summaryrefslogtreecommitdiff
path: root/Objects
diff options
context:
space:
mode:
Diffstat (limited to 'Objects')
-rw-r--r--Objects/abstract.c11
-rw-r--r--Objects/bytearrayobject.c100
-rw-r--r--Objects/bytesobject.c1344
-rw-r--r--Objects/dictobject.c55
-rw-r--r--Objects/listsort.txt2
-rw-r--r--Objects/longobject.c126
-rw-r--r--Objects/object.c5
-rw-r--r--Objects/setobject.c575
-rw-r--r--Objects/stringlib/codecs.h201
-rw-r--r--Objects/stringlib/fastsearch.h150
-rw-r--r--Objects/stringlib/unicode_format.h2
-rw-r--r--Objects/structseq.c24
-rw-r--r--Objects/typeobject.c62
-rw-r--r--Objects/unicodeobject.c836
14 files changed, 2145 insertions, 1348 deletions
diff --git a/Objects/abstract.c b/Objects/abstract.c
index a0362e74e4..3e1ff97547 100644
--- a/Objects/abstract.c
+++ b/Objects/abstract.c
@@ -141,8 +141,11 @@ PyObject_GetItem(PyObject *o, PyObject *key)
return null_error();
m = o->ob_type->tp_as_mapping;
- if (m && m->mp_subscript)
- return m->mp_subscript(o, key);
+ if (m && m->mp_subscript) {
+ PyObject *item = m->mp_subscript(o, key);
+ assert((item != NULL) ^ (PyErr_Occurred() != NULL));
+ return item;
+ }
if (o->ob_type->tp_as_sequence) {
if (PyIndex_Check(key)) {
@@ -1544,8 +1547,10 @@ PySequence_GetItem(PyObject *s, Py_ssize_t i)
if (i < 0) {
if (m->sq_length) {
Py_ssize_t l = (*m->sq_length)(s);
- if (l < 0)
+ if (l < 0) {
+ assert(PyErr_Occurred());
return NULL;
+ }
i += l;
}
}
diff --git a/Objects/bytearrayobject.c b/Objects/bytearrayobject.c
index c59ad2499a..96ab57d24c 100644
--- a/Objects/bytearrayobject.c
+++ b/Objects/bytearrayobject.c
@@ -282,26 +282,14 @@ PyByteArray_Concat(PyObject *a, PyObject *b)
static PyObject *
bytearray_format(PyByteArrayObject *self, PyObject *args)
{
- PyObject *bytes_in, *bytes_out, *res;
- char *bytestring;
-
- if (self == NULL || !PyByteArray_Check(self) || args == NULL) {
+ if (self == NULL || !PyByteArray_Check(self)) {
PyErr_BadInternalCall();
return NULL;
}
- bytestring = PyByteArray_AS_STRING(self);
- bytes_in = PyBytes_FromString(bytestring);
- if (bytes_in == NULL)
- return NULL;
- bytes_out = _PyBytes_Format(bytes_in, args);
- Py_DECREF(bytes_in);
- if (bytes_out == NULL)
- return NULL;
- res = PyByteArray_FromObject(bytes_out);
- Py_DECREF(bytes_out);
- if (res == NULL)
- return NULL;
- return res;
+
+ return _PyBytes_FormatEx(PyByteArray_AS_STRING(self),
+ PyByteArray_GET_SIZE(self),
+ args, 1);
}
/* Functions stuffed into the type object */
@@ -1171,16 +1159,15 @@ bytearray_find_internal(PyByteArrayObject *self, PyObject *args, int dir)
ADJUST_INDICES(start, end, len);
if (end - start < sub_len)
res = -1;
- else if (sub_len == 1
-#ifndef HAVE_MEMRCHR
- && dir > 0
-#endif
- ) {
- unsigned char needle = *sub;
- int mode = (dir > 0) ? FAST_SEARCH : FAST_RSEARCH;
- res = stringlib_fastsearch_memchr_1char(
- PyByteArray_AS_STRING(self) + start, end - start,
- needle, needle, mode);
+ else if (sub_len == 1) {
+ if (dir > 0)
+ res = stringlib_find_char(
+ PyByteArray_AS_STRING(self) + start, end - start,
+ *sub);
+ else
+ res = stringlib_rfind_char(
+ PyByteArray_AS_STRING(self) + start, end - start,
+ *sub);
if (res >= 0)
res += start;
}
@@ -2801,22 +2788,6 @@ bytearray_splitlines_impl(PyByteArrayObject *self, int keepends)
);
}
-static int
-hex_digit_to_int(Py_UCS4 c)
-{
- if (c >= 128)
- return -1;
- if (Py_ISDIGIT(c))
- return c - '0';
- else {
- if (Py_ISUPPER(c))
- c = Py_TOLOWER(c);
- if (c >= 'a' && c <= 'f')
- return c - 'a' + 10;
- }
- return -1;
-}
-
/*[clinic input]
@classmethod
bytearray.fromhex
@@ -2835,48 +2806,7 @@ static PyObject *
bytearray_fromhex_impl(PyObject*cls, PyObject *string)
/*[clinic end generated code: output=df3da60129b3700c input=907bbd2d34d9367a]*/
{
- PyObject *newbytes;
- char *buf;
- Py_ssize_t hexlen, byteslen, i, j;
- int top, bot;
- void *data;
- unsigned int kind;
-
- assert(PyUnicode_Check(string));
- if (PyUnicode_READY(string))
- return NULL;
- kind = PyUnicode_KIND(string);
- data = PyUnicode_DATA(string);
- hexlen = PyUnicode_GET_LENGTH(string);
-
- byteslen = hexlen/2; /* This overestimates if there are spaces */
- newbytes = PyByteArray_FromStringAndSize(NULL, byteslen);
- if (!newbytes)
- return NULL;
- buf = PyByteArray_AS_STRING(newbytes);
- for (i = j = 0; i < hexlen; i += 2) {
- /* skip over spaces in the input */
- while (PyUnicode_READ(kind, data, i) == ' ')
- i++;
- if (i >= hexlen)
- break;
- top = hex_digit_to_int(PyUnicode_READ(kind, data, i));
- bot = hex_digit_to_int(PyUnicode_READ(kind, data, i+1));
- if (top == -1 || bot == -1) {
- PyErr_Format(PyExc_ValueError,
- "non-hexadecimal number found in "
- "fromhex() arg at position %zd", i);
- goto error;
- }
- buf[j++] = (top << 4) + bot;
- }
- if (PyByteArray_Resize(newbytes, j) < 0)
- goto error;
- return newbytes;
-
- error:
- Py_DECREF(newbytes);
- return NULL;
+ return _PyBytes_FromHex(string, 1);
}
PyDoc_STRVAR(hex__doc__,
diff --git a/Objects/bytesobject.c b/Objects/bytesobject.c
index 51d0871c8b..f9805162fe 100644
--- a/Objects/bytesobject.c
+++ b/Objects/bytesobject.c
@@ -30,6 +30,10 @@ static PyBytesObject *nullstring;
*/
#define PyBytesObject_SIZE (offsetof(PyBytesObject, ob_sval) + 1)
+/* Forward declaration */
+Py_LOCAL_INLINE(Py_ssize_t) _PyBytesWriter_GetSize(_PyBytesWriter *writer,
+ char *str);
+
/*
For PyBytes_FromString(), the parameter `str' points to a null-terminated
string containing exactly `size' bytes.
@@ -174,190 +178,184 @@ PyBytes_FromString(const char *str)
PyObject *
PyBytes_FromFormatV(const char *format, va_list vargs)
{
- va_list count;
- Py_ssize_t n = 0;
- const char* f;
char *s;
- PyObject* string;
+ const char *f;
+ const char *p;
+ Py_ssize_t prec;
+ int longflag;
+ int size_tflag;
+ /* Longest 64-bit formatted numbers:
+ - "18446744073709551615\0" (21 bytes)
+ - "-9223372036854775808\0" (21 bytes)
+ Decimal takes the most space (it isn't enough for octal.)
+
+ Longest 64-bit pointer representation:
+ "0xffffffffffffffff\0" (19 bytes). */
+ char buffer[21];
+ _PyBytesWriter writer;
+
+ _PyBytesWriter_Init(&writer);
+
+ s = _PyBytesWriter_Alloc(&writer, strlen(format));
+ if (s == NULL)
+ return NULL;
+ writer.overallocate = 1;
+
+#define WRITE_BYTES(str) \
+ do { \
+ s = _PyBytesWriter_WriteBytes(&writer, s, (str), strlen(str)); \
+ if (s == NULL) \
+ goto error; \
+ } while (0)
- Py_VA_COPY(count, vargs);
- /* step 1: figure out how large a buffer we need */
for (f = format; *f; f++) {
- if (*f == '%') {
- const char* p = f;
- while (*++f && *f != '%' && !Py_ISALPHA(*f))
- ;
-
- /* skip the 'l' or 'z' in {%ld, %zd, %lu, %zu} since
- * they don't affect the amount of space we reserve.
- */
- if ((*f == 'l' || *f == 'z') &&
- (f[1] == 'd' || f[1] == 'u'))
- ++f;
-
- switch (*f) {
- case 'c':
- {
- int c = va_arg(count, int);
- if (c < 0 || c > 255) {
- PyErr_SetString(PyExc_OverflowError,
- "PyBytes_FromFormatV(): %c format "
- "expects an integer in range [0; 255]");
- return NULL;
- }
- n++;
- break;
+ if (*f != '%') {
+ *s++ = *f;
+ continue;
+ }
+
+ p = f++;
+
+ /* ignore the width (ex: 10 in "%10s") */
+ while (Py_ISDIGIT(*f))
+ f++;
+
+ /* parse the precision (ex: 10 in "%.10s") */
+ prec = 0;
+ if (*f == '.') {
+ f++;
+ for (; Py_ISDIGIT(*f); f++) {
+ prec = (prec * 10) + (*f - '0');
}
- case '%':
- n++;
- break;
- case 'd': case 'u': case 'i': case 'x':
- (void) va_arg(count, int);
- /* 20 bytes is enough to hold a 64-bit
- integer. Decimal takes the most space.
- This isn't enough for octal. */
- n += 20;
- break;
- case 's':
- s = va_arg(count, char*);
- n += strlen(s);
- break;
- case 'p':
- (void) va_arg(count, int);
- /* maximum 64-bit pointer representation:
- * 0xffffffffffffffff
- * so 19 characters is enough.
- * XXX I count 18 -- what's the extra for?
- */
- n += 19;
- break;
- default:
- /* if we stumble upon an unknown
- formatting code, copy the rest of
- the format string to the output
- string. (we cannot just skip the
- code, since there's no way to know
- what's in the argument list) */
- n += strlen(p);
- goto expand;
+ }
+
+ while (*f && *f != '%' && !Py_ISALPHA(*f))
+ f++;
+
+ /* handle the long flag ('l'), but only for %ld and %lu.
+ others can be added when necessary. */
+ longflag = 0;
+ if (*f == 'l' && (f[1] == 'd' || f[1] == 'u')) {
+ longflag = 1;
+ ++f;
+ }
+
+ /* handle the size_t flag ('z'). */
+ size_tflag = 0;
+ if (*f == 'z' && (f[1] == 'd' || f[1] == 'u')) {
+ size_tflag = 1;
+ ++f;
+ }
+
+ /* substract bytes preallocated for the format string
+ (ex: 2 for "%s") */
+ writer.min_size -= (f - p + 1);
+
+ switch (*f) {
+ case 'c':
+ {
+ int c = va_arg(vargs, int);
+ if (c < 0 || c > 255) {
+ PyErr_SetString(PyExc_OverflowError,
+ "PyBytes_FromFormatV(): %c format "
+ "expects an integer in range [0; 255]");
+ goto error;
}
- } else
- n++;
- }
- expand:
- /* step 2: fill the buffer */
- /* Since we've analyzed how much space we need for the worst case,
- use sprintf directly instead of the slower PyOS_snprintf. */
- string = PyBytes_FromStringAndSize(NULL, n);
- if (!string)
- return NULL;
+ writer.min_size++;
+ *s++ = (unsigned char)c;
+ break;
+ }
- s = PyBytes_AsString(string);
+ case 'd':
+ if (longflag)
+ sprintf(buffer, "%ld", va_arg(vargs, long));
+ else if (size_tflag)
+ sprintf(buffer, "%" PY_FORMAT_SIZE_T "d",
+ va_arg(vargs, Py_ssize_t));
+ else
+ sprintf(buffer, "%d", va_arg(vargs, int));
+ assert(strlen(buffer) < sizeof(buffer));
+ WRITE_BYTES(buffer);
+ break;
- for (f = format; *f; f++) {
- if (*f == '%') {
- const char* p = f++;
+ case 'u':
+ if (longflag)
+ sprintf(buffer, "%lu",
+ va_arg(vargs, unsigned long));
+ else if (size_tflag)
+ sprintf(buffer, "%" PY_FORMAT_SIZE_T "u",
+ va_arg(vargs, size_t));
+ else
+ sprintf(buffer, "%u",
+ va_arg(vargs, unsigned int));
+ assert(strlen(buffer) < sizeof(buffer));
+ WRITE_BYTES(buffer);
+ break;
+
+ case 'i':
+ sprintf(buffer, "%i", va_arg(vargs, int));
+ assert(strlen(buffer) < sizeof(buffer));
+ WRITE_BYTES(buffer);
+ break;
+
+ case 'x':
+ sprintf(buffer, "%x", va_arg(vargs, int));
+ assert(strlen(buffer) < sizeof(buffer));
+ WRITE_BYTES(buffer);
+ break;
+
+ case 's':
+ {
Py_ssize_t i;
- int longflag = 0;
- int size_tflag = 0;
- /* parse the width.precision part (we're only
- interested in the precision value, if any) */
- n = 0;
- while (Py_ISDIGIT(*f))
- n = (n*10) + *f++ - '0';
- if (*f == '.') {
- f++;
- n = 0;
- while (Py_ISDIGIT(*f))
- n = (n*10) + *f++ - '0';
- }
- while (*f && *f != '%' && !Py_ISALPHA(*f))
- f++;
- /* handle the long flag, but only for %ld and %lu.
- others can be added when necessary. */
- if (*f == 'l' && (f[1] == 'd' || f[1] == 'u')) {
- longflag = 1;
- ++f;
- }
- /* handle the size_t flag. */
- if (*f == 'z' && (f[1] == 'd' || f[1] == 'u')) {
- size_tflag = 1;
- ++f;
- }
- switch (*f) {
- case 'c':
- {
- int c = va_arg(vargs, int);
- /* c has been checked for overflow in the first step */
- *s++ = (unsigned char)c;
- break;
+ p = va_arg(vargs, char*);
+ i = strlen(p);
+ if (prec > 0 && i > prec)
+ i = prec;
+ s = _PyBytesWriter_WriteBytes(&writer, s, p, i);
+ if (s == NULL)
+ goto error;
+ break;
+ }
+
+ case 'p':
+ sprintf(buffer, "%p", va_arg(vargs, void*));
+ assert(strlen(buffer) < sizeof(buffer));
+ /* %p is ill-defined: ensure leading 0x. */
+ if (buffer[1] == 'X')
+ buffer[1] = 'x';
+ else if (buffer[1] != 'x') {
+ memmove(buffer+2, buffer, strlen(buffer)+1);
+ buffer[0] = '0';
+ buffer[1] = 'x';
}
- case 'd':
- if (longflag)
- sprintf(s, "%ld", va_arg(vargs, long));
- else if (size_tflag)
- sprintf(s, "%" PY_FORMAT_SIZE_T "d",
- va_arg(vargs, Py_ssize_t));
- else
- sprintf(s, "%d", va_arg(vargs, int));
- s += strlen(s);
- break;
- case 'u':
- if (longflag)
- sprintf(s, "%lu",
- va_arg(vargs, unsigned long));
- else if (size_tflag)
- sprintf(s, "%" PY_FORMAT_SIZE_T "u",
- va_arg(vargs, size_t));
- else
- sprintf(s, "%u",
- va_arg(vargs, unsigned int));
- s += strlen(s);
- break;
- case 'i':
- sprintf(s, "%i", va_arg(vargs, int));
- s += strlen(s);
- break;
- case 'x':
- sprintf(s, "%x", va_arg(vargs, int));
- s += strlen(s);
- break;
- case 's':
- p = va_arg(vargs, char*);
- i = strlen(p);
- if (n > 0 && i > n)
- i = n;
- Py_MEMCPY(s, p, i);
- s += i;
- break;
- case 'p':
- sprintf(s, "%p", va_arg(vargs, void*));
- /* %p is ill-defined: ensure leading 0x. */
- if (s[1] == 'X')
- s[1] = 'x';
- else if (s[1] != 'x') {
- memmove(s+2, s, strlen(s)+1);
- s[0] = '0';
- s[1] = 'x';
- }
- s += strlen(s);
- break;
- case '%':
- *s++ = '%';
- break;
- default:
- strcpy(s, p);
- s += strlen(s);
- goto end;
+ WRITE_BYTES(buffer);
+ break;
+
+ case '%':
+ writer.min_size++;
+ *s++ = '%';
+ break;
+
+ default:
+ if (*f == 0) {
+ /* fix min_size if we reached the end of the format string */
+ writer.min_size++;
}
- } else
- *s++ = *f;
+
+ /* invalid format string: copy unformatted string and exit */
+ WRITE_BYTES(p);
+ return _PyBytesWriter_Finish(&writer, s);
+ }
}
- end:
- _PyBytes_Resize(&string, s - PyBytes_AS_STRING(string));
- return string;
+#undef WRITE_BYTES
+
+ return _PyBytesWriter_Finish(&writer, s);
+
+ error:
+ _PyBytesWriter_Dealloc(&writer);
+ return NULL;
}
PyObject *
@@ -409,12 +407,14 @@ getnextarg(PyObject *args, Py_ssize_t arglen, Py_ssize_t *p_argidx)
/* Returns a new reference to a PyBytes object, or NULL on failure. */
-static PyObject *
-formatfloat(PyObject *v, int flags, int prec, int type)
+static char*
+formatfloat(PyObject *v, int flags, int prec, int type,
+ PyObject **p_result, _PyBytesWriter *writer, char *str)
{
char *p;
PyObject *result;
double x;
+ size_t len;
x = PyFloat_AsDouble(v);
if (x == -1.0 && PyErr_Occurred()) {
@@ -431,9 +431,21 @@ formatfloat(PyObject *v, int flags, int prec, int type)
if (p == NULL)
return NULL;
- result = PyBytes_FromStringAndSize(p, strlen(p));
+
+ len = strlen(p);
+ if (writer != NULL) {
+ str = _PyBytesWriter_Prepare(writer, str, len);
+ if (str == NULL)
+ return NULL;
+ Py_MEMCPY(str, p, len);
+ str += len;
+ return str;
+ }
+
+ result = PyBytes_FromStringAndSize(p, len);
PyMem_Free(p);
- return result;
+ *p_result = result;
+ return str;
}
static PyObject *
@@ -557,36 +569,36 @@ format_obj(PyObject *v, const char **pbuf, Py_ssize_t *plen)
return NULL;
}
-/* fmt%(v1,v2,...) is roughly equivalent to sprintf(fmt, v1, v2, ...)
-
- FORMATBUFLEN is the length of the buffer in which the ints &
- chars are formatted. XXX This is a magic number. Each formatting
- routine does bounds checking to ensure no overflow, but a better
- solution may be to malloc a buffer of appropriate size for each
- format. For now, the current solution is sufficient.
