Package Methods (0.14.0a0)

_get_client_info(
    module: typing.Optional[str] = None,
) -> google.api_core.gapic_v1.client_info.ClientInfo

_get_storage_client(
    module: typing.Optional[str] = None,
) -> google.cloud.storage.client.Client

create_batches(
    gcs_bucket_name: str, gcs_prefix: str, batch_size: int = 1000
) -> typing.List[
    google.cloud.documentai_v1.types.document_io.BatchDocumentsInputConfig
]

create_gcs_uri(gcs_bucket_name: str, gcs_prefix: str) -> str

get_blob(
    gcs_uri: str, module: typing.Optional[str] = "get-bytes"
) -> google.cloud.storage.blob.Blob

get_blobs(
    gcs_uri: typing.Optional[str] = None,
    gcs_bucket_name: typing.Optional[str] = None,
    gcs_prefix: typing.Optional[str] = "/",
    module: typing.Optional[str] = "get-bytes",
) -> typing.List[google.cloud.storage.blob.Blob]

get_bytes(gcs_bucket_name: str, gcs_prefix: str) -> typing.List[bytes]

list_gcs_document_tree(
    gcs_bucket_name: str, gcs_prefix: str
) -> typing.Dict[str, typing.List[str]]

print_gcs_document_tree(
    gcs_bucket_name: str, gcs_prefix: str, files_to_display: int = 4
) -> None

split_gcs_uri(gcs_uri: str) -> typing.Tuple[str, str]

upload_file(
    gcs_output_directory: str,
    file_name: str,
    file_content: str,
    content_type: str = "application/json",
    module: typing.Optional[str] = "upload-file",
) -> None

_apply_text_offset(
    documentai_object: typing.Union[typing.Dict[str, typing.Dict], typing.List],
    text_offset: int,
) -> None

_bigquery_column_name(input_string: str) -> str

_dict_to_bigquery(
    dic: typing.Dict[str, typing.Union[str, typing.List[str]]],
    dataset_name: str,
    table_name: str,
    project_id: typing.Optional[str],
) -> google.cloud.bigquery.job.load.LoadJob

_entities_from_shards(
    shards: typing.List[google.cloud.documentai_v1.types.document.Document],
) -> typing.List[google.cloud.documentai_toolbox.wrappers.entity.Entity]

_get_batch_process_metadata(
    operation_name: str,
    location: typing.Optional[str] = None,
    timeout: typing.Optional[float] = None,
) -> google.cloud.documentai_v1.types.document_processor_service.BatchProcessMetadata

_get_shards(
    gcs_bucket_name: str, gcs_prefix: str
) -> typing.List[google.cloud.documentai_v1.types.document.Document]

_insert_into_dictionary_with_list(
    dic: typing.Dict[str, typing.Union[str, typing.List[str]]], key: str, value: str
) -> typing.Dict[str, typing.Union[str, typing.List[str]]]

_pages_from_shards(
    shards: typing.List[google.cloud.documentai_v1.types.document.Document],
) -> typing.List[google.cloud.documentai_toolbox.wrappers.page.Page]

_get_hocr_bounding_box(
    element_with_layout: typing.Union[
        google.cloud.documentai_v1.types.document.Document.Page.Paragraph,
        google.cloud.documentai_v1.types.document.Document.Page,
        google.cloud.documentai_v1.types.document.Document.Page.Token,
        google.cloud.documentai_v1.types.document.Document.Page.Block,
        google.cloud.documentai_v1.types.document.Document.Page.Symbol,
    ],
    page_dimension: google.cloud.documentai_v1.types.document.Document.Page.Dimension,
) -> typing.Optional[str]

_text_from_layout(
    layout: google.cloud.documentai_v1.types.document.Document.Page.Layout, text: str
) -> str

_trim_text(text: str) -> str

convert_document_to_annotate_file_json_response() -> str

convert_document_to_annotate_file_response() -> (
    google.cloud.vision_v1.types.image_annotator.AnnotateFileResponse
)

entities_to_bigquery(
    dataset_name: str, table_name: str, project_id: typing.Optional[str] = None
) -> google.cloud.bigquery.job.load.LoadJob

entities_to_dict() -> typing.Dict[str, typing.Union[str, typing.List[str]]]

export_hocr_str(title: str) -> str

export_images(
    output_path: str, output_file_prefix: str, output_file_extension: str
) -> typing.List[str]

form_fields_to_bigquery(
    dataset_name: str, table_name: str, project_id: typing.Optional[str] = None
) -> google.cloud.bigquery.job.load.LoadJob

form_fields_to_dict() -> typing.Dict[str, typing.Union[str, typing.List[str]]]

from_batch_process_metadata(
    metadata: google.cloud.documentai_v1.types.document_processor_service.BatchProcessMetadata,
) -> typing.List[google.cloud.documentai_toolbox.wrappers.document.Document]

from_batch_process_operation(
    location: str, operation_name: str, timeout: typing.Optional[float] = None
) -> typing.List[google.cloud.documentai_toolbox.wrappers.document.Document]

from_document_path(
    document_path: str,
) -> google.cloud.documentai_toolbox.wrappers.document.Document

from_documentai_document(
    documentai_document: google.cloud.documentai_v1.types.document.Document,
) -> google.cloud.documentai_toolbox.wrappers.document.Document

from_gcs(
    gcs_bucket_name: str, gcs_prefix: str, gcs_input_uri: typing.Optional[str] = None
) -> google.cloud.documentai_toolbox.wrappers.document.Document

from_gcs_uri(
    gcs_uri: str, gcs_input_uri: typing.Optional[str] = None
) -> google.cloud.documentai_toolbox.wrappers.document.Document

get_entity_by_type(
    target_type: str,
) -> typing.List[google.cloud.documentai_toolbox.wrappers.entity.Entity]

get_form_field_by_name(
    target_field: str,
) -> typing.List[google.cloud.documentai_toolbox.wrappers.page.FormField]

search_pages(
    target_string: typing.Optional[str] = None, pattern: typing.Optional[str] = None
) -> typing.List[google.cloud.documentai_toolbox.wrappers.page.Page]

split_pdf(pdf_path: str, output_path: str) -> typing.List[str]

to_merged_documentai_document() -> (
    google.cloud.documentai_v1.types.document.Document
)

crop_image(
    documentai_page: google.cloud.documentai_v1.types.document.Document.Page,
) -> typing.Optional[PIL.Image.Image]

_get_elements(element_type: typing.Type, attribute_name: str) -> typing.List

_extract_table_rows(
    table_rows: typing.Iterable[
        google.cloud.documentai_v1.types.document.Document.Page.Table.TableRow
    ],
) -> typing.List[typing.List[str]]

to_dataframe() -> pandas.core.frame.DataFrame

_get_children_of_element(
    potential_children: typing.List[
        google.cloud.documentai_toolbox.wrappers.page._BasePageElement
    ],
) -> typing.List[google.cloud.documentai_toolbox.wrappers.page._BasePageElement]