def save(self, path, fname_prefix=None):
"""
Save serialized TextDoc content and metadata to disk.
Args:
path (str): directory on disk where content + metadata will be saved
fname_prefix (str, optional): prepend standard filenames 'spacy_doc.bin'
and 'metadata.json' with additional identifying information
.. warn:: If the `spacy.Vocab` object used to save this document is not the
same as the one used to load it, there will be problems! Consequently,
this functionality is only useful as short-term but not long-term storage.
"""
if fname_prefix:
meta_fname = os.path.join(
path, '_'.join([fname_prefix, 'metadata.json']))
doc_fname = os.path.join(path,
'_'.join([fname_prefix, 'spacy_doc.bin']))
else:
meta_fname = os.path.join(path, 'metadata.json')
doc_fname = os.path.join(path, 'spacy_doc.bin')
package_info = {
'textacy_lang': self.lang,
'spacy_version': spacy.about.__version__
}
fileio.write_json(dict(package_info, **self.metadata), meta_fname)
fileio.write_spacy_docs(self.spacy_doc, doc_fname)
def save(self, path, name=None):
"""
Save ``Doc`` content and metadata to disk.
Args:
path (str): Directory on disk where content + metadata will be saved.
name (str): Prepend default filenames 'spacy_doc.bin' and 'metadata.json'
with a name to identify/uniquify this particular document.
.. warning:: If the ``spacy.Vocab`` object used to save this document is
not the same as the one used to load it, there will be problems!
Consequently, this functionality is only useful as short-term but
not long-term storage.
"""
if name:
meta_fname = os.path.join(path, '_'.join([name, 'metadata.json']))
doc_fname = os.path.join(path, '_'.join([name, 'spacy_doc.bin']))
else:
meta_fname = os.path.join(path, 'metadata.json')
doc_fname = os.path.join(path, 'spacy_doc.bin')
package_info = {'textacy_lang': self.lang,
'spacy_version': spacy.about.__version__}
fileio.write_json(
dict(package_info, **self.metadata), meta_fname)
fileio.write_spacy_docs(self.spacy_doc, doc_fname)
def save(self, path, fname_prefix=None):
"""
Save serialized TextCorpus content and metadata to disk.
Args:
path (str): directory on disk where content + metadata will be saved
fname_prefix (str, optional): prepend standard filenames 'spacy_docs.bin'
and 'metadatas.json' with additional identifying information
.. warn:: If the `spacy.Vocab` object used to save this corpus is not the
same as the one used to load it, there will be problems! Consequently,
this functionality is only useful as short-term but not long-term storage.
"""
if fname_prefix:
info_fname = os.path.join(path, '_'.join([fname_prefix, 'info.json']))
meta_fname = os.path.join(path, '_'.join([fname_prefix, 'metadatas.json']))
docs_fname = os.path.join(path, '_'.join([fname_prefix, 'spacy_docs.bin']))
else:
info_fname = os.path.join(path, 'info.json')
meta_fname = os.path.join(path, 'metadatas.json')
docs_fname = os.path.join(path, 'spacy_docs.bin')
package_info = {'textacy_lang': self.lang, 'spacy_version': spacy.about.__version__}
fileio.write_json(package_info, info_fname)
fileio.write_json_lines((doc.metadata for doc in self), meta_fname)
fileio.write_spacy_docs((doc.spacy_doc for doc in self), docs_fname)
def test_read_write_json(self):
expected = [{'idx': i, 'sent': sent.text}
for i, sent in enumerate(self.spacy_doc.sents)]
filename = os.path.join(self.tempdir, 'test_read_write_json.json')
fileio.write_json(expected, filename)
observed = list(fileio.read_json(filename, prefix=''))[0]
self.assertEqual(observed, expected)
def save(self, path, name=None):
"""
Save ``Doc`` content and metadata to disk.
Args:
path (str): Directory on disk where content + metadata will be saved.
name (str): Prepend default filenames 'spacy_doc.bin' and 'metadata.json'
with a name to identify/uniquify this particular document.
.. warning:: If the ``spacy.Vocab`` object used to save this document is
not the same as the one used to load it, there will be problems!
Consequently, this functionality is only useful as short-term but
not long-term storage.
