def texts2json(ids, names, field, text_docs):
"""Convert a set of text documents into a
JSON array of document objects."""
docs = []
names = read_names(names)
ids = read_names(ids)
for idx, path in enumerate(text_docs):
tokens_doc = open(path, "r")
content = ""
with click.open_file(path):
content = tokens_doc.read()
# ordered so that these attributes stay at the top
doc = OrderedDict()
if idx < len(ids) - 1:
doc["id"] = ids[idx]
else:
doc["id"] = path
if idx < len(names) - 1:
doc["name"] = names[idx]
else:
doc["name"] = path
doc[field] = content
docs.append(doc)
tokens_doc.close()
out_content = json.dumps(docs, indent=2)
output(out_content)
def texts2json(ids, names, field, text_docs):
'''Convert a set of text documents into a
JSON array of document objects.'''
docs = []
names = read_names(names)
ids = read_names(ids)
for idx, path in enumerate(text_docs):
tokens_doc = open(path, 'r')
content = ""
with click.open_file(path):
content = tokens_doc.read()
# ordered so that these attributes stay at the top
doc = OrderedDict()
if idx < len(ids) - 1:
doc['id'] = ids[idx]
else:
doc['id'] = path
if idx < len(names) - 1:
doc['name'] = names[idx]
else:
doc['name'] = path
doc[field] = content
docs.append(doc)
tokens_doc.close()
out_content = json.dumps(docs, indent=2)
output(out_content)
def tokens2stem(tokens, algorithm):
'''Stem a list of tokens to get their root.'''
content = read_tokens(tokens)
stemmer = ALGOS[algorithm]()
if algorithm == 'wordnet':
for token in content:
output(stemmer.lemmatize(token))
else:
for token in content:
output(stemmer.stem(token))
def words2ngrams(sep, length, tokens):
'''Tokenize words into ngrams. ngrams are n-length word tokens.
Punctuation is considered as a separate token.'''
content = read_tokens(tokens)
ngrams = list(nltk.ngrams(content, length))
[output(sep.join(ngram)) for ngram in ngrams]
def words2bigrams(sep, tokens):
'''Tokenize words into bigrams. Bigrams are two word tokens.
Punctuation is considered as a separate token.'''
content = read_tokens(tokens)
bigrams = list(nltk.bigrams(content))
[output(sep.join(bigram)) for bigram in bigrams]
def filterwords(language, custom, tokens):
'''Remove stop words from tokens, returning tokens without stop words.'''
content = read_tokens(tokens)
stopwords = get_stopwords(language)
if custom:
stopwords = stopwords + read_tokens(custom)
[output(token) for token in content if token.lower() not in stopwords]
def filterwords(language, custom, tokens):
'''Remove stop words from tokens, returning tokens without stop words.'''
content = read_tokens(tokens)
stopwords = get_stopwords(language)
if custom:
stopwords = stopwords + read_tokens(custom)
[output(token) for token in content
if token.lower() not in stopwords]
def tokens2pos(sep, tokens):
'''Tokenize words into their parts of speech. Each item
is the original word with its role as the second part
of the item. Punctuation is considered as a separate token.'''
content = read_tokens(tokens)
nltk.data.path.append(data_item())
tags = nltk.pos_tag(content)
[output("{},{}".format(t[0], t[1])) for t in tags]
def tokens2pos(sep, tokens):
'''Tokenize words into their parts of speech. Each item
is the original word with its role as the second part
of the item. Punctuation is considered as a separate token.'''
content = read_tokens(tokens)
nltk.data.path.append(data_item())
tags = nltk.pos_tag(content)
[output("{},{}".format(t[0], t[1])) for t in tags]
def top_bigrams(sep, measure, freq, scores, tokens):
'''Find top most interesting bi-grams in a token document.
Uses the --measure argument to determine what measure to use to define
'interesting'.
'''
output(sep)
content = read_tokens(tokens)
bcf = nltk.collocations.BigramCollocationFinder.from_words(content)
bcf.apply_freq_filter(freq)
nltk_measure = MEASURES[measure]
bigrams = bcf.score_ngrams(nltk_measure)
out = [b[0] for b in bigrams]
if scores:
out = [b[0] + tuple([str(b[1])]) for b in bigrams]
[output(sep.join(line)) for line in out]
def transliterate(file):
'''Convert international text to ascii.'''
content = ''.join(file.readlines())
try:
content = content.decode(chardet.detect(content)['encoding'])
except AttributeError:
# Strings do not have a decode method in python 3.
pass
[output(unidecode(content).encode('ascii', 'ignore'))]
def text2punc(text):
'''Tokenize text into punctuation tokens.
Words and numbers are removed, leaving only punctuation.'''
# from: http://stackoverflow.com/questions/17485092/how-to-just-keep-punctuation-with-a-string-in-python
content = '\n'.join([open(f).read() for f in text])
out = re.sub(r'[^{}]+'.format(punctuation), ' ', content)
out = out.split()
[output(p) for p in out]
def text2punc(text):
'''Tokenize text into punctuation tokens.
Words and numbers are removed, leaving only punctuation.'''
