C++ PyUnicode_GET_LENGTH函数代码示例

static PyObject *
zipimport_zipimporter_get_data_impl(ZipImporter *self, PyObject *path)
/*[clinic end generated code: output=65dc506aaa268436 input=fa6428b74843c4ae]*/
{
    PyObject *key;
    PyObject *toc_entry;
    Py_ssize_t path_start, path_len, len;

    if (self->archive == NULL) {
        PyErr_SetString(PyExc_ValueError,
                        "zipimporter.__init__() wasn't called");
        return NULL;
    }

#ifdef ALTSEP
    path = _PyObject_CallMethodId((PyObject *)&PyUnicode_Type, &PyId_replace,
                                  "OCC", path, ALTSEP, SEP);
    if (!path)
        return NULL;
#else
    Py_INCREF(path);
#endif
    if (PyUnicode_READY(path) == -1)
        goto error;

    path_len = PyUnicode_GET_LENGTH(path);

    len = PyUnicode_GET_LENGTH(self->archive);
    path_start = 0;
    if (PyUnicode_Tailmatch(path, self->archive, 0, len, -1)
        && PyUnicode_READ_CHAR(path, len) == SEP) {
        path_start = len + 1;
    }

    key = PyUnicode_Substring(path, path_start, path_len);
    if (key == NULL)
        goto error;
    toc_entry = PyDict_GetItem(self->files, key);
    if (toc_entry == NULL) {
        PyErr_SetFromErrnoWithFilenameObject(PyExc_OSError, key);
        Py_DECREF(key);
        goto error;
    }
    Py_DECREF(key);
    Py_DECREF(path);
    return get_data(self->archive, toc_entry);
  error:
    Py_DECREF(path);
    return NULL;
}

static PyObject *
zipimporter_get_data(PyObject *obj, PyObject *args)
{
    ZipImporter *self = (ZipImporter *)obj;
    PyObject *path, *key;
#ifdef ALTSEP
    _Py_IDENTIFIER(replace);
#endif
    PyObject *toc_entry;
    Py_ssize_t path_start, path_len, len;

    if (!PyArg_ParseTuple(args, "U:zipimporter.get_data", &path))
        return NULL;

#ifdef ALTSEP
    path = _PyObject_CallMethodId(path, &PyId_replace, "CC", ALTSEP, SEP);
    if (!path)
        return NULL;
#else
    Py_INCREF(path);
#endif
    if (PyUnicode_READY(path) == -1)
        goto error;

    path_len = PyUnicode_GET_LENGTH(path);

    len = PyUnicode_GET_LENGTH(self->archive);
    path_start = 0;
    if (PyUnicode_Tailmatch(path, self->archive, 0, len, -1)
        && PyUnicode_READ_CHAR(path, len) == SEP) {
        path_start = len + 1;
    }

    key = PyUnicode_Substring(path, path_start, path_len);
    if (key == NULL)
        goto error;
    toc_entry = PyDict_GetItem(self->files, key);
    if (toc_entry == NULL) {
        PyErr_SetFromErrnoWithFilenameObject(PyExc_IOError, key);
        Py_DECREF(key);
        goto error;
    }
    Py_DECREF(key);
    Py_DECREF(path);
    return get_data(self->archive, toc_entry);
  error:
    Py_DECREF(path);
    return NULL;
}

static int
asciistr_getbuffer(PyObject *exporter, Py_buffer *view, int flags)
{

    return (PyBuffer_FillInfo(view, exporter, PyUnicode_DATA(exporter),
        PyUnicode_GET_LENGTH(exporter), 1, flags));
}

