класс String

static VALUE
rb_str_format_m(VALUE str, VALUE arg)
{
    VALUE tmp = rb_check_array_type(arg);

    if (!NIL_P(tmp)) {
        VALUE rv = rb_str_format(RARRAY_LENINT(tmp), RARRAY_CONST_PTR(tmp), str);
        RB_GC_GUARD(tmp);
        return rv;
    }
    return rb_str_format(1, &arg, str);
}

VALUE
rb_str_times(VALUE str, VALUE times)
{
    VALUE str2;
    long n, len;
    char *ptr2;
    int termlen;

    len = NUM2LONG(times);
    if (len < 0) {
        rb_raise(rb_eArgError, "negative argument");
    }
    if (len && LONG_MAX/len <  RSTRING_LEN(str)) {
        rb_raise(rb_eArgError, "argument too big");
    }

    len *= RSTRING_LEN(str);
    termlen = TERM_LEN(str);
    str2 = rb_str_new_with_class(str, 0, (len + termlen - 1));
    ptr2 = RSTRING_PTR(str2);
    if (len) {
        n = RSTRING_LEN(str);
        memcpy(ptr2, RSTRING_PTR(str), n);
        while (n <= len/2) {
            memcpy(ptr2 + n, ptr2, n);
            n *= 2;
        }
        memcpy(ptr2 + n, ptr2, len-n);
    }
    STR_SET_LEN(str2, len);
    TERM_FILL(&ptr2[len], termlen);
    OBJ_INFECT(str2, str);
    rb_enc_cr_str_copy_for_substr(str2, str);

    return str2;
}

VALUE
rb_str_plus(VALUE str1, VALUE str2)
{
    VALUE str3;
    rb_encoding *enc;
    char *ptr1, *ptr2, *ptr3;
    long len1, len2;
    int termlen;

    StringValue(str2);
    enc = rb_enc_check(str1, str2);
    RSTRING_GETMEM(str1, ptr1, len1);
    RSTRING_GETMEM(str2, ptr2, len2);
    termlen = rb_enc_mbminlen(enc);
    str3 = str_new0(rb_cString, 0, len1+len2, termlen);
    ptr3 = RSTRING_PTR(str3);
    memcpy(ptr3, ptr1, len1);
    memcpy(ptr3+len1, ptr2, len2);
    TERM_FILL(&ptr3[len1+len2], termlen);

    FL_SET_RAW(str3, OBJ_TAINTED_RAW(str1) | OBJ_TAINTED_RAW(str2));
    ENCODING_CODERANGE_SET(str3, rb_enc_to_index(enc),
                           ENC_CODERANGE_AND(ENC_CODERANGE(str1), ENC_CODERANGE(str2)));
    RB_GC_GUARD(str1);
    RB_GC_GUARD(str2);
    return str3;
}

VALUE
rb_str_concat(VALUE str1, VALUE str2)
{
    unsigned int code;
    rb_encoding *enc = STR_ENC_GET(str1);

    if (FIXNUM_P(str2) || RB_TYPE_P(str2, T_BIGNUM)) {
        if (rb_num_to_uint(str2, &code) == 0) {
        }
        else if (FIXNUM_P(str2)) {
            rb_raise(rb_eRangeError, "%ld out of char range", FIX2LONG(str2));
        }
        else {
            rb_raise(rb_eRangeError, "bignum out of char range");
        }
    }
    else {
        return rb_str_append(str1, str2);
    }

    if (enc == rb_usascii_encoding()) {
        /* US-ASCII automatically extended to ASCII-8BIT */
        char buf[1];
        buf[0] = (char)code;
        if (code > 0xFF) {
            rb_raise(rb_eRangeError, "%u out of char range", code);
        }
        rb_str_cat(str1, buf, 1);
        if (code > 127) {
            rb_enc_associate(str1, rb_ascii8bit_encoding());
            ENC_CODERANGE_SET(str1, ENC_CODERANGE_VALID);
        }
    }
    else {
        long pos = RSTRING_LEN(str1);
        int cr = ENC_CODERANGE(str1);
        int len;
        char *buf;

        switch (len = rb_enc_codelen(code, enc)) {
          case ONIGERR_INVALID_CODE_POINT_VALUE:
            rb_raise(rb_eRangeError, "invalid codepoint 0x%X in %s", code, rb_enc_name(enc));
            break;
          case ONIGERR_TOO_BIG_WIDE_CHAR_VALUE:
          case 0:
            rb_raise(rb_eRangeError, "%u out of char range", code);
            break;
        }
        buf = ALLOCA_N(char, len + 1);
        rb_enc_mbcput(code, buf, enc);
        if (rb_enc_precise_mbclen(buf, buf + len + 1, enc) != len) {
            rb_raise(rb_eRangeError, "invalid codepoint 0x%X in %s", code, rb_enc_name(enc));
        }
        rb_str_resize(str1, pos+len);
        memcpy(RSTRING_PTR(str1) + pos, buf, len);
        if (cr == ENC_CODERANGE_7BIT && code > 127)
            cr = ENC_CODERANGE_VALID;
        ENC_CODERANGE_SET(str1, cr);
    }
    return str1;
}

static VALUE
rb_str_cmp_m(VALUE str1, VALUE str2)
{
    int result;

    if (!RB_TYPE_P(str2, T_STRING)) {
        VALUE tmp = rb_check_funcall(str2, rb_intern("to_str"), 0, 0);
        if (RB_TYPE_P(tmp, T_STRING)) {
            result = rb_str_cmp(str1, tmp);
        }
        else {
            return rb_invcmp(str1, str2);
        }
    }
    else {
        result = rb_str_cmp(str1, str2);
    }
    return INT2FIX(result);
}

VALUE
rb_str_equal(VALUE str1, VALUE str2)
{
    if (str1 == str2) return Qtrue;
    if (!RB_TYPE_P(str2, T_STRING)) {
        if (!rb_respond_to(str2, rb_intern("to_str"))) {
            return Qfalse;
        }
        return rb_equal(str2, str1);
    }
    return str_eql(str1, str2);
}

VALUE
rb_str_equal(VALUE str1, VALUE str2)
{
    if (str1 == str2) return Qtrue;
    if (!RB_TYPE_P(str2, T_STRING)) {
        if (!rb_respond_to(str2, rb_intern("to_str"))) {
            return Qfalse;
        }
        return rb_equal(str2, str1);
    }
    return str_eql(str1, str2);
}

static VALUE
rb_str_match(VALUE x, VALUE y)
{
    if (SPECIAL_CONST_P(y)) goto generic;
    switch (BUILTIN_TYPE(y)) {
      case T_STRING:
        rb_raise(rb_eTypeError, "type mismatch: String given");

      case T_REGEXP:
        return rb_reg_match(y, x);

      generic:
      default:
        return rb_funcall(y, rb_intern("=~"), 1, x);
    }
}

static VALUE
rb_str_aref_m(int argc, VALUE *argv, VALUE str)
{
    if (argc == 2) {
        if (RB_TYPE_P(argv[0], T_REGEXP)) {
            return rb_str_subpat(str, argv[0], argv[1]);
        }
        return rb_str_substr(str, NUM2LONG(argv[0]), NUM2LONG(argv[1]));
    }
    rb_check_arity(argc, 1, 2);
    return rb_str_aref(str, argv[0]);
}

static VALUE
rb_str_aset_m(int argc, VALUE *argv, VALUE str)
{
    if (argc == 3) {
        if (RB_TYPE_P(argv[0], T_REGEXP)) {
            rb_str_subpat_set(str, argv[0], argv[1], argv[2]);
        }
        else {
            rb_str_splice(str, NUM2LONG(argv[0]), NUM2LONG(argv[1]), argv[2]);
        }
        return argv[2];
    }
    rb_check_arity(argc, 2, 3);
    return rb_str_aset(str, argv[0], argv[1]);
}

static VALUE
rb_str_is_ascii_only_p(VALUE str)
{
    int cr = rb_enc_str_coderange(str);

    return cr == ENC_CODERANGE_7BIT ? Qtrue : Qfalse;
}

static VALUE
rb_str_b(VALUE str)
{
    VALUE str2 = str_alloc(rb_cString);
    str_replace_shared_without_enc(str2, str);
    OBJ_INFECT_RAW(str2, str);
    ENC_CODERANGE_CLEAR(str2);
    return str2;
}

