123456789101112131415161718192021222324252627282930313233343536373839404142434445464748495051525354555657585960616263646566676869707172737475767778798081828384858687888990919293949596979899100101102103104105106107108109110111112113114115116117118119120121122123124125126127128129130131132133134135136137138139140141142143144145146147148149150151152153154155156157158159160161162163164165166167168169170171172173174175176177178179180181182183184185186187188189190191192193194195196197198199200201202203204205206207208209210211212213214215216217218219220221222223224225226227228229230231232233234235236237238239240241242243244245246247248249250 |
- <?xml version="1.0"?>
- <!DOCTYPE kanjidic2 [
- <!-- Version 1.3
- This is the DTD of the XML-format kanji file combining information from
- the KANJIDIC and KANJD212 files. It is intended to be largely self-
- documenting, with each field being accompanied by an explanatory
- comment.
- The file covers the following kanji:
- (a) the 6,355 kanji from JIS X 0208;
- (b) the 5,801 kanji from JIS X 0212;
- (c) the 3,625 kanji from JIS X 0213 as follows:
- (i) the 2,741 kanji which are also in JIS X 0212 have
- JIS X 0213 code-points (kuten) added to the existing entry;
- (ii) the 884 "new" kanji have new entries.
- At the end of the explanation for a number of fields there is a tag
- with the format [N]. This indicates the leading letter(s) of the
- equivalent field in the KANJIDIC and KANJD212 files.
- The KANJIDIC documentation should also be read for additional
- information about the information in the file.
- --><!ELEMENT kanjidic2 (header , character*)>
- <!ELEMENT header (file_version , database_version , date_of_creation)>
- <!ELEMENT file_version (#PCDATA)>
- <!ELEMENT database_version (#PCDATA)>
- <!ELEMENT date_of_creation (#PCDATA)>
- <!ELEMENT character (literal , codepoint , radical , misc , dic_number? , query_code? , reading_meaning? , nanori?)*>
- <!ELEMENT literal (#PCDATA)>
- <!ELEMENT codepoint (cp_value)+>
- <!ELEMENT cp_value (#PCDATA)>
- <!ATTLIST cp_value cp_type CDATA #REQUIRED>
- <!ELEMENT radical (rad_value)+>
- <!ELEMENT rad_value (#PCDATA)>
- <!ATTLIST rad_value rad_type CDATA #REQUIRED>
- <!ELEMENT misc (grade? , stroke_count+ , variant* , freq* , rad_name*)>
- <!ELEMENT grade (#PCDATA)>
- <!ELEMENT stroke_count (#PCDATA)>
- <!ELEMENT variant (#PCDATA)>
- <!ATTLIST variant var_type CDATA #REQUIRED>
- <!ELEMENT freq (#PCDATA)>
- <!ELEMENT rad_name (#PCDATA)>
- <!ELEMENT dic_number (dic_ref)+>
- <!ELEMENT dic_ref (#PCDATA)>
- <!ATTLIST dic_ref dr_type CDATA #REQUIRED>
- <!ATTLIST dic_ref m_vol CDATA #IMPLIED>
- <!ATTLIST dic_ref m_page CDATA #IMPLIED>
- <!ELEMENT query_code (q_code)+>
- <!ELEMENT q_code (#PCDATA)>
- <!ATTLIST q_code qc_type CDATA #REQUIRED>
- <!ELEMENT reading_meaning (rmgroup* , nanori*)>
- <!ELEMENT nanori (#PCDATA)>
- <!ELEMENT rmgroup (reading* , meaning*)>
- <!ELEMENT reading (#PCDATA)>
- <!ATTLIST reading r_type CDATA #REQUIRED>
- <!ATTLIST reading r_status CDATA #IMPLIED>
- <!ELEMENT meaning (#PCDATA)>
- <!ATTLIST meaning m_lang CDATA #IMPLIED>
- ]>
- <kanjidic2>
- </kanjidic2>
|