From 064fa06253b5357883c1ef0fd0aef0428cacc784 Mon Sep 17 00:00:00 2001
From: zilto <zilto@github.com>
Date: Fri, 10 Jan 2025 13:37:08 -0500
Subject: [PATCH 1/4] added projection kwarg

---
 sources/mongodb/__init__.py          |  11 ++-
 sources/mongodb/helpers.py           | 104 +++++++++++++++++++++++----
 tests/mongodb/test_mongodb_source.py | 100 ++++++++++++++++++++++++++
 3 files changed, 200 insertions(+), 15 deletions(-)

diff --git a/sources/mongodb/__init__.py b/sources/mongodb/__init__.py
index db6b9d054..351b850e7 100644
--- a/sources/mongodb/__init__.py
+++ b/sources/mongodb/__init__.py
@@ -1,6 +1,6 @@
 """Source that loads collections form any a mongo database, supports incremental loads."""
 
-from typing import Any, Dict, Iterable, List, Optional
+from typing import Any, Dict, Iterable, List, Optional, Union, Mapping
 
 import dlt
 from dlt.common.data_writers import TDataItemFormat
@@ -73,6 +73,7 @@ def mongodb(
             parallel=parallel,
             limit=limit,
             filter_=filter_ or {},
+            projection=None,
         )
 
 
@@ -90,6 +91,7 @@ def mongodb_collection(
     chunk_size: Optional[int] = 10000,
     data_item_format: Optional[TDataItemFormat] = "object",
     filter_: Optional[Dict[str, Any]] = None,
+    projection: Optional[Union[Mapping[str, Any], Iterable[str]]] = None,
 ) -> Any:
     """
     A DLT source which loads a collection from a mongo database using PyMongo.
@@ -109,6 +111,12 @@ def mongodb_collection(
                 object - Python objects (dicts, lists).
                 arrow - Apache Arrow tables.
         filter_ (Optional[Dict[str, Any]]): The filter to apply to the collection.
+        projection: (Optional[Union[Mapping[str, Any], Iterable[str]]]): The projection to select columns
+            when loading the collection. Supported inputs:
+                include (list) - ["year", "title"]
+                include (dict) - {"year": 1, "title": 1}
+                exclude (dict) - {"released": 0, "runtime": 0}
+            Note: Can't mix include and exclude statements '{"title": 1, "released": 0}`
 
     Returns:
         Iterable[DltResource]: A list of DLT resources for each collection to be loaded.
@@ -136,4 +144,5 @@ def mongodb_collection(
         chunk_size=chunk_size,
         data_item_format=data_item_format,
         filter_=filter_ or {},
+        projection=projection,
     )
diff --git a/sources/mongodb/helpers.py b/sources/mongodb/helpers.py
index fe5dcc69c..0c0182ed1 100644
--- a/sources/mongodb/helpers.py
+++ b/sources/mongodb/helpers.py
@@ -1,7 +1,7 @@
 """Mongo database source helpers"""
 
 from itertools import islice
-from typing import TYPE_CHECKING, Any, Dict, Iterator, List, Optional, Tuple
+from typing import TYPE_CHECKING, Any, Dict, Iterator, List, Optional, Tuple, Union, Iterable, Mapping
 
 import dlt
 from bson.decimal128 import Decimal128
@@ -18,6 +18,7 @@
 from pymongo import ASCENDING, DESCENDING, MongoClient
 from pymongo.collection import Collection
 from pymongo.cursor import Cursor
+from pymongo.helpers import _fields_list_to_dict
 
 
 if TYPE_CHECKING:
@@ -106,6 +107,41 @@ def _filter_op(self) -> Dict[str, Any]:
                 filt[self.cursor_field]["$gt"] = self.incremental.end_value
 
         return filt
+    
+    def _projection_op(self, projection) -> Optional[Dict[str, Any]]:
+        """Build a projection operator.
+        
+        A tuple of fields to include or a dict specifying fields to include or exclude.
+        The incremental `primary_key` needs to be handle differently for inclusion
+        and exclusion projections.
+
+        Returns:
+            Tuple[str, ...] | Dict[str, Any]: A tuple or dictionary with the projection operator.
+        """
+        if projection is None:
+            return None
+
+        projection_dict = dict(_fields_list_to_dict(projection, "projection"))
+
+        # NOTE we can still filter on primary_key if it's excluded from projection
+        if self.incremental:
+            # this is an inclusion projection
+            if any(v == 1 for v in projection.values()):
+                # ensure primary_key is included
+                projection_dict.update({self.incremental.primary_key: 1})
+            # this is an exclusion projection
+            else:
+                try:
+                    # ensure primary_key isn't excluded
+                    projection_dict.pop(self.incremental.primary_key)
+                except KeyError:
+                    pass  # primary_key was properly not included in exclusion projection
+                else:
+                    dlt.common.logger.warn(
+                        f"Primary key `{self.incremental.primary_key} was removed from exclusion projection"
+                    )
+
+        return projection_dict
 
     def _limit(self, cursor: Cursor, limit: Optional[int] = None) -> TCursor:  # type: ignore
         """Apply a limit to the cursor, if needed.
@@ -128,7 +164,10 @@ def _limit(self, cursor: Cursor, limit: Optional[int] = None) -> TCursor:  # typ
         return cursor
 
     def load_documents(
-        self, filter_: Dict[str, Any], limit: Optional[int] = None
+        self,
+        filter_: Dict[str, Any],
+        limit: Optional[int] = None,
+        projection: Optional[Union[Mapping[str, Any], Iterable[str]]] = None,
     ) -> Iterator[TDataItem]:
         """Construct the query and load the documents from the collection.
 
@@ -143,7 +182,9 @@ def load_documents(
         _raise_if_intersection(filter_op, filter_)
         filter_op.update(filter_)
 
-        cursor = self.collection.find(filter=filter_op)
+        projection_op = self._projection_op(projection)
+
+        cursor = self.collection.find(filter=filter_op, projection=projection_op)
         if self._sort_op:
             cursor = cursor.sort(self._sort_op)
 
@@ -171,7 +212,11 @@ def _create_batches(self, limit: Optional[int] = None) -> List[Dict[str, int]]:
 
         return batches
 
-    def _get_cursor(self, filter_: Dict[str, Any]) -> TCursor:
+    def _get_cursor(
+        self,
+        filter_: Dict[str, Any],
+        projection: Optional[Union[Mapping[str, Any], Iterable[str]]] = None,
+    ) -> TCursor:
         """Get a reading cursor for the collection.
 
         Args:
@@ -184,7 +229,9 @@ def _get_cursor(self, filter_: Dict[str, Any]) -> TCursor:
         _raise_if_intersection(filter_op, filter_)
         filter_op.update(filter_)
 
-        cursor = self.collection.find(filter=filter_op)
+        projection_op = self._projection_op(projection)
+
+        cursor = self.collection.find(filter=filter_op, projection=projection_op)
         if self._sort_op:
             cursor = cursor.sort(self._sort_op)
 
@@ -201,7 +248,10 @@ def _run_batch(self, cursor: TCursor, batch: Dict[str, int]) -> TDataItem:
         return data
 
     def _get_all_batches(
-        self, filter_: Dict[str, Any], limit: Optional[int] = None
+        self,
+        filter_: Dict[str, Any],
+        limit: Optional[int] = None,
+        projection: Optional[Union[Mapping[str, Any], Iterable[str]]] = None,
     ) -> Iterator[TDataItem]:
         """Load all documents from the collection in parallel batches.
 
@@ -213,13 +263,16 @@ def _get_all_batches(
             Iterator[TDataItem]: An iterator of the loaded documents.
         """
         batches = self._create_batches(limit=limit)
-        cursor = self._get_cursor(filter_=filter_)
+        cursor = self._get_cursor(filter_=filter_, projection=projection)
 
         for batch in batches:
             yield self._run_batch(cursor=cursor, batch=batch)
 
     def load_documents(
-        self, filter_: Dict[str, Any], limit: Optional[int] = None
+        self,
+        filter_: Dict[str, Any],
+        limit: Optional[int] = None,
+        projection: Optional[Union[Mapping[str, Any], Iterable[str]]] = None,
     ) -> Iterator[TDataItem]:
         """Load documents from the collection in parallel.
 
@@ -230,7 +283,9 @@ def load_documents(
         Yields:
             Iterator[TDataItem]: An iterator of the loaded documents.
         """
-        for document in self._get_all_batches(limit=limit, filter_=filter_):
+        for document in self._get_all_batches(
+            limit=limit, filter_=filter_, projection=projection
+        ):
             yield document
 
 
@@ -241,7 +296,10 @@ class CollectionArrowLoader(CollectionLoader):
     """
 
     def load_documents(
-        self, filter_: Dict[str, Any], limit: Optional[int] = None
+        self,
+        filter_: Dict[str, Any],
+        limit: Optional[int] = None,
+        projection: Optional[Union[Mapping[str, Any], Iterable[str]]] = None,
     ) -> Iterator[Any]:
         """
         Load documents from the collection in Apache Arrow format.
@@ -264,7 +322,12 @@ def load_documents(
         _raise_if_intersection(filter_op, filter_)
         filter_op.update(filter_)
 
-        cursor = self.collection.find_raw_batches(filter_, batch_size=self.chunk_size)
+        projection_op = self._projection_op(projection)
+
+        # NOTE the `filter_op` isn't passed
+        cursor = self.collection.find_raw_batches(
+            filter_, batch_size=self.chunk_size, projection=projection_op
+        )
         if self._sort_op:
             cursor = cursor.sort(self._sort_op)  # type: ignore
 
@@ -283,7 +346,11 @@ class CollectionArrowLoaderParallel(CollectionLoaderParallel):
     Apache Arrow for data processing.
     """
 
-    def _get_cursor(self, filter_: Dict[str, Any]) -> TCursor:
+    def _get_cursor(
+        self,
+        filter_: Dict[str, Any],
+        projection: Optional[Union[Mapping[str, Any], Iterable[str]]] = None,
+    ) -> TCursor:
         """Get a reading cursor for the collection.
 
         Args:
@@ -296,8 +363,10 @@ def _get_cursor(self, filter_: Dict[str, Any]) -> TCursor:
         _raise_if_intersection(filter_op, filter_)
         filter_op.update(filter_)
 
+        projection_op = self._projection_op(projection)
+
         cursor = self.collection.find_raw_batches(
-            filter=filter_op, batch_size=self.chunk_size
+            filter=filter_op, batch_size=self.chunk_size, projection=projection_op
         )
         if self._sort_op:
             cursor = cursor.sort(self._sort_op)  # type: ignore
@@ -326,6 +395,7 @@ def collection_documents(
     client: TMongoClient,
     collection: TCollection,
     filter_: Dict[str, Any],
+    projection: Union[Dict[str, Any], List[str]],  # TODO kwargs reserved for dlt?
     incremental: Optional[dlt.sources.incremental[Any]] = None,
     parallel: bool = False,
     limit: Optional[int] = None,
@@ -348,6 +418,12 @@ def collection_documents(
             Supported formats:
                 object - Python objects (dicts, lists).
                 arrow - Apache Arrow tables.
+        projection: (Optional[Union[Mapping[str, Any], Iterable[str]]]): The projection to select columns
+            when loading the collection. Supported inputs:
+                include (list) - ["year", "title"]
+                include (dict) - {"year": 1, "title": 1}
+                exclude (dict) - {"released": 0, "runtime": 0}
+            Note: Can't mix include and exclude statements '{"title": 1, "released": 0}`
 
     Returns:
         Iterable[DltResource]: A list of DLT resources for each collection to be loaded.
@@ -372,7 +448,7 @@ def collection_documents(
     loader = LoaderClass(
         client, collection, incremental=incremental, chunk_size=chunk_size
     )
-    for data in loader.load_documents(limit=limit, filter_=filter_):
+    for data in loader.load_documents(limit=limit, filter_=filter_, projection=projection):
         yield data
 
 
diff --git a/tests/mongodb/test_mongodb_source.py b/tests/mongodb/test_mongodb_source.py
index b39ce6997..88f4ba1c5 100644
--- a/tests/mongodb/test_mongodb_source.py
+++ b/tests/mongodb/test_mongodb_source.py
@@ -409,6 +409,106 @@ def test_filter_intersect(destination_name):
         pipeline.run(movies)
 
 
+@pytest.mark.parametrize("destination_name", ALL_DESTINATIONS)
+def test_projection_list_inclusion(destination_name):
+    pipeline = dlt.pipeline(
+        pipeline_name="mongodb_test",
+        destination=destination_name,
+        dataset_name="mongodb_test_data",
+        full_refresh=True,
+    )
+    collection_name = "movies"
+    projection = ["title", "poster"]
+    expected_columns = projection + ["_id", "_dlt_id", "_dlt_load_id"]
+
+    movies = mongodb_collection(
+        collection=collection_name,
+        projection=projection,
+        limit=2
+    )
+    pipeline.run(movies)
+    loaded_columns = pipeline.default_schema.get_table_columns(collection_name).keys()
+
+    assert set(loaded_columns) == set(expected_columns)
+
+
+@pytest.mark.parametrize("destination_name", ALL_DESTINATIONS)
+def test_projection_dict_inclusion(destination_name):
+    pipeline = dlt.pipeline(
+        pipeline_name="mongodb_test",
+        destination=destination_name,
+        dataset_name="mongodb_test_data",
+        full_refresh=True,
+    )
+    collection_name = "movies"
+    projection = {"title": 1, "poster": 1}
+    expected_columns = list(projection.keys()) + ["_id", "_dlt_id", "_dlt_load_id"]
+
+    movies = mongodb_collection(
+        collection=collection_name,
+        projection=projection,
+        limit=2
+    )
+    pipeline.run(movies)
+    loaded_columns = pipeline.default_schema.get_table_columns(collection_name).keys()
+
+    assert set(loaded_columns) == set(expected_columns)
+
+
+@pytest.mark.parametrize("destination_name", ALL_DESTINATIONS)
+def test_projection_dict_exclusion(destination_name):
+    pipeline = dlt.pipeline(
+        pipeline_name="mongodb_test",
+        destination=destination_name,
+        dataset_name="mongodb_test_data",
+        full_refresh=True,
+    )
+    collection_name = "movies"
+    columns_to_exclude = [
+        "runtime", "released", "year", "plot", "fullplot", "lastupdated", "type",
+        "directors", "imdb", "cast", "countries", "genres", "tomatoes", "num_mflix_comments",
+        "rated", "awards"
+    ]
+    projection = {col: 0 for col in columns_to_exclude}
+    expected_columns = ["title", "poster", "_id", "_dlt_id", "_dlt_load_id"]
+
+    movies = mongodb_collection(
+        collection=collection_name,
+        projection=projection,
+        limit=2
+    )
+    pipeline.run(movies)
+    loaded_columns = pipeline.default_schema.get_table_columns(collection_name).keys()
+
+    assert set(loaded_columns) == set(expected_columns)
+
+
+@pytest.mark.parametrize("destination_name", ALL_DESTINATIONS)
+def test_projection_nested_field(destination_name):
+    pipeline = dlt.pipeline(
+        pipeline_name="mongodb_test",
+        destination=destination_name,
+        dataset_name="mongodb_test_data",
+        full_refresh=True,
+    )
+    collection_name = "movies"
+    projection = ["imdb.votes", "poster"]
+    expected_columns = ["imdb__votes", "poster", "_id", "_dlt_id", "_dlt_load_id"]
+    # other documents nested under `imdb` shouldn't be loaded
+    not_expected_columns = ["imdb__rating", "imdb__id"]
+
+    movies = mongodb_collection(
+        collection=collection_name,
+        projection=projection,
+        limit=2
+    )
+    pipeline.run(movies)
+    loaded_columns = pipeline.default_schema.get_table_columns(collection_name).keys()
+
+    assert set(loaded_columns) == set(expected_columns)
+    assert len(set(loaded_columns).intersection(not_expected_columns)) == 0
+
+
 @pytest.mark.parametrize("destination_name", ALL_DESTINATIONS)
 @pytest.mark.parametrize("data_item_format", ["object", "arrow"])
 def test_mongodb_without_pymongoarrow(

From 39a644810b236bc05143a71e712b7f9ccfef7527 Mon Sep 17 00:00:00 2001
From: zilto <zilto@github.com>
Date: Wed, 15 Jan 2025 20:50:32 -0500
Subject: [PATCH 2/4] upgrade pymongo and pymongoarrow

---
 poetry.lock                | 276 ++++++++++++++++++++++++++++++++++++-
 pyproject.toml             |   4 +-
 sources/mongodb/helpers.py |  15 +-
 3 files changed, 281 insertions(+), 14 deletions(-)

diff --git a/poetry.lock b/poetry.lock
index 6c1979521..b2b827e6d 100644
--- a/poetry.lock
+++ b/poetry.lock
@@ -1,4 +1,4 @@
-# This file is automatically @generated by Poetry 1.7.1 and should not be changed by hand.
+# This file is automatically @generated by Poetry 2.0.0 and should not be changed by hand.
 
 [[package]]
 name = "adlfs"
@@ -6,6 +6,7 @@ version = "2023.10.0"
 description = "Access Azure Datalake Gen1 with fsspec and dask"
 optional = false
 python-versions = ">=3.8"
+groups = ["filesystem"]
 files = [
     {file = "adlfs-2023.10.0-py3-none-any.whl", hash = "sha256:dfdc8cc782bd78262435fb1bc2a8cfdbdd80342bb1b1ae9dfff968de912b0b09"},
     {file = "adlfs-2023.10.0.tar.gz", hash = "sha256:f5cf06c5b0074d17d43838d4c434791a98420d9e768b36a1a02c7b3930686543"},
@@ -28,6 +29,7 @@ version = "2.5.4"
 description = "Async client for aws services using botocore and aiohttp"
 optional = false
 python-versions = ">=3.7"
+groups = ["filesystem"]
 files = [
     {file = "aiobotocore-2.5.4-py3-none-any.whl", hash = "sha256:4b32218728ca3d0be83835b604603a0cd6c329066e884bb78149334267f92440"},
     {file = "aiobotocore-2.5.4.tar.gz", hash = "sha256:60341f19eda77e41e1ab11eef171b5a98b5dbdb90804f5334b6f90e560e31fae"},
@@ -49,6 +51,7 @@ version = "3.8.6"
 description = "Async http client/server framework (asyncio)"
 optional = false
 python-versions = ">=3.6"
+groups = ["main", "facebook_ads", "filesystem", "unstructured_data", "unstructured_data_lint"]
 files = [
     {file = "aiohttp-3.8.6-cp310-cp310-macosx_10_9_universal2.whl", hash = "sha256:41d55fc043954cddbbd82503d9cc3f4814a40bcef30b3569bc7b5e34130718c1"},
     {file = "aiohttp-3.8.6-cp310-cp310-macosx_10_9_x86_64.whl", hash = "sha256:1d84166673694841d8953f0a8d0c90e1087739d24632fe86b1a08819168b4566"},
@@ -157,6 +160,7 @@ version = "0.11.0"
 description = "itertools and builtins for AsyncIO and mixed iterables"
 optional = false
 python-versions = ">=3.6"
+groups = ["filesystem"]
 files = [
     {file = "aioitertools-0.11.0-py3-none-any.whl", hash = "sha256:04b95e3dab25b449def24d7df809411c10e62aab0cbe31a50ca4e68748c43394"},
     {file = "aioitertools-0.11.0.tar.gz", hash = "sha256:42c68b8dd3a69c2bf7f2233bf7df4bb58b557bca5252ac02ed5187bbc67d6831"},
@@ -171,6 +175,7 @@ version = "1.3.1"
 description = "aiosignal: a list of registered asynchronous callbacks"
 optional = false
 python-versions = ">=3.7"
+groups = ["main", "facebook_ads", "filesystem", "unstructured_data", "unstructured_data_lint"]
 files = [
     {file = "aiosignal-1.3.1-py3-none-any.whl", hash = "sha256:f8376fb07dd1e86a584e4fcdec80b36b7f81aac666ebc724e2c090300dd83b17"},
     {file = "aiosignal-1.3.1.tar.gz", hash = "sha256:54cd96e15e1649b75d6c87526a6ff0b6c1b0dd3459f43d9ca11d48c339b68cfc"},
@@ -185,6 +190,7 @@ version = "4.0.0"
 description = "High level compatibility layer for multiple asynchronous event loop implementations"
 optional = false
 python-versions = ">=3.8"
+groups = ["unstructured_data"]
 files = [
     {file = "anyio-4.0.0-py3-none-any.whl", hash = "sha256:cfdb2b588b9fc25ede96d8db56ed50848b0b649dca3dd1df0b11f683bb9e0b5f"},
     {file = "anyio-4.0.0.tar.gz", hash = "sha256:f7ed51751b2c2add651e5747c891b47e26d2a21be5d32d9311dfe9692f3e5d7a"},
@@ -206,6 +212,7 @@ version = "0.0.1"
 description = ""
 optional = false
 python-versions = "*"
+groups = ["unstructured_data"]
 files = [
     {file = "argilla-0.0.1-py3-none-any.whl", hash = "sha256:8bdc3c505bcfb47ba4b91f5658034eae53bf7d4f9317980397605c0c55817396"},
     {file = "argilla-0.0.1.tar.gz", hash = "sha256:5017854754e89f573b31af25b25b803f51cea9ca1fa0bcf00505dee1f45cf7c9"},
@@ -217,6 +224,7 @@ version = "3.2.2"
 description = "Asana API client"
 optional = false
 python-versions = "*"
+groups = ["asana_dlt"]
 files = [
     {file = "asana-3.2.2-py2.py3-none-any.whl", hash = "sha256:e8426ae5f5cda2c27d29874145acb589b91e673a84e3fbd45404679499d9604a"},
     {file = "asana-3.2.2.tar.gz", hash = "sha256:3a0c64ad5baaa8c52465fe400cedbc873b2127a77df135af518fd8da1af8d6b9"},
@@ -232,6 +240,7 @@ version = "0.3.3"
 description = "Some handy helper functions for Python's AST module."
 optional = false
 python-versions = ">=3.6"
+groups = ["dev"]
 files = [
     {file = "astatine-0.3.3-py3-none-any.whl", hash = "sha256:6d8c914f01fbea252cb8f31563f2e766a9ab03c02b9bcc37d18f7d9138828401"},
     {file = "astatine-0.3.3.tar.gz", hash = "sha256:0c58a7844b5890ff16da07dbfeb187341d8324cb4378940f89d795cbebebce08"},
@@ -247,6 +256,7 @@ version = "2.4.0"
 description = "Annotate AST trees with source code positions"
 optional = false
 python-versions = "*"
+groups = ["dev"]
 files = [
     {file = "asttokens-2.4.0-py2.py3-none-any.whl", hash = "sha256:cf8fc9e61a86461aa9fb161a14a0841a03c405fa829ac6b202670b3495d2ce69"},
     {file = "asttokens-2.4.0.tar.gz", hash = "sha256:2e0171b991b2c959acc6c49318049236844a5da1d65ba2672c4880c1c894834e"},
@@ -264,6 +274,7 @@ version = "1.6.3"
 description = "An AST unparser for Python"
 optional = false
 python-versions = "*"
+groups = ["main", "dltpure"]
 files = [
     {file = "astunparse-1.6.3-py2.py3-none-any.whl", hash = "sha256:c2652417f2c8b5bb325c885ae329bdf3f86424075c4fd1a128674bc6fba4b8e8"},
     {file = "astunparse-1.6.3.tar.gz", hash = "sha256:5ad93a8456f0d084c3456d059fd9a92cce667963232cbf763eac3bc5b7940872"},
@@ -279,6 +290,7 @@ version = "4.0.3"
 description = "Timeout context manager for asyncio programs"
 optional = false
 python-versions = ">=3.7"
+groups = ["main", "facebook_ads", "filesystem", "unstructured_data", "unstructured_data_lint"]
 files = [
     {file = "async-timeout-4.0.3.tar.gz", hash = "sha256:4640d96be84d82d02ed59ea2b7105a0f7b33abe8703703cd0ab0bf87c427522f"},
     {file = "async_timeout-4.0.3-py3-none-any.whl", hash = "sha256:7405140ff1230c310e51dc27b3145b9092d659ce68ff733fb0cefe3ee42be028"},
@@ -290,6 +302,7 @@ version = "23.1.0"
 description = "Classes Without Boilerplate"
 optional = false
 python-versions = ">=3.7"
+groups = ["main", "dev", "facebook_ads", "filesystem", "salesforce", "scrapy", "unstructured_data", "unstructured_data_lint"]
 files = [
     {file = "attrs-23.1.0-py3-none-any.whl", hash = "sha256:1f28b4522cdc2fb4256ac1a020c78acf9cba2c6b461ccd2c126f3aa8e8335d04"},
     {file = "attrs-23.1.0.tar.gz", hash = "sha256:6279836d581513a26f1bf235f9acd333bc9115683f14f7e8fae46c98fc50e015"},
@@ -308,6 +321,7 @@ version = "22.10.0"
 description = "Self-service finite-state machines for the programmer on the go."
 optional = false
 python-versions = "*"
+groups = ["dev", "scrapy"]
 files = [
     {file = "Automat-22.10.0-py2.py3-none-any.whl", hash = "sha256:c3164f8742b9dc440f3682482d32aaff7bb53f71740dd018533f9de286b64180"},
     {file = "Automat-22.10.0.tar.gz", hash = "sha256:e56beb84edad19dcc11d30e8d9b895f75deeb5ef5e96b84a467066b3b84bb04e"},
@@ -326,6 +340,7 @@ version = "1.29.4"
 description = "Microsoft Azure Core Library for Python"
 optional = false
 python-versions = ">=3.7"
+groups = ["filesystem"]
 files = [
     {file = "azure-core-1.29.4.tar.gz", hash = "sha256:500b3aa9bf2e90c5ccc88bb105d056114ca0ce7d0ce73afb8bc4d714b2fc7568"},
     {file = "azure_core-1.29.4-py3-none-any.whl", hash = "sha256:b03261bcba22c0b9290faf9999cedd23e849ed2577feee90515694cea6bc74bf"},
@@ -345,6 +360,7 @@ version = "0.0.53"
 description = "Azure Data Lake Store Filesystem Client Library for Python"
 optional = false
 python-versions = "*"
+groups = ["filesystem"]
 files = [
     {file = "azure-datalake-store-0.0.53.tar.gz", hash = "sha256:05b6de62ee3f2a0a6e6941e6933b792b800c3e7f6ffce2fc324bc19875757393"},
     {file = "azure_datalake_store-0.0.53-py2.py3-none-any.whl", hash = "sha256:a30c902a6e360aa47d7f69f086b426729784e71c536f330b691647a51dc42b2b"},
@@ -361,6 +377,7 @@ version = "1.14.1"
 description = "Microsoft Azure Identity Library for Python"
 optional = false
 python-versions = ">=3.7"
+groups = ["filesystem"]
 files = [
     {file = "azure-identity-1.14.1.zip", hash = "sha256:48e2a9dbdc59b4f095f841d867d9a8cbe4c1cdbbad8251e055561afd47b4a9b8"},
     {file = "azure_identity-1.14.1-py3-none-any.whl", hash = "sha256:3a5bef8e9c3281e864e869739be8d67424bff616cddae96b546ca2a5168d863d"},
@@ -378,6 +395,7 @@ version = "12.18.3"
 description = "Microsoft Azure Blob Storage Client Library for Python"
 optional = false
 python-versions = ">=3.7"
+groups = ["filesystem"]
 files = [
     {file = "azure-storage-blob-12.18.3.tar.gz", hash = "sha256:d8ced0deee3367fa3d4f3d1a03cd9edadf4440c0a371f503d623fa6c807554ee"},
     {file = "azure_storage_blob-12.18.3-py3-none-any.whl", hash = "sha256:c278dde2ac41857a68d615c9f2b36d894ba877a7e84d62795603c7e79d0bb5e9"},
@@ -398,6 +416,7 @@ version = "2.2.1"
 description = "Function decoration for backoff and retry"
 optional = false
 python-versions = ">=3.7,<4.0"
+groups = ["unstructured_data"]
 files = [
     {file = "backoff-2.2.1-py3-none-any.whl", hash = "sha256:63579f9a0628e06278f7e47b7d7d5b6ce20dc65c5e96a6f3ca99a6adca0396e8"},
     {file = "backoff-2.2.1.tar.gz", hash = "sha256:03f829f5bb1923180821643f8753b0502c3b682293992485b0eef2807afa5cba"},
@@ -409,6 +428,8 @@ version = "0.2.1"
 description = "Backport of the standard library zoneinfo module"
 optional = false
 python-versions = ">=3.6"
+groups = ["main", "dev", "dltpure", "salesforce"]
+markers = "python_version < \"3.9\""
 files = [
     {file = "backports.zoneinfo-0.2.1-cp36-cp36m-macosx_10_14_x86_64.whl", hash = "sha256:da6013fd84a690242c310d77ddb8441a559e9cb3d3d59ebac9aca1a57b2e18bc"},
     {file = "backports.zoneinfo-0.2.1-cp36-cp36m-manylinux1_i686.whl", hash = "sha256:89a48c0d158a3cc3f654da4c2de1ceba85263fafb861b98b59040a5086259722"},
@@ -437,6 +458,7 @@ version = "1.7.5"
 description = "Security oriented static analyser for python code."
 optional = false
 python-versions = ">=3.7"
+groups = ["dev"]
 files = [
     {file = "bandit-1.7.5-py3-none-any.whl", hash = "sha256:75665181dc1e0096369112541a056c59d1c5f66f9bb74a8d686c3c362b83f549"},
     {file = "bandit-1.7.5.tar.gz", hash = "sha256:bdfc739baa03b880c2d15d0431b31c658ffc348e907fe197e54e0389dd59e11e"},
@@ -460,6 +482,7 @@ version = "23.9.1"
 description = "The uncompromising code formatter."
 optional = false
 python-versions = ">=3.8"
+groups = ["dev"]
 files = [
     {file = "black-23.9.1-cp310-cp310-macosx_10_16_arm64.whl", hash = "sha256:d6bc09188020c9ac2555a498949401ab35bb6bf76d4e0f8ee251694664df6301"},
     {file = "black-23.9.1-cp310-cp310-macosx_10_16_universal2.whl", hash = "sha256:13ef033794029b85dfea8032c9d3b92b42b526f1ff4bf13b2182ce4e917f5100"},
@@ -506,6 +529,7 @@ version = "1.31.17"
 description = "Low-level, data-driven core of boto 3."
 optional = false
 python-versions = ">= 3.7"
+groups = ["filesystem"]
 files = [
     {file = "botocore-1.31.17-py3-none-any.whl", hash = "sha256:6ac34a1d34aa3750e78b77b8596617e2bab938964694d651939dba2cbde2c12b"},
     {file = "botocore-1.31.17.tar.gz", hash = "sha256:396459065dba4339eb4da4ec8b4e6599728eb89b7caaceea199e26f7d824a41c"},
@@ -525,6 +549,7 @@ version = "5.3.1"
 description = "Extensible memoizing collections and decorators"
 optional = false
 python-versions = ">=3.7"
+groups = ["main", "filesystem", "google_ads", "google_analytics", "google_sheets"]
 files = [
     {file = "cachetools-5.3.1-py3-none-any.whl", hash = "sha256:95ef631eeaea14ba2e36f06437f36463aac3a096799e876ee55e5cdccb102590"},
     {file = "cachetools-5.3.1.tar.gz", hash = "sha256:dce83f2d9b4e1f732a8cd44af8e8fab2dbe46201467fc98b3ef8f269092bf62b"},
@@ -536,6 +561,7 @@ version = "2023.7.22"
 description = "Python package for providing Mozilla's CA Bundle."
 optional = false
 python-versions = ">=3.6"
+groups = ["main", "airtable", "asana_dlt", "dev", "dltpure", "facebook_ads", "filesystem", "google_ads", "google_analytics", "google_sheets", "salesforce", "scrapy", "stripe_analytics", "unstructured_data", "unstructured_data_lint"]
 files = [
     {file = "certifi-2023.7.22-py3-none-any.whl", hash = "sha256:92d6037539857d8206b8f6ae472e8b77db8058fec5937a1ef3f54304089edbb9"},
     {file = "certifi-2023.7.22.tar.gz", hash = "sha256:539cc1d13202e33ca466e88b2807e29f4c13049d6d87031a3c110744495cb082"},
@@ -547,6 +573,7 @@ version = "1.16.0"
 description = "Foreign Function Interface for Python calling C code."
 optional = false
 python-versions = ">=3.8"
+groups = ["main", "filesystem", "salesforce", "scrapy", "unstructured_data"]
 files = [
     {file = "cffi-1.16.0-cp310-cp310-macosx_10_9_x86_64.whl", hash = "sha256:6b3d6606d369fc1da4fd8c357d026317fbb9c9b75d36dc16e90e84c26854b088"},
     {file = "cffi-1.16.0-cp310-cp310-macosx_11_0_arm64.whl", hash = "sha256:ac0f5edd2360eea2f1daa9e26a41db02dd4b0451b48f7c318e217ee092a213e9"},
@@ -601,6 +628,7 @@ files = [
     {file = "cffi-1.16.0-cp39-cp39-win_amd64.whl", hash = "sha256:3686dffb02459559c74dd3d81748269ffb0eb027c39a6fc99502de37d501faa8"},
     {file = "cffi-1.16.0.tar.gz", hash = "sha256:bcb3ef43e58665bbda2fb198698fcae6776483e0c4a631aa5647806c25e02cc0"},
 ]
+markers = {main = "platform_python_implementation == \"PyPy\""}
 
