib/parquet-worker-transport.d.ts +8 -0
- package/dist/lib/parquet-worker-transport.d.ts.map +1 -0
- package/dist/lib/parquet-worker-transport.js +40 -0
- package/dist/lib/parquet-worker-transport.js.map +1 -0
- package/dist/lib/parsers/convert-parquet-tables.d.ts +16 -0
- package/dist/lib/parsers/convert-parquet-tables.d.ts.map +1 -0
- package/dist/lib/parsers/convert-parquet-tables.js +30 -0
- package/dist/lib/parsers/convert-parquet-tables.js.map +1 -0
- package/dist/lib/parsers/get-parquet-schema.d.ts.map +1 -1
- package/dist/lib/parsers/get-parquet-schema.js +6 -2
- package/dist/lib/parsers/get-parquet-schema.js.map +1 -1
- package/dist/lib/parsers/parse-geoparquet-to-geojson.d.ts +4 -4
- package/dist/lib/parsers/parse-geoparquet-to-geojson.d.ts.map +1 -1
- package/dist/lib/parsers/parse-geoparquet-to-geojson.js +19 -6
- package/dist/lib/parsers/parse-geoparquet-to-geojson.js.map +1 -1
- package/dist/lib/parsers/parse-parquet-tables.d.ts +37 -0
- package/dist/lib/parsers/parse-parquet-tables.d.ts.map +1 -0
- package/dist/lib/parsers/parse-parquet-tables.js +50 -0
- package/dist/lib/parsers/parse-parquet-tables.js.map +1 -0
- package/dist/lib/parsers/parse-parquet-to-arrow-js.d.ts +19 -0
- package/dist/lib/parsers/parse-parquet-to-arrow-js.d.ts.map +1 -0
- package/dist/lib/parsers/parse-parquet-to-arrow-js.js +921 -0
- package/dist/lib/parsers/parse-parquet-to-arrow-js.js.map +1 -0
- package/dist/lib/parsers/parse-parquet-to-arrow.d.ts +7 -7
- package/dist/lib/parsers/parse-parquet-to-arrow.d.ts.map +1 -1
- package/dist/lib/parsers/parse-parquet-to-arrow.js +45 -32
- package/dist/lib/parsers/parse-parquet-to-arrow.js.map +1 -1
- package/dist/lib/parsers/parse-parquet-to-columns.d.ts +3 -3
- package/dist/lib/parsers/parse-parquet-to-columns.d.ts.map +1 -1
- package/dist/lib/parsers/parse-parquet-to-columns.js +4 -5
- package/dist/lib/parsers/parse-parquet-to-columns.js.map +1 -1
- package/dist/lib/parsers/parse-parquet-to-json.d.ts +3 -3
- package/dist/lib/parsers/parse-parquet-to-json.d.ts.map +1 -1
- package/dist/lib/parsers/parse-parquet-to-json.js +95 -28
- package/dist/lib/parsers/parse-parquet-to-json.js.map +1 -1
- package/dist/lib/slice-parquet-batch.d.ts +9 -0
- package/dist/lib/slice-parquet-batch.d.ts.map +1 -0
- package/dist/lib/slice-parquet-batch.js +28 -0
- package/dist/lib/slice-parquet-batch.js.map +1 -0
- package/dist/lib/sources/parquet-range-file.d.ts +80 -0
- package/dist/lib/sources/parquet-range-file.d.ts.map +1 -0
- package/dist/lib/sources/parquet-range-file.js +267 -0
- package/dist/lib/sources/parquet-range-file.js.map +1 -0
- package/dist/lib/sources/single-batch-queue.d.ts +24 -0
- package/dist/lib/sources/single-batch-queue.d.ts.map +1 -0
- package/dist/lib/sources/single-batch-queue.js +91 -0
- package/dist/lib/sources/single-batch-queue.js.map +1 -0
- package/dist/lib/utils/load-wasm-node.d.ts +3 -0
- package/dist/lib/utils/load-wasm-node.d.ts.map +1 -0
- package/dist/lib/utils/load-wasm-node.js +23 -0
- package/dist/lib/utils/load-wasm-node.js.map +1 -0
- package/dist/lib/utils/load-wasm.d.ts +2 -2
- package/dist/lib/utils/load-wasm.d.ts.map +1 -1
- package/dist/lib/utils/load-wasm.js +28 -12
- package/dist/lib/utils/load-wasm.js.map +1 -1
- package/dist/lib/utils/make-stream-iterator.d.ts +2 -0
- package/dist/lib/utils/make-stream-iterator.d.ts.map +1 -1
- package/dist/lib/utils/make-stream-iterator.js +123 -14
- package/dist/lib/utils/make-stream-iterator.js.map +1 -1
- package/dist/lib/utils/normalize-parquet-options.d.ts +5 -0
- package/dist/lib/utils/normalize-parquet-options.d.ts.map +1 -0
- package/dist/lib/utils/normalize-parquet-options.js +25 -0
- package/dist/lib/utils/normalize-parquet-options.js.map +1 -0
- package/dist/parquet-dataset-source.cjs +38974 -0
- package/dist/parquet-dataset-source.cjs.map +6 -0
- package/dist/parquet-dataset-source.d.ts +81 -0
- package/dist/parquet-dataset-source.d.ts.map +1 -0
- package/dist/parquet-dataset-source.js +602 -0
- package/dist/parquet-dataset-source.js.map +1 -0
- package/dist/parquet-encoded-page-types.d.ts +108 -0
- package/dist/parquet-encoded-page-types.d.ts.map +1 -0
- package/dist/parquet-encoded-page-types.js +5 -0
- package/dist/parquet-encoded-page-types.js.map +1 -0
- package/dist/parquet-format.d.ts +2 -0
- package/dist/parquet-format.d.ts.map +1 -1
- package/dist/parquet-format.js +2 -0
- package/dist/parquet-format.js.map +1 -1
- package/dist/parquet-js-loader-types.d.ts +59 -0
- package/dist/parquet-js-loader-types.d.ts.map +1 -0
- package/dist/parquet-js-loader-types.js +34 -0
- package/dist/parquet-js-loader-types.js.map +1 -0
- package/dist/parquet-js-loader.d.ts +18 -22
- package/dist/parquet-js-loader.d.ts.map +1 -1
- package/dist/parquet-js-loader.js +53 -14
- package/dist/parquet-js-loader.js.map +1 -1
- package/dist/parquet-js-writer.d.ts +65 -0
- package/dist/parquet-js-writer.d.ts.map +1 -0
- package/dist/parquet-js-writer.js +28 -0
- package/dist/parquet-js-writer.js.map +1 -0
- package/dist/parquet-loader-base.d.ts +25 -0
- package/dist/parquet-loader-base.d.ts.map +1 -0
- package/dist/parquet-loader-base.js +23 -0
- package/dist/parquet-loader-base.js.map +1 -0
- package/dist/parquet-loader-options.d.ts +55 -0
- package/dist/parquet-loader-options.d.ts.map +1 -0
- package/dist/parquet-loader-options.js +10 -0
- package/dist/parquet-loader-options.js.map +1 -0
- package/dist/parquet-loader-types.d.ts +61 -0
- package/dist/parquet-loader-types.d.ts.map +1 -0
- package/dist/parquet-loader-types.js +17 -0
- package/dist/parquet-loader-types.js.map +1 -0
- package/dist/parquet-loader.d.ts +42 -0
- package/dist/parquet-loader.d.ts.map +1 -0
- package/dist/parquet-loader.js +68 -0
- package/dist/parquet-loader.js.map +1 -0
- package/dist/parquet-source-capabilities.d.ts +43 -0
- package/dist/parquet-source-capabilities.d.ts.map +1 -0
- package/dist/parquet-source-capabilities.js +32 -0
- package/dist/parquet-source-capabilities.js.map +1 -0
- package/dist/parquet-source-loader-types.d.ts +82 -0
- package/dist/parquet-source-loader-types.d.ts.map +1 -0
- package/dist/parquet-source-loader-types.js +84 -0
- package/dist/parquet-source-loader-types.js.map +1 -0
- package/dist/parquet-source-loader.cjs +38261 -0
- package/dist/parquet-source-loader.cjs.map +6 -0
- package/dist/parquet-source-loader.d.ts +167 -0
- package/dist/parquet-source-loader.d.ts.map +1 -0
- package/dist/parquet-source-loader.js +1438 -0
- package/dist/parquet-source-loader.js.map +1 -0
- package/dist/parquet-source-types.d.ts +534 -0
- package/dist/parquet-source-types.d.ts.map +1 -0
- package/dist/parquet-source-types.js +5 -0
- package/dist/parquet-source-types.js.map +1 -0
- package/dist/parquet-source-worker-factory.d.ts +4 -0
- package/dist/parquet-source-worker-factory.d.ts.map +1 -0
- package/dist/parquet-source-worker-factory.js +6 -0
- package/dist/parquet-source-worker-factory.js.map +1 -0
- package/dist/parquet-source-worker-url.d.ts +3 -0
- package/dist/parquet-source-worker-url.d.ts.map +1 -0
- package/dist/parquet-source-worker-url.js +22 -0
- package/dist/parquet-source-worker-url.js.map +1 -0
- package/dist/parquet-source-worker.js +38871 -0
- package/dist/parquet-source-worker.js.map +7 -0
- package/dist/parquet-worker-node.cjs +78507 -0
- package/dist/parquet-worker-node.cjs.map +7 -0
- package/dist/parquet-worker-url.d.ts +3 -0
- package/dist/parquet-worker-url.d.ts.map +1 -0
- package/dist/parquet-worker-url.js +19 -0
- package/dist/parquet-worker-url.js.map +1 -0
- package/dist/parquet-worker.js +20094 -0
- package/dist/parquet-worker.js.map +7 -0
- package/dist/parquet-writer.d.ts +10 -0
- package/dist/parquet-writer.d.ts.map +1 -0
- package/dist/parquet-writer.js +27 -0
- package/dist/parquet-writer.js.map +1 -0
- package/dist/parquet_wasm_bg.wasm +0 -0
- package/dist/parquetjs/codecs/byte-stream-split.d.ts +9 -0
- package/dist/parquetjs/codecs/byte-stream-split.d.ts.map +1 -0
- package/dist/parquetjs/codecs/byte-stream-split.js +159 -0
- package/dist/parquetjs/codecs/byte-stream-split.js.map +1 -0
- package/dist/parquetjs/codecs/declare.d.ts +35 -3
- package/dist/parquetjs/codecs/declare.d.ts.map +1 -1
- package/dist/parquetjs/codecs/declare.js +17 -1
- package/dist/parquetjs/codecs/declare.js.map +1 -1
- package/dist/parquetjs/codecs/delta.d.ts +17 -0
- package/dist/parquetjs/codecs/delta.d.ts.map +1 -0
- package/dist/parquetjs/codecs/delta.js +788 -0
