Author: Tyler Wade <way...@gmail.com>
Branch: utf8-unicode2
Changeset: r73353:20c49b3d0e22
Date: 2014-09-06 15:42 -0500
http://bitbucket.org/pypy/pypy/changeset/20c49b3d0e22/
Log: Rename this method
diff --git a/pypy/interpreter/test/test_utf8.py
b/pypy/interpreter/test/test_utf8.py
--- a/pypy/interpreter/test/test_utf8.py
+++ b/pypy/interpreter/test/test_utf8.py
@@ -109,13 +109,13 @@
def test_convert_indices():
s = build_utf8str()
- assert s.index_of_char(0) == 0
- assert s.index_of_char(1) == 1
- assert s.index_of_char(2) == 3
- assert s.index_of_char(3) == 6
+ assert s.byte_index_of_char(0) == 0
+ assert s.byte_index_of_char(1) == 1
+ assert s.byte_index_of_char(2) == 3
+ assert s.byte_index_of_char(3) == 6
for i in range(len(s)):
- assert s.char_index_of_byte(s.index_of_char(i)) == i
+ assert s.char_index_of_byte(s.byte_index_of_char(i)) == i
def test_join():
s = Utf8Str(' ')
diff --git a/pypy/interpreter/utf8.py b/pypy/interpreter/utf8.py
--- a/pypy/interpreter/utf8.py
+++ b/pypy/interpreter/utf8.py
@@ -57,7 +57,7 @@
return res
def utf8ord(ustr, start=0):
- start = ustr.index_of_char(start)
+ start = ustr.byte_index_of_char(start)
return utf8ord_bytes(ustr.bytes, start)
@specialize.argtype(0)
@@ -161,10 +161,10 @@
self._len = length
- def index_of_char(self, char):
+ def byte_index_of_char(self, char):
return self._cache_scheme.byte_index_of_char(char)
- def index_of_char_from_known(self, char, start_char, start_byte):
+ def byte_index_of_char_from_known(self, char, start_char, start_byte):
if start_char > char:
pos = start_char
byte_pos = start_byte
@@ -246,7 +246,7 @@
if self._is_ascii:
return Utf8Str(self.bytes[start:stop], True)
- start_byte = self.index_of_char(start)
+ start_byte = self.byte_index_of_char(start)
stop_byte = start_byte
stop_pos = start
# TODO: Is detecting ascii-ness here actually useful? If it will
@@ -364,11 +364,11 @@
if start < 0:
start = 0
else:
- start = self.index_of_char(start)
+ start = self.byte_index_of_char(start)
elif start > len(self):
start = -1
else:
- start = self.index_of_char(start)
+ start = self.byte_index_of_char(start)
if end is None or end >= len(self):
end = len(self.bytes)
@@ -377,11 +377,11 @@
if end < 0:
end = 0
else:
- end = self.index_of_char(end)
+ end = self.byte_index_of_char(end)
elif end > len(self):
end = len(self.bytes)
else:
- end = self.index_of_char(end)
+ end = self.byte_index_of_char(end)
return start, end
@@ -755,8 +755,8 @@
if isinstance(s, str):
self._builder.append_slice(s, start, end)
elif isinstance(s, Utf8Str):
- self._builder.append_slice(s.bytes, s.index_of_char(start),
- s.index_of_char(end))
+ self._builder.append_slice(s.bytes, s.byte_index_of_char(start),
+ s.byte_index_of_char(end))
if not s._is_ascii:
self._is_ascii = False
else:
@@ -852,7 +852,7 @@
self._pos = start
self._calculated_pos = start
- self._byte_pos = str.index_of_char(start)
+ self._byte_pos = str.byte_index_of_char(start)
self._current = utf8ord_bytes(self._str.bytes, self._byte_pos)
def _calc_current(self):
@@ -932,7 +932,7 @@
if end_dist[0] < min[0]:
min = end_dist
- b = self.str.index_of_char_from_known(pos, min[1], min[2])
+ b = self.str.byte_index_of_char_from_known(pos, min[1], min[2])
self.prev_pos = pos
self.prev_byte_pos = b
return b
diff --git a/pypy/module/cpyext/unicodeobject.py
b/pypy/module/cpyext/unicodeobject.py
--- a/pypy/module/cpyext/unicodeobject.py
+++ b/pypy/module/cpyext/unicodeobject.py
@@ -693,8 +693,8 @@
suffix match), 0 otherwise. Return -1 if an error occurred."""
str = space.unicode_w(w_str)
substr = space.unicode_w(w_substr)
- start = str.index_of_char(start)
- end = str.index_of_char(end)
+ start = str.byte_index_of_char(start)
+ end = str.byte_index_of_char(end)
if rffi.cast(lltype.Signed, direction) <= 0:
return rstring.startswith(str.bytes, substr.bytes, start, end)
else:
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
@@ -334,11 +334,13 @@
def _startswith(self, space, value, w_prefix, start, end):
return startswith(value.bytes, self._op_val(space, w_prefix).bytes,
- value.index_of_char(start), value.index_of_char(end))
+ value.byte_index_of_char(start),
+ value.byte_index_of_char(end))
def _endswith(self, space, value, w_prefix, start, end):
return endswith(value.bytes, self._op_val(space, w_prefix).bytes,
- value.index_of_char(start), value.index_of_char(end))
+ value.byte_index_of_char(start),
+ value.byte_index_of_char(end))
@staticmethod
def _split(value, sep=None, maxsplit=-1):
_______________________________________________
pypy-commit mailing list
pypy-commit@python.org
https://mail.python.org/mailman/listinfo/pypy-commit
