WIP

kanjidic.go

@@ -45,6 +45,12 @@ type KanjidicCharacter struct {
 	// for finding a required kanji. The type of code is defined by the
 	// qc_type attribute.
 	QueryCode KanjidicQueryCode `xml:"query_code"`
+
+	// The readings for the kanji in several languages, and the meanings, also
+	// in several languages. The readings and meanings are grouped to enable
+	// the handling of the situation where the meaning is differentiated by
+	// reading. [T1]
+	ReadingMeaning KanjidicReadingMeaning `xml:"reading_meaning"`
 }
 
 type KanjidicCodepoint struct {
@@ -203,3 +209,105 @@ type KanjiDicReference struct {
 	// See above under "moro".
 	Page string `xml:"m_page,attr"`
 }
+
+type KanjidicQueryCode struct {
+	// The q_code contains the actual query-code value, according to the
+	// qc_type attribute.
+	Values []KanjidicQueryCodeValue `xml:"q_code"`
+}
+
+type KanjidicQueryCodeValue struct {
+	Value string `xml:",chardata"`
+
+	// The qc_type attribute defines the type of query code. The current values
+	// are:
+	//   skip -  Halpern's SKIP (System  of  Kanji  Indexing  by  Patterns)
+	//   	code. The  format is n-nn-nn.  See the KANJIDIC  documentation
+	//   	for  a description of the code and restrictions on  the
+	//   	commercial  use  of this data. [P]  There are also
+	// 	a number of misclassification codes, indicated by the
+	// 	"skip_misclass" attribute.
+	//   sh_desc - the descriptor codes for The Kanji Dictionary (Tuttle
+	//   	1996) by Spahn and Hadamitzky. They are in the form nxnn.n,
+	//   	e.g.  3k11.2, where the  kanji has 3 strokes in the
+	//   	identifying radical, it is radical "k" in the SH
+	//   	classification system, there are 11 other strokes, and it is
+	//   	the 2nd kanji in the 3k11 sequence. (I am very grateful to
+	//   	Mark Spahn for providing the list of these descriptor codes
+	//   	for the kanji in this file.) [I]
+	//   four_corner - the "Four Corner" code for the kanji. This is a code
+	//   	invented by Wang Chen in 1928. See the KANJIDIC documentation
+	//   	for  an overview of  the Four Corner System. [Q]
+
+	//   deroo - the codes developed by the late Father Joseph De Roo, and
+	//   	published in  his book "2001 Kanji" (Bonjinsha). Fr De Roo
+	//   	gave his permission for these codes to be included. [DR]
+	//   misclass - a possible misclassification of the kanji according
+	// 	to one of the code types. (See the "Z" codes in the KANJIDIC
+	// 	documentation for more details.)
+	Type string `xml:"qc_type,attr"`
+
+	// The values of this attribute indicate the type if
+	// misclassification:
+	// - posn - a mistake in the division of the kanji
+	// - stroke_count - a mistake in the number of strokes
+	// - stroke_and_posn - mistakes in both division and strokes
+	// - stroke_diff - ambiguous stroke counts depending on glyph
+	Misclassification string `xml:"skip_misclass,attr"`
+}
+
+type KanjidicReadingMeaning struct {
+	ReadingMeaning KandjicReadingMeaningGroup `xml:"rmgroup"`
+
+	// Japanese readings that are now only associated with names.
+	Nanori KanjidicNanori `xml:"nanori"`
+}
+
+type KanjidicReadingMeaningGroup struct {
+	// The reading element contains the reading or pronunciation
+	// of the kanji.
+	Readings []KanjidicReading `xml:"reading"`
+
+	// The meaning associated with the kanji.
+	Meanings []KanjidicMeanings `xml:"meanings"`
+}
+
+type KanjidicReading struct {
+	Value string `xml:",chardata"`
+
+	// The r_type attribute defines the type of reading in the reading
+	// element. The current values are:
+	//   pinyin - the modern PinYin romanization of the Chinese reading
+	//   	of the kanji. The tones are represented by a concluding
+	//   	digit. [Y]
+	//   korean_r - the romanized form of the Korean reading(s) of the
+	//   	kanji.  The readings are in the (Republic of Korea) Ministry
+	//   	of Education style of romanization. [W]
+	//   korean_h - the Korean reading(s) of the kanji in hangul.
+	//   ja_on - the "on" Japanese reading of the kanji, in katakana.
+	//   	Another attribute r_status, if present, will indicate with
+	//   	a value of "jy" whether the reading is approved for a
+	//   	"Jouyou kanji".
+	// 	A further attribute on_type, if present,  will indicate with
+	// 	a value of kan, go, tou or kan'you the type of on-reading.
+	//   ja_kun - the "kun" Japanese reading of the kanji, usually in
+	// 	hiragana.
+	//   	Where relevant the okurigana is also included separated by a
+	//   	".". Readings associated with prefixes and suffixes are
+	//   	marked with a "-". A second attribute r_status, if present,
+	//   	will indicate with a value of "jy" whether the reading is
+	//   	approved for a "Jouyou kanji".
+	Type string `xml:"r_type"`
+
+	// See under ja_on above.
+	OnType *string `xml:"on_type"`
+
+	// See under ja_on and ja_kun above.
+	JouyouStatus *string `xml:"r_status"`
+}
+
+type KanjidicMeaning struct {
+}
+
+type KanjidicNanori struct {
+}