# File lib/scanf.rb, line 753
def block_scanf(fstr) #:yield: current_match
  fs = Scanf::FormatString.new(fstr)
  str = self.dup
  final = []
  begin
    current = str.scanf(fs)
    final.push(yield(current)) unless current.empty?
    str = fs.string_left
  end until current.empty? || str.empty?
  return final
end

static VALUE
rb_str_bytes(VALUE str)
{
    return rb_str_enumerate_bytes(str, 1);
}

static VALUE
rb_str_bytesize(VALUE str)
{
    return LONG2NUM(RSTRING_LEN(str));
}

static VALUE
rb_str_byteslice(int argc, VALUE *argv, VALUE str)
{
    if (argc == 2) {
        return str_byte_substr(str, NUM2LONG(argv[0]), NUM2LONG(argv[1]));
    }
    rb_check_arity(argc, 1, 2);
    return str_byte_aref(str, argv[0]);
}

static VALUE
rb_str_capitalize(VALUE str)
{
    str = rb_str_dup(str);
    rb_str_capitalize_bang(str);
    return str;
}

static VALUE
rb_str_capitalize_bang(VALUE str)
{
    rb_encoding *enc;
    char *s, *send;
    int modify = 0;
    unsigned int c;
    int n;

    str_modify_keep_cr(str);
    enc = STR_ENC_GET(str);
    rb_str_check_dummy_enc(enc);
    if (RSTRING_LEN(str) == 0 || !RSTRING_PTR(str)) return Qnil;
    s = RSTRING_PTR(str); send = RSTRING_END(str);

    c = rb_enc_codepoint_len(s, send, &n, enc);
    if (rb_enc_islower(c, enc)) {
        rb_enc_mbcput(rb_enc_toupper(c, enc), s, enc);
        modify = 1;
    }
    s += n;
    while (s < send) {
        c = rb_enc_codepoint_len(s, send, &n, enc);
        if (rb_enc_isupper(c, enc)) {
            rb_enc_mbcput(rb_enc_tolower(c, enc), s, enc);
            modify = 1;
        }
        s += n;
    }

    if (modify) return str;
    return Qnil;
}

static VALUE
rb_str_casecmp(VALUE str1, VALUE str2)
{
    long len;
    rb_encoding *enc;
    char *p1, *p1end, *p2, *p2end;

    StringValue(str2);
    enc = rb_enc_compatible(str1, str2);
    if (!enc) {
        return Qnil;
    }

    p1 = RSTRING_PTR(str1); p1end = RSTRING_END(str1);
    p2 = RSTRING_PTR(str2); p2end = RSTRING_END(str2);
    if (single_byte_optimizable(str1) && single_byte_optimizable(str2)) {
        while (p1 < p1end && p2 < p2end) {
            if (*p1 != *p2) {
                unsigned int c1 = TOUPPER(*p1 & 0xff);
                unsigned int c2 = TOUPPER(*p2 & 0xff);
                if (c1 != c2)
                    return INT2FIX(c1 < c2 ? -1 : 1);
            }
            p1++;
            p2++;
        }
    }
    else {
        while (p1 < p1end && p2 < p2end) {
            int l1, c1 = rb_enc_ascget(p1, p1end, &l1, enc);
            int l2, c2 = rb_enc_ascget(p2, p2end, &l2, enc);

            if (0 <= c1 && 0 <= c2) {
                c1 = TOUPPER(c1);
                c2 = TOUPPER(c2);
                if (c1 != c2)
                    return INT2FIX(c1 < c2 ? -1 : 1);
            }
            else {
                int r;
                l1 = rb_enc_mbclen(p1, p1end, enc);
                l2 = rb_enc_mbclen(p2, p2end, enc);
                len = l1 < l2 ? l1 : l2;
                r = memcmp(p1, p2, len);
                if (r != 0)
                    return INT2FIX(r < 0 ? -1 : 1);
                if (l1 != l2)
                    return INT2FIX(l1 < l2 ? -1 : 1);
            }
            p1 += l1;
            p2 += l2;
        }
    }
    if (RSTRING_LEN(str1) == RSTRING_LEN(str2)) return INT2FIX(0);
    if (RSTRING_LEN(str1) > RSTRING_LEN(str2)) return INT2FIX(1);
    return INT2FIX(-1);
}

static VALUE
rb_str_crypt(VALUE str, VALUE salt)
{
    extern char *crypt(const char *, const char *);
    VALUE result;
    const char *s, *saltp;
    char *res;
#ifdef BROKEN_CRYPT
    char salt_8bit_clean[3];
#endif

    StringValue(salt);
    mustnot_wchar(str);
    mustnot_wchar(salt);
    if (RSTRING_LEN(salt) < 2) {
      short_salt:
        rb_raise(rb_eArgError, "salt too short (need >=2 bytes)");
    }

    s = RSTRING_PTR(str);
    if (!s) s = "";
    saltp = RSTRING_PTR(salt);
    if (!saltp[0] || !saltp[1]) goto short_salt;
#ifdef BROKEN_CRYPT
    if (!ISASCII((unsigned char)saltp[0]) || !ISASCII((unsigned char)saltp[1])) {
        salt_8bit_clean[0] = saltp[0] & 0x7f;
        salt_8bit_clean[1] = saltp[1] & 0x7f;
        salt_8bit_clean[2] = '\0';
        saltp = salt_8bit_clean;
    }
#endif
    res = crypt(s, saltp);
    if (!res) {
        rb_sys_fail("crypt");
    }
    result = rb_str_new_cstr(res);
    FL_SET_RAW(result, OBJ_TAINTED_RAW(str) | OBJ_TAINTED_RAW(salt));
    return result;
}

static VALUE
rb_str_delete(int argc, VALUE *argv, VALUE str)
{
    str = rb_str_dup(str);
    rb_str_delete_bang(argc, argv, str);
    return str;
}

static VALUE
rb_str_delete_bang(int argc, VALUE *argv, VALUE str)
{
    char squeez[TR_TABLE_SIZE];
    rb_encoding *enc = 0;
    char *s, *send, *t;
    VALUE del = 0, nodel = 0;
    int modify = 0;
    int i, ascompat, cr;

    if (RSTRING_LEN(str) == 0 || !RSTRING_PTR(str)) return Qnil;
    rb_check_arity(argc, 1, UNLIMITED_ARGUMENTS);
    for (i=0; i<argc; i++) {
        VALUE s = argv[i];

        StringValue(s);
        enc = rb_enc_check(str, s);
        tr_setup_table(s, squeez, i==0, &del, &nodel, enc);
    }

    str_modify_keep_cr(str);
    ascompat = rb_enc_asciicompat(enc);
    s = t = RSTRING_PTR(str);
    send = RSTRING_END(str);
    cr = ascompat ? ENC_CODERANGE_7BIT : ENC_CODERANGE_VALID;
    while (s < send) {
        unsigned int c;
        int clen;

        if (ascompat && (c = *(unsigned char*)s) < 0x80) {
            if (squeez[c]) {
                modify = 1;
            }
            else {
                if (t != s) *t = c;
                t++;
            }
            s++;
        }
        else {
            c = rb_enc_codepoint_len(s, send, &clen, enc);

            if (tr_find(c, squeez, del, nodel)) {
                modify = 1;
            }
            else {
                if (t != s) rb_enc_mbcput(c, t, enc);
                t += clen;
                if (cr == ENC_CODERANGE_7BIT) cr = ENC_CODERANGE_VALID;
            }
            s += clen;
        }
    }
    TERM_FILL(t, TERM_LEN(str));
    STR_SET_LEN(str, t - RSTRING_PTR(str));
    ENC_CODERANGE_SET(str, cr);

    if (modify) return str;
    return Qnil;
}

static VALUE
rb_str_downcase(VALUE str)
{
    str = rb_str_dup(str);
    rb_str_downcase_bang(str);
    return str;
}

static VALUE
rb_str_downcase_bang(VALUE str)
{
    rb_encoding *enc;
    char *s, *send;
    int modify = 0;

    str_modify_keep_cr(str);
    enc = STR_ENC_GET(str);
    rb_str_check_dummy_enc(enc);
    s = RSTRING_PTR(str); send = RSTRING_END(str);
    if (single_byte_optimizable(str)) {
        while (s < send) {
            unsigned int c = *(unsigned char*)s;

            if (rb_enc_isascii(c, enc) && 'A' <= c && c <= 'Z') {
                *s = 'a' + (c - 'A');
                modify = 1;
            }
            s++;
        }
    }
    else {
        int ascompat = rb_enc_asciicompat(enc);

        while (s < send) {
            unsigned int c;
            int n;

            if (ascompat && (c = *(unsigned char*)s) < 0x80) {
                if (rb_enc_isascii(c, enc) && 'A' <= c && c <= 'Z') {
                    *s = 'a' + (c - 'A');
                    modify = 1;
                }
                s++;
            }
            else {
                c = rb_enc_codepoint_len(s, send, &n, enc);
                if (rb_enc_isupper(c, enc)) {
                    /* assuming toupper returns codepoint with same size */
                    rb_enc_mbcput(rb_enc_tolower(c, enc), s, enc);
                    modify = 1;
                }
                s += n;
            }
        }
    }

    if (modify) return str;
    return Qnil;
}

VALUE
rb_str_dump(VALUE str)
{
    rb_encoding *enc = rb_enc_get(str);
    long len;
    const char *p, *pend;
    char *q, *qend;
    VALUE result;
    int u8 = (enc == rb_utf8_encoding());

    len = 2;                    /* "" */
    p = RSTRING_PTR(str); pend = p + RSTRING_LEN(str);
    while (p < pend) {
        unsigned char c = *p++;
        switch (c) {
          case '"':  case '\\':
          case '\n': case '\r':
          case '\t': case '\f':
          case '\013': case '\010': case '\007': case '\033':
            len += 2;
            break;

          case '#':
            len += IS_EVSTR(p, pend) ? 2 : 1;
            break;

          default:
            if (ISPRINT(c)) {
                len++;
            }
            else {
                if (u8 && c > 0x7F) { /* \u{NN} */
                    int n = rb_enc_precise_mbclen(p-1, pend, enc);
                    if (MBCLEN_CHARFOUND_P(n)) {
                        unsigned int cc = rb_enc_mbc_to_codepoint(p-1, pend, enc);
                        while (cc >>= 4) len++;
                        len += 5;
                        p += MBCLEN_CHARFOUND_LEN(n)-1;
                        break;
                    }
                }
                len += 4;     /* \xNN */
            }
            break;
        }
    }
    if (!rb_enc_asciicompat(enc)) {
        len += 19;             /* ".force_encoding('')" */
        len += strlen(enc->name);
    }

    result = rb_str_new_with_class(str, 0, len);
    p = RSTRING_PTR(str); pend = p + RSTRING_LEN(str);
    q = RSTRING_PTR(result); qend = q + len + 1;

