#5391 make mmap work exclusively with bytes
diff --git a/Doc/library/mmap.rst b/Doc/library/mmap.rst
index ceca29a..c3dba43 100644
--- a/Doc/library/mmap.rst
+++ b/Doc/library/mmap.rst
@@ -6,13 +6,13 @@
:synopsis: Interface to memory-mapped files for Unix and Windows.
-Memory-mapped file objects behave like both strings and like file objects.
-Unlike normal string objects, however, these are mutable. You can use mmap
-objects in most places where strings are expected; for example, you can use
-the :mod:`re` module to search through a memory-mapped file. Since they're
-mutable, you can change a single character by doing ``obj[index] = 'a'``, or
-change a substring by assigning to a slice: ``obj[i1:i2] = '...'``. You can
-also read and write data starting at the current file position, and
+Memory-mapped file objects behave like both :class:`bytes` and like file
+objects. Unlike normal :class:`bytes` objects, however, these are mutable.
+You can use mmap objects in most places where :class:`bytes` are expected; for
+example, you can use the :mod:`re` module to search through a memory-mapped file.
+Since they're mutable, you can change a single byte by doing ``obj[index] = 97``,
+or change a subsequence by assigning to a slice: ``obj[i1:i2] = b'...'``.
+You can also read and write data starting at the current file position, and
:meth:`seek` through the file to different positions.
A memory-mapped file is created by the :class:`mmap` constructor, which is
@@ -94,21 +94,21 @@
# write a simple example file
with open("hello.txt", "wb") as f:
- f.write("Hello Python!\n")
+ f.write(b"Hello Python!\n")
with open("hello.txt", "r+b") as f:
# memory-map the file, size 0 means whole file
map = mmap.mmap(f.fileno(), 0)
# read content via standard file methods
- print(map.readline()) # prints "Hello Python!"
+ print(map.readline()) # prints b"Hello Python!\n"
# read content via slice notation
- print(map[:5]) # prints "Hello"
+ print(map[:5]) # prints b"Hello"
# update content using slice notation;
# note that new content must have same size
- map[6:] = " world!\n"
+ map[6:] = b" world!\n"
# ... and read again using standard file methods
map.seek(0)
- print(map.readline()) # prints "Hello world!"
+ print(map.readline()) # prints b"Hello world!\n"
# close the map
map.close()
@@ -120,7 +120,7 @@
import os
map = mmap.mmap(-1, 13)
- map.write("Hello world!")
+ map.write(b"Hello world!")
pid = os.fork()
@@ -140,10 +140,10 @@
result in an exception being raised.
- .. method:: find(string[, start[, end]])
+ .. method:: find(sub[, start[, end]])
- Returns the lowest index in the object where the substring *string* is
- found, such that *string* is contained in the range [*start*, *end*].
+ Returns the lowest index in the object where the subsequence *sub* is
+ found, such that *sub* is contained in the range [*start*, *end*].
Optional arguments *start* and *end* are interpreted as in slice notation.
Returns ``-1`` on failure.
@@ -172,15 +172,15 @@
.. method:: read(num)
- Return a string containing up to *num* bytes starting from the current
- file position; the file position is updated to point after the bytes that
- were returned.
+ Return a :class:`bytes` containing up to *num* bytes starting from the
+ current file position; the file position is updated to point after the
+ bytes that were returned.
.. method:: read_byte()
- Returns a string of length 1 containing the character at the current file
- position, and advances the file position by 1.
+ Returns a byte at the current file position as an integer, and advances
+ the file position by 1.
.. method:: readline()
@@ -196,10 +196,10 @@
throw a :exc:`TypeError` exception.
- .. method:: rfind(string[, start[, end]])
+ .. method:: rfind(sub[, start[, end]])
- Returns the highest index in the object where the substring *string* is
- found, such that *string* is contained in the range [*start*, *end*].
+ Returns the highest index in the object where the subsequence *sub* is
+ found, such that *sub* is contained in the range [*start*, *end*].
Optional arguments *start* and *end* are interpreted as in slice notation.
Returns ``-1`` on failure.
@@ -223,9 +223,9 @@
Returns the current position of the file pointer.
- .. method:: write(string)
+ .. method:: write(bytes)
- Write the bytes in *string* into memory at the current position of the
+ Write the bytes in *bytes* into memory at the current position of the
file pointer; the file position is updated to point after the bytes that
were written. If the mmap was created with :const:`ACCESS_READ`, then
writing to it will throw a :exc:`TypeError` exception.
@@ -233,7 +233,7 @@
.. method:: write_byte(byte)
- Write the single-character string *byte* into memory at the current
+ Write the the integer *byte* into memory at the current
position of the file pointer; the file position is advanced by ``1``. If
the mmap was created with :const:`ACCESS_READ`, then writing to it will
throw a :exc:`TypeError` exception.
