Encoding::Converter.asciicompat_encoding("ISO-2022-JP") #=> #<Encoding:stateless-ISO-2022-JP>
Encoding::Converter.asciicompat_encoding("UTF-16BE") #=> #<Encoding:UTF-8>
Encoding::Converter.asciicompat_encoding("UTF-8") #=> nil

static VALUE
econv_s_asciicompat_encoding(VALUE klass, VALUE arg)
{
    const char *arg_name, *result_name;
    rb_encoding *arg_enc, *result_enc;

    enc_arg(&arg, &arg_name, &arg_enc);

    result_name = rb_econv_asciicompat_encoding(arg_name);

    if (result_name == NULL)
        return Qnil;

    result_enc = make_encoding(result_name);

    return rb_enc_from_encoding(result_enc);
}

Encoding::Converter.new(source_encoding, destination_encoding) 单击以切换源

Encoding::Converter.new(source_encoding, destination_encoding, opt)

Encoding::Converter.new(convpath)

可能的选项元素

hash form:
  :invalid => nil            # raise error on invalid byte sequence (default)
  :invalid => :replace       # replace invalid byte sequence
  :undef => nil              # raise error on undefined conversion (default)
  :undef => :replace         # replace undefined conversion
  :replace => string         # replacement string ("?" or "\uFFFD" if not specified)
  :newline => :universal     # decorator for converting CRLF and CR to LF
  :newline => :lf            # decorator for converting CRLF and CR to LF when writing
  :newline => :crlf          # decorator for converting LF to CRLF
  :newline => :cr            # decorator for converting LF to CR
  :universal_newline => true # decorator for converting CRLF and CR to LF
  :crlf_newline => true      # decorator for converting LF to CRLF
  :cr_newline => true        # decorator for converting LF to CR
  :lf_newline => true        # decorator for converting CRLF and CR to LF when writing
  :xml => :text              # escape as XML CharData.
  :xml => :attr              # escape as XML AttValue
integer form:
  Encoding::Converter::INVALID_REPLACE
  Encoding::Converter::UNDEF_REPLACE
  Encoding::Converter::UNDEF_HEX_CHARREF
  Encoding::Converter::UNIVERSAL_NEWLINE_DECORATOR
  Encoding::Converter::LF_NEWLINE_DECORATOR
  Encoding::Converter::CRLF_NEWLINE_DECORATOR
  Encoding::Converter::CR_NEWLINE_DECORATOR
  Encoding::Converter::XML_TEXT_DECORATOR
  Encoding::Converter::XML_ATTR_CONTENT_DECORATOR
  Encoding::Converter::XML_ATTR_QUOTE_DECORATOR

Encoding::Converter.new 创建 Encoding::Converter 的实例。

Source_encoding 和 destination_encoding 应为字符串或 Encoding 对象。

opt 应为 nil、哈希或整数。

convpath 应为数组。convpath 可能包含

包含编码或编码名称的两元素数组，或
表示装饰器名称的字符串。

Encoding::Converter.new 可选择采用一个选项。该选项应为哈希或整数。选项哈希可以包含 :invalid => nil 等。选项整数应为常量的逻辑或，例如 Encoding::Converter::INVALID_REPLACE 等。

:invalid => nil

在无效字节序列上引发错误。这是默认行为。

:invalid => :replace

用替换字符串替换无效字节序列。

:undef => nil

如果 source_encoding 中的字符未在 destination_encoding 中定义，则引发错误。这是默认行为。

:undef => :replace

用替换字符串替换 destination_encoding 中未定义的字符。

:replace => string

指定替换字符串。如果未指定，则 Unicode 编码使用 “uFFFD”，其他编码使用 “?”。

:universal_newline => true

将 CRLF 和 CR 转换为 LF。

:crlf_newline => true

将 LF 转换为 CRLF。

:cr_newline => true

将 LF 转换为 CR。

:lf_newline => true

将 CRLF 和 CR 转换为 LF（写入时）。

:xml => :text

转义为 XML CharData。此表单可用作 HTML 4.0 PCDATA。

‘&’ -> ‘&’
‘<’ -> ‘<’
‘>’ -> ‘>’
destination_encoding 中未定义的字符 -> 十六进制 CharRef，例如 &#xHH;

