Module specs._types

Spec definitions. TypedDicts are used for easy serialization.

Sub-modules

specs._types._client

TypeDict definitions for client_specs.py

specs._types._match

TypeDict definitions for matchops classes.

specs._types._section

section spec typed dict

specs._types._summary

Type definitions for summary and condense specs.

specs._types._table

TypedDicts for use in table_specs.py

Classes

class ClientSpecStatic (*args, **kwargs)

Top level keys that must be present in ClientSpec objects

Attributes

db_secret_name : str

Name of the secret containing the database credentials.

api_secret_name : str

Name of the secret containing the api credentials.

managed_fields : dict[str, ManagedField]

client level standard fields.

managed_fields_context_rules : list[ContextRule]

client level context rules.

summary_key_addendum : list[str]

additional summary keys specific to client.

summary_map_addendum : dict[str, ReduceSpec]

dict of additional summary reduce specs.

Ancestors

• builtins.dict

Class variables

var api_secret_name : str

var db_secret_name : str

var managed_fields : dict[str, utilities.managed_fields.ManagedField]

var managed_fields_context_rules : list[utilities.managed_fields.ContextRule]

var summary_key_addendum : list[str]

var summary_map_addendum : dict[str, ReduceSpec]

class FacilitySpec (*args, **kwargs)

Facility entry in client_specs.builtin_client_specs.

Attributes

azure_secret_name : str

stores endpoint and subscription key for Azure Computer Vision OCR operations.

dest_prefix : str

The final s3 folder specification for processed PDFs.

extract_func : partial | pu.ExtractFunc

Function used for text extraction.

facility_name : str

MUST MATCH FACILITY NAME FROM ACE SALESFORCE.

failed_prefix : str

The final s3 folder specification for failed PDFs.

first_dos : str

The first date of service to be coded for facility.

insurance_integration_mode (Literal['0', '1'] | None): overrides equivalent env var when set.

max_keys : int

Override max keys passed to extract_buckets for this facility.

match_specs_key : str

Key for this facility in match_specs.

output_dir : str | None

Optional directory for saving intermediate outputs.

provider_integration_mode (Literal['0', '1', '2'] | None): overrides equivalent env var when set.

s3_prefix : str

Non-filename portion of source PDF s3 keys.

section_specs_key : str

Key in section_specs.

send_func : Callable

S3Batch output processing function.

source_prefix : str

The final s3 folder specification for unprocessed PDFs.

summary_key_addendum : list[str]

List of additional summary keys valid for this facility.

summary_map_addendum : dict[str, ReduceSpec]

dict of additional summary reduce specs.

summary_specs_key : str

Key for summary type in summary_specs.

table_specs_key : str

Key for facility type in table_specs.

transform_specs_key : str

Key for facility type in transform_specs.

use_autocoding : bool

Flag to enable/disable autocoding for the facility.

use_docuvision : bool

Flag to enable/disable docuvision for the facility.

managed_fields : dict[str, ManagedField]

Custom standard field values (optional).

managed_fields_context_rules

list[ContextRule]: facility level context rules.

dv_preferred_networks : list[str] | None

List of DocuVision neural networks preferred for this facility.

dv_required_page_types : set[str] | None

if supplied, docuvision will only create a case for a pid if at least one of the pages assigned to that pid has a noteType in this set.

send_reject_notifications : bool

if True, include a UserNotification for each rejected s3 file input in the ClaimMaker Alert email to the client. Defaults to False.

file_groups : list[S3FileGroup]

list of file groups specifying how to process every file type according to a matched regex

Ancestors

• builtins.dict

Class variables

var azure_secret_name : str

var dest_prefix : str

var dv_preferred_networks : list[str] | None

var dv_required_page_types : set[str] | None

var extract_func : functools.partial[dict[str, utilities.utils.FileContentsEntry]] | collections.abc.Callable[[dict[str, utilities.library_utils.PDFLibProto]], dict[str, utilities.utils.FileContentsEntry]]

var facility_name : str

var failed_prefix : str

var file_groups : list[utilities.client_utils.S3FileGroup]

var first_dos : str

var insurance_integration_mode : Optional[Literal['0', '1']]

var managed_fields : dict[str, utilities.managed_fields.ManagedField]

var managed_fields_context_rules : list[utilities.managed_fields.ContextRule]

var match_specs_key : str

var max_keys : int

var output_dir : str | None

var provider_integration_mode : Optional[Literal['0', '1', '2']]

var s3_prefix : str

var section_specs_key : str

var send_func : collections.abc.Callable[..., dict[str, bool]]

var send_reject_notifications : bool

var source_prefix : str

var summary_key_addendum : list[str]

var summary_map_addendum : dict[str, ReduceSpec]

var summary_specs_key : str

var table_specs_key : str | None

var transform_specs_key : str

var use_autocoding : bool

var use_docuvision : bool

class MatchSpec (*args, **kwargs)

Spec definition for reference file dataframe matching.

Attributes

schedule_other : partial[DataFrameMatcher]

partial function for matching other csvs to schedule.

schedule_demo : partial[DataFrameMatcher]

partial function for matching demographics to schedule.

Ancestors

• builtins.dict

Class variables

var schedule_demo : functools.partial[DataFrameMatcher]

var schedule_other : functools.partial[DataFrameMatcher]

class ReduceSpec (*args, **kwargs)

TypedDict defining the fields required in a summary_map entry.

