Index

A

ABOVE (textractor.data.constants.Direction attribute) ACCOUNT_NUMBER (textractor.data.constants.AnalyzeExpenseFields attribute) add_cells() (textractor.entities.table.Table method) add_children() (textractor.entities.document_entity.DocumentEntity method) add_prefixes_and_suffixes_as_words (textractor.data.text_linearization_config.TextLinearizationConfig attribute) add_prefixes_and_suffixes_in_text (textractor.data.text_linearization_config.TextLinearizationConfig attribute) ADDRESS (textractor.data.constants.AnalyzeExpenseFields attribute) (textractor.data.constants.AnalyzeIDFields attribute) ADDRESS_BLOCK (textractor.data.constants.AnalyzeExpenseFields attribute) ALL (textractor.data.constants.CLIOverlay attribute) (textractor.data.constants.CLIPrint attribute)

AMOUNT_DUE (textractor.data.constants.AnalyzeExpenseFields attribute) AMOUNT_PAID (textractor.data.constants.AnalyzeExpenseFields attribute) ANALYZE (textractor.data.constants.TextractAPI attribute) analyze_document() (textractor.textractor.Textractor method) analyze_expense() (textractor.textractor.Textractor method) analyze_id() (textractor.textractor.Textractor method) AnalyzeExpenseFields (class in textractor.data.constants) AnalyzeExpenseFieldsGroup (class in textractor.data.constants) AnalyzeExpenseLineItemFields (class in textractor.data.constants) AnalyzeIDFields (class in textractor.data.constants) area (textractor.entities.bbox.BoundingBox property) as_denormalized_numpy() (textractor.entities.bbox.BoundingBox method)

B

bbox (textractor.entities.document_entity.DocumentEntity property) (textractor.entities.expense_document.ExpenseDocument property) (textractor.entities.expense_field.ExpenseField property) (textractor.entities.expense_field.LineItemGroup property) (textractor.entities.expense_field.LineItemRow property)

BELOW (textractor.data.constants.Direction attribute) BoundingBox (class in textractor.entities.bbox)

C

CellTypes (class in textractor.data.constants) center_is_inside() (textractor.entities.bbox.BoundingBox class method) checkboxes (textractor.entities.document.Document property) (textractor.entities.page.Page property) (textractor.entities.table.Table property) (textractor.entities.table_cell.TableCell property) children (textractor.entities.document_entity.DocumentEntity property) CITY (textractor.data.constants.AnalyzeExpenseFields attribute) CITY_IN_ADDRESS (textractor.data.constants.AnalyzeIDFields attribute) CLASS (textractor.data.constants.AnalyzeIDFields attribute) CLIOverlay (class in textractor.data.constants) CLIPrint (class in textractor.data.constants) col_index (textractor.entities.table_cell.TableCell property) col_span (textractor.entities.table_cell.TableCell property)

column_count (textractor.entities.table.Table property) COLUMN_HEADER (textractor.data.constants.CellTypes attribute) column_headers (textractor.entities.table.Table property) confidence (textractor.entities.document_entity.DocumentEntity property) (textractor.entities.expense_field.ExpenseType attribute) (textractor.entities.identity_field.IdentityField property) container_layouts (textractor.entities.page.Page property) contains_checkbox (textractor.entities.value.Value property) COSINE (textractor.data.constants.SimilarityMetric attribute) COUNTRY (textractor.data.constants.AnalyzeExpenseFields attribute) COUNTY (textractor.data.constants.AnalyzeIDFields attribute) create_expense_from_field() (in module textractor.parsers.response_parser) CSV (textractor.data.constants.TableFormat attribute) CUSTOMER_NUMBER (textractor.data.constants.AnalyzeExpenseFields attribute)

D

DATE_OF_BIRTH (textractor.data.constants.AnalyzeIDFields attribute) DATE_OF_ISSUE (textractor.data.constants.AnalyzeIDFields attribute) DELIVERY_DATE (textractor.data.constants.AnalyzeExpenseFields attribute) detect_document_text() (textractor.textractor.Textractor method) DETECT_TEXT (textractor.data.constants.TextractAPI attribute) Direction (class in textractor.data.constants) directional_finder() (textractor.entities.document.Document method) (textractor.entities.page.Page method)

DirectionalFinderType (class in textractor.data.constants) DISCOUNT (textractor.data.constants.AnalyzeExpenseFields attribute) Document (class in textractor.entities.document) document (textractor.entities.lazy_document.LazyDocument property) DOCUMENT_NUMBER (textractor.data.constants.AnalyzeIDFields attribute) DocumentEntity (class in textractor.entities.document_entity) DUE_DATE (textractor.data.constants.AnalyzeExpenseFields attribute)