- package/dist/parquetjs/codecs/delta.js.map +1 -0
- package/dist/parquetjs/codecs/dictionary.d.ts +5 -2
- package/dist/parquetjs/codecs/dictionary.d.ts.map +1 -1
- package/dist/parquetjs/codecs/dictionary.js +16 -4
- package/dist/parquetjs/codecs/dictionary.js.map +1 -1
- package/dist/parquetjs/codecs/index.d.ts.map +1 -1
- package/dist/parquetjs/codecs/index.js +22 -0
- package/dist/parquetjs/codecs/index.js.map +1 -1
- package/dist/parquetjs/codecs/plain.d.ts +3 -3
- package/dist/parquetjs/codecs/plain.d.ts.map +1 -1
- package/dist/parquetjs/codecs/plain.js +231 -78
- package/dist/parquetjs/codecs/plain.js.map +1 -1
- package/dist/parquetjs/codecs/rle.d.ts +7 -3
- package/dist/parquetjs/codecs/rle.d.ts.map +1 -1
- package/dist/parquetjs/codecs/rle.js +613 -69
- package/dist/parquetjs/codecs/rle.js.map +1 -1
- package/dist/parquetjs/compression.d.ts +16 -8
- package/dist/parquetjs/compression.d.ts.map +1 -1
- package/dist/parquetjs/compression.js +114 -141
- package/dist/parquetjs/compression.js.map +1 -1
- package/dist/parquetjs/encoder/dictionary-planner.d.ts +17 -0
- package/dist/parquetjs/encoder/dictionary-planner.d.ts.map +1 -0
- package/dist/parquetjs/encoder/dictionary-planner.js +67 -0
- package/dist/parquetjs/encoder/dictionary-planner.js.map +1 -0
- package/dist/parquetjs/encoder/page-planner.d.ts +11 -0
- package/dist/parquetjs/encoder/page-planner.d.ts.map +1 -0
- package/dist/parquetjs/encoder/page-planner.js +60 -0
- package/dist/parquetjs/encoder/page-planner.js.map +1 -0
- package/dist/parquetjs/encoder/parquet-encoder.d.ts +54 -5
- package/dist/parquetjs/encoder/parquet-encoder.d.ts.map +1 -1
- package/dist/parquetjs/encoder/parquet-encoder.js +930 -66
- package/dist/parquetjs/encoder/parquet-encoder.js.map +1 -1
- package/dist/parquetjs/parquet-thrift/BoundingBox.d.ts +29 -0
- package/dist/parquetjs/parquet-thrift/BoundingBox.d.ts.map +1 -0
- package/dist/parquetjs/parquet-thrift/BoundingBox.js +85 -0
- package/dist/parquetjs/parquet-thrift/BoundingBox.js.map +1 -0
- package/dist/parquetjs/parquet-thrift/BsonType.d.ts +1 -1
- package/dist/parquetjs/parquet-thrift/BsonType.d.ts.map +1 -1
- package/dist/parquetjs/parquet-thrift/BsonType.js +1 -1
- package/dist/parquetjs/parquet-thrift/BsonType.js.map +1 -1
- package/dist/parquetjs/parquet-thrift/ColumnChunk.d.ts +7 -2
- package/dist/parquetjs/parquet-thrift/ColumnChunk.d.ts.map +1 -1
- package/dist/parquetjs/parquet-thrift/ColumnChunk.js +37 -2
- package/dist/parquetjs/parquet-thrift/ColumnChunk.js.map +1 -1
- package/dist/parquetjs/parquet-thrift/ColumnCryptoMetaData.d.ts +35 -0
- package/dist/parquetjs/parquet-thrift/ColumnCryptoMetaData.d.ts.map +1 -0
- package/dist/parquetjs/parquet-thrift/ColumnCryptoMetaData.js +135 -0
- package/dist/parquetjs/parquet-thrift/ColumnCryptoMetaData.js.map +1 -0
- package/dist/parquetjs/parquet-thrift/ColumnIndex.d.ts +6 -6
- package/dist/parquetjs/parquet-thrift/ColumnIndex.d.ts.map +1 -1
- package/dist/parquetjs/parquet-thrift/ColumnIndex.js +3 -3
- package/dist/parquetjs/parquet-thrift/ColumnIndex.js.map +1 -1
- package/dist/parquetjs/parquet-thrift/ColumnMetaData.d.ts +12 -2
- package/dist/parquetjs/parquet-thrift/ColumnMetaData.d.ts.map +1 -1
- package/dist/parquetjs/parquet-thrift/ColumnMetaData.js +75 -2
- package/dist/parquetjs/parquet-thrift/ColumnMetaData.js.map +1 -1
- package/dist/parquetjs/parquet-thrift/ColumnOrder.d.ts +1 -1
- package/dist/parquetjs/parquet-thrift/ColumnOrder.d.ts.map +1 -1
- package/dist/parquetjs/parquet-thrift/ColumnOrder.js +1 -1
- package/dist/parquetjs/parquet-thrift/ColumnOrder.js.map +1 -1
- package/dist/parquetjs/parquet-thrift/DataPageHeader.d.ts +1 -1
- package/dist/parquetjs/parquet-thrift/DataPageHeader.d.ts.map +1 -1
- package/dist/parquetjs/parquet-thrift/DataPageHeader.js +1 -1
- package/dist/parquetjs/parquet-thrift/DataPageHeader.js.map +1 -1
- package/dist/parquetjs/parquet-thrift/DataPageHeaderV2.d.ts +1 -1
- package/dist/parquetjs/parquet-thrift/DataPageHeaderV2.d.ts.map +1 -1
- package/dist/parquetjs/parquet-thrift/DataPageHeaderV2.js +1 -1
- package/dist/parquetjs/parquet-thrift/DataPageHeaderV2.js.map +1 -1
- package/dist/parquetjs/parquet-thrift/DateType.d.ts +1 -1
- package/dist/parquetjs/parquet-thrift/DateType.d.ts.map +1 -1
- package/dist/parquetjs/parquet-thrift/DateType.js +1 -1
- package/dist/parquetjs/parquet-thrift/DateType.js.map +1 -1
- package/dist/parquetjs/parquet-thrift/DecimalType.d.ts +1 -1
- package/dist/parquetjs/parquet-thrift/DecimalType.d.ts.map +1 -1
- package/dist/parquetjs/parquet-thrift/DecimalType.js +1 -1
- package/dist/parquetjs/parquet-thrift/DecimalType.js.map +1 -1
- package/dist/parquetjs/parquet-thrift/DictionaryPageHeader.d.ts +1 -1
- package/dist/parquetjs/parquet-thrift/DictionaryPageHeader.d.ts.map +1 -1
- package/dist/parquetjs/parquet-thrift/DictionaryPageHeader.js +1 -1
- package/dist/parquetjs/parquet-thrift/DictionaryPageHeader.js.map +1 -1
- package/dist/parquetjs/parquet-thrift/EdgeInterpolationAlgorithm.d.ts +8 -0
- package/dist/parquetjs/parquet-thrift/EdgeInterpolationAlgorithm.d.ts.map +1 -0
- package/dist/parquetjs/parquet-thrift/EdgeInterpolationAlgorithm.js +14 -0
- package/dist/parquetjs/parquet-thrift/EdgeInterpolationAlgorithm.js.map +1 -0
- package/dist/parquetjs/parquet-thrift/Encoding.d.ts +2 -1
- package/dist/parquetjs/parquet-thrift/Encoding.d.ts.map +1 -1
- package/dist/parquetjs/parquet-thrift/Encoding.js +1 -0
- package/dist/parquetjs/parquet-thrift/Encoding.js.map +1 -1
- package/dist/parquetjs/parquet-thrift/EncryptionAlgorithm.d.ts +22 -0
- package/dist/parquetjs/parquet-thrift/EncryptionAlgorithm.d.ts.map +1 -0
- package/dist/parquetjs/parquet-thrift/EncryptionAlgorithm.js +111 -0
- package/dist/parquetjs/parquet-thrift/EncryptionAlgorithm.js.map +1 -0
- package/dist/parquetjs/parquet-thrift/EnumType.d.ts +1 -1
- package/dist/parquetjs/parquet-thrift/EnumType.d.ts.map +1 -1
- package/dist/parquetjs/parquet-thrift/EnumType.js +1 -1
- package/dist/parquetjs/parquet-thrift/EnumType.js.map +1 -1
- package/dist/parquetjs/parquet-thrift/FileCryptoMetaData.d.ts +16 -0
- package/dist/parquetjs/parquet-thrift/FileCryptoMetaData.d.ts.map +1 -0
- package/dist/parquetjs/parquet-thrift/FileCryptoMetaData.js +57 -0
- package/dist/parquetjs/parquet-thrift/FileCryptoMetaData.js.map +1 -0
- package/dist/parquetjs/parquet-thrift/FileMetaData.d.ts +7 -2
- package/dist/parquetjs/parquet-thrift/FileMetaData.d.ts.map +1 -1
- package/dist/parquetjs/parquet-thrift/FileMetaData.js +37 -2
- package/dist/parquetjs/parquet-thrift/FileMetaData.js.map +1 -1
- package/dist/parquetjs/parquet-thrift/Float16Type.d.ts +9 -0
- package/dist/parquetjs/parquet-thrift/Float16Type.d.ts.map +1 -0
- package/dist/parquetjs/parquet-thrift/Float16Type.js +27 -0
- package/dist/parquetjs/parquet-thrift/Float16Type.js.map +1 -0
- package/dist/parquetjs/parquet-thrift/GeographyType.d.ts +14 -0
- package/dist/parquetjs/parquet-thrift/GeographyType.d.ts.map +1 -0
- package/dist/parquetjs/parquet-thrift/GeographyType.js +51 -0
- package/dist/parquetjs/parquet-thrift/GeographyType.js.map +1 -0
- package/dist/parquetjs/parquet-thrift/GeometryType.d.ts +11 -0
- package/dist/parquetjs/parquet-thrift/GeometryType.d.ts.map +1 -0
- package/dist/parquetjs/parquet-thrift/GeometryType.js +41 -0
- package/dist/parquetjs/parquet-thrift/GeometryType.js.map +1 -0
- package/dist/parquetjs/parquet-thrift/GeospatialStatistics.d.ts +18 -0
- package/dist/parquetjs/parquet-thrift/GeospatialStatistics.d.ts.map +1 -0
- package/dist/parquetjs/parquet-thrift/GeospatialStatistics.js +62 -0
- package/dist/parquetjs/parquet-thrift/GeospatialStatistics.js.map +1 -0
- package/dist/parquetjs/parquet-thrift/IndexPageHeader.d.ts +1 -1
- package/dist/parquetjs/parquet-thrift/IndexPageHeader.d.ts.map +1 -1
- package/dist/parquetjs/parquet-thrift/IndexPageHeader.js +1 -1
- package/dist/parquetjs/parquet-thrift/IndexPageHeader.js.map +1 -1
- package/dist/parquetjs/parquet-thrift/IntType.d.ts +1 -1
- package/dist/parquetjs/parquet-thrift/IntType.d.ts.map +1 -1
- package/dist/parquetjs/parquet-thrift/IntType.js +1 -1
- package/dist/parquetjs/parquet-thrift/IntType.js.map +1 -1
- package/dist/parquetjs/parquet-thrift/JsonType.d.ts +1 -1
- package/dist/parquetjs/parquet-thrift/JsonType.d.ts.map +1 -1
- package/dist/parquetjs/parquet-thrift/JsonType.js +1 -1
- package/dist/parquetjs/parquet-thrift/JsonType.js.map +1 -1