# from: http://stackoverflow.com/questions/17485092/how-to-just-keep-punctuation-with-a-string-in-python
content = '\n'.join([open(f).read() for f in text])
out = re.sub(r'[^{}]+'.format(punctuation), ' ', content)
out = out.split()
[output(p) for p in out]
def text2sentences(text):
'''Tokenize text into sentence tokens.'''
content = '\n'.join([open(f).read() for f in text])
sentences = []
try:
sentences = sent_tokenize(content)
except LookupError as err:
click.echo(message="Error with tokenization", nl=True)
click.echo(message="Have you run \"textkit download\"?", nl=True)
click.echo(message="\nOriginal Error:", nl=True)
click.echo(err)
[output(s.strip()) for s in sentences]
def text2sentences(text):
"""Tokenize text into sentence tokens."""
content = "\n".join([open(f).read() for f in text])
sentences = []
try:
sentences = sent_tokenize(content)
except LookupError as err:
click.echo(message="Error with tokenization", nl=True)
click.echo(message='Have you run "textkit download"?', nl=True)
click.echo(message="\nOriginal Error:", nl=True)
click.echo(err)
[output(s.strip()) for s in sentences]
def tokens2json(ids, names, field, split, sep, token_docs):
'''Convert a set of token documents into a
JSON array of document objects.'''
docs = []
names = read_names(names)
ids = read_names(ids)
for idx, path in enumerate(token_docs):
if path == '-':
tokens_doc = sys.stdin
else:
tokens_doc = open(path, 'r')
if split:
content = read_csv(tokens_doc, sep)
content = coerce_types(content)
else:
content = read_tokens(tokens_doc)
# ordered so that these attributes stay at the top
doc = OrderedDict()
if idx < len(ids) - 1:
doc['id'] = ids[idx]
else:
doc['id'] = path
if idx < len(names) - 1:
doc['name'] = names[idx]
else:
doc['name'] = path
doc[field] = content
docs.append(doc)
tokens_doc.close()
out_content = json.dumps(docs, indent=2)
output(out_content)
def text2words(text):
'''Tokenize text into word tokens.
Punctuation is considered as a separate token.'''
content = '\n'.join([open(f).read() for f in text])
tokens = []
try:
tokens = nltk.word_tokenize(content)
except LookupError as err:
click.echo(message="Error with tokenization", nl=True)
click.echo(message="Have you run \"textkit download\"?", nl=True)
click.echo(message="\nOriginal Error:", nl=True)
click.echo(err)
[output(token) for token in tokens]
def words2bigrams(sep, tokens):
"""Tokenize words into bigrams. Bigrams are two word tokens.
Punctuation is considered as a separate token."""
content = read_tokens(tokens)
bigrams = []
try:
bigrams = list(nltk.bigrams(content))
except LookupError as err:
click.echo(message="Error with tokenization", nl=True)
click.echo(message='Have you run "textkit download"?', nl=True)
click.echo(message="\nOriginal Error:", nl=True)
click.echo(err)
[output(sep.join(bigram)) for bigram in bigrams]
def words2bigrams(sep, tokens):
'''Tokenize words into bigrams. Bigrams are two word tokens.
Punctuation is considered as a separate token.'''
content = read_tokens(tokens)
bigrams = []
try:
bigrams = list(nltk.bigrams(content))
except LookupError as err:
click.echo(message="Error with tokenization", nl=True)
click.echo(message="Have you run \"textkit download\"?", nl=True)
click.echo(message="\nOriginal Error:", nl=True)
click.echo(err)
[output(sep.join(bigram)) for bigram in bigrams]
def filterpunc(tokens):
'''Remove tokens that are only punctuation from a list of tokens.'''
content = read_tokens(tokens)
[output(token) for token in content if token not in punctuation]
def nonewlines(text):
'''Remove newlines from a text file.'''
content = '\n'.join([open(f).read() for f in text])
content = re.sub('\n|\r\n|\r', ' ', content).strip()
output(content)
def text2words(text):
'''Tokenize text into word tokens.
Punctuation is considered as a separate token.'''
content = '\n'.join([open(f).read() for f in text])
tokens = nltk.word_tokenize(content)
[output(token) for token in tokens]
def uppercase(tokens):
'''Transform all tokens to uppercase.'''
content = read_tokens(tokens)
[output(token.upper()) for token in content]
def filterlengths(minimum, tokens):
'''Remove tokens that are shorter then the minimum length provided.'''
content = read_tokens(tokens)
[output(token) for token in content if len(token) >= minimum]
def uppercase(tokens):
'''Transform all tokens to uppercase.'''
content = read_tokens(tokens)
[output(token.upper()) for token in content]
def filterlengths(minimum, tokens):
'''Remove tokens that are shorter then the minimum length provided.'''
content = read_tokens(tokens)
[output(token) for token in content if len(token) >= minimum]
def tokens2text(sep, tokens):
'''Combine tokens in a token document into a single text file.'''
content = read_tokens(tokens)
out = sep.join(content)
output(out)
def nonewlines(text):
"""Remove newlines from a text file."""
content = "\n".join([open(f).read() for f in text])
content = content.replace("\n", " ").strip()
output(content)
def showstops(language):
'''Display stop words used by textkit for a given language.'''
stopwords = get_stopwords(language)
[output(token) for token in stopwords]
def text2sentences(text):
'''Tokenize text into sentence tokens.'''
content = '\n'.join([open(f).read() for f in text])
sentences = sent_tokenize(content)
[output(s.strip()) for s in sentences]
def text2sentences(text):
'''Tokenize text into sentence tokens.'''
content = '\n'.join([open(f).read() for f in text])
sentences = sent_tokenize(content)
[output(s.strip()) for s in sentences]
def tokens2lower(tokens):
'''Transform all tokens to lowercase.'''
content = read_tokens(tokens)
[output(token.lower()) for token in content]
def nonewlines(text):
'''Remove newlines from a text file.'''
content = '\n'.join([open(f).read() for f in text])
content = content.replace('\n', ' ').strip()
output(content)
