Author: Matti Picus <[email protected]>
Branch: unicode-utf8-py3
Changeset: r95136:fa0322eb4ef4
Date: 2018-09-17 08:04 +0300
http://bitbucket.org/pypy/pypy/changeset/fa0322eb4ef4/
Log: merge heads
diff --git a/README.rst b/README.rst
--- a/README.rst
+++ b/README.rst
@@ -4,7 +4,7 @@
Welcome to PyPy!
-PyPy is an interperter that implements the Python programming language, based
+PyPy is an interpreter that implements the Python programming language, based
on the RPython compiler framework for dynamic language implementations.
The home page for the interpreter is:
@@ -15,29 +15,29 @@
http://doc.pypy.org/
-More documentation about the RPython framework can be found here
+More documentation about the RPython framework can be found here:
- http://rpython.readthedocs.io
+ http://rpython.readthedocs.io/
-The source for the documentation is in the pypy/doc directory
+The source for the documentation is in the pypy/doc directory.
+
Using PyPy instead of CPython
-=============================
+-----------------------------
-Please read the information at http://pypy.org to find the correct way to
+Please read the information at http://pypy.org/ to find the correct way to
download and use PyPy as an alternative to CPython.
+
Building
-========
+--------
Building PyPy is not the recommended way to obtain the PyPy alternative python
interpreter. It is time-consuming and requires significant computing resources.
-More information can be found here
+More information can be found here:
http://doc.pypy.org/en/latest/build.html
Enjoy and send us feedback!
the pypy-dev team <[email protected]>
-
-
diff --git a/pypy/interpreter/unicodehelper.py
b/pypy/interpreter/unicodehelper.py
--- a/pypy/interpreter/unicodehelper.py
+++ b/pypy/interpreter/unicodehelper.py
@@ -282,7 +282,7 @@
pos = rutf8._pos_at_index(s, newindex)
return result.build()
-def utf8_encode_ascii(s, errors, errorhandler):
+def utf8_encode_ascii(s, errors, errorhandler, allow_surrogates=False):
""" Don't be confused - this is a slowpath for errors e.g. "ignore"
or an obscure errorhandler
"""
@@ -1200,14 +1200,15 @@
else:
res_8, newindex = errorhandler(
errors, public_encoding_name, 'surrogates not allowed',
- s, pos - 1, pos)
- for cp in rutf8.Utf8StringIterator(res_8):
- if cp < 0xD800:
+ s, pos, pos+1)
+ #for cp in rutf8.Utf8StringIterator(res_8):
+ for cp in res_8:
+ if cp < 0xD800 or allow_surrogates:
_STORECHAR(result, cp, byteorder)
else:
errorhandler('strict', public_encoding_name,
'surrogates not allowed',
- s, pos-1, pos)
+ s, pos, pos+1)
if index != newindex: # Should be uncommon
index = newindex
pos = rutf8._pos_at_index(s, newindex)
diff --git a/pypy/module/_cffi_backend/ctypeptr.py
b/pypy/module/_cffi_backend/ctypeptr.py
--- a/pypy/module/_cffi_backend/ctypeptr.py
+++ b/pypy/module/_cffi_backend/ctypeptr.py
@@ -313,9 +313,7 @@
if isinstance(self.ctitem, ctypeprim.W_CTypePrimitiveBool):
self._must_be_string_of_zero_or_one(value)
keepalives[i] = value
- buf, buf_flag = rffi.get_nonmovingbuffer_final_null(value)
- rffi.cast(rffi.CCHARPP, cdata)[0] = buf
- return ord(buf_flag) # 4, 5 or 6
+ return misc.write_string_as_charp(cdata, value)
#
if (space.isinstance_w(w_init, space.w_list) or
space.isinstance_w(w_init, space.w_tuple)):
diff --git a/pypy/module/_cffi_backend/misc.py
b/pypy/module/_cffi_backend/misc.py
--- a/pypy/module/_cffi_backend/misc.py
+++ b/pypy/module/_cffi_backend/misc.py
@@ -3,7 +3,7 @@
from pypy.interpreter.error import OperationError, oefmt
from rpython.rlib import jit
-from rpython.rlib.objectmodel import specialize
+from rpython.rlib.objectmodel import specialize, we_are_translated
from rpython.rlib.rarithmetic import r_uint, r_ulonglong
from rpython.rlib.unroll import unrolling_iterable
from rpython.rtyper.lltypesystem import lltype, llmemory, rffi
@@ -102,6 +102,12 @@
def write_raw_longdouble_data(target, source):
rffi.cast(rffi.LONGDOUBLEP, target)[0] = source
[email protected]_look_inside # lets get_nonmovingbuffer_final_null be inlined
+def write_string_as_charp(target, string):
+ buf, buf_flag = rffi.get_nonmovingbuffer_final_null(string)
