Index

A

add_div() (in module text_preparation.importers.bnf.helpers) add_gn_property() (in module text_preparation.importers.tetml.helpers) add_issue() (text_preparation.importers.bcul.classes.BculNewspaperPage method) (text_preparation.importers.bl.classes.BlNewspaperPage method) (text_preparation.importers.bnf.classes.BnfNewspaperPage method) (text_preparation.importers.bnf_en.classes.BnfEnNewspaperPage method) (text_preparation.importers.classes.CanonicalAudioRecord method) (text_preparation.importers.classes.CanonicalPage method) (text_preparation.importers.ina.classes.INABroadcastAudioRecord method) (text_preparation.importers.lux.classes.LuxNewspaperPage method) (text_preparation.importers.mets_alto.classes.MetsAltoCanonicalPage method) (text_preparation.importers.olive.classes.OliveNewspaperPage method) (text_preparation.importers.rero.classes.ReroNewspaperPage method) (text_preparation.importers.swa.classes.SWANewspaperPage method) (text_preparation.importers.swissinfo.classes.SwissInfoRadioBulletinPage method) (text_preparation.importers.tetml.classes.TetmlNewspaperPage method) add_property() (in module text_preparation.utils) alias (text_preparation.importers.bcul.classes.BculNewspaperIssue attribute) (text_preparation.importers.bl.classes.BlNewspaperIssue attribute) (text_preparation.importers.bnf.classes.BnfNewspaperIssue attribute) (text_preparation.importers.bnf_en.classes.BnfEnNewspaperIssue attribute) (text_preparation.importers.classes.CanonicalIssue attribute) (text_preparation.importers.ina.classes.INABroadcastIssue attribute) (text_preparation.importers.lux.classes.LuxNewspaperIssue attribute) (text_preparation.importers.mets_alto.classes.MetsAltoCanonicalIssue attribute) (text_preparation.importers.olive.classes.OliveNewspaperIssue attribute) (text_preparation.importers.rero.classes.ReroNewspaperIssue attribute) (text_preparation.importers.swa.classes.SWANewspaperIssue attribute) (text_preparation.importers.swissinfo.classes.SwissInfoRadioBulletinIssue attribute)

archive (text_preparation.importers.olive.classes.OliveNewspaperIssue attribute) (text_preparation.importers.olive.classes.OliveNewspaperPage attribute) (text_preparation.importers.swa.classes.SWANewspaperIssue attribute) ark_id (text_preparation.importers.bl.classes.BlNewspaperIssue attribute) (text_preparation.importers.bnf.classes.BnfNewspaperIssue attribute) (text_preparation.importers.lux.classes.LuxNewspaperIssue attribute) (text_preparation.importers.mets_alto.classes.MetsAltoCanonicalIssue attribute) (text_preparation.importers.rero.classes.ReroNewspaperIssue attribute) ark_link (text_preparation.importers.bnf.classes.BnfNewspaperPage attribute) (text_preparation.importers.bnf_en.classes.BnfEnNewspaperIssue attribute) (text_preparation.importers.bnf_en.classes.BnfEnNewspaperPage attribute) assign_editions() (in module text_preparation.importers.bnf.detect) audio_records (text_preparation.importers.classes.CanonicalIssue attribute) (text_preparation.importers.ina.classes.INABroadcastIssue attribute)

B

basedir (text_preparation.importers.bl.classes.BlNewspaperPage attribute) (text_preparation.importers.bnf.classes.BnfNewspaperPage attribute) (text_preparation.importers.bnf_en.classes.BnfEnNewspaperPage attribute) (text_preparation.importers.lux.classes.LuxNewspaperPage attribute) (text_preparation.importers.mets_alto.classes.MetsAltoCanonicalPage attribute) (text_preparation.importers.rero.classes.ReroNewspaperPage attribute) (text_preparation.importers.swa.classes.SWANewspaperPage attribute) BculIssueDir (in module text_preparation.importers.bcul.detect) BculNewspaperIssue (class in text_preparation.importers.bcul.classes) BculNewspaperPage (class in text_preparation.importers.bcul.classes)

BlIssueDir (in module text_preparation.importers.bl.detect) BlNewspaperIssue (class in text_preparation.importers.bl.classes) BlNewspaperPage (class in text_preparation.importers.bl.classes) BnfEnIssueDir (in module text_preparation.importers.bnf_en.detect) BnfEnNewspaperIssue (class in text_preparation.importers.bnf_en.classes) BnfEnNewspaperPage (class in text_preparation.importers.bnf_en.classes) BnfIssueDir (in module text_preparation.importers.bnf.detect) BnfNewspaperIssue (class in text_preparation.importers.bnf.classes) BnfNewspaperPage (class in text_preparation.importers.bnf.classes) BoxStrategy (class in text_preparation.importers.olive.helpers)

