Класс String

static VALUE
rb_str_init(int argc, VALUE *argv, VALUE str)
{
    static ID keyword_ids[2];
    VALUE orig, opt, venc, vcapa;
    VALUE kwargs[2];
    rb_encoding *enc = 0;
    int n;

    if (!keyword_ids[0]) {
        keyword_ids[0] = rb_id_encoding();
        CONST_ID(keyword_ids[1], "capacity");
    }

    n = rb_scan_args(argc, argv, "01:", &orig, &opt);
    if (!NIL_P(opt)) {
        rb_get_kwargs(opt, keyword_ids, 0, 2, kwargs);
        venc = kwargs[0];
        vcapa = kwargs[1];
        if (!UNDEF_P(venc) && !NIL_P(venc)) {
            enc = rb_to_encoding(venc);
        }
        if (!UNDEF_P(vcapa) && !NIL_P(vcapa)) {
            long capa = NUM2LONG(vcapa);
            long len = 0;
            int termlen = enc ? rb_enc_mbminlen(enc) : 1;

            if (capa < STR_BUF_MIN_SIZE) {
                capa = STR_BUF_MIN_SIZE;
            }
            if (n == 1) {
                StringValue(orig);
                len = RSTRING_LEN(orig);
                if (capa < len) {
                    capa = len;
                }
                if (orig == str) n = 0;
            }
            str_modifiable(str);
            if (STR_EMBED_P(str) || FL_TEST(str, STR_SHARED|STR_NOFREE)) {
                /* make noembed always */
                const size_t size = (size_t)capa + termlen;
                const char *const old_ptr = RSTRING_PTR(str);
                const size_t osize = RSTRING_LEN(str) + TERM_LEN(str);
                char *new_ptr = ALLOC_N(char, size);
                if (STR_EMBED_P(str)) RUBY_ASSERT((long)osize <= str_embed_capa(str));
                memcpy(new_ptr, old_ptr, osize < size ? osize : size);
                FL_UNSET_RAW(str, STR_SHARED|STR_NOFREE);
                RSTRING(str)->as.heap.ptr = new_ptr;
            }
            else if (STR_HEAP_SIZE(str) != (size_t)capa + termlen) {
                SIZED_REALLOC_N(RSTRING(str)->as.heap.ptr, char,
                        (size_t)capa + termlen, STR_HEAP_SIZE(str));
            }
            STR_SET_LEN(str, len);
            TERM_FILL(&RSTRING(str)->as.heap.ptr[len], termlen);
            if (n == 1) {
                memcpy(RSTRING(str)->as.heap.ptr, RSTRING_PTR(orig), len);
                rb_enc_cr_str_exact_copy(str, orig);
            }
            FL_SET(str, STR_NOEMBED);
            RSTRING(str)->as.heap.aux.capa = capa;
        }
        else if (n == 1) {
            rb_str_replace(str, orig);
        }
        if (enc) {
            rb_enc_associate(str, enc);
            ENC_CODERANGE_CLEAR(str);
        }
    }
    else if (n == 1) {
        rb_str_replace(str, orig);
    }
    return str;
}

static VALUE
rb_str_s_try_convert(VALUE dummy, VALUE str)
{
    return rb_check_string_type(str);
}

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

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

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

    if (times == INT2FIX(1)) {
        return str_duplicate(rb_cString, str);
    }
    if (times == INT2FIX(0)) {
        str2 = str_alloc_embed(rb_cString, 0);
        rb_enc_copy(str2, str);
        return str2;
    }
    len = NUM2LONG(times);
    if (len < 0) {
        rb_raise(rb_eArgError, "negative argument");
    }
    if (RSTRING_LEN(str) == 1 && RSTRING_PTR(str)[0] == 0) {
        if (STR_EMBEDDABLE_P(len, 1)) {
            str2 = str_alloc_embed(rb_cString, len + 1);
            memset(RSTRING_PTR(str2), 0, len + 1);
        }
        else {
            str2 = str_alloc_heap(rb_cString);
            RSTRING(str2)->as.heap.aux.capa = len;
            RSTRING(str2)->as.heap.ptr = ZALLOC_N(char, (size_t)len + 1);
        }
        STR_SET_LEN(str2, len);
        rb_enc_copy(str2, str);
        return str2;
    }
    if (len && LONG_MAX/len <  RSTRING_LEN(str)) {
        rb_raise(rb_eArgError, "argument too big");
    }

    len *= RSTRING_LEN(str);
    termlen = TERM_LEN(str);
    str2 = str_enc_new(rb_cString, 0, len, STR_ENC_GET(str));
    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);
    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_str(str1, str2);
    RSTRING_GETMEM(str1, ptr1, len1);
    RSTRING_GETMEM(str2, ptr2, len2);
    termlen = rb_enc_mbminlen(enc);
    if (len1 > LONG_MAX - len2) {
        rb_raise(rb_eArgError, "string size too big");
    }
    str3 = str_enc_new(rb_cString, 0, len1+len2, enc);
    ptr3 = RSTRING_PTR(str3);
    memcpy(ptr3, ptr1, len1);
    memcpy(ptr3+len1, ptr2, len2);
    TERM_FILL(&ptr3[len1+len2], termlen);

    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;
}

static VALUE
str_uplus(VALUE str)
{
    if (OBJ_FROZEN(str) || CHILLED_STRING_P(str)) {
        return rb_str_dup(str);
    }
    else {
        return str;
    }
}

static VALUE
str_uminus(VALUE str)
{
    if (!BARE_STRING_P(str) && !rb_obj_frozen_p(str)) {
        str = rb_str_dup(str);
    }
    return rb_fstring(str);
}

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

    if (RB_INTEGER_TYPE_P(str2)) {
        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);
    }

    encidx = rb_ascii8bit_appendable_encoding_index(enc, code);

    if (encidx >= 0) {
        rb_str_buf_cat_byte(str1, (unsigned char)code);
    }
    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;
        }
        else if (cr == ENC_CODERANGE_BROKEN) {
            cr = ENC_CODERANGE_UNKNOWN;
        }
        ENC_CODERANGE_SET(str1, cr);
    }
    return str1;
}

static VALUE
rb_str_cmp_m(VALUE str1, VALUE str2)
{
    int result;
    VALUE s = rb_check_string_type(str2);
    if (NIL_P(s)) {
        return rb_invcmp(str1, str2);
    }
    result = rb_str_cmp(str1, s);
    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, idTo_str)) {
            return Qfalse;
        }
        return rb_equal(str2, str1);
    }
    return rb_str_eql_internal(str1, str2);
}

static VALUE
rb_str_match(VALUE x, VALUE y)
{
    switch (OBJ_BUILTIN_TYPE(y)) {
      case T_STRING:
        rb_raise(rb_eTypeError, "type mismatch: String given");

      case T_REGEXP:
        return rb_reg_match(y, x);

      default:
        return rb_funcall(y, idEqTilde, 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]);
        }
        else {
            return rb_str_substr_two_fixnums(str, argv[0], argv[1], TRUE);
        }
    }
    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_update(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]);
}

VALUE
rb_str_append_as_bytes(int argc, VALUE *argv, VALUE str)
{
    long needed_capacity = 0;
    volatile VALUE t0;
    enum ruby_value_type *types = ALLOCV_N(enum ruby_value_type, t0, argc);

    for (int index = 0; index < argc; index++) {
        VALUE obj = argv[index];
        enum ruby_value_type type = types[index] = rb_type(obj);
        switch (type) {
          case T_FIXNUM:
          case T_BIGNUM:
            needed_capacity++;
            break;
          case T_STRING:
            needed_capacity += RSTRING_LEN(obj);
            break;
          default:
            rb_raise(
                rb_eTypeError,
                "wrong argument type %"PRIsVALUE" (expected String or Integer)",
                rb_obj_class(obj)
            );
            break;
        }
    }

    str_ensure_available_capa(str, needed_capacity);
    char *sptr = RSTRING_END(str);

    for (int index = 0; index < argc; index++) {
        VALUE obj = argv[index];
        enum ruby_value_type type = types[index];
        switch (type) {
          case T_FIXNUM:
          case T_BIGNUM: {
            argv[index] = obj = rb_int_and(obj, INT2FIX(0xff));
            char byte = (char)(NUM2INT(obj) & 0xFF);
            *sptr = byte;
            sptr++;
            break;
          }
          case T_STRING: {
            const char *ptr;
            long len;
            RSTRING_GETMEM(obj, ptr, len);
            memcpy(sptr, ptr, len);
            sptr += len;
            break;
          }
          default:
            rb_bug("append_as_bytes arguments should have been validated");
        }
    }