// Convert a Python Unicode object to a QString.
QString qpycore_PyObject_AsQString(PyObject *obj)
{
#if defined(PYQT_PEP_393)
    SIP_SSIZE_T len = PyUnicode_GET_LENGTH(obj);

    switch (PyUnicode_KIND(obj))
    {
    case PyUnicode_1BYTE_KIND:
        return QString::fromLatin1((char *)PyUnicode_1BYTE_DATA(obj), len);

    case PyUnicode_2BYTE_KIND:
        // The (QChar *) cast should be safe.
        return QString((QChar *)PyUnicode_2BYTE_DATA(obj), len);

    case PyUnicode_4BYTE_KIND:
        return QString::fromUcs4(PyUnicode_4BYTE_DATA(obj), len);
    }

    return QString();
#elif defined(Py_UNICODE_WIDE)
    return QString::fromUcs4((const uint *)PyUnicode_AS_UNICODE(obj),
            PyUnicode_GET_SIZE(obj));
#else
    return QString::fromUtf16((const ushort *)PyUnicode_AS_UNICODE(obj),
            PyUnicode_GET_SIZE(obj));
#endif
}

static PyObject *
Reader_iternext(ReaderObj *self)
{
    PyObject *fields = NULL;
    Py_UCS4 c;
    Py_ssize_t pos, linelen;
    unsigned int kind;
    void *data;
    PyObject *lineobj;

    if (parse_reset(self) < 0)
        return NULL;
    do {
        lineobj = PyIter_Next(self->input_iter);
        if (lineobj == NULL) {
            /* End of input OR exception */
            if (!PyErr_Occurred() && self->field_len != 0)
                PyErr_Format(error_obj,
                             "newline inside string");
            return NULL;
        }
        if (!PyUnicode_Check(lineobj)) {
            PyErr_Format(error_obj,
                         "iterator should return strings, "
                         "not %.200s "
                         "(did you open the file in text mode?)",
                         lineobj->ob_type->tp_name
                );
            Py_DECREF(lineobj);
            return NULL;
        }
        ++self->line_num;
        kind = PyUnicode_KIND(lineobj);
        data = PyUnicode_DATA(lineobj);
        pos = 0;
        linelen = PyUnicode_GET_LENGTH(lineobj);
        while (linelen--) {
            c = PyUnicode_READ(kind, data, pos);
            if (c == '\0') {
                Py_DECREF(lineobj);
                PyErr_Format(error_obj,
                             "line contains NULL byte");
                goto err;
            }
            if (parse_process_char(self, c) < 0) {
                Py_DECREF(lineobj);
                goto err;
            }
            pos++;
        }
        Py_DECREF(lineobj);
        if (parse_process_char(self, 0) < 0)
            goto err;
    } while (self->state != START_RECORD);

    fields = self->fields;
    self->fields = NULL;
err:
    return fields;
}

static int
join_append(WriterObj *self, PyObject *field, int *quoted, int quote_empty)
{
    unsigned int field_kind = -1;
    void *field_data = NULL;
    Py_ssize_t field_len = 0;
    Py_ssize_t rec_len;

    if (field != NULL) {
        field_kind = PyUnicode_KIND(field);
        field_data = PyUnicode_DATA(field);
        field_len = PyUnicode_GET_LENGTH(field);
    }
    rec_len = join_append_data(self, field_kind, field_data, field_len,
                               quote_empty, quoted, 0);
    if (rec_len < 0)
        return 0;

    /* grow record buffer if necessary */
    if (!join_check_rec_size(self, rec_len))
        return 0;

    self->rec_len = join_append_data(self, field_kind, field_data, field_len,
                                     quote_empty, quoted, 1);
    self->num_fields++;

    return 1;
}

// Convert a Python Unicode object to a QString.
QString qpycore_PyObject_AsQString(PyObject *obj)
{
#if defined(PYQT_PEP_393)
    SIP_SSIZE_T len = PyUnicode_GET_LENGTH(obj);

    switch (PyUnicode_KIND(obj))
    {
    case PyUnicode_1BYTE_KIND:
        return QString::fromLatin1((char *)PyUnicode_1BYTE_DATA(obj), len);

    case PyUnicode_2BYTE_KIND:
        // The (QChar *) cast should be safe.
        return QString((QChar *)PyUnicode_2BYTE_DATA(obj), len);

    case PyUnicode_4BYTE_KIND:
#if QT_VERSION >= 0x040200
        return QString::fromUcs4(PyUnicode_4BYTE_DATA(obj), len);
#else
        // Note that this code doesn't handle code points greater than 0xffff
        // very well.

