Index

A

add_child() (pagexml.model.physical_document_model.PageXMLPage method) (pagexml.model.physical_document_model.PageXMLScan method) (pagexml.model.physical_document_model.PageXMLTextRegion method) add_logical_parent_id_to_metadata() (pagexml.model.physical_document_model.LogicalStructureDoc method) add_parent_id_to_metadata() (pagexml.model.physical_document_model.StructureDoc method)

add_type() (pagexml.model.physical_document_model.StructureDoc method) analyse_line_chars() (pagexml.analysis.text_stats.LineAnalyser method) analyse_line_word_categories() (pagexml.analysis.text_stats.LineWordAnalyser method) analyse_line_words() (pagexml.analysis.text_stats.LineAnalyser method) average_baseline_height() (in module pagexml.analysis.layout_stats)

B

Baseline (class in pagexml.model.physical_document_model) baseline_is_below() (in module pagexml.model.physical_document_model)

bottom (pagexml.model.physical_document_model.Coords property) box (pagexml.model.physical_document_model.Coords property)

C

categorise_line_width() (in module pagexml.analysis.layout_stats) column_bounding_box_surrounds_lines() (in module pagexml.column_parser) combine_adjacent_lines() (in module pagexml.helper.pagexml_helper) compute_baseline_distances() (in module pagexml.analysis.layout_stats) compute_bounding_box_distances() (in module pagexml.analysis.layout_stats) compute_columns_stats() (in module pagexml.analysis.layout_stats) compute_complement_keyness() (in module pagexml.analysis.text_stats) compute_expected() (in module pagexml.analysis.text_stats) compute_height_stats() (in module pagexml.analysis.layout_stats) compute_keyness() (in module pagexml.analysis.text_stats)

compute_lines_stats() (in module pagexml.analysis.layout_stats) compute_log_likelihood() (in module pagexml.analysis.text_stats) compute_pages_stats() (in module pagexml.analysis.layout_stats) compute_pagexml_stats() (in module pagexml.analysis.layout_stats) compute_pixel_dist() (in module pagexml.column_parser) compute_points_distances() (in module pagexml.analysis.layout_stats) compute_scans_stats() (in module pagexml.analysis.layout_stats) compute_textregion_distance() (in module pagexml.analysis.layout_stats) compute_textregions_stats() (in module pagexml.analysis.layout_stats) Coords (class in pagexml.model.physical_document_model) coords_list_to_hull_coords() (in module pagexml.model.physical_document_model)

D

derive_boundary_points() (in module pagexml.analysis.stats) determine_column_type() (in module pagexml.column_parser)

determine_freq_gap_interval() (in module pagexml.column_parser) determine_word_break() (in module pagexml.analysis.text_stats) determine_word_break_typical_merge_end() (in module pagexml.analysis.text_stats)

E

edges_to_hull_points() (in module pagexml.model.physical_document_model) elements_overlap() (in module pagexml.helper.pagexml_helper) end_is_common_word() (in module pagexml.analysis.text_stats)

end_start_are_bigram() (in module pagexml.analysis.text_stats) end_start_are_hyphenated_compound() (in module pagexml.analysis.text_stats) Extractor (class in pagexml.helper.file_helper)

F

find_baseline_overlap_start_indexes() (in module pagexml.model.physical_document_model) find_column_gaps() (in module pagexml.column_parser) find_line_width_boundary_points() (in module pagexml.analysis.layout_stats)

find_lowest_point() (in module pagexml.analysis.layout_stats) find_overlapping_columns() (in module pagexml.column_parser) find_term_in_context() (in module pagexml.helper.text_helper)

G

get_all_text_regions() (pagexml.model.physical_document_model.PageXMLPage method) (pagexml.model.physical_document_model.PageXMLTextRegion method) get_archive_functions() (in module pagexml.helper.file_helper) get_archived_file_names() (in module pagexml.helper.file_helper) get_archived_files_infos() (in module pagexml.helper.file_helper) get_archiver_mode() (in module pagexml.helper.file_helper) get_baseline_y() (in module pagexml.analysis.layout_stats) get_bbox() (in module pagexml.helper.text_helper) get_bottom_points() (in module pagexml.analysis.layout_stats) get_boundary_width_ranges() (in module pagexml.analysis.layout_stats) get_custom_tags() (in module pagexml.helper.pagexml_helper) get_doc_stats() (in module pagexml.analysis.stats) get_doc_words() (in module pagexml.analysis.text_stats) get_horizontal_diff() (in module pagexml.model.physical_document_model) get_horizontal_diff_ratio() (in module pagexml.model.physical_document_model) get_horizontal_overlap() (in module pagexml.model.physical_document_model) get_horizontal_overlap_ratio() (in module pagexml.model.physical_document_model) get_inner_text_regions() (pagexml.model.physical_document_model.PageXMLPage method) (pagexml.model.physical_document_model.PageXMLTextRegion method) get_keyness_vocab() (in module pagexml.analysis.text_stats) get_line_distances() (in module pagexml.analysis.layout_stats) get_line_format_json() (in module pagexml.helper.text_helper) get_line_format_tsv() (in module pagexml.helper.text_helper) get_line_height_stats() (in module pagexml.analysis.layout_stats)