    STR_SET_LEN(str, RSTRING_LEN(str) + needed_capacity);
    TERM_FILL(sptr, TERM_LEN(str)); /* sentinel */

    int cr = ENC_CODERANGE(str);
    switch (cr) {
      case ENC_CODERANGE_7BIT: {
        for (int index = 0; index < argc; index++) {
            VALUE obj = argv[index];
            enum ruby_value_type type = types[index];
            switch (type) {
              case T_FIXNUM:
              case T_BIGNUM: {
                if (!ISASCII(NUM2INT(obj))) {
                    goto clear_cr;
                }
                break;
              }
              case T_STRING: {
                if (ENC_CODERANGE(obj) != ENC_CODERANGE_7BIT) {
                    goto clear_cr;
                }
                break;
              }
              default:
                rb_bug("append_as_bytes arguments should have been validated");
            }
        }
        break;
      }
      case ENC_CODERANGE_VALID:
        if (ENCODING_GET_INLINED(str) == ENCINDEX_ASCII_8BIT) {
            goto keep_cr;
        }
        else {
            goto clear_cr;
        }
        break;
      default:
        goto clear_cr;
        break;
    }

    RB_GC_GUARD(t0);

  clear_cr:
    // If no fast path was hit, we clear the coderange.
    // append_as_bytes is predominently meant to be used in
    // buffering situation, hence it's likely the coderange
    // will never be scanned, so it's not worth spending time
    // precomputing the coderange except for simple and common
    // situations.
    ENC_CODERANGE_CLEAR(str);
  keep_cr:
    return str;
}

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

    return RBOOL(cr == ENC_CODERANGE_7BIT);
}

static VALUE
rb_str_b(VALUE str)
{
    VALUE str2;
    if (STR_EMBED_P(str)) {
        str2 = str_alloc_embed(rb_cString, RSTRING_LEN(str) + TERM_LEN(str));
    }
    else {
        str2 = str_alloc_heap(rb_cString);
    }
    str_replace_shared_without_enc(str2, str);

    if (rb_enc_asciicompat(STR_ENC_GET(str))) {
        // BINARY strings can never be broken; they're either 7-bit ASCII or VALID.
        // If we know the receiver's code range then we know the result's code range.
        int cr = ENC_CODERANGE(str);
        switch (cr) {
          case ENC_CODERANGE_7BIT:
            ENC_CODERANGE_SET(str2, ENC_CODERANGE_7BIT);
            break;
          case ENC_CODERANGE_BROKEN:
          case ENC_CODERANGE_VALID:
            ENC_CODERANGE_SET(str2, ENC_CODERANGE_VALID);
            break;
          default:
            ENC_CODERANGE_CLEAR(str2);
            break;
        }
    }

    return str2;
}

static VALUE
rb_str_byteindex_m(int argc, VALUE *argv, VALUE str)
{
    VALUE sub;
    VALUE initpos;
    long pos;

    if (rb_scan_args(argc, argv, "11", &sub, &initpos) == 2) {
        long slen = RSTRING_LEN(str);
        pos = NUM2LONG(initpos);
        if (pos < 0 ? (pos += slen) < 0 : pos > slen) {
            if (RB_TYPE_P(sub, T_REGEXP)) {
                rb_backref_set(Qnil);
            }
            return Qnil;
        }
    }
    else {
        pos = 0;
    }

    str_ensure_byte_pos(str, pos);

    if (RB_TYPE_P(sub, T_REGEXP)) {
        if (rb_reg_search(sub, str, pos, 0) >= 0) {
            VALUE match = rb_backref_get();
            struct re_registers *regs = RMATCH_REGS(match);
            pos = BEG(0);
            return LONG2NUM(pos);
        }
    }
    else {
        StringValue(sub);
        pos = rb_str_byteindex(str, sub, pos);
        if (pos >= 0) return LONG2NUM(pos);
    }
    return Qnil;
}

static VALUE
rb_str_byterindex_m(int argc, VALUE *argv, VALUE str)
{
    VALUE sub;
    VALUE initpos;
    long pos, len = RSTRING_LEN(str);

    if (rb_scan_args(argc, argv, "11", &sub, &initpos) == 2) {
        pos = NUM2LONG(initpos);
        if (pos < 0 && (pos += len) < 0) {
            if (RB_TYPE_P(sub, T_REGEXP)) {
                rb_backref_set(Qnil);
            }
            return Qnil;
        }
        if (pos > len) pos = len;
    }
    else {
        pos = len;
    }

    str_ensure_byte_pos(str, pos);

    if (RB_TYPE_P(sub, T_REGEXP)) {
        if (rb_reg_search(sub, str, pos, 1) >= 0) {
            VALUE match = rb_backref_get();
            struct re_registers *regs = RMATCH_REGS(match);
            pos = BEG(0);
            return LONG2NUM(pos);
        }
    }
    else {
        StringValue(sub);
        pos = rb_str_byterindex(str, sub, pos);
        if (pos >= 0) return LONG2NUM(pos);
    }
    return Qnil;
}

static VALUE
rb_str_bytes(VALUE str)
{
    VALUE ary = WANTARRAY("bytes", RSTRING_LEN(str));
    return rb_str_enumerate_bytes(str, ary);
}

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) {
        long beg = NUM2LONG(argv[0]);
        long len = NUM2LONG(argv[1]);
        return str_byte_substr(str, beg, len, TRUE);
    }
    rb_check_arity(argc, 1, 2);
    return str_byte_aref(str, argv[0]);
}

static VALUE
rb_str_bytesplice(int argc, VALUE *argv, VALUE str)
{
    long beg, len, vbeg, vlen;
    VALUE val;
    int cr;

    rb_check_arity(argc, 2, 5);
    if (!(argc == 2 || argc == 3 || argc == 5)) {
        rb_raise(rb_eArgError, "wrong number of arguments (given %d, expected 2, 3, or 5)", argc);
    }
    if (argc == 2 || (argc == 3 && !RB_INTEGER_TYPE_P(argv[0]))) {
        if (!rb_range_beg_len(argv[0], &beg, &len, RSTRING_LEN(str), 2)) {
            rb_raise(rb_eTypeError, "wrong argument type %s (expected Range)",
                     rb_builtin_class_name(argv[0]));
        }
        val = argv[1];
        StringValue(val);
        if (argc == 2) {
            /* bytesplice(range, str) */
            vbeg = 0;
            vlen = RSTRING_LEN(val);
        }
        else {
            /* bytesplice(range, str, str_range) */
            if (!rb_range_beg_len(argv[2], &vbeg, &vlen, RSTRING_LEN(val), 2)) {
                rb_raise(rb_eTypeError, "wrong argument type %s (expected Range)",
                         rb_builtin_class_name(argv[2]));
            }
        }
    }
    else {
        beg = NUM2LONG(argv[0]);
        len = NUM2LONG(argv[1]);
        val = argv[2];
        StringValue(val);
        if (argc == 3) {
            /* bytesplice(index, length, str) */
            vbeg = 0;
            vlen = RSTRING_LEN(val);
        }
        else {
            /* bytesplice(index, length, str, str_index, str_length) */
            vbeg = NUM2LONG(argv[3]);
            vlen = NUM2LONG(argv[4]);
        }
    }
    str_check_beg_len(str, &beg, &len);
    str_check_beg_len(val, &vbeg, &vlen);
    str_modify_keep_cr(str);

    if (RB_UNLIKELY(ENCODING_GET_INLINED(str) != ENCODING_GET_INLINED(val))) {
        rb_enc_associate(str, rb_enc_check(str, val));
    }

    rb_str_update_1(str, beg, len, val, vbeg, vlen);
    cr = ENC_CODERANGE_AND(ENC_CODERANGE(str), ENC_CODERANGE(val));
    if (cr != ENC_CODERANGE_BROKEN)
        ENC_CODERANGE_SET(str, cr);
    return str;
}

static VALUE
rb_str_capitalize(int argc, VALUE *argv, VALUE str)
{
    rb_encoding *enc;
    OnigCaseFoldType flags = ONIGENC_CASE_UPCASE | ONIGENC_CASE_TITLECASE;
    VALUE ret;

    flags = check_case_options(argc, argv, flags);
    enc = str_true_enc(str);
    if (RSTRING_LEN(str) == 0 || !RSTRING_PTR(str)) return str;
    if (flags&ONIGENC_CASE_ASCII_ONLY) {
        ret = rb_str_new(0, RSTRING_LEN(str));
        rb_str_ascii_casemap(str, ret, &flags, enc);
    }
    else {
        ret = rb_str_casemap(str, &flags, enc);
    }
    return ret;
}

static VALUE
rb_str_capitalize_bang(int argc, VALUE *argv, VALUE str)
{
    rb_encoding *enc;
    OnigCaseFoldType flags = ONIGENC_CASE_UPCASE | ONIGENC_CASE_TITLECASE;