    *q++ = '"';
    while (p < pend) {
        unsigned char c = *p++;

        if (c == '"' || c == '\\') {
            *q++ = '\\';
            *q++ = c;
        }
        else if (c == '#') {
            if (IS_EVSTR(p, pend)) *q++ = '\\';
            *q++ = '#';
        }
        else if (c == '\n') {
            *q++ = '\\';
            *q++ = 'n';
        }
        else if (c == '\r') {
            *q++ = '\\';
            *q++ = 'r';
        }
        else if (c == '\t') {
            *q++ = '\\';
            *q++ = 't';
        }
        else if (c == '\f') {
            *q++ = '\\';
            *q++ = 'f';
        }
        else if (c == '\013') {
            *q++ = '\\';
            *q++ = 'v';
        }
        else if (c == '\010') {
            *q++ = '\\';
            *q++ = 'b';
        }
        else if (c == '\007') {
            *q++ = '\\';
            *q++ = 'a';
        }
        else if (c == '\033') {
            *q++ = '\\';
            *q++ = 'e';
        }
        else if (ISPRINT(c)) {
            *q++ = c;
        }
        else {
            *q++ = '\\';
            if (u8) {
                int n = rb_enc_precise_mbclen(p-1, pend, enc) - 1;
                if (MBCLEN_CHARFOUND_P(n)) {
                    int cc = rb_enc_mbc_to_codepoint(p-1, pend, enc);
                    p += n;
                    snprintf(q, qend-q, "u{%x}", cc);
                    q += strlen(q);
                    continue;
                }
            }
            snprintf(q, qend-q, "x%02X", c);
            q += 3;
        }
    }
    *q++ = '"';
    *q = '\0';
    if (!rb_enc_asciicompat(enc)) {
        snprintf(q, qend-q, ".force_encoding(\"%s\")", enc->name);
        enc = rb_ascii8bit_encoding();
    }
    OBJ_INFECT_RAW(result, str);
    /* result from dump is ASCII */
    rb_enc_associate(result, enc);
    ENC_CODERANGE_SET(result, ENC_CODERANGE_7BIT);
    return result;
}

static VALUE
rb_str_each_byte(VALUE str)
{
    return rb_str_enumerate_bytes(str, 0);
}

static VALUE
rb_str_each_char(VALUE str)
{
    return rb_str_enumerate_chars(str, 0);
}

static VALUE
rb_str_each_codepoint(VALUE str)
{
    return rb_str_enumerate_codepoints(str, 0);
}

static VALUE
rb_str_each_line(int argc, VALUE *argv, VALUE str)
{
    return rb_str_enumerate_lines(argc, argv, str, 0);
}

static VALUE
rb_str_empty(VALUE str)
{
    if (RSTRING_LEN(str) == 0)
        return Qtrue;
    return Qfalse;
}

static VALUE
str_encode(int argc, VALUE *argv, VALUE str)
{
    VALUE newstr = str;
    int encidx = str_transcode(argc, argv, &newstr);
    return encoded_dup(newstr, str, encidx);
}

static VALUE
str_encode_bang(int argc, VALUE *argv, VALUE str)
{
    VALUE newstr;
    int encidx;

    rb_check_frozen(str);

    newstr = str;
    encidx = str_transcode(argc, argv, &newstr);

    if (encidx < 0) return str;
    if (newstr == str) {
        rb_enc_associate_index(str, encidx);
        return str;
    }
    rb_str_shared_replace(str, newstr);
    return str_encode_associate(str, encidx);
}

VALUE
rb_obj_encoding(VALUE obj)
{
    int idx = rb_enc_get_index(obj);
    if (idx < 0) {
	rb_raise(rb_eTypeError, "unknown encoding");
    }
    return rb_enc_from_encoding_index(idx & ENC_INDEX_MASK);
}

static VALUE
rb_str_end_with(int argc, VALUE *argv, VALUE str)
{
    int i;
    char *p, *s, *e;
    rb_encoding *enc;

    for (i=0; i<argc; i++) {
        VALUE tmp = argv[i];
        StringValue(tmp);
        enc = rb_enc_check(str, tmp);
        if (RSTRING_LEN(str) < RSTRING_LEN(tmp)) continue;
        p = RSTRING_PTR(str);
        e = p + RSTRING_LEN(str);
        s = e - RSTRING_LEN(tmp);
        if (rb_enc_left_char_head(p, s, e, enc) != s)
            continue;
        if (memcmp(s, RSTRING_PTR(tmp), RSTRING_LEN(tmp)) == 0)
            return Qtrue;
    }
    return Qfalse;
}

static VALUE
rb_str_eql(VALUE str1, VALUE str2)
{
    if (str1 == str2) return Qtrue;
    if (!RB_TYPE_P(str2, T_STRING)) return Qfalse;
    return str_eql(str1, str2);
}

static VALUE
rb_str_force_encoding(VALUE str, VALUE enc)
{
    str_modifiable(str);
    rb_enc_associate(str, rb_to_encoding(enc));
    ENC_CODERANGE_CLEAR(str);
    return str;
}

static VALUE
rb_str_getbyte(VALUE str, VALUE index)
{
    long pos = NUM2LONG(index);

    if (pos < 0)
        pos += RSTRING_LEN(str);
    if (pos < 0 ||  RSTRING_LEN(str) <= pos)
        return Qnil;

    return INT2FIX((unsigned char)RSTRING_PTR(str)[pos]);
}

static VALUE
rb_str_gsub(int argc, VALUE *argv, VALUE str)
{
    return str_gsub(argc, argv, str, 0);
}

static VALUE
rb_str_gsub_bang(int argc, VALUE *argv, VALUE str)
{
    str_modify_keep_cr(str);
    return str_gsub(argc, argv, str, 1);
}

static VALUE
rb_str_lstrip_bang(VALUE str)
{
    rb_encoding *enc;
    char *start, *s;
    long olen, loffset;

    str_modify_keep_cr(str);
    enc = STR_ENC_GET(str);
    RSTRING_GETMEM(str, start, olen);
    loffset = lstrip_offset(str, start, start+olen, enc);
    if (loffset > 0) {
        long len = olen-loffset;
        s = start + loffset;
        memmove(start, s, len);
        STR_SET_LEN(str, len);
#if !SHARABLE_MIDDLE_SUBSTRING
        TERM_FILL(start+len, rb_enc_mbminlen(enc));
#endif
        return str;
    }
    return Qnil;
}

static VALUE
rb_str_match_m(int argc, VALUE *argv, VALUE str)
{
    VALUE re, result;
    if (argc < 1)
        rb_check_arity(argc, 1, 2);
    re = argv[0];
    argv[0] = str;
    result = rb_funcall2(get_pat(re), rb_intern("match"), argc, argv);
    if (!NIL_P(result) && rb_block_given_p()) {
        return rb_yield(result);
    }
    return result;
}

VALUE
rb_str_succ(VALUE orig)
{
    VALUE str;
    str = rb_str_new_with_class(orig, RSTRING_PTR(orig), RSTRING_LEN(orig));
    rb_enc_cr_str_copy_for_substr(str, orig);
    OBJ_INFECT(str, orig);
    return str_succ(str);
}

static VALUE
rb_str_succ_bang(VALUE str)
{
    rb_str_modify(str);
    str_succ(str);
    return str;
}

static VALUE
rb_str_oct(VALUE str)
{
    return rb_str_to_inum(str, -8, FALSE);
}

VALUE
rb_str_ord(VALUE s)
{
    unsigned int c;

    c = rb_enc_codepoint(RSTRING_PTR(s), RSTRING_END(s), STR_ENC_GET(s));
    return UINT2NUM(c);
}

static VALUE
rb_str_partition(VALUE str, VALUE sep)
{
    long pos;

    sep = get_pat_quoted(sep, 0);
    if (RB_TYPE_P(sep, T_REGEXP)) {
        pos = rb_reg_search(sep, str, 0, 0);
        if (pos < 0) {
          failed:
            return rb_ary_new3(3, str, str_new_empty(str), str_new_empty(str));
        }
        sep = rb_str_subpat(str, sep, INT2FIX(0));
        if (pos == 0 && RSTRING_LEN(sep) == 0) goto failed;
    }
    else {
        pos = rb_str_index(str, sep, 0);
        if (pos < 0) goto failed;
    }
    return rb_ary_new3(3, rb_str_subseq(str, 0, pos),
                          sep,
                          rb_str_subseq(str, pos+RSTRING_LEN(sep),
                                             RSTRING_LEN(str)-pos-RSTRING_LEN(sep)));
}

static VALUE
rb_str_prepend(VALUE str, VALUE str2)
{
    StringValue(str2);
    StringValue(str);
    rb_str_update(str, 0L, 0L, str2);
    return str;
}

static VALUE
str_scrub_bang(int argc, VALUE *argv, VALUE str)
{
    VALUE repl = argc ? (rb_check_arity(argc, 0, 1), argv[0]) : Qnil;
    VALUE new = rb_str_scrub(str, repl);
    if (!NIL_P(new)) rb_str_replace(str, new);
    return str;
}

static VALUE
rb_str_setbyte(VALUE str, VALUE index, VALUE value)
{
    long pos = NUM2LONG(index);
    int byte = NUM2INT(value);

    rb_str_modify(str);

    if (pos < -RSTRING_LEN(str) || RSTRING_LEN(str) <= pos)
        rb_raise(rb_eIndexError, "index %ld out of string", pos);
    if (pos < 0)
        pos += RSTRING_LEN(str);