        QString qstr;

        Py_UCS4 *ucode = PyUnicode_4BYTE_DATA(obj);

        for (SIP_SSIZE_T i = 0; i < len; ++i)
            qstr.append((uint)ucode[i]);

        return qstr;
#endif
    }

    return QString();
#elif defined(Py_UNICODE_WIDE)
#if QT_VERSION >= 0x040200
    return QString::fromUcs4((const uint *)PyUnicode_AS_UNICODE(obj),
            PyUnicode_GET_SIZE(obj));
#else
    // Note that this code doesn't handle code points greater than 0xffff very
    // well.

    QString qstr;

    Py_UNICODE *ucode = PyUnicode_AS_UNICODE(obj);
    SIP_SSIZE_T len = PyUnicode_GET_SIZE(obj);

    for (SIP_SSIZE_T i = 0; i < len; ++i)
        qstr.append((uint)ucode[i]);

    return qstr;
#endif
#else
    return QString::fromUtf16((const ushort *)PyUnicode_AS_UNICODE(obj),
            PyUnicode_GET_SIZE(obj));
#endif
}

static PyObject *
complex__format__(PyObject* self, PyObject* args)
{
    PyObject *format_spec;

    if (!PyArg_ParseTuple(args, "U:__format__", &format_spec))
    return NULL;
    return _PyComplex_FormatAdvanced(self, format_spec, 0,
                                     PyUnicode_GET_LENGTH(format_spec));
}

static int
_str_shared(PyObject *obj, _PyCrossInterpreterData *data)
{
    struct _shared_str_data *shared = PyMem_NEW(struct _shared_str_data, 1);
    shared->kind = PyUnicode_KIND(obj);
    shared->buffer = PyUnicode_DATA(obj);
    shared->len = PyUnicode_GET_LENGTH(obj) - 1;
    data->data = (void *)shared;
    data->obj = obj;  // Will be "released" (decref'ed) when data released.
    data->new_object = _new_str_object;
    data->free = PyMem_Free;
    return 0;
}

static PyObject *
syslog_get_argv(void)
{
    /* Figure out what to use for as the program "ident" for openlog().
     * This swallows exceptions and continues rather than failing out,
     * because the syslog module can still be used because openlog(3)
     * is optional.
     */

    Py_ssize_t argv_len, scriptlen;
    PyObject *scriptobj;
    Py_ssize_t slash;
    PyObject *argv = PySys_GetObject("argv");

    if (argv == NULL) {
        return(NULL);
    }

    argv_len = PyList_Size(argv);
    if (argv_len == -1) {
        PyErr_Clear();
        return(NULL);
    }
    if (argv_len == 0) {
        return(NULL);
    }

    scriptobj = PyList_GetItem(argv, 0);
    if (!PyUnicode_Check(scriptobj)) {
        return(NULL);
    }
    scriptlen = PyUnicode_GET_LENGTH(scriptobj);
    if (scriptlen == 0) {
        return(NULL);
    }

    slash = PyUnicode_FindChar(scriptobj, SEP, 0, scriptlen, -1);
    if (slash == -2)
        return NULL;
    if (slash != -1) {
        return PyUnicode_Substring(scriptobj, slash, scriptlen);
    } else {
        Py_INCREF(scriptobj);
        return(scriptobj);
    }

    return(NULL);
}

/* all_name_chars(s): true iff s matches [a-zA-Z0-9_]* */
static int
all_name_chars(PyObject *o)
{
    const unsigned char *s, *e;

    if (!PyUnicode_IS_ASCII(o))
        return 0;

    s = PyUnicode_1BYTE_DATA(o);
    e = s + PyUnicode_GET_LENGTH(o);
    for (; s != e; s++) {
        if (!Py_ISALNUM(*s) && *s != '_')
            return 0;
    }
    return 1;
}

