Index

Symbols

--ai invoice2data command line option --ai-fallback invoice2data command line option --copy invoice2data command line option --csv-lines invoice2data command line option --debug invoice2data command line option --debug-optimized-str invoice2data command line option --exclude-built-in-templates invoice2data command line option --filename-format invoice2data command line option --in-automation invoice2data command line option --input-reader invoice2data command line option --interactive invoice2data command line option --move invoice2data command line option --new-template invoice2data command line option --no-color invoice2data command line option

--output-date-format invoice2data command line option --output-format invoice2data command line option --output-name invoice2data command line option --template-folder invoice2data command line option --template-out invoice2data command line option --version invoice2data command line option -c invoice2data command line option -d invoice2data command line option -f invoice2data command line option -i invoice2data command line option -m invoice2data command line option -o invoice2data command line option -t invoice2data command line option

A

ai_fallback_extract() (in module invoice2data.ai.fallback) AIConfig (class in invoice2data.ai.config)

AIProvider (class in invoice2data.ai.__interface__) api_key (invoice2data.ai.config.AIConfig attribute) available_modules() (in module invoice2data.input)

B

base_url (invoice2data.ai.config.AIConfig attribute)

C

Candidate (class in invoice2data.extract.candidates)

classify_identifier() (in module invoice2data.extract.validators) compile() (in module invoice2data.extract._regex)

D

defusedxml_available() (in module invoice2data.output.to_xml)

dict_to_tags() (in module invoice2data.output.to_xml) doctr_available() (in module invoice2data.input.doctr)

E

end (invoice2data.extract.candidates.Candidate attribute) ENGINE (in module invoice2data.extract._regex) extract() (in module invoice2data.extract.plugins.camelot) (in module invoice2data.extract.plugins.lines) (in module invoice2data.extract.plugins.tables)

extract_data() (in module invoice2data) extract_structured() (invoice2data.ai.__interface__.AIProvider method) extract_text() (in module invoice2data.input)

F

field_regex() (in module invoice2data.extract.template_builder) field_regex_from_candidate() (in module invoice2data.extract.template_builder) fields (invoice2data.exceptions.RequiredFieldsMissingError attribute) find_amounts() (in module invoice2data.extract.candidates) find_candidates() (in module invoice2data.extract.candidates)

find_dates() (in module invoice2data.extract.candidates) find_identifiers() (in module invoice2data.extract.candidates) findall() (in module invoice2data.extract._regex) finditer() (in module invoice2data.extract._regex) format_item() (in module invoice2data.output.to_json)

G

generate_template() (in module invoice2data.ai.template_generator)

get_provider() (in module invoice2data.ai.__interface__)

I

INPUT_FILES invoice2data command line option INPUT_MODULES (in module invoice2data.input) invoice2data command line option --ai --ai-fallback --copy --csv-lines --debug --debug-optimized-str --exclude-built-in-templates --filename-format --in-automation --input-reader --interactive --move --new-template --no-color --output-date-format --output-format --output-name --template-folder --template-out --version -c -d -f -i -m -o -t INPUT_FILES invoice2data.ai.__interface__ module invoice2data.ai.config module invoice2data.ai.fallback module invoice2data.ai.schema_json module invoice2data.ai.template_generator module invoice2data.exceptions module invoice2data.extract._dates module invoice2data.extract._regex module invoice2data.extract.candidates module invoice2data.extract.loader module invoice2data.extract.parsers.lines module invoice2data.extract.parsers.regex module invoice2data.extract.parsers.static module invoice2data.extract.plugins.camelot module invoice2data.extract.plugins.lines module

invoice2data.extract.plugins.tables module invoice2data.extract.schema module invoice2data.extract.suggestions module invoice2data.extract.template_builder module invoice2data.extract.validators module invoice2data.input module invoice2data.input.doctr module invoice2data.input.gvision module invoice2data.input.hotpdf module invoice2data.input.ocrmypdf module invoice2data.input.paddleocr module invoice2data.input.pdfium module invoice2data.input.pdfminer_wrapper module invoice2data.input.pdfoxide module invoice2data.input.pdfplumber module invoice2data.input.pdftotext module invoice2data.input.tesseract module invoice2data.input.text module invoice2data.output module invoice2data.output.to_csv module invoice2data.output.to_json module invoice2data.output.to_xml module INVOICE_FIELDS (in module invoice2data.extract.schema) invoice_json_schema() (in module invoice2data.ai.schema_json) InvoiceProcessingError is_available() (in module invoice2data.extract.plugins.camelot) (in module invoice2data.input) (in module invoice2data.input.doctr) (in module invoice2data.input.gvision) (in module invoice2data.input.hotpdf) (in module invoice2data.input.ocrmypdf) (in module invoice2data.input.paddleocr) (in module invoice2data.input.pdfium) (in module invoice2data.input.pdfminer_wrapper) (in module invoice2data.input.pdfoxide) (in module invoice2data.input.pdfplumber) (in module invoice2data.input.pdftotext) (in module invoice2data.input.tesseract) (invoice2data.ai.__interface__.AIProvider method)

