Issue python#15984: Merge PyUnicode doc from 3.5

vadmium · vadmium · commit cda80940ed44 · 2016-04-15T02:27:11.000Z
diff --git a/Doc/c-api/exceptions.rst b/Doc/c-api/exceptions.rst
@@ -285,7 +285,7 @@ an error value).
 .. c:function:: int PyErr_WarnEx(PyObject *category, const char *message, Py_ssize_t stack_level)
 
    Issue a warning message.  The *category* argument is a warning category (see
-   below) or *NULL*; the *message* argument is an UTF-8 encoded string.  *stack_level* is a
+   below) or *NULL*; the *message* argument is a UTF-8 encoded string.  *stack_level* is a
    positive number giving a number of stack frames; the warning will be issued from
    the  currently executing line of code in that stack frame.  A *stack_level* of 1
    is the function calling :c:func:`PyErr_WarnEx`, 2 is  the function above that,
@@ -617,7 +617,7 @@ The following functions are used to create and modify Unicode exceptions from C.
 .. c:function:: PyObject* PyUnicodeTranslateError_Create(const Py_UNICODE *object, Py_ssize_t length, Py_ssize_t start, Py_ssize_t end, const char *reason)
 
    Create a :class:`UnicodeTranslateError` object with the attributes *object*,
-   *length*, *start*, *end* and *reason*. *reason* is an UTF-8 encoded string.
+   *length*, *start*, *end* and *reason*. *reason* is a UTF-8 encoded string.
 
 .. c:function:: PyObject* PyUnicodeDecodeError_GetEncoding(PyObject *exc)
                 PyObject* PyUnicodeEncodeError_GetEncoding(PyObject *exc)
diff --git a/Doc/c-api/import.rst b/Doc/c-api/import.rst
@@ -72,7 +72,7 @@ Importing Modules
 
 .. c:function:: PyObject* PyImport_ImportModuleLevel(const char *name, PyObject *globals, PyObject *locals, PyObject *fromlist, int level)
 
-   Similar to :c:func:`PyImport_ImportModuleLevelObject`, but the name is an
+   Similar to :c:func:`PyImport_ImportModuleLevelObject`, but the name is a
    UTF-8 encoded string instead of a Unicode object.
 
    .. versionchanged:: 3.3
diff --git a/Doc/c-api/method.rst b/Doc/c-api/method.rst
@@ -49,7 +49,7 @@ Method Objects
 .. index:: object: method
 
 Methods are bound function objects. Methods are always bound to an instance of
-an user-defined class. Unbound methods (methods bound to a class object) are
+a user-defined class. Unbound methods (methods bound to a class object) are
 no longer available.
 
 
diff --git a/Doc/c-api/module.rst b/Doc/c-api/module.rst
@@ -50,7 +50,7 @@ Module Objects
 
 .. c:function:: PyObject* PyModule_New(const char *name)
 
-   Similar to :c:func:`PyImport_NewObject`, but the name is an UTF-8 encoded
+   Similar to :c:func:`PyImport_NewObject`, but the name is a UTF-8 encoded
    string instead of a Unicode object.
 
 
diff --git a/Doc/c-api/unicode.rst b/Doc/c-api/unicode.rst
@@ -423,7 +423,7 @@ APIs:
 
 .. c:function:: PyObject *PyUnicode_FromString(const char *u)
 
-   Create a Unicode object from an UTF-8 encoded null-terminated char buffer
+   Create a Unicode object from a UTF-8 encoded null-terminated char buffer
    *u*.
 
 
@@ -556,14 +556,13 @@ APIs:
 .. c:function:: PyObject* PyUnicode_FromEncodedObject(PyObject *obj, \
                                const char *encoding, const char *errors)
 
-   Coerce an encoded object *obj* to an Unicode object and return a reference with
-   incremented refcount.
+   Decode an encoded object *obj* to a Unicode object.
 
    :class:`bytes`, :class:`bytearray` and other
    :term:`bytes-like objects <bytes-like object>`
    are decoded according to the given *encoding* and using the error handling
    defined by *errors*. Both can be *NULL* to have the interface use the default
-   values (see the next section for details).
+   values (see :ref:`builtincodecs` for details).
 