-*/
-#define FORMATBUFLEN (size_t)120
+/* fmt%(v1,v2,...) is roughly equivalent to sprintf(fmt, v1, v2, ...) */
PyObject *
-_PyBytes_Format(PyObject *format, PyObject *args)
+_PyBytes_FormatEx(const char *format, Py_ssize_t format_len,
+ PyObject *args, int use_bytearray)
{
- char *fmt, *res;
+ const char *fmt;
+ char *res;
Py_ssize_t arglen, argidx;
- Py_ssize_t reslen, rescnt, fmtcnt;
+ Py_ssize_t fmtcnt;
int args_owned = 0;
- PyObject *result;
PyObject *dict = NULL;
- if (format == NULL || !PyBytes_Check(format) || args == NULL) {
+ _PyBytesWriter writer;
+
+ if (args == NULL) {
PyErr_BadInternalCall();
return NULL;
}
- fmt = PyBytes_AS_STRING(format);
- fmtcnt = PyBytes_GET_SIZE(format);
- reslen = rescnt = fmtcnt + 100;
- result = PyBytes_FromStringAndSize((char *)NULL, reslen);
- if (result == NULL)
+ fmt = format;
+ fmtcnt = format_len;
+
+ _PyBytesWriter_Init(&writer);
+ writer.use_bytearray = use_bytearray;
+
+ res = _PyBytesWriter_Alloc(&writer, fmtcnt);
+ if (res == NULL)
return NULL;
- res = PyBytes_AsString(result);
+ if (!use_bytearray)
+ writer.overallocate = 1;
+
if (PyTuple_Check(args)) {
arglen = PyTuple_GET_SIZE(args);
argidx = 0;
@@ -600,18 +612,23 @@ _PyBytes_Format(PyObject *format, PyObject *args)
!PyByteArray_Check(args)) {
dict = args;
}
+
while (--fmtcnt >= 0) {
if (*fmt != '%') {
- if (--rescnt < 0) {
- rescnt = fmtcnt + 100;
- reslen += rescnt;
- if (_PyBytes_Resize(&result, reslen))
- return NULL;
- res = PyBytes_AS_STRING(result)
- + reslen - rescnt;
- --rescnt;
- }
- *res++ = *fmt++;
+ Py_ssize_t len;
+ char *pos;
+
+ pos = strchr(fmt + 1, '%');
+ if (pos != NULL)
+ len = pos - fmt;
+ else
+ len = format_len - (fmt - format);
+ assert(len != 0);
+
+ Py_MEMCPY(res, fmt, len);
+ res += len;
+ fmt += len;
+ fmtcnt -= (len - 1);
}
else {
/* Got a format specifier */
@@ -626,10 +643,14 @@ _PyBytes_Format(PyObject *format, PyObject *args)
int sign;
Py_ssize_t len = 0;
char onechar; /* For byte_converter() */
+ Py_ssize_t alloc;
+#ifdef Py_DEBUG
+ char *before;
+#endif
fmt++;
if (*fmt == '(') {
- char *keystart;
+ const char *keystart;
Py_ssize_t keylen;
PyObject *key;
int pcount = 1;
@@ -673,6 +694,8 @@ _PyBytes_Format(PyObject *format, PyObject *args)
arglen = -1;
argidx = -2;
}
+
+ /* Parse flags. Example: "%+i" => flags=F_SIGN. */
while (--fmtcnt >= 0) {
switch (c = *fmt++) {
case '-': flags |= F_LJUST; continue;
@@ -683,6 +706,8 @@ _PyBytes_Format(PyObject *format, PyObject *args)
}
break;
}
+
+ /* Parse width. Example: "%10s" => width=10 */
if (c == '*') {
v = getnextarg(args, arglen, &argidx);
if (v == NULL)
@@ -717,6 +742,8 @@ _PyBytes_Format(PyObject *format, PyObject *args)
width = width*10 + (c - '0');
}
}
+
+ /* Parse precision. Example: "%.3f" => prec=3 */
if (c == '.') {
prec = 0;
if (--fmtcnt >= 0)
@@ -771,13 +798,19 @@ _PyBytes_Format(PyObject *format, PyObject *args)
if (v == NULL)
goto error;
}
+
+ if (fmtcnt < 0) {
+ /* last writer: disable writer overallocation */
+ writer.overallocate = 0;
+ }
+
sign = 0;
fill = ' ';
switch (c) {
case '%':
- pbuf = "%";
- len = 1;
- break;
+ *res++ = '%';
+ continue;
+
case 'r':
// %r is only for 2/3 code; 3 only code should use %a
case 'a':
@@ -790,6 +823,7 @@ _PyBytes_Format(PyObject *format, PyObject *args)
if (prec >= 0 && len > prec)
len = prec;
break;
+
case 's':
// %s is only for 2/3 code; 3 only code should use %b
case 'b':
@@ -799,12 +833,49 @@ _PyBytes_Format(PyObject *format, PyObject *args)
if (prec >= 0 && len > prec)
len = prec;
break;
+
case 'i':
case 'd':
case 'u':
case 'o':
case 'x':
case 'X':
+ if (PyLong_CheckExact(v)
+ && width == -1 && prec == -1
+ && !(flags & (F_SIGN | F_BLANK))
+ && c != 'X')
+ {
+ /* Fast path */
+ int alternate = flags & F_ALT;
+ int base;
+
+ switch(c)
+ {
+ default:
+ assert(0 && "'type' not in [diuoxX]");
+ case 'd':
+ case 'i':
+ case 'u':
+ base = 10;
+ break;
+ case 'o':
+ base = 8;
+ break;
+ case 'x':
+ case 'X':
+ base = 16;
+ break;
+ }
+
+ /* Fast path */
+ writer.min_size -= 2; /* size preallocated for "%d" */
+ res = _PyLong_FormatBytesWriter(&writer, res,
+ v, base, alternate);
+ if (res == NULL)
+ goto error;
+ continue;
+ }
+
temp = formatlong(v, flags, prec, c);
if (!temp)
goto error;
@@ -815,14 +886,25 @@ _PyBytes_Format(PyObject *format, PyObject *args)
if (flags & F_ZERO)
fill = '0';
break;
+
case 'e':
case 'E':
case 'f':
case 'F':
case 'g':
case 'G':
- temp = formatfloat(v, flags, prec, c);
- if (temp == NULL)
+ if (width == -1 && prec == -1
+ && !(flags & (F_SIGN | F_BLANK)))
+ {
+ /* Fast path */
+ writer.min_size -= 2; /* size preallocated for "%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))
goto error;
pbuf = PyBytes_AS_STRING(temp);
len = PyBytes_GET_SIZE(temp);
@@ -830,21 +912,28 @@ _PyBytes_Format(PyObject *format, PyObject *args)
if (flags & F_ZERO)
fill = '0';
break;
+
case 'c':
pbuf = &onechar;
len = byte_converter(v, &onechar);
if (!len)
goto error;
+ if (width == -1) {
+ /* Fast path */
+ *res++ = onechar;
+ continue;
+ }
break;
+
default:
PyErr_Format(PyExc_ValueError,
"unsupported format character '%c' (0x%x) "
"at index %zd",
c, c,
- (Py_ssize_t)(fmt - 1 -
- PyBytes_AsString(format)));
+ (Py_ssize_t)(fmt - 1 - format));
goto error;
}
+
if (sign) {
if (*pbuf == '-' || *pbuf == '+') {
sign = *pbuf++;
@@ -859,29 +948,31 @@ _PyBytes_Format(PyObject *format, PyObject *args)
}
if (width < len)
width = len;
- if (rescnt - (sign != 0) < width) {
- reslen -= rescnt;
- rescnt = width + fmtcnt + 100;
- reslen += rescnt;
- if (reslen < 0) {
- Py_DECREF(result);
- Py_XDECREF(temp);
- return PyErr_NoMemory();
- }
- if (_PyBytes_Resize(&result, reslen)) {
- Py_XDECREF(temp);
- return NULL;
- }
- res = PyBytes_AS_STRING(result)
- + reslen - rescnt;
+
+ alloc = width;
+ if (sign != 0 && len == width)
+ alloc++;
+ /* 2: size preallocated for %s */
+ if (alloc > 2) {
+ res = _PyBytesWriter_Prepare(&writer, res, alloc - 2);
+ if (res == NULL)
+ goto error;
}
+#ifdef Py_DEBUG
+ before = res;
+#endif
+
+ /* Write the sign if needed */
if (sign) {
if (fill != ' ')
*res++ = sign;
- rescnt--;
if (width > len)
width--;
}
+
+ /* Write the numeric prefix for "x", "X" and "o" formats
+ if the alternate form is used.
+ For example, write "0x" for the "%#x" format. */
if ((flags & F_ALT) && (c == 'x' || c == 'X')) {
assert(pbuf[0] == '0');
assert(pbuf[1] == c);
@@ -889,18 +980,21 @@ _PyBytes_Format(PyObject *format, PyObject *args)
*res++ = *pbuf++;
*res++ = *pbuf++;
}
- rescnt -= 2;
width -= 2;
if (width < 0)
width = 0;
len -= 2;
}
+
+ /* Pad left with the fill character if needed */
if (width > len && !(flags & F_LJUST)) {
- do {
- --rescnt;
- *res++ = fill;
- } while (--width > len);
+ memset(res, fill, width - len);
+ res += (width - len);
+ width = len;
}
+
+ /* If padding with spaces: write sign if needed and/or numeric
+ prefix if the alternate form is used */
if (fill == ' ') {
if (sign)
*res++ = sign;
@@ -912,13 +1006,17 @@ _PyBytes_Format(PyObject *format, PyObject *args)
*res++ = *pbuf++;
}
}
+
+ /* Copy bytes */
Py_MEMCPY(res, pbuf, len);
res += len;
- rescnt -= len;
- while (--width >= len) {
- --rescnt;
- *res++ = ' ';
+
+ /* Pad right with the fill character if needed */
+ if (width > len) {
+ memset(res, ' ', width - len);
+ res += (width - len);
}
+
if (dict && (argidx < arglen) && c != '%') {
PyErr_SetString(PyExc_TypeError,
"not all arguments converted during bytes formatting");
@@ -926,22 +1024,31 @@ _PyBytes_Format(PyObject *format, PyObject *args)
goto error;
}
Py_XDECREF(temp);
+
+#ifdef Py_DEBUG
+ /* check that we computed the exact size for this write */
+ assert((res - before) == alloc);
+#endif
} /* '%' */
+
+ /* If overallocation was disabled, ensure that it was the last
+ write. Otherwise, we missed an optimization */
+ assert(writer.overallocate || fmtcnt < 0 || use_bytearray);
} /* until end */
+
if (argidx < arglen && !dict) {
PyErr_SetString(PyExc_TypeError,
"not all arguments converted during bytes formatting");
goto error;
}
+
if (args_owned) {
Py_DECREF(args);
}
- if (_PyBytes_Resize(&result, reslen - rescnt))
- return NULL;
- return result;
+ return _PyBytesWriter_Finish(&writer, res);
error:
- Py_DECREF(result);
+ _PyBytesWriter_Dealloc(&writer);
if (args_owned) {
Py_DECREF(args);
}
@@ -961,6 +1068,42 @@ bytes_dealloc(PyObject *op)
the string is UTF-8 encoded and should be re-encoded in the
specified encoding. */
+static char *
+_PyBytes_DecodeEscapeRecode(const char **s, const char *end,
+ const char *errors, const char *recode_encoding,
+ _PyBytesWriter *writer, char *p)
+{
+ PyObject *u, *w;
+ const char* t;
+
+ t = *s;
+ /* Decode non-ASCII bytes as UTF-8. */
+ while (t < end && (*t & 0x80))
+ t++;
+ u = PyUnicode_DecodeUTF8(*s, t - *s, errors);
+ if (u == NULL)
+ return NULL;
+
+ /* Recode them in target encoding. */
+ w = PyUnicode_AsEncodedString(u, recode_encoding, errors);
+ Py_DECREF(u);
+ if (w == NULL)
+ return NULL;
+ assert(PyBytes_Check(w));
+
+ /* Append bytes to output buffer. */
+ writer->min_size--; /* substract 1 preallocated byte */
+ p = _PyBytesWriter_WriteBytes(writer, p,
+ PyBytes_AS_STRING(w),
+ PyBytes_GET_SIZE(w));
+ Py_DECREF(w);
+ if (p == NULL)
+ return NULL;
+
+ *s = t;
+ return p;
+}
+
PyObject *PyBytes_DecodeEscape(const char *s,
Py_ssize_t len,
const char *errors,
@@ -968,54 +1111,42 @@ PyObject *PyBytes_DecodeEscape(const char *s,
const char *recode_encoding)
{
int c;
- char *p, *buf;
+ char *p;
const char *end;
- PyObject *v;
- Py_ssize_t newlen = recode_encoding ? 4*len:len;
- v = PyBytes_FromStringAndSize((char *)NULL, newlen);
- if (v == NULL)
+ _PyBytesWriter writer;
+
+ _PyBytesWriter_Init(&writer);
+
+ p = _PyBytesWriter_Alloc(&writer, len);
+ if (p == NULL)
return NULL;
- p = buf = PyBytes_AsString(v);
+ writer.overallocate = 1;
+
end = s + len;
while (s < end) {
if (*s != '\\') {
non_esc:
- if (recode_encoding && (*s & 0x80)) {
- PyObject *u, *w;
- char *r;
- const char* t;
- Py_ssize_t rn;
- t = s;
- /* Decode non-ASCII bytes as UTF-8. */
- while (t < end && (*t & 0x80)) t++;
- u = PyUnicode_DecodeUTF8(s, t - s, errors);
- if(!u) goto failed;
-
- /* Recode them in target encoding. */
- w = PyUnicode_AsEncodedString(
- u, recode_encoding, errors);
- Py_DECREF(u);
- if (!w) goto failed;
-
- /* Append bytes to output buffer. */
- assert(PyBytes_Check(w));
- r = PyBytes_AS_STRING(w);
- rn = PyBytes_GET_SIZE(w);
- Py_MEMCPY(p, r, rn);
- p += rn;
- Py_DECREF(w);
- s = t;
- } else {
+ if (!(recode_encoding && (*s & 0x80))) {
*p++ = *s++;
}
+ else {
+ /* non-ASCII character and need to recode */
+ p = _PyBytes_DecodeEscapeRecode(&s, end,
+ errors, recode_encoding,
+ &writer, p);
+ if (p == NULL)
+ goto failed;
+ }
continue;
}
+
s++;
- if (s==end) {
+ if (s == end) {
PyErr_SetString(PyExc_ValueError,
"Trailing \\ in string");
goto failed;
}
+
switch (*s++) {
/* XXX This assumes ASCII! */
case '\n': break;
@@ -1040,28 +1171,18 @@ PyObject *PyBytes_DecodeEscape(const char *s,
*p++ = c;
break;
case 'x':
- if (s+1 < end && Py_ISXDIGIT(s[0]) && Py_ISXDIGIT(s[1])) {
- unsigned int x = 0;
- c = Py_CHARMASK(*s);
- s++;
- if (Py_ISDIGIT(c))
- x = c - '0';
- else if (Py_ISLOWER(c))
- x = 10 + c - 'a';
- else
- x = 10 + c - 'A';
- x = x << 4;
- c = Py_CHARMASK(*s);
- s++;
- if (Py_ISDIGIT(c))
- x += c - '0';
- else if (Py_ISLOWER(c))
- x += 10 + c - 'a';
- else
- x += 10 + c - 'A';
- *p++ = x;
- break;
+ if (s+1 < end) {
+ int digit1, digit2;
+ digit1 = _PyLong_DigitValue[Py_CHARMASK(s[0])];
+ digit2 = _PyLong_DigitValue[Py_CHARMASK(s[1])];
+ if (digit1 < 16 && digit2 < 16) {
+ *p++ = (unsigned char)((digit1 << 4) + digit2);
+ s += 2;
+ break;
+ }
}
+ /* invalid hexadecimal digits */
+
if (!errors || strcmp(errors, "strict") == 0) {
PyErr_Format(PyExc_ValueError,
"invalid \\x escape at position %d",
@@ -1083,6 +1204,7 @@ PyObject *PyBytes_DecodeEscape(const char *s,
if (s < end && Py_ISXDIGIT(s[0]))
s++; /* and a hexdigit */
break;
+
default:
*p++ = '\\';
s--;
@@ -1090,11 +1212,11 @@ PyObject *PyBytes_DecodeEscape(const char *s,
UTF-8 bytes may follow. */
}
}
- if (p-buf < newlen)
- _PyBytes_Resize(&v, p - buf);
- return v;
+
+ return _PyBytesWriter_Finish(&writer, p);
+
failed:
- Py_DECREF(v);
+ _PyBytesWriter_Dealloc(&writer);
return NULL;
}
@@ -1815,16 +1937,15 @@ bytes_find_internal(PyBytesObject *self, PyObject *args, int dir)
ADJUST_INDICES(start, end, len);
if (end - start < sub_len)
res = -1;
- else if (sub_len == 1
-#ifndef HAVE_MEMRCHR
- && dir > 0
-#endif
- ) {
- unsigned char needle = *sub;
- int mode = (dir > 0) ? FAST_SEARCH : FAST_RSEARCH;
- res = stringlib_fastsearch_memchr_1char(
- PyBytes_AS_STRING(self) + start, end - start,
- needle, needle, mode);
+ else if (sub_len == 1) {
+ if (dir > 0)
+ res = stringlib_find_char(
+ PyBytes_AS_STRING(self) + start, end - start,
+ *sub);
+ else
+ res = stringlib_rfind_char(
+ PyBytes_AS_STRING(self) + start, end - start,
+ *sub);
if (res >= 0)
res += start;
}
@@ -2975,22 +3096,6 @@ bytes_splitlines_impl(PyBytesObject*self, int keepends)
);
}
-static int
-hex_digit_to_int(Py_UCS4 c)
-{
- if (c >= 128)
- return -1;
- if (Py_ISDIGIT(c))
- return c - '0';
- else {
- if (Py_ISUPPER(c))
- c = Py_TOLOWER(c);
- if (c >= 'a' && c <= 'f')
- return c - 'a' + 10;
- }
- return -1;
-}
-
/*[clinic input]
@classmethod
bytes.fromhex
@@ -3008,47 +3113,83 @@ static PyObject *
bytes_fromhex_impl(PyTypeObject *type, PyObject *string)
/*[clinic end generated code: output=0973acc63661bb2e input=bf4d1c361670acd3]*/
{
- PyObject *newstring;
+ return _PyBytes_FromHex(string, 0);
+}
+
+PyObject*
+_PyBytes_FromHex(PyObject *string, int use_bytearray)
+{
char *buf;
- Py_ssize_t hexlen, byteslen, i, j;
- int top, bot;
- void *data;
- unsigned int kind;
+ Py_ssize_t hexlen, invalid_char;
+ unsigned int top, bot;
+ Py_UCS1 *str, *end;
+ _PyBytesWriter writer;
+
+ _PyBytesWriter_Init(&writer);
+ writer.use_bytearray = use_bytearray;
assert(PyUnicode_Check(string));
if (PyUnicode_READY(string))
return NULL;
- kind = PyUnicode_KIND(string);
- data = PyUnicode_DATA(string);
hexlen = PyUnicode_GET_LENGTH(string);
- byteslen = hexlen/2; /* This overestimates if there are spaces */
- newstring = PyBytes_FromStringAndSize(NULL, byteslen);
- if (!newstring)
+ if (!PyUnicode_IS_ASCII(string)) {
+ void *data = PyUnicode_DATA(string);
+ unsigned int kind = PyUnicode_KIND(string);
+ Py_ssize_t i;
+
+ /* search for the first non-ASCII character */
+ for (i = 0; i < hexlen; i++) {
+ if (PyUnicode_READ(kind, data, i) >= 128)
+ break;
+ }
+ invalid_char = i;
+ goto error;
+ }
+
+ assert(PyUnicode_KIND(string) == PyUnicode_1BYTE_KIND);
+ str = PyUnicode_1BYTE_DATA(string);
+
+ /* This overestimates if there are spaces */
+ buf = _PyBytesWriter_Alloc(&writer, hexlen / 2);
+ if (buf == NULL)
return NULL;
- buf = PyBytes_AS_STRING(newstring);
- for (i = j = 0; i < hexlen; i += 2) {
+
+ end = str + hexlen;
+ while (str < end) {
/* skip over spaces in the input */
- while (PyUnicode_READ(kind, data, i) == ' ')
- i++;
- if (i >= hexlen)
- break;
- top = hex_digit_to_int(PyUnicode_READ(kind, data, i));
- bot = hex_digit_to_int(PyUnicode_READ(kind, data, i+1));
- if (top == -1 || bot == -1) {
- PyErr_Format(PyExc_ValueError,
- "non-hexadecimal number found in "
- "fromhex() arg at position %zd", i);
+ if (*str == ' ') {
+ do {
+ str++;
+ } while (*str == ' ');
+ if (str >= end)
+ break;
+ }
+
+ top = _PyLong_DigitValue[*str];
+ if (top >= 16) {
+ invalid_char = str - PyUnicode_1BYTE_DATA(string);
goto error;
}
- buf[j++] = (top << 4) + bot;
+ str++;
+
+ bot = _PyLong_DigitValue[*str];
+ if (bot >= 16) {
+ invalid_char = str - PyUnicode_1BYTE_DATA(string);
+ goto error;
+ }
+ str++;
+
+ *buf++ = (unsigned char)((top << 4) + bot);
}
- if (j != byteslen && _PyBytes_Resize(&newstring, j) < 0)
- goto error;
- return newstring;
+