get_line_text() (in module pagexml.analysis.text_stats) get_line_width_stats() (in module pagexml.analysis.layout_stats) get_line_widths() (in module pagexml.analysis.layout_stats) get_line_words() (in module pagexml.helper.text_helper) get_lines() (pagexml.model.physical_document_model.PageXMLPage method) (pagexml.model.physical_document_model.PageXMLTextRegion method) get_observed() (in module pagexml.analysis.text_stats) get_page_lines_words() (in module pagexml.helper.text_helper) get_stats() (pagexml.analysis.text_stats.LineAnalyser method) get_text_heights() (in module pagexml.analysis.layout_stats) get_text_regions_in_reading_order() (pagexml.model.physical_document_model.PageXMLPage method) (pagexml.model.physical_document_model.PageXMLTextRegion method) get_textregion_avg_char_width() (in module pagexml.analysis.layout_stats) get_textregion_avg_line_distance() (in module pagexml.analysis.layout_stats) get_textregion_avg_line_width() (in module pagexml.analysis.layout_stats) get_textregion_line_distances() (in module pagexml.analysis.layout_stats) get_typical_start_end_words() (in module pagexml.analysis.text_stats) get_vertical_diff() (in module pagexml.model.physical_document_model) get_vertical_diff_ratio() (in module pagexml.model.physical_document_model) get_vertical_overlap() (in module pagexml.model.physical_document_model) get_vertical_overlap_ratio() (in module pagexml.model.physical_document_model) get_word_cat_stats() (in module pagexml.analysis.text_stats) get_words() (pagexml.model.physical_document_model.PageXMLTextLine method) (pagexml.model.physical_document_model.PageXMLTextRegion method) get_words_per_line() (in module pagexml.analysis.text_stats)

H

handle_extra_lines() (in module pagexml.column_parser) has_baseline() (in module pagexml.model.physical_document_model) has_common_merge_end() (in module pagexml.analysis.text_stats) has_non_merge_word() (in module pagexml.analysis.text_stats) has_type() (pagexml.model.physical_document_model.StructureDoc method)

has_word_break_symbol() (in module pagexml.analysis.text_stats) height (pagexml.model.physical_document_model.Coords property) horizontal_distance() (in module pagexml.model.physical_document_model) horizontal_group_lines() (in module pagexml.helper.pagexml_helper) horizontally_merge_lines() (in module pagexml.helper.pagexml_helper)

I

in_same_column() (in module pagexml.model.physical_document_model) interpolate_baseline_points() (in module pagexml.analysis.layout_stats) interpolate_points() (in module pagexml.analysis.layout_stats) is_below() (in module pagexml.model.physical_document_model) (pagexml.model.physical_document_model.PageXMLTextLine method) is_full_text_column() (in module pagexml.column_parser) is_header_footer_column() (in module pagexml.column_parser)

is_horizontally_overlapping() (in module pagexml.model.physical_document_model) is_next_to() (in module pagexml.model.physical_document_model) (pagexml.model.physical_document_model.PageXMLTextLine method) is_noise_column() (in module pagexml.column_parser) is_non_mid_word() (in module pagexml.analysis.text_stats) is_text_column() (in module pagexml.column_parser) is_vertically_overlapping() (in module pagexml.model.physical_document_model)

J

json (pagexml.model.physical_document_model.Coords property) (pagexml.model.physical_document_model.PageXMLColumn property) (pagexml.model.physical_document_model.PageXMLPage property) (pagexml.model.physical_document_model.PageXMLScan property) (pagexml.model.physical_document_model.PageXMLTextLine property) (pagexml.model.physical_document_model.PageXMLTextRegion property) (pagexml.model.physical_document_model.PageXMLWord property) (pagexml.model.physical_document_model.PhysicalStructureDoc property) (pagexml.model.physical_document_model.StructureDoc property)

json_to_column_container() (in module pagexml.parser) json_to_pagexml_column() (in module pagexml.parser) json_to_pagexml_doc() (in module pagexml.parser) json_to_pagexml_line() (in module pagexml.parser) json_to_pagexml_page() (in module pagexml.parser) json_to_pagexml_scan() (in module pagexml.parser) json_to_pagexml_text_region() (in module pagexml.parser) json_to_pagexml_word() (in module pagexml.parser)