"""
if name:
meta_fname = os.path.join(path, '_'.join([name, 'metadata.json']))
doc_fname = os.path.join(path, '_'.join([name, 'spacy_doc.bin']))
else:
meta_fname = os.path.join(path, 'metadata.json')
doc_fname = os.path.join(path, 'spacy_doc.bin')
package_info = {'textacy_lang': self.lang,
'spacy_version': spacy.about.__version__}
fileio.write_json(
dict(package_info, **self.metadata), meta_fname)
fileio.write_spacy_docs(self.spacy_doc, doc_fname)
def save(self, path, fname_prefix=None, compression=None):
"""
Save serialized TextCorpus content and metadata to disk.
Args:
path (str): directory on disk where content + metadata will be saved
fname_prefix (str, optional): prepend standard filenames 'spacy_docs.bin'
and 'metadatas.json' with additional identifying information
compression ({'gzip', 'bz2', 'lzma'} or None): type of compression
used to reduce size of metadatas json file
.. warn:: If the `spacy.Vocab` object used to save this corpus is not the
same as the one used to load it, there will be problems! Consequently,
this functionality is only useful as short-term but not long-term storage.
"""
if fname_prefix:
info_fname = os.path.join(path, '_'.join([fname_prefix, 'info.json']))
meta_fname = os.path.join(path, '_'.join([fname_prefix, 'metadatas.json']))
docs_fname = os.path.join(path, '_'.join([fname_prefix, 'spacy_docs.bin']))
else:
info_fname = os.path.join(path, 'info.json')
meta_fname = os.path.join(path, 'metadatas.json')
docs_fname = os.path.join(path, 'spacy_docs.bin')
meta_fname = meta_fname + ('.gz' if compression == 'gzip'
else '.bz2' if compression == 'bz2'
else '.xz' if compression == 'lzma'
else '')
meta_mode = 'wt' if PY2 is False or compression is None else 'wb'
package_info = {'textacy_lang': self.lang, 'spacy_version': spacy.about.__version__}
fileio.write_json(package_info, info_fname)
fileio.write_json_lines(
(doc.metadata for doc in self), meta_fname, mode=meta_mode,
ensure_ascii=False, separators=(',', ':'))
fileio.write_spacy_docs((doc.spacy_doc for doc in self), docs_fname)
def test_read_write_json_prefix(self):
to_write = [{'idx': i, 'sent': sent.text}
for i, sent in enumerate(self.spacy_doc.sents)]
expected = [item['sent'] for item in to_write]
filename = os.path.join(self.tempdir, 'test_read_write_json_prefix.json')
fileio.write_json(to_write, filename)
observed = list(fileio.read_json(filename, prefix='item.sent'))
self.assertEqual(observed, expected)
def test_read_write_json(self):
expected = [{
'idx': i,
'sent': sent.text
} for i, sent in enumerate(self.spacy_doc.sents)]
filename = os.path.join(self.tempdir, 'test_read_write_json.json')
fileio.write_json(expected, filename)
observed = list(fileio.read_json(filename, prefix=''))[0]
self.assertEqual(observed, expected)
def test_read_write_json_prefix(self):
to_write = [{'idx': i, 'sent': sent.text}
for i, sent in enumerate(self.spacy_doc.sents)]
for prefix in ('idx', 'sent'):
expected = [item[prefix] for item in to_write]
filename = os.path.join(
self.tempdir, 'test_read_write_json_prefix.json')
fileio.write_json(to_write, filename, auto_make_dirs=True)
observed = list(fileio.read_json(filename, prefix='item.' + prefix))
self.assertEqual(observed, expected)
def test_read_write_json_unicode(self):
expected = [{'idx': i, 'sent': sent.text}
for i, sent in enumerate(self.spacy_doc.sents)]
for ext in ('.json', '.json.gz', '.json.bz2', '.json.xz'):
filename = os.path.join(
self.tempdir, 'test_read_write_json_unicode' + ext)
if PY2 is True and ext != '.json':
self.assertRaises(
ValueError, fileio.open_sesame,
filename, 'wt', None, True)
else:
fileio.write_json(expected, filename, mode='wt',
auto_make_dirs=True)
