PyUnicode_EncodeFS() raises an exception if _Py_wchar2char() fails

 * Add error_pos optional argument to _Py_wchar2char()
 * PyUnicode_EncodeFS() raises a UnicodeEncodeError or MemoryError if
   _Py_wchar2char() fails

diff --git a/Include/fileutils.h b/Include/fileutils.h
index 11ebebfba9c877a55be5a35f6eb0ed6b7a14f3de..2fade9b95cd8364947a24c478569e86543abcc4d 100644 (file)
--- a/Include/fileutils.h
+++ b/Include/fileutils.h
@@ -10,7 +10,8 @@ PyAPI_FUNC(wchar_t *) _Py_char2wchar(
     size_t *size);
 
 PyAPI_FUNC(char*) _Py_wchar2char(
-    const wchar_t *text);
+    const wchar_t *text,
+    size_t *error_pos);
 
 #if defined(HAVE_STAT) && !defined(MS_WINDOWS)
 PyAPI_FUNC(int) _Py_wstat(

diff --git a/Modules/main.c b/Modules/main.c
index 008b6a4d10efceecdc298eea11da06ba8a4391d6..590104d88831f967f87030f20dd1449b0db05a17 100644 (file)
--- a/Modules/main.c
+++ b/Modules/main.c
@@ -646,7 +646,7 @@ Py_Main(int argc, wchar_t **argv)
             if (fp == NULL) {
                 char *cfilename_buffer;
                 const char *cfilename;
-                cfilename_buffer = _Py_wchar2char(filename);
+                cfilename_buffer = _Py_wchar2char(filename, NULL);
                 if (cfilename_buffer != NULL)
                     cfilename = cfilename_buffer;
                 else

diff --git a/Objects/unicodeobject.c b/Objects/unicodeobject.c
index cff756a1cece738fa7aeb4997d51e6fabd0d2c79..2250f45e9a379c2c60c441f2f0615f84dc91146a 100644 (file)
--- a/Objects/unicodeobject.c
+++ b/Objects/unicodeobject.c
@@ -1606,14 +1606,31 @@ PyUnicode_EncodeFSDefault(PyObject *unicode)
         wchar_t *wchar;
         char *bytes;
         PyObject *bytes_obj;
+        size_t error_pos;
 
         wchar = PyUnicode_AsWideCharString(unicode, NULL);
         if (wchar == NULL)
             return NULL;
-        bytes = _Py_wchar2char(wchar);
-        PyMem_Free(wchar);
-        if (bytes == NULL)
+        bytes = _Py_wchar2char(wchar, &error_pos);
+        if (bytes == NULL) {
+            if (error_pos != (size_t)-1) {
+                char *errmsg = strerror(errno);
+                PyObject *exc = NULL;
+                if (errmsg == NULL)
+                    errmsg = "Py_wchar2char() failed";
+                raise_encode_exception(&exc,
+                    "filesystemencoding",
+                    PyUnicode_AS_UNICODE(unicode), PyUnicode_GET_SIZE(unicode),
+                    error_pos, error_pos+1,
+                    errmsg);
+                Py_XDECREF(exc);
+            }
+            else
+                PyErr_NoMemory();
+            PyMem_Free(wchar);
             return NULL;
+        }
+        PyMem_Free(wchar);
 
         bytes_obj = PyBytes_FromString(bytes);
         PyMem_Free(bytes);

diff --git a/Python/fileutils.c b/Python/fileutils.c
index 03fc0cb79dd3de26fda10cac7ea3c3bc2b1e9c69..18e98e513c6298e034f28544de66f3853ce80270 100644 (file)
--- a/Python/fileutils.c
+++ b/Python/fileutils.c
@@ -132,15 +132,21 @@ oom:
    This function is the reverse of _Py_char2wchar().
 
    Return a pointer to a newly allocated byte string (use PyMem_Free() to free
-   the memory), or NULL on error (conversion error or memory error). */
+   the memory), or NULL on conversion or memory allocation error.
+
+   If error_pos is not NULL: *error_pos is the index of the invalid character
+   on conversion error, or (size_t)-1 otherwise. */
 char*
-_Py_wchar2char(const wchar_t *text)
+_Py_wchar2char(const wchar_t *text, size_t *error_pos)
 {
     const size_t len = wcslen(text);
     char *result = NULL, *bytes = NULL;
     size_t i, size, converted;
     wchar_t c, buf[2];
 
+    if (error_pos != NULL)
+        *error_pos = (size_t)-1;
+
     /* The function works in two steps:
        1. compute the length of the output buffer in bytes (size)
        2. outputs the bytes */
@@ -168,6 +174,8 @@ _Py_wchar2char(const wchar_t *text)
                 if (converted == (size_t)-1) {
                     if (result != NULL)
                         PyMem_Free(result);
+                    if (error_pos != NULL)
+                        *error_pos = i;
                     return NULL;
                 }
                 if (bytes != NULL) {
@@ -208,7 +216,7 @@ _Py_wstat(const wchar_t* path, struct stat *buf)
 {
     int err;
     char *fname;
-    fname = _Py_wchar2char(path);
+    fname = _Py_wchar2char(path, NULL);
     if (fname == NULL) {
         errno = EINVAL;
         return -1;
@@ -263,7 +271,7 @@ _Py_wfopen(const wchar_t *path, const wchar_t *mode)
         errno = EINVAL;
         return NULL;
     }
-    cpath = _Py_wchar2char(path);
+    cpath = _Py_wchar2char(path, NULL);
     if (cpath == NULL)
         return NULL;
     f = fopen(cpath, cmode);
@@ -317,7 +325,7 @@ _Py_wreadlink(const wchar_t *path, wchar_t *buf, size_t bufsiz)
     int res;
     size_t r1;
 
-    cpath = _Py_wchar2char(path);
+    cpath = _Py_wchar2char(path, NULL);
     if (cpath == NULL) {
         errno = EINVAL;
         return -1;
@@ -361,7 +369,7 @@ _Py_wrealpath(const wchar_t *path,
     wchar_t *wresolved_path;
     char *res;
     size_t r;
-    cpath = _Py_wchar2char(path);
+    cpath = _Py_wchar2char(path, NULL);
     if (cpath == NULL) {
         errno = EINVAL;
         return NULL;