 [package.dependencies]
 pycparser = "*"
@@ -611,6 +639,7 @@ version = "5.2.0"
 description = "Universal encoding detector for Python 3"
 optional = false
 python-versions = ">=3.7"
+groups = ["unstructured_data"]
 files = [
     {file = "chardet-5.2.0-py3-none-any.whl", hash = "sha256:e1cf59446890a00105fe7b7912492ea04b6e6f06d4b742b2c788469e34c82970"},
     {file = "chardet-5.2.0.tar.gz", hash = "sha256:1b3b6ff479a8c414bc3fa2c0852995695c4a026dcd6d0633b2dd092ca39c1cf7"},
@@ -622,6 +651,7 @@ version = "3.3.0"
 description = "The Real First Universal Charset Detector. Open, modern and actively maintained alternative to Chardet."
 optional = false
 python-versions = ">=3.7.0"
+groups = ["main", "airtable", "asana_dlt", "dev", "dltpure", "facebook_ads", "filesystem", "google_ads", "google_analytics", "google_sheets", "salesforce", "scrapy", "stripe_analytics", "unstructured_data", "unstructured_data_lint"]
 files = [
     {file = "charset-normalizer-3.3.0.tar.gz", hash = "sha256:63563193aec44bce707e0c5ca64ff69fa72ed7cf34ce6e11d5127555756fd2f6"},
     {file = "charset_normalizer-3.3.0-cp310-cp310-macosx_10_9_universal2.whl", hash = "sha256:effe5406c9bd748a871dbcaf3ac69167c38d72db8c9baf3ff954c344f31c4cbe"},
@@ -721,6 +751,7 @@ version = "0.3.29"
 description = "Chroma."
 optional = false
 python-versions = ">=3.7"
+groups = ["unstructured_data"]
 files = [
     {file = "chromadb-0.3.29-py3-none-any.whl", hash = "sha256:d681a3e4f3284715dd146774be84cad3d2f8c529bd004ba249e1d3deb70ac68e"},
     {file = "chromadb-0.3.29.tar.gz", hash = "sha256:29d47835da494fc1b58da40abb1435689d4ba1c93df6c64664a5d91521cb80e9"},
@@ -751,6 +782,7 @@ version = "8.1.7"
 description = "Composable command line interface toolkit"
 optional = false
 python-versions = ">=3.7"
+groups = ["main", "dev", "dltpure", "unstructured_data"]
 files = [
     {file = "click-8.1.7-py3-none-any.whl", hash = "sha256:ae74fb96c20a0277a1d615f1e4d73c8414f5a98db8b799a7931d1582f3390c28"},
     {file = "click-8.1.7.tar.gz", hash = "sha256:ca9853ad459e787e2192211578cc907e7594e294c7ccc834310722b41b9ca6de"},
@@ -765,6 +797,7 @@ version = "0.6.14"
 description = "ClickHouse Database Core Driver for Python, Pandas, and Superset"
 optional = false
 python-versions = "~=3.7"
+groups = ["unstructured_data"]
 files = [
     {file = "clickhouse-connect-0.6.14.tar.gz", hash = "sha256:0531bbd5b8bdee616bf1cca5ddcb0af86db12e2b48fd39257a8ecdf32200bd57"},
     {file = "clickhouse_connect-0.6.14-cp310-cp310-macosx_10_9_x86_64.whl", hash = "sha256:04affbd255fb8b1e4a882ddc1336c86530976d05578f47bb65e3a53471d291e4"},
@@ -853,10 +886,12 @@ version = "0.4.6"
 description = "Cross-platform colored terminal text."
 optional = false
 python-versions = "!=3.0.*,!=3.1.*,!=3.2.*,!=3.3.*,!=3.4.*,!=3.5.*,!=3.6.*,>=2.7"
+groups = ["main", "dev", "dltpure", "pytest", "unstructured_data", "unstructured_data_lint"]
 files = [
     {file = "colorama-0.4.6-py2.py3-none-any.whl", hash = "sha256:4f1d9991f5acc0ca119f9d443620b77f9d6b33703e51011c16baf57afb285fc6"},
     {file = "colorama-0.4.6.tar.gz", hash = "sha256:08695f5cb7ed6e0531a20572697297273c47b8cae5a63ffc6d6ed5c201be6e44"},
 ]
+markers = {main = "platform_system == \"Windows\"", dev = "sys_platform == \"win32\" or platform_system == \"Windows\"", dltpure = "platform_system == \"Windows\"", pytest = "sys_platform == \"win32\"", unstructured_data = "sys_platform == \"win32\" or platform_system == \"Windows\"", unstructured_data_lint = "platform_system == \"Windows\""}
 
