def tokenize_and_abstract(
self,
source_code):
"""As per the superclass."""
try:
java_tokens = tokenizer.tokenize(source_code)
except tokenizer.LexerError as e:
logging.warn('The tokenizer raised exception `%s` while parsing %s', e,
source_code)
return (
(cubert_tokenizer.quote_special(
unified_tokenizer.TokenKind.ERROR.name),
unified_tokenizer.TokenKind.ERROR),
(cubert_tokenizer.quote_special(unified_tokenizer.TokenKind.EOS),
unified_tokenizer.TokenKind.EOS),
)
agnostic_tokens: List[Tuple[str, unified_tokenizer.TokenKind]] = []
for token in java_tokens:
# The token kind is the subclass type of the token.
token_type = type(token)
if token_type not in JavaTokenizer._TOKEN_TYPE_MAP:
raise ValueError('Received Java token type %s, but it was unexpected, '
'while tokenizing \n%s\n' % (token_type, source_code))
agnostic_tokens.append(
(token.value, JavaTokenizer._TOKEN_TYPE_MAP[token_type]))
return agnostic_tokens
def tokenize_and_abstract(self, source_code):
"""As per the superclass."""
agnostic_tokens: List[unified_tokenizer.AbstractToken] = []
try:
java_tokens = tokenizer.tokenize(source_code)
for token in java_tokens:
# The token kind is the subclass type of the token.
token_type = type(token)
if token_type not in JavaTokenizer._TOKEN_TYPE_MAP:
raise ValueError(
'Received Java token type %s, but it was unexpected, '
'while tokenizing \n%s\n' % (token_type, source_code))
# The tokenizer seems to take some liberties with Unicode, returning
# invalid characters. This cleans spellings up.
spelling = token.value.encode('utf-8',
errors='replace').decode('utf-8')
agnostic_tokens.append(
unified_tokenizer.AbstractToken(
spelling,
JavaTokenizer._TOKEN_TYPE_MAP[token_type],
unified_tokenizer.
TokenMetadata(start=unified_tokenizer.Position(
# JavaTokenizer counts lines and columns from 1.
line=token.position.line - 1,
column=token.position.column - 1))))
except (tokenizer.LexerError, TypeError) as e:
# Sometimes, javalang returns a TypeError when reading a number.
# See
# https://github.com/c2nes/javalang/blob/0664afb7f4d40254312693f2e833c1ed4ac551c7/javalang/tokenizer.py#L370
logging.warn(
'The tokenizer raised exception `%r` while parsing %s', e,
source_code)
agnostic_tokens.append(
unified_tokenizer.AbstractToken(
cubert_tokenizer.quote_special(
unified_tokenizer.TokenKind.ERROR.name),
unified_tokenizer.TokenKind.ERROR,
unified_tokenizer.TokenMetadata()))
# javalang doesn't seem to ever return `EndOfinput` despite there being a
# token type for it. We insert it here.
agnostic_tokens.append(
unified_tokenizer.AbstractToken(
cubert_tokenizer.quote_special(
unified_tokenizer.TokenKind.EOS.name),
unified_tokenizer.TokenKind.EOS,
unified_tokenizer.TokenMetadata()))
return agnostic_tokens
def __init__(self, *args, **kwargs):
super(JavaTokenizer, self).__init__(*args, **kwargs)
self.update_mappings({
# By default, replace \n and \r. We choose special names that are
# different from the Python token types (i.e., NL).
'\n':
cubert_tokenizer.quote_special('NLCHAR'),
'\r':
cubert_tokenizer.quote_special('CR'),
unified_tokenizer.SENTINEL:
cubert_tokenizer.quote_special(unified_tokenizer.SENTINEL_ESCAPE),
})
def untokenize_abstract(self, whole_tokens):
tokens: List[str] = []
for token in whole_tokens[:-1]: # Skip EOS. The caller checked it's there.
