def __init__(self,
constants=ScansionConstants(),
syllabifier=Syllabifier(),
optional_transform: bool = False,
*args,
**kwargs):
super().__init__(*args, **kwargs)
self.constants = constants
self.remove_punct_map = StringUtils.remove_punctuation_dict()
self.punctuation_substitutions = StringUtils.punctuation_for_spaces_dict(
)
self.metrical_validator = MetricalValidator(constants)
self.formatter = ScansionFormatter(constants)
self.syllabifier = syllabifier
self.optional_transform = optional_transform
self.inverted_amphibrach_re = re.compile(r"{}\s*{}\s*{}".format(
self.constants.STRESSED, self.constants.UNSTRESSED,
self.constants.STRESSED))
self.syllable_matcher = re.compile(
r"[{}]".format(self.constants.VOWELS +
self.constants.ACCENTED_VOWELS +
self.constants.LIQUIDS + self.constants.MUTES))
self.SPONDAIC_PENTAMETER = self.constants.SPONDEE + self.constants.SPONDEE + \
self.constants.STRESSED + self.constants.DACTYL + \
self.constants.DACTYL + self.constants.OPTIONAL_ENDING
self.DACTYLIC_PENTAMETER = self.constants.DACTYL + self.constants.DACTYL + \
self.constants.STRESSED + self.constants.DACTYL + \
self.constants.DACTYL + self.constants.OPTIONAL_ENDING
def __init__(self, constants=None, syllabifier=None,
optional_transform: bool = False, *args, **kwargs)->None:
"""
:param constants: None or a class that implements ScansionConstants
:param syllabifier: None or a class that implements Syllabifier methods
:param optional_tranform: boolean, whether or not to apply aggresive verse transformations.
:param kwargs:
"""
super().__init__(*args, **kwargs)
self.constants = ScansionConstants() if constants is None else constants
self.syllabifier = Syllabifier() if syllabifier is None else syllabifier
self.remove_punct_map = string_utils.remove_punctuation_dict()
self.punctuation_substitutions = string_utils.punctuation_for_spaces_dict()
self.metrical_validator = MetricalValidator(self.constants)
self.formatter = ScansionFormatter(self.constants)
self.optional_transform = optional_transform
self.inverted_amphibrach_re = re.compile(
r"{}\s*{}\s*{}".format(self.constants.STRESSED,
self.constants.UNSTRESSED,
self.constants.STRESSED))
self.syllable_matcher = re.compile(r"[{}]".format(self.constants.VOWELS +
self.constants.ACCENTED_VOWELS +
self.constants.LIQUIDS +
self.constants.MUTES))
self.SPONDAIC_PENTAMETER = self.constants.SPONDEE + self.constants.SPONDEE + \
self.constants.STRESSED + self.constants.DACTYL + \
self.constants.DACTYL + self.constants.OPTIONAL_ENDING
self.DACTYLIC_PENTAMETER = self.constants.DACTYL + self.constants.DACTYL + \
self.constants.STRESSED + self.constants.DACTYL + \
self.constants.DACTYL + self.constants.OPTIONAL_ENDING
def __init__(self, constants=ScansionConstants()):
self.constants = constants
self.stress_accent_dict = dict(
zip(
list(self.constants.VOWELS + self.constants.ACCENTED_VOWELS),
list(self.constants.ACCENTED_VOWELS +
self.constants.ACCENTED_VOWELS)))
def __init__(self, constants=ScansionConstants()):
self.constants = constants
self.VALID_HEXAMETERS = [
self._build_hexameter_template(bin(x)[3:]) for x in range(32, 64)
]
self.VALID_HENDECASYLLABLES = self._build_hendecasyllable_templates()
self.VALID_PENTAMETERS = self._build_pentameter_templates()
def demacronize(string_matrix: List[List[str]]) -> List[List[str]]:
"""
Transform macronized vowels into normal vowels
:param string_matrix: a data matrix: a list wrapping a list of strings, with each sublist being a sentence.