C

CanonicalAudioRecord (class in text_preparation.importers.classes) CanonicalIssue (class in text_preparation.importers.classes) CanonicalPage (class in text_preparation.importers.classes) check_if_to_be_copied() (in module text_preparation.importer_scripts.preprocessing.bl_reorganize_original_data) ci_has_problem() (in module text_preparation.rebuilders.helpers) ci_id (text_preparation.importers.bcul.classes.BculNewspaperPage property) (text_preparation.importers.swa.classes.SWANewspaperPage property) ci_without_problem() (in module text_preparation.rebuilders.helpers) cleanup() (in module text_preparation.importers.core) (in module text_preparation.rebuilders.rebuilder) clusters (text_preparation.importers.olive.classes.OliveNewspaperIssue attribute) combine_article_parts() (in module text_preparation.importers.olive.helpers) compress() (in module text_preparation.rebuilders.rebuilder) compress_issues() (in module text_preparation.importers.core) compress_supports() (in module text_preparation.importers.core) compute_agg_coords() (in module text_preparation.importers.swissinfo.helpers) compute_bb() (in module text_preparation.importers.tetml.helpers)

compute_box() (in module text_preparation.importers.olive.helpers) (in module text_preparation.importers.tetml.helpers) compute_scale_factor() (in module text_preparation.importers.olive.helpers) construct_iiif_arks() (in module text_preparation.importers.bnf_en.detect) content_elements (text_preparation.importers.olive.classes.OliveNewspaperIssue attribute) content_items (text_preparation.importers.bcul.classes.BculNewspaperIssue attribute) (text_preparation.importers.olive.classes.OliveNewspaperIssue attribute) (text_preparation.importers.swa.classes.SWANewspaperIssue attribute) convert_box() (in module text_preparation.importers.olive.helpers) convert_coordinates() (in module text_preparation.importers.lux.helpers) (in module text_preparation.importers.rero.classes) convert_image_coordinates() (in module text_preparation.importers.olive.helpers) convert_page_coordinates() (in module text_preparation.importers.olive.helpers) coords_to_xy() (in module text_preparation.utils) coords_to_xywh() (in module text_preparation.utils) copy_files_for_NLP() (in module text_preparation.importer_scripts.preprocessing.bl_reorganize_original_data) create_iiif() (text_preparation.importers.ina.classes.INABroadcastAudioRecord method)

D

date (text_preparation.importers.bcul.classes.BculNewspaperIssue attribute) (text_preparation.importers.bl.classes.BlNewspaperIssue attribute) (text_preparation.importers.bnf.classes.BnfNewspaperIssue attribute) (text_preparation.importers.bnf_en.classes.BnfEnNewspaperIssue attribute) (text_preparation.importers.classes.CanonicalIssue attribute) (text_preparation.importers.ina.classes.INABroadcastIssue attribute) (text_preparation.importers.lux.classes.LuxNewspaperIssue attribute) (text_preparation.importers.mets_alto.classes.MetsAltoCanonicalIssue attribute) (text_preparation.importers.olive.classes.OliveNewspaperIssue attribute) (text_preparation.importers.rero.classes.ReroNewspaperIssue attribute) (text_preparation.importers.swa.classes.SWANewspaperIssue attribute) (text_preparation.importers.swissinfo.classes.SwissInfoRadioBulletinIssue attribute) detect_issues() (in module text_preparation.importers.bcul.detect) (in module text_preparation.importers.bl.detect) (in module text_preparation.importers.bnf.detect) (in module text_preparation.importers.bnf_en.detect) (in module text_preparation.importers.ina.detect) (in module text_preparation.importers.lux.detect) (in module text_preparation.importers.rero.detect) (in module text_preparation.importers.swa.detect) (in module text_preparation.importers.swissinfo.detect)

dir2issue() (in module text_preparation.importers.bcul.detect) (in module text_preparation.importers.bl.detect) (in module text_preparation.importers.bnf.detect) (in module text_preparation.importers.bnf_en.detect) (in module text_preparation.importers.core) (in module text_preparation.importers.ina.detect) (in module text_preparation.importers.lux.detect) (in module text_preparation.importers.rero.detect) (in module text_preparation.importers.swissinfo.detect) dir2olivedir() (in module text_preparation.importers.olive.detect) dirs2issues() (in module text_preparation.importers.core) distill_coordinates() (in module text_preparation.importers.mets_alto.alto) div_has_body() (in module text_preparation.importers.lux.helpers) draw_box_on_img() (in module text_preparation.utils)

