summaryrefslogtreecommitdiffstats
path: root/Parser
diff options
context:
space:
mode:
authorPablo Galindo Salgado <Pablogsal@gmail.com>2021-11-14 01:06:41 (GMT)
committerGitHub <noreply@github.com>2021-11-14 01:06:41 (GMT)
commit25835c518aa7446f3680b62c1fb43827e0f190d9 (patch)
tree42aaedbf01d1b90eeb5987c7920d52db9bed2235 /Parser
parentf8da00ef04fdadf7cd9821e8ec4b317ecf3ed663 (diff)
downloadcpython-25835c518aa7446f3680b62c1fb43827e0f190d9.zip
cpython-25835c518aa7446f3680b62c1fb43827e0f190d9.tar.gz
cpython-25835c518aa7446f3680b62c1fb43827e0f190d9.tar.bz2
bpo-45738: Fix computation of error location for invalid continuation (GH-29550)
characters in the parser
Diffstat (limited to 'Parser')
-rw-r--r--Parser/pegen.c15
-rw-r--r--Parser/tokenizer.c1
2 files changed, 5 insertions, 11 deletions
diff --git a/Parser/pegen.c b/Parser/pegen.c
index b00eff3..8a3f740 100644
--- a/Parser/pegen.c
+++ b/Parser/pegen.c
@@ -351,14 +351,7 @@ tokenizer_error(Parser *p)
msg = "too many levels of indentation";
break;
case E_LINECONT: {
- char* loc = strrchr(p->tok->buf, '\n');
- const char* last_char = p->tok->cur - 1;
- if (loc != NULL && loc != last_char) {
- col_offset = p->tok->cur - loc - 1;
- p->tok->buf = loc;
- } else {
- col_offset = last_char - p->tok->buf - 1;
- }
+ col_offset = p->tok->cur - p->tok->buf - 1;
msg = "unexpected character after line continuation character";
break;
}
@@ -366,7 +359,9 @@ tokenizer_error(Parser *p)
msg = "unknown parsing error";
}
- RAISE_ERROR_KNOWN_LOCATION(p, errtype, p->tok->lineno, col_offset, p->tok->lineno, -1, msg);
+ RAISE_ERROR_KNOWN_LOCATION(p, errtype, p->tok->lineno,
+ col_offset >= 0 ? col_offset : 0,
+ p->tok->lineno, -1, msg);
return -1;
}
@@ -497,7 +492,7 @@ _PyPegen_raise_error_known_location(Parser *p, PyObject *errtype,
does not physically exist */
assert(p->tok->fp == NULL || p->tok->fp == stdin || p->tok->done == E_EOF || !uses_utf8_codec);
- if (p->tok->lineno <= lineno) {
+ if (p->tok->lineno <= lineno && p->tok->inp > p->tok->buf) {
Py_ssize_t size = p->tok->inp - p->tok->buf;
error_line = PyUnicode_DecodeUTF8(p->tok->buf, size, "replace");
}
diff --git a/Parser/tokenizer.c b/Parser/tokenizer.c
index 8a19458..f281c42 100644
--- a/Parser/tokenizer.c
+++ b/Parser/tokenizer.c
@@ -1970,7 +1970,6 @@ tok_get(struct tok_state *tok, const char **p_start, const char **p_end)
c = tok_nextc(tok);
if (c != '\n') {
tok->done = E_LINECONT;
- tok->cur = tok->inp;
return ERRORTOKEN;
}
c = tok_nextc(tok);