:return: string_matrix
>>> demacronize([['ōdī', 'et', 'amō',]])
[['odi', 'et', 'amo']]
"""
scansion = ScansionConstants()
accent_dropper = str.maketrans(scansion.ACCENTED_VOWELS, scansion.VOWELS)
return [[word.translate(accent_dropper) for word in sentence]
for sentence in string_matrix]
def __init__(self, constants=ScansionConstants()):
self.constants = constants
self.consonant_matcher = re.compile("[{}]".format(constants.CONSONANTS))
self.vowel_matcher = re.compile(
"[{}]".format(constants.VOWELS + constants.ACCENTED_VOWELS))
self.consonantal_i_matcher = re.compile(
r"\b[iIīĪ][{}]".format(constants.VOWELS + constants.ACCENTED_VOWELS))
self.remove_punct_map = string_utils.remove_punctuation_dict()
self.kw_matcher = re.compile("[kK][w]")
self.ACCEPTABLE_CHARS = constants.ACCENTED_VOWELS + constants.VOWELS + ' ' \
+ constants.CONSONANTS
self.diphthongs = [d for d in constants.DIPTHONGS if d not in ["ui", "Ui", "uī"]]
def __init__(self,
constants=ScansionConstants(),
syllabifier=Syllabifier(),
**kwargs):
self.constants = constants
self.remove_punct_map = string_utils.remove_punctuation_dict()
self.punctuation_substitutions = string_utils.punctuation_for_spaces_dict(
)
self.metrical_validator = MetricalValidator(constants)
self.formatter = ScansionFormatter(constants)
self.syllabifier = syllabifier
self.inverted_amphibrach_re = re.compile(r"{}\s*{}\s*{}".format(
self.constants.STRESSED, self.constants.UNSTRESSED,
self.constants.STRESSED))
self.syllable_matcher = re.compile(
r"[{}]".format(self.constants.VOWELS +
self.constants.ACCENTED_VOWELS +
self.constants.LIQUIDS + self.constants.MUTES))
def __init__(self, constants=None, syllabifier=None, **kwargs):
"""
:param constants: None or a class that implements ScansionConstants
:param syllabifier: None or a class that implements Syllabifier methods
:param kwargs:
"""
self.constants = ScansionConstants(
) if constants is None else constants
self.syllabifier = Syllabifier(
) if syllabifier is None else syllabifier
self.remove_punct_map = string_utils.remove_punctuation_dict()
self.punctuation_substitutions = string_utils.punctuation_for_spaces_dict(
)
self.metrical_validator = MetricalValidator(self.constants)