 [[package]]
 name = "coloredlogs"
@@ -864,6 +899,7 @@ version = "15.0.1"
 description = "Colored terminal output for Python's logging module"
 optional = false
 python-versions = ">=2.7, !=3.0.*, !=3.1.*, !=3.2.*, !=3.3.*, !=3.4.*"
+groups = ["unstructured_data"]
 files = [
     {file = "coloredlogs-15.0.1-py2.py3-none-any.whl", hash = "sha256:612ee75c546f53e92e70049c9dbfcc18c935a2b9a53b66085ce9ef6a6e5c0934"},
     {file = "coloredlogs-15.0.1.tar.gz", hash = "sha256:7c991aa71a4577af2f82600d8f8f3a89f936baeaf9b50a9c197da014e5bf16b0"},
@@ -881,6 +917,7 @@ version = "2.3.0"
 description = "Confluent's Python client for Apache Kafka"
 optional = false
 python-versions = "*"
+groups = ["dev"]
 files = [
     {file = "confluent-kafka-2.3.0.tar.gz", hash = "sha256:4069e7b56e0baf9db18c053a605213f0ab2d8f23715dca7b3bd97108df446ced"},
     {file = "confluent_kafka-2.3.0-cp310-cp310-macosx_10_9_x86_64.whl", hash = "sha256:5df845755cd3ebb9165ca00fd1d3a7d514c61e84d9fcbe7babb91193fe9b369c"},
@@ -932,6 +969,7 @@ version = "0.3.2"
 description = ""
 optional = false
 python-versions = "*"
+groups = ["sql_database"]
 files = [
     {file = "connectorx-0.3.2-cp310-cp310-macosx_10_7_x86_64.whl", hash = "sha256:98274242c64a2831a8b1c86e0fa2c46a557dd8cbcf00c3adcf5a602455fb02d7"},
     {file = "connectorx-0.3.2-cp310-cp310-macosx_11_0_arm64.whl", hash = "sha256:e2b11ba49efd330a7348bef3ce09c98218eea21d92a12dd75cd8f0ade5c99ffc"},
@@ -957,6 +995,7 @@ version = "23.10.4"
 description = "Symbolic constants in Python"
 optional = false
 python-versions = ">=3.8"
+groups = ["dev", "scrapy"]
 files = [
     {file = "constantly-23.10.4-py3-none-any.whl", hash = "sha256:3fd9b4d1c3dc1ec9757f3c52aef7e53ad9323dbe39f51dfd4c43853b68dfa3f9"},
     {file = "constantly-23.10.4.tar.gz", hash = "sha256:aa92b70a33e2ac0bb33cd745eb61776594dc48764b06c35e0efd050b7f1c7cbd"},
@@ -968,6 +1007,7 @@ version = "41.0.4"
 description = "cryptography is a package which provides cryptographic recipes and primitives to Python developers."
 optional = false
 python-versions = ">=3.7"
+groups = ["filesystem", "salesforce", "scrapy", "unstructured_data"]
 files = [
     {file = "cryptography-41.0.4-cp37-abi3-macosx_10_12_universal2.whl", hash = "sha256:80907d3faa55dc5434a16579952ac6da800935cd98d14dbd62f6f042c7f5e839"},
     {file = "cryptography-41.0.4-cp37-abi3-macosx_10_12_x86_64.whl", hash = "sha256:35c00f637cd0b9d5b6c6bd11b6c3359194a8eba9c46d4e875a3660e3b400005f"},
@@ -1013,6 +1053,7 @@ version = "1.2.0"
 description = "cssselect parses CSS3 Selectors and translates them to XPath 1.0"
 optional = false
 python-versions = ">=3.7"
+groups = ["scrapy"]
 files = [
     {file = "cssselect-1.2.0-py2.py3-none-any.whl", hash = "sha256:da1885f0c10b60c03ed5eccbb6b68d6eff248d91976fcde348f395d54c9fd35e"},
     {file = "cssselect-1.2.0.tar.gz", hash = "sha256:666b19839cfaddb9ce9d36bfe4c969132c647b92fc9088c4e23f786b30f1b3dc"},
@@ -1024,6 +1065,7 @@ version = "2.2.1"
 description = "Library to convert python requests object to curl command."
 optional = false
 python-versions = "*"
+groups = ["facebook_ads"]
 files = [
     {file = "curlify-2.2.1.tar.gz", hash = "sha256:0d3f02e7235faf952de8ef45ef469845196d30632d5838bcd5aee217726ddd6d"},
 ]
@@ -1037,6 +1079,7 @@ version = "0.5.9"
 description = "Easily serialize dataclasses to and from JSON"
 optional = false
 python-versions = ">=3.6"
+groups = ["unstructured_data", "unstructured_data_lint"]
 files = [
     {file = "dataclasses-json-0.5.9.tar.gz", hash = "sha256:e9ac87b73edc0141aafbce02b44e93553c3123ad574958f0fe52a534b6707e8e"},
     {file = "dataclasses_json-0.5.9-py3-none-any.whl", hash = "sha256:1280542631df1c375b7bc92e5b86d39e06c44760d7e3571a537b3b8acabf2f0c"},
@@ -1056,6 +1099,7 @@ version = "1.3.1"
 description = "Pandas Data Types for SQL systems (BigQuery, Spanner)"
 optional = false
 python-versions = ">=3.7"
+groups = ["main"]
 files = [
     {file = "db_dtypes-1.3.1-py2.py3-none-any.whl", hash = "sha256:fbc9d1740d94aaf2b5ae24601cfc875a69b4635bb9d049e3c3036e9f10203af8"},
     {file = "db_dtypes-1.3.1.tar.gz", hash = "sha256:a058f05dab100891f3e76a7a3db9ad0f107f18dd3d1bdd13680749a2f07eae77"},
@@ -1073,6 +1117,7 @@ version = "5.1.1"
 description = "Decorators for Humans"
 optional = false
 python-versions = ">=3.5"
+groups = ["main", "filesystem"]
 files = [
     {file = "decorator-5.1.1-py3-none-any.whl", hash = "sha256:b8c3f85900b9dc423225913c5aace94729fe1fa9763b38939a95226f02d37186"},
     {file = "decorator-5.1.1.tar.gz", hash = "sha256:637996211036b6385ef91435e4fae22989472f9d571faba8927ba8253acbc330"},
@@ -1084,6 +1129,7 @@ version = "1.3.0"
 description = "dlt is an open-source python-first scalable data loading library that does not require any backend to run."
 optional = false
 python-versions = "<3.13,>=3.8.1"
+groups = ["main", "dltpure"]
 files = [
     {file = "dlt-1.3.0-py3-none-any.whl", hash = "sha256:e2583ed0ad4a0d9941b8f9cb0e078f4443bcbeb0e1cf1cce586cf35107ccf266"},
     {file = "dlt-1.3.0.tar.gz", hash = "sha256:57eecee99ace25b6d37027a78f59f8c735d1913cc81f1101e1b47bf96fc544b8"},
@@ -1160,6 +1206,7 @@ version = "2.4.2"
 description = "DNS toolkit"
 optional = false
 python-versions = ">=3.8,<4.0"
+groups = ["mongodb"]
 files = [
     {file = "dnspython-2.4.2-py3-none-any.whl", hash = "sha256:57c6fbaaeaaf39c891292012060beb141791735dbb4004798328fc2c467402d8"},
     {file = "dnspython-2.4.2.tar.gz", hash = "sha256:8dcfae8c7460a2f84b4072e26f1c9f4101ca20c071649cb7c34e8b6a93d58984"},
@@ -1179,6 +1226,7 @@ version = "3.6.1"
 description = "Helpful functions for Python 🐍 🛠️"
 optional = false
 python-versions = ">=3.6"
+groups = ["dev"]
 files = [
     {file = "domdf_python_tools-3.6.1-py3-none-any.whl", hash = "sha256:e18158460850957f18e740eb94ede56f580ddb0cb162ab9d9834ed8bbb1b6431"},
     {file = "domdf_python_tools-3.6.1.tar.gz", hash = "sha256:acc04563d23bce4d437dd08af6b9bea788328c412772a044d8ca428a7ad861be"},
@@ -1199,6 +1247,7 @@ version = "0.10.3"
 description = "DuckDB in-process database"
 optional = false
 python-versions = ">=3.7.0"
+groups = ["main", "unstructured_data"]
 files = [
     {file = "duckdb-0.10.3-cp310-cp310-macosx_10_9_universal2.whl", hash = "sha256:cd25cc8d001c09a19340739ba59d33e12a81ab285b7a6bed37169655e1cefb31"},
     {file = "duckdb-0.10.3-cp310-cp310-macosx_10_9_x86_64.whl", hash = "sha256:2f9259c637b917ca0f4c63887e8d9b35ec248f5d987c886dfc4229d66a791009"},
@@ -1255,6 +1304,7 @@ version = "1.1.0"
 description = "An implementation of lxml.xmlfile for the standard library"
 optional = false
 python-versions = ">=3.6"
+groups = ["unstructured_data"]
 files = [
     {file = "et_xmlfile-1.1.0-py3-none-any.whl", hash = "sha256:a2ba85d1d6a74ef63837eed693bcb89c3f752169b0e3e7ae5b16ca5e1b3deada"},
     {file = "et_xmlfile-1.1.0.tar.gz", hash = "sha256:8eb9e2bc2f8c97e37a2dc85a09ecdcdec9d8a396530a6d5a33b30b9a92da0c5c"},
@@ -1266,6 +1316,8 @@ version = "1.1.3"
 description = "Backport of PEP 654 (exception groups)"
 optional = false
 python-versions = ">=3.7"
+groups = ["dev", "pytest", "unstructured_data"]
+markers = "python_version < \"3.11\""
 files = [
     {file = "exceptiongroup-1.1.3-py3-none-any.whl", hash = "sha256:343280667a4585d195ca1cf9cef84a4e178c4b6cf2274caef9859782b567d5e3"},
     {file = "exceptiongroup-1.1.3.tar.gz", hash = "sha256:097acd85d473d75af5bb98e41b61ff7fe35efe6675e4f9370ec6ec5126d160e9"},
@@ -1280,6 +1332,7 @@ version = "17.0.4"
 description = "Facebook Business SDK"
 optional = false
 python-versions = "*"
+groups = ["facebook_ads"]
 files = [
     {file = "facebook_business-17.0.4-py3-none-any.whl", hash = "sha256:c3a4afbe019c1fd2454eeeefb4e895ed3276d506115fbf9a993135f6af1c1a88"},
     {file = "facebook_business-17.0.4.tar.gz", hash = "sha256:52b516a237ab4cbf083053d3cc062995ff4732fca487b46543c4eab3bdbbf188"},
@@ -1298,6 +1351,7 @@ version = "0.85.1"
 description = "FastAPI framework, high performance, easy to learn, fast to code, ready for production"
 optional = false
 python-versions = ">=3.7"
+groups = ["unstructured_data"]
 files = [
     {file = "fastapi-0.85.1-py3-none-any.whl", hash = "sha256:de3166b6b1163dc22da4dc4ebdc3192fcbac7700dd1870a1afa44de636a636b5"},
     {file = "fastapi-0.85.1.tar.gz", hash = "sha256:1facd097189682a4ff11cbd01334a992e51b56be663b2bd50c2c09523624f144"},
@@ -1319,6 +1373,7 @@ version = "3.12.4"
 description = "A platform independent file lock."
 optional = false
 python-versions = ">=3.8"
+groups = ["scrapy", "unstructured_data"]
 files = [
     {file = "filelock-3.12.4-py3-none-any.whl", hash = "sha256:08c21d87ded6e2b9da6728c3dff51baf1dcecf973b768ef35bcbc3447edb9ad4"},
     {file = "filelock-3.12.4.tar.gz", hash = "sha256:2e6f249f1f3654291606e046b09f1fd5eac39b360664c27f5aad072012f8bcbd"},
@@ -1335,6 +1390,7 @@ version = "1.2.0"
 description = "Infer file type and MIME type of any file/buffer. No external dependencies."
 optional = false
 python-versions = "*"
+groups = ["unstructured_data"]
 files = [
     {file = "filetype-1.2.0-py2.py3-none-any.whl", hash = "sha256:7ce71b6880181241cf7ac8697a2f1eb6a8bd9b429f7ad6d27b8db9ba5f1c2d25"},
     {file = "filetype-1.2.0.tar.gz", hash = "sha256:66b56cd6474bf41d8c54660347d37afcc3f7d1970648de365c102ef77548aadb"},
@@ -1346,6 +1402,7 @@ version = "6.1.0"
 description = "the modular source code checker: pep8 pyflakes and co"
 optional = false
 python-versions = ">=3.8.1"
+groups = ["dev"]
 files = [
     {file = "flake8-6.1.0-py2.py3-none-any.whl", hash = "sha256:ffdfce58ea94c6580c77888a86506937f9a1a227dfcd15f245d694ae20a6b6e5"},
     {file = "flake8-6.1.0.tar.gz", hash = "sha256:d5b3857f07c030bdb5bf41c7f53799571d75c4491748a3adcd47de929e34cd23"},
@@ -1362,6 +1419,7 @@ version = "22.12.6"
 description = "A plugin for flake8 finding likely bugs and design problems in your program. Contains warnings that don't belong in pyflakes and pycodestyle."
 optional = false
 python-versions = ">=3.7"
+groups = ["dev"]
 files = [
     {file = "flake8-bugbear-22.12.6.tar.gz", hash = "sha256:4cdb2c06e229971104443ae293e75e64c6107798229202fbe4f4091427a30ac0"},
     {file = "flake8_bugbear-22.12.6-py3-none-any.whl", hash = "sha256:b69a510634f8a9c298dfda2b18a8036455e6b19ecac4fe582e4d7a0abfa50a30"},
@@ -1380,6 +1438,7 @@ version = "2.1.0"
 description = "Check for python builtins being used as variables or parameters."
 optional = false
 python-versions = ">=3.7"
+groups = ["dev"]
 files = [
     {file = "flake8-builtins-2.1.0.tar.gz", hash = "sha256:12ff1ee96dd4e1f3141141ee6c45a5c7d3b3c440d0949e9b8d345c42b39c51d4"},
     {file = "flake8_builtins-2.1.0-py3-none-any.whl", hash = "sha256:469e8f03d6d0edf4b1e62b6d5a97dce4598592c8a13ec8f0952e7a185eba50a1"},
@@ -1397,6 +1456,7 @@ version = "0.5.0.post1"
 description = "A Flake8 plugin to identify incorrect use of encodings."
 optional = false
 python-versions = ">=3.6"
+groups = ["dev"]
 files = [
     {file = "flake8_encodings-0.5.0.post1-py3-none-any.whl", hash = "sha256:d2fecca0e89ba09c86e5d61cf6bdb1b337f0d74746aac67bbcf0c517b4cb6cba"},
     {file = "flake8_encodings-0.5.0.post1.tar.gz", hash = "sha256:082c0163325c85b438a8106e876283b5ed3cbfc53e68d89130d70be8be4c9977"},
@@ -1418,6 +1478,7 @@ version = "0.2.1"
 description = "A helper library for Flake8 plugins."
 optional = false
 python-versions = ">=3.6"
+groups = ["dev"]
 files = [
     {file = "flake8_helper-0.2.1-py3-none-any.whl", hash = "sha256:9123cdf351ad32ee8a51b85036052302c478122d62fb512c0773e111b3d05241"},
     {file = "flake8_helper-0.2.1.tar.gz", hash = "sha256:479f86d1c52df8e49ff876ecd3873242699f93eeece7e6675cdca9c37c9b0a16"},
@@ -1432,6 +1493,7 @@ version = "4.10.0"
 description = "A flake8 plugin that helps you write tidier imports."
 optional = false
 python-versions = ">=3.8"
+groups = ["dev"]
 files = [
     {file = "flake8_tidy_imports-4.10.0-py3-none-any.whl", hash = "sha256:b0387fb2ea200441bd142309e716fb7b8f4b0937bdf5f8b7c0c118a5f5e2b8ed"},
     {file = "flake8_tidy_imports-4.10.0.tar.gz", hash = "sha256:bd6cf86465402d2b86903009b748d85a628e599e17b76e810c9857e3a2815173"},
@@ -1446,6 +1508,7 @@ version = "23.5.26"
 description = "The FlatBuffers serialization format for Python"
 optional = false
 python-versions = "*"
+groups = ["unstructured_data"]
 files = [
     {file = "flatbuffers-23.5.26-py2.py3-none-any.whl", hash = "sha256:c0ff356da363087b915fde4b8b45bdda73432fc17cddb3c8157472eab1422ad1"},
     {file = "flatbuffers-23.5.26.tar.gz", hash = "sha256:9ea1144cac05ce5d86e2859f431c6cd5e66cd9c78c558317c7955fb8d4c78d89"},
@@ -1457,6 +1520,7 @@ version = "1.4.0"
 description = "A list-like structure which implements collections.abc.MutableSequence"
 optional = false
 python-versions = ">=3.8"
+groups = ["main", "facebook_ads", "filesystem", "unstructured_data", "unstructured_data_lint"]
 files = [
     {file = "frozenlist-1.4.0-cp310-cp310-macosx_10_9_universal2.whl", hash = "sha256:764226ceef3125e53ea2cb275000e309c0aa5464d43bd72abd661e27fffc26ab"},
     {file = "frozenlist-1.4.0-cp310-cp310-macosx_10_9_x86_64.whl", hash = "sha256:d6484756b12f40003c6128bfcc3fa9f0d49a687e171186c2d85ec82e3758c559"},
@@ -1527,6 +1591,7 @@ version = "2024.3.1"
 description = "File-system specification"
 optional = false
 python-versions = ">=3.8"
+groups = ["main", "dltpure", "filesystem", "unstructured_data"]
 files = [
     {file = "fsspec-2024.3.1-py3-none-any.whl", hash = "sha256:918d18d41bf73f0e2b261824baeb1b124bcf771767e3a26425cd7dec3332f512"},
     {file = "fsspec-2024.3.1.tar.gz", hash = "sha256:f39780e282d7d117ffb42bb96992f8a90795e4d0fb0f661a70ca39fe9c43ded9"},
@@ -1562,6 +1627,7 @@ version = "2024.3.1"
 description = "Convenient Filesystem interface over GCS"
 optional = false
 python-versions = ">=3.8"
+groups = ["main", "filesystem"]
 files = [
     {file = "gcsfs-2024.3.1-py2.py3-none-any.whl", hash = "sha256:57ec693a25b74637f00e7a834b4f1dcd7a7511217f7f640072d6fb51a7794bac"},
     {file = "gcsfs-2024.3.1.tar.gz", hash = "sha256:d34bdb8a1a51e1b2552ae9e47d1933dec41162ba6b6cc8ea470aef693a8a6aa6"},
@@ -1586,6 +1652,7 @@ version = "4.0.10"
 description = "Git Object Database"
 optional = false
 python-versions = ">=3.7"
+groups = ["main", "dev", "dltpure"]
 files = [
     {file = "gitdb-4.0.10-py3-none-any.whl", hash = "sha256:c286cf298426064079ed96a9e4a9d39e7f3e9bf15ba60701e95f5492f28415c7"},
     {file = "gitdb-4.0.10.tar.gz", hash = "sha256:6eb990b69df4e15bad899ea868dc46572c3f75339735663b81de79b06f17eb9a"},
@@ -1600,6 +1667,7 @@ version = "3.1.37"
 description = "GitPython is a Python library used to interact with Git repositories"
 optional = false
 python-versions = ">=3.7"
+groups = ["main", "dev", "dltpure"]
 files = [
     {file = "GitPython-3.1.37-py3-none-any.whl", hash = "sha256:5f4c4187de49616d710a77e98ddf17b4782060a1788df441846bddefbb89ab33"},
     {file = "GitPython-3.1.37.tar.gz", hash = "sha256:f9b9ddc0761c125d5780eab2d64be4873fc6817c2899cbcb34b02344bdc7bc54"},
@@ -1617,6 +1685,7 @@ version = "0.12.0"
 description = "A Git URL parsing module (supports parsing and rewriting)"
 optional = false
 python-versions = ">=3.8"
+groups = ["main", "dltpure"]
 files = [
     {file = "giturlparse-0.12.0-py2.py3-none-any.whl", hash = "sha256:412b74f2855f1da2fefa89fd8dde62df48476077a72fc19b62039554d27360eb"},
     {file = "giturlparse-0.12.0.tar.gz", hash = "sha256:c0fff7c21acc435491b1779566e038757a205c1ffdcb47e4f81ea52ad8c3859a"},
@@ -1628,6 +1697,7 @@ version = "21.3.0"
 description = "Client library for the Google Ads API"
 optional = false
 python-versions = ">=3.7"
+groups = ["google_ads"]
 files = [
     {file = "google-ads-21.3.0.tar.gz", hash = "sha256:bd4fcb6bd5e55bace413e889e82012d48578aa28f7b4d726c86e2d594c753c6c"},
     {file = "google_ads-21.3.0-py3-none-any.whl", hash = "sha256:961943fc737941a38f1a826681f7974448df7c60e6c8db2ac7168b26d66738a7"},
@@ -1653,6 +1723,7 @@ version = "0.16.3"
 description = "Google Analytics Data API client library"
 optional = false
 python-versions = ">=3.7"
+groups = ["google_analytics"]
 files = [
     {file = "google-analytics-data-0.16.3.tar.gz", hash = "sha256:f29431ec63ab462f7a9b42227521d148c877307c629e308c284025ad834aab52"},
     {file = "google_analytics_data-0.16.3-py2.py3-none-any.whl", hash = "sha256:bb73f36707a5a2966e87c9439c25cd8004d58305b0ef01c6f2f50128c08feb13"},
@@ -1672,6 +1743,7 @@ version = "2.12.0"
 description = "Google API client core library"
 optional = false
 python-versions = ">=3.7"
+groups = ["main", "filesystem", "google_ads", "google_analytics", "google_sheets"]
 files = [
     {file = "google-api-core-2.12.0.tar.gz", hash = "sha256:c22e01b1e3c4dcd90998494879612c38d0a3411d1f7b679eb89e2abe3ce1f553"},
     {file = "google_api_core-2.12.0-py3-none-any.whl", hash = "sha256:ec6054f7d64ad13b41e43d96f735acbd763b0f3b695dabaa2d579673f6a6e160"},
@@ -1702,6 +1774,7 @@ version = "2.129.0"
 description = "Google API Client Library for Python"
 optional = false
 python-versions = ">=3.7"
+groups = ["google_ads", "google_analytics", "google_sheets"]
 files = [
     {file = "google-api-python-client-2.129.0.tar.gz", hash = "sha256:984cc8cc8eb4923468b1926d2b8effc5b459a4dda3c845896eb87c153b28ef84"},
     {file = "google_api_python_client-2.129.0-py2.py3-none-any.whl", hash = "sha256:d50f7e2dfdbb7fc2732f6a0cba1c54d7bb676390679526c6bb628c901e43ec86"},
@@ -1720,6 +1793,7 @@ version = "2.23.3"
 description = "Google Authentication Library"
 optional = false
 python-versions = ">=3.7"
+groups = ["main", "filesystem", "google_ads", "google_analytics", "google_sheets"]
 files = [
     {file = "google-auth-2.23.3.tar.gz", hash = "sha256:6864247895eea5d13b9c57c9e03abb49cb94ce2dc7c58e91cba3248c7477c9e3"},
     {file = "google_auth-2.23.3-py2.py3-none-any.whl", hash = "sha256:a8f4608e65c244ead9e0538f181a96c6e11199ec114d41f1d7b1bffa96937bda"},
@@ -1743,6 +1817,7 @@ version = "0.2.0"
 description = "Google Authentication Library: httplib2 transport"
 optional = false
 python-versions = "*"
+groups = ["google_ads", "google_analytics", "google_sheets"]
 files = [
     {file = "google-auth-httplib2-0.2.0.tar.gz", hash = "sha256:38aa7badf48f974f1eb9861794e9c0cb2a0511a4ec0679b1f886d108f5640e05"},
     {file = "google_auth_httplib2-0.2.0-py2.py3-none-any.whl", hash = "sha256:b65a0a2123300dd71281a7bf6e64d65a0759287df52729bdd1ae2e47dc311a3d"},
@@ -1758,6 +1833,7 @@ version = "1.1.0"
 description = "Google Authentication Library"
 optional = false
 python-versions = ">=3.6"
+groups = ["main", "filesystem", "google_ads", "google_analytics"]
 files = [
     {file = "google-auth-oauthlib-1.1.0.tar.gz", hash = "sha256:83ea8c3b0881e453790baff4448e8a6112ac8778d1de9da0b68010b843937afb"},
     {file = "google_auth_oauthlib-1.1.0-py2.py3-none-any.whl", hash = "sha256:089c6e587d36f4803ac7e0720c045c6a8b1fd1790088b8424975b90d0ee61c12"},
@@ -1776,6 +1852,7 @@ version = "3.25.0"
 description = "Google BigQuery API client library"
 optional = false
 python-versions = ">=3.7"
+groups = ["main"]
 files = [
     {file = "google-cloud-bigquery-3.25.0.tar.gz", hash = "sha256:5b2aff3205a854481117436836ae1403f11f2594e6810a98886afd57eda28509"},
     {file = "google_cloud_bigquery-3.25.0-py2.py3-none-any.whl", hash = "sha256:7f0c371bc74d2a7fb74dacbc00ac0f90c8c2bec2289b51dd6685a275873b1ce9"},
@@ -1807,6 +1884,7 @@ version = "2.3.3"
 description = "Google Cloud API client core library"
 optional = false
 python-versions = ">=3.7"
+groups = ["main", "filesystem"]
 files = [
     {file = "google-cloud-core-2.3.3.tar.gz", hash = "sha256:37b80273c8d7eee1ae816b3a20ae43585ea50506cb0e60f3cf5be5f87f1373cb"},
     {file = "google_cloud_core-2.3.3-py2.py3-none-any.whl", hash = "sha256:fbd11cad3e98a7e5b0343dc07cb1039a5ffd7a5bb96e1f1e27cee4bda4a90863"},
@@ -1825,6 +1903,7 @@ version = "2.12.0"
 description = "Google Cloud Storage API client library"
 optional = false
 python-versions = ">=3.7"
+groups = ["main", "filesystem"]
 files = [
     {file = "google-cloud-storage-2.12.0.tar.gz", hash = "sha256:57c0bcda2f5e11f008a155d8636d8381d5abab46b58e0cae0e46dd5e595e6b46"},
     {file = "google_cloud_storage-2.12.0-py2.py3-none-any.whl", hash = "sha256:bc52563439d42981b6e21b071a76da2791672776eda3ba99d13a8061ebbd6e5e"},
@@ -1847,6 +1926,7 @@ version = "1.5.0"
 description = "A python wrapper of the C library 'Google CRC32C'"
 optional = false
 python-versions = ">=3.7"
+groups = ["main", "filesystem"]
 files = [
     {file = "google-crc32c-1.5.0.tar.gz", hash = "sha256:89284716bc6a5a415d4eaa11b1726d2d60a0cd12aadf5439828353662ede9dd7"},
     {file = "google_crc32c-1.5.0-cp310-cp310-macosx_10_9_universal2.whl", hash = "sha256:596d1f98fc70232fcb6590c439f43b350cb762fb5d61ce7b0e9db4539654cc13"},
@@ -1927,6 +2007,7 @@ version = "2.6.0"
 description = "Utilities for Google Media Downloads and Resumable Uploads"
 optional = false
 python-versions = ">= 3.7"
+groups = ["main", "filesystem"]
 files = [
     {file = "google-resumable-media-2.6.0.tar.gz", hash = "sha256:972852f6c65f933e15a4a210c2b96930763b47197cdf4aa5f5bea435efb626e7"},
     {file = "google_resumable_media-2.6.0-py2.py3-none-any.whl", hash = "sha256:fc03d344381970f79eebb632a3c18bb1828593a2dc5572b5f90115ef7d11e81b"},
@@ -1945,6 +2026,7 @@ version = "1.61.0"
 description = "Common protobufs used in Google APIs"
 optional = false
 python-versions = ">=3.7"
+groups = ["main", "filesystem", "google_ads", "google_analytics", "google_sheets"]
 files = [
     {file = "googleapis-common-protos-1.61.0.tar.gz", hash = "sha256:8a64866a97f6304a7179873a465d6eee97b7a24ec6cfd78e0f575e96b821240b"},
     {file = "googleapis_common_protos-1.61.0-py2.py3-none-any.whl", hash = "sha256:22f1915393bb3245343f6efe87f6fe868532efc12aa26b391b15132e1279f1c0"},
@@ -1962,6 +2044,8 @@ version = "1.0.3"
 description = "Backport of the Python 3.9 graphlib module for Python 3.6+"
 optional = false
 python-versions = ">=3.6,<4.0"
+groups = ["main", "dltpure", "unstructured_data"]
+markers = "python_version < \"3.9\""
 files = [
     {file = "graphlib_backport-1.0.3-py3-none-any.whl", hash = "sha256:24246967b9e7e6a91550bc770e6169585d35aa32790258579a8a3899a8c18fde"},
     {file = "graphlib_backport-1.0.3.tar.gz", hash = "sha256:7bb8fc7757b8ae4e6d8000a26cd49e9232aaa9a3aa57edb478474b8424bfaae2"},
@@ -1973,6 +2057,7 @@ version = "2.0.2"
 description = "Lightweight in-process concurrent programming"
 optional = false
 python-versions = ">=2.7,!=3.0.*,!=3.1.*,!=3.2.*,!=3.3.*,!=3.4.*"
+groups = ["dev", "sql_database", "unstructured_data", "unstructured_data_lint"]
 files = [
     {file = "greenlet-2.0.2-cp27-cp27m-macosx_10_14_x86_64.whl", hash = "sha256:bdfea8c661e80d3c1c99ad7c3ff74e6e87184895bbaca6ee8cc61209f8b9b85d"},
     {file = "greenlet-2.0.2-cp27-cp27m-manylinux2010_x86_64.whl", hash = "sha256:9d14b83fab60d5e8abe587d51c75b252bcc21683f24699ada8fb275d7712f5a9"},
@@ -2050,6 +2135,7 @@ version = "1.59.0"
 description = "HTTP/2-based RPC framework"
 optional = false
 python-versions = ">=3.7"
+groups = ["main", "google_ads", "google_analytics"]
 files = [
     {file = "grpcio-1.59.0-cp310-cp310-linux_armv7l.whl", hash = "sha256:225e5fa61c35eeaebb4e7491cd2d768cd8eb6ed00f2664fa83a58f29418b39fd"},
     {file = "grpcio-1.59.0-cp310-cp310-macosx_12_0_universal2.whl", hash = "sha256:b95ec8ecc4f703f5caaa8d96e93e40c7f589bad299a2617bdb8becbcce525539"},
@@ -2116,6 +2202,7 @@ version = "1.59.0"
 description = "Status proto mapping for gRPC"
 optional = false
 python-versions = ">=3.6"
+groups = ["main", "google_ads", "google_analytics"]
 files = [
     {file = "grpcio-status-1.59.0.tar.gz", hash = "sha256:f93b9c33e0a26162ef8431bfcffcc3e1fb217ccd8d7b5b3061b6e9f813e698b5"},
     {file = "grpcio_status-1.59.0-py3-none-any.whl", hash = "sha256:cb5a222b14a80ee050bff9676623822e953bff0c50d2d29180de723652fdf10d"},
@@ -2132,6 +2219,7 @@ version = "0.14.0"
 description = "A pure-Python, bring-your-own-I/O implementation of HTTP/1.1"
 optional = false
 python-versions = ">=3.7"
+groups = ["unstructured_data"]
 files = [
     {file = "h11-0.14.0-py3-none-any.whl", hash = "sha256:e3fe4ac4b851c468cc8363d500db52c2ead036020723024a109d37346efaa761"},
     {file = "h11-0.14.0.tar.gz", hash = "sha256:8f19fbbe99e72420ff35c00b27a34cb9937e902a8b810e2c88300c6f0a3b699d"},
@@ -2143,6 +2231,7 @@ version = "0.3.1"
 description = "hexbytes: Python `bytes` subclass that decodes hex, with a readable console output"
 optional = false
 python-versions = ">=3.7, <4"
+groups = ["main", "dltpure"]
 files = [
     {file = "hexbytes-0.3.1-py3-none-any.whl", hash = "sha256:383595ad75026cf00abd570f44b368c6cdac0c6becfae5c39ff88829877f8a59"},
     {file = "hexbytes-0.3.1.tar.gz", hash = "sha256:a3fe35c6831ee8fafd048c4c086b986075fc14fd46258fa24ecb8d65745f9a9d"},
@@ -2160,6 +2249,7 @@ version = "0.7.0"
 description = "hnswlib"
 optional = false
 python-versions = "*"
+groups = ["unstructured_data"]
 files = [
     {file = "hnswlib-0.7.0.tar.gz", hash = "sha256:bc459668e7e44bb7454b256b90c98c5af750653919d9a91698dafcf416cf64c4"},
 ]
@@ -2173,6 +2263,7 @@ version = "0.22.0"
 description = "A comprehensive HTTP client library."
 optional = false
 python-versions = ">=2.7, !=3.0.*, !=3.1.*, !=3.2.*, !=3.3.*"
+groups = ["google_ads", "google_analytics", "google_sheets"]
 files = [
     {file = "httplib2-0.22.0-py3-none-any.whl", hash = "sha256:14ae0a53c1ba8f3d37e9e27cf37eabb0fb9980f435ba405d546948b009dd64dc"},
     {file = "httplib2-0.22.0.tar.gz", hash = "sha256:d7a10bc5ef5ab08322488bde8c726eeee5c8618723fdb399597ec58f3d82df81"},
@@ -2187,6 +2278,7 @@ version = "0.6.0"
 description = "A collection of framework independent HTTP protocol utils."
 optional = false
 python-versions = ">=3.5.0"
+groups = ["unstructured_data"]
 files = [
     {file = "httptools-0.6.0-cp310-cp310-macosx_10_9_universal2.whl", hash = "sha256:818325afee467d483bfab1647a72054246d29f9053fd17cc4b86cda09cc60339"},
     {file = "httptools-0.6.0-cp310-cp310-macosx_10_9_x86_64.whl", hash = "sha256:72205730bf1be875003692ca54a4a7c35fac77b4746008966061d9d41a61b0f5"},
@@ -2234,6 +2326,7 @@ version = "0.17.3"
 description = "Client library to download and publish models, datasets and other repos on the huggingface.co hub"
 optional = false
 python-versions = ">=3.8.0"
+groups = ["unstructured_data"]
 files = [
     {file = "huggingface_hub-0.17.3-py3-none-any.whl", hash = "sha256:545eb3665f6ac587add946e73984148f2ea5c7877eac2e845549730570c1933a"},
     {file = "huggingface_hub-0.17.3.tar.gz", hash = "sha256:40439632b211311f788964602bf8b0d9d6b7a2314fba4e8d67b2ce3ecea0e3fd"},
@@ -2267,6 +2360,7 @@ version = "10.0"
 description = "Human friendly output for text interfaces using Python"
 optional = false
 python-versions = ">=2.7, !=3.0.*, !=3.1.*, !=3.2.*, !=3.3.*, !=3.4.*"
+groups = ["unstructured_data"]
 files = [
     {file = "humanfriendly-10.0-py2.py3-none-any.whl", hash = "sha256:1697e1a8a8f550fd43c2865cd84542fc175a61dcb779b6fee18cf6b6ccba1477"},
     {file = "humanfriendly-10.0.tar.gz", hash = "sha256:6b0b831ce8f15f7300721aa49829fc4e83921a9a301cc7f606be6686a2288ddc"},
@@ -2281,6 +2375,7 @@ version = "4.8.0"
 description = "Python humanize utilities"
 optional = false
 python-versions = ">=3.8"
+groups = ["main", "dltpure"]
 files = [
     {file = "humanize-4.8.0-py3-none-any.whl", hash = "sha256:8bc9e2bb9315e61ec06bf690151ae35aeb65651ab091266941edf97c90836404"},
     {file = "humanize-4.8.0.tar.gz", hash = "sha256:9783373bf1eec713a770ecaa7c2d7a7902c98398009dfa3d8a2df91eec9311e8"},
@@ -2295,6 +2390,7 @@ version = "21.0.0"
 description = "A featureful, immutable, and correct URL for Python."
 optional = false
 python-versions = ">=2.6, !=3.0.*, !=3.1.*, !=3.2.*, !=3.3.*"
+groups = ["dev", "scrapy"]
 files = [
     {file = "hyperlink-21.0.0-py2.py3-none-any.whl", hash = "sha256:e6b14c37ecb73e89c77d78cdb4c2cc8f3fb59a885c5b3f819ff4ed80f25af1b4"},
     {file = "hyperlink-21.0.0.tar.gz", hash = "sha256:427af957daa58bc909471c6c40f74c5450fa123dd093fc53efd2e91d2705a56b"},
@@ -2309,6 +2405,7 @@ version = "3.4"
 description = "Internationalized Domain Names in Applications (IDNA)"
 optional = false
 python-versions = ">=3.5"
+groups = ["main", "airtable", "asana_dlt", "dev", "dltpure", "facebook_ads", "filesystem", "google_ads", "google_analytics", "google_sheets", "salesforce", "scrapy", "stripe_analytics", "unstructured_data", "unstructured_data_lint"]
 files = [
     {file = "idna-3.4-py3-none-any.whl", hash = "sha256:90b77e79eaa3eba6de819a0c442c0b4ceefc341a7a2ab77d7562bf49f425c5c2"},
     {file = "idna-3.4.tar.gz", hash = "sha256:814f528e8dead7d329833b91c5faa87d60bf71824cd12a7530b5526063d02cb4"},
@@ -2320,10 +2417,12 @@ version = "6.8.0"
 description = "Read metadata from Python packages"
 optional = false
 python-versions = ">=3.8"
+groups = ["dev", "unstructured_data"]
 files = [
     {file = "importlib_metadata-6.8.0-py3-none-any.whl", hash = "sha256:3ebb78df84a805d7698245025b975d9d67053cd94c79245ba4b3eb694abe68bb"},
     {file = "importlib_metadata-6.8.0.tar.gz", hash = "sha256:dbace7892d8c0c4ac1ad096662232f831d4e64f4c4545bd53016a3e9d4654743"},
 ]
+markers = {dev = "python_version < \"3.9\"", unstructured_data = "python_version < \"3.10\""}
 
