Indic NLP Langinfo

This code is from: https://github.com/anoopkunchukuttan/indic_nlp_library

source

is_number_offset

def is_number_offset(
    c_offset
):

Is the offset a number

source

is_approximant_offset

def is_approximant_offset(
    c_offset
):

Is the offset an approximant consonant

source

is_fricative_offset

def is_fricative_offset(
    c_offset
):

Is the offset a fricative consonant

source

is_nasal_offset

def is_nasal_offset(
    c_offset
):

Is the offset a nasal consonant

source

is_unaspirated_offset

def is_unaspirated_offset(
    c_offset
):

Is the offset a unaspirated consonant

source

is_aspirated_offset

def is_aspirated_offset(
    c_offset
):

Is the offset a aspirated consonant

source

is_unvoiced_offset

def is_unvoiced_offset(
    c_offset
):

Is the offset a unvoiced consonant

source

is_voiced_offset

def is_voiced_offset(
    c_offset
):

Is the offset a voiced consonant

source

is_labial_offset

def is_labial_offset(
    c_offset
):

Is the offset a labial

source

is_dental_offset

def is_dental_offset(
    c_offset
):

Is the offset a dental

source

is_retroflex_offset

def is_retroflex_offset(
    c_offset
):

Is the offset a retroflex

source

is_palatal_offset

def is_palatal_offset(
    c_offset
):

Is the offset a palatal

source

is_velar_offset

def is_velar_offset(
    c_offset
):

Is the offset a velar

source

is_consonant_offset

def is_consonant_offset(
    c_offset
):

Is the offset a consonant

source

is_aum_offset

def is_aum_offset(
    c_offset
):

Is the offset a vowel sign (maatraa)

source

is_nukta_offset

def is_nukta_offset(
    c_offset
):

Is the offset the halanta offset

source

is_halanta_offset

def is_halanta_offset(
    c_offset
):

Is the offset the halanta offset

source

is_vowel_sign_offset

def is_vowel_sign_offset(
    c_offset
):

Is the offset a vowel sign (maatraa)

source

is_vowel_offset

def is_vowel_offset(
    c_offset
):

Is the offset a vowel

source

is_number

def is_number(
    c, lang
):

Is the character a number

source

is_approximant

def is_approximant(
    c, lang
):

Is the character an approximant consonant

source

is_fricative

def is_fricative(
    c, lang
):

Is the character a fricative consonant

source

is_nasal

def is_nasal(
    c, lang
):

Is the character a nasal consonant

source

is_unaspirated

def is_unaspirated(
    c, lang
):

Is the character a unaspirated consonant

source

is_aspirated

def is_aspirated(
    c, lang
):

Is the character a aspirated consonant

source

is_unvoiced

def is_unvoiced(
    c, lang
):

Is the character a unvoiced consonant

source

is_voiced

def is_voiced(
    c, lang
):

Is the character a voiced consonant

source

is_labial

def is_labial(
    c, lang
):

Is the character a labial

source

is_dental

def is_dental(
    c, lang
):

Is the character a dental

source

is_retroflex

def is_retroflex(
    c, lang
):

Is the character a retroflex

source

is_palatal

def is_palatal(
    c, lang
):

Is the character a palatal

source

is_velar

def is_velar(
    c, lang
):

Is the character a velar

source

is_consonant

def is_consonant(
    c, lang
):

Is the character a consonant

source

is_aum

def is_aum(
    c, lang
):

Is the character a vowel sign (maatraa)

source

is_nukta

def is_nukta(
    c, lang
):

Is the character the halanta character

source

is_halanta

def is_halanta(
    c, lang
):

Is the character the halanta character

source

is_vowel_sign

def is_vowel_sign(
    c, lang
):

Is the character a vowel sign (maatraa)

source

is_vowel

def is_vowel(
    c, lang
):

Is the character a vowel

source

is_indiclang_char

def is_indiclang_char(
    c, lang
):

Applicable to Brahmi derived Indic scripts

source

in_coordinated_range

def in_coordinated_range(
    c_offset
):

Applicable to Brahmi derived Indic scripts

source

offset_to_char

def offset_to_char(
    c, lang
):

Applicable to Brahmi derived Indic scripts

source

get_offset

def get_offset(
    c, lang
):

Applicable to Brahmi derived Indic scripts

source

is_danda_delim

def is_danda_delim(
    lang
):

Returns True if danda/double danda is a possible delimiter for the language