diff --git a/Lib/test/test_mmap.py b/Lib/test/test_mmap.py
index 99cc63f..f3e28cc 100644
--- a/Lib/test/test_mmap.py
+++ b/Lib/test/test_mmap.py
@@ -37,7 +37,7 @@
# Simple sanity checks
tp = str(type(m)) # SF bug 128713: segfaulted on Linux
- self.assertEqual(m.find('foo'), PAGESIZE)
+ self.assertEqual(m.find(b'foo'), PAGESIZE)
self.assertEqual(len(m), 2*PAGESIZE)
@@ -262,38 +262,38 @@
def test_find_end(self):
# test the new 'end' parameter works as expected
- f = open(TESTFN, 'w+')
- data = 'one two ones'
+ f = open(TESTFN, 'wb+')
+ data = b'one two ones'
n = len(data)
f.write(data)
f.flush()
m = mmap.mmap(f.fileno(), n)
f.close()
- self.assertEqual(m.find('one'), 0)
- self.assertEqual(m.find('ones'), 8)
- self.assertEqual(m.find('one', 0, -1), 0)
- self.assertEqual(m.find('one', 1), 8)
- self.assertEqual(m.find('one', 1, -1), 8)
- self.assertEqual(m.find('one', 1, -2), -1)
+ self.assertEqual(m.find(b'one'), 0)
+ self.assertEqual(m.find(b'ones'), 8)
+ self.assertEqual(m.find(b'one', 0, -1), 0)
+ self.assertEqual(m.find(b'one', 1), 8)
+ self.assertEqual(m.find(b'one', 1, -1), 8)
+ self.assertEqual(m.find(b'one', 1, -2), -1)
def test_rfind(self):
# test the new 'end' parameter works as expected
- f = open(TESTFN, 'w+')
- data = 'one two ones'
+ f = open(TESTFN, 'wb+')
+ data = b'one two ones'
n = len(data)
f.write(data)
f.flush()
m = mmap.mmap(f.fileno(), n)
f.close()
- self.assertEqual(m.rfind('one'), 8)
- self.assertEqual(m.rfind('one '), 0)
- self.assertEqual(m.rfind('one', 0, -1), 8)
- self.assertEqual(m.rfind('one', 0, -2), 0)
- self.assertEqual(m.rfind('one', 1, -1), 8)
- self.assertEqual(m.rfind('one', 1, -2), -1)
+ self.assertEqual(m.rfind(b'one'), 8)
+ self.assertEqual(m.rfind(b'one '), 0)
+ self.assertEqual(m.rfind(b'one', 0, -1), 8)
+ self.assertEqual(m.rfind(b'one', 0, -2), 0)
+ self.assertEqual(m.rfind(b'one', 1, -1), 8)
+ self.assertEqual(m.rfind(b'one', 1, -2), -1)
def test_double_close(self):
@@ -506,21 +506,15 @@
# Test write_byte()
for i in range(len(data)):
self.assertEquals(m.tell(), i)
- m.write_byte(data[i:i+1])
+ m.write_byte(data[i])
self.assertEquals(m.tell(), i+1)
- self.assertRaises(ValueError, m.write_byte, b"x")
+ self.assertRaises(ValueError, m.write_byte, b"x"[0])
self.assertEquals(m[:], data)
# Test read_byte()
m.seek(0)
for i in range(len(data)):
self.assertEquals(m.tell(), i)
- # XXX: Disable this test for now because it's not clear
- # which type of object m.read_byte returns. Currently, it
- # returns 1-length str (unicode).
- if 0:
- self.assertEquals(m.read_byte(), data[i:i+1])
- else:
- m.read_byte()
+ self.assertEquals(m.read_byte(), data[i])
self.assertEquals(m.tell(), i+1)
self.assertRaises(ValueError, m.read_byte)
# Test read()
diff --git a/Misc/NEWS b/Misc/NEWS
index 0774988..b567ad1 100644
--- a/Misc/NEWS
+++ b/Misc/NEWS
@@ -11,6 +11,7 @@
Core and Builtins
-----------------
+
- Implement PEP 378, Format Specifier for Thousands Separator, for
integers.
@@ -128,6 +129,8 @@
Extension Modules
-----------------
+- Issue #5391: mmap now deals exclusively with bytes.
+
- Issue #5463: In struct module, remove deprecated overflow wrapping
when packing an integer: struct.pack('=L', -1) now raises
struct.error instead of returning b'\xff\xff\xff\xff'. The
diff --git a/Modules/mmapmodule.c b/Modules/mmapmodule.c
index b9c46cd..299eafd 100644
--- a/Modules/mmapmodule.c
+++ b/Modules/mmapmodule.c
@@ -204,7 +204,7 @@
if (self->pos < self->size) {
char value = self->data[self->pos];
self->pos += 1;
- return Py_BuildValue("c", value);
+ return Py_BuildValue("b", value);
} else {
PyErr_SetString(PyExc_ValueError, "read byte out of range");
return NULL;
@@ -264,7 +264,7 @@
Py_ssize_t len;
CHECK_VALID(NULL);
- if (!PyArg_ParseTuple(args, reverse ? "s#|nn:rfind" : "s#|nn:find",
+ if (!PyArg_ParseTuple(args, reverse ? "y#|nn:rfind" : "y#|nn:find",
&needle, &len, &start, &end)) {
return NULL;
} else {
@@ -348,7 +348,7 @@
char *data;
CHECK_VALID(NULL);
- if (!PyArg_ParseTuple(args, "s#:write", &data, &length))
+ if (!PyArg_ParseTuple(args, "y#:write", &data, &length))
return(NULL);
if (!is_writable(self))
@@ -371,7 +371,7 @@
char value;
CHECK_VALID(NULL);
- if (!PyArg_ParseTuple(args, "c:write_byte", &value))
+ if (!PyArg_ParseTuple(args, "b:write_byte", &value))
return(NULL);
if (!is_writable(self))