 [package.dependencies]
 zipp = ">=0.5"
@@ -2339,6 +2438,8 @@ version = "6.4.0"
 description = "Read resources from Python packages"
 optional = false
 python-versions = ">=3.8"
+groups = ["main", "dev", "dltpure", "salesforce"]
+markers = "python_version < \"3.9\""
 files = [
     {file = "importlib_resources-6.4.0-py3-none-any.whl", hash = "sha256:50d10f043df931902d4194ea07ec57960f66a80449ff867bfe782b4c486ba78c"},
     {file = "importlib_resources-6.4.0.tar.gz", hash = "sha256:cdb2b453b8046ca4e3798eb1d84f3cce1446a0e8e7b5ef4efb600f19fc398145"},
@@ -2357,6 +2458,7 @@ version = "22.10.0"
 description = "\"A small library that versions your Python projects.\""
 optional = false
 python-versions = "*"
+groups = ["dev", "scrapy"]
 files = [
     {file = "incremental-22.10.0-py2.py3-none-any.whl", hash = "sha256:b864a1f30885ee72c5ac2835a761b8fe8aa9c28b9395cacf27286602688d3e51"},
     {file = "incremental-22.10.0.tar.gz", hash = "sha256:912feeb5e0f7e0188e6f42241d2f450002e11bbc0937c65865045854c24c0bd0"},
@@ -2372,6 +2474,7 @@ version = "0.5.1"
 description = "A port of Ruby on Rails inflector to Python"
 optional = false
 python-versions = ">=3.5"
+groups = ["airtable"]
 files = [
     {file = "inflection-0.5.1-py2.py3-none-any.whl", hash = "sha256:f38b2b640938a4f35ade69ac3d053042959b62a0f1076a5bbaa1b9526605a8a2"},
     {file = "inflection-0.5.1.tar.gz", hash = "sha256:1a29730d366e996aaacffb2f1f1cb9593dc38e2ddd30c91250c6dde09ea9b417"},
@@ -2383,6 +2486,7 @@ version = "2.0.0"
 description = "brain-dead simple config-ini parsing"
 optional = false
 python-versions = ">=3.7"
+groups = ["dev", "pytest"]
 files = [
     {file = "iniconfig-2.0.0-py3-none-any.whl", hash = "sha256:b6a85871a79d2e3b22d2d1b94ac2824226a63c6b741c88f7ae975f18b6778374"},
     {file = "iniconfig-2.0.0.tar.gz", hash = "sha256:2d91e135bf72d31a410b17c16da610a82cb55f6b0477d1a902134b24a455b8b3"},
@@ -2394,6 +2498,7 @@ version = "0.6.1"
 description = "An ISO 8601 date/time/duration parser and formatter"
 optional = false
 python-versions = "*"
+groups = ["filesystem", "salesforce"]
 files = [
     {file = "isodate-0.6.1-py2.py3-none-any.whl", hash = "sha256:0751eece944162659049d35f4f549ed815792b38793f07cf73381c1c87cbed96"},
     {file = "isodate-0.6.1.tar.gz", hash = "sha256:48c5881de7e8b0a0d648cb024c8062dc84e7b840ed81e864c7614fd3c127bde9"},
@@ -2408,6 +2513,7 @@ version = "0.8.0"
 description = "Common interface for data container classes"
 optional = false
 python-versions = ">=3.7"
+groups = ["scrapy"]
 files = [
     {file = "itemadapter-0.8.0-py3-none-any.whl", hash = "sha256:2ac1fbcc363b789a18639935ca322e50a65a0a7dfdd8d973c34e2c468e6c0f94"},
     {file = "itemadapter-0.8.0.tar.gz", hash = "sha256:77758485fb0ac10730d4b131363e37d65cb8db2450bfec7a57c3f3271f4a48a9"},
@@ -2419,6 +2525,7 @@ version = "1.1.0"
 description = "Base library for scrapy's ItemLoader"
 optional = false
 python-versions = ">=3.7"
+groups = ["scrapy"]
 files = [
     {file = "itemloaders-1.1.0-py3-none-any.whl", hash = "sha256:c8c82fe0c11fc4cdd08ec04df0b3c43f3cb7190002edb517e02d55de8efc2aeb"},
     {file = "itemloaders-1.1.0.tar.gz", hash = "sha256:21d81c61da6a08b48e5996288cdf3031c0f92e5d0075920a0242527523e14a48"},
@@ -2436,6 +2543,7 @@ version = "1.0.1"
 description = "JSON Matching Expressions"
 optional = false
 python-versions = ">=3.7"
+groups = ["filesystem", "scrapy"]
 files = [
     {file = "jmespath-1.0.1-py3-none-any.whl", hash = "sha256:02e2e4cc71b5bcab88332eebf907519190dd9e6e82107fa7f83b1003a6252980"},
     {file = "jmespath-1.0.1.tar.gz", hash = "sha256:90261b206d6defd58fdd5e85f478bf633a2901798906be2ad389150c5c60edbe"},
@@ -2447,6 +2555,7 @@ version = "1.3.2"
 description = "Lightweight pipelining with Python functions"
 optional = false
 python-versions = ">=3.7"
+groups = ["unstructured_data"]
 files = [
     {file = "joblib-1.3.2-py3-none-any.whl", hash = "sha256:ef4331c65f239985f3f2220ecc87db222f08fd22097a3dd5698f693875f8cbb9"},
     {file = "joblib-1.3.2.tar.gz", hash = "sha256:92f865e621e17784e7955080b6d042489e3b8e294949cc44c6eac304f59772b1"},
@@ -2458,6 +2567,7 @@ version = "1.6.0"
 description = "A final implementation of JSONPath for Python that aims to be standard compliant, including arithmetic and binary comparison operators and providing clear AST for metaprogramming."
 optional = false
 python-versions = "*"
+groups = ["main", "dltpure"]
 files = [
     {file = "jsonpath-ng-1.6.0.tar.gz", hash = "sha256:5483f8e9d74c39c9abfab554c070ae783c1c8cbadf5df60d561bc705ac68a07e"},
     {file = "jsonpath_ng-1.6.0-py3-none-any.whl", hash = "sha256:6fd04833412c4b3d9299edf369542f5e67095ca84efa17cbb7f06a34958adc9f"},
@@ -2472,6 +2582,7 @@ version = "0.0.219"
 description = "Building applications with LLMs through composability"
 optional = false
 python-versions = ">=3.8.1,<4.0"
+groups = ["unstructured_data", "unstructured_data_lint"]
 files = [
     {file = "langchain-0.0.219-py3-none-any.whl", hash = "sha256:1f08a00e622f1c75087d6013f34e82be3f8dd1859266eb583a0fd7bc045090cf"},
     {file = "langchain-0.0.219.tar.gz", hash = "sha256:842f8212939e5ac4005906d2215574ffb3e34d2fe28f5bc0f46eb3b28fb29c5d"},
@@ -2511,6 +2622,7 @@ version = "0.0.20"
 description = "Client library to connect to the LangSmith LLM Tracing and Evaluation Platform."
 optional = false
 python-versions = ">=3.8.1,<4.0"
+groups = ["unstructured_data", "unstructured_data_lint"]
 files = [
     {file = "langchainplus_sdk-0.0.20-py3-none-any.whl", hash = "sha256:07a869d476755803aa04c4986ce78d00c2fe4ff584c0eaa57d7570c9664188db"},
     {file = "langchainplus_sdk-0.0.20.tar.gz", hash = "sha256:3d300e2e3290f68cc9d842c059f9458deba60e776c9e790309688cad1bfbb219"},
@@ -2527,6 +2639,7 @@ version = "4.9.3"
 description = "Powerful and Pythonic XML processing library combining libxml2/libxslt with the ElementTree API."
 optional = false
 python-versions = ">=2.7, !=3.0.*, !=3.1.*, !=3.2.*, !=3.3.*, != 3.4.*"
+groups = ["salesforce", "scrapy", "unstructured_data"]
 files = [
     {file = "lxml-4.9.3-cp27-cp27m-macosx_11_0_x86_64.whl", hash = "sha256:b0a545b46b526d418eb91754565ba5b63b1c0b12f9bd2f808c852d9b4b2f9b5c"},
     {file = "lxml-4.9.3-cp27-cp27m-manylinux_2_5_i686.manylinux1_i686.whl", hash = "sha256:075b731ddd9e7f68ad24c635374211376aa05a281673ede86cbe1d1b3455279d"},
@@ -2634,6 +2747,7 @@ version = "4.3.2"
 description = "LZ4 Bindings for Python"
 optional = false
 python-versions = ">=3.7"
+groups = ["unstructured_data"]
 files = [
     {file = "lz4-4.3.2-cp310-cp310-macosx_10_9_x86_64.whl", hash = "sha256:1c4c100d99eed7c08d4e8852dd11e7d1ec47a3340f49e3a96f8dfbba17ffb300"},
     {file = "lz4-4.3.2-cp310-cp310-macosx_11_0_arm64.whl", hash = "sha256:edd8987d8415b5dad25e797043936d91535017237f72fa456601be1479386c92"},
@@ -2683,6 +2797,7 @@ version = "1.15.1"
 description = "Small library to dynamically create python functions."
 optional = false
 python-versions = "*"
+groups = ["main", "dltpure"]
 files = [
     {file = "makefun-1.15.1-py2.py3-none-any.whl", hash = "sha256:a63cfc7b47a539c76d97bd4fdb833c7d0461e759fd1225f580cb4be6200294d4"},
     {file = "makefun-1.15.1.tar.gz", hash = "sha256:40b0f118b6ded0d8d78c78f1eb679b8b6b2462e3c1b3e05fb1b2da8cd46b48a5"},
@@ -2694,6 +2809,7 @@ version = "3.5"
 description = "Python implementation of John Gruber's Markdown."
 optional = false
 python-versions = ">=3.8"
+groups = ["unstructured_data"]
 files = [
     {file = "Markdown-3.5-py3-none-any.whl", hash = "sha256:4afb124395ce5fc34e6d9886dab977fd9ae987fc6e85689f08278cf0c69d4bf3"},
     {file = "Markdown-3.5.tar.gz", hash = "sha256:a807eb2e4778d9156c8f07876c6e4d50b5494c5665c4834f67b06459dfd877b3"},
@@ -2712,6 +2828,7 @@ version = "3.0.0"
 description = "Python port of markdown-it. Markdown parsing, done right!"
 optional = false
 python-versions = ">=3.8"
+groups = ["dev"]
 files = [
     {file = "markdown-it-py-3.0.0.tar.gz", hash = "sha256:e3f60a94fa066dc52ec76661e37c851cb232d92f9886b15cb560aaada2df8feb"},
     {file = "markdown_it_py-3.0.0-py3-none-any.whl", hash = "sha256:355216845c60bd96232cd8d8c40e8f9765cc86f46880e43a8fd22dc1a1a8cab1"},
@@ -2736,6 +2853,7 @@ version = "3.20.1"
 description = "A lightweight library for converting complex datatypes to and from native Python datatypes."
 optional = false
 python-versions = ">=3.8"
+groups = ["unstructured_data", "unstructured_data_lint"]
 files = [
     {file = "marshmallow-3.20.1-py3-none-any.whl", hash = "sha256:684939db93e80ad3561392f47be0230743131560a41c5110684c16e21ade0a5c"},
     {file = "marshmallow-3.20.1.tar.gz", hash = "sha256:5d2371bbe42000f2b3fb5eaa065224df7d8f8597bc19a1bbfa5bfe7fba8da889"},
@@ -2756,6 +2874,7 @@ version = "1.5.1"
 description = "Enum field for Marshmallow"
 optional = false
 python-versions = "*"
+groups = ["unstructured_data", "unstructured_data_lint"]
 files = [
     {file = "marshmallow-enum-1.5.1.tar.gz", hash = "sha256:38e697e11f45a8e64b4a1e664000897c659b60aa57bfa18d44e226a9920b6e58"},
     {file = "marshmallow_enum-1.5.1-py2.py3-none-any.whl", hash = "sha256:57161ab3dbfde4f57adeb12090f39592e992b9c86d206d02f6bd03ebec60f072"},
@@ -2770,6 +2889,7 @@ version = "0.7.0"
 description = "McCabe checker, plugin for flake8"
 optional = false
 python-versions = ">=3.6"
+groups = ["dev"]
 files = [
     {file = "mccabe-0.7.0-py2.py3-none-any.whl", hash = "sha256:6c2d30ab6be0e4a46919781807b4f0d834ebdd6c6e3dca0bda5a15f863427b6e"},
     {file = "mccabe-0.7.0.tar.gz", hash = "sha256:348e0240c33b60bbdf4e523192ef919f28cb2c3d7d5c7794f74009290f236325"},
@@ -2781,6 +2901,7 @@ version = "0.1.2"
 description = "Markdown URL utilities"
 optional = false
 python-versions = ">=3.7"
+groups = ["dev"]
 files = [
     {file = "mdurl-0.1.2-py3-none-any.whl", hash = "sha256:84008a41e51615a49fc9966191ff91509e3c40b939176e643fd50a5c2196b8f8"},
     {file = "mdurl-0.1.2.tar.gz", hash = "sha256:bb413d29f5eea38f31dd4754dd7377d4465116fb207585f97bf925588687c1ba"},
@@ -2792,6 +2913,7 @@ version = "7.1.0"
 description = "Mimesis: Fake Data Generator."
 optional = false
 python-versions = ">=3.8,<4.0"
+groups = ["dev"]
 files = [
     {file = "mimesis-7.1.0-py3-none-any.whl", hash = "sha256:da65bea6d6d5d5d87d5c008e6b23ef5f96a49cce436d9f8708dabb5152da0290"},
     {file = "mimesis-7.1.0.tar.gz", hash = "sha256:c83b55d35536d7e9b9700a596b7ccfb639a740e3e1fb5e08062e8ab2a67dcb37"},
@@ -2803,6 +2925,7 @@ version = "1.6"
 description = "An implementation of time.monotonic() for Python 2 & < 3.3"
 optional = false
 python-versions = "*"
+groups = ["unstructured_data"]
 files = [
     {file = "monotonic-1.6-py2.py3-none-any.whl", hash = "sha256:68687e19a14f11f26d140dd5c86f3dba4bf5df58003000ed467e0e2a69bca96c"},
     {file = "monotonic-1.6.tar.gz", hash = "sha256:3a55207bcfed53ddd5c5bae174524062935efed17792e9de2ad0205ce9ad63f7"},
@@ -2814,6 +2937,7 @@ version = "10.1.0"
 description = "More routines for operating on iterables, beyond itertools"
 optional = false
 python-versions = ">=3.8"
+groups = ["salesforce"]
 files = [
     {file = "more-itertools-10.1.0.tar.gz", hash = "sha256:626c369fa0eb37bac0291bce8259b332fd59ac792fa5497b59837309cd5b114a"},
     {file = "more_itertools-10.1.0-py3-none-any.whl", hash = "sha256:64e0735fcfdc6f3464ea133afe8ea4483b1c5fe3a3d69852e6503b43a0b222e6"},
@@ -2825,6 +2949,7 @@ version = "1.3.0"
 description = "Python library for arbitrary-precision floating-point arithmetic"
 optional = false
 python-versions = "*"
+groups = ["unstructured_data"]
 files = [
     {file = "mpmath-1.3.0-py3-none-any.whl", hash = "sha256:a0b2b9fe80bbcd81a6647ff13108738cfb482d481d826cc0e02f5b35e5c88d2c"},
     {file = "mpmath-1.3.0.tar.gz", hash = "sha256:7a28eb2a9774d00c7bc92411c19a89209d5da7c4c9a9e227be8330a23a25b91f"},
@@ -2842,6 +2967,7 @@ version = "1.24.1"
 description = "The Microsoft Authentication Library (MSAL) for Python library"
 optional = false
 python-versions = ">=2.7"
+groups = ["filesystem"]
 files = [
     {file = "msal-1.24.1-py2.py3-none-any.whl", hash = "sha256:ce4320688f95c301ee74a4d0e9dbcfe029a63663a8cc61756f40d0d0d36574ad"},
     {file = "msal-1.24.1.tar.gz", hash = "sha256:aa0972884b3c6fdec53d9a0bd15c12e5bd7b71ac1b66d746f54d128709f3f8f8"},
@@ -2861,6 +2987,7 @@ version = "1.0.0"
 description = "Microsoft Authentication Library extensions (MSAL EX) provides a persistence API that can save your data on disk, encrypted on Windows, macOS and Linux. Concurrent data access will be coordinated by a file lock mechanism."
 optional = false
 python-versions = "*"
+groups = ["filesystem"]
 files = [
     {file = "msal-extensions-1.0.0.tar.gz", hash = "sha256:c676aba56b0cce3783de1b5c5ecfe828db998167875126ca4b47dc6436451354"},
     {file = "msal_extensions-1.0.0-py2.py3-none-any.whl", hash = "sha256:91e3db9620b822d0ed2b4d1850056a0f133cba04455e62f11612e40f5502f2ee"},
@@ -2879,6 +3006,7 @@ version = "1.2.0"
 description = "This module enables reading, parsing and converting Microsoft Outlook MSG E-Mail files."
 optional = false
 python-versions = ">=3.4"
+groups = ["unstructured_data"]
 files = [
     {file = "msg_parser-1.2.0-py2.py3-none-any.whl", hash = "sha256:d47a2f0b2a359cb189fad83cc991b63ea781ecc70d91410324273fbf93e95375"},
     {file = "msg_parser-1.2.0.tar.gz", hash = "sha256:0de858d4fcebb6c8f6f028da83a17a20fe01cdce67c490779cf43b3b0162aa66"},
@@ -2896,6 +3024,7 @@ version = "6.0.4"
 description = "multidict implementation"
 optional = false
 python-versions = ">=3.7"
+groups = ["main", "facebook_ads", "filesystem", "unstructured_data", "unstructured_data_lint"]
 files = [
     {file = "multidict-6.0.4-cp310-cp310-macosx_10_9_universal2.whl", hash = "sha256:0b1a97283e0c85772d613878028fec909f003993e1007eafa715b24b377cb9b8"},
     {file = "multidict-6.0.4-cp310-cp310-macosx_10_9_x86_64.whl", hash = "sha256:eeb6dcc05e911516ae3d1f207d4b0520d07f54484c49dfc294d6e7d63b734171"},
@@ -2979,6 +3108,7 @@ version = "1.10.0"
 description = "Optional static typing for Python"
 optional = false
 python-versions = ">=3.8"
+groups = ["dev"]
 files = [
     {file = "mypy-1.10.0-cp310-cp310-macosx_10_9_x86_64.whl", hash = "sha256:da1cbf08fb3b851ab3b9523a884c232774008267b1f83371ace57f412fe308c2"},
     {file = "mypy-1.10.0-cp310-cp310-macosx_11_0_arm64.whl", hash = "sha256:12b6bfc1b1a66095ab413160a6e520e1dc076a28f3e22f7fb25ba3b000b4ef99"},
@@ -3026,6 +3156,7 @@ version = "1.0.0"
 description = "Type system extensions for programs checked with the mypy type checker."
 optional = false
 python-versions = ">=3.5"
+groups = ["dev", "unstructured_data", "unstructured_data_lint"]
 files = [
     {file = "mypy_extensions-1.0.0-py3-none-any.whl", hash = "sha256:4392f6c0eb8a5668a69e23d168ffa70f0be9ccfd32b5cc2d26a34ae5b844552d"},
     {file = "mypy_extensions-1.0.0.tar.gz", hash = "sha256:75dbf8955dc00442a438fc4d0666508a9a97b6bd41aa2f0ffe9d2f2725af0782"},
@@ -3037,6 +3168,7 @@ version = "8.4.0"
 description = "Simple yet flexible natural sorting in Python."
 optional = false
 python-versions = ">=3.7"
+groups = ["dev"]
 files = [
     {file = "natsort-8.4.0-py3-none-any.whl", hash = "sha256:4732914fb471f56b5cce04d7bae6f164a592c7712e1c85f9ef585e197299521c"},
     {file = "natsort-8.4.0.tar.gz", hash = "sha256:45312c4a0e5507593da193dedd04abb1469253b601ecaf63445ad80f0a1ea581"},
@@ -3052,6 +3184,7 @@ version = "3.8.1"
 description = "Natural Language Toolkit"
 optional = false
 python-versions = ">=3.7"
+groups = ["unstructured_data"]
 files = [
     {file = "nltk-3.8.1-py3-none-any.whl", hash = "sha256:fd5c9109f976fa86bcadba8f91e47f5e9293bd034474752e92a520f81c93dda5"},
     {file = "nltk-3.8.1.zip", hash = "sha256:1834da3d0682cba4f2cede2f9aad6b0fafb6461ba451db0efb6f9c39798d64d3"},
@@ -3077,6 +3210,7 @@ version = "2.8.6"
 description = "Fast numerical expression evaluator for NumPy"
 optional = false
 python-versions = ">=3.7"
+groups = ["unstructured_data", "unstructured_data_lint"]
 files = [
     {file = "numexpr-2.8.6-cp310-cp310-macosx_10_9_x86_64.whl", hash = "sha256:80acbfefb68bd92e708e09f0a02b29e04d388b9ae72f9fcd57988aca172a7833"},
     {file = "numexpr-2.8.6-cp310-cp310-macosx_11_0_arm64.whl", hash = "sha256:6e884687da8af5955dc9beb6a12d469675c90b8fb38b6c93668c989cfc2cd982"},
@@ -3119,6 +3253,7 @@ version = "1.24.4"
 description = "Fundamental package for array computing in Python"
 optional = false
 python-versions = ">=3.8"
+groups = ["main", "dev", "mongodb", "stripe_analytics", "unstructured_data", "unstructured_data_lint"]
 files = [
     {file = "numpy-1.24.4-cp310-cp310-macosx_10_9_x86_64.whl", hash = "sha256:c0bfb52d2169d58c1cdb8cc1f16989101639b34c7d3ce60ed70b19c63eba0b64"},
     {file = "numpy-1.24.4-cp310-cp310-macosx_11_0_arm64.whl", hash = "sha256:ed094d4f0c177b1b8e7aa9cba7d6ceed51c0e569a5318ac0ca9a090680a6a1b1"},
@@ -3156,6 +3291,7 @@ version = "3.2.2"
 description = "A generic, spec-compliant, thorough implementation of the OAuth request-signing logic"
 optional = false
 python-versions = ">=3.6"
+groups = ["main", "asana_dlt", "filesystem", "google_ads", "google_analytics"]
 files = [
     {file = "oauthlib-3.2.2-py3-none-any.whl", hash = "sha256:8139f29aac13e25d502680e9e19963e83f16838d48a0d71c287fe40e7067fbca"},
     {file = "oauthlib-3.2.2.tar.gz", hash = "sha256:9859c40929662bec5d64f34d01c99e093149682a3f38915dc0655d5a633dd918"},
@@ -3172,6 +3308,7 @@ version = "0.46"
 description = "Python package to parse, read and write Microsoft OLE2 files (Structured Storage or Compound Document, Microsoft Office)"
 optional = false
 python-versions = ">=2.7, !=3.0.*, !=3.1.*, !=3.2.*, !=3.3.*"
+groups = ["unstructured_data"]
 files = [
     {file = "olefile-0.46.zip", hash = "sha256:133b031eaf8fd2c9399b78b8bc5b8fcbe4c31e85295749bb17a87cba8f3c3964"},
 ]
@@ -3182,6 +3319,7 @@ version = "1.16.1"
 description = "ONNX Runtime is a runtime accelerator for Machine Learning models"
 optional = false
 python-versions = "*"
+groups = ["unstructured_data"]
 files = [
     {file = "onnxruntime-1.16.1-cp310-cp310-macosx_10_15_x86_64.whl", hash = "sha256:28b2c7f444b4119950b69370801cd66067f403d19cbaf2a444735d7c269cce4a"},
     {file = "onnxruntime-1.16.1-cp310-cp310-macosx_11_0_arm64.whl", hash = "sha256:c24e04f33e7899f6aebb03ed51e51d346c1f906b05c5569d58ac9a12d38a2f58"},
@@ -3223,6 +3361,7 @@ version = "0.27.10"
 description = "Python client library for the OpenAI API"
 optional = false
 python-versions = ">=3.7.1"
+groups = ["unstructured_data", "unstructured_data_lint"]
 files = [
     {file = "openai-0.27.10-py3-none-any.whl", hash = "sha256:beabd1757e3286fa166dde3b70ebb5ad8081af046876b47c14c41e203ed22a14"},
     {file = "openai-0.27.10.tar.gz", hash = "sha256:60e09edf7100080283688748c6803b7b3b52d5a55d21890f3815292a0552d83b"},
@@ -3245,6 +3384,7 @@ version = "1.2.4"
 description = "OpenAPI (v3) specification schema as pydantic class"
 optional = false
 python-versions = ">=3.6.1"
+groups = ["unstructured_data", "unstructured_data_lint"]
 files = [
     {file = "openapi-schema-pydantic-1.2.4.tar.gz", hash = "sha256:3e22cf58b74a69f752cc7e5f1537f6e44164282db2700cbbcd3bb99ddd065196"},
     {file = "openapi_schema_pydantic-1.2.4-py3-none-any.whl", hash = "sha256:a932ecc5dcbb308950282088956e94dea069c9823c84e507d64f6b622222098c"},
@@ -3259,6 +3399,7 @@ version = "3.1.2"
 description = "A Python library to read/write Excel 2010 xlsx/xlsm files"
 optional = false
 python-versions = ">=3.6"
+groups = ["unstructured_data"]
 files = [
     {file = "openpyxl-3.1.2-py2.py3-none-any.whl", hash = "sha256:f91456ead12ab3c6c2e9491cf33ba6d08357d802192379bb482f1033ade496f5"},
     {file = "openpyxl-3.1.2.tar.gz", hash = "sha256:a6f5977418eff3b2d5500d54d9db50c8277a368436f4e4f8ddb1be3422870184"},
@@ -3273,6 +3414,8 @@ version = "3.9.9"
 description = "Fast, correct Python JSON library supporting dataclasses, datetimes, and numpy"
 optional = false
 python-versions = ">=3.8"
+groups = ["main", "dltpure"]
+markers = "platform_python_implementation != \"PyPy\""
 files = [
     {file = "orjson-3.9.9-cp310-cp310-macosx_10_15_x86_64.macosx_11_0_arm64.macosx_10_15_universal2.whl", hash = "sha256:f28090060a31f4d11221f9ba48b2273b0d04b702f4dcaa197c38c64ce639cc51"},
     {file = "orjson-3.9.9-cp310-cp310-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:8038ba245d0c0a6337cfb6747ea0c51fe18b0cf1a4bc943d530fd66799fae33d"},
@@ -3332,6 +3475,7 @@ version = "7.4.0"
 description = "A decorator to automatically detect mismatch when overriding a method."
 optional = false
 python-versions = ">=3.6"
+groups = ["unstructured_data"]
 files = [
     {file = "overrides-7.4.0-py3-none-any.whl", hash = "sha256:3ad24583f86d6d7a49049695efe9933e67ba62f0c7625d53c59fa832ce4b8b7d"},
     {file = "overrides-7.4.0.tar.gz", hash = "sha256:9502a3cca51f4fac40b5feca985b6703a5c1f6ad815588a7ca9e285b9dca6757"},
@@ -3343,6 +3487,7 @@ version = "23.2"
 description = "Core utilities for Python packages"
 optional = false
 python-versions = ">=3.7"
+groups = ["main", "dev", "dltpure", "mongodb", "pytest", "scrapy", "unstructured_data", "unstructured_data_lint"]
 files = [
     {file = "packaging-23.2-py3-none-any.whl", hash = "sha256:8c491190033a9af7e1d931d0b5dacc2ef47509b34dd0de67ed209b5203fc88c7"},
     {file = "packaging-23.2.tar.gz", hash = "sha256:048fb0e9405036518eaaf48a55953c750c11e1a1b68e0dd1a9d62ed0c092cfc5"},
@@ -3354,6 +3499,7 @@ version = "2.0.3"
 description = "Powerful data structures for data analysis, time series, and statistics"
 optional = false
 python-versions = ">=3.8"
+groups = ["main", "mongodb", "stripe_analytics", "unstructured_data"]
 files = [
     {file = "pandas-2.0.3-cp310-cp310-macosx_10_9_x86_64.whl", hash = "sha256:e4c7c9f27a4185304c7caf96dc7d91bc60bc162221152de697c98eb0b2648dd8"},
     {file = "pandas-2.0.3-cp310-cp310-macosx_11_0_arm64.whl", hash = "sha256:f167beed68918d62bffb6ec64f2e1d8a7d297a038f86d4aed056b9493fca407f"},
@@ -3421,6 +3567,7 @@ version = "2.0.2.230605"
 description = "Type annotations for pandas"
 optional = false
 python-versions = ">=3.8"
+groups = ["dev"]
 files = [
     {file = "pandas_stubs-2.0.2.230605-py3-none-any.whl", hash = "sha256:39106b602f3cb6dc5f728b84e1b32bde6ecf41ee34ee714c66228009609fbada"},
     {file = "pandas_stubs-2.0.2.230605.tar.gz", hash = "sha256:624c7bb06d38145a44b61be459ccd19b038e0bf20364a025ecaab78fea65e858"},
@@ -3436,6 +3583,7 @@ version = "1.8.1"
 description = "Parsel is a library to extract data from HTML and XML using XPath and CSS selectors"
 optional = false
 python-versions = ">=3.7"
+groups = ["scrapy"]
 files = [
     {file = "parsel-1.8.1-py2.py3-none-any.whl", hash = "sha256:2708fc74daeeb4ce471e2c2e9089b650ec940c7a218053e57421e69b5b00f82c"},
     {file = "parsel-1.8.1.tar.gz", hash = "sha256:aff28e68c9b3f1a901db2a4e3f158d8480a38724d7328ee751c1a4e1c1801e39"},
@@ -3454,6 +3602,7 @@ version = "0.11.2"
 description = "Utility library for gitignore style pattern matching of file paths."
 optional = false
 python-versions = ">=3.7"
+groups = ["dev"]
 files = [
     {file = "pathspec-0.11.2-py3-none-any.whl", hash = "sha256:1d6ed233af05e679efb96b1851550ea95bbb64b7c490b0f5aa52996c11e92a20"},
     {file = "pathspec-0.11.2.tar.gz", hash = "sha256:e0d8d0ac2f12da61956eb2306b69f9469b42f4deb0f3cb6ed47b9cce9996ced3"},
@@ -3465,6 +3614,7 @@ version = "3.2.0"
 description = "pathvalidate is a Python library to sanitize/validate a string such as filenames/file-paths/etc."
 optional = false
 python-versions = ">=3.7"
+groups = ["main", "dltpure"]
 files = [
     {file = "pathvalidate-3.2.0-py3-none-any.whl", hash = "sha256:cc593caa6299b22b37f228148257997e2fa850eea2daf7e4cc9205cef6908dee"},
     {file = "pathvalidate-3.2.0.tar.gz", hash = "sha256:5e8378cf6712bff67fbe7a8307d99fa8c1a0cb28aa477056f8fc374f0dff24ad"},
@@ -3480,6 +3630,7 @@ version = "5.11.1"
 description = "Python Build Reasonableness"
 optional = false
 python-versions = ">=2.6"
+groups = ["dev"]
 files = [
     {file = "pbr-5.11.1-py2.py3-none-any.whl", hash = "sha256:567f09558bae2b3ab53cb3c1e2e33e726ff3338e7bae3db5dc954b3a44eef12b"},
     {file = "pbr-5.11.1.tar.gz", hash = "sha256:aefc51675b0b533d56bb5fd1c8c6c0522fe31896679882e1c4c63d5e4a0fccb3"},
@@ -3491,6 +3642,7 @@ version = "1.16.3"
 description = "A wrapper around the pdftoppm and pdftocairo command line tools to convert PDF to a PIL Image list."
 optional = false
 python-versions = "*"
+groups = ["unstructured_data"]
 files = [
     {file = "pdf2image-1.16.3-py3-none-any.whl", hash = "sha256:b6154164af3677211c22cbb38b2bd778b43aca02758e962fe1e231f6d3b0e380"},
     {file = "pdf2image-1.16.3.tar.gz", hash = "sha256:74208810c2cef4d9e347769b8e62a52303982ddb4f2dfd744c7ab4b940ae287e"},
@@ -3505,6 +3657,7 @@ version = "20221105"
 description = "PDF parser and analyzer"
 optional = false
 python-versions = ">=3.6"
+groups = ["unstructured_data"]
 files = [
     {file = "pdfminer.six-20221105-py3-none-any.whl", hash = "sha256:1eaddd712d5b2732f8ac8486824533514f8ba12a0787b3d5fe1e686cd826532d"},
     {file = "pdfminer.six-20221105.tar.gz", hash = "sha256:8448ab7b939d18b64820478ecac5394f482d7a79f5f7eaa7703c6c959c175e1d"},
@@ -3525,6 +3678,7 @@ version = "3.0.0"
 description = "Python datetimes made easy"
 optional = false
 python-versions = ">=3.8"
+groups = ["main", "dev", "dltpure", "salesforce"]
 files = [
     {file = "pendulum-3.0.0-cp310-cp310-macosx_10_12_x86_64.whl", hash = "sha256:2cf9e53ef11668e07f73190c805dbdf07a1939c3298b78d5a9203a86775d1bfd"},
     {file = "pendulum-3.0.0-cp310-cp310-macosx_11_0_arm64.whl", hash = "sha256:fb551b9b5e6059377889d2d878d940fd0bbb80ae4810543db18e6f77b02c5ef6"},
@@ -3626,6 +3780,7 @@ version = "9.5.0"
 description = "Python Imaging Library (Fork)"
 optional = false
 python-versions = ">=3.7"
+groups = ["unstructured_data"]
 files = [
     {file = "Pillow-9.5.0-cp310-cp310-macosx_10_10_x86_64.whl", hash = "sha256:ace6ca218308447b9077c14ea4ef381ba0b67ee78d64046b3f19cf4e1139ad16"},
     {file = "Pillow-9.5.0-cp310-cp310-macosx_11_0_arm64.whl", hash = "sha256:d3d403753c9d5adc04d4694d35cf0391f0f3d57c8e0030aac09d7678fa8030aa"},
@@ -3705,6 +3860,7 @@ version = "3.11.0"
 description = "A small Python package for determining appropriate platform-specific dirs, e.g. a \"user data dir\"."
 optional = false
 python-versions = ">=3.7"
+groups = ["dev", "salesforce"]
 files = [
     {file = "platformdirs-3.11.0-py3-none-any.whl", hash = "sha256:e9d171d00af68be50e9202731309c4e658fd8bc76f55c11c7dd760d023bda68e"},
     {file = "platformdirs-3.11.0.tar.gz", hash = "sha256:cf8ee52a3afdb965072dcc652433e0c7e3e40cf5ea1477cd4b3b1d2eb75495b3"},
@@ -3720,6 +3876,7 @@ version = "1.3.0"
 description = "plugin and hook calling mechanisms for python"
 optional = false
 python-versions = ">=3.8"
+groups = ["main", "dev", "dltpure", "pytest"]
 files = [
     {file = "pluggy-1.3.0-py3-none-any.whl", hash = "sha256:d89c696a773f8bd377d18e5ecda92b7a3793cbe66c87060a6fb58c7b6e1061f7"},
     {file = "pluggy-1.3.0.tar.gz", hash = "sha256:cf61ae8f126ac6f7c451172cf30e3e43d3ca77615509771b3a984a0730651e12"},
@@ -3735,6 +3892,7 @@ version = "3.11"
 description = "Python Lex & Yacc"
 optional = false
 python-versions = "*"
+groups = ["main", "dltpure"]
 files = [
     {file = "ply-3.11-py2.py3-none-any.whl", hash = "sha256:096f9b8350b65ebd2fd1346b12452efe5b9607f7482813ffca50c22722a807ce"},
     {file = "ply-3.11.tar.gz", hash = "sha256:00c7c1aaa88358b9c765b6d3000c6eec0ba42abca5351b095321aef446081da3"},
@@ -3746,6 +3904,7 @@ version = "2.8.2"
 description = "Wraps the portalocker recipe for easy usage"
 optional = false
 python-versions = ">=3.8"
+groups = ["filesystem"]
 files = [
     {file = "portalocker-2.8.2-py3-none-any.whl", hash = "sha256:cfb86acc09b9aa7c3b43594e19be1345b9d16af3feb08bf92f23d4dce513a28e"},
     {file = "portalocker-2.8.2.tar.gz", hash = "sha256:2b035aa7828e46c58e9b31390ee1f169b98e1066ab10b9a6a861fe7e25ee4f33"},
@@ -3765,6 +3924,7 @@ version = "3.0.2"
 description = "Integrate PostHog into any python application."
 optional = false
 python-versions = "*"
+groups = ["unstructured_data"]
 files = [
     {file = "posthog-3.0.2-py2.py3-none-any.whl", hash = "sha256:a8c0af6f2401fbe50f90e68c4143d0824b54e872de036b1c2f23b5abb39d88ce"},
     {file = "posthog-3.0.2.tar.gz", hash = "sha256:701fba6e446a4de687c6e861b587e7b7741955ad624bf34fe013c06a0fec6fb3"},
@@ -3788,6 +3948,7 @@ version = "0.3.0"
 description = "Pure-Python robots.txt parser with support for modern conventions"
 optional = false
 python-versions = ">=3.7"
+groups = ["scrapy"]
 files = [
     {file = "Protego-0.3.0-py2.py3-none-any.whl", hash = "sha256:db38f6a945839d8162a4034031a21490469566a2726afb51d668497c457fb0aa"},
     {file = "Protego-0.3.0.tar.gz", hash = "sha256:04228bffde4c6bcba31cf6529ba2cfd6e1b70808fdc1d2cb4301be6b28d6c568"},
@@ -3799,6 +3960,7 @@ version = "1.22.3"
 description = "Beautiful, Pythonic protocol buffers."
 optional = false
 python-versions = ">=3.6"
+groups = ["google_ads", "google_analytics"]
 files = [
     {file = "proto-plus-1.22.3.tar.gz", hash = "sha256:fdcd09713cbd42480740d2fe29c990f7fbd885a67efc328aa8be6ee3e9f76a6b"},
     {file = "proto_plus-1.22.3-py3-none-any.whl", hash = "sha256:a49cd903bc0b6ab41f76bf65510439d56ca76f868adf0274e738bfdd096894df"},
@@ -3816,6 +3978,7 @@ version = "4.24.4"
 description = ""
 optional = false
 python-versions = ">=3.7"
+groups = ["main", "filesystem", "google_ads", "google_analytics", "google_sheets", "unstructured_data"]
 files = [
     {file = "protobuf-4.24.4-cp310-abi3-win32.whl", hash = "sha256:ec9912d5cb6714a5710e28e592ee1093d68c5ebfeda61983b3f40331da0b1ebb"},
     {file = "protobuf-4.24.4-cp310-abi3-win_amd64.whl", hash = "sha256:1badab72aa8a3a2b812eacfede5020472e16c6b2212d737cefd685884c191085"},
@@ -3838,6 +4001,7 @@ version = "2.9.9"
 description = "psycopg2 - Python-PostgreSQL Database Adapter"
 optional = false
 python-versions = ">=3.7"
+groups = ["main", "pg_replication"]
 files = [
     {file = "psycopg2-binary-2.9.9.tar.gz", hash = "sha256:7f01846810177d829c7692f1f5ada8096762d9172af1b1a28d4ab5b77c923c1c"},
     {file = "psycopg2_binary-2.9.9-cp310-cp310-macosx_10_9_x86_64.whl", hash = "sha256:c2470da5418b76232f02a2fcd2229537bb2d5a7096674ce61859c3229f2eb202"},
@@ -3919,6 +4083,8 @@ version = "2.9.0"
 description = ".. image:: https://travis-ci.org/chtd/psycopg2cffi.svg?branch=master"
 optional = false
 python-versions = "*"
+groups = ["main"]
+markers = "platform_python_implementation == \"PyPy\""
 files = [
     {file = "psycopg2cffi-2.9.0.tar.gz", hash = "sha256:7e272edcd837de3a1d12b62185eb85c45a19feda9e62fa1b120c54f9e8d35c52"},
 ]
@@ -3933,6 +4099,7 @@ version = "3.3.0"
 description = "Apache Pulsar Python client library"
 optional = false
 python-versions = "*"
+groups = ["unstructured_data"]
 files = [
     {file = "pulsar_client-3.3.0-cp310-cp310-macosx_10_15_universal2.whl", hash = "sha256:c31afd3e67a044ff93177df89e08febf214cc965e95ede097d9fe8755af00e01"},
     {file = "pulsar_client-3.3.0-cp310-cp310-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:1f66982284571674b215324cc26b5c2f7c56c7043113c47a7084cb70d67a8afb"},
@@ -3980,6 +4147,7 @@ version = "1.11.0"
 description = "library with cross-python path, ini-parsing, io, code, log facilities"
 optional = false
 python-versions = ">=2.7, !=3.0.*, !=3.1.*, !=3.2.*, !=3.3.*, !=3.4.*"
+groups = ["dev", "pytest"]
 files = [
     {file = "py-1.11.0-py2.py3-none-any.whl", hash = "sha256:607c53218732647dff4acdfcd50cb62615cedf612e72d1724fb1a0cc6405b378"},
     {file = "py-1.11.0.tar.gz", hash = "sha256:51c75c4126074b472f746a24399ad32f6053d1b34b68d2fa41e558e6f4a98719"},
@@ -3991,6 +4159,7 @@ version = "2.1.0.post1"
 description = "Python Client for the Airtable API"
 optional = false
 python-versions = "*"
+groups = ["airtable"]
 files = [
     {file = "pyairtable-2.1.0.post1-py2.py3-none-any.whl", hash = "sha256:a80eb85f7c020bf41679bb00ca57da11aeaa43769afbc73619276798a2ca182e"},
     {file = "pyairtable-2.1.0.post1.tar.gz", hash = "sha256:e588249e68cf338dcdca9908537ed16d5a22ae72345ec930022b230ba96e5f84"},
@@ -4009,6 +4178,7 @@ version = "16.0.0"
 description = "Python library for Apache Arrow"
 optional = false
 python-versions = ">=3.8"
+groups = ["main", "mongodb"]
 files = [
     {file = "pyarrow-16.0.0-cp310-cp310-macosx_10_15_x86_64.whl", hash = "sha256:22a1fdb1254e5095d629e29cd1ea98ed04b4bbfd8e42cc670a6b639ccc208b60"},
     {file = "pyarrow-16.0.0-cp310-cp310-macosx_11_0_arm64.whl", hash = "sha256:574a00260a4ed9d118a14770edbd440b848fcae5a3024128be9d0274dbcaf858"},
@@ -4057,6 +4227,7 @@ version = "0.5.0"
 description = "Pure-Python implementation of ASN.1 types and DER/BER/CER codecs (X.208)"
 optional = false
 python-versions = "!=3.0.*,!=3.1.*,!=3.2.*,!=3.3.*,!=3.4.*,!=3.5.*,>=2.7"
+groups = ["main", "filesystem", "google_ads", "google_analytics", "google_sheets", "scrapy"]
 files = [
     {file = "pyasn1-0.5.0-py2.py3-none-any.whl", hash = "sha256:87a2121042a1ac9358cabcaf1d07680ff97ee6404333bacca15f76aa8ad01a57"},
     {file = "pyasn1-0.5.0.tar.gz", hash = "sha256:97b7290ca68e62a832558ec3976f15cbf911bf5d7c7039d8b861c2a0ece69fde"},
@@ -4068,6 +4239,7 @@ version = "0.3.0"
 description = "A collection of ASN.1-based protocols modules"
 optional = false
 python-versions = "!=3.0.*,!=3.1.*,!=3.2.*,!=3.3.*,!=3.4.*,!=3.5.*,>=2.7"
+groups = ["main", "filesystem", "google_ads", "google_analytics", "google_sheets", "scrapy"]
 files = [
     {file = "pyasn1_modules-0.3.0-py2.py3-none-any.whl", hash = "sha256:d3ccd6ed470d9ffbc716be08bd90efbd44d0734bc9303818f7336070984a162d"},
     {file = "pyasn1_modules-0.3.0.tar.gz", hash = "sha256:5bd01446b736eb9d31512a30d46c1ac3395d676c6f3cafa4c03eb54b9925631c"},
@@ -4082,6 +4254,7 @@ version = "2.11.1"
 description = "Python style guide checker"
 optional = false
 python-versions = ">=3.8"
+groups = ["dev"]
 files = [
     {file = "pycodestyle-2.11.1-py2.py3-none-any.whl", hash = "sha256:44fe31000b2d866f2e41841b18528a505fbd7fef9017b04eff4e2648a0fadc67"},
     {file = "pycodestyle-2.11.1.tar.gz", hash = "sha256:41ba0e7afc9752dfb53ced5489e89f8186be00e599e712660695b7a75ff2663f"},
@@ -4093,6 +4266,7 @@ version = "22.3.5"
 description = "ISO country, subdivision, language, currency and script definitions and their translations"
 optional = false
 python-versions = ">=3.6, <4"
+groups = ["facebook_ads"]
 files = [
     {file = "pycountry-22.3.5.tar.gz", hash = "sha256:b2163a246c585894d808f18783e19137cb70a0c18fb36748dc01fc6f109c1646"},
 ]
@@ -4106,10 +4280,12 @@ version = "2.21"
 description = "C parser in Python"
 optional = false
 python-versions = ">=2.7, !=3.0.*, !=3.1.*, !=3.2.*, !=3.3.*"
+groups = ["main", "filesystem", "salesforce", "scrapy", "unstructured_data"]
 files = [
     {file = "pycparser-2.21-py2.py3-none-any.whl", hash = "sha256:8ee45429555515e1f6b185e78100aea234072576aa43ab53aefcae078162fca9"},
     {file = "pycparser-2.21.tar.gz", hash = "sha256:e644fdec12f7872f86c58ff790da456218b10f863970249516d60a5eaca77206"},
 ]
+markers = {main = "platform_python_implementation == \"PyPy\""}
 
