[Python-checkins] cpython: _PyBytesWriter: simplify code to avoid "prealloc" parameters

Fri Oct 9 07:16:34 EDT 2015

https://hg.python.org/cpython/rev/cf075c6b1c1e
changeset: 98617:cf075c6b1c1e
user: Victor Stinner <victor.stinner at gmail.com>
date: Fri Oct 09 12:38:53 2015 +0200
summary:
 _PyBytesWriter: simplify code to avoid "prealloc" parameters
Substract preallocate bytes from min_size before calling
_PyBytesWriter_Prepare().
files:
 Objects/bytesobject.c | 16 +++----
 Objects/stringlib/codecs.h | 20 +++++---
 Objects/unicodeobject.c | 58 ++++++++++++-------------
 3 files changed, 47 insertions(+), 47 deletions(-)

diff --git a/Objects/bytesobject.c b/Objects/bytesobject.c
--- a/Objects/bytesobject.c
+++ b/Objects/bytesobject.c
@@ -411,8 +411,7 @@
 
 static char*
 formatfloat(PyObject *v, int flags, int prec, int type,
- PyObject **p_result, _PyBytesWriter *writer, char *str,
- Py_ssize_t prealloc)
+ PyObject **p_result, _PyBytesWriter *writer, char *str)
 {
 char *p;
 PyObject *result;
@@ -437,11 +436,9 @@
 
 len = strlen(p);
 if (writer != NULL) {
- if ((Py_ssize_t)len > prealloc) {
- str = _PyBytesWriter_Prepare(writer, str, len - prealloc);
- if (str == NULL)
- return NULL;
- }
+ str = _PyBytesWriter_Prepare(writer, str, len);
+ if (str == NULL)
+ return NULL;
 Py_MEMCPY(str, p, len);
 str += len;
 return str;
@@ -865,13 +862,14 @@
 && !(flags & (F_SIGN | F_BLANK)))
 {
 /* Fast path */
- res = formatfloat(v, flags, prec, c, NULL, &writer, res, 1);
+ writer.min_size -= 2; /* size preallocated by "%f" */
+ res = formatfloat(v, flags, prec, c, NULL, &writer, res);
 if (res == NULL)
 goto error;
 continue;
 }
 
- if (!formatfloat(v, flags, prec, c, &temp, NULL, res, 1))
+ if (!formatfloat(v, flags, prec, c, &temp, NULL, res))
 goto error;
 pbuf = PyBytes_AS_STRING(temp);
 len = PyBytes_GET_SIZE(temp);
diff --git a/Objects/stringlib/codecs.h b/Objects/stringlib/codecs.h
--- a/Objects/stringlib/codecs.h
+++ b/Objects/stringlib/codecs.h
@@ -345,7 +345,9 @@
 break;
 
 case _Py_ERROR_BACKSLASHREPLACE:
- p = backslashreplace(&writer, max_char_size, p,
+ /* substract preallocated bytes */
+ writer.min_size -= max_char_size * (endpos - startpos);
+ p = backslashreplace(&writer, p,
 unicode, startpos, endpos);
 if (p == NULL)
 goto error;
@@ -353,7 +355,9 @@
 break;
 
 case _Py_ERROR_XMLCHARREFREPLACE:
- p = xmlcharrefreplace(&writer, max_char_size, p,
+ /* substract preallocated bytes */
+ writer.min_size -= max_char_size * (endpos - startpos);
+ p = xmlcharrefreplace(&writer, p,
 unicode, startpos, endpos);
 if (p == NULL)
 goto error;
@@ -381,17 +385,17 @@
 if (!rep)
 goto error;
 
+ /* substract preallocated bytes */
+ writer.min_size -= max_char_size;
+
 if (PyBytes_Check(rep))
 repsize = PyBytes_GET_SIZE(rep);
 else
 repsize = PyUnicode_GET_LENGTH(rep);
 
