unstructured-ingest 0.3.13__py3-none-any.whl

unstructured_ingest/v2/processes/partitioner.py

@@ -0,0 +1,188 @@
+from abc import ABC
+from dataclasses import dataclass
+from pathlib import Path
+from typing import Any, Optional
+
+from pydantic import BaseModel, Field, SecretStr
+
+from unstructured_ingest.utils.data_prep import flatten_dict
+from unstructured_ingest.utils.dep_check import requires_dependencies
+from unstructured_ingest.v2.interfaces.process import BaseProcess
+from unstructured_ingest.v2.logger import logger
+from unstructured_ingest.v2.unstructured_api import call_api_async
+
+
+class PartitionerConfig(BaseModel):
+    strategy: str = Field(
+        default="auto",
+        description="The method that will be used to process the documents. ",
+        examples=["fast", "hi_res", "auto"],
+    )
+    ocr_languages: Optional[list[str]] = Field(
+        default=None,
+        description="A list of language packs to specify which languages to use for OCR, "
+        "The appropriate Tesseract language pack needs to be installed.",
+        examples=["eng", "deu", "eng,deu"],
+    )
+    encoding: Optional[str] = Field(
+        default=None,
+        description="Text encoding to use when reading documents. "
+        "By default the encoding is detected automatically.",
+    )
+    additional_partition_args: Optional[dict[str, Any]] = Field(
+        default=None, description="Additional values to pass through to partition()"
+    )
+    skip_infer_table_types: Optional[list[str]] = Field(
+        default=None, description="Optional list of document types to skip table extraction on"
+    )
+    fields_include: list[str] = Field(
+        default_factory=lambda: ["element_id", "text", "type", "metadata", "embeddings"],
+        description="If set, include the specified top-level fields in an element.",
+    )
+    flatten_metadata: bool = Field(
+        default=False,
+        description="Results in flattened json elements. "
+        "Specifically, the metadata key values are brought to "
+        "the top-level of the element, and the `metadata` key itself is removed.",
+    )
+    metadata_exclude: list[str] = Field(
+        default_factory=list,
+        description="If set, drop the specified metadata fields if they exist.",
+    )
+    element_exclude: list[str] = Field(
+        default_factory=list,
+        description="If set, drop the specified element types, if they exist.",
+    )
+    metadata_include: list[str] = Field(
+        default_factory=list,
+        description="If set, include the specified metadata "
+        "fields if they exist and drop all other fields. ",
+    )
+    partition_endpoint: Optional[str] = Field(
+        default="https://api.unstructuredapp.io/general/v0/general",
+        description="If partitioning via api, use the following host.",
+    )
+    partition_by_api: bool = Field(
+        default=False,
+        description="Use a remote API to partition the files."
+        " Otherwise, use the function from partition.auto",
+    )
+    api_key: Optional[SecretStr] = Field(
+        default=None, description="API Key for partition endpoint."
+    )
+    hi_res_model_name: Optional[str] = Field(
+        default=None, description="Model name for hi-res strategy."
+    )
+
+    def model_post_init(self, __context: Any) -> None:
+        if self.metadata_exclude and self.metadata_include:
+            raise ValueError(
+                "metadata_exclude and metadata_include are "
+                "mutually exclusive with each other. Cannot specify both."
+            )
+
+    def to_partition_kwargs(self) -> dict[str, Any]:
+        partition_kwargs: dict[str, Any] = {
+            "strategy": self.strategy,
+            "languages": self.ocr_languages,
+            "hi_res_model_name": self.hi_res_model_name,
+            "skip_infer_table_types": self.skip_infer_table_types,
+        }
+        # Don't inject information if None and allow default values in method to be used
+        partition_kwargs = {k: v for k, v in partition_kwargs.items() if v is not None}
+        if self.additional_partition_args:
+            partition_kwargs.update(self.additional_partition_args)
+        return partition_kwargs
+
+
+@dataclass
+class Partitioner(BaseProcess, ABC):
+    config: PartitionerConfig
+
+    def is_async(self) -> bool:
+        return self.config.partition_by_api
+
+    def postprocess(self, elements: list[dict]) -> list[dict]:
+        element_dicts = [e.copy() for e in elements]
+        if self.config.element_exclude:
+            element_dicts = list(
+                filter(
+                    lambda element: element["type"] not in self.config.element_exclude,
+                    element_dicts,
+                )
+            )
+        for elem in element_dicts:
+            if self.config.metadata_exclude:
+                ex_list = self.config.metadata_exclude
+                for ex in ex_list:
+                    if "." in ex:  # handle nested fields
+                        nested_fields = ex.split(".")
