diff options
Diffstat (limited to 'test/rexml/data/ticket_68.xml')
| -rw-r--r-- | test/rexml/data/ticket_68.xml | 590 |
1 files changed, 590 insertions, 0 deletions
diff --git a/test/rexml/data/ticket_68.xml b/test/rexml/data/ticket_68.xml new file mode 100644 index 0000000000..7ab34b08cd --- /dev/null +++ b/test/rexml/data/ticket_68.xml @@ -0,0 +1,590 @@ +<?xml version="1.0" encoding="UTF-8"?> +<!-- Rev 1.05 + Changed the <gram> element name to <pos> + Added the g_gend attribute + moved the s_inf element +--> +<!-- Rev 1.04 + Changes: + Rename the project "JMdict" and add the g_lang attribute to the + <gloss> entity - 08 May 1999 + Moved the <gram>, <field> and <misc> elements down to be in the + <sense> region, as suggested by Chris Czeyka. I have also tidied up + some of the "*" as he suggested. - 27 May 2000 + Added the re_nokanji element - Sep 2003. + --> +<!DOCTYPE JMdict [ +<!ELEMENT JMdict (entry*)> +<!-- --> +<!ELEMENT entry (ent_seq, k_ele*, r_ele+, info*, sense+)> + <!-- Entries consist of kanji elements, reading elements, + general information and sense elements. Each entry must have at + least one reading element and one sense element. Others are optional. + --> +<!ELEMENT ent_seq (#PCDATA)> + <!-- A unique numeric sequence number for each entry + --> +<!ELEMENT k_ele (keb, ke_inf*, ke_pri*)> + <!-- The kanji element, or in its absence, the reading element, is + the defining component of each entry. + The overwhelming majority of entries will have a single kanji + element associated with a word in Japanese. Where there are + multiple kanji elements within an entry, they will be orthographical + variants of the same word, either using variations in okurigana, or + alternative and equivalent kanji. Common "mis-spellings" may be + included, provided they are associated with appropriate information + fields. Synonyms are not included; they may be indicated in the + cross-reference field associated with the sense element. + --> +<!ELEMENT keb (#PCDATA)> + <!-- This element will contain a word or short phrase in Japanese + which is written using at least one kanji. The valid characters are + kanji, kana, related characters such as chouon and kurikaeshi, and + in exceptional cases, letters from other alphabets. + --> +<!ELEMENT ke_inf (#PCDATA)> + <!-- This is a coded information field related specifically to the + orthography of the keb, and will typically indicate some unusual + aspect, such as okurigana irregularity. + --> +<!ELEMENT ke_pri (#PCDATA)> + <!-- This and the equivalent re_pri field are provided to record + information about the relative priority of the entry, and consist + of codes indicating the word appears in various references which + can be taken as an indication of the frequency with which the word + is used. This field is intended for use either by applications which + want to concentrate on entries of a particular priority, or to + generate subset files. + The current values in this field are: + - news1/2: appears in the "wordfreq" file compiled by Alexandre Girardi + from the Mainichi Shimbun. (See the Monash ftp archive for a copy.) + Words in the first 12,000 in that file are marked "news1" and words + in the second 12,000 are marked "news2". + - ichi1/2: appears in the "Ichimango goi bunruishuu", Senmon Kyouiku + Publishing, Tokyo, 1998. + - spec1 and spec2: a small number of words use this marker when they + are detected as being common, but are not included in other lists. + - gai1: common loanwords, based on the wordfreq file. + - nfxx: this is an indicator of frequency-of-use ranking in the + wordfreq file. "xx" is the number of the set of 500 words in which + the entry can be found, with "01" assigned to the first 500, "02" + to the second, and so on. + + The reason both the kanji and reading elements are tagged is because + on occasions a priority is only associated with a particular + kanji/reading pair. + --> +<!