- if (repsize > max_char_size) {
- p = _PyBytesWriter_Prepare(&writer, p,
- repsize - max_char_size);
- if (p == NULL)
- goto error;
- }
+ p = _PyBytesWriter_Prepare(&writer, p, repsize);
+ if (p == NULL)
+ goto error;
 
 if (PyBytes_Check(rep)) {
 memcpy(p, PyBytes_AS_STRING(rep), repsize);
diff --git a/Objects/unicodeobject.c b/Objects/unicodeobject.c
--- a/Objects/unicodeobject.c
+++ b/Objects/unicodeobject.c
@@ -565,11 +565,10 @@
 /* Implementation of the "backslashreplace" error handler for 8-bit encodings:
 ASCII, Latin1, UTF-8, etc. */
 static char*
-backslashreplace(_PyBytesWriter *writer, Py_ssize_t prealloc_per_char,
- char *str,
+backslashreplace(_PyBytesWriter *writer, char *str,
 PyObject *unicode, Py_ssize_t collstart, Py_ssize_t collend)
 {
- Py_ssize_t size, i, prealloc;
+ Py_ssize_t size, i;
 Py_UCS4 ch;
 enum PyUnicode_Kind kind;
 void *data;
@@ -600,12 +599,9 @@
 size += incr;
 }
 
- prealloc = prealloc_per_char * (collend - collstart);
- if (size > prealloc) {
- str = _PyBytesWriter_Prepare(writer, str, size - prealloc);
- if (str == NULL)
- return NULL;
- }
+ str = _PyBytesWriter_Prepare(writer, str, size);
+ if (str == NULL)
+ return NULL;
 
 /* generate replacement */
 for (i = collstart; i < collend; ++i) {
@@ -636,11 +632,10 @@
 /* Implementation of the "xmlcharrefreplace" error handler for 8-bit encodings:
 ASCII, Latin1, UTF-8, etc. */
 static char*
-xmlcharrefreplace(_PyBytesWriter *writer, Py_ssize_t prealloc_per_char,
- char *str,
+xmlcharrefreplace(_PyBytesWriter *writer, char *str,
 PyObject *unicode, Py_ssize_t collstart, Py_ssize_t collend)
 {
- Py_ssize_t size, i, prealloc;
+ Py_ssize_t size, i;
 Py_UCS4 ch;
 enum PyUnicode_Kind kind;
 void *data;
@@ -679,12 +674,9 @@
 size += incr;
 }
 
- prealloc = prealloc_per_char * (collend - collstart);
- if (size > prealloc) {
- str = _PyBytesWriter_Prepare(writer, str, size - prealloc);
- if (str == NULL)
- return NULL;
- }
+ str = _PyBytesWriter_Prepare(writer, str, size);
+ if (str == NULL)
+ return NULL;
 
 /* generate replacement */
 for (i = collstart; i < collend; ++i) {
@@ -6666,7 +6658,9 @@
 break;
 
 case _Py_ERROR_BACKSLASHREPLACE:
- str = backslashreplace(&writer, 1, str,
+ /* substract preallocated bytes */
+ writer.min_size -= (collend - collstart);
+ str = backslashreplace(&writer, str,
 unicode, collstart, collend);
 if (str == NULL)
 goto onError;
@@ -6674,7 +6668,9 @@
 break;
 
 case _Py_ERROR_XMLCHARREFREPLACE:
- str = xmlcharrefreplace(&writer, 1, str,
+ /* substract preallocated bytes */
+ writer.min_size -= (collend - collstart);
+ str = xmlcharrefreplace(&writer, str,
 unicode, collstart, collend);
 if (str == NULL)
 goto onError;
@@ -6705,14 +6701,17 @@
 PyUnicode_READY(repunicode) == -1))
 goto onError;
 
+ /* substract preallocated bytes */
+ writer.min_size -= 1;
+
 if (PyBytes_Check(repunicode)) {
 /* Directly copy bytes result to output. */
 repsize = PyBytes_Size(repunicode);
- if (repsize > 1) {
- str = _PyBytesWriter_Prepare(&writer, str, repsize-1);
- if (str == NULL)
- goto onError;
- }
+
+ str = _PyBytesWriter_Prepare(&writer, str, repsize);
+ if (str == NULL)
+ goto onError;
+
 memcpy(str, PyBytes_AsString(repunicode), repsize);
 str += repsize;
 pos = newpos;
@@ -6724,11 +6723,10 @@
 have+the replacement+the rest of the string, so
 we won't have to check space for encodable characters) */
 repsize = PyUnicode_GET_LENGTH(repunicode);
- if (repsize > 1) {
- str = _PyBytesWriter_Prepare(&writer, str, repsize-1);
- if (str == NULL)
- goto onError;
- }
+
+ str = _PyBytesWriter_Prepare(&writer, str, repsize);
+ if (str == NULL)
+ goto onError;
 
 /* check if there is anything unencodable in the replacement
 and copy it to the output */
-- 
Repository URL: https://hg.python.org/cpython
