def syllabify(self): """ Syllables may play a role in verse classification. """ if len(self.long_lines) == 0: logger.error("No text was imported") self.syllabified_text = [] else: syllabifier = Syllabifier(language="old_norse", break_geminants=True) syllabified_text = [] for i, line in enumerate(self.long_lines): syllabified_text.append([]) for j, viisuordh in enumerate(line): syllabified_text[i].append([]) words = [] for word in tokenize_old_norse_words(viisuordh): # punctuation is not necessary here word = word.replace(",", "") word = word.replace(".", "") word = word.replace(";", "") word = word.replace("!", "") word = word.replace("?", "") word = word.replace("-", "") word = word.replace(":", "") if word != '': words.append(syllabifier.syllabify(word.lower())) syllabified_text[i][j].append(words) self.syllabified_text = syllabified_text
def syllabify(self, syllabifier): """ :param syllabifier: :return: """ for viisuordh in tokenize_old_norse_words(self.text): word = normalize(viisuordh) if word: self.syllabified.append(syllabifier.syllabify(word))
def __init__(self, text): self.text = text self.tokenized_text = tokenize_old_norse_words(text) self.first_sounds = [] self.syllabified = [] self.transcribed = [] self.alliterations = [] self.phonological_features_text = [] self.n_alliterations = 0 self.syllabified_phonological_features_text = []
def syllabify(self, syllabifier): """ :param syllabifier: :return: """ for viisuordh in tokenize_old_norse_words(self.text): word = normalize(viisuordh) if word: self.syllabified.append(syllabifier.syllabify(word))
def __init__(self, text): self.text = text self.tokenized_text = tokenize_old_norse_words(text) self.short_lines = None self.first_sounds = [] self.syllabified = [] self.transcribed = [] self.alliterations = [] self.phonological_features_text = [] self.n_alliterations = 0 self.syllabified_phonological_features_text = []
def test_syllabification_old_norse(self): old_norse_syllabifier = Syllabifier(language="old_norse", break_geminants=True) text = "Gefjun dró frá Gylfa glöð djúpröðul óðla, svá at af rennirauknum rauk, Danmarkar auka. Báru öxn ok átta" \ " ennitungl, þars gengu fyrir vineyjar víðri valrauf, fjögur höfuð." words = tokenize_old_norse_words(text) syllabified_words = [old_norse_syllabifier.legal_onsets(old_norse_syllabifier.syllabify_SSP(word.lower()), invalid_onsets) for word in words if word not in ",."] target = [['gef', 'jun'], ['dró'], ['frá'], ['gyl', 'fa'], ['glöð'], ['djúp', 'rö', 'ðul'], ['óðl', 'a'], ['svá'], ['at'], ['af'], ['ren', 'ni', 'rauk', 'num'], ['rauk'], ['dan', 'mar', 'kar'], ['auk', 'a'], ['bár', 'u'], ['öxn'], ['ok'], ['át', 'ta'], ['en', 'ni', 'tungl'], ['þars'], ['geng', 'u'], ['fy', 'rir'], ['vi', 'ney', 'jar'], ['víðr', 'i'], ['val', 'rauf'], ['fjö', 'gur'], ['hö', 'fuð']] self.assertListEqual(syllabified_words, target)
def to_phonetics(self, transcriber): """ Phontic transcription of the ShortLine instances. :param transcriber: :return: """ for viisuordh in tokenize_old_norse_words(self.text): word = normalize(viisuordh) if word != "": transcribed_word = transcriber.main(word) pfl = transcriber.first_process(word) self.transcribed.append(transcribed_word) self.phonological_features_text.append(pfl) self.get_first_sounds()
def to_phonetics(self, transcriber): """ Phontic transcription of the ShortLine instances. :param transcriber: :return: """ for viisuordh in tokenize_old_norse_words(self.text): word = normalize(viisuordh) if word: transcribed_word = transcriber.text_to_phonetic_representation(word) pfl = transcriber.text_to_phonemes(word) self.transcribed.append(transcribed_word) self.phonological_features_text.append(pfl) self.get_first_sounds()