E

enclosing_bbox() (textractor.entities.bbox.BoundingBox class method) ENDORSEMENTS (textractor.data.constants.AnalyzeIDFields attribute) entity_layout_prefix (textractor.data.text_linearization_config.TextLinearizationConfig attribute) entity_layout_suffix (textractor.data.text_linearization_config.TextLinearizationConfig attribute) EntityList (class in textractor.visualizers.entitylist) EUCLIDEAN (textractor.data.constants.SimilarityMetric attribute) Expense (class in textractor.entities.expense_field) EXPENSE (textractor.data.constants.TextractAPI attribute) expense_documents (textractor.entities.document.Document property) (textractor.entities.page.Page property) EXPENSE_ROW (textractor.data.constants.AnalyzeExpenseLineItemFields attribute) ExpenseDocument (class in textractor.entities.expense_document)

ExpenseField (class in textractor.entities.expense_field) ExpenseGroupProperty (class in textractor.entities.expense_field) EXPENSES (textractor.data.constants.CLIPrint attribute) expenses (textractor.entities.expense_field.LineItemRow property) ExpenseType (class in textractor.entities.expense_field) EXPIRATION_DATE (textractor.data.constants.AnalyzeIDFields attribute) export_kv_to_csv() (textractor.entities.document.Document method) (textractor.entities.page.Page method) export_kv_to_txt() (textractor.entities.document.Document method) (textractor.entities.page.Page method) export_tables_to_excel() (textractor.entities.document.Document method) (textractor.entities.page.Page method)

F

FANCY_GRID (textractor.data.constants.TableFormat attribute) Fields (class in textractor.entities.expense_document) fields (textractor.entities.identity_document.IdentityDocument property) FieldsGroups (class in textractor.entities.expense_document) figure_layout_prefix (textractor.data.text_linearization_config.TextLinearizationConfig attribute) figure_layout_suffix (textractor.data.text_linearization_config.TextLinearizationConfig attribute) figures (textractor.entities.page_layout.PageLayout property) filter_checkboxes() (textractor.entities.document.Document method) (textractor.entities.page.Page method) FIRST_NAME (textractor.data.constants.AnalyzeIDFields attribute) FLOATING_FOOTER (textractor.data.constants.CellTypes attribute) FLOATING_TITLE (textractor.data.constants.CellTypes attribute)

footer_layout_prefix (textractor.data.text_linearization_config.TextLinearizationConfig attribute) footer_layout_suffix (textractor.data.text_linearization_config.TextLinearizationConfig attribute) footers (textractor.entities.page_layout.PageLayout property) (textractor.entities.table.Table property) FORMS (textractor.data.constants.CLIOverlay attribute) (textractor.data.constants.CLIPrint attribute) (textractor.data.constants.TextractFeatures attribute) from_denormalized_borders() (textractor.entities.bbox.BoundingBox class method) from_denormalized_corners() (textractor.entities.bbox.BoundingBox class method) from_denormalized_dict() (textractor.entities.bbox.BoundingBox class method) from_denormalized_xywh() (textractor.entities.bbox.BoundingBox class method) from_normalized_dict() (textractor.entities.bbox.BoundingBox class method)

G

geometry (textractor.entities.expense_field.Expense property) get() (textractor.entities.document.Document method) (textractor.entities.expense_field.LineItemRow method) (textractor.entities.identity_document.IdentityDocument method) (textractor.entities.page.Page method) get_cells_by_type() (textractor.entities.table.Table method) get_columns_by_name() (textractor.entities.table.Table method) get_distance() (textractor.entities.bbox.BoundingBox method) get_group_bboxes() (textractor.entities.expense_document.FieldsGroups method) get_intersection() (textractor.entities.bbox.BoundingBox method) get_result() (textractor.textractor.Textractor method) get_table_range() (textractor.entities.table.Table method) get_text() (textractor.entities.linearizable.Linearizable method) get_text_and_words() (textractor.entities.document.Document method) (textractor.entities.expense_document.ExpenseDocument method) (textractor.entities.expense_field.Expense method) (textractor.entities.expense_field.ExpenseField method) (textractor.entities.expense_field.LineItemGroup method) (textractor.entities.expense_field.LineItemRow method) (textractor.entities.key_value.KeyValue method) (textractor.entities.layout.Layout method) (textractor.entities.line.Line method) (textractor.entities.linearizable.Linearizable method) (textractor.entities.page.Page method) (textractor.entities.query.Query method) (textractor.entities.query_result.QueryResult method) (textractor.entities.selection_element.SelectionElement method) (textractor.entities.signature.Signature method) (textractor.entities.table.Table method) (textractor.entities.table_cell.TableCell method) (textractor.entities.table_footer.TableFooter method) (textractor.entities.table_title.TableTitle method) (textractor.entities.value.Value method) (textractor.entities.word.Word method) (textractor.visualizers.entitylist.EntityList method)

