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 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