- package/dist/parquetjs/parquet-thrift/KeyValue.d.ts +1 -1
- package/dist/parquetjs/parquet-thrift/KeyValue.d.ts.map +1 -1
- package/dist/parquetjs/parquet-thrift/KeyValue.js +1 -1
- package/dist/parquetjs/parquet-thrift/KeyValue.js.map +1 -1
- package/dist/parquetjs/parquet-thrift/ListType.d.ts +1 -1
- package/dist/parquetjs/parquet-thrift/ListType.d.ts.map +1 -1
- package/dist/parquetjs/parquet-thrift/ListType.js +1 -1
- package/dist/parquetjs/parquet-thrift/ListType.js.map +1 -1
- package/dist/parquetjs/parquet-thrift/LogicalType.d.ts +17 -1
- package/dist/parquetjs/parquet-thrift/LogicalType.d.ts.map +1 -1
- package/dist/parquetjs/parquet-thrift/LogicalType.js +97 -1
- package/dist/parquetjs/parquet-thrift/LogicalType.js.map +1 -1
- package/dist/parquetjs/parquet-thrift/MapType.d.ts +1 -1
- package/dist/parquetjs/parquet-thrift/MapType.d.ts.map +1 -1
- package/dist/parquetjs/parquet-thrift/MapType.js +1 -1
- package/dist/parquetjs/parquet-thrift/MapType.js.map +1 -1
- package/dist/parquetjs/parquet-thrift/MicroSeconds.d.ts +1 -1
- package/dist/parquetjs/parquet-thrift/MicroSeconds.d.ts.map +1 -1
- package/dist/parquetjs/parquet-thrift/MicroSeconds.js +1 -1
- package/dist/parquetjs/parquet-thrift/MicroSeconds.js.map +1 -1
- package/dist/parquetjs/parquet-thrift/MilliSeconds.d.ts +1 -1
- package/dist/parquetjs/parquet-thrift/MilliSeconds.d.ts.map +1 -1
- package/dist/parquetjs/parquet-thrift/MilliSeconds.js +1 -1
- package/dist/parquetjs/parquet-thrift/MilliSeconds.js.map +1 -1
- package/dist/parquetjs/parquet-thrift/NanoSeconds.d.ts +9 -0
- package/dist/parquetjs/parquet-thrift/NanoSeconds.d.ts.map +1 -0
- package/dist/parquetjs/parquet-thrift/NanoSeconds.js +27 -0
- package/dist/parquetjs/parquet-thrift/NanoSeconds.js.map +1 -0
- package/dist/parquetjs/parquet-thrift/NullType.d.ts +1 -1
- package/dist/parquetjs/parquet-thrift/NullType.d.ts.map +1 -1
- package/dist/parquetjs/parquet-thrift/NullType.js +1 -1
- package/dist/parquetjs/parquet-thrift/NullType.js.map +1 -1
- package/dist/parquetjs/parquet-thrift/OffsetIndex.d.ts +1 -1
- package/dist/parquetjs/parquet-thrift/OffsetIndex.d.ts.map +1 -1
- package/dist/parquetjs/parquet-thrift/OffsetIndex.js +1 -1
- package/dist/parquetjs/parquet-thrift/OffsetIndex.js.map +1 -1
- package/dist/parquetjs/parquet-thrift/PageEncodingStats.d.ts +1 -1
- package/dist/parquetjs/parquet-thrift/PageEncodingStats.d.ts.map +1 -1
- package/dist/parquetjs/parquet-thrift/PageEncodingStats.js +1 -1
- package/dist/parquetjs/parquet-thrift/PageEncodingStats.js.map +1 -1
- package/dist/parquetjs/parquet-thrift/PageHeader.d.ts +1 -1
- package/dist/parquetjs/parquet-thrift/PageHeader.d.ts.map +1 -1
- package/dist/parquetjs/parquet-thrift/PageHeader.js +1 -1
- package/dist/parquetjs/parquet-thrift/PageHeader.js.map +1 -1
- package/dist/parquetjs/parquet-thrift/PageLocation.d.ts +2 -2
- package/dist/parquetjs/parquet-thrift/PageLocation.d.ts.map +1 -1
- package/dist/parquetjs/parquet-thrift/PageLocation.js +2 -2
- package/dist/parquetjs/parquet-thrift/PageLocation.js.map +1 -1
- package/dist/parquetjs/parquet-thrift/RowGroup.d.ts +2 -2
- package/dist/parquetjs/parquet-thrift/RowGroup.d.ts.map +1 -1
- package/dist/parquetjs/parquet-thrift/RowGroup.js +2 -2
- package/dist/parquetjs/parquet-thrift/RowGroup.js.map +1 -1
- package/dist/parquetjs/parquet-thrift/SchemaElement.d.ts +1 -1
- package/dist/parquetjs/parquet-thrift/SchemaElement.d.ts.map +1 -1
- package/dist/parquetjs/parquet-thrift/SchemaElement.js +1 -1
- package/dist/parquetjs/parquet-thrift/SchemaElement.js.map +1 -1
- package/dist/parquetjs/parquet-thrift/SizeStatistics.d.ts +26 -0
- package/dist/parquetjs/parquet-thrift/SizeStatistics.d.ts.map +1 -0
- package/dist/parquetjs/parquet-thrift/SizeStatistics.js +85 -0
- package/dist/parquetjs/parquet-thrift/SizeStatistics.js.map +1 -0
- package/dist/parquetjs/parquet-thrift/SortingColumn.d.ts +1 -1
- package/dist/parquetjs/parquet-thrift/SortingColumn.d.ts.map +1 -1
- package/dist/parquetjs/parquet-thrift/SortingColumn.js +1 -1
- package/dist/parquetjs/parquet-thrift/SortingColumn.js.map +1 -1
- package/dist/parquetjs/parquet-thrift/Statistics.d.ts +14 -10
- package/dist/parquetjs/parquet-thrift/Statistics.d.ts.map +1 -1
- package/dist/parquetjs/parquet-thrift/Statistics.js +38 -2
- package/dist/parquetjs/parquet-thrift/Statistics.js.map +1 -1
- package/dist/parquetjs/parquet-thrift/StringType.d.ts +1 -1
- package/dist/parquetjs/parquet-thrift/StringType.d.ts.map +1 -1
- package/dist/parquetjs/parquet-thrift/StringType.js +1 -1
- package/dist/parquetjs/parquet-thrift/StringType.js.map +1 -1
- package/dist/parquetjs/parquet-thrift/TimeType.d.ts +1 -1
- package/dist/parquetjs/parquet-thrift/TimeType.d.ts.map +1 -1
- package/dist/parquetjs/parquet-thrift/TimeType.js +1 -1
- package/dist/parquetjs/parquet-thrift/TimeType.js.map +1 -1
- package/dist/parquetjs/parquet-thrift/TimeUnit.d.ts +5 -1
- package/dist/parquetjs/parquet-thrift/TimeUnit.d.ts.map +1 -1
- package/dist/parquetjs/parquet-thrift/TimeUnit.js +25 -1
- package/dist/parquetjs/parquet-thrift/TimeUnit.js.map +1 -1
- package/dist/parquetjs/parquet-thrift/TimestampType.d.ts +1 -1
- package/dist/parquetjs/parquet-thrift/TimestampType.d.ts.map +1 -1
- package/dist/parquetjs/parquet-thrift/TimestampType.js +1 -1
- package/dist/parquetjs/parquet-thrift/TimestampType.js.map +1 -1
- package/dist/parquetjs/parquet-thrift/TypeDefinedOrder.d.ts +1 -1
- package/dist/parquetjs/parquet-thrift/TypeDefinedOrder.d.ts.map +1 -1
- package/dist/parquetjs/parquet-thrift/TypeDefinedOrder.js +1 -1
- package/dist/parquetjs/parquet-thrift/TypeDefinedOrder.js.map +1 -1
- package/dist/parquetjs/parquet-thrift/UUIDType.d.ts +1 -1
- package/dist/parquetjs/parquet-thrift/UUIDType.d.ts.map +1 -1
- package/dist/parquetjs/parquet-thrift/UUIDType.js +1 -1
- package/dist/parquetjs/parquet-thrift/UUIDType.js.map +1 -1
- package/dist/parquetjs/parquet-thrift/VariantType.d.ts +11 -0
- package/dist/parquetjs/parquet-thrift/VariantType.d.ts.map +1 -0
- package/dist/parquetjs/parquet-thrift/VariantType.js +41 -0
- package/dist/parquetjs/parquet-thrift/VariantType.js.map +1 -0
- package/dist/parquetjs/parquet-thrift/index.d.ts +12 -2
- package/dist/parquetjs/parquet-thrift/index.d.ts.map +1 -1
- package/dist/parquetjs/parquet-thrift/index.js +12 -2
- package/dist/parquetjs/parquet-thrift/index.js.map +1 -1
- package/dist/parquetjs/parser/decoders.d.ts +23 -3
- package/dist/parquetjs/parser/decoders.d.ts.map +1 -1
- package/dist/parquetjs/parser/decoders.js +687 -119
- package/dist/parquetjs/parser/decoders.js.map +1 -1
- package/dist/parquetjs/parser/encoded-pages.d.ts +24 -0
- package/dist/parquetjs/parser/encoded-pages.d.ts.map +1 -0
- package/dist/parquetjs/parser/encoded-pages.js +206 -0
- package/dist/parquetjs/parser/encoded-pages.js.map +1 -0
- package/dist/parquetjs/parser/parquet-reader.d.ts +111 -10
- package/dist/parquetjs/parser/parquet-reader.d.ts.map +1 -1
- package/dist/parquetjs/parser/parquet-reader.js +836 -69
- package/dist/parquetjs/parser/parquet-reader.js.map +1 -1
- package/dist/parquetjs/schema/declare.d.ts +83 -10
- package/dist/parquetjs/schema/declare.d.ts.map +1 -1
- package/dist/parquetjs/schema/declare.js.map +1 -1
- package/dist/parquetjs/schema/schema.d.ts +3 -0
- package/dist/parquetjs/schema/schema.d.ts.map +1 -1
- package/dist/parquetjs/schema/schema.js +31 -3
- package/dist/parquetjs/schema/schema.js.map +1 -1
- package/dist/parquetjs/schema/shred.d.ts +2 -0
- package/dist/parquetjs/schema/shred.d.ts.map +1 -1
- package/dist/parquetjs/schema/shred.js +285 -29
- package/dist/parquetjs/schema/shred.js.map +1 -1
- package/dist/parquetjs/schema/types.d.ts.map +1 -1
- package/dist/parquetjs/schema/types.js +290 -71
- package/dist/parquetjs/schema/types.js.map +1 -1
- package/dist/parquetjs/schema/variant.d.ts +3 -0
- package/dist/parquetjs/schema/variant.d.ts.map +1 -0
- package/dist/parquetjs/schema/variant.js +248 -0
- package/dist/parquetjs/schema/variant.js.map +1 -0
- package/dist/parquetjs/utils/binary-utils.d.ts +41 -0
- package/dist/parquetjs/utils/binary-utils.d.ts.map +1 -0
- package/dist/parquetjs/utils/binary-utils.js +106 -0
- package/dist/parquetjs/utils/binary-utils.js.map +1 -0
- package/dist/parquetjs/utils/crc32.d.ts +3 -0
- package/dist/parquetjs/utils/crc32.d.ts.map +1 -0
- package/dist/parquetjs/utils/crc32.js +15 -0
- package/dist/parquetjs/utils/crc32.js.map +1 -0