:xml => :attr

转义为 XML AttValue。转换结果用 “….” 引号引起来。此表单可用作 HTML 4.0 属性值。

‘&’ -> ‘&’
‘<’ -> ‘<’
‘>’ -> ‘>’
‘“’ -> ‘"’
destination_encoding 中未定义的字符 -> 十六进制 CharRef，例如 &#xHH;

示例

# UTF-16BE to UTF-8
ec = Encoding::Converter.new("UTF-16BE", "UTF-8")

# Usually, decorators such as newline conversion are inserted last.
ec = Encoding::Converter.new("UTF-16BE", "UTF-8", :universal_newline => true)
p ec.convpath #=> [[#<Encoding:UTF-16BE>, #<Encoding:UTF-8>],
              #    "universal_newline"]

# But, if the last encoding is ASCII incompatible,
# decorators are inserted before the last conversion.
ec = Encoding::Converter.new("UTF-8", "UTF-16BE", :crlf_newline => true)
p ec.convpath #=> ["crlf_newline",
              #    [#<Encoding:UTF-8>, #<Encoding:UTF-16BE>]]

# Conversion path can be specified directly.
ec = Encoding::Converter.new(["universal_newline", ["EUC-JP", "UTF-8"], ["UTF-8", "UTF-16BE"]])
p ec.convpath #=> ["universal_newline",
              #    [#<Encoding:EUC-JP>, #<Encoding:UTF-8>],
              #    [#<Encoding:UTF-8>, #<Encoding:UTF-16BE>]]

static VALUE
econv_init(int argc, VALUE *argv, VALUE self)
{
    VALUE ecopts;
    VALUE snamev, dnamev;
    const char *sname, *dname;
    rb_encoding *senc, *denc;
    rb_econv_t *ec;
    int ecflags;
    VALUE convpath;

    if (rb_check_typeddata(self, &econv_data_type)) {
        rb_raise(rb_eTypeError, "already initialized");
    }

    if (argc == 1 && !NIL_P(convpath = rb_check_array_type(argv[0]))) {
        ec = rb_econv_init_by_convpath(self, convpath, &sname, &dname, &senc, &denc);
        ecflags = 0;
        ecopts = Qnil;
    }
    else {
        econv_args(argc, argv, &snamev, &dnamev, &sname, &dname, &senc, &denc, &ecflags, &ecopts);
        ec = rb_econv_open_opts(sname, dname, ecflags, ecopts);
    }

    if (!ec) {
        VALUE exc = rb_econv_open_exc(sname, dname, ecflags);
        RB_GC_GUARD(snamev);
        RB_GC_GUARD(dnamev);
        rb_exc_raise(exc);
    }

    if (!DECORATOR_P(sname, dname)) {
        if (!senc)
            senc = make_dummy_encoding(sname);
        if (!denc)
            denc = make_dummy_encoding(dname);
        RB_GC_GUARD(snamev);
        RB_GC_GUARD(dnamev);
    }

    ec->source_encoding = senc;
    ec->destination_encoding = denc;

    DATA_PTR(self) = ec;

    return self;
}

Encoding::Converter.search_convpath(source_encoding, destination_encoding) → ary 点击切换源代码

Encoding::Converter.search_convpath(source_encoding, destination_encoding, opt) → ary

