mtasaka
commented
1 year ago Something like: (just fixed compilation, have not checked if this really works)
--- qutepart-3.3.3/qutepart/syntax/cParser.c.pep623 2022-08-10 19:15:37.000000000 +0900
+++ qutepart-3.3.3/qutepart/syntax/cParser.c 2023-07-07 17:24:19.578531671 +0900
@@ -213,7 +213,7 @@ typedef struct {
/* Type-specific fields go here. */
PyObject* parentContext;
PyObject* format;
- Py_UNICODE textType;
+ Py_UCS4 textType;
PyObject* attribute;
ContextSwitcher* context;
bool lookAhead;
@@ -254,8 +254,8 @@ typedef struct {
PyObject* wholeLineUnicodeTextLower;
PyObject* wholeLineUtf8Text;
PyObject* wholeLineUtf8TextLower;
- Py_UNICODE* unicodeText;
- Py_UNICODE* unicodeTextLower;
+ Py_UCS4* unicodeText;
+ Py_UCS4* unicodeTextLower;
const char* utf8Text;
const char* utf8TextLower;
size_t textLen;
@@ -290,7 +290,7 @@ typedef struct {
AbstractRule** rulesC;
size_t rulesSize;
bool dynamic;
- Py_UNICODE textType;
+ Py_UCS4 textType;
PyObject* textTypePython;
} Context;
@@ -396,12 +396,12 @@ _listToDynamicallyAllocatedArray(PyObjec
* DeliminatorSet
********************************************************************************/
static bool
-_isDeliminatorNoCache(Py_UNICODE character, PyObject* setAsUnicodeString)
+_isDeliminatorNoCache(Py_UCS4 character, PyObject* setAsUnicodeString)
{
- Py_ssize_t deliminatorSetLen = PyUnicode_GET_SIZE(setAsUnicodeString);
+ Py_ssize_t deliminatorSetLen = PyUnicode_GET_LENGTH(setAsUnicodeString);
Py_ssize_t i;
- Py_UNICODE* deliminatorSetUnicode = PyUnicode_AS_UNICODE(setAsUnicodeString);
+ Py_UCS4* deliminatorSetUnicode = PyUnicode_AsUCS4Copy(setAsUnicodeString);
for(i = 0; i < deliminatorSetLen; i++)
if (deliminatorSetUnicode[i] == character)
@@ -411,7 +411,7 @@ _isDeliminatorNoCache(Py_UNICODE charact
}
static bool
-_isDeliminator(Py_UNICODE character, DeliminatorSet* deliminatorSet)
+_isDeliminator(Py_UCS4 character, DeliminatorSet* deliminatorSet)
{
if (character < DELIMINATOR_SET_CACHE_SIZE)
return deliminatorSet->cache[character];
@@ -489,7 +489,7 @@ AbstractRuleParams_init(AbstractRulePara
ASSIGN_PYOBJECT_FIELD(format);
if (Py_None != textType)
- self->textType = PyUnicode_AsUnicode(textType)[0];
+ self->textType = PyUnicode_AsUCS4Copy(textType)[0];
else
self->textType = 0;
@@ -575,7 +575,7 @@ TextToMatchObject_internal_make(unsigned
{
TextToMatchObject_internal textToMatchObject;
- textToMatchObject.wholeLineLen = PyUnicode_GET_SIZE(unicodeText);
+ textToMatchObject.wholeLineLen = PyUnicode_GET_LENGTH(unicodeText);
textToMatchObject.currentColumnIndex = column;
textToMatchObject.wholeLineUnicodeText = unicodeText;
textToMatchObject.wholeLineUnicodeTextLower = PyObject_CallMethod(unicodeText, "lower", "");
@@ -611,8 +611,8 @@ TextToMatchObject_internal_update(TextTo
unsigned int i;
unsigned int prevTextLen;
unsigned int step;
- Py_UNICODE* wholeLineUnicodeBuffer = PyUnicode_AS_UNICODE(self->wholeLineUnicodeText);
- Py_UNICODE* wholeLineUnicodeBufferLower = PyUnicode_AS_UNICODE(self->wholeLineUnicodeTextLower);
