bpo-25324: copy tok_name before changing it (#1608)
* add test to check if were modifying token
* copy list so import tokenize doesnt have side effects on token
* shorten line
* add tokenize tokens to token.h to get them to show up in token
* move ERRORTOKEN back to its previous location, and fix nitpick
* copy comments from token.h automatically
* fix whitespace and make more pythonic
* change to fix comments from @haypo
* update token.rst and Misc/NEWS
* change wording
* some more wording changes
diff --git a/Lib/token.py b/Lib/token.py
index 5fdb222..091f80b 100644
--- a/Lib/token.py
+++ b/Lib/token.py
@@ -63,11 +63,17 @@
ATEQUAL = 50
RARROW = 51
ELLIPSIS = 52
+# Don't forget to update the table _PyParser_TokenNames in tokenizer.c!
OP = 53
AWAIT = 54
ASYNC = 55
ERRORTOKEN = 56
-N_TOKENS = 57
+# These aren't used by the C tokenizer but are needed for tokenize.py
+COMMENT = 57
+NL = 58
+ENCODING = 59
+N_TOKENS = 60
+# Special definitions for cooperation with parser
NT_OFFSET = 256
#--end constants--
@@ -102,15 +108,26 @@
with fp:
lines = fp.read().split("\n")
prog = re.compile(
- "#define[ \t][ \t]*([A-Z0-9][A-Z0-9_]*)[ \t][ \t]*([0-9][0-9]*)",
+ r"#define[ \t][ \t]*([A-Z0-9][A-Z0-9_]*)[ \t][ \t]*([0-9][0-9]*)",
re.IGNORECASE)
+ comment_regex = re.compile(
+ r"^\s*/\*\s*(.+?)\s*\*/\s*$",
+ re.IGNORECASE)
+
tokens = {}
+ prev_val = None
for line in lines:
match = prog.match(line)
if match:
name, val = match.group(1, 2)
val = int(val)
- tokens[val] = name # reverse so we can sort them...
+ tokens[val] = {'token': name} # reverse so we can sort them...
+ prev_val = val
+ else:
+ comment_match = comment_regex.match(line)
+ if comment_match and prev_val is not None:
+ comment = comment_match.group(1)
+ tokens[prev_val]['comment'] = comment
keys = sorted(tokens.keys())
# load the output skeleton from the target:
try:
@@ -127,8 +144,10 @@
sys.stderr.write("target does not contain format markers")
sys.exit(3)
lines = []
- for val in keys:
- lines.append("%s = %d" % (tokens[val], val))
+ for key in keys:
+ lines.append("%s = %d" % (tokens[key]["token"], key))
+ if "comment" in tokens[key]:
+ lines.append("# %s" % tokens[key]["comment"])
format[start:end] = lines
try:
fp = open(outFileName, 'w')