 [[package]]
 name = "pydantic"
@@ -4117,6 +4293,7 @@ version = "1.10.13"
 description = "Data validation and settings management using python type hints"
 optional = false
 python-versions = ">=3.7"
+groups = ["airtable", "unstructured_data", "unstructured_data_lint"]
 files = [
     {file = "pydantic-1.10.13-cp310-cp310-macosx_10_9_x86_64.whl", hash = "sha256:efff03cc7a4f29d9009d1c96ceb1e7a70a65cfe86e89d34e4a5f2ab1e5693737"},
     {file = "pydantic-1.10.13-cp310-cp310-macosx_11_0_arm64.whl", hash = "sha256:3ecea2b9d80e5333303eeb77e180b90e95eea8f765d08c3d278cd56b00345d01"},
@@ -4169,6 +4346,8 @@ version = "2.0.7"
 description = "Multi-producer multi-consumer in-memory signal dispatch system"
 optional = false
 python-versions = "*"
+groups = ["scrapy"]
+markers = "platform_python_implementation == \"CPython\""
 files = [
     {file = "PyDispatcher-2.0.7-py3-none-any.whl", hash = "sha256:96543bea04115ffde08f851e1d45cacbfd1ee866ac42127d9b476dc5aefa7de0"},
     {file = "PyDispatcher-2.0.7.tar.gz", hash = "sha256:b777c6ad080dc1bad74a4c29d6a46914fa6701ac70f94b0d66fbcfde62f5be31"},
@@ -4183,6 +4362,7 @@ version = "3.1.0"
 description = "passive checker of Python programs"
 optional = false
 python-versions = ">=3.8"
+groups = ["dev"]
 files = [
     {file = "pyflakes-3.1.0-py2.py3-none-any.whl", hash = "sha256:4132f6d49cb4dae6819e5379898f2b8cce3c5f23994194c24b77d5da2e36f774"},
     {file = "pyflakes-3.1.0.tar.gz", hash = "sha256:a0aae034c444db0071aa077972ba4768d40c830d9539fd45bf4cd3f8f6992efc"},
@@ -4194,6 +4374,7 @@ version = "2.16.1"
 description = "Pygments is a syntax highlighting package written in Python."
 optional = false
 python-versions = ">=3.7"
+groups = ["dev"]
 files = [
     {file = "Pygments-2.16.1-py3-none-any.whl", hash = "sha256:13fc09fa63bc8d8671a6d247e1eb303c4b343eaee81d861f3404db2935653692"},
     {file = "Pygments-2.16.1.tar.gz", hash = "sha256:1daff0494820c69bc8941e407aa20f577374ee88364ee10a98fdbe0aece96e29"},
@@ -4208,6 +4389,7 @@ version = "2.8.0"
 description = "JSON Web Token implementation in Python"
 optional = false
 python-versions = ">=3.7"
+groups = ["filesystem", "salesforce"]
 files = [
     {file = "PyJWT-2.8.0-py3-none-any.whl", hash = "sha256:59127c392cc44c2da5bb3192169a91f429924e17aff6534d70fdc02ab3e04320"},
     {file = "PyJWT-2.8.0.tar.gz", hash = "sha256:57e28d156e3d5c10088e0c68abb90bfac3df82b40a71bd0daa20c65ccd5c23de"},
@@ -4228,6 +4410,7 @@ version = "4.5.0"
 description = "Python driver for MongoDB <http://www.mongodb.org>"
 optional = false
 python-versions = ">=3.7"
+groups = ["mongodb"]
 files = [
     {file = "pymongo-4.5.0-cp310-cp310-macosx_10_9_universal2.whl", hash = "sha256:2d4fa1b01fa7e5b7bb8d312e3542e211b320eb7a4e3d8dc884327039d93cb9e0"},
     {file = "pymongo-4.5.0-cp310-cp310-manylinux1_i686.whl", hash = "sha256:dfcd2b9f510411de615ccedd47462dae80e82fdc09fe9ab0f0f32f11cf57eeb5"},
@@ -4330,6 +4513,7 @@ version = "1.4.0"
 description = "\"Tools for using NumPy, Pandas, Polars, and PyArrow with MongoDB\""
 optional = false
 python-versions = ">=3.8"
+groups = ["mongodb"]
 files = [
     {file = "pymongoarrow-1.4.0-cp310-cp310-macosx_10_15_x86_64.whl", hash = "sha256:57a438dad3808c10931ffadd6028c8107133d254229996f8260e7c61417d98fe"},
     {file = "pymongoarrow-1.4.0-cp310-cp310-macosx_11_0_arm64.whl", hash = "sha256:de545ecfc591288c75b602b4baeb6cd9f7db9ff6890c69d46dcb63eebd5e379d"},
@@ -4373,6 +4557,7 @@ version = "1.1.0"
 description = "Pure Python MySQL Driver"
 optional = false
 python-versions = ">=3.7"
+groups = ["sql_database"]
 files = [
     {file = "PyMySQL-1.1.0-py3-none-any.whl", hash = "sha256:8969ec6d763c856f7073c4c64662882675702efcb114b4bcbb955aea3a069fa7"},
     {file = "PyMySQL-1.1.0.tar.gz", hash = "sha256:4f13a7df8bf36a51e81dd9f3605fede45a4878fe02f9236349fd82a3f0612f96"},
@@ -4388,6 +4573,7 @@ version = "23.2.0"
 description = "Python wrapper module around the OpenSSL library"
 optional = false
 python-versions = ">=3.6"
+groups = ["scrapy"]
 files = [
     {file = "pyOpenSSL-23.2.0-py3-none-any.whl", hash = "sha256:24f0dc5227396b3e831f4c7f602b950a5e9833d292c8e4a2e06b709292806ae2"},
     {file = "pyOpenSSL-23.2.0.tar.gz", hash = "sha256:276f931f55a452e7dea69c7173e984eb2a4407ce413c918aa34b55f82f9b8bac"},
@@ -4406,6 +4592,7 @@ version = "1.11"
 description = "Thin wrapper for pandoc."
 optional = false
 python-versions = ">=3.6"
+groups = ["unstructured_data"]
 files = [
     {file = "pypandoc-1.11-py3-none-any.whl", hash = "sha256:b260596934e9cfc6513056110a7c8600171d414f90558bf4407e68b209be8007"},
     {file = "pypandoc-1.11.tar.gz", hash = "sha256:7f6d68db0e57e0f6961bec2190897118c4d305fc2d31c22cd16037f22ee084a5"},
@@ -4417,6 +4604,7 @@ version = "3.1.1"
 description = "pyparsing module - Classes and methods to define and execute parsing grammars"
 optional = false
 python-versions = ">=3.6.8"
+groups = ["google_ads", "google_analytics", "google_sheets"]
 files = [
     {file = "pyparsing-3.1.1-py3-none-any.whl", hash = "sha256:32c7c0b711493c72ff18a981d24f28aaf9c1fb7ed5e9667c9e84e3db623bdbfb"},
     {file = "pyparsing-3.1.1.tar.gz", hash = "sha256:ede28a1a32462f5a9705e07aea48001a08f7cf81a021585011deba701581a0db"},
@@ -4431,6 +4619,7 @@ version = "3.0.1"
 description = "A pure-python PDF library capable of splitting, merging, cropping, and transforming PDF files"
 optional = false
 python-versions = ">=3.6"
+groups = ["dev"]
 files = [
     {file = "PyPDF2-3.0.1.tar.gz", hash = "sha256:a74408f69ba6271f71b9352ef4ed03dc53a31aa404d29b5d31f53bfecfee1440"},
     {file = "pypdf2-3.0.1-py3-none-any.whl", hash = "sha256:d16e4205cfee272fbdc0568b68d82be796540b1537508cef59388f839c191928"},
@@ -4452,6 +4641,8 @@ version = "2.1.2"
 description = "Multi-producer-multi-consumer signal dispatching mechanism"
 optional = false
 python-versions = "*"
+groups = ["scrapy"]
+markers = "platform_python_implementation == \"PyPy\""
 files = [
     {file = "PyPyDispatcher-2.1.2.tar.gz", hash = "sha256:b6bec5dfcff9d2535bca2b23c80eae367b1ac250a645106948d315fcfa9130f2"},
 ]
@@ -4462,6 +4653,8 @@ version = "3.4.1"
 description = "A python implementation of GNU readline."
 optional = false
 python-versions = "*"
+groups = ["unstructured_data"]
+markers = "sys_platform == \"win32\""
 files = [
     {file = "pyreadline3-3.4.1-py3-none-any.whl", hash = "sha256:b0efb6516fd4fb07b45949053826a62fa4cb353db5be2bbb4a7aa1fdd1e345fb"},
     {file = "pyreadline3-3.4.1.tar.gz", hash = "sha256:6f3d1f7b8a31ba32b73917cefc1f28cc660562f39aea8646d30bd6eff21f7bae"},
@@ -4473,6 +4666,7 @@ version = "7.4.2"
 description = "pytest: simple powerful testing with Python"
 optional = false
 python-versions = ">=3.7"
+groups = ["dev", "pytest"]
 files = [
     {file = "pytest-7.4.2-py3-none-any.whl", hash = "sha256:1d881c6124e08ff0a1bb75ba3ec0bfd8b5354a01c194ddd5a0a870a48d99b002"},
     {file = "pytest-7.4.2.tar.gz", hash = "sha256:a766259cfab564a2ad52cb1aae1b881a75c3eb7e34ca3779697c23ed47c47069"},
@@ -4495,6 +4689,7 @@ version = "1.6.0"
 description = "run tests in isolated forked subprocesses"
 optional = false
 python-versions = ">=3.7"
+groups = ["dev", "pytest"]
 files = [
     {file = "pytest-forked-1.6.0.tar.gz", hash = "sha256:4dafd46a9a600f65d822b8f605133ecf5b3e1941ebb3588e943b4e3eb71a5a3f"},
     {file = "pytest_forked-1.6.0-py3-none-any.whl", hash = "sha256:810958f66a91afb1a1e2ae83089d8dc1cd2437ac96b12963042fbb9fb4d16af0"},
@@ -4510,6 +4705,7 @@ version = "3.12.0"
 description = "Thin-wrapper around the mock package for easier use with pytest"
 optional = false
 python-versions = ">=3.8"
+groups = ["dev", "pytest"]
 files = [
     {file = "pytest-mock-3.12.0.tar.gz", hash = "sha256:31a40f038c22cad32287bb43932054451ff5583ff094bca6f675df2f8bc1a6e9"},
     {file = "pytest_mock-3.12.0-py3-none-any.whl", hash = "sha256:0972719a7263072da3a21c7f4773069bcc7486027d7e8e1f81d98a47e701bc4f"},
@@ -4527,6 +4723,7 @@ version = "2.8.2"
 description = "Extensions to the standard Python datetime module"
 optional = false
 python-versions = "!=3.0.*,!=3.1.*,!=3.2.*,>=2.7"
+groups = ["main", "dev", "dltpure", "filesystem", "mongodb", "salesforce", "stripe_analytics", "unstructured_data"]
 files = [
     {file = "python-dateutil-2.8.2.tar.gz", hash = "sha256:0123cacc1627ae19ddf3c27a5de5bd67ee4586fbdd6440d9748f8abb483d3e86"},
     {file = "python_dateutil-2.8.2-py2.py3-none-any.whl", hash = "sha256:961d03dc3453ebbc59dbdea9e4e11c5651520a876d0f4db161e8674aae935da9"},
@@ -4541,6 +4738,7 @@ version = "1.0.1"
 description = "Create, read, and update Microsoft Word .docx files."
 optional = false
 python-versions = ">=3.7"
+groups = ["unstructured_data"]
 files = [
     {file = "python-docx-1.0.1.tar.gz", hash = "sha256:255148e15a4414244ec75f50e92d19864e52a7416768c65491707a7414659524"},
     {file = "python_docx-1.0.1-py3-none-any.whl", hash = "sha256:851340c49b36f917a1838a44c602a5a0702c0c3507b9890969545732dc10d2d1"},
@@ -4556,6 +4754,7 @@ version = "1.0.0"
 description = "Read key-value pairs from a .env file and set them as environment variables"
 optional = false
 python-versions = ">=3.8"
+groups = ["unstructured_data"]
 files = [
     {file = "python-dotenv-1.0.0.tar.gz", hash = "sha256:a8df96034aae6d2d50a4ebe8216326c61c3eb64836776504fcca410e5937a3ba"},
     {file = "python_dotenv-1.0.0-py3-none-any.whl", hash = "sha256:f5971a9226b701070a4bf2c38c89e5a3f0d64de8debda981d1db98583009122a"},
@@ -4570,6 +4769,7 @@ version = "0.4.27"
 description = "File type identification using libmagic"
 optional = false
 python-versions = ">=2.7, !=3.0.*, !=3.1.*, !=3.2.*, !=3.3.*, !=3.4.*"
+groups = ["unstructured_data"]
 files = [
     {file = "python-magic-0.4.27.tar.gz", hash = "sha256:c1ba14b08e4a5f5c31a302b7721239695b2f0f058d125bd5ce1ee36b9d9d3c3b"},
     {file = "python_magic-0.4.27-py2.py3-none-any.whl", hash = "sha256:c212960ad306f700aa0d01e5d7a325d20548ff97eb9920dcd29513174f0294d3"},
@@ -4581,6 +4781,7 @@ version = "0.6.22"
 description = "Generate and manipulate Open XML PowerPoint (.pptx) files"
 optional = false
 python-versions = "*"
+groups = ["unstructured_data"]
 files = [
     {file = "python-pptx-0.6.22.tar.gz", hash = "sha256:38f8ee92dde31d24b4562560e61b0357e5d97ecf75c4352ae6616d5a32978654"},
     {file = "python_pptx-0.6.22-py3-none-any.whl", hash = "sha256:3d097c29e08de2da1fc3c6752169087065efa4153216e77fc1b27dff1bcdcb46"},
@@ -4597,6 +4798,7 @@ version = "2023.3.post1"
 description = "World timezone definitions, modern and historical"
 optional = false
 python-versions = "*"
+groups = ["main", "dltpure", "mongodb", "salesforce", "stripe_analytics", "unstructured_data"]
 files = [
     {file = "pytz-2023.3.post1-py2.py3-none-any.whl", hash = "sha256:ce42d816b81b68506614c11e8937d3aa9e41007ceb50bfdcb0749b921bf646c7"},
     {file = "pytz-2023.3.post1.tar.gz", hash = "sha256:7b4fddbeb94a1eba4b557da24f19fdf9db575192544270a9101d8509f9f43d7b"},
@@ -4608,6 +4810,8 @@ version = "306"
 description = "Python for Window Extensions"
 optional = false
 python-versions = "*"
+groups = ["filesystem"]
+markers = "platform_system == \"Windows\""
 files = [
     {file = "pywin32-306-cp310-cp310-win32.whl", hash = "sha256:06d3420a5155ba65f0b72f2699b5bacf3109f36acbe8923765c22938a69dfc8d"},
     {file = "pywin32-306-cp310-cp310-win_amd64.whl", hash = "sha256:84f4471dbca1887ea3803d8848a1616429ac94a4a8d05f4bc9c5dcfd42ca99c8"},
@@ -4631,6 +4835,7 @@ version = "6.0.1"
 description = "YAML parser and emitter for Python"
 optional = false
 python-versions = ">=3.6"
+groups = ["main", "dev", "dltpure", "google_ads", "unstructured_data", "unstructured_data_lint"]
 files = [
     {file = "PyYAML-6.0.1-cp310-cp310-macosx_10_9_x86_64.whl", hash = "sha256:d858aa552c999bc8a8d57426ed01e40bef403cd8ccdd0fc5f6f04a00414cac2a"},
     {file = "PyYAML-6.0.1-cp310-cp310-macosx_11_0_arm64.whl", hash = "sha256:fd66fc5d0da6d9815ba2cebeb4205f95818ff4b79c3ebe268e75d961704af52f"},
@@ -4691,6 +4896,7 @@ version = "1.6.2"
 description = "Collection of persistent (disk-based) and non-persistent (memory-based) queues"
 optional = false
 python-versions = ">=3.5"
+groups = ["scrapy"]
 files = [
     {file = "queuelib-1.6.2-py2.py3-none-any.whl", hash = "sha256:4b96d48f650a814c6fb2fd11b968f9c46178b683aad96d68f930fe13a8574d19"},
     {file = "queuelib-1.6.2.tar.gz", hash = "sha256:4b207267f2642a8699a1f806045c56eb7ad1a85a10c0e249884580d139c2fcd2"},
@@ -4702,6 +4908,7 @@ version = "2023.10.3"
 description = "Alternative regular expression module, to replace re."
 optional = false
 python-versions = ">=3.7"
+groups = ["unstructured_data"]
 files = [
     {file = "regex-2023.10.3-cp310-cp310-macosx_10_9_x86_64.whl", hash = "sha256:4c34d4f73ea738223a094d8e0ffd6d2c1a1b4c175da34d6b0de3d8d69bee6bcc"},
     {file = "regex-2023.10.3-cp310-cp310-macosx_11_0_arm64.whl", hash = "sha256:a8f4e49fc3ce020f65411432183e6775f24e02dff617281094ba6ab079ef0915"},
@@ -4799,6 +5006,7 @@ version = "2.31.0"
 description = "Python HTTP for Humans."
 optional = false
 python-versions = ">=3.7"
+groups = ["main", "airtable", "asana_dlt", "dev", "dltpure", "facebook_ads", "filesystem", "google_ads", "google_analytics", "google_sheets", "salesforce", "scrapy", "stripe_analytics", "unstructured_data", "unstructured_data_lint"]
 files = [
     {file = "requests-2.31.0-py3-none-any.whl", hash = "sha256:58cd2187c01e70e6e26505bca751777aa9f2ee0b7f4300988b709f44e013003f"},
     {file = "requests-2.31.0.tar.gz", hash = "sha256:942c5a758f98d790eaed1a29cb6eefc7ffb0d1cf7af05c3d2791656dbd6ad1e1"},
@@ -4820,6 +5028,7 @@ version = "1.5.1"
 description = "File transport adapter for Requests"
 optional = false
 python-versions = "*"
+groups = ["salesforce", "scrapy"]
 files = [
     {file = "requests-file-1.5.1.tar.gz", hash = "sha256:07d74208d3389d01c38ab89ef403af0cfec63957d53a0081d8eca738d0247d8e"},
     {file = "requests_file-1.5.1-py2.py3-none-any.whl", hash = "sha256:dfe5dae75c12481f68ba353183c53a65e6044c923e64c24b2209f6c7570ca953"},
@@ -4835,6 +5044,7 @@ version = "1.11.0"
 description = "Mock out responses from the requests package"
 optional = false
 python-versions = "*"
+groups = ["dev"]
 files = [
     {file = "requests-mock-1.11.0.tar.gz", hash = "sha256:ef10b572b489a5f28e09b708697208c4a3b2b89ef80a9f01584340ea357ec3c4"},
     {file = "requests_mock-1.11.0-py2.py3-none-any.whl", hash = "sha256:f7fae383f228633f6bececebdab236c478ace2284d6292c6e7e2867b9ab74d15"},
@@ -4854,6 +5064,7 @@ version = "1.3.1"
 description = "OAuthlib authentication support for Requests."
 optional = false
 python-versions = ">=2.7, !=3.0.*, !=3.1.*, !=3.2.*, !=3.3.*"
+groups = ["main", "asana_dlt", "filesystem", "google_ads", "google_analytics"]
 files = [
     {file = "requests-oauthlib-1.3.1.tar.gz", hash = "sha256:75beac4a47881eeb94d5ea5d6ad31ef88856affe2332b9aafb52c6452ccf0d7a"},
     {file = "requests_oauthlib-1.3.1-py2.py3-none-any.whl", hash = "sha256:2577c501a2fb8d05a304c09d090d6e47c306fef15809d102b327cf8364bddab5"},
@@ -4872,6 +5083,7 @@ version = "1.0.0"
 description = "A utility belt for advanced users of python-requests"
 optional = false
 python-versions = ">=2.7, !=3.0.*, !=3.1.*, !=3.2.*, !=3.3.*"
+groups = ["salesforce"]
 files = [
     {file = "requests-toolbelt-1.0.0.tar.gz", hash = "sha256:7681a0a3d047012b5bdc0ee37d7f8f07ebe76ab08caeccfc3921ce23c88d5bc6"},
     {file = "requests_toolbelt-1.0.0-py2.py3-none-any.whl", hash = "sha256:cccfdd665f0a24fcf4726e690f65639d272bb0637b9b92dfd91a5568ccf6bd06"},
@@ -4886,6 +5098,7 @@ version = "0.5.0"
 description = "This is a small Python module for parsing Pip requirement files."
 optional = false
 python-versions = ">=3.6,<4.0"
+groups = ["main", "dltpure"]
 files = [
     {file = "requirements-parser-0.5.0.tar.gz", hash = "sha256:3336f3a3ae23e06d3f0f88595e4052396e3adf91688787f637e5d2ca1a904069"},
     {file = "requirements_parser-0.5.0-py3-none-any.whl", hash = "sha256:e7fcdcd04f2049e73a9fb150d8a0f9d51ce4108f5f7cbeac74c484e17b12bcd9"},
@@ -4900,6 +5113,7 @@ version = "13.6.0"
 description = "Render rich text, tables, progress bars, syntax highlighting, markdown and more to the terminal"
 optional = false
 python-versions = ">=3.7.0"
+groups = ["dev"]
 files = [
     {file = "rich-13.6.0-py3-none-any.whl", hash = "sha256:2b38e2fe9ca72c9a00170a1a2d20c63c790d0e10ef1fe35eba76e1e7b1d7d245"},
     {file = "rich-13.6.0.tar.gz", hash = "sha256:5c14d22737e6d5084ef4771b62d5d4363165b403455a30a1c8ca39dc7b644bef"},
@@ -4919,6 +5133,7 @@ version = "4.9"
 description = "Pure-Python RSA implementation"
 optional = false
 python-versions = ">=3.6,<4"
+groups = ["main", "filesystem", "google_ads", "google_analytics", "google_sheets"]
 files = [
     {file = "rsa-4.9-py3-none-any.whl", hash = "sha256:90260d9058e514786967344d0ef75fa8727eed8a7d2e43ce9f4bcf1b536174f7"},
     {file = "rsa-4.9.tar.gz", hash = "sha256:e38464a49c6c85d7f1351b0126661487a7e0a14a50f1675ec50eb34d4f20ef21"},
@@ -4933,6 +5148,7 @@ version = "2024.3.1"
 description = "Convenient Filesystem interface over S3"
 optional = false
 python-versions = ">= 3.8"
+groups = ["filesystem"]
 files = [
     {file = "s3fs-2024.3.1-py3-none-any.whl", hash = "sha256:f4566a5446c473740d272ec08e0b4aae8db1aa05f662c42ff0aa2c89bb5060ea"},
     {file = "s3fs-2024.3.1.tar.gz", hash = "sha256:1b8bc8dbd65e7b60f5487378f6eeffe1de59aa72caa9efca6dad6ab877405487"},
@@ -4953,6 +5169,7 @@ version = "2.11.1"
 description = "A high-level Web Crawling and Web Scraping framework"
 optional = false
 python-versions = ">=3.8"
+groups = ["scrapy"]
 files = [
     {file = "Scrapy-2.11.1-py2.py3-none-any.whl", hash = "sha256:f1edee0cd214512054c01a8d031a8d213dddb53492b02c9e66256e3efe90d175"},
     {file = "Scrapy-2.11.1.tar.gz", hash = "sha256:733a039c7423e52b69bf2810b5332093d4e42a848460359c07b02ecff8f73ebe"},
@@ -4984,6 +5201,7 @@ version = "3.0.2"
 description = "Python helper for Semantic Versioning (https://semver.org)"
 optional = false
 python-versions = ">=3.7"
+groups = ["main", "dltpure"]
 files = [
     {file = "semver-3.0.2-py3-none-any.whl", hash = "sha256:b1ea4686fe70b981f85359eda33199d60c53964284e0cfb4977d243e37cf4bf4"},
     {file = "semver-3.0.2.tar.gz", hash = "sha256:6253adb39c70f6e51afed2fa7152bcd414c411286088fb4b9effb133885ab4cc"},
@@ -4995,6 +5213,7 @@ version = "24.1.0"
 description = "Service identity verification for pyOpenSSL & cryptography."
 optional = false
 python-versions = ">=3.8"
+groups = ["scrapy"]
 files = [
     {file = "service_identity-24.1.0-py3-none-any.whl", hash = "sha256:a28caf8130c8a5c1c7a6f5293faaf239bbfb7751e4862436920ee6f2616f568a"},
     {file = "service_identity-24.1.0.tar.gz", hash = "sha256:6829c9d62fb832c2e1c435629b0a8c476e1929881f28bee4d20bc24161009221"},
@@ -5019,6 +5238,7 @@ version = "68.2.2"
 description = "Easily download, build, install, upgrade, and uninstall Python packages"
 optional = false
 python-versions = ">=3.8"
+groups = ["main", "dev", "dltpure", "facebook_ads", "google_ads", "scrapy"]
 files = [
     {file = "setuptools-68.2.2-py3-none-any.whl", hash = "sha256:b454a35605876da60632df1a60f736524eb73cc47bbc9f3f1ef1b644de74fd2a"},
     {file = "setuptools-68.2.2.tar.gz", hash = "sha256:4ac1475276d2f1c48684874089fefcd83bd7162ddaafb81fac866ba0db282a87"},
@@ -5035,6 +5255,7 @@ version = "1.12.5"
 description = "A basic Salesforce.com REST API client."
 optional = false
 python-versions = "*"
+groups = ["salesforce"]
 files = [
     {file = "simple-salesforce-1.12.5.tar.gz", hash = "sha256:ef65f72438e3b215619f6835d3d4356e147adf3a7ece6896d239127dd6aefcd1"},
     {file = "simple_salesforce-1.12.5-py2.py3-none-any.whl", hash = "sha256:07029575385d04132babfd6e19c1c8068c859d616a45dab07bbf9875bdc5ab93"},
@@ -5054,6 +5275,7 @@ version = "3.19.2"
 description = "Simple, fast, extensible JSON encoder/decoder for Python"
 optional = false
 python-versions = ">=2.5, !=3.0.*, !=3.1.*, !=3.2.*"
+groups = ["main", "dltpure"]
 files = [
     {file = "simplejson-3.19.2-cp27-cp27m-macosx_10_9_x86_64.whl", hash = "sha256:3471e95110dcaf901db16063b2e40fb394f8a9e99b3fe9ee3acc6f6ef72183a2"},
     {file = "simplejson-3.19.2-cp27-cp27m-manylinux1_i686.whl", hash = "sha256:3194cd0d2c959062b94094c0a9f8780ffd38417a5322450a0db0ca1a23e7fbd2"},
@@ -5161,6 +5383,7 @@ version = "1.16.0"
 description = "Python 2 and 3 compatibility utilities"
 optional = false
 python-versions = ">=2.7, !=3.0.*, !=3.1.*, !=3.2.*"
+groups = ["main", "dev", "dltpure", "facebook_ads", "filesystem", "mongodb", "salesforce", "scrapy", "stripe_analytics", "unstructured_data"]
 files = [
     {file = "six-1.16.0-py2.py3-none-any.whl", hash = "sha256:8abb2f1d86890a2dfb989f9a77cfcfd3e47c2a354b01111771326f8aa26e0254"},
