diff --git a/.dockerignore b/.dockerignore index de35e8c8c9..50fd5cc94a 100644 --- a/.dockerignore +++ b/.dockerignore @@ -14,3 +14,7 @@ assets **/.pytest_cache **/.coverage **/coverage.xml +**/target +**/*.rs.bk +**/.cargo/registry +**/.cargo/git \ No newline at end of file diff --git a/.github/workflows/_unit-tests-python.yml b/.github/workflows/_unit-tests-python.yml index ae80bd68fc..9a48316d93 100644 --- a/.github/workflows/_unit-tests-python.yml +++ b/.github/workflows/_unit-tests-python.yml @@ -31,9 +31,9 @@ jobs: uses: actions/setup-python@v5 with: python-version: ${{ env.python-version }} - cache: "poetry" - cache-dependency-path: | - ${{ inputs.working-directory }}/poetry.lock + # cache: "poetry" + # cache-dependency-path: | + # ${{ inputs.working-directory }}/poetry.lock - name: Install packages run: sudo apt update; sudo apt install -y ffmpeg libavcodec-extra libsndfile1 - name: Install dependencies diff --git a/Makefile b/Makefile index 39325fd7db..0ba07a42c7 100644 --- a/Makefile +++ b/Makefile @@ -49,6 +49,7 @@ e2e: .PHONY: install install: + $(MAKE) -C libs/libviewer install $(MAKE) -C libs/libcommon install $(MAKE) -C libs/libapi install $(MAKE) -C jobs/cache_maintenance install diff --git a/jobs/mongodb_migration/poetry.lock b/jobs/mongodb_migration/poetry.lock index ee1909d5f6..5c1e57686c 100644 --- a/jobs/mongodb_migration/poetry.lock +++ b/jobs/mongodb_migration/poetry.lock @@ -1,4 +1,4 @@ -# This file is automatically @generated by Poetry 2.1.4 and should not be changed by hand. +# This file is automatically @generated by Poetry 2.2.1 and should not be changed by hand. [[package]] name = "aiobotocore" @@ -513,6 +513,21 @@ files = [ {file = "charset_normalizer-3.4.3.tar.gz", hash = "sha256:6fce4b8500244f6fcb71465d4a4930d132ba9ab8e71a7859e6a5d59851068d14"}, ] +[[package]] +name = "click" +version = "8.3.0" +description = "Composable command line interface toolkit" +optional = false +python-versions = ">=3.10" +groups = ["main"] +files = [ + {file = "click-8.3.0-py3-none-any.whl", hash = "sha256:9b9f285302c6e3064f4330c05f05b81945b2a39544279343e6e7c5f27a9baddc"}, + {file = "click-8.3.0.tar.gz", hash = "sha256:e7b8232224eba16f4ebe410c25ced9f7875cb5f3263ffc93cc3e8da705e229c4"}, +] + +[package.dependencies] +colorama = {version = "*", markers = "platform_system == \"Windows\""} + [[package]] name = "colorama" version = "0.4.6" @@ -1071,6 +1086,7 @@ environs = "^14.3.0" filelock = "^3.18.0" fsspec = {version = "2024.3.1", extras = ["s3"]} huggingface-hub = {version = "^0.31.0", extras = ["hf-transfer"]} +libviewer = {path = "../libviewer", develop = true} mongo-types = "0.15.1" mongoengine = "^0.29.1" networkx = "^3.0" @@ -1102,6 +1118,25 @@ tqdm = "^4.66.3" type = "directory" url = "../../libs/libcommon" +[[package]] +name = "libviewer" +version = "0.1.0" +description = "Library for utils common to all the services" +optional = false +python-versions = "3.12.11" +groups = ["main"] +files = [] +develop = true + +[package.dependencies] +click = "*" +huggingface_hub = "*" +pyarrow = "*" + +[package.source] +type = "directory" +url = "../../libs/libviewer" + [[package]] name = "license-expression" version = "30.4.4" diff --git a/libs/libapi/poetry.lock b/libs/libapi/poetry.lock index be6e161cf4..63067e9719 100644 --- a/libs/libapi/poetry.lock +++ b/libs/libapi/poetry.lock @@ -1,4 +1,4 @@ -# This file is automatically @generated by Poetry 2.1.4 and should not be changed by hand. +# This file is automatically @generated by Poetry 2.2.1 and should not be changed by hand. [[package]] name = "aiobotocore" @@ -513,6 +513,21 @@ files = [ {file = "charset_normalizer-3.4.3.tar.gz", hash = "sha256:6fce4b8500244f6fcb71465d4a4930d132ba9ab8e71a7859e6a5d59851068d14"}, ] +[[package]] +name = "click" +version = "8.3.0" +description = "Composable command line interface toolkit" +optional = false +python-versions = ">=3.10" +groups = ["main"] +files = [ + {file = "click-8.3.0-py3-none-any.whl", hash = "sha256:9b9f285302c6e3064f4330c05f05b81945b2a39544279343e6e7c5f27a9baddc"}, + {file = "click-8.3.0.tar.gz", hash = "sha256:e7b8232224eba16f4ebe410c25ced9f7875cb5f3263ffc93cc3e8da705e229c4"}, +] + +[package.dependencies] +colorama = {version = "*", markers = "platform_system == \"Windows\""} + [[package]] name = "colorama" version = "0.4.6" @@ -1149,6 +1164,7 @@ environs = "^14.3.0" filelock = "^3.18.0" fsspec = {version = "2024.3.1", extras = ["s3"]} huggingface-hub = {version = "^0.31.0", extras = ["hf-transfer"]} +libviewer = {path = "../libviewer", develop = true} mongo-types = "0.15.1" mongoengine = "^0.29.1" networkx = "^3.0" @@ -1180,6 +1196,25 @@ tqdm = "^4.66.3" type = "directory" url = "../libcommon" +[[package]] +name = "libviewer" +version = "0.1.0" +description = "Library for utils common to all the services" +optional = false +python-versions = "3.12.11" +groups = ["main"] +files = [] +develop = true + +[package.dependencies] +click = "*" +huggingface_hub = "*" +pyarrow = "*" + +[package.source] +type = "directory" +url = "../libviewer" + [[package]] name = "license-expression" version = "30.4.4" diff --git a/libs/libcommon/poetry.lock b/libs/libcommon/poetry.lock index 3209b55ebb..d2a40c8b84 100644 --- a/libs/libcommon/poetry.lock +++ b/libs/libcommon/poetry.lock @@ -1,4 +1,4 @@ -# This file is automatically @generated by Poetry 2.1.4 and should not be changed by hand. +# This file is automatically @generated by Poetry 2.2.1 and should not be changed by hand. [[package]] name = "aiobotocore" @@ -548,6 +548,21 @@ files = [ {file = "charset_normalizer-3.4.3.tar.gz", hash = "sha256:6fce4b8500244f6fcb71465d4a4930d132ba9ab8e71a7859e6a5d59851068d14"}, ] +[[package]] +name = "click" +version = "8.3.0" +description = "Composable command line interface toolkit" +optional = false +python-versions = ">=3.10" +groups = ["main"] +files = [ + {file = "click-8.3.0-py3-none-any.whl", hash = "sha256:9b9f285302c6e3064f4330c05f05b81945b2a39544279343e6e7c5f27a9baddc"}, + {file = "click-8.3.0.tar.gz", hash = "sha256:e7b8232224eba16f4ebe410c25ced9f7875cb5f3263ffc93cc3e8da705e229c4"}, +] + +[package.dependencies] +colorama = {version = "*", markers = "platform_system == \"Windows\""} + [[package]] name = "colorama" version = "0.4.6" @@ -1146,6 +1161,25 @@ files = [ {file = "jmespath-1.0.1.tar.gz", hash = "sha256:90261b206d6defd58fdd5e85f478bf633a2901798906be2ad389150c5c60edbe"}, ] +[[package]] +name = "libviewer" +version = "0.1.0" +description = "Library for utils common to all the services" +optional = false +python-versions = "3.12.11" +groups = ["main"] +files = [] +develop = true + +[package.dependencies] +click = "*" +huggingface_hub = "*" +pyarrow = "*" + +[package.source] +type = "directory" +url = "../libviewer" + [[package]] name = "license-expression" version = "30.4.4" @@ -4394,4 +4428,4 @@ propcache = ">=0.2.1" [metadata] lock-version = "2.1" python-versions = "3.12.11" -content-hash = "1fec84a265400701a217d6054bb2e11a93ea6afb8f8d775a6beb81c3d449f075" +content-hash = "aeef170e3d403b3ad292571d083a7f6618cff475ceebce54dde493903ec23b32" diff --git a/libs/libcommon/pyproject.toml b/libs/libcommon/pyproject.toml index 518666d178..ddfbb850d0 100644 --- a/libs/libcommon/pyproject.toml +++ b/libs/libcommon/pyproject.toml @@ -15,6 +15,7 @@ environs = "^14.3.0" filelock = "^3.18.0" fsspec = {version = "2024.3.1", extras = ["s3"]} huggingface-hub = {version = "^0.31.0", extras = ["hf-transfer"]} +libviewer = {path = "../libviewer", develop = true} mongo-types = "0.15.1" mongoengine = "^0.29.1" networkx = "^3.0" diff --git a/libs/libcommon/src/libcommon/parquet_utils.py b/libs/libcommon/src/libcommon/parquet_utils.py index fd08d0c930..cd473fc2fc 100644 --- a/libs/libcommon/src/libcommon/parquet_utils.py +++ b/libs/libcommon/src/libcommon/parquet_utils.py @@ -1,7 +1,7 @@ import asyncio import logging import os -from collections.abc import Iterable +from collections.abc import Iterable, Sequence from dataclasses import dataclass, field from functools import lru_cache from pathlib import Path @@ -17,6 +17,7 @@ from datasets.utils.py_utils import size_str from fsspec.implementations.http import HTTPFile, HTTPFileSystem from huggingface_hub import HfFileSystem +from libviewer import Dataset as LibviewerDataset # type: ignore [import-untyped] from pyarrow.lib import ArrowInvalid from libcommon.constants import CONFIG_PARQUET_METADATA_KIND @@ -454,42 +455,38 @@ def query(self, offset: int, length: int) -> pa.Table: @staticmethod def from_parquet_metadata_items( - parquet_file_metadata_items: list[ParquetFileMetadataItem], - features: Optional[Features], + parquet_files: list[ParquetFileMetadataItem], + features: Features, parquet_metadata_directory: StrPath, httpfs: HTTPFileSystem, hf_token: Optional[str], max_arrow_data_in_memory: int, - unsupported_features: list[FeatureType] = [], + unsupported_features: Sequence[FeatureType] = (), ) -> "ParquetIndexWithMetadata": - if not parquet_file_metadata_items: + if not parquet_files: raise EmptyParquetMetadataError("No parquet files found.") + if not features: + raise ValueError("Features must be provided.") - partial = parquet_export_is_partial(parquet_file_metadata_items[0]["url"]) + partial = parquet_export_is_partial(parquet_files[0]["url"]) with StepProfiler( method="parquet_index_with_metadata.from_parquet_metadata_items", step="get the index from parquet metadata", ): try: - parquet_files_metadata = sorted( - parquet_file_metadata_items, key=lambda parquet_file_metadata: parquet_file_metadata["filename"] - ) - parquet_files_urls = [parquet_file_metadata["url"] for parquet_file_metadata in parquet_files_metadata] + parquet_files_urls = [f["url"] for f in parquet_files] metadata_paths = [ - os.path.join(parquet_metadata_directory, parquet_file_metadata["parquet_metadata_subpath"]) - for parquet_file_metadata in parquet_files_metadata + os.path.join(parquet_metadata_directory, f["parquet_metadata_subpath"]) for f in parquet_files ] - num_bytes = [parquet_file_metadata["size"] for parquet_file_metadata in parquet_files_metadata] - num_rows = [parquet_file_metadata["num_rows"] for parquet_file_metadata in parquet_files_metadata] + num_bytes = [f["size"] for f in parquet_files] + num_rows = [f["num_rows"] for f in parquet_files] except Exception as e: raise ParquetResponseFormatError(f"Could not parse the list of parquet files: {e}") from e with StepProfiler( method="parquet_index_with_metadata.from_parquet_metadata_items", step="get the dataset's features" ): - if features is None: # config-parquet version<6 didn't have features - features = Features.from_arrow_schema(pq.read_schema(metadata_paths[0])) supported_columns, unsupported_columns = get_supported_unsupported_columns( features, unsupported_features=unsupported_features, @@ -519,58 +516,99 @@ def __init__( hf_token: Optional[str], parquet_metadata_directory: StrPath, max_arrow_data_in_memory: int, - unsupported_features: list[FeatureType] = [], + unsupported_features: Sequence[FeatureType] = (), + data_store: str = "hf://", ): self.dataset = dataset self.config = config self.split = split - self.httpfs = httpfs - self.parquet_index = self._init_parquet_index( + + self._init_dataset_info(parquet_metadata_directory) + self._init_parquet_index( hf_token=hf_token, + httpfs=httpfs, parquet_metadata_directory=parquet_metadata_directory, max_arrow_data_in_memory=max_arrow_data_in_memory, unsupported_features=unsupported_features, ) + self._init_viewer_index(data_store=data_store, metadata_store=f"file://{parquet_metadata_directory}") + + def _init_dataset_info(self, parquet_metadata_directory: StrPath) -> None: + # get the list of parquet files and features + with StepProfiler(method="rows_index._get_dataset_metadata", step="all"): + response = get_previous_step_or_raise( + kind=CONFIG_PARQUET_METADATA_KIND, dataset=self.dataset, config=self.config, split=None + ) + + # set the revision of the dataset + self.revision = response["dataset_git_revision"] + + # get the list of parquet files + parquet_files = response["content"]["parquet_files_metadata"] + # filter only files for the current split and config + parquet_files = [f for f in parquet_files if f["split"] == self.split and f["config"] == self.config] + # sort by filename to have a deterministic order + parquet_files = sorted(parquet_files, key=lambda x: x["filename"]) + if not parquet_files: + raise EmptyParquetMetadataError("No parquet files found.") + self.parquet_files = parquet_files + + # retrieve the features from the mongo response + features = response["content"].get("features") + if features: + self.features = Features.from_dict(features) + else: + # config-parquet version<6 didn't have features + first_metadata_file = os.path.join( + parquet_metadata_directory, parquet_files[0]["parquet_metadata_subpath"] + ) + arrow_schema = pq.read_schema(first_metadata_file) + self.features = Features.from_arrow_schema(arrow_schema) def _init_parquet_index( self, + httpfs: HfFileSystem, hf_token: Optional[str], parquet_metadata_directory: StrPath, max_arrow_data_in_memory: int, - unsupported_features: list[FeatureType] = [], - ) -> ParquetIndexWithMetadata: - with StepProfiler(method="rows_index._init_parquet_index", step="all"): - # get the list of parquet files - with StepProfiler(method="rows_index._init_parquet_index", step="get list of parquet files for split"): - response = get_previous_step_or_raise( - kind=CONFIG_PARQUET_METADATA_KIND, - dataset=self.dataset, - config=self.config, - split=None, - ) - self.revision = response["dataset_git_revision"] - content = response["content"] - if content.get("features"): # config-parquet-metadata version<2 didn't have features - features = Features.from_dict(content["features"]) - else: - features = None - logging.info( - f"Create ParquetIndexWithMetadata for dataset={self.dataset}, config={self.config}, split={self.split}" - ) - return ParquetIndexWithMetadata.from_parquet_metadata_items( - [ - parquet_item - for parquet_item in content["parquet_files_metadata"] - if parquet_item["split"] == self.split and parquet_item["config"] == self.config - ], - features=features, - parquet_metadata_directory=parquet_metadata_directory, - httpfs=self.httpfs, - hf_token=hf_token, - max_arrow_data_in_memory=max_arrow_data_in_memory, - unsupported_features=unsupported_features, + unsupported_features: Sequence[FeatureType], + ) -> None: + logging.info( + f"Create ParquetIndexWithMetadata for dataset={self.dataset}, config={self.config}, split={self.split}" + ) + self.parquet_index = ParquetIndexWithMetadata.from_parquet_metadata_items( + parquet_files=self.parquet_files, + features=self.features, + parquet_metadata_directory=parquet_metadata_directory, + httpfs=httpfs, + hf_token=hf_token, + max_arrow_data_in_memory=max_arrow_data_in_memory, + unsupported_features=unsupported_features, + ) + + def _init_viewer_index(self, data_store: str, metadata_store: str) -> None: + logging.info(f"Create libviewer.Dataset for dataset={self.dataset}, config={self.config}, split={self.split}") + + # construct the required parquet_files list for libviewer.Dataset + files = [] + for f in self.parquet_files: + files.append( + { + "path": f"{f['config']}/{f['split']}/{f['filename']}", + "size": f["size"], + "num_rows": f["num_rows"], + "metadata_path": f["parquet_metadata_subpath"], + } ) + self.viewer_index = LibviewerDataset( + name=self.dataset, + files=files, + revision=self.revision, + data_store=data_store, + metadata_store=metadata_store, + ) + # note that this cache size is global for the class, not per instance @lru_cache(maxsize=1) def query(self, offset: int, length: int) -> pa.Table: @@ -592,6 +630,19 @@ def query(self, offset: int, length: int) -> pa.Table: ) return self.parquet_index.query(offset=offset, length=length) + def query_with_page_pruning(self, offset: int, length: int) -> pa.Table: + logging.info( + f"Query libviewer.Dataset for dataset={self.dataset}, config={self.config}," + f" split={self.split}, offset={offset}, length={length}, with page pruning" + ) + # IndexError is not ideal but .query() raises it for invalid offsets + if offset < 0: + raise IndexError("Offset must be non-negative") + if length < 0: + raise IndexError("Length must be non-negative") + batches, _files_to_index = self.viewer_index.sync_scan(offset=offset, limit=length) + return pa.Table.from_batches(batches, schema=self.features.arrow_schema) + # note that this cache size is global for the class, not per instance @lru_cache(maxsize=1) def query_truncated_binary(self, offset: int, length: int) -> tuple[pa.Table, list[str]]: @@ -633,12 +684,7 @@ def __init__( self.all_columns_supported_datasets_allow_list = all_columns_supported_datasets_allow_list @lru_cache(maxsize=1) - def get_rows_index( - self, - dataset: str, - config: str, - split: str, - ) -> RowsIndex: + def get_rows_index(self, dataset: str, config: str, split: str, data_store: str = "hf://") -> RowsIndex: filter_features = ( self.all_columns_supported_datasets_allow_list != "all" and dataset not in self.all_columns_supported_datasets_allow_list @@ -653,4 +699,5 @@ def get_rows_index( parquet_metadata_directory=self.parquet_metadata_directory, max_arrow_data_in_memory=self.max_arrow_data_in_memory, unsupported_features=unsupported_features, + data_store=data_store, ) diff --git a/libs/libcommon/src/libcommon/viewer_utils/features.py b/libs/libcommon/src/libcommon/viewer_utils/features.py index fdd20357f6..007d6694d3 100644 --- a/libs/libcommon/src/libcommon/viewer_utils/features.py +++ b/libs/libcommon/src/libcommon/viewer_utils/features.py @@ -4,6 +4,7 @@ import json import logging import os +from collections.abc import Sequence from io import BytesIO from typing import Any, Optional, Union from zlib import adler32 @@ -528,7 +529,7 @@ def to_features_list(features: Features) -> list[FeatureItem]: def get_supported_unsupported_columns( features: Features, - unsupported_features: list[FeatureType] = [], + unsupported_features: Sequence[FeatureType] = (), ) -> tuple[list[str], list[str]]: supported_columns, unsupported_columns = [], [] diff --git a/libs/libcommon/tests/test_parquet_utils.py b/libs/libcommon/tests/test_parquet_utils.py index bcd77039e2..a38fd32580 100644 --- a/libs/libcommon/tests/test_parquet_utils.py +++ b/libs/libcommon/tests/test_parquet_utils.py @@ -15,6 +15,7 @@ from datasets.table import embed_table_storage from fsspec import AbstractFileSystem from fsspec.implementations.http import HTTPFileSystem +from libviewer import Dataset as LibviewerDataset # type: ignore [import-untyped] from libcommon.parquet_utils import ( Indexer, @@ -355,7 +356,8 @@ def rows_index_with_parquet_metadata( ) -> Generator[RowsIndex, None, None]: with ds_sharded_fs.open("default/train/0003.parquet") as f: with patch("libcommon.parquet_utils.HTTPFile", return_value=f): - yield indexer.get_rows_index("ds_sharded", "default", "train") + data_store = f"file://{ds_sharded_fs.local_root_dir}" + yield indexer.get_rows_index("ds_sharded", "default", "train", data_store=data_store) @pytest.fixture @@ -465,6 +467,27 @@ def test_rows_index_query_with_parquet_metadata( rows_index_with_parquet_metadata.query(offset=-1, length=2) +def test_rows_index_query_with_page_pruning(rows_index_with_parquet_metadata: RowsIndex, ds_sharded: Dataset) -> None: + assert isinstance(rows_index_with_parquet_metadata.viewer_index, LibviewerDataset) + + result = rows_index_with_parquet_metadata.query_with_page_pruning(offset=1, length=3) + assert result.to_pydict() == ds_sharded[1:4] + + result = rows_index_with_parquet_metadata.query_with_page_pruning(offset=1, length=0) + assert result.to_pydict() == ds_sharded[:0] + + result = rows_index_with_parquet_metadata.query_with_page_pruning(offset=999999, length=1) + assert result.to_pydict() == ds_sharded[:0] + + result = rows_index_with_parquet_metadata.query_with_page_pruning(offset=1, length=99999999) + assert result.to_pydict() == ds_sharded[1:] + + with pytest.raises(IndexError): + rows_index_with_parquet_metadata.query_with_page_pruning(offset=0, length=-1) + with pytest.raises(IndexError): + rows_index_with_parquet_metadata.query_with_page_pruning(offset=-1, length=2) + + def test_rows_index_query_with_too_big_rows(rows_index_with_too_big_rows: RowsIndex, ds_sharded: Dataset) -> None: with pytest.raises(TooBigRows): rows_index_with_too_big_rows.query(offset=0, length=3) diff --git a/libs/libviewer/.gitignore b/libs/libviewer/.gitignore new file mode 100644 index 0000000000..030bfdcfa4 --- /dev/null +++ b/libs/libviewer/.gitignore @@ -0,0 +1,194 @@ +# Generated by Cargo +# will have compiled files and executables +debug/ +target/ + +# These are backup files generated by rustfmt +**/*.rs.bk + +# MSVC Windows builds of rustc generate these, which store debugging information +*.pdb + +# RustRover +# JetBrains specific template is maintained in a separate JetBrains.gitignore that can +# be found at https://github.com/github/gitignore/blob/main/Global/JetBrains.gitignore +# and can be added to the global gitignore or merged into this file. For a more nuclear +# option (not recommended) you can uncomment the following to ignore the entire idea folder. +#.idea/ + +# Byte-compiled / optimized / DLL files +__pycache__/ +*.py[cod] +*$py.class + +# C extensions +*.so + +# Distribution / packaging +.Python +build/ +develop-eggs/ +dist/ +downloads/ +eggs/ +.eggs/ +lib/ +lib64/ +parts/ +sdist/ +var/ +wheels/ +share/python-wheels/ +*.egg-info/ +.installed.cfg +*.egg +MANIFEST + +# PyInstaller +# Usually these files are written by a python script from a template +# before PyInstaller builds the exe, so as to inject date/other infos into it. +*.manifest +*.spec + +# Installer logs +pip-log.txt +pip-delete-this-directory.txt + +# Unit test / coverage reports +htmlcov/ +.tox/ +.nox/ +.coverage +.coverage.