self.formatter = ScansionFormatter(self.constants)
self.inverted_amphibrach_re = re.compile(r"{}\s*{}\s*{}".format(
self.constants.STRESSED, self.constants.UNSTRESSED,
self.constants.STRESSED))
self.syllable_matcher = re.compile(
r"[{}]".format(self.constants.VOWELS +
self.constants.ACCENTED_VOWELS +
self.constants.LIQUIDS + self.constants.MUTES))
def __init__(self):
self.alternate_font_greek_to_roman = dict([
("I", "i"),
("Α", "A"),
("Αι", "Ae"),
("Β", "B"),
("Γ", "G"),
("Δ", "D"),
("Ε", "E"),
("Ει", "E"),
("Ζ", "Z"),
("Η", "Ē"),
("Θ", "Th"),
("Ι", "I"),
("Κ", "K"),
("Λ", "L"),
("Μ", "M"),
("Ν", "N"),
("Ξ", "X"),
("Ο", "O"),
("Οι", "Oe"),
("Ου", "Ou"),
("Π", "P"),
("Ρ", "R"),
("Σ", "S"),
("Τ", "T"),
("Υ", "Y"),
("Υι", "Ui"),
("Φ", "Ph"),
("Χ", "Kh"),
("Ψ", "Ps"),
("Ω", "Ō"),
("α", "a"),
("αι", "ae"),
("β", "b"),
("γ", "g"),
("γγ", "ng"),
("γκ", "nc"),
("γξ", "nx"),
("γχ", "nch"),
("δ", "d"),
("ε", "e"),
("ει", "ei"),
("ζ", "z"),
("η", "ē"),
("θ", "th"),
("ι", "i"),
("κ", "k"),
("λ", "l"),
("μ", "m"),
("ν", "n"),
("ξ", "x"),
("ο", "o"),
("οι", "oe"),
("ου", "ou"),
("π", "p"),
("ρ", "r"),
("ς", "s"),
("σ", "s"),
("τ", "t"),
("υ", "u"),
("υι", "ui"),
("φ", "ph"),
("χ", "kh"),
("ψ", "ps"),
("ω", "ō"),
]) # type: Dict[str, str]
self.greek_to_roman = dict([
("W", "V"),
("j", "i"),
("w", "v"),
("¯", " "),
("Ō", "O"),
("ʼ", " "),
("ʽ", " "),
("˘", " "),
("̀", " "),
("́", " "),
("̄", " "),
("̈", " "),
("̓", " "),
("̔", " "),
("͂", " "),
("ͅ", " "),
("ʹ", " "),
("Ά", "A"),
("ΐ", "i"),
("ά", "a"),
("έ", "e"),
("ή", "ē"),
("ί", "i"),
("ΰ", "u"),
("ϊ", "i"),
("ϋ", "u"),
("ό", "o"),
("ύ", "u"),
("ώ", "ō"),
("ϛ", "s"),
("ϝ", " "),
("ϟ", " "),
("ϡ", " "),
("ἀ", "a"),
("ἁ", "ha"),
("ἂ", "a"),
("ἃ", "ha"),
("ἄ", "a"),
("ἅ", "ha"),
("ἆ", "a"),
("ἇ", "ha"),
("Ἀ", "A"),
("Ἁ", "Ha"),
("Ἂ", "Ha"),
("Ἃ", "Ha "),
("Ἄ", "A"),
("Ἅ", "Ha"),
("Ἆ", "A"),
("ἐ", "e"),
("ἑ", "he"),
("ἒ", "e"),
("ἓ", "he"),
("ἔ", "e"),
("ἕ", "he"),
("Ἐ", "E"),
("Ἑ", "He"),
("Ἓ", "He"),
("Ἔ", "E"),
("Ἕ", "E"),
("ἠ", "ē"),
("ἡ", "hē"),
("ἢ", "ē"),
("ἣ", "hē"),
("ἤ", "ē"),
("ἥ", "hē"),
("ἦ", "ē"),
("ἧ", "hē"),
("Ἠ", "Ē"),
("Ἡ", "Hē"),
("Ἢ", "Hē"),
("Ἤ", "Ē"),