返回转换路径。

p Encoding::Converter.search_convpath("ISO-8859-1", "EUC-JP")
#=> [[#<Encoding:ISO-8859-1>, #<Encoding:UTF-8>],
#    [#<Encoding:UTF-8>, #<Encoding:EUC-JP>]]

p Encoding::Converter.search_convpath("ISO-8859-1", "EUC-JP", universal_newline: true)
or
p Encoding::Converter.search_convpath("ISO-8859-1", "EUC-JP", newline: :universal)
#=> [[#<Encoding:ISO-8859-1>, #<Encoding:UTF-8>],
#    [#<Encoding:UTF-8>, #<Encoding:EUC-JP>],
#    "universal_newline"]

p Encoding::Converter.search_convpath("ISO-8859-1", "UTF-32BE", universal_newline: true)
or
p Encoding::Converter.search_convpath("ISO-8859-1", "UTF-32BE", newline: :universal)
#=> [[#<Encoding:ISO-8859-1>, #<Encoding:UTF-8>],
#    "universal_newline",
#    [#<Encoding:UTF-8>, #<Encoding:UTF-32BE>]]

static VALUE
econv_s_search_convpath(int argc, VALUE *argv, VALUE klass)
{
    VALUE snamev, dnamev;
    const char *sname, *dname;
    rb_encoding *senc, *denc;
    int ecflags;
    VALUE ecopts;
    VALUE convpath;

    econv_args(argc, argv, &snamev, &dnamev, &sname, &dname, &senc, &denc, &ecflags, &ecopts);

    convpath = Qnil;
    transcode_search_path(sname, dname, search_convpath_i, &convpath);

    if (NIL_P(convpath)) {
        VALUE exc = rb_econv_open_exc(sname, dname, ecflags);
        RB_GC_GUARD(snamev);
        RB_GC_GUARD(dnamev);
        rb_exc_raise(exc);
    }

    if (decorate_convpath(convpath, ecflags) == -1) {
        VALUE exc = rb_econv_open_exc(sname, dname, ecflags);
        RB_GC_GUARD(snamev);
        RB_GC_GUARD(dnamev);
        rb_exc_raise(exc);
    }

    return convpath;
}

公共实例方法

ec == other → true 或 false 点击切换源代码

static VALUE
econv_equal(VALUE self, VALUE other)
{
    rb_econv_t *ec1 = check_econv(self);
    rb_econv_t *ec2;
    int i;

    if (!rb_typeddata_is_kind_of(other, &econv_data_type)) {
        return Qnil;
    }
    ec2 = DATA_PTR(other);
    if (!ec2) return Qfalse;
    if (ec1->source_encoding_name != ec2->source_encoding_name &&
        strcmp(ec1->source_encoding_name, ec2->source_encoding_name))
        return Qfalse;
    if (ec1->destination_encoding_name != ec2->destination_encoding_name &&
        strcmp(ec1->destination_encoding_name, ec2->destination_encoding_name))
        return Qfalse;
    if (ec1->flags != ec2->flags) return Qfalse;
    if (ec1->replacement_enc != ec2->replacement_enc &&
        strcmp(ec1->replacement_enc, ec2->replacement_enc))
        return Qfalse;
    if (ec1->replacement_len != ec2->replacement_len) return Qfalse;
    if (ec1->replacement_str != ec2->replacement_str &&
        memcmp(ec1->replacement_str, ec2->replacement_str, ec2->replacement_len))
        return Qfalse;

    if (ec1->num_trans != ec2->num_trans) return Qfalse;
    for (i = 0; i < ec1->num_trans; i++) {
        if (ec1->elems[i].tc->transcoder != ec2->elems[i].tc->transcoder)
            return Qfalse;
    }
    return Qtrue;
}

convert(source_string) → destination_string 单击以切换源

转换 source_string 并返回 destination_string。

source_string 被假定为 source 的一部分。即：在内部指定 :partial_input=>true。finish 方法应最后使用。

ec = Encoding::Converter.new("utf-8", "euc-jp")
puts ec.convert("\u3042").dump     #=> "\xA4\xA2"
puts ec.finish.dump                #=> ""

