sec_parser.processing_steps.page_header_classifier

Classes

`PageHeaderCandidate`
`PageHeaderClassifier`

Module Contents

class sec_parser.processing_steps.page_header_classifier.PageHeaderCandidate

TEXT_LENGTH_THRESHOLD = 100

OCCURRENCE_THRESHOLD = 5

MOST_COMMON_CANDIDATE_LIMIT = None

text: str

style: sec_parser.semantic_elements.highlighted_text_element.TextStyle | None

class sec_parser.processing_steps.page_header_classifier.PageHeaderClassifier(types_to_process: set[type[sec_parser.semantic_elements.abstract_semantic_element.AbstractSemanticElement]] | None = None, types_to_exclude: set[type[sec_parser.semantic_elements.abstract_semantic_element.AbstractSemanticElement]] | None = None)

Bases: sec_parser.processing_steps.abstract_classes.abstract_elementwise_processing_step.AbstractElementwiseProcessingStep

_NUM_ITERATIONS = 2

_element_to_page_header_candidate: dict[sec_parser.semantic_elements.abstract_semantic_element.AbstractSemanticElement, PageHeaderCandidate]

_candidate_count: collections.Counter[PageHeaderCandidate]

_most_common_candidates: dict[PageHeaderCandidate, int] | None = None

_process_element(element: sec_parser.semantic_elements.abstract_semantic_element.AbstractSemanticElement, context: sec_parser.processing_steps.abstract_classes.abstract_elementwise_processing_step.ElementProcessingContext) → sec_parser.semantic_elements.abstract_semantic_element.AbstractSemanticElement

_find_page_header_candidates(element: sec_parser.semantic_elements.abstract_semantic_element.AbstractSemanticElement) → None

_classify_elements(element: sec_parser.semantic_elements.abstract_semantic_element.AbstractSemanticElement) → sec_parser.semantic_elements.abstract_semantic_element.AbstractSemanticElement

_get_most_common_candidates() → dict[PageHeaderCandidate, int]