    RSTRING_PTR(str)[pos] = byte;

    return value;
}

# File lib/shellwords.rb, line 199
def shellescape
  Shellwords.escape(self)
end

# File lib/shellwords.rb, line 188
def shellsplit
  Shellwords.split(self)
end

VALUE
rb_str_length(VALUE str)
{
    return LONG2NUM(str_strlen(str, NULL));
}

static VALUE
rb_str_aref_m(int argc, VALUE *argv, VALUE str)
{
    if (argc == 2) {
        if (RB_TYPE_P(argv[0], T_REGEXP)) {
            return rb_str_subpat(str, argv[0], argv[1]);
        }
        return rb_str_substr(str, NUM2LONG(argv[0]), NUM2LONG(argv[1]));
    }
    rb_check_arity(argc, 1, 2);
    return rb_str_aref(str, argv[0]);
}

static VALUE
rb_str_slice_bang(int argc, VALUE *argv, VALUE str)
{
    VALUE result;
    VALUE buf[3];
    int i;

    rb_check_arity(argc, 1, 2);
    for (i=0; i<argc; i++) {
        buf[i] = argv[i];
    }
    str_modify_keep_cr(str);
    result = rb_str_aref_m(argc, buf, str);
    if (!NIL_P(result)) {
        buf[i] = rb_str_new(0,0);
        rb_str_aset_m(argc+1, buf, str);
    }
    return result;
}

static VALUE
rb_str_split_m(int argc, VALUE *argv, VALUE str)
{
    rb_encoding *enc;
    VALUE spat;
    VALUE limit;
    enum {awk, string, regexp} split_type;
    long beg, end, i = 0;
    int lim = 0;
    VALUE result, tmp;

    if (rb_scan_args(argc, argv, "02", &spat, &limit) == 2) {
        lim = NUM2INT(limit);
        if (lim <= 0) limit = Qnil;
        else if (lim == 1) {
            if (RSTRING_LEN(str) == 0)
                return rb_ary_new2(0);
            return rb_ary_new3(1, str);
        }
        i = 1;
    }

    enc = STR_ENC_GET(str);
    if (NIL_P(spat) && NIL_P(spat = rb_fs)) {
        split_type = awk;
    }
    else {
        spat = get_pat_quoted(spat, 0);
        if (BUILTIN_TYPE(spat) == T_STRING) {
            rb_encoding *enc2 = STR_ENC_GET(spat);

            mustnot_broken(spat);
            split_type = string;
            if (RSTRING_LEN(spat) == 0) {
                /* Special case - split into chars */
                spat = rb_reg_regcomp(spat);
                split_type = regexp;
            }
            else if (rb_enc_asciicompat(enc2) == 1) {
                if (RSTRING_LEN(spat) == 1 && RSTRING_PTR(spat)[0] == ' '){
                    split_type = awk;
                }
            }
            else {
                int l;
                if (rb_enc_ascget(RSTRING_PTR(spat), RSTRING_END(spat), &l, enc2) == ' ' &&
                    RSTRING_LEN(spat) == l) {
                    split_type = awk;
                }
            }
        }
        else {
            split_type = regexp;
        }
    }

    result = rb_ary_new();
    beg = 0;
    if (split_type == awk) {
        char *ptr = RSTRING_PTR(str);
        char *eptr = RSTRING_END(str);
        char *bptr = ptr;
        int skip = 1;
        unsigned int c;

        end = beg;
        if (is_ascii_string(str)) {
            while (ptr < eptr) {
                c = (unsigned char)*ptr++;
                if (skip) {
                    if (ascii_isspace(c)) {
                        beg = ptr - bptr;
                    }
                    else {
                        end = ptr - bptr;
                        skip = 0;
                        if (!NIL_P(limit) && lim <= i) break;
                    }
                }
                else if (ascii_isspace(c)) {
                    rb_ary_push(result, rb_str_subseq(str, beg, end-beg));
                    skip = 1;
                    beg = ptr - bptr;
                    if (!NIL_P(limit)) ++i;
                }
                else {
                    end = ptr - bptr;
                }
            }
        }
        else {
            while (ptr < eptr) {
                int n;

                c = rb_enc_codepoint_len(ptr, eptr, &n, enc);
                ptr += n;
                if (skip) {
                    if (rb_isspace(c)) {
                        beg = ptr - bptr;
                    }
                    else {
                        end = ptr - bptr;
                        skip = 0;
                        if (!NIL_P(limit) && lim <= i) break;
                    }
                }
                else if (rb_isspace(c)) {
                    rb_ary_push(result, rb_str_subseq(str, beg, end-beg));
                    skip = 1;
                    beg = ptr - bptr;
                    if (!NIL_P(limit)) ++i;
                }
                else {
                    end = ptr - bptr;
                }
            }
        }
    }
    else if (split_type == string) {
        char *ptr = RSTRING_PTR(str);
        char *temp = ptr;
        char *eptr = RSTRING_END(str);
        char *sptr = RSTRING_PTR(spat);
        long slen = RSTRING_LEN(spat);

        mustnot_broken(str);
        enc = rb_enc_check(str, spat);
        while (ptr < eptr &&
               (end = rb_memsearch(sptr, slen, ptr, eptr - ptr, enc)) >= 0) {
            /* Check we are at the start of a char */
            char *t = rb_enc_right_char_head(ptr, ptr + end, eptr, enc);
            if (t != ptr + end) {
                ptr = t;
                continue;
            }
            rb_ary_push(result, rb_str_subseq(str, ptr - temp, end));
            ptr += end + slen;
            if (!NIL_P(limit) && lim <= ++i) break;
        }
        beg = ptr - temp;
    }
    else {
        char *ptr = RSTRING_PTR(str);
        long len = RSTRING_LEN(str);
        long start = beg;
        long idx;
        int last_null = 0;
        struct re_registers *regs;

        while ((end = rb_reg_search(spat, str, start, 0)) >= 0) {
            regs = RMATCH_REGS(rb_backref_get());
            if (start == end && BEG(0) == END(0)) {
                if (!ptr) {
                    rb_ary_push(result, str_new_empty(str));
                    break;
                }
                else if (last_null == 1) {
                    rb_ary_push(result, rb_str_subseq(str, beg,
                                                      rb_enc_fast_mbclen(ptr+beg,
                                                                         ptr+len,
                                                                         enc)));
                    beg = start;
                }
                else {
                    if (start == len)
                        start++;
                    else
                        start += rb_enc_fast_mbclen(ptr+start,ptr+len,enc);
                    last_null = 1;
                    continue;
                }
            }
            else {
                rb_ary_push(result, rb_str_subseq(str, beg, end-beg));
                beg = start = END(0);
            }
            last_null = 0;

            for (idx=1; idx < regs->num_regs; idx++) {
                if (BEG(idx) == -1) continue;
                if (BEG(idx) == END(idx))
                    tmp = str_new_empty(str);
                else
                    tmp = rb_str_subseq(str, BEG(idx), END(idx)-BEG(idx));
                rb_ary_push(result, tmp);
            }
            if (!NIL_P(limit) && lim <= ++i) break;
        }
    }
    if (RSTRING_LEN(str) > 0 && (!NIL_P(limit) || RSTRING_LEN(str) > beg || lim < 0)) {
        if (RSTRING_LEN(str) == beg)
            tmp = str_new_empty(str);
        else
            tmp = rb_str_subseq(str, beg, RSTRING_LEN(str)-beg);
        rb_ary_push(result, tmp);
    }
    if (NIL_P(limit) && lim == 0) {
        long len;
        while ((len = RARRAY_LEN(result)) > 0 &&
               (tmp = RARRAY_AREF(result, len-1), RSTRING_LEN(tmp) == 0))
            rb_ary_pop(result);
    }

    return result;
}

static VALUE
rb_str_squeeze(int argc, VALUE *argv, VALUE str)
{
    str = rb_str_dup(str);
    rb_str_squeeze_bang(argc, argv, str);
    return str;
}

static VALUE
rb_str_squeeze_bang(int argc, VALUE *argv, VALUE str)
{
    char squeez[TR_TABLE_SIZE];
    rb_encoding *enc = 0;
    VALUE del = 0, nodel = 0;
    char *s, *send, *t;
    int i, modify = 0;
    int ascompat, singlebyte = single_byte_optimizable(str);
    unsigned int save;

    if (argc == 0) {
        enc = STR_ENC_GET(str);
    }
    else {
        for (i=0; i<argc; i++) {
            VALUE s = argv[i];