ec = Encoding::Converter.new("euc-jp", "utf-8")
puts ec.convert("\xA4").dump       #=> ""
puts ec.convert("\xA2").dump       #=> "\xE3\x81\x82"
puts ec.finish.dump                #=> ""

ec = Encoding::Converter.new("utf-8", "iso-2022-jp")
puts ec.convert("\xE3").dump       #=> "".force_encoding("ISO-2022-JP")
puts ec.convert("\x81").dump       #=> "".force_encoding("ISO-2022-JP")
puts ec.convert("\x82").dump       #=> "\e$B$\"".force_encoding("ISO-2022-JP")
puts ec.finish.dump                #=> "\e(B".force_encoding("ISO-2022-JP")

如果发生转换错误，则会引发 Encoding::UndefinedConversionError 或 Encoding::InvalidByteSequenceError。 Encoding::Converter#convert 不提供从这些异常中恢复或重新开始的方法。当您想要处理这些转换错误时，请使用 Encoding::Converter#primitive_convert。

static VALUE
econv_convert(VALUE self, VALUE source_string)
{
    VALUE ret, dst;
    VALUE av[5];
    int ac;
    rb_econv_t *ec = check_econv(self);

    StringValue(source_string);

    dst = rb_str_new(NULL, 0);

    av[0] = rb_str_dup(source_string);
    av[1] = dst;
    av[2] = Qnil;
    av[3] = Qnil;
    av[4] = INT2NUM(ECONV_PARTIAL_INPUT);
    ac = 5;

    ret = econv_primitive_convert(ac, av, self);

    if (ret == sym_invalid_byte_sequence ||
        ret == sym_undefined_conversion ||
        ret == sym_incomplete_input) {
        VALUE exc = make_econv_exception(ec);
        rb_exc_raise(exc);
    }

    if (ret == sym_finished) {
        rb_raise(rb_eArgError, "converter already finished");
    }

    if (ret != sym_source_buffer_empty) {
        rb_bug("unexpected result of econv_primitive_convert");
    }

    return dst;
}

convpath → ary 单击以切换源

返回 ec 的转换路径。

结果是转换的数组。

ec = Encoding::Converter.new("ISO-8859-1", "EUC-JP", crlf_newline: true)
p ec.convpath
#=> [[#<Encoding:ISO-8859-1>, #<Encoding:UTF-8>],
#    [#<Encoding:UTF-8>, #<Encoding:EUC-JP>],
#    "crlf_newline"]

数组的每个元素都是编码或字符串的成对。成对表示编码转换。字符串表示装饰器。

在上面的示例中，[#<Encoding:ISO-8859-1>,

static VALUE
econv_convpath(VALUE self)
{
    rb_econv_t *ec = check_econv(self);
    VALUE result;
    int i;

    result = rb_ary_new();
    for (i = 0; i < ec->num_trans; i++) {
        const rb_transcoder *tr = ec->elems[i].tc->transcoder;
        VALUE v;
        if (DECORATOR_P(tr->src_encoding, tr->dst_encoding))
            v = rb_str_new_cstr(tr->dst_encoding);
        else
            v = rb_assoc_new(make_encobj(tr->src_encoding), make_encobj(tr->dst_encoding));
        rb_ary_push(result, v);
    }
    return result;
}

destination_encoding → encoding 单击以切换源

将目标编码作为 Encoding 对象返回。

static VALUE
econv_destination_encoding(VALUE self)
{
    rb_econv_t *ec = check_econv(self);
    return econv_get_encoding(ec->destination_encoding);
}

finish → string 单击以切换源

完成转换器。它返回已转换字符串的最后部分。

ec = Encoding::Converter.new("utf-8", "iso-2022-jp")
p ec.convert("\u3042")     #=> "\e$B$\""
p ec.finish                #=> "\e(B"

static VALUE
econv_finish(VALUE self)
{
    VALUE ret, dst;
    VALUE av[5];
    int ac;
    rb_econv_t *ec = check_econv(self);