     {file = "six-1.16.0.tar.gz", hash = "sha256:1e61c37477a1626458e36f7b1d82aa5c9b094fa4802892072e49de9c60c4c926"},
@@ -5172,6 +5395,7 @@ version = "5.0.1"
 description = "A pure Python implementation of a sliding window memory map manager"
 optional = false
 python-versions = ">=3.7"
+groups = ["main", "dev", "dltpure"]
 files = [
     {file = "smmap-5.0.1-py3-none-any.whl", hash = "sha256:e6d8668fa5f93e706934a62d7b4db19c8d9eb8cf2adbb75ef1b675aa332b69da"},
     {file = "smmap-5.0.1.tar.gz", hash = "sha256:dceeb6c0028fdb6734471eb07c0cd2aae706ccaecab45965ee83f11c8d3b1f62"},
@@ -5183,6 +5407,7 @@ version = "1.3.0"
 description = "Sniff out which async library your code is running under"
 optional = false
 python-versions = ">=3.7"
+groups = ["unstructured_data"]
 files = [
     {file = "sniffio-1.3.0-py3-none-any.whl", hash = "sha256:eecefdce1e5bbfb7ad2eeaabf7c1eeb404d7757c379bd1f7e5cce9d8bf425384"},
     {file = "sniffio-1.3.0.tar.gz", hash = "sha256:e60305c5e5d314f5389259b7f22aaa33d8f7dee49763119234af3755c55b9101"},
@@ -5194,6 +5419,7 @@ version = "2.0.22"
 description = "Database Abstraction Library"
 optional = false
 python-versions = ">=3.7"
+groups = ["sql_database", "unstructured_data", "unstructured_data_lint"]
 files = [
     {file = "SQLAlchemy-2.0.22-cp310-cp310-macosx_10_9_x86_64.whl", hash = "sha256:f146c61ae128ab43ea3a0955de1af7e1633942c2b2b4985ac51cc292daf33222"},
     {file = "SQLAlchemy-2.0.22-cp310-cp310-macosx_11_0_arm64.whl", hash = "sha256:875de9414393e778b655a3d97d60465eb3fae7c919e88b70cc10b40b9f56042d"},
@@ -5280,6 +5506,7 @@ version = "0.20.4"
 description = "The little ASGI library that shines."
 optional = false
 python-versions = ">=3.7"
+groups = ["unstructured_data"]
 files = [
     {file = "starlette-0.20.4-py3-none-any.whl", hash = "sha256:c0414d5a56297d37f3db96a84034d61ce29889b9eaccf65eb98a0b39441fcaa3"},
     {file = "starlette-0.20.4.tar.gz", hash = "sha256:42fcf3122f998fefce3e2c5ad7e5edbf0f02cf685d646a83a08d404726af5084"},
@@ -5298,6 +5525,7 @@ version = "5.1.0"
 description = "Manage dynamic plugins for Python applications"
 optional = false
 python-versions = ">=3.8"
+groups = ["dev"]
 files = [
     {file = "stevedore-5.1.0-py3-none-any.whl", hash = "sha256:8cc040628f3cea5d7128f2e76cf486b2251a4e543c7b938f58d9a377f6694a2d"},
     {file = "stevedore-5.1.0.tar.gz", hash = "sha256:a54534acf9b89bc7ed264807013b505bf07f74dbe4bcfa37d32bd063870b087c"},
@@ -5312,6 +5540,7 @@ version = "5.5.0"
 description = "Python bindings for the Stripe API"
 optional = false
 python-versions = ">=2.7, !=3.0.*, !=3.1.*, !=3.2.*, !=3.3.*"
+groups = ["stripe_analytics"]
 files = [
     {file = "stripe-5.5.0-py2.py3-none-any.whl", hash = "sha256:b4947da66dbb3de8969004ba6398f9a019c6b1b3ffe6aa88d5b07ac560a52b28"},
     {file = "stripe-5.5.0.tar.gz", hash = "sha256:04a9732b37a46228ecf0e496163a3edd93596b0e6200029fbc48911638627e19"},
@@ -5326,6 +5555,7 @@ version = "1.12"
 description = "Computer algebra system (CAS) in Python"
 optional = false
 python-versions = ">=3.8"
+groups = ["unstructured_data"]
 files = [
     {file = "sympy-1.12-py3-none-any.whl", hash = "sha256:c3588cd4295d0c0f603d0f2ae780587e64e2efeedb3521e46b9bb1d08d184fa5"},
     {file = "sympy-1.12.tar.gz", hash = "sha256:ebf595c8dac3e0fdc4152c51878b498396ec7f30e7a914d6071e674d49420fb8"},
@@ -5340,6 +5570,7 @@ version = "0.9.0"
 description = "Pretty-print tabular data"
 optional = false
 python-versions = ">=3.7"
+groups = ["unstructured_data"]
 files = [
     {file = "tabulate-0.9.0-py3-none-any.whl", hash = "sha256:024ca478df22e9340661486f85298cff5f6dcdba14f3813e8830015b9ed1948f"},
     {file = "tabulate-0.9.0.tar.gz", hash = "sha256:0095b12bf5966de529c0feb1fa08671671b3368eec77d7ef7ab114be2c068b3c"},
@@ -5354,6 +5585,7 @@ version = "8.2.3"
 description = "Retry code until it succeeds"
 optional = false
 python-versions = ">=3.7"
+groups = ["main", "dltpure", "unstructured_data", "unstructured_data_lint"]
 files = [
     {file = "tenacity-8.2.3-py3-none-any.whl", hash = "sha256:ce510e327a630c9e1beaf17d42e6ffacc88185044ad85cf74c0a8887c6a0f88c"},
     {file = "tenacity-8.2.3.tar.gz", hash = "sha256:5398ef0d78e63f40007c1fb4c0bff96e1911394d2fa8d194f77619c05ff6cc8a"},
@@ -5368,6 +5600,7 @@ version = "0.4.0"
 description = "tiktoken is a fast BPE tokeniser for use with OpenAI's models"
 optional = false
 python-versions = ">=3.8"
+groups = ["unstructured_data"]
 files = [
     {file = "tiktoken-0.4.0-cp310-cp310-macosx_10_9_x86_64.whl", hash = "sha256:176cad7f053d2cc82ce7e2a7c883ccc6971840a4b5276740d0b732a2b2011f8a"},
     {file = "tiktoken-0.4.0-cp310-cp310-macosx_11_0_arm64.whl", hash = "sha256:450d504892b3ac80207700266ee87c932df8efea54e05cefe8613edc963c1285"},
@@ -5413,6 +5646,7 @@ version = "5.1.1"
 description = "Accurately separates a URL's subdomain, domain, and public suffix, using the Public Suffix List (PSL). By default, this includes the public ICANN TLDs and their exceptions. You can optionally support the Public Suffix List's private domains as well."
 optional = false
 python-versions = ">=3.8"
+groups = ["scrapy"]
 files = [
     {file = "tldextract-5.1.1-py3-none-any.whl", hash = "sha256:b9c4510a8766d377033b6bace7e9f1f17a891383ced3c5d50c150f181e9e1cc2"},
     {file = "tldextract-5.1.1.tar.gz", hash = "sha256:9b6dbf803cb5636397f0203d48541c0da8ba53babaf0e8a6feda2d88746813d4"},
@@ -5433,6 +5667,7 @@ version = "0.14.1"
 description = ""
 optional = false
 python-versions = ">=3.7"
+groups = ["unstructured_data"]
 files = [
     {file = "tokenizers-0.14.1-cp310-cp310-macosx_10_7_x86_64.whl", hash = "sha256:04ec1134a18ede355a05641cdc7700f17280e01f69f2f315769f02f7e295cf1e"},
     {file = "tokenizers-0.14.1-cp310-cp310-macosx_11_0_arm64.whl", hash = "sha256:638abedb39375f0ddce2de536fc9c976639b2d1b7202d715c2e7a25f0ebfd091"},
@@ -5548,6 +5783,8 @@ version = "2.0.1"
 description = "A lil' TOML parser"
 optional = false
 python-versions = ">=3.7"
+groups = ["dev", "pytest"]
+markers = "python_version < \"3.11\""
 files = [
     {file = "tomli-2.0.1-py3-none-any.whl", hash = "sha256:939de3e7a6161af0c887ef91b7d41a53e7c5a1ca976325f429cb46ea9bc30ecc"},
     {file = "tomli-2.0.1.tar.gz", hash = "sha256:de526c12914f0c550d15924c62d72abc48d6fe7364aa87328337a31007fe8a4f"},
@@ -5559,6 +5796,7 @@ version = "0.12.1"
 description = "Style preserving TOML library"
 optional = false
 python-versions = ">=3.7"
+groups = ["main", "dltpure"]
 files = [
     {file = "tomlkit-0.12.1-py3-none-any.whl", hash = "sha256:712cbd236609acc6a3e2e97253dfc52d4c2082982a88f61b640ecf0817eab899"},
     {file = "tomlkit-0.12.1.tar.gz", hash = "sha256:38e1ff8edb991273ec9f6181244a6a391ac30e9f5098e7535640ea6be97a7c86"},
@@ -5570,6 +5808,7 @@ version = "4.66.1"
 description = "Fast, Extensible Progress Meter"
 optional = false
 python-versions = ">=3.7"
+groups = ["unstructured_data", "unstructured_data_lint"]
 files = [
     {file = "tqdm-4.66.1-py3-none-any.whl", hash = "sha256:d302b3c5b53d47bce91fea46679d9c3c6508cf6332229aa1e7d8653723793386"},
     {file = "tqdm-4.66.1.tar.gz", hash = "sha256:d88e651f9db8d8551a62556d3cff9e3034274ca5d66e93197cf2490e2dcb69c7"},
@@ -5590,6 +5829,7 @@ version = "22.10.0"
 description = "An asynchronous networking framework written in Python"
 optional = false
 python-versions = ">=3.7.1"
+groups = ["dev", "scrapy"]
 files = [
     {file = "Twisted-22.10.0-py3-none-any.whl", hash = "sha256:86c55f712cc5ab6f6d64e02503352464f0400f66d4f079096d744080afcccbd0"},
     {file = "Twisted-22.10.0.tar.gz", hash = "sha256:32acbd40a94f5f46e7b42c109bfae2b302250945561783a8b7a059048f2d4d31"},
@@ -5628,6 +5868,8 @@ version = "1.0.4"
 description = "An extension for use in the twisted I/O Completion Ports reactor."
 optional = false
 python-versions = "*"
+groups = ["dev", "scrapy"]
+markers = "platform_system == \"Windows\""
 files = [
     {file = "twisted-iocpsupport-1.0.4.tar.gz", hash = "sha256:858096c0d15e33f15ac157f455d8f86f2f2cdd223963e58c0f682a3af8362d89"},
     {file = "twisted_iocpsupport-1.0.4-cp310-cp310-win32.whl", hash = "sha256:afa2b630797f9ed2f27f3d9f55e3f72b4244911e45a8c82756f44babbf0b243e"},
@@ -5656,6 +5898,7 @@ version = "2.9.21.20240218"
 description = "Typing stubs for psycopg2"
 optional = false
 python-versions = ">=3.8"
+groups = ["dev"]
 files = [
     {file = "types-psycopg2-2.9.21.20240218.tar.gz", hash = "sha256:3084cd807038a62c80fb5be78b41d855b48a060316101ea59fd85c302efb57d4"},
     {file = "types_psycopg2-2.9.21.20240218-py3-none-any.whl", hash = "sha256:cac96264e063cbce28dee337a973d39e6df4ca671252343cb4f8e5ef6db5e67d"},
@@ -5667,6 +5910,7 @@ version = "2023.3.1.1"
 description = "Typing stubs for pytz"
 optional = false
 python-versions = "*"
+groups = ["dev"]
 files = [
     {file = "types-pytz-2023.3.1.1.tar.gz", hash = "sha256:cc23d0192cd49c8f6bba44ee0c81e4586a8f30204970fc0894d209a6b08dab9a"},
     {file = "types_pytz-2023.3.1.1-py3-none-any.whl", hash = "sha256:1999a123a3dc0e39a2ef6d19f3f8584211de9e6a77fe7a0259f04a524e90a5cf"},
@@ -5678,6 +5922,7 @@ version = "2.31.0.6"
 description = "Typing stubs for requests"
 optional = false
 python-versions = ">=3.7"
+groups = ["dev"]
 files = [
     {file = "types-requests-2.31.0.6.tar.gz", hash = "sha256:cd74ce3b53c461f1228a9b783929ac73a666658f223e28ed29753771477b3bd0"},
     {file = "types_requests-2.31.0.6-py3-none-any.whl", hash = "sha256:a2db9cb228a81da8348b49ad6db3f5519452dd20a9c1e1a868c83c5fe88fd1a9"},
@@ -5692,6 +5937,7 @@ version = "68.2.0.0"
 description = "Typing stubs for setuptools"
 optional = false
 python-versions = "*"
+groups = ["main", "dltpure"]
 files = [
     {file = "types-setuptools-68.2.0.0.tar.gz", hash = "sha256:a4216f1e2ef29d089877b3af3ab2acf489eb869ccaf905125c69d2dc3932fd85"},
     {file = "types_setuptools-68.2.0.0-py3-none-any.whl", hash = "sha256:77edcc843e53f8fc83bb1a840684841f3dc804ec94562623bfa2ea70d5a2ba1b"},
@@ -5703,6 +5949,7 @@ version = "3.5.2.14"
 description = "Typing stubs for stripe"
 optional = false
 python-versions = "*"
+groups = ["stripe_analytics"]
 files = [
     {file = "types-stripe-3.5.2.14.tar.gz", hash = "sha256:bcc020aa5ba9acd796b9f2ac21f044c8e377ce2c0f570057f0f64c4b4637bbe7"},
     {file = "types_stripe-3.5.2.14-py3-none-any.whl", hash = "sha256:f5f1249f72a35ada1db95523edc7e8f7b543dc8434b2ff23eaa9ec2e251c2e59"},
@@ -5714,6 +5961,7 @@ version = "1.26.25.14"
 description = "Typing stubs for urllib3"
 optional = false
 python-versions = "*"
+groups = ["dev"]
 files = [
     {file = "types-urllib3-1.26.25.14.tar.gz", hash = "sha256:229b7f577c951b8c1b92c1bc2b2fdb0b49847bd2af6d1cc2a2e3dd340f3bda8f"},
     {file = "types_urllib3-1.26.25.14-py3-none-any.whl", hash = "sha256:9683bbb7fb72e32bfe9d2be6e04875fbe1b3eeec3cbb4ea231435aa7fd6b4f0e"},
@@ -5725,6 +5973,7 @@ version = "4.8.0"
 description = "Backported and Experimental Type Hints for Python 3.8+"
 optional = false
 python-versions = ">=3.8"
+groups = ["main", "airtable", "dev", "dltpure", "filesystem", "scrapy", "sql_database", "unstructured_data", "unstructured_data_lint"]
 files = [
     {file = "typing_extensions-4.8.0-py3-none-any.whl", hash = "sha256:8f92fc8806f9a6b641eaa5318da32b44d401efaac0f6678c9bc448ba3605faa0"},
     {file = "typing_extensions-4.8.0.tar.gz", hash = "sha256:df8e4339e9cb77357558cbdbceca33c303714cf861d1eef15e1070055ae8b7ef"},
@@ -5736,6 +5985,7 @@ version = "0.9.0"
 description = "Runtime inspection utilities for typing module."
 optional = false
 python-versions = "*"
+groups = ["unstructured_data", "unstructured_data_lint"]
 files = [
     {file = "typing_inspect-0.9.0-py3-none-any.whl", hash = "sha256:9ee6fc59062311ef8547596ab6b955e1b8aa46242d854bfc78f4f6b0eff35f9f"},
     {file = "typing_inspect-0.9.0.tar.gz", hash = "sha256:b23fc42ff6f6ef6954e4852c1fb512cdd18dbea03134f91f856a95ccc9461f78"},
@@ -5751,6 +6001,7 @@ version = "2023.3"
 description = "Provider of IANA time zone data"
 optional = false
 python-versions = ">=2"
+groups = ["main", "dev", "dltpure", "mongodb", "salesforce", "stripe_analytics", "unstructured_data"]
 files = [
     {file = "tzdata-2023.3-py2.py3-none-any.whl", hash = "sha256:7e65763eef3120314099b6939b5546db7adce1e7d6f2e179e3df563c70511eda"},
     {file = "tzdata-2023.3.tar.gz", hash = "sha256:11ef1e08e54acb0d4f95bdb1be05da659673de4acbd21bf9c69e94cc5e907a3a"},
@@ -5762,6 +6013,7 @@ version = "0.7.12"
 description = "A library that prepares raw documents for downstream ML tasks."
 optional = false
 python-versions = ">=3.7.0"
+groups = ["unstructured_data"]
 files = [
     {file = "unstructured-0.7.12-py3-none-any.whl", hash = "sha256:6dec4f23574e213f30bccb680a4fb84c95617092ce4abf5d8955cc71af402fef"},
     {file = "unstructured-0.7.12.tar.gz", hash = "sha256:3dcddea34f52e1070f38fd10063b3b0f64bc4cbe5b778d6b86b5d33262d625cd"},
@@ -5809,6 +6061,7 @@ version = "4.1.1"
 description = "Implementation of RFC 6570 URI Templates"
 optional = false
 python-versions = ">=3.6"
+groups = ["google_ads", "google_analytics", "google_sheets"]
 files = [
     {file = "uritemplate-4.1.1-py2.py3-none-any.whl", hash = "sha256:830c08b8d99bdd312ea4ead05994a38e8936266f84b9a7878232db50b044e02e"},
     {file = "uritemplate-4.1.1.tar.gz", hash = "sha256:4346edfc5c3b79f694bccd6d6099a322bbeb628dbf2cd86eea55a456ce5124f0"},
@@ -5820,6 +6073,7 @@ version = "1.26.17"
 description = "HTTP library with thread-safe connection pooling, file post, and more."
 optional = false
 python-versions = ">=2.7, !=3.0.*, !=3.1.*, !=3.2.*, !=3.3.*, !=3.4.*, !=3.5.*"
+groups = ["main", "airtable", "asana_dlt", "dev", "dltpure", "facebook_ads", "filesystem", "google_ads", "google_analytics", "google_sheets", "salesforce", "scrapy", "stripe_analytics", "unstructured_data", "unstructured_data_lint"]
 files = [
     {file = "urllib3-1.26.17-py2.py3-none-any.whl", hash = "sha256:94a757d178c9be92ef5539b8840d48dc9cf1b2709c9d6b588232a055c524458b"},
     {file = "urllib3-1.26.17.tar.gz", hash = "sha256:24d6a242c28d29af46c3fae832c36db3bbebcc533dd1bb549172cd739c82df21"},
@@ -5836,6 +6090,7 @@ version = "0.23.2"
 description = "The lightning-fast ASGI server."
 optional = false
 python-versions = ">=3.8"
+groups = ["unstructured_data"]
 files = [
     {file = "uvicorn-0.23.2-py3-none-any.whl", hash = "sha256:1f9be6558f01239d4fdf22ef8126c39cb1ad0addf76c40e760549d2c2f43ab53"},
     {file = "uvicorn-0.23.2.tar.gz", hash = "sha256:4d3cc12d7727ba72b64d12d3cc7743124074c0a69f7b201512fc50c3e3f1569a"},
@@ -5862,6 +6117,8 @@ version = "0.18.0"
 description = "Fast implementation of asyncio event loop on top of libuv"
 optional = false
 python-versions = ">=3.7.0"
+groups = ["unstructured_data"]
+markers = "(sys_platform != \"win32\" and sys_platform != \"cygwin\") and platform_python_implementation != \"PyPy\""
 files = [
     {file = "uvloop-0.18.0-cp310-cp310-macosx_10_9_universal2.whl", hash = "sha256:1f354d669586fca96a9a688c585b6257706d216177ac457c92e15709acaece10"},
     {file = "uvloop-0.18.0-cp310-cp310-macosx_10_9_x86_64.whl", hash = "sha256:280904236a5b333a273292b3bcdcbfe173690f69901365b973fa35be302d7781"},
@@ -5911,6 +6168,7 @@ version = "2.1.2"
 description = "Library of web-related functions"
 optional = false
 python-versions = ">=3.7"
+groups = ["scrapy"]
 files = [
     {file = "w3lib-2.1.2-py3-none-any.whl", hash = "sha256:c4432926e739caa8e3f49f5de783f336df563d9490416aebd5d39fb896d264e7"},
     {file = "w3lib-2.1.2.tar.gz", hash = "sha256:ed5b74e997eea2abe3c1321f916e344144ee8e9072a6f33463ee8e57f858a4b1"},
@@ -5922,6 +6180,7 @@ version = "0.21.0"
 description = "Simple, modern and high performance file watching and code reload in python."
 optional = false
 python-versions = ">=3.8"
+groups = ["unstructured_data"]
 files = [
     {file = "watchfiles-0.21.0-cp310-cp310-macosx_10_7_x86_64.whl", hash = "sha256:27b4035013f1ea49c6c0b42d983133b136637a527e48c132d368eb19bf1ac6aa"},
     {file = "watchfiles-0.21.0-cp310-cp310-macosx_11_0_arm64.whl", hash = "sha256:c81818595eff6e92535ff32825f31c116f867f64ff8cdf6562cd1d6b2e1e8f3e"},
@@ -6009,6 +6268,7 @@ version = "11.0.3"
 description = "An implementation of the WebSocket Protocol (RFC 6455 & 7692)"
 optional = false
 python-versions = ">=3.7"
+groups = ["unstructured_data"]
 files = [
     {file = "websockets-11.0.3-cp310-cp310-macosx_10_9_universal2.whl", hash = "sha256:3ccc8a0c387629aec40f2fc9fdcb4b9d5431954f934da3eaf16cdc94f67dbfac"},
     {file = "websockets-11.0.3-cp310-cp310-macosx_10_9_x86_64.whl", hash = "sha256:d67ac60a307f760c6e65dad586f556dde58e683fab03323221a4e530ead6f74d"},
@@ -6088,6 +6348,7 @@ version = "0.41.2"
 description = "A built-package format for Python"
 optional = false
 python-versions = ">=3.7"
+groups = ["main", "dltpure"]
 files = [
     {file = "wheel-0.41.2-py3-none-any.whl", hash = "sha256:75909db2664838d015e3d9139004ee16711748a52c8f336b52882266540215d8"},
     {file = "wheel-0.41.2.tar.gz", hash = "sha256:0c5ac5ff2afb79ac23ab82bab027a0be7b5dbcf2e54dc50efe4bf507de1f7985"},
@@ -6102,6 +6363,8 @@ version = "1.4.2"
 description = ""
 optional = false
 python-versions = ">=3.7"
+groups = ["main", "dltpure"]
+markers = "os_name == \"nt\""
 files = [
     {file = "win-precise-time-1.4.2.tar.gz", hash = "sha256:89274785cbc5f2997e01675206da3203835a442c60fd97798415c6b3c179c0b9"},
     {file = "win_precise_time-1.4.2-cp310-cp310-win32.whl", hash = "sha256:7fa13a2247c2ef41cd5e9b930f40716eacc7fc1f079ea72853bd5613fe087a1a"},
@@ -6124,6 +6387,7 @@ version = "1.15.0"
 description = "Module for decorators, wrappers and monkey patching."
 optional = false
 python-versions = "!=3.0.*,!=3.1.*,!=3.2.*,!=3.3.*,!=3.4.*,>=2.7"
+groups = ["filesystem"]
 files = [
     {file = "wrapt-1.15.0-cp27-cp27m-macosx_10_9_x86_64.whl", hash = "sha256:ca1cccf838cd28d5a0883b342474c630ac48cac5df0ee6eacc9c7290f76b11c1"},
     {file = "wrapt-1.15.0-cp27-cp27m-manylinux1_i686.whl", hash = "sha256:e826aadda3cae59295b95343db8f3d965fb31059da7de01ee8d1c40a60398b29"},
@@ -6208,6 +6472,7 @@ version = "2.0.1"
 description = "Library for developers to extract data from Microsoft Excel (tm) .xls spreadsheet files"
 optional = false
 python-versions = ">=2.7, !=3.0.*, !=3.1.*, !=3.2.*, !=3.3.*, !=3.4.*, !=3.5.*"
+groups = ["unstructured_data"]
 files = [
     {file = "xlrd-2.0.1-py2.py3-none-any.whl", hash = "sha256:6a33ee89877bd9abc1158129f6e94be74e2679636b8a205b43b85206c3f0bbdd"},
     {file = "xlrd-2.0.1.tar.gz", hash = "sha256:f72f148f54442c6b056bf931dbc34f986fd0c3b0b6b5a58d013c9aef274d0c88"},
@@ -6224,6 +6489,7 @@ version = "3.1.7"
 description = "A Python module for creating Excel XLSX files."
 optional = false
 python-versions = ">=3.6"
+groups = ["unstructured_data"]
 files = [
     {file = "XlsxWriter-3.1.7-py3-none-any.whl", hash = "sha256:8c730c4beb468696c4160aa1d6d168fb4c1a20dd972b212cd8cc1e74ddeab1b6"},
     {file = "XlsxWriter-3.1.7.tar.gz", hash = "sha256:353042efb0f8551ce72baa087e98228f3394fcb380e8b96313edf1eec8d50823"},
@@ -6235,6 +6501,7 @@ version = "1.9.2"
 description = "Yet another URL library"
 optional = false
 python-versions = ">=3.7"
+groups = ["main", "facebook_ads", "filesystem", "unstructured_data", "unstructured_data_lint"]
 files = [
     {file = "yarl-1.9.2-cp310-cp310-macosx_10_9_universal2.whl", hash = "sha256:8c2ad583743d16ddbdf6bb14b5cd76bf43b0d0006e918809d5d4ddf7bde8dd82"},
     {file = "yarl-1.9.2-cp310-cp310-macosx_10_9_x86_64.whl", hash = "sha256:82aa6264b36c50acfb2424ad5ca537a2060ab6de158a5bd2a72a032cc75b9eb8"},
@@ -6322,6 +6589,7 @@ version = "4.2.1"
 description = "A Python SOAP client"
 optional = false
 python-versions = ">=3.7"
+groups = ["salesforce"]
 files = [
     {file = "zeep-4.2.1-py3-none-any.whl", hash = "sha256:6754feb4c34a4b6d65fbc359252bf6654dcce3937bf1d95aae4402a60a8f5939"},
     {file = "zeep-4.2.1.tar.gz", hash = "sha256:72093acfdb1d8360ed400869b73fbf1882b95c4287f798084c42ee0c1ff0e425"},
@@ -6349,10 +6617,12 @@ version = "3.17.0"
 description = "Backport of pathlib-compatible object wrapper for zip files"
 optional = false
 python-versions = ">=3.8"
+groups = ["main", "dev", "dltpure", "salesforce", "unstructured_data"]
 files = [
     {file = "zipp-3.17.0-py3-none-any.whl", hash = "sha256:0e923e726174922dce09c53c59ad483ff7bbb8e572e00c7f7c46b88556409f31"},
     {file = "zipp-3.17.0.tar.gz", hash = "sha256:84e64a1c28cf7e91ed2078bb8cc8c259cb19b76942096c8d7b84947690cabaf0"},
 ]
+markers = {main = "python_version < \"3.9\"", dev = "python_version < \"3.9\"", dltpure = "python_version < \"3.9\"", salesforce = "python_version < \"3.9\"", unstructured_data = "python_version < \"3.10\""}
 