Attributes

reduce : Callable

function to reduce a list of values to a single value

key_filters : list[str]

if the source table key contains a value in this list, exclude its value from consideration.

value_filters : list[Callable]

if any of these functions return True for for a candidate value, exclude it from consideration.

queries : dict[str, Callable]

collect candidate values by querying the source table for keys that match the regex defined in the query key and reduce the results using the function defined in the query value.

Ancestors

• builtins.dict

Class variables

var key_filters : list[str]

var queries : dict[str, collections.abc.Callable[[list[str]], str | bool | list[typing.Any]]]

var reduce : collections.abc.Callable[[collections.abc.Sequence[typing.Any]], str | bool | list[typing.Any]] | str

var value_filters : list[collections.abc.Callable[..., bool]]

class SectionSpec (*args, **kwargs)

Section spec TypedDict definition.

Attributes

exact_titles : list[str]

list of exact section titles to match

force_names : list[ForceNameTuple]

list of tuples of check functions and names to force if the check function returns True when passed a current section's title.

strip_ends : list[str]

list of strings to strip from the end of a section title.

heading_breaks : list[HBTuple]

list of tuples of break strings to remove unwanted data from section titles.

sect_start_checks : list[Callable]

list of functions to check if a section has started when passed the list of remaining extracted lines of text.

end_sect_latches : list[LTTuple]

list of tuples containing a latch function that should return True when passed the list of remaining lines if the section is ending, a trigger function to end the section based on the current line, and an unlatch function to clear the "section ending" latch based on the current line.

sect_start_dqs : list[su.SectStartDisqualifier]

list of su.SectStartDisqualifier. Disqualify section starts based on the currently extracting section name and the remaining extracted text.

line_roll_checks : list[su.LineRollCheck]

list of LineRoleCheck tuples defining tests to detect and functions to correct improper line wrapping in the source document.

wrap_lines : bool

if True, search for horizontally distributed table layouts and move tables in the rightmost column such that they appear below the table in the leftmost column.

document_strippers : list[StripperTuple]

list of tuples defining document stripper classes and their kwargs.

Ancestors

• builtins.dict

Class variables

var document_strippers : list[utilities.section_utils.StripperTuple]

var end_sect_latches : list[utilities.section_utils.LTTuple]

var exact_titles : list[str]

var force_names : list[utilities.section_utils.ForceNameTuple]

var heading_breaks : list[utilities.section_utils.HBTuple]

var line_roll_checks : list[utilities.section_utils.LineRollCheck]

var sect_start_checks : list[collections.abc.Callable[[collections.abc.Sequence[str]], bool]]

var sect_start_dqs : list[utilities.section_utils.SectStartDisqualifier]

var strip_ends : list[str]

var wrap_lines : bool

class SummarySpec (*args, **kwargs)

Typed dict for required summary spec keys.

Attributes

summary_func : str

must be a valid summary function name from TableTransformer()

summary_args : dict[str, Any]

kwargs for summary_func

summary_key_addendum : list[str]

list of valid output keys not appearing in summary_map

summary_map : CondenseSpec

map of output keys to ReduceSpecs

summary_meets_claimmaker_standard : bool

enables "claimmaker only" operations. See aws_s3_batch.py for more information.

Ancestors

• builtins.dict

Class variables

var summary_args : dict[str, typing.Any]

var summary_func : str

var summary_key_addendum : list[str]

var summary_map : dict[str, ReduceSpec]

var summary_meets_claimmaker_standard : bool

class TableSpec (*args, **kwargs)

TypedDict representing args/configuration items for parsing the tables of a single section.

Attributes

save_full_text : bool

if True, save the full text of the table

split_table_columns : list[str]

list of column names to split on

row_indent : int

lines indented by at least this many spaces are appended to the list of lines in the previous table.

force_table_names : list[ForceNameTuple]

list of tuples of check functions and names to force if the check function returns True when passed a current table's title.

rollup_cascade_reference : RollupCascadeManager

container class for defining rollup/cascade operations.

heading_indent : int

lines indented by exactly this many spaces are autmotically considered to be table headings.

stripped_head_key : str

key to use when storing data stripped from a table heading.

heading_contains : list[str]

list of strings to check for in the line to detect it as a table heading.

start_checks : list[TableStartCheck]

list of tuples of check functions for starting new tables.

end_checks : list[TableEndCheck]

list of tuples of check functions for ending the current table.

interpreter : Callable

function to interpret the table

interpreter_kwargs : SwappingInterpreterKwArgs

kwargs for interpreter

process_residual : bool

if True, process residual text after removing all lines assigned to other tables.

heading_breaks : list[HBTuple]

list of tuples of break strings to remove unwanted data from table titles. Inherited from section specs.

Ancestors

• builtins.dict

Class variables

var end_checks : list[utilities.table_utils.TableEndCheck]

var force_table_names : list[utilities.section_utils.ForceNameTuple]

var heading_breaks : list[utilities.section_utils.HBTuple]

var heading_contains : list[str]

var heading_indent : int

var interpreter : collections.abc.Callable[..., list[dict[str, str]] | utilities.table_utils.SubtableParser]

var interpreter_kwargs : utilities.table_utils.SwappingInterpreterKwArgs

var process_residual : bool

var rollup_cascade_reference : RollupCascadeManager

var row_indent : int

var save_full_text : bool

var split_table_columns : list[str]

var start_checks : list[utilities.table_utils.TableStartCheck]

var stripped_head_key : str