    flags = check_case_options(argc, argv, flags);
    str_modify_keep_cr(str);
    enc = str_true_enc(str);
    if (RSTRING_LEN(str) == 0 || !RSTRING_PTR(str)) return Qnil;
    if (flags&ONIGENC_CASE_ASCII_ONLY)
        rb_str_ascii_casemap(str, str, &flags, enc);
    else
        str_shared_replace(str, rb_str_casemap(str, &flags, enc));

    if (ONIGENC_CASE_MODIFIED&flags) return str;
    return Qnil;
}

static VALUE
rb_str_casecmp(VALUE str1, VALUE str2)
{
    VALUE s = rb_check_string_type(str2);
    if (NIL_P(s)) {
        return Qnil;
    }
    return str_casecmp(str1, s);
}

static VALUE
rb_str_casecmp_p(VALUE str1, VALUE str2)
{
    VALUE s = rb_check_string_type(str2);
    if (NIL_P(s)) {
        return Qnil;
    }
    return str_casecmp_p(str1, s);
}

static VALUE
rb_str_center(int argc, VALUE *argv, VALUE str)
{
    return rb_str_justify(argc, argv, str, 'c');
}

static VALUE
rb_str_chars(VALUE str)
{
    VALUE ary = WANTARRAY("chars", rb_str_strlen(str));
    return rb_str_enumerate_chars(str, ary);
}

static VALUE
rb_str_chomp(int argc, VALUE *argv, VALUE str)
{
    VALUE rs = chomp_rs(argc, argv);
    if (NIL_P(rs)) return str_duplicate(rb_cString, str);
    return rb_str_subseq(str, 0, chompped_length(str, rs));
}

static VALUE
rb_str_chomp_bang(int argc, VALUE *argv, VALUE str)
{
    VALUE rs;
    str_modifiable(str);
    if (RSTRING_LEN(str) == 0 && argc < 2) return Qnil;
    rs = chomp_rs(argc, argv);
    if (NIL_P(rs)) return Qnil;
    return rb_str_chomp_string(str, rs);
}

static VALUE
rb_str_chop(VALUE str)
{
    return rb_str_subseq(str, 0, chopped_length(str));
}

static VALUE
rb_str_chop_bang(VALUE str)
{
    str_modify_keep_cr(str);
    if (RSTRING_LEN(str) > 0) {
        long len;
        len = chopped_length(str);
        STR_SET_LEN(str, len);
        TERM_FILL(&RSTRING_PTR(str)[len], TERM_LEN(str));
        if (ENC_CODERANGE(str) != ENC_CODERANGE_7BIT) {
            ENC_CODERANGE_CLEAR(str);
        }
        return str;
    }
    return Qnil;
}

static VALUE
rb_str_chr(VALUE str)
{
    return rb_str_substr(str, 0, 1);
}

static VALUE
rb_str_clear(VALUE str)
{
    str_discard(str);
    STR_SET_EMBED(str);
    STR_SET_LEN(str, 0);
    RSTRING_PTR(str)[0] = 0;
    if (rb_enc_asciicompat(STR_ENC_GET(str)))
        ENC_CODERANGE_SET(str, ENC_CODERANGE_7BIT);
    else
        ENC_CODERANGE_SET(str, ENC_CODERANGE_VALID);
    return str;
}

static VALUE
rb_str_codepoints(VALUE str)
{
    VALUE ary = WANTARRAY("codepoints", rb_str_strlen(str));
    return rb_str_enumerate_codepoints(str, ary);
}

static VALUE
rb_str_concat_multi(int argc, VALUE *argv, VALUE str)
{
    str_modifiable(str);

    if (argc == 1) {
        return rb_str_concat(str, argv[0]);
    }
    else if (argc > 1) {
        int i;
        VALUE arg_str = rb_str_tmp_new(0);
        rb_enc_copy(arg_str, str);
        for (i = 0; i < argc; i++) {
            rb_str_concat(arg_str, argv[i]);
        }
        rb_str_buf_append(str, arg_str);
    }

    return str;
}

static VALUE
rb_str_count(int argc, VALUE *argv, VALUE str)
{
    char table[TR_TABLE_SIZE];
    rb_encoding *enc = 0;
    VALUE del = 0, nodel = 0, tstr;
    char *s, *send;
    int i;
    int ascompat;
    size_t n = 0;

    rb_check_arity(argc, 1, UNLIMITED_ARGUMENTS);

    tstr = argv[0];
    StringValue(tstr);
    enc = rb_enc_check(str, tstr);
    if (argc == 1) {
        const char *ptstr;
        if (RSTRING_LEN(tstr) == 1 && rb_enc_asciicompat(enc) &&
            (ptstr = RSTRING_PTR(tstr),
             ONIGENC_IS_ALLOWED_REVERSE_MATCH(enc, (const unsigned char *)ptstr, (const unsigned char *)ptstr+1)) &&
            !is_broken_string(str)) {
            int clen;
            unsigned char c = rb_enc_codepoint_len(ptstr, ptstr+1, &clen, enc);

            s = RSTRING_PTR(str);
            if (!s || RSTRING_LEN(str) == 0) return INT2FIX(0);
            send = RSTRING_END(str);
            while (s < send) {
                if (*(unsigned char*)s++ == c) n++;
            }
            return SIZET2NUM(n);
        }
    }

    tr_setup_table(tstr, table, TRUE, &del, &nodel, enc);
    for (i=1; i<argc; i++) {
        tstr = argv[i];
        StringValue(tstr);
        enc = rb_enc_check(str, tstr);
        tr_setup_table(tstr, table, FALSE, &del, &nodel, enc);
    }

    s = RSTRING_PTR(str);
    if (!s || RSTRING_LEN(str) == 0) return INT2FIX(0);
    send = RSTRING_END(str);
    ascompat = rb_enc_asciicompat(enc);
    while (s < send) {
        unsigned int c;

        if (ascompat && (c = *(unsigned char*)s) < 0x80) {
            if (table[c]) {
                n++;
            }
            s++;
        }
        else {
            int clen;
            c = rb_enc_codepoint_len(s, send, &clen, enc);
            if (tr_find(c, table, del, nodel)) {
                n++;
            }
            s += clen;
        }
    }

    return SIZET2NUM(n);
}

static VALUE
rb_str_crypt(VALUE str, VALUE salt)
{
#ifdef HAVE_CRYPT_R
    VALUE databuf;
    struct crypt_data *data;
#   define CRYPT_END() ALLOCV_END(databuf)
#else
    extern char *crypt(const char *, const char *);
#   define CRYPT_END() rb_nativethread_lock_unlock(&crypt_mutex.lock)
#endif
    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);
    s = StringValueCStr(str);
    saltp = RSTRING_PTR(salt);
    if (RSTRING_LEN(salt) < 2 || !saltp[0] || !saltp[1]) {
        rb_raise(rb_eArgError, "salt too short (need >=2 bytes)");
    }

#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
#ifdef HAVE_CRYPT_R
    data = ALLOCV(databuf, sizeof(struct crypt_data));
# ifdef HAVE_STRUCT_CRYPT_DATA_INITIALIZED
    data->initialized = 0;
# endif
    res = crypt_r(s, saltp, data);
#else
    crypt_mutex_initialize();
    rb_nativethread_lock_lock(&crypt_mutex.lock);
    res = crypt(s, saltp);
#endif
    if (!res) {
        int err = errno;
        CRYPT_END();
        rb_syserr_fail(err, "crypt");
    }
    result = rb_str_new_cstr(res);
    CRYPT_END();
    return result;
}

static VALUE
rb_str_delete(int argc, VALUE *argv, VALUE str)
{
    str = str_duplicate(rb_cString, 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_delete_prefix(VALUE str, VALUE prefix)
{
    long prefixlen;

    prefixlen = deleted_prefix_length(str, prefix);
    if (prefixlen <= 0) return str_duplicate(rb_cString, str);

    return rb_str_subseq(str, prefixlen, RSTRING_LEN(str) - prefixlen);
}

static VALUE
rb_str_delete_prefix_bang(VALUE str, VALUE prefix)
{
    long prefixlen;
    str_modify_keep_cr(str);

    prefixlen = deleted_prefix_length(str, prefix);
    if (prefixlen <= 0) return Qnil;

    return rb_str_drop_bytes(str, prefixlen);
}

static VALUE
rb_str_delete_suffix(VALUE str, VALUE suffix)
{
    long suffixlen;

    suffixlen = deleted_suffix_length(str, suffix);
    if (suffixlen <= 0) return str_duplicate(rb_cString, str);

    return rb_str_subseq(str, 0, RSTRING_LEN(str) - suffixlen);
}

static VALUE
rb_str_delete_suffix_bang(VALUE str, VALUE suffix)
{
    long olen, suffixlen, len;
    str_modifiable(str);

    suffixlen = deleted_suffix_length(str, suffix);
    if (suffixlen <= 0) return Qnil;