+ return _PyBytesWriter_Finish(&writer, buf);
error:
- Py_XDECREF(newstring);
+ PyErr_Format(PyExc_ValueError,
+ "non-hexadecimal number found in "
+ "fromhex() arg at position %zd", invalid_char);
+ _PyBytesWriter_Dealloc(&writer);
return NULL;
}
@@ -3131,11 +3272,15 @@ bytes_methods[] = {
};
static PyObject *
-bytes_mod(PyObject *v, PyObject *w)
+bytes_mod(PyObject *self, PyObject *args)
{
- if (!PyBytes_Check(v))
- Py_RETURN_NOTIMPLEMENTED;
- return _PyBytes_Format(v, w);
+ if (self == NULL || !PyBytes_Check(self)) {
+ PyErr_BadInternalCall();
+ return NULL;
+ }
+
+ return _PyBytes_FormatEx(PyBytes_AS_STRING(self), PyBytes_GET_SIZE(self),
+ args, 0);
}
static PyNumberMethods bytes_as_number = {
@@ -3244,103 +3389,95 @@ bytes_new(PyTypeObject *type, PyObject *args, PyObject *kwds)
return PyBytes_FromObject(x);
}
-PyObject *
-PyBytes_FromObject(PyObject *x)
+static PyObject*
+_PyBytes_FromBuffer(PyObject *x)
{
- PyObject *new, *it;
- Py_ssize_t i, size;
+ PyObject *new;
+ Py_buffer view;
- if (x == NULL) {
- PyErr_BadInternalCall();
+ if (PyObject_GetBuffer(x, &view, PyBUF_FULL_RO) < 0)
return NULL;
- }
- if (PyBytes_CheckExact(x)) {
- Py_INCREF(x);
- return x;
- }
+ new = PyBytes_FromStringAndSize(NULL, view.len);
+ if (!new)
+ goto fail;
+ if (PyBuffer_ToContiguous(((PyBytesObject *)new)->ob_sval,
+ &view, view.len, 'C') < 0)
+ goto fail;
+ PyBuffer_Release(&view);
+ return new;
- /* Use the modern buffer interface */
- if (PyObject_CheckBuffer(x)) {
- Py_buffer view;
- if (PyObject_GetBuffer(x, &view, PyBUF_FULL_RO) < 0)
- return NULL;
- new = PyBytes_FromStringAndSize(NULL, view.len);
- if (!new)
- goto fail;
- if (PyBuffer_ToContiguous(((PyBytesObject *)new)->ob_sval,
- &view, view.len, 'C') < 0)
- goto fail;
- PyBuffer_Release(&view);
- return new;
- fail:
- Py_XDECREF(new);
- PyBuffer_Release(&view);
- return NULL;
- }
- if (PyUnicode_Check(x)) {
- PyErr_SetString(PyExc_TypeError,
- "cannot convert unicode object to bytes");
- return NULL;
- }
+fail:
+ Py_XDECREF(new);
+ PyBuffer_Release(&view);
+ return NULL;
+}
- if (PyList_CheckExact(x)) {
- new = PyBytes_FromStringAndSize(NULL, Py_SIZE(x));
- if (new == NULL)
- return NULL;
- for (i = 0; i < Py_SIZE(x); i++) {
- Py_ssize_t value = PyNumber_AsSsize_t(
- PyList_GET_ITEM(x, i), PyExc_ValueError);
- if (value == -1 && PyErr_Occurred()) {
- Py_DECREF(new);
- return NULL;
- }
- if (value < 0 || value >= 256) {
- PyErr_SetString(PyExc_ValueError,
- "bytes must be in range(0, 256)");
- Py_DECREF(new);
- return NULL;
- }
- ((PyBytesObject *)new)->ob_sval[i] = (char) value;
- }
- return new;
- }
- if (PyTuple_CheckExact(x)) {
- new = PyBytes_FromStringAndSize(NULL, Py_SIZE(x));
- if (new == NULL)
- return NULL;
- for (i = 0; i < Py_SIZE(x); i++) {
- Py_ssize_t value = PyNumber_AsSsize_t(
- PyTuple_GET_ITEM(x, i), PyExc_ValueError);
- if (value == -1 && PyErr_Occurred()) {
- Py_DECREF(new);
- return NULL;
- }
- if (value < 0 || value >= 256) {
- PyErr_SetString(PyExc_ValueError,
- "bytes must be in range(0, 256)");
- Py_DECREF(new);
- return NULL;
- }
- ((PyBytesObject *)new)->ob_sval[i] = (char) value;
- }
- return new;
- }
+#define _PyBytes_FROM_LIST_BODY(x, GET_ITEM) \
+ do { \
+ PyObject *bytes; \
+ Py_ssize_t i; \
+ Py_ssize_t value; \
+ char *str; \
+ PyObject *item; \
+ \
+ bytes = PyBytes_FromStringAndSize(NULL, Py_SIZE(x)); \
+ if (bytes == NULL) \
+ return NULL; \
+ str = ((PyBytesObject *)bytes)->ob_sval; \
+ \
+ for (i = 0; i < Py_SIZE(x); i++) { \
+ item = GET_ITEM((x), i); \
+ value = PyNumber_AsSsize_t(item, PyExc_ValueError); \
+ if (value == -1 && PyErr_Occurred()) \
+ goto error; \
+ \
+ if (value < 0 || value >= 256) { \
+ PyErr_SetString(PyExc_ValueError, \
+ "bytes must be in range(0, 256)"); \
+ goto error; \
+ } \
+ *str++ = (char) value; \
+ } \
+ return bytes; \
+ \
+ error: \
+ Py_DECREF(bytes); \
+ return NULL; \
+ } while (0)
+
+static PyObject*
+_PyBytes_FromList(PyObject *x)
+{
+ _PyBytes_FROM_LIST_BODY(x, PyList_GET_ITEM);
+}
+
+static PyObject*
+_PyBytes_FromTuple(PyObject *x)
+{
+ _PyBytes_FROM_LIST_BODY(x, PyTuple_GET_ITEM);
+}
+
+static PyObject *
+_PyBytes_FromIterator(PyObject *x)
+{
+ char *str;
+ PyObject *it;
+ Py_ssize_t i, size;
+ _PyBytesWriter writer;
+
+ _PyBytesWriter_Init(&writer);
/* For iterator version, create a string object and resize as needed */
size = PyObject_LengthHint(x, 64);
if (size == -1 && PyErr_Occurred())
return NULL;
- /* Allocate an extra byte to prevent PyBytes_FromStringAndSize() from
- returning a shared empty bytes string. This required because we
- want to call _PyBytes_Resize() the returned object, which we can
- only do on bytes objects with refcount == 1. */
- if (size == 0)
- size = 1;
- new = PyBytes_FromStringAndSize(NULL, size);
- if (new == NULL)
+
+ str = _PyBytesWriter_Alloc(&writer, size);
+ if (str == NULL)
return NULL;
- assert(Py_REFCNT(new) == 1);
+ writer.overallocate = 1;
+ size = writer.allocated;
/* Get the iterator */
it = PyObject_GetIter(x);
@@ -3375,24 +3512,55 @@ PyBytes_FromObject(PyObject *x)
/* Append the byte */
if (i >= size) {
- size = 2 * size + 1;
- if (_PyBytes_Resize(&new, size) < 0)
- goto error;
+ str = _PyBytesWriter_Resize(&writer, str, size+1);
+ if (str == NULL)
+ return NULL;
+ size = writer.allocated;
}
- ((PyBytesObject *)new)->ob_sval[i] = (char) value;
+ *str++ = (char) value;
}
- _PyBytes_Resize(&new, i);
-
- /* Clean up and return success */
Py_DECREF(it);
- return new;
+
+ return _PyBytesWriter_Finish(&writer, str);
error:
+ _PyBytesWriter_Dealloc(&writer);
Py_XDECREF(it);
- Py_XDECREF(new);
return NULL;
}
+PyObject *
+PyBytes_FromObject(PyObject *x)
+{
+ if (x == NULL) {
+ PyErr_BadInternalCall();
+ return NULL;
+ }
+
+ if (PyBytes_CheckExact(x)) {
+ Py_INCREF(x);
+ return x;
+ }
+
+ /* Use the modern buffer interface */
+ if (PyObject_CheckBuffer(x))
+ return _PyBytes_FromBuffer(x);
+
+ if (PyList_CheckExact(x))
+ return _PyBytes_FromList(x);
+
+ if (PyTuple_CheckExact(x))
+ return _PyBytes_FromTuple(x);
+
+ if (PyUnicode_Check(x)) {
+ PyErr_SetString(PyExc_TypeError,
+ "cannot convert unicode object to bytes");
+ return NULL;
+ }
+
+ return _PyBytes_FromIterator(x);
+}
+
static PyObject *
bytes_subtype_new(PyTypeObject *type, PyObject *args, PyObject *kwds)
{
@@ -3740,3 +3908,277 @@ bytes_iter(PyObject *seq)
_PyObject_GC_TRACK(it);
return (PyObject *)it;
}
+
+
+/* _PyBytesWriter API */
+
+#ifdef MS_WINDOWS
+ /* On Windows, overallocate by 50% is the best factor */
+# define OVERALLOCATE_FACTOR 2
+#else
+ /* On Linux, overallocate by 25% is the best factor */
+# define OVERALLOCATE_FACTOR 4
+#endif
+
+void
+_PyBytesWriter_Init(_PyBytesWriter *writer)
+{
+ /* Set all attributes before small_buffer to 0 */
+ memset(writer, 0, offsetof(_PyBytesWriter, small_buffer));
+#ifdef Py_DEBUG
+ memset(writer->small_buffer, 0xCB, sizeof(writer->small_buffer));
+#endif
+}
+
+void
+_PyBytesWriter_Dealloc(_PyBytesWriter *writer)
+{
+ Py_CLEAR(writer->buffer);
+}
+
+Py_LOCAL_INLINE(char*)
+_PyBytesWriter_AsString(_PyBytesWriter *writer)
+{
+ if (writer->use_small_buffer) {
+ assert(writer->buffer == NULL);
+ return writer->small_buffer;
+ }
+ else if (writer->use_bytearray) {
+ assert(writer->buffer != NULL);
+ return PyByteArray_AS_STRING(writer->buffer);
+ }
+ else {
+ assert(writer->buffer != NULL);
+ return PyBytes_AS_STRING(writer->buffer);
+ }
+}
+
+Py_LOCAL_INLINE(Py_ssize_t)
+_PyBytesWriter_GetSize(_PyBytesWriter *writer, char *str)
+{
+ char *start = _PyBytesWriter_AsString(writer);
+ assert(str != NULL);
+ assert(str >= start);
+ assert(str - start <= writer->allocated);
+ return str - start;
+}
+
+Py_LOCAL_INLINE(void)
+_PyBytesWriter_CheckConsistency(_PyBytesWriter *writer, char *str)
+{
+#ifdef Py_DEBUG
+ char *start, *end;
+
+ if (writer->use_small_buffer) {
+ assert(writer->buffer == NULL);
+ }
+ else {
+ assert(writer->buffer != NULL);
+ if (writer->use_bytearray)
+ assert(PyByteArray_CheckExact(writer->buffer));
+ else
+ assert(PyBytes_CheckExact(writer->buffer));
+ assert(Py_REFCNT(writer->buffer) == 1);
+ }
+
+ if (writer->use_bytearray) {
+ /* bytearray has its own overallocation algorithm,
+ writer overallocation must be disabled */
+ assert(!writer->overallocate);
+ }
+
+ assert(0 <= writer->allocated);
+ assert(0 <= writer->min_size && writer->min_size <= writer->allocated);
+ /* the last byte must always be null */
+ start = _PyBytesWriter_AsString(writer);
+ assert(start[writer->allocated] == 0);
+
+ end = start + writer->allocated;
+ assert(str != NULL);
+ assert(start <= str && str <= end);
+#endif
+}
+
+void*
+_PyBytesWriter_Resize(_PyBytesWriter *writer, void *str, Py_ssize_t size)
+{
+ Py_ssize_t allocated, pos;
+
+ _PyBytesWriter_CheckConsistency(writer, str);
+ assert(writer->allocated < size);
+
+ allocated = size;
+ if (writer->overallocate
+ && allocated <= (PY_SSIZE_T_MAX - allocated / OVERALLOCATE_FACTOR)) {
+ /* overallocate to limit the number of realloc() */
+ allocated += allocated / OVERALLOCATE_FACTOR;
+ }
+
+ pos = _PyBytesWriter_GetSize(writer, str);
+ if (!writer->use_small_buffer) {
+ if (writer->use_bytearray) {
+ if (PyByteArray_Resize(writer->buffer, allocated))
+ goto error;
+ /* writer->allocated can be smaller than writer->buffer->ob_alloc,
+ but we cannot use ob_alloc because bytes may need to be moved
+ to use the whole buffer. bytearray uses an internal optimization
+ to avoid moving or copying bytes when bytes are removed at the
+ beginning (ex: del bytearray[:1]). */
+ }
+ else {
+ if (_PyBytes_Resize(&writer->buffer, allocated))
+ goto error;
+ }
+ }
+ else {
+ /* convert from stack buffer to bytes object buffer */
+ assert(writer->buffer == NULL);
+
+ if (writer->use_bytearray)
+ writer->buffer = PyByteArray_FromStringAndSize(NULL, allocated);
+ else
+ writer->buffer = PyBytes_FromStringAndSize(NULL, allocated);
+ if (writer->buffer == NULL)
+ goto error;
+
+ if (pos != 0) {
+ char *dest;
+ if (writer->use_bytearray)
+ dest = PyByteArray_AS_STRING(writer->buffer);
+ else
+ dest = PyBytes_AS_STRING(writer->buffer);
+ Py_MEMCPY(dest,
+ writer->small_buffer,
+ pos);
+ }
+
+ writer->use_small_buffer = 0;
+#ifdef Py_DEBUG
+ memset(writer->small_buffer, 0xDB, sizeof(writer->small_buffer));
+#endif
+ }
+ writer->allocated = allocated;
+
+ str = _PyBytesWriter_AsString(writer) + pos;
+ _PyBytesWriter_CheckConsistency(writer, str);
+ return str;
+
+error:
+ _PyBytesWriter_Dealloc(writer);
+ return NULL;
+}
+
+void*
+_PyBytesWriter_Prepare(_PyBytesWriter *writer, void *str, Py_ssize_t size)
+{
+ Py_ssize_t new_min_size;
+
+ _PyBytesWriter_CheckConsistency(writer, str);
+ assert(size >= 0);
+
+ if (size == 0) {
+ /* nothing to do */
+ return str;
+ }
+
+ if (writer->min_size > PY_SSIZE_T_MAX - size) {
+ PyErr_NoMemory();
+ _PyBytesWriter_Dealloc(writer);
+ return NULL;
+ }
+ new_min_size = writer->min_size + size;
+
+ if (new_min_size > writer->allocated)
+ str = _PyBytesWriter_Resize(writer, str, new_min_size);
+
+ writer->min_size = new_min_size;
+ return str;
+}
+
+/* Allocate the buffer to write size bytes.
+ Return the pointer to the beginning of buffer data.
+ Raise an exception and return NULL on error. */
+void*
+_PyBytesWriter_Alloc(_PyBytesWriter *writer, Py_ssize_t size)
+{
+ /* ensure that _PyBytesWriter_Alloc() is only called once */
+ assert(writer->min_size == 0 && writer->buffer == NULL);
+ assert(size >= 0);
+
+ writer->use_small_buffer = 1;
+#ifdef Py_DEBUG
+ writer->allocated = sizeof(writer->small_buffer) - 1;
+ /* In debug mode, don't use the full small buffer because it is less
+ efficient than bytes and bytearray objects to detect buffer underflow
+ and buffer overflow. Use 10 bytes of the small buffer to test also
+ code using the smaller buffer in debug mode.
+
+ Don't modify the _PyBytesWriter structure (use a shorter small buffer)
+ in debug mode to also be able to detect stack overflow when running
+ tests in debug mode. The _PyBytesWriter is large (more than 512 bytes),
+ if Py_EnterRecursiveCall() is not used in deep C callback, we may hit a
+ stack overflow. */
+ writer->allocated = Py_MIN(writer->allocated, 10);
+ /* _PyBytesWriter_CheckConsistency() requires the last byte to be 0,
+ to detect buffer overflow */
+ writer->small_buffer[writer->allocated] = 0;
+#else
+ writer->allocated = sizeof(writer->small_buffer);
+#endif
+ return _PyBytesWriter_Prepare(writer, writer->small_buffer, size);
+}
+
+PyObject *
+_PyBytesWriter_Finish(_PyBytesWriter *writer, void *str)
+{
+ Py_ssize_t size;
+ PyObject *result;
+
+ _PyBytesWriter_CheckConsistency(writer, str);
+
+ size = _PyBytesWriter_GetSize(writer, str);
+ if (size == 0 && !writer->use_bytearray) {
+ Py_CLEAR(writer->buffer);
+ /* Get the empty byte string singleton */
+ result = PyBytes_FromStringAndSize(NULL, 0);
+ }
+ else if (writer->use_small_buffer) {
+ result = PyBytes_FromStringAndSize(writer->small_buffer, size);
+ }
+ else {
+ result = writer->buffer;
+ writer->buffer = NULL;
+
+ if (size != writer->allocated) {
+ if (writer->use_bytearray) {
+ if (PyByteArray_Resize(result, size)) {
+ Py_DECREF(result);
+ return NULL;
+ }
+ }
+ else {
+ if (_PyBytes_Resize(&result, size)) {
+ assert(result == NULL);
+ return NULL;
+ }
+ }
+ }
+ }
+ return result;
+}
+
+void*
+_PyBytesWriter_WriteBytes(_PyBytesWriter *writer, void *ptr,
+ const void *bytes, Py_ssize_t size)
+{
+ char *str = (char *)ptr;
+
+ str = _PyBytesWriter_Prepare(writer, str, size);
+ if (str == NULL)
+ return NULL;
+
+ Py_MEMCPY(str, bytes, size);
+ str += size;
+
+ return str;
+}
diff --git a/Objects/dictobject.c b/Objects/dictobject.c
index f53cd40796..6f57db01c0 100644
--- a/Objects/dictobject.c
+++ b/Objects/dictobject.c
@@ -1165,39 +1165,42 @@ _PyDict_GetItemIdWithError(PyObject *dp, struct _Py_Identifier *key)
return PyDict_GetItemWithError(dp, kv);
}
-/* Fast version of global value lookup.
+/* Fast version of global value lookup (LOAD_GLOBAL).
* Lookup in globals, then builtins.
+ *
+ * Raise an exception and return NULL if an error occurred (ex: computing the
+ * key hash failed, key comparison failed, ...). Return NULL if the key doesn't
+ * exist. Return the value if the key exists.
*/
PyObject *
_PyDict_LoadGlobal(PyDictObject *globals, PyDictObject *builtins, PyObject *key)
{
- PyObject *x;
- if (PyUnicode_CheckExact(key)) {
- PyObject **value_addr;
- Py_hash_t hash = ((PyASCIIObject *)key)->hash;
- if (hash != -1) {
- PyDictKeyEntry *e;
- e = globals->ma_keys->dk_lookup(globals, key, hash, &value_addr);
- if (e == NULL) {
- return NULL;
- }
- x = *value_addr;
- if (x != NULL)
- return x;
- e = builtins->ma_keys->dk_lookup(builtins, key, hash, &value_addr);
- if (e == NULL) {
- return NULL;
- }
- x = *value_addr;
- return x;
- }
+ Py_hash_t hash;
+ PyDictKeyEntry *entry;
+ PyObject **value_addr;
+ PyObject *value;
+
+ if (!PyUnicode_CheckExact(key) ||
+ (hash = ((PyASCIIObject *) key)->hash) == -1)
+ {
+ hash = PyObject_Hash(key);
+ if (hash == -1)
+ return NULL;
}
- x = PyDict_GetItemWithError((PyObject *)globals, key);
- if (x != NULL)
- return x;
- if (PyErr_Occurred())
+
+ /* namespace 1: globals */
+ entry = globals->ma_keys->dk_lookup(globals, key, hash, &value_addr);
+ if (entry == NULL)
return NULL;
- return PyDict_GetItemWithError((PyObject *)builtins, key);
+ value = *value_addr;
+ if (value != NULL)
+ return value;
+
+ /* namespace 2: builtins */
+ entry = builtins->ma_keys->dk_lookup(builtins, key, hash, &value_addr);
+ if (entry == NULL)
+ return NULL;
+ return *value_addr;
}
/* CAUTION: PyDict_SetItem() must guarantee that it won't resize the
diff --git a/Objects/listsort.txt b/Objects/listsort.txt
index 832e4f2ea6..fef982f8a6 100644
--- a/Objects/listsort.txt
+++ b/Objects/listsort.txt
@@ -486,7 +486,7 @@ sub-run, yet finding such very efficiently when they exist.