* +.cache +nosetests.xml +coverage.xml +*.cover +*.py,cover +.hypothesis/ +.pytest_cache/ +cover/ + +# Translations +*.mo +*.pot + +# Django stuff: +*.log +local_settings.py +db.sqlite3 +db.sqlite3-journal + +# Flask stuff: +instance/ +.webassets-cache + +# Scrapy stuff: +.scrapy + +# Sphinx documentation +docs/_build/ + +# PyBuilder +.pybuilder/ +target/ + +# Jupyter Notebook +.ipynb_checkpoints + +# IPython +profile_default/ +ipython_config.py + +# pyenv +# For a library or package, you might want to ignore these files since the code is +# intended to run in multiple environments; otherwise, check them in: +# .python-version + +# pipenv +# According to pypa/pipenv#598, it is recommended to include Pipfile.lock in version control. +# However, in case of collaboration, if having platform-specific dependencies or dependencies +# having no cross-platform support, pipenv may install dependencies that don't work, or not +# install all needed dependencies. +#Pipfile.lock + +# UV +# Similar to Pipfile.lock, it is generally recommended to include uv.lock in version control. +# This is especially recommended for binary packages to ensure reproducibility, and is more +# commonly ignored for libraries. +#uv.lock + +# poetry +# Similar to Pipfile.lock, it is generally recommended to include poetry.lock in version control. +# This is especially recommended for binary packages to ensure reproducibility, and is more +# commonly ignored for libraries. +# https://python-poetry.org/docs/basic-usage/#commit-your-poetrylock-file-to-version-control +#poetry.lock + +# pdm +# Similar to Pipfile.lock, it is generally recommended to include pdm.lock in version control. +#pdm.lock +# pdm stores project-wide configurations in .pdm.toml, but it is recommended to not include it +# in version control. +# https://pdm.fming.dev/latest/usage/project/#working-with-version-control +.pdm.toml +.pdm-python +.pdm-build/ + +# PEP 582; used by e.g. github.com/David-OConnor/pyflow and github.com/pdm-project/pdm +__pypackages__/ + +# Celery stuff +celerybeat-schedule +celerybeat.pid + +# SageMath parsed files +*.sage.py + +# Environments +.env +.venv +env/ +venv/ +ENV/ +env.bak/ +venv.bak/ + +# Spyder project settings +.spyderproject +.spyproject + +# Rope project settings +.ropeproject + +# mkdocs documentation +/site + +# mypy +.mypy_cache/ +.dmypy.json +dmypy.json + +# Pyre type checker +.pyre/ + +# pytype static type analyzer +.pytype/ + +# Cython debug symbols +cython_debug/ + +# PyCharm +# JetBrains specific template is maintained in a separate JetBrains.gitignore that can +# be found at https://github.com/github/gitignore/blob/main/Global/JetBrains.gitignore +# and can be added to the global gitignore or merged into this file. For a more nuclear +# option (not recommended) you can uncomment the following to ignore the entire idea folder. +#.idea/ + +# Ruff stuff: +.ruff_cache/ + +# PyPI configuration file +.pypirc + +data/ \ No newline at end of file diff --git a/libs/libviewer/Cargo.lock b/libs/libviewer/Cargo.lock new file mode 100644 index 0000000000..c2c9a3f62f --- /dev/null +++ b/libs/libviewer/Cargo.lock @@ -0,0 +1,2997 @@ +# This file is automatically @generated by Cargo. +# It is not intended for manual editing. +version = 4 + +[[package]] +name = "addr2line" +version = "0.24.2" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "dfbe277e56a376000877090da837660b4427aad530e3028d44e0bffe4f89a1c1" +dependencies = [ + "gimli", +] + +[[package]] +name = "adler2" +version = "2.0.0" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "512761e0bb2578dd7380c6baaa0f4ce03e84f95e960231d1dec8bf4d7d6e2627" + +[[package]] +name = "ahash" +version = "0.8.11" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "e89da841a80418a9b391ebaea17f5c112ffaaa96f621d2c285b5174da76b9011" +dependencies = [ + "cfg-if", + "const-random", + "getrandom 0.2.16", + "once_cell", + "version_check", + "zerocopy 0.7.35", +] + +[[package]] +name = "aho-corasick" +version = "1.1.3" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "8e60d3430d3a69478ad0993f19238d2df97c507009a52b3c10addcd7f6bcb916" +dependencies = [ + "memchr", +] + +[[package]] +name = "alloc-no-stdlib" +version = "2.0.4" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "cc7bb162ec39d46ab1ca8c77bf72e890535becd1751bb45f64c597edb4c8c6b3" + +[[package]] +name = "alloc-stdlib" +version = "0.2.2" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "94fb8275041c72129eb51b7d0322c29b8387a0386127718b096429201a5d6ece" +dependencies = [ + "alloc-no-stdlib", +] + +[[package]] +name = "android-tzdata" +version = "0.1.1" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "e999941b234f3131b00bc13c22d06e8c5ff726d1b6318ac7eb276997bbb4fef0" + +[[package]] +name = "android_system_properties" +version = "0.1.5" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "819e7219dbd41043ac279b19830f2efc897156490d7fd6ea916720117ee66311" +dependencies = [ + "libc", +] + +[[package]] +name = "anyhow" +version = "1.0.98" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "e16d2d3311acee920a9eb8d33b8cbc1787ce4a264e85f964c2404b969bdcd487" + +[[package]] +name = "arrow" +version = "56.2.0" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "6e833808ff2d94ed40d9379848a950d995043c7fb3e81a30b383f4c6033821cc" +dependencies = [ + "arrow-arith", + "arrow-array", + "arrow-buffer", + "arrow-cast", + "arrow-csv", + "arrow-data", + "arrow-ipc", + "arrow-json", + "arrow-ord", + "arrow-pyarrow", + "arrow-row", + "arrow-schema", + "arrow-select", + "arrow-string", +] + +[[package]] +name = "arrow-arith" +version = "56.2.0" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "ad08897b81588f60ba983e3ca39bda2b179bdd84dced378e7df81a5313802ef8" +dependencies = [ + "arrow-array", + "arrow-buffer", + "arrow-data", + "arrow-schema", + "chrono", + "num", +] + +[[package]] +name = "arrow-array" +version = "56.2.0" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "8548ca7c070d8db9ce7aa43f37393e4bfcf3f2d3681df278490772fd1673d08d" +dependencies = [ + "ahash", + "arrow-buffer", + "arrow-data", + "arrow-schema", + "chrono", + "half", + "hashbrown 0.16.0", + "num", +] + +[[package]] +name = "arrow-buffer" +version = "56.2.0" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "e003216336f70446457e280807a73899dd822feaf02087d31febca1363e2fccc" +dependencies = [ + "bytes", + "half", + "num", +] + +[[package]] +name = "arrow-cast" +version = "56.2.0" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "919418a0681298d3a77d1a315f625916cb5678ad0d74b9c60108eb15fd083023" +dependencies = [ + "arrow-array", + "arrow-buffer", + "arrow-data", + "arrow-schema", + "arrow-select", + "atoi", + "base64", + "chrono", + "half", + "lexical-core", + "num", + "ryu", +] + +[[package]] +name = "arrow-csv" +version = "56.2.0" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "bfa9bf02705b5cf762b6f764c65f04ae9082c7cfc4e96e0c33548ee3f67012eb" +dependencies = [ + "arrow-array", + "arrow-cast", + "arrow-schema", + "chrono", + "csv", + "csv-core", + "regex", +] + +[[package]] +name = "arrow-data" +version = "56.2.0" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "a5c64fff1d142f833d78897a772f2e5b55b36cb3e6320376f0961ab0db7bd6d0" +dependencies = [ + "arrow-buffer", + "arrow-schema", + "half", + "num", +] + +[[package]] +name = "arrow-ipc" +version = "56.2.0" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "1d3594dcddccc7f20fd069bc8e9828ce37220372680ff638c5e00dea427d88f5" +dependencies = [ + "arrow-array", + "arrow-buffer", + "arrow-data", + "arrow-schema", + "arrow-select", + "flatbuffers", +] + +[[package]] +name = "arrow-json" +version = "56.2.0" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "88cf36502b64a127dc659e3b305f1d993a544eab0d48cce704424e62074dc04b" +dependencies = [ + "arrow-array", + "arrow-buffer", + "arrow-cast", + "arrow-data", + "arrow-schema", + "chrono", + "half", + "indexmap", + "lexical-core", + "memchr", + "num", + "serde", + "serde_json", + "simdutf8", +] + +[[package]] +name = "arrow-ord" +version = "56.2.0" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "3c8f82583eb4f8d84d4ee55fd1cb306720cddead7596edce95b50ee418edf66f" +dependencies = [ + "arrow-array", + "arrow-buffer", + "arrow-data", + "arrow-schema", + "arrow-select", +] + +[[package]] +name = "arrow-pyarrow" +version = "56.2.0" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "7d924b32e96f8bb74d94cd82bd97b313c432fcb0ea331689ef9e7c6b8be4b258" +dependencies = [ + "arrow-array", + "arrow-data", + "arrow-schema", + "pyo3", +] + +[[package]] +name = "arrow-row" +version = "56.2.0" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "9d07ba24522229d9085031df6b94605e0f4b26e099fb7cdeec37abd941a73753" +dependencies = [ + "arrow-array", + "arrow-buffer", + "arrow-data", + "arrow-schema", + "half", +] + +[[package]] +name = "arrow-schema" +version = "56.2.0" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "b3aa9e59c611ebc291c28582077ef25c97f1975383f1479b12f3b9ffee2ffabe" +dependencies = [ + "bitflags", +] + +[[package]] +name = "arrow-select" +version = "56.2.0" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "8c41dbbd1e97bfcaee4fcb30e29105fb2c75e4d82ae4de70b792a5d3f66b2e7a" +dependencies = [ + "ahash", + "arrow-array", + "arrow-buffer", + "arrow-data", + "arrow-schema", + "num", +] + +[[package]] +name = "arrow-string" +version = "56.2.0" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "53f5183c150fbc619eede22b861ea7c0eebed8eaac0333eaa7f6da5205fd504d" +dependencies = [ + "arrow-array", + "arrow-buffer", + "arrow-data", + "arrow-schema", + "arrow-select", + "memchr", + "num", + "regex", + "regex-syntax", +] + +[[package]] +name = "async-trait" +version = "0.1.88" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "e539d3fca749fcee5236ab05e93a52867dd549cc157c8cb7f99595f3cedffdb5" +dependencies = [ + "proc-macro2", + "quote", + "syn", +] + +[[package]] +name = "atoi" +version = "2.0.0" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "f28d99ec8bfea296261ca1af174f24225171fea9664ba9003cbebee704810528" +dependencies = [ + "num-traits", +] + +[[package]] +name = "autocfg" +version = "1.4.0" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "ace50bade8e6234aa140d9a2f552bbee1db4d353f69b8217bc503490fc1a9f26" + +[[package]] +name = "backon" +version = "1.5.0" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "fd0b50b1b78dbadd44ab18b3c794e496f3a139abb9fbc27d9c94c4eebbb96496" +dependencies = [ + "fastrand", + "gloo-timers", + "tokio", +] + +[[package]] +name = "backtrace" +version = "0.3.74" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "8d82cb332cdfaed17ae235a638438ac4d4839913cc2af585c3c6746e8f8bee1a" +dependencies = [ + "addr2line", + "cfg-if", + "libc", + "miniz_oxide", + "object", + "rustc-demangle", + "windows-targets 0.52.6", +] + +[[package]] +name = "base64" +version = "0.22.1" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "72b3254f16251a8381aa12e40e3c4d2f0199f8c6508fbecb9d91f575e0fbb8c6" + +[[package]] +name = "bitflags" +version = "2.9.0" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "5c8214115b7bf84099f1309324e63141d4c5d7cc26862f97a0a857dbefe165bd" + +[[package]] +name = "block-buffer" +version = "0.10.4" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "3078c7629b62d3f0439517fa394996acacc5cbc91c5a20d8c658e77abd503a71" +dependencies = [ + "generic-array", +] + +[[package]] +name = "brotli" +version = "8.0.1" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "9991eea70ea4f293524138648e41ee89b0b2b12ddef3b255effa43c8056e0e0d" +dependencies = [ + "alloc-no-stdlib", + "alloc-stdlib", + "brotli-decompressor", +] + +[[package]] +name = "brotli-decompressor" +version = "5.0.0" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "874bb8112abecc98cbd6d81ea4fa7e94fb9449648c93cc89aa40c81c24d7de03" +dependencies = [ + "alloc-no-stdlib", + "alloc-stdlib", +] + +[[package]] +name = "bumpalo" +version = "3.17.0" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "1628fb46dfa0b37568d12e5edd512553eccf6a22a78e8bde00bb4aed84d5bdbf" + +[[package]] +name = "byteorder" +version = "1.5.0" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "1fd0f2584146f6f2ef48085050886acf353beff7305ebd1ae69500e27c67f64b" + +[[package]] +name = "bytes" +version = "1.10.1" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "d71b6127be86fdcfddb610f7182ac57211d4b18a3e9c82eb2d17662f2227ad6a" + +[[package]] +name = "cc" +version = "1.2.20" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "04da6a0d40b948dfc4fa8f5bbf402b0fc1a64a28dbf7d12ffd683550f2c1b63a" +dependencies = [ + "jobserver", + "libc", + "shlex", +] + +[[package]] +name = "cfg-if" +version = "1.0.0" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "baf1de4339761588bc0619e3cbc0120ee582ebb74b53b4efbf79117bd2da40fd" + +[[package]] +name = "cfg_aliases" +version = "0.2.1" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "613afe47fcd5fac7ccf1db93babcb082c5994d996f20b8b159f2ad1658eb5724" + +[[package]] +name = "chrono" +version = "0.4.41" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "c469d952047f47f91b68d1cba3f10d63c11d73e4636f24f08daf0278abf01c4d" +dependencies = [ + "android-tzdata", + "iana-time-zone", + "num-traits", + "windows-link", +] + +[[package]] +name = "const-random" +version = "0.1.18" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "87e00182fe74b066627d63b85fd550ac2998d4b0bd86bfed477a0ae4c7c71359" +dependencies = [ + "const-random-macro", +] + +[[package]] +name = "const-random-macro" +version = "0.1.16" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "f9d839f2a20b0aee515dc581a6172f2321f96cab76c1a38a4c584a194955390e" +dependencies = [ + "getrandom 0.2.16", + "once_cell", + "tiny-keccak", +] + +[[package]] +name = "core-foundation-sys" +version = "0.8.7" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "773648b94d0e5d620f64f280777445740e61fe701025087ec8b57f45c791888b" + +[[package]] +name = "crc32fast" +version = "1.4.2" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "a97769d94ddab943e4510d138150169a2758b5ef3eb191a9ee688de3e23ef7b3" +dependencies = [ + "cfg-if", +] + +[[package]] +name = "crunchy" +version = "0.2.3" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "43da5946c66ffcc7745f48db692ffbb10a83bfe0afd96235c5c2a4fb23994929" + +[[package]] +name = "crypto-common" +version = "0.1.6" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "1bfb12502f3fc46cca1bb51ac28df9d618d813cdc3d2f25b9fe775a34af26bb3" +dependencies = [ + "generic-array", + "typenum", +] + +[[package]] +name = "csv" +version = "1.3.1" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "acdc4883a9c96732e4733212c01447ebd805833b7275a73ca3ee080fd77afdaf" +dependencies = [ + "csv-core", + "itoa", + "ryu", + "serde", +] + +[[package]] +name = "csv-core" +version = "0.1.12" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "7d02f3b0da4c6504f86e9cd789d8dbafab48c2321be74e9987593de5a894d93d" +dependencies = [ + "memchr", +] + +[[package]] +name = "digest" +version = "0.10.7" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "9ed9a281f7bc9b7576e61468ba615a66a5c8cfdff42420a70aa82701a3b1e292" +dependencies = [ + "block-buffer", + "crypto-common", +] + +[[package]] +name = "displaydoc" +version = "0.2.5" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "97369cbbc041bc366949bc74d34658d6cda5621039731c6310521892a3a20ae0" +dependencies = [ + "proc-macro2", + "quote", + "syn", +] + +[[package]] +name = "either" +version = "1.15.0" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "48c757948c5ede0e46177b7add2e67155f70e33c07fea8284df6576da70b3719" + +[[package]] +name = "equivalent" +version = "1.0.2" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "877a4ace8713b0bcf2a4e7eec82529c029f1d0619886d18145fea96c3ffe5c0f" + +[[package]] +name = "errno" +version = "0.3.11" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "976dd42dc7e85965fe702eb8164f21f450704bdde31faefd6471dba214cb594e" +dependencies = [ + "libc", + "windows-sys 0.59.0", +] + +[[package]] +name = "fastrand" +version = "2.3.0" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "37909eebbb50d72f9059c3b6d82c0463f2ff062c9e95845c43a6c9c0355411be" + +[[package]] +name = "flatbuffers" +version = "25.2.10" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "1045398c1bfd89168b5fd3f1fc11f6e70b34f6f66300c87d44d3de849463abf1" +dependencies = [ + "bitflags", + "rustc_version", +] + +[[package]] +name = "flate2" +version = "1.1.1" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "7ced92e76e966ca2fd84c8f7aa01a4aea65b0eb6648d72f7c8f3e2764a67fece" +dependencies = [ + "crc32fast", + "libz-rs-sys", + "miniz_oxide", +] + +[[package]] +name = "fnv" +version = "1.0.7" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "3f9eec918d3f24069decb9af1554cad7c880e2da24a9afd88aca000531ab82c1" + +[[package]] +name = "form_urlencoded" +version = "1.2.1" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "e13624c2627564efccf4934284bdd98cbaa14e79b0b5a141218e507b3a823456" +dependencies = [ + "percent-encoding", +] + +[[package]] +name = "futures" +version = "0.3.31" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "65bc07b1a8bc7c85c5f2e110c476c7389b4554ba72af57d8445ea63a576b0876" +dependencies = [ + "futures-channel", + "futures-core", + "futures-executor", + "futures-io", + "futures-sink", + "futures-task", + "futures-util", +] + +[[package]] +name = "futures-channel" +version = "0.3.31" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "2dff15bf788c671c1934e366d07e30c1814a8ef514e1af724a602e8a2fbe1b10" +dependencies = [ + "futures-core", + "futures-sink", +] + +[[package]] +name = "futures-core" +version = "0.3.31" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "05f29059c0c2090612e8d742178b0580d2dc940c837851ad723096f87af6663e" + +[[package]] +name = "futures-executor" +version = "0.3.31" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "1e28d1d997f585e54aebc3f97d39e72338912123a67330d723fdbb564d646c9f" +dependencies = [ + "futures-core", + "futures-task", + "futures-util", +] + +[[package]] +name = "futures-io" +version = "0.3.31" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "9e5c1b78ca4aae1ac06c48a526a655760685149f0d465d21f37abfe57ce075c6" + +[[package]] +name = "futures-macro" +version = "0.3.31" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "162ee34ebcb7c64a8abebc059ce0fee27c2262618d7b60ed8faf72fef13c3650" +dependencies = [ + "proc-macro2", + "quote", + "syn", +] + +[[package]] +name = "futures-sink" +version = "0.3.31" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "e575fab7d1e0dcb8d0c7bcf9a63ee213816ab51902e6d244a95819acacf1d4f7" + +[[package]] +name = "futures-task" +version = "0.3.31" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "f90f7dce0722e95104fcb095585910c0977252f286e354b5e3bd38902cd99988" + +[[package]] +name = "futures-util" +version = "0.3.31" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "9fa08315bb612088cc391249efdc3bc77536f16c91f6cf495e6fbe85b20a4a81" +dependencies = [ + "futures-channel", + "futures-core", + "futures-io", + "futures-macro", + "futures-sink", + "futures-task", + "memchr", + "pin-project-lite", + "pin-utils", + "slab", +] + +[[package]] +name = "generic-array" +version = "0.14.7" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "85649ca51fd72272d7821adaf274ad91c288277713d9c18820d8499a7ff69e9a" +dependencies = [ + "typenum", + "version_check", +] + +[[package]] +name = "getrandom" +version = "0.2.16" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "335ff9f135e4384c8150d6f27c6daed433577f86b4750418338c01a1a2528592" +dependencies = [ + "cfg-if", + "js-sys", + "libc", + "wasi 0.11.0+wasi-snapshot-preview1", + "wasm-bindgen", +] + +[[package]] +name = "getrandom" +version = "0.3.2" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "73fea8450eea4bac3940448fb7ae50d91f034f941199fcd9d909a5a07aa455f0" +dependencies = [ + "cfg-if", + "js-sys", + "libc", + "r-efi", + "wasi 0.14.2+wasi-0.2.4", + "wasm-bindgen", +] + +[[package]] +name = "gimli" +version = "0.31.1" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "07e28edb80900c19c28f1072f2e8aeca7fa06b23cd4169cefe1af5aa3260783f" + +[[package]] +name = "gloo-timers" +version = "0.3.0" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "bbb143cf96099802033e0d4f4963b19fd2e0b728bcf076cd9cf7f6634f092994" +dependencies = [ + "futures-channel", + "futures-core", + "js-sys", + "wasm-bindgen", +] + +[[package]] +name = "half" +version = "2.6.0" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "459196ed295495a68f7d7fe1d84f6c4b7ff0e21fe3017b2f283c6fac3ad803c9" +dependencies = [ + "cfg-if", + "crunchy", + "num-traits", +] + +[[package]] +name = "hashbrown" +version = "0.15.2" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "bf151400ff0baff5465007dd2f3e717f3fe502074ca563069ce3a6629d07b289" + +[[package]] +name = "hashbrown" +version = "0.16.0" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "5419bdc4f6a9207fbeba6d11b604d481addf78ecd10c11ad51e76c2f6482748d" + +[[package]] +name = "heck" +version = "0.5.0" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "2304e00983f87ffb38b55b444b5e3b60a884b5d30c0fca7d82fe33449bbe55ea" + +[[package]] +name = "hermit-abi" +version = "0.5.1" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "f154ce46856750ed433c8649605bf7ed2de3bc35fd9d2a9f30cddd873c80cb08" + +[[package]] +name = "http" +version = "1.3.1" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "f4a85d31aea989eead29a3aaf9e1115a180df8282431156e533de47660892565" +dependencies = [ + "bytes", + "fnv", + "itoa", +] + +[[package]] +name = "http-body" +version = "1.0.1" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "1efedce1fb8e6913f23e0c92de8e62cd5b772a67e7b3946df930a62566c93184" +dependencies = [ + "bytes", + "http", +] + +[[package]] +name = "http-body-util" +version = "0.1.3" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "b021d93e26becf5dc7e1b75b1bed1fd93124b374ceb73f43d4d4eafec896a64a" +dependencies = [ + "bytes", + "futures-core", + "http", + "http-body", + "pin-project-lite", +] + +[[package]] +name = "httparse" +version = "1.10.1" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "6dbf3de79e51f3d586ab4cb9d5c3e2c14aa28ed23d180cf89b4df0454a69cc87" + +[[package]] +name = "humantime" +version = "2.2.0" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "9b112acc8b3adf4b107a8ec20977da0273a8c386765a3ec0229bd500a1443f9f" + +[[package]] +name = "hyper" +version = "1.6.0" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "cc2b571658e38e0c01b1fdca3bbbe93c00d3d71693ff2770043f8c29bc7d6f80" +dependencies = [ + "bytes", + "futures-channel", + "futures-util", + "http", + "http-body", + "httparse", + "itoa", + "pin-project-lite", + "smallvec", + "tokio", + "want", +] + +[[package]] +name = "hyper-rustls" +version = "0.27.7" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "e3c93eb611681b207e1fe55d5a71ecf91572ec8a6705cdb6857f7d8d5242cf58" +dependencies = [ + "http", + "hyper", + "hyper-util", + "rustls", + "rustls-pki-types", + "tokio", + "tokio-rustls", + "tower-service", + "webpki-roots 1.0.0", +] + +[[package]] +name = "hyper-util" +version = "0.1.11" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "497bbc33a26fdd4af9ed9c70d63f61cf56a938375fbb32df34db9b1cd6d643f2" +dependencies = [ + "bytes", + "futures-channel", + "futures-util", + "http", + "http-body", + "hyper", + "libc", + "pin-project-lite", + "socket2", + "tokio", + "tower-service", + "tracing", +] + +[[package]] +name = "iana-time-zone" +version = "0.1.63" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "b0c919e5debc312ad217002b8048a17b7d83f80703865bbfcfebb0458b0b27d8" +dependencies = [ + "android_system_properties", + "core-foundation-sys", + "iana-time-zone-haiku", + "js-sys", + "log", + "wasm-bindgen", + "windows-core", +] + +[[package]] +name = "iana-time-zone-haiku" +version = "0.1.2" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "f31827a206f56af32e590ba56d5d2d085f558508192593743f16b2306495269f" +dependencies = [ + "cc", +] + +[[package]] +name = "icu_collections" +version = "1.5.0" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "db2fa452206ebee18c4b5c2274dbf1de17008e874b4dc4f0aea9d01ca79e4526" +dependencies = [ + "displaydoc", + "yoke", + "zerofrom", + "zerovec", +] + +[[package]] +name = "icu_locid" +version = "1.5.0" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "13acbb8371917fc971be86fc8057c41a64b521c184808a698c02acc242dbf637" +dependencies = [ + "displaydoc", + "litemap", + "tinystr", + "writeable", + "zerovec", +] + +[[package]] +name = "icu_locid_transform" +version = "1.5.0" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "01d11ac35de8e40fdeda00d9e1e9d92525f3f9d887cdd7aa81d727596788b54e" +dependencies = [ + "displaydoc", + "icu_locid", + "icu_locid_transform_data", + "icu_provider", + "tinystr", + "zerovec", +] + +[[package]] +name = "icu_locid_transform_data" +version = "1.5.1" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "7515e6d781098bf9f7205ab3fc7e9709d34554ae0b21ddbcb5febfa4bc7df11d" + +[[package]] +name = "icu_normalizer" +version = "1.5.0" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "19ce3e0da2ec68599d193c93d088142efd7f9c5d6fc9b803774855747dc6a84f" +dependencies = [ + "displaydoc", + "icu_collections", + "icu_normalizer_data", + "icu_properties", + "icu_provider", + "smallvec", + "utf16_iter", + "utf8_iter", + "write16", + "zerovec", +] + +[[package]] +name = "icu_normalizer_data" +version = "1.5.1" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "c5e8338228bdc8ab83303f16b797e177953730f601a96c25d10cb3ab0daa0cb7" + +[[package]] +name = "icu_properties" +version = "1.5.1" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "93d6020766cfc6302c15dbbc9c8778c37e62c14427cb7f6e601d849e092aeef5" +dependencies = [ + "displaydoc", + "icu_collections", + "icu_locid_transform", + "icu_properties_data", + "icu_provider", + "tinystr", + "zerovec", +] + +[[package]] +name = "icu_properties_data" +version = "1.5.1" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "85fb8799753b75aee8d2a21d7c14d9f38921b54b3dbda10f5a3c7a7b82dba5e2" + +[[package]] +name = "icu_provider" +version = "1.5.0" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "6ed421c8a8ef78d3e2dbc98a973be2f3770cb42b606e3ab18d6237c4dfde68d9" +dependencies = [ + "displaydoc", + "icu_locid", + "icu_provider_macros", + "stable_deref_trait", + "tinystr", + "writeable", + "yoke", + "zerofrom", + "zerovec", +] + +[[package]] +name = "icu_provider_macros" +version = "1.5.0" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "1ec89e9337638ecdc08744df490b221a7399bf8d164eb52a665454e60e075ad6" +dependencies = [ + "proc-macro2", + "quote", + "syn", +] + +[[package]] +name = "idna" +version = "1.0.3" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "686f825264d630750a544639377bae737628043f20d38bbc029e8f29ea968a7e" +dependencies = [ + "idna_adapter", + "smallvec", + "utf8_iter", +] + +[[package]] +name = "idna_adapter" +version = "1.2.0" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "daca1df1c957320b2cf139ac61e7bd64fed304c5040df000a745aa1de3b4ef71" +dependencies = [ + "icu_normalizer", + "icu_properties", +] + +[[package]] +name = "indexmap" +version = "2.9.0" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "cea70ddb795996207ad57735b50c5982d8844f38ba9ee5f1aedcfb708a2aa11e" +dependencies = [ + "equivalent", + "hashbrown 0.15.2", +] + +[[package]] +name = "indoc" +version = "2.0.6" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "f4c7245a08504955605670dbf141fceab975f15ca21570696aebe9d2e71576bd" + +[[package]] +name = "integer-encoding" +version = "3.0.4" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "8bb03732005da905c88227371639bf1ad885cc712789c011c31c5fb3ab3ccf02" + +[[package]] +name = "ipnet" +version = "2.11.0" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "469fb0b9cefa57e3ef31275ee7cacb78f2fdca44e4765491884a2b119d4eb130" + +[[package]] +name = "itertools" +version = "0.14.0" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "2b192c782037fadd9cfa75548310488aabdbf3d2da73885b31bd0abd03351285" +dependencies = [ + "either", +] + +[[package]] +name = "itoa" +version = "1.0.15" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "4a5f13b858c8d314ee3e8f639011f7ccefe71f97f96e50151fb991f267928e2c" + +[[package]] +name = "jobserver" +version = "0.1.33" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "38f262f097c174adebe41eb73d66ae9c06b2844fb0da69969647bbddd9b0538a" +dependencies = [ + "getrandom 0.3.2", + "libc", +] + +[[package]] +name = "js-sys" +version = "0.3.77" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "1cfaf33c695fc6e08064efbc1f72ec937429614f25eef83af942d0e227c3a28f" +dependencies = [ + "once_cell", + "wasm-bindgen", +] + +[[package]] +name = "lexical-core" +version = "1.0.5" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "b765c31809609075565a70b4b71402281283aeda7ecaf4818ac14a7b2ade8958" +dependencies = [ + "lexical-parse-float", + "lexical-parse-integer", + "lexical-util", + "lexical-write-float", + "lexical-write-integer", +] + +[[package]] +name = "lexical-parse-float" +version = "1.0.5" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "de6f9cb01fb0b08060209a057c048fcbab8717b4c1ecd2eac66ebfe39a65b0f2" +dependencies = [ + "lexical-parse-integer", + "lexical-util", + "static_assertions", +] + +[[package]] +name = "lexical-parse-integer" +version = "1.0.5" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "72207aae22fc0a121ba7b6d479e42cbfea549af1479c3f3a4f12c70dd66df12e" +dependencies = [ + "lexical-util", + "static_assertions", +] + +[[package]] +name = "lexical-util" +version = "1.0.6" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "5a82e24bf537fd24c177ffbbdc6ebcc8d54732c35b50a3f28cc3f4e4c949a0b3" +dependencies = [ + "static_assertions", +] + +[[package]] +name = "lexical-write-float" +version = "1.0.5" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "c5afc668a27f460fb45a81a757b6bf2f43c2d7e30cb5a2dcd3abf294c78d62bd" +dependencies = [ + "lexical-util", + "lexical-write-integer", + "static_assertions", +] + +[[package]] +name = "lexical-write-integer" +version = "1.0.5" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "629ddff1a914a836fb245616a7888b62903aae58fa771e1d83943035efa0f978" +dependencies = [ + "lexical-util", + "static_assertions", +] + +[[package]] +name = "libc" +version = "0.2.172" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "d750af042f7ef4f724306de029d18836c26c1765a54a6a3f094cbd23a7267ffa" + +[[package]] +name = "libm" +version = "0.2.13" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "c9627da5196e5d8ed0b0495e61e518847578da83483c37288316d9b2e03a7f72" + +[[package]] +name = "libviewer" +version = "0.1.0" +dependencies = [ + "arrow", + "futures", + "object_store", + "object_store_opendal", + "opendal", + "parquet", + "pyo3", + "pyo3-async-runtimes", + "tempfile", + "thiserror", + "thrift", + "tokio", + "url", +] + +[[package]] +name = "libz-rs-sys" +version = "0.5.0" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "6489ca9bd760fe9642d7644e827b0c9add07df89857b0416ee15c1cc1a3b8c5a" +dependencies = [ + "zlib-rs", +] + +[[package]] +name = "linux-raw-sys" +version = "0.9.4" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "cd945864f07fe9f5371a27ad7b52a172b4b499999f1d97574c9fa68373937e12" + +[[package]] +name = "litemap" +version = "0.7.5" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "23fb14cb19457329c82206317a5663005a4d404783dc74f4252769b0d5f42856" + +[[package]] +name = "lock_api" +version = "0.4.12" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "07af8b9cdd281b7915f413fa73f29ebd5d55d0d3f0155584dade1ff18cea1b17" +dependencies = [ + "autocfg", + "scopeguard", +] + +[[package]] +name = "log" +version = "0.4.27" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "13dc2df351e3202783a1fe0d44375f7295ffb4049267b0f3018346dc122a1d94" + +[[package]] +name = "lru-slab" +version = "0.1.2" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "112b39cec0b298b6c1999fee3e31427f74f676e4cb9879ed1a121b43661a4154" + +[[package]] +name = "lz4_flex" +version = "0.11.3" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "75761162ae2b0e580d7e7c390558127e5f01b4194debd6221fd8c207fc80e3f5" +dependencies = [ + "twox-hash 1.6.3", +] + +[[package]] +name = "md-5" +version = "0.10.6" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "d89e7ee0cfbedfc4da3340218492196241d89eefb6dab27de5df917a6d2e78cf" +dependencies = [ + "cfg-if", + "digest", +] + +[[package]] +name = "memchr" +version = "2.7.4" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "78ca9ab1a0babb1e7d5695e3530886289c18cf2f87ec19a575a0abdce112e3a3" + +[[package]] +name = "memoffset" +version = "0.9.1" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "488016bfae457b036d996092f6cb448677611ce4449e970ceaf42695203f218a" +dependencies = [ + "autocfg", +] + +[[package]] +name = "mime" +version = "0.3.17" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "6877bb514081ee2a7ff5ef9de3281f14a4dd4bceac4c09388074a6b5df8a139a" + +[[package]] +name = "miniz_oxide" +version = "0.8.8" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "3be647b768db090acb35d5ec5db2b0e1f1de11133ca123b9eacf5137868f892a" +dependencies = [ + "adler2", +] + +[[package]] +name = "mio" +version = "1.0.3" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "2886843bf800fba2e3377cff24abf6379b4c4d5c6681eaf9ea5b0d15090450bd" +dependencies = [ + "libc", + "wasi 0.11.0+wasi-snapshot-preview1", + "windows-sys 0.52.0", +] + +[[package]] +name = "num" +version = "0.4.3" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "35bd024e8b2ff75562e5f34e7f4905839deb4b22955ef5e73d2fea1b9813cb23" +dependencies = [ + "num-bigint", + "num-complex", + "num-integer", + "num-iter", + "num-rational", + "num-traits", +] + +[[package]] +name = "num-bigint" +version = "0.4.6" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "a5e44f723f1133c9deac646763579fdb3ac745e418f2a7af9cd0c431da1f20b9" +dependencies = [ + "num-integer", + "num-traits", +] + +[[package]] +name = "num-complex" +version = "0.4.6" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "73f88a1307638156682bada9d7604135552957b7818057dcef22705b4d509495" +dependencies = [ + "num-traits", +] + +[[package]] +name = "num-integer" +version = "0.1.46" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "7969661fd2958a5cb096e56c8e1ad0444ac2bbcd0061bd28660485a44879858f" +dependencies = [ + "num-traits", +] + +[[package]] +name = "num-iter" +version = "0.1.45" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "1429034a0490724d0075ebb2bc9e875d6503c3cf69e235a8941aa757d83ef5bf" +dependencies = [ + "autocfg", + "num-integer", + "num-traits", +] + +[[package]] +name = "num-rational" +version = "0.4.2" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "f83d14da390562dca69fc84082e73e548e1ad308d24accdedd2720017cb37824" +dependencies = [ + "num-bigint", + "num-integer", + "num-traits", +] + +[[package]] +name = "num-traits" +version = "0.2.19" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "071dfc062690e90b734c0b2273ce72ad0ffa95f0c74596bc250dcfd960262841" +dependencies = [ + "autocfg", + "libm", +] + +[[package]] +name = "num_cpus" +version = "1.17.0" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "91df4bbde75afed763b708b7eee1e8e7651e02d97f6d5dd763e89367e957b23b" +dependencies = [ + "hermit-abi", + "libc", +] + +[[package]] +name = "object" +version = "0.36.7" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "62948e14d923ea95ea2c7c86c71013138b66525b86bdc08d2dcc262bdb497b87" +dependencies = [ + "memchr", +] + +[[package]] +name = "object_store" +version = "0.12.0" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "e9ce831b09395f933addbc56d894d889e4b226eba304d4e7adbab591e26daf1e" +dependencies = [ + "async-trait", + "bytes", + "chrono", + "futures", + "http", + "humantime", + "itertools", + "parking_lot", + "percent-encoding", + "thiserror", + "tokio", + "tracing", + "url", + "walkdir", +] + +[[package]] +name = "object_store_opendal" +version = "0.52.0" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "953cacb624212ffad8f34818584b33715d8ba5b1c9bc82c38b2e47a646e7e362" +dependencies = [ + "async-trait", + "bytes", + "futures", + "object_store", + "opendal", + "pin-project", + "tokio", +] + +[[package]] +name = "once_cell" +version = "1.21.3" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "42f5e15c9953c5e4ccceeb2e7382a716482c34515315f7b03532b8b4e8393d2d" + +[[package]] +name = "opendal" +version = "0.53.2" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "11ff9e9656d1cb3c58582ea18e6d9e71076a7ab2614207821d1242d7da2daed5" +dependencies = [ + "anyhow", + "async-trait", + "backon", + "base64", + "bytes", + "chrono", + "futures", + "getrandom 0.2.16", + "http", + "http-body", + "log", + "md-5", + "percent-encoding", + "quick-xml", + "reqwest", + "serde", + "serde_json", + "tokio", + "uuid", +] + +[[package]] +name = "ordered-float" +version = "2.10.1" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "68f19d67e5a2795c94e73e0bb1cc1a7edeb2e28efd39e2e1c9b7a40c1108b11c" +dependencies = [ + "num-traits", +] + +[[package]] +name = "parking_lot" +version = "0.12.3" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "f1bf18183cf54e8d6059647fc3063646a1801cf30896933ec2311622cc4b9a27" +dependencies = [ + "lock_api", + "parking_lot_core", +] + +[[package]] +name = "parking_lot_core" +version = "0.9.10" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "1e401f977ab385c9e4e3ab30627d6f26d00e2c73eef317493c4ec6d468726cf8" +dependencies = [ + "cfg-if", + "libc", + "redox_syscall", + "smallvec", + "windows-targets 0.52.6", +] + +[[package]] +name = "parquet" +version = "56.2.0" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "f0dbd48ad52d7dccf8ea1b90a3ddbfaea4f69878dd7683e51c507d4bc52b5b27" +dependencies = [ + "ahash", + "arrow-array", + "arrow-buffer", + "arrow-cast", + "arrow-data", + "arrow-ipc", + "arrow-schema", + "arrow-select", + "base64", + "brotli", + "bytes", + "chrono", + "flate2", + "futures", + "half", + "hashbrown 0.16.0", + "lz4_flex", + "num", + "num-bigint", + "object_store", + "paste", + "seq-macro", + "simdutf8", + "snap", + "thrift", + "tokio", + "twox-hash 2.1.0", + "zstd", +] + +[[package]] +name = "paste" +version = "1.0.15" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "57c0d7b74b563b49d38dae00a0c37d4d6de9b432382b2892f0574ddcae73fd0a" + +[[package]] +name = "percent-encoding" +version = "2.3.1" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "e3148f5046208a5d56bcfc03053e3ca6334e51da8dfb19b6cdc8b306fae3283e" + +[[package]] +name = "pin-project" +version = "1.1.10" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "677f1add503faace112b9f1373e43e9e054bfdd22ff1a63c1bc485eaec6a6a8a" +dependencies = [ + "pin-project-internal", +] + +[[package]] +name = "pin-project-internal" +version = "1.1.10" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "6e918e4ff8c4549eb882f14b3a4bc8c8bc93de829416eacf579f1207a8fbf861" +dependencies = [ + "proc-macro2", + "quote", + "syn", +] + +[[package]] +name = "pin-project-lite" +version = "0.2.16" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "3b3cff922bd51709b605d9ead9aa71031d81447142d828eb4a6eba76fe619f9b" + +[[package]] +name = "pin-utils" +version = "0.1.0" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "8b870d8c151b6f2fb93e84a13146138f05d02ed11c7e7c54f8826aaaf7c9f184" + +[[package]] +name = "pkg-config" +version = "0.3.32" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "7edddbd0b52d732b21ad9a5fab5c704c14cd949e5e9a1ec5929a24fded1b904c" + +[[package]] +name = "portable-atomic" +version = "1.11.0" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "350e9b48cbc6b0e028b0473b114454c6316e57336ee184ceab6e53f72c178b3e" + +[[package]] +name = "ppv-lite86" +version = "0.2.21" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "85eae3c4ed2f50dcfe72643da4befc30deadb458a9b590d720cde2f2b1e97da9" +dependencies = [ + "zerocopy 0.8.25", +] + +[[package]] +name = "proc-macro2" +version = "1.0.95" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "02b3e5e68a3a1a02aad3ec490a98007cbc13c37cbe84a3cd7b8e406d76e7f778" +dependencies = [ + "unicode-ident", +] + +[[package]] +name = "pyo3" +version = "0.25.1" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "8970a78afe0628a3e3430376fc5fd76b6b45c4d43360ffd6cdd40bdde72b682a" +dependencies = [ + "indoc", + "libc", + "memoffset", + "once_cell", + "portable-atomic", + "pyo3-build-config", + "pyo3-ffi", + "pyo3-macros", + "unindent", +] + +[[package]] +name = "pyo3-async-runtimes" +version = "0.25.0" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "d73cc6b1b7d8b3cef02101d37390dbdfe7e450dfea14921cae80a9534ba59ef2" +dependencies = [ + "futures", + "once_cell", + "pin-project-lite", + "pyo3", + "tokio", +] + +[[package]] +name = "pyo3-build-config" +version = "0.25.1" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "458eb0c55e7ece017adeba38f2248ff3ac615e53660d7c71a238d7d2a01c7598" +dependencies = [ + "once_cell", + "target-lexicon", +] + +[[package]] +name = "pyo3-ffi" +version = "0.25.1" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "7114fe5457c61b276ab77c5055f206295b812608083644a5c5b2640c3102565c" +dependencies = [ + "libc", + "pyo3-build-config", +] + +[[package]] +name = "pyo3-macros" +version = "0.25.1" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "a8725c0a622b374d6cb051d11a0983786448f7785336139c3c94f5aa6bef7e50" +dependencies = [ + "proc-macro2", + "pyo3-macros-backend", + "quote", + "syn", +] + +[[package]] +name = "pyo3-macros-backend" +version = "0.25.1" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "4109984c22491085343c05b0dbc54ddc405c3cf7b4374fc533f5c3313a572ccc" +dependencies = [ + "heck", + "proc-macro2", + "pyo3-build-config", + "quote", + "syn", +] + +[[package]] +name = "quick-xml" +version = "0.37.5" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "331e97a1af0bf59823e6eadffe373d7b27f485be8748f71471c662c1f269b7fb" +dependencies = [ + "memchr", + "serde", +] + +[[package]] +name = "quinn" +version = "0.11.8" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "626214629cda6781b6dc1d316ba307189c85ba657213ce642d9c77670f8202c8" +dependencies = [ + "bytes", + "cfg_aliases", + "pin-project-lite", + "quinn-proto", + "quinn-udp", + "rustc-hash", + "rustls", + "socket2", + "thiserror", + "tokio", + "tracing", + "web-time", +] + +[[package]] +name = "quinn-proto" +version = "0.11.12" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "49df843a9161c85bb8aae55f101bc0bac8bcafd637a620d9122fd7e0b2f7422e" +dependencies = [ + "bytes", + "getrandom 0.3.2", + "lru-slab", + "rand", + "ring", + "rustc-hash", + "rustls", + "rustls-pki-types", + "slab", + "thiserror", + "tinyvec", + "tracing", + "web-time", +] + +[[package]] +name = "quinn-udp" +version = "0.5.12" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "ee4e529991f949c5e25755532370b8af5d114acae52326361d68d47af64aa842" +dependencies = [ + "cfg_aliases", + "libc", + "once_cell", + "socket2", + "tracing", + "windows-sys 0.59.0", +] + +[[package]] +name = "quote" +version = "1.0.40" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "1885c039570dc00dcb4ff087a89e185fd56bae234ddc7f056a945bf36467248d" +dependencies = [ + "proc-macro2", +] + +[[package]] +name = "r-efi" +version = "5.2.0" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "74765f6d916ee2faa39bc8e68e4f3ed8949b48cccdac59983d287a7cb71ce9c5" + +[[package]] +name = "rand" +version = "0.9.1" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "9fbfd9d094a40bf3ae768db9361049ace4c0e04a4fd6b359518bd7b73a73dd97" +dependencies = [ + "rand_chacha", + "rand_core", +] + +[[package]] +name = "rand_chacha" +version = "0.9.0" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "d3022b5f1df60f26e1ffddd6c66e8aa15de382ae63b3a0c1bfc0e4d3e3f325cb" +dependencies = [ + "ppv-lite86", + "rand_core", +] + +[[package]] +name = "rand_core" +version = "0.9.3" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "99d9a13982dcf210057a8a78572b2217b667c3beacbf3a0d8b454f6f82837d38" +dependencies = [ + "getrandom 0.3.2", +] + +[[package]] +name = "redox_syscall" +version = "0.5.11" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "d2f103c6d277498fbceb16e84d317e2a400f160f46904d5f5410848c829511a3" +dependencies = [ + "bitflags", +] + +[[package]] +name = "regex" +version = "1.11.1" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "b544ef1b4eac5dc2db33ea63606ae9ffcfac26c1416a2806ae0bf5f56b201191" +dependencies = [ + "aho-corasick", + "memchr", + "regex-automata", + "regex-syntax", +] + +[[package]] +name = "regex-automata" +version = "0.4.9" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "809e8dc61f6de73b46c85f4c96486310fe304c434cfa43669d7b40f711150908" +dependencies = [ + "aho-corasick", + "memchr", + "regex-syntax", +] + +[[package]] +name = "regex-syntax" +version = "0.8.5" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "2b15c43186be67a4fd63bee50d0303afffcef381492ebe2c5d87f324e1b8815c" + +[[package]] +name = "reqwest" +version = "0.12.15" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "d19c46a6fdd48bc4dab94b6103fccc55d34c67cc0ad04653aad4ea2a07cd7bbb" +dependencies = [ + "base64", + "bytes", + "futures-core", + "futures-util", + "http", + "http-body", + "http-body-util", + "hyper", + "hyper-rustls", + "hyper-util", + "ipnet", + "js-sys", + "log", + "mime", + "once_cell", + "percent-encoding", + "pin-project-lite", + "quinn", + "rustls", + "rustls-pemfile", + "rustls-pki-types", + "serde", + "serde_json", + "serde_urlencoded", + "sync_wrapper", + "tokio", + "tokio-rustls", + "tokio-util", + "tower", + "tower-service", + "url", + "wasm-bindgen", + "wasm-bindgen-futures", + "wasm-streams", + "web-sys", + "webpki-roots 0.26.11", + "windows-registry", +] + +[[package]] +name = "ring" +version = "0.17.14" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "a4689e6c2294d81e88dc6261c768b63bc4fcdb852be6d1352498b114f61383b7" +dependencies = [ + "cc", + "cfg-if", + "getrandom 0.2.16", + "libc", + "untrusted", + "windows-sys 0.52.0", +] + +[[package]] +name = "rustc-demangle" +version = "0.1.24" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "719b953e2095829ee67db738b3bfa9fa368c94900df327b3f07fe6e794d2fe1f" + +[[package]] +name = "rustc-hash" +version = "2.1.1" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "357703d41365b4b27c590e3ed91eabb1b663f07c4c084095e60cbed4362dff0d" + +[[package]] +name = "rustc_version" +version = "0.4.1" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "cfcb3a22ef46e85b45de6ee7e79d063319ebb6594faafcf1c225ea92ab6e9b92" +dependencies = [ + "semver", +] + +[[package]] +name = "rustix" +version = "1.0.5" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "d97817398dd4bb2e6da002002db259209759911da105da92bec29ccb12cf58bf" +dependencies = [ + "bitflags", + "errno", + "libc", + "linux-raw-sys", + "windows-sys 0.59.0", +] + +[[package]] +name = "rustls" +version = "0.23.27" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "730944ca083c1c233a75c09f199e973ca499344a2b7ba9e755c457e86fb4a321" +dependencies = [ + "once_cell", + "ring", + "rustls-pki-types", + "rustls-webpki", + "subtle", + "zeroize", +] + +[[package]] +name = "rustls-pemfile" +version = "2.2.0" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "dce314e5fee3f39953d46bb63bb8a46d40c2f8fb7cc5a3b6cab2bde9721d6e50" +dependencies = [ + "rustls-pki-types", +] + +[[package]] +name = "rustls-pki-types" +version = "1.12.0" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "229a4a4c221013e7e1f1a043678c5cc39fe5171437c88fb47151a21e6f5b5c79" +dependencies = [ + "web-time", + "zeroize", +] + +[[package]] +name = "rustls-webpki" +version = "0.103.3" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "e4a72fe2bcf7a6ac6fd7d0b9e5cb68aeb7d4c0a0271730218b3e92d43b4eb435" +dependencies = [ + "ring", + "rustls-pki-types", + "untrusted", +] + +[[package]] +name = "rustversion" +version = "1.0.20" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "eded382c5f5f786b989652c49544c4877d9f015cc22e145a5ea8ea66c2921cd2" + +[[package]] +name = "ryu" +version = "1.0.20" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "28d3b2b1366ec20994f1fd18c3c594f05c5dd4bc44d8bb0c1c632c8d6829481f" + +[[package]] +name = "same-file" +version = "1.0.6" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "93fc1dc3aaa9bfed95e02e6eadabb4baf7e3078b0bd1b4d7b6b0b68378900502" +dependencies = [ + "winapi-util", +] + +[[package]] +name = "scopeguard" +version = "1.2.0" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "94143f37725109f92c262ed2cf5e59bce7498c01bcc1502d7b9afe439a4e9f49" + +[[package]] +name = "semver" +version = "1.0.26" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "56e6fa9c48d24d85fb3de5ad847117517440f6beceb7798af16b4a87d616b8d0" + +[[package]] +name = "seq-macro" +version = "0.3.6" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "1bc711410fbe7399f390ca1c3b60ad0f53f80e95c5eb935e52268a0e2cd49acc" + +[[package]] +name = "serde" +version = "1.0.219" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "5f0e2c6ed6606019b4e29e69dbaba95b11854410e5347d525002456dbbb786b6" +dependencies = [ + "serde_derive", +] + +[[package]] +name = "serde_derive" +version = "1.0.219" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "5b0276cf7f2c73365f7157c8123c21cd9a50fbbd844757af28ca1f5925fc2a00" +dependencies = [ + "proc-macro2", + "quote", + "syn", +] + +[[package]] +name = "serde_json" +version = "1.0.140" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "20068b6e96dc6c9bd23e01df8827e6c7e1f2fddd43c21810382803c136b99373" +dependencies = [ + "itoa", + "memchr", + "ryu", + "serde", +] + +[[package]] +name = "serde_urlencoded" +version = "0.7.1" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "d3491c14715ca2294c4d6a88f15e84739788c1d030eed8c110436aafdaa2f3fd" +dependencies = [ + "form_urlencoded", + "itoa", + "ryu", + "serde", +] + +[[package]] +name = "shlex" +version = "1.3.0" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "0fda2ff0d084019ba4d7c6f371c95d8fd75ce3524c3cb8fb653a3023f6323e64" + +[[package]] +name = "simdutf8" +version = "0.1.5" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "e3a9fe34e3e7a50316060351f37187a3f546bce95496156754b601a5fa71b76e" + +[[package]] +name = "slab" +version = "0.4.9" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "8f92a496fb766b417c996b9c5e57daf2f7ad3b0bebe1ccfca4856390e3d3bb67" +dependencies = [ + "autocfg", +] + +[[package]] +name = "smallvec" +version = "1.15.0" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "8917285742e9f3e1683f0a9c4e6b57960b7314d0b08d30d1ecd426713ee2eee9" + +[[package]] +name = "snap" +version = "1.1.1" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "1b6b67fb9a61334225b5b790716f609cd58395f895b3fe8b328786812a40bc3b" + +[[package]] +name = "socket2" +version = "0.5.9" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "4f5fd57c80058a56cf5c777ab8a126398ece8e442983605d280a44ce79d0edef" +dependencies = [ + "libc", + "windows-sys 0.52.0", +] + +[[package]] +name = "stable_deref_trait" +version = "1.2.0" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "a8f112729512f8e442d81f95a8a7ddf2b7c6b8a1a6f509a95864142b30cab2d3" + +[[package]] +name = "static_assertions" +version = "1.1.0" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "a2eb9349b6444b326872e140eb1cf5e7c522154d69e7a0ffb0fb81c06b37543f" + +[[package]] +name = "subtle" +version = "2.6.1" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "13c2bddecc57b384dee18652358fb23172facb8a2c51ccc10d74c157bdea3292" + +[[package]] +name = "syn" +version = "2.0.101" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "8ce2b7fc941b3a24138a0a7cf8e858bfc6a992e7978a068a5c760deb0ed43caf" +dependencies = [ + "proc-macro2", + "quote", + "unicode-ident", +] + +[[package]] +name = "sync_wrapper" +version = "1.0.2" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "0bf256ce5efdfa370213c1dabab5935a12e49f2c58d15e9eac2870d3b4f27263" +dependencies = [ + "futures-core", +] + +[[package]] +name = "synstructure" +version = "0.13.1" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "c8af7666ab7b6390ab78131fb5b0fce11d6b7a6951602017c35fa82800708971" +dependencies = [ + "proc-macro2", + "quote", + "syn", +] + +[[package]] +name = "target-lexicon" +version = "0.13.2" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "e502f78cdbb8ba4718f566c418c52bc729126ffd16baee5baa718cf25dd5a69a" + +[[package]] +name = "tempfile" +version = "3.20.0" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "e8a64e3985349f2441a1a9ef0b853f869006c3855f2cda6862a94d26ebb9d6a1" +dependencies = [ + "fastrand", + "getrandom 0.3.2", + "once_cell", + "rustix", + "windows-sys 0.59.0", +] + +[[package]] +name = "thiserror" +version = "2.0.12" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "567b8a2dae586314f7be2a752ec7474332959c6460e02bde30d702a66d488708" +dependencies = [ + "thiserror-impl", +] + +[[package]] +name = "thiserror-impl" +version = "2.0.12" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "7f7cf42b4507d8ea322120659672cf1b9dbb93f8f2d4ecfd6e51350ff5b17a1d" +dependencies = [ + "proc-macro2", + "quote", + "syn", +] + +[[package]] +name = "threadpool" +version = "1.8.1" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "d050e60b33d41c19108b32cea32164033a9013fe3b46cbd4457559bfbf77afaa" +dependencies = [ + "num_cpus", +] + +[[package]] +name = "thrift" +version = "0.17.0" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "7e54bc85fc7faa8bc175c4bab5b92ba8d9a3ce893d0e9f42cc455c8ab16a9e09" +dependencies = [ + "byteorder", + "integer-encoding", + "log", + "ordered-float", + "threadpool", +] + +[[package]] +name = "tiny-keccak" +version = "2.0.2" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "2c9d3793400a45f954c52e73d068316d76b6f4e36977e3fcebb13a2721e80237" +dependencies = [ + "crunchy", +] + +[[package]] +name = "tinystr" +version = "0.7.6" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "9117f5d4db391c1cf6927e7bea3db74b9a1c1add8f7eda9ffd5364f40f57b82f" +dependencies = [ + "displaydoc", + "zerovec", +] + +[[package]] +name = "tinyvec" +version = "1.9.0" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "09b3661f17e86524eccd4371ab0429194e0d7c008abb45f7a7495b1719463c71" +dependencies = [ + "tinyvec_macros", +] + +[[package]] +name = "tinyvec_macros" +version = "0.1.1" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "1f3ccbac311fea05f86f61904b462b55fb3df8837a366dfc601a0161d0532f20" + +[[package]] +name = "tokio" +version = "1.45.1" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "75ef51a33ef1da925cea3e4eb122833cb377c61439ca401b770f54902b806779" +dependencies = [ + "backtrace", + "bytes", + "libc", + "mio", + "pin-project-lite", + "socket2", + "tokio-macros", + "windows-sys 0.52.0", +] + +[[package]] +name = "tokio-macros" +version = "2.5.0" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "6e06d43f1345a3bcd39f6a56dbb7dcab2ba47e68e8ac134855e7e2bdbaf8cab8" +dependencies = [ + "proc-macro2", + "quote", + "syn", +] + +[[package]] +name = "tokio-rustls" +version = "0.26.2" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "8e727b36a1a0e8b74c376ac2211e40c2c8af09fb4013c60d910495810f008e9b" +dependencies = [ + "rustls", + "tokio", +] + +[[package]] +name = "tokio-util" +version = "0.7.15" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "66a539a9ad6d5d281510d5bd368c973d636c02dbf8a67300bfb6b950696ad7df" +dependencies = [ + "bytes", + "futures-core", + "futures-sink", + "pin-project-lite", + "tokio", +] + +[[package]] +name = "tower" +version = "0.5.2" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "d039ad9159c98b70ecfd540b2573b97f7f52c3e8d9f8ad57a24b916a536975f9" +dependencies = [ + "futures-core", + "futures-util", + "pin-project-lite", + "sync_wrapper", + "tokio", + "tower-layer", + "tower-service", +] + +[[package]] +name = "tower-layer" +version = "0.3.3" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "121c2a6cda46980bb0fcd1647ffaf6cd3fc79a013de288782836f6df9c48780e" + +[[package]] +name = "tower-service" +version = "0.3.3" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "8df9b6e13f2d32c91b9bd719c00d1958837bc7dec474d94952798cc8e69eeec3" + +[[package]] +name = "tracing" +version = "0.1.41" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "784e0ac535deb450455cbfa28a6f0df145ea1bb7ae51b821cf5e7927fdcfbdd0" +dependencies = [ + "pin-project-lite", + "tracing-attributes", + "tracing-core", +] + +[[package]] +name = "tracing-attributes" +version = "0.1.28" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "395ae124c09f9e6918a2310af6038fba074bcf474ac352496d5910dd59a2226d" +dependencies = [ + "proc-macro2", + "quote", + "syn", +] + +[[package]] +name = "tracing-core" +version = "0.1.33" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "e672c95779cf947c5311f83787af4fa8fffd12fb27e4993211a84bdfd9610f9c" +dependencies = [ + "once_cell", +] + +[[package]] +name = "try-lock" +version = "0.2.5" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "e421abadd41a4225275504ea4d6566923418b7f05506fbc9c0fe86ba7396114b" + +[[package]] +name = "twox-hash" +version = "1.6.3" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "97fee6b57c6a41524a810daee9286c02d7752c4253064d0b05472833a438f675" +dependencies = [ + "cfg-if", + "static_assertions", +] + +[[package]] +name = "twox-hash" +version = "2.1.0" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "e7b17f197b3050ba473acf9181f7b1d3b66d1cf7356c6cc57886662276e65908" + +[[package]] +name = "typenum" +version = "1.18.0" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "1dccffe3ce07af9386bfd29e80c0ab1a8205a2fc34e4bcd40364df902cfa8f3f" + +[[package]] +name = "unicode-ident" +version = "1.0.18" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "5a5f39404a5da50712a4c1eecf25e90dd62b613502b7e925fd4e4d19b5c96512" + +[[package]] +name = "unindent" +version = "0.2.4" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "7264e107f553ccae879d21fbea1d6724ac785e8c3bfc762137959b5802826ef3" + +[[package]] +name = "untrusted" +version = "0.9.0" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "8ecb6da28b8a351d773b68d5825ac39017e680750f980f3a1a85cd8dd28a47c1" + +[[package]] +name = "url" +version = "2.5.4" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "32f8b686cadd1473f4bd0117a5d28d36b1ade384ea9b5069a1c40aefed7fda60" +dependencies = [ + "form_urlencoded", + "idna", + "percent-encoding", +] + +[[package]] +name = "utf16_iter" +version = "1.0.5" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "c8232dd3cdaed5356e0f716d285e4b40b932ac434100fe9b7e0e8e935b9e6246" + +[[package]] +name = "utf8_iter" +version = "1.0.4" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "b6c140620e7ffbb22c2dee59cafe6084a59b5ffc27a8859a5f0d494b5d52b6be" + +[[package]] +name = "uuid" +version = "1.16.0" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "458f7a779bf54acc9f347480ac654f68407d3aab21269a6e3c9f922acd9e2da9" +dependencies = [ + "getrandom 0.3.2", + "js-sys", + "serde", + "wasm-bindgen", +] + +[[package]] +name = "version_check" +version = "0.9.5" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "0b928f33d975fc6ad9f86c8f283853ad26bdd5b10b7f1542aa2fa15e2289105a" + +[[package]] +name = "walkdir" +version = "2.5.0" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "29790946404f91d9c5d06f9874efddea1dc06c5efe94541a7d6863108e3a5e4b" +dependencies = [ + "same-file", + "winapi-util", +] + +[[package]] +name = "want" +version = "0.3.1" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "bfa7760aed19e106de2c7c0b581b509f2f25d3dacaf737cb82ac61bc6d760b0e" +dependencies = [ + "try-lock", +] + +[[package]] +name = "wasi" +version = "0.11.0+wasi-snapshot-preview1" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "9c8d87e72b64a3b4db28d11ce29237c246188f4f51057d65a7eab63b7987e423" + +[[package]] +name = "wasi" +version = "0.14.2+wasi-0.2.4" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "9683f9a5a998d873c0d21fcbe3c083009670149a8fab228644b8bd36b2c48cb3" +dependencies = [ + "wit-bindgen-rt", +] + +[[package]] +name = "wasm-bindgen" +version = "0.2.100" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "1edc8929d7499fc4e8f0be2262a241556cfc54a0bea223790e71446f2aab1ef5" +dependencies = [ + "cfg-if", + "once_cell", + "rustversion", + "wasm-bindgen-macro", +] + +[[package]] +name = "wasm-bindgen-backend" +version = "0.2.100" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "2f0a0651a5c2bc21487bde11ee802ccaf4c51935d0d3d42a6101f98161700bc6" +dependencies = [ + "bumpalo", + "log", + "proc-macro2", + "quote", + "syn", + "wasm-bindgen-shared", +] + +[[package]] +name = "wasm-bindgen-futures" +version = "0.4.50" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "555d470ec0bc3bb57890405e5d4322cc9ea83cebb085523ced7be4144dac1e61" +dependencies = [ + "cfg-if", + "js-sys", + "once_cell", + "wasm-bindgen", + "web-sys", +] + +[[package]] +name = "wasm-bindgen-macro" +version = "0.2.100" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "7fe63fc6d09ed3792bd0897b314f53de8e16568c2b3f7982f468c0bf9bd0b407" +dependencies = [ + "quote", + "wasm-bindgen-macro-support", +] + +[[package]] +name = "wasm-bindgen-macro-support" +version = "0.2.100" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "8ae87ea40c9f689fc23f209965b6fb8a99ad69aeeb0231408be24920604395de" +dependencies = [ + "proc-macro2", + "quote", + "syn", + "wasm-bindgen-backend", + "wasm-bindgen-shared", +] + +[[package]] +name = "wasm-bindgen-shared" +version = "0.2.100" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "1a05d73b933a847d6cccdda8f838a22ff101ad9bf93e33684f39c1f5f0eece3d" +dependencies = [ + "unicode-ident", +] + +[[package]] +name = "wasm-streams" +version = "0.4.2" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "15053d8d85c7eccdbefef60f06769760a563c7f0a9d6902a13d35c7800b0ad65" +dependencies = [ + "futures-util", + "js-sys", + "wasm-bindgen", + "wasm-bindgen-futures", + "web-sys", +] + +[[package]] +name = "web-sys" +version = "0.3.77" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "33b6dd2ef9186f1f2072e409e99cd22a975331a6b3591b12c764e0e55c60d5d2" +dependencies = [ + "js-sys", + "wasm-bindgen", +] + +[[package]] +name = "web-time" +version = "1.1.0" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "5a6580f308b1fad9207618087a65c04e7a10bc77e02c8e84e9b00dd4b12fa0bb" +dependencies = [ + "js-sys", + "wasm-bindgen", +] + +[[package]] +name = "webpki-roots" +version = "0.26.11" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "521bc38abb08001b01866da9f51eb7c5d647a19260e00054a8c7fd5f9e57f7a9" +dependencies = [ + "webpki-roots 1.0.0", +] + +[[package]] +name = "webpki-roots" +version = "1.0.0" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "2853738d1cc4f2da3a225c18ec6c3721abb31961096e9dbf5ab35fa88b19cfdb" +dependencies = [ + "rustls-pki-types", +] + +[[package]] +name = "winapi-util" +version = "0.1.9" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "cf221c93e13a30d793f7645a0e7762c55d169dbb0a49671918a2319d289b10bb" +dependencies = [ + "windows-sys 0.59.0", +] + +[[package]] +name = "windows-core" +version = "0.61.0" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "4763c1de310c86d75a878046489e2e5ba02c649d185f21c67d4cf8a56d098980" +dependencies = [ + "windows-implement", + "windows-interface", + "windows-link", + "windows-result", + "windows-strings 0.4.0", +] + +[[package]] +name = "windows-implement" +version = "0.60.0" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "a47fddd13af08290e67f4acabf4b459f647552718f683a7b415d290ac744a836" +dependencies = [ + "proc-macro2", + "quote", + "syn", +] + +[[package]] +name = "windows-interface" +version = "0.59.1" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "bd9211b69f8dcdfa817bfd14bf1c97c9188afa36f4750130fcdf3f400eca9fa8" +dependencies = [ + "proc-macro2", + "quote", + "syn", +] + +[[package]] +name = "windows-link" +version = "0.1.1" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "76840935b766e1b0a05c0066835fb9ec80071d4c09a16f6bd5f7e655e3c14c38" + +[[package]] +name = "windows-registry" +version = "0.4.0" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "4286ad90ddb45071efd1a66dfa43eb02dd0dfbae1545ad6cc3c51cf34d7e8ba3" +dependencies = [ + "windows-result", + "windows-strings 0.3.1", + "windows-targets 0.53.0", +] + +[[package]] +name = "windows-result" +version = "0.3.2" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "c64fd11a4fd95df68efcfee5f44a294fe71b8bc6a91993e2791938abcc712252" +dependencies = [ + "windows-link", +] + +[[package]] +name = "windows-strings" +version = "0.3.1" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "87fa48cc5d406560701792be122a10132491cff9d0aeb23583cc2dcafc847319" +dependencies = [ + "windows-link", +] + +[[package]] +name = "windows-strings" +version = "0.4.0" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "7a2ba9642430ee452d5a7aa78d72907ebe8cfda358e8cb7918a2050581322f97" +dependencies = [ + "windows-link", +] + +[[package]] +name = "windows-sys" +version = "0.52.0" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "282be5f36a8ce781fad8c8ae18fa3f9beff57ec1b52cb3de0789201425d9a33d" +dependencies = [ + "windows-targets 0.52.6", +] + +[[package]] +name = "windows-sys" +version = "0.59.0" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "1e38bc4d79ed67fd075bcc251a1c39b32a1776bbe92e5bef1f0bf1f8c531853b" +dependencies = [ + "windows-targets 0.52.6", +] + +[[package]] +name = "windows-targets" +version = "0.52.6" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "9b724f72796e036ab90c1021d4780d4d3d648aca59e491e6b98e725b84e99973" +dependencies = [ + "windows_aarch64_gnullvm 0.52.6", + "windows_aarch64_msvc 0.52.6", + "windows_i686_gnu 0.52.6", + "windows_i686_gnullvm 0.52.6", + "windows_i686_msvc 0.52.6", + "windows_x86_64_gnu 0.52.6", + "windows_x86_64_gnullvm 0.52.6", + "windows_x86_64_msvc 0.52.6", +] + +[[package]] +name = "windows-targets" +version = "0.53.0" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "b1e4c7e8ceaaf9cb7d7507c974735728ab453b67ef8f18febdd7c11fe59dca8b" +dependencies = [ + "windows_aarch64_gnullvm 0.53.0", + "windows_aarch64_msvc 0.53.0", + "windows_i686_gnu 0.53.0", + "windows_i686_gnullvm 0.53.0", + "windows_i686_msvc 0.53.0", + "windows_x86_64_gnu 0.53.0", + "windows_x86_64_gnullvm 0.53.0", + "windows_x86_64_msvc 0.53.0", +] + +[[package]] +name = "windows_aarch64_gnullvm" +version = "0.52.6" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "32a4622180e7a0ec044bb555404c800bc9fd9ec262ec147edd5989ccd0c02cd3" + +[[package]] +name = "windows_aarch64_gnullvm" +version = "0.53.0" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "86b8d5f90ddd19cb4a147a5fa63ca848db3df085e25fee3cc10b39b6eebae764" + +[[package]] +name = "windows_aarch64_msvc" +version = "0.52.6" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "09ec2a7bb152e2252b53fa7803150007879548bc709c039df7627cabbd05d469" + +[[package]] +name = "windows_aarch64_msvc" +version = "0.53.0" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "c7651a1f62a11b8cbd5e0d42526e55f2c99886c77e007179efff86c2b137e66c" + +[[package]] +name = "windows_i686_gnu" +version = "0.52.6" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "8e9b5ad5ab802e97eb8e295ac6720e509ee4c243f69d781394014ebfe8bbfa0b" + +[[package]] +name = "windows_i686_gnu" +version = "0.53.0" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "c1dc67659d35f387f5f6c479dc4e28f1d4bb90ddd1a5d3da2e5d97b42d6272c3" + +[[package]] +name = "windows_i686_gnullvm" +version = "0.52.6" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "0eee52d38c090b3caa76c563b86c3a4bd71ef1a819287c19d586d7334ae8ed66" + +[[package]] +name = "windows_i686_gnullvm" +version = "0.53.0" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "9ce6ccbdedbf6d6354471319e781c0dfef054c81fbc7cf83f338a4296c0cae11" + +[[package]] +name = "windows_i686_msvc" +version = "0.52.6" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "240948bc05c5e7c6dabba28bf89d89ffce3e303022809e73deaefe4f6ec56c66" + +[[package]] +name = "windows_i686_msvc" +version = "0.53.0" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "581fee95406bb13382d2f65cd4a908ca7b1e4c2f1917f143ba16efe98a589b5d" + +[[package]] +name = "windows_x86_64_gnu" +version = "0.52.6" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "147a5c80aabfbf0c7d901cb5895d1de30ef2907eb21fbbab29ca94c5b08b1a78" + +[[package]] +name = "windows_x86_64_gnu" +version = "0.53.0" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "2e55b5ac9ea33f2fc1716d1742db15574fd6fc8dadc51caab1c16a3d3b4190ba" + +[[package]] +name = "windows_x86_64_gnullvm" +version = "0.52.6" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "24d5b23dc417412679681396f2b49f3de8c1473deb516bd34410872eff51ed0d" + +[[package]] +name = "windows_x86_64_gnullvm" +version = "0.53.0" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "0a6e035dd0599267ce1ee132e51c27dd29437f63325753051e71dd9e42406c57" + +[[package]] +name = "windows_x86_64_msvc" +version = "0.52.6" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "589f6da84c646204747d1270a2a5661ea66ed1cced2631d546fdfb155959f9ec" + +[[package]] +name = "windows_x86_64_msvc" +version = "0.53.0" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "271414315aff87387382ec3d271b52d7ae78726f5d44ac98b4f4030c91880486" + +[[package]] +name = "wit-bindgen-rt" +version = "0.39.0" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "6f42320e61fe2cfd34354ecb597f86f413484a798ba44a8ca1165c58d42da6c1" +dependencies = [ + "bitflags", +] + +[[package]] +name = "write16" +version = "1.0.0" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "d1890f4022759daae28ed4fe62859b1236caebfc61ede2f63ed4e695f3f6d936" + +[[package]] +name = "writeable" +version = "0.5.5" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "1e9df38ee2d2c3c5948ea468a8406ff0db0b29ae1ffde1bcf20ef305bcc95c51" + +[[package]] +name = "yoke" +version = "0.7.5" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "120e6aef9aa629e3d4f52dc8cc43a015c7724194c97dfaf45180d2daf2b77f40" +dependencies = [ + "serde", + "stable_deref_trait", + "yoke-derive", + "zerofrom", +] + +[[package]] +name = "yoke-derive" +version = "0.7.5" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "2380878cad4ac9aac1e2435f3eb4020e8374b5f13c296cb75b4620ff8e229154" +dependencies = [ + "proc-macro2", + "quote", + "syn", + "synstructure", +] + +[[package]] +name = "zerocopy" +version = "0.7.35" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "1b9b4fd18abc82b8136838da5d50bae7bdea537c574d8dc1a34ed098d6c166f0" +dependencies = [ + "zerocopy-derive 0.7.35", +] + +[[package]] +name = "zerocopy" +version = "0.8.25" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "a1702d9583232ddb9174e01bb7c15a2ab8fb1bc6f227aa1233858c351a3ba0cb" +dependencies = [ + "zerocopy-derive 0.8.25", +] + +[[package]] +name = "zerocopy-derive" +version = "0.7.35" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "fa4f8080344d4671fb4e831a13ad1e68092748387dfc4f55e356242fae12ce3e" +dependencies = [ + "proc-macro2", + "quote", + "syn", +] + +[[package]] +name = "zerocopy-derive" +version = "0.8.25" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "28a6e20d751156648aa063f3800b706ee209a32c0b4d9f24be3d980b01be55ef" +dependencies = [ + "proc-macro2", + "quote", + "syn", +] + +[[package]] +name = "zerofrom" +version = "0.1.6" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "50cc42e0333e05660c3587f3bf9d0478688e15d870fab3346451ce7f8c9fbea5" +dependencies = [ + "zerofrom-derive", +] + +[[package]] +name = "zerofrom-derive" +version = "0.1.6" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "d71e5d6e06ab090c67b5e44993ec16b72dcbaabc526db883a360057678b48502" +dependencies = [ + "proc-macro2", + "quote", + "syn", + "synstructure", +] + +[[package]] +name = "zeroize" +version = "1.8.1" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "ced3678a2879b30306d323f4542626697a464a97c0a07c9aebf7ebca65cd4dde" + +[[package]] +name = "zerovec" +version = "0.10.4" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "aa2b893d79df23bfb12d5461018d408ea19dfafe76c2c7ef6d4eba614f8ff079" +dependencies = [ + "yoke", + "zerofrom", + "zerovec-derive", +] + +[[package]] +name = "zerovec-derive" +version = "0.10.3" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "6eafa6dfb17584ea3e2bd6e76e0cc15ad7af12b09abdd1ca55961bed9b1063c6" +dependencies = [ + "proc-macro2", + "quote", + "syn", +] + +[[package]] +name = "zlib-rs" +version = "0.5.0" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "868b928d7949e09af2f6086dfc1e01936064cc7a819253bce650d4e2a2d63ba8" + +[[package]] +name = "zstd" +version = "0.13.3" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "e91ee311a569c327171651566e07972200e76fcfe2242a4fa446149a3881c08a" +dependencies = [ + "zstd-safe", +] + +[[package]] +name = "zstd-safe" +version = "7.2.4" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "8f49c4d5f0abb602a93fb8736af2a4f4dd9512e36f7f570d66e65ff867ed3b9d" +dependencies = [ + "zstd-sys", +] + +[[package]] +name = "zstd-sys" +version = "2.0.15+zstd.1.5.7" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "eb81183ddd97d0c74cedf1d50d85c8d08c1b8b68ee863bdee9e706eedba1a237" +dependencies = [ + "cc", + "pkg-config", +] diff --git a/libs/libviewer/Cargo.toml b/libs/libviewer/Cargo.toml new file mode 100644 index 0000000000..b7ca5bed87 --- /dev/null +++ b/libs/libviewer/Cargo.toml @@ -0,0 +1,24 @@ +[package] +name = "libviewer" +version = "0.1.0" +edition = "2021" + +[lib] +name = "libviewer" +# "cdylib" is necessary to produce a shared library for Python to import from +crate-type = ["cdylib"] + +[dependencies] +arrow = { version = "56.2", features = ["pyarrow"] } +futures = "0.3" +object_store = "0.12.0" +object_store_opendal = "0.52.0" +opendal = { version = "0.53.2", features = ["services-huggingface"] } +parquet = { version = "56.2", features = ["async", "object_store"] } +pyo3 = { version = "^0.25", features = ["extension-module"] } +pyo3-async-runtimes = { version = "^0.25", features = ["tokio-runtime"] } +tempfile = "3.20.0" +thiserror = "2.0.12" +thrift = "0.17" +tokio = "1.45" +url = "2.5.4" diff --git a/libs/libviewer/Makefile b/libs/libviewer/Makefile new file mode 100644 index 0000000000..d5ea83e94c --- /dev/null +++ b/libs/libviewer/Makefile @@ -0,0 +1,8 @@ +MATURIN := $(shell command -v maturin 2>/dev/null) +ifndef MATURIN +$(error maturin not found in PATH. Please install it first.) +endif + +.PHONY: install +install: + $(MATURIN) develop -r \ No newline at end of file diff --git a/libs/libviewer/README.md b/libs/libviewer/README.md new file mode 100644 index 0000000000..d1053699ea --- /dev/null +++ b/libs/libviewer/README.md @@ -0,0 +1,30 @@ +## Install + +```bash +pip install maturin +maturin develop -r +``` + +## Index Dataset + +```bash +dv --use-cache nvidia/OpenCodeReasoning index +``` + +This uses `huggingface_hub` to download and cache the dataset files. +Then creates a metadata file for each parque file in the dataset with +offset index included. + +Remove `--use-cache` to directly download the files from the hub. + +## Execute a limit/offset query + +```bash +dv --use-cache nvidia/OpenCodeReasoning query --limit 10 --offset 0 +``` + +This will query the dataset using the local metadata index files. +The scanner only reads the necessary parquet pages to minimize the +network traffic. + +Remove `--use-cache` to directly query data from the hub. \ No newline at end of file diff --git a/libs/libviewer/build.py b/libs/libviewer/build.py new file mode 100644 index 0000000000..1a41256d04 --- /dev/null +++ b/libs/libviewer/build.py @@ -0,0 +1,42 @@ +import os +import shlex +import shutil +import subprocess +import zipfile + +from pathlib import Path + + +def maturin(*args): + subprocess.call(["maturin", *list(args)]) + + +def build(): + build_dir = Path(__file__).parent.joinpath("build") + build_dir.mkdir(parents=True, exist_ok=True) + + wheels_dir = Path(__file__).parent.joinpath("target/wheels") + if wheels_dir.exists(): + shutil.rmtree(wheels_dir) + + cargo_args = [] + if os.getenv("MATURIN_BUILD_ARGS"): + cargo_args = shlex.split(os.getenv("MATURIN_BUILD_ARGS", "")) + + maturin("build", "-r", *cargo_args) + + # We won't use the wheel built by maturin directly since + # we want Poetry to build it, but we need to retrieve the + # compiled extensions from the maturin wheel. + wheel = next(iter(wheels_dir.glob("*.whl"))) + with zipfile.ZipFile(wheel.as_posix()) as whl: + whl.extractall(wheels_dir.as_posix()) + + for extension in wheels_dir.rglob("**/*.so"): + shutil.copyfile(extension, Path(__file__).parent.joinpath("libviewer", extension.name)) + + shutil.rmtree(wheels_dir) + + +if __name__ == "__main__": + build() \ No newline at end of file diff --git a/libs/libviewer/libviewer/__init__.py b/libs/libviewer/libviewer/__init__.py new file mode 100644 index 0000000000..53ee17ceb6 --- /dev/null +++ b/libs/libviewer/libviewer/__init__.py @@ -0,0 +1,72 @@ +import os + +from huggingface_hub import hf_hub_download, list_repo_files + +from ._internal import PyDataset + + +__all__ = ["Dataset"] + + +# TODO(kszucs): add config/split arguments to restrict the dataset files +class Dataset(PyDataset): + # it can also be constructed from an explicit list of [ + # {"data_path": ..., "data_size": ..., "metadata_path": ...}, + # ... + # ] + + def from_hub(repo, metadata_store, revision=None): + """Create a Dataset from Hugging Face Hub.""" + repo_files = list_repo_files(repo, repo_type="dataset", revision=revision) + + parquet_files = [] + for filename in repo_files: + if filename.endswith(".parquet"): + parquet_files.append( + { + "path": filename, + "size": None, + "num_rows": None, + "metadata_path": filename, + } + ) + if not parquet_files: + raise ValueError(f"No parquet files found in the dataset '{repo}'.") + + return Dataset( + repo, + parquet_files, + revision=revision, + data_store=f"hf://datasets/{repo}", + metadata_store=metadata_store, + ) + + def from_cache(repo, metadata_store, revision=None, download=False): + """Create a Dataset from HF local cache.""" + repo_files = list_repo_files(repo, repo_type="dataset", revision=revision) + + parquet_files = [] + for filename in repo_files: + if filename.endswith(".parquet"): + data_path = hf_hub_download( + repo, filename, repo_type="dataset", local_files_only=not download + ) + data_size = os.path.getsize(data_path) + parquet_files.append( + { + "path": data_path, + "size": data_size, + "num_rows": None, + "metadata_path": filename, + } + ) + if not parquet_files: + raise ValueError(f"No parquet files found in the dataset '{repo}'.") + + return Dataset( + repo, + parquet_files, + revision=revision, + data_store="file://", + metadata_store=metadata_store, + ) diff --git a/libs/libviewer/libviewer/cli.py b/libs/libviewer/libviewer/cli.py new file mode 100644 index 0000000000..743e97b1ba --- /dev/null +++ b/libs/libviewer/libviewer/cli.py @@ -0,0 +1,108 @@ +import click +import pathlib + +from libviewer import Dataset + + +@click.group() +@click.argument("dataset", type=str, required=True) +@click.option( + "--revision", "-r", type=str, default=None, help="The dataset revision to use" +) +@click.option( + "--metadata-dir", + "-m", + default="data", + type=pathlib.Path, + show_default=True, + help="The output directory to save the dataset's metadata", +) +@click.option( + "--use-cache", + "-l", + is_flag=True, + default=False, + help="Load the dataset from the local cache instead of the Hugging Face Hub", +) +@click.option( + "--download", + "-d", + is_flag=True, + default=False, + help="Whether to download the dataset files if loading from cache", +) +@click.pass_context +def cli(ctx, dataset, revision, metadata_dir, use_cache, download): + """Dataset Viewer with parquet page pruning""" + ctx.ensure_object(dict) + ctx.obj["dataset_name"] = dataset + ctx.obj["metadata_dir"] = metadata_dir + + metadata_store = f"file://{metadata_dir.absolute()}/{dataset}" + if use_cache: + print("Loading dataset from local cache...") + ctx.obj["dataset"] = Dataset.from_cache( + dataset, metadata_store, revision=revision, download=download + ) + else: + print("Loading dataset from Hugging Face Hub...") + ctx.obj["dataset"] = Dataset.from_hub( + dataset, metadata_store, revision=revision + ) + + +@cli.command() +@click.option( + "--offset", + "-o", + type=int, + default=0, + show_default=True, + help="The offset to start querying from", +) +@click.option( + "--limit", + "-l", + type=int, + default=10, + show_default=True, + help="The number of records to query", +) +@click.pass_context +def query(ctx, offset, limit): + """Query a dataset""" + print( + f"Querying dataset '{ctx.obj['dataset_name']}' with offset {offset} and limit {limit}" + ) + + dataset = ctx.obj["dataset"] + batches, files_to_index = dataset.sync_scan(limit, offset) + + # Print the result + for batch in batches: + print(f"Batch length: {len(batch)}") + + # Print the files that should be indexed + if files_to_index: + print("Files that should be indexed:") + for file in files_to_index: + print(f" - {file}") + else: + print("No files should be indexed.") + + +@cli.command() +@click.pass_context +def index(ctx): + """Download and index parquet files from a dataset.""" + + dataset = ctx.obj["dataset"] + metadata_dir = ctx.obj["metadata_dir"] + + print(f"Indexing dataset '{dataset}' in '{metadata_dir}'") + + # Ensure the metadata directory exists + metadata_dir.mkdir(parents=True, exist_ok=True) + + print("Indexing dataset with offset index enabled...") + dataset.sync_index() diff --git a/libs/libviewer/poetry.lock b/libs/libviewer/poetry.lock new file mode 100644 index 0000000000..7cb0004c56 --- /dev/null +++ b/libs/libviewer/poetry.lock @@ -0,0 +1,500 @@ +# This file is automatically @generated by Poetry 2.1.3 and should not be changed by hand. + +[[package]] +name = "certifi" +version = "2025.6.15" +description = "Python package for providing Mozilla's CA Bundle." +optional = false +python-versions = ">=3.7" +groups = ["main"] +files = [ + {file = "certifi-2025.6.15-py3-none-any.whl", hash = "sha256:2e0c7ce7cb5d8f8634ca55d2ba7e6ec2689a2fd6537d8dec1296a477a4910057"}, + {file = "certifi-2025.6.15.tar.gz", hash = "sha256:d747aa5a8b9bbbb1bb8c22bb13e22bd1f18e9796defa16bab421f7f7a317323b"}, +] + +[[package]] +name = "charset-normalizer" +version = "3.4.2" +description = "The Real First Universal Charset Detector. Open, modern and actively maintained alternative to Chardet." +optional = false +python-versions = ">=3.7" +groups = ["main"] +files = [ + {file = "charset_normalizer-3.4.2-cp310-cp310-macosx_10_9_universal2.whl", hash = "sha256:7c48ed483eb946e6c04ccbe02c6b4d1d48e51944b6db70f697e089c193404941"}, + {file = "charset_normalizer-3.4.2-cp310-cp310-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:b2d318c11350e10662026ad0eb71bb51c7812fc8590825304ae0bdd4ac283acd"}, + {file = "charset_normalizer-3.4.2-cp310-cp310-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:9cbfacf36cb0ec2897ce0ebc5d08ca44213af24265bd56eca54bee7923c48fd6"}, + {file = "charset_normalizer-3.4.2-cp310-cp310-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:18dd2e350387c87dabe711b86f83c9c78af772c748904d372ade190b5c7c9d4d"}, + {file = "charset_normalizer-3.4.2-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:8075c35cd58273fee266c58c0c9b670947c19df5fb98e7b66710e04ad4e9ff86"}, + {file = "charset_normalizer-3.4.2-cp310-cp310-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:5bf4545e3b962767e5c06fe1738f951f77d27967cb2caa64c28be7c4563e162c"}, + {file = "charset_normalizer-3.4.2-cp310-cp310-musllinux_1_2_aarch64.whl", hash = "sha256:7a6ab32f7210554a96cd9e33abe3ddd86732beeafc7a28e9955cdf22ffadbab0"}, + {file = "charset_normalizer-3.4.2-cp310-cp310-musllinux_1_2_i686.whl", hash = "sha256:b33de11b92e9f75a2b545d6e9b6f37e398d86c3e9e9653c4864eb7e89c5773ef"}, + {file = "charset_normalizer-3.4.2-cp310-cp310-musllinux_1_2_ppc64le.whl", hash = "sha256:8755483f3c00d6c9a77f490c17e6ab0c8729e39e6390328e42521ef175380ae6"}, + {file = "charset_normalizer-3.4.2-cp310-cp310-musllinux_1_2_s390x.whl", hash = "sha256:68a328e5f55ec37c57f19ebb1fdc56a248db2e3e9ad769919a58672958e8f366"}, + {file = "charset_normalizer-3.4.2-cp310-cp310-musllinux_1_2_x86_64.whl", hash = "sha256:21b2899062867b0e1fde9b724f8aecb1af14f2778d69aacd1a5a1853a597a5db"}, + {file = "charset_normalizer-3.4.2-cp310-cp310-win32.whl", hash = "sha256:e8082b26888e2f8b36a042a58307d5b917ef2b1cacab921ad3323ef91901c71a"}, + {file = "charset_normalizer-3.4.2-cp310-cp310-win_amd64.whl", hash = "sha256:f69a27e45c43520f5487f27627059b64aaf160415589230992cec34c5e18a509"}, + {file = "charset_normalizer-3.4.2-cp311-cp311-macosx_10_9_universal2.whl", hash = "sha256:be1e352acbe3c78727a16a455126d9ff83ea2dfdcbc83148d2982305a04714c2"}, + {file = "charset_normalizer-3.4.2-cp311-cp311-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:aa88ca0b1932e93f2d961bf3addbb2db902198dca337d88c89e1559e066e7645"}, + {file = "charset_normalizer-3.4.2-cp311-cp311-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:d524ba3f1581b35c03cb42beebab4a13e6cdad7b36246bd22541fa585a56cccd"}, + {file = "charset_normalizer-3.4.2-cp311-cp311-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:28a1005facc94196e1fb3e82a3d442a9d9110b8434fc1ded7a24a2983c9888d8"}, + {file = "charset_normalizer-3.4.2-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:fdb20a30fe1175ecabed17cbf7812f7b804b8a315a25f24678bcdf120a90077f"}, + {file = "charset_normalizer-3.4.2-cp311-cp311-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:0f5d9ed7f254402c9e7d35d2f5972c9bbea9040e99cd2861bd77dc68263277c7"}, + {file = "charset_normalizer-3.4.2-cp311-cp311-musllinux_1_2_aarch64.whl", hash = "sha256:efd387a49825780ff861998cd959767800d54f8308936b21025326de4b5a42b9"}, + {file = "charset_normalizer-3.4.2-cp311-cp311-musllinux_1_2_i686.whl", hash = "sha256:f0aa37f3c979cf2546b73e8222bbfa3dc07a641585340179d768068e3455e544"}, + {file = "charset_normalizer-3.4.2-cp311-cp311-musllinux_1_2_ppc64le.whl", hash = "sha256:e70e990b2137b29dc5564715de1e12701815dacc1d056308e2b17e9095372a82"}, + {file = "charset_normalizer-3.4.2-cp311-cp311-musllinux_1_2_s390x.whl", hash = "sha256:0c8c57f84ccfc871a48a47321cfa49ae1df56cd1d965a09abe84066f6853b9c0"}, + {file = "charset_normalizer-3.4.2-cp311-cp311-musllinux_1_2_x86_64.whl", hash = "sha256:6b66f92b17849b85cad91259efc341dce9c1af48e2173bf38a85c6329f1033e5"}, + {file = "charset_normalizer-3.4.2-cp311-cp311-win32.whl", hash = "sha256:daac4765328a919a805fa5e2720f3e94767abd632ae410a9062dff5412bae65a"}, + {file = "charset_normalizer-3.4.2-cp311-cp311-win_amd64.whl", hash = "sha256:e53efc7c7cee4c1e70661e2e112ca46a575f90ed9ae3fef200f2a25e954f4b28"}, + {file = "charset_normalizer-3.4.2-cp312-cp312-macosx_10_13_universal2.whl", hash = "sha256:0c29de6a1a95f24b9a1aa7aefd27d2487263f00dfd55a77719b530788f75cff7"}, + {file = "charset_normalizer-3.4.2-cp312-cp312-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:cddf7bd982eaa998934a91f69d182aec997c6c468898efe6679af88283b498d3"}, + {file = "charset_normalizer-3.4.2-cp312-cp312-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:fcbe676a55d7445b22c10967bceaaf0ee69407fbe0ece4d032b6eb8d4565982a"}, + {file = "charset_normalizer-3.4.2-cp312-cp312-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:d41c4d287cfc69060fa91cae9683eacffad989f1a10811995fa309df656ec214"}, + {file = "charset_normalizer-3.4.2-cp312-cp312-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:4e594135de17ab3866138f496755f302b72157d115086d100c3f19370839dd3a"}, + {file = "charset_normalizer-3.4.2-cp312-cp312-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:cf713fe9a71ef6fd5adf7a79670135081cd4431c2943864757f0fa3a65b1fafd"}, + {file = "charset_normalizer-3.4.2-cp312-cp312-musllinux_1_2_aarch64.whl", hash = "sha256:a370b3e078e418187da8c3674eddb9d983ec09445c99a3a263c2011993522981"}, + {file = "charset_normalizer-3.4.2-cp312-cp312-musllinux_1_2_i686.whl", hash = "sha256:a955b438e62efdf7e0b7b52a64dc5c3396e2634baa62471768a64bc2adb73d5c"}, + {file = "charset_normalizer-3.4.2-cp312-cp312-musllinux_1_2_ppc64le.whl", hash = "sha256:7222ffd5e4de8e57e03ce2cef95a4c43c98fcb72ad86909abdfc2c17d227fc1b"}, + {file = "charset_normalizer-3.4.2-cp312-cp312-musllinux_1_2_s390x.whl", hash = "sha256:bee093bf902e1d8fc0ac143c88902c3dfc8941f7ea1d6a8dd2bcb786d33db03d"}, + {file = "charset_normalizer-3.4.2-cp312-cp312-musllinux_1_2_x86_64.whl", hash = "sha256:dedb8adb91d11846ee08bec4c8236c8549ac721c245678282dcb06b221aab59f"}, + {file = "charset_normalizer-3.4.2-cp312-cp312-win32.whl", hash = "sha256:db4c7bf0e07fc3b7d89ac2a5880a6a8062056801b83ff56d8464b70f65482b6c"}, + {file = "charset_normalizer-3.4.2-cp312-cp312-win_amd64.whl", hash = "sha256:5a9979887252a82fefd3d3ed2a8e3b937a7a809f65dcb1e068b090e165bbe99e"}, + {file = "charset_normalizer-3.4.2-cp313-cp313-macosx_10_13_universal2.whl", hash = "sha256:926ca93accd5d36ccdabd803392ddc3e03e6d4cd1cf17deff3b989ab8e9dbcf0"}, + {file = "charset_normalizer-3.4.2-cp313-cp313-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:eba9904b0f38a143592d9fc0e19e2df0fa2e41c3c3745554761c5f6447eedabf"}, + {file = "charset_normalizer-3.4.2-cp313-cp313-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:3fddb7e2c84ac87ac3a947cb4e66d143ca5863ef48e4a5ecb83bd48619e4634e"}, + {file = "charset_normalizer-3.4.2-cp313-cp313-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:98f862da73774290f251b9df8d11161b6cf25b599a66baf087c1ffe340e9bfd1"}, + {file = "charset_normalizer-3.4.2-cp313-cp313-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:6c9379d65defcab82d07b2a9dfbfc2e95bc8fe0ebb1b176a3190230a3ef0e07c"}, + {file = "charset_normalizer-3.4.2-cp313-cp313-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:e635b87f01ebc977342e2697d05b56632f5f879a4f15955dfe8cef2448b51691"}, + {file = "charset_normalizer-3.4.2-cp313-cp313-musllinux_1_2_aarch64.whl", hash = "sha256:1c95a1e2902a8b722868587c0e1184ad5c55631de5afc0eb96bc4b0d738092c0"}, + {file = "charset_normalizer-3.4.2-cp313-cp313-musllinux_1_2_i686.whl", hash = "sha256:ef8de666d6179b009dce7bcb2ad4c4a779f113f12caf8dc77f0162c29d20490b"}, + {file = "charset_normalizer-3.4.2-cp313-cp313-musllinux_1_2_ppc64le.whl", hash = "sha256:32fc0341d72e0f73f80acb0a2c94216bd704f4f0bce10aedea38f30502b271ff"}, + {file = "charset_normalizer-3.4.2-cp313-cp313-musllinux_1_2_s390x.whl", hash = "sha256:289200a18fa698949d2b39c671c2cc7a24d44096784e76614899a7ccf2574b7b"}, + {file = "charset_normalizer-3.4.2-cp313-cp313-musllinux_1_2_x86_64.whl", hash = "sha256:4a476b06fbcf359ad25d34a057b7219281286ae2477cc5ff5e3f70a246971148"}, + {file = "charset_normalizer-3.4.2-cp313-cp313-win32.whl", hash = "sha256:aaeeb6a479c7667fbe1099af9617c83aaca22182d6cf8c53966491a0f1b7ffb7"}, + {file = "charset_normalizer-3.4.2-cp313-cp313-win_amd64.whl", hash = "sha256:aa6af9e7d59f9c12b33ae4e9450619cf2488e2bbe9b44030905877f0b2324980"}, + {file = "charset_normalizer-3.4.2-cp37-cp37m-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:1cad5f45b3146325bb38d6855642f6fd609c3f7cad4dbaf75549bf3b904d3184"}, + {file = "charset_normalizer-3.4.2-cp37-cp37m-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:b2680962a4848b3c4f155dc2ee64505a9c57186d0d56b43123b17ca3de18f0fa"}, + {file = "charset_normalizer-3.4.2-cp37-cp37m-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:36b31da18b8890a76ec181c3cf44326bf2c48e36d393ca1b72b3f484113ea344"}, + {file = "charset_normalizer-3.4.2-cp37-cp37m-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:f4074c5a429281bf056ddd4c5d3b740ebca4d43ffffe2ef4bf4d2d05114299da"}, + {file = "charset_normalizer-3.4.2-cp37-cp37m-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:c9e36a97bee9b86ef9a1cf7bb96747eb7a15c2f22bdb5b516434b00f2a599f02"}, + {file = "charset_normalizer-3.4.2-cp37-cp37m-musllinux_1_2_aarch64.whl", hash = "sha256:1b1bde144d98e446b056ef98e59c256e9294f6b74d7af6846bf5ffdafd687a7d"}, + {file = "charset_normalizer-3.4.2-cp37-cp37m-musllinux_1_2_i686.whl", hash = "sha256:915f3849a011c1f593ab99092f3cecfcb4d65d8feb4a64cf1bf2d22074dc0ec4"}, + {file = "charset_normalizer-3.4.2-cp37-cp37m-musllinux_1_2_ppc64le.whl", hash = "sha256:fb707f3e15060adf5b7ada797624a6c6e0138e2a26baa089df64c68ee98e040f"}, + {file = "charset_normalizer-3.4.2-cp37-cp37m-musllinux_1_2_s390x.whl", hash = "sha256:25a23ea5c7edc53e0f29bae2c44fcb5a1aa10591aae107f2a2b2583a9c5cbc64"}, + {file = "charset_normalizer-3.4.2-cp37-cp37m-musllinux_1_2_x86_64.whl", hash = "sha256:770cab594ecf99ae64c236bc9ee3439c3f46be49796e265ce0cc8bc17b10294f"}, + {file = "charset_normalizer-3.4.2-cp37-cp37m-win32.whl", hash = "sha256:6a0289e4589e8bdfef02a80478f1dfcb14f0ab696b5a00e1f4b8a14a307a3c58"}, + {file = "charset_normalizer-3.4.2-cp37-cp37m-win_amd64.whl", hash = "sha256:6fc1f5b51fa4cecaa18f2bd7a003f3dd039dd615cd69a2afd6d3b19aed6775f2"}, + {file = "charset_normalizer-3.4.2-cp38-cp38-macosx_10_9_universal2.whl", hash = "sha256:76af085e67e56c8816c3ccf256ebd136def2ed9654525348cfa744b6802b69eb"}, + {file = "charset_normalizer-3.4.2-cp38-cp38-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:e45ba65510e2647721e35323d6ef54c7974959f6081b58d4ef5d87c60c84919a"}, + {file = "charset_normalizer-3.4.2-cp38-cp38-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:046595208aae0120559a67693ecc65dd75d46f7bf687f159127046628178dc45"}, + {file = "charset_normalizer-3.4.2-cp38-cp38-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:75d10d37a47afee94919c4fab4c22b9bc2a8bf7d4f46f87363bcf0573f3ff4f5"}, + {file = "charset_normalizer-3.4.2-cp38-cp38-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:6333b3aa5a12c26b2a4d4e7335a28f1475e0e5e17d69d55141ee3cab736f66d1"}, + {file = "charset_normalizer-3.4.2-cp38-cp38-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:e8323a9b031aa0393768b87f04b4164a40037fb2a3c11ac06a03ffecd3618027"}, + {file = "charset_normalizer-3.4.2-cp38-cp38-musllinux_1_2_aarch64.whl", hash = "sha256:24498ba8ed6c2e0b56d4acbf83f2d989720a93b41d712ebd4f4979660db4417b"}, + {file = "charset_normalizer-3.4.2-cp38-cp38-musllinux_1_2_i686.whl", hash = "sha256:844da2b5728b5ce0e32d863af26f32b5ce61bc4273a9c720a9f3aa9df73b1455"}, + {file = "charset_normalizer-3.4.2-cp38-cp38-musllinux_1_2_ppc64le.whl", hash = "sha256:65c981bdbd3f57670af8b59777cbfae75364b483fa8a9f420f08094531d54a01"}, + {file = "charset_normalizer-3.4.2-cp38-cp38-musllinux_1_2_s390x.whl", hash = "sha256:3c21d4fca343c805a52c0c78edc01e3477f6dd1ad7c47653241cf2a206d4fc58"}, + {file = "charset_normalizer-3.4.2-cp38-cp38-musllinux_1_2_x86_64.whl", hash = "sha256:dc7039885fa1baf9be153a0626e337aa7ec8bf96b0128605fb0d77788ddc1681"}, + {file = "charset_normalizer-3.4.2-cp38-cp38-win32.whl", hash = "sha256:8272b73e1c5603666618805fe821edba66892e2870058c94c53147602eab29c7"}, + {file = "charset_normalizer-3.4.2-cp38-cp38-win_amd64.whl", hash = "sha256:70f7172939fdf8790425ba31915bfbe8335030f05b9913d7ae00a87d4395620a"}, + {file = "charset_normalizer-3.4.2-cp39-cp39-macosx_10_9_universal2.whl", hash = "sha256:005fa3432484527f9732ebd315da8da8001593e2cf46a3d817669f062c3d9ed4"}, + {file = "charset_normalizer-3.4.2-cp39-cp39-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:e92fca20c46e9f5e1bb485887d074918b13543b1c2a1185e69bb8d17ab6236a7"}, + {file = "charset_normalizer-3.4.2-cp39-cp39-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:50bf98d5e563b83cc29471fa114366e6806bc06bc7a25fd59641e41445327836"}, + {file = "charset_normalizer-3.4.2-cp39-cp39-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:721c76e84fe669be19c5791da68232ca2e05ba5185575086e384352e2c309597"}, + {file = "charset_normalizer-3.4.2-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:82d8fd25b7f4675d0c47cf95b594d4e7b158aca33b76aa63d07186e13c0e0ab7"}, + {file = "charset_normalizer-3.4.2-cp39-cp39-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:b3daeac64d5b371dea99714f08ffc2c208522ec6b06fbc7866a450dd446f5c0f"}, + {file = "charset_normalizer-3.4.2-cp39-cp39-musllinux_1_2_aarch64.whl", hash = "sha256:dccab8d5fa1ef9bfba0590ecf4d46df048d18ffe3eec01eeb73a42e0d9e7a8ba"}, + {file = "charset_normalizer-3.4.2-cp39-cp39-musllinux_1_2_i686.whl", hash = "sha256:aaf27faa992bfee0264dc1f03f4c75e9fcdda66a519db6b957a3f826e285cf12"}, + {file = "charset_normalizer-3.4.2-cp39-cp39-musllinux_1_2_ppc64le.whl", hash = "sha256:eb30abc20df9ab0814b5a2524f23d75dcf83cde762c161917a2b4b7b55b1e518"}, + {file = "charset_normalizer-3.4.2-cp39-cp39-musllinux_1_2_s390x.whl", hash = "sha256:c72fbbe68c6f32f251bdc08b8611c7b3060612236e960ef848e0a517ddbe76c5"}, + {file = "charset_normalizer-3.4.2-cp39-cp39-musllinux_1_2_x86_64.whl", hash = "sha256:982bb1e8b4ffda883b3d0a521e23abcd6fd17418f6d2c4118d257a10199c0ce3"}, + {file = "charset_normalizer-3.4.2-cp39-cp39-win32.whl", hash = "sha256:43e0933a0eff183ee85833f341ec567c0980dae57c464d8a508e1b2ceb336471"}, + {file = "charset_normalizer-3.4.2-cp39-cp39-win_amd64.whl", hash = "sha256:d11b54acf878eef558599658b0ffca78138c8c3655cf4f3a4a673c437e67732e"}, + {file = "charset_normalizer-3.4.2-py3-none-any.whl", hash = "sha256:7f56930ab0abd1c45cd15be65cc741c28b1c9a34876ce8c17a2fa107810c0af0"}, + {file = "charset_normalizer-3.4.2.tar.gz", hash = "sha256:5baececa9ecba31eff645232d59845c07aa030f0c81ee70184a90d35099a0e63"}, +] + +[[package]] +name = "click" +version = "8.1.8" +description = "Composable command line interface toolkit" +optional = false +python-versions = ">=3.7" +groups = ["main"] +files = [ + {file = "click-8.1.8-py3-none-any.whl", hash = "sha256:63c132bbbed01578a06712a2d1f497bb62d9c1c0d329b7903a866228027263b2"}, + {file = "click-8.1.8.tar.gz", hash = "sha256:ed53c9d8990d83c2a27deae68e4ee337473f6330c040a31d4225c9574d16096a"}, +] + +[package.dependencies] +colorama = {version = "*", markers = "platform_system == \"Windows\""} + +[[package]] +name = "colorama" +version = "0.4.6" +description = "Cross-platform colored terminal text." +optional = false +python-versions = "!=3.0.*,!=3.1.*,!=3.2.*,!=3.3.*,!=3.4.*,!=3.5.*,!=3.6.*,>=2.7" +groups = ["main"] +markers = "platform_system == \"Windows\"" +files = [ + {file = "colorama-0.4.6-py2.py3-none-any.whl", hash = "sha256:4f1d9991f5acc0ca119f9d443620b77f9d6b33703e51011c16baf57afb285fc6"}, + {file = "colorama-0.4.6.tar.gz", hash = "sha256:08695f5cb7ed6e0531a20572697297273c47b8cae5a63ffc6d6ed5c201be6e44"}, +] + +[[package]] +name = "filelock" +version = "3.18.0" +description = "A platform independent file lock." +optional = false +python-versions = ">=3.9" +groups = ["main"] +files = [ + {file = "filelock-3.18.0-py3-none-any.whl", hash = "sha256:c401f4f8377c4464e6db25fff06205fd89bdd83b65eb0488ed1b160f780e21de"}, + {file = "filelock-3.18.0.tar.gz", hash = "sha256:adbc88eabb99d2fec8c9c1b229b171f18afa655400173ddc653d5d01501fb9f2"}, +] + +[package.extras] +docs = ["furo (>=2024.8.6)", "sphinx (>=8.1.3)", "sphinx-autodoc-typehints (>=3)"] +testing = ["covdefaults (>=2.3)", "coverage (>=7.6.10)", "diff-cover (>=9.2.1)", "pytest (>=8.3.4)", "pytest-asyncio (>=0.25.2)", "pytest-cov (>=6)", "pytest-mock (>=3.14)", "pytest-timeout (>=2.3.1)", "virtualenv (>=20.28.1)"] +typing = ["typing-extensions (>=4.12.2) ; python_version < \"3.11\""] + +[[package]] +name = "fsspec" +version = "2025.5.1" +description = "File-system specification" +optional = false +python-versions = ">=3.9" +groups = ["main"] +files = [ + {file = "fsspec-2025.5.1-py3-none-any.whl", hash = "sha256:24d3a2e663d5fc735ab256263c4075f374a174c3410c0b25e5bd1970bceaa462"}, + {file = "fsspec-2025.5.1.tar.gz", hash = "sha256:2e55e47a540b91843b755e83ded97c6e897fa0942b11490113f09e9c443c2475"}, +] + +[package.extras] +abfs = ["adlfs"] +adl = ["adlfs"] +arrow = ["pyarrow (>=1)"] +dask = ["dask", "distributed"] +dev = ["pre-commit", "ruff"] +doc = ["numpydoc", "sphinx", "sphinx-design", "sphinx-rtd-theme", "yarl"] +dropbox = ["dropbox", "dropboxdrivefs", "requests"] +full = ["adlfs", "aiohttp (!=4.0.0a0,!=4.0.0a1)", "dask", "distributed", "dropbox", "dropboxdrivefs", "fusepy", "gcsfs", "libarchive-c", "ocifs", "panel", "paramiko", "pyarrow (>=1)", "pygit2", "requests", "s3fs", "smbprotocol", "tqdm"] +fuse = ["fusepy"] +gcs = ["gcsfs"] +git = ["pygit2"] +github = ["requests"] +gs = ["gcsfs"] +gui = ["panel"] +hdfs = ["pyarrow (>=1)"] +http = ["aiohttp (!=4.0.0a0,!=4.0.0a1)"] +libarchive = ["libarchive-c"] +oci = ["ocifs"] +s3 = ["s3fs"] +sftp = ["paramiko"] +smb = ["smbprotocol"] +ssh = ["paramiko"] +test = ["aiohttp (!=4.0.0a0,!=4.0.0a1)", "numpy", "pytest", "pytest-asyncio (!=0.22.0)", "pytest-benchmark", "pytest-cov", "pytest-mock", "pytest-recording", "pytest-rerunfailures", "requests"] +test-downstream = ["aiobotocore (>=2.5.4,<3.0.0)", "dask[dataframe,test]", "moto[server] (>4,<5)", "pytest-timeout", "xarray"] +test-full = ["adlfs", "aiohttp (!=4.0.0a0,!=4.0.0a1)", "cloudpickle", "dask", "distributed", "dropbox", "dropboxdrivefs", "fastparquet", "fusepy", "gcsfs", "jinja2", "kerchunk", "libarchive-c", "lz4", "notebook", "numpy", "ocifs", "pandas", "panel", "paramiko", "pyarrow", "pyarrow (>=1)", "pyftpdlib", "pygit2", "pytest", "pytest-asyncio (!=0.22.0)", "pytest-benchmark", "pytest-cov", "pytest-mock", "pytest-recording", "pytest-rerunfailures", "python-snappy", "requests", "smbprotocol", "tqdm", "urllib3", "zarr", "zstandard"] +tqdm = ["tqdm"] + +[[package]] +name = "huggingface-hub" +version = "0.31.4" +description = "Client library to download and publish models, datasets and other repos on the huggingface.co hub" +optional = false +python-versions = ">=3.8.0" +groups = ["main"] +files = [ + {file = "huggingface_hub-0.31.4-py3-none-any.whl", hash = "sha256:4f70704760296cc69b612916056e9845f5490a33782b924fc531767967acc15d"}, + {file = "huggingface_hub-0.31.4.tar.gz", hash = "sha256:5a7bc710b9f9c028aee5b1476867b4ec5c1b92f043cb364d5fdc54354757e4ce"}, +] + +[package.dependencies] +filelock = "*" +fsspec = ">=2023.5.0" +packaging = ">=20.9" +pyyaml = ">=5.1" +requests = "*" +tqdm = ">=4.42.1" +typing-extensions = ">=3.7.4.3" + +[package.extras] +all = ["InquirerPy (==0.3.4)", "Jinja2", "Pillow", "aiohttp", "fastapi", "gradio (>=4.0.0)", "jedi", "libcst (==1.4.0)", "mypy (==1.5.1)", "numpy", "pytest (>=8.1.1,<8.2.2)", "pytest-asyncio", "pytest-cov", "pytest-env", "pytest-mock", "pytest-rerunfailures", "pytest-vcr", "pytest-xdist", "ruff (>=0.9.0)", "soundfile", "types-PyYAML", "types-requests", "types-simplejson", "types-toml", "types-tqdm", "types-urllib3", "typing-extensions (>=4.8.0)", "urllib3 (<2.0)"] +cli = ["InquirerPy (==0.3.4)"] +dev = ["InquirerPy (==0.3.4)", "Jinja2", "Pillow", "aiohttp", "fastapi", "gradio (>=4.0.0)", "jedi", "libcst (==1.4.0)", "mypy (==1.5.1)", "numpy", "pytest (>=8.1.1,<8.2.2)", "pytest-asyncio", "pytest-cov", "pytest-env", "pytest-mock", "pytest-rerunfailures", "pytest-vcr", "pytest-xdist", "ruff (>=0.9.0)", "soundfile", "types-PyYAML", "types-requests", "types-simplejson", "types-toml", "types-tqdm", "types-urllib3", "typing-extensions (>=4.8.0)", "urllib3 (<2.0)"] +fastai = ["fastai (>=2.4)", "fastcore (>=1.3.27)", "toml"] +hf-transfer = ["hf-transfer (>=0.1.4)"] +hf-xet = ["hf-xet (>=1.1.1,<2.0.0)"] +inference = ["aiohttp"] +quality = ["libcst (==1.4.0)", "mypy (==1.5.1)", "ruff (>=0.9.0)"] +tensorflow = ["graphviz", "pydot", "tensorflow"] +tensorflow-testing = ["keras (<3.0)", "tensorflow"] +testing = ["InquirerPy (==0.3.4)", "Jinja2", "Pillow", "aiohttp", "fastapi", "gradio (>=4.0.0)", "jedi", "numpy", "pytest (>=8.1.1,<8.2.2)", "pytest-asyncio", "pytest-cov", "pytest-env", "pytest-mock", "pytest-rerunfailures", "pytest-vcr", "pytest-xdist", "soundfile", "urllib3 (<2.0)"] +torch = ["safetensors[torch]", "torch"] +typing = ["types-PyYAML", "types-requests", "types-simplejson", "types-toml", "types-tqdm", "types-urllib3", "typing-extensions (>=4.8.0)"] + +[[package]] +name = "idna" +version = "3.10" +description = "Internationalized Domain Names in Applications (IDNA)" +optional = false +python-versions = ">=3.6" +groups = ["main"] +files = [ + {file = "idna-3.10-py3-none-any.whl", hash = "sha256:946d195a0d259cbba61165e88e65941f16e9b36ea6ddb97f00452bae8b1287d3"}, + {file = "idna-3.10.tar.gz", hash = "sha256:12f65c9b470abda6dc35cf8e63cc574b1c52b11df2c86030af0ac09b01b13ea9"}, +] + +[package.extras] +all = ["flake8 (>=7.1.1)", "mypy (>=1.11.2)", "pytest (>=8.3.2)", "ruff (>=0.6.2)"] + +[[package]] +name = "numpy" +version = "1.26.4" +description = "Fundamental package for array computing in Python" +optional = false +python-versions = ">=3.9" +groups = ["main"] +files = [ + {file = "numpy-1.26.4-cp310-cp310-macosx_10_9_x86_64.whl", hash = "sha256:9ff0f4f29c51e2803569d7a51c2304de5554655a60c5d776e35b4a41413830d0"}, + {file = "numpy-1.26.4-cp310-cp310-macosx_11_0_arm64.whl", hash = "sha256:2e4ee3380d6de9c9ec04745830fd9e2eccb3e6cf790d39d7b98ffd19b0dd754a"}, + {file = "numpy-1.26.4-cp310-cp310-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:d209d8969599b27ad20994c8e41936ee0964e6da07478d6c35016bc386b66ad4"}, + {file = "numpy-1.26.4-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:ffa75af20b44f8dba823498024771d5ac50620e6915abac414251bd971b4529f"}, + {file = "numpy-1.26.4-cp310-cp310-musllinux_1_1_aarch64.whl", hash = "sha256:62b8e4b1e28009ef2846b4c7852046736bab361f7aeadeb6a5b89ebec3c7055a"}, + {file = "numpy-1.26.4-cp310-cp310-musllinux_1_1_x86_64.whl", hash = "sha256:a4abb4f9001ad2858e7ac189089c42178fcce737e4169dc61321660f1a96c7d2"}, + {file = "numpy-1.26.4-cp310-cp310-win32.whl", hash = "sha256:bfe25acf8b437eb2a8b2d49d443800a5f18508cd811fea3181723922a8a82b07"}, + {file = "numpy-1.26.4-cp310-cp310-win_amd64.whl", hash = "sha256:b97fe8060236edf3662adfc2c633f56a08ae30560c56310562cb4f95500022d5"}, + {file = "numpy-1.26.4-cp311-cp311-macosx_10_9_x86_64.whl", hash = "sha256:4c66707fabe114439db9068ee468c26bbdf909cac0fb58686a42a24de1760c71"}, + {file = "numpy-1.26.4-cp311-cp311-macosx_11_0_arm64.whl", hash = "sha256:edd8b5fe47dab091176d21bb6de568acdd906d1887a4584a15a9a96a1dca06ef"}, + {file = "numpy-1.26.4-cp311-cp311-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:7ab55401287bfec946ced39700c053796e7cc0e3acbef09993a9ad2adba6ca6e"}, + {file = "numpy-1.26.4-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:666dbfb6ec68962c033a450943ded891bed2d54e6755e35e5835d63f4f6931d5"}, + {file = "numpy-1.26.4-cp311-cp311-musllinux_1_1_aarch64.whl", hash = "sha256:96ff0b2ad353d8f990b63294c8986f1ec3cb19d749234014f4e7eb0112ceba5a"}, + {file = "numpy-1.26.4-cp311-cp311-musllinux_1_1_x86_64.whl", hash = "sha256:60dedbb91afcbfdc9bc0b1f3f402804070deed7392c23eb7a7f07fa857868e8a"}, + {file = "numpy-1.26.4-cp311-cp311-win32.whl", hash = "sha256:1af303d6b2210eb850fcf03064d364652b7120803a0b872f5211f5234b399f20"}, + {file = "numpy-1.26.4-cp311-cp311-win_amd64.whl", hash = "sha256:cd25bcecc4974d09257ffcd1f098ee778f7834c3ad767fe5db785be9a4aa9cb2"}, + {file = "numpy-1.26.4-cp312-cp312-macosx_10_9_x86_64.whl", hash = "sha256:b3ce300f3644fb06443ee2222c2201dd3a89ea6040541412b8fa189341847218"}, + {file = "numpy-1.26.4-cp312-cp312-macosx_11_0_arm64.whl", hash = "sha256:03a8c78d01d9781b28a6989f6fa1bb2c4f2d51201cf99d3dd875df6fbd96b23b"}, + {file = "numpy-1.26.4-cp312-cp312-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:9fad7dcb1aac3c7f0584a5a8133e3a43eeb2fe127f47e3632d43d677c66c102b"}, + {file = "numpy-1.26.4-cp312-cp312-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:675d61ffbfa78604709862923189bad94014bef562cc35cf61d3a07bba02a7ed"}, + {file = "numpy-1.26.4-cp312-cp312-musllinux_1_1_aarch64.whl", hash = "sha256:ab47dbe5cc8210f55aa58e4805fe224dac469cde56b9f731a4c098b91917159a"}, + {file = "numpy-1.26.4-cp312-cp312-musllinux_1_1_x86_64.whl", hash = "sha256:1dda2e7b4ec9dd512f84935c5f126c8bd8b9f2fc001e9f54af255e8c5f16b0e0"}, + {file = "numpy-1.26.4-cp312-cp312-win32.whl", hash = "sha256:50193e430acfc1346175fcbdaa28ffec49947a06918b7b92130744e81e640110"}, + {file = "numpy-1.26.4-cp312-cp312-win_amd64.whl", hash = "sha256:08beddf13648eb95f8d867350f6a018a4be2e5ad54c8d8caed89ebca558b2818"}, + {file = "numpy-1.26.4-cp39-cp39-macosx_10_9_x86_64.whl", hash = "sha256:7349ab0fa0c429c82442a27a9673fc802ffdb7c7775fad780226cb234965e53c"}, + {file = "numpy-1.26.4-cp39-cp39-macosx_11_0_arm64.whl", hash = "sha256:52b8b60467cd7dd1e9ed082188b4e6bb35aa5cdd01777621a1658910745b90be"}, + {file = "numpy-1.26.4-cp39-cp39-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:d5241e0a80d808d70546c697135da2c613f30e28251ff8307eb72ba696945764"}, + {file = "numpy-1.26.4-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:f870204a840a60da0b12273ef34f7051e98c3b5961b61b0c2c1be6dfd64fbcd3"}, + {file = "numpy-1.26.4-cp39-cp39-musllinux_1_1_aarch64.whl", hash = "sha256:679b0076f67ecc0138fd2ede3a8fd196dddc2ad3254069bcb9faf9a79b1cebcd"}, + {file = "numpy-1.26.4-cp39-cp39-musllinux_1_1_x86_64.whl", hash = "sha256:47711010ad8555514b434df65f7d7b076bb8261df1ca9bb78f53d3b2db02e95c"}, + {file = "numpy-1.26.4-cp39-cp39-win32.whl", hash = "sha256:a354325ee03388678242a4d7ebcd08b5c727033fcff3b2f536aea978e15ee9e6"}, + {file = "numpy-1.26.4-cp39-cp39-win_amd64.whl", hash = "sha256:3373d5d70a5fe74a2c1bb6d2cfd9609ecf686d47a2d7b1d37a8f3b6bf6003aea"}, + {file = "numpy-1.26.4-pp39-pypy39_pp73-macosx_10_9_x86_64.whl", hash = "sha256:afedb719a9dcfc7eaf2287b839d8198e06dcd4cb5d276a3df279231138e83d30"}, + {file = "numpy-1.26.4-pp39-pypy39_pp73-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:95a7476c59002f2f6c590b9b7b998306fba6a5aa646b1e22ddfeaf8f78c3a29c"}, + {file = "numpy-1.26.4-pp39-pypy39_pp73-win_amd64.whl", hash = "sha256:7e50d0a0cc3189f9cb0aeb3a6a6af18c16f59f004b866cd2be1c14b36134a4a0"}, + {file = "numpy-1.26.4.tar.gz", hash = "sha256:2a02aba9ed12e4ac4eb3ea9421c420301a0c6460d9830d74a9df87efa4912010"}, +] + +[[package]] +name = "packaging" +version = "25.0" +description = "Core utilities for Python packages" +optional = false +python-versions = ">=3.8" +groups = ["main"] +files = [ + {file = "packaging-25.0-py3-none-any.whl", hash = "sha256:29572ef2b1f17581046b3a2227d5c611fb25ec70ca1ba8554b24b0e69331a484"}, + {file = "packaging-25.0.tar.gz", hash = "sha256:d443872c98d677bf60f6a1f2f8c1cb748e8fe762d2bf9d3148b5599295b0fc4f"}, +] + +[[package]] +name = "pyarrow" +version = "15.0.2" +description = "Python library for Apache Arrow" +optional = false +python-versions = ">=3.8" +groups = ["main"] +files = [ + {file = "pyarrow-15.0.2-cp310-cp310-macosx_10_15_x86_64.whl", hash = "sha256:88b340f0a1d05b5ccc3d2d986279045655b1fe8e41aba6ca44ea28da0d1455d8"}, + {file = "pyarrow-15.0.2-cp310-cp310-macosx_11_0_arm64.whl", hash = "sha256:eaa8f96cecf32da508e6c7f69bb8401f03745c050c1dd42ec2596f2e98deecac"}, + {file = "pyarrow-15.0.2-cp310-cp310-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:23c6753ed4f6adb8461e7c383e418391b8d8453c5d67e17f416c3a5d5709afbd"}, + {file = "pyarrow-15.0.2-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:f639c059035011db8c0497e541a8a45d98a58dbe34dc8fadd0ef128f2cee46e5"}, + {file = "pyarrow-15.0.2-cp310-cp310-manylinux_2_28_aarch64.whl", hash = "sha256:290e36a59a0993e9a5224ed2fb3e53375770f07379a0ea03ee2fce2e6d30b423"}, + {file = "pyarrow-15.0.2-cp310-cp310-manylinux_2_28_x86_64.whl", hash = "sha256:06c2bb2a98bc792f040bef31ad3e9be6a63d0cb39189227c08a7d955db96816e"}, + {file = "pyarrow-15.0.2-cp310-cp310-win_amd64.whl", hash = "sha256:f7a197f3670606a960ddc12adbe8075cea5f707ad7bf0dffa09637fdbb89f76c"}, + {file = "pyarrow-15.0.2-cp311-cp311-macosx_10_15_x86_64.whl", hash = "sha256:5f8bc839ea36b1f99984c78e06e7a06054693dc2af8920f6fb416b5bca9944e4"}, + {file = "pyarrow-15.0.2-cp311-cp311-macosx_11_0_arm64.whl", hash = "sha256:f5e81dfb4e519baa6b4c80410421528c214427e77ca0ea9461eb4097c328fa33"}, + {file = "pyarrow-15.0.2-cp311-cp311-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:3a4f240852b302a7af4646c8bfe9950c4691a419847001178662a98915fd7ee7"}, + {file = "pyarrow-15.0.2-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:4e7d9cfb5a1e648e172428c7a42b744610956f3b70f524aa3a6c02a448ba853e"}, + {file = "pyarrow-15.0.2-cp311-cp311-manylinux_2_28_aarch64.whl", hash = "sha256:2d4f905209de70c0eb5b2de6763104d5a9a37430f137678edfb9a675bac9cd98"}, + {file = "pyarrow-15.0.2-cp311-cp311-manylinux_2_28_x86_64.whl", hash = "sha256:90adb99e8ce5f36fbecbbc422e7dcbcbed07d985eed6062e459e23f9e71fd197"}, + {file = "pyarrow-15.0.2-cp311-cp311-win_amd64.whl", hash = "sha256:b116e7fd7889294cbd24eb90cd9bdd3850be3738d61297855a71ac3b8124ee38"}, + {file = "pyarrow-15.0.2-cp312-cp312-macosx_10_15_x86_64.whl", hash = "sha256:25335e6f1f07fdaa026a61c758ee7d19ce824a866b27bba744348fa73bb5a440"}, + {file = "pyarrow-15.0.2-cp312-cp312-macosx_11_0_arm64.whl", hash = "sha256:90f19e976d9c3d8e73c80be84ddbe2f830b6304e4c576349d9360e335cd627fc"}, + {file = "pyarrow-15.0.2-cp312-cp312-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:a22366249bf5fd40ddacc4f03cd3160f2d7c247692945afb1899bab8a140ddfb"}, + {file = "pyarrow-15.0.2-cp312-cp312-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:c2a335198f886b07e4b5ea16d08ee06557e07db54a8400cc0d03c7f6a22f785f"}, + {file = "pyarrow-15.0.2-cp312-cp312-manylinux_2_28_aarch64.whl", hash = "sha256:3e6d459c0c22f0b9c810a3917a1de3ee704b021a5fb8b3bacf968eece6df098f"}, + {file = "pyarrow-15.0.2-cp312-cp312-manylinux_2_28_x86_64.whl", hash = "sha256:033b7cad32198754d93465dcfb71d0ba7cb7cd5c9afd7052cab7214676eec38b"}, + {file = "pyarrow-15.0.2-cp312-cp312-win_amd64.whl", hash = "sha256:29850d050379d6e8b5a693098f4de7fd6a2bea4365bfd073d7c57c57b95041ee"}, + {file = "pyarrow-15.0.2-cp38-cp38-macosx_10_15_x86_64.whl", hash = "sha256:7167107d7fb6dcadb375b4b691b7e316f4368f39f6f45405a05535d7ad5e5058"}, + {file = "pyarrow-15.0.2-cp38-cp38-macosx_11_0_arm64.whl", hash = "sha256:e85241b44cc3d365ef950432a1b3bd44ac54626f37b2e3a0cc89c20e45dfd8bf"}, + {file = "pyarrow-15.0.2-cp38-cp38-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:248723e4ed3255fcd73edcecc209744d58a9ca852e4cf3d2577811b6d4b59818"}, + {file = "pyarrow-15.0.2-cp38-cp38-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:3ff3bdfe6f1b81ca5b73b70a8d482d37a766433823e0c21e22d1d7dde76ca33f"}, + {file = "pyarrow-15.0.2-cp38-cp38-manylinux_2_28_aarch64.whl", hash = "sha256:f3d77463dee7e9f284ef42d341689b459a63ff2e75cee2b9302058d0d98fe142"}, + {file = "pyarrow-15.0.2-cp38-cp38-manylinux_2_28_x86_64.whl", hash = "sha256:8c1faf2482fb89766e79745670cbca04e7018497d85be9242d5350cba21357e1"}, + {file = "pyarrow-15.0.2-cp38-cp38-win_amd64.whl", hash = "sha256:28f3016958a8e45a1069303a4a4f6a7d4910643fc08adb1e2e4a7ff056272ad3"}, + {file = "pyarrow-15.0.2-cp39-cp39-macosx_10_15_x86_64.whl", hash = "sha256:89722cb64286ab3d4daf168386f6968c126057b8c7ec3ef96302e81d8cdb8ae4"}, + {file = "pyarrow-15.0.2-cp39-cp39-macosx_11_0_arm64.whl", hash = "sha256:cd0ba387705044b3ac77b1b317165c0498299b08261d8122c96051024f953cd5"}, + {file = "pyarrow-15.0.2-cp39-cp39-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:ad2459bf1f22b6a5cdcc27ebfd99307d5526b62d217b984b9f5c974651398832"}, + {file = "pyarrow-15.0.2-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:58922e4bfece8b02abf7159f1f53a8f4d9f8e08f2d988109126c17c3bb261f22"}, + {file = "pyarrow-15.0.2-cp39-cp39-manylinux_2_28_aarch64.whl", hash = "sha256:adccc81d3dc0478ea0b498807b39a8d41628fa9210729b2f718b78cb997c7c91"}, + {file = "pyarrow-15.0.2-cp39-cp39-manylinux_2_28_x86_64.whl", hash = "sha256:8bd2baa5fe531571847983f36a30ddbf65261ef23e496862ece83bdceb70420d"}, + {file = "pyarrow-15.0.2-cp39-cp39-win_amd64.whl", hash = "sha256:6669799a1d4ca9da9c7e06ef48368320f5856f36f9a4dd31a11839dda3f6cc8c"}, + {file = "pyarrow-15.0.2.tar.gz", hash = "sha256:9c9bc803cb3b7bfacc1e96ffbfd923601065d9d3f911179d81e72d99fd74a3d9"}, +] + +[package.dependencies] +numpy = ">=1.16.6,<2" + +[[package]] +name = "pyyaml" +version = "6.0.2" +description = "YAML parser and emitter for Python" +optional = false +python-versions = ">=3.8" +groups = ["main"] +files = [ + {file = "PyYAML-6.0.2-cp310-cp310-macosx_10_9_x86_64.whl", hash = "sha256:0a9a2848a5b7feac301353437eb7d5957887edbf81d56e903999a75a3d743086"}, + {file = "PyYAML-6.0.2-cp310-cp310-macosx_11_0_arm64.whl", hash = "sha256:29717114e51c84ddfba879543fb232a6ed60086602313ca38cce623c1d62cfbf"}, + {file = "PyYAML-6.0.2-cp310-cp310-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:8824b5a04a04a047e72eea5cec3bc266db09e35de6bdfe34c9436ac5ee27d237"}, + {file = "PyYAML-6.0.2-cp310-cp310-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:7c36280e6fb8385e520936c3cb3b8042851904eba0e58d277dca80a5cfed590b"}, + {file = "PyYAML-6.0.2-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:ec031d5d2feb36d1d1a24380e4db6d43695f3748343d99434e6f5f9156aaa2ed"}, + {file = "PyYAML-6.0.2-cp310-cp310-musllinux_1_1_aarch64.whl", hash = "sha256:936d68689298c36b53b29f23c6dbb74de12b4ac12ca6cfe0e047bedceea56180"}, + {file = "PyYAML-6.0.2-cp310-cp310-musllinux_1_1_x86_64.whl", hash = "sha256:23502f431948090f597378482b4812b0caae32c22213aecf3b55325e049a6c68"}, + {file = "PyYAML-6.0.2-cp310-cp310-win32.whl", hash = "sha256:2e99c6826ffa974fe6e27cdb5ed0021786b03fc98e5ee3c5bfe1fd5015f42b99"}, + {file = "PyYAML-6.0.2-cp310-cp310-win_amd64.whl", hash = "sha256:a4d3091415f010369ae4ed1fc6b79def9416358877534caf6a0fdd2146c87a3e"}, + {file = "PyYAML-6.0.2-cp311-cp311-macosx_10_9_x86_64.whl", hash = "sha256:cc1c1159b3d456576af7a3e4d1ba7e6924cb39de8f67111c735f6fc832082774"}, + {file = "PyYAML-6.0.2-cp311-cp311-macosx_11_0_arm64.whl", hash = "sha256:1e2120ef853f59c7419231f3bf4e7021f1b936f6ebd222406c3b60212205d2ee"}, + {file = "PyYAML-6.0.2-cp311-cp311-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:5d225db5a45f21e78dd9358e58a98702a0302f2659a3c6cd320564b75b86f47c"}, + {file = "PyYAML-6.0.2-cp311-cp311-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:5ac9328ec4831237bec75defaf839f7d4564be1e6b25ac710bd1a96321cc8317"}, + {file = "PyYAML-6.0.2-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:3ad2a3decf9aaba3d29c8f537ac4b243e36bef957511b4766cb0057d32b0be85"}, + {file = "PyYAML-6.0.2-cp311-cp311-musllinux_1_1_aarch64.whl", hash = "sha256:ff3824dc5261f50c9b0dfb3be22b4567a6f938ccce4587b38952d85fd9e9afe4"}, + {file = "PyYAML-6.0.2-cp311-cp311-musllinux_1_1_x86_64.whl", hash = "sha256:797b4f722ffa07cc8d62053e4cff1486fa6dc094105d13fea7b1de7d8bf71c9e"}, + {file = "PyYAML-6.0.2-cp311-cp311-win32.whl", hash = "sha256:11d8f3dd2b9c1207dcaf2ee0bbbfd5991f571186ec9cc78427ba5bd32afae4b5"}, + {file = "PyYAML-6.0.2-cp311-cp311-win_amd64.whl", hash = "sha256:e10ce637b18caea04431ce14fabcf5c64a1c61ec9c56b071a4b7ca131ca52d44"}, + {file = "PyYAML-6.0.2-cp312-cp312-macosx_10_9_x86_64.whl", hash = "sha256:c70c95198c015b85feafc136515252a261a84561b7b1d51e3384e0655ddf25ab"}, + {file = "PyYAML-6.0.2-cp312-cp312-macosx_11_0_arm64.whl", hash = "sha256:ce826d6ef20b1bc864f0a68340c8b3287705cae2f8b4b1d932177dcc76721725"}, + {file = "PyYAML-6.0.2-cp312-cp312-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:1f71ea527786de97d1a0cc0eacd1defc0985dcf6b3f17bb77dcfc8c34bec4dc5"}, + {file = "PyYAML-6.0.2-cp312-cp312-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:9b22676e8097e9e22e36d6b7bda33190d0d400f345f23d4065d48f4ca7ae0425"}, + {file = "PyYAML-6.0.2-cp312-cp312-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:80bab7bfc629882493af4aa31a4cfa43a4c57c83813253626916b8c7ada83476"}, + {file = "PyYAML-6.0.2-cp312-cp312-musllinux_1_1_aarch64.whl", hash = "sha256:0833f8694549e586547b576dcfaba4a6b55b9e96098b36cdc7ebefe667dfed48"}, + {file = "PyYAML-6.0.2-cp312-cp312-musllinux_1_1_x86_64.whl", hash = "sha256:8b9c7197f7cb2738065c481a0461e50ad02f18c78cd75775628afb4d7137fb3b"}, + {file = "PyYAML-6.0.2-cp312-cp312-win32.whl", hash = "sha256:ef6107725bd54b262d6dedcc2af448a266975032bc85ef0172c5f059da6325b4"}, + {file = "PyYAML-6.0.2-cp312-cp312-win_amd64.whl", hash = "sha256:7e7401d0de89a9a855c839bc697c079a4af81cf878373abd7dc625847d25cbd8"}, + {file = "PyYAML-6.0.2-cp313-cp313-macosx_10_13_x86_64.whl", hash = "sha256:efdca5630322a10774e8e98e1af481aad470dd62c3170801852d752aa7a783ba"}, + {file = "PyYAML-6.0.2-cp313-cp313-macosx_11_0_arm64.whl", hash = "sha256:50187695423ffe49e2deacb8cd10510bc361faac997de9efef88badc3bb9e2d1"}, + {file = "PyYAML-6.0.2-cp313-cp313-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:0ffe8360bab4910ef1b9e87fb812d8bc0a308b0d0eef8c8f44e0254ab3b07133"}, + {file = "PyYAML-6.0.2-cp313-cp313-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:17e311b6c678207928d649faa7cb0d7b4c26a0ba73d41e99c4fff6b6c3276484"}, + {file = "PyYAML-6.0.2-cp313-cp313-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:70b189594dbe54f75ab3a1acec5f1e3faa7e8cf2f1e08d9b561cb41b845f69d5"}, + {file = "PyYAML-6.0.2-cp313-cp313-musllinux_1_1_aarch64.whl", hash = "sha256:41e4e3953a79407c794916fa277a82531dd93aad34e29c2a514c2c0c5fe971cc"}, + {file = "PyYAML-6.0.2-cp313-cp313-musllinux_1_1_x86_64.whl", hash = "sha256:68ccc6023a3400877818152ad9a1033e3db8625d899c72eacb5a668902e4d652"}, + {file = "PyYAML-6.0.2-cp313-cp313-win32.whl", hash = "sha256:bc2fa7c6b47d6bc618dd7fb02ef6fdedb1090ec036abab80d4681424b84c1183"}, + {file = "PyYAML-6.0.2-cp313-cp313-win_amd64.whl", hash = "sha256:8388ee1976c416731879ac16da0aff3f63b286ffdd57cdeb95f3f2e085687563"}, + {file = "PyYAML-6.0.2-cp38-cp38-macosx_10_9_x86_64.whl", hash = "sha256:24471b829b3bf607e04e88d79542a9d48bb037c2267d7927a874e6c205ca7e9a"}, + {file = "PyYAML-6.0.2-cp38-cp38-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:d7fded462629cfa4b685c5416b949ebad6cec74af5e2d42905d41e257e0869f5"}, + {file = "PyYAML-6.0.2-cp38-cp38-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:d84a1718ee396f54f3a086ea0a66d8e552b2ab2017ef8b420e92edbc841c352d"}, + {file = "PyYAML-6.0.2-cp38-cp38-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:9056c1ecd25795207ad294bcf39f2db3d845767be0ea6e6a34d856f006006083"}, + {file = "PyYAML-6.0.2-cp38-cp38-musllinux_1_1_x86_64.whl", hash = "sha256:82d09873e40955485746739bcb8b4586983670466c23382c19cffecbf1fd8706"}, + {file = "PyYAML-6.0.2-cp38-cp38-win32.whl", hash = "sha256:43fa96a3ca0d6b1812e01ced1044a003533c47f6ee8aca31724f78e93ccc089a"}, + {file = "PyYAML-6.0.2-cp38-cp38-win_amd64.whl", hash = "sha256:01179a4a8559ab5de078078f37e5c1a30d76bb88519906844fd7bdea1b7729ff"}, + {file = "PyYAML-6.0.2-cp39-cp39-macosx_10_9_x86_64.whl", hash = "sha256:688ba32a1cffef67fd2e9398a2efebaea461578b0923624778664cc1c914db5d"}, + {file = "PyYAML-6.0.2-cp39-cp39-macosx_11_0_arm64.whl", hash = "sha256:a8786accb172bd8afb8be14490a16625cbc387036876ab6ba70912730faf8e1f"}, + {file = "PyYAML-6.0.2-cp39-cp39-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:d8e03406cac8513435335dbab54c0d385e4a49e4945d2909a581c83647ca0290"}, + {file = "PyYAML-6.0.2-cp39-cp39-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:f753120cb8181e736c57ef7636e83f31b9c0d1722c516f7e86cf15b7aa57ff12"}, + {file = "PyYAML-6.0.2-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:3b1fdb9dc17f5a7677423d508ab4f243a726dea51fa5e70992e59a7411c89d19"}, + {file = "PyYAML-6.0.2-cp39-cp39-musllinux_1_1_aarch64.whl", hash = "sha256:0b69e4ce7a131fe56b7e4d770c67429700908fc0752af059838b1cfb41960e4e"}, + {file = "PyYAML-6.0.2-cp39-cp39-musllinux_1_1_x86_64.whl", hash = "sha256:a9f8c2e67970f13b16084e04f134610fd1d374bf477b17ec1599185cf611d725"}, + {file = "PyYAML-6.0.2-cp39-cp39-win32.whl", hash = "sha256:6395c297d42274772abc367baaa79683958044e5d3835486c16da75d2a694631"}, + {file = "PyYAML-6.0.2-cp39-cp39-win_amd64.whl", hash = "sha256:39693e1f8320ae4f43943590b49779ffb98acb81f788220ea932a6b6c51004d8"}, + {file = "pyyaml-6.0.2.tar.gz", hash = "sha256:d584d9ec91ad65861cc08d42e834324ef890a082e591037abe114850ff7bbc3e"}, +] + +[[package]] +name = "requests" +version = "2.32.4" +description = "Python HTTP for Humans." +optional = false +python-versions = ">=3.8" +groups = ["main"] +files = [ + {file = "requests-2.32.4-py3-none-any.whl", hash = "sha256:27babd3cda2a6d50b30443204ee89830707d396671944c998b5975b031ac2b2c"}, + {file = "requests-2.32.4.tar.gz", hash = "sha256:27d0316682c8a29834d3264820024b62a36942083d52caf2f14c0591336d3422"}, +] + +[package.dependencies] +certifi = ">=2017.4.17" +charset_normalizer = ">=2,<4" +idna = ">=2.5,<4" +urllib3 = ">=1.21.1,<3" + +[package.extras] +socks = ["PySocks (>=1.5.6,!=1.5.7)"] +use-chardet-on-py3 = ["chardet (>=3.0.2,<6)"] + +[[package]] +name = "tqdm" +version = "4.67.1" +description = "Fast, Extensible Progress Meter" +optional = false +python-versions = ">=3.7" +groups = ["main"] +files = [ + {file = "tqdm-4.67.1-py3-none-any.whl", hash = "sha256:26445eca388f82e72884e0d580d5464cd801a3ea01e63e5601bdff9ba6a48de2"}, + {file = "tqdm-4.67.1.tar.gz", hash = "sha256:f8aef9c52c08c13a65f30ea34f4e5aac3fd1a34959879d7e59e63027286627f2"}, +] + +[package.dependencies] +colorama = {version = "*", markers = "platform_system == \"Windows\""} + +[package.extras] +dev = ["nbval", "pytest (>=6)", "pytest-asyncio (>=0.24)", "pytest-cov", "pytest-timeout"] +discord = ["requests"] +notebook = ["ipywidgets (>=6)"] +slack = ["slack-sdk"] +telegram = ["requests"] + +[[package]] +name = "typing-extensions" +version = "4.14.1" +description = "Backported and Experimental Type Hints for Python 3.9+" +optional = false +python-versions = ">=3.9" +groups = ["main"] +files = [ + {file = "typing_extensions-4.14.1-py3-none-any.whl", hash = "sha256:d1e1e3b58374dc93031d6eda2420a48ea44a36c2b4766a4fdeb3710755731d76"}, + {file = "typing_extensions-4.14.1.tar.gz", hash = "sha256:38b39f4aeeab64884ce9f74c94263ef78f3c22467c8724005483154c26648d36"}, +] + +[[package]] +name = "urllib3" +version = "2.5.0" +description = "HTTP library with thread-safe connection pooling, file post, and more." +optional = false +python-versions = ">=3.9" +groups = ["main"] +files = [ + {file = "urllib3-2.5.0-py3-none-any.whl", hash = "sha256:e6b01673c0fa6a13e374b50871808eb3bf7046c4b125b216f6bf1cc604cff0dc"}, + {file = "urllib3-2.5.0.tar.gz", hash = "sha256:3fc47733c7e419d4bc3f6b3dc2b4f890bb743906a30d56ba4a5bfa4bbff92760"}, +] + +[package.extras] +brotli = ["brotli (>=1.0.9) ; platform_python_implementation == \"CPython\"", "brotlicffi (>=0.8.0) ; platform_python_implementation != \"CPython\""] +h2 = ["h2 (>=4,<5)"] +socks = ["pysocks (>=1.5.6,!=1.5.7,<2.0)"] +zstd = ["zstandard (>=0.18.0)"] + +[metadata] +lock-version = "2.1" +python-versions = "3.9.18" +content-hash = "ce0b46e8192bad2bc3af39e2ef72557fa098b8158039db1f6e9164dba34571a6" diff --git a/libs/libviewer/poetry.toml b/libs/libviewer/poetry.toml new file mode 100644 index 0000000000..ab1033bd37 --- /dev/null +++ b/libs/libviewer/poetry.toml @@ -0,0 +1,2 @@ +[virtualenvs] +in-project = true diff --git a/libs/libviewer/pyproject.toml b/libs/libviewer/pyproject.toml new file mode 100644 index 0000000000..9f0d06e478 --- /dev/null +++ b/libs/libviewer/pyproject.toml @@ -0,0 +1,43 @@ +[tool.poetry] +authors = ["Krisztián Szűcs "] +description = "Library for utils common to all the services" +name = "libviewer" +version = "0.1.0" +license = "Apache-2.0" + +[tool.poetry.dependencies] +python = "3.12.11" +click = "8.1.8" +pyarrow = "15.0.2" +huggingface-hub = {version = "^0.31.0", extras = ["hf-transfer"]} + +[tool.poetry.build] +script = "build.py" + +[build-system] +requires = ["poetry-core", "maturin>=1.0,<2.0"] +build-backend = "poetry.core.masonry.api" + +[project] +name = "libviewer" +requires-python = ">=3.9.18" +classifiers = [ + "Programming Language :: Rust", + "Programming Language :: Python :: Implementation :: CPython", + "Programming Language :: Python :: Implementation :: PyPy", +] +dynamic = ["version"] +dependencies = [ + "click", + "pyarrow", + "huggingface_hub" +] + +[project.scripts] +dv = "libviewer.cli:cli" + +[tool.maturin] +# bindings = "pyo3" +module-name = "libviewer._internal" +# "extension-module" tells pyo3 we want to build an extension module (skips linking against libpython.so) +features = ["pyo3/extension-module"] \ No newline at end of file diff --git a/libs/libviewer/src/dataset.rs b/libs/libviewer/src/dataset.rs new file mode 100644 index 0000000000..d83fdbc7a1 --- /dev/null +++ b/libs/libviewer/src/dataset.rs @@ -0,0 +1,295 @@ +use std::sync::Arc; + +use arrow::array::RecordBatch; +use futures::future; +use futures::TryStreamExt; +use object_store::prefix::PrefixStore; +use object_store::ObjectStore; +use object_store_opendal::OpendalStore; +use opendal::services::Huggingface; +use opendal::Operator; +use parquet::file::metadata::ParquetMetaData; +use thiserror::Error; +use tokio::task; +use url::Url; + +use crate::parquet::{read_batch_stream, read_metadata, write_metadata}; +use crate::IndexedFile; + +#[derive(Error, Debug)] +pub enum DatasetError { + #[error("Failed to parse URL: {0}")] + Url(#[from] url::ParseError), + + #[error("Failed to parse object store URL: {0}")] + OpendalError(#[from] opendal::Error), + + #[error("IO error: {0}")] + Io(#[from] std::io::Error), + + #[error("Arrow error: {0}")] + Arrow(#[from] arrow::error::ArrowError), + + #[error("Parquet error: {0}")] + Parquet(#[from] ::parquet::errors::ParquetError), + + #[error("Object store error: {0}")] + ObjectStore(#[from] object_store::Error), + + #[error("Object store path error: {0}")] + ObjectStorePath(#[from] object_store::path::Error), + + #[error("Join error: {0}")] + JoinError(#[from] tokio::task::JoinError), +} + +type Result = std::result::Result; + +#[derive(Debug)] +struct ParquetScan { + file: IndexedFile, + limit: u64, + offset: u64, + metadata: Arc, +} + +impl ParquetScan { + fn has_offset_index(&self) -> bool { + self.metadata.offset_index().is_some() + } + + fn estimate_scan_size(&self) -> i64 { + let mut scan_size = 0; + let mut rows_to_skip = self.offset; + let mut rows_needed = self.limit; + + for row_group in self.metadata.row_groups() { + let num_rows = row_group.num_rows() as u64; + + // Skip row groups until we reach the offset + if rows_to_skip >= num_rows { + rows_to_skip -= num_rows; + continue; + } + + // Calculate how many rows to read from this row group + let rows_in_group = num_rows - rows_to_skip; + let rows_to_read = rows_needed.min(rows_in_group); + + // Accumulate the size if we need to scan any rows from this row group + if rows_to_read > 0 { + scan_size += row_group.compressed_size(); + rows_needed -= rows_to_read; + } + + // After the first row group, we don't need to skip any more rows + rows_to_skip = 0; + + // Stop if we've accumulated enough rows + if rows_needed == 0 { + break; + } + } + + scan_size + } + + fn shall_index(&self, scan_size_limit: i64) -> bool { + // TODO(kszucs): reconsider the case when we want to index: + // 1. file reads with row groups larger than the scan size limit + // 2. file reads with overall size larger than the scan size limit (multiple row groups) + + // If the file has an offset index, we don't need to index it again + if self.has_offset_index() { + return false; + } + // If the estimated scan size is larger than the limit, we should index it + self.estimate_scan_size() > scan_size_limit + } + + async fn execute(&self, data_store: Arc) -> Result> { + let stream = read_batch_stream( + data_store, + self.file.path.clone(), + self.metadata.clone(), + self.offset, + self.limit, + )?; + Ok(stream.try_collect::>().await?) + } +} + +fn store_from_uri( + uri: &str, + repo: &str, + revision: Option<&str>, +) -> Result, DatasetError> { + let url = Url::parse(uri)?; + + if uri.starts_with("hf://") { + // You can parse additional parameters from the URI if needed + let builder = Huggingface::default().repo_type("dataset").repo_id(repo); + let builder = if let Some(rev) = revision { + builder.revision(rev) + } else { + builder + }; + let operator = Operator::new(builder)?.finish(); + let store = OpendalStore::new(operator); + Ok(Arc::new(store)) + } else { + let (store, prefix) = object_store::parse_url(&url)?; + let store = PrefixStore::new(store, prefix); + Ok(Arc::new(store)) + } +} + +#[derive(Clone, Debug)] +pub struct Dataset { + /// The name of the dataset + pub name: String, + /// The parquet files in the dataset + pub files: Vec, + /// Optional revision (branch, tag, commit) for the dataset + pub revision: Option, + /// The underlying object store for the dataset + data_store: Arc, + pub data_store_uri: String, + /// The local metadata store for the dataset + metadata_store: Arc, + pub metadata_store_uri: String, + /// Scan size limit for triggering indexing + indexing_size_threshold: i64, +} + +impl Dataset { + pub fn try_new( + name: &str, + files: Vec, + revision: Option<&str>, + data_uri: &str, + metadata_uri: &str, + indexing_size_threshold: i64, + ) -> Result { + Ok(Self { + name: name.to_string(), + files, + revision: revision.map(|s| s.to_string()), + data_store: store_from_uri(data_uri, name, revision)?, + data_store_uri: data_uri.to_string(), + metadata_store: store_from_uri(metadata_uri, name, revision)?, + metadata_store_uri: metadata_uri.to_string(), + indexing_size_threshold, + }) + } + + async fn plan(&self, limit: Option, offset: Option) -> Result> { + // collect the list of files which must be scanned depending on the number of rows in each file + // and have a list of (file, offset, limit) tuples which produce the final result after concatenation + let mut scans = Vec::::new(); + let mut current_offset: u64 = 0; + + let offset = offset.unwrap_or(0); + let mut