a faster implementation if tabsize=0

pypy · Mar 2, 2024 · 0d2d72e · 0d2d72e
1 parent 14c41dc
commit 0d2d72e
Show file tree

Hide file tree

Showing 3 changed files with 8 additions and 4 deletions.
diff --git a/pypy/objspace/std/test/test_bytesobject.py b/pypy/objspace/std/test/test_bytesobject.py
@@ -502,8 +502,6 @@ def test_expandtabs(self):
 
     def test_expandtabs_overflows_gracefully(self):
         import sys
-        if sys.maxint > (1 << 32):
-            skip("Wrong platform")
         raises((MemoryError, OverflowError), b't\tt\t'.expandtabs, sys.maxint)
 
     def test_expandtabs_0(self):

diff --git a/pypy/objspace/std/test/test_unicodeobject.py b/pypy/objspace/std/test/test_unicodeobject.py
@@ -769,6 +769,7 @@ def test_expandtabs_0(self):
 
     def test_expandtabs_bug(self):
         assert u"a\u266f\ttest".expandtabs() == u'a\u266f      test'
+        assert u"a\u266f\ttest".expandtabs(0) == u'a\u266ftest'
 
     def test_translate(self):
         assert u'bbbc' == u'abababc'.translate({ord('a'):None})

diff --git a/pypy/objspace/std/unicodeobject.py b/pypy/objspace/std/unicodeobject.py
@@ -461,12 +461,17 @@ def descr_expandtabs(self, space, tabsize=8):
         value = self._utf8
         if not value:
             return self._empty()
+        if tabsize == 0:
+            res, replacements = replace_count(value, '\t', '')
+            if not replacements and type(self) is W_UnicodeObject:
+                return self
+            newlength = self._length - replacements
+            return W_UnicodeObject(res, newlength)
 
         splitted = value.split('\t')
 
         try:
-            if tabsize > 0:
-                ovfcheck(len(splitted) * tabsize)
+            ovfcheck(len(splitted) * tabsize)
         except OverflowError:
             raise oefmt(space.w_OverflowError, "new string is too long")
         newlen = self._len() - len(splitted) + 1