observed = list(fileio.read_json(filename, mode='rt', prefix=''))[0]
self.assertEqual(observed, expected)
def test_read_write_json_unicode(self):
expected = [{'idx': i, 'sent': sent.text}
for i, sent in enumerate(self.spacy_doc.sents)]
for ext in ('.json', '.json.gz', '.json.bz2', '.json.xz'):
filename = os.path.join(
self.tempdir, 'test_read_write_json_unicode' + ext)
if PY2 is True and ext != '.json':
self.assertRaises(
ValueError, fileio.open_sesame,
filename, 'wt', None, True)
else:
fileio.write_json(expected, filename, mode='wt',
auto_make_dirs=True)
observed = list(fileio.read_json(filename, mode='rt', prefix=''))[0]
self.assertEqual(observed, expected)
def test_read_write_json_bytes(self):
expected = [{'idx': i, 'sent': sent.text}
for i, sent in enumerate(self.spacy_doc.sents)]
for ext in ('.json', '.json.gz', '.json.bz2', '.json.xz'):
filename = os.path.join(
self.tempdir, 'test_read_write_json_bytes' + ext)
if PY2 is True:
fileio.write_json(expected, filename, mode='wb',
auto_make_dirs=True)
observed = list(fileio.read_json(filename, mode='rb', prefix=''))[0]
self.assertEqual(observed, expected)
else:
self.assertRaises(
TypeError,
lambda: fileio.write_json(expected, filename, 'wb',
auto_make_dirs=True))
def save(self, path, fname_prefix=None):
"""
Save serialized TextDoc content and metadata to disk.
Args:
path (str): directory on disk where content + metadata will be saved
fname_prefix (str, optional): prepend standard filenames 'spacy_doc.bin'
and 'metadata.json' with additional identifying information
"""
if fname_prefix:
meta_fname = os.path.join(path, '_'.join([fname_prefix, 'metadata.json']))
doc_fname = os.path.join(path, '_'.join([fname_prefix, 'spacy_doc.bin']))
else:
meta_fname = os.path.join(path, 'metadata.json')
doc_fname = os.path.join(path, 'spacy_doc.bin')
package_info = {'textacy_lang': self.lang,
'spacy_version': spacy.about.__version__}
fileio.write_json(
dict(package_info, **self.metadata), meta_fname)
fileio.write_spacy_docs(self.spacy_doc, doc_fname)
def save(self, path, fname_prefix=None, compression=None):
"""
Save serialized TextCorpus content and metadata to disk.
Args:
path (str): directory on disk where content + metadata will be saved
fname_prefix (str, optional): prepend standard filenames 'spacy_docs.bin'
and 'metadatas.json' with additional identifying information
compression ({'gzip', 'bz2', 'lzma'} or None): type of compression
used to reduce size of metadatas json file
.. warn:: If the `spacy.Vocab` object used to save this corpus is not the
same as the one used to load it, there will be problems! Consequently,
this functionality is only useful as short-term but not long-term storage.
"""
if fname_prefix:
info_fname = os.path.join(path,
'_'.join([fname_prefix, 'info.json']))
meta_fname = os.path.join(
path, '_'.join([fname_prefix, 'metadatas.json']))
docs_fname = os.path.join(
path, '_'.join([fname_prefix, 'spacy_docs.bin']))
else:
info_fname = os.path.join(path, 'info.json')
meta_fname = os.path.join(path, 'metadatas.json')
docs_fname = os.path.join(path, 'spacy_docs.bin')
meta_fname = meta_fname + ('.gz' if compression == 'gzip' else
'.bz2' if compression == 'bz2' else
'.xz' if compression == 'lzma' else '')
meta_mode = 'wt' if PY2 is False or compression is None else 'wb'
package_info = {
'textacy_lang': self.lang,
'spacy_version': spacy.about.__version__
}
fileio.write_json(package_info, info_fname)
fileio.write_json_lines((doc.metadata for doc in self),
meta_fname,
mode=meta_mode,
ensure_ascii=False,
separators=(',', ':'))
fileio.write_spacy_docs((doc.spacy_doc for doc in self), docs_fname)
def save(self, path, name=None, compression=None):
"""
Save ``Corpus`` content and metadata to disk.
