def __init__(self,
max_output_token_length=MAX_OUTPUT_TOKEN_LENGTH,
reserved=()):
self.types_to_skip = ()
self.reserved = reserved
self.mappings: Dict[str, str]
self.update_mappings({
# By default, replace \n and \r. This is meant primarily for literals.
'\n':
unified_tokenizer.quote_special('NLCHAR'),
'\r':
unified_tokenizer.quote_special('CR'),
unified_tokenizer.SENTINEL:
unified_tokenizer.quote_special(unified_tokenizer.SENTINEL_ESCAPE),
})
self.max_output_token_length = max_output_token_length
def untokenize(self, token_list):
"""Untokenizes via `untokenize_abstract`."""
# Untokenize agnostic.
if (not token_list
or token_list[-1] != unified_tokenizer.quote_special(
unified_tokenizer.TokenKind.EOS.name)):
raise ValueError(
'Token list %r should end with the EOS token %r.' %
(token_list,
unified_tokenizer.quote_special(
unified_tokenizer.TokenKind.EOS.name)))
whole_tokens = unified_tokenizer.reconstitute_full_unsanitary_tokens(
token_list,
sanitization_mapping=self.mappings,
sentinel=unified_tokenizer.SENTINEL)
return self.untokenize_abstract(whole_tokens)
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 == unified_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):
"""As per the superclass."""
agnostic_tokens: List[unified_tokenizer.AbstractToken] = []
try:
java_tokens = list(
extended_javalang_tokenizer.tokenize_extended(source_code))
except (javalang.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.warning(
'The tokenizer raised exception `%r` while parsing %s', e,
source_code)
# We don't try to do recovery from errors quite yet. Mark the error as
# occurring at whatever position we are in and terminate
agnostic_tokens.append(
unified_tokenizer.AbstractToken(
unified_tokenizer.quote_special(
unified_tokenizer.TokenKind.ERROR.name),
unified_tokenizer.TokenKind.ERROR,
unified_tokenizer.TokenMetadata(
start=unified_tokenizer.Position(line=0, column=0),
end=unified_tokenizer.Position(line=0, column=0))))
agnostic_tokens.append(
unified_tokenizer.AbstractToken(
unified_tokenizer.quote_special(
unified_tokenizer.TokenKind.EOS.name),
unified_tokenizer.TokenKind.EOS,
unified_tokenizer.TokenMetadata(
start=unified_tokenizer.Position(line=0, column=0),
end=unified_tokenizer.Position(line=0, column=0))))
else:
start_line = 0
start_column = 0
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))
# JavaTokenizer counts lines and columns from 1.
start_line = token.position.line - 1
start_column = token.position.column - 1
# 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(
line=start_line, column=start_column))))
# At this point, we have all the tokens, either as produced and abstracted,
# or a placeholder error and eos in case of an exception. However, the
# tokens only have start positions. Since the extended tokenizer guarantees
# that tokens abut, we take a second pass, backwards, setting the end
# position of a token from the start position of token following it. The
# final token, `EOS` already has an end position, so we don't modify it.
eos = agnostic_tokens[-1]
if not eos.metadata.start:
# This should be there. Raise an exception
raise AssertionError(
'The end of input token is missing positioning '
'information: %s' % eos)
later_token_start: unified_tokenizer.Position = eos.metadata.start
# The EOS token has an empty extent, so the end and the start are set to be
# the same.
filled_agnostic_tokens = [
dataclasses.replace(eos,
metadata=dataclasses.replace(
eos.metadata, end=eos.metadata.start))
]
# Go backwards, from the element before `eos` to the beginning.
for token in (agnostic_tokens[i]
for i in range(len(agnostic_tokens) - 2, -1, -1)):
filled_token = dataclasses.replace(token,
metadata=dataclasses.replace(
token.metadata,
end=later_token_start))
filled_agnostic_tokens.append(filled_token)
later_token_start = token.metadata.start
# Now we have the tokens, including end position, but they're reversed.
# The final step is to break down whitespace tokens into primitive
# WHITESPACE tokens and NEWLINE tokens.
with_broken_whitespace = []
for token in filled_agnostic_tokens[::-1]:
if token.kind is not unified_tokenizer.TokenKind.WHITESPACE:
with_broken_whitespace.append(token)
else:
# This is whitespace. Replace it with primitive tokens.
with_broken_whitespace.extend(
unified_tokenizer.fill_range_with_whitespace(
token.metadata.start, token.metadata.end))
return with_broken_whitespace
# 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.
"""Tests for java_tokenizer."""
from typing import Sequence, Tuple
from absl.testing import absltest
from absl.testing import parameterized
import java_tokenizer
import unified_tokenizer
_NEWLINE_NAME = unified_tokenizer.quote_special(
unified_tokenizer.TokenKind.NEWLINE.name)
class JavaTokenizerTest(parameterized.TestCase):
@parameterized.named_parameters(
(
'nothing',
'',
(),
),
(
'same_line',
"""TokenA TokenB""",
# 0 67
(
def token_from_token_type(token_type):
"""Turns a token type into a reserved token string."""