I first learned about the galloping strategy in a related context; see:
"Adaptive Set Intersections, Unions, and Differences" (2000)
- Erik D. Demaine, Alejandro López-Ortiz, J. Ian Munro
+ Erik D. Demaine, Alejandro López-Ortiz, J. Ian Munro
and its followup(s). An earlier paper called the same strategy
"exponential search":
diff --git a/Objects/longobject.c b/Objects/longobject.c
index d821e4bfb6..d05de8bf07 100644
--- a/Objects/longobject.c
+++ b/Objects/longobject.c
@@ -1582,10 +1582,12 @@ divrem1(PyLongObject *a, digit n, digit *prem)
static int
long_to_decimal_string_internal(PyObject *aa,
PyObject **p_output,
- _PyUnicodeWriter *writer)
+ _PyUnicodeWriter *writer,
+ _PyBytesWriter *bytes_writer,
+ char **bytes_str)
{
PyLongObject *scratch, *a;
- PyObject *str;
+ PyObject *str = NULL;
Py_ssize_t size, strlen, size_a, i, j;
digit *pout, *pin, rem, tenpow;
int negative;
@@ -1662,7 +1664,13 @@ long_to_decimal_string_internal(PyObject *aa,
return -1;
}
kind = writer->kind;
- str = NULL;
+ }
+ else if (bytes_writer) {
+ *bytes_str = _PyBytesWriter_Prepare(bytes_writer, *bytes_str, strlen);
+ if (*bytes_str == NULL) {
+ Py_DECREF(scratch);
+ return -1;
+ }
}
else {
str = PyUnicode_New(strlen, '9');
@@ -1673,13 +1681,8 @@ long_to_decimal_string_internal(PyObject *aa,
kind = PyUnicode_KIND(str);
}
-#define WRITE_DIGITS(TYPE) \
+#define WRITE_DIGITS(p) \
do { \
- if (writer) \
- p = (TYPE*)PyUnicode_DATA(writer->buffer) + writer->pos + strlen; \
- else \
- p = (TYPE*)PyUnicode_DATA(str) + strlen; \
- \
/* pout[0] through pout[size-2] contribute exactly \
_PyLong_DECIMAL_SHIFT digits each */ \
for (i=0; i < size - 1; i++) { \
@@ -1699,6 +1702,16 @@ long_to_decimal_string_internal(PyObject *aa,
/* and sign */ \
if (negative) \
*--p = '-'; \
+ } while (0)
+
+#define WRITE_UNICODE_DIGITS(TYPE) \
+ do { \
+ if (writer) \
+ p = (TYPE*)PyUnicode_DATA(writer->buffer) + writer->pos + strlen; \
+ else \
+ p = (TYPE*)PyUnicode_DATA(str) + strlen; \
+ \
+ WRITE_DIGITS(p); \
\
/* check we've counted correctly */ \
if (writer) \
@@ -1708,25 +1721,34 @@ long_to_decimal_string_internal(PyObject *aa,
} while (0)
/* fill the string right-to-left */
- if (kind == PyUnicode_1BYTE_KIND) {
+ if (bytes_writer) {
+ char *p = *bytes_str + strlen;
+ WRITE_DIGITS(p);
+ assert(p == *bytes_str);
+ }
+ else if (kind == PyUnicode_1BYTE_KIND) {
Py_UCS1 *p;
- WRITE_DIGITS(Py_UCS1);
+ WRITE_UNICODE_DIGITS(Py_UCS1);
}
else if (kind == PyUnicode_2BYTE_KIND) {
Py_UCS2 *p;
- WRITE_DIGITS(Py_UCS2);
+ WRITE_UNICODE_DIGITS(Py_UCS2);
}
else {
Py_UCS4 *p;
assert (kind == PyUnicode_4BYTE_KIND);
- WRITE_DIGITS(Py_UCS4);
+ WRITE_UNICODE_DIGITS(Py_UCS4);
}
#undef WRITE_DIGITS
+#undef WRITE_UNICODE_DIGITS
Py_DECREF(scratch);
if (writer) {
writer->pos += strlen;
}
+ else if (bytes_writer) {
+ (*bytes_str) += strlen;
+ }
else {
assert(_PyUnicode_CheckConsistency(str, 1));
*p_output = (PyObject *)str;
@@ -1738,7 +1760,7 @@ static PyObject *
long_to_decimal_string(PyObject *aa)
{
PyObject *v;
- if (long_to_decimal_string_internal(aa, &v, NULL) == -1)
+ if (long_to_decimal_string_internal(aa, &v, NULL, NULL, NULL) == -1)
return NULL;
return v;
}
@@ -1750,10 +1772,11 @@ long_to_decimal_string(PyObject *aa)
static int
long_format_binary(PyObject *aa, int base, int alternate,
- PyObject **p_output, _PyUnicodeWriter *writer)
+ PyObject **p_output, _PyUnicodeWriter *writer,
+ _PyBytesWriter *bytes_writer, char **bytes_str)
{
PyLongObject *a = (PyLongObject *)aa;
- PyObject *v;
+ PyObject *v = NULL;
Py_ssize_t sz;
Py_ssize_t size_a;
enum PyUnicode_Kind kind;
@@ -1810,7 +1833,11 @@ long_format_binary(PyObject *aa, int base, int alternate,
if (_PyUnicodeWriter_Prepare(writer, sz, 'x') == -1)
return -1;
kind = writer->kind;
- v = NULL;
+ }
+ else if (bytes_writer) {
+ *bytes_str = _PyBytesWriter_Prepare(bytes_writer, *bytes_str, sz);
+ if (*bytes_str == NULL)
+ return -1;
}
else {
v = PyUnicode_New(sz, 'x');
@@ -1819,13 +1846,8 @@ long_format_binary(PyObject *aa, int base, int alternate,
kind = PyUnicode_KIND(v);
}
-#define WRITE_DIGITS(TYPE) \
+#define WRITE_DIGITS(p) \
do { \
- if (writer) \
- p = (TYPE*)PyUnicode_DATA(writer->buffer) + writer->pos + sz; \
- else \
- p = (TYPE*)PyUnicode_DATA(v) + sz; \
- \
if (size_a == 0) { \
*--p = '0'; \
} \
@@ -1860,30 +1882,50 @@ long_format_binary(PyObject *aa, int base, int alternate,
} \
if (negative) \
*--p = '-'; \
+ } while (0)
+
+#define WRITE_UNICODE_DIGITS(TYPE) \
+ do { \
+ if (writer) \
+ p = (TYPE*)PyUnicode_DATA(writer->buffer) + writer->pos + sz; \
+ else \
+ p = (TYPE*)PyUnicode_DATA(v) + sz; \
+ \
+ WRITE_DIGITS(p); \
+ \
if (writer) \
assert(p == ((TYPE*)PyUnicode_DATA(writer->buffer) + writer->pos)); \
else \
assert(p == (TYPE*)PyUnicode_DATA(v)); \
} while (0)
- if (kind == PyUnicode_1BYTE_KIND) {
+ if (bytes_writer) {
+ char *p = *bytes_str + sz;
+ WRITE_DIGITS(p);
+ assert(p == *bytes_str);
+ }
+ else if (kind == PyUnicode_1BYTE_KIND) {
Py_UCS1 *p;
- WRITE_DIGITS(Py_UCS1);
+ WRITE_UNICODE_DIGITS(Py_UCS1);
}
else if (kind == PyUnicode_2BYTE_KIND) {
Py_UCS2 *p;
- WRITE_DIGITS(Py_UCS2);
+ WRITE_UNICODE_DIGITS(Py_UCS2);
}
else {
Py_UCS4 *p;
assert (kind == PyUnicode_4BYTE_KIND);
- WRITE_DIGITS(Py_UCS4);
+ WRITE_UNICODE_DIGITS(Py_UCS4);
}
#undef WRITE_DIGITS
+#undef WRITE_UNICODE_DIGITS
if (writer) {
writer->pos += sz;
}
+ else if (bytes_writer) {
+ (*bytes_str) += sz;
+ }
else {
assert(_PyUnicode_CheckConsistency(v, 1));
*p_output = v;
@@ -1897,9 +1939,9 @@ _PyLong_Format(PyObject *obj, int base)
PyObject *str;
int err;
if (base == 10)
- err = long_to_decimal_string_internal(obj, &str, NULL);
+ err = long_to_decimal_string_internal(obj, &str, NULL, NULL, NULL);
else
- err = long_format_binary(obj, base, 1, &str, NULL);
+ err = long_format_binary(obj, base, 1, &str, NULL, NULL, NULL);
if (err == -1)
return NULL;
return str;
@@ -1911,9 +1953,31 @@ _PyLong_FormatWriter(_PyUnicodeWriter *writer,
int base, int alternate)
{
if (base == 10)
- return long_to_decimal_string_internal(obj, NULL, writer);
+ return long_to_decimal_string_internal(obj, NULL, writer,
+ NULL, NULL);
else
- return long_format_binary(obj, base, alternate, NULL, writer);
+ return long_format_binary(obj, base, alternate, NULL, writer,
+ NULL, NULL);
+}
+
+char*
+_PyLong_FormatBytesWriter(_PyBytesWriter *writer, char *str,
+ PyObject *obj,
+ int base, int alternate)
+{
+ char *str2;
+ int res;
+ str2 = str;
+ if (base == 10)
+ res = long_to_decimal_string_internal(obj, NULL, NULL,
+ writer, &str2);
+ else
+ res = long_format_binary(obj, base, alternate, NULL, NULL,
+ writer, &str2);
+ if (res < 0)
+ return NULL;
+ assert(str2 != NULL);
+ return str2;
}
/* Table of digit values for 8-bit string -> integer conversion.
diff --git a/Objects/object.c b/Objects/object.c
index 6fc4df1639..e1718eafcd 100644
--- a/Objects/object.c
+++ b/Objects/object.c
@@ -686,11 +686,10 @@ do_richcompare(PyObject *v, PyObject *w, int op)
res = (v != w) ? Py_True : Py_False;
break;
default:
- /* XXX Special-case None so it doesn't show as NoneType() */
PyErr_Format(PyExc_TypeError,
- "unorderable types: %.100s() %s %.100s()",
- v->ob_type->tp_name,
+ "'%s' not supported between instances of '%.100s' and '%.100s'",
opstrings[op],
+ v->ob_type->tp_name,
w->ob_type->tp_name);
return NULL;
}
diff --git a/Objects/setobject.c b/Objects/setobject.c
index 2faaf12954..9468ee673e 100644
--- a/Objects/setobject.c
+++ b/Objects/setobject.c
@@ -29,7 +29,6 @@
#include "Python.h"
#include "structmember.h"
-#include "stringlib/eq.h"
/* Object used as dummy key to fill deleted entries */
static PyObject _dummy_struct;
@@ -51,19 +50,20 @@ static PyObject _dummy_struct;
static setentry *
set_lookkey(PySetObject *so, PyObject *key, Py_hash_t hash)
{
- setentry *table = so->table;
- setentry *freeslot = NULL;
+ setentry *table;
setentry *entry;
- size_t perturb = hash;
+ size_t perturb;
size_t mask = so->mask;
size_t i = (size_t)hash & mask; /* Unsigned for defined overflow behavior */
size_t j;
int cmp;
- entry = &table[i];
+ entry = &so->table[i];
if (entry->key == NULL)
return entry;
+ perturb = hash;
+
while (1) {
if (entry->hash == hash) {
PyObject *startkey = entry->key;
@@ -73,8 +73,9 @@ set_lookkey(PySetObject *so, PyObject *key, Py_hash_t hash)
return entry;
if (PyUnicode_CheckExact(startkey)
&& PyUnicode_CheckExact(key)
- && unicode_eq(startkey, key))
+ && _PyUnicode_EQ(startkey, key))
return entry;
+ table = so->table;
Py_INCREF(startkey);
cmp = PyObject_RichCompareBool(startkey, key, Py_EQ);
Py_DECREF(startkey);
@@ -86,14 +87,12 @@ set_lookkey(PySetObject *so, PyObject *key, Py_hash_t hash)
return entry;
mask = so->mask; /* help avoid a register spill */
}
- if (entry->hash == -1 && freeslot == NULL)
- freeslot = entry;
if (i + LINEAR_PROBES <= mask) {
for (j = 0 ; j < LINEAR_PROBES ; j++) {
entry++;
- if (entry->key == NULL)
- goto found_null;
+ if (entry->hash == 0 && entry->key == NULL)
+ return entry;
if (entry->hash == hash) {
PyObject *startkey = entry->key;
assert(startkey != dummy);
@@ -101,8 +100,9 @@ set_lookkey(PySetObject *so, PyObject *key, Py_hash_t hash)
return entry;
if (PyUnicode_CheckExact(startkey)
&& PyUnicode_CheckExact(key)
- && unicode_eq(startkey, key))
+ && _PyUnicode_EQ(startkey, key))
return entry;
+ table = so->table;
Py_INCREF(startkey);
cmp = PyObject_RichCompareBool(startkey, key, Py_EQ);
Py_DECREF(startkey);
@@ -114,7 +114,104 @@ set_lookkey(PySetObject *so, PyObject *key, Py_hash_t hash)
return entry;
mask = so->mask;
}
- if (entry->hash == -1 && freeslot == NULL)
+ }
+ }
+
+ perturb >>= PERTURB_SHIFT;
+ i = (i * 5 + 1 + perturb) & mask;
+
+ entry = &so->table[i];
+ if (entry->key == NULL)
+ return entry;
+ }
+}
+
+static int set_table_resize(PySetObject *, Py_ssize_t);
+
+static int
+set_add_entry(PySetObject *so, PyObject *key, Py_hash_t hash)
+{
+ setentry *table;
+ setentry *freeslot;
+ setentry *entry;
+ size_t perturb;
+ size_t mask;
+ size_t i; /* Unsigned for defined overflow behavior */
+ size_t j;
+ int cmp;
+
+ /* Pre-increment is necessary to prevent arbitrary code in the rich
+ comparison from deallocating the key just before the insertion. */
+ Py_INCREF(key);
+
+ restart:
+
+ mask = so->mask;
+ i = (size_t)hash & mask;
+
+ entry = &so->table[i];
+ if (entry->key == NULL)
+ goto found_unused;
+
+ freeslot = NULL;
+ perturb = hash;
+
+ while (1) {
+ if (entry->hash == hash) {
+ PyObject *startkey = entry->key;
+ /* startkey cannot be a dummy because the dummy hash field is -1 */
+ assert(startkey != dummy);
+ if (startkey == key)
+ goto found_active;
+ if (PyUnicode_CheckExact(startkey)
+ && PyUnicode_CheckExact(key)
+ && _PyUnicode_EQ(startkey, key))
+ goto found_active;
+ table = so->table;
+ Py_INCREF(startkey);
+ cmp = PyObject_RichCompareBool(startkey, key, Py_EQ);
+ Py_DECREF(startkey);
+ if (cmp > 0) /* likely */
+ goto found_active;
+ if (cmp < 0)
+ goto comparison_error;
+ /* Continuing the search from the current entry only makes
+ sense if the table and entry are unchanged; otherwise,
+ we have to restart from the beginning */
+ if (table != so->table || entry->key != startkey)
+ goto restart;
+ mask = so->mask; /* help avoid a register spill */
+ }
+ else if (entry->hash == -1 && freeslot == NULL)
+ freeslot = entry;
+
+ if (i + LINEAR_PROBES <= mask) {
+ for (j = 0 ; j < LINEAR_PROBES ; j++) {
+ entry++;
+ if (entry->hash == 0 && entry->key == NULL)
+ goto found_unused_or_dummy;
+ if (entry->hash == hash) {
+ PyObject *startkey = entry->key;
+ assert(startkey != dummy);
+ if (startkey == key)
+ goto found_active;
+ if (PyUnicode_CheckExact(startkey)
+ && PyUnicode_CheckExact(key)
+ && _PyUnicode_EQ(startkey, key))
+ goto found_active;
+ table = so->table;
+ Py_INCREF(startkey);
+ cmp = PyObject_RichCompareBool(startkey, key, Py_EQ);
+ Py_DECREF(startkey);
+ if (cmp > 0)
+ goto found_active;
+ if (cmp < 0)
+ goto comparison_error;
+ if (table != so->table || entry->key != startkey)
+ goto restart;
+ mask = so->mask;
+ }
+ else if (entry->hash == -1 && freeslot == NULL)
freeslot = entry;
}
}
@@ -122,29 +219,51 @@ set_lookkey(PySetObject *so, PyObject *key, Py_hash_t hash)
perturb >>= PERTURB_SHIFT;
i = (i * 5 + 1 + perturb) & mask;
- entry = &table[i];
+ entry = &so->table[i];
if (entry->key == NULL)
- goto found_null;
+ goto found_unused_or_dummy;
}
- found_null:
- return freeslot == NULL ? entry : freeslot;
+
+ found_unused_or_dummy:
+ if (freeslot == NULL)
+ goto found_unused;
+ so->used++;
+ freeslot->key = key;
+ freeslot->hash = hash;
+ return 0;
+
+ found_unused:
+ so->fill++;
+ so->used++;
+ entry->key = key;
+ entry->hash = hash;
+ if ((size_t)so->fill*3 < mask*2)
+ return 0;
+ return set_table_resize(so, so->used);
+
+ found_active:
+ Py_DECREF(key);
+ return 0;
+
+ comparison_error:
+ Py_DECREF(key);
+ return -1;
}
/*
Internal routine used by set_table_resize() to insert an item which is
known to be absent from the set. This routine also assumes that
the set contains no deleted entries. Besides the performance benefit,
-using set_insert_clean() in set_table_resize() is dangerous (SF bug #1456209).
-Note that no refcounts are changed by this routine; if needed, the caller
-is responsible for incref'ing `key`.
+there is also safety benefit since using set_add_entry() risks making
+a callback in the middle of a set_table_resize(), see issue 1456209.
+The caller is responsible for updating the key's reference count and
+the setobject's fill and used fields.
*/
static void
-set_insert_clean(PySetObject *so, PyObject *key, Py_hash_t hash)
+set_insert_clean(setentry *table, size_t mask, PyObject *key, Py_hash_t hash)
{
- setentry *table = so->table;
setentry *entry;
size_t perturb = hash;
- size_t mask = (size_t)so->mask;
size_t i = (size_t)hash & mask;
size_t j;
@@ -165,45 +284,11 @@ set_insert_clean(PySetObject *so, PyObject *key, Py_hash_t hash)
found_null:
entry->key = key;
entry->hash = hash;
- so->fill++;
- so->used++;
}
/* ======== End logic for probing the hash table ========================== */
/* ======================================================================== */
-
-/*
-Internal routine to insert a new key into the table.
-Used by the public insert routine.
-Eats a reference to key.
-*/
-static int
-set_insert_key(PySetObject *so, PyObject *key, Py_hash_t hash)
-{
- setentry *entry;
-
- entry = set_lookkey(so, key, hash);
- if (entry == NULL)
- return -1;
- if (entry->key == NULL) {
- /* UNUSED */
- entry->key = key;
- entry->hash = hash;
- so->fill++;
- so->used++;
- } else if (entry->key == dummy) {
- /* DUMMY */
- entry->key = key;
- entry->hash = hash;
- so->used++;
- } else {
- /* ACTIVE */
- Py_DECREF(key);
- }
- return 0;
-}
-
/*
Restructure the table by allocating a new table and reinserting all
keys again. When entries have been deleted, the new table may
@@ -216,10 +301,13 @@ set_table_resize(PySetObject *so, Py_ssize_t minused)
setentry *oldtable, *newtable, *entry;
Py_ssize_t oldfill = so->fill;
Py_ssize_t oldused = so->used;
+ Py_ssize_t oldmask = so->mask;
+ size_t newmask;
int is_oldtable_malloced;
setentry small_copy[PySet_MINSIZE];
assert(minused >= 0);
+ minused = (minused > 50000) ? minused * 2 : minused * 4;
/* Find the smallest table size > minused. */
/* XXX speed-up with intrinsics */
@@ -267,25 +355,24 @@ set_table_resize(PySetObject *so, Py_ssize_t minused)
/* Make the set empty, using the new table. */
assert(newtable != oldtable);
memset(newtable, 0, sizeof(setentry) * newsize);
- so->fill = 0;
- so->used = 0;
+ so->fill = oldused;
+ so->used = oldused;
so->mask = newsize - 1;
so->table = newtable;
/* Copy the data over; this is refcount-neutral for active entries;
dummy entries aren't copied over, of course */
+ newmask = (size_t)so->mask;
if (oldfill == oldused) {
- for (entry = oldtable; oldused > 0; entry++) {
+ for (entry = oldtable; entry <= oldtable + oldmask; entry++) {
if (entry->key != NULL) {
- oldused--;
- set_insert_clean(so, entry->key, entry->hash);
+ set_insert_clean(newtable, newmask, entry->key, entry->hash);
}
}
} else {
- for (entry = oldtable; oldused > 0; entry++) {
+ for (entry = oldtable; entry <= oldtable + oldmask; entry++) {
if (entry->key != NULL && entry->key != dummy) {
- oldused--;
- set_insert_clean(so, entry->key, entry->hash);
+ set_insert_clean(newtable, newmask, entry->key, entry->hash);
}
}
}
@@ -295,31 +382,42 @@ set_table_resize(PySetObject *so, Py_ssize_t minused)
return 0;
}
-/* CAUTION: set_add_key/entry() must guarantee it won't resize the table */
+static int
+set_contains_entry(PySetObject *so, PyObject *key, Py_hash_t hash)
+{
+ setentry *entry;
+
+ entry = set_lookkey(so, key, hash);
+ if (entry != NULL)
+ return entry->key != NULL;
+ return -1;
+}
+
+#define DISCARD_NOTFOUND 0
+#define DISCARD_FOUND 1
static int
-set_add_entry(PySetObject *so, setentry *entry)
+set_discard_entry(PySetObject *so, PyObject *key, Py_hash_t hash)
{
- Py_ssize_t n_used;
- PyObject *key = entry->key;
- Py_hash_t hash = entry->hash;
+ setentry *entry;
+ PyObject *old_key;
- assert(so->fill <= so->mask); /* at least one empty slot */
- n_used = so->used;
- Py_INCREF(key);
- if (set_insert_key(so, key, hash)) {
- Py_DECREF(key);
+ entry = set_lookkey(so, key, hash);
+ if (entry == NULL)
return -1;
- }
- if (!(so->used > n_used && so->fill*3 >= (so->mask+1)*2))
- return 0;
- return set_table_resize(so, so->used>50000 ? so->used*2 : so->used*4);
+ if (entry->key == NULL)
+ return DISCARD_NOTFOUND;
+ old_key = entry->key;
+ entry->key = dummy;
+ entry->hash = -1;
+ so->used--;
+ Py_DECREF(old_key);
+ return DISCARD_FOUND;
}
static int
set_add_key(PySetObject *so, PyObject *key)
{
- setentry entry;
Py_hash_t hash;
if (!PyUnicode_CheckExact(key) ||
@@ -328,50 +426,35 @@ set_add_key(PySetObject *so, PyObject *key)
if (hash == -1)
return -1;
}
- entry.key = key;
- entry.hash = hash;
- return set_add_entry(so, &entry);
+ return set_add_entry(so, key, hash);
}
-#define DISCARD_NOTFOUND 0
-#define DISCARD_FOUND 1
-
static int
-set_discard_entry(PySetObject *so, setentry *oldentry)
+set_contains_key(PySetObject *so, PyObject *key)
{
- setentry *entry;
- PyObject *old_key;
+ Py_hash_t hash;
- entry = set_lookkey(so, oldentry->key, oldentry->hash);
- if (entry == NULL)
- return -1;
- if (entry->key == NULL || entry->key == dummy)
- return DISCARD_NOTFOUND;
- old_key = entry->key;
- entry->key = dummy;
- entry->hash = -1;
- so->used--;
- Py_DECREF(old_key);
- return DISCARD_FOUND;
+ if (!PyUnicode_CheckExact(key) ||
+ (hash = ((PyASCIIObject *) key)->hash) == -1) {
+ hash = PyObject_Hash(key);
+ if (hash == -1)
+ return -1;
+ }
+ return set_contains_entry(so, key, hash);
}
static int
set_discard_key(PySetObject *so, PyObject *key)
{
- setentry entry;
Py_hash_t hash;
- assert (PyAnySet_Check(so));
-
if (!PyUnicode_CheckExact(key) ||
(hash = ((PyASCIIObject *) key)->hash) == -1) {
hash = PyObject_Hash(key);
if (hash == -1)
return -1;
}
- entry.key = key;
- entry.hash = hash;
- return set_discard_entry(so, &entry);
+ return set_discard_entry(so, key, hash);
}
static void
@@ -452,20 +535,22 @@ set_next(PySetObject *so, Py_ssize_t *pos_ptr, setentry **entry_ptr)
{
Py_ssize_t i;
Py_ssize_t mask;
- setentry *table;
+ setentry *entry;
assert (PyAnySet_Check(so));
i = *pos_ptr;
assert(i >= 0);
- table = so->table;
mask = so->mask;
- while (i <= mask && (table[i].key == NULL || table[i].key == dummy))
+ entry = &so->table[i];
+ while (i <= mask && (entry->key == NULL || entry->key == dummy)) {
i++;
+ entry++;
+ }
*pos_ptr = i+1;
if (i > mask)
return 0;
- assert(table[i].key != NULL);
- *entry_ptr = &table[i];
+ assert(entry != NULL);
+ *entry_ptr = entry;
return 1;
}
@@ -563,8 +648,8 @@ set_merge(PySetObject *so, PyObject *otherset)
* incrementally resizing as we insert new keys. Expect
* that there will be no (or few) overlapping keys.