- package/dist/parquetjs/utils/file-utils.d.ts +1 -1
- package/dist/parquetjs/utils/file-utils.d.ts.map +1 -1
- package/dist/parquetjs/utils/file-utils.js +3 -3
- package/dist/parquetjs/utils/file-utils.js.map +1 -1
- package/dist/parquetjs/utils/read-utils.d.ts +25 -7
- package/dist/parquetjs/utils/read-utils.d.ts.map +1 -1
- package/dist/parquetjs/utils/read-utils.js +66 -39
- package/dist/parquetjs/utils/read-utils.js.map +1 -1
- package/dist/parquetjs/utils/thrift-runtime.d.ts +106 -0
- package/dist/parquetjs/utils/thrift-runtime.d.ts.map +1 -0
- package/dist/parquetjs/utils/thrift-runtime.js +50 -0
- package/dist/parquetjs/utils/thrift-runtime.js.map +1 -0
- package/dist/parquetjs/utils/uint8-array-compact-protocol-writer.d.ts +78 -0
- package/dist/parquetjs/utils/uint8-array-compact-protocol-writer.d.ts.map +1 -0
- package/dist/parquetjs/utils/uint8-array-compact-protocol-writer.js +213 -0
- package/dist/parquetjs/utils/uint8-array-compact-protocol-writer.js.map +1 -0
- package/dist/parquetjs/utils/uint8-array-compact-protocol.d.ts +80 -0
- package/dist/parquetjs/utils/uint8-array-compact-protocol.d.ts.map +1 -0
- package/dist/parquetjs/utils/uint8-array-compact-protocol.js +276 -0
- package/dist/parquetjs/utils/uint8-array-compact-protocol.js.map +1 -0
- package/dist/parquetjs/utils/uint8-array-transport.d.ts +25 -0
- package/dist/parquetjs/utils/uint8-array-transport.d.ts.map +1 -0
- package/dist/parquetjs/utils/uint8-array-transport.js +62 -0
- package/dist/parquetjs/utils/uint8-array-transport.js.map +1 -0
- package/dist/polyfills/process.d.ts +12 -0
- package/dist/polyfills/process.d.ts.map +1 -0
- package/dist/polyfills/process.js +17 -0
- package/dist/polyfills/process.js.map +1 -0
- package/dist/unbundled.d.ts +10 -0
- package/dist/unbundled.d.ts.map +1 -0
- package/dist/unbundled.js +11 -0
- package/dist/unbundled.js.map +1 -0
- package/dist/wasm.d.ts +3 -0
- package/dist/wasm.d.ts.map +1 -0
- package/dist/wasm.js +6 -0
- package/dist/wasm.js.map +1 -0
- package/dist/workers/parquet-source-worker.d.ts +2 -0
- package/dist/workers/parquet-source-worker.d.ts.map +1 -0
- package/dist/workers/parquet-source-worker.js +17 -0
- package/dist/workers/parquet-source-worker.js.map +1 -0
- package/dist/workers/parquet-worker-node.d.ts +2 -0
- package/dist/workers/parquet-worker-node.d.ts.map +1 -0
- package/dist/workers/parquet-worker-node.js +5 -0
- package/dist/workers/parquet-worker-node.js.map +1 -0
- package/dist/workers/parquet-worker.d.ts +2 -0
- package/dist/workers/parquet-worker.d.ts.map +1 -0
- package/dist/workers/parquet-worker.js +27 -0
- package/dist/workers/parquet-worker.js.map +1 -0
- package/package.json +84 -40
- package/src/bundled.ts +43 -0
- package/src/delta-format.ts +12 -0
- package/src/delta-source-loader-types.ts +40 -0
- package/src/delta-source.ts +305 -0
- package/src/delta-types.ts +40 -0
- package/src/geoparquet-loader-with-parser.ts +95 -0
- package/src/geoparquet-loader.ts +54 -0
- package/src/iceberg-rest-catalog.ts +122 -0
- package/src/iceberg-table-source.ts +1037 -0
- package/src/iceberg-types.ts +165 -0
- package/src/index.ts +105 -26
- package/src/lib/arrow/convert-columns-to-row-group.ts +3 -0
- package/src/lib/arrow/convert-schema-from-parquet.ts +193 -32
- package/src/lib/arrow/convert-schema-to-parquet.ts +16 -7
- package/src/lib/arrow/create-nested-arrow-vector.ts +705 -0
- package/src/lib/constants.ts +0 -2
- package/src/lib/encoders/encode-arrow-to-parquet.ts +10 -16
- package/src/lib/encoders/encode-table-to-parquet-js.ts +526 -0
- package/src/lib/geo/geoparquet-covering.ts +201 -0
- package/src/lib/geo/geospatial-metadata.ts +547 -0
- package/src/lib/parquet-bloom-filter-planner.ts +86 -0
- package/src/lib/parquet-bloom-filter.ts +345 -0
- package/src/lib/parquet-encryption.ts +344 -0
- package/src/lib/parquet-page-index.ts +727 -0
- package/src/lib/parquet-predicate.ts +410 -0
- package/src/lib/parquet-source-worker-client.ts +41 -0
- package/src/lib/parquet-source-worker-decoder.ts +252 -0
- package/src/lib/parquet-source-worker-file.ts +56 -0
- package/src/lib/parquet-source-worker-types.ts +132 -0
- package/src/lib/parquet-worker-transport.ts +57 -0
- package/src/lib/parsers/convert-parquet-tables.ts +39 -0
- package/src/lib/parsers/get-parquet-schema.ts +6 -2
- package/src/lib/parsers/parse-geoparquet-to-geojson.ts +27 -14
- package/src/lib/parsers/parse-parquet-tables.ts +82 -0
- package/src/lib/parsers/parse-parquet-to-arrow-js.ts +1213 -0
- package/src/lib/parsers/parse-parquet-to-arrow.ts +62 -36
- package/src/lib/parsers/parse-parquet-to-columns.ts +9 -8
- package/src/lib/parsers/parse-parquet-to-json.ts +119 -35
- package/src/lib/slice-parquet-batch.ts +32 -0
- package/src/lib/sources/parquet-range-file.ts +365 -0
- package/src/lib/sources/single-batch-queue.ts +95 -0
- package/src/lib/utils/load-wasm-node.ts +25 -0
- package/src/lib/utils/load-wasm.ts +36 -13
- package/src/lib/utils/make-stream-iterator.ts +126 -14
- package/src/lib/utils/normalize-parquet-options.ts +30 -0
- package/src/parquet-dataset-source.ts +800 -0
- package/src/parquet-encoded-page-types.ts +122 -0
- package/src/parquet-format.ts +2 -0
- package/src/parquet-js-loader-types.ts +53 -0
- package/src/parquet-js-loader.ts +76 -19
- package/src/parquet-js-writer.ts +98 -0
- package/src/parquet-loader-base.ts +34 -0
- package/src/parquet-loader-options.ts +62 -0
- package/src/parquet-loader-types.ts +35 -0
- package/src/parquet-loader.ts +115 -0
- package/src/parquet-source-capabilities.ts +73 -0
- package/src/parquet-source-loader-types.ts +97 -0
- package/src/parquet-source-loader.ts +2254 -0
- package/src/parquet-source-types.ts +627 -0
- package/src/parquet-source-worker-factory.ts +8 -0
- package/src/parquet-source-worker-url.ts +23 -0
- package/src/parquet-worker-url.ts +23 -0
- package/src/parquet-writer.ts +42 -0
- package/src/parquetjs/LICENSE +23 -1
- package/src/parquetjs/codecs/byte-stream-split.ts +221 -0
- package/src/parquetjs/codecs/declare.ts +62 -3
- package/src/parquetjs/codecs/delta.ts +1047 -0
- package/src/parquetjs/codecs/dictionary.ts +22 -4
- package/src/parquetjs/codecs/index.ts +22 -0
- package/src/parquetjs/codecs/plain.ts +317 -89
- package/src/parquetjs/codecs/rle.ts +852 -82
- package/src/parquetjs/compression.ts +137 -156
- package/src/parquetjs/encoder/dictionary-planner.ts +104 -0
- package/src/parquetjs/encoder/page-planner.ts +83 -0
- package/src/parquetjs/encoder/parquet-encoder.ts +1374 -95
- package/src/parquetjs/parquet-thrift/BoundingBox.ts +108 -0
- package/src/parquetjs/parquet-thrift/BsonType.ts +1 -1
- package/src/parquetjs/parquet-thrift/ColumnChunk.ts +37 -2
- package/src/parquetjs/parquet-thrift/ColumnCryptoMetaData.ts +139 -0
- package/src/parquetjs/parquet-thrift/ColumnIndex.ts +13 -13
- package/src/parquetjs/parquet-thrift/ColumnMetaData.ts +75 -2
- package/src/parquetjs/parquet-thrift/ColumnOrder.ts +1 -1
- package/src/parquetjs/parquet-thrift/DataPageHeader.ts +1 -1
- package/src/parquetjs/parquet-thrift/DataPageHeaderV2.ts +1 -1
- package/src/parquetjs/parquet-thrift/DateType.ts +1 -1
- package/src/parquetjs/parquet-thrift/DecimalType.ts +1 -1
- package/src/parquetjs/parquet-thrift/DictionaryPageHeader.ts +1 -1
- package/src/parquetjs/parquet-thrift/EdgeInterpolationAlgorithm.ts +13 -0
- package/src/parquetjs/parquet-thrift/Encoding.ts +2 -1
- package/src/parquetjs/parquet-thrift/EncryptionAlgorithm.ts +127 -0
- package/src/parquetjs/parquet-thrift/EnumType.ts +1 -1
- package/src/parquetjs/parquet-thrift/FileCryptoMetaData.ts +60 -0
- package/src/parquetjs/parquet-thrift/FileMetaData.ts +37 -2
- package/src/parquetjs/parquet-thrift/Float16Type.ts +28 -0
- package/src/parquetjs/parquet-thrift/GeographyType.ts +54 -0
- package/src/parquetjs/parquet-thrift/GeometryType.ts +43 -0
- package/src/parquetjs/parquet-thrift/GeospatialStatistics.ts +68 -0
- package/src/parquetjs/parquet-thrift/IndexPageHeader.ts +1 -1
- package/src/parquetjs/parquet-thrift/IntType.ts +1 -1
- package/src/parquetjs/parquet-thrift/JsonType.ts +1 -1
- package/src/parquetjs/parquet-thrift/KeyValue.ts +1 -1
- package/src/parquetjs/parquet-thrift/ListType.ts +1 -1
- package/src/parquetjs/parquet-thrift/LogicalType.ts +97 -1
- package/src/parquetjs/parquet-thrift/MapType.ts +1 -1
- package/src/parquetjs/parquet-thrift/MicroSeconds.ts +1 -1
- package/src/parquetjs/parquet-thrift/MilliSeconds.ts +1 -1
