Author: fijal
Branch: unicode-utf8
Changeset: r93264:f312060a4a01
Date: 2017-12-03 16:27 +0100
http://bitbucket.org/pypy/pypy/changeset/f312060a4a01/
Log: fix the warnings module, add we_are_translated for now
diff --git a/pypy/module/_rawffi/interp_rawffi.py
b/pypy/module/_rawffi/interp_rawffi.py
--- a/pypy/module/_rawffi/interp_rawffi.py
+++ b/pypy/module/_rawffi/interp_rawffi.py
@@ -596,9 +596,9 @@
return space.w_None
wcharp_addr = rffi.cast(rffi.CWCHARP, address)
if maxlength == -1:
- s = rffi.wcharp2unicode(wcharp_addr)
+ s = rffi.wcharp2utf8(wcharp_addr)
else:
- s = rffi.wcharp2unicoden(wcharp_addr, maxlength)
+ s = rffi.wcharpsize2utf8(wcharp_addr, maxlength)
return space.newunicode(s)
@unwrap_spec(address=r_uint, maxlength=int)
diff --git a/pypy/module/_warnings/interp_warnings.py
b/pypy/module/_warnings/interp_warnings.py
--- a/pypy/module/_warnings/interp_warnings.py
+++ b/pypy/module/_warnings/interp_warnings.py
@@ -1,3 +1,6 @@
+
+from rpython.rlib import rutf8
+
from pypy.interpreter.gateway import unwrap_spec, WrappedDefault
from pypy.interpreter.error import OperationError, oefmt
@@ -208,10 +211,11 @@
except OperationError as e:
if e.async(space):
raise
- message = u"%s:%d: %s: %s\n" % (space.unicode_w(w_filename), lineno,
- space.unicode_w(w_name),
- space.unicode_w(w_text))
- w_message = space.newunicode(message)
+ message = "%s:%d: %s: %s\n" % (space.utf8_w(w_filename), lineno,
+ space.utf8_w(w_name),
+ space.utf8_w(w_text))
+ lgt, flag = rutf8.check_utf8(message, True)
+ w_message = space.newutf8(message, lgt, flag)
else:
w_message = space.newtext(message)
space.call_method(w_stderr, "write", w_message)
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
@@ -49,14 +49,15 @@
self._index_storage = rutf8.null_storage()
# XXX checking, remove before any performance measurments
# ifdef not_running_in_benchmark
- lgt, flag_check = rutf8.check_utf8(utf8str, True)
- assert lgt == length
- if flag_check == rutf8.FLAG_ASCII:
- # there are cases where we copy part of REULAR that happens
- # to be ascii
- assert flag in (rutf8.FLAG_ASCII, rutf8.FLAG_REGULAR)
- else:
- assert flag == flag_check
+ if not we_are_translated():
+ lgt, flag_check = rutf8.check_utf8(utf8str, True)
+ assert lgt == length
+ if flag_check == rutf8.FLAG_ASCII:
+ # there are cases where we copy part of REULAR that happens
+ # to be ascii
+ assert flag in (rutf8.FLAG_ASCII, rutf8.FLAG_REGULAR)
+ else:
+ assert flag == flag_check
# the storage can be one of:
# - null, unicode with no surrogates
# - rutf8.UTF8_HAS_SURROGATES
@@ -1173,7 +1174,7 @@
s = space.charbuf_w(w_obj)
unicodehelper.check_ascii_or_raise(space, s)
return space.newutf8(s, len(s), rutf8.FLAG_ASCII)
- if encoding == 'utf-8':
+ if encoding == 'utf-8' or encoding == 'utf8':
s = space.charbuf_w(w_obj)
lgt, flag = unicodehelper.check_utf8_or_raise(space, s)
return space.newutf8(s, lgt, flag)
diff --git a/rpython/rtyper/lltypesystem/rffi.py
b/rpython/rtyper/lltypesystem/rffi.py
--- a/rpython/rtyper/lltypesystem/rffi.py
+++ b/rpython/rtyper/lltypesystem/rffi.py
@@ -1019,7 +1019,7 @@
s = StringBuilder(size)
for i in range(size):
rutf8.unichr_as_utf8_append(s, ord(w[i]))
- return s.build()
+ return s.build()
def utf82wcharp(utf8, utf8len):
from rpython.rlib import rutf8
_______________________________________________
pypy-commit mailing list
pypy-commit@python.org
https://mail.python.org/mailman/listinfo/pypy-commit