    dst = rb_str_new(NULL, 0);

    av[0] = Qnil;
    av[1] = dst;
    av[2] = Qnil;
    av[3] = Qnil;
    av[4] = INT2FIX(0);
    ac = 5;

    ret = econv_primitive_convert(ac, av, self);

    if (ret == sym_invalid_byte_sequence ||
        ret == sym_undefined_conversion ||
        ret == sym_incomplete_input) {
        VALUE exc = make_econv_exception(ec);
        rb_exc_raise(exc);
    }

    if (ret != sym_finished) {
        rb_bug("unexpected result of econv_primitive_convert");
    }

    return dst;
}

insert_output(string) → nil 单击以切换源

将字符串插入编码转换器。该字符串将被转换为目标编码并在以后的转换中输出。

如果目标编码是有状态的，则根据状态转换字符串并更新状态。

仅当发生转换错误时才应使用此方法。

ec = Encoding::Converter.new("utf-8", "iso-8859-1")
src = "HIRAGANA LETTER A is \u{3042}."
dst = ""
p ec.primitive_convert(src, dst)    #=> :undefined_conversion
puts "[#{dst.dump}, #{src.dump}]"   #=> ["HIRAGANA LETTER A is ", "."]
ec.insert_output("<err>")
p ec.primitive_convert(src, dst)    #=> :finished
puts "[#{dst.dump}, #{src.dump}]"   #=> ["HIRAGANA LETTER A is <err>.", ""]

ec = Encoding::Converter.new("utf-8", "iso-2022-jp")
src = "\u{306F 3041 3068 2661 3002}" # U+2661 is not representable in iso-2022-jp
dst = ""
p ec.primitive_convert(src, dst)    #=> :undefined_conversion
puts "[#{dst.dump}, #{src.dump}]"   #=> ["\e$B$O$!$H".force_encoding("ISO-2022-JP"), "\xE3\x80\x82"]
ec.insert_output "?"                # state change required to output "?".
p ec.primitive_convert(src, dst)    #=> :finished
puts "[#{dst.dump}, #{src.dump}]"   #=> ["\e$B$O$!$H\e(B?\e$B!#\e(B".force_encoding("ISO-2022-JP"), ""]

static VALUE
econv_insert_output(VALUE self, VALUE string)
{
    const char *insert_enc;

    int ret;

    rb_econv_t *ec = check_econv(self);

    StringValue(string);
    insert_enc = rb_econv_encoding_to_insert_output(ec);
    string = rb_str_encode(string, rb_enc_from_encoding(rb_enc_find(insert_enc)), 0, Qnil);

    ret = rb_econv_insert_output(ec, (const unsigned char *)RSTRING_PTR(string), RSTRING_LEN(string), insert_enc);
    if (ret == -1) {
        rb_raise(rb_eArgError, "too big string");
    }

    return Qnil;
}

inspect → string 单击以切换源

返回 ec 的可打印版本

ec = Encoding::Converter.new("iso-8859-1", "utf-8")
puts ec.inspect    #=> #<Encoding::Converter: ISO-8859-1 to UTF-8>

static VALUE
econv_inspect(VALUE self)
{
    const char *cname = rb_obj_classname(self);
    rb_econv_t *ec;

    TypedData_Get_Struct(self, rb_econv_t, &econv_data_type, ec);
    if (!ec)
        return rb_sprintf("#<%s: uninitialized>", cname);
    else {
        const char *sname = ec->source_encoding_name;
        const char *dname = ec->destination_encoding_name;
        VALUE str;
        str = rb_sprintf("#<%s: ", cname);
        econv_description(sname, dname, ec->flags, str);
        rb_str_cat2(str, ">");
        return str;
    }
}