- package/src/parquetjs/parquet-thrift/NanoSeconds.ts +28 -0
- package/src/parquetjs/parquet-thrift/NullType.ts +1 -1
- package/src/parquetjs/parquet-thrift/OffsetIndex.ts +1 -1
- package/src/parquetjs/parquet-thrift/PageEncodingStats.ts +1 -1
- package/src/parquetjs/parquet-thrift/PageHeader.ts +1 -1
- package/src/parquetjs/parquet-thrift/PageLocation.ts +2 -2
- package/src/parquetjs/parquet-thrift/RowGroup.ts +2 -2
- package/src/parquetjs/parquet-thrift/SchemaElement.ts +1 -1
- package/src/parquetjs/parquet-thrift/SizeStatistics.ts +98 -0
- package/src/parquetjs/parquet-thrift/SortingColumn.ts +1 -1
- package/src/parquetjs/parquet-thrift/Statistics.ts +50 -14
- package/src/parquetjs/parquet-thrift/StringType.ts +1 -1
- package/src/parquetjs/parquet-thrift/TimeType.ts +1 -1
- package/src/parquetjs/parquet-thrift/TimeUnit.ts +25 -1
- package/src/parquetjs/parquet-thrift/TimestampType.ts +1 -1
- package/src/parquetjs/parquet-thrift/TypeDefinedOrder.ts +1 -1
- package/src/parquetjs/parquet-thrift/UUIDType.ts +1 -1
- package/src/parquetjs/parquet-thrift/VariantType.ts +43 -0
- package/src/parquetjs/parquet-thrift/index.ts +12 -4
- package/src/parquetjs/parser/decoders.ts +922 -143
- package/src/parquetjs/parser/encoded-pages.ts +278 -0
- package/src/parquetjs/parser/parquet-reader.ts +1334 -83
- package/src/parquetjs/schema/declare.ts +121 -9
- package/src/parquetjs/schema/schema.ts +33 -3
- package/src/parquetjs/schema/shred.ts +345 -41
- package/src/parquetjs/schema/types.ts +308 -84
- package/src/parquetjs/schema/variant.ts +313 -0
- package/src/parquetjs/utils/binary-utils.ts +132 -0
- package/src/parquetjs/utils/crc32.ts +15 -0
- package/src/parquetjs/utils/file-utils.ts +4 -4
- package/src/parquetjs/utils/read-utils.ts +77 -51
- package/src/parquetjs/utils/thrift-runtime.ts +109 -0
- package/src/parquetjs/utils/uint8-array-compact-protocol-writer.ts +254 -0
- package/src/parquetjs/utils/uint8-array-compact-protocol.ts +322 -0
- package/src/parquetjs/utils/uint8-array-transport.ts +79 -0
- package/src/polyfills/process.ts +17 -0
- package/src/unbundled.ts +47 -0
- package/src/wasm.ts +6 -0
- package/src/workers/parquet-source-worker.ts +21 -0
- package/src/workers/parquet-worker-node.ts +5 -0
- package/src/workers/parquet-worker.ts +31 -0
- package/dist/parquet-arrow-loader.d.ts +0 -43
- package/dist/parquet-arrow-loader.d.ts.map +0 -1
- package/dist/parquet-arrow-loader.js +0 -49
- package/dist/parquet-arrow-loader.js.map +0 -1
- package/dist/parquet-arrow-writer.d.ts +0 -9
- package/dist/parquet-arrow-writer.d.ts.map +0 -1
- package/dist/parquet-arrow-writer.js +0 -23
- package/dist/parquet-arrow-writer.js.map +0 -1
- package/dist/parquet-json-loader.d.ts +0 -148
- package/dist/parquet-json-loader.d.ts.map +0 -1
- package/dist/parquet-json-loader.js +0 -106
- package/dist/parquet-json-loader.js.map +0 -1
- package/dist/parquet-json-writer.d.ts +0 -19
- package/dist/parquet-json-writer.d.ts.map +0 -1
- package/dist/parquet-json-writer.js +0 -20
- package/dist/parquet-json-writer.js.map +0 -1
- package/dist/polyfills/buffer/buffer-polyfill.browser.d.ts +0 -3
- package/dist/polyfills/buffer/buffer-polyfill.browser.d.ts.map +0 -1
- package/dist/polyfills/buffer/buffer-polyfill.browser.js +0 -12
- package/dist/polyfills/buffer/buffer-polyfill.browser.js.map +0 -1
- package/dist/polyfills/buffer/buffer-polyfill.node.d.ts +0 -3
- package/dist/polyfills/buffer/buffer-polyfill.node.d.ts.map +0 -1
- package/dist/polyfills/buffer/buffer-polyfill.node.js +0 -17
- package/dist/polyfills/buffer/buffer-polyfill.node.js.map +0 -1
- package/dist/polyfills/buffer/buffer.d.ts +0 -222
- package/dist/polyfills/buffer/buffer.d.ts.map +0 -1
- package/dist/polyfills/buffer/buffer.js +0 -1868
- package/dist/polyfills/buffer/buffer.js.map +0 -1
- package/dist/polyfills/buffer/index.d.ts +0 -4
- package/dist/polyfills/buffer/index.d.ts.map +0 -1
- package/dist/polyfills/buffer/index.js +0 -9
- package/dist/polyfills/buffer/index.js.map +0 -1
- package/dist/polyfills/buffer/install-buffer-polyfill.d.ts +0 -2
- package/dist/polyfills/buffer/install-buffer-polyfill.d.ts.map +0 -1
- package/dist/polyfills/buffer/install-buffer-polyfill.js +0 -10
- package/dist/polyfills/buffer/install-buffer-polyfill.js.map +0 -1
- package/dist/workers/parquet-json-worker.d.ts +0 -2
- package/dist/workers/parquet-json-worker.d.ts.map +0 -1
- package/dist/workers/parquet-json-worker.js +0 -7
- package/dist/workers/parquet-json-worker.js.map +0 -1
- package/src/parquet-arrow-loader.ts +0 -74
- package/src/parquet-arrow-writer.ts +0 -33
- package/src/parquet-json-loader.ts +0 -160
- package/src/parquet-json-writer.ts +0 -27
- package/src/parquetjs/modules.d.ts +0 -25
- package/src/polyfills/buffer/buffer-polyfill.browser.ts +0 -14
- package/src/polyfills/buffer/buffer-polyfill.node.ts +0 -19
- package/src/polyfills/buffer/buffer.ts +0 -2205
- package/src/polyfills/buffer/index.ts +0 -11
- package/src/polyfills/buffer/install-buffer-polyfill.ts +0 -12
- package/src/workers/parquet-json-worker.ts +0 -8
|
@@ -0,0 +1,27 @@
|
|
|
1
|
+
// loaders.gl
|
|
2
|
+
// SPDX-License-Identifier: MIT
|
|
3
|
+
// Copyright (c) vis.gl contributors
|
|
4
|
+
import { createLoaderWorker } from '@loaders.gl/loader-utils';
|
|
5
|
+
import { ParquetLoaderWithParser } from "../parquet-loader.js";
|
|
6
|
+
/** Worker-local Parquet loader with a package-relative default WASM URL. */
|
|
7
|
+
const ParquetWorkerLoader = {
|
|
8
|
+
...ParquetLoaderWithParser,
|
|
9
|
+
parse(arrayBuffer, options) {
|
|
10
|
+
return ParquetLoaderWithParser.parse(arrayBuffer, addWorkerWasmUrl(options));
|
|
11
|
+
}
|
|
12
|
+
};
|
|
13
|
+
/** Adds the package-local WASM asset URL when the caller did not provide one. */
|
|
14
|
+
function addWorkerWasmUrl(options) {
|
|
15
|
+
if (options?.parquet?.wasmUrl || typeof globalThis.location?.href !== 'string') {
|
|
16
|
+
return options;
|
|
17
|
+
}
|
|
18
|
+
return {
|
|
19
|
+
...options,
|
|
20
|
+
parquet: {
|
|
21
|
+
...options?.parquet,
|
|
22
|
+
wasmUrl: new URL('parquet_wasm_bg.wasm', globalThis.location.href).toString()
|
|
23
|
+
}
|
|
24
|
+
};
|
|
25
|
+
}
|
|
26
|
+
createLoaderWorker(ParquetWorkerLoader);
|
|
27
|
+
//# sourceMappingURL=parquet-worker.js.map
|
|
@@ -0,0 +1 @@
|
|
|
1
|
+
{"version":3,"file":"parquet-worker.js","sourceRoot":"","sources":["../../src/workers/parquet-worker.ts"],"names":[],"mappings":"AAAA,aAAa;AACb,+BAA+B;AAC/B,oCAAoC;AAEpC,OAAO,EAAC,kBAAkB,EAAC,MAAM,0BAA0B,CAAC;AAE5D,OAAO,EAAC,uBAAuB,EAAC,6BAA0B;AAE1D,4EAA4E;AAC5E,MAAM,mBAAmB,GAAG;IAC1B,GAAG,uBAAuB;IAC1B,KAAK,CAAC,WAAwB,EAAE,OAA8B;QAC5D,OAAO,uBAAuB,CAAC,KAAK,CAAC,WAAW,EAAE,gBAAgB,CAAC,OAAO,CAAC,CAAC,CAAC;IAC/E,CAAC;CACF,CAAC;AAEF,iFAAiF;AACjF,SAAS,gBAAgB,CAAC,OAA8B;IACtD,IAAI,OAAO,EAAE,OAAO,EAAE,OAAO,IAAI,OAAO,UAAU,CAAC,QAAQ,EAAE,IAAI,KAAK,QAAQ,EAAE,CAAC;QAC/E,OAAO,OAAO,CAAC;IACjB,CAAC;IACD,OAAO;QACL,GAAG,OAAO;QACV,OAAO,EAAE;YACP,GAAG,OAAO,EAAE,OAAO;YACnB,OAAO,EAAE,IAAI,GAAG,CAAC,sBAAsB,EAAE,UAAU,CAAC,QAAQ,CAAC,IAAI,CAAC,CAAC,QAAQ,EAAE;SAC9E;KACF,CAAC;AACJ,CAAC;AAED,kBAAkB,CAAC,mBAAmB,CAAC,CAAC"}
|
package/package.json
CHANGED
|
@@ -1,6 +1,6 @@
|
|
|
1
1
|
{
|
|
2
2
|
"name": "@loaders.gl/parquet",
|
|
3
|
-
"version": "
|
|
3
|
+
"version": "5.0.0-alpha.10",
|
|
4
4
|
"description": "Framework-independent loader for Apache Parquet files",
|
|
5
5
|
"license": "MIT",
|
|
6
6
|
"type": "module",
|
|
@@ -31,13 +31,71 @@
|
|
|
31
31
|
"import": "./dist/index.js",
|
|
32
32
|
"require": "./dist/index.cjs"
|
|
33
33
|
},
|
|
34
|
-
"./
|
|
35
|
-
"
|
|
34
|
+
"./unbundled": {
|
|
35
|
+
"types": "./dist/unbundled.d.ts",
|
|
36
|
+
"import": "./dist/unbundled.js"
|
|
37
|
+
},
|
|
38
|
+
"./bundled": {
|
|
39
|
+
"types": "./dist/bundled.d.ts",
|
|
40
|
+
"import": "./dist/bundled.js"
|
|
41
|
+
},
|
|
42
|
+
"./parquet-loader": {
|
|
43
|
+
"types": "./dist/parquet-loader.d.ts",
|
|
44
|
+
"import": "./dist/parquet-loader.js"
|
|
45
|
+
},
|
|
46
|
+
"./iceberg-table-source": {
|
|
47
|
+
"types": "./dist/iceberg-table-source.d.ts",
|
|
48
|
+
"import": "./dist/iceberg-table-source.js"
|
|
49
|
+
},
|
|
50
|
+
"./iceberg-types": {
|
|
51
|
+
"types": "./dist/iceberg-types.d.ts",
|
|
52
|
+
"import": "./dist/iceberg-types.js"
|
|
53
|
+
},
|
|
54
|
+
"./iceberg-rest-catalog": {
|
|
55
|
+
"types": "./dist/iceberg-rest-catalog.d.ts",
|
|
56
|
+
"import": "./dist/iceberg-rest-catalog.js"
|
|
57
|
+
},
|
|
58
|
+
"./delta-source": {
|
|