E

edition (text_preparation.importers.bcul.classes.BculNewspaperIssue attribute) (text_preparation.importers.bl.classes.BlNewspaperIssue attribute) (text_preparation.importers.bnf.classes.BnfNewspaperIssue attribute) (text_preparation.importers.bnf_en.classes.BnfEnNewspaperIssue attribute) (text_preparation.importers.classes.CanonicalIssue attribute) (text_preparation.importers.ina.classes.INABroadcastIssue attribute) (text_preparation.importers.lux.classes.LuxNewspaperIssue attribute) (text_preparation.importers.mets_alto.classes.MetsAltoCanonicalIssue attribute) (text_preparation.importers.olive.classes.OliveNewspaperIssue attribute) (text_preparation.importers.rero.classes.ReroNewspaperIssue attribute) (text_preparation.importers.swa.classes.SWANewspaperIssue attribute) (text_preparation.importers.swissinfo.classes.SwissInfoRadioBulletinIssue attribute)

empty_folder() (in module text_preparation.utils) encode_ark() (in module text_preparation.importers.lux.helpers) encoding (text_preparation.importers.bl.classes.BlNewspaperPage attribute) (text_preparation.importers.bnf.classes.BnfNewspaperPage attribute) (text_preparation.importers.bnf_en.classes.BnfEnNewspaperPage attribute) (text_preparation.importers.lux.classes.LuxNewspaperPage attribute) (text_preparation.importers.mets_alto.classes.MetsAltoCanonicalPage attribute) (text_preparation.importers.rero.classes.ReroNewspaperPage attribute) (text_preparation.importers.swa.classes.SWANewspaperPage attribute) extract_date() (in module text_preparation.importer_scripts.preprocessing.bl_reorganize_original_data) extract_time_coords_from_elem() (in module text_preparation.importers.ina.helpers)

F

FedgazNewspaperIssue (class in text_preparation.importers.fedgaz.classes) FedgazNewspaperPage (class in text_preparation.importers.fedgaz.classes) file_exists (text_preparation.importers.swa.classes.SWANewspaperPage property) filename (text_preparation.importers.bl.classes.BlNewspaperPage attribute) (text_preparation.importers.bnf.classes.BnfNewspaperPage attribute) (text_preparation.importers.bnf_en.classes.BnfEnNewspaperPage attribute) (text_preparation.importers.lux.classes.LuxNewspaperPage attribute) (text_preparation.importers.mets_alto.classes.MetsAltoCanonicalPage attribute) (text_preparation.importers.rero.classes.ReroNewspaperPage attribute) (text_preparation.importers.swa.classes.SWANewspaperPage attribute)

filter_and_process_cis() (in module text_preparation.rebuilders.rebuilder) filter_special_symbols() (in module text_preparation.importers.tetml.helpers) find_mit_file() (in module text_preparation.importers.bcul.helpers) find_page_file_in_dir() (in module text_preparation.importers.bcul.helpers) find_section_articles() (in module text_preparation.importers.lux.helpers) fix_api_year_mismatch() (in module text_preparation.importers.bnf_en.detect)

G

get_api_id() (in module text_preparation.importers.bnf_en.detect) get_canonical_path() (in module text_preparation.importer_scripts.preprocessing.swissinfo_extract_ocr_from_pdfs) get_ci_divs() (text_preparation.importers.bcul.classes.BculNewspaperPage method) get_clusters() (in module text_preparation.importers.olive.helpers) get_dates() (in module text_preparation.importers.bnf.helpers) get_div_coords() (in module text_preparation.importers.bcul.helpers) get_dmd_sec() (in module text_preparation.importers.mets_alto.mets) get_id() (in module text_preparation.importers.bnf.detect) (in module text_preparation.importers.bnf_en.detect) get_iiif_and_coords() (in module text_preparation.rebuilders.helpers) get_iiif_image() (text_preparation.importers.swa.classes.SWANewspaperPage method)

get_issue_schema() (in module text_preparation.utils) get_issues_iiif_arks() (in module text_preparation.importers.bnf_en.detect) get_journal_name() (in module text_preparation.importers.bnf.helpers) get_metadata() (in module text_preparation.importers.tetml.helpers) get_number() (in module text_preparation.importers.bnf.detect) get_page_number() (in module text_preparation.importers.bcul.helpers) get_page_schema() (in module text_preparation.utils) get_placed_image() (in module text_preparation.importers.tetml.helpers) get_reading_order() (in module text_preparation.utils) get_scale_factor() (in module text_preparation.importers.olive.helpers) get_tif_shape() (in module text_preparation.importers.tetml.helpers) get_utterances() (in module text_preparation.importers.ina.helpers)

