From 309b4f73009424be65d712d2798f11bf7525d952 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Rapha=C3=ABl=20Bournhonesque?= Date: Thu, 14 Nov 2024 15:29:51 +0100 Subject: [PATCH] feat: declare the schema of the Parquet file (#8) * deps: remove ipykernel dep * fix: remove timer decorator * feat: declare the schema of the Parquet file We used to use duckdb, but there were issues to to incorrect type guessing by duckdb. By validating and modifying the data before Parquet generation, we can control completely the schema. --- openfoodfacts_exports/exports/parquet.py | 763 +++++++++++++++-------- pyproject.toml | 7 +- uv.lock | 465 ++------------ 3 files changed, 576 insertions(+), 659 deletions(-) diff --git a/openfoodfacts_exports/exports/parquet.py b/openfoodfacts_exports/exports/parquet.py index cdd1aae..21bc4fd 100644 --- a/openfoodfacts_exports/exports/parquet.py +++ b/openfoodfacts_exports/exports/parquet.py @@ -3,160 +3,23 @@ import tempfile from pathlib import Path -import duckdb +import orjson import pyarrow as pa import pyarrow.parquet as pq -from pydantic import BaseModel, model_validator from huggingface_hub import HfApi +from more_itertools import chunked +from openfoodfacts.utils import jsonl_iter +from pydantic import BaseModel, Field, field_serializer, model_validator from openfoodfacts_exports import settings -from openfoodfacts_exports.utils import timer logger = logging.getLogger(__name__) PARQUET_DATASET_PATH = settings.DATASET_DIR / "openfoodfacts-products.parquet" -SQL_QUERY = r""" -SET threads to 4; -SET preserve_insertion_order = false; -COPY ( - SELECT - code, - additives_n, - additives_tags, - allergens_from_ingredients, - allergens_from_user, - allergens_tags, - brands, - brands_tags, - categories_properties_tags, - categories, - checkers_tags, - cities_tags, - compared_to_category, - complete, - completeness, - correctors_tags, - countries_tags, - created_t, - creator, - data_quality_errors_tags, - data_quality_info_tags, - data_quality_warnings_tags, - data_sources_tags, - ecoscore_data, - ecoscore_grade, - ecoscore_score, - ecoscore_tags, - editors, - emb_codes, - emb_codes_tags, - entry_dates_tags, - environment_impact_level, - food_groups_tags, - forest_footprint_data, - generic_name, - grades, - images, - informers_tags, - ingredients_analysis_tags, - ingredients_from_palm_oil_n, - ingredients_n, - ingredients_tags, - ingredients_text_with_allergens, - ingredients_text, - COLUMNS('ingredients_text_\w{2}$'), - ingredients_with_specified_percent_n, - ingredients_with_unspecified_percent_n, - ciqual_food_name_tags, - ingredients_percent_analysis, - ingredients_original_tags, - ingredients_without_ciqual_codes_n, - ingredients_without_ciqual_codes, - ingredients, - known_ingredients_n, - labels_tags, - lang, - languages_tags, - languages_codes, - last_edit_dates_tags, - last_editor, - last_image_t, - last_modified_by, - last_modified_t, - last_updated_t, - link, - main_countries_tags, - manufacturing_places, - manufacturing_places_tags, - max_imgid, - misc_tags, - minerals_tags, - new_additives_n, - no_nutrition_data, - nova_group, - nova_groups, - nova_groups_markers, - nova_groups_tags, - nucleotides_tags, - nutrient_levels_tags, - unknown_nutrients_tags, - nutriments, - nutriscore_data, - nutriscore_grade, - nutriscore_score, - nutriscore_tags, - nutrition_data_prepared_per, - nutrition_data, - nutrition_grades_tags, - nutrition_score_beverage, - nutrition_score_warning_fruits_vegetables_nuts_estimate_from_ingredients, - nutrition_score_warning_no_fiber, - nutrition_score_warning_no_fruits_vegetables_nuts, - obsolete_since_date, - obsolete, - origins_tags, - packaging_recycling_tags, - packaging_shapes_tags, - packaging_tags, - packagings_materials, - packagings_n, - packagings_n, - photographers, - pnns_groups_1_tags, - pnns_groups_2_tags, - popularity_key, - popularity_tags, - product_name, - product_quantity_unit, - product_quantity, - purchase_places_tags, - quantity, - rev, - scans_n, - scores, - serving_quantity, - serving_size, - sources, - sources_fields, - specific_ingredients, - states_tags, - stores, - stores_tags, - traces_tags, - unique_scans_n, - unknown_ingredients_n, - vitamins_tags, - weighers_tags, - with_non_nutritive_sweeteners, - with_sweeteners, - FROM read_ndjson('{dataset_path}', ignore_errors=True) -) TO '{output_path}' (FORMAT PARQUET) -; -""" - -_SIZE_SCHEMA = pa.struct( + +IMAGE_SIZE_SCHEMA = pa.struct( [ pa.field("h", pa.int32(), nullable=True), pa.field("w", pa.int32(), nullable=True), @@ -172,10 +35,10 @@ "sizes", pa.struct( [ - pa.field("100", _SIZE_SCHEMA, nullable=True), - pa.field("200", _SIZE_SCHEMA, nullable=True), - pa.field("400", _SIZE_SCHEMA, nullable=True), - pa.field("full", _SIZE_SCHEMA, nullable=True), + pa.field("100", IMAGE_SIZE_SCHEMA, nullable=True), + pa.field("200", IMAGE_SIZE_SCHEMA, nullable=True), + pa.field("400", IMAGE_SIZE_SCHEMA, nullable=True), + pa.field("full", IMAGE_SIZE_SCHEMA, nullable=True), ] ), nullable=True, @@ -186,9 +49,168 @@ ) ) -ALLOWED_IMAGE_SIZE_KEYS = {"100", "200", "400", "full"} +INGREDIENTS_TEXT_DATATYPE = pa.list_( + pa.struct( + [ + pa.field("lang", pa.string()), + pa.field("text", pa.string()), + ], + ) +) + + +LANGUAGE_FIELD_DATATYPE = pa.list_( + pa.struct( + [ + pa.field("lang", pa.string()), + pa.field("text", pa.string()), + ] + ), +) -SCHEMAS = {"images": IMAGES_DATATYPE} +NUTRIMENTS_DATATYPE = pa.list_( + pa.struct( + [ + pa.field("name", pa.string()), + pa.field("value", pa.float32(), nullable=True), + pa.field("100g", pa.float32(), nullable=True), + pa.field("serving", pa.float32(), nullable=True), + pa.field("unit", pa.string(), nullable=True), + pa.field("prepared_value", pa.float32(), nullable=True), + pa.field("prepared_100g", pa.float32(), nullable=True), + pa.field("prepared_serving", pa.float32(), nullable=True), + pa.field("prepared_unit", pa.string(), nullable=True), + ] + ) +) + +PACKAGING_FIELD_DATATYPE = pa.list_( + pa.struct( + [ + pa.field("material", pa.string(), nullable=True), + pa.field("number_of_units", pa.int32(), nullable=True), + pa.field("quantity_per_unit", pa.string(), nullable=True), + pa.field("quantity_per_unit_unit", pa.string(), nullable=True), + pa.field("quantity_per_unit_value", pa.string(), nullable=True), + pa.field("recycling", pa.string(), nullable=True), + pa.field("shape", pa.string(), nullable=True), + pa.field("weight_measured", pa.float32(), nullable=True), + ] + ) +) + +PRODUCT_SCHEMA = pa.schema( + [ + pa.field("additives_n", pa.int32(), nullable=True), + pa.field("additives_tags", pa.list_(pa.string()), nullable=True), + pa.field("allergens_tags", pa.list_(pa.string()), nullable=True), + pa.field("brands_tags", pa.list_(pa.string()), nullable=True), + pa.field("brands", pa.string(), nullable=True), + pa.field("categories", pa.string(), nullable=True), + pa.field("categories_tags", pa.list_(pa.string()), nullable=True), + pa.field("checkers_tags", pa.list_(pa.string()), nullable=True), + pa.field("ciqual_food_name_tags", pa.list_(pa.string()), nullable=True), + pa.field("cities_tags", pa.list_(pa.string()), nullable=True), + pa.field("code", pa.string()), + pa.field("compared_to_category", pa.string(), nullable=True), + pa.field("complete", pa.int32(), nullable=True), + pa.field("completeness", pa.float32(), nullable=True), + pa.field("correctors_tags", pa.list_(pa.string()), nullable=True), + pa.field("countries_tags", pa.list_(pa.string()), nullable=True), + pa.field("created_t", pa.int64(), nullable=True), + pa.field("creator", pa.string(), nullable=True), + pa.field("data_quality_errors_tags", pa.list_(pa.string()), nullable=True), + pa.field("data_quality_info_tags", pa.list_(pa.string()), nullable=True), + pa.field("data_quality_warnings_tags", pa.list_(pa.string()), nullable=True), + pa.field("data_sources_tags", pa.list_(pa.string()), nullable=True), + pa.field("ecoscore_grade", pa.string(), nullable=True), + pa.field("ecoscore_score", pa.int32(), nullable=True), + pa.field("ecoscore_tags", pa.list_(pa.string()), nullable=True), + pa.field("editors", pa.list_(pa.string()), nullable=True), + pa.field("emb_codes_tags", pa.list_(pa.string()), nullable=True), + pa.field("emb_codes", pa.string(), nullable=True), + pa.field("entry_dates_tags", pa.list_(pa.string()), nullable=True), + pa.field("food_groups_tags", pa.list_(pa.string()), nullable=True), + pa.field("generic_name", pa.string(), nullable=True), + pa.field("images", IMAGES_DATATYPE, nullable=True), + pa.field("informers_tags", pa.list_(pa.string()), nullable=True), + pa.field("ingredients_analysis_tags", pa.list_(pa.string()), nullable=True), + pa.field("ingredients_from_palm_oil_n", pa.int32(), nullable=True), + pa.field("ingredients_n", pa.int32(), nullable=True), + pa.field("ingredients_original_tags", pa.list_(pa.string()), nullable=True), + pa.field("ingredients_percent_analysis", pa.int32(), nullable=True), + pa.field("ingredients_tags", pa.list_(pa.string()), nullable=True), + pa.field("ingredients_text", LANGUAGE_FIELD_DATATYPE, nullable=True), + pa.field("ingredients_with_specified_percent_n", pa.int32(), nullable=True), + pa.field("ingredients_with_unspecified_percent_n", pa.int32(), nullable=True), + pa.field("ingredients_without_ciqual_codes_n", pa.int32(), nullable=True), + pa.field( + "ingredients_without_ciqual_codes", pa.list_(pa.string()), nullable=True + ), + pa.field("ingredients", pa.string(), nullable=True), + pa.field("known_ingredients_n", pa.int32(), nullable=True), + pa.field("labels_tags", pa.list_(pa.string()), nullable=True), + pa.field("labels", pa.string(), nullable=True), + pa.field("lang", pa.string(), nullable=True), + pa.field("languages_tags", pa.list_(pa.string()), nullable=True), + pa.field("last_edit_dates_tags", pa.list_(pa.string()), nullable=True), + pa.field("last_editor", pa.string(), nullable=True), + pa.field("last_image_t", pa.int64(), nullable=True), + pa.field("last_modified_by", pa.string(), nullable=True), + pa.field("last_modified_t", pa.int64(), nullable=True), + pa.field("last_updated_t", pa.int64(), nullable=True), + pa.field("link", pa.string(), nullable=True), + pa.field("main_countries_tags", pa.list_(pa.string()), nullable=True), + pa.field("manufacturing_places_tags", pa.list_(pa.string()), nullable=True), + pa.field("manufacturing_places", pa.string(), nullable=True), + pa.field("max_imgid", pa.int32(), nullable=True), + pa.field("minerals_tags", pa.list_(pa.string()), nullable=True), + pa.field("misc_tags", pa.list_(pa.string()), nullable=True), + pa.field("new_additives_n", pa.int32(), nullable=True), + pa.field("no_nutrition_data", pa.bool_(), nullable=True), + pa.field("nova_group", pa.int32(), nullable=True), + pa.field("nova_groups_tags", pa.list_(pa.string()), nullable=True), + pa.field("nova_groups", pa.string(), nullable=True), + pa.field("nucleotides_tags", pa.list_(pa.string()), nullable=True), + pa.field("nutrient_levels_tags", pa.list_(pa.string()), nullable=True), + pa.field("nutriments", NUTRIMENTS_DATATYPE, nullable=True), + pa.field("nutriscore_grade", pa.string(), nullable=True), + pa.field("nutriscore_score", pa.int32(), nullable=True), + pa.field("nutrition_data_per", pa.string(), nullable=True), + pa.field("obsolete", pa.bool_()), + pa.field("origins_tags", pa.list_(pa.string()), nullable=True), + pa.field("origins", pa.string(), nullable=True), + pa.field("packagings_complete", pa.bool_(), nullable=True), + pa.field("packaging_recycling_tags", pa.list_(pa.string()), nullable=True), + pa.field("packaging_shapes_tags", pa.list_(pa.string()), nullable=True), + pa.field("packaging_tags", pa.list_(pa.string()), nullable=True), + pa.field("packaging_text", LANGUAGE_FIELD_DATATYPE, nullable=True), + pa.field("packaging", pa.string(), nullable=True), + pa.field("packagings", PACKAGING_FIELD_DATATYPE, nullable=True), + pa.field("photographers", pa.list_(pa.string()), nullable=True), + pa.field("popularity_key", pa.int64(), nullable=True), + pa.field("popularity_tags", pa.list_(pa.string()), nullable=True), + pa.field("product_name", LANGUAGE_FIELD_DATATYPE, nullable=True), + pa.field("product_quantity_unit", pa.string(), nullable=True), + pa.field("product_quantity", pa.string(), nullable=True), + pa.field("purchase_places_tags", pa.list_(pa.string()), nullable=True), + pa.field("quantity", pa.string(), nullable=True), + pa.field("rev", pa.int32(), nullable=True), + pa.field("scans_n", pa.int32(), nullable=True), + pa.field("serving_quantity", pa.string(), nullable=True), + pa.field("serving_size", pa.string(), nullable=True), + pa.field("states_tags", pa.list_(pa.string()), nullable=True), + pa.field("stores_tags", pa.list_(pa.string()), nullable=True), + pa.field("stores", pa.string(), nullable=True), + pa.field("traces_tags", pa.list_(pa.string()), nullable=True), + pa.field("unique_scans_n", pa.int32(), nullable=True), + pa.field("unknown_ingredients_n", pa.int32(), nullable=True), + pa.field("unknown_nutrients_tags", pa.list_(pa.string()), nullable=True), + pa.field("vitamins_tags", pa.list_(pa.string()), nullable=True), + pa.field("with_non_nutritive_sweeteners", pa.int32(), nullable=True), + pa.field("with_sweeteners", pa.int32(), nullable=True), + ] +) class