gh-90533: Implement BytesIO.peek()

Doc/library/io.rst

@@ -739,6 +739,15 @@ than raw I/O does.
 
       Return :class:`bytes` containing the entire contents of the buffer.
 
+   .. method:: peek(size=0, /)
+
+      Return bytes from the current position onwards without advancing the position.
+      At least one byte of data is returned if not at EOF.
+      Return an empty :class:`bytes` object at EOF.
+      The number of read bytes depends on the buffer size
+      and the current position in the internal buffer.
+
+      .. versionadded:: 3.15
 
    .. method:: read1(size=-1, /)
 

Doc/whatsnew/3.15.rst

@@ -981,6 +981,14 @@ inspect
   for :func:`~inspect.getdoc`.
   (Contributed by Serhiy Storchaka in :gh:`132686`.)
 
+
+io
+--
+
+* Add :meth:`io.BytesIO.peek`.
+  (Contributed by Marcel Martin in :gh:`90533`.)
+
+
 json
 ----
 

Lib/_pyio.py

@@ -996,6 +996,13 @@ def tell(self):
             raise ValueError("tell on closed file")
         return self._pos
 
+    def peek(self, size=0):
+        if self.closed:
+            raise ValueError("peek on closed file")
+        if size < 1:
+            return self._buffer[self._pos:self._pos + DEFAULT_BUFFER_SIZE]
+        return self._buffer[self._pos:self._pos + min(size, DEFAULT_BUFFER_SIZE)]
+
     def truncate(self, pos=None):
         if self.closed:
             raise ValueError("truncate on closed file")

Lib/test/test_free_threading/test_io.py

@@ -67,6 +67,10 @@ def readinto(barrier, b, into, *ignore):
             barrier.wait()
             b.readinto(into)
 
+        def peek(barrier, b, *ignore):
+            barrier.wait()
+            b.peek()
+
         def close(barrier, b, *ignore):
             barrier.wait()
             b.close()
@@ -103,6 +107,7 @@ def sizeof(barrier, b, *ignore):
         self.check([truncate] + [readline] * 10, self.ioclass(b'0\n'*20480))
         self.check([truncate] + [readlines] * 10, self.ioclass(b'0\n'*20480))
         self.check([truncate] + [readinto] * 10, self.ioclass(b'0\n'*204800), bytearray(b'0\n'*204800))
+        self.check([truncate] + [peek] * 10, self.ioclass(b'0\n'*204800))
         self.check([close] + [write] * 10, self.ioclass())
         self.check([truncate] + [getvalue] * 10, self.ioclass(b'0\n'*204800))
         self.check([truncate] + [getbuffer] * 10, self.ioclass(b'0\n'*204800))

Lib/test/test_io/test_memoryio.py

@@ -566,6 +566,72 @@ def test_issue141311(self):
         buf = bytearray(2)
         self.assertEqual(0, memio.readinto(buf))
 
+    def test_peek(self):
+        buf = self.buftype("1234567890")
+        with self.ioclass(buf) as memio:
+            self.assertEqual(memio.tell(), 0)
+            self.assertEqual(memio.peek(1), buf[:1])
+            self.assertEqual(memio.peek(1), buf[:1])
+            self.assertEqual(memio.peek(), buf)
+            self.assertEqual(memio.peek(3), buf[:3])
+            self.assertEqual(memio.peek(5), buf[:5])
+            self.assertEqual(memio.peek(0), buf)
+            self.assertEqual(memio.peek(len(buf) + 100), buf)
+            self.assertEqual(memio.peek(-1), buf)
+            self.assertEqual(memio.tell(), 0)
+
+            memio.read(1)
+            self.assertEqual(memio.tell(), 1)
+            self.assertEqual(memio.peek(1), buf[1:2])
+            self.assertEqual(memio.peek(), buf[1:])
+            self.assertEqual(memio.peek(3), buf[1:4])
+            self.assertEqual(memio.peek(5), buf[1:6])
+            self.assertEqual(memio.peek(0), buf[1:])
+            self.assertEqual(memio.peek(len(buf) + 100), buf[1:])
+            self.assertEqual(memio.peek(-1), buf[1:])
+            self.assertEqual(memio.tell(), 1)
+
+            memio.read()
+            self.assertEqual(memio.tell(), len(buf))
+            self.assertEqual(memio.peek(1), self.EOF)
+            self.assertEqual(memio.peek(3), self.EOF)
+            self.assertEqual(memio.peek(5), self.EOF)
+            self.assertEqual(memio.peek(0), b"")
+            self.assertEqual(memio.tell(), len(buf))
+
+            # Peeking works after writing
+            abc = self.buftype("abc")
+            memio.write(abc)
+            self.assertEqual(memio.peek(), self.EOF)
+            memio.seek(len(buf))
+            self.assertEqual(memio.peek(), abc)
+            self.assertEqual(memio.peek(-1), abc)
+            self.assertEqual(memio.peek(len(abc) + 100), abc)
+            self.assertEqual(memio.tell(), len(buf))
+
+        # Length of returned bytes object is capped to DEFAULT_BUFFER_SIZE
+        buf = self.buftype("a" * (io.DEFAULT_BUFFER_SIZE + 10))
+        with self.ioclass(buf) as memio:
+            self.assertEqual(len(memio.peek()), io.DEFAULT_BUFFER_SIZE)
+            self.assertEqual(len(memio.peek(io.DEFAULT_BUFFER_SIZE + 1)), io.DEFAULT_BUFFER_SIZE)
+
+        with self.ioclass(buf) as memio:
+            memio.seek(len(buf))
+            self.assertEqual(memio.peek(), self.EOF)
+
+        # Current position beyond buffer end
+        with self.ioclass(buf) as memio:
+            memio.seek(len(buf) + 100)
+            self.assertEqual(memio.peek(), self.EOF)
+        with self.ioclass(buf) as memio:
+            memio.read()
+            memio.truncate(0)
+            self.assertEqual(memio.tell(), len(buf))
+            self.assertEqual(memio.peek(), self.EOF)
+
+
+        self.assertRaises(ValueError, memio.peek)
+
     def test_unicode(self):
         memio = self.ioclass()
 