L

left (pagexml.model.physical_document_model.Coords property) line_ends_with_word_break() (in module pagexml.helper.pagexml_helper) line_starts_with_big_capital() (in module pagexml.analysis.layout_stats) LineAnalyser (class in pagexml.analysis.text_stats)

LineCharAnalyser (class in pagexml.analysis.text_stats) LineIterable (class in pagexml.helper.pagexml_helper) LineReader (class in pagexml.helper.text_helper) LineWordAnalyser (class in pagexml.analysis.text_stats) LogicalStructureDoc (class in pagexml.model.physical_document_model)

M

make_column_range_columns() (in module pagexml.column_parser) make_derived_column() (in module pagexml.column_parser) make_line_analyser() (in module pagexml.analysis.text_stats) make_line_format_file() (in module pagexml.helper.text_helper) make_line_range() (in module pagexml.helper.pagexml_helper) make_line_text() (in module pagexml.helper.pagexml_helper) make_list() (in module pagexml.helper.text_helper) make_skipgram_similarity_dict() (in module pagexml.helper.text_helper) make_text_region_text() (in module pagexml.helper.pagexml_helper) merge_analysers() (in module pagexml.analysis.text_stats) merge_columns() (in module pagexml.column_parser) merge_is_more_common() (in module pagexml.analysis.text_stats) merge_lines() (in module pagexml.helper.pagexml_helper) merge_overlapping_columns() (in module pagexml.column_parser) merge_sets() (in module pagexml.helper.pagexml_helper) merge_textregions() (in module pagexml.helper.pagexml_helper)

module pagexml pagexml.analysis pagexml.analysis.layout_stats pagexml.analysis.stats pagexml.analysis.text_stats pagexml.column_parser pagexml.helper pagexml.helper.file_helper pagexml.helper.pagexml_helper pagexml.helper.text_helper pagexml.model pagexml.model.physical_document_model pagexml.parser pagexml.plotting pagexml.plotting.plot_dist

N

new_gap_pixel_interval() (in module pagexml.column_parser) num_lines (pagexml.model.physical_document_model.PageXMLTextRegion property) num_text_regions (pagexml.model.physical_document_model.PageXMLTextRegion property)

num_tokens() (pagexml.analysis.text_stats.LineAnalyser method) num_types() (pagexml.analysis.text_stats.LineAnalyser method) num_words (pagexml.model.physical_document_model.PageXMLTextLine property) (pagexml.model.physical_document_model.PageXMLTextRegion property)

P

pagexml module pagexml.analysis module pagexml.analysis.layout_stats module pagexml.analysis.stats module pagexml.analysis.text_stats module pagexml.column_parser module pagexml.helper module pagexml.helper.file_helper module pagexml.helper.pagexml_helper module pagexml.helper.text_helper module pagexml.model module pagexml.model.physical_document_model module pagexml.parser module pagexml.plotting module pagexml.plotting.plot_dist module pagexml_to_line_format() (in module pagexml.helper.pagexml_helper) PageXMLColumn (class in pagexml.model.physical_document_model) PageXMLDoc (class in pagexml.model.physical_document_model) PageXMLPage (class in pagexml.model.physical_document_model)

PageXMLScan (class in pagexml.model.physical_document_model) PageXMLTextLine (class in pagexml.model.physical_document_model) PageXMLTextRegion (class in pagexml.model.physical_document_model) PageXMLWord (class in pagexml.model.physical_document_model) parse_archived_filename() (in module pagexml.helper.file_helper) parse_baseline() (in module pagexml.parser) parse_conf() (in module pagexml.parser) parse_coords() (in module pagexml.parser) parse_custom_metadata() (in module pagexml.parser) parse_custom_metadata_element() (in module pagexml.parser) parse_custom_metadata_element_list() (in module pagexml.parser) parse_derived_coords() (in module pagexml.model.physical_document_model) parse_line_words() (in module pagexml.parser) parse_page_image_size() (in module pagexml.parser) parse_page_metadata() (in module pagexml.parser) parse_page_reading_order() (in module pagexml.parser) parse_pagexml_file() (in module pagexml.parser) parse_pagexml_files() (in module pagexml.parser) parse_pagexml_files_from_archive() (in module pagexml.parser) parse_pagexml_files_from_directory() (in module pagexml.parser) parse_pagexml_from_json() (in module pagexml.parser) parse_pagexml_json() (in module pagexml.parser) parse_points() (in module pagexml.model.physical_document_model) parse_text_equiv() (in module pagexml.parser) parse_textline() (in module pagexml.parser) parse_textline_list() (in module pagexml.parser) parse_textregion() (in module pagexml.parser) parse_textregion_list() (in module pagexml.parser) PhysicalStructureDoc (class in pagexml.model.physical_document_model) plot_dist_stats() (in module pagexml.plotting.plot_dist) points_to_hull_edges() (in module pagexml.model.physical_document_model) pretty_print_textregion() (in module pagexml.helper.pagexml_helper) print_counter_stats() (pagexml.analysis.text_stats.WordBreakDetector method) print_textregion_stats() (in module pagexml.helper.pagexml_helper)