ImageSize(BaseModel): @@ -196,10 +218,13 @@ class ImageSize(BaseModel): w: int | None = None +ALLOWED_IMAGE_SIZE_KEYS = {"100", "200", "400", "full"} + + class Image(BaseModel): """`Images` schema for postprocessing used for field postprocessing.""" - key: str + key: str | None = None sizes: dict[str, ImageSize | None] uploaded_t: int | None = None imgid: int | None = None @@ -207,46 +232,326 @@ class Image(BaseModel): @model_validator(mode="after") def ignore_extra_sizes(self): - """Literal doesn't accept extra values, returning an error in case of additional - keys. + """Literal doesn't accept extra values, returning an error in case of + additional keys. """ self.sizes = { k: v for k, v in self.sizes.items() if k in ALLOWED_IMAGE_SIZE_KEYS } return self + +class Ingredient(BaseModel): + percent_max: float | None = None + percent_min: float | None = None + is_in_taxonomy: int | None = None + percent_estimate: float | None = None + vegan: str | None = None + id: str | None = None + text: str | None = None + vegetarian: str | None = None + ciqual_food_code: str | None = None + percent: float | None = None + from_palm_oil: str | None = None + ingredients: list["Ingredient"] | None = None + ecobalyse_code: str | None = None + processing: str | None = None + labels: str | None = None + origins: str | None = None + ecobalyse_proxy_code: str | None = None + quantity: str | None = None + quantity_g: float | None = None + ciqual_proxy_food_code: str | None = None + + @model_validator(mode="before") + @classmethod + def parse_nested_ingredients(cls, data: dict): + if "ingredients" in data and isinstance(data["ingredients"], list): + data["ingredients"] = [ + cls.model_validate(ing) for ing in data["ingredients"] + ] + return data + + +class LanguageField(BaseModel): + lang: str + text: str + + +class NutrimentField(BaseModel): + name: str + value: float | None = None + per_100g: float | None = Field(default=None, alias="100g") + serving: float | None = None + unit: str | None = None + prepared_value: float | None = None + prepared_100g: float | None = None + prepared_serving: float | None = None + prepared_unit: str | None = None + + +class PackagingField(BaseModel): + material: str | None = None + number_of_units: int | None = None + quantity_per_unit: str | None = None + quantity_per_unit_unit: str | None = None + quantity_per_unit_value: str | None = Field( + default=None, coerce_numbers_to_str=True + ) + recycling: str | None = None + shape: str | None = None + weight_measured: float | None = None + + +class Product(BaseModel): + additives_n: int | None = None + additives_tags: list[str] | None = None + allergens_tags: list[str] | None = None + brands_tags: list[str] | None = None + brands: str | None = None + categories: str | None = None + categories_tags: list[str] | None = None + checkers_tags: list[str] | None = None + ciqual_food_name_tags: list[str] | None = None + cities_tags: list[str] | None = None + code: str + compared_to_category: str | None = None + complete: int | None = None + completeness: float | None = None + correctors_tags: list[str] | None = None + countries_tags: list[str] | None = None + created_t: int | None = None + creator: str | None = None + data_quality_errors_tags: list[str] | None = None + data_quality_info_tags: list[str] | None = None + data_quality_warnings_tags: list[str] | None = None + data_sources_tags: list[str] | None = None + ecoscore_grade: str | None = None + ecoscore_score: int | None = None + ecoscore_tags: list[str] | None = None + editors: list[str] | None = None + emb_codes_tags: list[str] | None = None + emb_codes: str | None = None + entry_dates_tags: list[str] | None = None + food_groups_tags: list[str] | None = None + generic_name: str | None = None + images: list[Image] | None = None + informers_tags: list[str] | None = None + ingredients_analysis_tags: list[str] | None = None + ingredients_from_palm_oil_n: int | None = None + ingredients_n: int | None = None + ingredients_original_tags: list[str] | None = None + ingredients_percent_analysis: int | None = None + ingredients_tags: list[str] | None = None + ingredients_with_specified_percent_n: int | None = None + ingredients_with_unspecified_percent_n: int | None = None + ingredients_without_ciqual_codes_n: int | None = None + ingredients_without_ciqual_codes: list[str] | None = None + ingredients: list[Ingredient] | None = None + known_ingredients_n: int | None = None + labels_tags: list[str] | None = None + labels: str | None = None + lang: str | None = None + languages_tags: list[str] | None = None + last_edit_dates_tags: list[str] | None = None + last_editor: str | None = None + last_image_t: int | None = None + last_modified_by: str | None = None + last_modified_t: int | None = None + last_updated_t: int | None = None + link: str | None = None + main_countries_tags: list[str] | None = None + manufacturing_places_tags: list[str] | None = None + manufacturing_places: str | None = None + max_imgid: int | None = None + minerals_tags: list[str] | None = None + misc_tags: list[str] | None = None + new_additives_n: int | None = None + no_nutrition_data: bool | None = None + nova_group: int | None = None + nova_groups_tags: list[str] | None = None + nova_groups: str | None = None + nucleotides_tags: list[str] | None = None + nutrient_levels_tags: list[str] | None = None + nutriments: list[NutrimentField] | None = None + nutriscore_grade: str | None = None + nutriscore_score: int | None = None + nutrition_data_per: str | None = None + obsolete: bool = False + origins_tags: list[str] | None = None + origins: str | None = None + packagings_complete: bool | None = None + packaging_recycling_tags: list[str] | None = None + packaging_shapes_tags: list[str] | None = None + packaging_tags: list[str] | None = None + packaging_text: list[LanguageField] | None = None + packaging: str | None = None + packagings: list[PackagingField] | None = None + photographers: list[str] | None = None + popularity_key: int | None = None + popularity_tags: list[str] | None = None + product_name: list[LanguageField] | None = None + product_quantity_unit: str | None = None + product_quantity: str | None = Field(default=None, coerce_numbers_to_str=True) + purchase_places_tags: list[str] | None = None + quantity: str | None = None + rev: int | None = None + scans_n: int | None = None + serving_quantity: str | None = Field(default=None, coerce_numbers_to_str=True) + serving_size: str | None = None + states_tags: list[str] | None = None + stores_tags: list[str] | None = None + stores: str | None = None + traces_tags: list[str] | None = None + unique_scans_n: int | None = None + unknown_ingredients_n: int | None = None + unknown_nutrients_tags: list[str] | None = None + vitamins_tags: list[str] | None = None + with_non_nutritive_sweeteners: int | None = None + with_sweeteners: int | None = None + ingredients_text: list[LanguageField] | None = None + + @model_validator(mode="before") + @classmethod + def parse_bool_values(cls, data: dict): + """Parse boolean values from string to bool.""" + data.pop("obsolete", None) + for field_name in ("no_nutrition_data",): + if field_name in data: + data[field_name] = data[field_name] in ( + "on", + "true", + 1, + True, + ) + return data + @model_validator(mode="before") @classmethod - def parse_int_from_string(cls, data: dict): - """Some int are considered as string like '"1517312996"', leading to - int parsing issues + def parse_nutriments(cls, data: dict): + nutriments = data.pop("nutriments", None) + parsed_nutriments: dict[str, dict] = {} + nutriments_end_mapping = { + "_prepared_100g": "prepared_100g", + "_prepared_serving": "prepared_serving", + "_prepared_unit": "prepared_unit", + "_prepared_value": "prepared_value", + "_unit": "unit", + "_value": "value", + "_100g": "100g", + "_serving": "serving", + } + if nutriments: + for key, value in nutriments.items(): + for end_key, new_key in nutriments_end_mapping.items(): + if key.endswith(end_key): + key = key.replace(end_key, "") + parsed_nutriments.setdefault(key, {}) + parsed_nutriments[key][new_key] = value + + data["nutriments"] = [ + {"name": key, **value} for key, value in parsed_nutriments.items() + ] + + else: + data["nutriments"] = None + return data + + @model_validator(mode="before") + @classmethod + def parse_language_fields(cls, data: dict) -> dict: + """Parse language fields (such as `ingredients_text`) into a list of + dictionaries with `lang` and `text` keys. + + In Open Food Facts, main language is stored in the field without a + suffix, while other languages are stored with a suffix of the + language code. + + To make the schema compatible with Parquet, we convert these fields + into a list of dictionaries with `lang` and `text` keys. + This way, the structure is consistent across all language fields. + + The main language is stored with a `lang` value of "main", while other + languages are stored with their language code (2-letter code). """ - imgid = data.get("imgid") - uploaded_t = data.get("uploaded_t") - if imgid and isinstance(imgid, str): - data.update({"imgid": imgid.strip('"')}) - if uploaded_t and isinstance(uploaded_t, str): - data.update({"uploaded_t": uploaded_t.strip('"')}) + for field_name in ("ingredients_text", "product_name", "packaging_text"): + main_language_value = data.pop(field_name, None) + data[field_name] = [] + + if main_language_value: + data[field_name].append({"lang": "main", "text": main_language_value}) + + for key in list(data.keys()): + if key.startswith(f"{field_name}_"): + lang = key.rsplit("_", maxsplit=1)[-1] + value = data.pop(key) + # Sometimes we have a "debug" field that is not a language + # Sometimes we have a language field with a None value + if len(lang) == 2 and value is not None and len(value): + data[field_name].append({"lang": lang, "text": value}) + + if data[field_name] == {}: + data[field_name] = None + + return data + + @model_validator(mode="before") + @classmethod + def parse_images(cls, data: dict) -> dict: + """Parse images field into a list of dictionaries with `key`, `imgid`, + `sizes`, `uploaded_t`, and `uploader` keys. + + In Open Food Facts, images are stored as a dictionary with the image + key as the key and the image data as the value. + + To make the schema compatible with Parquet, we convert these fields + into a list of dictionaries with `key`, `imgid`, `sizes`, `uploaded_t`, + and `uploader` keys. We copy the image key (ex: `3`, `nutrition_fr`,...) + from the original dictionary and add it as a field under the `key` key. + """ + images = data.pop("images", None) + data["images"] = [] + if images: + for key, value in images.items(): + data["images"].append({"key": key, **value}) + return data + + @model_validator(mode="before") + @classmethod + def parse_ecoscore_score(cls, data: dict): + ecoscore_score = data.get("ecoscore_score") + if ecoscore_score and isinstance(ecoscore_score, float): + # Some `ecoscore_score` are float, we need to convert them to int + # to prevent Pydantic from raising an error + data["ecoscore_score"] = int(ecoscore_score) + return data + @field_serializer("ingredients") + def serialize_ingredients( + self, ingredients: list[Ingredient] | None, _info + ) -> str | None: + """Ingredients can be nested, which seems difficult to implement as an + Arrow struct. + To alleviate this, we serialize the ingredients as a JSON string.""" + if ingredients is None: + return None + return orjson.dumps([ing.model_dump() for ing in ingredients]).decode("utf-8") + def export_parquet(dataset_path: Path, output_path: Path) -> None: """Convert a JSONL dataset to Parquet format and push it to Hugging Face - Hub. - """ + Hub.""" logger.info("Start JSONL export to Parquet.") with tempfile.TemporaryDirectory() as tmp_dir: tmp_converted_parquet_path = Path(tmp_dir) / "converted_data.parquet" - tmp_postprocessed_parquet_path = Path(tmp_dir) / "postprocessed_data.parquet" convert_jsonl_to_parquet( - output_file_path=tmp_converted_parquet_path, dataset_path=dataset_path - ) - postprocess_parquet( - parquet_path=tmp_converted_parquet_path, - output_path=tmp_postprocessed_parquet_path, + output_file_path=tmp_converted_parquet_path, + dataset_path=dataset_path, + schema=PRODUCT_SCHEMA, ) # Move dataset file to output_path - shutil.move(tmp_postprocessed_parquet_path, output_path) + shutil.move(tmp_converted_parquet_path, output_path) if settings.ENABLE_HF_PUSH: push_parquet_file_to_hf(data_path=output_path) @@ -258,22 +563,45 @@ def export_parquet(dataset_path: Path, output_path: Path) -> None: def convert_jsonl_to_parquet( output_file_path: Path, dataset_path: Path, + schema: pa.Schema = PRODUCT_SCHEMA, + batch_size: int = 1024, ) -> None: - logger.info("Start conversion from JSONL to Parquet.") - if not dataset_path.exists(): - raise FileNotFoundError(f"{str(dataset_path)} was not found.") - query = SQL_QUERY.replace("{dataset_path}", str(dataset_path)).replace( - "{output_path}", str(output_file_path) - ) - try: - duckdb.sql(query) - except duckdb.Error as e: - logger.error( - "Error executing query: %s \nError message: %s", - query, e - ) - raise - logger.info("JSONL successfully converted into Parquet file.") + """Convert the Open Food Facts JSONL dataset to Parquet format. + + Args: + output_file_path (Path): The path where the Parquet file will be saved. + dataset_path (Path): The path to the Open Food Facts JSONL dataset. + schema (pa.Schema): The schema of the Parquet file. + batch_size (int, optional): The size of the batches used to convert the + dataset. Defaults to 1024. + """ + writer = None + DTYPE_MAP = { + "images": IMAGES_DATATYPE, + "nutriments": NUTRIMENTS_DATATYPE, + "packagings": PACKAGING_FIELD_DATATYPE, + } + for batch in chunked(jsonl_iter(dataset_path), batch_size): + # We use by_alias=True because some fields start with a digit + # (ex: nutriments.100g), and we cannot declare the schema with + # Pydantic without an alias. + products = [Product(**item).model_dump(by_alias=True) for item in batch] + keys = products[0].keys() + data = { + key: pa.array( + [product[key] for product in products], + # Don't let pyarrow guess type for complex types + type=DTYPE_MAP.get(key, None), + ) + for key in keys + } + record_batch = pa.record_batch(data, schema=schema) + if writer is None: + writer = pq.ParquetWriter(output_file_path, schema=record_batch.schema) + writer.write_batch(record_batch) + + if writer is not None: + writer.close() def push_parquet_file_to_hf( @@ -294,70 +622,7 @@ def push_parquet_file_to_hf( repo_id=repo_id, revision=revision, repo_type="dataset", - path_in_repo="products.parquet", + path_in_repo="food.parquet", commit_message=commit_message, ) logger.info("Data succesfully pushed to Hugging Face at %s", repo_id) - - -@timer -def postprocess_parquet( - parquet_path: Path, output_path: Path, batch_size: int = 10000 -) -> None: - logger.info("Start postprocessing parquet") - parquet_file = pq.ParquetFile(parquet_path) - updated_schema = update_schema(parquet_file.schema.to_arrow_schema()) - with pq.ParquetWriter(output_path, schema=updated_schema) as writer: - for batch in parquet_file.iter_batches(batch_size=batch_size): - batch = postprocess_arrow_batch(batch) - writer.write_batch(batch) - logger.info("Parquet post processing done.") - - -def update_schema(schema: pa.Schema) -> pa.Schema: - for field_name, field_datatype in SCHEMAS.items(): - schema = _update_schema_by_field( - schema=schema, field_name=field_name, field_datatype=field_datatype - ) - return schema - - -def _update_schema_by_field( - schema: pa.Schema, field_name: str, field_datatype: pa.DataType -) -> pa.schema: - field_index = schema.get_field_index(field_name) - schema = schema.remove(field_index) - schema = schema.insert(field_index, pa.field(field_name, field_datatype)) - return schema - - -def postprocess_arrow_batch(batch: pa.RecordBatch) -> pa.RecordBatch: - """Add new processing features here.""" - batch = postprocess_images(batch) - return batch - - -def postprocess_images( - batch: pa.RecordBatch, datatype: pa.DataType = IMAGES_DATATYPE -) -> pa.RecordBatch: - """The `Images` field is a nested JSON with inconsistent data type. - We extract and structure the data as a list of dict using Pydantic. - Each dict corresponds to an image from the same product. - - ### Notes: - The process is quite long (20 - 30 min). - Possibilities: concurrency, pyarrow.compute, ... - """ - # Duckdb converted the json filed into a map_array: - # https://arrow.apache.org/docs/python/generated/pyarrow.MapArray.html#pyarrow-maparray - postprocessed_images = [ - [Image(key=key, **value).model_dump() for key, value in image] if image else [] - for image in batch["images"].to_pylist() - ] - images_col_index = batch.schema.get_field_index("images") - batch = batch.set_column( - images_col_index, - pa.field("images", datatype), - pa.array(postprocessed_images, type=datatype), - ) - return batch diff --git a/pyproject.toml b/pyproject.toml index db006b5..3799fc7 100644 --- a/pyproject.toml +++ b/pyproject.toml @@ -9,7 +9,9 @@ dependencies = [ "duckdb==1.1.2", "huggingface-hub>=0.26.2", "minio>=7.2.10", + "more-itertools>=10.5.0", "openfoodfacts>=1.1.5", + "orjson>=3.10.11", "pyarrow>=18.0.0", "pytz>=2024.2", "requests>=2.32.3", @@ -17,8 +19,6 @@ dependencies = [ "sentry-sdk>=2.18.0", "toml>=0.10.2", "typer>=0.12.5", - "types-pytz>=2024.2.0.20241003", - "types-toml>=0.10.8.20240310", ] @@ -32,9 +32,10 @@ max-doc-length = 88 [dependency-groups] dev = [ "coverage[toml]>=7.6.4", - "ipykernel>=6.29.5", "pre-commit>=4.0.1", "pytest-cov>=6.0.0", "pytest>=8.3.3", "ruff>=0.7.3", + "types-pytz>=2024.2.0.20241003", + "types-toml>=0.10.8.20240310", ] diff --git a/uv.lock b/uv.lock index f7461e8..656774e 100644 --- a/uv.lock +++ b/uv.lock @@ -16,15 +16,6 @@ wheels = [ { url = "https://files.pythonhosted.org/packages/78/b6/6307fbef88d9b5ee7421e68d78a9f162e0da4900bc5f5793f6d3d0e34fb8/annotated_types-0.7.0-py3-none-any.whl", hash = "sha256:1f02e8b43a8fbbc3f3e0d4f0f4bfc8131bcb4eebe8849b8e5c773f3a1c582a53", size = 13643 }, ] -[[package]] -name = "appnope" -version = "0.1.4" -source = { registry = "https://pypi.org/simple" } -sdist = { url = "https://files.pythonhosted.org/packages/35/5d/752690df9ef5b76e169e68d6a129fa6d08a7100ca7f754c89495db3c6019/appnope-0.1.4.tar.gz", hash = "sha256:1de3860566df9caf38f01f86f65e0e13e379af54f9e4bee1e66b48f2efffd1ee", size = 4170 } -wheels = [ - { url = "https://files.pythonhosted.org/packages/81/29/5ecc3a15d5a33e31b26c11426c45c501e439cb865d0bff96315d86443b78/appnope-0.1.4-py2.py3-none-any.whl", hash = "sha256:502575ee11cd7a28c0205f379b525beefebab9d161b7c964670864014ed7213c", size = 4321 }, -] - [[package]] name = "apscheduler" version = "3.10.4" @@ -72,18 +63,6 @@ wheels = [ { url = "https://files.pythonhosted.org/packages/5a/e4/bf8034d25edaa495da3c8a3405627d2e35758e44ff6eaa7948092646fdcc/argon2_cffi_bindings-21.2.0-cp38-abi3-macosx_10_9_universal2.whl", hash = "sha256:e415e3f62c8d124ee16018e491a009937f8cf7ebf5eb430ffc5de21b900dad93", size = 53104 }, ] -[[package]] -name = "asttokens" -version = "2.4.1" -source = { registry = "https://pypi.org/simple" } -dependencies = [ - { name = "six" }, -] -sdist = { url = "https://files.pythonhosted.org/packages/45/1d/f03bcb60c4a3212e15f99a56085d93093a497718adf828d050b9d675da81/asttokens-2.4.1.tar.gz", hash = "sha256:b03869718ba9a6eb027e134bfdf69f38a236d681c83c160d510768af11254ba0", size = 62284 } -wheels = [ - { url = "https://files.pythonhosted.org/packages/45/86/4736ac618d82a20d87d2f92ae19441ebc7ac9e7a581d7e58bbe79233b24a/asttokens-2.4.1-py2.py3-none-any.whl", hash = "sha256:051ed49c3dcae8913ea7cd08e46a606dba30b79993209636c4875bc1d637bc24", size = 27764 }, -] - [[package]] name = "async-timeout" version = "4.0.3" @@ -258,18 +237,6 @@ wheels = [ { url = "https://files.pythonhosted.org/packages/d1/d6/3965ed04c63042e047cb6a3e6ed1a63a35087b6a609aa3a15ed8ac56c221/colorama-0.4.6-py2.py3-none-any.whl", hash = "sha256:4f1d9991f5acc0ca119f9d443620b77f9d6b33703e51011c16baf57afb285fc6", size = 25335 }, ] -[[package]] -name = "comm" -version = "0.2.2" -source = { registry = "https://pypi.org/simple" } -dependencies = [ - { name = "traitlets" }, -] -sdist = { url = "https://files.pythonhosted.org/packages/e9/a8/fb783cb0abe2b5fded9f55e5703015cdf1c9c85b3669087c538dd15a6a86/comm-0.2.2.tar.gz", hash = "sha256:3fd7a84065306e07bea1773df6eb8282de51ba82f77c72f9c85716ab11fe980e", size = 6210 } -wheels = [ - { url = "https://files.pythonhosted.org/packages/e6/75/49e5bfe642f71f272236b5b2d2691cf915a7283cc0ceda56357b61daa538/comm-0.2.2-py3-none-any.whl", hash = "sha256:e6fb86cb70ff661ee8c9c14e7d36d6de3b4066f1441be4063df9c5009f0a64d3", size = 7180 }, -] - [[package]] name = "coverage" version = "7.6.4" @@ -334,40 +301,6 @@ toml = [ { name = "tomli", marker = "python_full_version <= '3.11'" }, ] -[[package]] -name = "debugpy" -version = "1.8.8" -source = { registry = "https://pypi.org/simple" } -sdist = { url = "https://files.pythonhosted.org/packages/e4/5e/7667b95c9d7ddb25c047143a3a47685f9be2a5d3d177a85a730b22dc6e5c/debugpy-1.8.8.zip", hash = "sha256:e6355385db85cbd666be703a96ab7351bc9e6c61d694893206f8001e22aee091", size = 4928684 } -wheels = [ - { url = "https://files.pythonhosted.org/packages/77/79/677d71c342d5f24baf81d262c9e0c19cac3b17b4e4587c0574eaa3964ab1/debugpy-1.8.8-cp310-cp310-macosx_14_0_x86_64.whl", hash = "sha256:e59b1607c51b71545cb3496876544f7186a7a27c00b436a62f285603cc68d1c6", size = 2088337 }, - { url = "https://files.pythonhosted.org/packages/11/b3/4119fa89b66bcc64a3b186ea52ee7c22bccc5d1765ee890887678b0e3e76/debugpy-1.8.8-cp310-cp310-manylinux_2_5_x86_64.manylinux1_x86_64.manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:a6531d952b565b7cb2fbd1ef5df3d333cf160b44f37547a4e7cf73666aca5d8d", size = 3567953 }, - { url = "https://files.pythonhosted.org/packages/e8/4a/01f70b44af27c13d720446ce9bf14467c90411e90e6c6ffbb7c45845d23d/debugpy-1.8.8-cp310-cp310-win32.whl", hash = "sha256:b01f4a5e5c5fb1d34f4ccba99a20ed01eabc45a4684f4948b5db17a319dfb23f", size = 5128658 }, - { url = "https://files.pythonhosted.org/packages/2b/a5/c4210f3842db0911a49b3030bfc217e0772bfd33d7aa50996bc762e8a334/debugpy-1.8.8-cp310-cp310-win_amd64.whl", hash = "sha256:535f4fb1c024ddca5913bb0eb17880c8f24ba28aa2c225059db145ee557035e9", size = 5157545 }, - { url = "https://files.pythonhosted.org/packages/38/55/6b5596ea6d5490e17abc2896f1fbe83d31205a22629805daccd30686721c/debugpy-1.8.8-cp311-cp311-macosx_14_0_universal2.whl", hash = "sha256:c399023146e40ae373753a58d1be0a98bf6397fadc737b97ad612886b53df318", size = 2187057 }, - { url = "https://files.pythonhosted.org/packages/3f/f7/c2ee07f6335c3620c1435aef2c4d3d4853f6b7fb0789aa2c52a84498ef90/debugpy-1.8.8-cp311-cp311-manylinux_2_5_x86_64.manylinux1_x86_64.manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:09cc7b162586ea2171eea055985da2702b0723f6f907a423c9b2da5996ad67ba", size = 3139844 }, - { url = "https://files.pythonhosted.org/packages/0d/68/01d335338b68bdebab11de573f4631c7bf0404666ccbf474621123497702/debugpy-1.8.8-cp311-cp311-win32.whl", hash = "sha256:eea8821d998ebeb02f0625dd0d76839ddde8cbf8152ebbe289dd7acf2cdc6b98", size = 5049405 }, - { url = "https://files.pythonhosted.org/packages/22/1d/3f69460b4b8f01dace3882513de71a446eb37ee57fe2112be948fadebde8/debugpy-1.8.8-cp311-cp311-win_amd64.whl", hash = "sha256:d4483836da2a533f4b1454dffc9f668096ac0433de855f0c22cdce8c9f7e10c4", size = 5075025 }, - { url = "https://files.pythonhosted.org/packages/c2/04/8e79824c4d9100049bda056aeaf8f2765d1325a4521a87f8bb373c977236/debugpy-1.8.8-cp312-cp312-macosx_14_0_universal2.whl", hash = "sha256:0cc94186340be87b9ac5a707184ec8f36547fb66636d1029ff4f1cc020e53996", size = 2514549 }, - { url = "https://files.pythonhosted.org/packages/a5/6b/c336d1eba1aedc9f654aefcdfe47ec41657d149f28ca1477c5f9009681c6/debugpy-1.8.8-cp312-cp312-manylinux_2_5_x86_64.manylinux1_x86_64.manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:64674e95916e53c2e9540a056e5f489e0ad4872645399d778f7c598eacb7b7f9", size = 4229617 }, - { url = "https://files.pythonhosted.org/packages/63/9c/d9276c41e9e14164b31bcba789c87a355c091d0fc2d4e4e36a4881c9aa54/debugpy-1.8.8-cp312-cp312-win32.whl", hash = "sha256:5c6e885dbf12015aed73770f29dec7023cb310d0dc2ba8bfbeb5c8e43f80edc9", size = 5167033 }, - { url = "https://files.pythonhosted.org/packages/6d/1c/fd4bc22196b2d0defaa9f644ea4d676d0cb53b6434091b5fa2d4e49c85f2/debugpy-1.8.8-cp312-cp312-win_amd64.whl", hash = "sha256:19ffbd84e757a6ca0113574d1bf5a2298b3947320a3e9d7d8dc3377f02d9f864", size = 5209968 }, - { url = "https://files.pythonhosted.org/packages/90/45/6745f342bbf41bde7eb5dbf5567b794a4a5498a7a729146cb3101b875b30/debugpy-1.8.8-cp313-cp313-macosx_14_0_universal2.whl", hash = "sha256:705cd123a773d184860ed8dae99becd879dfec361098edbefb5fc0d3683eb804", size = 2499523 }, - { url = "https://files.pythonhosted.org/packages/5c/39/0374610062a384648db9b7b315d0c906facf23613bfd19527135a7c0a420/debugpy-1.8.8-cp313-cp313-manylinux_2_5_x86_64.manylinux1_x86_64.manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:890fd16803f50aa9cb1a9b9b25b5ec321656dd6b78157c74283de241993d086f", size = 4218219 }, - { url = "https://files.pythonhosted.org/packages/cc/19/5b8a68eb9bbafd6bfd27ba0ed93d411f3fd50935ecdd2df242de2110a7c9/debugpy-1.8.8-cp313-cp313-win32.whl", hash = "sha256:90244598214bbe704aa47556ec591d2f9869ff9e042e301a2859c57106649add", size = 5171845 }, - { url = "https://files.pythonhosted.org/packages/cd/04/7381dab68e40ca877d5beffc25ad1a0d3d2557cf7465405435fac9e27ef5/debugpy-1.8.8-cp313-cp313-win_amd64.whl", hash = "sha256:4b93e4832fd4a759a0c465c967214ed0c8a6e8914bced63a28ddb0dd8c5f078b", size = 5206890 }, - { url = "https://files.pythonhosted.org/packages/03/99/ec2190d03df5dbd610418919bd1c3d8e6f61d0a97894e11ade6d3260cfb8/debugpy-1.8.8-py2.py3-none-any.whl", hash = "sha256:ec684553aba5b4066d4de510859922419febc710df7bba04fe9e7ef3de15d34f", size = 5157124 }, -] - -[[package]] -name = "decorator" -version = "5.1.1" -source = { registry = "https://pypi.org/simple" } -sdist = { url = "https://files.pythonhosted.org/packages/66/0c/8d907af351aa16b42caae42f9d6aa37b900c67308052d10fdce809f8d952/decorator-5.1.1.tar.gz", hash = "sha256:637996211036b6385ef91435e4fae22989472f9d571faba8927ba8253acbc330", size = 35016 } -wheels = [ - { url = "https://files.pythonhosted.org/packages/d5/50/83c593b07763e1161326b3b8c6686f0f4b0f24d5526546bee538c89837d6/decorator-5.1.1-py3-none-any.whl", hash = "sha256:b8c3f85900b9dc423225913c5aace94729fe1fa9763b38939a95226f02d37186", size = 9073 }, -] - [[package]] name = "distlib" version = "0.3.9" @@ -426,15 +359,6 @@ wheels = [ { url = "https://files.pythonhosted.org/packages/02/cc/b7e31358aac6ed1ef2bb790a9746ac2c69bcb3c8588b41616914eb106eaf/exceptiongroup-1.2.2-py3-none-any.whl", hash = "sha256:3111b9d131c238bec2f8f516e123e14ba243563fb135d3fe885990585aa7795b", size = 16453 }, ] -[[package]] -name = "executing" -version = "2.1.0" -source = { registry = "https://pypi.org/simple" } -sdist = { url = "https://files.pythonhosted.org/packages/8c/e3/7d45f492c2c4a0e8e0fad57d081a7c8a0286cdd86372b070cca1ec0caa1e/executing-2.1.0.tar.gz", hash = "sha256:8ea27ddd260da8150fa5a708269c4a10e76161e2496ec3e587da9e3c0fe4b9ab", size = 977485 } -wheels = [ - { url = "https://files.pythonhosted.org/packages/b5/fd/afcd0496feca3276f509df3dbd5dae726fcc756f1a08d9e25abe1733f962/executing-2.1.0-py2.py3-none-any.whl", hash = "sha256:8d63781349375b5ebccc3142f4b30350c0cd9c79f921cde38be2be4637e98eaf", size = 25805 }, -] - [[package]] name = "filelock" version = "3.16.1" @@ -498,94 +422,6 @@ wheels = [ { url = "https://files.pythonhosted.org/packages/ef/a6/62565a6e1cf69e10f5727360368e451d4b7f58beeac6173dc9db836a5b46/iniconfig-2.0.0-py3-none-any.whl", hash = "sha256:b6a85871a79d2e3b22d2d1b94ac2824226a63c6b741c88f7ae975f18b6778374", size = 5892 }, ] -[[package]] -name = "ipykernel" -version = "6.29.5" -source = { registry = "https://pypi.org/simple" } -dependencies = [ - { name = "appnope", marker = "platform_system == 'Darwin'" }, - { name = "comm" }, - { name = "debugpy" }, - { name = "ipython" }, - { name = "jupyter-client" }, - { name = "jupyter-core" }, - { name = "matplotlib-inline" }, - { name = "nest-asyncio" }, - { name = "packaging" }, - { name = "psutil" }, - { name = "pyzmq" }, - { name = "tornado" }, - { name = "traitlets" }, -] -sdist = { url = "https://files.pythonhosted.org/packages/e9/5c/67594cb0c7055dc50814b21731c22a601101ea3b1b50a9a1b090e11f5d0f/ipykernel-6.29.5.tar.gz", hash = "sha256:f093a22c4a40f8828f8e330a9c297cb93dcab13bd9678ded6de8e5cf81c56215", size = 163367 } -wheels = [ - { url = "https://files.pythonhosted.org/packages/94/5c/368ae6c01c7628438358e6d337c19b05425727fbb221d2a3c4303c372f42/ipykernel-6.29.5-py3-none-any.whl", hash = "sha256:afdb66ba5aa354b09b91379bac28ae4afebbb30e8b39510c9690afb7a10421b5", size = 117173 }, -] - -[[package]] -name = "ipython" -version = "8.29.0" -source = { registry = "https://pypi.org/simple" } -dependencies = [ - { name = "colorama", marker = "sys_platform == 'win32'" }, - { name = "decorator" }, - { name = "exceptiongroup", marker = "python_full_version < '3.11'" }, - { name = "jedi" }, - { name = "matplotlib-inline" }, - { name = "pexpect", marker = "sys_platform != 'emscripten' and sys_platform != 'win32'" }, - { name = "prompt-toolkit" }, - { name = "pygments" }, - { name = "stack-data" }, - { name = "traitlets" }, - { name = "typing-extensions", marker = "python_full_version < '3.12'" }, -] -sdist = { url = "https://files.pythonhosted.org/packages/85/e0/a3f36dde97e12121106807d80485423ae4c5b27ce60d40d4ab0bab18a9db/ipython-8.29.0.tar.gz", hash = "sha256:40b60e15b22591450eef73e40a027cf77bd652e757523eebc5bd7c7c498290eb", size = 5497513 } -wheels = [ - { url = "https://files.pythonhosted.org/packages/c5/a5/c15ed187f1b3fac445bb42a2dedd8dec1eee1718b35129242049a13a962f/ipython-8.29.0-py3-none-any.whl", hash = "sha256:0188a1bd83267192123ccea7f4a8ed0a78910535dbaa3f37671dca76ebd429c8", size = 819911 }, -] - -[[package]] -name = "jedi" -version = "0.19.2" -source = { registry = "https://pypi.org/simple" } -dependencies = [ - { name = "parso" }, -] -sdist = { url = "https://files.pythonhosted.org/packages/72/3a/79a912fbd4d8dd6fbb02bf69afd3bb72cf0c729bb3063c6f4498603db17a/jedi-0.19.2.tar.gz", hash = "sha256:4770dc3de41bde3966b02eb84fbcf557fb33cce26ad23da12c742fb50ecb11f0", size = 1231287 } -wheels = [ - { url = "https://files.pythonhosted.org/packages/c0/5a/9cac0c82afec3d09ccd97c8b6502d48f165f9124db81b4bcb90b4af974ee/jedi-0.19.2-py2.py3-none-any.whl", hash = "sha256:a8ef22bde8490f57fe5c7681a3c83cb58874daf72b4784de3cce5b6ef6edb5b9", size = 1572278 }, -] - -[[package]] -name = "jupyter-client" -version = "8.6.3" -source = { registry = "https://pypi.org/simple" } -dependencies = [ - { name = "jupyter-core" }, - { name = "python-dateutil" }, - { name = "pyzmq" }, - { name = "tornado" }, - { name = "traitlets" }, -] -sdist = { url = "https://files.pythonhosted.org/packages/71/22/bf9f12fdaeae18019a468b68952a60fe6dbab5d67cd2a103cac7659b41ca/jupyter_client-8.6.3.tar.gz", hash = "sha256:35b3a0947c4a6e9d589eb97d7d4cd5e90f910ee73101611f01283732bd6d9419", size = 342019 } -wheels = [ - { url = "https://files.pythonhosted.org/packages/11/85/b0394e0b6fcccd2c1eeefc230978a6f8cb0c5df1e4cd3e7625735a0d7d1e/jupyter_client-8.6.3-py3-none-any.whl", hash = "sha256:e8a19cc986cc45905ac3362915f410f3af85424b4c0905e94fa5f2cb08e8f23f", size = 106105 }, -] - -[[package]] -name = "jupyter-core" -version = "5.7.2" -source = { registry = "https://pypi.org/simple" } -dependencies = [ - { name = "platformdirs" }, - { name = "pywin32", marker = "platform_python_implementation != 'PyPy' and sys_platform == 'win32'" }, - { name = "traitlets" }, -] -sdist = { url = "https://files.pythonhosted.org/packages/00/11/b56381fa6c3f4cc5d2cf54a7dbf98ad9aa0b339ef7a601d6053538b079a7/jupyter_core-5.7.2.tar.gz", hash = "sha256:aa5f8d32bbf6b431ac830496da7392035d6f61b4f54872f15c4bd2a9c3f536d9", size = 87629 } -wheels = [ - { url = "https://files.pythonhosted.org/packages/c9/fb/108ecd1fe961941959ad0ee4e12ee7b8b1477247f30b1fdfd83ceaf017f0/jupyter_core-5.7.2-py3-none-any.whl", hash = "sha256:4f7315d2f6b4bcf2e3e7cb6e46772eba760ae459cd1f59d29eb57b0a01bd7409", size = 28965 }, -] - [[package]] name = "markdown-it-py" version = "3.0.0" @@ -598,18 +434,6 @@ wheels = [ { url = "https://files.pythonhosted.org/packages/42/d7/1ec15b46af6af88f19b8e5ffea08fa375d433c998b8a7639e76935c14f1f/markdown_it_py-3.0.0-py3-none-any.whl", hash = "sha256:355216845c60bd96232cd8d8c40e8f9765cc86f46880e43a8fd22dc1a1a8cab1", size = 87528 }, ] -[[package]] -name = "matplotlib-inline" -version = "0.1.7" -source = { registry = "https://pypi.org/simple" } -dependencies = [ - { name = "traitlets" }, -] -sdist = { url = "https://files.pythonhosted.org/packages/99/5b/a36a337438a14116b16480db471ad061c36c3694df7c2084a0da7ba538b7/matplotlib_inline-0.1.7.tar.gz", hash = "sha256:8423b23ec666be3d16e16b60bdd8ac4e86e840ebd1dd11a30b9f117f2fa0ab90", size = 8159 } -wheels = [ - { url = "https://files.pythonhosted.org/packages/8f/8e/9ad090d3553c280a8060fbf6e24dc1c0c29704ee7d1c372f0c174aa59285/matplotlib_inline-0.1.7-py3-none-any.whl", hash = "sha256:df192d39a4ff8f21b1895d72e6a13f5fcc5099f00fa84384e0ea28c2cc0653ca", size = 9899 }, -] - [[package]] name = "mdurl" version = "0.1.2" @@ -636,12 +460,12 @@ wheels = [ ] [[package]] -name = "nest-asyncio" -version = "1.6.0" +name = "more-itertools" +version = "10.5.0" source = { registry = "https://pypi.org/simple" } -sdist = { url = "https://files.pythonhosted.org/packages/83/f8/51569ac65d696c8ecbee95938f89d4abf00f47d58d48f6fbabfe8f0baefe/nest_asyncio-1.6.0.tar.gz", hash = "sha256:6f172d5449aca15afd6c646851f4e31e02c598d553a667e38cafa997cfec55fe", size = 7418 } +sdist = { url = "https://files.pythonhosted.org/packages/51/78/65922308c4248e0eb08ebcbe67c95d48615cc6f27854b6f2e57143e9178f/more-itertools-10.5.0.tar.gz", hash = "sha256:5482bfef7849c25dc3c6dd53a6173ae4795da2a41a80faea6700d9f5846c5da6", size = 121020 } wheels = [ - { url = "https://files.pythonhosted.org/packages/a0/c4/c2971a3ba4c6103a3d10c4b0f24f461ddc027f0f09763220cf35ca1401b3/nest_asyncio-1.6.0-py3-none-any.whl", hash = "sha256:87af6efd6b5e897c81050477ef65c62e2b2f35d51703cae01aff2905b1852e1c", size = 5195 }, + { url = "https://files.pythonhosted.org/packages/48/7e/3a64597054a70f7c86eb0a7d4fc315b8c1ab932f64883a297bdffeb5f967/more_itertools-10.5.0-py3-none-any.whl", hash = "sha256:037b0d3203ce90cca8ab1defbbdac29d5f993fc20131f3664dc8d6acfa872aef", size = 60952 }, ] [[package]] @@ -670,13 +494,15 @@ wheels = [ [[package]] name = "openfoodfacts-exports" version = "0.1.1" -source = { editable = "." } +source = { virtual = "." } dependencies = [ { name = "apscheduler" }, { name = "duckdb" }, { name = "huggingface-hub" }, { name = "minio" }, + { name = "more-itertools" }, { name = "openfoodfacts" }, + { name = "orjson" }, { name = "pyarrow" }, { name = "pytz" }, { name = "requests" }, @@ -684,18 +510,17 @@ dependencies = [ { name = "sentry-sdk" }, { name = "toml" }, { name = "typer" }, - { name = "types-pytz" }, - { name = "types-toml" }, ] [package.dev-dependencies] dev = [ { name = "coverage", extra = ["toml"] }, - { name = "ipykernel" }, { name = "pre-commit" }, { name = "pytest" }, { name = "pytest-cov" }, { name = "ruff" }, + { name = "types-pytz" }, + { name = "types-toml" }, ] [package.metadata] @@ -704,7 +529,9 @@ requires-dist = [ { name = "duckdb", specifier = "==1.1.2" }, { name = "huggingface-hub", specifier = ">=0.26.2" }, { name = "minio", specifier = ">=7.2.10" }, + { name = "more-itertools", specifier = ">=10.5.0" }, { name = "openfoodfacts", specifier = ">=1.1.5" }, + { name = "orjson", specifier = ">=3.10.11" }, { name = "pyarrow", specifier = ">=18.0.0" }, { name = "pytz", specifier = ">=2024.2" }, { name = "requests", specifier = ">=2.32.3" }, @@ -712,18 +539,62 @@ requires-dist = [ { name = "sentry-sdk", specifier = ">=2.18.0" }, { name = "toml", specifier = ">=0.10.2" }, { name = "typer", specifier = ">=0.12.5" }, - { name = "types-pytz", specifier = ">=2024.2.0.20241003" }, - { name = "types-toml", specifier = ">=0.10.8.20240310" }, ] [package.metadata.requires-dev] dev = [ { name = "coverage", extras = ["toml"], specifier = ">=7.6.4" }, - { name = "ipykernel", specifier = ">=6.29.5" }, { name = "pre-commit", specifier = ">=4.0.1" }, { name = "pytest", specifier = ">=8.3.3" }, { name = "pytest-cov", specifier = ">=6.0.0" }, { name = "ruff", specifier = ">=0.7.3" }, + { name = "types-pytz", specifier = ">=2024.2.0.20241003" }, + { name = "types-toml", specifier = ">=0.10.8.20240310" }, +] + +[[package]] +name = "orjson" +version = "3.10.11" +source = { registry = "https://pypi.org/simple" } +sdist = { url = "https://files.pythonhosted.org/packages/db/3a/10320029954badc7eaa338a15ee279043436f396e965dafc169610e4933f/orjson-3.10.11.tar.gz", hash = "sha256:e35b6d730de6384d5b2dab5fd23f0d76fae8bbc8c353c2f78210aa5fa4beb3ef", size = 5444879 } +wheels = [ + { url = "https://files.pythonhosted.org/packages/3e/63/f7d412e09f6e2c4e2562ddc44e86f2316a7ce9d7f353afa7cbce4f6a78d5/orjson-3.10.11-cp310-cp310-macosx_10_15_x86_64.macosx_11_0_arm64.macosx_10_15_universal2.whl", hash = "sha256:6dade64687f2bd7c090281652fe18f1151292d567a9302b34c2dbb92a3872f1f", size = 266434 }, + { url = "https://files.pythonhosted.org/packages/a2/6a/3dfcd3a8c0e588581c8d1f3d9002cca970432da8a8096c1a42b99914a34d/orjson-3.10.11-cp310-cp310-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:82f07c550a6ccd2b9290849b22316a609023ed851a87ea888c0456485a7d196a", size = 151884 }, + { url = "https://files.pythonhosted.org/packages/41/02/8981bc5ccbc04a2bd49cd86224d5b1e2c7417fb33e83590c66c3a028ede5/orjson-3.10.11-cp310-cp310-manylinux_2_17_armv7l.manylinux2014_armv7l.whl", hash = "sha256:bd9a187742d3ead9df2e49240234d728c67c356516cf4db018833a86f20ec18c", size = 167371 }, + { url = "https://files.pythonhosted.org/packages/df/3f/772a12a417444eccc54fa597955b689848eb121d5e43dd7da9f6658c314d/orjson-3.10.11-cp310-cp310-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:77b0fed6f209d76c1c39f032a70df2d7acf24b1812ca3e6078fd04e8972685a3", size = 154367 }, + { url = "https://files.pythonhosted.org/packages/8a/63/d0d6ba28410ec603fc31726a49dc782c72c0a64f4cd0a6734a6d8bc07a4a/orjson-3.10.11-cp310-cp310-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:63fc9d5fe1d4e8868f6aae547a7b8ba0a2e592929245fff61d633f4caccdcdd6", size = 165726 }, + { url = "https://files.pythonhosted.org/packages/97/6e/d291bf382173af7788b368e4c22d02c7bdb9b7ac29b83e92930841321c16/orjson-3.10.11-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:65cd3e3bb4fbb4eddc3c1e8dce10dc0b73e808fcb875f9fab40c81903dd9323e", size = 142522 }, + { url = "https://files.pythonhosted.org/packages/6d/3b/7364c10fcadf7c08e3658fe7103bf3b0408783f91022be4691fbe0b5ba1d/orjson-3.10.11-cp310-cp310-musllinux_1_2_aarch64.whl", hash = "sha256:6f67c570602300c4befbda12d153113b8974a3340fdcf3d6de095ede86c06d92", size = 146931 }, + { url = "https://files.pythonhosted.org/packages/95/8c/43f454e642cc85ef845cda6efcfddc6b5fe46b897b692412022012e1272c/orjson-3.10.11-cp310-cp310-musllinux_1_2_x86_64.whl", hash = "sha256:1f39728c7f7d766f1f5a769ce4d54b5aaa4c3f92d5b84817053cc9995b977acc", size = 142900 }, + { url = "https://files.pythonhosted.org/packages/bb/29/ca24efe043501b4a4584d728fdc65af5cfc070ab9021a07fb195bce98919/orjson-3.10.11-cp310-none-win32.whl", hash = "sha256:1789d9db7968d805f3d94aae2c25d04014aae3a2fa65b1443117cd462c6da647", size = 144456 }, + { url = "https://files.pythonhosted.org/packages/b7/ec/f15dc012928459cfb96ed86178d92fddb5c01847f2c53fd8be2fa62dee6c/orjson-3.10.11-cp310-none-win_amd64.whl", hash = "sha256:5576b1e5a53a5ba8f8df81872bb0878a112b3ebb1d392155f00f54dd86c83ff6", size = 136442 }, + { url = "https://files.pythonhosted.org/packages/1e/25/c869a1fbd481dcb02c70032fd6a7243de7582bc48c7cae03d6f0985a11c0/orjson-3.10.11-cp311-cp311-macosx_10_15_x86_64.macosx_11_0_arm64.macosx_10_15_universal2.whl", hash = "sha256:1444f9cb7c14055d595de1036f74ecd6ce15f04a715e73f33bb6326c9cef01b6", size = 266432 }, + { url = "https://files.pythonhosted.org/packages/6a/a4/2307155ee92457d28345308f7d8c0e712348404723025613adeffcb531d0/orjson-3.10.11-cp311-cp311-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:cdec57fe3b4bdebcc08a946db3365630332dbe575125ff3d80a3272ebd0ddafe", size = 151884 }, + { url = "https://files.pythonhosted.org/packages/aa/82/daf1b2596dd49fe44a1bd92367568faf6966dcb5d7f99fd437c3d0dc2de6/orjson-3.10.11-cp311-cp311-manylinux_2_17_armv7l.manylinux2014_armv7l.whl", hash = "sha256:4eed32f33a0ea6ef36ccc1d37f8d17f28a1d6e8eefae5928f76aff8f1df85e67", size = 167371 }, + { url = "https://files.pythonhosted.org/packages/63/a8/680578e4589be5fdcfe0186bdd7dc6fe4a39d30e293a9da833cbedd5a56e/orjson-3.10.11-cp311-cp311-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:80df27dd8697242b904f4ea54820e2d98d3f51f91e97e358fc13359721233e4b", size = 154368 }, + { url = "https://files.pythonhosted.org/packages/6e/ce/9cb394b5b01ef34579eeca6d704b21f97248f607067ce95a24ba9ea2698e/orjson-3.10.11-cp311-cp311-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:705f03cee0cb797256d54de6695ef219e5bc8c8120b6654dd460848d57a9af3d", size = 165725 }, + { url = "https://files.pythonhosted.org/packages/49/24/55eeb05cfb36b9e950d05743e6f6fdb7d5f33ca951a27b06ea6d03371aed/orjson-3.10.11-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:03246774131701de8e7059b2e382597da43144a9a7400f178b2a32feafc54bd5", size = 142522 }, + { url = "https://files.pythonhosted.org/packages/94/0c/3a6a289e56dcc9fe67dc6b6d33c91dc5491f9ec4a03745efd739d2acf0ff/orjson-3.10.11-cp311-cp311-musllinux_1_2_aarch64.whl", hash = "sha256:8b5759063a6c940a69c728ea70d7c33583991c6982915a839c8da5f957e0103a", size = 146934 }, + { url = "https://files.pythonhosted.org/packages/1d/5c/a08c0e90a91e2526029a4681ff8c6fc4495b8bab77d48801144e378c7da9/orjson-3.10.11-cp311-cp311-musllinux_1_2_x86_64.whl", hash = "sha256:677f23e32491520eebb19c99bb34675daf5410c449c13416f7f0d93e2cf5f981", size = 142904 }, + { url = "https://files.pythonhosted.org/packages/2c/c9/710286a60b14e88288ca014d43befb08bb0a4a6a0f51b875f8c2f05e8205/orjson-3.10.11-cp311-none-win32.whl", hash = "sha256:a11225d7b30468dcb099498296ffac36b4673a8398ca30fdaec1e6c20df6aa55", size = 144459 }, + { url = "https://files.pythonhosted.org/packages/7d/68/ef7b920e0a09e02b1a30daca1b4864938463797995c2fabe457c1500220a/orjson-3.10.11-cp311-none-win_amd64.whl", hash = "sha256:df8c677df2f9f385fcc85ab859704045fa88d4668bc9991a527c86e710392bec", size = 136444 }, + { url = "https://files.pythonhosted.org/packages/78/f2/a712dbcef6d84ff53e13056e7dc69d9d4844bd1e35e51b7431679ddd154d/orjson-3.10.11-cp312-cp312-macosx_10_15_x86_64.macosx_11_0_arm64.macosx_10_15_universal2.whl", hash = "sha256:360a4e2c0943da7c21505e47cf6bd725588962ff1d739b99b14e2f7f3545ba51", size = 266505 }, + { url = "https://files.pythonhosted.org/packages/94/54/53970831786d71f98fdc13c0f80451324c9b5c20fbf42f42ef6147607ee7/orjson-3.10.11-cp312-cp312-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:496e2cb45de21c369079ef2d662670a4892c81573bcc143c4205cae98282ba97", size = 151745 }, + { url = "https://files.pythonhosted.org/packages/35/38/482667da1ca7ef95d44d4d2328257a144fd2752383e688637c53ed474d2a/orjson-3.10.11-cp312-cp312-manylinux_2_17_armv7l.manylinux2014_armv7l.whl", hash = "sha256:7dfa8db55c9792d53c5952900c6a919cfa377b4f4534c7a786484a6a4a350c19", size = 167274 }, + { url = "https://files.pythonhosted.org/packages/23/2f/5bb0a03e819781d82dadb733fde8ebbe20d1777d1a33715d45ada4d82ce8/orjson-3.10.11-cp312-cp312-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:51f3382415747e0dbda9dade6f1e1a01a9d37f630d8c9049a8ed0e385b7a90c0", size = 154605 }, + { url = "https://files.pythonhosted.org/packages/49/e9/14cc34d45c7bd51665aff9b1bb6b83475a61c52edb0d753fffe1adc97764/orjson-3.10.11-cp312-cp312-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:f35a1b9f50a219f470e0e497ca30b285c9f34948d3c8160d5ad3a755d9299433", size = 165874 }, + { url = "https://files.pythonhosted.org/packages/7b/61/c2781ecf90f99623e97c67a31e8553f38a1ecebaf3189485726ac8641576/orjson-3.10.11-cp312-cp312-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:e2f3b7c5803138e67028dde33450e054c87e0703afbe730c105f1fcd873496d5", size = 142813 }, + { url = "https://files.pythonhosted.org/packages/4d/4f/18c83f78b501b6608569b1610fcb5a25c9bb9ab6a7eb4b3a55131e0fba37/orjson-3.10.11-cp312-cp312-musllinux_1_2_aarch64.whl", hash = "sha256:f91d9eb554310472bd09f5347950b24442600594c2edc1421403d7610a0998fd", size = 146762 }, + { url = "https://files.pythonhosted.org/packages/ba/19/ea80d5b575abd3f76a790409c2b7b8a60f3fc9447965c27d09613b8bddf4/orjson-3.10.11-cp312-cp312-musllinux_1_2_x86_64.whl", hash = "sha256:dfbb2d460a855c9744bbc8e36f9c3a997c4b27d842f3d5559ed54326e6911f9b", size = 143186 }, + { url = "https://files.pythonhosted.org/packages/2c/f5/d835fee01a0284d4b78effc24d16e7609daac2ff6b6851ca1bdd3b6194fc/orjson-3.10.11-cp312-none-win32.whl", hash = "sha256:d4a62c49c506d4d73f59514986cadebb7e8d186ad510c518f439176cf8d5359d", size = 144489 }, + { url = "https://files.pythonhosted.org/packages/03/60/748e0e205060dec74328dfd835e47902eb5522ae011766da76bfff64e2f4/orjson-3.10.11-cp312-none-win_amd64.whl", hash = "sha256:f1eec3421a558ff7a9b010a6c7effcfa0ade65327a71bb9b02a1c3b77a247284", size = 136614 }, + { url = "https://files.pythonhosted.org/packages/13/92/400970baf46b987c058469e9e779fb7a40d54a5754914d3634cca417e054/orjson-3.10.11-cp313-cp313-macosx_10_15_x86_64.macosx_11_0_arm64.macosx_10_15_universal2.whl", hash = "sha256:c46294faa4e4d0eb73ab68f1a794d2cbf7bab33b1dda2ac2959ffb7c61591899", size = 266402 }, + { url = "https://files.pythonhosted.org/packages/3c/fa/f126fc2d817552bd1f67466205abdcbff64eab16f6844fe6df2853528675/orjson-3.10.11-cp313-cp313-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:52e5834d7d6e58a36846e059d00559cb9ed20410664f3ad156cd2cc239a11230", size = 140826 }, + { url = "https://files.pythonhosted.org/packages/ad/18/9b9664d7d4af5b4fe9fe6600b7654afc0684bba528260afdde10c4a530aa/orjson-3.10.11-cp313-cp313-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:a2fc947e5350fdce548bfc94f434e8760d5cafa97fb9c495d2fef6757aa02ec0", size = 142593 }, + { url = "https://files.pythonhosted.org/packages/20/f9/a30c68f12778d5e58e6b5cdd26f86ee2d0babce1a475073043f46fdd8402/orjson-3.10.11-cp313-cp313-musllinux_1_2_aarch64.whl", hash = "sha256:0efabbf839388a1dab5b72b5d3baedbd6039ac83f3b55736eb9934ea5494d258", size = 146777 }, + { url = "https://files.pythonhosted.org/packages/f2/97/12047b0c0e9b391d589fb76eb40538f522edc664f650f8e352fdaaf77ff5/orjson-3.10.11-cp313-cp313-musllinux_1_2_x86_64.whl", hash = "sha256:a3f29634260708c200c4fe148e42b4aae97d7b9fee417fbdd74f8cfc265f15b0", size = 142961 }, + { url = "https://files.pythonhosted.org/packages/a4/97/d904e26c1cabf2dd6ab1b0909e9b790af28a7f0fcb9d8378d7320d4869eb/orjson-3.10.11-cp313-none-win32.whl", hash = "sha256:1a1222ffcee8a09476bbdd5d4f6f33d06d0d6642df2a3d78b7a195ca880d669b", size = 144486 }, + { url = "https://files.pythonhosted.org/packages/42/62/3760bd1e6e949321d99bab238d08db2b1266564d2f708af668f57109bb36/orjson-3.10.11-cp313-none-win_amd64.whl", hash = "sha256:bc274ac261cc69260913b2d1610760e55d3c0801bb3457ba7b9004420b6b4270", size = 136361 }, ] [[package]] @@ -735,27 +606,6 @@ wheels = [ { url = "https://files.pythonhosted.org/packages/08/aa/cc0199a5f0ad350994d660967a8efb233fe0416e4639146c089643407ce6/packaging-24.1-py3-none-any.whl", hash = "sha256:5b8f2217dbdbd2f7f384c41c628544e6d52f2d0f53c6d0c3ea61aa5d1d7ff124", size = 53985 }, ] -[[package]] -name = "parso" -version = "0.8.4" -source = { registry = "https://pypi.org/simple" } -sdist = { url = "https://files.pythonhosted.org/packages/66/94/68e2e17afaa9169cf6412ab0f28623903be73d1b32e208d9e8e541bb086d/parso-0.8.4.tar.gz", hash = "sha256:eb3a7b58240fb99099a345571deecc0f9540ea5f4dd2fe14c2a99d6b281ab92d", size = 400609 } -wheels = [ - { url = "https://files.pythonhosted.org/packages/c6/ac/dac4a63f978e4dcb3c6d3a78c4d8e0192a113d288502a1216950c41b1027/parso-0.8.4-py2.py3-none-any.whl", hash = "sha256:a418670a20291dacd2dddc80c377c5c3791378ee1e8d12bffc35420643d43f18", size = 103650 }, -] - -[[package]] -name = "pexpect" -version = "4.9.0" -source = { registry = "https://pypi.org/simple" } -dependencies = [ - { name = "ptyprocess" }, -] -sdist = { url = "https://files.pythonhosted.org/packages/42/92/cc564bf6381ff43ce1f4d06852fc19a2f11d180f23dc32d9588bee2f149d/pexpect-4.9.0.tar.gz", hash = "sha256:ee7d41123f3c9911050ea2c2dac107568dc43b2d3b0c7557a33212c398ead30f", size = 166450 } -wheels = [ - { url = "https://files.pythonhosted.org/packages/9e/c3/059298687310d527a58bb01f3b1965787ee3b40dce76752eda8b44e9a2c5/pexpect-4.9.0-py2.py3-none-any.whl", hash = "sha256:7236d1e080e4936be2dc3e326cec0af72acf9212a7e1d060210e70a47e253523", size = 63772 }, -] - [[package]] name = "platformdirs" version = "4.3.6" @@ -790,51 +640,6 @@ wheels = [ { url = "https://files.pythonhosted.org/packages/16/8f/496e10d51edd6671ebe0432e33ff800aa86775d2d147ce7d43389324a525/pre_commit-4.0.1-py2.py3-none-any.whl", hash = "sha256:efde913840816312445dc98787724647c65473daefe420785f885e8ed9a06878", size = 218713 }, ] -[[package]] -name = "prompt-toolkit" -version = "3.0.48" -source = { registry = "https://pypi.org/simple" } -dependencies = [ - { name = "wcwidth" }, -] -sdist = { url = "https://files.pythonhosted.org/packages/2d/4f/feb5e137aff82f7c7f3248267b97451da3644f6cdc218edfe549fb354127/prompt_toolkit-3.0.48.tar.gz", hash = "sha256:d6623ab0477a80df74e646bdbc93621143f5caf104206aa29294d53de1a03d90", size = 424684 } -wheels = [ - { url = "https://files.pythonhosted.org/packages/a9/6a/fd08d94654f7e67c52ca30523a178b3f8ccc4237fce4be90d39c938a831a/prompt_toolkit-3.0.48-py3-none-any.whl", hash = "sha256:f49a827f90062e411f1ce1f854f2aedb3c23353244f8108b89283587397ac10e", size = 386595 }, -] - -[[package]] -name = "psutil" -version = "6.1.0" -source = { registry = "https://pypi.org/simple" } -sdist = { url = "https://files.pythonhosted.org/packages/26/10/2a30b13c61e7cf937f4adf90710776b7918ed0a9c434e2c38224732af310/psutil-6.1.0.tar.gz", hash = "sha256:353815f59a7f64cdaca1c0307ee13558a0512f6db064e92fe833784f08539c7a", size = 508565 } -wheels = [ - { url = "https://files.pythonhosted.org/packages/01/9e/8be43078a171381953cfee33c07c0d628594b5dbfc5157847b85022c2c1b/psutil-6.1.0-cp36-abi3-macosx_10_9_x86_64.whl", hash = "sha256:6e2dcd475ce8b80522e51d923d10c7871e45f20918e027ab682f94f1c6351688", size = 247762 }, - { url = "https://files.pythonhosted.org/packages/1d/cb/313e80644ea407f04f6602a9e23096540d9dc1878755f3952ea8d3d104be/psutil-6.1.0-cp36-abi3-macosx_11_0_arm64.whl", hash = "sha256:0895b8414afafc526712c498bd9de2b063deaac4021a3b3c34566283464aff8e", size = 248777 }, - { url = "https://files.pythonhosted.org/packages/65/8e/bcbe2025c587b5d703369b6a75b65d41d1367553da6e3f788aff91eaf5bd/psutil-6.1.0-cp36-abi3-manylinux_2_12_i686.manylinux2010_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:9dcbfce5d89f1d1f2546a2090f4fcf87c7f669d1d90aacb7d7582addece9fb38", size = 284259 }, - { url = "https://files.pythonhosted.org/packages/58/4d/8245e6f76a93c98aab285a43ea71ff1b171bcd90c9d238bf81f7021fb233/psutil-6.1.0-cp36-abi3-manylinux_2_12_x86_64.manylinux2010_x86_64.manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:498c6979f9c6637ebc3a73b3f87f9eb1ec24e1ce53a7c5173b8508981614a90b", size = 287255 }, - { url = "https://files.pythonhosted.org/packages/27/c2/d034856ac47e3b3cdfa9720d0e113902e615f4190d5d1bdb8df4b2015fb2/psutil-6.1.0-cp36-abi3-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:d905186d647b16755a800e7263d43df08b790d709d575105d419f8b6ef65423a", size = 288804 }, - { url = "https://files.pythonhosted.org/packages/ea/55/5389ed243c878725feffc0d6a3bc5ef6764312b6fc7c081faaa2cfa7ef37/psutil-6.1.0-cp37-abi3-win32.whl", hash = "sha256:1ad45a1f5d0b608253b11508f80940985d1d0c8f6111b5cb637533a0e6ddc13e", size = 250386 }, - { url = "https://files.pythonhosted.org/packages/11/91/87fa6f060e649b1e1a7b19a4f5869709fbf750b7c8c262ee776ec32f3028/psutil-6.1.0-cp37-abi3-win_amd64.whl", hash = "sha256:a8fb3752b491d246034fa4d279ff076501588ce8cbcdbb62c32fd7a377d996be", size = 254228 }, -] - -[[package]] -name = "ptyprocess" -version = "0.7.0" -source = { registry = "https://pypi.org/simple" } -sdist = { url = "https://files.pythonhosted.org/packages/20/e5/16ff212c1e452235a90aeb09066144d0c5a6a8c0834397e03f5224495c4e/ptyprocess-0.7.0.tar.gz", hash = "sha256:5c5d0a3b48ceee0b48485e0c26037c0acd7d29765ca3fbb5cb3831d347423220", size = 70762 } -wheels = [ - { url = "https://files.pythonhosted.org/packages/22/a6/858897256d0deac81a172289110f31629fc4cee19b6f01283303e18c8db3/ptyprocess-0.7.0-py2.py3-none-any.whl", hash = "sha256:4b41f3967fce3af57cc7e94b888626c18bf37a083e3651ca8feeb66d492fef35", size = 13993 }, -] - -[[package]] -name = "pure-eval" -version = "0.2.3" -source = { registry = "https://pypi.org/simple" } -sdist = { url = "https://files.pythonhosted.org/packages/cd/05/0a34433a064256a578f1783a10da6df098ceaa4a57bbeaa96a6c0352786b/pure_eval-0.2.3.tar.gz", hash = "sha256:5f4e983f40564c576c7c8635ae88db5956bb2229d7e9237d03b3c0b0190eaf42", size = 19752 } -wheels = [ - { url = "https://files.pythonhosted.org/packages/8e/37/efad0257dc6e593a18957422533ff0f87ede7c9c6ea010a2177d738fb82f/pure_eval-0.2.3-py3-none-any.whl", hash = "sha256:1db8e35b67b3d218d818ae653e27f06c3aa420901fa7b081ca98cbedc874e0d0", size = 11842 }, -] - [[package]] name = "pyarrow" version = "18.0.0" @@ -1030,18 +835,6 @@ wheels = [ { url = "https://files.pythonhosted.org/packages/36/3b/48e79f2cd6a61dbbd4807b4ed46cb564b4fd50a76166b1c4ea5c1d9e2371/pytest_cov-6.0.0-py3-none-any.whl", hash = "sha256:eee6f1b9e61008bd34975a4d5bab25801eb31898b032dd55addc93e96fcaaa35", size = 22949 }, ] -[[package]] -name = "python-dateutil" -version = "2.9.0.post0" -source = { registry = "https://pypi.org/simple" } -dependencies = [ - { name = "six" }, -] -sdist = { url = "https://files.pythonhosted.org/packages/66/c0/0c8b6ad9f17a802ee498c46e004a0eb49bc148f2fd230864601a86dcf6db/python-dateutil-2.9.0.post0.tar.gz", hash = "sha256:37dd54208da7e1cd875388217d5e00ebd4179249f90fb72437e91a35459a0ad3", size = 342432 } -wheels = [ - { url = "https://files.pythonhosted.org/packages/ec/57/56b9bcc3c9c6a792fcbaf139543cee77261f3651ca9da0c93f5c1221264b/python_dateutil-2.9.0.post0-py2.py3-none-any.whl", hash = "sha256:a8b2bc7bffae282281c8140a97d3aa9c14da0b136dfe83f850eea9a5f7470427", size = 229892 }, -] - [[package]] name = "pytz" version = "2024.2" @@ -1051,25 +844,6 @@ wheels = [ { url = "https://files.pythonhosted.org/packages/11/c3/005fcca25ce078d2cc29fd559379817424e94885510568bc1bc53d7d5846/pytz-2024.2-py2.py3-none-any.whl", hash = "sha256:31c7c1817eb7fae7ca4b8c7ee50c72f93aa2dd863de768e1ef4245d426aa0725", size = 508002 }, ] -[[package]] -name = "pywin32" -version = "308" -source = { registry = "https://pypi.org/simple" } -wheels = [ - { url = "https://files.pythonhosted.org/packages/72/a6/3e9f2c474895c1bb61b11fa9640be00067b5c5b363c501ee9c3fa53aec01/pywin32-308-cp310-cp310-win32.whl", hash = "sha256:796ff4426437896550d2981b9c2ac0ffd75238ad9ea2d3bfa67a1abd546d262e", size = 5927028 }, - { url = "https://files.pythonhosted.org/packages/d9/b4/84e2463422f869b4b718f79eb7530a4c1693e96b8a4e5e968de38be4d2ba/pywin32-308-cp310-cp310-win_amd64.whl", hash = "sha256:4fc888c59b3c0bef905ce7eb7e2106a07712015ea1c8234b703a088d46110e8e", size = 6558484 }, - { url = "https://files.pythonhosted.org/packages/9f/8f/fb84ab789713f7c6feacaa08dad3ec8105b88ade8d1c4f0f0dfcaaa017d6/pywin32-308-cp310-cp310-win_arm64.whl", hash = "sha256:a5ab5381813b40f264fa3495b98af850098f814a25a63589a8e9eb12560f450c", size = 7971454 }, - { url = "https://files.pythonhosted.org/packages/eb/e2/02652007469263fe1466e98439831d65d4ca80ea1a2df29abecedf7e47b7/pywin32-308-cp311-cp311-win32.whl", hash = "sha256:5d8c8015b24a7d6855b1550d8e660d8daa09983c80e5daf89a273e5c6fb5095a", size = 5928156 }, - { url = "https://files.pythonhosted.org/packages/48/ef/f4fb45e2196bc7ffe09cad0542d9aff66b0e33f6c0954b43e49c33cad7bd/pywin32-308-cp311-cp311-win_amd64.whl", hash = "sha256:575621b90f0dc2695fec346b2d6302faebd4f0f45c05ea29404cefe35d89442b", size = 6559559 }, - { url = "https://files.pythonhosted.org/packages/79/ef/68bb6aa865c5c9b11a35771329e95917b5559845bd75b65549407f9fc6b4/pywin32-308-cp311-cp311-win_arm64.whl", hash = "sha256:100a5442b7332070983c4cd03f2e906a5648a5104b8a7f50175f7906efd16bb6", size = 7972495 }, - { url = "https://files.pythonhosted.org/packages/00/7c/d00d6bdd96de4344e06c4afbf218bc86b54436a94c01c71a8701f613aa56/pywin32-308-cp312-cp312-win32.whl", hash = "sha256:587f3e19696f4bf96fde9d8a57cec74a57021ad5f204c9e627e15c33ff568897", size = 5939729 }, - { url = "https://files.pythonhosted.org/packages/21/27/0c8811fbc3ca188f93b5354e7c286eb91f80a53afa4e11007ef661afa746/pywin32-308-cp312-cp312-win_amd64.whl", hash = "sha256:00b3e11ef09ede56c6a43c71f2d31857cf7c54b0ab6e78ac659497abd2834f47", size = 6543015 }, - { url = "https://files.pythonhosted.org/packages/9d/0f/d40f8373608caed2255781a3ad9a51d03a594a1248cd632d6a298daca693/pywin32-308-cp312-cp312-win_arm64.whl", hash = "sha256:9b4de86c8d909aed15b7011182c8cab38c8850de36e6afb1f0db22b8959e3091", size = 7976033 }, - { url = "https://files.pythonhosted.org/packages/a9/a4/aa562d8935e3df5e49c161b427a3a2efad2ed4e9cf81c3de636f1fdddfd0/pywin32-308-cp313-cp313-win32.whl", hash = "sha256:1c44539a37a5b7b21d02ab34e6a4d314e0788f1690d65b48e9b0b89f31abbbed", size = 5938579 }, - { url = "https://files.pythonhosted.org/packages/c7/50/b0efb8bb66210da67a53ab95fd7a98826a97ee21f1d22949863e6d588b22/pywin32-308-cp313-cp313-win_amd64.whl", hash = "sha256:fd380990e792eaf6827fcb7e187b2b4b1cede0585e3d0c9e84201ec27b9905e4", size = 6542056 }, - { url = "https://files.pythonhosted.org/packages/26/df/2b63e3e4f2df0224f8aaf6d131f54fe4e8c96400eb9df563e2aae2e1a1f9/pywin32-308-cp313-cp313-win_arm64.whl", hash = "sha256:ef313c46d4c18dfb82a2431e3051ac8f112ccee1a34f29c263c583c568db63cd", size = 7974986 }, -] - [[package]] name = "pyyaml" version = "6.0.2" @@ -1114,79 +888,6 @@ wheels = [ { url = "https://files.pythonhosted.org/packages/fa/de/02b54f42487e3d3c6efb3f89428677074ca7bf43aae402517bc7cca949f3/PyYAML-6.0.2-cp313-cp313-win_amd64.whl", hash = "sha256:8388ee1976c416731879ac16da0aff3f63b286ffdd57cdeb95f3f2e085687563", size = 156446 }, ] -[[package]] -name = "pyzmq" -version = "26.2.0" -source = { registry = "https://pypi.org/simple" } -dependencies = [ - { name = "cffi", marker = "implementation_name == 'pypy'" }, -] -sdist = { url = "https://files.pythonhosted.org/packages/fd/05/bed626b9f7bb2322cdbbf7b4bd8f54b1b617b0d2ab2d3547d6e39428a48e/pyzmq-26.2.0.tar.gz", hash = "sha256:070672c258581c8e4f640b5159297580a9974b026043bd4ab0470be9ed324f1f", size = 271975 } -wheels = [ - { url = "https://files.pythonhosted.org/packages/1f/a8/9837c39aba390eb7d01924ace49d761c8dbe7bc2d6082346d00c8332e431/pyzmq-26.2.0-cp310-cp310-macosx_10_15_universal2.whl", hash = "sha256:ddf33d97d2f52d89f6e6e7ae66ee35a4d9ca6f36eda89c24591b0c40205a3629", size = 1340058 }, - { url = "https://files.pythonhosted.org/packages/a2/1f/a006f2e8e4f7d41d464272012695da17fb95f33b54342612a6890da96ff6/pyzmq-26.2.0-cp310-cp310-macosx_10_9_x86_64.whl", hash = "sha256:dacd995031a01d16eec825bf30802fceb2c3791ef24bcce48fa98ce40918c27b", size = 1008818 }, - { url = "https://files.pythonhosted.org/packages/b6/09/b51b6683fde5ca04593a57bbe81788b6b43114d8f8ee4e80afc991e14760/pyzmq-26.2.0-cp310-cp310-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:89289a5ee32ef6c439086184529ae060c741334b8970a6855ec0b6ad3ff28764", size = 673199 }, - { url = "https://files.pythonhosted.org/packages/c9/78/486f3e2e824f3a645238332bf5a4c4b4477c3063033a27c1e4052358dee2/pyzmq-26.2.0-cp310-cp310-manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:5506f06d7dc6ecf1efacb4a013b1f05071bb24b76350832c96449f4a2d95091c", size = 911762 }, - { url = "https://files.pythonhosted.org/packages/5e/3b/2eb1667c9b866f53e76ee8b0c301b0469745a23bd5a87b7ee3d5dd9eb6e5/pyzmq-26.2.0-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:8ea039387c10202ce304af74def5021e9adc6297067f3441d348d2b633e8166a", size = 868773 }, - { url = "https://files.pythonhosted.org/packages/16/29/ca99b4598a9dc7e468b5417eda91f372b595be1e3eec9b7cbe8e5d3584e8/pyzmq-26.2.0-cp310-cp310-manylinux_2_28_x86_64.whl", hash = "sha256:a2224fa4a4c2ee872886ed00a571f5e967c85e078e8e8c2530a2fb01b3309b88", size = 868834 }, - { url = "https://files.pythonhosted.org/packages/ad/e5/9efaeb1d2f4f8c50da04144f639b042bc52869d3a206d6bf672ab3522163/pyzmq-26.2.0-cp310-cp310-musllinux_1_1_aarch64.whl", hash = "sha256:28ad5233e9c3b52d76196c696e362508959741e1a005fb8fa03b51aea156088f", size = 1202861 }, - { url = "https://files.pythonhosted.org/packages/c3/62/c721b5608a8ac0a69bb83cbb7d07a56f3ff00b3991a138e44198a16f94c7/pyzmq-26.2.0-cp310-cp310-musllinux_1_1_i686.whl", hash = "sha256:1c17211bc037c7d88e85ed8b7d8f7e52db6dc8eca5590d162717c654550f7282", size = 1515304 }, - { url = "https://files.pythonhosted.org/packages/87/84/e8bd321aa99b72f48d4606fc5a0a920154125bd0a4608c67eab742dab087/pyzmq-26.2.0-cp310-cp310-musllinux_1_1_x86_64.whl", hash = "sha256:b8f86dd868d41bea9a5f873ee13bf5551c94cf6bc51baebc6f85075971fe6eea", size = 1414712 }, - { url = "https://files.pythonhosted.org/packages/cd/cd/420e3fd1ac6977b008b72e7ad2dae6350cc84d4c5027fc390b024e61738f/pyzmq-26.2.0-cp310-cp310-win32.whl", hash = "sha256:46a446c212e58456b23af260f3d9fb785054f3e3653dbf7279d8f2b5546b21c2", size = 578113 }, - { url = "https://files.pythonhosted.org/packages/5c/57/73930d56ed45ae0cb4946f383f985c855c9b3d4063f26416998f07523c0e/pyzmq-26.2.0-cp310-cp310-win_amd64.whl", hash = "sha256:49d34ab71db5a9c292a7644ce74190b1dd5a3475612eefb1f8be1d6961441971", size = 641631 }, - { url = "https://files.pythonhosted.org/packages/61/d2/ae6ac5c397f1ccad59031c64beaafce7a0d6182e0452cc48f1c9c87d2dd0/pyzmq-26.2.0-cp310-cp310-win_arm64.whl", hash = "sha256:bfa832bfa540e5b5c27dcf5de5d82ebc431b82c453a43d141afb1e5d2de025fa", size = 543528 }, - { url = "https://files.pythonhosted.org/packages/12/20/de7442172f77f7c96299a0ac70e7d4fb78cd51eca67aa2cf552b66c14196/pyzmq-26.2.0-cp311-cp311-macosx_10_15_universal2.whl", hash = "sha256:8f7e66c7113c684c2b3f1c83cdd3376103ee0ce4c49ff80a648643e57fb22218", size = 1340639 }, - { url = "https://files.pythonhosted.org/packages/98/4d/5000468bd64c7910190ed0a6c76a1ca59a68189ec1f007c451dc181a22f4/pyzmq-26.2.0-cp311-cp311-macosx_10_9_x86_64.whl", hash = "sha256:3a495b30fc91db2db25120df5847d9833af237546fd59170701acd816ccc01c4", size = 1008710 }, - { url = "https://files.pythonhosted.org/packages/e1/bf/c67fd638c2f9fbbab8090a3ee779370b97c82b84cc12d0c498b285d7b2c0/pyzmq-26.2.0-cp311-cp311-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:77eb0968da535cba0470a5165468b2cac7772cfb569977cff92e240f57e31bef", size = 673129 }, - { url = "https://files.pythonhosted.org/packages/86/94/99085a3f492aa538161cbf27246e8886ff850e113e0c294a5b8245f13b52/pyzmq-26.2.0-cp311-cp311-manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:6ace4f71f1900a548f48407fc9be59c6ba9d9aaf658c2eea6cf2779e72f9f317", size = 910107 }, - { url = "https://files.pythonhosted.org/packages/31/1d/346809e8a9b999646d03f21096428453465b1bca5cd5c64ecd048d9ecb01/pyzmq-26.2.0-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:92a78853d7280bffb93df0a4a6a2498cba10ee793cc8076ef797ef2f74d107cf", size = 867960 }, - { url = "https://files.pythonhosted.org/packages/ab/68/6fb6ae5551846ad5beca295b7bca32bf0a7ce19f135cb30e55fa2314e6b6/pyzmq-26.2.0-cp311-cp311-manylinux_2_28_x86_64.whl", hash = "sha256:689c5d781014956a4a6de61d74ba97b23547e431e9e7d64f27d4922ba96e9d6e", size = 869204 }, - { url = "https://files.pythonhosted.org/packages/0f/f9/18417771dee223ccf0f48e29adf8b4e25ba6d0e8285e33bcbce078070bc3/pyzmq-26.2.0-cp311-cp311-musllinux_1_1_aarch64.whl", hash = "sha256:0aca98bc423eb7d153214b2df397c6421ba6373d3397b26c057af3c904452e37", size = 1203351 }, - { url = "https://files.pythonhosted.org/packages/e0/46/f13e67fe0d4f8a2315782cbad50493de6203ea0d744610faf4d5f5b16e90/pyzmq-26.2.0-cp311-cp311-musllinux_1_1_i686.whl", hash = "sha256:1f3496d76b89d9429a656293744ceca4d2ac2a10ae59b84c1da9b5165f429ad3", size = 1514204 }, - { url = "https://files.pythonhosted.org/packages/50/11/ddcf7343b7b7a226e0fc7b68cbf5a5bb56291fac07f5c3023bb4c319ebb4/pyzmq-26.2.0-cp311-cp311-musllinux_1_1_x86_64.whl", hash = "sha256:5c2b3bfd4b9689919db068ac6c9911f3fcb231c39f7dd30e3138be94896d18e6", size = 1414339 }, - { url = "https://files.pythonhosted.org/packages/01/14/1c18d7d5b7be2708f513f37c61bfadfa62161c10624f8733f1c8451b3509/pyzmq-26.2.0-cp311-cp311-win32.whl", hash = "sha256:eac5174677da084abf378739dbf4ad245661635f1600edd1221f150b165343f4", size = 576928 }, - { url = "https://files.pythonhosted.org/packages/3b/1b/0a540edd75a41df14ec416a9a500b9fec66e554aac920d4c58fbd5756776/pyzmq-26.2.0-cp311-cp311-win_amd64.whl", hash = "sha256:5a509df7d0a83a4b178d0f937ef14286659225ef4e8812e05580776c70e155d5", size = 642317 }, - { url = "https://files.pythonhosted.org/packages/98/77/1cbfec0358078a4c5add529d8a70892db1be900980cdb5dd0898b3d6ab9d/pyzmq-26.2.0-cp311-cp311-win_arm64.whl", hash = "sha256:c0e6091b157d48cbe37bd67233318dbb53e1e6327d6fc3bb284afd585d141003", size = 543834 }, - { url = "https://files.pythonhosted.org/packages/28/2f/78a766c8913ad62b28581777ac4ede50c6d9f249d39c2963e279524a1bbe/pyzmq-26.2.0-cp312-cp312-macosx_10_15_universal2.whl", hash = "sha256:ded0fc7d90fe93ae0b18059930086c51e640cdd3baebdc783a695c77f123dcd9", size = 1343105 }, - { url = "https://files.pythonhosted.org/packages/b7/9c/4b1e2d3d4065be715e007fe063ec7885978fad285f87eae1436e6c3201f4/pyzmq-26.2.0-cp312-cp312-macosx_10_9_x86_64.whl", hash = "sha256:17bf5a931c7f6618023cdacc7081f3f266aecb68ca692adac015c383a134ca52", size = 1008365 }, - { url = "https://files.pythonhosted.org/packages/4f/ef/5a23ec689ff36d7625b38d121ef15abfc3631a9aecb417baf7a4245e4124/pyzmq-26.2.0-cp312-cp312-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:55cf66647e49d4621a7e20c8d13511ef1fe1efbbccf670811864452487007e08", size = 665923 }, - { url = "https://files.pythonhosted.org/packages/ae/61/d436461a47437d63c6302c90724cf0981883ec57ceb6073873f32172d676/pyzmq-26.2.0-cp312-cp312-manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:4661c88db4a9e0f958c8abc2b97472e23061f0bc737f6f6179d7a27024e1faa5", size = 903400 }, - { url = "https://files.pythonhosted.org/packages/47/42/fc6d35ecefe1739a819afaf6f8e686f7f02a4dd241c78972d316f403474c/pyzmq-26.2.0-cp312-cp312-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:ea7f69de383cb47522c9c208aec6dd17697db7875a4674c4af3f8cfdac0bdeae", size = 860034 }, - { url = "https://files.pythonhosted.org/packages/07/3b/44ea6266a6761e9eefaa37d98fabefa112328808ac41aa87b4bbb668af30/pyzmq-26.2.0-cp312-cp312-manylinux_2_28_x86_64.whl", hash = "sha256:7f98f6dfa8b8ccaf39163ce872bddacca38f6a67289116c8937a02e30bbe9711", size = 860579 }, - { url = "https://files.pythonhosted.org/packages/38/6f/4df2014ab553a6052b0e551b37da55166991510f9e1002c89cab7ce3b3f2/pyzmq-26.2.0-cp312-cp312-musllinux_1_1_aarch64.whl", hash = "sha256:e3e0210287329272539eea617830a6a28161fbbd8a3271bf4150ae3e58c5d0e6", size = 1196246 }, - { url = "https://files.pythonhosted.org/packages/38/9d/ee240fc0c9fe9817f0c9127a43238a3e28048795483c403cc10720ddef22/pyzmq-26.2.0-cp312-cp312-musllinux_1_1_i686.whl", hash = "sha256:6b274e0762c33c7471f1a7471d1a2085b1a35eba5cdc48d2ae319f28b6fc4de3", size = 1507441 }, - { url = "https://files.pythonhosted.org/packages/85/4f/01711edaa58d535eac4a26c294c617c9a01f09857c0ce191fd574d06f359/pyzmq-26.2.0-cp312-cp312-musllinux_1_1_x86_64.whl", hash = "sha256:29c6a4635eef69d68a00321e12a7d2559fe2dfccfa8efae3ffb8e91cd0b36a8b", size = 1406498 }, - { url = "https://files.pythonhosted.org/packages/07/18/907134c85c7152f679ed744e73e645b365f3ad571f38bdb62e36f347699a/pyzmq-26.2.0-cp312-cp312-win32.whl", hash = "sha256:989d842dc06dc59feea09e58c74ca3e1678c812a4a8a2a419046d711031f69c7", size = 575533 }, - { url = "https://files.pythonhosted.org/packages/ce/2c/a6f4a20202a4d3c582ad93f95ee78d79bbdc26803495aec2912b17dbbb6c/pyzmq-26.2.0-cp312-cp312-win_amd64.whl", hash = "sha256:2a50625acdc7801bc6f74698c5c583a491c61d73c6b7ea4dee3901bb99adb27a", size = 637768 }, - { url = "https://files.pythonhosted.org/packages/5f/0e/eb16ff731632d30554bf5af4dbba3ffcd04518219d82028aea4ae1b02ca5/pyzmq-26.2.0-cp312-cp312-win_arm64.whl", hash = "sha256:4d29ab8592b6ad12ebbf92ac2ed2bedcfd1cec192d8e559e2e099f648570e19b", size = 540675 }, - { url = "https://files.pythonhosted.org/packages/04/a7/0f7e2f6c126fe6e62dbae0bc93b1bd3f1099cf7fea47a5468defebe3f39d/pyzmq-26.2.0-cp313-cp313-macosx_10_13_x86_64.whl", hash = "sha256:9dd8cd1aeb00775f527ec60022004d030ddc51d783d056e3e23e74e623e33726", size = 1006564 }, - { url = "https://files.pythonhosted.org/packages/31/b6/a187165c852c5d49f826a690857684333a6a4a065af0a6015572d2284f6a/pyzmq-26.2.0-cp313-cp313-macosx_10_15_universal2.whl", hash = "sha256:28c812d9757fe8acecc910c9ac9dafd2ce968c00f9e619db09e9f8f54c3a68a3", size = 1340447 }, - { url = "https://files.pythonhosted.org/packages/68/ba/f4280c58ff71f321602a6e24fd19879b7e79793fb8ab14027027c0fb58ef/pyzmq-26.2.0-cp313-cp313-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:4d80b1dd99c1942f74ed608ddb38b181b87476c6a966a88a950c7dee118fdf50", size = 665485 }, - { url = "https://files.pythonhosted.org/packages/77/b5/c987a5c53c7d8704216f29fc3d810b32f156bcea488a940e330e1bcbb88d/pyzmq-26.2.0-cp313-cp313-manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:8c997098cc65e3208eca09303630e84d42718620e83b733d0fd69543a9cab9cb", size = 903484 }, - { url = "https://files.pythonhosted.org/packages/29/c9/07da157d2db18c72a7eccef8e684cefc155b712a88e3d479d930aa9eceba/pyzmq-26.2.0-cp313-cp313-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:7ad1bc8d1b7a18497dda9600b12dc193c577beb391beae5cd2349184db40f187", size = 859981 }, - { url = "https://files.pythonhosted.org/packages/43/09/e12501bd0b8394b7d02c41efd35c537a1988da67fc9c745cae9c6c776d31/pyzmq-26.2.0-cp313-cp313-manylinux_2_28_x86_64.whl", hash = "sha256:bea2acdd8ea4275e1278350ced63da0b166421928276c7c8e3f9729d7402a57b", size = 860334 }, - { url = "https://files.pythonhosted.org/packages/eb/ff/f5ec1d455f8f7385cc0a8b2acd8c807d7fade875c14c44b85c1bddabae21/pyzmq-26.2.0-cp313-cp313-musllinux_1_1_aarch64.whl", hash = "sha256:23f4aad749d13698f3f7b64aad34f5fc02d6f20f05999eebc96b89b01262fb18", size = 1196179 }, - { url = "https://files.pythonhosted.org/packages/ec/8a/bb2ac43295b1950fe436a81fc5b298be0b96ac76fb029b514d3ed58f7b27/pyzmq-26.2.0-cp313-cp313-musllinux_1_1_i686.whl", hash = "sha256:a4f96f0d88accc3dbe4a9025f785ba830f968e21e3e2c6321ccdfc9aef755115", size = 1507668 }, - { url = "https://files.pythonhosted.org/packages/a9/49/dbc284ebcfd2dca23f6349227ff1616a7ee2c4a35fe0a5d6c3deff2b4fed/pyzmq-26.2.0-cp313-cp313-musllinux_1_1_x86_64.whl", hash = "sha256:ced65e5a985398827cc9276b93ef6dfabe0273c23de8c7931339d7e141c2818e", size = 1406539 }, - { url = "https://files.pythonhosted.org/packages/00/68/093cdce3fe31e30a341d8e52a1ad86392e13c57970d722c1f62a1d1a54b6/pyzmq-26.2.0-cp313-cp313-win32.whl", hash = "sha256:31507f7b47cc1ead1f6e86927f8ebb196a0bab043f6345ce070f412a59bf87b5", size = 575567 }, - { url = "https://files.pythonhosted.org/packages/92/ae/6cc4657148143412b5819b05e362ae7dd09fb9fe76e2a539dcff3d0386bc/pyzmq-26.2.0-cp313-cp313-win_amd64.whl", hash = "sha256:70fc7fcf0410d16ebdda9b26cbd8bf8d803d220a7f3522e060a69a9c87bf7bad", size = 637551 }, - { url = "https://files.pythonhosted.org/packages/6c/67/fbff102e201688f97c8092e4c3445d1c1068c2f27bbd45a578df97ed5f94/pyzmq-26.2.0-cp313-cp313-win_arm64.whl", hash = "sha256:c3789bd5768ab5618ebf09cef6ec2b35fed88709b104351748a63045f0ff9797", size = 540378 }, - { url = "https://files.pythonhosted.org/packages/3f/fe/2d998380b6e0122c6c4bdf9b6caf490831e5f5e2d08a203b5adff060c226/pyzmq-26.2.0-cp313-cp313t-macosx_10_13_x86_64.whl", hash = "sha256:034da5fc55d9f8da09015d368f519478a52675e558c989bfcb5cf6d4e16a7d2a", size = 1007378 }, - { url = "https://files.pythonhosted.org/packages/4a/f4/30d6e7157f12b3a0390bde94d6a8567cdb88846ed068a6e17238a4ccf600/pyzmq-26.2.0-cp313-cp313t-macosx_10_15_universal2.whl", hash = "sha256:c92d73464b886931308ccc45b2744e5968cbaade0b1d6aeb40d8ab537765f5bc", size = 1329532 }, - { url = "https://files.pythonhosted.org/packages/82/86/3fe917870e15ee1c3ad48229a2a64458e36036e64b4afa9659045d82bfa8/pyzmq-26.2.0-cp313-cp313t-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:794a4562dcb374f7dbbfb3f51d28fb40123b5a2abadee7b4091f93054909add5", size = 653242 }, - { url = "https://files.pythonhosted.org/packages/50/2d/242e7e6ef6c8c19e6cb52d095834508cd581ffb925699fd3c640cdc758f1/pyzmq-26.2.0-cp313-cp313t-manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:aee22939bb6075e7afededabad1a56a905da0b3c4e3e0c45e75810ebe3a52672", size = 888404 }, - { url = "https://files.pythonhosted.org/packages/ac/11/7270566e1f31e4ea73c81ec821a4b1688fd551009a3d2bab11ec66cb1e8f/pyzmq-26.2.0-cp313-cp313t-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:2ae90ff9dad33a1cfe947d2c40cb9cb5e600d759ac4f0fd22616ce6540f72797", size = 845858 }, - { url = "https://files.pythonhosted.org/packages/91/d5/72b38fbc69867795c8711bdd735312f9fef1e3d9204e2f63ab57085434b9/pyzmq-26.2.0-cp313-cp313t-manylinux_2_28_x86_64.whl", hash = "sha256:43a47408ac52647dfabbc66a25b05b6a61700b5165807e3fbd40063fcaf46386", size = 847375 }, - { url = "https://files.pythonhosted.org/packages/dd/9a/10ed3c7f72b4c24e719c59359fbadd1a27556a28b36cdf1cd9e4fb7845d5/pyzmq-26.2.0-cp313-cp313t-musllinux_1_1_aarch64.whl", hash = "sha256:25bf2374a2a8433633c65ccb9553350d5e17e60c8eb4de4d92cc6bd60f01d306", size = 1183489 }, - { url = "https://files.pythonhosted.org/packages/72/2d/8660892543fabf1fe41861efa222455811adac9f3c0818d6c3170a1153e3/pyzmq-26.2.0-cp313-cp313t-musllinux_1_1_i686.whl", hash = "sha256:007137c9ac9ad5ea21e6ad97d3489af654381324d5d3ba614c323f60dab8fae6", size = 1492932 }, - { url = "https://files.pythonhosted.org/packages/7b/d6/32fd69744afb53995619bc5effa2a405ae0d343cd3e747d0fbc43fe894ee/pyzmq-26.2.0-cp313-cp313t-musllinux_1_1_x86_64.whl", hash = "sha256:470d4a4f6d48fb34e92d768b4e8a5cc3780db0d69107abf1cd7ff734b9766eb0", size = 1392485 }, - { url = "https://files.pythonhosted.org/packages/53/fb/36b2b2548286e9444e52fcd198760af99fd89102b5be50f0660fcfe902df/pyzmq-26.2.0-pp310-pypy310_pp73-macosx_10_15_x86_64.whl", hash = "sha256:706e794564bec25819d21a41c31d4df2d48e1cc4b061e8d345d7fb4dd3e94072", size = 906955 }, - { url = "https://files.pythonhosted.org/packages/77/8f/6ce54f8979a01656e894946db6299e2273fcee21c8e5fa57c6295ef11f57/pyzmq-26.2.0-pp310-pypy310_pp73-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:8b435f2753621cd36e7c1762156815e21c985c72b19135dac43a7f4f31d28dd1", size = 565701 }, - { url = "https://files.pythonhosted.org/packages/ee/1c/bf8cd66730a866b16db8483286078892b7f6536f8c389fb46e4beba0a970/pyzmq-26.2.0-pp310-pypy310_pp73-manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:160c7e0a5eb178011e72892f99f918c04a131f36056d10d9c1afb223fc952c2d", size = 794312 }, - { url = "https://files.pythonhosted.org/packages/71/43/91fa4ff25bbfdc914ab6bafa0f03241d69370ef31a761d16bb859f346582/pyzmq-26.2.0-pp310-pypy310_pp73-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:2c4a71d5d6e7b28a47a394c0471b7e77a0661e2d651e7ae91e0cab0a587859ca", size = 752775 }, - { url = "https://files.pythonhosted.org/packages/ec/d2/3b2ab40f455a256cb6672186bea95cd97b459ce4594050132d71e76f0d6f/pyzmq-26.2.0-pp310-pypy310_pp73-win_amd64.whl", hash = "sha256:90412f2db8c02a3864cbfc67db0e3dcdbda336acf1c469526d3e869394fe001c", size = 550762 }, -] - [[package]] name = "redis" version = "5.2.0" @@ -1297,20 +998,6 @@ wheels = [ { url = "https://files.pythonhosted.org/packages/d9/5a/e7c31adbe875f2abbb91bd84cf2dc52d792b5a01506781dbcf25c91daf11/six-1.16.0-py2.py3-none-any.whl", hash = "sha256:8abb2f1d86890a2dfb989f9a77cfcfd3e47c2a354b01111771326f8aa26e0254", size = 11053 }, ] -[[package]] -name = "stack-data" -version = "0.6.3" -source = { registry = "https://pypi.org/simple" } -dependencies = [ - { name = "asttokens" }, - { name = "executing" }, - { name = "pure-eval" }, -] -sdist = { url = "https://files.pythonhosted.org/packages/28/e3/55dcc2cfbc3ca9c29519eb6884dd1415ecb53b0e934862d3559ddcb7e20b/stack_data-0.6.3.tar.gz", hash = "sha256:836a778de4fec4dcd1dcd89ed8abff8a221f58308462e1c4aa2a3cf30148f0b9", size = 44707 } -wheels = [ - { url = "https://files.pythonhosted.org/packages/f1/7b/ce1eafaf1a76852e2ec9b22edecf1daa58175c090266e9f6c64afcd81d91/stack_data-0.6.3-py3-none-any.whl", hash = "sha256:d5558e0c25a4cb0853cddad3d77da9891a08cb85dd9f9f91b9f8cd66e511e695", size = 24521 }, -] - [[package]] name = "toml" version = "0.10.2" @@ -1329,24 +1016,6 @@ wheels = [ { url = "https://files.pythonhosted.org/packages/cf/db/ce8eda256fa131af12e0a76d481711abe4681b6923c27efb9a255c9e4594/tomli-2.0.2-py3-none-any.whl", hash = "sha256:2ebe24485c53d303f690b0ec092806a085f07af5a5aa1464f3931eec36caaa38", size = 13237 }, ] -[[package]] -name = "tornado" -version = "6.4.1" -source = { registry = "https://pypi.org/simple" } -sdist = { url = "https://files.pythonhosted.org/packages/ee/66/398ac7167f1c7835406888a386f6d0d26ee5dbf197d8a571300be57662d3/tornado-6.4.1.tar.gz", hash = "sha256:92d3ab53183d8c50f8204a51e6f91d18a15d5ef261e84d452800d4ff6fc504e9", size = 500623 } -wheels = [ - { url = "https://files.pythonhosted.org/packages/00/d9/c33be3c1a7564f7d42d87a8d186371a75fd142097076767a5c27da941fef/tornado-6.4.1-cp38-abi3-macosx_10_9_universal2.whl", hash = "sha256:163b0aafc8e23d8cdc3c9dfb24c5368af84a81e3364745ccb4427669bf84aec8", size = 435924 }, - { url = "https://files.pythonhosted.org/packages/2e/0f/721e113a2fac2f1d7d124b3279a1da4c77622e104084f56119875019ffab/tornado-6.4.1-cp38-abi3-macosx_10_9_x86_64.whl", hash = "sha256:6d5ce3437e18a2b66fbadb183c1d3364fb03f2be71299e7d10dbeeb69f4b2a14", size = 433883 }, - { url = "https://files.pythonhosted.org/packages/13/cf/786b8f1e6fe1c7c675e79657448178ad65e41c1c9765ef82e7f6f765c4c5/tornado-6.4.1-cp38-abi3-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:e2e20b9113cd7293f164dc46fffb13535266e713cdb87bd2d15ddb336e96cfc4", size = 437224 }, - { url = "https://files.pythonhosted.org/packages/e4/8e/a6ce4b8d5935558828b0f30f3afcb2d980566718837b3365d98e34f6067e/tornado-6.4.1-cp38-abi3-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:8ae50a504a740365267b2a8d1a90c9fbc86b780a39170feca9bcc1787ff80842", size = 436597 }, - { url = "https://files.pythonhosted.org/packages/22/d4/54f9d12668b58336bd30defe0307e6c61589a3e687b05c366f804b7faaf0/tornado-6.4.1-cp38-abi3-manylinux_2_5_x86_64.manylinux1_x86_64.manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:613bf4ddf5c7a95509218b149b555621497a6cc0d46ac341b30bd9ec19eac7f3", size = 436797 }, - { url = "https://files.pythonhosted.org/packages/cf/3f/2c792e7afa7dd8b24fad7a2ed3c2f24a5ec5110c7b43a64cb6095cc106b8/tornado-6.4.1-cp38-abi3-musllinux_1_2_aarch64.whl", hash = "sha256:25486eb223babe3eed4b8aecbac33b37e3dd6d776bc730ca14e1bf93888b979f", size = 437516 }, - { url = "https://files.pythonhosted.org/packages/71/63/c8fc62745e669ac9009044b889fc531b6f88ac0f5f183cac79eaa950bb23/tornado-6.4.1-cp38-abi3-musllinux_1_2_i686.whl", hash = "sha256:454db8a7ecfcf2ff6042dde58404164d969b6f5d58b926da15e6b23817950fc4", size = 436958 }, - { url = "https://files.pythonhosted.org/packages/94/d4/f8ac1f5bd22c15fad3b527e025ce219bd526acdbd903f52053df2baecc8b/tornado-6.4.1-cp38-abi3-musllinux_1_2_x86_64.whl", hash = "sha256:a02a08cc7a9314b006f653ce40483b9b3c12cda222d6a46d4ac63bb6c9057698", size = 436882 }, - { url = "https://files.pythonhosted.org/packages/4b/3e/a8124c21cc0bbf144d7903d2a0cadab15cadaf683fa39a0f92bc567f0d4d/tornado-6.4.1-cp38-abi3-win32.whl", hash = "sha256:d9a566c40b89757c9aa8e6f032bcdb8ca8795d7c1a9762910c722b1635c9de4d", size = 438092 }, - { url = "https://files.pythonhosted.org/packages/d9/2f/3f2f05e84a7aff787a96d5fb06821323feb370fe0baed4db6ea7b1088f32/tornado-6.4.1-cp38-abi3-win_amd64.whl", hash = "sha256:b24b8982ed444378d7f21d563f4180a2de31ced9d8d84443907a0a64da2072e7", size = 438532 }, -] - [[package]] name = "tqdm" version = "4.66.6" @@ -1359,15 +1028,6 @@ wheels = [ { url = "https://files.pythonhosted.org/packages/41/73/02342de9c2d20922115f787e101527b831c0cffd2105c946c4a4826bcfd4/tqdm-4.66.6-py3-none-any.whl", hash = "sha256:223e8b5359c2efc4b30555531f09e9f2f3589bcd7fdd389271191031b49b7a63", size = 78326 }, ] -[[package]] -name = "traitlets" -version = "5.14.3" -source = { registry = "https://pypi.org/simple" } -sdist = { url = "https://files.pythonhosted.org/packages/eb/79/72064e6a701c2183016abbbfedaba506d81e30e232a68c9f0d6f6fcd1574/traitlets-5.14.3.tar.gz", hash = "sha256:9ed0579d3502c94b4b3732ac120375cda96f923114522847de4b3bb98b96b6b7", size = 161621 } -wheels = [ - { url = "https://files.pythonhosted.org/packages/00/c0/8f5d070730d7836adc9c9b6408dec68c6ced86b304a9b26a14df072a6e8c/traitlets-5.14.3-py3-none-any.whl", hash = "sha256:b74e89e397b1ed28cc831db7aea759ba6640cb3de13090ca145426688ff1ac4f", size = 85359 }, -] - [[package]] name = "typer" version = "0.12.5" @@ -1453,12 +1113,3 @@ sdist = { url = "https://files.pythonhosted.org/packages/8c/b3/7b6a79c5c8cf6d90e wheels = [ { url = "https://files.pythonhosted.org/packages/ae/92/78324ff89391e00c8f4cf6b8526c41c6ef36b4ea2d2c132250b1a6fc2b8d/virtualenv-20.27.1-py3-none-any.whl", hash = "sha256:f11f1b8a29525562925f745563bfd48b189450f61fb34c4f9cc79dd5aa32a1f4", size = 3117838 }, ] - -[[package]] -name = "wcwidth" -version = "0.2.13" -source = { registry = "https://pypi.org/simple" } -sdist = { url = "https://files.pythonhosted.org/packages/6c/63/53559446a878410fc5a5974feb13d31d78d752eb18aeba59c7fef1af7598/wcwidth-0.2.13.tar.gz", hash = "sha256:72ea0c06399eb286d978fdedb6923a9eb47e1c486ce63e9b4e64fc18303972b5", size = 101301 } -wheels = [ - { url = "https://files.pythonhosted.org/packages/fd/84/fd2ba7aafacbad3c4201d395674fc6348826569da3c0937e75505ead3528/wcwidth-0.2.13-py2.py3-none-any.whl", hash = "sha256:3da69048e4540d84af32131829ff948f1e022c1c6bdb8d6102117aac784f6859", size = 34166 }, -]