def _setup(self, word) -> List[str]:
"""
Prepares a word for syllable processing.
If the word starts with a prefix, process it separately.
:param word:
:return:
"""
if len(word) == 1:
return [word]
for prefix in self.constants.PREFIXES:
if word.startswith(prefix):
(first, rest) = StringUtils.split_on(word, prefix)
if self._contains_vowels(rest):
return StringUtils.remove_blank_spaces(
self._process(first) + self._process(rest))
# a word like pror can happen from ellision
return StringUtils.remove_blank_spaces(self._process(word))
if word in self.constants.UI_EXCEPTIONS.keys():
return self.constants.UI_EXCEPTIONS[word]
return StringUtils.remove_blank_spaces(self._process(word))
def _setup(self, word) -> List[str]:
"""
Prepares a word for syllable processing.
If the word starts with a prefix, process it separately.
:param word:
:return:
"""
if len(word) == 1:
return [word]
for prefix in self.constants.PREFIXES:
if word.startswith(prefix):
(first, rest) = string_utils.split_on(word, prefix)
if self._contains_vowels(rest):
return string_utils.remove_blank_spaces(
self._process(first) + self._process(rest))
# a word like pror can happen from ellision
return string_utils.remove_blank_spaces(self._process(word))
if word in self.constants.UI_EXCEPTIONS.keys():
return self.constants.UI_EXCEPTIONS[word]
return string_utils.remove_blank_spaces(self._process(word))
def get_syllable_count(self, syllables: List[str]) -> int:
"""
Counts the number of syllable groups that would occur after ellision.
Often we will want preserve the position and separation of syllables so that they
can be used to reconstitute a line, and apply stresses to the original word positions.
However, we also want to be able to count the number of syllables accurately.
:param syllables:
:return:
>>> syllabifier = Syllabifier()
>>> print(syllabifier.get_syllable_count([
... 'Jām', 'tūm', 'c', 'au', 'sus', 'es', 'u', 'nus', 'I', 'ta', 'lo', 'rum']))
11
"""
tmp_syllables = copy.deepcopy(syllables)
return len(string_utils.remove_blank_spaces(
string_utils.move_consonant_right(tmp_syllables,
self._find_solo_consonant(tmp_syllables))))
def get_syllable_count(self, syllables: List[str]) -> int:
"""
Counts the number of syllable groups that would occur after ellision.
Often we will want preserve the position and separation of syllables so that they
can be used to reconstitute a line, and apply stresses to the original word positions.
However, we also want to be able to count the number of syllables accurately.
:param syllables:
:return:
>>> syllabifier = Syllabifier()
>>> print(syllabifier.get_syllable_count([
... 'Jām', 'tūm', 'c', 'au', 'sus', 'es', 'u', 'nus', 'I', 'ta', 'lo', 'rum']))
11
"""
tmp_syllables = copy.deepcopy(syllables)
return len(string_utils.remove_blank_spaces(
string_utils.move_consonant_right(tmp_syllables,
self._find_solo_consonant(tmp_syllables))))
def syllabify(self, words: str) -> List[str]:
"""
Parse a Latin word into a list of syllable strings.
:param words: a string containing one latin word or many words separated by spaces.
:return: list of string, each representing a syllable.