+ rffi.cast(rffi.CCHARPP, target)[0] = buf
+ return ord(buf_flag) # 4, 5 or 6
+
# ____________________________________________________________
sprintf_longdouble = rffi.llexternal(
@@ -129,21 +135,14 @@
# This version accepts a Python int too, and does convertions from
# other types of objects. It refuses floats.
try:
- value = space.int_w(w_ob)
+ return space.int_w(w_ob, allow_conversion=False)
except OperationError as e:
if not (e.match(space, space.w_OverflowError) or
e.match(space, space.w_TypeError)):
raise
- else:
- return value
- try:
- bigint = space.bigint_w(w_ob, allow_conversion=False)
- except OperationError as e:
- if not e.match(space, space.w_TypeError):
- raise
if _is_a_float(space, w_ob):
raise
- bigint = space.bigint_w(space.int(w_ob), allow_conversion=False)
+ bigint = space.bigint_w(w_ob, allow_conversion=True)
try:
return bigint.tolonglong()
except OverflowError:
@@ -151,20 +150,15 @@
def as_long(space, w_ob):
# Same as as_long_long(), but returning an int instead.
- if space.is_w(space.type(w_ob), space.w_int): # shortcut
- return space.int_w(w_ob)
try:
- bigint = space.bigint_w(w_ob, allow_conversion=False)
+ return space.int_w(w_ob, allow_conversion=False)
except OperationError as e:
- if not e.match(space, space.w_TypeError):
+ if not (e.match(space, space.w_OverflowError) or
+ e.match(space, space.w_TypeError)):
raise
if _is_a_float(space, w_ob):
raise
- bigint = space.bigint_w(space.int(w_ob), allow_conversion=False)
- try:
- return bigint.toint()
- except OverflowError:
- raise OperationError(space.w_OverflowError, space.newtext(ovf_msg))
+ return space.int_w(w_ob, allow_conversion=True)
def as_unsigned_long_long(space, w_ob, strict):
# (possibly) convert and cast a Python object to an unsigned long long.
@@ -172,23 +166,19 @@
# objects. If 'strict', complains with OverflowError; if 'not strict',
# mask the result and round floats.
try:
- value = space.int_w(w_ob)
+ value = space.int_w(w_ob, allow_conversion=False)
except OperationError as e:
if not (e.match(space, space.w_OverflowError) or
e.match(space, space.w_TypeError)):
raise
+ if strict and _is_a_float(space, w_ob):
+ raise
else:
if strict and value < 0:
raise OperationError(space.w_OverflowError, space.newtext(neg_msg))
return r_ulonglong(value)
- try:
- bigint = space.bigint_w(w_ob, allow_conversion=False)
- except OperationError as e:
- if not e.match(space, space.w_TypeError):
- raise
- if strict and _is_a_float(space, w_ob):
- raise
- bigint = space.bigint_w(space.int(w_ob), allow_conversion=False)
+ # note that if not 'strict', then space.int() will round down floats
+ bigint = space.bigint_w(space.int(w_ob), allow_conversion=False)
if strict:
try:
return bigint.toulonglong()
@@ -202,13 +192,19 @@
def as_unsigned_long(space, w_ob, strict):
# same as as_unsigned_long_long(), but returning just an Unsigned
try:
- bigint = space.bigint_w(w_ob, allow_conversion=False)
+ value = space.int_w(w_ob, allow_conversion=False)
except OperationError as e:
- if not e.match(space, space.w_TypeError):
+ if not (e.match(space, space.w_OverflowError) or
+ e.match(space, space.w_TypeError)):
raise
if strict and _is_a_float(space, w_ob):
raise