I

id (text_preparation.importers.bcul.classes.BculNewspaperIssue attribute) (text_preparation.importers.bcul.classes.BculNewspaperPage attribute) (text_preparation.importers.bl.classes.BlNewspaperIssue attribute) (text_preparation.importers.bl.classes.BlNewspaperPage attribute) (text_preparation.importers.bnf.classes.BnfNewspaperIssue attribute) (text_preparation.importers.bnf.classes.BnfNewspaperPage attribute) (text_preparation.importers.bnf_en.classes.BnfEnNewspaperIssue attribute) (text_preparation.importers.bnf_en.classes.BnfEnNewspaperPage attribute) (text_preparation.importers.classes.CanonicalAudioRecord attribute) (text_preparation.importers.classes.CanonicalIssue attribute) (text_preparation.importers.classes.CanonicalPage attribute) (text_preparation.importers.ina.classes.INABroadcastAudioRecord attribute) (text_preparation.importers.ina.classes.INABroadcastIssue attribute) (text_preparation.importers.lux.classes.LuxNewspaperIssue attribute) (text_preparation.importers.lux.classes.LuxNewspaperPage attribute) (text_preparation.importers.mets_alto.classes.MetsAltoCanonicalIssue attribute) (text_preparation.importers.mets_alto.classes.MetsAltoCanonicalPage attribute) (text_preparation.importers.olive.classes.OliveNewspaperIssue attribute) (text_preparation.importers.olive.classes.OliveNewspaperPage attribute) (text_preparation.importers.rero.classes.ReroNewspaperIssue attribute) (text_preparation.importers.rero.classes.ReroNewspaperPage attribute) (text_preparation.importers.swa.classes.SWANewspaperIssue attribute) (text_preparation.importers.swa.classes.SWANewspaperPage attribute) (text_preparation.importers.swissinfo.classes.SwissInfoRadioBulletinIssue attribute) (text_preparation.importers.swissinfo.classes.SwissInfoRadioBulletinPage attribute) iiif (text_preparation.importers.swa.classes.SWANewspaperPage attribute) iiif_base_uri (text_preparation.importers.bcul.classes.BculNewspaperPage attribute) iiif_manifest (text_preparation.importers.bcul.classes.BculNewspaperIssue attribute) image_dirs (text_preparation.importers.olive.classes.OliveNewspaperIssue attribute) image_info (text_preparation.importers.olive.classes.OliveNewspaperPage attribute) image_properties (text_preparation.importers.bl.classes.BlNewspaperIssue attribute) (text_preparation.importers.bnf.classes.BnfNewspaperIssue attribute) (text_preparation.importers.bnf_en.classes.BnfEnNewspaperIssue attribute) (text_preparation.importers.lux.classes.LuxNewspaperIssue attribute) (text_preparation.importers.mets_alto.classes.MetsAltoCanonicalIssue attribute) (text_preparation.importers.rero.classes.ReroNewspaperIssue attribute) import_issues() (in module text_preparation.importers.core)

INABroadcastAudioRecord (class in text_preparation.importers.ina.classes) INABroadcastIssue (class in text_preparation.importers.ina.classes) INAIssueDir (in module text_preparation.importers.ina.detect) insert_whitespace() (in module text_preparation.tokenization) is_audio_issue() (in module text_preparation.importers.core) is_gzip (text_preparation.importers.bnf.classes.BnfNewspaperPage attribute) (text_preparation.importers.bnf_en.classes.BnfEnNewspaperPage attribute) is_json (text_preparation.importers.bcul.classes.BculNewspaperIssue attribute) is_multi_date() (in module text_preparation.importers.bnf.helpers) is_xml (text_preparation.importers.bcul.classes.BculNewspaperIssue attribute) issue (text_preparation.importers.bcul.classes.BculNewspaperPage attribute) (text_preparation.importers.bl.classes.BlNewspaperPage attribute) (text_preparation.importers.bnf.classes.BnfNewspaperPage attribute) (text_preparation.importers.bnf_en.classes.BnfEnNewspaperPage attribute) (text_preparation.importers.classes.CanonicalAudioRecord attribute) (text_preparation.importers.classes.CanonicalPage attribute) (text_preparation.importers.ina.classes.INABroadcastAudioRecord attribute) (text_preparation.importers.lux.classes.LuxNewspaperPage attribute) (text_preparation.importers.mets_alto.classes.MetsAltoCanonicalPage attribute) (text_preparation.importers.olive.classes.OliveNewspaperPage attribute) (text_preparation.importers.rero.classes.ReroNewspaperPage attribute) (text_preparation.importers.swa.classes.SWANewspaperPage attribute) (text_preparation.importers.swissinfo.classes.SwissInfoRadioBulletinPage attribute) issue2supports() (in module text_preparation.importers.core) issue_data (text_preparation.importers.bcul.classes.BculNewspaperIssue attribute) (text_preparation.importers.bl.classes.BlNewspaperIssue attribute) (text_preparation.importers.bnf.classes.BnfNewspaperIssue attribute) (text_preparation.importers.bnf_en.classes.BnfEnNewspaperIssue attribute) (text_preparation.importers.classes.CanonicalIssue attribute) (text_preparation.importers.ina.classes.INABroadcastIssue attribute) (text_preparation.importers.lux.classes.LuxNewspaperIssue attribute) (text_preparation.importers.mets_alto.classes.MetsAltoCanonicalIssue attribute) (text_preparation.importers.olive.classes.OliveNewspaperIssue attribute) (text_preparation.importers.rero.classes.ReroNewspaperIssue attribute) (text_preparation.importers.swa.classes.SWANewspaperIssue attribute) (text_preparation.importers.swissinfo.classes.SwissInfoRadioBulletinIssue attribute) issue_uid (text_preparation.importers.bnf.classes.BnfNewspaperIssue attribute) issuedir (text_preparation.importers.classes.CanonicalIssue property)

