smoothtext.internal package

Submodules

smoothtext.internal.syllabifier module

class smoothtext.internal.syllabifier.SyllabifierBase

Bases: object

abstract count(token)
Return type:

int

abstract syllabify(token)
Return type:

list[str]

class smoothtext.internal.syllabifier.SyllabifierEng(backend, language)

Bases: SyllabifierBase

count(token)
Return type:

int

syllabify(token)
Return type:

list[str]

class smoothtext.internal.syllabifier.SyllabifierGer

Bases: SyllabifierPyphenBase

class smoothtext.internal.syllabifier.SyllabifierPyphenBase(language)

Bases: SyllabifierBase

count(token)
Return type:

int

syllabify(token)
Return type:

list[str]

class smoothtext.internal.syllabifier.SyllabifierRus

Bases: SyllabifierPyphenBase

class smoothtext.internal.syllabifier.SyllabifierTur

Bases: SyllabifierBase

count(token)
Return type:

int

syllabify(token)
Return type:

list[str]

smoothtext.internal.tokenizer module

class smoothtext.internal.tokenizer.NLTKTokenizer(language)

Bases: TokenizerBase

sentencize(text)
Return type:

list[str]

tokenize(text, split_sentences)
Return type:

list[str]

word_frequencies(text, lemmatize)
Return type:

dict[str, int]

class smoothtext.internal.tokenizer.StanzaTokenizer(language)

Bases: TokenizerBase

static processors(language)
Return type:

str

sentencize(text)
Return type:

list[str]

tokenize(text, split_sentences)
Return type:

list[str]

word_frequencies(text, lemmatize)
Return type:

dict[str, int]

class smoothtext.internal.tokenizer.TokenizerBase

Bases: object

abstract sentencize(text)
Return type:

list[str]

abstract tokenize(text, split_sentences)
Return type:

list[str]

abstract word_frequencies(text, lemmatize)
Return type:

dict[str, int]

Module contents