Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

[3.12] gh-105259: Ensure we don't show newline characters for trailing NEWLINE tokens (GH-105364) #105367

Merged
merged 1 commit into from
Jun 6, 2023
Merged

[3.12] gh-105259: Ensure we don't show newline characters for trailing NEWLINE tokens (GH-105364) #105367

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
2 changes: 1 addition & 1 deletion Lib/test/test_tokenize.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1870,7 +1870,7 @@ def readline(encoding):
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"]:
Expand Down
2 changes: 2 additions & 0 deletions Misc/NEWS.d/next/Core and Builtins/2023-06-06-11-37-53.gh-issue-105259.E2BGKL.rst
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,2 @@
Don't include newline character for trailing ``NEWLINE`` tokens emitted in
the :mod:`tokenize` module. Patch by Pablo Galindo
7 changes: 7 additions & 0 deletions Parser/tokenizer.c
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -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;
Expand Down Expand Up @@ -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;
Expand Down Expand Up @@ -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();
Expand Down Expand Up @@ -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();
Expand Down
1 change: 1 addition & 0 deletions Parser/tokenizer.h
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -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
Expand Down
10 changes: 6 additions & 4 deletions Python/Python-tokenize.c
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -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++;
}
Expand Down