Mirror
/
cpython
mirror of https://github.com/python/cpython
4
1
Fork 0
Code Issues Releases Wiki Activity

gh-105259: Ensure we don't show newline characters for trailing NEWLINE tokens (#105364)

This commit is contained in:
Pablo Galindo Salgado 2023-06-06 13:52:16 +02:00 committed by GitHub
parent 0202aa002e
commit c0a6ed3934
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
5 changed files with 17 additions and 5 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
Lib/test/test_tokenize.py
View File

@ -1870,7 +1870,7 @@ class CTokenizeTest(TestCase):
TokenInfo(type=NUMBER, string='1', start=(1, 0), end=(1, 1), line='1+1\n'),
TokenInfo(type=OP, string='+', start=(1, 1), end=(1, 2), line='1+1\n'),
TokenInfo(type=NUMBER, string='1', start=(1, 2), end=(1, 3), line='1+1\n'),
TokenInfo(type=NEWLINE, string='\n', start=(1, 3), end=(1, 4), line='1+1\n'),
TokenInfo(type=NEWLINE, string='', start=(1, 3), end=(1, 4), line='1+1\n'),
TokenInfo(type=ENDMARKER, string='', start=(2, 0), end=(2, 0), line='')
]
for encoding in ["utf-8", "latin-1", "utf-16"]:

2
Misc/NEWS.d/next/Core and Builtins/2023-06-06-11-37-53.gh-issue-105259.E2BGKL.rst Normal file
View File

@ -0,0 +1,2 @@
Don't include newline character for trailing ``NEWLINE`` tokens emitted in
the :mod:`tokenize` module. Patch by Pablo Galindo

7
Parser/tokenizer.c
View File

@ -114,6 +114,7 @@ tok_new(void)
tok->report_warnings = 1;
tok->tok_extra_tokens = 0;
tok->comment_newline = 0;
tok->implicit_newline = 0;
tok->tok_mode_stack[0] = (tokenizer_mode){.kind =TOK_REGULAR_MODE, .f_string_quote='\0', .f_string_quote_size = 0, .f_string_debug=0};
tok->tok_mode_stack_index = 0;
tok->tok_report_warnings = 1;
@ -355,10 +356,12 @@ tok_concatenate_interactive_new_line(struct tok_state *tok, const char *line) {
return -1;
}
strcpy(new_str + current_size, line);
tok->implicit_newline = 0;
if (last_char != '\n') {
/* Last line does not end in \n, fake one */
new_str[current_size + line_size - 1] = '\n';
new_str[current_size + line_size] = '\0';
tok->implicit_newline = 1;
}
tok->interactive_src_start = new_str;
tok->interactive_src_end = new_str + current_size + line_size;
@ -1262,11 +1265,13 @@ tok_underflow_file(struct tok_state *tok) {
tok->done = E_EOF;
return 0;
}
tok->implicit_newline = 0;
if (tok->inp[-1] != '\n') {
assert(tok->inp + 1 < tok->end);
/* Last line does not end in \n, fake one */
*tok->inp++ = '\n';
*tok->inp = '\0';
tok->implicit_newline = 1;
}
ADVANCE_LINENO();
@ -1304,11 +1309,13 @@ tok_underflow_readline(struct tok_state* tok) {
tok->done = E_EOF;
return 0;
}
tok->implicit_newline = 0;
if (tok->inp[-1] != '\n') {
assert(tok->inp + 1 < tok->end);
/* Last line does not end in \n, fake one */
*tok->inp++ = '\n';
*tok->inp = '\0';
tok->implicit_newline = 1;
}
ADVANCE_LINENO();

1
Parser/tokenizer.h
View File

@ -131,6 +131,7 @@ struct tok_state {
int tok_report_warnings;
int tok_extra_tokens;
int comment_newline;
int implicit_newline;
#ifdef Py_DEBUG
int debug;
#endif

10
Python/Python-tokenize.c
View File

@ -243,10 +243,12 @@ tokenizeriter_next(tokenizeriterobject *it)
}
else if (type == NEWLINE) {
Py_DECREF(str);
if (it->tok->start[0] == '\r') {
str = PyUnicode_FromString("\r\n");
} else {
str = PyUnicode_FromString("\n");
if (!it->tok->implicit_newline) {
if (it->tok->start[0] == '\r') {
str = PyUnicode_FromString("\r\n");
} else {
str = PyUnicode_FromString("\n");
}
}
end_col_offset++;
}