classroom.utils.korean module

class classroom.utils.korean.Korean(text)

Bases: object

class Filter

Bases: object

do(sequence, character, index)

post(sequence)

pre(sequence)

class Syllable(**kwargs)

Bases: object

combine()

decompose()

has_double_coda()

has_double_onset()

index_coda = None

index_nucleus = None

index_onset = None

is_completed()

letter = None

phoneme_coda = None

phoneme_nucleus = None

phoneme_onset = None

romanize()

exception SyllableFailedException

Bases: Exception

exception TypeErrorException

Bases: Exception

character_list = None

static is_korean(text, **kwargs)

static is_korean_phoneme(text, **kwargs)

join()

parse()

phoneme_coda_dict = {' ': 0, 'ㄱ': 1, 'ㄲ': 2, 'ㄳ': 3, 'ㄴ': 4, 'ㄵ': 5, 'ㄶ': 6, 'ㄷ': 7, 'ㄹ': 8, 'ㄺ': 9, 'ㄻ': 10, 'ㄼ': 11, 'ㄽ': 12, 'ㄾ': 13, 'ㄿ': 14, 'ㅀ': 15, 'ㅁ': 16, 'ㅂ': 17, 'ㅄ': 18, 'ㅅ': 19, 'ㅆ': 20, 'ㅇ': 21, 'ㅈ': 22, 'ㅊ': 23, 'ㅋ': 24, 'ㅌ': 25, 'ㅍ': 26, 'ㅎ': 27}

phoneme_coda_list = [' ', 'ㄱ', 'ㄲ', 'ㄳ', 'ㄴ', 'ㄵ', 'ㄶ', 'ㄷ', 'ㄹ', 'ㄺ', 'ㄻ', 'ㄼ', 'ㄽ', 'ㄾ', 'ㄿ', 'ㅀ', 'ㅁ', 'ㅂ', 'ㅄ', 'ㅅ', 'ㅆ', 'ㅇ', 'ㅈ', 'ㅊ', 'ㅋ', 'ㅌ', 'ㅍ', 'ㅎ']

phoneme_coda_list_len = 28

phoneme_double_consonant_dict = {'ㄲ': ['ㄱ', 'ㄱ'], 'ㄳ': ['ㄱ', 'ㅅ'], 'ㄵ': ['ㄴ', 'ㅈ'], 'ㄶ': ['ㄴ', 'ㅎ'], 'ㄸ': ['ㄷ', 'ㄷ'], 'ㄺ': ['ㄹ', 'ㄱ'], 'ㄻ': ['ㄹ', 'ㅁ'], 'ㄼ': ['ㄹ', 'ㅂ'], 'ㄽ': ['ㄹ', 'ㅅ'], 'ㄾ': ['ㄹ', 'ㅌ'], 'ㄿ': ['ㄹ', 'ㅍ'], 'ㅀ': ['ㄹ', 'ㅎ'], 'ㅃ': ['ㅂ', 'ㅂ'], 'ㅄ': ['ㅂ', 'ㅅ'], 'ㅆ': ['ㅅ', 'ㅅ'], 'ㅉ': ['ㅈ', 'ㅈ']}

phoneme_lenis_to_asprite_dict = {'ㄱ': 'ㅋ', 'ㄷ': 'ㅌ', 'ㅂ': 'ㅍ', 'ㅈ': 'ㅊ'}

phoneme_lenis_to_fortis_dict = {'ㄱ': 'ㄲ', 'ㄷ': 'ㄸ', 'ㅂ': 'ㅃ', 'ㅅ': 'ㅆ', 'ㅈ': 'ㅉ'}

phoneme_nucleus_combine_dict = {'ㅗ+ㅏ': 'ㅘ', 'ㅗ+ㅐ': 'ㅙ', 'ㅗ+ㅣ': 'ㅚ', 'ㅜ+ㅓ': 'ㅝ', 'ㅜ+ㅔ': 'ㅞ', 'ㅜ+ㅣ': 'ㅟ', 'ㅡ+ㅣ': 'ㅢ'}

phoneme_nucleus_dict = {'ㅏ': 0, 'ㅐ': 1, 'ㅑ': 2, 'ㅒ': 3, 'ㅓ': 4, 'ㅔ': 5, 'ㅕ': 6, 'ㅖ': 7, 'ㅗ': 8, 'ㅘ': 9, 'ㅙ': 10, 'ㅚ': 11, 'ㅛ': 12, 'ㅜ': 13, 'ㅝ': 14, 'ㅞ': 15, 'ㅟ': 16, 'ㅠ': 17, 'ㅡ': 18, 'ㅢ': 19, 'ㅣ': 20}