            StringValue(s);
            enc = rb_enc_check(str, s);
            if (singlebyte && !single_byte_optimizable(s))
                singlebyte = 0;
            tr_setup_table(s, squeez, i==0, &del, &nodel, enc);
        }
    }

    str_modify_keep_cr(str);
    s = t = RSTRING_PTR(str);
    if (!s || RSTRING_LEN(str) == 0) return Qnil;
    send = RSTRING_END(str);
    save = -1;
    ascompat = rb_enc_asciicompat(enc);

    if (singlebyte) {
        while (s < send) {
            unsigned int c = *(unsigned char*)s++;
            if (c != save || (argc > 0 && !squeez[c])) {
                *t++ = save = c;
            }
        }
    }
    else {
        while (s < send) {
            unsigned int c;
            int clen;

            if (ascompat && (c = *(unsigned char*)s) < 0x80) {
                if (c != save || (argc > 0 && !squeez[c])) {
                    *t++ = save = c;
                }
                s++;
            }
            else {
                c = rb_enc_codepoint_len(s, send, &clen, enc);

                if (c != save || (argc > 0 && !tr_find(c, squeez, del, nodel))) {
                    if (t != s) rb_enc_mbcput(c, t, enc);
                    save = c;
                    t += clen;
                }
                s += clen;
            }
        }
    }

    TERM_FILL(t, TERM_LEN(str));
    if (t - RSTRING_PTR(str) != RSTRING_LEN(str)) {
        STR_SET_LEN(str, t - RSTRING_PTR(str));
        modify = 1;
    }

    if (modify) return str;
    return Qnil;
}

static VALUE
rb_str_start_with(int argc, VALUE *argv, VALUE str)
{
    int i;

    for (i=0; i<argc; i++) {
        VALUE tmp = argv[i];
        StringValue(tmp);
        rb_enc_check(str, tmp);
        if (RSTRING_LEN(str) < RSTRING_LEN(tmp)) continue;
        if (memcmp(RSTRING_PTR(str), RSTRING_PTR(tmp), RSTRING_LEN(tmp)) == 0)
            return Qtrue;
    }
    return Qfalse;
}

static VALUE
rb_str_strip(VALUE str)
{
    char *start;
    long olen, loffset, roffset;
    rb_encoding *enc = STR_ENC_GET(str);

    RSTRING_GETMEM(str, start, olen);
    loffset = lstrip_offset(str, start, start+olen, enc);
    roffset = rstrip_offset(str, start+loffset, start+olen, enc);

    if (loffset <= 0 && roffset <= 0) return rb_str_dup(str);
    return rb_str_subseq(str, loffset, olen-loffset-roffset);
}

static VALUE
rb_str_strip_bang(VALUE str)
{
    char *start;
    long olen, loffset, roffset;
    rb_encoding *enc;

    str_modify_keep_cr(str);
    enc = STR_ENC_GET(str);
    RSTRING_GETMEM(str, start, olen);
    loffset = lstrip_offset(str, start, start+olen, enc);
    roffset = rstrip_offset(str, start+loffset, start+olen, enc);

    if (loffset > 0 || roffset > 0) {
        long len = olen-roffset;
        if (loffset > 0) {
            len -= loffset;
            memmove(start, start + loffset, len);
        }
        STR_SET_LEN(str, len);
#if !SHARABLE_MIDDLE_SUBSTRING
        TERM_FILL(start+len, rb_enc_mbminlen(enc));
#endif
        return str;
    }
    return Qnil;
}

static VALUE
rb_str_sub(int argc, VALUE *argv, VALUE str)
{
    str = rb_str_dup(str);
    rb_str_sub_bang(argc, argv, str);
    return str;
}

static VALUE
rb_str_sub_bang(int argc, VALUE *argv, VALUE str)
{
    VALUE pat, repl, hash = Qnil;
    int iter = 0;
    int tainted = 0;
    long plen;
    int min_arity = rb_block_given_p() ? 1 : 2;
    long beg;

    rb_check_arity(argc, min_arity, 2);
    if (argc == 1) {
        iter = 1;
    }
    else {
        repl = argv[1];
        hash = rb_check_hash_type(argv[1]);
        if (NIL_P(hash)) {
            StringValue(repl);
        }
        tainted = OBJ_TAINTED_RAW(repl);
    }

    pat = get_pat_quoted(argv[0], 1);

    str_modifiable(str);
    beg = rb_pat_search(pat, str, 0, 1);
    if (beg >= 0) {
        rb_encoding *enc;
        int cr = ENC_CODERANGE(str);
        long beg0, end0;
        VALUE match, match0 = Qnil;
        struct re_registers *regs;
        char *p, *rp;
        long len, rlen;

        match = rb_backref_get();
        regs = RMATCH_REGS(match);
        if (RB_TYPE_P(pat, T_STRING)) {
            beg0 = beg;
            end0 = beg0 + RSTRING_LEN(pat);
            match0 = pat;
        }
        else {
            beg0 = BEG(0);
            end0 = END(0);
            if (iter) match0 = rb_reg_nth_match(0, match);
        }

        if (iter || !NIL_P(hash)) {
            p = RSTRING_PTR(str); len = RSTRING_LEN(str);

            if (iter) {
                repl = rb_obj_as_string(rb_yield(match0));
            }
            else {
                repl = rb_hash_aref(hash, rb_str_subseq(str, beg0, end0 - beg0));
                repl = rb_obj_as_string(repl);
            }
            str_mod_check(str, p, len);
            rb_check_frozen(str);
        }
        else {
            repl = rb_reg_regsub(repl, str, regs, RB_TYPE_P(pat, T_STRING) ? Qnil : pat);
        }

        enc = rb_enc_compatible(str, repl);
        if (!enc) {
            rb_encoding *str_enc = STR_ENC_GET(str);
            p = RSTRING_PTR(str); len = RSTRING_LEN(str);
            if (coderange_scan(p, beg0, str_enc) != ENC_CODERANGE_7BIT ||
                coderange_scan(p+end0, len-end0, str_enc) != ENC_CODERANGE_7BIT) {
                rb_raise(rb_eEncCompatError, "incompatible character encodings: %s and %s",
                         rb_enc_name(str_enc),
                         rb_enc_name(STR_ENC_GET(repl)));
            }
            enc = STR_ENC_GET(repl);
        }
        rb_str_modify(str);
        rb_enc_associate(str, enc);
        tainted |= OBJ_TAINTED_RAW(repl);
        if (ENC_CODERANGE_UNKNOWN < cr && cr < ENC_CODERANGE_BROKEN) {
            int cr2 = ENC_CODERANGE(repl);
            if (cr2 == ENC_CODERANGE_BROKEN ||
                (cr == ENC_CODERANGE_VALID && cr2 == ENC_CODERANGE_7BIT))
                cr = ENC_CODERANGE_UNKNOWN;
            else
                cr = cr2;
        }
        plen = end0 - beg0;
        rp = RSTRING_PTR(repl); rlen = RSTRING_LEN(repl);
        len = RSTRING_LEN(str);
        if (rlen > plen) {
            RESIZE_CAPA(str, len + rlen - plen);
        }
        p = RSTRING_PTR(str);
        if (rlen != plen) {
            memmove(p + beg0 + rlen, p + beg0 + plen, len - beg0 - plen);
        }
        memcpy(p + beg0, rp, rlen);
        len += rlen - plen;
        STR_SET_LEN(str, len);
        TERM_FILL(&RSTRING_PTR(str)[len], TERM_LEN(str));
        ENC_CODERANGE_SET(str, cr);
        FL_SET_RAW(str, tainted);

        return str;
    }
    return Qnil;
}

VALUE
rb_str_succ(VALUE orig)
{
    VALUE str;
    str = rb_str_new_with_class(orig, RSTRING_PTR(orig), RSTRING_LEN(orig));
    rb_enc_cr_str_copy_for_substr(str, orig);
    OBJ_INFECT(str, orig);
    return str_succ(str);
}

static VALUE
rb_str_succ_bang(VALUE str)
{
    rb_str_modify(str);
    str_succ(str);
    return str;
}

static VALUE
rb_str_sum(int argc, VALUE *argv, VALUE str)
{
    VALUE vbits;
    int bits;
    char *ptr, *p, *pend;
    long len;
    VALUE sum = INT2FIX(0);
    unsigned long sum0 = 0;

    if (argc == 0) {
        bits = 16;
    }
    else {
        rb_scan_args(argc, argv, "01", &vbits);
        bits = NUM2INT(vbits);
        if (bits < 0)
            bits = 0;
    }
    ptr = p = RSTRING_PTR(str);
    len = RSTRING_LEN(str);
    pend = p + len;

    while (p < pend) {
        if (FIXNUM_MAX - UCHAR_MAX < sum0) {
            sum = rb_funcall(sum, '+', 1, LONG2FIX(sum0));
            str_mod_check(str, ptr, len);
            sum0 = 0;
        }
        sum0 += (unsigned char)*p;
        p++;
    }

    if (bits == 0) {
        if (sum0) {
            sum = rb_funcall(sum, '+', 1, LONG2FIX(sum0));
        }
    }
    else {
        if (sum == INT2FIX(0)) {
            if (bits < (int)sizeof(long)*CHAR_BIT) {
                sum0 &= (((unsigned long)1)<<bits)-1;
            }
            sum = LONG2FIX(sum0);
        }
        else {
            VALUE mod;

            if (sum0) {
                sum = rb_funcall(sum, '+', 1, LONG2FIX(sum0));
            }

            mod = rb_funcall(INT2FIX(1), rb_intern("<<"), 1, INT2FIX(bits));
            mod = rb_funcall(mod, '-', 1, INT2FIX(1));
            sum = rb_funcall(sum, '&', 1, mod);
        }
    }
    return sum;
}

static VALUE
rb_str_swapcase(VALUE str)
{
    str = rb_str_dup(str);
    rb_str_swapcase_bang(str);
    return str;
}

static VALUE
rb_str_swapcase_bang(VALUE str)
{
    rb_encoding *enc;
    char *s, *send;
    int modify = 0;
    int n;

    str_modify_keep_cr(str);
    enc = STR_ENC_GET(str);
    rb_str_check_dummy_enc(enc);
    s = RSTRING_PTR(str); send = RSTRING_END(str);
    while (s < send) {
        unsigned int c = rb_enc_codepoint_len(s, send, &n, enc);

        if (rb_enc_isupper(c, enc)) {
            /* assuming toupper returns codepoint with same size */
            rb_enc_mbcput(rb_enc_tolower(c, enc), s, enc);
            modify = 1;
        }
        else if (rb_enc_islower(c, enc)) {
            /* assuming tolower returns codepoint with same size */
            rb_enc_mbcput(rb_enc_toupper(c, enc), s, enc);
            modify = 1;
        }
        s += n;
    }

    if (modify) return str;
    return Qnil;
}

static VALUE
rb_str_tr_s(VALUE str, VALUE src, VALUE repl)
{
    str = rb_str_dup(str);
    tr_trans(str, src, repl, 1);
    return str;
}

static VALUE
rb_str_tr_s_bang(VALUE str, VALUE src, VALUE repl)
{
    return tr_trans(str, src, repl, 1);
}