    olen = RSTRING_LEN(str);
    str_modify_keep_cr(str);
    len = olen - suffixlen;
    STR_SET_LEN(str, len);
    TERM_FILL(&RSTRING_PTR(str)[len], TERM_LEN(str));
    if (ENC_CODERANGE(str) != ENC_CODERANGE_7BIT) {
        ENC_CODERANGE_CLEAR(str);
    }
    return str;
}

static VALUE
rb_str_downcase(int argc, VALUE *argv, VALUE str)
{
    rb_encoding *enc;
    OnigCaseFoldType flags = ONIGENC_CASE_DOWNCASE;
    VALUE ret;

    flags = check_case_options(argc, argv, flags);
    enc = str_true_enc(str);
    if (case_option_single_p(flags, enc, str)) {
        ret = rb_str_new(RSTRING_PTR(str), RSTRING_LEN(str));
        str_enc_copy_direct(ret, str);
        downcase_single(ret);
    }
    else if (flags&ONIGENC_CASE_ASCII_ONLY) {
        ret = rb_str_new(0, RSTRING_LEN(str));
        rb_str_ascii_casemap(str, ret, &flags, enc);
    }
    else {
        ret = rb_str_casemap(str, &flags, enc);
    }

    return ret;
}

static VALUE
rb_str_downcase_bang(int argc, VALUE *argv, VALUE str)
{
    rb_encoding *enc;
    OnigCaseFoldType flags = ONIGENC_CASE_DOWNCASE;

    flags = check_case_options(argc, argv, flags);
    str_modify_keep_cr(str);
    enc = str_true_enc(str);
    if (case_option_single_p(flags, enc, str)) {
        if (downcase_single(str))
            flags |= ONIGENC_CASE_MODIFIED;
    }
    else if (flags&ONIGENC_CASE_ASCII_ONLY)
        rb_str_ascii_casemap(str, str, &flags, enc);
    else
        str_shared_replace(str, rb_str_casemap(str, &flags, enc));

    if (ONIGENC_CASE_MODIFIED&flags) return str;
    return Qnil;
}

VALUE
rb_str_dump(VALUE str)
{
    int encidx = rb_enc_get_index(str);
    rb_encoding *enc = rb_enc_from_index(encidx);
    long len;
    const char *p, *pend;
    char *q, *qend;
    VALUE result;
    int u8 = (encidx == rb_utf8_encindex());
    static const char nonascii_suffix[] = ".dup.force_encoding(\"%s\")";

    len = 2;                    /* "" */
    if (!rb_enc_asciicompat(enc)) {
        len += strlen(nonascii_suffix) - rb_strlen_lit("%s");
        len += strlen(enc->name);
    }

    p = RSTRING_PTR(str); pend = p + RSTRING_LEN(str);
    while (p < pend) {
        int clen;
        unsigned char c = *p++;

        switch (c) {
          case '"':  case '\\':
          case '\n': case '\r':
          case '\t': case '\f':
          case '\013': case '\010': case '\007': case '\033':
            clen = 2;
            break;

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

          default:
            if (ISPRINT(c)) {
                clen = 1;
            }
            else {
                if (u8 && c > 0x7F) {   /* \u notation */
                    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);
                        if (cc <= 0xFFFF)
                            clen = 6;  /* \uXXXX */
                        else if (cc <= 0xFFFFF)
                            clen = 9;  /* \u{XXXXX} */
                        else
                            clen = 10; /* \u{XXXXXX} */
                        p += MBCLEN_CHARFOUND_LEN(n)-1;
                        break;
                    }
                }
                clen = 4;       /* \xNN */
            }
            break;
        }

        if (clen > LONG_MAX - len) {
            rb_raise(rb_eRuntimeError, "string size too big");
        }
        len += clen;
    }

    result = rb_str_new(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;
                    if (cc <= 0xFFFF)
                        snprintf(q, qend-q, "u%04X", cc);    /* \uXXXX */
                    else
                        snprintf(q, qend-q, "u{%X}", cc);  /* \u{XXXXX} or \u{XXXXXX} */
                    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, nonascii_suffix, enc->name);
        encidx = rb_ascii8bit_encindex();
    }
    /* result from dump is ASCII */
    rb_enc_associate_index(result, encidx);
    ENC_CODERANGE_SET(result, ENC_CODERANGE_7BIT);
    return result;
}

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

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

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

static VALUE
rb_str_each_grapheme_cluster(VALUE str)
{
    RETURN_SIZED_ENUMERATOR(str, 0, 0, rb_str_each_grapheme_cluster_size);
    return rb_str_enumerate_grapheme_clusters(str, 0);
}

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

static VALUE
rb_str_empty(VALUE str)
{
    return RBOOL(RSTRING_LEN(str) == 0);
}

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;

    for (i=0; i<argc; i++) {
        VALUE tmp = argv[i];
        const char *p, *s, *e;
        long slen, tlen;
        rb_encoding *enc;

        StringValue(tmp);
        enc = rb_enc_check(str, tmp);
        if ((tlen = RSTRING_LEN(tmp)) == 0) return Qtrue;
        if ((slen = RSTRING_LEN(str)) < tlen) continue;
        p = RSTRING_PTR(str);
        e = p + slen;
        s = e - tlen;
        if (!at_char_boundary(p, s, e, enc))
            continue;
        if (memcmp(s, RSTRING_PTR(tmp), tlen) == 0)
            return Qtrue;
    }
    return Qfalse;
}

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

static VALUE
rb_str_force_encoding(VALUE str, VALUE enc)
{
    str_modifiable(str);

    rb_encoding *encoding = rb_to_encoding(enc);
    int idx = rb_enc_to_index(encoding);

    // If the encoding is unchanged, we do nothing.
    if (ENCODING_GET(str) == idx) {
        return str;
    }

    rb_enc_associate_index(str, idx);

    // If the coderange was 7bit and the new encoding is ASCII-compatible
    // we can keep the coderange.
    if (ENC_CODERANGE(str) == ENC_CODERANGE_7BIT && encoding && rb_enc_asciicompat(encoding)) {
        return str;
    }

    ENC_CODERANGE_CLEAR(str);
    return str;
}

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_grapheme_clusters(VALUE str)
{
    VALUE ary = WANTARRAY("grapheme_clusters", rb_str_strlen(str));
    return rb_str_enumerate_grapheme_clusters(str, ary);
}

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_hash_m(VALUE str)
{
    st_index_t hval = rb_str_hash(str);
    return ST2FIX(hval);
}

static VALUE
rb_str_hex(VALUE str)
{
    return rb_str_to_inum(str, 16, FALSE);
}

VALUE
rb_str_include(VALUE str, VALUE arg)
{
    long i;

    StringValue(arg);
    i = rb_str_index(str, arg, 0);

    return RBOOL(i != -1);
}

static VALUE
rb_str_index_m(int argc, VALUE *argv, VALUE str)
{
    VALUE sub;
    VALUE initpos;
    rb_encoding *enc = STR_ENC_GET(str);
    long pos;

    if (rb_scan_args(argc, argv, "11", &sub, &initpos) == 2) {
        long slen = str_strlen(str, enc); /* str's enc */
        pos = NUM2LONG(initpos);
        if (pos < 0 ? (pos += slen) < 0 : pos > slen) {
            if (RB_TYPE_P(sub, T_REGEXP)) {
                rb_backref_set(Qnil);
            }
            return Qnil;
        }
    }
    else {
        pos = 0;
    }

    if (RB_TYPE_P(sub, T_REGEXP)) {
        pos = str_offset(RSTRING_PTR(str), RSTRING_END(str), pos,
                         enc, single_byte_optimizable(str));

        if (rb_reg_search(sub, str, pos, 0) >= 0) {
            VALUE match = rb_backref_get();
            struct re_registers *regs = RMATCH_REGS(match);
            pos = rb_str_sublen(str, BEG(0));
            return LONG2NUM(pos);
        }
    }
    else {
        StringValue(sub);
        pos = rb_str_index(str, sub, pos);
        if (pos >= 0) {
            pos = rb_str_sublen(str, pos);
            return LONG2NUM(pos);
        }
    }
    return Qnil;
}

static VALUE
rb_str_insert(VALUE str, VALUE idx, VALUE str2)
{
    long pos = NUM2LONG(idx);

    if (pos == -1) {
        return rb_str_append(str, str2);
    }
    else if (pos < 0) {
        pos++;
    }
    rb_str_update(str, pos, 0, str2);
    return str;
}