- bigint = space.bigint_w(space.int(w_ob), allow_conversion=False)
+ else:
+ if strict and value < 0:
+ raise OperationError(space.w_OverflowError, space.newtext(neg_msg))
+ return r_uint(value)
+ # note that if not 'strict', then space.int() will round down floats
+ bigint = space.bigint_w(space.int(w_ob), allow_conversion=False)
if strict:
try:
return bigint.touint()
@@ -241,7 +237,12 @@
def _standard_object_as_bool(space, w_ob):
if space.isinstance_w(w_ob, space.w_int):
- return space.bigint_w(w_ob).tobool()
+ try:
+ return space.int_w(w_ob) != 0
+ except OperationError as e:
+ if not e.match(space, space.w_OverflowError):
+ raise
+ return space.bigint_w(w_ob).tobool()
if space.isinstance_w(w_ob, space.w_float):
return space.float_w(w_ob) != 0.0
raise _NotStandardObject
diff --git a/pypy/module/_cffi_backend/test/_backend_test_c.py
b/pypy/module/_cffi_backend/test/_backend_test_c.py
--- a/pypy/module/_cffi_backend/test/_backend_test_c.py
+++ b/pypy/module/_cffi_backend/test/_backend_test_c.py
@@ -334,8 +334,18 @@
max = (1 << (8*size-1)) - 1
assert newp(pp, min)[0] == min
assert newp(pp, max)[0] == max
+ py.test.raises(OverflowError, newp, pp, min - 2 ** 32)
+ py.test.raises(OverflowError, newp, pp, min - 2 ** 64)
+ py.test.raises(OverflowError, newp, pp, max + 2 ** 32)
+ py.test.raises(OverflowError, newp, pp, max + 2 ** 64)
py.test.raises(OverflowError, newp, pp, min - 1)
py.test.raises(OverflowError, newp, pp, max + 1)
+ py.test.raises(OverflowError, newp, pp, min - 1 - 2 ** 32)
+ py.test.raises(OverflowError, newp, pp, min - 1 - 2 ** 64)
+ py.test.raises(OverflowError, newp, pp, max + 1)
+ py.test.raises(OverflowError, newp, pp, max + 1 + 2 ** 32)
+ py.test.raises(OverflowError, newp, pp, max + 1 + 2 ** 64)
+ py.test.raises(TypeError, newp, pp, 1.0)
for name in ['char', 'short', 'int', 'long', 'long long']:
p = new_primitive_type('unsigned ' + name)
pp = new_pointer_type(p)
diff --git a/pypy/module/_codecs/interp_codecs.py
b/pypy/module/_codecs/interp_codecs.py
--- a/pypy/module/_codecs/interp_codecs.py
+++ b/pypy/module/_codecs/interp_codecs.py
@@ -649,9 +649,13 @@
w_arg = space.convert_arg_to_w_unicode(w_arg, errors)
if errors is None:
errors = 'strict'
+ allow_surrogates = False
+ if errors in ('surrogatepass',):
+ allow_surrogates = True
state = space.fromcache(CodecState)
ulen = w_arg._length
- result = func(w_arg._utf8, errors, state.encode_error_handler)
+ result = func(w_arg._utf8, errors, state.encode_error_handler,
+ allow_surrogates=allow_surrogates)
return space.newtuple([space.newbytes(result), space.newint(ulen)])
wrap_encoder.__name__ = func.__name__
globals()[name] = wrap_encoder
diff --git a/pypy/objspace/std/unicodeobject.py
b/pypy/objspace/std/unicodeobject.py
--- a/pypy/objspace/std/unicodeobject.py
+++ b/pypy/objspace/std/unicodeobject.py
@@ -1170,7 +1170,7 @@
first = u[0]
it = rutf8.Utf8StringIterator(u)
code = it.next()
- if not (unicodedb.isxidstart(code) or first == u'_'):
+ if not (unicodedb.isxidstart(code) or first == '_'):
return False
for ch in it:
_______________________________________________
pypy-commit mailing list
[email protected]
https://mail.python.org/mailman/listinfo/pypy-commit