+                        current_elem = elem
+                        for f in nested_fields[:-1]:
+                            if f in current_elem:
+                                current_elem = current_elem[f]
+                        field_to_exclude = nested_fields[-1]
+                        if field_to_exclude in current_elem:
+                            current_elem.pop(field_to_exclude, None)
+                    else:  # handle top-level fields
+                        elem["metadata"].pop(ex, None)  # type: ignore[attr-defined]
+            elif self.config.metadata_include:
+                in_list = self.config.metadata_include
+                for k in list(elem["metadata"].keys()):  # type: ignore[attr-defined]
+                    if k not in in_list:
+                        elem["metadata"].pop(k, None)  # type: ignore[attr-defined]
+            in_list = self.config.fields_include
+            elem = {k: v for k, v in elem.items() if k in in_list}
+
+            if self.config.flatten_metadata and "metadata" in elem:
+                metadata = elem.pop("metadata")
+                elem.update(flatten_dict(metadata, keys_to_omit=["data_source_record_locator"]))
+        return element_dicts
+
+    @requires_dependencies(dependencies=["unstructured"])
+    def partition_locally(
+        self, filename: Path, metadata: Optional[dict] = None, **kwargs
+    ) -> list[dict]:
+        from unstructured.documents.elements import DataSourceMetadata
+        from unstructured.partition.auto import partition
+        from unstructured.staging.base import elements_to_dicts
+
+        @dataclass
+        class FileDataSourceMetadata(DataSourceMetadata):
+            filesize_bytes: Optional[int] = None
+
+        logger.debug(f"using local partition with kwargs: {self.config.to_partition_kwargs()}")
+        logger.debug(f"partitioning file {filename} with metadata {metadata}")
+        elements = partition(
+            filename=str(filename.resolve()),
+            data_source_metadata=FileDataSourceMetadata.from_dict(metadata),
+            **self.config.to_partition_kwargs(),
+        )
+        return self.postprocess(elements=elements_to_dicts(elements))
+
+    @requires_dependencies(dependencies=["unstructured_client"], extras="remote")
+    async def partition_via_api(
+        self, filename: Path, metadata: Optional[dict] = None, **kwargs
+    ) -> list[dict]:
+        metadata = metadata or {}
+        logger.debug(f"partitioning file {filename} with metadata: {metadata}")
+
+        elements = await call_api_async(
+            server_url=self.config.partition_endpoint,
+            api_key=self.config.api_key.get_secret_value(),
+            filename=filename,
+            api_parameters=self.config.to_partition_kwargs(),
+        )
+
+        # Append the data source metadata the auto partition does for you
+        for element in elements:
+            element["metadata"]["data_source"] = metadata
+        return self.postprocess(elements=elements)
+
+    def run(self, filename: Path, metadata: Optional[dict] = None, **kwargs) -> list[dict]:
+        return self.partition_locally(filename, metadata=metadata, **kwargs)
+
+    async def run_async(
+        self, filename: Path, metadata: Optional[dict] = None, **kwargs
+    ) -> list[dict]:
+        return await self.partition_via_api(filename, metadata=metadata, **kwargs)

unstructured_ingest/v2/processes/uncompress.py

@@ -0,0 +1,61 @@
+from abc import ABC
+from copy import copy
+from dataclasses import dataclass, field
+from pathlib import Path
+from typing import Any
+from uuid import NAMESPACE_DNS, uuid5
+
+from pydantic import BaseModel
+
+from unstructured_ingest.utils.compression import TAR_FILE_EXT, ZIP_FILE_EXT, uncompress_file
+from unstructured_ingest.v2.interfaces import FileData, SourceIdentifiers
+from unstructured_ingest.v2.interfaces.process import BaseProcess
+from unstructured_ingest.v2.logger import logger
+
+
+class UncompressConfig(BaseModel):
+    pass
+
+
+@dataclass
+class Uncompressor(BaseProcess, ABC):
+    config: UncompressConfig = field(default_factory=UncompressConfig)
+
+    def is_async(self) -> bool:
+        return True
+
+    def run(self, file_data: FileData, **kwargs: Any) -> list[FileData]:
+        local_filepath = Path(file_data.local_download_path)
+        if local_filepath.suffix not in TAR_FILE_EXT + ZIP_FILE_EXT:
+            return [file_data]
+        new_path = uncompress_file(filename=str(local_filepath))
