Mercurial > public > mercurial-scm > hg
diff mercurial/__init__.py @ 30051:3139ec39b505
py3: handle multiple arguments in .encode() and .decode()
There is a case and more can be present where these functions have
multiple arguments. Our transformer used to handle the first argument, so
added a loop to handle more arguments if present.
| author | Pulkit Goyal <7895pulkit@gmail.com> |
|---|---|
| date | Fri, 07 Oct 2016 14:04:49 +0200 |
| parents | 178c89e8519a |
| children | eaaedad68011 |
line wrap: on
line diff
--- a/mercurial/__init__.py Fri Oct 07 12:13:28 2016 +0200 +++ b/mercurial/__init__.py Fri Oct 07 14:04:49 2016 +0200 @@ -278,21 +278,30 @@ # .encode() and .decode() on str/bytes/unicode don't accept # byte strings on Python 3. Rewrite the token to include the # unicode literal prefix so the string transformer above doesn't - # add the byte prefix. + # add the byte prefix. The loop helps in handling multiple + # arguments. if (fn in ('encode', 'decode') and prevtoken.type == token.OP and prevtoken.string == '.'): # (OP, '.') # (NAME, 'encode') # (OP, '(') + # [(VARIABLE, encoding)] + # [(OP, '.')] + # [(VARIABLE, encoding)] + # [(OP, ',')] # (STRING, 'utf-8') # (OP, ')') + j = i try: - st = tokens[i + 2] - if (st.type == token.STRING and - st.string[0] in ("'", '"')): - rt = tokenize.TokenInfo(st.type, 'u%s' % st.string, + while (tokens[j + 1].string in ('(', ',', '.')): + st = tokens[j + 2] + if (st.type == token.STRING and + st.string[0] in ("'", '"')): + rt = tokenize.TokenInfo(st.type, + 'u%s' % st.string, st.start, st.end, st.line) - tokens[i + 2] = rt + tokens[j + 2] = rt + j = j + 2 except IndexError: pass @@ -303,7 +312,7 @@ # ``replacetoken`` or any mechanism that changes semantics of module # loading is changed. Otherwise cached bytecode may get loaded without # the new transformation mechanisms applied. - BYTECODEHEADER = b'HG\x00\x02' + BYTECODEHEADER = b'HG\x00\x03' class hgloader(importlib.machinery.SourceFileLoader): """Custom module loader that transforms source code.