 [package.extras]
 docs = ["furo", "jaraco.packaging (>=9.3)", "jaraco.tidelift (>=1.4)", "rst.linker (>=1.9)", "sphinx (<7.2.5)", "sphinx (>=3.5)", "sphinx-lint"]
@@ -6364,6 +6634,7 @@ version = "6.2"
 description = "Interfaces for Python"
 optional = false
 python-versions = ">=3.7"
+groups = ["dev", "scrapy"]
 files = [
     {file = "zope.interface-6.2-cp310-cp310-macosx_10_9_x86_64.whl", hash = "sha256:506f5410b36e5ba494136d9fa04c548eaf1a0d9c442b0b0e7a0944db7620e0ab"},
     {file = "zope.interface-6.2-cp310-cp310-macosx_11_0_arm64.whl", hash = "sha256:b386b8b9d2b6a5e1e4eadd4e62335571244cb9193b7328c2b6e38b64cfda4f0e"},
@@ -6417,6 +6688,7 @@ version = "0.21.0"
 description = "Zstandard bindings for Python"
 optional = false
 python-versions = ">=3.7"
+groups = ["unstructured_data"]
 files = [
     {file = "zstandard-0.21.0-cp310-cp310-macosx_10_9_x86_64.whl", hash = "sha256:649a67643257e3b2cff1c0a73130609679a5673bf389564bc6d4b164d822a7ce"},
     {file = "zstandard-0.21.0-cp310-cp310-macosx_11_0_arm64.whl", hash = "sha256:144a4fe4be2e747bf9c646deab212666e39048faa4372abb6a250dab0f347a29"},
@@ -6470,6 +6742,6 @@ cffi = {version = ">=1.11", markers = "platform_python_implementation == \"PyPy\
 cffi = ["cffi (>=1.11)"]
 