*/
- if ((so->fill + other->used)*3 >= (so->mask+1)*2) {
- if (set_table_resize(so, (so->used + other->used)*2) != 0)
+ if ((so->fill + other->used)*3 >= so->mask*2) {
+ if (set_table_resize(so, so->used + other->used) != 0)
return -1;
}
so_entry = so->table;
@@ -589,11 +674,15 @@ set_merge(PySetObject *so, PyObject *otherset)
/* If our table is empty, we can use set_insert_clean() */
if (so->fill == 0) {
- for (i = 0; i <= other->mask; i++, other_entry++) {
+ setentry *newtable = so->table;
+ size_t newmask = (size_t)so->mask;
+ so->fill = other->used;
+ so->used = other->used;
+ for (i = other->mask + 1; i > 0 ; i--, other_entry++) {
key = other_entry->key;
if (key != NULL && key != dummy) {
Py_INCREF(key);
- set_insert_clean(so, key, other_entry->hash);
+ set_insert_clean(newtable, newmask, key, other_entry->hash);
}
}
return 0;
@@ -604,46 +693,13 @@ set_merge(PySetObject *so, PyObject *otherset)
other_entry = &other->table[i];
key = other_entry->key;
if (key != NULL && key != dummy) {
- Py_INCREF(key);
- if (set_insert_key(so, key, other_entry->hash)) {
- Py_DECREF(key);
+ if (set_add_entry(so, key, other_entry->hash))
return -1;
- }
}
}
return 0;
}
-static int
-set_contains_entry(PySetObject *so, setentry *entry)
-{
- PyObject *key;
- setentry *lu_entry;
-
- lu_entry = set_lookkey(so, entry->key, entry->hash);
- if (lu_entry == NULL)
- return -1;
- key = lu_entry->key;
- return key != NULL && key != dummy;
-}
-
-static int
-set_contains_key(PySetObject *so, PyObject *key)
-{
- setentry entry;
- Py_hash_t hash;
-
- if (!PyUnicode_CheckExact(key) ||
- (hash = ((PyASCIIObject *) key)->hash) == -1) {
- hash = PyObject_Hash(key);
- if (hash == -1)
- return -1;
- }
- entry.key = key;
- entry.hash = hash;
- return set_contains_entry(so, &entry);
-}
-
static PyObject *
set_pop(PySetObject *so)
{
@@ -685,43 +741,64 @@ set_traverse(PySetObject *so, visitproc visit, void *arg)
return 0;
}
-static Py_hash_t
-frozenset_hash(PyObject *self)
+/* Work to increase the bit dispersion for closely spaced hash values.
+ This is important because some use cases have many combinations of a
+ small number of elements with nearby hashes so that many distinct
+ combinations collapse to only a handful of distinct hash values. */
+
+static Py_uhash_t
+_shuffle_bits(Py_uhash_t h)
{
- /* Most of the constants in this hash algorithm are randomly choosen
- large primes with "interesting bit patterns" and that passed
- tests for good collision statistics on a variety of problematic
- datasets such as:
+ return ((h ^ 89869747UL) ^ (h << 16)) * 3644798167UL;
+}
- ps = []
- for r in range(21):
- ps += itertools.combinations(range(20), r)
- num_distinct_hashes = len({hash(frozenset(s)) for s in ps})
+/* Most of the constants in this hash algorithm are randomly chosen
+ large primes with "interesting bit patterns" and that passed tests
+ for good collision statistics on a variety of problematic datasets
+ including powersets and graph structures (such as David Eppstein's
+ graph recipes in Lib/test/test_set.py) */
- */
+static Py_hash_t
+frozenset_hash(PyObject *self)
+{
PySetObject *so = (PySetObject *)self;
- Py_uhash_t h, hash = 1927868237UL;
+ Py_uhash_t hash = 0;
setentry *entry;
- Py_ssize_t pos = 0;
if (so->hash != -1)
return so->hash;
- hash *= (Py_uhash_t)PySet_GET_SIZE(self) + 1;
- while (set_next(so, &pos, &entry)) {
- /* Work to increase the bit dispersion for closely spaced hash
- values. This is important because some use cases have many
- combinations of a small number of elements with nearby
- hashes so that many distinct combinations collapse to only
- a handful of distinct hash values. */
- h = entry->hash;
- hash ^= ((h ^ 89869747UL) ^ (h << 16)) * 3644798167UL;
- }
- /* Make the final result spread-out in a different pattern
- than the algorithm for tuples or other python objects. */
+ /* Xor-in shuffled bits from every entry's hash field because xor is
+ commutative and a frozenset hash should be independent of order.
+
+ For speed, include null entries and dummy entries and then
+ subtract out their effect afterwards so that the final hash
+ depends only on active entries. This allows the code to be
+ vectorized by the compiler and it saves the unpredictable
+ branches that would arise when trying to exclude null and dummy
+ entries on every iteration. */
+
+ for (entry = so->table; entry <= &so->table[so->mask]; entry++)
+ hash ^= _shuffle_bits(entry->hash);
+
+ /* Remove the effect of an odd number of NULL entries */
+ if ((so->mask + 1 - so->fill) & 1)
+ hash ^= _shuffle_bits(0);
+
+ /* Remove the effect of an odd number of dummy entries */
+ if ((so->fill - so->used) & 1)
+ hash ^= _shuffle_bits(-1);
+
+ /* Factor in the number of active entries */
+ hash ^= ((Py_uhash_t)PySet_GET_SIZE(self) + 1) * 1927868237UL;
+
+ /* Disperse patterns arising in nested frozensets */
hash = hash * 69069U + 907133923UL;
+
+ /* -1 is reserved as an error code */
if (hash == (Py_uhash_t)-1)
hash = 590923713UL;
+
so->hash = hash;
return hash;
}
@@ -868,7 +945,7 @@ PyTypeObject PySetIter_Type = {
PyObject_GenericGetAttr, /* tp_getattro */
0, /* tp_setattro */
0, /* tp_as_buffer */
- Py_TPFLAGS_DEFAULT | Py_TPFLAGS_HAVE_GC,/* tp_flags */
+ Py_TPFLAGS_DEFAULT | Py_TPFLAGS_HAVE_GC, /* tp_flags */
0, /* tp_doc */
(traverseproc)setiter_traverse, /* tp_traverse */
0, /* tp_clear */
@@ -913,18 +990,14 @@ set_update_internal(PySetObject *so, PyObject *other)
* incrementally resizing as we insert new keys. Expect
* that there will be no (or few) overlapping keys.
*/
- if (dictsize == -1)
+ if (dictsize < 0)
return -1;
- if ((so->fill + dictsize)*3 >= (so->mask+1)*2) {
- if (set_table_resize(so, (so->used + dictsize)*2) != 0)
+ if ((so->fill + dictsize)*3 >= so->mask*2) {
+ if (set_table_resize(so, so->used + dictsize) != 0)
return -1;
}
while (_PyDict_Next(other, &pos, &key, &value, &hash)) {
- setentry an_entry;
-
- an_entry.hash = hash;
- an_entry.key = key;
- if (set_add_entry(so, &an_entry))
+ if (set_add_entry(so, key, hash))
return -1;
}
return 0;
@@ -1204,6 +1277,8 @@ set_intersection(PySetObject *so, PyObject *other)
{
PySetObject *result;
PyObject *key, *it, *tmp;
+ Py_hash_t hash;
+ int rv;
if ((PyObject *)so == other)
return set_copy(so);
@@ -1223,13 +1298,15 @@ set_intersection(PySetObject *so, PyObject *other)
}
while (set_next((PySetObject *)other, &pos, &entry)) {
- int rv = set_contains_entry(so, entry);
- if (rv == -1) {
+ key = entry->key;
+ hash = entry->hash;
+ rv = set_contains_entry(so, key, hash);
+ if (rv < 0) {
Py_DECREF(result);
return NULL;
}
if (rv) {
- if (set_add_entry(result, entry)) {
+ if (set_add_entry(result, key, hash)) {
Py_DECREF(result);
return NULL;
}
@@ -1245,32 +1322,15 @@ set_intersection(PySetObject *so, PyObject *other)
}
while ((key = PyIter_Next(it)) != NULL) {
- int rv;
- setentry entry;
- Py_hash_t hash = PyObject_Hash(key);
-
- if (hash == -1) {
- Py_DECREF(it);
- Py_DECREF(result);
- Py_DECREF(key);
- return NULL;
- }
- entry.hash = hash;
- entry.key = key;
- rv = set_contains_entry(so, &entry);
- if (rv == -1) {
- Py_DECREF(it);
- Py_DECREF(result);
- Py_DECREF(key);
- return NULL;
- }
+ hash = PyObject_Hash(key);
+ if (hash == -1)
+ goto error;
+ rv = set_contains_entry(so, key, hash);
+ if (rv < 0)
+ goto error;
if (rv) {
- if (set_add_entry(result, &entry)) {
- Py_DECREF(it);
- Py_DECREF(result);
- Py_DECREF(key);
- return NULL;
- }
+ if (set_add_entry(result, key, hash))
+ goto error;
}
Py_DECREF(key);
}
@@ -1280,6 +1340,11 @@ set_intersection(PySetObject *so, PyObject *other)
return NULL;
}
return (PyObject *)result;
+ error:
+ Py_DECREF(it);
+ Py_DECREF(result);
+ Py_DECREF(key);
+ return NULL;
}
static PyObject *
@@ -1366,6 +1431,7 @@ static PyObject *
set_isdisjoint(PySetObject *so, PyObject *other)
{
PyObject *key, *it, *tmp;
+ int rv;
if ((PyObject *)so == other) {
if (PySet_GET_SIZE(so) == 0)
@@ -1384,8 +1450,8 @@ set_isdisjoint(PySetObject *so, PyObject *other)
other = tmp;
}
while (set_next((PySetObject *)other, &pos, &entry)) {
- int rv = set_contains_entry(so, entry);
- if (rv == -1)
+ rv = set_contains_entry(so, entry->key, entry->hash);
+ if (rv < 0)
return NULL;
if (rv)
Py_RETURN_FALSE;
@@ -1398,8 +1464,6 @@ set_isdisjoint(PySetObject *so, PyObject *other)
return NULL;
while ((key = PyIter_Next(it)) != NULL) {
- int rv;
- setentry entry;
Py_hash_t hash = PyObject_Hash(key);
if (hash == -1) {
@@ -1407,11 +1471,9 @@ set_isdisjoint(PySetObject *so, PyObject *other)
Py_DECREF(it);
return NULL;
}
- entry.hash = hash;
- entry.key = key;
- rv = set_contains_entry(so, &entry);
+ rv = set_contains_entry(so, key, hash);
Py_DECREF(key);
- if (rv == -1) {
+ if (rv < 0) {
Py_DECREF(it);
return NULL;
}
@@ -1440,7 +1502,7 @@ set_difference_update_internal(PySetObject *so, PyObject *other)
Py_ssize_t pos = 0;
while (set_next((PySetObject *)other, &pos, &entry))
- if (set_discard_entry(so, entry) == -1)
+ if (set_discard_entry(so, entry->key, entry->hash) < 0)
return -1;
} else {
PyObject *key, *it;
@@ -1449,7 +1511,7 @@ set_difference_update_internal(PySetObject *so, PyObject *other)
return -1;
while ((key = PyIter_Next(it)) != NULL) {
- if (set_discard_key(so, key) == -1) {
+ if (set_discard_key(so, key) < 0) {
Py_DECREF(it);
Py_DECREF(key);
return -1;
@@ -1460,10 +1522,10 @@ set_difference_update_internal(PySetObject *so, PyObject *other)
if (PyErr_Occurred())
return -1;
}
- /* If more than 1/5 are dummies, then resize them away. */
- if ((so->fill - so->used) * 5 < so->mask)
+ /* If more than 1/4th are dummies, then resize them away. */
+ if ((size_t)(so->fill - so->used) <= (size_t)so->mask / 4)
return 0;
- return set_table_resize(so, so->used>50000 ? so->used*2 : so->used*4);
+ return set_table_resize(so, so->used);
}
static PyObject *
@@ -1490,7 +1552,7 @@ set_copy_and_difference(PySetObject *so, PyObject *other)
result = set_copy(so);
if (result == NULL)
return NULL;
- if (set_difference_update_internal((PySetObject *) result, other) != -1)
+ if (set_difference_update_internal((PySetObject *) result, other) == 0)
return result;
Py_DECREF(result);
return NULL;
@@ -1500,8 +1562,11 @@ static PyObject *
set_difference(PySetObject *so, PyObject *other)
{
PyObject *result;
+ PyObject *key;
+ Py_hash_t hash;
setentry *entry;
Py_ssize_t pos = 0;
+ int rv;
if (!PyAnySet_Check(other) && !PyDict_CheckExact(other)) {
return set_copy_and_difference(so, other);
@@ -1519,17 +1584,15 @@ set_difference(PySetObject *so, PyObject *other)
if (PyDict_CheckExact(other)) {
while (set_next(so, &pos, &entry)) {
- setentry entrycopy;
- int rv;
- entrycopy.hash = entry->hash;
- entrycopy.key = entry->key;
- rv = _PyDict_Contains(other, entry->key, entry->hash);
+ key = entry->key;
+ hash = entry->hash;
+ rv = _PyDict_Contains(other, key, hash);
if (rv < 0) {
Py_DECREF(result);
return NULL;
}
if (!rv) {
- if (set_add_entry((PySetObject *)result, &entrycopy)) {
+ if (set_add_entry((PySetObject *)result, key, hash)) {
Py_DECREF(result);
return NULL;
}
@@ -1540,13 +1603,15 @@ set_difference(PySetObject *so, PyObject *other)
/* Iterate over so, checking for common elements in other. */
while (set_next(so, &pos, &entry)) {
- int rv = set_contains_entry((PySetObject *)other, entry);
- if (rv == -1) {
+ key = entry->key;
+ hash = entry->hash;
+ rv = set_contains_entry((PySetObject *)other, key, hash);
+ if (rv < 0) {
Py_DECREF(result);
return NULL;
}
if (!rv) {
- if (set_add_entry((PySetObject *)result, entry)) {
+ if (set_add_entry((PySetObject *)result, key, hash)) {
Py_DECREF(result);
return NULL;
}
@@ -1608,29 +1673,24 @@ set_symmetric_difference_update(PySetObject *so, PyObject *other)
PySetObject *otherset;
PyObject *key;
Py_ssize_t pos = 0;
+ Py_hash_t hash;
setentry *entry;
+ int rv;
if ((PyObject *)so == other)
return set_clear(so);
if (PyDict_CheckExact(other)) {
PyObject *value;
- int rv;
- Py_hash_t hash;
while (_PyDict_Next(other, &pos, &key, &value, &hash)) {
- setentry an_entry;
-
Py_INCREF(key);
- an_entry.hash = hash;
- an_entry.key = key;
-
- rv = set_discard_entry(so, &an_entry);
- if (rv == -1) {
+ rv = set_discard_entry(so, key, hash);
+ if (rv < 0) {
Py_DECREF(key);
return NULL;
}
if (rv == DISCARD_NOTFOUND) {
- if (set_add_entry(so, &an_entry)) {
+ if (set_add_entry(so, key, hash)) {
Py_DECREF(key);
return NULL;
}
@@ -1650,13 +1710,15 @@ set_symmetric_difference_update(PySetObject *so, PyObject *other)
}
while (set_next(otherset, &pos, &entry)) {
- int rv = set_discard_entry(so, entry);
- if (rv == -1) {
+ key = entry->key;
+ hash = entry->hash;
+ rv = set_discard_entry(so, key, hash);
+ if (rv < 0) {
Py_DECREF(otherset);
return NULL;
}
if (rv == DISCARD_NOTFOUND) {
- if (set_add_entry(so, entry)) {
+ if (set_add_entry(so, key, hash)) {
Py_DECREF(otherset);
return NULL;
}
@@ -1718,6 +1780,7 @@ set_issubset(PySetObject *so, PyObject *other)
{
setentry *entry;
Py_ssize_t pos = 0;
+ int rv;
if (!PyAnySet_Check(other)) {
PyObject *tmp, *result;
@@ -1732,8 +1795,8 @@ set_issubset(PySetObject *so, PyObject *other)
Py_RETURN_FALSE;
while (set_next(so, &pos, &entry)) {
- int rv = set_contains_entry((PySetObject *)other, entry);
- if (rv == -1)
+ rv = set_contains_entry((PySetObject *)other, entry->key, entry->hash);
+ if (rv < 0)
return NULL;
if (!rv)
Py_RETURN_FALSE;
@@ -1824,7 +1887,7 @@ set_contains(PySetObject *so, PyObject *key)
int rv;
rv = set_contains_key(so, key);
- if (rv == -1) {
+ if (rv < 0) {
if (!PySet_Check(key) || !PyErr_ExceptionMatches(PyExc_TypeError))
return -1;
PyErr_Clear();
@@ -1843,7 +1906,7 @@ set_direct_contains(PySetObject *so, PyObject *key)
long result;
result = set_contains(so, key);
- if (result == -1)
+ if (result < 0)
return NULL;
return PyBool_FromLong(result);
}
@@ -1857,7 +1920,7 @@ set_remove(PySetObject *so, PyObject *key)
int rv;
rv = set_discard_key(so, key);
- if (rv == -1) {
+ if (rv < 0) {
if (!PySet_Check(key) || !PyErr_ExceptionMatches(PyExc_TypeError))
return NULL;
PyErr_Clear();
@@ -1866,7 +1929,7 @@ set_remove(PySetObject *so, PyObject *key)
return NULL;
rv = set_discard_key(so, tmpkey);
Py_DECREF(tmpkey);
- if (rv == -1)
+ if (rv < 0)
return NULL;
}
@@ -1889,7 +1952,7 @@ set_discard(PySetObject *so, PyObject *key)
int rv;
rv = set_discard_key(so, key);
- if (rv == -1) {
+ if (rv < 0) {
if (!PySet_Check(key) || !PyErr_ExceptionMatches(PyExc_TypeError))
return NULL;
PyErr_Clear();
@@ -1898,7 +1961,7 @@ set_discard(PySetObject *so, PyObject *key)
return NULL;
rv = set_discard_key(so, tmpkey);
Py_DECREF(tmpkey);
- if (rv == -1)
+ if (rv < 0)
return NULL;
}
Py_RETURN_NONE;
@@ -2125,7 +2188,7 @@ static PyMethodDef frozenset_methods[] = {
copy_doc},
{"difference", (PyCFunction)set_difference_multi, METH_VARARGS,
difference_doc},
- {"intersection",(PyCFunction)set_intersection_multi, METH_VARARGS,
+ {"intersection", (PyCFunction)set_intersection_multi, METH_VARARGS,
intersection_doc},
{"isdisjoint", (PyCFunction)set_isdisjoint, METH_O,
isdisjoint_doc},
@@ -2196,7 +2259,7 @@ PyTypeObject PyFrozenSet_Type = {
(traverseproc)set_traverse, /* tp_traverse */
(inquiry)set_clear_internal, /* tp_clear */
(richcmpfunc)set_richcompare, /* tp_richcompare */
- offsetof(PySetObject, weakreflist), /* tp_weaklistoffset */
+ offsetof(PySetObject, weakreflist), /* tp_weaklistoffset */
(getiterfunc)set_iter, /* tp_iter */
0, /* tp_iternext */
frozenset_methods, /* tp_methods */
diff --git a/Objects/stringlib/codecs.h b/Objects/stringlib/codecs.h
index 0fc6b582d2..2beb604f11 100644
--- a/Objects/stringlib/codecs.h
+++ b/Objects/stringlib/codecs.h
@@ -263,50 +263,34 @@ STRINGLIB(utf8_encoder)(PyObject *unicode,
#define MAX_SHORT_UNICHARS 300 /* largest size we'll do on the stack */
Py_ssize_t i; /* index into s of next input byte */
- PyObject *result; /* result string object */
char *p; /* next free byte in output buffer */
- Py_ssize_t nallocated; /* number of result bytes allocated */
- Py_ssize_t nneeded; /* number of result bytes needed */
#if STRINGLIB_SIZEOF_CHAR > 1
- PyObject *errorHandler = NULL;
+ PyObject *error_handler_obj = NULL;
PyObject *exc = NULL;
PyObject *rep = NULL;
+ _Py_error_handler error_handler = _Py_ERROR_UNKNOWN;
#endif
#if STRINGLIB_SIZEOF_CHAR == 1
const Py_ssize_t max_char_size = 2;
- char stackbuf[MAX_SHORT_UNICHARS * 2];
#elif STRINGLIB_SIZEOF_CHAR == 2
const Py_ssize_t max_char_size = 3;
- char stackbuf[MAX_SHORT_UNICHARS * 3];
#else /* STRINGLIB_SIZEOF_CHAR == 4 */
const Py_ssize_t max_char_size = 4;
- char stackbuf[MAX_SHORT_UNICHARS * 4];
#endif
+ _PyBytesWriter writer;
assert(size >= 0);
+ _PyBytesWriter_Init(&writer);
- if (size <= MAX_SHORT_UNICHARS) {
- /* Write into the stack buffer; nallocated can't overflow.
- * At the end, we'll allocate exactly as much heap space as it
- * turns out we need.
