def __init__(self, root, items, encoding=None):
gaps_re = r'(?u)(?<=/\.)\s+|\s*\S*_CODE\s*|\s*\S*_ID\s*'
sent_tokenizer = RegexpTokenizer(gaps_re, gaps=True)
TaggedCorpusReader.__init__(self,
root,
items,
sep='_',
sent_tokenizer=sent_tokenizer)
def __init__(self, root, items, encoding="utf8"):
gaps_re = r"(?u)(?<=/\.)\s+|\s*\S*_CODE\s*|\s*\S*_ID\s*"
sent_tokenizer = RegexpTokenizer(gaps_re, gaps=True)
TaggedCorpusReader.__init__(self,
root,
items,
sep="_",
sent_tokenizer=sent_tokenizer)
def __init__(self, poem_title):
"""
>>> pel_reader = PoeticEddaLemmatizationReader("Völuspá")
:param poem_title:
"""
assert poem_title in poetic_edda_titles
TaggedCorpusReader.__init__(
self,
os.path.join(poetic_edda, poem_title, "txt_files",
"lemmatization"), "lemmatized.txt")
def __init__(self, poem_title, _type=None):
"""
>>> pel_reader = PoeticEddaLemmatizationReader("Völuspá")
:param poem_title:
"""
assert poem_title in poetic_edda_titles
if _type == "tei":
TaggedCorpusReader.__init__(self, os.path.join(CORPUS_PATH, poetic_edda, poem_title, "txt_files",
"lemmatization"),
"tei_lemmatized_complete.txt")
elif _type == "test":
TaggedCorpusReader.__init__(self, os.path.join(CORPUS_PATH, poetic_edda, poem_title, "txt_files",
"lemmatization"),
"test_lemmatized_complete.txt")
else:
TaggedCorpusReader.__init__(self, os.path.join(CORPUS_PATH, poetic_edda, poem_title, "txt_files",
"lemmatization"),
"lemmatized.txt")
def __init__(self, root, items, encoding='utf8'):
gaps_re = r'(?u)(?<=/\.)\s+|\s*\S*_CODE\s*|\s*\S*_ID\s*'
sent_tokenizer = RegexpTokenizer(gaps_re, gaps=True)
TaggedCorpusReader.__init__(self, root, items, sep='_',
sent_tokenizer=sent_tokenizer)
def __init__(self, poem_title):
TaggedCorpusReader.__init__(
self,
os.path.join(poetic_edda, poem_title, "txt_files", "syllabified"),
"syllabified.txt")
def __init__(self, poem_title):
assert poem_title in poetic_edda_titles
TaggedCorpusReader.__init__(
self, os.path.join(poetic_edda, poem_title, "txt_files", "pos"),
"pos_tagged.txt")