# File lib/unicode_normalize.rb, line 30
def unicode_normalize(form = :nfc)
  require 'unicode_normalize/normalize.rb' unless defined? UnicodeNormalize
  ## The following line can be uncommented to avoid repeated checking for
  ## UnicodeNormalize. However, tests didn't show any noticeable speedup
  ## when doing this. This comment also applies to the commented out lines
  ## in String#unicode_normalize! and String#unicode_normalized?.
  # String.send(:define_method, :unicode_normalize, ->(form = :nfc) { UnicodeNormalize.normalize(self, form) } )
  UnicodeNormalize.normalize(self, form)
end

# File lib/unicode_normalize.rb, line 46
def unicode_normalize!(form = :nfc)
  require 'unicode_normalize/normalize.rb' unless defined? UnicodeNormalize
  # String.send(:define_method, :unicode_normalize!, ->(form = :nfc) { replace(unicode_normalize(form)) } )
  replace(unicode_normalize(form))
end

# File lib/unicode_normalize.rb, line 71
def unicode_normalized?(form = :nfc)
  require 'unicode_normalize/normalize.rb' unless defined? UnicodeNormalize
  # String.send(:define_method, :unicode_normalized?, ->(form = :nfc) { UnicodeNormalize.normalized?(self, form) } )
  UnicodeNormalize.normalized?(self, form)
end

static VALUE
pack_unpack(VALUE str, VALUE fmt)
{
    static const char hexdigits[] = "0123456789abcdef";
    char *s, *send;
    char *p, *pend;
    VALUE ary;
    char type;
    long len, tmp_len;
    int star;
#ifdef NATINT_PACK
    int natint;                 /* native integer */
#endif
    int block_p = rb_block_given_p();
    int signed_p, integer_size, bigendian_p;
#define UNPACK_PUSH(item) do {\
        VALUE item_val = (item);\
        if (block_p) {\
            rb_yield(item_val);\
        }\
        else {\
            rb_ary_push(ary, item_val);\
        }\
    } while (0)

    StringValue(str);
    StringValue(fmt);
    s = RSTRING_PTR(str);
    send = s + RSTRING_LEN(str);
    p = RSTRING_PTR(fmt);
    pend = p + RSTRING_LEN(fmt);

    ary = block_p ? Qnil : rb_ary_new();
    while (p < pend) {
        int explicit_endian = 0;
        type = *p++;
#ifdef NATINT_PACK
        natint = 0;
#endif

        if (ISSPACE(type)) continue;
        if (type == '#') {
            while ((p < pend) && (*p != '\n')) {
                p++;
            }
            continue;
        }

        star = 0;
        {
          modifiers:
            switch (*p) {
              case '_':
              case '!':

                if (strchr(natstr, type)) {
#ifdef NATINT_PACK
                    natint = 1;
#endif
                    p++;
                }
                else {
                    rb_raise(rb_eArgError, "'%c' allowed only after types %s", *p, natstr);
                }
                goto modifiers;

              case '<':
              case '>':
                if (!strchr(endstr, type)) {
                    rb_raise(rb_eArgError, "'%c' allowed only after types %s", *p, endstr);
                }
                if (explicit_endian) {
                    rb_raise(rb_eRangeError, "Can't use both '<' and '>'");
                }
                explicit_endian = *p++;
                goto modifiers;
            }
        }

        if (p >= pend)
            len = 1;
        else if (*p == '*') {
            star = 1;
            len = send - s;
            p++;
        }
        else if (ISDIGIT(*p)) {
            errno = 0;
            len = STRTOUL(p, (char**)&p, 10);
            if (len < 0 || errno) {
                rb_raise(rb_eRangeError, "pack length too big");
            }
        }
        else {
            len = (type != '@');
        }

        switch (type) {
          case '%':
            rb_raise(rb_eArgError, "%% is not supported");
            break;

          case 'A':
            if (len > send - s) len = send - s;
            {
                long end = len;
                char *t = s + len - 1;

                while (t >= s) {
                    if (*t != ' ' && *t != '\0') break;
                    t--; len--;
                }
                UNPACK_PUSH(infected_str_new(s, len, str));
                s += end;
            }
            break;

          case 'Z':
            {
                char *t = s;

                if (len > send-s) len = send-s;
                while (t < s+len && *t) t++;
                UNPACK_PUSH(infected_str_new(s, t-s, str));
                if (t < send) t++;
                s = star ? t : s+len;
            }
            break;

          case 'a':
            if (len > send - s) len = send - s;
            UNPACK_PUSH(infected_str_new(s, len, str));
            s += len;
            break;

          case 'b':
            {
                VALUE bitstr;
                char *t;
                int bits;
                long i;

                if (p[-1] == '*' || len > (send - s) * 8)
                    len = (send - s) * 8;
                bits = 0;
                bitstr = rb_usascii_str_new(0, len);
                t = RSTRING_PTR(bitstr);
                for (i=0; i<len; i++) {
                    if (i & 7) bits >>= 1;
                    else bits = (unsigned char)*s++;
                    *t++ = (bits & 1) ? '1' : '0';
                }
                UNPACK_PUSH(bitstr);
            }
            break;

          case 'B':
            {
                VALUE bitstr;
                char *t;
                int bits;
                long i;

                if (p[-1] == '*' || len > (send - s) * 8)
                    len = (send - s) * 8;
                bits = 0;
                bitstr = rb_usascii_str_new(0, len);
                t = RSTRING_PTR(bitstr);
                for (i=0; i<len; i++) {
                    if (i & 7) bits <<= 1;
                    else bits = (unsigned char)*s++;
                    *t++ = (bits & 128) ? '1' : '0';
                }
                UNPACK_PUSH(bitstr);
            }
            break;

          case 'h':
            {
                VALUE bitstr;
                char *t;
                int bits;
                long i;

                if (p[-1] == '*' || len > (send - s) * 2)
                    len = (send - s) * 2;
                bits = 0;
                bitstr = rb_usascii_str_new(0, len);
                t = RSTRING_PTR(bitstr);
                for (i=0; i<len; i++) {
                    if (i & 1)
                        bits >>= 4;
                    else
                        bits = (unsigned char)*s++;
                    *t++ = hexdigits[bits & 15];
                }
                UNPACK_PUSH(bitstr);
            }
            break;

          case 'H':
            {
                VALUE bitstr;
                char *t;
                int bits;
                long i;

                if (p[-1] == '*' || len > (send - s) * 2)
                    len = (send - s) * 2;
                bits = 0;
                bitstr = rb_usascii_str_new(0, len);
                t = RSTRING_PTR(bitstr);
                for (i=0; i<len; i++) {
                    if (i & 1)
                        bits <<= 4;
                    else
                        bits = (unsigned char)*s++;
                    *t++ = hexdigits[(bits >> 4) & 15];
                }
                UNPACK_PUSH(bitstr);
            }
            break;

          case 'c':
            signed_p = 1;
            integer_size = 1;
            bigendian_p = BIGENDIAN_P(); /* not effective */
            goto unpack_integer;

          case 'C':
            signed_p = 0;
            integer_size = 1;
            bigendian_p = BIGENDIAN_P(); /* not effective */
            goto unpack_integer;

          case 's':
            signed_p = 1;
            integer_size = NATINT_LEN(short, 2);
            bigendian_p = BIGENDIAN_P();
            goto unpack_integer;

          case 'S':
            signed_p = 0;
            integer_size = NATINT_LEN(short, 2);
            bigendian_p = BIGENDIAN_P();
            goto unpack_integer;

          case 'i':
            signed_p = 1;
            integer_size = (int)sizeof(int);
            bigendian_p = BIGENDIAN_P();
            goto unpack_integer;

          case 'I':
            signed_p = 0;
            integer_size = (int)sizeof(int);
            bigendian_p = BIGENDIAN_P();
            goto unpack_integer;

          case 'l':
            signed_p = 1;
            integer_size = NATINT_LEN(long, 4);
            bigendian_p = BIGENDIAN_P();
            goto unpack_integer;

          case 'L':
            signed_p = 0;
            integer_size = NATINT_LEN(long, 4);
            bigendian_p = BIGENDIAN_P();
            goto unpack_integer;