>>> syllabifier = Syllabifier()
>>> print(syllabifier.syllabify("fuit"))
['fu', 'it']
>>> print(syllabifier.syllabify("libri"))
['li', 'bri']
>>> print(syllabifier.syllabify("contra"))
['con', 'tra']
>>> print(syllabifier.syllabify("iaculum"))
['ja', 'cu', 'lum']
>>> print(syllabifier.syllabify("amo"))
['a', 'mo']
>>> print(syllabifier.syllabify("bracchia"))
['brac', 'chi', 'a']
>>> print(syllabifier.syllabify("deinde"))
['dein', 'de']
>>> print(syllabifier.syllabify("certabant"))
['cer', 'ta', 'bant']
>>> print(syllabifier.syllabify("aere"))
['ae', 're']
>>> print(syllabifier.syllabify("adiungere"))
['ad', 'jun', 'ge', 're']
>>> print(syllabifier.syllabify("mōns"))
['mōns']
>>> print(syllabifier.syllabify("domus"))
['do', 'mus']
>>> print(syllabifier.syllabify("lixa"))
['li', 'xa']
>>> print(syllabifier.syllabify("asper"))
['as', 'per']
>>> # handle doubles
>>> print(syllabifier.syllabify("siccus"))
['sic', 'cus']
>>> # handle liquid + liquid
>>> print(syllabifier.syllabify("almus"))
['al', 'mus']
>>> # handle liquid + mute
>>> print(syllabifier.syllabify("ambo"))
['am', 'bo']
>>> print(syllabifier.syllabify("anguis"))
['an', 'guis']
>>> print(syllabifier.syllabify("arbor"))
['ar', 'bor']
>>> print(syllabifier.syllabify("pulcher"))
['pul', 'cher']
>>> print(syllabifier.syllabify("ruptus"))
['ru', 'ptus']
>>> print(syllabifier.syllabify("Bīthÿnus"))
['Bī', 'thÿ', 'nus']
>>> print(syllabifier.syllabify("sanguen"))
['san', 'guen']
>>> print(syllabifier.syllabify("unguentum"))
['un', 'guen', 'tum']
>>> print(syllabifier.syllabify("lingua"))
['lin', 'gua']
>>> print(syllabifier.syllabify("linguā"))
['lin', 'guā']
>>> print(syllabifier.syllabify("languidus"))
['lan', 'gui', 'dus']
>>> print(syllabifier.syllabify("suis"))
['su', 'is']
>>> print(syllabifier.syllabify("habui"))
['ha', 'bu', 'i']
>>> print(syllabifier.syllabify("habuit"))
['ha', 'bu', 'it']
>>> print(syllabifier.syllabify("qui"))
['qui']
>>> print(syllabifier.syllabify("quibus"))
['qui', 'bus']
>>> print(syllabifier.syllabify("hui"))
['hui']
>>> print(syllabifier.syllabify("cui"))
['cui']
>>> print(syllabifier.syllabify("huic"))
['huic']
"""
cleaned = words.translate(self.remove_punct_map)
cleaned = cleaned.replace("qu", "kw")
cleaned = cleaned.replace("Qu", "Kw")
cleaned = cleaned.replace("gua", "gwa")
cleaned = cleaned.replace("Gua", "Gwa")
cleaned = cleaned.replace("gue", "gwe")
cleaned = cleaned.replace("Gue", "Gwe")
cleaned = cleaned.replace("gui", "gwi")
cleaned = cleaned.replace("Gui", "Gwi")
cleaned = cleaned.replace("guo", "gwo")
cleaned = cleaned.replace("Guo", "Gwo")
cleaned = cleaned.replace("guu", "gwu")
cleaned = cleaned.replace("Guu", "Gwu")
cleaned = cleaned.replace("guā", "gwā")
cleaned = cleaned.replace("Guā", "Gwā")
cleaned = cleaned.replace("guē", "gwē")
cleaned = cleaned.replace("Guē", "Gwē")
cleaned = cleaned.replace("guī", "gwī")
cleaned = cleaned.replace("Guī", "Gwī")
cleaned = cleaned.replace("guō", "gwō")
cleaned = cleaned.replace("Guō", "Gwō")
cleaned = cleaned.replace("guū", "gwū")
cleaned = cleaned.replace("Guū", "Gwū")
items = cleaned.strip().split(" ")
for char in cleaned:
if not char in self.ACCEPTABLE_CHARS:
LOG.error("Unsupported character found in %s " % cleaned)
return items
syllables: list = []
for item in items:
syllables += self._setup(item)
for idx, syl in enumerate(syllables):
if "kw" in syl:
syl = syl.replace("kw", "qu")
syllables[idx] = syl
if "Kw" in syl:
syl = syl.replace("Kw", "Qu")
syllables[idx] = syl
if "gw" in syl:
syl = syl.replace("gw", "gu")
syllables[idx] = syl
if "Gw" in syl:
syl = syl.replace("Gw", "Gu")
syllables[idx] = syl
return StringUtils.remove_blank_spaces(syllables)
def syllabify(self, words: str) -> List[str]:
"""
Parse a Latin word into a list of syllable strings.
:param words: a string containing one latin word or many words separated by spaces.
:return: list of string, each representing a syllable.