    All other objects, including Unicode objects, cause a :exc:`TypeError` to be
    set.
@@ -745,8 +744,11 @@ Extension modules can continue using them, as they will not be removed in Python
 
 .. c:function:: PyObject* PyUnicode_FromObject(PyObject *obj)
 
-   Shortcut for ``PyUnicode_FromEncodedObject(obj, NULL, "strict")`` which is used
-   throughout the interpreter whenever coercion to Unicode is needed.
+   Copy an instance of a Unicode subtype to a new true Unicode object if
+   necessary. If *obj* is already a true Unicode object (not a subtype),
+   return the reference with incremented refcount.
+
+   Objects other than Unicode or its subtypes will cause a :exc:`TypeError`.
 
 
 Locale Encoding
@@ -1224,7 +1226,7 @@ These are the UTF-16 codec APIs:
 
    If *Py_UNICODE_WIDE* is defined, a single :c:type:`Py_UNICODE` value may get
    represented as a surrogate pair. If it is not defined, each :c:type:`Py_UNICODE`
-   values is interpreted as an UCS-2 character.
+   values is interpreted as a UCS-2 character.
 
    Return *NULL* if an exception was raised by the codec.
 
diff --git a/Doc/howto/urllib2.rst b/Doc/howto/urllib2.rst
@@ -64,7 +64,7 @@ you can do so via the :func:`~urllib.request.urlretrieve` function::
     html = open(local_filename)
 
 Many uses of urllib will be that simple (note that instead of an 'http:' URL we
-could have used an URL starting with 'ftp:', 'file:', etc.).  However, it's the
+could have used a URL starting with 'ftp:', 'file:', etc.).  However, it's the
 purpose of this tutorial to explain the more complicated cases, concentrating on
 HTTP.
 
diff --git a/Doc/library/heapq.rst b/Doc/library/heapq.rst
@@ -242,7 +242,7 @@ for a tournament.  The numbers below are *k*, not ``a[k]``::
 
    15 16   17 18   19 20   21 22   23 24   25 26   27 28   29 30
 
-In the tree above, each cell *k* is topping ``2*k+1`` and ``2*k+2``. In an usual
+In the tree above, each cell *k* is topping ``2*k+1`` and ``2*k+2``. In a usual
 binary tournament we see in sports, each cell is the winner over the two cells
 it tops, and we can trace the winner down the tree to see all opponents s/he
 had.  However, in many computer applications of such tournaments, we do not need
diff --git a/Doc/library/logging.handlers.rst b/Doc/library/logging.handlers.rst
@@ -874,7 +874,7 @@ supports sending logging messages to a Web server, using either ``GET`` or
 
    .. method:: emit(record)
 
-      Sends the record to the Web server as an URL-encoded dictionary. The
+      Sends the record to the Web server as a URL-encoded dictionary. The
       :meth:`mapLogRecord` method is used to convert the record to the
       dictionary to be sent.
 
diff --git a/Doc/library/os.rst b/Doc/library/os.rst
@@ -1762,7 +1762,7 @@ features:
    ``os.path.join(os.path.dirname(path), result)``.
 
    If the *path* is a string object, the result will also be a string object,
-   and the call may raise an UnicodeDecodeError. If the *path* is a bytes
+   and the call may raise a UnicodeDecodeError. If the *path* is a bytes
    object, the result will be a bytes object.
 
    This function can also support :ref:`paths relative to directory descriptors
diff --git a/Doc/library/re.rst b/Doc/library/re.rst
@@ -12,7 +12,7 @@ those found in Perl.
 
 Both patterns and strings to be searched can be Unicode strings as well as
 8-bit strings. However, Unicode strings and 8-bit strings cannot be mixed:
-that is, you cannot match an Unicode string with a byte pattern or
+that is, you cannot match a Unicode string with a byte pattern or
 vice-versa; similarly, when asking for a substitution, the replacement
 string must be of the same type as both the pattern and the search string.
 
diff --git a/Doc/library/tkinter.ttk.rst b/Doc/library/tkinter.ttk.rst
@@ -701,7 +701,7 @@ the widget option ``displaycolumns``. The tree widget can also display column
 headings. Columns may be accessed by number or symbolic names listed in the
 widget option columns. See `Column Identifiers`_.
 