+        new_files = [i for i in Path(new_path).rglob("*") if i.is_file()]
+        responses = []
+        logger.debug(
+            "uncompressed {} files from original file {}: {}".format(
+                len(new_files), local_filepath, ", ".join([str(f) for f in new_files])
+            )
+        )
+        for f in new_files:
+            new_file_data = copy(file_data)
+            new_file_data.identifier = str(uuid5(NAMESPACE_DNS, str(f)))
+            new_file_data.local_download_path = str(f.resolve())
+            new_rel_download_path = str(f).replace(str(Path(local_filepath.parent)), "")[1:]
+            new_file_data.source_identifiers = SourceIdentifiers(
+                filename=f.name,
+                fullpath=str(file_data.source_identifiers.fullpath).replace(
+                    file_data.source_identifiers.filename, new_rel_download_path
+                ),
+                rel_path=(
+                    str(file_data.source_identifiers.rel_path).replace(
+                        file_data.source_identifiers.filename, new_rel_download_path
+                    )
+                    if file_data.source_identifiers.rel_path
+                    else None
+                ),
+            )
+            responses.append(new_file_data)
+        return responses
+
+    async def run_async(self, file_data: FileData, **kwargs: Any) -> list[FileData]:
+        return self.run(file_data=file_data, **kwargs)

unstructured_ingest/v2/unstructured_api.py

@@ -0,0 +1,128 @@
+from dataclasses import fields
+from pathlib import Path
+from typing import TYPE_CHECKING, Optional
+
+from unstructured_ingest.v2.errors import ProviderError, QuotaError, UserAuthError, UserError
+from unstructured_ingest.v2.logger import logger
+
+if TYPE_CHECKING:
+    from unstructured_client.models.operations import PartitionRequest
+
+
+def create_partition_request(filename: Path, parameters_dict: dict) -> "PartitionRequest":
+    """Given a filename and a dict of API parameters, return a PartitionRequest for use
+    by unstructured-client. Remove any params that aren't recognized by the SDK.
+
+    Args:
+        filename: Path to the file being partitioned
+        parameters_dict: A mapping of all API params we want to send
+
+    Returns: A PartitionRequest containing the file and all valid params
+    """
+    from unstructured_client.models.operations import PartitionRequest
+    from unstructured_client.models.shared import Files, PartitionParameters
+
+    # NOTE(austin): PartitionParameters is a Pydantic model in v0.26.0
+    # Prior to this it was a dataclass which doesn't have .__fields
+    try:
+        possible_fields = PartitionParameters.model_fields
+    except AttributeError:
+        possible_fields = [f.name for f in fields(PartitionParameters)]
+
+    filtered_partition_request = {k: v for k, v in parameters_dict.items() if k in possible_fields}
+    if len(filtered_partition_request) != len(parameters_dict):
+        logger.debug(
+            "Following fields were omitted due to not being "
+            "supported by the currently used unstructured client: {}".format(
+                ", ".join([v for v in parameters_dict if v not in filtered_partition_request])
+            )
+        )
+
+    logger.debug(f"using hosted partitioner with kwargs: {parameters_dict}")
+
+    with open(filename, "rb") as f:
+        files = Files(
+            content=f.read(),
+            file_name=str(filename.resolve()),
+        )
+        filtered_partition_request["files"] = files
+
+    partition_params = PartitionParameters(**filtered_partition_request)
+
+    return PartitionRequest(partition_parameters=partition_params)
+
+
+def wrap_error(e: Exception) -> Exception:
+    from unstructured_client.models.errors.sdkerror import SDKError
+
+    if not isinstance(e, SDKError):
+        logger.error(f"Uncaught Error calling API: {e}")
+        raise e
+    status_code = e.status_code
+    body = e.body
+    if status_code == 402:
+        return QuotaError(body)
+    if status_code in [401, 403]:
+        return UserAuthError(body)
+    if 400 <= status_code < 500:
+        return UserError(body)
+    if status_code >= 500:
+        return ProviderError(body)
+    logger.error(f"Uncaught Error calling API: {e}")
+    raise e
+
+
+async def call_api_async(
+    server_url: Optional[str], api_key: Optional[str], filename: Path, api_parameters: dict
+) -> list[dict]:
+    """Call the Unstructured API using unstructured-client.