Args:
path (str): Directory on disk where content + metadata will be saved.
name (str): Prepend default filenames 'spacy_docs.bin', 'metadatas.json',
and 'info.json' with a name to identify/uniquify this particular
corpus.
compression ({'gzip', 'bz2', 'lzma'} or None): Type of compression
used to reduce size of 'metadatas.json' file, if any.
.. warning:: If the ``spacy.Vocab`` object used to save this corpus is
not the same as the one used to load it, there will be problems!
Consequently, this functionality is only useful as short-term but
not long-term storage.
"""
if name:
info_fname = os.path.join(path, '_'.join([name, 'info.json']))
meta_fname = os.path.join(path, '_'.join([name, 'metadatas.json']))
docs_fname = os.path.join(path, '_'.join([name, 'spacy_docs.pkl']))
else:
info_fname = os.path.join(path, 'info.json')
meta_fname = os.path.join(path, 'metadatas.json')
docs_fname = os.path.join(path, 'spacy_docs.bin')
meta_fname = meta_fname + ('.gz' if compression == 'gzip' else
'.bz2' if compression == 'bz2' else
'.xz' if compression == 'lzma' else '')
meta_mode = 'wt' if is_python2 is False or compression is None else 'wb'
package_info = {
'textacy_lang': self.lang,
'spacy_version': spacy.about.__version__
}
fileio.write_json(package_info, info_fname)
fileio.write_json_lines((doc.metadata for doc in self),
meta_fname,
mode=meta_mode,
ensure_ascii=False,
separators=(',', ':'))
fileio.write_spacy_docs((doc.spacy_doc for doc in self), docs_fname)
def save(self, path, name=None, compression=None):
"""
Save ``Corpus`` content and metadata to disk.
Args:
path (str): Directory on disk where content + metadata will be saved.
name (str): Prepend default filenames 'spacy_docs.bin', 'metadatas.json',
and 'info.json' with a name to identify/uniquify this particular
corpus.
compression ({'gzip', 'bz2', 'lzma'} or None): Type of compression
used to reduce size of 'metadatas.json' file, if any.
.. warning:: If the ``spacy.Vocab`` object used to save this corpus is
not the same as the one used to load it, there will be problems!
Consequently, this functionality is only useful as short-term but
not long-term storage.
"""
if name:
info_fname = os.path.join(path, '_'.join([name, 'info.json']))
meta_fname = os.path.join(path, '_'.join([name, 'metadatas.json']))
docs_fname = os.path.join(path, '_'.join([name, 'spacy_docs.bin']))
else:
info_fname = os.path.join(path, 'info.json')
meta_fname = os.path.join(path, 'metadatas.json')
docs_fname = os.path.join(path, 'spacy_docs.bin')
meta_fname = meta_fname + ('.gz' if compression == 'gzip'
else '.bz2' if compression == 'bz2'
else '.xz' if compression == 'lzma'
else '')
meta_mode = 'wt' if PY2 is False or compression is None else 'wb'
package_info = {'textacy_lang': self.lang, 'spacy_version': spacy.about.__version__}
fileio.write_json(package_info, info_fname)
fileio.write_json_lines(
(doc.metadata for doc in self), meta_fname, mode=meta_mode,
ensure_ascii=False, separators=(',', ':'))
fileio.write_spacy_docs((doc.spacy_doc for doc in self), docs_fname)
def test_read_write_json_bytes(self):
expected = [{
'idx': i,
'sent': sent.text
} for i, sent in enumerate(self.spacy_doc.sents)]
for ext in ('.json', '.json.gz', '.json.bz2', '.json.xz'):
filename = os.path.join(self.tempdir,
'test_read_write_json_bytes' + ext)
if is_python2 is True:
if ext == '.json.xz':
self.assertRaises(ValueError, fileio.open_sesame, filename,
'wb', 'utf-8', True)
else:
fileio.write_json(expected,
filename,
mode='wb',
auto_make_dirs=True)
observed = list(
fileio.read_json(filename, mode='rb', prefix=''))[0]
self.assertEqual(observed, expected)
else:
self.assertRaises(
TypeError, lambda: fileio.write_json(
expected, filename, 'wb', auto_make_dirs=True))