+ Py_UCS4* wholeLineUnicodeBuffer = PyUnicode_AsUCS4Copy(self->wholeLineUnicodeText);
+ Py_UCS4* wholeLineUnicodeBufferLower = PyUnicode_AsUCS4Copy(self->wholeLineUnicodeTextLower);
// update text, textLen, column
self->unicodeText = wholeLineUnicodeBuffer + currentColumnIndex;
@@ -632,7 +632,7 @@ TextToMatchObject_internal_update(TextTo
if (currentColumnIndex > 0)
{
- Py_UNICODE prevChar = wholeLineUnicodeBuffer[currentColumnIndex - 1];
+ Py_UCS4 prevChar = wholeLineUnicodeBuffer[currentColumnIndex - 1];
bool previousCharIsSpace = Py_UNICODE_ISSPACE(prevChar);
// update firstNonSpace
@@ -1083,8 +1083,8 @@ DECLARE_RULE_METHODS_AND_TYPE(DetectChar
typedef struct {
AbstractRule_HEAD
/* Type-specific fields go here. */
- Py_UNICODE char_;
- Py_UNICODE char1_;
+ Py_UCS4 char_;
+ Py_UCS4 char1_;
} Detect2Chars;
@@ -1112,7 +1112,7 @@ Detect2Chars_init(Detect2Chars *self, Py
{
PyObject* abstractRuleParams = NULL;
PyObject* string = NULL;
- Py_UNICODE* unicode;
+ Py_UCS4* unicode;
self->_tryMatch = Detect2Chars_tryMatch;
@@ -1124,7 +1124,7 @@ Detect2Chars_init(Detect2Chars *self, Py
UNICODE_CHECK(string, -1);
- unicode = PyUnicode_AS_UNICODE(string);
+ unicode = PyUnicode_AsUCS4Copy(string);
self->char_ = unicode[0];
self->char1_ = unicode[1];
@@ -1154,9 +1154,9 @@ static RuleTryMatchResult_internal
AnyChar_tryMatch(AnyChar* self, TextToMatchObject_internal* textToMatchObject)
{
Py_ssize_t i;
- Py_ssize_t size = PyUnicode_GET_SIZE(self->string);
- Py_UNICODE* unicode = PyUnicode_AS_UNICODE(self->string);
- Py_UNICODE char_ = textToMatchObject->unicodeText[0];
+ Py_ssize_t size = PyUnicode_GET_LENGTH(self->string);
+ Py_UCS4* unicode = PyUnicode_AsUCS4Copy(self->string);
+ Py_UCS4 char_ = textToMatchObject->unicodeText[0];
for (i = 0; i < size; i++)
{
@@ -1673,7 +1673,7 @@ RegExpr_tryMatch(RegExpr* self, TextToMa
if (unicodeText == NULL) {
return MakeEmptyTryMatchResult();
}
- matchLen = PyUnicode_GET_SIZE(unicodeText);
+ matchLen = PyUnicode_GET_LENGTH(unicodeText);
Py_DECREF(unicodeText);
if (matchLen != 0) {
@@ -1736,7 +1736,7 @@ DECLARE_RULE_METHODS_AND_TYPE(RegExpr);
/********************************************************************************
* Int
********************************************************************************/
-size_t AbstractNumberRule_countDigits(Py_UNICODE* text, size_t textLen)
+size_t AbstractNumberRule_countDigits(Py_UCS4* text, size_t textLen)
{
size_t i;
@@ -1852,7 +1852,7 @@ AbstractNumberRule_tryMatch(AbstractRule
return MakeEmptyTryMatchResult();
matchEndIndex = textToMatchObject->currentColumnIndex + index;
- if (matchEndIndex < PyUnicode_GET_SIZE(textToMatchObject->wholeLineUnicodeText))
+ if (matchEndIndex < PyUnicode_GET_LENGTH(textToMatchObject->wholeLineUnicodeText))
{
size_t i;
bool haveMatch = false;
@@ -2000,7 +2000,7 @@ HlCOct_dealloc_fields(HlCOct* self)
}
static bool
-_isOctChar(Py_UNICODE symbol)
+_isOctChar(Py_UCS4 symbol)
{
return (symbol >= '0' && symbol <= '7');
}
@@ -2062,7 +2062,7 @@ HlCHex_dealloc_fields(HlCHex* self)
}
static bool
-_isHexChar(Py_UNICODE symbol)