VALUE
rb_str_inspect(VALUE str)
{
    int encidx = ENCODING_GET(str);
    rb_encoding *enc = rb_enc_from_index(encidx);
    const char *p, *pend, *prev;
    char buf[CHAR_ESC_LEN + 1];
    VALUE result = rb_str_buf_new(0);
    rb_encoding *resenc = rb_default_internal_encoding();
    int unicode_p = rb_enc_unicode_p(enc);
    int asciicompat = rb_enc_asciicompat(enc);

    if (resenc == NULL) resenc = rb_default_external_encoding();
    if (!rb_enc_asciicompat(resenc)) resenc = rb_usascii_encoding();
    rb_enc_associate(result, resenc);
    str_buf_cat2(result, "\"");

    p = RSTRING_PTR(str); pend = RSTRING_END(str);
    prev = p;
    while (p < pend) {
        unsigned int c, cc;
        int n;

        n = rb_enc_precise_mbclen(p, pend, enc);
        if (!MBCLEN_CHARFOUND_P(n)) {
            if (p > prev) str_buf_cat(result, prev, p - prev);
            n = rb_enc_mbminlen(enc);
            if (pend < p + n)
                n = (int)(pend - p);
            while (n--) {
                snprintf(buf, CHAR_ESC_LEN, "\\x%02X", *p & 0377);
                str_buf_cat(result, buf, strlen(buf));
                prev = ++p;
            }
            continue;
        }
        n = MBCLEN_CHARFOUND_LEN(n);
        c = rb_enc_mbc_to_codepoint(p, pend, enc);
        p += n;
        if ((asciicompat || unicode_p) &&
          (c == '"'|| c == '\\' ||
            (c == '#' &&
             p < pend &&
             MBCLEN_CHARFOUND_P(rb_enc_precise_mbclen(p,pend,enc)) &&
             (cc = rb_enc_codepoint(p,pend,enc),
              (cc == '$' || cc == '@' || cc == '{'))))) {
            if (p - n > prev) str_buf_cat(result, prev, p - n - prev);
            str_buf_cat2(result, "\\");
            if (asciicompat || enc == resenc) {
                prev = p - n;
                continue;
            }
        }
        switch (c) {
          case '\n': cc = 'n'; break;
          case '\r': cc = 'r'; break;
          case '\t': cc = 't'; break;
          case '\f': cc = 'f'; break;
          case '\013': cc = 'v'; break;
          case '\010': cc = 'b'; break;
          case '\007': cc = 'a'; break;
          case 033: cc = 'e'; break;
          default: cc = 0; break;
        }
        if (cc) {
            if (p - n > prev) str_buf_cat(result, prev, p - n - prev);
            buf[0] = '\\';
            buf[1] = (char)cc;
            str_buf_cat(result, buf, 2);
            prev = p;
            continue;
        }
        /* The special casing of 0x85 (NEXT_LINE) here is because
         * Oniguruma historically treats it as printable, but it
         * doesn't match the print POSIX bracket class or character
         * property in regexps.
         *
         * See Ruby Bug #16842 for details:
         * https://bugs.ruby-lang.org/issues/16842
         */
        if ((enc == resenc && rb_enc_isprint(c, enc) && c != 0x85) ||
            (asciicompat && rb_enc_isascii(c, enc) && ISPRINT(c))) {
            continue;
        }
        else {
            if (p - n > prev) str_buf_cat(result, prev, p - n - prev);
            rb_str_buf_cat_escaped_char(result, c, unicode_p);
            prev = p;
            continue;
        }
    }
    if (p > prev) str_buf_cat(result, prev, p - prev);
    str_buf_cat2(result, "\"");

    return result;
}

VALUE
rb_str_intern(VALUE str)
{
    VALUE sym;

    GLOBAL_SYMBOLS_ENTER(symbols);
    {
        sym = lookup_str_sym_with_lock(symbols, str);

        if (sym) {
            // ok
        }
        else if (USE_SYMBOL_GC) {
            rb_encoding *enc = rb_enc_get(str);
            rb_encoding *ascii = rb_usascii_encoding();
            if (enc != ascii && sym_check_asciionly(str, false)) {
                str = rb_str_dup(str);
                rb_enc_associate(str, ascii);
                OBJ_FREEZE(str);
                enc = ascii;
            }
            else {
                str = rb_str_dup(str);
                OBJ_FREEZE(str);
            }
            str = rb_fstring(str);
            int type = rb_str_symname_type(str, IDSET_ATTRSET_FOR_INTERN);
            if (type < 0) type = ID_JUNK;
            sym = dsymbol_alloc(symbols, rb_cSymbol, str, enc, type);
        }
        else {
            ID id = intern_str(str, 0);
            sym = ID2SYM(id);
        }
    }
    GLOBAL_SYMBOLS_LEAVE();
    return sym;
}

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

static VALUE
rb_str_lines(int argc, VALUE *argv, VALUE str)
{
    VALUE ary = WANTARRAY("lines", 0);
    return rb_str_enumerate_lines(argc, argv, str, ary);
}

static VALUE
rb_str_ljust(int argc, VALUE *argv, VALUE str)
{
    return rb_str_justify(argc, argv, str, 'l');
}

static VALUE
rb_str_lstrip(VALUE str)
{
    char *start;
    long len, loffset;
    RSTRING_GETMEM(str, start, len);
    loffset = lstrip_offset(str, start, start+len, STR_ENC_GET(str));
    if (loffset <= 0) return str_duplicate(rb_cString, str);
    return rb_str_subseq(str, loffset, len - loffset);
}

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);
        TERM_FILL(start+len, rb_enc_mbminlen(enc));
        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_funcallv(get_pat(re), rb_intern("match"), argc, argv);
    if (!NIL_P(result) && rb_block_given_p()) {
        return rb_yield(result);
    }
    return result;
}

static VALUE
rb_str_match_m_p(int argc, VALUE *argv, VALUE str)
{
    VALUE re;
    rb_check_arity(argc, 1, 2);
    re = get_pat(argv[0]);
    return rb_reg_match_p(re, str, argc > 1 ? NUM2LONG(argv[1]) : 0);
}

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

static 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)) {
        if (rb_reg_search(sep, str, 0, 0) < 0) {
            goto failed;
        }
        VALUE match = rb_backref_get();
        struct re_registers *regs = RMATCH_REGS(match);

        pos = BEG(0);
        sep = rb_str_subseq(str, pos, END(0) - pos);
    }
    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)));

  failed:
    return rb_ary_new3(3, str_duplicate(rb_cString, str), str_new_empty_String(str), str_new_empty_String(str));
}

static VALUE
rb_str_prepend_multi(int argc, VALUE *argv, VALUE str)
{
    str_modifiable(str);

    if (argc == 1) {
        rb_str_update(str, 0L, 0L, argv[0]);
    }
    else if (argc > 1) {
        int i;
        VALUE arg_str = rb_str_tmp_new(0);
        rb_enc_copy(arg_str, str);
        for (i = 0; i < argc; i++) {
            rb_str_append(arg_str, argv[i]);
        }
        rb_str_update(str, 0L, 0L, arg_str);
    }

    return str;
}

static VALUE
rb_str_reverse(VALUE str)
{
    rb_encoding *enc;
    VALUE rev;
    char *s, *e, *p;
    int cr;

    if (RSTRING_LEN(str) <= 1) return str_duplicate(rb_cString, str);
    enc = STR_ENC_GET(str);
    rev = rb_str_new(0, RSTRING_LEN(str));
    s = RSTRING_PTR(str); e = RSTRING_END(str);
    p = RSTRING_END(rev);
    cr = ENC_CODERANGE(str);

    if (RSTRING_LEN(str) > 1) {
        if (single_byte_optimizable(str)) {
            while (s < e) {
                *--p = *s++;
            }
        }
        else if (cr == ENC_CODERANGE_VALID) {
            while (s < e) {
                int clen = rb_enc_fast_mbclen(s, e, enc);

                p -= clen;
                memcpy(p, s, clen);
                s += clen;
            }
        }
        else {
            cr = rb_enc_asciicompat(enc) ?
                ENC_CODERANGE_7BIT : ENC_CODERANGE_VALID;
            while (s < e) {
                int clen = rb_enc_mbclen(s, e, enc);

                if (clen > 1 || (*s & 0x80)) cr = ENC_CODERANGE_UNKNOWN;
                p -= clen;
                memcpy(p, s, clen);
                s += clen;
            }
        }
    }
    STR_SET_LEN(rev, RSTRING_LEN(str));
    str_enc_copy_direct(rev, str);
    ENC_CODERANGE_SET(rev, cr);

    return rev;
}

static VALUE
rb_str_reverse_bang(VALUE str)
{
    if (RSTRING_LEN(str) > 1) {
        if (single_byte_optimizable(str)) {
            char *s, *e, c;

            str_modify_keep_cr(str);
            s = RSTRING_PTR(str);
            e = RSTRING_END(str) - 1;
            while (s < e) {
                c = *s;
                *s++ = *e;
                *e-- = c;
            }
        }
        else {
            str_shared_replace(str, rb_str_reverse(str));
        }
    }
    else {
        str_modify_keep_cr(str);
    }
    return str;
}

