README
¶
JMdict is a Japanese dictionary compiled by Jim Breen with Copyright (C) 2010
belonging to the Electronic Dictionary Research and Development Group at
Monash University. More information can be found here.
http://www.csse.monash.edu.au/~jwb/edict_doc.html
This package contains a basic means for parsing and working with
the JMdict file, specifically version 1.0.7 but probably other versions.
The library is unpolished, and there will likely be bugs. I make this
available in the hope that someone will find it useful.
in := os.Open('path')
dict := jmjmdict.Read(in)
Documentation
¶
Index ¶
- Constants
- func DescribeDialect(dialect Dialect) string
- func DescribeField(field Field) string
- func DescribeOrthography(orthography Orthography) string
- func DescribePosition(position Position) string
- type Audit
- type Bibl
- type Dialect
- type EntSeq
- type Entry
- type Field
- type Info
- type JMDict
- type KEle
- type KePriority
- type Keb
- type LSource
- type Links
- type Misc
- type Orthography
- type Position
- type Priority
- type PriorityCode
- type REle
- type RePriority
- type ReRestr
- type Reb
- type Sense
Constants ¶
const ( AdjI Position = "adj-i" // adjective (keiyoushi) AdjKu = "adj-ku" // `ku' adjective (archaic) AdjNa = "adj-na" // adjectival nouns or quasi-adjectives (keiyodoshi) AdjNari = "adj-nari" // archaic/formal form of na-adjective AdjNo = "adj-no" // nouns which may take the genitive case particle `no' AdjPreNoun = "adj-pn" // pre-noun adjectival (rentaishi) AdjShiku = "adj-shiku" // `shiku' adjective (archaic) AdjTaru = "adj-t" // `taru' adjective AdjFunctional = "adj-f" // noun or verb acting prenominally Adv = "adv" // adverb (fukushi) AdvTo = "adv-to" // adverb taking the `to' particle Aux = "aux" // auxiliary AuxAdj = "aux-adj" // auxiliary adjective AuxVerb = "aux-v" // auxiliary verb Conj = "conj" // conjunction Counter = "ctr" // counter Expression = "exp" // Expressions (phrases, clauses, etc.) Interjection = "int" // interjection (kandoushi) Noun = "n" // noun (common) (futsuumeishi) NounAdv = "n-adv" // adverbial noun (fukushitekimeishi) NounPropper = "n-pr" // proper noun NounPrefix = "n-pref" // noun, used as a prefix NounSuffix = "n-suf" // noun, used as a suffix NounTemporal = "n-t" // noun (temporal) (jisoumeishi) Numeric = "num" // numeric Pronoun = "pn" // pronoun Prefix = "pref" // prefix Particle = "prt" // particle Suffix = "suf" // suffix Verb1 = "v1" // Ichidan verb Verb2as = "v2a-s" // Nidan verb with 'u' ending (archaic) Verb2bk = "v2b-k" // Nidan verb (upper class) with `bu' ending (archaic) Verb2ds = "v2d-s" // Nidan verb (lower class) with `dzu' ending (archaic) Verb2gk = "v2g-k" // Nidan verb (upper class) with `gu' ending (archaic) Verb2gs = "v2g-s" // Nidan verb (lower class) with `gu' ending (archaic) Verb2hk = "v2h-k" // Nidan verb (upper class) with `hu/fu' ending (archaic) Verb2hs = "v2h-s" // Nidan verb (lower class) with `hu/fu' ending (archaic) Verb2kk = "v2k-k" // Nidan verb (upper class) with `ku' ending (archaic) Verb2ks = "v2k-s" // Nidan verb (lower class) with `ku' ending (archaic) Verb2ms = "v2m-s" // Nidan verb (lower class) with `mu' ending (archaic) Verb2ns = "v2n-s" // Nidan verb (lower class) with `nu' ending (archaic) Verb2rk = "v2r-k" // Nidan verb (upper class) with `ru' ending (archaic) Verb2rs = "v2r-s" // Nidan verb (lower class) with `ru' ending (archaic) Verb2ss = "v2s-s" // Nidan verb (lower class) with `su' ending (archaic) Verb2tk = "v2t-k" // Nidan verb (upper class) with `tsu' ending (archaic) Verb2ts = "v2t-s" // Nidan verb (lower class) with `tsu' ending (archaic) Verb2ws = "v2w-s" // Nidan verb (lower class) with `u' ending and `we' conjugation (archaic) Verb2yk = "v2y-k" // Nidan verb (upper class) with `yu' ending (archaic) Verb2ys = "v2y-s" // Nidan verb (lower class) with `yu' ending (archaic) Verb2zs = "v2z-s" // Nidan verb (lower class) with `zu' ending (archaic) Verb4b = "v4b" // Yodan verb with `bu' ending (archaic) Verb4h = "v4h" // Yodan verb with `hu/fu' ending (archaic) Verb4k = "v4k" // Yodan verb with `ku' ending (archaic) Verb4r = "v4r" // Yodan verb with `ru' ending (archaic) Verb4s = "v4s" // Yodan verb with `su' ending (archaic) Verb4t = "v4t" // Yodan verb with `tsu' ending (archaic) Verb5aru = "v5aru" // Godan verb - -aru