-- --> +<!ELEMENT r_ele (reb, re_nokanji?, re_restr*, re_inf*, re_pri*)> + <!-- The reading element typically contains the valid readings + of the word(s) in the kanji element using modern kanadzukai. + Where there are multiple reading elements, they will typically be + alternative readings of the kanji element. In the absence of a + kanji element, i.e. in the case of a word or phrase written + entirely in kana, these elements will define the entry. + --> +<!ELEMENT reb (#PCDATA)> + <!-- this element content is restricted to kana and related + characters such as chouon and kurikaeshi. Kana usage will be + consistent between the keb and reb elements; e.g. if the keb + contains katakana, so too will the reb. + --> +<!ELEMENT re_nokanji (#PCDATA)> + <!-- This element, which will usually have a null value, indicates + that the reb, while associated with the keb, cannot be regarded + as a true reading of the kanji. It is typically used for words + such as foreign place names, gairaigo which can be in kanji or + katakana, etc. + --> +<!ELEMENT re_restr (#PCDATA)> + <!-- This element is used to indicate when the reading only applies + to a subset of the keb elements in the entry. In its absence, all + readings apply to all kanji elements. The contents of this element + must exactly match those of one of the keb elements. + --> +<!ELEMENT re_inf (#PCDATA)> + <!-- General coded information pertaining to the specific reading. + Typically it will be used to indicate some unusual aspect of + the reading. --> +<!ELEMENT re_pri (#PCDATA)> + <!-- See the comment on ke_pri above. --> +<!-- --> +<!ELEMENT info (lang*, dial*, links*, bibl*, etym*, audit*)> + <!-- general coded information relating to the entry as a whole.--> +<!ELEMENT lang (#PCDATA)> + <!-- For loan-words, the ISO 639 two-letter code for the originating + language. --> +<!ELEMENT dial (#PCDATA)> + <!-- For words specifically associated with regional dialects in + Japanese, the entity code for that dialect, e.g. ksb for Kansaiben. + --> +<!ELEMENT bibl (bib_tag?, bib_txt?)> +<!ELEMENT bib_tag (#PCDATA)> +<!ELEMENT bib_txt (#PCDATA)> + <!-- Bibliographic information about the entry. The bib_tag will a + coded reference to an entry in an external bibliographic database. + The bib_txt field may be used for brief (local) descriptions.--> +<!ELEMENT etym (#PCDATA)> + <!-- This field is used to hold information about the etymology + of the entry. --> +<!ELEMENT links (link_tag, link_desc, link_uri)> +<!ELEMENT link_tag (#PCDATA)> +<!ELEMENT link_desc (#PCDATA)> +<!ELEMENT link_uri (#PCDATA)> + <!-- This element holds details of linking information to + entries in other electronic repositories. The link_tag will be + coded to indicate the type of link (text, image, sound), the + link_desc will provided a textual label for the link, and the + link_uri contains the actual URI. --> +<!ELEMENT audit (upd_date, upd_detl)> +<!ELEMENT upd_date (#PCDATA)> +<!ELEMENT upd_detl (#PCDATA)> + <!