59
|
+
"types": "./dist/delta-source.d.ts",
|
|
60
|
+
"import": "./dist/delta-source.js"
|
|
61
|
+
},
|
|
62
|
+
"./delta-source-loader-types": {
|
|
63
|
+
"types": "./dist/delta-source-loader-types.d.ts",
|
|
64
|
+
"import": "./dist/delta-source-loader-types.js"
|
|
65
|
+
},
|
|
66
|
+
"./delta-types": {
|
|
67
|
+
"types": "./dist/delta-types.d.ts",
|
|
68
|
+
"import": "./dist/delta-types.js"
|
|
36
69
|
},
|
|
37
70
|
"./parquet-js-loader": {
|
|
38
71
|
"types": "./dist/parquet-js-loader.d.ts",
|
|
39
72
|
"import": "./dist/parquet-js-loader.js"
|
|
40
|
-
}
|
|
73
|
+
},
|
|
74
|
+
"./parquet-source-loader": {
|
|
75
|
+
"types": "./dist/parquet-source-loader.d.ts",
|
|
76
|
+
"import": "./dist/parquet-source-loader.js",
|
|
77
|
+
"require": "./dist/parquet-source-loader.cjs"
|
|
78
|
+
},
|
|
79
|
+
"./parquet-dataset-source": {
|
|
80
|
+
"types": "./dist/parquet-dataset-source.d.ts",
|
|
81
|
+
"import": "./dist/parquet-dataset-source.js",
|
|
82
|
+
"require": "./dist/parquet-dataset-source.cjs"
|
|
83
|
+
},
|
|
84
|
+
"./parquet-worker.js": {
|
|
85
|
+
"import": "./dist/parquet-worker.js"
|
|
86
|
+
},
|
|
87
|
+
"./parquet-worker-node.cjs": {
|
|
88
|
+
"import": "./dist/parquet-worker-node.cjs",
|
|
89
|
+
"require": "./dist/parquet-worker-node.cjs"
|
|
90
|
+
},
|
|
91
|
+
"./parquet-source-worker.js": {
|
|
92
|
+
"import": "./dist/parquet-source-worker.js"
|
|
93
|
+
},
|
|
94
|
+
"./wasm": {
|
|
95
|
+
"types": "./dist/wasm.d.ts",
|
|
96
|
+
"import": "./dist/wasm.js"
|
|
97
|
+
},
|
|
98
|
+
"./parquet_wasm_bg.wasm": "./dist/parquet_wasm_bg.wasm"
|
|
41
99
|
},
|
|
42
100
|
"sideEffects": false,
|
|
43
101
|
"files": [
|
|
@@ -46,15 +104,15 @@
|
|
|
46
104
|
"README.md"
|
|
47
105
|
],
|
|
48
106
|
"scripts": {
|
|
49
|
-
"pre-build": "
|
|
107
|
+
"pre-build": "npm run copy-wasm && npm run build-worker && npm run build-worker-node && npm run build-source-worker",
|
|
50
108
|
"build-bundle": "ocular-bundle ./bundle.ts --output=dist/dist.min.js",
|
|
51
109
|
"build-bundle-dev": "ocular-bundle ./bundle.ts --env=dev --output=dist/dist.dev.js",
|
|
52
|
-
"
|
|
53
|
-
"
|
|
110
|
+
"copy-wasm": "cp ../../node_modules/parquet-wasm/esm/parquet_wasm_bg.wasm dist/parquet_wasm_bg.wasm",
|
|
111
|
+
"build-worker": "esbuild src/workers/parquet-worker.ts --outfile=dist/parquet-worker.js --target=esnext --platform=browser --bundle --sourcemap --inject:src/polyfills/process.ts --banner:js=var\\ global=globalThis\\; --define:__VERSION__=\\\"$npm_package_version\\\"",
|
|
112
|
+
"build-worker-node": "esbuild src/workers/parquet-worker.ts --outfile=dist/parquet-worker-node.cjs --platform=node --target=node16 --bundle --sourcemap --tree-shaking=false --define:__VERSION__=\\\"$npm_package_version\\\"",
|
|
113
|
+
"build-source-worker": "esbuild src/workers/parquet-source-worker.ts --outfile=dist/parquet-source-worker.js --target=esnext --platform=browser --bundle --sourcemap --inject:src/polyfills/process.ts --banner:js=var\\ global=globalThis\\; --define:__VERSION__=\\\"$npm_package_version\\\""
|
|
54
114
|
},
|
|
55
115
|
"browser": {
|
|
56
|
-
"./dist/polyfills/buffer/buffer-polyfill.node.js": "./dist/polyfills/buffer/buffer-polyfill.browser.js",
|
|
57
|
-
"./src/polyfills/buffer/buffer-polyfill.node.ts": "./src/polyfills/buffer/buffer-polyfill.browser.ts",
|
|
58
116
|
"child_process": false,
|
|
59
117
|
"events": false,
|
|
60
118
|
"fs": false,
|
|
@@ -63,43 +121,29 @@
|
|
|
63
121
|
"tls": false,
|
|
64
122
|
"util": false
|
|
65
123
|
},
|
|
66
|
-
"comments": [
|
|
67
|
-
"base64-js and ieee754 are used by buffer polyfill"
|
|
68
|
-
],
|
|
69
124
|
"dependencies": {
|
|
70
|
-
"@loaders.gl/arrow": "
|
|
71
|
-
"@loaders.gl/
|
|
72
|
-
"@loaders.gl/
|
|
73
|
-
"@loaders.gl/
|
|
74
|
-
"@loaders.gl/
|
|
75
|
-
"@loaders.gl/
|
|
76
|
-
"@loaders.gl/
|
|
77
|
-
"@loaders.gl/
|
|
125
|
+
"@loaders.gl/arrow": "5.0.0-alpha.10",
|
|
126
|
+
"@loaders.gl/avro": "5.0.0-alpha.10",
|
|
127
|
+
"@loaders.gl/bson": "5.0.0-alpha.10",
|
|
128
|
+
"@loaders.gl/compression": "5.0.0-alpha.10",
|
|
129
|
+
"@loaders.gl/geoarrow": "5.0.0-alpha.10",
|
|
130
|
+
"@loaders.gl/gis": "5.0.0-alpha.10",
|
|
131
|
+
"@loaders.gl/loader-utils": "5.0.0-alpha.10",
|
|
132
|
+
"@loaders.gl/schema": "5.0.0-alpha.10",
|
|
133
|
+
"@loaders.gl/schema-utils": "5.0.0-alpha.10",
|
|
134
|
+
"@loaders.gl/wkt": "5.0.0-alpha.10",
|
|
78
135
|
"@probe.gl/log": "^4.1.1",
|
|
79
|
-
"
|
|
80
|
-
"base64-js": "^1.3.1",
|
|
81
|
-
"brotli": "^1.3.2",
|
|
82
|
-
"ieee754": "^1.2.1",
|
|
83
|
-
"int53": "^0.2.4",
|
|
84
|
-
"isomorphic-ws": "^5.0.0",
|
|
85
|
-
"lz4js": "^0.2.0",
|
|
86
|
-
"node-int64": "^0.4.0",
|
|
87
|
-
"object-stream": "0.0.1",
|
|
88
|
-
"parquet-wasm": "^0.6.1",
|
|
89
|
-
"snappyjs": "^0.6.0",
|
|
90
|
-
"thrift": "^0.19.0",
|
|
91
|
-
"util": "^0.12.5",
|
|
92
|
-
"varint": "^6.0.0",
|
|
93
|
-
"zstd-codec": "^0.1"
|
|
136
|
+
"parquet-wasm": "0.7.2"
|
|
94
137
|
},
|
|
95
138
|
"devDependencies": {
|
|
96
|
-
"
|
|
97
|
-
"
|
|
98
|
-
"
|
|
139
|
+
"brotli": "^1.3.2",
|
|
140
|
+
"hyparquet": "1.29.0",
|
|
141
|
+
"hyparquet-compressors": "1.1.1",
|
|
142
|
+
"zstd-codec": "^0.1"
|
|
99
143
|
},
|
|
100
144
|
"peerDependencies": {
|
|
101
|
-
"@loaders.gl/core": "~
|
|
145
|
+
"@loaders.gl/core": "~5.0.0-alpha.0",
|
|
102
146
|
"apache-arrow": ">= 17.0.0"
|
|
103
147
|
},
|
|
104
|
-
"gitHead": "
|
|
148
|
+
"gitHead": "7cbfaef633e86356c946541dab4977b522745b6c"
|
|
105
149
|
}
|
package/src/bundled.ts
ADDED
|
@@ -0,0 +1,43 @@
|
|
|
1
|
+
// loaders.gl
|
|
2
|
+
// SPDX-License-Identifier: MIT
|
|
3
|
+
// Copyright (c) vis.gl contributors
|
|
4
|
+
|
|
5
|
+
export type {ParquetLoaderOptions} from './parquet-loader-types';
|
|
6
|
+
export type {GeoParquetLoaderOptions} from './geoparquet-loader';
|
|
7
|
+
export {ParquetLoaderWithParser as ParquetLoader} from './parquet-loader';
|
|
8
|
+
export {GeoParquetLoaderWithParser as GeoParquetLoader} from './geoparquet-loader-with-parser';
|
|
9
|
+
export {ParquetJSLoaderWithParser as ParquetJSLoader} from './parquet-js-loader';
|
|
10
|
+
export {
|
|
11
|
+
ParquetSourceLoader,
|
|
12
|
+
ParquetSource,
|
|
13
|
+
type ParquetDeferredPageFilter,
|
|
14
|
+
type ParquetEncodedColumnChunk,
|
|
15
|
+
type ParquetEncodedPage,
|
|
16
|
+
type ParquetEncodedPageBatch,
|
|
17
|
+
type ParquetEncodedPageReadOptions,
|
|
18
|
+
type ParquetEncodedPageSection,
|
|
19
|
+
type ParquetPageCompressionState,
|
|
20
|
+
type ParquetSourceLoaderOptions,
|
|
21
|
+
type ParquetSourceReadOptions,
|
|
22
|
+
type ParquetSourceMetadata,
|
|
23
|
+
type ParquetRowGroupMetadata,
|
|
24
|
+
type ParquetSortingColumn,
|
|
25
|
+
type ParquetColumnChunkMetadata,
|
|
26
|
+
type ParquetGeospatialBoundingBox,
|
|
27
|
+
type ParquetGeospatialStatistics,
|
|
28
|
+
type ParquetBatchMetadata,
|
|
29
|
+
type ParquetSourceBatch
|
|
30
|
+
} from './parquet-source-loader';
|
|
31
|
+
export {
|
|
32
|
+
ParquetDatasetSource,
|
|
33
|
+
type ParquetDatasetBatch,
|
|
34
|
+
type ParquetDatasetFile,
|
|
35
|
+
type ParquetDatasetFileProvider,
|
|
36
|
+
type ParquetDatasetReadOptions,
|
|
37
|
+
type ParquetDatasetSourceOptions,
|
|
38
|
+
type ParquetDatasetTelemetry
|
|
39
|
+
} from './parquet-dataset-source';
|
|
40
|
+
export {
|
|
41
|
+
PARQUET_SOURCE_CAPABILITIES,
|
|
42
|
+
type ParquetSourceCapabilities
|
|
43
|
+
} from './parquet-source-capabilities';
|
|
@@ -0,0 +1,12 @@
|
|
|
1
|
+
// loaders.gl
|
|
2
|
+
// SPDX-License-Identifier: MIT
|
|
3
|
+
// Copyright (c) vis.gl contributors
|
|
4
|
+
|
|
5
|
+
/** Metadata describing the Delta Lake transaction-log format. */
|
|
6
|
+
export const DeltaFormat = {
|
|
7
|
+
name: 'Delta Lake',
|
|
8
|
+
id: 'delta',
|
|
9
|
+
module: 'parquet',
|
|
10
|
+
extensions: ['json', 'checkpoint.parquet'],
|
|
11
|
+
mimeTypes: ['application/json']
|
|
12
|
+
};
|
|
@@ -0,0 +1,40 @@
|
|
|
1
|
+
// loaders.gl
|
|
2
|
+
// SPDX-License-Identifier: MIT
|
|
3
|
+
// Copyright (c) vis.gl contributors
|
|
4
|
+
|
|
5
|
+
import type {SourceLoader} from '@loaders.gl/loader-utils';
|
|
6
|
+
import {DeltaFormat} from './delta-format';
|
|
7
|
+
import type {DeltaSourceOptions} from './delta-types';
|
|
8
|
+
import type {DeltaTableSource} from './delta-source';
|
|
9
|
+
|
|
10
|
+
// __VERSION__ is injected by babel-plugin-version-inline
|
|
11
|
+
// @ts-ignore TS2304: Cannot find name '__VERSION__'.