static NUMBA_INLINE Py_UCS4 __Numba_PyObject_AsPy_UCS4(PyObject* x) {
   long ival;
   if (PyUnicode_Check(x)) {
       Py_ssize_t length;
       #if CYTHON_PEP393_ENABLED
       length = PyUnicode_GET_LENGTH(x);
       if (likely(length == 1)) {
           return PyUnicode_READ_CHAR(x, 0);
       }
       #else
       length = PyUnicode_GET_SIZE(x);
       if (likely(length == 1)) {
           return PyUnicode_AS_UNICODE(x)[0];
       }
       #if Py_UNICODE_SIZE == 2
       else if (PyUnicode_GET_SIZE(x) == 2) {
           Py_UCS4 high_val = PyUnicode_AS_UNICODE(x)[0];
           if (high_val >= 0xD800 && high_val <= 0xDBFF) {
               Py_UCS4 low_val = PyUnicode_AS_UNICODE(x)[1];
               if (low_val >= 0xDC00 && low_val <= 0xDFFF) {
                   return 0x10000 + (((high_val & ((1<<10)-1)) << 10) | (low_val & ((1<<10)-1)));
               }
           }
       }
       #endif
       #endif
       PyErr_Format(PyExc_ValueError,
                    "only single character unicode strings can be converted to Py_UCS4, "
                    "got length %" CYTHON_FORMAT_SSIZE_T "d", length);
       return (Py_UCS4)-1;
   }
   ival = __Numba_PyInt_AsLong(x);
   if (unlikely(ival < 0)) {
       if (!PyErr_Occurred())
           PyErr_SetString(PyExc_OverflowError,
                           "cannot convert negative value to Py_UCS4");
       return (Py_UCS4)-1;
   } else if (unlikely(ival > 1114111)) {
       PyErr_SetString(PyExc_OverflowError,
                       "value too large to convert to Py_UCS4");
       return (Py_UCS4)-1;
   }
   return (Py_UCS4)ival;
}

static PyObject *
complex__format__(PyObject* self, PyObject* args)
{
    PyObject *format_spec;
    _PyUnicodeWriter writer;
    int ret;

    if (!PyArg_ParseTuple(args, "U:__format__", &format_spec))
        return NULL;

    _PyUnicodeWriter_Init(&writer);
    ret = _PyComplex_FormatAdvancedWriter(
        &writer,
        self,
        format_spec, 0, PyUnicode_GET_LENGTH(format_spec));
    if (ret == -1) {
        _PyUnicodeWriter_Dealloc(&writer);
        return NULL;
    }
    return _PyUnicodeWriter_Finish(&writer);
}

static int
join_append_lineterminator(WriterObj *self)
{
    Py_ssize_t terminator_len, i;
    unsigned int term_kind;
    void *term_data;

    terminator_len = PyUnicode_GET_LENGTH(self->dialect->lineterminator);
    if (terminator_len == -1)
        return 0;

    /* grow record buffer if necessary */
    if (!join_check_rec_size(self, self->rec_len + terminator_len))
        return 0;

    term_kind = PyUnicode_KIND(self->dialect->lineterminator);
    term_data = PyUnicode_DATA(self->dialect->lineterminator);
    for (i = 0; i < terminator_len; i++)
        self->rec[self->rec_len + i] = PyUnicode_READ(term_kind, term_data, i);
    self->rec_len += terminator_len;

    return 1;
}

Py_ssize_t
PyUnicode_INDEX(const char *text, Py_ssize_t index)
{
	PyObject *u;
	Py_ssize_t i;

	/* Prevent excessive micro allocations */
	char buffer[256];
	size_t buffer_size = Py_ARRAY_LENGTH(buffer);

	char *s = buffer;
	size_t l;

	/* Short-circuit */
	if (index == 0)
		return 0;

	l = strlen(text);
	if (index > l)
		index = l;
	if (index >= buffer_size) {
		s = PyMem_RawMalloc(index+1);
		if (s == NULL)
			return -1;
	}
	strncpy(s, text, index);
	s[index] = '\0';
	u = PyUnicode_DECODE(s);
	if (s != buffer)
		PyMem_RawFree(s);
	if (u == NULL)
		return -1;
	i = PyUnicode_GET_LENGTH(u);
	Py_DECREF(u);
	return i;
}