get_words_by_type() (textractor.entities.document.Document method) (textractor.entities.key_value.KeyValue method) (textractor.entities.line.Line method) (textractor.entities.page.Page method) (textractor.entities.table.Table method) (textractor.entities.table_cell.TableCell method) (textractor.entities.value.Value method) GITHUB (textractor.data.constants.TableFormat attribute) GRATUITY (textractor.data.constants.AnalyzeExpenseFields attribute) GRID (textractor.data.constants.TableFormat attribute) group_properties (textractor.entities.expense_field.ExpenseField property)

H

HANDWRITING (textractor.data.constants.TextTypes attribute) has_result (textractor.entities.query.Query property) header_prefix (textractor.data.text_linearization_config.TextLinearizationConfig attribute) header_suffix (textractor.data.text_linearization_config.TextLinearizationConfig attribute) headers (textractor.entities.page_layout.PageLayout property) height (textractor.entities.document_entity.DocumentEntity property) heuristic_h_tolerance (textractor.data.text_linearization_config.TextLinearizationConfig attribute) heuristic_line_break_threshold (textractor.data.text_linearization_config.TextLinearizationConfig attribute)

heuristic_overlap_ratio (textractor.data.text_linearization_config.TextLinearizationConfig attribute) hide_figure_layout (textractor.data.text_linearization_config.TextLinearizationConfig attribute) hide_footer_layout (textractor.data.text_linearization_config.TextLinearizationConfig attribute) hide_header_layout (textractor.data.text_linearization_config.TextLinearizationConfig attribute) hide_key_value_layout (textractor.data.text_linearization_config.TextLinearizationConfig attribute) hide_page_num_layout (textractor.data.text_linearization_config.TextLinearizationConfig attribute) hide_table_layout (textractor.data.text_linearization_config.TextLinearizationConfig attribute) HTML (textractor.data.constants.TableFormat attribute)

I

id (textractor.entities.expense_field.ExpenseGroupProperty attribute) ID_TYPE (textractor.data.constants.AnalyzeIDFields attribute) identity_document (textractor.entities.document.Document property) identity_documents (textractor.entities.document.Document property) IdentityDocument (class in textractor.entities.identity_document) IdentityField (class in textractor.entities.identity_field) IDS (textractor.data.constants.CLIPrint attribute) images (textractor.entities.document.Document property) independent_words() (textractor.entities.document.Document method) (textractor.entities.page.Page method) index (textractor.entities.expense_field.LineItemGroup property)

INVOICE_RECEIPT_DATE (textractor.data.constants.AnalyzeExpenseFields attribute) INVOICE_RECEIPT_ID (textractor.data.constants.AnalyzeExpenseFields attribute) is_column_header (textractor.entities.table_cell.TableCell property) is_floating (textractor.entities.table_title.TableTitle property) is_footer (textractor.entities.table_cell.TableCell property) is_inside() (textractor.entities.bbox.BoundingBox class method) is_section_title (textractor.entities.table_cell.TableCell property) is_selected() (textractor.entities.key_value.KeyValue method) (textractor.entities.selection_element.SelectionElement method) is_summary (textractor.entities.table_cell.TableCell property) is_title (textractor.entities.table_cell.TableCell property) ITEM (textractor.data.constants.AnalyzeExpenseLineItemFields attribute)

J

JIRA (textractor.data.constants.TableFormat attribute)

K

key (textractor.entities.expense_field.ExpenseField property) (textractor.entities.identity_field.IdentityField property) (textractor.entities.key_value.KeyValue property) key_id (textractor.entities.value.Value property) key_prefix (textractor.data.text_linearization_config.TextLinearizationConfig attribute) key_suffix (textractor.data.text_linearization_config.TextLinearizationConfig attribute) key_value_layout_prefix (textractor.data.text_linearization_config.TextLinearizationConfig attribute) key_value_layout_suffix (textractor.data.text_linearization_config.TextLinearizationConfig attribute) key_value_prefix (textractor.data.text_linearization_config.TextLinearizationConfig attribute)

