Close #17694: Add minimum length to _PyUnicodeWriter

* Add also min_char attribute to _PyUnicodeWriter structure (currently unused)
 * _PyUnicodeWriter_Init() has no more argument (except the writer itself):
   min_length and overallocate must be set explicitly
 * In error handlers, only enable overallocation if the replacement string
   is longer than 1 character
 * CJK decoders don't use overallocation anymore
 * Set min_length, instead of preallocating memory using
   _PyUnicodeWriter_Prepare(), in many decoders
 * _PyUnicode_DecodeUnicodeInternal() checks for integer overflow
This commit is contained in:
Victor Stinner 2013-04-17 23:02:17 +02:00
parent e84a51c38e
commit 8f674ccd64
7 changed files with 81 additions and 71 deletions

View file

@ -898,22 +898,28 @@ typedef struct {
Py_UCS4 maxchar;
Py_ssize_t size;
Py_ssize_t pos;
/* minimum length of the buffer when overallocation is enabled,
see _PyUnicodeWriter_Init() */
/* minimum number of allocated characters (default: 0) */
Py_ssize_t min_length;
/* minimum character (default: 127, ASCII) */
Py_UCS4 min_char;
/* If non-zero, overallocate the buffer by 25% (default: 0). */
unsigned char overallocate;
/* If readonly is 1, buffer is a shared string (cannot be modified)
and size is set to 0. */
unsigned char readonly;
} _PyUnicodeWriter ;
/* Initialize a Unicode writer.
If min_length is greater than zero, _PyUnicodeWriter_Prepare()
overallocates the buffer and min_length is the minimum length in characters
of the buffer. */
*
* By default, the minimum buffer size is 0 character and overallocation is
* disabled. Set min_length, min_char and overallocate attributes to control
* the allocation of the buffer. */
PyAPI_FUNC(void)
_PyUnicodeWriter_Init(_PyUnicodeWriter *writer, Py_ssize_t min_length);
_PyUnicodeWriter_Init(_PyUnicodeWriter *writer);
/* Prepare the buffer to write 'length' characters
with the specified maximum character.