#9078: fix some Unicode C API descriptions, in comments and docs.

diff --git a/Doc/c-api/unicode.rst b/Doc/c-api/unicode.rst
index b5a9ab1e201d69c4e80182a56360c4aab930d42f..7334c09035b9911ea476a3311664de2f205c4ff9 100644 (file)
--- a/Doc/c-api/unicode.rst
+++ b/Doc/c-api/unicode.rst
@@ -346,10 +346,10 @@ APIs:
    Coerce an encoded object *obj* to an Unicode object and return a reference with
    incremented refcount.
 
-   String and other char buffer compatible objects 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).
+   :class:`bytes`, :class:`bytearray` and other char buffer compatible objects
+   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).
 
    All other objects, including Unicode objects, cause a :exc:`TypeError` to be
    set.

diff --git a/Include/unicodeobject.h b/Include/unicodeobject.h
index 569511f6f76bd8d17d33db275248b1df0a5b4f0e..6448cdab80d9fd6325b4dfa73deec7f87b64ceb9 100644 (file)
--- a/Include/unicodeobject.h
+++ b/Include/unicodeobject.h
@@ -498,14 +498,14 @@ PyAPI_FUNC(PyObject*) PyUnicode_FromUnicode(
     Py_ssize_t size             /* size of buffer */
     );
 
-/* Similar to PyUnicode_FromUnicode(), but u points to Latin-1 encoded bytes */
+/* Similar to PyUnicode_FromUnicode(), but u points to UTF-8 encoded bytes */
 PyAPI_FUNC(PyObject*) PyUnicode_FromStringAndSize(
     const char *u,        /* char buffer */
     Py_ssize_t size       /* size of buffer */
     );
 
 /* Similar to PyUnicode_FromUnicode(), but u points to null-terminated
-   Latin-1 encoded bytes */
+   UTF-8 encoded bytes */
 PyAPI_FUNC(PyObject*) PyUnicode_FromString(
     const char *u        /* string */
     );
@@ -550,7 +550,7 @@ PyAPI_FUNC(int) PyUnicode_Resize(
 
    Coercion is done in the following way:
 
-   1. String and other char buffer compatible objects are decoded
+   1. bytes, bytearray and other char buffer compatible objects are decoded
       under the assumptions that they contain data using the current
       default encoding. Decoding is done in "strict" mode.
 
@@ -574,7 +574,7 @@ PyAPI_FUNC(PyObject*) PyUnicode_FromEncodedObject(
    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 the default encoding as basis for decoding the object.
+   using UTF-8 encoding as basis for decoding the object.
 
    The API returns NULL in case of an error. The caller is responsible
    for decref'ing the returned objects.
@@ -606,7 +606,7 @@ PyAPI_FUNC(void) _Py_ReleaseInternedUnicodeStrings(void);
 
 #ifdef HAVE_WCHAR_H
 
-/* Create a Unicode Object from the whcar_t buffer w of the given
+/* Create a Unicode Object from the wchar_t buffer w of the given
    size.
 
    The buffer is copied into the new object. */
@@ -665,7 +665,7 @@ PyAPI_FUNC(int) PyUnicode_ClearFreeList(void);
    parameters encoding and errors have the same semantics as the ones
    of the builtin unicode() API.
 
-   Setting encoding to NULL causes the default encoding to be used.
+   Setting encoding to NULL causes the default encoding (UTF-8) to be used.
 
    Error handling is set by errors which may also be set to NULL
    meaning to use the default handling defined for the codec. Default

diff --git a/Objects/unicodeobject.c b/Objects/unicodeobject.c
index 4328f9370b69d35bf68ccfdba5c053e6641796a2..b25bcec47f2cc2c7712832dca3d3cb1d61007227 100644 (file)
--- a/Objects/unicodeobject.c
+++ b/Objects/unicodeobject.c
@@ -1273,7 +1273,7 @@ PyObject *PyUnicode_FromEncodedObject(register PyObject *obj,
            case of a TypeError. */
         if (PyErr_ExceptionMatches(PyExc_TypeError))
             PyErr_Format(PyExc_TypeError,
-                         "coercing to str: need string or buffer, "
+                         "coercing to str: need bytes, bytearray or char buffer, "
                          "%.80s found",
                          Py_TYPE(obj)->tp_name);
         goto onError;