Merging the py3k-pep3137 branch back into the py3k branch.
No detailed change log; just check out the change log for the py3k-pep3137
branch. The most obvious changes:
- str8 renamed to bytes (PyString at the C level);
- bytes renamed to buffer (PyBytes at the C level);
- PyString and PyUnicode are no longer compatible.
I.e. we now have an immutable bytes type and a mutable bytes type.
The behavior of PyString was modified quite a bit, to make it more
bytes-like. Some changes are still on the to-do list.
diff --git a/Lib/encodings/__init__.py b/Lib/encodings/__init__.py
index 87e5745..d72eae9 100644
--- a/Lib/encodings/__init__.py
+++ b/Lib/encodings/__init__.py
@@ -52,7 +52,7 @@
non-ASCII characters, these must be Latin-1 compatible.
"""
- if isinstance(encoding, str8):
+ if isinstance(encoding, bytes):
encoding = str(encoding, "ascii")
chars = []
punct = False
diff --git a/Lib/encodings/idna.py b/Lib/encodings/idna.py
index b81e5fa..30f507a 100644
--- a/Lib/encodings/idna.py
+++ b/Lib/encodings/idna.py
@@ -151,9 +151,9 @@
raise UnicodeError("unsupported error handling "+errors)
if not input:
- return b"", 0
+ return b'', 0
- result = b""
+ result = buffer()
labels = dots.split(input)
if labels and not labels[-1]:
trailing_dot = b'.'
@@ -165,7 +165,7 @@
# Join with U+002E
result.extend(b'.')
result.extend(ToASCII(label))
- return result+trailing_dot, len(input)
+ return bytes(result+trailing_dot), len(input)
def decode(self, input, errors='strict'):
@@ -216,7 +216,7 @@
if labels:
trailing_dot = b'.'
- result = b""
+ result = buffer()
size = 0
for label in labels:
if size:
@@ -228,7 +228,7 @@
result += trailing_dot
size += len(trailing_dot)
- return (result, size)
+ return (bytes(result), size)
class IncrementalDecoder(codecs.BufferedIncrementalDecoder):
def _buffer_decode(self, input, errors, final):
diff --git a/Lib/encodings/punycode.py b/Lib/encodings/punycode.py
index f08c807..56e6958 100644
--- a/Lib/encodings/punycode.py
+++ b/Lib/encodings/punycode.py
@@ -10,7 +10,7 @@
def segregate(str):
"""3.1 Basic code point segregation"""
- base = b""
+ base = buffer()
extended = set()
for c in str:
if ord(c) < 128:
@@ -18,7 +18,7 @@
else:
extended.add(c)
extended = sorted(extended)
- return (base, extended)
+ return bytes(base), extended
def selective_len(str, max):
"""Return the length of str, considering only characters below max."""
@@ -78,13 +78,13 @@
digits = b"abcdefghijklmnopqrstuvwxyz0123456789"
def generate_generalized_integer(N, bias):
"""3.3 Generalized variable-length integers"""
- result = b""
+ result = buffer()
j = 0
while 1:
t = T(j, bias)
if N < t:
result.append(digits[N])
- return result
+ return bytes(result)
result.append(digits[t + ((N - t) % (36 - t))])
N = (N - t) // (36 - t)
j += 1
@@ -107,13 +107,13 @@
def generate_integers(baselen, deltas):
"""3.4 Bias adaptation"""
# Punycode parameters: initial bias = 72, damp = 700, skew = 38
- result = b""
+ result = buffer()
bias = 72
for points, delta in enumerate(deltas):
s = generate_generalized_integer(delta, bias)
result.extend(s)
bias = adapt(delta, points==0, baselen+points+1)
- return result
+ return bytes(result)
def punycode_encode(text):
base, extended = segregate(text)