if token == cubert_tokenizer.quote_special(
unified_tokenizer.TokenKind.NEWLINE.name):
tokens.append('\n')
else:
tokens.append(token)
return ''.join(tokens)
def tokenize_and_abstract(
self,
source_code):
"""Produces a language-agnostic tokenization of the input code."""
token_pairs = [] # type: List[Tuple[Text, int]]
try:
token_tuples = unified_tokenizer.code_to_tokens(source_code)
token_pairs = [(six.ensure_text(token_name), token_type)
for token_type, token_name, _, _, _ in token_tuples]
except (tokenize.TokenError, IndentationError) as e:
logging.warning('The tokenizer raised exception `%s` while parsing %s', e,
source_code)
token_pairs = [
(cubert_tokenizer.quote_special(
unified_tokenizer.TokenKind.ERROR.name), tokenize.ERRORTOKEN),
('', tokenize.ENDMARKER),
]
agnostic_tokens = [] # type: List[Tuple[Text, unified_tokenizer.TokenKind]]
for spelling, kind in token_pairs:
adjusted_spelling = spelling
token_kind = unified_tokenizer.TokenKind.NONE
if kind == tokenize.NAME:
# Disambiguate identifiers from keywords.
if keyword.iskeyword(spelling):
token_kind = unified_tokenizer.TokenKind.KEYWORD
else:
token_kind = unified_tokenizer.TokenKind.IDENTIFIER
else:
if kind in PythonTokenizer._TOKEN_TYPES_TO_TOKENIZE_BY_TYPE:
# Replace spelling with type.
adjusted_spelling = cubert_tokenizer.token_from_token_type(kind)
elif kind is tokenize.INDENT:
# For INDENT, in particular, we also record the actual spelling too.
adjusted_spelling = '{indent}{spelling}'.format(
indent=cubert_tokenizer.token_from_token_type(kind),
spelling=spelling)
elif kind == tokenize.ENDMARKER:
adjusted_spelling = cubert_tokenizer.quote_special(
unified_tokenizer.TokenKind.EOS.name)
# Map everything according to table.
try:
token_kind = PythonTokenizer._TOKEN_TYPE_MAP[kind]
except KeyError as ke:
# It's possible we're here because of async/await. Those kept being
# turned into keywords and then removed from keywords, so we can't
# rely on knowing which they are. We'll check by spelling.
# See: https://bugs.python.org/issue30406
# and https://bugs.python.org/issue33260
# and https://bugs.python.org/issue35975
if spelling in ('async', 'await'):
token_kind = unified_tokenizer.TokenKind.KEYWORD
else:
raise ValueError('While trying to turn Python token %r into an '
'agnostic one, raised %r.' %
((spelling, kind), ke))
agnostic_tokens.append((adjusted_spelling, token_kind))
return agnostic_tokens
class PythonTokenizer(cubert_tokenizer.CuBertTokenizer):
"""Tokenizer that extracts Python's lexical elements preserving strings."""
_TOKEN_TYPE_MAP = {
tokenize.COMMENT: unified_tokenizer.TokenKind.COMMENT,
tokenize.DEDENT: unified_tokenizer.TokenKind.KEYWORD,
tokenize.ENDMARKER: unified_tokenizer.TokenKind.EOS,
tokenize.ERRORTOKEN: unified_tokenizer.TokenKind.ERROR,
tokenize.INDENT: unified_tokenizer.TokenKind.KEYWORD,
tokenize.NEWLINE: unified_tokenizer.TokenKind.NEWLINE,
tokenize.NL: unified_tokenizer.TokenKind.PUNCTUATION,
tokenize.NUMBER: unified_tokenizer.TokenKind.NUMBER,
tokenize.OP: unified_tokenizer.TokenKind.PUNCTUATION,
tokenize.STRING: unified_tokenizer.TokenKind.STRING,
}
_REVERSE_TOKEN_MAP = {
cubert_tokenizer.token_from_token_type(tokenize.INDENT):
tokenize.INDENT,
cubert_tokenizer.token_from_token_type(tokenize.DEDENT):
tokenize.DEDENT,
cubert_tokenizer.quote_special(unified_tokenizer.TokenKind.EOS.name):
tokenize.ENDMARKER,
cubert_tokenizer.quote_special(unified_tokenizer.TokenKind.ERROR.name):
tokenize.ERRORTOKEN,
cubert_tokenizer.quote_special(unified_tokenizer.TokenKind.NEWLINE.name):
tokenize.NEWLINE,
cubert_tokenizer.token_from_token_type(tokenize.NL):