|
|
12
|
+
const VERSION = typeof __VERSION__ !== 'undefined' ? __VERSION__ : 'latest';
|
|
13
|
+
|
|
14
|
+
/** Metadata-only Delta source loader options. */
|
|
15
|
+
export type DeltaSourceLoaderOptions = DeltaSourceOptions;
|
|
16
|
+
|
|
17
|
+
/** Loads the parser-bearing Delta source implementation on demand. */
|
|
18
|
+
async function preloadDeltaSourceLoader(): Promise<SourceLoader<DeltaTableSource>> {
|
|
19
|
+
const {DeltaSourceLoaderWithParser} = await import('@loaders.gl/parquet/delta-source');
|
|
20
|
+
return DeltaSourceLoaderWithParser;
|
|
21
|
+
}
|
|
22
|
+
|
|
23
|
+
/** Metadata-only Delta source loader; runtime code is available through `preload()`. */
|
|
24
|
+
export const DeltaSourceLoader = {
|
|
25
|
+
...DeltaFormat,
|
|
26
|
+
dataType: null as unknown as DeltaTableSource,
|
|
27
|
+
batchType: null as never,
|
|
28
|
+
name: 'DeltaSourceLoader',
|
|
29
|
+
version: VERSION,
|
|
30
|
+
type: 'delta',
|
|
31
|
+
fromUrl: true,
|
|
32
|
+
fromBlob: true,
|
|
33
|
+
options: {},
|
|
34
|
+
defaultOptions: {},
|
|
35
|
+
testURL: (url: string): boolean =>
|
|
36
|
+
/\/_delta_log\/(?:\d{20}\.json|_last_checkpoint)(?:$|[?#])/i.test(url),
|
|
37
|
+
preload: preloadDeltaSourceLoader
|
|
38
|
+
} as const satisfies Omit<SourceLoader<DeltaTableSource>, 'createDataSource'> & {
|
|
39
|
+
preload: () => Promise<SourceLoader<DeltaTableSource>>;
|
|
40
|
+
};
|
|
@@ -0,0 +1,305 @@
|
|
|
1
|
+
// loaders.gl
|
|
2
|
+
// SPDX-License-Identifier: MIT
|
|
3
|
+
// Copyright (c) vis.gl contributors
|
|
4
|
+
|
|
5
|
+
import type {
|
|
6
|
+
ScanFragment,
|
|
7
|
+
ScanFragmentProvider,
|
|
8
|
+
ScanQueryMetadata,
|
|
9
|
+
ScanQueryMetadataOptions,
|
|
10
|
+
TableScanSource,
|
|
11
|
+
SourceLoader
|
|
12
|
+
} from '@loaders.gl/loader-utils';
|
|
13
|
+
import {createScanQueryMetadata, DataSource} from '@loaders.gl/loader-utils';
|
|
14
|
+
import {ParquetDatasetSource} from './parquet-dataset-source';
|
|
15
|
+
import {PARQUET_TABLE_QUERY_CAPABILITIES} from './parquet-source-capabilities';
|
|
16
|
+
import type {DeltaAction, DeltaScanOptions, DeltaSourceOptions} from './delta-types';
|
|
17
|
+
import type {
|
|
18
|
+
ParquetDatasetBatch,
|
|
19
|
+
ParquetDatasetExplain,
|
|
20
|
+
ParquetPredicate
|
|
21
|
+
} from './parquet-source-types';
|
|
22
|
+
import {DeltaFormat} from './delta-format';
|
|
23
|
+
|
|
24
|
+
// __VERSION__ is injected by babel-plugin-version-inline
|
|
25
|
+
// @ts-ignore TS2304: Cannot find name '__VERSION__'.
|
|
26
|
+
const VERSION = typeof __VERSION__ !== 'undefined' ? __VERSION__ : 'latest';
|
|
27
|
+
|
|
28
|
+
/** Lightweight Delta Lake snapshot source backed by a newline-delimited commit log. */
|
|
29
|
+
export class DeltaTableSource
|
|
30
|
+
extends DataSource<string | Blob, DeltaSourceOptions>
|
|
31
|
+
implements
|
|
32
|
+
TableScanSource<ParquetDatasetBatch, ParquetPredicate>,
|
|
33
|
+
ScanFragmentProvider<ParquetPredicate>
|
|
34
|
+
{
|
|
35
|
+
private readonly actionsPromises = new Map<string, Promise<readonly DeltaAction[]>>();
|
|
36
|
+
|
|
37
|
+
/** Creates a source from a Delta commit JSON URL or Blob. */
|
|
38
|
+
constructor(data: string | Blob, options: DeltaSourceOptions = {}) {
|
|
39
|
+
super(data, options);
|
|
40
|
+
}
|
|
41
|
+
|
|
42
|
+
/** Discovers the active Parquet files represented by the commit log. */
|
|
43
|
+
async getScanFragments(options: DeltaScanOptions = {}): Promise<readonly ScanFragment[]> {
|
|
44
|
+
const actions = await this.getActions(options.version, options.signal);
|
|
45
|
+
const activeFiles = selectActiveDeltaFiles(actions);
|
|
46
|
+
return Object.freeze(
|
|
47
|
+
activeFiles.map(file =>
|
|
48
|
+
Object.freeze({
|
|
49
|
+
id: file.path,
|
|
50
|
+
uri: this.resolveDataFile(file.path),
|
|
51
|
+
partitionValues: file.partitionValues,
|
|
52
|
+
byteLength: file.size,
|
|
53
|
+
rowCount: getDeltaRecordCount(file.stats),
|
|
54
|
+
metadata: {stats: file.stats}
|
|
55
|
+
})
|
|
56
|
+
)
|
|
57
|
+
);
|
|
58
|
+
}
|
|
59
|
+
|
|
60
|
+
/** Discovers schema and snapshot statistics without decoding all rows. */
|
|
61
|
+
async getQueryMetadata(options: ScanQueryMetadataOptions = {}): Promise<ScanQueryMetadata> {
|
|
62
|
+
const fragments = await this.getScanFragments(options);
|
|
63
|
+
if (!fragments.length) {
|
|
64
|
+
throw new Error('Delta snapshot contains no active Parquet files');
|
|
65
|
+
}
|
|
66
|
+
const dataset = this.createDataset(fragments);
|
|
67
|
+
const schema = await dataset.getSchema({signal: options.signal});
|
|
68
|
+
return createScanQueryMetadata({
|
|
69
|
+
sourceType: 'delta',
|
|
70
|
+
queryType: 'table',
|
|
71
|
+
execution: {status: 'supported', method: 'read'},
|
|
72
|
+
name: this.data instanceof Blob ? undefined : this.data,
|
|
73
|
+
schema,
|
|
74
|
+
capabilities: {table: PARQUET_TABLE_QUERY_CAPABILITIES},
|
|
75
|
+
statistics: {
|
|
76
|
+
rowCount: fragments.reduce((total, fragment) => total + Number(fragment.rowCount || 0), 0),
|
|
77
|
+
byteLength: fragments.reduce(
|
|
78
|
+
(total, fragment) => total + Number(fragment.byteLength || 0),
|
|
79
|
+
0
|
|
80
|
+
)
|
|
81
|
+
}
|
|
82
|
+
});
|
|
83
|
+
}
|
|
84
|
+
|
|
85
|
+
/** Explains the Delta snapshot and delegated Parquet physical plans. */
|
|
86
|
+
async getScanPlan(options: DeltaScanOptions = {}): Promise<ParquetDatasetExplain> {
|
|
87
|
+
return this.createDataset(await this.getScanFragments(options)).getScanPlan(options);
|
|
88
|
+
}
|
|
89
|
+
|
|
90
|
+
/** Reads the active snapshot through the shared Parquet dataset executor. */
|
|
91
|
+
read(options: DeltaScanOptions = {}): AsyncIterable<ParquetDatasetBatch> {
|
|
92
|
+
return this.createDatasetFromOptions(options).read(options);
|
|
93
|
+
}
|
|
94
|
+
|
|
95
|
+
/** Alias for `read()` used by scan-aware consumers. */
|
|
96
|
+
scan(options: DeltaScanOptions = {}): AsyncIterable<ParquetDatasetBatch> {
|
|
97
|
+
return this.read(options);
|
|
98
|
+
}
|
|
99
|
+
|
|
100
|
+
private async getActions(
|
|
101
|
+
requestedVersion?: number,
|
|
102
|
+
signal?: AbortSignal
|
|
103
|
+
): Promise<readonly DeltaAction[]> {
|
|
104
|
+
const version = this.getSnapshotVersion(requestedVersion);
|
|
105
|
+
const cacheKey = version === undefined ? 'single-commit' : String(version);
|
|
106
|
+
let actionsPromise = this.actionsPromises.get(cacheKey);
|
|
107
|
+
if (!actionsPromise) {
|
|
108
|
+
actionsPromise = this.loadActions(version, signal);
|
|
109
|
+
this.actionsPromises.set(cacheKey, actionsPromise);
|
|
110
|
+
}
|
|
111
|
+
return actionsPromise;
|
|
112
|
+
}
|
|
113
|
+
|
|
114
|
+
/** Returns the configured or URL-derived snapshot version, when available. */
|
|
115
|
+
private getSnapshotVersion(version?: number): number | undefined {
|
|
116
|
+
const selectedVersion = version ?? this.options.delta?.version;
|
|
117
|
+
if (selectedVersion !== undefined) {
|
|
118
|
+
if (!Number.isSafeInteger(selectedVersion) || selectedVersion < 0) {
|
|
119
|
+
throw new Error('Delta snapshot version must be a non-negative safe integer');
|
|
120
|
+
}
|
|
121
|
+
return selectedVersion;
|
|
122
|
+
}
|
|
123
|
+
if (typeof this.data !== 'string') return undefined;
|
|
124
|
+
const match = /\/_delta_log\/(\d{20})\.json(?:$|[?#])/i.exec(this.data);
|
|
125
|
+
return match ? Number(match[1]) : undefined;
|
|
126
|
+
}
|
|
127
|
+
|
|
128
|
+
/** Reads one commit log or replays all commits through the requested version. */
|
|
129
|
+
private async loadActions(
|
|
130
|
+
version: number | undefined,
|
|
131
|
+
signal?: AbortSignal
|
|
132
|
+
): Promise<readonly DeltaAction[]> {
|
|
133
|
+
if (typeof this.data !== 'string' || version === undefined) {
|
|
134
|
+
const text =
|
|
135
|
+
typeof this.data === 'string'
|
|
136
|
+
? await this.readResponse(
|
|
137
|
+
await this.fetch(this.url, {
|
|
138
|
+
headers: this.options.delta?.headers,
|
|
139
|
+
signal
|
|
140
|
+
})
|
|
141
|
+
)
|
|
142
|
+
: await this.data.text();
|
|
143
|
+
const actions = parseDeltaActions(text);
|
|
144
|
+
validateDeltaActions(actions);
|
|
145
|
+
return actions;
|
|
146
|
+
}
|
|
147
|
+
|
|
148
|
+
const tableRoot = this.data.replace(/\/_delta_log\/[^/?#]+(?:[?#].*)?$/i, '');
|
|
149
|
+
const actions: DeltaAction[] = [];
|
|
150
|
+