>>> syllabifier = Syllabifier()
>>> print(syllabifier.syllabify("fuit"))
['fu', 'it']
>>> print(syllabifier.syllabify("libri"))
['li', 'bri']
>>> print(syllabifier.syllabify("contra"))
['con', 'tra']
>>> print(syllabifier.syllabify("iaculum"))
['ja', 'cu', 'lum']
>>> print(syllabifier.syllabify("amo"))
['a', 'mo']
>>> print(syllabifier.syllabify("bracchia"))
['brac', 'chi', 'a']
>>> print(syllabifier.syllabify("deinde"))
['dein', 'de']
>>> print(syllabifier.syllabify("certabant"))
['cer', 'ta', 'bant']
>>> print(syllabifier.syllabify("aere"))
['ae', 're']
>>> print(syllabifier.syllabify("adiungere"))
['ad', 'jun', 'ge', 're']
>>> print(syllabifier.syllabify("mōns"))
['mōns']
>>> print(syllabifier.syllabify("domus"))
['do', 'mus']
>>> print(syllabifier.syllabify("lixa"))
['li', 'xa']
>>> print(syllabifier.syllabify("asper"))
['as', 'per']
>>> # handle doubles
>>> print(syllabifier.syllabify("siccus"))
['sic', 'cus']
>>> # handle liquid + liquid
>>> print(syllabifier.syllabify("almus"))
['al', 'mus']
>>> # handle liquid + mute
>>> print(syllabifier.syllabify("ambo"))
['am', 'bo']
>>> print(syllabifier.syllabify("anguis"))
['an', 'guis']
>>> print(syllabifier.syllabify("arbor"))
['ar', 'bor']
>>> print(syllabifier.syllabify("pulcher"))
['pul', 'cher']
>>> print(syllabifier.syllabify("ruptus"))
['ru', 'ptus']
>>> print(syllabifier.syllabify("Bīthÿnus"))
['Bī', 'thÿ', 'nus']
>>> print(syllabifier.syllabify("sanguen"))
['san', 'guen']
>>> print(syllabifier.syllabify("unguentum"))
['un', 'guen', 'tum']
>>> print(syllabifier.syllabify("lingua"))
['lin', 'gua']
>>> print(syllabifier.syllabify("linguā"))
['lin', 'guā']
>>> print(syllabifier.syllabify("languidus"))
['lan', 'gui', 'dus']
>>> print(syllabifier.syllabify("suis"))
['su', 'is']
>>> print(syllabifier.syllabify("habui"))
['ha', 'bu', 'i']
>>> print(syllabifier.syllabify("habuit"))
['ha', 'bu', 'it']
>>> print(syllabifier.syllabify("qui"))
['qui']
>>> print(syllabifier.syllabify("quibus"))
['qui', 'bus']
>>> print(syllabifier.syllabify("hui"))
['hui']
>>> print(syllabifier.syllabify("cui"))
['cui']
>>> print(syllabifier.syllabify("huic"))
['huic']
"""
cleaned = words.translate(self.remove_punct_map)
cleaned = cleaned.replace("qu", "kw")
cleaned = cleaned.replace("Qu", "Kw")
cleaned = cleaned.replace("gua", "gwa")
cleaned = cleaned.replace("Gua", "Gwa")
cleaned = cleaned.replace("gue", "gwe")
cleaned = cleaned.replace("Gue", "Gwe")
cleaned = cleaned.replace("gui", "gwi")
cleaned = cleaned.replace("Gui", "Gwi")
cleaned = cleaned.replace("guo", "gwo")
cleaned = cleaned.replace("Guo", "Gwo")
cleaned = cleaned.replace("guu", "gwu")
cleaned = cleaned.replace("Guu", "Gwu")
cleaned = cleaned.replace("guā", "gwā")
cleaned = cleaned.replace("Guā", "Gwā")
cleaned = cleaned.replace("guē", "gwē")
cleaned = cleaned.replace("Guē", "Gwē")
cleaned = cleaned.replace("guī", "gwī")
cleaned = cleaned.replace("Guī", "Gwī")
cleaned = cleaned.replace("guō", "gwō")
cleaned = cleaned.replace("Guō", "Gwō")
cleaned = cleaned.replace("guū", "gwū")
cleaned = cleaned.replace("Guū", "Gwū")
items = cleaned.strip().split(" ")
for char in cleaned:
if not char in self.ACCEPTABLE_CHARS:
LOG.error("Unsupported character found in %s " % cleaned)
return items
syllables: list = []
for item in items:
syllables += self._setup(item)
for idx, syl in enumerate(syllables):
if "kw" in syl:
syl = syl.replace("kw", "qu")
syllables[idx] = syl
if "Kw" in syl:
syl = syl.replace("Kw", "Qu")
syllables[idx] = syl
if "gw" in syl:
syl = syl.replace("gw", "gu")
syllables[idx] = syl
if "Gw" in syl:
syl = syl.replace("Gw", "Gu")
syllables[idx] = syl
return string_utils.remove_blank_spaces(syllables)