- PyUnicode_1BYTE_KIND (1):
* character type = Py_UCS1 (8 bits, unsigned)
- * if ascii is set, all characters must be in range
- U+0000-U+007F, otherwise at least one character must be in range
+ * all characters are in the range U+0000-U+00FF (latin1)
+ * if ascii is set, all characters are in the range U+0000-U+007F
+ (ASCII), otherwise at least one character is in the range
U+0080-U+00FF
- PyUnicode_2BYTE_KIND (2):
* character type = Py_UCS2 (16 bits, unsigned)
- * at least one character must be in range U+0100-U+FFFF
+ * all characters are in the range U+0000-U+FFFF (BMP)
+ * at least one character is in the range U+0100-U+FFFF
- PyUnicode_4BYTE_KIND (4):
* character type = Py_UCS4 (32 bits, unsigned)
- * at least one character must be in range U+10000-U+10FFFF
+ * all characters are in the range U+0000-U+10FFFF
+ * at least one character is in the range U+10000-U+10FFFF
*/
unsigned int kind:3;
/* Compact is with respect to the allocation scheme. Compact unicode
one block for the PyUnicodeObject struct and another for its data
buffer. */
unsigned int compact:1;
- /* The string only contains characters in range U+0000-U+007F (ASCII)
+ /* The string only contains characters in the range U+0000-U+007F (ASCII)
and the kind is PyUnicode_1BYTE_KIND. If ascii is set and compact is
set, use the PyASCIIObject structure. */
unsigned int ascii:1;
maxchar = ch;
}
if (kind == PyUnicode_1BYTE_KIND) {
- if (ascii->state.ascii == 0)
+ if (ascii->state.ascii == 0) {
assert(maxchar >= 128);
+ assert(maxchar <= 255);
+ }
else
assert(maxchar < 128);
}
- else if (kind == PyUnicode_2BYTE_KIND)
+ else if (kind == PyUnicode_2BYTE_KIND) {
assert(maxchar >= 0x100);
- else
+ assert(maxchar <= 0xFFFF);
+ }
+ else {
assert(maxchar >= 0x10000);
+ assert(maxchar <= 0x10FFFF);
+ }
}
if (check_content && !unicode_is_singleton(op))
assert(ascii->hash == -1);