 [metadata]
-lock-version = "2.0"
+lock-version = "2.1"
 python-versions = ">=3.8.1,<3.13"
 content-hash = "e216234bd35e71ef0c8e5a498c2cc616df417c5b14658b00aed9d935ba5a782e"
diff --git a/pyproject.toml b/pyproject.toml
index a1a431d54..7fe872f3b 100644
--- a/pyproject.toml
+++ b/pyproject.toml
@@ -93,8 +93,8 @@ chromadb = "^0.3.26"
 tiktoken = "^0.4.0"
 
 [tool.poetry.group.mongodb.dependencies]
-pymongo = "^4.3.3"
-pymongoarrow = ">=1.3.0"
+pymongo = "^4.10.0"
+pymongoarrow = "^1.5.0"
 
 [tool.poetry.group.airtable.dependencies]
 pyairtable = "^2.1.0.post1"
diff --git a/sources/mongodb/helpers.py b/sources/mongodb/helpers.py
index 0c0182ed1..a9f2b5eba 100644
--- a/sources/mongodb/helpers.py
+++ b/sources/mongodb/helpers.py
@@ -18,7 +18,7 @@
 from pymongo import ASCENDING, DESCENDING, MongoClient
 from pymongo.collection import Collection
 from pymongo.cursor import Cursor
-from pymongo.helpers import _fields_list_to_dict
+from pymongo.helpers_shared import _fields_list_to_dict
 
 
 if TYPE_CHECKING:
@@ -312,11 +312,7 @@ def load_documents(
             Iterator[Any]: An iterator of the loaded documents.
         """
         from pymongoarrow.context import PyMongoArrowContext  # type: ignore
-        from pymongoarrow.lib import process_bson_stream  # type: ignore
-
-        context = PyMongoArrowContext.from_schema(
-            None, codec_options=self.collection.codec_options
-        )
+        from pymongoarrow.lib import process_bson_stream
 
         filter_op = self._filter_op
         _raise_if_intersection(filter_op, filter_)
@@ -333,9 +329,11 @@ def load_documents(
 
         cursor = self._limit(cursor, limit)  # type: ignore
 
+        context = PyMongoArrowContext.from_schema(
+            None, codec_options=self.collection.codec_options
+        )
         for batch in cursor:
             process_bson_stream(batch, context)
-
             table = context.finish()
             yield convert_arrow_columns(table)
 
@@ -345,7 +343,6 @@ class CollectionArrowLoaderParallel(CollectionLoaderParallel):
     Mongo DB collection parallel loader, which uses
     Apache Arrow for data processing.
     """
-
     def _get_cursor(
         self,
         filter_: Dict[str, Any],
@@ -383,10 +380,8 @@ def _run_batch(self, cursor: TCursor, batch: Dict[str, int]) -> TDataItem:
         context = PyMongoArrowContext.from_schema(
             None, codec_options=self.collection.codec_options
         )
-
         for chunk in cursor.skip(batch["skip"]).limit(batch["limit"]):
             process_bson_stream(chunk, context)
-
             table = context.finish()
             yield convert_arrow_columns(table)
 

From 33c80634abbc700fda1df8480d83c41869f1c8a9 Mon Sep 17 00:00:00 2001
From: zilto <zilto@github.com>
Date: Thu, 16 Jan 2025 17:23:22 -0500
Subject: [PATCH 3/4] added pymongoarrow_schema; linting

---
 sources/mongodb/__init__.py          |  31 ++++--
 sources/mongodb/helpers.py           | 136 +++++++++++++++++++++++----
 tests/mongodb/test_mongodb_source.py |  31 +++---
 3 files changed, 160 insertions(+), 38 deletions(-)

diff --git a/sources/mongodb/__init__.py b/sources/mongodb/__init__.py
index 351b850e7..cea713a3e 100644
--- a/sources/mongodb/__init__.py
+++ b/sources/mongodb/__init__.py
@@ -24,6 +24,8 @@ def mongodb(
     parallel: Optional[bool] = dlt.config.value,
     limit: Optional[int] = None,
     filter_: Optional[Dict[str, Any]] = None,
+    projection: Optional[Union[Mapping[str, Any], Iterable[str]]] = None,
+    pymongoarrow_schema: Optional[Any] = None
 ) -> Iterable[DltResource]:
     """
     A DLT source which loads data from a mongo database using PyMongo.
@@ -41,6 +43,13 @@ def mongodb(
             The maximum number of documents to load. The limit is
             applied to each requested collection separately.
         filter_ (Optional[Dict[str, Any]]): The filter to apply to the collection.
+        projection: (Optional[Union[Mapping[str, Any], Iterable[str]]]): The projection to select fields of a collection
+            when loading the collection. Supported inputs:
+                include (list) - ["year", "title"]
+                include (dict) - {"year": True, "title": True}
+                exclude (dict) - {"released": False, "runtime": False}
+            Note: Can't mix include and exclude statements '{"title": True, "released": False}`
+        pymongoarrow_schema (pymongoarrow.schema.Schema): Mapping of expected field types of a collection to convert BSON to Arrow
 
     Returns:
         Iterable[DltResource]: A list of DLT resources for each collection to be loaded.
@@ -73,12 +82,15 @@ def mongodb(
             parallel=parallel,
             limit=limit,
             filter_=filter_ or {},
-            projection=None,
+            projection=projection,
+            pymongoarrow_schema=pymongoarrow_schema,
         )
 
 
-@dlt.common.configuration.with_config(
-    sections=("sources", "mongodb"), spec=MongoDbCollectionResourceConfiguration
+@dlt.resource(
+    name=lambda args: args["collection"],
+    standalone=True,
+    spec=MongoDbCollectionResourceConfiguration,
 )
 def mongodb_collection(
     connection_url: str = dlt.secrets.value,
@@ -91,7 +103,8 @@ def mongodb_collection(
     chunk_size: Optional[int] = 10000,
     data_item_format: Optional[TDataItemFormat] = "object",
     filter_: Optional[Dict[str, Any]] = None,
-    projection: Optional[Union[Mapping[str, Any], Iterable[str]]] = None,
+    projection: Optional[Union[Mapping[str, Any], Iterable[str]]] = dlt.config.value,
+    pymongoarrow_schema: Optional[Any] = None
 ) -> Any:
     """
     A DLT source which loads a collection from a mongo database using PyMongo.
@@ -111,12 +124,13 @@ def mongodb_collection(
                 object - Python objects (dicts, lists).
                 arrow - Apache Arrow tables.
         filter_ (Optional[Dict[str, Any]]): The filter to apply to the collection.
-        projection: (Optional[Union[Mapping[str, Any], Iterable[str]]]): The projection to select columns
+        projection: (Optional[Union[Mapping[str, Any], Iterable[str]]]): The projection to select fields
             when loading the collection. Supported inputs:
                 include (list) - ["year", "title"]
-                include (dict) - {"year": 1, "title": 1}
-                exclude (dict) - {"released": 0, "runtime": 0}
-            Note: Can't mix include and exclude statements '{"title": 1, "released": 0}`
+                include (dict) - {"year": True, "title": True}
+                exclude (dict) - {"released": False, "runtime": False}
+            Note: Can't mix include and exclude statements '{"title": True, "released": False}`
+        pymongoarrow_schema (pymongoarrow.schema.Schema): Mapping of expected field types to convert BSON to Arrow
 
     Returns:
         Iterable[DltResource]: A list of DLT resources for each collection to be loaded.
@@ -145,4 +159,5 @@ def mongodb_collection(
         data_item_format=data_item_format,
         filter_=filter_ or {},
         projection=projection,
+        pymongoarrow_schema=pymongoarrow_schema,
     )
diff --git a/sources/mongodb/helpers.py b/sources/mongodb/helpers.py
index a9f2b5eba..817a58fdd 100644
--- a/sources/mongodb/helpers.py
+++ b/sources/mongodb/helpers.py
@@ -107,10 +107,10 @@ def _filter_op(self) -> Dict[str, Any]:
                 filt[self.cursor_field]["$gt"] = self.incremental.end_value
 
         return filt
-    
-    def _projection_op(self, projection) -> Optional[Dict[str, Any]]:
+
+    def _projection_op(self, projection:Optional[Union[Mapping[str, Any], Iterable[str]]]) -> Optional[Dict[str, Any]]:
         """Build a projection operator.
-        
+
         A tuple of fields to include or a dict specifying fields to include or exclude.
         The incremental `primary_key` needs to be handle differently for inclusion
         and exclusion projections.
@@ -123,17 +123,16 @@ def _projection_op(self, projection) -> Optional[Dict[str, Any]]:
 
         projection_dict = dict(_fields_list_to_dict(projection, "projection"))
 
-        # NOTE we can still filter on primary_key if it's excluded from projection
         if self.incremental:
             # this is an inclusion projection
-            if any(v == 1 for v in projection.values()):
+            if any(v == 1 for v in projection_dict.values()):
                 # ensure primary_key is included
-                projection_dict.update({self.incremental.primary_key: 1})
+                projection_dict.update(m={self.incremental.primary_key: 1})
             # this is an exclusion projection
             else:
                 try:
                     # ensure primary_key isn't excluded
-                    projection_dict.pop(self.incremental.primary_key)
+                    projection_dict.pop(self.incremental.primary_key)  # type: ignore
                 except KeyError:
                     pass  # primary_key was properly not included in exclusion projection
                 else:
@@ -174,6 +173,7 @@ def load_documents(
         Args:
             filter_ (Dict[str, Any]): The filter to apply to the collection.
             limit (Optional[int]): The number of documents to load.
+            projection: selection of fields to create Cursor
 
         Yields:
             Iterator[TDataItem]: An iterator of the loaded documents.
@@ -279,6 +279,7 @@ def load_documents(
         Args:
             filter_ (Dict[str, Any]): The filter to apply to the collection.
             limit (Optional[int]): The number of documents to load.
+            projection: selection of fields to create Cursor
 
         Yields:
             Iterator[TDataItem]: An iterator of the loaded documents.
@@ -300,6 +301,7 @@ def load_documents(
         filter_: Dict[str, Any],
         limit: Optional[int] = None,
         projection: Optional[Union[Mapping[str, Any], Iterable[str]]] = None,
+        pymongoarrow_schema: Any = None,
     ) -> Iterator[Any]:
         """
         Load documents from the collection in Apache Arrow format.
@@ -307,12 +309,14 @@ def load_documents(
         Args:
             filter_ (Dict[str, Any]): The filter to apply to the collection.
             limit (Optional[int]): The number of documents to load.
+            projection: selection of fields to create Cursor
+            pymongoarrow_schema: mapping of field types to convert BSON to Arrow
 
         Yields:
             Iterator[Any]: An iterator of the loaded documents.
         """
         from pymongoarrow.context import PyMongoArrowContext  # type: ignore
-        from pymongoarrow.lib import process_bson_stream
+        from pymongoarrow.lib import process_bson_stream  # type: ignore
 
         filter_op = self._filter_op
         _raise_if_intersection(filter_op, filter_)
@@ -330,7 +334,8 @@ def load_documents(
         cursor = self._limit(cursor, limit)  # type: ignore
 
         context = PyMongoArrowContext.from_schema(
-            None, codec_options=self.collection.codec_options
+            schema=pymongoarrow_schema,
+            codec_options=self.collection.codec_options
         )
         for batch in cursor:
             process_bson_stream(batch, context)
@@ -343,6 +348,58 @@ class CollectionArrowLoaderParallel(CollectionLoaderParallel):
     Mongo DB collection parallel loader, which uses
     Apache Arrow for data processing.
     """
+    def load_documents(
+        self,
+        filter_: Dict[str, Any],
+        limit: Optional[int] = None,
+        projection: Optional[Union[Mapping[str, Any], Iterable[str]]] = None,
+        pymongoarrow_schema: Any = None,
+    ) -> Iterator[TDataItem]:
+        """Load documents from the collection in parallel.
+
+        Args:
+            filter_ (Dict[str, Any]): The filter to apply to the collection.
+            limit (Optional[int]): The number of documents to load.
+            projection: selection of fields to create Cursor
+            pymongoarrow_schema: mapping of field types to convert BSON to Arrow
+
+        Yields:
+            Iterator[TDataItem]: An iterator of the loaded documents.
+        """
+        yield from self._get_all_batches(
+            limit=limit,
+            filter_=filter_,
+            projection=projection,
+            pymongoarrow_schema=pymongoarrow_schema
+        )
+
+    def _get_all_batches(
+        self,
+        filter_: Dict[str, Any],
+        limit: Optional[int] = None,
+        projection: Optional[Union[Mapping[str, Any], Iterable[str]]] = None,
+        pymongoarrow_schema: Any = None,
+    ) -> Iterator[TDataItem]:
+        """Load all documents from the collection in parallel batches.
+
+        Args:
+            filter_ (Dict[str, Any]): The filter to apply to the collection.
+            limit (Optional[int]): The maximum number of documents to load.
+            projection: selection of fields to create Cursor
+            pymongoarrow_schema: mapping of field types to convert BSON to Arrow
+
+        Yields:
+            Iterator[TDataItem]: An iterator of the loaded documents.
+        """
+        batches = self._create_batches(limit=limit)
+        cursor = self._get_cursor(filter_=filter_, projection=projection)
+        for batch in batches:
+            yield self._run_batch(
+                cursor=cursor,
+                batch=batch,
+                pymongoarrow_schema=pymongoarrow_schema,
+            )
+
     def _get_cursor(
         self,
         filter_: Dict[str, Any],
@@ -352,6 +409,7 @@ def _get_cursor(
 
         Args:
             filter_ (Dict[str, Any]): The filter to apply to the collection.
+            projection: selection of fields to create Cursor
 
         Returns:
             Cursor: The cursor for the collection.
@@ -371,14 +429,20 @@ def _get_cursor(
         return cursor
 
     @dlt.defer
-    def _run_batch(self, cursor: TCursor, batch: Dict[str, int]) -> TDataItem:
+    def _run_batch(
+        self,
+        cursor: TCursor,
+        batch: Dict[str, int],
+        pymongoarrow_schema: Any = None,
+    ) -> TDataItem:
         from pymongoarrow.context import PyMongoArrowContext
         from pymongoarrow.lib import process_bson_stream
 
         cursor = cursor.clone()
 
         context = PyMongoArrowContext.from_schema(
-            None, codec_options=self.collection.codec_options
+            schema=pymongoarrow_schema,
+            codec_options=self.collection.codec_options
         )
         for chunk in cursor.skip(batch["skip"]).limit(batch["limit"]):
             process_bson_stream(chunk, context)
@@ -390,7 +454,8 @@ def collection_documents(
     client: TMongoClient,
     collection: TCollection,
     filter_: Dict[str, Any],
-    projection: Union[Dict[str, Any], List[str]],  # TODO kwargs reserved for dlt?
+    projection: Union[Dict[str, Any], List[str]],
+    pymongoarrow_schema: "pymongoarrow.schema.Schema",
     incremental: Optional[dlt.sources.incremental[Any]] = None,
     parallel: bool = False,
     limit: Optional[int] = None,
@@ -413,12 +478,13 @@ def collection_documents(
             Supported formats:
                 object - Python objects (dicts, lists).
                 arrow - Apache Arrow tables.
-        projection: (Optional[Union[Mapping[str, Any], Iterable[str]]]): The projection to select columns
+        projection: (Optional[Union[Mapping[str, Any], Iterable[str]]]): The projection to select fields
             when loading the collection. Supported inputs:
                 include (list) - ["year", "title"]
-                include (dict) - {"year": 1, "title": 1}
-                exclude (dict) - {"released": 0, "runtime": 0}
-            Note: Can't mix include and exclude statements '{"title": 1, "released": 0}`
+                include (dict) - {"year": True, "title": True}
+                exclude (dict) - {"released": False, "runtime": False}
+            Note: Can't mix include and exclude statements '{"title": True, "released": False}`
+        pymongoarrow_schema (pymongoarrow.schema.Schema): Mapping of expected field types of a collection to convert BSON to Arrow
 
     Returns:
         Iterable[DltResource]: A list of DLT resources for each collection to be loaded.
@@ -429,6 +495,19 @@ def collection_documents(
         )
         data_item_format = "object"
 
+    if data_item_format != "arrow" and pymongoarrow_schema:
+        dlt.common.logger.warn(
+            "Received value for `pymongoarrow_schema`, but `data_item_format=='object'` "
+            "Use `data_item_format=='arrow'` to enforce schema."
+        )
+
+    if data_item_format == "arrow" and pymongoarrow_schema and projection:
+        dlt.common.logger.warn(
+            "Received values for both `pymongoarrow_schema` and `projection`. Since both "
+            "create a projection to select fields, `projection` will be ignored."
+        )
+
+
     if parallel:
         if data_item_format == "arrow":
             LoaderClass = CollectionArrowLoaderParallel
@@ -443,11 +522,24 @@ def collection_documents(
     loader = LoaderClass(
         client, collection, incremental=incremental, chunk_size=chunk_size
     )
-    for data in loader.load_documents(limit=limit, filter_=filter_, projection=projection):
-        yield data
+    if isinstance(loader, (CollectionArrowLoader, CollectionArrowLoaderParallel)):
+        yield from loader.load_documents(
+            limit=limit,
+            filter_=filter_,
+            projection=projection,
+            pymongoarrow_schema=pymongoarrow_schema,
+        )
+    else:
+        yield from loader.load_documents(limit=limit, filter_=filter_, projection=projection)
 
 
 def convert_mongo_objs(value: Any) -> Any:
+    """MongoDB to dlt type conversion when using Python loaders.
+
+    Notes:
+        The method `ObjectId.__str__()` creates an hexstring using `binascii.hexlify(__id).decode()`
+
+    """
     if isinstance(value, (ObjectId, Decimal128)):
         return str(value)
     if isinstance(value, _datetime.datetime):
@@ -464,6 +556,13 @@ def convert_mongo_objs(value: Any) -> Any:
 def convert_arrow_columns(table: Any) -> Any:
     """Convert the given table columns to Python types.
 
+    Notes:
+        Calling str() matches the `convert_mongo_obs()` used in non-arrow code.
+        Pymongoarrow converts ObjectId to `fixed_size_binary[12]`, which can't be
+        converted to a string as a vectorized operation because it contains ASCII characters.
+
+        Instead, you need to loop over values using: `value.as_buffer().hex().decode()`
+
     Args:
         table (pyarrow.lib.Table): The table to convert.
 
@@ -539,6 +638,7 @@ class MongoDbCollectionResourceConfiguration(BaseConfiguration):
     incremental: Optional[dlt.sources.incremental] = None  # type: ignore[type-arg]
     write_disposition: Optional[str] = dlt.config.value
     parallel: Optional[bool] = False
+    projection: Optional[Union[Mapping[str, Any], Iterable[str]]] = dlt.config.value
 
 
 __source_name__ = "mongodb"
diff --git a/tests/mongodb/test_mongodb_source.py b/tests/mongodb/test_mongodb_source.py
index 88f4ba1c5..ec75a6dea 100644
--- a/tests/mongodb/test_mongodb_source.py
+++ b/tests/mongodb/test_mongodb_source.py
@@ -422,9 +422,7 @@ def test_projection_list_inclusion(destination_name):
     expected_columns = projection + ["_id", "_dlt_id", "_dlt_load_id"]
 
     movies = mongodb_collection(
-        collection=collection_name,
-        projection=projection,
-        limit=2
+        collection=collection_name, projection=projection, limit=2
     )
     pipeline.run(movies)
     loaded_columns = pipeline.default_schema.get_table_columns(collection_name).keys()
@@ -445,9 +443,7 @@ def test_projection_dict_inclusion(destination_name):
     expected_columns = list(projection.keys()) + ["_id", "_dlt_id", "_dlt_load_id"]
 
     movies = mongodb_collection(
-        collection=collection_name,
-        projection=projection,
-        limit=2
+        collection=collection_name, projection=projection, limit=2
     )
     pipeline.run(movies)
     loaded_columns = pipeline.default_schema.get_table_columns(collection_name).keys()
@@ -465,17 +461,28 @@ def test_projection_dict_exclusion(destination_name):
     )
     collection_name = "movies"
     columns_to_exclude = [
-        "runtime", "released", "year", "plot", "fullplot", "lastupdated", "type",
-        "directors", "imdb", "cast", "countries", "genres", "tomatoes", "num_mflix_comments",
-        "rated", "awards"
+        "runtime",
+        "released",
+        "year",
+        "plot",
+        "fullplot",
+        "lastupdated",
+        "type",
+        "directors",
+        "imdb",
+        "cast",
+        "countries",
+        "genres",
+        "tomatoes",
+        "num_mflix_comments",
+        "rated",
+        "awards",
     ]
     projection = {col: 0 for col in columns_to_exclude}
     expected_columns = ["title", "poster", "_id", "_dlt_id", "_dlt_load_id"]
 
     movies = mongodb_collection(
-        collection=collection_name,
-        projection=projection,
-        limit=2
+        collection=collection_name, projection=projection, limit=2
     )
     pipeline.run(movies)
     loaded_columns = pipeline.default_schema.get_table_columns(collection_name).keys()

From 393d2752129aa26666570f25d3a220ae5e86aaf8 Mon Sep 17 00:00:00 2001
From: zilto <zilto@github.com>
Date: Fri, 28 Feb 2025 15:17:16 -0500
Subject: [PATCH 4/4] fix linting and formatting

---
 sources/mongodb/__init__.py |  4 ++--
 sources/mongodb/helpers.py  | 40 +++++++++++++++++++++++++++----------
 2 files changed, 31 insertions(+), 13 deletions(-)

diff --git a/sources/mongodb/__init__.py b/sources/mongodb/__init__.py
index cea713a3e..f659f0c21 100644
--- a/sources/mongodb/__init__.py
+++ b/sources/mongodb/__init__.py
@@ -25,7 +25,7 @@ def mongodb(
     limit: Optional[int] = None,
     filter_: Optional[Dict[str, Any]] = None,
     projection: Optional[Union[Mapping[str, Any], Iterable[str]]] = None,
-    pymongoarrow_schema: Optional[Any] = None
+    pymongoarrow_schema: Optional[Any] = None,
 ) -> Iterable[DltResource]:
     """
     A DLT source which loads data from a mongo database using PyMongo.
@@ -104,7 +104,7 @@ def mongodb_collection(
     data_item_format: Optional[TDataItemFormat] = "object",
     filter_: Optional[Dict[str, Any]] = None,
     projection: Optional[Union[Mapping[str, Any], Iterable[str]]] = dlt.config.value,
-    pymongoarrow_schema: Optional[Any] = None
+    pymongoarrow_schema: Optional[Any] = None,
 ) -> Any:
     """
     A DLT source which loads a collection from a mongo database using PyMongo.
diff --git a/sources/mongodb/helpers.py b/sources/mongodb/helpers.py
index 817a58fdd..5584750bb 100644
--- a/sources/mongodb/helpers.py
+++ b/sources/mongodb/helpers.py
@@ -1,7 +1,18 @@
 """Mongo database source helpers"""
 
 from itertools import islice
-from typing import TYPE_CHECKING, Any, Dict, Iterator, List, Optional, Tuple, Union, Iterable, Mapping
+from typing import (
+    TYPE_CHECKING,
+    Any,
+    Dict,
+    Iterator,
+    List,
+    Optional,
+    Tuple,
+    Union,
+    Iterable,
+    Mapping,
+)
 
 import dlt
 from bson.decimal128 import Decimal128
@@ -23,7 +34,7 @@
 
 if TYPE_CHECKING:
     TMongoClient = MongoClient[Any]
-    TCollection = Collection[Any]  # type: ignore
+    TCollection = Collection[Any]
     TCursor = Cursor[Any]
 else:
     TMongoClient = Any
@@ -108,7 +119,9 @@ def _filter_op(self) -> Dict[str, Any]:
 
         return filt
 
-    def _projection_op(self, projection:Optional[Union[Mapping[str, Any], Iterable[str]]]) -> Optional[Dict[str, Any]]:
+    def _projection_op(
+        self, projection: Optional[Union[Mapping[str, Any], Iterable[str]]]
+    ) -> Optional[Dict[str, Any]]:
         """Build a projection operator.
 
         A tuple of fields to include or a dict specifying fields to include or exclude.
@@ -334,8 +347,7 @@ def load_documents(
         cursor = self._limit(cursor, limit)  # type: ignore
 
         context = PyMongoArrowContext.from_schema(
-            schema=pymongoarrow_schema,
-            codec_options=self.collection.codec_options
+            schema=pymongoarrow_schema, codec_options=self.collection.codec_options
         )
         for batch in cursor:
             process_bson_stream(batch, context)
@@ -348,6 +360,7 @@ class CollectionArrowLoaderParallel(CollectionLoaderParallel):
     Mongo DB collection parallel loader, which uses
     Apache Arrow for data processing.
     """
+
     def load_documents(
         self,
         filter_: Dict[str, Any],
@@ -370,7 +383,7 @@ def load_documents(
             limit=limit,
             filter_=filter_,
             projection=projection,
-            pymongoarrow_schema=pymongoarrow_schema
+            pymongoarrow_schema=pymongoarrow_schema,
         )
 
     def _get_all_batches(
@@ -441,8 +454,7 @@ def _run_batch(
         cursor = cursor.clone()
 
         context = PyMongoArrowContext.from_schema(
-            schema=pymongoarrow_schema,
-            codec_options=self.collection.codec_options
+            schema=pymongoarrow_schema, codec_options=self.collection.codec_options
         )
         for chunk in cursor.skip(batch["skip"]).limit(batch["limit"]):
             process_bson_stream(chunk, context)
@@ -507,7 +519,6 @@ def collection_documents(
             "create a projection to select fields, `projection` will be ignored."
         )
 
-
     if parallel:
         if data_item_format == "arrow":
             LoaderClass = CollectionArrowLoaderParallel
@@ -530,7 +541,9 @@ def collection_documents(
             pymongoarrow_schema=pymongoarrow_schema,
         )
     else:
-        yield from loader.load_documents(limit=limit, filter_=filter_, projection=projection)
+        yield from loader.load_documents(
+            limit=limit, filter_=filter_, projection=projection
+        )
 
 
 def convert_mongo_objs(value: Any) -> Any:
@@ -561,7 +574,12 @@ def convert_arrow_columns(table: Any) -> Any:
         Pymongoarrow converts ObjectId to `fixed_size_binary[12]`, which can't be
         converted to a string as a vectorized operation because it contains ASCII characters.
 
-        Instead, you need to loop over values using: `value.as_buffer().hex().decode()`
+        Instead, you need to loop over values using:
+        ```python
+        pyarrow.array([v.as_buffer().hex() for v in object_id_array], type=pyarrow.string())
+        # pymongoarrow simplifies this by allowing this syntax
+        [str(v) for v in object_id_array]
+        ```
 
     Args:
         table (pyarrow.lib.Table): The table to convert.