          case 'q':
            signed_p = 1;
            integer_size = NATINT_LEN_Q;
            bigendian_p = BIGENDIAN_P();
            goto unpack_integer;

          case 'Q':
            signed_p = 0;
            integer_size = NATINT_LEN_Q;
            bigendian_p = BIGENDIAN_P();
            goto unpack_integer;

          case 'n':
            signed_p = 0;
            integer_size = 2;
            bigendian_p = 1;
            goto unpack_integer;

          case 'N':
            signed_p = 0;
            integer_size = 4;
            bigendian_p = 1;
            goto unpack_integer;

          case 'v':
            signed_p = 0;
            integer_size = 2;
            bigendian_p = 0;
            goto unpack_integer;

          case 'V':
            signed_p = 0;
            integer_size = 4;
            bigendian_p = 0;
            goto unpack_integer;

          unpack_integer:
            if (explicit_endian) {
                bigendian_p = explicit_endian == '>';
            }
            PACK_LENGTH_ADJUST_SIZE(integer_size);
            while (len-- > 0) {
                int flags = bigendian_p ? INTEGER_PACK_BIG_ENDIAN : INTEGER_PACK_LITTLE_ENDIAN;
                VALUE val;
                if (signed_p)
                    flags |= INTEGER_PACK_2COMP;
                val = rb_integer_unpack(s, integer_size, 1, 0, flags);
                UNPACK_PUSH(val);
                s += integer_size;
            }
            PACK_ITEM_ADJUST();
            break;

          case 'f':
          case 'F':
            PACK_LENGTH_ADJUST_SIZE(sizeof(float));
            while (len-- > 0) {
                float tmp;
                memcpy(&tmp, s, sizeof(float));
                s += sizeof(float);
                UNPACK_PUSH(DBL2NUM((double)tmp));
            }
            PACK_ITEM_ADJUST();
            break;

          case 'e':
            PACK_LENGTH_ADJUST_SIZE(sizeof(float));
            while (len-- > 0) {
                FLOAT_CONVWITH(tmp);
                memcpy(tmp.buf, s, sizeof(float));
                s += sizeof(float);
                VTOHF(tmp);
                UNPACK_PUSH(DBL2NUM(tmp.f));
            }
            PACK_ITEM_ADJUST();
            break;

          case 'E':
            PACK_LENGTH_ADJUST_SIZE(sizeof(double));
            while (len-- > 0) {
                DOUBLE_CONVWITH(tmp);
                memcpy(tmp.buf, s, sizeof(double));
                s += sizeof(double);
                VTOHD(tmp);
                UNPACK_PUSH(DBL2NUM(tmp.d));
            }
            PACK_ITEM_ADJUST();
            break;

          case 'D':
          case 'd':
            PACK_LENGTH_ADJUST_SIZE(sizeof(double));
            while (len-- > 0) {
                double tmp;
                memcpy(&tmp, s, sizeof(double));
                s += sizeof(double);
                UNPACK_PUSH(DBL2NUM(tmp));
            }
            PACK_ITEM_ADJUST();
            break;

          case 'g':
            PACK_LENGTH_ADJUST_SIZE(sizeof(float));
            while (len-- > 0) {
                FLOAT_CONVWITH(tmp);
                memcpy(tmp.buf, s, sizeof(float));
                s += sizeof(float);
                NTOHF(tmp);
                UNPACK_PUSH(DBL2NUM(tmp.f));
            }
            PACK_ITEM_ADJUST();
            break;

          case 'G':
            PACK_LENGTH_ADJUST_SIZE(sizeof(double));
            while (len-- > 0) {
                DOUBLE_CONVWITH(tmp);
                memcpy(tmp.buf, s, sizeof(double));
                s += sizeof(double);
                NTOHD(tmp);
                UNPACK_PUSH(DBL2NUM(tmp.d));
            }
            PACK_ITEM_ADJUST();
            break;

          case 'U':
            if (len > send - s) len = send - s;
            while (len > 0 && s < send) {
                long alen = send - s;
                unsigned long l;

                l = utf8_to_uv(s, &alen);
                s += alen; len--;
                UNPACK_PUSH(ULONG2NUM(l));
            }
            break;

          case 'u':
            {
                VALUE buf = infected_str_new(0, (send - s)*3/4, str);
                char *ptr = RSTRING_PTR(buf);
                long total = 0;

                while (s < send && (unsigned char)*s > ' ' && (unsigned char)*s < 'a') {
                    long a,b,c,d;
                    char hunk[3];

                    len = ((unsigned char)*s++ - ' ') & 077;

                    total += len;
                    if (total > RSTRING_LEN(buf)) {
                        len -= total - RSTRING_LEN(buf);
                        total = RSTRING_LEN(buf);
                    }

                    while (len > 0) {
                        long mlen = len > 3 ? 3 : len;

                        if (s < send && (unsigned char)*s >= ' ' && (unsigned char)*s < 'a')
                            a = ((unsigned char)*s++ - ' ') & 077;
                        else
                            a = 0;
                        if (s < send && (unsigned char)*s >= ' ' && (unsigned char)*s < 'a')
                            b = ((unsigned char)*s++ - ' ') & 077;
                        else
                            b = 0;
                        if (s < send && (unsigned char)*s >= ' ' && (unsigned char)*s < 'a')
                            c = ((unsigned char)*s++ - ' ') & 077;
                        else
                            c = 0;
                        if (s < send && (unsigned char)*s >= ' ' && (unsigned char)*s < 'a')
                            d = ((unsigned char)*s++ - ' ') & 077;
                        else
                            d = 0;
                        hunk[0] = (char)(a << 2 | b >> 4);
                        hunk[1] = (char)(b << 4 | c >> 2);
                        hunk[2] = (char)(c << 6 | d);
                        memcpy(ptr, hunk, mlen);
                        ptr += mlen;
                        len -= mlen;
                    }
                    if (s < send && (unsigned char)*s != '\r' && *s != '\n')
                        s++; /* possible checksum byte */
                    if (s < send && *s == '\r') s++;
                    if (s < send && *s == '\n') s++;
                }

                rb_str_set_len(buf, total);
                UNPACK_PUSH(buf);
            }
            break;

          case 'm':
            {
                VALUE buf = infected_str_new(0, (send - s + 3)*3/4, str); /* +3 is for skipping paddings */
                char *ptr = RSTRING_PTR(buf);
                int a = -1,b = -1,c = 0,d = 0;
                static signed char b64_xtable[256];

                if (b64_xtable['/'] <= 0) {
                    int i;

                    for (i = 0; i < 256; i++) {
                        b64_xtable[i] = -1;
                    }
                    for (i = 0; i < 64; i++) {
                        b64_xtable[(unsigned char)b64_table[i]] = (char)i;
                    }
                }
                if (len == 0) {
                    while (s < send) {
                        a = b = c = d = -1;
                        a = b64_xtable[(unsigned char)*s++];
                        if (s >= send || a == -1) rb_raise(rb_eArgError, "invalid base64");
                        b = b64_xtable[(unsigned char)*s++];
                        if (s >= send || b == -1) rb_raise(rb_eArgError, "invalid base64");
                        if (*s == '=') {
                            if (s + 2 == send && *(s + 1) == '=') break;
                            rb_raise(rb_eArgError, "invalid base64");
                        }
                        c = b64_xtable[(unsigned char)*s++];
                        if (s >= send || c == -1) rb_raise(rb_eArgError, "invalid base64");
                        if (s + 1 == send && *s == '=') break;
                        d = b64_xtable[(unsigned char)*s++];
                        if (d == -1) rb_raise(rb_eArgError, "invalid base64");
                        *ptr++ = castchar(a << 2 | b >> 4);
                        *ptr++ = castchar(b << 4 | c >> 2);
                        *ptr++ = castchar(c << 6 | d);
                    }
                    if (c == -1) {
                        *ptr++ = castchar(a << 2 | b >> 4);
                        if (b & 0xf) rb_raise(rb_eArgError, "invalid base64");
                    }
                    else if (d == -1) {
                        *ptr++ = castchar(a << 2 | b >> 4);
                        *ptr++ = castchar(b << 4 | c >> 2);
                        if (c & 0x3) rb_raise(rb_eArgError, "invalid base64");
                    }
                }
                else {
                    while (s < send) {
                        a = b = c = d = -1;
                        while ((a = b64_xtable[(unsigned char)*s]) == -1 && s < send) {s++;}
                        if (s >= send) break;
                        s++;
                        while ((b = b64_xtable[(unsigned char)*s]) == -1 && s < send) {s++;}
                        if (s >= send) break;
                        s++;
                        while ((c = b64_xtable[(unsigned char)*s]) == -1 && s < send) {if (*s == '=') break; s++;}
                        if (*s == '=' || s >= send) break;
                        s++;
                        while ((d = b64_xtable[(unsigned char)*s]) == -1 && s < send) {if (*s == '=') break; s++;}
                        if (*s == '=' || s >= send) break;
                        s++;
                        *ptr++ = castchar(a << 2 | b >> 4);
                        *ptr++ = castchar(b << 4 | c >> 2);
                        *ptr++ = castchar(c << 6 | d);
                        a = -1;
                    }
                    if (a != -1 && b != -1) {
                        if (c == -1)
                            *ptr++ = castchar(a << 2 | b >> 4);
                        else {
                            *ptr++ = castchar(a << 2 | b >> 4);
                            *ptr++ = castchar(b << 4 | c >> 2);
                        }
                    }
                }
                rb_str_set_len(buf, ptr - RSTRING_PTR(buf));
                UNPACK_PUSH(buf);
            }
            break;