KEY_VALUE_SET (textractor.data.constants.DirectionalFinderType attribute) (textractor.data.constants.TextractType attribute) key_value_suffix (textractor.data.text_linearization_config.TextLinearizationConfig attribute) key_values (textractor.entities.document.Document property) (textractor.entities.page.Page property) (textractor.entities.page_layout.PageLayout property) keys() (textractor.entities.document.Document method) (textractor.entities.identity_document.IdentityDocument method) (textractor.entities.page.Page method) KeyValue (class in textractor.entities.key_value)

L

LAST_NAME (textractor.data.constants.AnalyzeIDFields attribute) LATEX (textractor.data.constants.TableFormat attribute) LATEX_BOOKTABS (textractor.data.constants.TableFormat attribute) LATEX_LONGTABLE (textractor.data.constants.TableFormat attribute) LATEX_RAW (textractor.data.constants.TableFormat attribute) Layout (class in textractor.entities.layout) LAYOUT (textractor.data.constants.TextractFeatures attribute) layout_element_separator (textractor.data.text_linearization_config.TextLinearizationConfig attribute) LAYOUTS (textractor.data.constants.CLIOverlay attribute) (textractor.data.constants.CLIPrint attribute) layouts (textractor.entities.document.Document property) (textractor.entities.page.Page property) LazyDocument (class in textractor.entities.lazy_document) leaf_layouts (textractor.entities.page.Page property) LEFT (textractor.data.constants.Direction attribute)

LEVENSHTEIN (textractor.data.constants.SimilarityMetric attribute) Line (class in textractor.entities.line) line_items_groups (textractor.entities.expense_document.ExpenseDocument property) Linearizable (class in textractor.entities.linearizable) LineItemGroup (class in textractor.entities.expense_field) LineItemRow (class in textractor.entities.expense_field) LINES (textractor.data.constants.CLIOverlay attribute) (textractor.data.constants.TextractType attribute) lines (textractor.entities.document.Document property) (textractor.entities.page.Page property) list_element_prefix (textractor.data.text_linearization_config.TextLinearizationConfig attribute) list_element_separator (textractor.data.text_linearization_config.TextLinearizationConfig attribute) list_element_suffix (textractor.data.text_linearization_config.TextLinearizationConfig attribute) list_layout_prefix (textractor.data.text_linearization_config.TextLinearizationConfig attribute) list_layout_suffix (textractor.data.text_linearization_config.TextLinearizationConfig attribute) lists (textractor.entities.page_layout.PageLayout property)

M

max_number_of_consecutive_new_lines (textractor.data.text_linearization_config.TextLinearizationConfig attribute) max_number_of_consecutive_spaces (textractor.data.text_linearization_config.TextLinearizationConfig attribute) MEDIAWIKI (textractor.data.constants.TableFormat attribute) merge_direction() (textractor.entities.table_cell.TableCell method) MIDDLE_NAME (textractor.data.constants.AnalyzeIDFields attribute) module textractor.data.constants textractor.data.text_linearization_config textractor.entities.bbox textractor.entities.document textractor.entities.document_entity textractor.entities.expense_document textractor.entities.expense_field textractor.entities.identity_document textractor.entities.identity_field textractor.entities.key_value textractor.entities.layout textractor.entities.lazy_document textractor.entities.line textractor.entities.linearizable textractor.entities.page textractor.entities.page_layout textractor.entities.query textractor.entities.query_result textractor.entities.selection_element textractor.entities.signature textractor.entities.table textractor.entities.table_cell textractor.entities.table_footer textractor.entities.table_title textractor.entities.value textractor.entities.word textractor.parsers.response_parser textractor.textractor textractor.visualizers.entitylist

MOINMOIN (textractor.data.constants.TableFormat attribute)

N

NAME (textractor.data.constants.AnalyzeExpenseFields attribute)

NOT_SELECTED (textractor.data.constants.SelectionStatus attribute)

O

ocr_confidence (textractor.entities.key_value.KeyValue property) open() (textractor.entities.document.Document class method)

ORDER_DATE (textractor.data.constants.AnalyzeExpenseFields attribute) ORGTBL (textractor.data.constants.TableFormat attribute) OTHER (textractor.data.constants.AnalyzeExpenseFields attribute)

