[pypy-commit] pypy unicode-utf8: disable speedups for now

[fijal]

Author: fijal
Branch: unicode-utf8
Changeset: r90570:3e38274ddd35
Date: 2017-03-05 19:42 +0400
http://bitbucket.org/pypy/pypy/changeset/3e38274ddd35/

Log:	disable speedups for now

diff --git a/pypy/module/_pypyjson/interp_decoder.py b/pypy/module/_pypyjson/interp_decoder.py
--- a/pypy/module/_pypyjson/interp_decoder.py
+++ b/pypy/module/_pypyjson/interp_decoder.py
@@ -295,7 +295,7 @@
             i += 1
             bits |= ord(ch)
             if ch == '"':
-                if bits & 0x80:
+                if 1 or bits & 0x80:
                     # the 8th bit is set, it's an utf8 strnig
                     content_utf8 = self.getslice(start, i-1)
                     content_unicode = unicodehelper.decode_utf8(self.space, content_utf8)
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
@@ -20,6 +20,7 @@
 from pypy.objspace.std.formatting import mod_format
 from pypy.objspace.std.stringmethods import StringMethods
 from pypy.objspace.std.util import IDTAG_SPECIAL, IDTAG_SHIFT
+from pypy.objspace.std.sliceobject import unwrap_start_stop
 
 __all__ = ['W_UnicodeObject', 'wrapunicode', 'plain_str2unicode',
            'encode_object', 'decode_object', 'unicode_from_object',
@@ -75,6 +76,13 @@
             uid = (base << IDTAG_SHIFT) | IDTAG_SPECIAL
         return space.newint(uid)
 
+    def _convert_idx_params_unicode(self, space, w_start, w_end):
+        """ Specialcase this for unicode - one less element in the tuple
+        """
+        lenself = self._len()
+        start, end = unwrap_start_stop(space, lenself, w_start, w_end)
+        return start, end
+
     def str_w(self, space):
         return space.text_w(space.str(self))
 
@@ -125,8 +133,8 @@
         return rutf8.compute_length_utf8(self._utf8)
 
     def _val(self, space):
-        #import pdb
-        #pdb.set_trace()
+        import pdb
+        pdb.set_trace()
         return self._utf8.decode('utf8')
 
     @staticmethod
@@ -446,9 +454,6 @@
             i = rutf8.next_codepoint_pos(val, i)
         return space.newbool(cased)
 
-    def _starts_ends_overflow(self, prefix):
-        return len(prefix) == 0
-
     def descr_add(self, space, w_other):
         try:
             w_other = self.convert_arg_to_w_unicode(space, w_other)
@@ -722,6 +727,26 @@
         assert rpos >= lpos    # annotator hint, don't remove
         return self._utf8_sliced(lpos, rpos, lgt)
 
+    def descr_startswith(self, space, w_prefix, w_start=None, w_end=None):
+        (start, end) = self._convert_idx_params_unicode(space, w_start, w_end)
+        if space.isinstance_w(w_prefix, space.w_tuple):
+            return self._startswith_tuple(space, w_prefix, start, end)
+        return space.newbool(self._startswith(space, w_prefix, start, end))
+
+    def _startswith_tuple(self, space, w_prefix, start, end):
+        for w_prefix in space.fixedview(w_prefix):
+            if self._startswith(space, w_prefix, start, end):
+                return space.w_True
+        return space.w_False
+
+    def _startswith(self, space, w_prefix, start, end):
+        prefix = self.convert_arg_to_w_unicode(space, w_prefix)._utf8
+        if start > self._len():
+            return len(prefix) == 0 # bug-to-bug cpython compatibility
+        xxx
+        return startswith(self._utf8, prefix, start, end)
+
+
     def descr_getnewargs(self, space):
         return space.newtuple([W_UnicodeObject(self._utf8, self._length)])