-Each item is identified by an unique name. The widget will generate item IDs
+Each item is identified by a unique name. The widget will generate item IDs
 if they are not supplied by the caller. There is a distinguished root item,
 named ``{}``. The root item itself is not displayed; its children appear at the
 top level of the hierarchy.
diff --git a/Doc/library/webbrowser.rst b/Doc/library/webbrowser.rst
@@ -33,7 +33,7 @@ browsers are not available on Unix, the controlling process will launch a new
 browser and wait.
 
 The script :program:`webbrowser` can be used as a command-line interface for the
-module. It accepts an URL as the argument. It accepts the following optional
+module. It accepts a URL as the argument. It accepts the following optional
 parameters: ``-n`` opens the URL in a new browser window, if possible;
 ``-t`` opens the URL in a new browser page ("tab"). The options are,
 naturally, mutually exclusive.  Usage example::
diff --git a/Doc/library/xml.etree.elementtree.rst b/Doc/library/xml.etree.elementtree.rst
@@ -978,7 +978,7 @@ QName Objects
    to get proper namespace handling on output.  *text_or_uri* is a string
    containing the QName value, in the form {uri}local, or, if the tag argument
    is given, the URI part of a QName.  If *tag* is given, the first argument is
-   interpreted as an URI, and this argument is interpreted as a local name.
+   interpreted as a URI, and this argument is interpreted as a local name.
    :class:`QName` instances are opaque.
 
 
diff --git a/Doc/library/xml.sax.reader.rst b/Doc/library/xml.sax.reader.rst
@@ -98,7 +98,7 @@ The :class:`XMLReader` interface supports the following methods:
 
    Process an input source, producing SAX events. The *source* object can be a
    system identifier (a string identifying the input source -- typically a file
-   name or an URL), a file-like object, or an :class:`InputSource` object. When
+   name or a URL), a file-like object, or an :class:`InputSource` object. When
    :meth:`parse` returns, the input is completely processed, and the parser object
    can be discarded or reset.
 
diff --git a/Doc/library/xmlrpc.client.rst b/Doc/library/xmlrpc.client.rst
@@ -420,7 +420,7 @@ by providing an invalid URI::
 
    import xmlrpc.client
 
-   # create a ServerProxy with an URI that doesn't respond to XMLRPC requests
+   # create a ServerProxy with a URI that doesn't respond to XMLRPC requests
    proxy = xmlrpc.client.ServerProxy("http://google.com/")
 
    try:
diff --git a/Include/bytesobject.h b/Include/bytesobject.h
@@ -89,7 +89,7 @@ PyAPI_FUNC(PyObject *) _PyBytes_Join(PyObject *sep, PyObject *x);
 #endif
 
 /* Provides access to the internal data buffer and size of a string
-   object or the default encoded version of an Unicode object. Passing
+   object or the default encoded version of a Unicode object. Passing
    NULL as *len parameter will force the string buffer to be
    0-terminated (passing a string with embedded NULL characters will
    cause an exception).  */
diff --git a/Include/unicodeobject.h b/Include/unicodeobject.h
@@ -823,7 +823,7 @@ PyAPI_FUNC(int) PyUnicode_WriteChar(
 PyAPI_FUNC(Py_UNICODE) PyUnicode_GetMax(void);
 #endif
 
-/* Resize an Unicode object. The length is the number of characters, except
+/* Resize a Unicode object. The length is the number of characters, except
    if the kind of the string is PyUnicode_WCHAR_KIND: in this case, the length
    is the number of Py_UNICODE characters.
 
@@ -844,17 +844,13 @@ PyAPI_FUNC(int) PyUnicode_Resize(
     Py_ssize_t length           /* New length */
     );
 
-/* Coerce obj to an Unicode object and return a reference with
-   *incremented* refcount.
+/* Decode obj to an Unicode object.
 
-   Coercion is done in the following way:
+   bytes, bytearray and other bytes-like objects are decoded according to the
+   given encoding and error handler. The encoding and error handler can be
+   NULL to have the interface use UTF-8 and "strict".
 
-   1. bytes, bytearray and other bytes-like objects are decoded
-      under the assumptions that they contain data using the UTF-8
-      encoding. Decoding is done in "strict" mode.
-
-   2. All other objects (including Unicode objects) raise an
-      exception.
+   All other objects (including Unicode objects) raise an exception.
 