K

keep_title() (in module text_preparation.importers.olive.helpers)

L

LuxIssueDir (in module text_preparation.importers.lux.detect)

LuxNewspaperIssue (class in text_preparation.importers.lux.classes) LuxNewspaperPage (class in text_preparation.importers.lux.classes)

M

main() (in module text_preparation.importer_scripts.preprocessing.bl_reorganize_original_data) (in module text_preparation.rebuilders.rebuilder) merge_pseudo_tokens() (in module text_preparation.importers.olive.helpers) merge_tokens() (in module text_preparation.importers.olive.helpers) MetsAltoCanonicalIssue (class in text_preparation.importers.mets_alto.classes) MetsAltoCanonicalPage (class in text_preparation.importers.mets_alto.classes) mit_file (text_preparation.importers.bcul.classes.BculNewspaperIssue attribute) module text_preparation.importer_scripts.preprocessing.bl_reorganize_original_data text_preparation.importer_scripts.preprocessing.swissinfo_extract_ocr_from_pdfs text_preparation.importers.bcul.classes text_preparation.importers.bcul.detect text_preparation.importers.bcul.helpers text_preparation.importers.bl.classes text_preparation.importers.bl.detect text_preparation.importers.bnf.classes text_preparation.importers.bnf.detect text_preparation.importers.bnf.helpers text_preparation.importers.bnf.parsers text_preparation.importers.bnf_en.classes text_preparation.importers.bnf_en.detect text_preparation.importers.core text_preparation.importers.fedgaz.classes text_preparation.importers.generic_importer text_preparation.importers.ina.classes text_preparation.importers.ina.detect text_preparation.importers.ina.helpers text_preparation.importers.lux.classes text_preparation.importers.lux.detect text_preparation.importers.lux.helpers text_preparation.importers.mets_alto.alto text_preparation.importers.mets_alto.classes text_preparation.importers.mets_alto.mets text_preparation.importers.olive.classes text_preparation.importers.olive.detect text_preparation.importers.olive.helpers text_preparation.importers.olive.parsers text_preparation.importers.rero.classes text_preparation.importers.rero.detect text_preparation.importers.swa.classes text_preparation.importers.swa.detect text_preparation.importers.swissinfo.classes text_preparation.importers.swissinfo.detect text_preparation.importers.swissinfo.helpers text_preparation.importers.tetml.classes text_preparation.importers.tetml.detect text_preparation.importers.tetml.helpers text_preparation.importers.tetml.parsers text_preparation.rebuilders.helpers text_preparation.rebuilders.rebuilder text_preparation.tokenization text_preparation.utils