-- The audit element will contain the date and other information + about updates to the entry. Can be used to record the source of + the material. --> +<!-- --> +<!ELEMENT sense (stagk*, stagr*, pos*, xref*, ant*, field*, misc*, s_inf*, gloss*, example*)> + <!-- The sense element will record the translational equivalent + of the Japanese word, plus other related information. Where there + are several distinctly different meanings of the word, multiple + sense elements will be employed. + --> +<!ELEMENT stagk (#PCDATA)> +<!ELEMENT stagr (#PCDATA)> + <!-- These elements, if present, indicate that the sense is restricted + to the lexeme represented by the keb and/or reb. --> +<!ELEMENT xref (#PCDATA)*> + <!-- This element is used to indicate a cross-reference to another + entry with a similar or related meaning or sense. The content of + this element must exactly match that of a keb or reb element in + another entry. + --> +<!ELEMENT ant (#PCDATA)*> + <!-- This element is used to indicate another entry which is an + antonym of the current entry/sense. The content of this element + must exactly match that of a keb or reb element in another entry. + --> +<!ELEMENT pos (#PCDATA)> + <!-- Part-of-speech information about the entry/sense. Should use + appropriate entity codes. + --> +<!ELEMENT field (#PCDATA)> + <!-- Information about the field of application of the entry. When + absent, general application is implied. Entity coding for specific + fields of application. --> +<!ELEMENT misc (#PCDATA)> + <!-- This element is used for other relevant information about + the entry. --> +<!ELEMENT gloss (#PCDATA | pri)*> + <!-- Within each sense will be one or more "glosses", i.e. + target-language words or phrases which are equivalents to the + Japanese word. This element would normally be present, however it + may be omitted in entries which are purely for a cross-reference. + --> +<!ATTLIST gloss g_lang CDATA "en"> + <!-- The g_lang attribute defines the target language of the + gloss. It will be coded using the two-letter language code from + the ISO 639 standard. When absent, the value "en" (i.e. English) + is the default value. --> +<!ATTLIST gloss g_gend CDATA #IMPLIED> + <!-- The g_gend attribute defines the gender of the gloss (typically + a noun in the target language. When absent, the gender is either + not relevant or has yet to be provided. + --> +<!ELEMENT pri (#PCDATA)> + <!-- These elements highlight particular target-language words which + are strongly associated with the Japanese word. The purpose is to + establish a set of target-language words which can effectively be + used as head-words in a reverse target-language/Japanese relationship. + --> +<!ELEMENT example (#PCDATA)> + <!-- The example elements provide for pairs of short Japanese and + target-language phrases or sentences which exemplify the usage of the + Japanese head-word and the target-language gloss. Words in example + fields would typically not be indexed by a dictionary application. + --> +<!ELEMENT s_inf (#PCDATA)> + <!-- The sense-information elements provided for additional + information to be recorded about a sense. Typical usage would + be to indicate such things as level of currency of a sense, the + regional variations, etc. + --> +<!