mirrors/cpython
1
0
Fork 0
mirror of https://github.com/python/cpython.git synced 2025-07-28 21:55:21 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 9

bpo-46091: Correctly calculate indentation levels for whitespace lines with continuation characters (GH-30130)

Browse source
This commit is contained in:
Pablo Galindo Salgado 2022-01-25 22:12:14 +00:00 • committed by GitHub
parent b1cb843050
commit a0efc0c196
No known key found for this signature in database
GPG key ID: 4AEE18F83AFDEB23
5 changed files with 165 additions and 16 deletions
Download patch file Download diff file Expand all files Collapse all files

46
Parser/tokenizer.c
View file

@ -1347,6 +1347,24 @@ tok_decimal_tail(struct tok_state *tok)
/* Get next token, after space stripping etc. */
static inline int
tok_continuation_line(struct tok_state *tok) {
int c = tok_nextc(tok);
if (c != '\n') {
tok->done = E_LINECONT;
return -1;
}
c = tok_nextc(tok);
if (c == EOF) {
tok->done = E_EOF;
tok->cur = tok->inp;
return -1;
} else {
tok_backup(tok, c);
}
return c;
}
static int
tok_get(struct tok_state *tok, const char **p_start, const char **p_end)
{
@ -1363,6 +1381,7 @@ tok_get(struct tok_state *tok, const char **p_start, const char **p_end)
int col = 0;
int altcol = 0;
tok->atbol = 0;
int cont_line_col = 0;
for (;;) {
c = tok_nextc(tok);
if (c == ' ') {
@ -1375,14 +1394,23 @@ tok_get(struct tok_state *tok, const char **p_start, const char **p_end)
else if (c == '\014') {/* Control-L (formfeed) */
col = altcol = 0; /* For Emacs users */
}
else if (c == '\\') {
// Indentation cannot be split over multiple physical lines
// using backslashes. This means that if we found a backslash
// preceded by whitespace, **the first one we find** determines
// the level of indentation of whatever comes next.
cont_line_col = cont_line_col ? cont_line_col : col;
if ((c = tok_continuation_line(tok)) == -1) {
return ERRORTOKEN;
}
}
else {
break;
}
}
tok_backup(tok, c);
if (c == '#' || c == '\n' || c == '\\') {
if (c == '#' || c == '\n') {
/* Lines with only whitespace and/or comments
and/or a line continuation character
shouldn't affect the indentation and are
not passed to the parser as NEWLINE tokens,
except *totally* empty lines in interactive
@ -1403,6 +1431,8 @@ tok_get(struct tok_state *tok, const char **p_start, const char **p_end)
may need to skip to the end of a comment */
}
if (!blankline && tok->level == 0) {
col = cont_line_col ? cont_line_col : col;
altcol = cont_line_col ? cont_line_col : altcol;
if (col == tok->indstack[tok->indent]) {
/* No change */
if (altcol != tok->altindstack[tok->indent]) {
@ -1964,19 +1994,9 @@ tok_get(struct tok_state *tok, const char **p_start, const char **p_end)
/* Line continuation */
if (c == '\\') {
c = tok_nextc(tok);
if (c != '\n') {
tok->done = E_LINECONT;
if ((c = tok_continuation_line(tok)) == -1) {
return ERRORTOKEN;
}
c = tok_nextc(tok);
if (c == EOF) {
tok->done = E_EOF;
tok->cur = tok->inp;
return ERRORTOKEN;
} else {
tok_backup(tok, c);
}
tok->cont_line = 1;
goto again; /* Read next line */
}