N

normalize_hyphenation() (in module text_preparation.importers.olive.helpers) normalize_language() (in module text_preparation.importers.olive.helpers) normalize_line() (in module text_preparation.importers.olive.helpers) notes (text_preparation.importers.swa.classes.SWANewspaperIssue attribute) number (text_preparation.importers.bcul.classes.BculNewspaperPage attribute) (text_preparation.importers.bl.classes.BlNewspaperPage attribute) (text_preparation.importers.bnf.classes.BnfNewspaperPage attribute) (text_preparation.importers.bnf_en.classes.BnfEnNewspaperPage attribute) (text_preparation.importers.classes.CanonicalAudioRecord attribute) (text_preparation.importers.classes.CanonicalPage attribute) (text_preparation.importers.ina.classes.INABroadcastAudioRecord attribute) (text_preparation.importers.lux.classes.LuxNewspaperPage attribute) (text_preparation.importers.mets_alto.classes.MetsAltoCanonicalPage attribute) (text_preparation.importers.olive.classes.OliveNewspaperPage attribute) (text_preparation.importers.rero.classes.ReroNewspaperPage attribute) (text_preparation.importers.swa.classes.SWANewspaperPage attribute) (text_preparation.importers.swissinfo.classes.SwissInfoRadioBulletinPage attribute)

O

olive_detect_issues() (in module text_preparation.importers.olive.detect) olive_image_parser() (in module text_preparation.importers.olive.parsers) olive_parser() (in module text_preparation.importers.olive.parsers) olive_select_issues() (in module text_preparation.importers.olive.detect)

olive_toc_parser() (in module text_preparation.importers.olive.parsers) OliveIssueDir (in module text_preparation.importers.olive.detect) OliveNewspaperIssue (class in text_preparation.importers.olive.classes) OliveNewspaperPage (class in text_preparation.importers.olive.classes)

P

page_data (text_preparation.importers.bcul.classes.BculNewspaperPage attribute) (text_preparation.importers.bl.classes.BlNewspaperPage attribute) (text_preparation.importers.bnf.classes.BnfNewspaperPage attribute) (text_preparation.importers.bnf_en.classes.BnfEnNewspaperPage attribute) (text_preparation.importers.classes.CanonicalPage attribute) (text_preparation.importers.lux.classes.LuxNewspaperPage attribute) (text_preparation.importers.mets_alto.classes.MetsAltoCanonicalPage attribute) (text_preparation.importers.olive.classes.OliveNewspaperPage attribute) (text_preparation.importers.rero.classes.ReroNewspaperPage attribute) (text_preparation.importers.swa.classes.SWANewspaperPage attribute) (text_preparation.importers.swissinfo.classes.SwissInfoRadioBulletinPage attribute) page_width (text_preparation.importers.rero.classes.ReroNewspaperPage attribute) page_xml (text_preparation.importers.olive.classes.OliveNewspaperPage attribute) pages (text_preparation.importers.bcul.classes.BculNewspaperIssue attribute) (text_preparation.importers.bl.classes.BlNewspaperIssue attribute) (text_preparation.importers.bnf.classes.BnfNewspaperIssue attribute) (text_preparation.importers.bnf_en.classes.BnfEnNewspaperIssue attribute) (text_preparation.importers.classes.CanonicalIssue attribute) (text_preparation.importers.lux.classes.LuxNewspaperIssue attribute) (text_preparation.importers.mets_alto.classes.MetsAltoCanonicalIssue attribute) (text_preparation.importers.olive.classes.OliveNewspaperIssue attribute) (text_preparation.importers.rero.classes.ReroNewspaperIssue attribute) (text_preparation.importers.swa.classes.SWANewspaperIssue attribute) (text_preparation.importers.swissinfo.classes.SwissInfoRadioBulletinIssue attribute) pages_to_article() (in module text_preparation.rebuilders.helpers) parse() (text_preparation.importers.bcul.classes.BculNewspaperPage method) (text_preparation.importers.bnf.classes.BnfNewspaperPage method) (text_preparation.importers.classes.CanonicalAudioRecord method) (text_preparation.importers.classes.CanonicalPage method) (text_preparation.importers.fedgaz.classes.FedgazNewspaperPage method) (text_preparation.importers.ina.classes.INABroadcastAudioRecord method) (text_preparation.importers.mets_alto.classes.MetsAltoCanonicalPage method) (text_preparation.importers.olive.classes.OliveNewspaperPage method) (text_preparation.importers.swa.classes.SWANewspaperPage method) (text_preparation.importers.swissinfo.classes.SwissInfoRadioBulletinPage method) (text_preparation.importers.tetml.classes.TetmlNewspaperPage method)