+_isHexChar(Py_UCS4 symbol)
{
return (symbol >= '0' && symbol <= '9') ||
(symbol >= 'a' && symbol <= 'f');
@@ -2119,7 +2119,7 @@ DECLARE_RULE_METHODS_AND_TYPE(HlCHex);
********************************************************************************/
static bool
-_charInString(Py_UNICODE character, const char* string)
+_charInString(Py_UCS4 character, const char* string)
{
char charToSearch = (char)character;
@@ -2130,7 +2130,7 @@ _charInString(Py_UNICODE character, cons
}
static int
-_checkEscapedChar(Py_UNICODE* textLower, size_t textLen)
+_checkEscapedChar(Py_UCS4* textLower, size_t textLen)
{
size_t index = 0;
if (textLen > 1 && textLower[0] == '\\')
@@ -2270,8 +2270,8 @@ DECLARE_RULE_METHODS_AND_TYPE(HlCChar);
typedef struct {
AbstractRule_HEAD
/* Type-specific fields go here. */
- Py_UNICODE char_;
- Py_UNICODE char1_;
+ Py_UCS4 char_;
+ Py_UCS4 char1_;
} RangeDetect;
@@ -2320,8 +2320,8 @@ RangeDetect_init(RangeDetect *self, PyOb
UNICODE_CHECK(char1_, -1);
ASSIGN_FIELD(AbstractRuleParams, abstractRuleParams);
- self->char_ = PyUnicode_AS_UNICODE(char_)[0];
- self->char1_ = PyUnicode_AS_UNICODE(char1_)[0];
+ self->char_ = PyUnicode_AsUCS4Copy(char_)[0];
+ self->char1_ = PyUnicode_AsUCS4Copy(char1_)[0];
return 0;
}
@@ -2740,7 +2740,7 @@ Context_setValues(Context *self, PyObjec
ASSIGN_FIELD(ContextSwitcher, fallthroughContext);
ASSIGN_BOOL_FIELD(dynamic);
ASSIGN_PYOBJECT_FIELD(textTypePython);
- self->textType = PyUnicode_AsUnicode(textTypePython)[0];
+ self->textType = PyUnicode_AsUCS4Copy(textTypePython)[0];
Py_RETURN_NONE;
}
@@ -2782,7 +2782,7 @@ Context_appendSegment(PyObject* segmentL
}
static void
-Context_appendTextType(size_t fromIndex, size_t count, PyObject* textTypeMap, Py_UNICODE textType)
+Context_appendTextType(size_t fromIndex, size_t count, PyObject* textTypeMap, Py_UCS4 textType)
{
size_t i;
for (i = fromIndex; i < fromIndex + count; i++)
@@ -2808,7 +2808,7 @@ Context_parseBlock(Context* self,
unicodeText,
ContextStack_currentData(*pContextStack));
- wholeLineLen = PyUnicode_GET_SIZE(textToMatchObject.wholeLineUnicodeText);
+ wholeLineLen = PyUnicode_GET_LENGTH(textToMatchObject.wholeLineUnicodeText);
*pLineContinue = false;
@@ -2849,7 +2849,7 @@ Context_parseBlock(Context* self,
if (NULL != result.rule) // if something matched
{
PyObject* format;
- Py_UNICODE textType;
+ Py_UCS4 textType;
*pLineContinue = result.lineContinue;
if (parentParser->debugOutputEnabled)
@@ -3088,7 +3088,7 @@ Parser_parseBlock_internal(Parser *self,
Py_INCREF(Py_None);
}
- textLen = PyUnicode_GET_SIZE(unicodeText);
+ textLen = PyUnicode_GET_LENGTH(unicodeText);
textTypeMap = PyUnicode_New(textLen, 65535);
if (textLen > 0)
PyUnicode_Fill(textTypeMap, 0, textLen, ' ');
rapgro
python-qutepart fails to build with Python 3.12.0a3.
Leagcy Unicode APIs has been removed. See PEP 623 for detail. PyUnicode_WCHAR_KIND PyUnicode_AS_UNICODE() PyUnicode_AsUnicode() PyUnicode_AsUnicodeAndSize() PyUnicode_AS_DATA() PyUnicode_FromUnicode() PyUnicode_GET_SIZE() PyUnicode_GetSize() PyUnicode_GET_DATA_SIZE()