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

@ -633,7 +633,8 @@ MultibyteCodec_Decode(MultibyteCodecObject *self,
return make_tuple(PyUnicode_New(0, 0), 0);
}
_PyUnicodeWriter_Init(&buf.writer, datalen);
_PyUnicodeWriter_Init(&buf.writer);
buf.writer.min_length = datalen;
buf.excobj = NULL;
buf.inbuf = buf.inbuf_top = (unsigned char *)data;
buf.inbuf_end = buf.inbuf_top + datalen;
@ -839,7 +840,7 @@ decoder_prepare_buffer(MultibyteDecodeBuffer *buf, const char *data,
{
buf->inbuf = buf->inbuf_top = (const unsigned char *)data;
buf->inbuf_end = buf->inbuf_top + size;
_PyUnicodeWriter_Init(&buf->writer, size);
buf->writer.min_length += size;
return 0;
}
@ -1037,7 +1038,7 @@ mbidecoder_decode(MultibyteIncrementalDecoderObject *self,
data = pdata.buf;
size = pdata.len;
_PyUnicodeWriter_Init(&buf.writer, 1);
_PyUnicodeWriter_Init(&buf.writer);
buf.excobj = NULL;
origpending = self->pendingsize;
@ -1241,7 +1242,7 @@ mbstreamreader_iread(MultibyteStreamReaderObject *self,
if (sizehint == 0)
return PyUnicode_New(0, 0);
_PyUnicodeWriter_Init(&buf.writer, 1);
_PyUnicodeWriter_Init(&buf.writer);
buf.excobj = NULL;
cres = NULL;