-- The following entity codes are used for common elements within the +various information fields. +--> +<!ENTITY MA "martial arts term"> +<!ENTITY X "rude or X-rated term (not displayed in educational software)"> +<!ENTITY abbr "abbreviation"> +<!ENTITY adj "adjective (keiyoushi)"> +<!ENTITY adj-na "adjectival nouns or quasi-adjectives (keiyodoshi)"> +<!ENTITY adj-no "nouns which may take the genitive case particle `no'"> +<!ENTITY adj-pn "pre-noun adjectival (rentaishi)"> +<!ENTITY adj-t "`taru' adjective"> +<!ENTITY adv "adverb (fukushi)"> +<!ENTITY adv-n "adverbial noun"> +<!ENTITY adv-to "adverb taking the `to' particle"> +<!ENTITY arch "archaism"> +<!ENTITY ateji "ateji (phonetic) reading"> +<!ENTITY aux "auxiliary"> +<!ENTITY aux-v "auxiliary verb"> +<!ENTITY aux-adj "auxiliary adjective"> +<!ENTITY Buddh "Buddhist term"> +<!ENTITY chn "children's language"> +<!ENTITY col "colloquialism "> +<!ENTITY comp "computer terminology"> +<!ENTITY conj "conjunction"> +<!ENTITY derog "derogatory"> +<!ENTITY ek "exclusively kanji"> +<!ENTITY exp "Expressions (phrases, clauses, etc.)"> +<!ENTITY fam "familiar language "> +<!ENTITY fem "female term or language"> +<!ENTITY food "food term"> +<!ENTITY geom "geometry term"> +<!ENTITY gikun "gikun (meaning) reading"> +<!ENTITY gram "grammatical term"> +<!ENTITY hon "honorific or respectful (sonkeigo) language "> +<!ENTITY hum "humble (kenjougo) language "> +<!ENTITY iK "word containing irregular kanji usage"> +<!ENTITY id "idiomatic expression "> +<!ENTITY ik "word containing irregular kana usage"> +<!ENTITY int "interjection (kandoushi)"> +<!ENTITY io "irregular okurigana usage"> +<!ENTITY iv "irregular verb"> +<!ENTITY ling "linguistics terminology"> +<!ENTITY m-sl "manga slang"> +<!ENTITY male "male term or language"> +<!ENTITY male-sl "male slang"> +<!ENTITY math "mathematics"> +<!ENTITY mil "military"> +<!ENTITY n "noun (common) (futsuumeishi)"> +<!ENTITY n-adv "adverbial noun (fukushitekimeishi)"> +<!ENTITY n-suf "noun, used as a suffix"> +<!ENTITY n-pref "noun, used as a prefix"> +<!ENTITY n-t "noun (temporal) (jisoumeishi)"> +<!ENTITY neg "negative (in a negative sentence, or with negative verb)"> +<!ENTITY neg-v "negative verb (when used with)"> +<!ENTITY num "numeric"> +<!ENTITY oK "word containing out-dated kanji "> +<!ENTITY obs "obsolete term"> +<!ENTITY obsc "obscure term"> +<!ENTITY ok "out-dated or obsolete kana usage"> +<!ENTITY pol "polite (teineigo) language "> +<!ENTITY pref "prefix "> +<!ENTITY prt "particle "> +<!ENTITY physics "physics terminology"> +<!ENTITY qv "quod vide (see another entry)"> +<!ENTITY rare "rare"> +<!ENTITY sl "slang"> +<!ENTITY suf "suffix "> +<!ENTITY uK "word usually written using kanji alone "> +<!ENTITY uk "word usually written using kana alone "> +<!ENTITY v1 "Ichidan verb"> +<!ENTITY v5 "Godan verb (not completely classified)"> +<!ENTITY v5aru "Godan verb - -aru special class"> +<!ENTITY v5b "Godan verb with `bu' ending"> +<!ENTITY v5g "Godan verb with `gu' ending"> +<!ENTITY v5k "Godan verb with `ku' ending"> +<!ENTITY v5k-s "Godan verb - Iku/Yuku special class"> +<!ENTITY v5m "Godan verb with `mu' ending"> +<!ENTITY v5n "Godan verb with `nu' ending"> +<!ENTITY v5r "Godan verb with `ru' ending"> +<!ENTITY v5r-i "Godan verb with `ru' ending (irregular verb)"> +<!ENTITY v5s "Godan verb with `su' ending"> +<!ENTITY v5t "Godan verb with `tsu' ending"> +<!ENTITY v5u "Godan verb with `u' ending"> +<!ENTITY v5u-s "Godan verb with `u' ending (special class)"> +<!ENTITY v5uru "Godan verb - Uru old class verb (old form of Eru)"> +<!ENTITY vi "intransitive verb "> +<!ENTITY vk "Kuru verb - special class"> +<!ENTITY vs "noun or participle which takes the aux. verb suru"> +<!ENTITY vs-s "suru verb - special class"> +<!ENTITY vs-i "suru verb - irregular"> +<!ENTITY vz "zuru verb - (alternative form of -jiru verbs)"> +<!ENTITY vt "transitive verb"> +<!ENTITY vulg "vulgar expression or word "> +<!ENTITY mg "masculine gender"> +<!ENTITY fg "feminine gender"> +<!ENTITY ng "neuter gender"> +]> +<!