parse_articles() (text_preparation.importers.fedgaz.classes.FedgazNewspaperIssue method) (text_preparation.importers.tetml.classes.TetmlNewspaperIssue method) parse_char_tokens() (in module text_preparation.importers.bcul.helpers) parse_date() (in module text_preparation.importers.bcul.helpers) (in module text_preparation.importers.bnf.helpers) parse_dir() (in module text_preparation.importers.bnf_en.detect) parse_div_parts() (in module text_preparation.importers.bnf.parsers) parse_embedded_cis() (in module text_preparation.importers.bnf.parsers) parse_lines() (in module text_preparation.importers.swissinfo.helpers) parse_mets_amdsec() (in module text_preparation.importers.mets_alto.mets) parse_mets_filegroup() (in module text_preparation.importers.mets_alto.mets) parse_printspace() (in module text_preparation.importers.bnf.parsers) (in module text_preparation.importers.mets_alto.alto) parse_style() (in module text_preparation.importers.mets_alto.alto) parse_styles() (in module text_preparation.importers.olive.parsers) parse_textblock() (in module text_preparation.importers.bcul.helpers) parse_textline() (in module text_preparation.importers.bcul.helpers) (in module text_preparation.importers.mets_alto.alto) path (text_preparation.importers.bcul.classes.BculNewspaperIssue attribute) (text_preparation.importers.bcul.classes.BculNewspaperPage attribute) (text_preparation.importers.bl.classes.BlNewspaperIssue attribute) (text_preparation.importers.bnf.classes.BnfNewspaperIssue attribute) (text_preparation.importers.bnf_en.classes.BnfEnNewspaperIssue attribute) (text_preparation.importers.classes.CanonicalIssue attribute) (text_preparation.importers.ina.classes.INABroadcastIssue attribute) (text_preparation.importers.lux.classes.LuxNewspaperIssue attribute) (text_preparation.importers.mets_alto.classes.MetsAltoCanonicalIssue attribute) (text_preparation.importers.olive.classes.OliveNewspaperIssue attribute) (text_preparation.importers.rero.classes.ReroNewspaperIssue attribute) (text_preparation.importers.swa.classes.SWANewspaperIssue attribute) (text_preparation.importers.swissinfo.classes.SwissInfoRadioBulletinIssue attribute) (text_preparation.importers.swissinfo.classes.SwissInfoRadioBulletinPage attribute) pdf_to_jp2_and_ocr_json() (in module text_preparation.importer_scripts.preprocessing.swissinfo_extract_ocr_from_pdfs) process_blocks_of_page() (in module text_preparation.importer_scripts.preprocessing.swissinfo_extract_ocr_from_pdfs) process_supports() (in module text_preparation.importers.core)

Q

query_iiif_api() (text_preparation.importers.bcul.classes.BculNewspaperIssue method)

R

read_issue() (in module text_preparation.rebuilders.helpers) read_issue_supports() (in module text_preparation.rebuilders.helpers) read_page() (in module text_preparation.rebuilders.helpers) read_xml() (in module text_preparation.utils) rebuild_for_passim() (in module text_preparation.rebuilders.helpers) rebuild_for_solr() (in module text_preparation.rebuilders.helpers) rebuild_issues() (in module text_preparation.rebuilders.rebuilder) recompose_page() (in module text_preparation.importers.olive.helpers) recompose_ToC() (in module text_preparation.importers.olive.helpers) reconstruct_iiif_link() (in module text_preparation.rebuilders.helpers) record_data (text_preparation.importers.classes.CanonicalAudioRecord attribute) (text_preparation.importers.ina.classes.INABroadcastAudioRecord attribute)

rejoin_cis() (in module text_preparation.rebuilders.helpers) remove_filelocks() (in module text_preparation.importers.core) remove_key_from_block() (in module text_preparation.importer_scripts.preprocessing.swissinfo_extract_ocr_from_pdfs) remove_page_number() (in module text_preparation.importers.tetml.helpers) remove_section_cis() (in module text_preparation.importers.lux.helpers) Rero2IssueDir (in module text_preparation.importers.rero.detect) ReroNewspaperIssue (class in text_preparation.importers.rero.classes) ReroNewspaperPage (class in text_preparation.importers.rero.classes) rescale_block_coords() (in module text_preparation.importer_scripts.preprocessing.swissinfo_extract_ocr_from_pdfs) rescale_coords() (in module text_preparation.utils)

S

save_as_jp2() (in module text_preparation.importer_scripts.preprocessing.swissinfo_extract_ocr_from_pdfs) secondary_date (text_preparation.importers.bnf.classes.BnfNewspaperIssue attribute) SECTION (in module text_preparation.importers.bnf.helpers) section_is_article() (in module text_preparation.importers.lux.helpers) select_issues() (in module text_preparation.importers.bcul.detect) (in module text_preparation.importers.bl.detect) (in module text_preparation.importers.bnf.detect) (in module text_preparation.importers.bnf_en.detect) (in module text_preparation.importers.ina.detect) (in module text_preparation.importers.lux.detect) (in module text_preparation.importers.rero.detect) (in module text_preparation.importers.swa.detect) (in module text_preparation.importers.swissinfo.detect)

serialize_supports() (in module text_preparation.importers.core) SwaIssueDir (in module text_preparation.importers.swa.detect) SWANewspaperIssue (class in text_preparation.importers.swa.classes) SWANewspaperPage (class in text_preparation.importers.swa.classes) SwissInfoIssueDir (in module text_preparation.importers.swissinfo.detect) SwissInfoRadioBulletinIssue (class in text_preparation.importers.swissinfo.classes) SwissInfoRadioBulletinPage (class in text_preparation.importers.swissinfo.classes)