P

Page (class in textractor.entities.page) page (textractor.entities.expense_document.ExpenseDocument property) (textractor.entities.expense_field.Expense property) (textractor.entities.expense_field.ExpenseField property) (textractor.entities.expense_field.LineItemGroup property) (textractor.entities.expense_field.LineItemRow property) (textractor.entities.key_value.KeyValue property) (textractor.entities.layout.Layout property) (textractor.entities.line.Line property) (textractor.entities.query.Query property) (textractor.entities.query_result.QueryResult property) (textractor.entities.selection_element.SelectionElement property) (textractor.entities.signature.Signature property) (textractor.entities.table.Table property) (textractor.entities.table_cell.TableCell property) (textractor.entities.table_footer.TableFooter property) (textractor.entities.table_title.TableTitle property) (textractor.entities.value.Value property) (textractor.entities.word.Word property) page() (textractor.entities.document.Document method) page_id (textractor.entities.key_value.KeyValue property) (textractor.entities.layout.Layout property) (textractor.entities.line.Line property) (textractor.entities.query.Query property) (textractor.entities.query_result.QueryResult property) (textractor.entities.selection_element.SelectionElement property) (textractor.entities.signature.Signature property) (textractor.entities.table.Table property) (textractor.entities.table_cell.TableCell property) (textractor.entities.table_footer.TableFooter property) (textractor.entities.table_title.TableTitle property) (textractor.entities.value.Value property) (textractor.entities.word.Word property)

page_layout (textractor.entities.page.Page property) page_num_prefix (textractor.data.text_linearization_config.TextLinearizationConfig attribute) page_num_suffix (textractor.data.text_linearization_config.TextLinearizationConfig attribute) page_numbers (textractor.entities.page_layout.PageLayout property) PageLayout (class in textractor.entities.page_layout) pages (textractor.entities.document.Document property) parse() (in module textractor.parsers.response_parser) parse_analyze_id_response() (in module textractor.parsers.response_parser) parse_document_api_response() (in module textractor.parsers.response_parser) parser_analyze_expense_response() (in module textractor.parsers.response_parser) PAYMENT_TERMS (textractor.data.constants.AnalyzeExpenseFields attribute) PIPE (textractor.data.constants.TableFormat attribute) PLACE_OF_BIRTH (textractor.data.constants.AnalyzeIDFields attribute) PLAIN (textractor.data.constants.TableFormat attribute) PO_NUMBER (textractor.data.constants.AnalyzeExpenseFields attribute) PRESTO (textractor.data.constants.TableFormat attribute) PRETTY (textractor.data.constants.TableFormat attribute) pretty_print() (textractor.visualizers.entitylist.EntityList method) PRICE (textractor.data.constants.AnalyzeExpenseLineItemFields attribute) PRINTED (textractor.data.constants.TextTypes attribute) PRIOR_BALANCE (textractor.data.constants.AnalyzeExpenseFields attribute) PRODUCT_CODE (textractor.data.constants.AnalyzeExpenseLineItemFields attribute) PSQL (textractor.data.constants.TableFormat attribute)

Q

QUANTITY (textractor.data.constants.AnalyzeExpenseLineItemFields attribute) QUERIES (textractor.data.constants.CLIOverlay attribute) (textractor.data.constants.CLIPrint attribute) (textractor.data.constants.TextractFeatures attribute)

queries (textractor.entities.document.Document property) (textractor.entities.page.Page property) Query (class in textractor.entities.query) QueryResult (class in textractor.entities.query_result)

R

raw_object (textractor.entities.document_entity.DocumentEntity property) (textractor.entities.expense_field.ExpenseType attribute) RECEIVER (textractor.data.constants.AnalyzeExpenseFieldsGroup attribute) RECEIVER_ABN_NUMBER (textractor.data.constants.AnalyzeExpenseFields attribute) RECEIVER_ADDRESS (textractor.data.constants.AnalyzeExpenseFields attribute) RECEIVER_BILL_TO (textractor.data.constants.AnalyzeExpenseFieldsGroup attribute) RECEIVER_GST_NUMBER (textractor.data.constants.AnalyzeExpenseFields attribute) RECEIVER_NAME (textractor.data.constants.AnalyzeExpenseFields attribute) RECEIVER_PAN_NUMBER (textractor.data.constants.AnalyzeExpenseFields attribute) RECEIVER_PHONE (textractor.data.constants.AnalyzeExpenseFields attribute) RECEIVER_SHIP_TO (textractor.data.constants.AnalyzeExpenseFieldsGroup attribute) RECEIVER_SOLD_TO (textractor.data.constants.AnalyzeExpenseFieldsGroup attribute)

RECEIVER_VAT_NUMBER (textractor.data.constants.AnalyzeExpenseFields attribute) remove() (textractor.entities.document_entity.DocumentEntity method) remove_new_lines_in_leaf_elements (textractor.data.text_linearization_config.TextLinearizationConfig attribute) RESTRICTIONS (textractor.data.constants.AnalyzeIDFields attribute) return_duplicates() (textractor.entities.document.Document method) (textractor.entities.page.Page method) RIGHT (textractor.data.constants.Direction attribute) row_count (textractor.entities.table.Table property) row_index (textractor.entities.table_cell.TableCell property) row_span (textractor.entities.table_cell.TableCell property) rows (textractor.entities.expense_field.LineItemGroup property) RST (textractor.data.constants.TableFormat attribute)