last_error → exception or nil 单击以切换源

返回上次转换的异常对象。如果上次转换未产生错误，则返回 nil。

“error”表示Encoding::InvalidByteSequenceError和Encoding::UndefinedConversionError表示Encoding::Converter#convert和:invalid_byte_sequence、:incomplete_input和:undefined_conversion表示Encoding::Converter#primitive_convert。

ec = Encoding::Converter.new("utf-8", "iso-8859-1")
p ec.primitive_convert(src="\xf1abcd", dst="")       #=> :invalid_byte_sequence
p ec.last_error      #=> #<Encoding::InvalidByteSequenceError: "\xF1" followed by "a" on UTF-8>
p ec.primitive_convert(src, dst, nil, 1)             #=> :destination_buffer_full
p ec.last_error      #=> nil

static VALUE
econv_last_error(VALUE self)
{
    rb_econv_t *ec = check_econv(self);
    VALUE exc;

    exc = make_econv_exception(ec);
    if (NIL_P(exc))
        return Qnil;
    return exc;
}

primitive_convert(source_buffer, destination_buffer) → symbol 单击以切换源

primitive_convert(source_buffer, destination_buffer, destination_byteoffset) → symbol

primitive_convert(source_buffer, destination_buffer, destination_byteoffset, destination_bytesize) → symbol

primitive_convert(source_buffer, destination_buffer, destination_byteoffset, destination_bytesize, opt) → symbol

可能的opt元素

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

可能的结果

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

primitive_convert将source_buffer转换为destination_buffer。

source_buffer应为字符串或nil。nil表示空字符串。

destination_buffer应为字符串。

destination_byteoffset应为整数或nil。nil表示destination_buffer的末尾。如果省略，则假定为nil。

destination_bytesize应为整数或nil。nil表示无限制。如果省略，则假定为nil。

opt应为nil、哈希或整数。nil表示无标志。如果省略，则假定为nil。

primitive_convert将source_buffer的内容从开头转换，并将结果存储到destination_buffer中。

destination_byteoffset和destination_bytesize指定存储转换结果的区域。destination_byteoffset以字节为单位指定destination_buffer中的起始位置。如果destination_byteoffset为nil，则destination_buffer.bytesize用于附加结果。destination_bytesize指定最大字节数。如果destination_bytesize为nil，则目标大小不受限制。转换后，destination_buffer的大小调整为destination_byteoffset + 实际产生的字节数。此外，destination_buffer的编码设置为destination_encoding。

primitive_convert删除source_buffer的已转换部分。已删除的部分在destination_buffer中转换或缓存在Encoding::Converter对象中。

primitive_convert在满足以下条件之一时停止转换。

在源缓冲区中找到无效字节序列(:invalid_byte_sequence) primitive_errinfo和last_error方法返回错误的详细信息。
源缓冲区的意外结束(:incomplete_input) 仅在未指定:partial_input时发生。primitive_errinfo和last_error方法返回错误的详细信息。
字符无法在输出编码中表示（:undefined_conversion）primitive_errinfo 和 last_error 方法返回错误的详细信息。
在生成一些输出后，在输入完成前（:after_output）仅当指定 :after_output 时才会发生这种情况。
目标缓冲区已满（:destination_buffer_full）仅当 destination_bytesize 为非空时才会发生这种情况。
源缓冲区为空（:source_buffer_empty）仅当指定 :partial_input 时才会发生这种情况。
转换已完成（:finished）

示例

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"]

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 = rb_str_capacity(output);

        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)) {
        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);
}

primitive_errinfo → array 单击以切换源代码

primitive_errinfo 将有关最后一个错误的重要信息作为 5 元素数组返回

[result, enc1, enc2, error_bytes, readagain_bytes]

result 是 primitive_convert 的最后一个结果。

当 result 为 :invalid_byte_sequence、:incomplete_input 或 :undefined_conversion 时，其他元素才有意义。

enc1 和 enc2 将转换步骤表示为一对字符串。例如，从 EUC-JP 到 ISO-8859-1 的转换器将字符串转换如下：EUC-JP -> UTF-8 -> ISO-8859-1。因此，[enc1, enc2] 为 [“EUC-JP”， “UTF-8”] 或 [“UTF-8”， “ISO-8859-1”]。

error_bytes 和 readagain_bytes 指示导致错误的字节序列。error_bytes 是被丢弃的部分。readagain_bytes 是在下次转换时再次读取的缓冲部分。