- */
- nallocated = Py_SAFE_DOWNCAST(sizeof(stackbuf), size_t, int);
- result = NULL; /* will allocate after we're done */
- p = stackbuf;
- }
- else {
- if (size > PY_SSIZE_T_MAX / max_char_size) {
- /* integer overflow */
- return PyErr_NoMemory();
- }
- /* Overallocate on the heap, and give the excess back at the end. */
- nallocated = size * max_char_size;
- result = PyBytes_FromStringAndSize(NULL, nallocated);
- if (result == NULL)
- return NULL;
- p = PyBytes_AS_STRING(result);
+ if (size > PY_SSIZE_T_MAX / max_char_size) {
+ /* integer overflow */
+ return PyErr_NoMemory();
}
+ p = _PyBytesWriter_Alloc(&writer, size * max_char_size);
+ if (p == NULL)
+ return NULL;
+
for (i = 0; i < size;) {
Py_UCS4 ch = data[i++];
@@ -326,72 +310,118 @@ STRINGLIB(utf8_encoder)(PyObject *unicode,
}
#if STRINGLIB_SIZEOF_CHAR > 1
else if (Py_UNICODE_IS_SURROGATE(ch)) {
- Py_ssize_t newpos;
- Py_ssize_t repsize, k, startpos;
+ Py_ssize_t startpos, endpos, newpos;
+ Py_ssize_t k;
+ if (error_handler == _Py_ERROR_UNKNOWN)
+ error_handler = get_error_handler(errors);
+
startpos = i-1;
- rep = unicode_encode_call_errorhandler(
- errors, &errorHandler, "utf-8", "surrogates not allowed",
- unicode, &exc, startpos, startpos+1, &newpos);
- if (!rep)
- goto error;
-
- if (PyBytes_Check(rep))
- repsize = PyBytes_GET_SIZE(rep);
- else
- repsize = PyUnicode_GET_LENGTH(rep);
+ endpos = startpos+1;
+
+ while ((endpos < size) && Py_UNICODE_IS_SURROGATE(data[endpos]))
+ endpos++;
+
+ /* Only overallocate the buffer if it's not the last write */
+ writer.overallocate = (endpos < size);
+
+ switch (error_handler)
+ {
+ case _Py_ERROR_REPLACE:
+ memset(p, '?', endpos - startpos);
+ p += (endpos - startpos);
+ /* fall through the ignore handler */
+ case _Py_ERROR_IGNORE:
+ i += (endpos - startpos - 1);
+ break;
- if (repsize > max_char_size) {
- Py_ssize_t offset;
+ case _Py_ERROR_SURROGATEPASS:
+ for (k=startpos; k<endpos; k++) {
+ ch = data[k];
+ *p++ = (char)(0xe0 | (ch >> 12));
+ *p++ = (char)(0x80 | ((ch >> 6) & 0x3f));
+ *p++ = (char)(0x80 | (ch & 0x3f));
+ }
+ i += (endpos - startpos - 1);
+ break;
- if (result == NULL)
- offset = p - stackbuf;
- else
- offset = p - PyBytes_AS_STRING(result);
+ case _Py_ERROR_BACKSLASHREPLACE:
+ /* substract preallocated bytes */
+ writer.min_size -= max_char_size * (endpos - startpos);
+ p = backslashreplace(&writer, p,
+ unicode, startpos, endpos);
+ if (p == NULL)
+ goto error;
+ i += (endpos - startpos - 1);
+ break;
- if (nallocated > PY_SSIZE_T_MAX - repsize + max_char_size) {
- /* integer overflow */
- PyErr_NoMemory();
+ case _Py_ERROR_XMLCHARREFREPLACE:
+ /* substract preallocated bytes */
+ writer.min_size -= max_char_size * (endpos - startpos);
+ p = xmlcharrefreplace(&writer, p,
+ unicode, startpos, endpos);
+ if (p == NULL)
goto error;
+ i += (endpos - startpos - 1);
+ break;
+
+ case _Py_ERROR_SURROGATEESCAPE:
+ for (k=startpos; k<endpos; k++) {
+ ch = data[k];
+ if (!(0xDC80 <= ch && ch <= 0xDCFF))
+ break;
+ *p++ = (char)(ch & 0xff);
}
- nallocated += repsize - max_char_size;
- if (result != NULL) {
- if (_PyBytes_Resize(&result, nallocated) < 0)
- goto error;
- } else {
- result = PyBytes_FromStringAndSize(NULL, nallocated);
- if (result == NULL)
- goto error;
- Py_MEMCPY(PyBytes_AS_STRING(result), stackbuf, offset);
+ if (k >= endpos) {
+ i += (endpos - startpos - 1);
+ break;
}
- p = PyBytes_AS_STRING(result) + offset;
- }
+ startpos = k;
+ assert(startpos < endpos);
+ /* fall through the default handler */
+ default:
+ rep = unicode_encode_call_errorhandler(
+ errors, &error_handler_obj, "utf-8", "surrogates not allowed",
+ unicode, &exc, startpos, endpos, &newpos);
+ if (!rep)
+ goto error;
- if (PyBytes_Check(rep)) {
- char *prep = PyBytes_AS_STRING(rep);
- for(k = repsize; k > 0; k--)
- *p++ = *prep++;
- } else /* rep is unicode */ {
- enum PyUnicode_Kind repkind;
- void *repdata;
+ /* substract preallocated bytes */
+ writer.min_size -= max_char_size;
- if (PyUnicode_READY(rep) < 0)
- goto error;
- repkind = PyUnicode_KIND(rep);
- repdata = PyUnicode_DATA(rep);
+ if (PyBytes_Check(rep)) {
+ p = _PyBytesWriter_WriteBytes(&writer, p,
+ PyBytes_AS_STRING(rep),
+ PyBytes_GET_SIZE(rep));
+ }
+ else {
+ /* rep is unicode */
+ if (PyUnicode_READY(rep) < 0)
+ goto error;
- for(k=0; k<repsize; k++) {
- Py_UCS4 c = PyUnicode_READ(repkind, repdata, k);
- if (0x80 <= c) {
+ if (!PyUnicode_IS_ASCII(rep)) {
raise_encode_exception(&exc, "utf-8",
unicode,
i-1, i,
"surrogates not allowed");
goto error;
}
- *p++ = (char)c;
+
+ assert(PyUnicode_KIND(rep) == PyUnicode_1BYTE_KIND);
+ p = _PyBytesWriter_WriteBytes(&writer, p,
+ PyUnicode_DATA(rep),
+ PyUnicode_GET_LENGTH(rep));
}
+
+ if (p == NULL)
+ goto error;
+ Py_CLEAR(rep);
+
+ i = newpos;
}
- Py_CLEAR(rep);
+
+ /* If overallocation was disabled, ensure that it was the last
+ write. Otherwise, we missed an optimization */
+ assert(writer.overallocate || i == size);
}
else
#if STRINGLIB_SIZEOF_CHAR > 2
@@ -416,31 +446,18 @@ STRINGLIB(utf8_encoder)(PyObject *unicode,
#endif /* STRINGLIB_SIZEOF_CHAR > 1 */
}
- if (result == NULL) {
- /* This was stack allocated. */
- nneeded = p - stackbuf;
- assert(nneeded <= nallocated);
- result = PyBytes_FromStringAndSize(stackbuf, nneeded);
- }
- else {
- /* Cut back to size actually needed. */
- nneeded = p - PyBytes_AS_STRING(result);
- assert(nneeded <= nallocated);
- _PyBytes_Resize(&result, nneeded);
- }
-
#if STRINGLIB_SIZEOF_CHAR > 1
- Py_XDECREF(errorHandler);
+ Py_XDECREF(error_handler_obj);
Py_XDECREF(exc);
#endif
- return result;
+ return _PyBytesWriter_Finish(&writer, p);
#if STRINGLIB_SIZEOF_CHAR > 1
error:
Py_XDECREF(rep);
- Py_XDECREF(errorHandler);
+ Py_XDECREF(error_handler_obj);
Py_XDECREF(exc);
- Py_XDECREF(result);
+ _PyBytesWriter_Dealloc(&writer);
return NULL;
#endif
diff --git a/Objects/stringlib/fastsearch.h b/Objects/stringlib/fastsearch.h
index cda68e77c8..98165ad114 100644
--- a/Objects/stringlib/fastsearch.h
+++ b/Objects/stringlib/fastsearch.h
@@ -32,52 +32,98 @@
#define STRINGLIB_BLOOM(mask, ch) \
((mask & (1UL << ((ch) & (STRINGLIB_BLOOM_WIDTH -1)))))
-
Py_LOCAL_INLINE(Py_ssize_t)
-STRINGLIB(fastsearch_memchr_1char)(const STRINGLIB_CHAR* s, Py_ssize_t n,
- STRINGLIB_CHAR ch, unsigned char needle,
- int mode)
+STRINGLIB(find_char)(const STRINGLIB_CHAR* s, Py_ssize_t n, STRINGLIB_CHAR ch)
{
- if (mode == FAST_SEARCH) {
- const STRINGLIB_CHAR *ptr = s;
- const STRINGLIB_CHAR *e = s + n;
- while (ptr < e) {
- void *candidate = memchr((const void *) ptr, needle, (e - ptr) * sizeof(STRINGLIB_CHAR));
- if (candidate == NULL)
- return -1;
- ptr = (const STRINGLIB_CHAR *) _Py_ALIGN_DOWN(candidate, sizeof(STRINGLIB_CHAR));
- if (sizeof(STRINGLIB_CHAR) == 1 || *ptr == ch)
- return (ptr - s);
- /* False positive */
- ptr++;
- }
+ const STRINGLIB_CHAR *p, *e;
+
+ p = s;
+ e = s + n;
+ if (n > 10) {
+#if STRINGLIB_SIZEOF_CHAR == 1
+ p = memchr(s, ch, n);
+ if (p != NULL)
+ return (p - s);
return -1;
+#else
+ /* use memchr if we can choose a needle without two many likely
+ false positives */
+ unsigned char needle = ch & 0xff;
+ /* If looking for a multiple of 256, we'd have too
+ many false positives looking for the '\0' byte in UCS2
+ and UCS4 representations. */
+ if (needle != 0) {
+ while (p < e) {
+ void *candidate = memchr(p, needle,
+ (e - p) * sizeof(STRINGLIB_CHAR));
+ if (candidate == NULL)
+ return -1;
+ p = (const STRINGLIB_CHAR *)
+ _Py_ALIGN_DOWN(candidate, sizeof(STRINGLIB_CHAR));
+ if (*p == ch)
+ return (p - s);
+ /* False positive */
+ p++;
+ }
+ return -1;
+ }
+#endif
}
+ while (p < e) {
+ if (*p == ch)
+ return (p - s);
+ p++;
+ }
+ return -1;
+}
+
+Py_LOCAL_INLINE(Py_ssize_t)
+STRINGLIB(rfind_char)(const STRINGLIB_CHAR* s, Py_ssize_t n, STRINGLIB_CHAR ch)
+{
+ const STRINGLIB_CHAR *p;
#ifdef HAVE_MEMRCHR
/* memrchr() is a GNU extension, available since glibc 2.1.91.
it doesn't seem as optimized as memchr(), but is still quite
- faster than our hand-written loop in FASTSEARCH below */
- else if (mode == FAST_RSEARCH) {
- while (n > 0) {
- const STRINGLIB_CHAR *found;
- void *candidate = memrchr((const void *) s, needle, n * sizeof(STRINGLIB_CHAR));
- if (candidate == NULL)
- return -1;
- found = (const STRINGLIB_CHAR *) _Py_ALIGN_DOWN(candidate, sizeof(STRINGLIB_CHAR));
- n = found - s;
- if (sizeof(STRINGLIB_CHAR) == 1 || *found == ch)
- return n;
- /* False positive */
- }
+ faster than our hand-written loop below */
+
+ if (n > 10) {
+#if STRINGLIB_SIZEOF_CHAR == 1
+ p = memrchr(s, ch, n);
+ if (p != NULL)
+ return (p - s);
return -1;
- }
+#else
+ /* use memrchr if we can choose a needle without two many likely
+ false positives */
+ unsigned char needle = ch & 0xff;
+ /* If looking for a multiple of 256, we'd have too
+ many false positives looking for the '\0' byte in UCS2
+ and UCS4 representations. */
+ if (needle != 0) {
+ while (n > 0) {
+ void *candidate = memrchr(s, needle,
+ n * sizeof(STRINGLIB_CHAR));
+ if (candidate == NULL)
+ return -1;
+ p = (const STRINGLIB_CHAR *)
+ _Py_ALIGN_DOWN(candidate, sizeof(STRINGLIB_CHAR));
+ n = p - s;
+ if (*p == ch)
+ return n;
+ /* False positive */
+ }
+ return -1;
+ }
#endif
- else {
- assert(0); /* Should never get here */
- return 0;
}
-
-#undef DO_MEMCHR
+#endif /* HAVE_MEMRCHR */
+ p = s + n;
+ while (p > s) {
+ p--;
+ if (*p == ch)
+ return (p - s);
+ }
+ return -1;
}
Py_LOCAL_INLINE(Py_ssize_t)
@@ -99,25 +145,11 @@ FASTSEARCH(const STRINGLIB_CHAR* s, Py_ssize_t n,
if (m <= 0)
return -1;
/* use special case for 1-character strings */
- if (n > 10 && (mode == FAST_SEARCH
-#ifdef HAVE_MEMRCHR
- || mode == FAST_RSEARCH
-#endif
- )) {
- /* use memchr if we can choose a needle without two many likely
- false positives */
- unsigned char needle;
- needle = p[0] & 0xff;
-#if STRINGLIB_SIZEOF_CHAR > 1
- /* If looking for a multiple of 256, we'd have too
- many false positives looking for the '\0' byte in UCS2
- and UCS4 representations. */
- if (needle != 0)
-#endif
- return STRINGLIB(fastsearch_memchr_1char)
- (s, n, p[0], needle, mode);
- }
- if (mode == FAST_COUNT) {
+ if (mode == FAST_SEARCH)
+ return STRINGLIB(find_char)(s, n, p[0]);
+ else if (mode == FAST_RSEARCH)
+ return STRINGLIB(rfind_char)(s, n, p[0]);
+ else { /* FAST_COUNT */
for (i = 0; i < n; i++)
if (s[i] == p[0]) {
count++;
@@ -125,14 +157,6 @@ FASTSEARCH(const STRINGLIB_CHAR* s, Py_ssize_t n,
return maxcount;
}
return count;
- } else if (mode == FAST_SEARCH) {
- for (i = 0; i < n; i++)
- if (s[i] == p[0])
- return i;
- } else { /* FAST_RSEARCH */
- for (i = n - 1; i > -1; i--)
- if (s[i] == p[0])
- return i;
}
return -1;
}
diff --git a/Objects/stringlib/unicode_format.h b/Objects/stringlib/unicode_format.h
index aec221acff..d72e47d348 100644
--- a/Objects/stringlib/unicode_format.h
+++ b/Objects/stringlib/unicode_format.h
@@ -67,7 +67,7 @@ SubString_new_object(SubString *str)
return PyUnicode_Substring(str->str, str->start, str->end);
}
-/* return a new string. if str->str is NULL, return None */
+/* return a new string. if str->str is NULL, return a new empty string */
Py_LOCAL_INLINE(PyObject *)
SubString_new_object_or_empty(SubString *str)
{
diff --git a/Objects/structseq.c b/Objects/structseq.c
index 664344be6c..720973816e 100644
--- a/Objects/structseq.c
+++ b/Objects/structseq.c
@@ -16,14 +16,14 @@ _Py_IDENTIFIER(n_fields);
_Py_IDENTIFIER(n_unnamed_fields);
#define VISIBLE_SIZE(op) Py_SIZE(op)
-#define VISIBLE_SIZE_TP(tp) PyLong_AsLong( \
+#define VISIBLE_SIZE_TP(tp) PyLong_AsSsize_t( \
_PyDict_GetItemId((tp)->tp_dict, &PyId_n_sequence_fields))
-#define REAL_SIZE_TP(tp) PyLong_AsLong( \
+#define REAL_SIZE_TP(tp) PyLong_AsSsize_t( \
_PyDict_GetItemId((tp)->tp_dict, &PyId_n_fields))
#define REAL_SIZE(op) REAL_SIZE_TP(Py_TYPE(op))
-#define UNNAMED_FIELDS_TP(tp) PyLong_AsLong( \
+#define UNNAMED_FIELDS_TP(tp) PyLong_AsSsize_t( \
_PyDict_GetItemId((tp)->tp_dict, &PyId_n_unnamed_fields))
#define UNNAMED_FIELDS(op) UNNAMED_FIELDS_TP(Py_TYPE(op))
@@ -164,7 +164,8 @@ structseq_repr(PyStructSequence *obj)
#define TYPE_MAXSIZE 100
PyTypeObject *typ = Py_TYPE(obj);
- int i, removelast = 0;
+ Py_ssize_t i;
+ int removelast = 0;
Py_ssize_t len;
char buf[REPR_BUFFER_SIZE];
char *endofbuf, *pbuf = buf;
@@ -236,8 +237,7 @@ structseq_reduce(PyStructSequence* self)
PyObject* tup = NULL;
PyObject* dict = NULL;
PyObject* result;
- Py_ssize_t n_fields, n_visible_fields, n_unnamed_fields;
- int i;
+ Py_ssize_t n_fields, n_visible_fields, n_unnamed_fields, i;
n_fields = REAL_SIZE(self);
n_visible_fields = VISIBLE_SIZE(self);
@@ -325,7 +325,7 @@ PyStructSequence_InitType2(PyTypeObject *type, PyStructSequence_Desc *desc)
{
PyObject *dict;
PyMemberDef* members;
- int n_members, n_unnamed_members, i, k;
+ Py_ssize_t n_members, n_unnamed_members, i, k;
PyObject *v;
#ifdef Py_TRACE_REFS
@@ -373,9 +373,9 @@ PyStructSequence_InitType2(PyTypeObject *type, PyStructSequence_Desc *desc)
Py_INCREF(type);
dict = type->tp_dict;
-#define SET_DICT_FROM_INT(key, value) \
+#define SET_DICT_FROM_SIZE(key, value) \
do { \
- v = PyLong_FromLong((long) value); \
+ v = PyLong_FromSsize_t(value); \
if (v == NULL) \
return -1; \
if (PyDict_SetItemString(dict, key, v) < 0) { \
@@ -385,9 +385,9 @@ PyStructSequence_InitType2(PyTypeObject *type, PyStructSequence_Desc *desc)
Py_DECREF(v); \
} while (0)
- SET_DICT_FROM_INT(visible_length_key, desc->n_in_sequence);
- SET_DICT_FROM_INT(real_length_key, n_members);
- SET_DICT_FROM_INT(unnamed_fields_key, n_unnamed_members);
+ SET_DICT_FROM_SIZE(visible_length_key, desc->n_in_sequence);
+ SET_DICT_FROM_SIZE(real_length_key, n_members);
+ SET_DICT_FROM_SIZE(unnamed_fields_key, n_unnamed_members);
return 0;
}
diff --git a/Objects/typeobject.c b/Objects/typeobject.c
index 5b858bde03..341e18c455 100644
--- a/Objects/typeobject.c
+++ b/Objects/typeobject.c
@@ -904,25 +904,33 @@ type_call(PyTypeObject *type, PyObject *args, PyObject *kwds)
#endif
obj = type->tp_new(type, args, kwds);
- if (obj != NULL) {
- /* Ugly exception: when the call was type(something),
- don't call tp_init on the result. */
- if (type == &PyType_Type &&
- PyTuple_Check(args) && PyTuple_GET_SIZE(args) == 1 &&
- (kwds == NULL ||
- (PyDict_Check(kwds) && PyDict_Size(kwds) == 0)))
- return obj;
- /* If the returned object is not an instance of type,
- it won't be initialized. */
- if (!PyType_IsSubtype(Py_TYPE(obj), type))
- return obj;
- type = Py_TYPE(obj);
- if (type->tp_init != NULL) {
- int res = type->tp_init(obj, args, kwds);
- if (res < 0) {
- Py_DECREF(obj);
- obj = NULL;
- }
+ obj = _Py_CheckFunctionResult((PyObject*)type, obj, NULL);
+ if (obj == NULL)
+ return NULL;
+
+ /* Ugly exception: when the call was type(something),
+ don't call tp_init on the result. */
+ if (type == &PyType_Type &&
+ PyTuple_Check(args) && PyTuple_GET_SIZE(args) == 1 &&
+ (kwds == NULL ||
+ (PyDict_Check(kwds) && PyDict_Size(kwds) == 0)))
+ return obj;
+
+ /* If the returned object is not an instance of type,
+ it won't be initialized. */
+ if (!PyType_IsSubtype(Py_TYPE(obj), type))
+ return obj;
+
+ type = Py_TYPE(obj);
+ if (type->tp_init != NULL) {
+ int res = type->tp_init(obj, args, kwds);
+ if (res < 0) {
+ assert(PyErr_Occurred());
+ Py_DECREF(obj);
+ obj = NULL;
+ }
+ else {
+ assert(!PyErr_Occurred());
}
}
return obj;
@@ -4093,7 +4101,7 @@ _PyObject_GetItemsIter(PyObject *obj, PyObject **listitems,
}
static PyObject *
-reduce_newobj(PyObject *obj, int proto)
+reduce_newobj(PyObject *obj)
{
PyObject *args = NULL, *kwargs = NULL;
PyObject *copyreg;
@@ -4151,7 +4159,7 @@ reduce_newobj(PyObject *obj, int proto)
}
Py_DECREF(args);
}
- else if (proto >= 4) {
+ else {
_Py_IDENTIFIER(__newobj_ex__);
newobj = _PyObject_GetAttrId(copyreg, &PyId___newobj_ex__);
@@ -4169,16 +4177,6 @@ reduce_newobj(PyObject *obj, int proto)
return NULL;
}
}
- else {
- PyErr_SetString(PyExc_ValueError,
- "must use protocol 4 or greater to copy this "
- "object; since __getnewargs_ex__ returned "
- "keyword arguments.");
- Py_DECREF(args);
- Py_DECREF(kwargs);
- Py_DECREF(copyreg);
- return NULL;
- }
state = _PyObject_GetState(obj);
if (state == NULL) {
@@ -4223,7 +4221,7 @@ _common_reduce(PyObject *self, int proto)
PyObject *copyreg, *res;
if (proto >= 2)
- return reduce_newobj(self, proto);
+ return reduce_newobj(self);
copyreg = import_copyreg();
if (!copyreg)
diff --git a/Objects/unicodeobject.c b/Objects/unicodeobject.c
index c5b35e1194..a985d6fb42 100644
--- a/Objects/unicodeobject.c
+++ b/Objects/unicodeobject.c
@@ -42,6 +42,7 @@ OF OR IN CONNECTION WITH THE USE OR PERFORMANCE OF THIS SOFTWARE.
#include "Python.h"
#include "ucnhash.h"
#include "bytes_methods.h"
+#include "stringlib/eq.h"
#ifdef MS_WINDOWS
#include <windows.h>
@@ -162,6 +163,14 @@ extern "C" {
*_to++ = (to_type) *_iter++; \
} while (0)
+#ifdef MS_WINDOWS
+ /* On Windows, overallocate by 50% is the best factor */
+# define OVERALLOCATE_FACTOR 2
+#else
+ /* On Linux, overallocate by 25% is the best factor */
+# define OVERALLOCATE_FACTOR 4
+#endif
+
/* This dictionary holds all interned unicode strings. Note that references
to strings in this dictionary are *not* counted in the string's ob_refcnt.