R

read_7z_handle() (in module pagexml.helper.file_helper) read_inner_archive() (in module pagexml.helper.file_helper) read_line_format_file() (in module pagexml.helper.pagexml_helper) read_lines_from_line_files() (in module pagexml.helper.text_helper) read_page_7z_file() (in module pagexml.helper.file_helper) read_page_archive_file() (in module pagexml.helper.file_helper) read_page_archive_files() (in module pagexml.helper.file_helper) read_pagexml_dirs() (in module pagexml.parser) read_pagexml_docs_from_line_file() (in module pagexml.helper.text_helper)

read_pagexml_file() (in module pagexml.parser) read_tar_handle() (in module pagexml.helper.file_helper) read_zip_handle() (in module pagexml.helper.file_helper) remove_hyphen() (in module pagexml.helper.text_helper) remove_type() (pagexml.model.physical_document_model.StructureDoc method) remove_word_break_chars() (in module pagexml.helper.text_helper) reset_counters() (pagexml.analysis.text_stats.LineAnalyser method) (pagexml.analysis.text_stats.WordBreakDetector method) right (pagexml.model.physical_document_model.Coords property)

S

set_as_logical_parent() (pagexml.model.physical_document_model.LogicalStructureDoc method) set_as_parent() (pagexml.model.physical_document_model.StructureDoc method) set_counters() (pagexml.analysis.text_stats.WordBreakDetector method) set_derived_id() (pagexml.model.physical_document_model.PhysicalStructureDoc method) set_logical_parent() (pagexml.model.physical_document_model.LogicalStructureDoc method) set_parent() (pagexml.model.physical_document_model.StructureDoc method) set_parentage() (in module pagexml.model.physical_document_model) set_scan_id_as_metadata() (pagexml.model.physical_document_model.PageXMLScan method) set_stats() (pagexml.analysis.text_stats.LineAnalyser method) set_text_regions_in_reader_order() (pagexml.model.physical_document_model.PageXMLTextRegion method) show_word_break_context() (in module pagexml.analysis.text_stats) sort_coords_above_below_baseline() (in module pagexml.analysis.layout_stats) sort_lines() (in module pagexml.model.physical_document_model) sort_lines_in_column_ranges() (in module pagexml.column_parser) sort_lines_in_column_reading_order() (in module pagexml.helper.pagexml_helper)

sort_lines_in_reading_direction() (in module pagexml.helper.pagexml_helper) sort_lines_in_reading_order() (in module pagexml.helper.pagexml_helper) sort_lines_in_row_reading_order() (in module pagexml.helper.pagexml_helper) sort_regions_in_reading_order() (in module pagexml.helper.pagexml_helper) split_line_words() (in module pagexml.helper.text_helper) split_lines_on_column_gaps() (in module pagexml.column_parser) start_is_titleword() (in module pagexml.analysis.text_stats) start_word_has_incorrect_titlecase() (in module pagexml.analysis.text_stats) stats (pagexml.model.physical_document_model.PageXMLColumn property) (pagexml.model.physical_document_model.PageXMLDoc property) (pagexml.model.physical_document_model.PageXMLPage property) (pagexml.model.physical_document_model.PageXMLScan property) (pagexml.model.physical_document_model.PageXMLTextLine property) (pagexml.model.physical_document_model.PageXMLTextRegion property) StructureDoc (class in pagexml.model.physical_document_model)

T

top (pagexml.model.physical_document_model.Coords property)

transform_box_to_coords() (in module pagexml.helper.text_helper) types (pagexml.model.physical_document_model.StructureDoc property)

V

vertical_distance() (in module pagexml.model.physical_document_model)

W

width (pagexml.model.physical_document_model.Coords property) within_column() (in module pagexml.column_parser)

WordBreakDetector (class in pagexml.analysis.text_stats) write_pagexml_to_line_format() (in module pagexml.helper.pagexml_helper)