-- JMdict created: 2006-09-11 --> +<JMdict> +<!-- JMdict Japanese-Multilingual Dictionary file (XML format) --> +<!-- Using V1.05 of the DTD --> +<!-- Copyright J.W. Breen (jwb@csse.monash.edu.au) --> +<entry> +<ent_seq>1000000</ent_seq> +<k_ele> +<keb>ヽ</keb> +</k_ele> +<r_ele> +<reb>くりかえし</reb> +</r_ele> +<sense> +<pos>&n;</pos> +<gloss>repetition mark in katakana</gloss> +<gloss g_lang="de">Wiederholungszeichen für Katakana</gloss> +<gloss g_lang="de">normalerweise nur in vertikaler Schreibweise verwendet</gloss> +<gloss g_lang="fr">marque de la répétition dans katakana</gloss> +<gloss g_lang="fr">(JF2)</gloss> +</sense> +</entry> +<entry> +<ent_seq>1000010</ent_seq> +<k_ele> +<keb>ヾ</keb> +</k_ele> +<r_ele> +<reb>くりかえし</reb> +</r_ele> +<sense> +<pos>&n;</pos> +<gloss>voiced repetition mark in katakana</gloss> +<gloss g_lang="de">stimmhaftes Wiederholungszeichen für Katakana</gloss> +<gloss g_lang="de">normalerweise nur in vertikaler Schreibweise verwendet</gloss> +<gloss g_lang="fr">marque de la répétition sonore dans katakana</gloss> +<gloss g_lang="fr">(JF2)</gloss> +</sense> +</entry> +<entry> +<ent_seq>1000020</ent_seq> +<k_ele> +<keb>ゝ</keb> +</k_ele> +<r_ele> +<reb>くりかえし</reb> +</r_ele> +<sense> +<pos>&n;</pos> +<gloss>repetition mark in hiragana</gloss> +<gloss g_lang="de">Wiederholungszeichen für Hiragana</gloss> +<gloss g_lang="de">normalerweise nur in vertikaler Schreibweise verwendet</gloss> +<gloss g_lang="fr">marque de la répétition dans hiragana</gloss> +<gloss g_lang="fr">(JF2)</gloss> +</sense> +</entry> +<entry> +<ent_seq>1000030</ent_seq> +<k_ele> +<keb>ゞ</keb> +</k_ele> +<r_ele> +<reb>くりかえし</reb> +</r_ele> +<sense> +<pos>&n;</pos> +<gloss>voiced repetition mark in hiragana</gloss> +<gloss g_lang="de">stimmhaftes Wiederholungszeichen für Hiragana</gloss> +<gloss g_lang="de">normalerweise nur in vertikaler Schreibweise verwendet</gloss> +<gloss g_lang="fr">marque de la répétition sonore dans hiragana</gloss> +<gloss g_lang="fr">(JF2)</gloss> +</sense> +</entry> +<entry> +<ent_seq>1000040</ent_seq> +<k_ele> +<keb>〃</keb> +</k_ele> +<r_ele> +<reb>おなじく</reb> +</r_ele> +<sense> +<pos>&n;</pos> +<gloss>ditto mark</gloss> +<gloss g_lang="ru">знак "то же самое"</gloss> +<gloss g_lang="de">Wiederholungszeichen in Tabellen</gloss> +<gloss g_lang="fr">idem marque</gloss> +<gloss g_lang="fr">(JF2)</gloss> +</sense> +</entry> +<entry> +<ent_seq>1000050</ent_seq> +<k_ele> +<keb>仝</keb> +</k_ele> +<r_ele> +<reb>どうじょう</reb> +</r_ele> +<sense> +<pos>&n;</pos> +<gloss>"as above" mark</gloss> +<gloss g_lang="de">Abkürzung für "siehe oben"</gloss> +<gloss g_lang="fr">comme au-dessus</gloss> +<gloss g_lang="fr">(JF2)</gloss> +</sense> +</entry> +<entry> +<ent_seq>1000060</ent_seq> +<k_ele> +<keb>々</keb> +</k_ele> +<r_ele> +<reb>くりかえし</reb> +</r_ele> +<sense> +<pos>&n;</pos> +<gloss>repetition of kanji (sometimes voiced)</gloss> +<gloss g_lang="de">Wiederholungszeichen für Kanji</gloss> +<gloss g_lang="de">(Laut wird durch Wiederholung manchmal stimmhaft)</gloss> +<gloss