When the interned string reaches a refcnt of 0 the string deallocation
@@ -292,6 +301,38 @@ static unsigned char ascii_linebreak[] = {
#include "clinic/unicodeobject.c.h"
+typedef enum {
+ _Py_ERROR_UNKNOWN=0,
+ _Py_ERROR_STRICT,
+ _Py_ERROR_SURROGATEESCAPE,
+ _Py_ERROR_REPLACE,
+ _Py_ERROR_IGNORE,
+ _Py_ERROR_BACKSLASHREPLACE,
+ _Py_ERROR_SURROGATEPASS,
+ _Py_ERROR_XMLCHARREFREPLACE,
+ _Py_ERROR_OTHER
+} _Py_error_handler;
+
+static _Py_error_handler
+get_error_handler(const char *errors)
+{
+ if (errors == NULL || strcmp(errors, "strict") == 0)
+ return _Py_ERROR_STRICT;
+ if (strcmp(errors, "surrogateescape") == 0)
+ return _Py_ERROR_SURROGATEESCAPE;
+ if (strcmp(errors, "replace") == 0)
+ return _Py_ERROR_REPLACE;
+ if (strcmp(errors, "ignore") == 0)
+ return _Py_ERROR_IGNORE;
+ if (strcmp(errors, "backslashreplace") == 0)
+ return _Py_ERROR_BACKSLASHREPLACE;
+ if (strcmp(errors, "surrogatepass") == 0)
+ return _Py_ERROR_SURROGATEPASS;
+ if (strcmp(errors, "xmlcharrefreplace") == 0)
+ return _Py_ERROR_XMLCHARREFREPLACE;
+ return _Py_ERROR_OTHER;
+}
+
/* The max unicode value is always 0x10FFFF while using the PEP-393 API.
This function is kept for backward compatibility with the old API. */
Py_UNICODE
@@ -521,6 +562,129 @@ unicode_result_unchanged(PyObject *unicode)
return _PyUnicode_Copy(unicode);
}
+/* Implementation of the "backslashreplace" error handler for 8-bit encodings:
+ ASCII, Latin1, UTF-8, etc. */
+static char*
+backslashreplace(_PyBytesWriter *writer, char *str,
+ PyObject *unicode, Py_ssize_t collstart, Py_ssize_t collend)
+{
+ Py_ssize_t size, i;
+ Py_UCS4 ch;
+ enum PyUnicode_Kind kind;
+ void *data;
+
+ assert(PyUnicode_IS_READY(unicode));
+ kind = PyUnicode_KIND(unicode);
+ data = PyUnicode_DATA(unicode);
+
+ size = 0;
+ /* determine replacement size */
+ for (i = collstart; i < collend; ++i) {
+ Py_ssize_t incr;
+
+ ch = PyUnicode_READ(kind, data, i);
+ if (ch < 0x100)
+ incr = 2+2;
+ else if (ch < 0x10000)
+ incr = 2+4;
+ else {
+ assert(ch <= MAX_UNICODE);
+ incr = 2+8;
+ }
+ if (size > PY_SSIZE_T_MAX - incr) {
+ PyErr_SetString(PyExc_OverflowError,
+ "encoded result is too long for a Python string");
+ return NULL;
+ }
+ size += incr;
+ }
+
+ str = _PyBytesWriter_Prepare(writer, str, size);
+ if (str == NULL)
+ return NULL;
+
+ /* generate replacement */
+ for (i = collstart; i < collend; ++i) {
+ ch = PyUnicode_READ(kind, data, i);
+ *str++ = '\\';
+ if (ch >= 0x00010000) {
+ *str++ = 'U';
+ *str++ = Py_hexdigits[(ch>>28)&0xf];
+ *str++ = Py_hexdigits[(ch>>24)&0xf];
+ *str++ = Py_hexdigits[(ch>>20)&0xf];
+ *str++ = Py_hexdigits[(ch>>16)&0xf];
+ *str++ = Py_hexdigits[(ch>>12)&0xf];
+ *str++ = Py_hexdigits[(ch>>8)&0xf];
+ }
+ else if (ch >= 0x100) {
+ *str++ = 'u';
+ *str++ = Py_hexdigits[(ch>>12)&0xf];
+ *str++ = Py_hexdigits[(ch>>8)&0xf];
+ }
+ else
+ *str++ = 'x';
+ *str++ = Py_hexdigits[(ch>>4)&0xf];
+ *str++ = Py_hexdigits[ch&0xf];
+ }
+ return str;
+}
+
+/* Implementation of the "xmlcharrefreplace" error handler for 8-bit encodings:
+ ASCII, Latin1, UTF-8, etc. */
+static char*
+xmlcharrefreplace(_PyBytesWriter *writer, char *str,
+ PyObject *unicode, Py_ssize_t collstart, Py_ssize_t collend)
+{
+ Py_ssize_t size, i;
+ Py_UCS4 ch;
+ enum PyUnicode_Kind kind;
+ void *data;
+
+ assert(PyUnicode_IS_READY(unicode));
+ kind = PyUnicode_KIND(unicode);
+ data = PyUnicode_DATA(unicode);
+
+ size = 0;
+ /* determine replacement size */
+ for (i = collstart; i < collend; ++i) {
+ Py_ssize_t incr;
+
+ ch = PyUnicode_READ(kind, data, i);
+ if (ch < 10)
+ incr = 2+1+1;
+ else if (ch < 100)
+ incr = 2+2+1;
+ else if (ch < 1000)
+ incr = 2+3+1;
+ else if (ch < 10000)
+ incr = 2+4+1;
+ else if (ch < 100000)
+ incr = 2+5+1;
+ else if (ch < 1000000)
+ incr = 2+6+1;
+ else {
+ assert(ch <= MAX_UNICODE);
+ incr = 2+7+1;
+ }
+ if (size > PY_SSIZE_T_MAX - incr) {
+ PyErr_SetString(PyExc_OverflowError,
+ "encoded result is too long for a Python string");
+ return NULL;
+ }
+ size += incr;
+ }
+
+ str = _PyBytesWriter_Prepare(writer, str, size);
+ if (str == NULL)
+ return NULL;
+
+ /* generate replacement */
+ for (i = collstart; i < collend; ++i) {
+ str += sprintf(str, "&#%d;", PyUnicode_READ(kind, data, i));
+ }
+ return str;
+}
+
/* --- Bloom Filters ----------------------------------------------------- */
/* stuff to implement simple "bloom filters" for Unicode characters.
@@ -647,27 +811,26 @@ Py_LOCAL_INLINE(Py_ssize_t) findchar(const void *s, int kind,
Py_ssize_t size, Py_UCS4 ch,
int direction)
{
- int mode = (direction == 1) ? FAST_SEARCH : FAST_RSEARCH;
-
switch (kind) {
case PyUnicode_1BYTE_KIND:
- {
- Py_UCS1 ch1 = (Py_UCS1) ch;
- if (ch1 == ch)
- return ucs1lib_fastsearch((Py_UCS1 *) s, size, &ch1, 1, 0, mode);
- else
- return -1;
- }
+ if ((Py_UCS1) ch != ch)
+ return -1;
+ if (direction > 0)
+ return ucs1lib_find_char((Py_UCS1 *) s, size, (Py_UCS1) ch);
+ else
+ return ucs1lib_rfind_char((Py_UCS1 *) s, size, (Py_UCS1) ch);
case PyUnicode_2BYTE_KIND:
- {
- Py_UCS2 ch2 = (Py_UCS2) ch;
- if (ch2 == ch)
- return ucs2lib_fastsearch((Py_UCS2 *) s, size, &ch2, 1, 0, mode);
- else
- return -1;
- }
+ if ((Py_UCS2) ch != ch)
+ return -1;
+ if (direction > 0)
+ return ucs2lib_find_char((Py_UCS2 *) s, size, (Py_UCS2) ch);
+ else
+ return ucs2lib_rfind_char((Py_UCS2 *) s, size, (Py_UCS2) ch);
case PyUnicode_4BYTE_KIND:
- return ucs4lib_fastsearch((Py_UCS4 *) s, size, &ch, 1, 0, mode);
+ if (direction > 0)
+ return ucs4lib_find_char((Py_UCS4 *) s, size, ch);
+ else
+ return ucs4lib_rfind_char((Py_UCS4 *) s, size, ch);
default:
assert(0);
return -1;
@@ -3165,24 +3328,22 @@ wcstombs_errorpos(const wchar_t *wstr)
static int
locale_error_handler(const char *errors, int *surrogateescape)
{
- if (errors == NULL) {
- *surrogateescape = 0;
- return 0;
- }
-
- if (strcmp(errors, "strict") == 0) {
+ _Py_error_handler error_handler = get_error_handler(errors);
+ switch (error_handler)
+ {
+ case _Py_ERROR_STRICT:
*surrogateescape = 0;
return 0;
- }
- if (strcmp(errors, "surrogateescape") == 0) {
+ case _Py_ERROR_SURROGATEESCAPE:
*surrogateescape = 1;
return 0;
+ default:
+ PyErr_Format(PyExc_ValueError,
+ "only 'strict' and 'surrogateescape' error handlers "
+ "are supported, not '%s'",
+ errors);
+ return -1;
}
- PyErr_Format(PyExc_ValueError,
- "only 'strict' and 'surrogateescape' error handlers "
- "are supported, not '%s'",
- errors);
- return -1;
}
PyObject *
@@ -4688,8 +4849,9 @@ PyUnicode_DecodeUTF8Stateful(const char *s,
Py_ssize_t startinpos;
Py_ssize_t endinpos;
const char *errmsg = "";
- PyObject *errorHandler = NULL;
+ PyObject *error_handler_obj = NULL;
PyObject *exc = NULL;
+ _Py_error_handler error_handler = _Py_ERROR_UNKNOWN;
if (size == 0) {
if (consumed)
@@ -4714,6 +4876,7 @@ PyUnicode_DecodeUTF8Stateful(const char *s,
while (s < end) {
Py_UCS4 ch;
int kind = writer.kind;
+
if (kind == PyUnicode_1BYTE_KIND) {
if (PyUnicode_IS_ASCII(writer.buffer))
ch = asciilib_utf8_decode(&s, end, writer.data, &writer.pos);
@@ -4752,24 +4915,56 @@ PyUnicode_DecodeUTF8Stateful(const char *s,
continue;
}
- if (unicode_decode_call_errorhandler_writer(
- errors, &errorHandler,
- "utf-8", errmsg,
- &starts, &end, &startinpos, &endinpos, &exc, &s,
- &writer))
- goto onError;
+ if (error_handler == _Py_ERROR_UNKNOWN)
+ error_handler = get_error_handler(errors);
+
+ switch (error_handler) {
+ case _Py_ERROR_IGNORE:
+ s += (endinpos - startinpos);
+ break;
+
+ case _Py_ERROR_REPLACE:
+ if (_PyUnicodeWriter_WriteCharInline(&writer, 0xfffd) < 0)
+ goto onError;
+ s += (endinpos - startinpos);
+ break;
+
+ case _Py_ERROR_SURROGATEESCAPE:
+ {
+ Py_ssize_t i;
+
+ if (_PyUnicodeWriter_PrepareKind(&writer, PyUnicode_2BYTE_KIND) < 0)
+ goto onError;
+ for (i=startinpos; i<endinpos; i++) {
+ ch = (Py_UCS4)(unsigned char)(starts[i]);
+ PyUnicode_WRITE(writer.kind, writer.data, writer.pos,
+ ch + 0xdc00);
+ writer.pos++;
+ }
+ s += (endinpos - startinpos);
+ break;
+ }
+
+ default:
+ if (unicode_decode_call_errorhandler_writer(
+ errors, &error_handler_obj,
+ "utf-8", errmsg,
+ &starts, &end, &startinpos, &endinpos, &exc, &s,
+ &writer))
+ goto onError;
+ }
}
End:
if (consumed)
*consumed = s - starts;
- Py_XDECREF(errorHandler);
+ Py_XDECREF(error_handler_obj);
Py_XDECREF(exc);
return _PyUnicodeWriter_Finish(&writer);
onError:
- Py_XDECREF(errorHandler);
+ Py_XDECREF(error_handler_obj);
Py_XDECREF(exc);
_PyUnicodeWriter_Dealloc(&writer);
return NULL;
@@ -5860,11 +6055,10 @@ PyObject *
PyUnicode_AsUnicodeEscapeString(PyObject *unicode)
{
Py_ssize_t i, len;
- PyObject *repr;
char *p;
int kind;
void *data;
- Py_ssize_t expandsize = 0;
+ _PyBytesWriter writer;
/* Initial allocation is based on the longest-possible character
escape.
@@ -5880,35 +6074,28 @@ PyUnicode_AsUnicodeEscapeString(PyObject *unicode)
}
if (PyUnicode_READY(unicode) == -1)
return NULL;
+
+ _PyBytesWriter_Init(&writer);
+
len = PyUnicode_GET_LENGTH(unicode);
kind = PyUnicode_KIND(unicode);
data = PyUnicode_DATA(unicode);
- switch (kind) {
- case PyUnicode_1BYTE_KIND: expandsize = 4; break;
- case PyUnicode_2BYTE_KIND: expandsize = 6; break;
- case PyUnicode_4BYTE_KIND: expandsize = 10; break;
- }
- if (len == 0)
- return PyBytes_FromStringAndSize(NULL, 0);
-
- if (len > (PY_SSIZE_T_MAX - 2 - 1) / expandsize)
- return PyErr_NoMemory();
-
- repr = PyBytes_FromStringAndSize(NULL,
- 2
- + expandsize*len
- + 1);
- if (repr == NULL)
- return NULL;
-
- p = PyBytes_AS_STRING(repr);
+ p = _PyBytesWriter_Alloc(&writer, len);
+ if (p == NULL)
+ goto error;
+ writer.overallocate = 1;
for (i = 0; i < len; i++) {
Py_UCS4 ch = PyUnicode_READ(kind, data, i);
/* Escape backslashes */
if (ch == '\\') {
+ /* -1: substract 1 preallocated byte */
+ p = _PyBytesWriter_Prepare(&writer, p, 2-1);
+ if (p == NULL)
+ goto error;
+
*p++ = '\\';
*p++ = (char) ch;
continue;
@@ -5917,6 +6104,11 @@ PyUnicode_AsUnicodeEscapeString(PyObject *unicode)
/* Map 21-bit characters to '\U00xxxxxx' */
else if (ch >= 0x10000) {
assert(ch <= MAX_UNICODE);
+
+ p = _PyBytesWriter_Prepare(&writer, p, 10-1);
+ if (p == NULL)
+ goto error;
+
*p++ = '\\';
*p++ = 'U';
*p++ = Py_hexdigits[(ch >> 28) & 0x0000000F];
@@ -5932,6 +6124,10 @@ PyUnicode_AsUnicodeEscapeString(PyObject *unicode)
/* Map 16-bit characters to '\uxxxx' */
if (ch >= 256) {
+ p = _PyBytesWriter_Prepare(&writer, p, 6-1);
+ if (p == NULL)
+ goto error;
+
*p++ = '\\';
*p++ = 'u';
*p++ = Py_hexdigits[(ch >> 12) & 0x000F];
@@ -5942,20 +6138,37 @@ PyUnicode_AsUnicodeEscapeString(PyObject *unicode)
/* Map special whitespace to '\t', \n', '\r' */
else if (ch == '\t') {
+ p = _PyBytesWriter_Prepare(&writer, p, 2-1);
+ if (p == NULL)
+ goto error;
+
*p++ = '\\';
*p++ = 't';
}
else if (ch == '\n') {
+ p = _PyBytesWriter_Prepare(&writer, p, 2-1);
+ if (p == NULL)
+ goto error;
+
*p++ = '\\';
*p++ = 'n';
}
else if (ch == '\r') {
+ p = _PyBytesWriter_Prepare(&writer, p, 2-1);
+ if (p == NULL)
+ goto error;
+
*p++ = '\\';
*p++ = 'r';
}
/* Map non-printable US ASCII to '\xhh' */
else if (ch < ' ' || ch >= 0x7F) {
+ /* -1: substract 1 preallocated byte */
+ p = _PyBytesWriter_Prepare(&writer, p, 4-1);
+ if (p == NULL)
+ goto error;
+
*p++ = '\\';
*p++ = 'x';
*p++ = Py_hexdigits[(ch >> 4) & 0x000F];
@@ -5967,10 +6180,11 @@ PyUnicode_AsUnicodeEscapeString(PyObject *unicode)
*p++ = (char) ch;
}
- assert(p - PyBytes_AS_STRING(repr) > 0);
- if (_PyBytes_Resize(&repr, p - PyBytes_AS_STRING(repr)) < 0)
- return NULL;
- return repr;
+ return _PyBytesWriter_Finish(&writer, p);
+
+error:
+ _PyBytesWriter_Dealloc(&writer);
+ return NULL;
}
PyObject *
@@ -6099,13 +6313,12 @@ PyUnicode_DecodeRawUnicodeEscape(const char *s,
PyObject *
PyUnicode_AsRawUnicodeEscapeString(PyObject *unicode)
{
- PyObject *repr;
char *p;
- char *q;
- Py_ssize_t expandsize, pos;
+ Py_ssize_t pos;
int kind;
void *data;
Py_ssize_t len;
+ _PyBytesWriter writer;
if (!PyUnicode_Check(unicode)) {
PyErr_BadArgument();
@@ -6113,28 +6326,29 @@ PyUnicode_AsRawUnicodeEscapeString(PyObject *unicode)
}
if (PyUnicode_READY(unicode) == -1)
return NULL;
+
+ _PyBytesWriter_Init(&writer);
+
kind = PyUnicode_KIND(unicode);
data = PyUnicode_DATA(unicode);
len = PyUnicode_GET_LENGTH(unicode);
- /* 4 byte characters can take up 10 bytes, 2 byte characters can take up 6
- bytes, and 1 byte characters 4. */
- expandsize = kind * 2 + 2;
- if (len > PY_SSIZE_T_MAX / expandsize)
- return PyErr_NoMemory();
-
- repr = PyBytes_FromStringAndSize(NULL, expandsize * len);
- if (repr == NULL)
- return NULL;
- if (len == 0)
- return repr;
+ p = _PyBytesWriter_Alloc(&writer, len);
+ if (p == NULL)
+ goto error;
+ writer.overallocate = 1;
- p = q = PyBytes_AS_STRING(repr);
for (pos = 0; pos < len; pos++) {
Py_UCS4 ch = PyUnicode_READ(kind, data, pos);
/* Map 32-bit characters to '\Uxxxxxxxx' */
if (ch >= 0x10000) {
assert(ch <= MAX_UNICODE);
+
+ /* -1: substract 1 preallocated byte */
+ p = _PyBytesWriter_Prepare(&writer, p, 10-1);
+ if (p == NULL)
+ goto error;
+
*p++ = '\\';
*p++ = 'U';
*p++ = Py_hexdigits[(ch >> 28) & 0xf];
@@ -6148,6 +6362,11 @@ PyUnicode_AsRawUnicodeEscapeString(PyObject *unicode)
}
/* Map 16-bit characters to '\uxxxx' */
else if (ch >= 256) {
+ /* -1: substract 1 preallocated byte */
+ p = _PyBytesWriter_Prepare(&writer, p, 6-1);
+ if (p == NULL)
+ goto error;
+
*p++ = '\\';
*p++ = 'u';
*p++ = Py_hexdigits[(ch >> 12) & 0xf];
@@ -6160,10 +6379,11 @@ PyUnicode_AsRawUnicodeEscapeString(PyObject *unicode)
*p++ = (char) ch;
}
- assert(p > q);
- if (_PyBytes_Resize(&repr, p - q) < 0)
- return NULL;
- return repr;
+ return _PyBytesWriter_Finish(&writer, p);
+
+error:
+ _PyBytesWriter_Dealloc(&writer);
+ return NULL;
}
PyObject *
@@ -6394,25 +6614,22 @@ unicode_encode_call_errorhandler(const char *errors,
static PyObject *
unicode_encode_ucs1(PyObject *unicode,
const char *errors,
- unsigned int limit)
+ const Py_UCS4 limit)
{
/* input state */
Py_ssize_t pos=0, size;
int kind;
void *data;
- /* output object */
- PyObject *res;
/* pointer into the output */
char *str;
- /* current output position */
- Py_ssize_t ressize;
const char *encoding = (limit == 256) ? "latin-1" : "ascii";
const char *reason = (limit == 256) ? "ordinal not in range(256)" : "ordinal not in range(128)";
- PyObject *errorHandler = NULL;
+ PyObject *error_handler_obj = NULL;
PyObject *exc = NULL;
- /* the following variable is used for caching string comparisons
- * -1=not initialized, 0=unknown, 1=strict, 2=replace, 3=ignore, 4=xmlcharrefreplace */
- int known_errorHandler = -1;
+ _Py_error_handler error_handler = _Py_ERROR_UNKNOWN;
+ PyObject *rep = NULL;
+ /* output object */
+ _PyBytesWriter writer;
if (PyUnicode_READY(unicode) == -1)
return NULL;
@@ -6423,186 +6640,157 @@ unicode_encode_ucs1(PyObject *unicode,
replacements, if we need more, we'll resize */
if (size == 0)
return PyBytes_FromStringAndSize(NULL, 0);
- res = PyBytes_FromStringAndSize(NULL, size);
- if (res == NULL)
+
+ _PyBytesWriter_Init(&writer);
+ str = _PyBytesWriter_Alloc(&writer, size);
+ if (str == NULL)
return NULL;
- str = PyBytes_AS_STRING(res);
- ressize = size;
while (pos < size) {
- Py_UCS4 c = PyUnicode_READ(kind, data, pos);
+ Py_UCS4 ch = PyUnicode_READ(kind, data, pos);
/* can we encode this? */
- if (c<limit) {
+ if (ch < limit) {
/* no overflow check, because we know that the space is enough */
- *str++ = (char)c;
+ *str++ = (char)ch;
++pos;
}
else {
- Py_ssize_t requiredsize;
- PyObject *repunicode;
- Py_ssize_t repsize, newpos, respos, i;
+ Py_ssize_t newpos, i;
/* startpos for collecting unencodable chars */
Py_ssize_t collstart = pos;
- Py_ssize_t collend = pos;
+ Py_ssize_t collend = collstart + 1;
/* find all unecodable characters */
+
while ((collend < size) && (PyUnicode_READ(kind, data, collend) >= limit))
++collend;
+
+ /* Only overallocate the buffer if it's not the last write */
+ writer.overallocate = (collend < size);
+
/* cache callback name lookup (if not done yet, i.e. it's the first error) */
- if (known_errorHandler==-1) {
- if ((errors==NULL) || (!strcmp(errors, "strict")))