remaining_limit = limit.unwrap_or(u64::MAX); + + for file in &self.files { + let (metadata, num_rows) = match file.num_rows { + Some(rows) => (None, rows), + None => { + let metadata = + read_metadata(self.metadata_store.clone(), file.metadata_path.as_ref()) + .await?; + let num_rows = metadata.file_metadata().num_rows() as u64; + (Some(metadata), num_rows) + } + }; + + // here we handle file pruning based on the offset and limit + if current_offset + num_rows > offset { + // this file must be scanned, calculate the offset within the file + let file_offset = if offset > current_offset { + offset - current_offset + } else { + 0 + }; + + // calculate the limit for this file + let file_limit = remaining_limit.min(num_rows - file_offset); + remaining_limit -= file_limit; + + let metadata = match metadata { + Some(meta) => meta, + None => { + read_metadata(self.metadata_store.clone(), file.metadata_path.as_ref()) + .await? + } + }; + scans.push(ParquetScan { + file: file.clone(), + limit: file_limit, + offset: file_offset, + metadata: metadata, + }); + + if remaining_limit == 0 { + break; + } + } + + current_offset += num_rows; + } + Ok(scans) + } + + pub async fn index(&self, files: Option<&[IndexedFile]>) -> Result<()> { + let tasks = files + .unwrap_or(&self.files) + .iter() + .map(async move |file| { + let metadata = read_metadata(self.data_store.clone(), file.path.as_ref()).await?; + write_metadata( + metadata, + self.metadata_store.clone(), + file.metadata_path.as_ref(), + ) + .await + }) + .collect::>(); + + future::try_join_all(tasks).await?; + + Ok(()) + } + + pub async fn scan( + &self, + limit: Option, + offset: Option, + ) -> Result<(Vec, Vec)> { + // 1. create an object reader for each file in the access plan + // 2. generate a stream of record batches from each reader + // 3. flatten the streams into a single stream + // 4. collect the record batches into a single vector + + let plan = self.plan(limit, offset).await?; + let files_to_index: Vec = plan + .iter() + .filter(|scan| scan.shall_index(self.indexing_size_threshold)) + .map(|scan| scan.file.clone()) + .collect(); + + let tasks = plan.into_iter().map(|scan| { + let data_store = self.data_store.clone(); + task::spawn(async move { scan.execute(data_store).await }) + }); + let results = future::try_join_all(tasks).await?; + let batches = results + .into_iter() + .collect::>>()? + .into_iter() + .flatten() + .collect::>(); + + Ok((batches, files_to_index)) + } +} diff --git a/libs/libviewer/src/lib.rs b/libs/libviewer/src/lib.rs new file mode 100644 index 0000000000..86d011c134 --- /dev/null +++ b/libs/libviewer/src/lib.rs @@ -0,0 +1,155 @@ +mod dataset; +mod parquet; + +use arrow::pyarrow::IntoPyArrow; +use pyo3::exceptions::PyValueError; +use pyo3::prelude::*; +use pyo3_async_runtimes; +use tokio; + +use crate::dataset::{Dataset, DatasetError}; + +const INDEXING_SIZE_THRESHOLD: i64 = 100 * 1024 * 1024; // 100 MiB + +impl From for PyErr { + fn from(err: DatasetError) -> Self { + PyValueError::new_err(err.to_string()) + } +} + +#[derive(Debug, Clone, IntoPyObject, FromPyObject)] +pub struct IndexedFile { + #[pyo3(item)] + pub path: String, + #[pyo3(item)] + pub size: Option, + #[pyo3(item)] + pub num_rows: Option, + #[pyo3(item)] + pub metadata_path: String, +} + +#[pyclass(subclass)] +#[derive(Debug, Clone)] +struct PyDataset { + /// The wrapped dataset object + dataset: Dataset, +} + +#[pymethods] +impl PyDataset { + #[new] + #[pyo3(signature = (name, files, metadata_store, data_store = "hf://", revision = None, indexing_size_threshold = INDEXING_SIZE_THRESHOLD))] + fn new( + name: &str, + files: Vec, + metadata_store: &str, + data_store: &str, + revision: Option<&str>, + indexing_size_threshold: i64, + ) -> PyResult { + let dataset = Dataset::try_new( + name, + files, + revision, + data_store, + metadata_store, + indexing_size_threshold, + )?; + Ok(PyDataset { dataset }) + } + + fn __str__(&self) -> PyResult { + Ok(format!("{:?}", self.dataset)) + } + + #[getter] + fn name(&self) -> PyResult<&str> { + Ok(&self.dataset.name) + } + + #[getter] + fn revision(&self) -> PyResult> { + Ok(self.dataset.revision.as_deref()) + } + + #[getter] + fn files(&self) -> PyResult> { + Ok(self.dataset.files.clone()) + } + + #[getter] + fn data_store_uri(&self) -> PyResult<&str> { + Ok(&self.dataset.data_store_uri) + } + + #[getter] + fn metadata_store_uri(&self) -> PyResult<&str> { + Ok(&self.dataset.metadata_store_uri) + } + + #[pyo3(signature = (limit=None, offset=None))] + fn sync_scan( + &self, + py: Python<'_>, + limit: Option, + offset: Option, + ) -> PyResult<(Vec, Vec)> { + let rt = tokio::runtime::Runtime::new()?; + let (record_batches, files_to_index) = rt.block_on(self.dataset.scan(limit, offset))?; + let pyarrow_batches = record_batches + .into_iter() + .map(|batch| batch.into_pyarrow(py)) + .collect::>>()?; + Ok((pyarrow_batches, files_to_index)) + } + + #[pyo3(signature = (limit=None, offset=None))] + fn scan<'py>( + &self, + py: Python<'py>, + limit: Option, + offset: Option, + ) -> PyResult> { + let this = self.clone(); + pyo3_async_runtimes::tokio::future_into_py(py, async move { + let (record_batches, files_to_index) = this.dataset.scan(limit, offset).await?; + let pyarrow_batches = Python::with_gil(|py| { + record_batches + .into_iter() + .map(|batch| batch.into_pyarrow(py)) + .collect::>>() + })?; + Ok((pyarrow_batches, files_to_index)) + }) + } + + #[pyo3(signature = (files=None))] + fn sync_index(&self, files: Option>) -> PyResult<()> { + let rt = tokio::runtime::Runtime::new()?; + rt.block_on(self.dataset.index(files.as_deref()))?; + Ok(()) + } + + #[pyo3(signature = (files=None))] + fn index<'py>( + &self, + py: Python<'py>, + files: Option>, + ) -> PyResult> { + let this = self.clone(); + pyo3_async_runtimes::tokio::future_into_py(py, async move { + Ok(this.dataset.index(files.as_deref()).await?) + }) + } +} + +/// A Python module implemented in Rust. The name of this function must match +/// the `lib.name` setting in the `Cargo.toml`, else Python will not be able to +/// import the module. +#[pymodule] +#[pyo3(name = "_internal")] +fn dv(m: &Bound<'_, PyModule>) -> PyResult<()> { + m.add_class::()?; + Ok(()) +} diff --git a/libs/libviewer/src/parquet.rs b/libs/libviewer/src/parquet.rs new file mode 100644 index 0000000000..89d427bafc --- /dev/null +++ b/libs/libviewer/src/parquet.rs @@ -0,0 +1,85 @@ +use futures::Stream; +use std::sync::Arc; + +use arrow::record_batch::RecordBatch; +use object_store::path::Path; +use object_store::ObjectStore; +use parquet::arrow::arrow_reader::{ArrowReaderMetadata, ArrowReaderOptions}; +use parquet::arrow::async_reader::ParquetObjectReader; +use parquet::arrow::ParquetRecordBatchStreamBuilder; +use parquet::arrow::ProjectionMask; +use parquet::errors::ParquetError; +use parquet::file::metadata::{ + PageIndexPolicy, ParquetMetaData, ParquetMetaDataReader, ParquetMetaDataWriter, +}; + +type Result = std::result::Result; + +pub async fn read_metadata( + store: Arc, + path: impl Into, +) -> Result> { + let path = path.into(); + + let mut object_reader = ParquetObjectReader::new(store, path.clone()); + let metadata_reader = ParquetMetaDataReader::new() + .with_column_index_policy(PageIndexPolicy::Skip) + .with_offset_index_policy(PageIndexPolicy::Optional); + // .with_prefetch_hint(16 * 1024); + + // TODO(kszucs): if file_size is known then use load_and_finish + // let metadata = if let Some(file_size) = self.file_size { + // metadata.load_and_finish(self, file_size).await? + // } else { + // metadata.load_via_suffix_and_finish(self).await? + // }; + let metadata = metadata_reader + .load_via_suffix_and_finish(&mut object_reader) + .await?; + + Ok(Arc::new(metadata)) +} + +// TODO(kszucs): consider to return with the PutResult's ETag +pub async fn write_metadata( + metadata: Arc, + store: Arc, + path: impl Into, +) -> Result<()> { + // Use ParquetMetaDataWriter to serialize the metadata into in-memory buffer + let mut buffer = Vec::new(); + let writer = ParquetMetaDataWriter::new(&mut buffer, &metadata); + writer.finish()?; + + // Upload the metadata buffer to the metadata store + store.put(&path.into(), buffer.into()).await?; + Ok(()) +} + +pub fn read_batch_stream( + store: Arc, + path: impl Into, + metadata: Arc, + offset: u64, + limit: u64, +) -> Result>> { + let path = path.into(); + let reader = ParquetObjectReader::new(store, path.clone()) + .with_preload_offset_index(false) + .with_preload_column_index(false); + // the page index configuration here shouldn't matter since the metadata is already + // read and stored in the ParquetFile struct + let reader_options = ArrowReaderOptions::default().with_page_index(true); + let reader_metadata = ArrowReaderMetadata::try_new(metadata, reader_options)?; + + // TODO(kszucs): projection pushdown can be handled here if needed + // let parquet_schema = reader_metadata.metadata().file_metadata().schema_descr(); + // let parquet_fields = ProjectionMask::leaves(parquet_schema, [0]); + let parquet_fields = ProjectionMask::all(); + let batch_stream = ParquetRecordBatchStreamBuilder::new_with_metadata(reader, reader_metadata) + .with_projection(parquet_fields) + .with_offset(offset as usize) + .with_limit(limit as usize) + .build()?; + Ok(batch_stream) +} diff --git a/services/rows/Dockerfile b/services/rows/Dockerfile index 5941a082ec..05a218c0b2 100644 --- a/services/rows/Dockerfile +++ b/services/rows/Dockerfile @@ -16,16 +16,27 @@ ENV PYTHONFAULTHANDLER=1 \ # System deps: RUN apt-get update \ - && apt-get install -y unzip wget procps htop ffmpeg libavcodec-extra libsndfile1 \ + && apt-get install -y unzip curl wget procps htop build-essential ffmpeg libavcodec-extra libsndfile1 \ && rm -rf /var/lib/apt/lists/* RUN pip install -U pip RUN pip install "poetry==$POETRY_VERSION" +# Install Rust toolchain and maturin +RUN curl https://sh.rustup.rs -sSf | sh -s -- -y \ + && . $HOME/.cargo/env \ + && pip install maturin \ + && rustc --version \ + && cargo --version + +# Add cargo bin dir to PATH (so maturin + cargo available globally) +ENV PATH="/root/.cargo/bin:${PATH}" + WORKDIR /src -COPY services/rows/poetry.lock ./services/rows/poetry.lock -COPY services/rows/pyproject.toml ./services/rows/pyproject.toml +COPY libs/libviewer ./libs/libviewer COPY libs/libcommon ./libs/libcommon COPY libs/libapi ./libs/libapi +COPY services/rows/poetry.lock ./services/rows/poetry.lock +COPY services/rows/pyproject.toml ./services/rows/pyproject.toml WORKDIR /src/services/rows/ RUN poetry install --no-cache --no-root COPY services/rows/src ./src diff --git a/services/rows/dev.Dockerfile b/services/rows/dev.Dockerfile index fc7933f5d9..9ace198dea 100644 --- a/services/rows/dev.Dockerfile +++ b/services/rows/dev.Dockerfile @@ -16,16 +16,25 @@ ENV PYTHONFAULTHANDLER=1 \ # System deps: RUN apt-get update \ - && apt-get install -y gcc g++ unzip wget procps htop ffmpeg libavcodec-extra libsndfile1 \ + && apt-get install -y gcc g++ unzip curl wget procps build-essential htop ffmpeg libavcodec-extra libsndfile1 \ && rm -rf /var/lib/apt/lists/* RUN pip install -U pip RUN pip install "poetry==$POETRY_VERSION" +# Install Rust toolchain and maturin +RUN curl https://sh.rustup.rs -sSf | sh -s -- -y \ + && . $HOME/.cargo/env \ + && pip install maturin \ + && rustc --version \ + && cargo --version + +# Add cargo bin dir to PATH (so maturin + cargo available globally) +ENV PATH="/root/.cargo/bin:${PATH}" + WORKDIR /src -COPY libs/libcommon/poetry.lock ./libs/libcommon/poetry.lock -COPY libs/libcommon/pyproject.toml ./libs/libcommon/pyproject.toml -COPY libs/libapi/poetry.lock ./libs/libapi/poetry.lock -COPY libs/libapi/pyproject.toml ./libs/libapi/pyproject.toml +COPY libs/libviewer ./libs/libviewer +COPY libs/libcommon ./libs/libcommon +COPY libs/libapi ./libs/libapi COPY services/rows/poetry.lock ./services/rows/poetry.lock COPY services/rows/pyproject.toml ./services/rows/pyproject.toml diff --git a/services/rows/poetry.lock b/services/rows/poetry.lock index d8e00603b2..2ceb82a742 100644 --- a/services/rows/poetry.lock +++ b/services/rows/poetry.lock @@ -1257,6 +1257,25 @@ tqdm = "^4.66.3" type = "directory" url = "../../libs/libcommon" +[[package]] +name = "libviewer" +version = "0.6.8" +description = "Library for utils common to all the services" +optional = false +python-versions = "3.12.11" +groups = ["main"] +files = [] +develop = true + +[package.dependencies] +click = "*" +huggingface_hub = "*" +pyarrow = "*" + +[package.source] +type = "directory" +url = "../../libs/libviewer" + [[package]] name = "license-expression" version = "30.4.4" @@ -4287,4 +4306,4 @@ propcache = ">=0.2.1" [metadata] lock-version = "2.1" python-versions = "3.12.11" -content-hash = "aefaed745ad637ff04036d3ea43286018d01663c43babad3d1ef6ac589e5de14" +content-hash = "cc7a991e8ed8b4348b007631d8b54f45a20a182179c0ad3dd5f0a0c7a5438697" diff --git a/services/rows/pyproject.toml b/services/rows/pyproject.toml index 7c89fd4818..c44c9ccf29 100644 --- a/services/rows/pyproject.toml +++ b/services/rows/pyproject.toml @@ -9,6 +9,7 @@ license = "Apache-2.0" python = "3.12.11" jsonschema = "^4.17.0" libapi = {path = "../../libs/libapi", develop = true} +libviewer = {path = "../../libs/libviewer", develop = true} soundfile = ">=0.12.1" uvicorn = "^0.30.1" watchdog = { extras = ["watchmedo"], version = "^2.2.1" } diff --git a/services/rows/src/rows/routes/rows.py b/services/rows/src/rows/routes/rows.py index b01c4f2b52..6a041d88a3 100644 --- a/services/rows/src/rows/routes/rows.py +++ b/services/rows/src/rows/routes/rows.py @@ -100,9 +100,10 @@ async def rows_endpoint(request: Request) -> Response: with StepProfiler(method="rows_endpoint", step="query the rows"): try: # Some datasets have very long binary data that we truncate - pa_table, truncated_columns = rows_index.query_truncated_binary( - offset=offset, length=length - ) + # pa_table, truncated_columns = rows_index.query_truncated_binary( + # offset=offset, length=length + # ) + pa_table = rows_index.query_with_page_pruning(offset=offset, length=length) except TooBigRows as err: raise TooBigContentError(str(err)) from None with StepProfiler(method="rows_endpoint", step="transform to a list"): @@ -118,7 +119,8 @@ async def rows_endpoint(request: Request) -> Response: unsupported_columns=rows_index.parquet_index.unsupported_columns, partial=rows_index.parquet_index.partial, num_rows_total=rows_index.parquet_index.num_rows_total, - truncated_columns=truncated_columns, + # truncated_columns=truncated_columns, + truncated_columns=None, ) except CachedArtifactNotFoundError: with StepProfiler(method="rows_endpoint", step="try backfill dataset"): diff --git a/services/search/Dockerfile b/services/search/Dockerfile index 6d07bd8786..00fa46c187 100644 --- a/services/search/Dockerfile +++ b/services/search/Dockerfile @@ -16,16 +16,27 @@ ENV PYTHONFAULTHANDLER=1 \ # System deps: RUN apt-get update \ - && apt-get install -y unzip wget procps htop ffmpeg libavcodec-extra libsndfile1 \ + && apt-get install -y unzip wget curl build-essential procps htop ffmpeg libavcodec-extra libsndfile1 \ && rm -rf /var/lib/apt/lists/* RUN pip install -U pip RUN pip install "poetry==$POETRY_VERSION" +# Install Rust toolchain and maturin +RUN curl https://sh.rustup.rs -sSf | sh -s -- -y \ + && . $HOME/.cargo/env \ + && pip install maturin \ + && rustc --version \ + && cargo --version + +# Add cargo bin dir to PATH (so maturin + cargo available globally) +ENV PATH="/root/.cargo/bin:${PATH}" + WORKDIR /src -COPY services/search/poetry.lock ./services/search/poetry.lock -COPY services/search/pyproject.toml ./services/search/pyproject.toml +COPY libs/libviewer ./libs/libviewer COPY libs/libcommon ./libs/libcommon COPY libs/libapi ./libs/libapi +COPY services/search/poetry.lock ./services/search/poetry.lock +COPY services/search/pyproject.toml ./services/search/pyproject.toml WORKDIR /src/services/search/ RUN poetry install --no-cache --no-root COPY services/search/src ./src diff --git a/services/search/dev.Dockerfile b/services/search/dev.Dockerfile index 8392fb671e..3bfc8885a5 100644 --- a/services/search/dev.Dockerfile +++ b/services/search/dev.Dockerfile @@ -16,16 +16,25 @@ ENV PYTHONFAULTHANDLER=1 \ # System deps: RUN apt-get update \ - && apt-get install -y gcc g++ unzip wget procps htop ffmpeg libavcodec-extra libsndfile1 \ + && apt-get install -y gcc g++ unzip curl build-essential wget procps htop ffmpeg libavcodec-extra libsndfile1 \ && rm -rf /var/lib/apt/lists/* RUN pip install -U pip RUN pip install "poetry==$POETRY_VERSION" +# Install Rust toolchain and maturin +RUN curl https://sh.rustup.rs -sSf | sh -s -- -y \ + && . $HOME/.cargo/env \ + && pip install maturin \ + && rustc --version \ + && cargo --version + +# Add cargo bin dir to PATH (so maturin + cargo available globally) +ENV PATH="/root/.cargo/bin:${PATH}" + WORKDIR /src -COPY libs/libcommon/poetry.lock ./libs/libcommon/poetry.lock -COPY libs/libcommon/pyproject.toml ./libs/libcommon/pyproject.toml -COPY libs/libapi/poetry.lock ./libs/libapi/poetry.lock -COPY libs/libapi/pyproject.toml ./libs/libapi/pyproject.toml +COPY libs/libviewer ./libs/libviewer +COPY libs/libcommon ./libs/libcommon +COPY libs/libapi ./libs/libapi COPY services/search/poetry.lock ./services/search/poetry.lock COPY services/search/pyproject.toml ./services/search/pyproject.toml diff --git a/services/search/poetry.lock b/services/search/poetry.lock index 1cc4716f7d..cecd430937 100644 --- a/services/search/poetry.lock +++ b/services/search/poetry.lock @@ -1,4 +1,4 @@ -# This file is automatically @generated by Poetry 2.1.4 and should not be changed by hand. +# This file is automatically @generated by Poetry 2.2.1 and should not be changed by hand. [[package]] name = "aiobotocore" @@ -1205,6 +1205,7 @@ environs = "^14.3.0" filelock = "^3.18.0" fsspec = {version = "2024.3.1", extras = ["s3"]} huggingface-hub = {version = "^0.31.0", extras = ["hf-transfer"]} +libviewer = {path = "../libviewer", develop = true} mongo-types = "0.15.1" mongoengine = "^0.29.1" networkx = "^3.0" @@ -1236,6 +1237,25 @@ tqdm = "^4.66.3" type = "directory" url = "../../libs/libcommon" +[[package]] +name = "libviewer" +version = "0.1.0" +description = "Library for utils common to all the services" +optional = false +python-versions = "3.12.11" +groups = ["main"] +files = [] +develop = true + +[package.dependencies] +click = "*" +huggingface_hub = "*" +pyarrow = "*" + +[package.source] +type = "directory" +url = "../../libs/libviewer" + [[package]] name = "license-expression" version = "30.4.4" diff --git a/services/worker/Dockerfile b/services/worker/Dockerfile index 9400ce2be6..f6aef3bf88 100644 --- a/services/worker/Dockerfile +++ b/services/worker/Dockerfile @@ -16,15 +16,26 @@ ENV PYTHONFAULTHANDLER=1 \ # System deps: RUN apt-get update \ - && apt-get install -y unzip wget procps htop ffmpeg libavcodec-extra libsndfile1 \ + && apt-get install -y unzip wget procps curl build-essential htop ffmpeg libavcodec-extra libsndfile1 \ && rm -rf /var/lib/apt/lists/* RUN pip install -U pip RUN pip install "poetry==$POETRY_VERSION" +# Install Rust toolchain and maturin +RUN curl https://sh.rustup.rs -sSf | sh -s -- -y \ + && . $HOME/.cargo/env \ + && pip install maturin \ + && rustc --version \ + && cargo --version + +# Add cargo bin dir to PATH (so maturin + cargo available globally) +ENV PATH="/root/.cargo/bin:${PATH}" + WORKDIR /src COPY services/worker/poetry.lock ./services/worker/poetry.lock COPY services/worker/pyproject.toml ./services/worker/pyproject.toml +COPY libs/libviewer ./libs/libviewer COPY libs/libcommon ./libs/libcommon WORKDIR /src/services/worker/ diff --git a/services/worker/dev.Dockerfile b/services/worker/dev.Dockerfile index 7d37b8aa2c..1ba68f6805 100644 --- a/services/worker/dev.Dockerfile +++ b/services/worker/dev.Dockerfile @@ -16,15 +16,25 @@ ENV PYTHONFAULTHANDLER=1 \ # System deps: RUN apt-get update \ - && apt-get install -y gcc g++ unzip wget procps htop ffmpeg libavcodec-extra libsndfile1 \ + && apt-get install -y gcc g++ unzip curl build-essential wget procps htop ffmpeg libavcodec-extra libsndfile1 \ && rm -rf /var/lib/apt/lists/* RUN pip install -U pip RUN pip install "poetry==$POETRY_VERSION" +# Install Rust toolchain and maturin +RUN curl https://sh.rustup.rs -sSf | sh -s -- -y \ + && . $HOME/.cargo/env \ + && pip install maturin \ + && rustc --version \ + && cargo --version + +# Add cargo bin dir to PATH (so maturin + cargo available globally) +ENV PATH="/root/.cargo/bin:${PATH}" + WORKDIR /src -COPY libs/libcommon/poetry.lock ./libs/libcommon/poetry.lock -COPY libs/libcommon/pyproject.toml ./libs/libcommon/pyproject.toml +COPY libs/libviewer ./libs/libviewer +COPY libs/libcommon ./libs/libcommon COPY services/worker/poetry.lock ./services/worker/poetry.lock COPY services/worker/pyproject.toml ./services/worker/pyproject.toml diff --git a/services/worker/poetry.lock b/services/worker/poetry.lock index 0ff278e473..bf61207884 100644 --- a/services/worker/poetry.lock +++ b/services/worker/poetry.lock @@ -1,4 +1,4 @@ -# This file is automatically @generated by Poetry 2.1.4 and should not be changed by hand. +# This file is automatically @generated by Poetry 2.2.1 and should not be changed by hand. [[package]] name = "aiobotocore" @@ -1607,6 +1607,7 @@ environs = "^14.3.0" filelock = "^3.18.0" fsspec = {version = "2024.3.1", extras = ["s3"]} huggingface-hub = {version = "^0.31.0", extras = ["hf-transfer"]} +libviewer = {path = "../libviewer", develop = true} mongo-types = "0.15.1" mongoengine = "^0.29.1" networkx = "^3.0" @@ -1638,6 +1639,25 @@ tqdm = "^4.66.3" type = "directory" url = "../../libs/libcommon" +[[package]] +name = "libviewer" +version = "0.1.0" +description = "Library for utils common to all the services" +optional = false +python-versions = "3.12.11" +groups = ["main"] +files = [] +develop = true + +[package.dependencies] +click = "*" +huggingface_hub = "*" +pyarrow = "*" + +[package.source] +type = "directory" +url = "../../libs/libviewer" + [[package]] name = "license-expression" version = "30.4.4"