("Ἥ", "Ē"),
("Ἦ", "Ē"),
("Ἧ", "Hē"),
("ἰ", "i"),
("ἱ", "hi"),
("ἲ", "i"),
("ἳ", "hi"),
("ἴ", "i"),
("ἵ", "hi"),
("ἶ", "i"),
("ἷ", "hi"),
("Ἰ", "I"),
("Ἱ", "Hi"),
("Ἴ", "I"),
("Ἵ", "I"),
("Ἶ", "I"),
("ὀ", "o"),
("ὁ", "ho"),
("ὂ", "o"),
("ὃ", "ho"),
("ὄ", "o"),
("ὅ", "ho"),
("Ὀ", "O"),
("Ὁ", "Ho"),
("Ὃ", "Ho"),
("Ὄ", "O"),
("Ὅ", "Ho"),
("ὐ", "u"),
("ὑ", "hu"),
("ὒ", "u"),
("ὓ", "hu"),
("ὔ", "u"),
("ὕ", "hu"),
("ὖ", "u"),
("ὗ", "hu"),
("Ὑ", "Hy"),
("Ὕ", "Y"),
("Ὗ", "Hu"),
("ὠ", "ō"),
("ὡ", "hō"),
("ὢ", "ō"),
("ὣ", "ho"),
("ὤ", "ō"),
("ὥ", "hō"),
("ὦ", "ō"),
("ὧ", "hō"),
("Ὠ", "O"),
("Ὡ", "Hō"),
("Ὣ", "Hō"),
("Ὤ", "O"),
("Ὥ", "Ō"),
("Ὦ", "O"),
("Ὧ", "Hō"),
("ὰ", "a"),
("ά", "a"),
("ὲ", "e"),
("έ", "e"),
("ὴ", "ē"),
("ή", "e"),
("ὶ", "i"),
("ί", "i"),
("ὸ", "o"),
("ό", "o"),
("ὺ", "u"),
("ύ", "u"),
("ὼ", "ō"),
("ώ", "ō"),
("ᾀ", "a"),
("ᾁ", "ha"),
("ᾄ", "a"),
("ᾅ", "ha"),
("ᾆ", "a"),
("ᾇ", "ha"),
("ᾐ", "ē"),
("ᾑ", "hē"),
("ᾔ", "ē"),
("ᾕ", "hē"),
("ᾖ", "ē"),
("ᾗ", "hē"),
("ᾘ", "Ē"),
("ᾠ", "ō"),
("ᾡ", "Hō"),
("ᾤ", "ō"),
("ᾦ", "ō"),
("ᾧ", "hō"),
("ᾬ", "Ō"),
("ᾲ", "a"),
("ᾳ", "a"),
("ᾴ", "a"),
("ᾶ", "a"),
("ᾷ", "a"),
("᾿", " "),
("ῂ", "ē"),
("ῃ", "ē"),
("ῄ", "ē"),
("ῆ", "ē"),
("ῇ", "ē"),
("ῒ", "i"),
("ΐ", "i"),
("ῖ", "i"),
("ῗ", "i"),
("ῢ", "u"),
("ῤ", "r"),
("ῥ", "rh"),
("ῦ", "u"),
("Ῥ", "Rh"),
("ῲ", "ō"),
("ῳ", "ō"),
("ῴ", "ō"),
("ῶ", "ō"),
("ῷ", "ō"),
]) # type: Dict[str, str]
self.greek_to_roman_dipthongs = dict([
(" Ἥ", "Hē"),
("Αὖ", "Au"),
("Αἱ", "Hai"),
("Αὑ", "Hau"),
("Αὕ", "Hau"),
("Αὗ", "Hau"),
("Γγ", "Ng"),
("Ει", "Ei"),
("Εὖ", "Eu"),
("Εἵ", "Hei"),
("Εἶ", "Ei"),
("Εἷ", "Hei"),
("Εὑ", "Heu"),
("Εὔ", "Eu"),
("Οι", "Oi"),
("Ου", "Ou"),
("Οἱ", "Hoi"),
("Οἳ", "Hoi"),
("Οἵ", "Hoi"),
("Οἷ", "Hoi"),
("Οὑ", "Hou"),
("Οὓ", "Hou"),
("Οὕ", "Hou"),
("Οὗ", "Hou"),
("Υἱ", "Hui"),
("αἱ", "hai"),
("αὑ", "hau"),
("αὕ", "hau"),
("αὖ", "au"),
("αὗ", "hau"),
("γγ", "ng"),
("ει", "ei"),
("εἵ", "hei"),
("εἶ", "ei"),
("εἷ", "hei"),
("εὑ", "heu"),
("εὔ", "eu"),
("εὖ", "eu"),
("οι", "oi"),
("ου", "ou"),
("οἱ", "hoi"),
("οἳ", "hoi"),
("οἵ", "hoi"),
("οἷ", "hoi"),
("οὑ", "hou"),
("οὓ", "hou"),
("οὕ", "hou"),
("οὗ", "hou"),
("υἱ", "hui"),