    The API returns NULL in case of an error. The caller is responsible
    for decref'ing the returned objects.
@@ -867,13 +863,9 @@ PyAPI_FUNC(PyObject*) PyUnicode_FromEncodedObject(
     const char *errors          /* error handling */
     );
 
-/* Coerce obj to an Unicode object and return a reference with
-   *incremented* refcount.
-
-   Unicode objects are passed back as-is (subclasses are converted to
-   true Unicode objects), all other objects are delegated to
-   PyUnicode_FromEncodedObject(obj, NULL, "strict") which results in
-   using UTF-8 encoding as basis for decoding the object.
+/* Copy an instance of a Unicode subtype to a new true Unicode object if
+   necessary. If obj is already a true Unicode object (not a subtype), return
+   the reference with *incremented* refcount.
 
    The API returns NULL in case of an error. The caller is responsible
    for decref'ing the returned objects.
@@ -998,7 +990,7 @@ _PyUnicodeWriter_WriteLatin1String(_PyUnicodeWriter *writer,
     Py_ssize_t len             /* length in bytes */
     );
 
-/* Get the value of the writer as an Unicode string. Clear the
+/* Get the value of the writer as a Unicode string. Clear the
    buffer of the writer. Raise an exception and return NULL
    on error. */
 PyAPI_FUNC(PyObject *)
diff --git a/Lib/asyncio/windows_events.py b/Lib/asyncio/windows_events.py
@@ -197,7 +197,7 @@ def _unregister_wait_cb(self, fut):
         #
         # If the IocpProactor already received the event, it's safe to call
         # _unregister() because we kept a reference to the Overlapped object
-        # which is used as an unique key.
+        # which is used as a unique key.
         self._proactor._unregister(self._ov)
         self._proactor = None
 
diff --git a/Lib/email/utils.py b/Lib/email/utils.py
@@ -87,7 +87,7 @@ def formataddr(pair, charset='utf-8'):
     'utf-8'.
     """
     name, address = pair
-    # The address MUST (per RFC) be ascii, so raise an UnicodeError if it isn't.
+    # The address MUST (per RFC) be ascii, so raise a UnicodeError if it isn't.
     address.encode('ascii')
     if name:
         try:
diff --git a/Lib/heapq.py b/Lib/heapq.py
@@ -54,7 +54,7 @@
 
 
 In the tree above, each cell `k' is topping `2*k+1' and `2*k+2'.  In
-an usual binary tournament we see in sports, each cell is the winner
+a usual binary tournament we see in sports, each cell is the winner
 over the two cells it tops, and we can trace the winner down the tree
 to see all opponents s/he had.  However, in many computer applications
 of such tournaments, we do not need to trace the history of a winner.
diff --git a/Lib/nntplib.py b/Lib/nntplib.py
@@ -165,7 +165,7 @@ class NNTPDataError(NNTPError):
 
 # Helper function(s)
 def decode_header(header_str):
-    """Takes an unicode string representing a munged header value
+    """Takes a unicode string representing a munged header value
     and decodes it as a (possibly non-ASCII) readable value."""
     parts = []
     for v, enc in _email_decode_header(header_str):
@@ -420,7 +420,7 @@ def _putline(self, line):
 
     def _putcmd(self, line):
         """Internal: send one command to the server (through _putline()).
-        The `line` must be an unicode string."""
+        The `line` must be a unicode string."""
         if self.debugging: print('*cmd*', repr(line))
         line = line.encode(self.encoding, self.errors)
         self._putline(line)
@@ -445,7 +445,7 @@ def _getline(self, strip_crlf=True):
     def _getresp(self):
         """Internal: get a response from the server.
         Raise various errors if the response indicates an error.
-        Returns an unicode string."""
+        Returns a unicode string."""
         resp = self._getline()
         if self.debugging: print('*resp*', repr(resp))
         resp = resp.decode(self.encoding, self.errors)
@@ -462,7 +462,7 @@ def _getlongresp(self, file=None):
         """Internal: get a response plus following text from the server.
         Raise various errors if the response indicates an error.
 