+
+    Args:
+        server_url: The base URL where the API is hosted
+        api_key: The user's API key (can be empty if this is a self hosted API)
+        filename: Path to the file being partitioned
+        api_parameters: A dict containing the requested API parameters
+
+    Returns: A list of the file's elements, or an empty list if there was an error
+    """
+    from unstructured_client import UnstructuredClient
+
+    client = UnstructuredClient(
+        server_url=server_url,
+        api_key_auth=api_key,
+    )
+    partition_request = create_partition_request(filename=filename, parameters_dict=api_parameters)
+    try:
+        res = await client.general.partition_async(request=partition_request)
+    except Exception as e:
+        raise wrap_error(e)
+
+    return res.elements or []
+
+
+def call_api(
+    server_url: Optional[str], api_key: Optional[str], filename: Path, api_parameters: dict
+) -> list[dict]:
+    """Call the Unstructured API using unstructured-client.
+
+    Args:
+        server_url: The base URL where the API is hosted
+        api_key: The user's API key (can be empty if this is a self hosted API)
+        filename: Path to the file being partitioned
+        api_parameters: A dict containing the requested API parameters
+
+    Returns: A list of the file's elements, or an empty list if there was an error
+    """
+    from unstructured_client import UnstructuredClient
+
+    client = UnstructuredClient(
+        server_url=server_url,
+        api_key_auth=api_key,
+    )
+    partition_request = create_partition_request(filename=filename, parameters_dict=api_parameters)
+    try:
+        res = client.general.partition(request=partition_request)
+    except Exception as e:
+        raise wrap_error(e)
+
+    return res.elements or []

unstructured_ingest/v2/utils.py

@@ -0,0 +1,61 @@
+import json
+from datetime import datetime
+from inspect import isclass
+from pathlib import Path
+from typing import Any
+from uuid import NAMESPACE_DNS, uuid5
+
+from pydantic import BaseModel
+from pydantic.types import _SecretBase
+
+from unstructured_ingest.v2.interfaces import FileData
+
+
+def is_secret(value: Any) -> bool:
+    # Case Secret[int]
+    if hasattr(value, "__origin__") and hasattr(value, "__args__"):
+        origin = value.__origin__
+        return isclass(origin) and issubclass(origin, _SecretBase)
+    # Case SecretStr
+    return isclass(value) and issubclass(value, _SecretBase)
+
+
+def serialize_base_model(model: BaseModel) -> dict:
+    # To get the full serialized dict regardless of if values are marked as Secret
+    model_dict = model.model_dump()
+    return serialize_base_dict(model_dict=model_dict)
+
+
+def serialize_base_dict(model_dict: dict) -> dict:
+    model_dict = model_dict.copy()
+    for k, v in model_dict.items():
+        if isinstance(v, _SecretBase):
+            secret_value = v.get_secret_value()
+            if isinstance(secret_value, BaseModel):
+                model_dict[k] = serialize_base_model(model=secret_value)
+            else:
+                model_dict[k] = secret_value
+        if isinstance(v, dict):
+            model_dict[k] = serialize_base_dict(model_dict=v)
+
+    return model_dict
+
+
+def serialize_base_model_json(model: BaseModel, **json_kwargs) -> str:
+    model_dict = serialize_base_model(model=model)
+
+    def json_serial(obj):
+        if isinstance(obj, Path):
+            return obj.as_posix()
+        if isinstance(obj, datetime):
+            return obj.isoformat()
+        raise TypeError("Type %s not serializable" % type(obj))
+
+    # Support json dumps kwargs such as sort_keys
+    return json.dumps(model_dict, default=json_serial, **json_kwargs)
+
+
+def get_enhanced_element_id(element_dict: dict, file_data: FileData) -> str:
+    element_id = element_dict.get("element_id")
+    new_data = f"{element_id}{file_data.identifier}"
+    return str(uuid5(NAMESPACE_DNS, new_data))

unstructured_ingest-0.3.13.dist-info/LICENSE.md

@@ -0,0 +1,201 @@
+                                 Apache License
+                           Version 2.0, January 2004
+                        http://www.apache.org/licenses/
+
+   TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
+
+   1. Definitions.