]) # type: Dict[str, str]
scansion_constants = ScansionConstants()
self.macrons_to_vowels = dict(
zip(
list(scansion_constants.ACCENTED_VOWELS),
list(scansion_constants.VOWELS),
)) # type: Dict[str, str]
def __init__(self):
self.alternate_font_greek_to_roman = dict([('I', 'i'), ('Α', 'A'),
('Αι', 'Ae'), ('Β', 'B'),
('Γ', 'G'), ('Δ', 'D'),
('Ε', 'E'), ('Ει', 'E'),
('Ζ', 'Z'), ('Η', 'Ē'),
('Θ', 'Th'), ('Ι', 'I'),
('Κ', 'K'), ('Λ', 'L'),
('Μ', 'M'), ('Ν', 'N'),
('Ξ', 'X'), ('Ο', 'O'),
('Οι', 'Oe'), ('Ου', 'Ou'),
('Π', 'P'), ('Ρ', 'R'),
('Σ', 'S'), ('Τ', 'T'),
('Υ', 'Y'), ('Υι', 'Ui'),
('Φ', 'Ph'), ('Χ', 'Kh'),
('Ψ', 'Ps'), ('Ω', 'Ō'),
('α', 'a'), ('αι', 'ae'),
('β', 'b'), ('γ', 'g'),
('γγ', 'ng'), ('γκ', 'nc'),
('γξ', 'nx'), ('γχ', 'nch'),
('δ', 'd'), ('ε', 'e'),
('ει', 'ei'), ('ζ', 'z'),
('η', 'ē'), ('θ', 'th'),
('ι', 'i'), ('κ', 'k'),
('λ', 'l'), ('μ', 'm'),
('ν', 'n'), ('ξ', 'x'),
('ο', 'o'), ('οι', 'oe'),
('ου', 'ou'), ('π', 'p'),
('ρ', 'r'), ('ς', 's'),
('σ', 's'), ('τ', 't'),
('υ', 'u'), ('υι', 'ui'),
('φ', 'ph'), ('χ', 'kh'),
('ψ', 'ps'), ('ω', 'ō')
]) # type: Dict[str, str]
self.greek_to_roman = dict([('W', 'V'), ('j', 'i'), ('w', 'v'),
('¯', ' '), ('Ō', 'O'), ('ʼ', ' '),
('ʽ', ' '), ('˘', ' '), ('̀', ' '),
('́', ' '), ('̄', ' '), ('̈', ' '),
('̓', ' '), ('̔', ' '), ('͂', ' '),
('ͅ', ' '), ('ʹ', ' '), ('Ά', 'A'),
('ΐ', 'i'), ('ά', 'a'), ('έ', 'e'),
('ή', 'ē'), ('ί', 'i'), ('ΰ', 'u'),
('ϊ', 'i'), ('ϋ', 'u'), ('ό', 'o'),
('ύ', 'u'), ('ώ', 'ō'), ('ϛ', 's'),
('ϝ', ' '), ('ϟ', ' '), ('ϡ', ' '),
('ἀ', 'a'), ('ἁ', 'ha'), ('ἂ', 'a'),
('ἃ', 'ha'), ('ἄ', 'a'), ('ἅ', 'ha'),
('ἆ', 'a'), ('ἇ', 'ha'), ('Ἀ', 'A'),
('Ἁ', 'Ha'), ('Ἂ', 'Ha'), ('Ἃ', 'Ha '),
('Ἄ', 'A'), ('Ἅ', 'Ha'), ('Ἆ', 'A'),
('ἐ', 'e'), ('ἑ', 'he'), ('ἒ', 'e'),
('ἓ', 'he'), ('ἔ', 'e'), ('ἕ', 'he'),
('Ἐ', 'E'), ('Ἑ', 'He'), ('Ἓ', 'He'),
('Ἔ', 'E'), ('Ἕ', 'E'), ('ἠ', 'ē'),
('ἡ', 'hē'), ('ἢ', 'ē'), ('ἣ', 'hē'),
('ἤ', 'ē'), ('ἥ', 'hē'), ('ἦ', 'ē'),
('ἧ', 'hē'), ('Ἠ', 'Ē'), ('Ἡ', 'Hē'),
('Ἢ', 'Hē'), ('Ἤ', 'Ē'), ('Ἥ', 'Ē'),
('Ἦ', 'Ē'), ('Ἧ', 'Hē'), ('ἰ', 'i'),
('ἱ', 'hi'), ('ἲ', 'i'), ('ἳ', 'hi'),
('ἴ', 'i'), ('ἵ', 'hi'), ('ἶ', 'i'),
('ἷ', 'hi'), ('Ἰ', 'I'), ('Ἱ', 'Hi'),
('Ἴ', 'I'), ('Ἵ', 'I'), ('Ἶ', 'I'),