-        Returns a (response, lines) tuple where `response` is an unicode
+        Returns a (response, lines) tuple where `response` is a unicode
         string and `lines` is a list of bytes objects.
         If `file` is a file-like object, it must be open in binary mode.
         """
diff --git a/Lib/ntpath.py b/Lib/ntpath.py
@@ -177,7 +177,7 @@ def splitunc(p):
     Return a 2-tuple (unc, rest); either part may be empty.
     If unc is not empty, it has the form '//host/mount' (or similar
     using backslashes).  unc+rest is always the input path.
-    Paths containing drive letters never have an UNC part.
+    Paths containing drive letters never have a UNC part.
     """
     import warnings
     warnings.warn("ntpath.splitunc is deprecated, use ntpath.splitdrive instead",
diff --git a/Lib/test/test_codecs.py b/Lib/test/test_codecs.py
@@ -2401,7 +2401,7 @@ def test_decode_unicode(self):
             self.assertRaises(TypeError, decoder, "xxx")
 
     def test_unicode_escape(self):
-        # Escape-decoding an unicode string is supported ang gives the same
+        # Escape-decoding a unicode string is supported ang gives the same
         # result as decoding the equivalent ASCII bytes string.
         self.assertEqual(codecs.unicode_escape_decode(r"\u1234"), ("\u1234", 6))
         self.assertEqual(codecs.unicode_escape_decode(br"\u1234"), ("\u1234", 6))
diff --git a/Lib/test/test_multibytecodec.py b/Lib/test/test_multibytecodec.py
@@ -67,7 +67,7 @@ def test_init_segfault(self):
                           _multibytecodec.MultibyteStreamWriter, None)
 
     def test_decode_unicode(self):
-        # Trying to decode an unicode string should raise a TypeError
+        # Trying to decode a unicode string should raise a TypeError
         for enc in ALL_CJKENCODINGS:
             self.assertRaises(TypeError, codecs.getdecoder(enc), "")
 
@@ -160,7 +160,7 @@ def test_iso2022(self):
         self.assertEqual(decoder.decode(b'B@$'), '\u4e16')
 
     def test_decode_unicode(self):
-        # Trying to decode an unicode string should raise a TypeError
+        # Trying to decode a unicode string should raise a TypeError
         for enc in ALL_CJKENCODINGS:
             decoder = codecs.getincrementaldecoder(enc)()
             self.assertRaises(TypeError, decoder.decode, "")
diff --git a/Lib/test/test_nntplib.py b/Lib/test/test_nntplib.py
@@ -609,7 +609,7 @@ def handle_XOVER(self, message_spec):
                     "\t\t6683\t16"
                     "\t"
                     "\n"
-                # An UTF-8 overview line from fr.comp.lang.python
+                # A UTF-8 overview line from fr.comp.lang.python
                 "59\tRe: Message d'erreur incompréhensible (par moi)"
                     "\tEric Brunel <eric.brunel@pragmadev.nospam.com>"
                     "\tWed, 15 Sep 2010 18:09:15 +0200"
diff --git a/Lib/test/test_unicode.py b/Lib/test/test_unicode.py
@@ -1774,7 +1774,7 @@ def to_bytestring(self, seq):
 
     def assertCorrectUTF8Decoding(self, seq, res, err):
         """
-        Check that an invalid UTF-8 sequence raises an UnicodeDecodeError when
+        Check that an invalid UTF-8 sequence raises a UnicodeDecodeError when
         'strict' is used, returns res when 'replace' is used, and that doesn't
         return anything when 'ignore' is used.
         """
diff --git a/Lib/test/test_zlib.py b/Lib/test/test_zlib.py
@@ -175,7 +175,7 @@ def test_speech128(self):
             self.assertEqual(zlib.decompress(ob), data)
 
     def test_incomplete_stream(self):
-        # An useful error message is given
+        # A useful error message is given
         x = zlib.compress(HAMLET_SCENE)
         self.assertRaisesRegex(zlib.error,
             "Error -5 while decompressing data: incomplete or truncated stream",
diff --git a/Misc/HISTORY b/Misc/HISTORY
diff --git a/Misc/NEWS b/Misc/NEWS
diff --git a/Modules/_heapqmodule.c b/Modules/_heapqmodule.c
diff --git a/Modules/_pickle.c b/Modules/_pickle.c
diff --git a/Modules/_tracemalloc.c b/Modules/_tracemalloc.c
diff --git a/Objects/codeobject.c b/Objects/codeobject.c
diff --git a/Objects/unicodeobject.c b/Objects/unicodeobject.c
diff --git a/Python/codecs.c b/Python/codecs.c