# We use the tok_name dict from tokenize, not token. The former has
# NL and COMMENT and such, whereas the latter doesn't.
return unified_tokenizer.quote_special(tokenize.tok_name[token_type])
def tokenize_and_abstract(self, source_code):
"""Produces a language-agnostic tokenization of the input code."""
agnostic_tokens: List[unified_tokenizer.AbstractToken] = []
try:
token_tuples = unified_tokenizer.code_to_tokens(source_code)
except (tokenize.TokenError, IndentationError) as e:
logging.warning(
'The tokenizer raised exception `%s` while parsing %s', e,
source_code)
# We don't try to do recovery from errors quite yet. Emit just an
# error and end-of-sequence and return.
agnostic_tokens.append(
unified_tokenizer.AbstractToken(
unified_tokenizer.quote_special(
unified_tokenizer.TokenKind.ERROR.name),
unified_tokenizer.TokenKind.ERROR,
unified_tokenizer.TokenMetadata(
start=unified_tokenizer.Position(line=0, column=0),
end=unified_tokenizer.Position(line=0, column=0))))
agnostic_tokens.append(
unified_tokenizer.AbstractToken(
unified_tokenizer.quote_special(
unified_tokenizer.TokenKind.EOS.name),
unified_tokenizer.TokenKind.EOS,
unified_tokenizer.TokenMetadata(
start=unified_tokenizer.Position(line=0, column=0),
end=unified_tokenizer.Position(line=0, column=0))))
return agnostic_tokens
for token_tuple in token_tuples:
spelling = token_tuple.string
kind = token_tuple.type
# We'll adjust the spelling of some tokens, e.g., those that we
# tokenize by their type rather than their original spelling. Indentation
# and dedentation tokens are like that.
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 = unified_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))
start_line, start_column = token_tuple.start
end_line, end_column = token_tuple.end
# Unlike other languages, NEWLINE tokens are reported as ending on the
# same line as where they started. We adjust that here, to stick to the
# same convention as other tokenizers.
if ((token_kind == unified_tokenizer.TokenKind.NEWLINE)
or (kind == tokenize.NL)):
end_line = start_line + 1
end_column = 0
agnostic_tokens.append(
unified_tokenizer.AbstractToken(
spelling=adjusted_spelling,
kind=token_kind,
metadata=unified_tokenizer.TokenMetadata(
# Python's tokenizer counts lines starting from 1, so we
# have to offset what we read from the `TokenInfo` tuple.
start=unified_tokenizer.Position(line=start_line - 1,
column=start_column),
end=unified_tokenizer.Position(line=end_line - 1,
column=end_column))))
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,
unified_tokenizer.quote_special(unified_tokenizer.TokenKind.EOS.name):
tokenize.ENDMARKER,
unified_tokenizer.quote_special(unified_tokenizer.TokenKind.ERROR.name):
tokenize.ERRORTOKEN,
unified_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.
# pytype: disable=module-attr
_NUMBERS = re.compile('(' + tokenize.Number + r')\Z')
# pytype: disable=module-attr
_SINGLE_STRINGS = re.compile('(' + tokenize.String + r')\Z')
_TRIPLE_STRING_BEGINNINGS = re.compile(tokenize.Triple) # pytype: disable=module-attr
# pytype: disable=module-attr
_COMMENTS = re.compile('(' + tokenize.Comment + r')\Z')
_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 tokenize_and_abstract(self, source_code):
"""Produces a language-agnostic tokenization of the input code."""
agnostic_tokens: List[unified_tokenizer.AbstractToken] = []
try:
token_tuples = unified_tokenizer.code_to_tokens(source_code)
except (tokenize.TokenError, IndentationError) as e:
logging.warning(
'The tokenizer raised exception `%s` while parsing %s', e,
source_code)
# We don't try to do recovery from errors quite yet. Emit just an
# error and end-of-sequence and return.
agnostic_tokens.append(
unified_tokenizer.AbstractToken(
unified_tokenizer.quote_special(
unified_tokenizer.TokenKind.ERROR.name),
unified_tokenizer.TokenKind.ERROR,
unified_tokenizer.TokenMetadata(
start=unified_tokenizer.Position(line=0, column=0),
end=unified_tokenizer.Position(line=0, column=0))))
agnostic_tokens.append(
unified_tokenizer.AbstractToken(
unified_tokenizer.quote_special(
unified_tokenizer.TokenKind.EOS.name),
unified_tokenizer.TokenKind.EOS,
unified_tokenizer.TokenMetadata(
start=unified_tokenizer.Position(line=0, column=0),
end=unified_tokenizer.Position(line=0, column=0))))
return agnostic_tokens
for token_tuple in token_tuples:
spelling = token_tuple.string
kind = token_tuple.type
# We'll adjust the spelling of some tokens, e.g., those that we
# tokenize by their type rather than their original spelling. Indentation
# and dedentation tokens are like that.
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 = unified_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))
start_line, start_column = token_tuple.start
end_line, end_column = token_tuple.end
# Unlike other languages, NEWLINE tokens are reported as ending on the
# same line as where they started. We adjust that here, to stick to the
# same convention as other tokenizers.
if ((token_kind == unified_tokenizer.TokenKind.NEWLINE)
or (kind == tokenize.NL)):
end_line = start_line + 1
end_column = 0
agnostic_tokens.append(
unified_tokenizer.AbstractToken(
spelling=adjusted_spelling,
kind=token_kind,
metadata=unified_tokenizer.TokenMetadata(
# Python's tokenizer counts lines starting from 1, so we
# have to offset what we read from the `TokenInfo` tuple.
start=unified_tokenizer.Position(line=start_line - 1,
column=start_column),
end=unified_tokenizer.Position(line=end_line - 1,
column=end_column))))
return agnostic_tokens
def untokenize_abstract(self, whole_tokens):
# Reconstruct Python tokenizer tuples, so that Python's untokenize can be
# invoked.
token_tuples: List[Tuple[int, str]] = []
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