Misc/NEWS.d/next/Library/2022-04-10-20-10-59.bpo-46375.8j1ogZ.rst

@@ -0,0 +1 @@
+Add :meth:`io.BytesIO.peek`.

Modules/_io/bytesio.c

@@ -420,8 +420,9 @@ _io_BytesIO_tell_impl(bytesio *self)
     return PyLong_FromSsize_t(self->pos);
 }
 
+// Read without advancing position
 static PyObject *
-read_bytes_lock_held(bytesio *self, Py_ssize_t size)
+peek_bytes_lock_held(bytesio *self, Py_ssize_t size)
 {
     _Py_CRITICAL_SECTION_ASSERT_OBJECT_LOCKED(self);
 
@@ -432,7 +433,6 @@ read_bytes_lock_held(bytesio *self, Py_ssize_t size)
     if (size > 1 &&
         self->pos == 0 && size == PyBytes_GET_SIZE(self->buf) &&
         FT_ATOMIC_LOAD_SSIZE_RELAXED(self->exports) == 0) {
-        self->pos += size;
         return Py_NewRef(self->buf);
     }
 
@@ -444,10 +444,20 @@ read_bytes_lock_held(bytesio *self, Py_ssize_t size)
     }
 
     output = PyBytes_AS_STRING(self->buf) + self->pos;
-    self->pos += size;
     return PyBytes_FromStringAndSize(output, size);
 }
 
+static PyObject *
+read_bytes_lock_held(bytesio *self, Py_ssize_t size)
+{
+    PyObject *bytes = peek_bytes_lock_held(self, size);
+    if (bytes != NULL) {
+        assert(PyBytes_GET_SIZE(bytes) == size);
+        self->pos += size;
+    }
+    return bytes;
+}
+
 /*[clinic input]
 @critical_section
 _io.BytesIO.read
@@ -499,6 +509,40 @@ _io_BytesIO_read1_impl(bytesio *self, Py_ssize_t size)
     return _io_BytesIO_read_impl(self, size);
 }
 
+
+/*[clinic input]
+@critical_section
+_io.BytesIO.peek
+    size: Py_ssize_t = 0
+    /
+
+Return bytes from the stream without advancing the position.
+
+Return an empty bytes object at EOF.
+[clinic start generated code]*/
+
+static PyObject *
+_io_BytesIO_peek_impl(bytesio *self, Py_ssize_t size)
+/*[clinic end generated code: output=fa4d8ce28b35db9b input=2ce74234b10aec3e]*/
+{
+    CHECK_CLOSED(self);
+
+    /* adjust invalid sizes */
+    Py_ssize_t n = self->string_size - self->pos;
+    if (n > DEFAULT_BUFFER_SIZE) {
+        n = DEFAULT_BUFFER_SIZE;
+    }
+    if (size < 1 || size > n) {
+        size = n;
+        /* n can be negative after truncate() or seek() */
+        if (size < 0) {
+            size = 0;
+        }
+    }
+    return peek_bytes_lock_held(self, size);
+}
+
+
 /*[clinic input]
 @critical_section
 _io.BytesIO.readline
@@ -1135,6 +1179,7 @@ static struct PyMethodDef bytesio_methods[] = {
     _IO_BYTESIO_READLINE_METHODDEF
     _IO_BYTESIO_READLINES_METHODDEF
     _IO_BYTESIO_READ_METHODDEF
+    _IO_BYTESIO_PEEK_METHODDEF
     _IO_BYTESIO_GETBUFFER_METHODDEF
     _IO_BYTESIO_GETVALUE_METHODDEF
     _IO_BYTESIO_SEEK_METHODDEF