static VALUE
rb_str_rindex_m(int argc, VALUE *argv, VALUE str)
{
    VALUE sub;
    VALUE initpos;
    rb_encoding *enc = STR_ENC_GET(str);
    long pos, len = str_strlen(str, enc); /* str's enc */

    if (rb_scan_args(argc, argv, "11", &sub, &initpos) == 2) {
        pos = NUM2LONG(initpos);
        if (pos < 0 && (pos += len) < 0) {
            if (RB_TYPE_P(sub, T_REGEXP)) {
                rb_backref_set(Qnil);
            }
            return Qnil;
        }
        if (pos > len) pos = len;
    }
    else {
        pos = len;
    }

    if (RB_TYPE_P(sub, T_REGEXP)) {
        /* enc = rb_enc_check(str, sub); */
        pos = str_offset(RSTRING_PTR(str), RSTRING_END(str), pos,
                         enc, single_byte_optimizable(str));

        if (rb_reg_search(sub, str, pos, 1) >= 0) {
            VALUE match = rb_backref_get();
            struct re_registers *regs = RMATCH_REGS(match);
            pos = rb_str_sublen(str, BEG(0));
            return LONG2NUM(pos);
        }
    }
    else {
        StringValue(sub);
        pos = rb_str_rindex(str, sub, pos);
        if (pos >= 0) {
            pos = rb_str_sublen(str, pos);
            return LONG2NUM(pos);
        }
    }
    return Qnil;
}

static VALUE
rb_str_rjust(int argc, VALUE *argv, VALUE str)
{
    return rb_str_justify(argc, argv, str, 'r');
}

static VALUE
rb_str_rpartition(VALUE str, VALUE sep)
{
    long pos = RSTRING_LEN(str);

    sep = get_pat_quoted(sep, 0);
    if (RB_TYPE_P(sep, T_REGEXP)) {
        if (rb_reg_search(sep, str, pos, 1) < 0) {
            goto failed;
        }
        VALUE match = rb_backref_get();
        struct re_registers *regs = RMATCH_REGS(match);

        pos = BEG(0);
        sep = rb_str_subseq(str, pos, END(0) - pos);
    }
    else {
        pos = rb_str_sublen(str, pos);
        pos = rb_str_rindex(str, sep, pos);
        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)));
  failed:
    return rb_ary_new3(3, str_new_empty_String(str), str_new_empty_String(str), str_duplicate(rb_cString, str));
}

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

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

    if (roffset <= 0) return str_duplicate(rb_cString, str);
    return rb_str_subseq(str, 0, olen-roffset);
}

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

    str_modify_keep_cr(str);
    enc = STR_ENC_GET(str);
    RSTRING_GETMEM(str, start, olen);
    roffset = rstrip_offset(str, start, start+olen, enc);
    if (roffset > 0) {
        long len = olen - roffset;

        STR_SET_LEN(str, len);
        TERM_FILL(start+len, rb_enc_mbminlen(enc));
        return str;
    }
    return Qnil;
}

static VALUE
rb_str_scan(VALUE str, VALUE pat)
{
    VALUE result;
    long start = 0;
    long last = -1, prev = 0;
    char *p = RSTRING_PTR(str); long len = RSTRING_LEN(str);

    pat = get_pat_quoted(pat, 1);
    mustnot_broken(str);
    if (!rb_block_given_p()) {
        VALUE ary = rb_ary_new();

        while (!NIL_P(result = scan_once(str, pat, &start, 0))) {
            last = prev;
            prev = start;
            rb_ary_push(ary, result);
        }
        if (last >= 0) rb_pat_search(pat, str, last, 1);
        else rb_backref_set(Qnil);
        return ary;
    }

    while (!NIL_P(result = scan_once(str, pat, &start, 1))) {
        last = prev;
        prev = start;
        rb_yield(result);
        str_mod_check(str, p, len);
    }
    if (last >= 0) rb_pat_search(pat, str, last, 1);
    return str;
}

static VALUE
str_scrub(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);
    return NIL_P(new) ? str_duplicate(rb_cString, str): new;
}

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;
}

VALUE
rb_str_setbyte(VALUE str, VALUE index, VALUE value)
{
    long pos = NUM2LONG(index);
    long len = RSTRING_LEN(str);
    char *ptr, *head, *left = 0;
    rb_encoding *enc;
    int cr = ENC_CODERANGE_UNKNOWN, width, nlen;

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

    VALUE v = rb_to_int(value);
    VALUE w = rb_int_and(v, INT2FIX(0xff));
    char byte = (char)(NUM2INT(w) & 0xFF);

    if (!str_independent(str))
        str_make_independent(str);
    enc = STR_ENC_GET(str);
    head = RSTRING_PTR(str);
    ptr = &head[pos];
    if (!STR_EMBED_P(str)) {
        cr = ENC_CODERANGE(str);
        switch (cr) {
          case ENC_CODERANGE_7BIT:
            left = ptr;
            *ptr = byte;
            if (ISASCII(byte)) goto end;
            nlen = rb_enc_precise_mbclen(left, head+len, enc);
            if (!MBCLEN_CHARFOUND_P(nlen))
                ENC_CODERANGE_SET(str, ENC_CODERANGE_BROKEN);
            else
                ENC_CODERANGE_SET(str, ENC_CODERANGE_VALID);
            goto end;
          case ENC_CODERANGE_VALID:
            left = rb_enc_left_char_head(head, ptr, head+len, enc);
            width = rb_enc_precise_mbclen(left, head+len, enc);
            *ptr = byte;
            nlen = rb_enc_precise_mbclen(left, head+len, enc);
            if (!MBCLEN_CHARFOUND_P(nlen))
                ENC_CODERANGE_SET(str, ENC_CODERANGE_BROKEN);
            else if (MBCLEN_CHARFOUND_LEN(nlen) != width || ISASCII(byte))
                ENC_CODERANGE_CLEAR(str);
            goto end;
        }
    }
    ENC_CODERANGE_CLEAR(str);
    *ptr = byte;

  end:
    return value;
}

# File lib/shellwords.rb, line 238
def shellescape
  Shellwords.escape(self)
end

# File lib/shellwords.rb, line 227
def shellsplit
  Shellwords.split(self)
end

static VALUE
rb_str_slice_bang(int argc, VALUE *argv, VALUE str)
{
    VALUE result = Qnil;
    VALUE indx;
    long beg, len = 1;
    char *p;

    rb_check_arity(argc, 1, 2);
    str_modify_keep_cr(str);
    indx = argv[0];
    if (RB_TYPE_P(indx, T_REGEXP)) {
        if (rb_reg_search(indx, str, 0, 0) < 0) return Qnil;
        VALUE match = rb_backref_get();
        struct re_registers *regs = RMATCH_REGS(match);
        int nth = 0;
        if (argc > 1 && (nth = rb_reg_backref_number(match, argv[1])) < 0) {
            if ((nth += regs->num_regs) <= 0) return Qnil;
        }
        else if (nth >= regs->num_regs) return Qnil;
        beg = BEG(nth);
        len = END(nth) - beg;
        goto subseq;
    }
    else if (argc == 2) {
        beg = NUM2LONG(indx);
        len = NUM2LONG(argv[1]);
        goto num_index;
    }
    else if (FIXNUM_P(indx)) {
        beg = FIX2LONG(indx);
        if (!(p = rb_str_subpos(str, beg, &len))) return Qnil;
        if (!len) return Qnil;
        beg = p - RSTRING_PTR(str);
        goto subseq;
    }
    else if (RB_TYPE_P(indx, T_STRING)) {
        beg = rb_str_index(str, indx, 0);
        if (beg == -1) return Qnil;
        len = RSTRING_LEN(indx);
        result = str_duplicate(rb_cString, indx);
        goto squash;
    }
    else {
        switch (rb_range_beg_len(indx, &beg, &len, str_strlen(str, NULL), 0)) {
          case Qnil:
            return Qnil;
          case Qfalse:
            beg = NUM2LONG(indx);
            if (!(p = rb_str_subpos(str, beg, &len))) return Qnil;
            if (!len) return Qnil;
            beg = p - RSTRING_PTR(str);
            goto subseq;
          default:
            goto num_index;
        }
    }

  num_index:
    if (!(p = rb_str_subpos(str, beg, &len))) return Qnil;
    beg = p - RSTRING_PTR(str);

  subseq:
    result = rb_str_new(RSTRING_PTR(str)+beg, len);
    rb_enc_cr_str_copy_for_substr(result, str);

  squash:
    if (len > 0) {
        if (beg == 0) {
            rb_str_drop_bytes(str, len);
        }
        else {
            char *sptr = RSTRING_PTR(str);
            long slen = RSTRING_LEN(str);
            if (beg + len > slen) /* pathological check */
                len = slen - beg;
            memmove(sptr + beg,
                    sptr + beg + len,
                    slen - (beg + len));
            slen -= len;
            STR_SET_LEN(str, slen);
            TERM_FILL(&sptr[slen], TERM_LEN(str));
        }
    }
    return result;
}