special class Verb5b = "v5b" // Godan verb with `bu' ending Verb5g = "v5g" // Godan verb with `gu' ending Verb5k = "v5k" // Godan verb with `ku' ending Verb5ks = "v5k-s" // Godan verb - Iku/Yuku special class Verb5m = "v5m" // Godan verb with `mu' ending Verb5n = "v5n" // Godan verb with `nu' ending Verb5r = "v5r" // Godan verb with `ru' ending Verb5ri = "v5r-i" // Godan verb with `ru' ending (irregular verb) Verb5s = "v5s" // Godan verb with `su' ending Verb5t = "v5t" // Godan verb with `tsu' ending Verb5u = "v5u" // Godan verb with `u' ending Verb5us = "v5u-s" // Godan verb with `u' ending (special class) VerbIntransitive = "vi" // intransitive verb VerbKuru = "vk" // Kuru verb - special class VerbNu = "vn" // irregular nu verb VerbRu = "vr" // irregular ru verb, plain form ends with -ri VerbSuru = "vs" // noun or participle which takes the aux. verb suru VerbSu = "vs-c" // su verb - precursor to the modern suru VerbIrregularSuru = "vs-i" // suru verb - irregular VerbSuruSpecial = "vs-s" // suru verb - special class VerbTransitive = "vt" // transitive verb VerbZuru = "vz" // Ichidan verb - zuru verb (alternative form of -jiru verbs) )
const ( Anatomical Field = "anat" // anatomical term Architecture = "archit" // architecture term Astronomy = "astron" // astronomy, etc. term Baseball = "baseb" // baseball term Biology = "biol" // biology term Botany = "bot" // botany term Business = "bus" // business term Chemistry = "chem" // chemistry term Computer = "comp" // computer terminology Economics = "econ" // economics term Engineering = "engr" // engineering term Finance = "finc" // finance term Food = "food" // food term Geology = "geol" // geology, etc. term Geometry = "geom" // geometry term Law = "law" // law, etc. term Linguistics = "ling" // linguistics terminology Martial = "MA" // martial arts term Mathematics = "math" // mathematics Medicine = "med" // medicine, etc. term Military = "mil" // military Music = "music" // music term Physics = "physics" // physics terminology Sports = "sports" // sports term Sumo = "sumo" // sumo term Zoology = "zool" // zoology term )
const ( Abbreviation Misc = "abbr" // abbreviation Archaism = "arch" // archaism ChildLanguage = "chn" // children's language Colloquialism = "col" // colloquialism Derogatory = "derog" // derogatory Familiar = "fam" // familiar language FemaleLanguage = "fem" // female term or language Honorific = "hon" // honorific or respectful (sonkeigo) language Humble = "hum" // humble (kenjougo) language Idiomatic = "id" // idiomatic expression Jocular = "joc" // jocular, humorous term MaleLanguage = "male" // male term or language Manga = "m-sl" // manga slang Obsolete = "obs" // obsolete term Obscure = "obsc" // obscure term Onomatopoeic = "on-mim" // onomatopoeic or mimetic word Poetical = "poet" // poetical term Polite = "pol" // polite (teineigo) language Proverb = "proverb" // proverb Rare = "rare" // rare Sensitive = "sens" // sensitive Slang = "sl" // slang KanaAlone = "uk" // word usually written using kana alone Vulgar = "vulg" // vulgar expression or word XRated = "X" // rude or X-rated term (not displayed in educational software) )
const ( HokkaidoBen Dialect = "hob" // Hokkaido-ben KansaiBen = "ksb" // Kansai-ben KantouBen = "ktb" // Kantou-ben KyotoBen = "kyb" // Kyoto-ben KyuushuuBen = "kyu" // Kyuushuu-ben NaganoBen = "nab" // Nagano-ben OsakaBen = "osb" // Osaka-ben RyuukyuuBen = "rkb" // Ryuukyuu-ben TouhokuBen = "thb" // Touhoku-ben TosaBen = "tsb" // Tosa-ben TsugaruBen = "tsug" // Tsugaru-ben )
const ( Ateji Orthography = "ateji" // ateji (phonetic) reading Gikun = "gikun" // gikun (meaning as reading) or jukujikun (special kanji reading) IrregularKanji = "iK" // word containing irregular kanji usage IrregularKana = "ik" // word containing irregular kana usage IrregularOkurigana = "io" // irregular okurigana usage OutdatedKanji = "oK" // out-dated or obsolete kanji usage OutdatedKana = "ok" // out-dated or obsolete kana usage OutdatedOrIrregularKana = "oik" // "old or irregular kana form KanjiAlone = "uK" // word usually written using kanji alone )
const ( Newspaper PriorityCode = "news" // news1/news2 BunruiShuu = "ichi" // ichi1/ichi2 LoanWord = "gai" // gai1/gai2 Special = "spec" // spec1/spec2 Frequency = "nf" // nfxx )
Variables ¶
This section is empty.
