diff options
| author | Ka-Ping Yee <ping@zesty.ca> | 2001-03-23 05:22:49 (GMT) |
|---|---|---|
| committer | Ka-Ping Yee <ping@zesty.ca> | 2001-03-23 05:22:49 (GMT) |
| commit | 28c62bbdb2545eddf04ba7e2f2daa0dcedbb6052 (patch) | |
| tree | 756f462453c72ddf29a2e48039780cafd96c8789 /Lib | |
| parent | ce7298ab42f40c079092fb79bec7d02c1175e99c (diff) | |
| download | cpython-28c62bbdb2545eddf04ba7e2f2daa0dcedbb6052.zip cpython-28c62bbdb2545eddf04ba7e2f2daa0dcedbb6052.tar.gz cpython-28c62bbdb2545eddf04ba7e2f2daa0dcedbb6052.tar.bz2 | |
Provide a StopTokenizing exception for conveniently exiting the loop.
Diffstat (limited to 'Lib')
| -rw-r--r-- | Lib/tokenize.py | 21 |
1 files changed, 11 insertions, 10 deletions
diff --git a/Lib/tokenize.py b/Lib/tokenize.py index e0e902b..2af595d 100644 --- a/Lib/tokenize.py +++ b/Lib/tokenize.py @@ -26,12 +26,6 @@ NL = N_TOKENS + 1 tok_name[NL] = 'NL' N_TOKENS += 2 -# Changes from 1.3: -# Ignore now accepts \f as whitespace. Operator now includes '**'. -# Ignore and Special now accept \n or \r\n at the end of a line. -# Imagnumber is new. Expfloat is corrected to reject '0e4'. -# Note: to quote a backslash in a regex, it must be doubled in a r'aw' string. - def group(*choices): return '(' + '|'.join(choices) + ')' def any(*choices): return apply(group, choices) + '*' def maybe(*choices): return apply(group, choices) + '?' @@ -103,14 +97,21 @@ endprogs = {"'": re.compile(Single), '"': re.compile(Double), tabsize = 8 -class TokenError(Exception): - pass +class TokenError(Exception): pass + +class StopTokenizing(Exception): pass def printtoken(type, token, (srow, scol), (erow, ecol), line): # for testing print "%d,%d-%d,%d:\t%s\t%s" % \ (srow, scol, erow, ecol, tok_name[type], repr(token)) def tokenize(readline, tokeneater=printtoken): + try: + tokenize_loop(readline, tokeneater) + except StopTokenizing: + pass + +def tokenize_loop(readline, tokeneater): lnum = parenlev = continued = 0 namechars, numchars = string.letters + '_', string.digits contstr, needcont = '', 0 @@ -178,8 +179,8 @@ def tokenize(readline, tokeneater=printtoken): spos, epos, pos = (lnum, start), (lnum, end), end token, initial = line[start:end], line[start] - if initial in numchars \ - or (initial == '.' and token != '.'): # ordinary number + if initial in numchars or \ + (initial == '.' and token != '.'): # ordinary number tokeneater(NUMBER, token, spos, epos, line) elif initial in '\r\n': tokeneater(parenlev > 0 and NL or NEWLINE, |