static VALUE
rb_str_split_m(int argc, VALUE *argv, VALUE str)
{
    rb_encoding *enc;
    VALUE spat;
    VALUE limit;
    split_type_t split_type;
    long beg, end, i = 0, empty_count = -1;
    int lim = 0;
    VALUE result, tmp;

    result = rb_block_given_p() ? Qfalse : Qnil;
    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 result ? rb_ary_new2(0) : str;
            tmp = str_duplicate(rb_cString, str);
            if (!result) {
                rb_yield(tmp);
                return str;
            }
            return rb_ary_new3(1, tmp);
        }
        i = 1;
    }
    if (NIL_P(limit) && !lim) empty_count = 0;

    enc = STR_ENC_GET(str);
    split_type = SPLIT_TYPE_REGEXP;
    if (!NIL_P(spat)) {
        spat = get_pat_quoted(spat, 0);
    }
    else if (NIL_P(spat = rb_fs)) {
        split_type = SPLIT_TYPE_AWK;
    }
    else if (!(spat = rb_fs_check(spat))) {
        rb_raise(rb_eTypeError, "value of $; must be String or Regexp");
    }
    else {
        rb_category_warn(RB_WARN_CATEGORY_DEPRECATED, "$; is set to non-nil value");
    }
    if (split_type != SPLIT_TYPE_AWK) {
        switch (BUILTIN_TYPE(spat)) {
          case T_REGEXP:
            rb_reg_options(spat); /* check if uninitialized */
            tmp = RREGEXP_SRC(spat);
            split_type = literal_split_pattern(tmp, SPLIT_TYPE_REGEXP);
            if (split_type == SPLIT_TYPE_AWK) {
                spat = tmp;
                split_type = SPLIT_TYPE_STRING;
            }
            break;

          case T_STRING:
            mustnot_broken(spat);
            split_type = literal_split_pattern(spat, SPLIT_TYPE_STRING);
            break;

          default:
            UNREACHABLE_RETURN(Qnil);
        }
    }

#define SPLIT_STR(beg, len) ( \
        empty_count = split_string(result, str, beg, len, empty_count), \
        str_mod_check(str, str_start, str_len))

    beg = 0;
    char *ptr = RSTRING_PTR(str);
    char *const str_start = ptr;
    const long str_len = RSTRING_LEN(str);
    char *const eptr = str_start + str_len;
    if (split_type == SPLIT_TYPE_AWK) {
        char *bptr = ptr;
        int skip = 1;
        unsigned int c;

        if (result) result = rb_ary_new();
        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)) {
                    SPLIT_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)) {
                    SPLIT_STR(beg, end-beg);
                    skip = 1;
                    beg = ptr - bptr;
                    if (!NIL_P(limit)) ++i;
                }
                else {
                    end = ptr - bptr;
                }
            }
        }
    }
    else if (split_type == SPLIT_TYPE_STRING) {
        char *substr_start = ptr;
        char *sptr = RSTRING_PTR(spat);
        long slen = RSTRING_LEN(spat);

        if (result) result = rb_ary_new();
        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;
            }
            SPLIT_STR(substr_start - str_start, (ptr+end) - substr_start);
            str_mod_check(spat, sptr, slen);
            ptr += end + slen;
            substr_start = ptr;
            if (!NIL_P(limit) && lim <= ++i) break;
        }
        beg = ptr - str_start;
    }
    else if (split_type == SPLIT_TYPE_CHARS) {
        int n;

        if (result) result = rb_ary_new_capa(RSTRING_LEN(str));
        mustnot_broken(str);
        enc = rb_enc_get(str);
        while (ptr < eptr &&
               (n = rb_enc_precise_mbclen(ptr, eptr, enc)) > 0) {
            SPLIT_STR(ptr - str_start, n);
            ptr += n;
            if (!NIL_P(limit) && lim <= ++i) break;
        }
        beg = ptr - str_start;
    }
    else {
        if (result) result = rb_ary_new();
        long len = RSTRING_LEN(str);
        long start = beg;
        long idx;
        int last_null = 0;
        struct re_registers *regs;
        VALUE match = 0;

        for (; rb_reg_search(spat, str, start, 0) >= 0;
             (match ? (rb_match_unbusy(match), rb_backref_set(match)) : (void)0)) {
            match = rb_backref_get();
            if (!result) rb_match_busy(match);
            regs = RMATCH_REGS(match);
            end = BEG(0);
            if (start == end && BEG(0) == END(0)) {
                if (!ptr) {
                    SPLIT_STR(0, 0);
                    break;
                }
                else if (last_null == 1) {
                    SPLIT_STR(beg, rb_enc_fast_mbclen(ptr+beg, eptr, enc));
                    beg = start;
                }
                else {
                    if (start == len)
                        start++;
                    else
                        start += rb_enc_fast_mbclen(ptr+start,eptr,enc);
                    last_null = 1;
                    continue;
                }
            }
            else {
                SPLIT_STR(beg, end-beg);
                beg = start = END(0);
            }
            last_null = 0;

            for (idx=1; idx < regs->num_regs; idx++) {
                if (BEG(idx) == -1) continue;
                SPLIT_STR(BEG(idx), END(idx)-BEG(idx));
            }
            if (!NIL_P(limit) && lim <= ++i) break;
        }
        if (match) rb_match_unbusy(match);
    }
    if (RSTRING_LEN(str) > 0 && (!NIL_P(limit) || RSTRING_LEN(str) > beg || lim < 0)) {
        SPLIT_STR(beg, RSTRING_LEN(str)-beg);
    }

    return result ? result : str;
}

static VALUE
rb_str_squeeze(int argc, VALUE *argv, VALUE str)
{
    str = str_duplicate(rb_cString, 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;
    unsigned 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 = (unsigned char *)RSTRING_PTR(str);
    if (!s || RSTRING_LEN(str) == 0) return Qnil;
    send = (unsigned char *)RSTRING_END(str);
    save = -1;
    ascompat = rb_enc_asciicompat(enc);

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

            if (ascompat && (c = *s) < 0x80) {
                if (c != save || (argc > 0 && !squeez[c])) {
                    *t++ = save = c;
                }
                s++;
            }
            else {
                c = rb_enc_codepoint_len((char *)s, (char *)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((char *)t, TERM_LEN(str));
    if ((char *)t - RSTRING_PTR(str) != RSTRING_LEN(str)) {
        STR_SET_LEN(str, (char *)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];
        if (RB_TYPE_P(tmp, T_REGEXP)) {
            if (rb_reg_start_with_p(tmp, str))
                return Qtrue;
        }
        else {
            const char *p, *s, *e;
            long slen, tlen;
            rb_encoding *enc;

            StringValue(tmp);
            enc = rb_enc_check(str, tmp);
            if ((tlen = RSTRING_LEN(tmp)) == 0) return Qtrue;
            if ((slen = RSTRING_LEN(str)) < tlen) continue;
            p = RSTRING_PTR(str);
            e = p + slen;
            s = p + tlen;
            if (!at_char_right_boundary(p, s, e, enc))
                continue;
            if (memcmp(p, RSTRING_PTR(tmp), tlen) == 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 str_duplicate(rb_cString, 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);
        TERM_FILL(start+len, rb_enc_mbminlen(enc));
        return str;
    }
    return Qnil;
}

static VALUE
rb_str_sub(int argc, VALUE *argv, VALUE str)
{
    str = str_duplicate(rb_cString, 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;
    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);
        }
    }

    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_inspect_name(str_enc),
                         rb_enc_inspect_name(STR_ENC_GET(repl)));
            }
            enc = STR_ENC_GET(repl);
        }
        rb_str_modify(str);
        rb_enc_associate(str, enc);
        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;
        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);
        }
        rp = RSTRING_PTR(repl);
        memmove(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);

