Function PyUnicode_DecodeUTF16Stateful

Lib/_pycodecs.py:1180–1296

(s, size, errors, byteorder="native", final=True)

def PyUnicode_DecodeUTF16Stateful(s, size, errors, byteorder="native", final=True):
    bo = 0  # /* assume native ordering by default */
    consumed = 0
    errmsg = ""

    if sys.byteorder == "little":
        ihi = 1
        ilo = 0
    else:
        ihi = 0
        ilo = 1

    # /* Unpack UTF-16 encoded data */

    ##    /* Check for BOM marks (U+FEFF) in the input and adjust current
    ##       byte order setting accordingly. In native mode, the leading BOM
    ##       mark is skipped, in all other modes, it is copied to the output
    ##       stream as-is (giving a ZWNBSP character). */
    q = 0
    p = []
    if byteorder == "native":
        if size >= 2:
            bom = (s[ihi] << 8) | s[ilo]
            # ifdef BYTEORDER_IS_LITTLE_ENDIAN
            if sys.byteorder == "little":
                if bom == 0xFEFF:
                    q += 2
                    bo = -1
                elif bom == 0xFFFE:
                    q += 2
                    bo = 1
            else:
                if bom == 0xFEFF:
                    q += 2
                    bo = 1
                elif bom == 0xFFFE:
                    q += 2
                    bo = -1
    elif byteorder == "little":
        bo = -1
    else:
        bo = 1

    if size == 0:
        return [""], 0, bo

    if bo == -1:
        # /* force LE */
        ihi = 1
        ilo = 0

    elif bo == 1:
        # /* force BE */
        ihi = 0
        ilo = 1

    while q < len(s):
        # /* remaining bytes at the end? (size should be even) */