mirrors/cpython
0
0
Fork 0
mirror of https://github.com/python/cpython.git synced 2024-11-23 09:54:58 +08:00
Code Issues Packages Projects Releases Wiki Activity

gh-102856: Tokenize performance improvement (#104731)

Browse Source
This commit is contained in:
Marta Gómez Macías 2023-05-22 02:29:04 +02:00 committed by GitHub
parent 4b107d86f3
commit 8817886ae5
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
2 changed files with 17 additions and 13 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

13
Lib/tokenize.py
View File

@ -449,16 +449,6 @@ def _tokenize(rl_gen, encoding):
source = b"".join(rl_gen).decode(encoding) source = b"".join(rl_gen).decode(encoding)
token = None token = None
for token in _generate_tokens_from_c_tokenizer(source, extra_tokens=True): for token in _generate_tokens_from_c_tokenizer(source, extra_tokens=True):
# TODO: Marta -> limpiar esto
if 6 < token.type <= 54:
token = token._replace(type=OP)
if token.type in {ASYNC, AWAIT}:
token = token._replace(type=NAME)
if token.type == NEWLINE:
l_start, c_start = token.start
l_end, c_end = token.end
token = token._replace(string='\n', start=(l_start, c_start), end=(l_end, c_end+1))
yield token yield token
if token is not None: if token is not None:
last_line, _ = token.start last_line, _ = token.start
@ -550,8 +540,7 @@ def _generate_tokens_from_c_tokenizer(source, extra_tokens=False):
"""Tokenize a source reading Python code as unicode strings using the internal C tokenizer""" """Tokenize a source reading Python code as unicode strings using the internal C tokenizer"""
import _tokenize as c_tokenizer import _tokenize as c_tokenizer
for info in c_tokenizer.TokenizerIter(source, extra_tokens=extra_tokens): for info in c_tokenizer.TokenizerIter(source, extra_tokens=extra_tokens):
tok, type, lineno, end_lineno, col_off, end_col_off, line = info yield TokenInfo._make(info)
yield TokenInfo(type, tok, (lineno, col_off), (end_lineno, end_col_off), line)
if __name__ == "__main__": if __name__ == "__main__":

17
Python/Python-tokenize.c
View File

@ -207,7 +207,22 @@ tokenizeriter_next(tokenizeriterobject *it)
end_col_offset = _PyPegen_byte_offset_to_character_offset(line, token.end - it->tok->line_start); end_col_offset = _PyPegen_byte_offset_to_character_offset(line, token.end - it->tok->line_start);
} }
result = Py_BuildValue("(NinnnnN)", str, type, lineno, end_lineno, col_offset, end_col_offset, line); if (it->tok->tok_extra_tokens) {
// Necessary adjustments to match the original Python tokenize
// implementation
if (type > DEDENT && type < OP) {
type = OP;
}
else if (type == ASYNC || type == AWAIT) {
type = NAME;
}
else if (type == NEWLINE) {
str = PyUnicode_FromString("\n");
end_col_offset++;
}
}
result = Py_BuildValue("(iN(nn)(nn)N)", type, str, lineno, col_offset, end_lineno, end_col_offset, line);
exit: exit:
_PyToken_Free(&token); _PyToken_Free(&token);
return result; return result;