S

s3_polling_interval (textractor.entities.lazy_document.LazyDocument property) same_layout_element_separator (textractor.data.text_linearization_config.TextLinearizationConfig attribute) same_paragraph_separator (textractor.data.text_linearization_config.TextLinearizationConfig attribute) search_lines() (textractor.entities.document.Document method) (textractor.entities.page.Page method) search_words() (textractor.entities.document.Document method) (textractor.entities.page.Page method) section_header_prefix (textractor.data.text_linearization_config.TextLinearizationConfig attribute) section_header_suffix (textractor.data.text_linearization_config.TextLinearizationConfig attribute) section_headers (textractor.entities.page_layout.PageLayout property) SECTION_TITLE (textractor.data.constants.CellTypes attribute) SELECTED (textractor.data.constants.SelectionStatus attribute) SELECTION_ELEMENT (textractor.data.constants.DirectionalFinderType attribute) (textractor.data.constants.TextractType attribute) selection_element_not_selected (textractor.data.text_linearization_config.TextLinearizationConfig attribute) selection_element_selected (textractor.data.text_linearization_config.TextLinearizationConfig attribute) SelectionElement (class in textractor.entities.selection_element) SelectionStatus (class in textractor.data.constants) SEMI_STRUCTURED (textractor.data.constants.TableTypes attribute) SERVICE_CHARGE (textractor.data.constants.AnalyzeExpenseFields attribute) SHIPPING_HANDLING_CHARGE (textractor.data.constants.AnalyzeExpenseFields attribute) Signature (class in textractor.entities.signature)

signature_token (textractor.data.text_linearization_config.TextLinearizationConfig attribute) SIGNATURES (textractor.data.constants.CLIOverlay attribute) (textractor.data.constants.CLIPrint attribute) (textractor.data.constants.TextractFeatures attribute) signatures (textractor.entities.document.Document property) (textractor.entities.page.Page property) SimilarityMetric (class in textractor.data.constants) SIMPLE (textractor.data.constants.TableFormat attribute) SpatialObject (class in textractor.entities.bbox) start_document_analysis() (textractor.textractor.Textractor method) start_document_text_detection() (textractor.textractor.Textractor method) start_expense_analysis() (textractor.textractor.Textractor method) STATE (textractor.data.constants.AnalyzeExpenseFields attribute) STATE_IN_ADDRESS (textractor.data.constants.AnalyzeIDFields attribute) STATE_NAME (textractor.data.constants.AnalyzeIDFields attribute) STREET (textractor.data.constants.AnalyzeExpenseFields attribute) strip_headers() (textractor.entities.table.Table method) STRUCTURED (textractor.data.constants.TableTypes attribute) SUBTOTAL (textractor.data.constants.AnalyzeExpenseFields attribute) SUFFIX (textractor.data.constants.AnalyzeIDFields attribute) SUMMARY_CELL (textractor.data.constants.CellTypes attribute) summary_fields_list (textractor.entities.expense_document.ExpenseDocument property)