- known_errorHandler = 1;
- else if (!strcmp(errors, "replace"))
- known_errorHandler = 2;
- else if (!strcmp(errors, "ignore"))
- known_errorHandler = 3;
- else if (!strcmp(errors, "xmlcharrefreplace"))
- known_errorHandler = 4;
- else
- known_errorHandler = 0;
- }
- switch (known_errorHandler) {
- case 1: /* strict */
+ if (error_handler == _Py_ERROR_UNKNOWN)
+ error_handler = get_error_handler(errors);
+
+ switch (error_handler) {
+ case _Py_ERROR_STRICT:
raise_encode_exception(&exc, encoding, unicode, collstart, collend, reason);
goto onError;
- case 2: /* replace */
- while (collstart++ < collend)
- *str++ = '?'; /* fall through */
- case 3: /* ignore */
+
+ case _Py_ERROR_REPLACE:
+ memset(str, '?', collend - collstart);
+ str += (collend - collstart);
+ /* fall through ignore error handler */
+ case _Py_ERROR_IGNORE:
pos = collend;
break;
- case 4: /* xmlcharrefreplace */
- respos = str - PyBytes_AS_STRING(res);
- requiredsize = respos;
- /* determine replacement size */
+
+ case _Py_ERROR_BACKSLASHREPLACE:
+ /* substract preallocated bytes */
+ writer.min_size -= (collend - collstart);
+ str = backslashreplace(&writer, str,
+ unicode, collstart, collend);
+ if (str == NULL)
+ goto onError;
+ pos = collend;
+ break;
+
+ case _Py_ERROR_XMLCHARREFREPLACE:
+ /* substract preallocated bytes */
+ writer.min_size -= (collend - collstart);
+ str = xmlcharrefreplace(&writer, str,
+ unicode, collstart, collend);
+ if (str == NULL)
+ goto onError;
+ pos = collend;
+ break;
+
+ case _Py_ERROR_SURROGATEESCAPE:
for (i = collstart; i < collend; ++i) {
- Py_UCS4 ch = PyUnicode_READ(kind, data, i);
- Py_ssize_t incr;
- if (ch < 10)
- incr = 2+1+1;
- else if (ch < 100)
- incr = 2+2+1;
- else if (ch < 1000)
- incr = 2+3+1;
- else if (ch < 10000)
- incr = 2+4+1;
- else if (ch < 100000)
- incr = 2+5+1;
- else if (ch < 1000000)
- incr = 2+6+1;
- else {
- assert(ch <= MAX_UNICODE);
- incr = 2+7+1;
+ ch = PyUnicode_READ(kind, data, i);
+ if (ch < 0xdc80 || 0xdcff < ch) {
+ /* Not a UTF-8b surrogate */
+ break;
}
- if (requiredsize > PY_SSIZE_T_MAX - incr)
- goto overflow;
- requiredsize += incr;
- }
- if (requiredsize > PY_SSIZE_T_MAX - (size - collend))
- goto overflow;
- requiredsize += size - collend;
- if (requiredsize > ressize) {
- if (ressize <= PY_SSIZE_T_MAX/2 && requiredsize < 2*ressize)
- requiredsize = 2*ressize;
- if (_PyBytes_Resize(&res, requiredsize))
- goto onError;
- str = PyBytes_AS_STRING(res) + respos;
- ressize = requiredsize;
- }
- /* generate replacement */
- for (i = collstart; i < collend; ++i) {
- str += sprintf(str, "&#%d;", PyUnicode_READ(kind, data, i));
+ *str++ = (char)(ch - 0xdc00);
+ ++pos;
}
- pos = collend;
- break;
+ if (i >= collend)
+ break;
+ collstart = pos;
+ assert(collstart != collend);
+ /* fallback to general error handling */
+
default:
- repunicode = unicode_encode_call_errorhandler(errors, &errorHandler,
- encoding, reason, unicode, &exc,
- collstart, collend, &newpos);
- if (repunicode == NULL || (PyUnicode_Check(repunicode) &&
- PyUnicode_READY(repunicode) == -1))
+ rep = unicode_encode_call_errorhandler(errors, &error_handler_obj,
+ encoding, reason, unicode, &exc,
+ collstart, collend, &newpos);
+ if (rep == NULL)
goto onError;
- if (PyBytes_Check(repunicode)) {
+
+ /* substract preallocated bytes */
+ writer.min_size -= 1;
+
+ if (PyBytes_Check(rep)) {
/* Directly copy bytes result to output. */
- repsize = PyBytes_Size(repunicode);
- if (repsize > 1) {
- /* Make room for all additional bytes. */
- respos = str - PyBytes_AS_STRING(res);
- if (ressize > PY_SSIZE_T_MAX - repsize - 1) {
- Py_DECREF(repunicode);
- goto overflow;
- }
- if (_PyBytes_Resize(&res, ressize+repsize-1)) {
- Py_DECREF(repunicode);
- goto onError;
- }
- str = PyBytes_AS_STRING(res) + respos;
- ressize += repsize-1;
- }
- memcpy(str, PyBytes_AsString(repunicode), repsize);
- str += repsize;
- pos = newpos;
- Py_DECREF(repunicode);
- break;
- }
- /* need more space? (at least enough for what we
- have+the replacement+the rest of the string, so
- we won't have to check space for encodable characters) */
- respos = str - PyBytes_AS_STRING(res);
- repsize = PyUnicode_GET_LENGTH(repunicode);
- requiredsize = respos;
- if (requiredsize > PY_SSIZE_T_MAX - repsize)
- goto overflow;
- requiredsize += repsize;
- if (requiredsize > PY_SSIZE_T_MAX - (size - collend))
- goto overflow;
- requiredsize += size - collend;
- if (requiredsize > ressize) {
- if (ressize <= PY_SSIZE_T_MAX/2 && requiredsize < 2*ressize)
- requiredsize = 2*ressize;
- if (_PyBytes_Resize(&res, requiredsize)) {
- Py_DECREF(repunicode);
+ str = _PyBytesWriter_WriteBytes(&writer, str,
+ PyBytes_AS_STRING(rep),
+ PyBytes_GET_SIZE(rep));
+ if (str == NULL)
goto onError;
- }
- str = PyBytes_AS_STRING(res) + respos;
- ressize = requiredsize;
}
- /* check if there is anything unencodable in the replacement
- and copy it to the output */
- for (i = 0; repsize-->0; ++i, ++str) {
- c = PyUnicode_READ_CHAR(repunicode, i);
- if (c >= limit) {
- raise_encode_exception(&exc, encoding, unicode,
- pos, pos+1, reason);
- Py_DECREF(repunicode);
+ else {
+ assert(PyUnicode_Check(rep));
+
+ if (PyUnicode_READY(rep) < 0)
goto onError;
+
+ if (PyUnicode_IS_ASCII(rep)) {
+ /* Fast path: all characters are smaller than limit */
+ assert(limit >= 128);
+ assert(PyUnicode_KIND(rep) == PyUnicode_1BYTE_KIND);
+ str = _PyBytesWriter_WriteBytes(&writer, str,
+ PyUnicode_DATA(rep),
+ PyUnicode_GET_LENGTH(rep));
+ }
+ else {
+ Py_ssize_t repsize = PyUnicode_GET_LENGTH(rep);
+
+ 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 */
+ for (i = 0; repsize-->0; ++i, ++str) {
+ ch = PyUnicode_READ_CHAR(rep, i);
+ if (ch >= limit) {
+ raise_encode_exception(&exc, encoding, unicode,
+ pos, pos+1, reason);
+ goto onError;
+ }
+ *str = (char)ch;
+ }
}
- *str = (char)c;
}
pos = newpos;
- Py_DECREF(repunicode);
+ Py_CLEAR(rep);
}
+
+ /* If overallocation was disabled, ensure that it was the last
+ write. Otherwise, we missed an optimization */
+ assert(writer.overallocate || pos == size);
}
}
- /* Resize if we allocated to much */
- size = str - PyBytes_AS_STRING(res);
- if (size < ressize) { /* If this falls res will be NULL */
- assert(size >= 0);
- if (_PyBytes_Resize(&res, size) < 0)
- goto onError;
- }
- Py_XDECREF(errorHandler);
+ Py_XDECREF(error_handler_obj);
Py_XDECREF(exc);
- return res;
-
- overflow:
- PyErr_SetString(PyExc_OverflowError,
- "encoded result is too long for a Python string");
+ return _PyBytesWriter_Finish(&writer, str);
onError:
- Py_XDECREF(res);
- Py_XDECREF(errorHandler);
+ Py_XDECREF(rep);
+ _PyBytesWriter_Dealloc(&writer);
+ Py_XDECREF(error_handler_obj);
Py_XDECREF(exc);
return NULL;
}
@@ -6662,8 +6850,9 @@ PyUnicode_DecodeASCII(const char *s,
Py_ssize_t endinpos;
Py_ssize_t outpos;
const char *e;
- PyObject *errorHandler = NULL;
+ PyObject *error_handler_obj = NULL;
PyObject *exc = NULL;
+ _Py_error_handler error_handler = _Py_ERROR_UNKNOWN;
if (size == 0)
_Py_RETURN_UNICODE_EMPTY();
@@ -6692,12 +6881,42 @@ PyUnicode_DecodeASCII(const char *s,
PyUnicode_WRITE(kind, data, writer.pos, c);
writer.pos++;
++s;
+ continue;
}
- else {
+
+ /* byte outsize range 0x00..0x7f: call the error handler */
+
+ if (error_handler == _Py_ERROR_UNKNOWN)
+ error_handler = get_error_handler(errors);
+
+ switch (error_handler)
+ {
+ case _Py_ERROR_REPLACE:
+ case _Py_ERROR_SURROGATEESCAPE:
+ /* Fast-path: the error handler only writes one character,
+ but we may switch to UCS2 at the first write */
+ if (_PyUnicodeWriter_PrepareKind(&writer, PyUnicode_2BYTE_KIND) < 0)
+ goto onError;
+ kind = writer.kind;
+ data = writer.data;
+
+ if (error_handler == _Py_ERROR_REPLACE)
+ PyUnicode_WRITE(kind, data, writer.pos, 0xfffd);
+ else
+ PyUnicode_WRITE(kind, data, writer.pos, c + 0xdc00);
+ writer.pos++;
+ ++s;
+ break;
+
+ case _Py_ERROR_IGNORE:
+ ++s;
+ break;
+
+ default:
startinpos = s-starts;
endinpos = startinpos + 1;
if (unicode_decode_call_errorhandler_writer(
- errors, &errorHandler,
+ errors, &error_handler_obj,
"ascii", "ordinal not in range(128)",
&starts, &e, &startinpos, &endinpos, &exc, &s,
&writer))
@@ -6706,13 +6925,13 @@ PyUnicode_DecodeASCII(const char *s,
data = writer.data;
}
}
- Py_XDECREF(errorHandler);
+ Py_XDECREF(error_handler_obj);
Py_XDECREF(exc);
return _PyUnicodeWriter_Finish(&writer);
onError:
_PyUnicodeWriter_Dealloc(&writer);
- Py_XDECREF(errorHandler);
+ Py_XDECREF(error_handler_obj);
Py_XDECREF(exc);
return NULL;
}
@@ -7111,7 +7330,6 @@ encode_code_page_strict(UINT code_page, PyObject **outbytes,
BOOL usedDefaultChar = FALSE;
BOOL *pusedDefaultChar = &usedDefaultChar;
int outsize;
- PyObject *exc = NULL;
wchar_t *p;
Py_ssize_t size;
const DWORD flags = encode_code_page_flags(code_page, NULL);
@@ -8078,7 +8296,7 @@ static int
charmap_encoding_error(
PyObject *unicode, Py_ssize_t *inpos, PyObject *mapping,
PyObject **exceptionObject,
- int *known_errorHandler, PyObject **errorHandler, const char *errors,
+ _Py_error_handler *error_handler, PyObject **error_handler_obj, const char *errors,
PyObject **res, Py_ssize_t *respos)
{
PyObject *repunicode = NULL; /* initialize to prevent gcc warning */
@@ -8125,23 +8343,15 @@ charmap_encoding_error(
}
/* cache callback name lookup
* (if not done yet, i.e. it's the first error) */
- if (*known_errorHandler==-1) {
- if ((errors==NULL) || (!strcmp(errors, "strict")))
- *known_errorHandler = 1;
- else if (!strcmp(errors, "replace"))
- *known_errorHandler = 2;
- else if (!strcmp(errors, "ignore"))
- *known_errorHandler = 3;
- else if (!strcmp(errors, "xmlcharrefreplace"))
- *known_errorHandler = 4;
- else
- *known_errorHandler = 0;
- }
- switch (*known_errorHandler) {
- case 1: /* strict */
+ if (*error_handler == _Py_ERROR_UNKNOWN)
+ *error_handler = get_error_handler(errors);
+
+ switch (*error_handler) {
+ case _Py_ERROR_STRICT:
raise_encode_exception(exceptionObject, encoding, unicode, collstartpos, collendpos, reason);
return -1;
- case 2: /* replace */
+
+ case _Py_ERROR_REPLACE:
for (collpos = collstartpos; collpos<collendpos; ++collpos) {
x = charmapencode_output('?', mapping, res, respos);
if (x==enc_EXCEPTION) {
@@ -8153,10 +8363,11 @@ charmap_encoding_error(
}
}
/* fall through */
- case 3: /* ignore */
+ case _Py_ERROR_IGNORE:
*inpos = collendpos;
break;
- case 4: /* xmlcharrefreplace */
+
+ case _Py_ERROR_XMLCHARREFREPLACE:
/* generate replacement (temporarily (mis)uses p) */
for (collpos = collstartpos; collpos < collendpos; ++collpos) {
char buffer[2+29+1+1];
@@ -8174,8 +8385,9 @@ charmap_encoding_error(
}
*inpos = collendpos;
break;
+
default:
- repunicode = unicode_encode_call_errorhandler(errors, errorHandler,
+ repunicode = unicode_encode_call_errorhandler(errors, error_handler_obj,
encoding, reason, unicode, exceptionObject,
collstartpos, collendpos, &newpos);
if (repunicode == NULL)
@@ -8238,12 +8450,9 @@ _PyUnicode_EncodeCharmap(PyObject *unicode,
Py_ssize_t size;
/* current output position */
Py_ssize_t respos = 0;
- PyObject *errorHandler = NULL;
+ PyObject *error_handler_obj = NULL;
PyObject *exc = NULL;
- /* the following variable is used for caching string comparisons
- * -1=not initialized, 0=unknown, 1=strict, 2=replace,
- * 3=ignore, 4=xmlcharrefreplace */
- int known_errorHandler = -1;
+ _Py_error_handler error_handler = _Py_ERROR_UNKNOWN;
void *data;
int kind;
@@ -8274,7 +8483,7 @@ _PyUnicode_EncodeCharmap(PyObject *unicode,
if (x==enc_FAILED) { /* unencodable character */
if (charmap_encoding_error(unicode, &inpos, mapping,
&exc,
- &known_errorHandler, &errorHandler, errors,
+ &error_handler, &error_handler_obj, errors,
&res, &respos)) {
goto onError;
}
@@ -8290,13 +8499,13 @@ _PyUnicode_EncodeCharmap(PyObject *unicode,
goto onError;
Py_XDECREF(exc);
- Py_XDECREF(errorHandler);
+ Py_XDECREF(error_handler_obj);
return res;
onError:
Py_XDECREF(res);
Py_XDECREF(exc);
- Py_XDECREF(errorHandler);
+ Py_XDECREF(error_handler_obj);
return NULL;
}
@@ -8622,7 +8831,7 @@ exit:
return res;
}
-PyObject *
+static PyObject *
_PyUnicode_TranslateCharmap(PyObject *input,
PyObject *mapping,
const char *errors)
@@ -10893,6 +11102,12 @@ PyUnicode_RichCompare(PyObject *left, PyObject *right, int op)
}
int
+_PyUnicode_EQ(PyObject *aa, PyObject *bb)
+{
+ return unicode_eq(aa, bb);
+}
+
+int
PyUnicode_Contains(PyObject *container, PyObject *element)
{
PyObject *str, *sub;
@@ -13225,44 +13440,50 @@ unicode_endswith(PyObject *self,
Py_LOCAL_INLINE(void)
_PyUnicodeWriter_Update(_PyUnicodeWriter *writer)
{
- if (!writer->readonly)
+ writer->maxchar = PyUnicode_MAX_CHAR_VALUE(writer->buffer);
+ writer->data = PyUnicode_DATA(writer->buffer);
+
+ if (!writer->readonly) {
+ writer->kind = PyUnicode_KIND(writer->buffer);
writer->size = PyUnicode_GET_LENGTH(writer->buffer);
+ }
else {
+ /* use a value smaller than PyUnicode_1BYTE_KIND() so
+ _PyUnicodeWriter_PrepareKind() will copy the buffer. */
+ writer->kind = PyUnicode_WCHAR_KIND;
+ assert(writer->kind <= PyUnicode_1BYTE_KIND);
+
/* Copy-on-write mode: set buffer size to 0 so
* _PyUnicodeWriter_Prepare() will copy (and enlarge) the buffer on
* next write. */
writer->size = 0;
}
- writer->maxchar = PyUnicode_MAX_CHAR_VALUE(writer->buffer);
- writer->data = PyUnicode_DATA(writer->buffer);
- writer->kind = PyUnicode_KIND(writer->buffer);
}
void
_PyUnicodeWriter_Init(_PyUnicodeWriter *writer)
{
memset(writer, 0, sizeof(*writer));
-#ifdef Py_DEBUG
- writer->kind = 5; /* invalid kind */
-#endif
+
+ /* ASCII is the bare minimum */
writer->min_char = 127;
+
+ /* use a value smaller than PyUnicode_1BYTE_KIND() so
+ _PyUnicodeWriter_PrepareKind() will copy the buffer. */
+ writer->kind = PyUnicode_WCHAR_KIND;
+ assert(writer->kind <= PyUnicode_1BYTE_KIND);
}
int
_PyUnicodeWriter_PrepareInternal(_PyUnicodeWriter *writer,
Py_ssize_t length, Py_UCS4 maxchar)
{
-#ifdef MS_WINDOWS
- /* On Windows, overallocate by 50% is the best factor */
-# define OVERALLOCATE_FACTOR 2
-#else
- /* On Linux, overallocate by 25% is the best factor */
-# define OVERALLOCATE_FACTOR 4
-#endif
Py_ssize_t newlen;
PyObject *newbuffer;
- assert(length > 0);
+ /* ensure that the _PyUnicodeWriter_Prepare macro was used */
+ assert((maxchar > writer->maxchar && length >= 0)
+ || length > 0);
if (length > PY_SSIZE_T_MAX - writer->pos) {
PyErr_NoMemory();
@@ -13328,6 +13549,28 @@ _PyUnicodeWriter_PrepareInternal(_PyUnicodeWriter *writer,
#undef OVERALLOCATE_FACTOR
}
+int
+_PyUnicodeWriter_PrepareKindInternal(_PyUnicodeWriter *writer,
+ enum PyUnicode_Kind kind)
+{
+ Py_UCS4 maxchar;
+
+ /* ensure that the _PyUnicodeWriter_PrepareKind macro was used */
+ assert(writer->kind < kind);
+
+ switch (kind)
+ {
+ case PyUnicode_1BYTE_KIND: maxchar = 0xff; break;
+ case PyUnicode_2BYTE_KIND: maxchar = 0xffff; break;
+ case PyUnicode_4BYTE_KIND: maxchar = 0x10ffff; break;
+ default:
+ assert(0 && "invalid kind");
+ return -1;
+ }
+
+ return _PyUnicodeWriter_PrepareInternal(writer, 0, maxchar);
+}
+
Py_LOCAL_INLINE(int)
_PyUnicodeWriter_WriteCharInline(_PyUnicodeWriter *writer, Py_UCS4 ch)
{
@@ -13498,17 +13741,26 @@ _PyUnicodeWriter_Finish(_PyUnicodeWriter *writer)
assert(PyUnicode_GET_LENGTH(str) == writer->pos);
return str;
}
- if (PyUnicode_GET_LENGTH(writer->buffer) != writer->pos) {
- PyObject *newbuffer;
- newbuffer = resize_compact(writer->buffer, writer->pos);
- if (newbuffer == NULL) {
- Py_CLEAR(writer->buffer);
- return NULL;
+ if (writer->pos == 0) {
+ Py_CLEAR(writer->buffer);
+
+ /* Get the empty Unicode string singleton ('') */
+ _Py_INCREF_UNICODE_EMPTY();
+ str = unicode_empty;
+ }
+ else {
+ str = writer->buffer;
+ writer->buffer = NULL;
+
+ if (PyUnicode_GET_LENGTH(str) != writer->pos) {
+ PyObject *str2;
+ str2 = resize_compact(str, writer->pos);
+ if (str2 == NULL)
+ return NULL;
+ str = str2;
}
- writer->buffer = newbuffer;
}
- str = writer->buffer;
- writer->buffer = NULL;
+
assert(_PyUnicode_CheckConsistency(str, 1));
return unicode_result_ready(str);
}
View Lorry Controller Status