Traceback (most recent call last):
File "recover_text.py", line 62, in
ptb_sentences = process_ptb(args["ptb"], folder, filename)
File "recover_text.py", line 22, in process_ptb
for parsed_sentence in parsed_sentences:
File "/Users/marvinmu/anaconda3/lib/python3.6/site-packages/nltk/corpus/reader/util.py", line 296, in iterate_from
tokens = self.read_block(self._stream)
File "/Users/marvinmu/anaconda3/lib/python3.6/site-packages/nltk/corpus/reader/api.py", line 445, in _read_parsed_sent_block
return list(filter(None, [self._parse(t) for t in self._read_block(stream)]))
File "/Users/marvinmu/anaconda3/lib/python3.6/site-packages/nltk/corpus/reader/bracket_parse.py", line 61, in _read_block
toks = read_regexp_block(stream, start_re=r'^(')
File "/Users/marvinmu/anaconda3/lib/python3.6/site-packages/nltk/corpus/reader/util.py", line 609, in read_regexp_block
line = stream.readline()
File "/Users/marvinmu/anaconda3/lib/python3.6/site-packages/nltk/data.py", line 1148, in readline
new_chars = self._read(readsize)
File "/Users/marvinmu/anaconda3/lib/python3.6/site-packages/nltk/data.py", line 1380, in _read
chars, bytes_decoded = self._incr_decode(bytes)
File "/Users/marvinmu/anaconda3/lib/python3.6/site-packages/nltk/data.py", line 1411, in _incr_decode
return self.decode(bytes, 'strict')
UnicodeDecodeError: 'ascii' codec can't decode byte 0xd5 in position 64: ordinal not in range(128)
thtb
commented
5 years ago
Traceback (most recent call last): File "recover_text.py", line 62, in
ptb_sentences = process_ptb(args["ptb"], folder, filename)
File "recover_text.py", line 22, in process_ptb
for parsed_sentence in parsed_sentences:
File "/Users/marvinmu/anaconda3/lib/python3.6/site-packages/nltk/corpus/reader/util.py", line 296, in iterate_from
tokens = self.read_block(self._stream)
File "/Users/marvinmu/anaconda3/lib/python3.6/site-packages/nltk/corpus/reader/api.py", line 445, in _read_parsed_sent_block
return list(filter(None, [self._parse(t) for t in self._read_block(stream)]))
File "/Users/marvinmu/anaconda3/lib/python3.6/site-packages/nltk/corpus/reader/bracket_parse.py", line 61, in _read_block
toks = read_regexp_block(stream, start_re=r'^(')
File "/Users/marvinmu/anaconda3/lib/python3.6/site-packages/nltk/corpus/reader/util.py", line 609, in read_regexp_block
line = stream.readline()
File "/Users/marvinmu/anaconda3/lib/python3.6/site-packages/nltk/data.py", line 1148, in readline
new_chars = self._read(readsize)
File "/Users/marvinmu/anaconda3/lib/python3.6/site-packages/nltk/data.py", line 1380, in _read
chars, bytes_decoded = self._incr_decode(bytes)
File "/Users/marvinmu/anaconda3/lib/python3.6/site-packages/nltk/data.py", line 1411, in _incr_decode
return self.decode(bytes, 'strict')
UnicodeDecodeError: 'ascii' codec can't decode byte 0xd5 in position 64: ordinal not in range(128)