        RB_GC_GUARD(match);

        return str;
    }
    return Qnil;
}

VALUE
rb_str_succ(VALUE orig)
{
    VALUE str;
    str = rb_str_new(RSTRING_PTR(orig), RSTRING_LEN(orig));
    rb_enc_cr_str_copy_for_substr(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)
{
    int bits = 16;
    char *ptr, *p, *pend;
    long len;
    VALUE sum = INT2FIX(0);
    unsigned long sum0 = 0;

    if (rb_check_arity(argc, 0, 1) && (bits = NUM2INT(argv[0])) < 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), idLTLT, 1, INT2FIX(bits));
            mod = rb_funcall(mod, '-', 1, INT2FIX(1));
            sum = rb_funcall(sum, '&', 1, mod);
        }
    }
    return sum;
}

static VALUE
rb_str_swapcase(int argc, VALUE *argv, VALUE str)
{
    rb_encoding *enc;
    OnigCaseFoldType flags = ONIGENC_CASE_UPCASE | ONIGENC_CASE_DOWNCASE;
    VALUE ret;

    flags = check_case_options(argc, argv, flags);
    enc = str_true_enc(str);
    if (RSTRING_LEN(str) == 0 || !RSTRING_PTR(str)) return str_duplicate(rb_cString, str);
    if (flags&ONIGENC_CASE_ASCII_ONLY) {
        ret = rb_str_new(0, RSTRING_LEN(str));
        rb_str_ascii_casemap(str, ret, &flags, enc);
    }
    else {
        ret = rb_str_casemap(str, &flags, enc);
    }
    return ret;
}

static VALUE
rb_str_swapcase_bang(int argc, VALUE *argv, VALUE str)
{
    rb_encoding *enc;
    OnigCaseFoldType flags = ONIGENC_CASE_UPCASE | ONIGENC_CASE_DOWNCASE;

    flags = check_case_options(argc, argv, flags);
    str_modify_keep_cr(str);
    enc = str_true_enc(str);
    if (flags&ONIGENC_CASE_ASCII_ONLY)
        rb_str_ascii_casemap(str, str, &flags, enc);
    else
        str_shared_replace(str, rb_str_casemap(str, &flags, enc));

    if (ONIGENC_CASE_MODIFIED&flags) return str;
    return Qnil;
}

static VALUE
string_to_c(VALUE self)
{
    VALUE num;

    rb_must_asciicompat(self);

    (void)parse_comp(rb_str_fill_terminator(self, 1), FALSE, &num);

    return num;
}

static VALUE
rb_str_to_f(VALUE str)
{
    return DBL2NUM(rb_str_to_dbl(str, FALSE));
}

static VALUE
rb_str_to_i(int argc, VALUE *argv, VALUE str)
{
    int base = 10;

    if (rb_check_arity(argc, 0, 1) && (base = NUM2INT(argv[0])) < 0) {
        rb_raise(rb_eArgError, "invalid radix %d", base);
    }
    return rb_str_to_inum(str, base, FALSE);
}

static VALUE
string_to_r(VALUE self)
{
    VALUE num;

    rb_must_asciicompat(self);

    num = parse_rat(RSTRING_PTR(self), RSTRING_END(self), 0, TRUE);

    if (RB_FLOAT_TYPE_P(num) && !FLOAT_ZERO_P(num))
        rb_raise(rb_eFloatDomainError, "Infinity");
    return num;
}

static VALUE
rb_str_to_s(VALUE str)
{
    if (rb_obj_class(str) != rb_cString) {
        return str_duplicate(rb_cString, str);
    }
    return str;
}

static VALUE
rb_str_tr(VALUE str, VALUE src, VALUE repl)
{
    str = str_duplicate(rb_cString, str);
    tr_trans(str, src, repl, 0);
    return str;
}

static VALUE
rb_str_tr_bang(VALUE str, VALUE src, VALUE repl)
{
    return tr_trans(str, src, repl, 0);
}

static VALUE
rb_str_tr_s(VALUE str, VALUE src, VALUE repl)
{
    str = str_duplicate(rb_cString, 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);
}

static VALUE
str_undump(VALUE str)
{
    const char *s = RSTRING_PTR(str);
    const char *s_end = RSTRING_END(str);
    rb_encoding *enc = rb_enc_get(str);
    VALUE undumped = rb_enc_str_new(s, 0L, enc);
    bool utf8 = false;
    bool binary = false;
    int w;

    rb_must_asciicompat(str);
    if (rb_str_is_ascii_only_p(str) == Qfalse) {
        rb_raise(rb_eRuntimeError, "non-ASCII character detected");
    }
    if (!str_null_check(str, &w)) {
        rb_raise(rb_eRuntimeError, "string contains null byte");
    }
    if (RSTRING_LEN(str) < 2) goto invalid_format;
    if (*s != '"') goto invalid_format;

    /* strip '"' at the start */
    s++;

    for (;;) {
        if (s >= s_end) {
            rb_raise(rb_eRuntimeError, "unterminated dumped string");
        }

        if (*s == '"') {
            /* epilogue */
            s++;
            if (s == s_end) {
                /* ascii compatible dumped string */
                break;
            }
            else {
                static const char force_encoding_suffix[] = ".force_encoding(\""; /* "\")" */
                static const char dup_suffix[] = ".dup";
                const char *encname;
                int encidx;
                ptrdiff_t size;

                /* check separately for strings dumped by older versions */
                size = sizeof(dup_suffix) - 1;
                if (s_end - s > size && memcmp(s, dup_suffix, size) == 0) s += size;

                size = sizeof(force_encoding_suffix) - 1;
                if (s_end - s <= size) goto invalid_format;
                if (memcmp(s, force_encoding_suffix, size) != 0) goto invalid_format;
                s += size;

                if (utf8) {
                    rb_raise(rb_eRuntimeError, "dumped string contained Unicode escape but used force_encoding");
                }

                encname = s;
                s = memchr(s, '"', s_end-s);
                size = s - encname;
                if (!s) goto invalid_format;
                if (s_end - s != 2) goto invalid_format;
                if (s[0] != '"' || s[1] != ')') goto invalid_format;

                encidx = rb_enc_find_index2(encname, (long)size);
                if (encidx < 0) {
                    rb_raise(rb_eRuntimeError, "dumped string has unknown encoding name");
                }
                rb_enc_associate_index(undumped, encidx);
            }
            break;
        }

        if (*s == '\\') {
            s++;
            if (s >= s_end) {
                rb_raise(rb_eRuntimeError, "invalid escape");
            }
            undump_after_backslash(undumped, &s, s_end, &enc, &utf8, &binary);
        }
        else {
            rb_str_cat(undumped, s++, 1);
        }
    }

    RB_GC_GUARD(str);

    return undumped;
invalid_format:
    rb_raise(rb_eRuntimeError, "invalid dumped string; not wrapped with '\"' nor '\"...\".force_encoding(\"...\")' form");
}

static VALUE
rb_str_unicode_normalize(int argc, VALUE *argv, VALUE str)
{
    return unicode_normalize_common(argc, argv, str, id_normalize);
}

static VALUE
rb_str_unicode_normalize_bang(int argc, VALUE *argv, VALUE str)
{
    return rb_str_replace(str, unicode_normalize_common(argc, argv, str, id_normalize));
}

static VALUE
rb_str_unicode_normalized_p(int argc, VALUE *argv, VALUE str)
{
    return unicode_normalize_common(argc, argv, str, id_normalized_p);
}

# File pack.rb, line 23
def unpack(fmt, offset: 0)
  Primitive.attr! :use_block
  Primitive.pack_unpack(fmt, offset)
end

# File pack.rb, line 33
def unpack1(fmt, offset: 0)
  Primitive.pack_unpack1(fmt, offset)
end

static VALUE
rb_str_upcase(int argc, VALUE *argv, VALUE str)
{
    rb_encoding *enc;
    OnigCaseFoldType flags = ONIGENC_CASE_UPCASE;
    VALUE ret;

    flags = check_case_options(argc, argv, flags);
    enc = str_true_enc(str);
    if (case_option_single_p(flags, enc, str)) {
        ret = rb_str_new(RSTRING_PTR(str), RSTRING_LEN(str));
        str_enc_copy_direct(ret, str);
        upcase_single(ret);
    }
    else if (flags&ONIGENC_CASE_ASCII_ONLY) {
        ret = rb_str_new(0, RSTRING_LEN(str));
        rb_str_ascii_casemap(str, ret, &flags, enc);
    }
    else {
        ret = rb_str_casemap(str, &flags, enc);
    }

    return ret;
}

static VALUE
rb_str_upcase_bang(int argc, VALUE *argv, VALUE str)
{
    rb_encoding *enc;
    OnigCaseFoldType flags = ONIGENC_CASE_UPCASE;

    flags = check_case_options(argc, argv, flags);
    str_modify_keep_cr(str);
    enc = str_true_enc(str);
    if (case_option_single_p(flags, enc, str)) {
        if (upcase_single(str))
            flags |= ONIGENC_CASE_MODIFIED;
    }
    else if (flags&ONIGENC_CASE_ASCII_ONLY)
        rb_str_ascii_casemap(str, str, &flags, enc);
    else
        str_shared_replace(str, rb_str_casemap(str, &flags, enc));

    if (ONIGENC_CASE_MODIFIED&flags) return str;
    return Qnil;
}

static VALUE
rb_str_upto(int argc, VALUE *argv, VALUE beg)
{
    VALUE end, exclusive;

    rb_scan_args(argc, argv, "11", &end, &exclusive);
    RETURN_ENUMERATOR(beg, argc, argv);
    return rb_str_upto_each(beg, end, RTEST(exclusive), str_upto_i, Qnil);
}

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

    return RBOOL(cr != ENC_CODERANGE_BROKEN);
}