示例

# \xff is invalid as EUC-JP.
ec = Encoding::Converter.new("EUC-JP", "Shift_JIS")
ec.primitive_convert(src="\xff", dst="", nil, 10)
p ec.primitive_errinfo
#=> [:invalid_byte_sequence, "EUC-JP", "Shift_JIS", "\xFF", ""]

# HIRAGANA LETTER A (\xa4\xa2 in EUC-JP) is not representable in ISO-8859-1.
# Since this error is occur in UTF-8 to ISO-8859-1 conversion,
# error_bytes is HIRAGANA LETTER A in UTF-8 (\xE3\x81\x82).
ec = Encoding::Converter.new("EUC-JP", "ISO-8859-1")
ec.primitive_convert(src="\xa4\xa2", dst="", nil, 10)
p ec.primitive_errinfo
#=> [:undefined_conversion, "UTF-8", "ISO-8859-1", "\xE3\x81\x82", ""]

# partial character is invalid
ec = Encoding::Converter.new("EUC-JP", "ISO-8859-1")
ec.primitive_convert(src="\xa4", dst="", nil, 10)
p ec.primitive_errinfo
#=> [:incomplete_input, "EUC-JP", "UTF-8", "\xA4", ""]

# Encoding::Converter::PARTIAL_INPUT prevents invalid errors by
# partial characters.
ec = Encoding::Converter.new("EUC-JP", "ISO-8859-1")
ec.primitive_convert(src="\xa4", dst="", nil, 10, Encoding::Converter::PARTIAL_INPUT)
p ec.primitive_errinfo
#=> [:source_buffer_empty, nil, nil, nil, nil]

# \xd8\x00\x00@ is invalid as UTF-16BE because
# no low surrogate after high surrogate (\xd8\x00).
# It is detected by 3rd byte (\00) which is part of next character.
# So the high surrogate (\xd8\x00) is discarded and
# the 3rd byte is read again later.
# Since the byte is buffered in ec, it is dropped from src.
ec = Encoding::Converter.new("UTF-16BE", "UTF-8")
ec.primitive_convert(src="\xd8\x00\x00@", dst="", nil, 10)
p ec.primitive_errinfo
#=> [:invalid_byte_sequence, "UTF-16BE", "UTF-8", "\xD8\x00", "\x00"]
p src
#=> "@"

# Similar to UTF-16BE, \x00\xd8@\x00 is invalid as UTF-16LE.
# The problem is detected by 4th byte.
ec = Encoding::Converter.new("UTF-16LE", "UTF-8")
ec.primitive_convert(src="\x00\xd8@\x00", dst="", nil, 10)
p ec.primitive_errinfo
#=> [:invalid_byte_sequence, "UTF-16LE", "UTF-8", "\x00\xD8", "@\x00"]
p src
#=> ""

static VALUE
econv_primitive_errinfo(VALUE self)
{
    rb_econv_t *ec = check_econv(self);

