Python の文字列

PEP 393 -- Flexible String Representation | Python.org

The Unicode string type is changed to support multiple internal representations, depending on the character with the largest Unicode ordinal (1, 2, or 4 bytes).

typedef struct {
  PyObject_HEAD
  Py_ssize_t length;
  Py_hash_t hash;
  struct {
      unsigned int interned:2;
      unsigned int kind:2;
      unsigned int compact:1;
      unsigned int ascii:1;
      unsigned int ready:1;
  } state;
  wchar_t *wstr;
} PyASCIIObject;

typedef struct {
  PyASCIIObject _base;
  Py_ssize_t utf8_length;
  char *utf8;
  Py_ssize_t wstr_length;
} PyCompactUnicodeObject;

typedef struct {
  PyCompactUnicodeObject _base;
  union {
      void *any;
      Py_UCS1 *latin1;
      Py_UCS2 *ucs2;
      Py_UCS4 *ucs4;
  } data;
} PyUnicodeObject;

思ったよりややこしい管理してた・・・。