K

kind (invoice2data.extract.candidates.Candidate attribute)

L

LINE_FIELD_ALIASES (in module invoice2data.extract.schema)

LINE_FIELDS (in module invoice2data.extract.schema) load_config() (in module invoice2data.ai.config)

M

model (invoice2data.ai.config.AIConfig attribute) module invoice2data.ai.__interface__ invoice2data.ai.config invoice2data.ai.fallback invoice2data.ai.schema_json invoice2data.ai.template_generator invoice2data.exceptions invoice2data.extract._dates invoice2data.extract._regex invoice2data.extract.candidates invoice2data.extract.loader invoice2data.extract.parsers.lines invoice2data.extract.parsers.regex invoice2data.extract.parsers.static invoice2data.extract.plugins.camelot invoice2data.extract.plugins.lines invoice2data.extract.plugins.tables invoice2data.extract.schema invoice2data.extract.suggestions invoice2data.extract.template_builder invoice2data.extract.validators invoice2data.input invoice2data.input.doctr invoice2data.input.gvision invoice2data.input.hotpdf invoice2data.input.ocrmypdf invoice2data.input.paddleocr invoice2data.input.pdfium invoice2data.input.pdfminer_wrapper invoice2data.input.pdfoxide invoice2data.input.pdfplumber invoice2data.input.pdftotext invoice2data.input.tesseract invoice2data.input.text invoice2data.output invoice2data.output.to_csv invoice2data.output.to_json invoice2data.output.to_xml

N

name (invoice2data.ai.__interface__.AIProvider attribute)

normalize_line_fields() (in module invoice2data.extract.schema) NoTemplateFoundError

O

ocrmypdf_available() (in module invoice2data.input.ocrmypdf)

open_output() (in module invoice2data.output) ordered_load() (in module invoice2data.extract.loader)

P

paddleocr_available() (in module invoice2data.input.paddleocr) parse() (in module invoice2data.extract.parsers.lines) (in module invoice2data.extract.parsers.regex) parse_block() (in module invoice2data.extract.parsers.lines) parse_by_rule() (in module invoice2data.extract.parsers.lines) parse_current_row() (in module invoice2data.extract.parsers.lines) parse_date() (in module invoice2data.extract._dates)

parse_line() (in module invoice2data.extract.parsers.lines) parsed (invoice2data.extract.candidates.Candidate attribute) pre_process_pdf() (in module invoice2data.input.ocrmypdf) prepare_template() (in module invoice2data.extract.loader) prettify() (in module invoice2data.output.to_xml) preview_field() (in module invoice2data.extract.template_builder) preview_template() (in module invoice2data.ai.template_generator) provider (invoice2data.ai.config.AIConfig attribute)

R

read_templates() (in module invoice2data.extract.loader)

RECOMMENDED_SCAN_OPTIONS (in module invoice2data.input.ocrmypdf) RequiredFieldsMissingError

S

search() (in module invoice2data.extract._regex) set_field_regex() (in module invoice2data.extract.template_builder) split() (in module invoice2data.extract._regex) start (invoice2data.extract.candidates.Candidate attribute) sub() (in module invoice2data.extract._regex) suggest_fields() (in module invoice2data.extract.suggestions)

suggest_from_text() (in module invoice2data.extract.suggestions) suggested_template() (in module invoice2data.extract.template_builder) SUPPORTS_AREA (in module invoice2data.input.doctr) (in module invoice2data.input.gvision) (in module invoice2data.input.paddleocr) (in module invoice2data.input.pdfium) supports_area() (in module invoice2data.input)

T

TAX_LINE_FIELDS (in module invoice2data.extract.schema) template_name (invoice2data.exceptions.RequiredFieldsMissingError attribute) TEMPLATE_SCHEMA (in module invoice2data.ai.template_generator) to_text() (in module invoice2data.input.doctr) (in module invoice2data.input.gvision) (in module invoice2data.input.hotpdf) (in module invoice2data.input.ocrmypdf) (in module invoice2data.input.paddleocr) (in module invoice2data.input.pdfium) (in module invoice2data.input.pdfminer_wrapper) (in module invoice2data.input.pdfoxide) (in module invoice2data.input.pdfplumber) (in module invoice2data.input.pdftotext) (in module invoice2data.input.tesseract) (in module invoice2data.input.text)

to_yaml() (in module invoice2data.extract.template_builder)

V

validate_bic() (in module invoice2data.extract.validators) validate_iban() (in module invoice2data.extract.validators) validate_output() (in module invoice2data.extract.schema)

validate_vat() (in module invoice2data.extract.validators) VALIDATORS (in module invoice2data.extract.validators) value (invoice2data.extract.candidates.Candidate attribute) VENDOR_BASE_URLS (in module invoice2data.ai.config)

W

write_to_file() (in module invoice2data.output.to_csv) (in module invoice2data.output.to_json) (in module invoice2data.output.to_xml)