Issue #28927: bytes.fromhex() and bytearray.fromhex() now ignore all ASCII

whitespace, not only spaces.  Patch by Robert Xiao.

diff --git a/Doc/library/stdtypes.rst b/Doc/library/stdtypes.rst
index 1e665affb827a8ce6fe10f5bfaf2a50ba70ea288..982d9f85828c7c77824f0f65a16756ed43c44a19 100644 (file)
--- a/Doc/library/stdtypes.rst
+++ b/Doc/library/stdtypes.rst
@@ -2314,11 +2314,15 @@ the bytes type has an additional class method to read data in that format:
 
    This :class:`bytes` class method returns a bytes object, decoding the
    given string object.  The string must contain two hexadecimal digits per
-   byte, with ASCII spaces being ignored.
+   byte, with ASCII whitespace being ignored.
 
    >>> bytes.fromhex('2Ef0 F1f2  ')
    b'.\xf0\xf1\xf2'
 
+   .. versionchanged:: 3.7
+      :meth:`bytes.fromhex` now skips all ASCII whitespace in the string,
+      not just spaces.
+
 A reverse conversion function exists to transform a bytes object into its
 hexadecimal representation.
 
@@ -2382,11 +2386,15 @@ the bytearray type has an additional class method to read data in that format:
 
    This :class:`bytearray` class method returns bytearray object, decoding
    the given string object.  The string must contain two hexadecimal digits
-   per byte, with ASCII spaces being ignored.
+   per byte, with ASCII whitespace being ignored.
 
    >>> bytearray.fromhex('2Ef0 F1f2  ')
    bytearray(b'.\xf0\xf1\xf2')
 
+   .. versionchanged:: 3.7
+      :meth:`bytearray.fromhex` now skips all ASCII whitespace in the string,
+      not just spaces.
+
 A reverse conversion function exists to transform a bytearray object into its
 hexadecimal representation.
 

diff --git a/Doc/whatsnew/3.7.rst b/Doc/whatsnew/3.7.rst
index ac3a151638ddd243d257780ac6f93ff272bcc6e5..0d19f25942da44ff521a129f4fb35e4d7557ada6 100644 (file)
--- a/Doc/whatsnew/3.7.rst
+++ b/Doc/whatsnew/3.7.rst
@@ -79,6 +79,10 @@ Other Language Changes
   now have more than 255 parameters.
   (Contributed by Serhiy Storchaka in :issue:`12844` and :issue:`18896`.)
 
+* :meth:`bytes.fromhex` and :meth:`bytearray.fromhex` now ignore all ASCII
+  whitespace, not only spaces.
+  (Contributed by Robert Xiao in :issue:`28927`.)
+
 
 New Modules
 ===========

diff --git a/Lib/test/test_bytes.py b/Lib/test/test_bytes.py
index b396a76a40d837b16520bb4335eaedf9ed2241b8..278cfccdf637f55e3f7a0d57dd819072e7e44bf2 100644 (file)
--- a/Lib/test/test_bytes.py
+++ b/Lib/test/test_bytes.py
@@ -293,6 +293,14 @@ class BaseBytesTest:
         b = bytearray([0x1a, 0x2b, 0x30])
         self.assertEqual(self.type2test.fromhex('1a2B30'), b)
         self.assertEqual(self.type2test.fromhex('  1A 2B  30   '), b)
+
+        # check that ASCII whitespace is ignored
+        self.assertEqual(self.type2test.fromhex(' 1A\n2B\t30\v'), b)
+        for c in "\x09\x0A\x0B\x0C\x0D\x20":
+            self.assertEqual(self.type2test.fromhex(c), self.type2test())
+        for c in "\x1C\x1D\x1E\x1F\x85\xa0\u2000\u2002\u2028":
+            self.assertRaises(ValueError, self.type2test.fromhex, c)
+
         self.assertEqual(self.type2test.fromhex('0000'), b'\0\0')
         self.assertRaises(TypeError, self.type2test.fromhex, b'1B')
         self.assertRaises(ValueError, self.type2test.fromhex, 'a')

diff --git a/Misc/NEWS b/Misc/NEWS
index 1aa0a7525f076960f115d7781439b72cccf6b2c7..15bc0ed6a7bced6e0b8b0d60274c0a00749dab0a 100644 (file)
--- a/Misc/NEWS
+++ b/Misc/NEWS
@@ -10,6 +10,9 @@ What's New in Python 3.7.0 alpha 1
 Core and Builtins
 -----------------
 
+- Issue #28927: bytes.fromhex() and bytearray.fromhex() now ignore all ASCII
+  whitespace, not only spaces.  Patch by Robert Xiao.
+
 - Issue #25677: Correct the positioning of the syntax error caret for
   indented blocks.  Based on patch by Michael Layzell.
 

diff --git a/Objects/bytesobject.c b/Objects/bytesobject.c
index 0df90335ed58e98945fea6bf58680eb96d0da9be..5bdfd62f9633d168c3ae98a509e88fc8a38a49bf 100644 (file)
--- a/Objects/bytesobject.c
+++ b/Objects/bytesobject.c
@@ -2378,10 +2378,10 @@ _PyBytes_FromHex(PyObject *string, int use_bytearray)
     end = str + hexlen;
     while (str < end) {
         /* skip over spaces in the input */
-        if (*str == ' ') {
+        if (Py_ISSPACE(*str)) {
             do {
                 str++;
-            } while (*str == ' ');
+            } while (Py_ISSPACE(*str));
             if (str >= end)
                 break;
         }