sktalk.corpus.parsing.cha

Classes

Abstract parser class.

Module Contents

class sktalk.corpus.parsing.cha.ChaFile(path: str)[source]

Bases: sktalk.corpus.parsing.parser.InputFile

Abstract parser class.

PARTICIPANT_REGEX = '(^\\*(?P<participant>[^:]+)\\:)?'[source]

UTTERANCE_REGEX = '\\s+(?P<utterance>.*)\\s+'[source]

TIMING_REGEX = '\\D(?P<timing>\\d{1,9}_\\d{1,9})\\D'[source]

LINE_REGEX[source]

SPACER_REGEX = '\\((?P<spacer>[\\d.]+)\\)'[source]

_pla_reader() → pylangacq.Reader[source]

_extract_metadata()[source]

_extract_utterances()[source]

static _extract_info(line)[source]

static _clean_utterance(utterance)[source]

static _clean_timing(timing)[source]