T

Table (class in textractor.entities.table) table_add_footer_as_paragraph (textractor.data.text_linearization_config.TextLinearizationConfig attribute) table_add_title_as_caption (textractor.data.text_linearization_config.TextLinearizationConfig attribute) TABLE_CELL (textractor.data.constants.TextractType attribute) table_cell_cross_merge_cell_placeholder (textractor.data.text_linearization_config.TextLinearizationConfig attribute) table_cell_empty_cell_placeholder (textractor.data.text_linearization_config.TextLinearizationConfig attribute) table_cell_header_prefix (textractor.data.text_linearization_config.TextLinearizationConfig attribute) table_cell_header_suffix (textractor.data.text_linearization_config.TextLinearizationConfig attribute) table_cell_left_merge_cell_placeholder (textractor.data.text_linearization_config.TextLinearizationConfig attribute) table_cell_merge_cell_placeholder (textractor.data.text_linearization_config.TextLinearizationConfig attribute) table_cell_prefix (textractor.data.text_linearization_config.TextLinearizationConfig attribute) table_cell_suffix (textractor.data.text_linearization_config.TextLinearizationConfig attribute) table_cell_top_merge_cell_placeholder (textractor.data.text_linearization_config.TextLinearizationConfig attribute) table_column_header_threshold (textractor.data.text_linearization_config.TextLinearizationConfig attribute) table_column_separator (textractor.data.text_linearization_config.TextLinearizationConfig attribute) table_duplicate_text_in_merged_cells (textractor.data.text_linearization_config.TextLinearizationConfig attribute) table_flatten_headers (textractor.data.text_linearization_config.TextLinearizationConfig attribute) table_flatten_semi_structured_as_plaintext (textractor.data.text_linearization_config.TextLinearizationConfig attribute) table_footers_prefix (textractor.data.text_linearization_config.TextLinearizationConfig attribute) table_footers_suffix (textractor.data.text_linearization_config.TextLinearizationConfig attribute) table_id (textractor.entities.table_cell.TableCell property) table_layout_prefix (textractor.data.text_linearization_config.TextLinearizationConfig attribute) table_layout_suffix (textractor.data.text_linearization_config.TextLinearizationConfig attribute) table_linearization_format (textractor.data.text_linearization_config.TextLinearizationConfig attribute) table_min_table_words (textractor.data.text_linearization_config.TextLinearizationConfig attribute) table_prefix (textractor.data.text_linearization_config.TextLinearizationConfig attribute) table_remove_column_headers (textractor.data.text_linearization_config.TextLinearizationConfig attribute) table_row_prefix (textractor.data.text_linearization_config.TextLinearizationConfig attribute) table_row_separator (textractor.data.text_linearization_config.TextLinearizationConfig attribute) table_row_suffix (textractor.data.text_linearization_config.TextLinearizationConfig attribute) table_suffix (textractor.data.text_linearization_config.TextLinearizationConfig attribute) table_tabulate_format (textractor.data.text_linearization_config.TextLinearizationConfig attribute) table_tabulate_remove_extra_hyphens (textractor.data.text_linearization_config.TextLinearizationConfig attribute) table_title_prefix (textractor.data.text_linearization_config.TextLinearizationConfig attribute) table_title_suffix (textractor.data.text_linearization_config.TextLinearizationConfig attribute) table_type (textractor.entities.table.Table property) TableCell (class in textractor.entities.table_cell) TableFooter (class in textractor.entities.table_footer) TableFormat (class in textractor.data.constants) TABLES (textractor.data.constants.CLIOverlay attribute) (textractor.data.constants.CLIPrint attribute) (textractor.data.constants.TextractFeatures attribute) (textractor.data.constants.TextractType attribute) tables (textractor.entities.document.Document property) (textractor.entities.page.Page property) (textractor.entities.page_layout.PageLayout property) TableTitle (class in textractor.entities.table_title) TableTypes (class in textractor.data.constants) TAX (textractor.data.constants.AnalyzeExpenseFields attribute) TAX_PAYER_ID (textractor.data.constants.AnalyzeExpenseFields attribute) TEXT (textractor.data.constants.CLIPrint attribute) text (textractor.entities.document.Document property) (textractor.entities.expense_field.Expense property) (textractor.entities.expense_field.ExpenseType attribute) (textractor.entities.layout.Layout property) (textractor.entities.line.Line property) (textractor.entities.linearizable.Linearizable property) (textractor.entities.page.Page property) (textractor.entities.table_cell.TableCell property) (textractor.entities.table_footer.TableFooter property) (textractor.entities.table_title.TableTitle property) (textractor.entities.word.Word property) text_prefix (textractor.data.text_linearization_config.TextLinearizationConfig attribute) text_suffix (textractor.data.text_linearization_config.TextLinearizationConfig attribute) text_type (textractor.entities.word.Word property) TEXTILE (textractor.data.constants.TableFormat attribute) TextLinearizationConfig (class in textractor.data.text_linearization_config) Textract_API_to_TextractAPI() (textractor.data.constants.TextractAPI class method) textract_polling_interval (textractor.entities.lazy_document.LazyDocument property) TextractAPI (class in textractor.data.constants) TextractAPI_to_Textract_API() (textractor.data.constants.TextractAPI class method) TextractFeatures (class in textractor.data.constants) Textractor (class in textractor.textractor) textractor.data.constants module textractor.data.text_linearization_config module