          case 'M':
            {
                VALUE buf = infected_str_new(0, send - s, str);
                char *ptr = RSTRING_PTR(buf), *ss = s;
                int c1, c2;

                while (s < send) {
                    if (*s == '=') {
                        if (++s == send) break;
                        if (s+1 < send && *s == '\r' && *(s+1) == '\n')
                            s++;
                        if (*s != '\n') {
                            if ((c1 = hex2num(*s)) == -1) break;
                            if (++s == send) break;
                            if ((c2 = hex2num(*s)) == -1) break;
                            *ptr++ = castchar(c1 << 4 | c2);
                        }
                    }
                    else {
                        *ptr++ = *s;
                    }
                    s++;
                    ss = s;
                }
                rb_str_set_len(buf, ptr - RSTRING_PTR(buf));
                rb_str_buf_cat(buf, ss, send-ss);
                ENCODING_CODERANGE_SET(buf, rb_ascii8bit_encindex(), ENC_CODERANGE_VALID);
                UNPACK_PUSH(buf);
            }
            break;

          case '@':
            if (len > RSTRING_LEN(str))
                rb_raise(rb_eArgError, "@ outside of string");
            s = RSTRING_PTR(str) + len;
            break;

          case 'X':
            if (len > s - RSTRING_PTR(str))
                rb_raise(rb_eArgError, "X outside of string");
            s -= len;
            break;

          case 'x':
            if (len > send - s)
                rb_raise(rb_eArgError, "x outside of string");
            s += len;
            break;

          case 'P':
            if (sizeof(char *) <= (size_t)(send - s)) {
                VALUE tmp = Qnil;
                char *t;

                memcpy(&t, s, sizeof(char *));
                s += sizeof(char *);

                if (t) {
                    VALUE a;
                    const VALUE *p, *pend;

                    if (!(a = str_associated(str))) {
                        rb_raise(rb_eArgError, "no associated pointer");
                    }
                    p = RARRAY_CONST_PTR(a);
                    pend = p + RARRAY_LEN(a);
                    while (p < pend) {
                        if (RB_TYPE_P(*p, T_STRING) && RSTRING_PTR(*p) == t) {
                            if (len < RSTRING_LEN(*p)) {
                                tmp = rb_tainted_str_new(t, len);
                                str_associate(tmp, a);
                            }
                            else {
                                tmp = *p;
                            }
                            break;
                        }
                        p++;
                    }
                    if (p == pend) {
                        rb_raise(rb_eArgError, "non associated pointer");
                    }
                }
                UNPACK_PUSH(tmp);
            }
            break;

          case 'p':
            if (len > (long)((send - s) / sizeof(char *)))
                len = (send - s) / sizeof(char *);
            while (len-- > 0) {
                if ((size_t)(send - s) < sizeof(char *))
                    break;
                else {
                    VALUE tmp = Qnil;
                    char *t;

                    memcpy(&t, s, sizeof(char *));
                    s += sizeof(char *);

                    if (t) {
                        VALUE a;
                        const VALUE *p, *pend;

                        if (!(a = str_associated(str))) {
                            rb_raise(rb_eArgError, "no associated pointer");
                        }
                        p = RARRAY_CONST_PTR(a);
                        pend = p + RARRAY_LEN(a);
                        while (p < pend) {
                            if (RB_TYPE_P(*p, T_STRING) && RSTRING_PTR(*p) == t) {
                                tmp = *p;
                                break;
                            }
                            p++;
                        }
                        if (p == pend) {
                            rb_raise(rb_eArgError, "non associated pointer");
                        }
                    }
                    UNPACK_PUSH(tmp);
                }
            }
            break;

          case 'w':
            {
                char *s0 = s;
                while (len > 0 && s < send) {
                    if (*s & 0x80) {
                        s++;
                    }
                    else {
                        s++;
                        UNPACK_PUSH(rb_integer_unpack(s0, s-s0, 1, 1, INTEGER_PACK_BIG_ENDIAN));
                        len--;
                        s0 = s;
                    }
                }
            }
            break;

          default:
            rb_warning("unknown unpack directive '%c' in '%s'",
                type, RSTRING_PTR(fmt));
            break;
        }
    }

    return ary;
}

static VALUE
rb_str_upcase(VALUE str)
{
    str = rb_str_dup(str);
    rb_str_upcase_bang(str);
    return str;
}

static VALUE
rb_str_upcase_bang(VALUE str)
{
    rb_encoding *enc;
    char *s, *send;
    int modify = 0;
    int n;

    str_modify_keep_cr(str);
    enc = STR_ENC_GET(str);
    rb_str_check_dummy_enc(enc);
    s = RSTRING_PTR(str); send = RSTRING_END(str);
    if (single_byte_optimizable(str)) {
        while (s < send) {
            unsigned int c = *(unsigned char*)s;

            if (rb_enc_isascii(c, enc) && 'a' <= c && c <= 'z') {
                *s = 'A' + (c - 'a');
                modify = 1;
            }
            s++;
        }
    }
    else {
        int ascompat = rb_enc_asciicompat(enc);

        while (s < send) {
            unsigned int c;

            if (ascompat && (c = *(unsigned char*)s) < 0x80) {
                if (rb_enc_isascii(c, enc) && 'a' <= c && c <= 'z') {
                    *s = 'A' + (c - 'a');
                    modify = 1;
                }
                s++;
            }
            else {
                c = rb_enc_codepoint_len(s, send, &n, enc);
                if (rb_enc_islower(c, enc)) {
                    /* assuming toupper returns codepoint with same size */
                    rb_enc_mbcput(rb_enc_toupper(c, enc), s, enc);
                    modify = 1;
                }
                s += n;
            }
        }
    }

    if (modify) return str;
    return Qnil;
}

static VALUE
rb_str_upto(int argc, VALUE *argv, VALUE beg)
{
    VALUE end, exclusive;
    VALUE current, after_end;
    ID succ;
    int n, excl, ascii;
    rb_encoding *enc;

    rb_scan_args(argc, argv, "11", &end, &exclusive);
    RETURN_ENUMERATOR(beg, argc, argv);
    excl = RTEST(exclusive);
    CONST_ID(succ, "succ");
    StringValue(end);
    enc = rb_enc_check(beg, end);
    ascii = (is_ascii_string(beg) && is_ascii_string(end));
    /* single character */
    if (RSTRING_LEN(beg) == 1 && RSTRING_LEN(end) == 1 && ascii) {
        char c = RSTRING_PTR(beg)[0];
        char e = RSTRING_PTR(end)[0];

        if (c > e || (excl && c == e)) return beg;
        for (;;) {
            rb_yield(rb_enc_str_new(&c, 1, enc));
            if (!excl && c == e) break;
            c++;
            if (excl && c == e) break;
        }
        return beg;
    }
    /* both edges are all digits */
    if (ascii && ISDIGIT(RSTRING_PTR(beg)[0]) && ISDIGIT(RSTRING_PTR(end)[0])) {
        char *s, *send;
        VALUE b, e;
        int width;

        s = RSTRING_PTR(beg); send = RSTRING_END(beg);
        width = rb_long2int(send - s);
        while (s < send) {
            if (!ISDIGIT(*s)) goto no_digits;
            s++;
        }
        s = RSTRING_PTR(end); send = RSTRING_END(end);
        while (s < send) {
            if (!ISDIGIT(*s)) goto no_digits;
            s++;
        }
        b = rb_str_to_inum(beg, 10, FALSE);
        e = rb_str_to_inum(end, 10, FALSE);
        if (FIXNUM_P(b) && FIXNUM_P(e)) {
            long bi = FIX2LONG(b);
            long ei = FIX2LONG(e);
            rb_encoding *usascii = rb_usascii_encoding();

            while (bi <= ei) {
                if (excl && bi == ei) break;
                rb_yield(rb_enc_sprintf(usascii, "%.*ld", width, bi));
                bi++;
            }
        }
        else {
            ID op = excl ? '<' : rb_intern("<=");
            VALUE args[2], fmt = rb_obj_freeze(rb_usascii_str_new_cstr("%.*d"));

            args[0] = INT2FIX(width);
            while (rb_funcall(b, op, 1, e)) {
                args[1] = b;
                rb_yield(rb_str_format(numberof(args), args, fmt));
                b = rb_funcall(b, succ, 0, 0);
            }
        }
        return beg;
    }
    /* normal case */
  no_digits:
    n = rb_str_cmp(beg, end);
    if (n > 0 || (excl && n == 0)) return beg;

    after_end = rb_funcall(end, succ, 0, 0);
    current = rb_str_dup(beg);
    while (!rb_str_equal(current, after_end)) {
        VALUE next = Qnil;
        if (excl || !rb_str_equal(current, end))
            next = rb_funcall(current, succ, 0, 0);
        rb_yield(current);
        if (NIL_P(next)) break;
        current = next;
        StringValue(current);
        if (excl && rb_str_equal(current, end)) break;
        if (RSTRING_LEN(current) > RSTRING_LEN(end) || RSTRING_LEN(current) == 0)
            break;
    }

    return beg;
}

static VALUE
rb_str_valid_encoding_p(VALUE str)
{
    int cr = rb_enc_str_coderange(str);

    return cr == ENC_CODERANGE_BROKEN ? Qfalse : Qtrue;
}