('ὀ', 'o'), ('ὁ', 'ho'), ('ὂ', 'o'),
('ὃ', 'ho'), ('ὄ', 'o'), ('ὅ', 'ho'),
('Ὀ', 'O'), ('Ὁ', 'Ho'), ('Ὃ', 'Ho'),
('Ὄ', 'O'), ('Ὅ', 'Ho'), ('ὐ', 'u'),
('ὑ', 'hu'), ('ὒ', 'u'), ('ὓ', 'hu'),
('ὔ', 'u'), ('ὕ', 'hu'), ('ὖ', 'u'),
('ὗ', 'hu'), ('Ὑ', 'Hy'), ('Ὕ', 'Y'),
('Ὗ', 'Hu'), ('ὠ', 'ō'), ('ὡ', 'hō'),
('ὢ', 'ō'), ('ὣ', 'ho'), ('ὤ', 'ō'),
('ὥ', 'hō'), ('ὦ', 'ō'), ('ὧ', 'hō'),
('Ὠ', 'O'), ('Ὡ', 'Hō'), ('Ὣ', 'Hō'),
('Ὤ', 'O'), ('Ὥ', 'Ō'), ('Ὦ', 'O'),
('Ὧ', 'Hō'), ('ὰ', 'a'), ('ά', 'a'),
('ὲ', 'e'), ('έ', 'e'), ('ὴ', 'ē'),
('ή', 'e'), ('ὶ', 'i'), ('ί', 'i'),
('ὸ', 'o'), ('ό', 'o'), ('ὺ', 'u'),
('ύ', 'u'), ('ὼ', 'ō'), ('ώ', 'ō'),
('ᾀ', 'a'), ('ᾁ', 'ha'), ('ᾄ', 'a'),
('ᾅ', 'ha'), ('ᾆ', 'a'), ('ᾇ', 'ha'),
('ᾐ', 'ē'), ('ᾑ', 'hē'), ('ᾔ', 'ē'),
('ᾕ', 'hē'), ('ᾖ', 'ē'), ('ᾗ', 'hē'),
('ᾘ', 'Ē'), ('ᾠ', 'ō'), ('ᾡ', 'Hō'),
('ᾤ', 'ō'), ('ᾦ', 'ō'), ('ᾧ', 'hō'),
('ᾬ', 'Ō'), ('ᾲ', 'a'), ('ᾳ', 'a'),
('ᾴ', 'a'), ('ᾶ', 'a'), ('ᾷ', 'a'),
('᾿', ' '), ('ῂ', 'ē'), ('ῃ', 'ē'),
('ῄ', 'ē'), ('ῆ', 'ē'), ('ῇ', 'ē'),
('ῒ', 'i'), ('ΐ', 'i'), ('ῖ', 'i'),
('ῗ', 'i'), ('ῢ', 'u'), ('ῤ', 'r'),
('ῥ', 'rh'), ('ῦ', 'u'), ('Ῥ', 'Rh'),
('ῲ', 'ō'), ('ῳ', 'ō'), ('ῴ', 'ō'),
('ῶ', 'ō'),
('ῷ', 'ō')]) # type: Dict[str, str]
self.greek_to_roman_dipthongs = dict([(' Ἥ', 'Hē'), ('Αὖ', 'Au'),
('Αἱ', 'Hai'), ('Αὑ', 'Hau'),
('Αὕ', 'Hau'), ('Αὗ', 'Hau'),
('Γγ', 'Ng'), ('Ει', 'Ei'),
('Εὖ', 'Eu'), ('Εἵ', 'Hei'),
('Εἶ', 'Ei'), ('Εἷ', 'Hei'),
('Εὑ', 'Heu'), ('Εὔ', 'Eu'),
('Οι', 'Oi'), ('Ου', 'Ou'),
('Οἱ', 'Hoi'), ('Οἳ', 'Hoi'),
('Οἵ', 'Hoi'), ('Οἷ', 'Hoi'),
('Οὑ', 'Hou'), ('Οὓ', 'Hou'),
('Οὕ', 'Hou'), ('Οὗ', 'Hou'),
('Υἱ', 'Hui'), ('αἱ', 'hai'),
('αὑ', 'hau'), ('αὕ', 'hau'),
('αὖ', 'au'), ('αὗ', 'hau'),
('γγ', 'ng'), ('ει', 'ei'),
('εἵ', 'hei'), ('εἶ', 'ei'),
('εἷ', 'hei'), ('εὑ', 'heu'),
('εὔ', 'eu'), ('εὖ', 'eu'),
('οι', 'oi'), ('ου', 'ou'),
('οἱ', 'hoi'), ('οἳ', 'hoi'),
('οἵ', 'hoi'), ('οἷ', 'hoi'),
('οὑ', 'hou'), ('οὓ', 'hou'),
('οὕ', 'hou'), ('οὗ', 'hou'),
('υἱ', 'hui')
]) # type: Dict[str, str]
scansion_constants = ScansionConstants()
self.macrons_to_vowels = dict(
zip(list(scansion_constants.ACCENTED_VOWELS),
list(scansion_constants.VOWELS))) # type: Dict[str, str]