+
+      "License" shall mean the terms and conditions for use, reproduction,
+      and distribution as defined by Sections 1 through 9 of this document.
+
+      "Licensor" shall mean the copyright owner or entity authorized by
+      the copyright owner that is granting the License.
+
+      "Legal Entity" shall mean the union of the acting entity and all
+      other entities that control, are controlled by, or are under common
+      control with that entity. For the purposes of this definition,
+      "control" means (i) the power, direct or indirect, to cause the
+      direction or management of such entity, whether by contract or
+      otherwise, or (ii) ownership of fifty percent (50%) or more of the
+      outstanding shares, or (iii) beneficial ownership of such entity.
+
+      "You" (or "Your") shall mean an individual or Legal Entity
+      exercising permissions granted by this License.
+
+      "Source" form shall mean the preferred form for making modifications,
+      including but not limited to software source code, documentation
+      source, and configuration files.
+
+      "Object" form shall mean any form resulting from mechanical
+      transformation or translation of a Source form, including but
+      not limited to compiled object code, generated documentation,
+      and conversions to other media types.
+
+      "Work" shall mean the work of authorship, whether in Source or
+      Object form, made available under the License, as indicated by a
+      copyright notice that is included in or attached to the work
+      (an example is provided in the Appendix below).
+
+      "Derivative Works" shall mean any work, whether in Source or Object
+      form, that is based on (or derived from) the Work and for which the
+      editorial revisions, annotations, elaborations, or other modifications
+      represent, as a whole, an original work of authorship. For the purposes
+      of this License, Derivative Works shall not include works that remain
+      separable from, or merely link (or bind by name) to the interfaces of,
+      the Work and Derivative Works thereof.
+
+      "Contribution" shall mean any work of authorship, including
+      the original version of the Work and any modifications or additions
+      to that Work or Derivative Works thereof, that is intentionally
+      submitted to Licensor for inclusion in the Work by the copyright owner
+      or by an individual or Legal Entity authorized to submit on behalf of
+      the copyright owner. For the purposes of this definition, "submitted"
+      means any form of electronic, verbal, or written communication sent
+      to the Licensor or its representatives, including but not limited to
+      communication on electronic mailing lists, source code control systems,
+      and issue tracking systems that are managed by, or on behalf of, the
+      Licensor for the purpose of discussing and improving the Work, but
+      excluding communication that is conspicuously marked or otherwise
+      designated in writing by the copyright owner as "Not a Contribution."
+
+      "Contributor" shall mean Licensor and any individual or Legal Entity
+      on behalf of whom a Contribution has been received by Licensor and
+      subsequently incorporated within the Work.
+
+   2. Grant of Copyright License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      copyright license to reproduce, prepare Derivative Works of,
+      publicly display, publicly perform, sublicense, and distribute the
+      Work and such Derivative Works in Source or Object form.
+
+   3. Grant of Patent License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      (except as stated in this section) patent license to make, have made,
+      use, offer to sell, sell, import, and otherwise transfer the Work,
+      where such license applies only to those patent claims licensable
+      by such Contributor that are necessarily infringed by their
+      Contribution(s) alone or by combination of their Contribution(s)
+      with the Work to which such Contribution(s) was submitted. If You
+      institute patent litigation against any entity (including a
+      cross-claim or counterclaim in a lawsuit) alleging that the Work
+      or a Contribution incorporated within the Work constitutes direct
+      or contributory patent infringement, then any patent licenses
+      granted to You under this License for that Work shall terminate
+      as of the date such litigation is filed.