tokenize.NL,
}
# Adding the end-of-string anchor \Z below, since re.fullmatch wasn't
# available in Python2.
_NUMBERS = re.compile('(' + tokenize.Number + r')\Z') # pytype: disable=module-attr
_SINGLE_STRINGS = re.compile('(' + tokenize.String + r')\Z') # pytype: disable=module-attr
_TRIPLE_STRING_BEGINNINGS = re.compile(tokenize.Triple) # pytype: disable=module-attr
_COMMENTS = re.compile('(' + tokenize.Comment + r')\Z') # pytype: disable=module-attr
_EXACT_TOKEN_TYPES = tokenize.EXACT_TOKEN_TYPES.keys() # pytype: disable=module-attr
# Token types that CubertTokenizer will tokenize by their type and not
# content.
_TOKEN_TYPES_TO_TOKENIZE_BY_TYPE = [
tokenize.NEWLINE, tokenize.DEDENT, tokenize.NL
]
def __init__(self, *args, **kwargs):
super(PythonTokenizer, self).__init__(*args, **kwargs)
# By default, we drop COMMENT tokens.
self.update_types_to_skip([unified_tokenizer.TokenKind.COMMENT])
self.update_mappings({
# By default, replace \n and \r. We choose special names that are
# different from the Python token types (i.e., NL).
'\n':
cubert_tokenizer.quote_special('NLCHAR'),
'\r':
cubert_tokenizer.quote_special('CR'),
unified_tokenizer.SENTINEL:
cubert_tokenizer.quote_special(unified_tokenizer.SENTINEL_ESCAPE),
})
def tokenize_and_abstract(
self,
source_code):
"""Produces a language-agnostic tokenization of the input code."""
token_pairs = [] # type: List[Tuple[Text, int]]
try:
token_tuples = unified_tokenizer.code_to_tokens(source_code)
token_pairs = [(six.ensure_text(token_name), token_type)
for token_type, token_name, _, _, _ in token_tuples]
except (tokenize.TokenError, IndentationError) as e:
logging.warning('The tokenizer raised exception `%s` while parsing %s', e,
source_code)
token_pairs = [
(cubert_tokenizer.quote_special(
unified_tokenizer.TokenKind.ERROR.name), tokenize.ERRORTOKEN),
('', tokenize.ENDMARKER),
]
agnostic_tokens = [] # type: List[Tuple[Text, unified_tokenizer.TokenKind]]
for spelling, kind in token_pairs:
adjusted_spelling = spelling
token_kind = unified_tokenizer.TokenKind.NONE
if kind == tokenize.NAME:
# Disambiguate identifiers from keywords.
if keyword.iskeyword(spelling):
token_kind = unified_tokenizer.TokenKind.KEYWORD
else:
token_kind = unified_tokenizer.TokenKind.IDENTIFIER
else:
if kind in PythonTokenizer._TOKEN_TYPES_TO_TOKENIZE_BY_TYPE:
# Replace spelling with type.
adjusted_spelling = cubert_tokenizer.token_from_token_type(kind)
elif kind is tokenize.INDENT:
# For INDENT, in particular, we also record the actual spelling too.
adjusted_spelling = '{indent}{spelling}'.format(
indent=cubert_tokenizer.token_from_token_type(kind),
spelling=spelling)
elif kind == tokenize.ENDMARKER:
adjusted_spelling = cubert_tokenizer.quote_special(
unified_tokenizer.TokenKind.EOS.name)
# Map everything according to table.
try:
token_kind = PythonTokenizer._TOKEN_TYPE_MAP[kind]
except KeyError as ke:
# It's possible we're here because of async/await. Those kept being
# turned into keywords and then removed from keywords, so we can't
# rely on knowing which they are. We'll check by spelling.
# See: https://bugs.python.org/issue30406
# and https://bugs.python.org/issue33260
# and https://bugs.python.org/issue35975
if spelling in ('async', 'await'):
token_kind = unified_tokenizer.TokenKind.KEYWORD
else:
raise ValueError('While trying to turn Python token %r into an '
'agnostic one, raised %r.' %
((spelling, kind), ke))
agnostic_tokens.append((adjusted_spelling, token_kind))
return agnostic_tokens
def untokenize_abstract(self, whole_tokens):
# Reconstruct Python tokenizer tuples, so that Python's untokenize can be
# invoked.
token_tuples = [] # type: List[Tuple[int, Text]]
for whole_token in whole_tokens:
if whole_token in PythonTokenizer._EXACT_TOKEN_TYPES:
token_tuples.append((tokenize.OP, whole_token))
elif cubert_tokenizer.token_from_token_type(
tokenize.INDENT) in whole_token:
# We baked the type and spelling into one token. Break them up.
spelling = whole_token.replace(
cubert_tokenizer.token_from_token_type(tokenize.INDENT), '')
token_tuples.append((tokenize.INDENT, spelling))
elif whole_token in PythonTokenizer._REVERSE_TOKEN_MAP:
python_kind = PythonTokenizer._REVERSE_TOKEN_MAP[whole_token]
if python_kind in (tokenize.DEDENT, tokenize.ENDMARKER,
tokenize.ERRORTOKEN):
spelling = ''
else: # python_kind in (tokenize.NEWLINE, tokenize.NL)
spelling = '\n'
token_tuples.append((python_kind, spelling))
elif keyword.iskeyword(whole_token):
token_tuples.append((tokenize.NAME, whole_token))
elif PythonTokenizer._NUMBERS.match(whole_token):
token_tuples.append((tokenize.NUMBER, whole_token))
elif PythonTokenizer._SINGLE_STRINGS.match(whole_token):
token_tuples.append((tokenize.STRING, whole_token))
elif PythonTokenizer._TRIPLE_STRING_BEGINNINGS.match(whole_token):
token_tuples.append((tokenize.STRING, whole_token))
elif PythonTokenizer._COMMENTS.match(whole_token):
token_tuples.append((tokenize.COMMENT, whole_token))
else:
# Everything else we map back to NAME.
token_tuples.append((tokenize.NAME, whole_token))
reconstructed = tokenize.untokenize(typing.cast(Any, token_tuples))
return reconstructed
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.
from typing import List
from unittest import mock
from absl.testing import absltest
from absl.testing import parameterized
from cubert import cubert_tokenizer
from cubert import python_tokenizer
from cubert import unified_tokenizer
_EOS_NAME = cubert_tokenizer.quote_special(unified_tokenizer.TokenKind.EOS.name)
_ERROR_NAME = cubert_tokenizer.quote_special(
unified_tokenizer.TokenKind.ERROR.name)
_NEWLINE_NAME = cubert_tokenizer.quote_special(
unified_tokenizer.TokenKind.NEWLINE.name)
class PythonTokenizerTest(parameterized.TestCase):
@mock.patch.object(
unified_tokenizer,
'code_to_tokens',
return_value=[(1000, 'spelling', 0, 0, 0)])
def test_python_tokenize_raises_on_unknown_python_token_kind(
self, unused_function_mock):
tokenizer = python_tokenizer.PythonTokenizer()
