Method: Encoding::Converter#primitive_convert

Defined in:

transcode.c

#primitive_convert(source_buffer, destination_buffer) ⇒ Object #primitive_convert(source_buffer, destination_buffer, destination_byteoffset) ⇒ Object #primitive_convert(source_buffer, destination_buffer, destination_byteoffset, destination_bytesize) ⇒ Object #primitive_convert(source_buffer, destination_buffer, destination_byteoffset, destination_bytesize, opt) ⇒ Object

possible opt elements:

hash form:
  :partial_input => true           # source buffer may be part of larger source
  :after_output => true            # stop conversion after output before input
integer form:
  Encoding::Converter::PARTIAL_INPUT
  Encoding::Converter::AFTER_OUTPUT

possible results:

:invalid_byte_sequence
:incomplete_input
:undefined_conversion
:after_output
:destination_buffer_full
:source_buffer_empty
:finished

primitive_convert converts source_buffer into destination_buffer.

source_buffer should be a string or nil. nil means an empty string.

destination_buffer should be a string.

destination_byteoffset should be an integer or nil. nil means the end of destination_buffer. If it is omitted, nil is assumed.

destination_bytesize should be an integer or nil. nil means unlimited. If it is omitted, nil is assumed.

opt should be nil, a hash or an integer. nil means no flags. If it is omitted, nil is assumed.

primitive_convert converts the content of source_buffer from beginning and store the result into destination_buffer.

destination_byteoffset and destination_bytesize specify the region which the converted result is stored. destination_byteoffset specifies the start position in destination_buffer in bytes. If destination_byteoffset is nil, destination_buffer.bytesize is used for appending the result. destination_bytesize specifies maximum number of bytes. If destination_bytesize is nil, destination size is unlimited. After conversion, destination_buffer is resized to destination_byteoffset + actually produced number of bytes. Also destination_buffer’s encoding is set to destination_encoding.

primitive_convert drops the converted part of source_buffer. the dropped part is converted in destination_buffer or buffered in Encoding::Converter object.

primitive_convert stops conversion when one of following condition met.

• invalid byte sequence found in source buffer (:invalid_byte_sequence) primitive_errinfo and last_error methods returns the detail of the error.

• unexpected end of source buffer (:incomplete_input) this occur only when :partial_input is not specified. primitive_errinfo and last_error methods returns the detail of the error.

• character not representable in output encoding (:undefined_conversion) primitive_errinfo and last_error methods returns the detail of the error.

• after some output is generated, before input is done (:after_output) this occur only when :after_output is specified.

• destination buffer is full (:destination_buffer_full) this occur only when destination_bytesize is non-nil.

• source buffer is empty (:source_buffer_empty) this occur only when :partial_input is specified.

• conversion is finished (:finished)

example:

ec = Encoding::Converter.new("UTF-8", "UTF-16BE")
ret = ec.primitive_convert(src="pi", dst="", nil, 100)
p [ret, src, dst] #=> [:finished, "", "\x00p\x00i"]

ec = Encoding::Converter.new("UTF-8", "UTF-16BE")
ret = ec.primitive_convert(src="pi", dst="", nil, 1)
p [ret, src, dst] #=> [:destination_buffer_full, "i", "\x00"]
ret = ec.primitive_convert(src, dst="", nil, 1)
p [ret, src, dst] #=> [:destination_buffer_full, "", "p"]
ret = ec.primitive_convert(src, dst="", nil, 1)
p [ret, src, dst] #=> [:destination_buffer_full, "", "\x00"]
ret = ec.primitive_convert(src, dst="", nil, 1)
p [ret, src, dst] #=> [:finished, "", "i"]

# File 'transcode.c', line 3680

static VALUE
econv_primitive_convert(int argc, VALUE *argv, VALUE self)
{
    VALUE input, output, output_byteoffset_v, output_bytesize_v, opt, flags_v;
    rb_econv_t *ec = check_econv(self);
    rb_econv_result_t res;
    const unsigned char *ip, *is;
    unsigned char *op, *os;
    long output_byteoffset, output_bytesize;
    unsigned long output_byteend;
    int flags;

    argc = rb_scan_args(argc, argv, "23:", &input, &output, &output_byteoffset_v, &output_bytesize_v, &flags_v, &opt);

    if (NIL_P(output_byteoffset_v))
        output_byteoffset = 0; /* dummy */
    else
        output_byteoffset = NUM2LONG(output_byteoffset_v);

    if (NIL_P(output_bytesize_v))
        output_bytesize = 0; /* dummy */
    else
        output_bytesize = NUM2LONG(output_bytesize_v);

    if (!NIL_P(flags_v)) {
	if (!NIL_P(opt)) {
	    rb_error_arity(argc + 1, 2, 5);
	}
	flags = NUM2INT(rb_to_int(flags_v));
    }
    else if (!NIL_P(opt)) {
        VALUE v;
        flags = 0;
        v = rb_hash_aref(opt, sym_partial_input);
        if (RTEST(v))
            flags |= ECONV_PARTIAL_INPUT;
        v = rb_hash_aref(opt, sym_after_output);
        if (RTEST(v))
            flags |= ECONV_AFTER_OUTPUT;
    }
    else {
        flags = 0;
    }

    StringValue(output);
    if (!NIL_P(input))
        StringValue(input);
    rb_str_modify(output);

    if (NIL_P(output_bytesize_v)) {
        output_bytesize = RSTRING_EMBED_LEN_MAX;
        if (!NIL_P(input) && output_bytesize < RSTRING_LEN(input))
            output_bytesize = RSTRING_LEN(input);
    }

  retry:

    if (NIL_P(output_byteoffset_v))
        output_byteoffset = RSTRING_LEN(output);

    if (output_byteoffset < 0)
        rb_raise(rb_eArgError, "negative output_byteoffset");

    if (RSTRING_LEN(output) < output_byteoffset)
        rb_raise(rb_eArgError, "output_byteoffset too big");

    if (output_bytesize < 0)
        rb_raise(rb_eArgError, "negative output_bytesize");

    output_byteend = (unsigned long)output_byteoffset +
                     (unsigned long)output_bytesize;

    if (output_byteend < (unsigned long)output_byteoffset ||
        LONG_MAX < output_byteend)
        rb_raise(rb_eArgError, "output_byteoffset+output_bytesize too big");

    if (rb_str_capacity(output) < output_byteend)
        rb_str_resize(output, output_byteend);

    if (NIL_P(input)) {
        ip = is = NULL;
    }
    else {
        ip = (const unsigned char *)RSTRING_PTR(input);
        is = ip + RSTRING_LEN(input);
    }

    op = (unsigned char *)RSTRING_PTR(output) + output_byteoffset;
    os = op + output_bytesize;

    res = rb_econv_convert(ec, &ip, is, &op, os, flags);
    rb_str_set_len(output, op-(unsigned char *)RSTRING_PTR(output));
    if (!NIL_P(input)) {
        OBJ_INFECT_RAW(output, input);
        rb_str_drop_bytes(input, ip - (unsigned char *)RSTRING_PTR(input));
    }

    if (NIL_P(output_bytesize_v) && res == econv_destination_buffer_full) {
        if (LONG_MAX / 2 < output_bytesize)
            rb_raise(rb_eArgError, "too long conversion result");
        output_bytesize *= 2;
        output_byteoffset_v = Qnil;
        goto retry;
    }

    if (ec->destination_encoding) {
        rb_enc_associate(output, ec->destination_encoding);
    }

    return econv_result_to_symbol(res);
}