phoneme_nucleus_list = ['ㅏ', 'ㅐ', 'ㅑ', 'ㅒ', 'ㅓ', 'ㅔ', 'ㅕ', 'ㅖ', 'ㅗ', 'ㅘ', 'ㅙ', 'ㅚ', 'ㅛ', 'ㅜ', 'ㅝ', 'ㅞ', 'ㅟ', 'ㅠ', 'ㅡ', 'ㅢ', 'ㅣ']

phoneme_nucleus_list_len = 21

phoneme_nucleus_phonetic_combine_dict = {'ㅗㅏ': 'ㅘ', 'ㅗㅐ': 'ㅙ', 'ㅗㅓ': 'ㅝ', 'ㅗㅔ': 'ㅞ', 'ㅗㅣ': 'ㅚ', 'ㅜㅏ': 'ㅘ', 'ㅜㅐ': 'ㅙ', 'ㅜㅓ': 'ㅝ', 'ㅜㅔ': 'ㅞ', 'ㅜㅣ': 'ㅟ', 'ㅡㅣ': 'ㅢ', 'ㅣㅏ': 'ㅑ', 'ㅣㅐ': 'ㅒ', 'ㅣㅓ': 'ㅕ', 'ㅣㅔ': 'ㅖ', 'ㅣㅗ': 'ㅛ', 'ㅣㅜ': 'ㅠ'}

phoneme_onset_dict = {'ㄱ': 0, 'ㄲ': 1, 'ㄴ': 2, 'ㄷ': 3, 'ㄸ': 4, 'ㄹ': 5, 'ㅁ': 6, 'ㅂ': 7, 'ㅃ': 8, 'ㅅ': 9, 'ㅆ': 10, 'ㅇ': 11, 'ㅈ': 12, 'ㅉ': 13, 'ㅊ': 14, 'ㅋ': 15, 'ㅌ': 16, 'ㅍ': 17, 'ㅎ': 18}

phoneme_onset_list = ['ㄱ', 'ㄲ', 'ㄴ', 'ㄷ', 'ㄸ', 'ㄹ', 'ㅁ', 'ㅂ', 'ㅃ', 'ㅅ', 'ㅆ', 'ㅇ', 'ㅈ', 'ㅉ', 'ㅊ', 'ㅋ', 'ㅌ', 'ㅍ', 'ㅎ']

phoneme_onset_list_len = 19

phoneme_set = {'ㅅ', 'ㅒ', 'ㅞ', 'ㅓ', 'ㅊ', 'ㅜ', 'ㄸ', 'ㅉ', 'ㅎ', 'ㄶ', 'ㅖ', 'ㄻ', 'ㅌ', 'ㅍ', 'ㅂ', 'ㄳ', 'ㄲ', 'ㅃ', 'ㄿ', ' ', 'ㄾ', 'ㅗ', 'ㅋ', 'ㅟ', 'ㄴ', 'ㅝ', 'ㄵ', 'ㅈ', 'ㄽ', 'ㄷ', 'ㅛ', 'ㅣ', 'ㅙ', 'ㄼ', 'ㅄ', 'ㅀ', 'ㅐ', 'ㅆ', 'ㅘ', 'ㅔ', 'ㅡ', 'ㄹ', 'ㄱ', 'ㅕ', 'ㅚ', 'ㅇ', 'ㅠ', 'ㅢ', 'ㄺ', 'ㅑ', 'ㅁ', 'ㅏ'}

roman_coda_list = ('-', 'g', 'kk', 'ks', 'n', 'nj', 'nh', 'd', 'r', 'lg', 'lm', 'lb', 'ls', 'lt', 'lp', 'lh', 'm', 'b', 'ps', 's', 'ss', 'ng', 'j', 'c', 'k', 't', 'p', 'h')

roman_nucleus_list = ('a', 'ae', 'ya', 'yae', 'eo', 'e', 'yeo', 'ye', 'o', 'wa', 'wae', 'oi', 'yo', 'u', 'wo', 'we', 'wi', 'yu', 'eu', 'ui', 'i')

roman_onset_list = ('g', 'kk', 'n', 'd', 'tt', 'r', 'm', 'b', 'pp', 's', 'ss', '-', 'j', 'jj', 'ch', 'k', 't', 'p', 'h')

romanize()

text = None

static transform(sequence, filters)

unicode_base_code = 44032

unicode_nucleus_offset = 28

unicode_onset_offset = 588