T

temp_pages (text_preparation.importers.swa.classes.SWANewspaperIssue attribute) tetml_detect_issues() (in module text_preparation.importers.tetml.detect) tetml_parser() (in module text_preparation.importers.tetml.parsers) tetml_select_issues() (in module text_preparation.importers.tetml.detect) TetmlIssueDir (in module text_preparation.importers.tetml.detect) TetmlNewspaperIssue (class in text_preparation.importers.tetml.classes) TetmlNewspaperPage (class in text_preparation.importers.tetml.classes) text_apply_breaks() (in module text_preparation.rebuilders.helpers) text_preparation.importer_scripts.preprocessing.bl_reorganize_original_data module text_preparation.importer_scripts.preprocessing.swissinfo_extract_ocr_from_pdfs module text_preparation.importers.bcul.classes module text_preparation.importers.bcul.detect module text_preparation.importers.bcul.helpers module text_preparation.importers.bl.classes module text_preparation.importers.bl.detect module text_preparation.importers.bnf.classes module text_preparation.importers.bnf.detect module text_preparation.importers.bnf.helpers module text_preparation.importers.bnf.parsers module text_preparation.importers.bnf_en.classes module text_preparation.importers.bnf_en.detect module text_preparation.importers.core module text_preparation.importers.fedgaz.classes module text_preparation.importers.generic_importer module text_preparation.importers.ina.classes module text_preparation.importers.ina.detect module text_preparation.importers.ina.helpers module text_preparation.importers.lux.classes module text_preparation.importers.lux.detect module

text_preparation.importers.lux.helpers module text_preparation.importers.mets_alto.alto module text_preparation.importers.mets_alto.classes module text_preparation.importers.mets_alto.mets module text_preparation.importers.olive.classes module text_preparation.importers.olive.detect module text_preparation.importers.olive.helpers module text_preparation.importers.olive.parsers module text_preparation.importers.rero.classes module text_preparation.importers.rero.detect module text_preparation.importers.swa.classes module text_preparation.importers.swa.detect module text_preparation.importers.swissinfo.classes module text_preparation.importers.swissinfo.detect module text_preparation.importers.swissinfo.helpers module text_preparation.importers.tetml.classes module text_preparation.importers.tetml.detect module text_preparation.importers.tetml.helpers module text_preparation.importers.tetml.parsers module text_preparation.rebuilders.helpers module text_preparation.rebuilders.rebuilder module text_preparation.tokenization module text_preparation.utils module toc_data (text_preparation.importers.olive.classes.OliveNewspaperIssue attribute) (text_preparation.importers.olive.classes.OliveNewspaperPage attribute) TokPosition (class in text_preparation.importers.fedgaz.classes)

U

upload() (in module text_preparation.rebuilders.rebuilder)

upload_issues() (in module text_preparation.importers.core) upload_supports() (in module text_preparation.importers.core)

V

validate() (text_preparation.importers.classes.CanonicalAudioRecord method) (text_preparation.importers.classes.CanonicalIssue method) (text_preparation.importers.classes.CanonicalPage method) validate_audio_schema() (in module text_preparation.utils)

validate_issue_schema() (in module text_preparation.utils) validate_page_schema() (in module text_preparation.utils) verify_imported_issues() (in module text_preparation.utils) verify_issue_has_ocr_files() (in module text_preparation.importers.bcul.helpers)

W

word2json() (in module text_preparation.importers.tetml.helpers) write_error() (in module text_preparation.importers.core) (in module text_preparation.utils)

write_jsonlines_file() (in module text_preparation.utils)

X

xml (text_preparation.importers.bcul.classes.BculNewspaperPage property) (text_preparation.importers.bnf.classes.BnfNewspaperIssue property) (text_preparation.importers.bnf.classes.BnfNewspaperPage property) (text_preparation.importers.ina.classes.INABroadcastAudioRecord property) (text_preparation.importers.mets_alto.classes.MetsAltoCanonicalIssue property) (text_preparation.importers.mets_alto.classes.MetsAltoCanonicalPage property)