summaryrefslogtreecommitdiffstats
path: root/Parser/tokenizer.h
diff options
context:
space:
mode:
authorBrett Cannon <bcannon@gmail.com>2008-10-17 03:38:50 (GMT)
committerBrett Cannon <bcannon@gmail.com>2008-10-17 03:38:50 (GMT)
commitda780432378e6298463889557ab43e0c156758cd (patch)
treedc622a9b62874851f90abc45524d3d2653cab9ba /Parser/tokenizer.h
parent9e9dcd6d4225faa6a8b19120f009e0253d16ab92 (diff)
downloadcpython-da780432378e6298463889557ab43e0c156758cd.zip
cpython-da780432378e6298463889557ab43e0c156758cd.tar.gz
cpython-da780432378e6298463889557ab43e0c156758cd.tar.bz2
Latin-1 source code was not being properly decoded when passed through
compile(). This was due to left-over special-casing before UTF-8 became the default source encoding. Closes issue #3574. Thanks to Victor Stinner for help with the patch.
Diffstat (limited to 'Parser/tokenizer.h')
-rw-r--r--Parser/tokenizer.h4
1 files changed, 2 insertions, 2 deletions
diff --git a/Parser/tokenizer.h b/Parser/tokenizer.h
index c45dea1..df9cbc7 100644
--- a/Parser/tokenizer.h
+++ b/Parser/tokenizer.h
@@ -49,14 +49,14 @@ struct tok_state {
enum decoding_state decoding_state;
int decoding_erred; /* whether erred in decoding */
int read_coding_spec; /* whether 'coding:...' has been read */
- char *encoding;
+ char *encoding; /* Source encoding. */
int cont_line; /* whether we are in a continuation line. */
const char* line_start; /* pointer to start of current line */
#ifndef PGEN
PyObject *decoding_readline; /* codecs.open(...).readline */
PyObject *decoding_buffer;
#endif
- const char* enc;
+ const char* enc; /* Encoding for the current str. */
const char* str;
};