textractor.entities.bbox module textractor.entities.document module textractor.entities.document_entity module textractor.entities.expense_document module textractor.entities.expense_field module textractor.entities.identity_document module textractor.entities.identity_field module textractor.entities.key_value module textractor.entities.layout module textractor.entities.lazy_document module textractor.entities.line module textractor.entities.linearizable module textractor.entities.page module textractor.entities.page_layout module textractor.entities.query module textractor.entities.query_result module textractor.entities.selection_element module textractor.entities.signature module textractor.entities.table module textractor.entities.table_cell module textractor.entities.table_footer module textractor.entities.table_title module textractor.entities.value module textractor.entities.word module textractor.parsers.response_parser module textractor.textractor module textractor.visualizers.entitylist module TextractType (class in textractor.data.constants) TextTypes (class in textractor.data.constants) title (textractor.entities.table.Table property) title_prefix (textractor.data.text_linearization_config.TextLinearizationConfig attribute) title_suffix (textractor.data.text_linearization_config.TextLinearizationConfig attribute) titles (textractor.entities.page_layout.PageLayout property) to_csv() (textractor.entities.expense_field.LineItemGroup method) (textractor.entities.table.Table method) to_excel() (textractor.entities.table.Table method) to_html() (textractor.entities.document.Document method) (textractor.entities.linearizable.Linearizable method) (textractor.entities.table.Table method) to_json() (textractor.entities.expense_field.LineItemGroup method) to_markdown() (textractor.entities.linearizable.Linearizable method) to_pandas() (textractor.entities.expense_field.LineItemGroup method) (textractor.entities.table.Table method) to_trp2() (textractor.entities.document.Document method) to_txt() (textractor.entities.table.Table method) TOTAL (textractor.data.constants.AnalyzeExpenseFields attribute) TSV (textractor.data.constants.TableFormat attribute) type (textractor.entities.expense_field.ExpenseField property) types (textractor.entities.expense_field.ExpenseGroupProperty attribute)

U

UNIT_PRICE (textractor.data.constants.AnalyzeExpenseLineItemFields attribute)

UNKNOWN (textractor.data.constants.TableTypes attribute) UNSAFEHTML (textractor.data.constants.TableFormat attribute)

V

Value (class in textractor.entities.value) value (textractor.entities.expense_field.ExpenseField property) (textractor.entities.identity_field.IdentityField property) (textractor.entities.key_value.KeyValue property) value_prefix (textractor.data.text_linearization_config.TextLinearizationConfig attribute) value_suffix (textractor.data.text_linearization_config.TextLinearizationConfig attribute) values() (textractor.entities.identity_document.IdentityDocument method) VENDOR (textractor.data.constants.AnalyzeExpenseFieldsGroup attribute) VENDOR_ABN_NUMBER (textractor.data.constants.AnalyzeExpenseFields attribute) VENDOR_ADDRESS (textractor.data.constants.AnalyzeExpenseFields attribute) VENDOR_GST_NUMBER (textractor.data.constants.AnalyzeExpenseFields attribute) VENDOR_NAME (textractor.data.constants.AnalyzeExpenseFields attribute)

VENDOR_PAN_NUMBER (textractor.data.constants.AnalyzeExpenseFields attribute) VENDOR_PHONE (textractor.data.constants.AnalyzeExpenseFields attribute) VENDOR_REMIT_TO (textractor.data.constants.AnalyzeExpenseFieldsGroup attribute) VENDOR_SUPPLIER (textractor.data.constants.AnalyzeExpenseFieldsGroup attribute) VENDOR_URL (textractor.data.constants.AnalyzeExpenseFields attribute) VENDOR_VAT_NUMBER (textractor.data.constants.AnalyzeExpenseFields attribute) VETERAN (textractor.data.constants.AnalyzeIDFields attribute) visit() (textractor.entities.document_entity.DocumentEntity method) visualize() (textractor.entities.document.Document method) (textractor.entities.document_entity.DocumentEntity method) (textractor.entities.page.Page method) (textractor.visualizers.entitylist.EntityList method)

W

width (textractor.entities.document_entity.DocumentEntity property) Word (class in textractor.entities.word) WORDS (textractor.data.constants.CLIOverlay attribute) (textractor.data.constants.TextractType attribute) words (textractor.entities.document.Document property) (textractor.entities.key_value.KeyValue property) (textractor.entities.layout.Layout property) (textractor.entities.line.Line property) (textractor.entities.page.Page property) (textractor.entities.selection_element.SelectionElement property) (textractor.entities.signature.Signature property) (textractor.entities.table.Table property) (textractor.entities.table_cell.TableCell property) (textractor.entities.table_footer.TableFooter property) (textractor.entities.table_title.TableTitle property) (textractor.entities.value.Value property) (textractor.entities.word.Word property)

X

x (textractor.entities.document_entity.DocumentEntity property)

Y

y (textractor.entities.document_entity.DocumentEntity property)

YOUTRACK (textractor.data.constants.TableFormat attribute)

Z

ZIP_CODE (textractor.data.constants.AnalyzeExpenseFields attribute)

ZIP_CODE_IN_ADDRESS (textractor.data.constants.AnalyzeIDFields attribute)