Index

_

__init__() (bp_text.database.BibTexDatabase method) (bp_text.file.File method) (bp_text.language.LanguageDetector method) (bp_text.page.Page method) (bp_text.pdf.PdfFile method) (bp_text.pdf.PdfPage method) (bp_text.pool.Pool method) (bp_text.pool.PoolItem method) (bp_text.text.Text method) (bp_text.textfragment.TextFragment method) (bp_text.txt.TxtFile method) (bp_text.txt.TxtPage method)

A

auto_extract (bp_text.pdf.PdfFile property)

B

BibTexDatabase (class in bp_text.database) bp_text.database module bp_text.file module bp_text.language module bp_text.page module bp_text.pdf module

bp_text.pool module bp_text.text module bp_text.textfragment module bp_text.txt module bp_text.utilities module

C

convert_langcode() (in module bp_text.language) convert_latex_umlauts() (in module bp_text.database) count_words() (bp_text.page.Page method) (bp_text.pdf.PdfPage method) (bp_text.txt.TxtPage method)

cycle_data() (in module bp_text.pool)

D

data (bp_text.database.BibTexDatabase property) (bp_text.file.File property) (bp_text.page.Page property) (bp_text.pdf.PdfFile property) (bp_text.pdf.PdfPage property) (bp_text.pool.Pool property) (bp_text.pool.PoolItem property) (bp_text.textfragment.TextFragment property) (bp_text.txt.TxtFile property) (bp_text.txt.TxtPage property)

Database (class in bp_text.database) default_get_data_func (bp_text.pool.PoolItem property) DEFAULT_LANGUAGES (in module bp_text.language) detect_lang() (bp_text.page.Page method) (bp_text.pdf.PdfPage method) (bp_text.txt.TxtPage method) detector (bp_text.language.LanguageDetector property) doc (bp_text.text.Text property)

E

entries (bp_text.database.BibTexDatabase property) extract_text() (bp_text.pdf.PdfFile method) (bp_text.pdf.PdfPage method)

extract_text_with_ocr() (bp_text.pdf.PdfFile method) extract_text_without_ocr() (bp_text.pdf.PdfFile method)

F

file (bp_text.file.File property) (bp_text.pdf.PdfFile property) (bp_text.pdf.PdfPage property) (bp_text.txt.TxtFile property) File (class in bp_text.file)

file_checksum (bp_text.file.File property) (bp_text.pdf.PdfFile property) (bp_text.txt.TxtFile property) file_checksum() (in module bp_text.utilities) find_entries() (bp_text.database.BibTexDatabase method) format_org() (bp_text.textfragment.TextFragment method)

G

get() (bp_text.pool.Pool method) get_data() (bp_text.pool.PoolItem method) get_entry_by_key() (bp_text.database.BibTexDatabase method) get_nlp() (in module bp_text.text)

get_nth_entry() (bp_text.database.BibTexDatabase method) get_page() (bp_text.pdf.PdfFile method) get_page_label() (bp_text.pdf.PdfFile method) get_primary_lang() (bp_text.pdf.PdfFile method) (bp_text.txt.TxtFile method)

I

iso_639_1_to_langid() (in module bp_text.language)

K

key (bp_text.pool.PoolItem property) (bp_text.textfragment.TextFragment property)

L

lang (bp_text.page.Page property) (bp_text.pdf.PdfFile property) (bp_text.pdf.PdfPage property) (bp_text.txt.TxtFile property) (bp_text.txt.TxtPage property)

LANG_SPACY_MODELS (in module bp_text.text) langid_to_iso_639_1() (in module bp_text.language) LanguageDetector (class in bp_text.language) languages (bp_text.language.LanguageDetector property) load() (bp_text.database.BibTexDatabase method) (bp_text.database.Database method)

M

make_pool() (bp_text.database.BibTexDatabase method) meta (bp_text.pool.PoolItem property) (bp_text.textfragment.TextFragment property) module bp_text.database bp_text.file bp_text.language bp_text.page bp_text.pdf bp_text.pool bp_text.text bp_text.textfragment bp_text.txt bp_text.utilities

N

next_data (bp_text.pool.PoolItem property)

P

Page (class in bp_text.page) page_label (bp_text.page.Page property) (bp_text.pdf.PdfPage property) (bp_text.textfragment.TextFragment property) (bp_text.txt.TxtPage property) page_num (bp_text.page.Page property) (bp_text.pdf.PdfPage property) (bp_text.txt.TxtPage property)

PdfFile (class in bp_text.pdf) PdfPage (class in bp_text.pdf) Pool (class in bp_text.pool) PoolItem (class in bp_text.pool)

R

random_data() (in module bp_text.pool) raw_text (bp_text.page.Page property) (bp_text.pdf.PdfPage property) (bp_text.txt.TxtPage property)

read_pickle() (in module bp_text.utilities) reader (bp_text.pdf.PdfFile property)

S

set_reader() (bp_text.pdf.PdfFile method)

split_fields_by() (bp_text.database.BibTexDatabase method)

T

text (bp_text.page.Page property) (bp_text.pdf.PdfPage property) (bp_text.text.Text property) (bp_text.txt.TxtPage property)

Text (class in bp_text.text) TextFragment (class in bp_text.textfragment) textfragments_to_org() (in module bp_text.textfragment) TxtFile (class in bp_text.txt) TxtPage (class in bp_text.txt)

U

update() (bp_text.file.File method) (bp_text.language.LanguageDetector method) (bp_text.page.Page method) (bp_text.pdf.PdfFile method) (bp_text.pdf.PdfPage method) (bp_text.text.Text method) (bp_text.txt.TxtFile method) (bp_text.txt.TxtPage method)

V

verbose (bp_text.file.File property) (bp_text.page.Page property) (bp_text.pdf.PdfFile property) (bp_text.pdf.PdfPage property) (bp_text.txt.TxtFile property) (bp_text.txt.TxtPage property)

W

write_pickle() (in module bp_text.utilities)