+
+   4. Redistribution. You may reproduce and distribute copies of the
+      Work or Derivative Works thereof in any medium, with or without
+      modifications, and in Source or Object form, provided that You
+      meet the following conditions:
+
+      (a) You must give any other recipients of the Work or
+          Derivative Works a copy of this License; and
+
+      (b) You must cause any modified files to carry prominent notices
+          stating that You changed the files; and
+
+      (c) You must retain, in the Source form of any Derivative Works
+          that You distribute, all copyright, patent, trademark, and
+          attribution notices from the Source form of the Work,
+          excluding those notices that do not pertain to any part of
+          the Derivative Works; and
+
+      (d) If the Work includes a "NOTICE" text file as part of its
+          distribution, then any Derivative Works that You distribute must
+          include a readable copy of the attribution notices contained
+          within such NOTICE file, excluding those notices that do not
+          pertain to any part of the Derivative Works, in at least one
+          of the following places: within a NOTICE text file distributed
+          as part of the Derivative Works; within the Source form or
+          documentation, if provided along with the Derivative Works; or,
+          within a display generated by the Derivative Works, if and
+          wherever such third-party notices normally appear. The contents
+          of the NOTICE file are for informational purposes only and
+          do not modify the License. You may add Your own attribution
+          notices within Derivative Works that You distribute, alongside
+          or as an addendum to the NOTICE text from the Work, provided
+          that such additional attribution notices cannot be construed
+          as modifying the License.
+
+      You may add Your own copyright statement to Your modifications and
+      may provide additional or different license terms and conditions
+      for use, reproduction, or distribution of Your modifications, or
+      for any such Derivative Works as a whole, provided Your use,
+      reproduction, and distribution of the Work otherwise complies with
+      the conditions stated in this License.
+
+   5. Submission of Contributions. Unless You explicitly state otherwise,
+      any Contribution intentionally submitted for inclusion in the Work
+      by You to the Licensor shall be under the terms and conditions of
+      this License, without any additional terms or conditions.
+      Notwithstanding the above, nothing herein shall supersede or modify
+      the terms of any separate license agreement you may have executed
+      with Licensor regarding such Contributions.
+
+   6. Trademarks. This License does not grant permission to use the trade
+      names, trademarks, service marks, or product names of the Licensor,
+      except as required for reasonable and customary use in describing the
+      origin of the Work and reproducing the content of the NOTICE file.
+
+   7. Disclaimer of Warranty. Unless required by applicable law or
+      agreed to in writing, Licensor provides the Work (and each
+      Contributor provides its Contributions) on an "AS IS" BASIS,
+      WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
+      implied, including, without limitation, any warranties or conditions
+      of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
+      PARTICULAR PURPOSE. You are solely responsible for determining the
+      appropriateness of using or redistributing the Work and assume any
+      risks associated with Your exercise of permissions under this License.
+
+   8. Limitation of Liability. In no event and under no legal theory,
+      whether in tort (including negligence), contract, or otherwise,
+      unless required by applicable law (such as deliberate and grossly
+      negligent acts) or agreed to in writing, shall any Contributor be
+      liable to You for damages, including any direct, indirect, special,
+      incidental, or consequential damages of any character arising as a
+      result of this License or out of the use or inability to use the
+      Work (including but not limited to damages for loss of goodwill,
+      work stoppage, computer failure or malfunction, or any and all
+      other commercial damages or losses), even if such Contributor
+      has been advised of the possibility of such damages.
+
+   9. Accepting Warranty or Additional Liability. While redistributing
+      the Work or Derivative Works thereof, You may choose to offer,
+      and charge a fee for, acceptance of support, warranty, indemnity,
+      or other liability obligations and/or rights consistent with this
+      License. However, in accepting such obligations, You may act only
+      on Your own behalf and on Your sole responsibility, not on behalf
+      of any other Contributor, and only if You agree to indemnify,
+      defend, and hold each Contributor harmless for any liability
+      incurred by, or claims asserted against, such Contributor by reason
+      of your accepting any such warranty or additional liability.
+
+   END OF TERMS AND CONDITIONS
+
+   APPENDIX: How to apply the Apache License to your work.
+
+      To apply the Apache License to your work, attach the following
+      boilerplate notice, with the fields enclosed by brackets "[]"
+      replaced with your own identifying information. (Don't include
+      the brackets!)  The text should be enclosed in the appropriate
+      comment syntax for the file format. We also recommend that a
+      file or class name and description of purpose be included on the
+      same "printed page" as the copyright notice for easier
+      identification within third-party archives.
+
+   Copyright 2022 Unstructured Technologies, Inc
+
+   Licensed under the Apache License, Version 2.0 (the "License");
+   you may not use this file except in compliance with the License.
+   You may obtain a copy of the License at
+
+       http://www.apache.org/licenses/LICENSE-2.0
+
+   Unless required by applicable law or agreed to in writing, software
+   distributed under the License is distributed on an "AS IS" BASIS,
+   WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+   See the License for the specific language governing permissions and
+   limitations under the License.