for (let currentVersion = 0; currentVersion <= version; currentVersion++) {
|
|
151
|
+
const commitURL = `${tableRoot}/_delta_log/${String(currentVersion).padStart(20, '0')}.json`;
|
|
152
|
+
const text = await this.readResponse(
|
|
153
|
+
await this.fetch(commitURL, {
|
|
154
|
+
headers: this.options.delta?.headers,
|
|
155
|
+
signal
|
|
156
|
+
})
|
|
157
|
+
);
|
|
158
|
+
actions.push(...parseDeltaActions(text));
|
|
159
|
+
}
|
|
160
|
+
const replayedActions = Object.freeze(actions);
|
|
161
|
+
validateDeltaActions(replayedActions);
|
|
162
|
+
return replayedActions;
|
|
163
|
+
}
|
|
164
|
+
|
|
165
|
+
private async readResponse(response: Response): Promise<string> {
|
|
166
|
+
if (!response.ok)
|
|
167
|
+
throw new Error(`Delta commit log request failed with status ${response.status}`);
|
|
168
|
+
return response.text();
|
|
169
|
+
}
|
|
170
|
+
|
|
171
|
+
private createDataset(fragments: readonly ScanFragment[]): ParquetDatasetSource {
|
|
172
|
+
return new ParquetDatasetSource(
|
|
173
|
+
fragments.map(fragment => ({
|
|
174
|
+
data: fragment.uri!,
|
|
175
|
+
id: fragment.id,
|
|
176
|
+
partitions: fragment.partitionValues as never,
|
|
177
|
+
metadata: fragment.metadata
|
|
178
|
+
})),
|
|
179
|
+
this.options
|
|
180
|
+
);
|
|
181
|
+
}
|
|
182
|
+
|
|
183
|
+
private createDatasetFromOptions(options: DeltaScanOptions): ParquetDatasetSource {
|
|
184
|
+
return new ParquetDatasetSource(
|
|
185
|
+
() =>
|
|
186
|
+
this.getScanFragments(options).then(fragments =>
|
|
187
|
+
fragments.map(fragment => ({
|
|
188
|
+
data: fragment.uri!,
|
|
189
|
+
id: fragment.id,
|
|
190
|
+
partitions: fragment.partitionValues as never
|
|
191
|
+
}))
|
|
192
|
+
),
|
|
193
|
+
this.options
|
|
194
|
+
);
|
|
195
|
+
}
|
|
196
|
+
|
|
197
|
+
private resolveDataFile(path: string): string {
|
|
198
|
+
if (this.options.delta?.baseUrl) return new URL(path, this.options.delta.baseUrl).toString();
|
|
199
|
+
if (typeof this.data === 'string') {
|
|
200
|
+
const tableRoot = this.data.replace(/\/_delta_log\/[^/]*$/i, '/');
|
|
201
|
+
return new URL(path, tableRoot).toString();
|
|
202
|
+
}
|
|
203
|
+
return path;
|
|
204
|
+
}
|
|
205
|
+
}
|
|
206
|
+
|
|
207
|
+
/** Parser-bearing Delta source loader exposed through the explicit source subpath. */
|
|
208
|
+
export const DeltaSourceLoaderWithParser = {
|
|
209
|
+
...DeltaFormat,
|
|
210
|
+
dataType: null as unknown as DeltaTableSource,
|
|
211
|
+
batchType: null as never,
|
|
212
|
+
name: 'DeltaSourceLoader',
|
|
213
|
+
version: VERSION,
|
|
214
|
+
type: 'delta',
|
|
215
|
+
fromUrl: true,
|
|
216
|
+
fromBlob: true,
|
|
217
|
+
options: {},
|
|
218
|
+
defaultOptions: {},
|
|
219
|
+
testURL: (url: string): boolean =>
|
|
220
|
+
/\/_delta_log\/(?:\d{20}\.json|_last_checkpoint)(?:$|[?#])/i.test(url),
|
|
221
|
+
createDataSource: (data: string | Blob, options: DeltaSourceOptions = {}): DeltaTableSource =>
|
|
222
|
+
new DeltaTableSource(data, options)
|
|
223
|
+
} as const satisfies SourceLoader<DeltaTableSource>;
|
|
224
|
+
|
|
225
|
+
/** Extracts Delta's optional `numRecords` statistic from an add action. */
|
|
226
|
+
function getDeltaRecordCount(
|
|
227
|
+
stats: string | Readonly<Record<string, unknown>> | undefined
|
|
228
|
+
): number | undefined {
|
|
229
|
+
const parsed = typeof stats === 'string' ? parseDeltaStats(stats) : stats;
|
|
230
|
+
const value = parsed?.numRecords;
|
|
231
|
+
return typeof value === 'number' && Number.isSafeInteger(value) ? value : undefined;
|
|
232
|
+
}
|
|
233
|
+
|
|
234
|
+
function parseDeltaStats(stats: string): Readonly<Record<string, unknown>> | undefined {
|
|
235
|
+
try {
|
|
236
|
+
const value: unknown = JSON.parse(stats);
|
|
237
|
+
return value && typeof value === 'object'
|
|
238
|
+
? (value as Readonly<Record<string, unknown>>)
|
|
239
|
+
: undefined;
|
|
240
|
+
} catch {
|
|
241
|
+
return undefined;
|
|
242
|
+
}
|
|
243
|
+
}
|
|
244
|
+
|
|
245
|
+
function selectActiveDeltaFiles(
|
|
246
|
+
actions: readonly DeltaAction[]
|
|
247
|
+
): Array<NonNullable<DeltaAction['add']>> {
|
|
248
|
+
const files = new Map<string, NonNullable<DeltaAction['add']>>();
|
|
249
|
+
for (const action of actions) {
|
|
250
|
+
if (action.add) {
|
|
251
|
+
files.set(action.add.path, action.add);
|
|
252
|
+
}
|
|
253
|
+
if (action.remove) files.delete(action.remove.path);
|
|
254
|
+
}
|
|
255
|
+
const activeFiles = [...files.values()];
|
|
256
|
+
const deletionVectorFile = activeFiles.find(file => file.deletionVector !== undefined);
|
|
257
|
+
if (deletionVectorFile) {
|
|
258
|
+
throw new Error(
|
|
259
|
+
`Delta deletion vectors are not supported for active file ${deletionVectorFile.path}`
|
|
260
|
+
);
|
|
261
|
+
}
|
|
262
|
+
return activeFiles;
|
|
263
|
+
}
|
|
264
|
+
|
|
265
|
+
/** Parses a newline-delimited Delta commit into typed actions. */
|
|
266
|
+
function parseDeltaActions(text: string): readonly DeltaAction[] {
|
|
267
|
+
return Object.freeze(
|
|
268
|
+
text
|
|
269
|
+
.split(/\r?\n/)
|
|
270
|
+
.filter(line => line.trim().length > 0)
|
|
271
|
+
.map(line => JSON.parse(line) as DeltaAction)
|
|
272
|
+
);
|
|
273
|
+
}
|
|
274
|
+
|
|
275
|
+
/** Rejects Delta protocol features that this Parquet snapshot adapter cannot interpret safely. */
|
|
276
|
+
function validateDeltaActions(actions: readonly DeltaAction[]): void {
|
|
277
|
+
for (const action of actions) {
|
|
278
|
+
const protocol = action.protocol;
|
|
279
|
+
if (protocol) {
|
|
280
|
+
if (
|
|
281
|
+
protocol.minReaderVersion !== undefined &&
|
|
282
|
+
(!Number.isSafeInteger(protocol.minReaderVersion) || protocol.minReaderVersion < 1)
|
|
283
|
+
) {
|
|
284
|
+
throw new Error('Delta protocol has an invalid minReaderVersion');
|
|
285
|
+
}
|
|
286
|
+
if ((protocol.minReaderVersion ?? 1) > 1) {
|
|
287
|
+
throw new Error(
|
|
288
|
+
`Delta reader protocol ${protocol.minReaderVersion} is not supported by this source`
|
|
289
|
+
);
|
|
290
|
+
}
|
|
291
|
+
if (protocol.readerFeatures?.length) {
|
|
292
|
+
throw new Error(
|
|
293
|
+
`Delta reader features are not supported: ${protocol.readerFeatures.join(', ')}`
|
|
294
|
+
);
|
|
295
|
+
}
|
|
296
|
+
}
|
|
297
|
+
|
|
298
|
+
const columnMappingMode = action.metaData?.configuration?.['delta.columnMapping.mode'];
|
|
299
|
+
if (columnMappingMode && columnMappingMode !== 'none') {
|
|
300
|
+
throw new Error(
|
|
301
|
+
`Delta column mapping mode "${columnMappingMode}" is not supported by this source`
|
|
302
|
+
);
|
|
303
|
+
}
|
|
304
|
+
}
|
|
305
|
+
}
|
|
@@ -0,0 +1,40 @@
|
|
|
1
|
+
// loaders.gl
|
|
2
|
+
// SPDX-License-Identifier: MIT
|
|
3
|
+
// Copyright (c) vis.gl contributors
|
|
4
|
+
|
|
5
|
+
import type {ParquetDatasetSourceOptions, ParquetDatasetReadOptions} from './parquet-source-types';
|
|
6
|
+
|
|
7
|
+
/** One Delta Lake transaction action from a commit log or checkpoint projection. */
|
|
8
|
+
export type DeltaAction = Readonly<{
|
|
9
|
+
protocol?: Readonly<{
|
|
10
|
+
minReaderVersion?: number;
|
|
11
|
+
readerFeatures?: readonly string[];
|
|
12
|
+
}>;
|
|
13
|
+
metaData?: Readonly<{
|
|
14
|
+
configuration?: Readonly<Record<string, string | null>>;
|
|
15
|
+
}>;
|
|
16
|
+
add?: Readonly<{
|
|
17
|
+
path: string;
|
|
18
|
+
size?: number;
|
|
19
|
+
partitionValues?: Readonly<Record<string, string | null>>;
|
|
20
|
+
stats?: string | Readonly<Record<string, unknown>>;
|
|
21
|
+
/** Delta deletion-vector descriptor, which is not decoded by this source. */
|
|
22
|
+
deletionVector?: unknown;
|
|
23
|
+
}>;
|
|
24
|
+
remove?: Readonly<{path: string}>;
|
|
25
|
+
}>;
|
|
26
|
+
|
|
27
|
+
/** Options for reading a Delta snapshot from its newline-delimited commit log. */
|
|
28
|
+
export type DeltaSourceOptions = ParquetDatasetSourceOptions & {
|
|
29
|
+
delta?: {
|
|
30
|
+
/** Snapshot version to replay when the source is a commit-log URL. */
|
|
31
|
+
version?: number;
|
|
32
|
+
/** Table root used to resolve relative Parquet add-file paths. */
|
|
33
|
+
baseUrl?: string;
|
|
34
|
+
/** Headers sent while reading commit-log files. */
|
|
35
|
+
headers?: HeadersInit;
|
|
36
|
+
};
|
|
37
|
+
};
|
|
38
|
+
|
|
39
|
+
/** Query options accepted by a Delta snapshot scan. */
|
|
40
|
+
export type DeltaScanOptions = ParquetDatasetReadOptions & {version?: number};
|