g_lang="fr">répétition de kanji(quelquefois a exprimé)</gloss> +<gloss g_lang="fr">(JF2)</gloss> +</sense> +</entry> +<entry> +<ent_seq>1000070</ent_seq> +<k_ele> +<keb>〆</keb> +</k_ele> +<r_ele> +<reb>しめ</reb> +</r_ele> +<sense> +<pos>&n;</pos> +<gloss>end or closure mark</gloss> +<gloss g_lang="de">Zeichen als eine Art Versiegelung über der zugeklebten Lasche auf der Rückseite eines Briefumschlages</gloss> +<gloss g_lang="fr">fin ou marque de la fermeture</gloss> +<gloss g_lang="fr">(JF2)</gloss> +</sense> +</entry> +<entry> +<ent_seq>1000080</ent_seq> +<k_ele> +<keb>〇</keb> +</k_ele> +<k_ele> +<keb>○</keb> +<ke_inf>&iK;</ke_inf> +</k_ele> +<r_ele> +<reb>かんすうじゼロ</reb> +</r_ele> +<sense> +<pos>&n;</pos> +<xref>漢数字</xref> +<xref>ゼロ</xref> +<gloss>"kanji" zero</gloss> +<gloss g_lang="de">Kanji-Ziffer für Null</gloss> +<gloss g_lang="fr">kanji</gloss> +<gloss g_lang="fr">(JF2)</gloss> +</sense> +</entry> +<entry> +<ent_seq>1000090</ent_seq> +<k_ele> +<keb>○</keb> +</k_ele> +<k_ele> +<keb>〇</keb> +<ke_inf>&iK;</ke_inf> +</k_ele> +<r_ele> +<reb>まる</reb> +</r_ele> +<sense> +<pos>&n;</pos> +<gloss>circle (sometimes used for zero)</gloss> +<gloss g_lang="ru">круг</gloss> +<gloss g_lang="ru">но́ль</gloss> +<gloss g_lang="de">Kreis</gloss> +<gloss g_lang="de">Markierung für "richtig"</gloss> +<gloss g_lang="de">Maru</gloss> +<gloss g_lang="de">(ein japan. Schriftfont hat mindestens drei verschiedene Codierungen und Darstellungen für "maru")</gloss> +<gloss g_lang="fr">entourez</gloss> +<gloss g_lang="fr">mettez à zéro</gloss> +<gloss g_lang="fr">(JF2)</gloss> +</sense> +</entry> +<entry> +<ent_seq>1000100</ent_seq> +<k_ele> +<keb>ＡＢＣ順</keb> +</k_ele> +<r_ele> +<reb>エービーシーじゅん</reb> +</r_ele> +<r_ele> +<reb>ええびいしいじゅん</reb> +</r_ele> +<sense> +<pos>&n;</pos> +<gloss>alphabetical order</gloss> +<gloss g_lang="de">alphabetische Ordnung</gloss> +<gloss g_lang="de">alphabetische Reihenfolge</gloss> +<gloss g_lang="fr">ordre alphabétique</gloss> +<gloss g_lang="fr">(JF2)</gloss> +</sense> +</entry> +<entry> +<ent_seq>1000110</ent_seq> +<k_ele> +<keb>ＣＤプレーヤー</keb> +</k_ele> +<r_ele> +<reb>シーディープレーヤー</reb> +</r_ele> +<sense> +<pos>&n;</pos> +<gloss>CD player</gloss> +<gloss g_lang="ru">CD плеер</gloss> +<gloss g_lang="ru">проигрыватель компакт-дисков</gloss> +</sense> +</entry> +<entry> +<ent_seq>1000120</ent_seq> +<k_ele> +<keb>Ｈな映画</keb> +</k_ele> +<k_ele> +<keb>エッチな映画</keb> +</k_ele> +<r_ele> +<reb>エッチなえいが</reb> +</r_ele> +<sense> +<pos>&n;</pos> +<gloss>pornographic film</gloss> +<gloss>salacious film</gloss> +</sense> +</entry> +<entry> +<ent_seq>1000130</ent_seq> +<k_ele> +<keb>Ｎ響</keb> +</k_ele> +<r_ele> +<reb>エヌきょう</reb> +</r_ele> +<sense> +<pos>&n;</pos> +<misc>&abbr;</misc> +<gloss>NHK Symphony Orchestra</gloss> +<gloss g_lang="fr">NHK Symphonie Orchestre(abbr)</gloss> +<gloss g_lang="fr">(JF2)</gloss> +</sense> +</entry> +<entry> +<ent_seq>1000140</ent_seq> +<r_ele> +<reb>Ｏバック</reb> +</r_ele> +<sense> +<pos>&n;</pos> +<gloss>O-back</gloss> +<gloss>skirt with peek-a-boo hole in rump</gloss> +<gloss g_lang="fr">O En arrière</gloss> +<gloss g_lang="fr">contournez avec coucou trou dans croupe</gloss> +<gloss g_lang="fr">(JF2)</gloss> +</sense> +</entry> +<entry> +<ent_seq>1000150</ent_seq> +<r_ele> +<reb>ＲＳ２３２ケーブル</reb> +</r_ele> +<sense> +<pos>&n;</pos> +<gloss>rs232 cable</gloss> +<gloss g_lang="fr">les rs232 câblent</gloss> +<gloss g_lang="fr">(JF2)</gloss> +</sense> +</entry> +</JMdict> |