    VALUE ary;

    ary = rb_ary_new2(5);

    rb_ary_store(ary, 0, econv_result_to_symbol(ec->last_error.result));
    rb_ary_store(ary, 4, Qnil);

    if (ec->last_error.source_encoding)
        rb_ary_store(ary, 1, rb_str_new2(ec->last_error.source_encoding));

    if (ec->last_error.destination_encoding)
        rb_ary_store(ary, 2, rb_str_new2(ec->last_error.destination_encoding));

    if (ec->last_error.error_bytes_start) {
        rb_ary_store(ary, 3, rb_str_new((const char *)ec->last_error.error_bytes_start, ec->last_error.error_bytes_len));
        rb_ary_store(ary, 4, rb_str_new((const char *)ec->last_error.error_bytes_start + ec->last_error.error_bytes_len, ec->last_error.readagain_len));
    }

    return ary;
}

putback → string 单击以切换源代码

putback(max_numbytes) → string

放回将被转换的字节。

字节由 invalid_byte_sequence 错误导致。当出现 invalid_byte_sequence 错误时，一些字节会被丢弃，一些字节会被缓冲以供以后转换。后一个字节可以放回。可以通过 Encoding::InvalidByteSequenceError#readagain_bytes 和 Encoding::Converter#primitive_errinfo 观察到。

ec = Encoding::Converter.new("utf-16le", "iso-8859-1")
src = "\x00\xd8\x61\x00"
dst = ""
p ec.primitive_convert(src, dst)   #=> :invalid_byte_sequence
p ec.primitive_errinfo     #=> [:invalid_byte_sequence, "UTF-16LE", "UTF-8", "\x00\xD8", "a\x00"]
p ec.putback               #=> "a\x00"
p ec.putback               #=> ""          # no more bytes to put back

static VALUE
econv_putback(int argc, VALUE *argv, VALUE self)
{
    rb_econv_t *ec = check_econv(self);
    int n;
    int putbackable;
    VALUE str, max;

    if (!rb_check_arity(argc, 0, 1) || NIL_P(max = argv[0])) {
        n = rb_econv_putbackable(ec);
    }
    else {
        n = NUM2INT(max);
        putbackable = rb_econv_putbackable(ec);
        if (putbackable < n)
            n = putbackable;
    }

    str = rb_str_new(NULL, n);
    rb_econv_putback(ec, (unsigned char *)RSTRING_PTR(str), n);

    if (ec->source_encoding) {
        rb_enc_associate(str, ec->source_encoding);
    }

    return str;
}

replacement → string 单击以切换源代码

返回替换字符串。

ec = Encoding::Converter.new("euc-jp", "us-ascii")
p ec.replacement    #=> "?"

ec = Encoding::Converter.new("euc-jp", "utf-8")
p ec.replacement    #=> "\uFFFD"

static VALUE
econv_get_replacement(VALUE self)
{
    rb_econv_t *ec = check_econv(self);
    int ret;
    rb_encoding *enc;

    ret = make_replacement(ec);
    if (ret == -1) {
        rb_raise(rb_eUndefinedConversionError, "replacement character setup failed");
    }

    enc = rb_enc_find(ec->replacement_enc);
    return rb_enc_str_new((const char *)ec->replacement_str, (long)ec->replacement_len, enc);
}

replacement = string 单击以切换源代码

设置替换字符串。

ec = Encoding::Converter.new("utf-8", "us-ascii", :undef => :replace)
ec.replacement = "<undef>"
p ec.convert("a \u3042 b")      #=> "a <undef> b"

static VALUE
econv_set_replacement(VALUE self, VALUE arg)
{
    rb_econv_t *ec = check_econv(self);
    VALUE string = arg;
    int ret;
    rb_encoding *enc;

    StringValue(string);
    enc = rb_enc_get(string);

    ret = rb_econv_set_replacement(ec,
            (const unsigned char *)RSTRING_PTR(string),
            RSTRING_LEN(string),
            rb_enc_name(enc));

    if (ret == -1) {
        /* xxx: rb_eInvalidByteSequenceError? */
        rb_raise(rb_eUndefinedConversionError, "replacement character setup failed");
    }

    return arg;
}

source_encoding → encoding 点击以切换源

将源编码作为 Encoding 对象返回。

static VALUE
econv_source_encoding(VALUE self)
{
    rb_econv_t *ec = check_econv(self);
    return econv_get_encoding(ec->source_encoding);
}