Functions ¶
func DescribeDialect ¶
Produce a human readable description of a Dialect
func DescribeField ¶
Produce a human readable description of a Field
func DescribeOrthography ¶
func DescribeOrthography(orthography Orthography) string
Produce a human readable description of an Orthography
func DescribePosition ¶
Produce a human readable description of a Position
Types ¶
type Audit ¶
type Audit struct {
XMLName xml.Name `xml:"audit"`
UpdDate string `xml:"upd_date"`
UpdDetl string `xml:"upd_detl"`
}
The audit element will contain the date and other information about updates to the entry. Can be used to record the source of
type Bibl ¶
type Bibl struct {
XMLName xml.Name `xml:"bibl"`
BibTag string `xml:"bib_tag"`
BibTxt string `xml:"bib_txt"`
}
Bibliographic information about the entry. The bib_tag will a coded reference to an entry in an external bibliographic database.
type Entry ¶
type Entry struct {
XMLName xml.Name `xml:"entry"`
Id EntSeq `xml:"ent_seq"`
Kanji []KEle `xml:"k_ele"`
Reading []REle `xml:"r_ele"`
Info Info `xml:"info"`
Sense []Sense `xml:"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.
type KEle ¶
type KEle struct {
XMLName xml.Name `xml:"k_ele"`
Phrase Keb `xml:"keb"`
Info []Orthography `xml:"ke_inf"`
Priority []KePriority `xml:"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.
type KePriority ¶
type Keb ¶
type Keb string
This element will contain a word or short phrase in Japanese which is written using at least one non-kana character (usually kanji, but can be other characters). The valid characters are kanji, kana, related characters such as chouon and kurikaeshi, and in exceptional cases, letters from other alphabets.
type Links ¶
type Links struct {
XMLName xml.Name `xml:"links"`
LinkTag string `xml:"link_tag"`
LinkDesc string `xml:"link_desc"`
LinkUri string `xml:"link_uri"`
}
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.
type Orthography ¶
type Orthography string
This is a coded information field related specifically to the orthography of the keb or reb, and will typically indicate some unusual aspect, such as okurigana irregularity.
type Priority ¶
type Priority struct {
// String representation of Priority which other fields
// will be parsed from after unmarshalling
Raw string `xml:",chardata"`
Code PriorityCode `xml:"-"`
Rank int `xml:"-"`
}
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. (The entries marked "ichi2" were demoted from ichi1 because they were observed to have low frequencies in the WWW and newspapers.) - 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. - gai1/2: 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 entries with news1, ichi1, spec1 and gai1 values are marked with a "(P)" in the EDICT and EDICT2 files.) 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.
type PriorityCode ¶
type PriorityCode string
type REle ¶
type REle struct {
XMLName xml.Name `xml:"r_ele"`
Phrase Reb `xml:"reb"`
// 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. A non-nil value represents true
ImproperReading *string `xml:"re_nokanji"`
Restrict []ReRestr `xml:"re_restr"`
Orthography []Orthography `xml:"re_inf"`
Priority []RePriority `xml:"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.
type RePriority ¶
type ReRestr ¶
type ReRestr string
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.
type Reb ¶
type Reb string
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.
type Sense ¶
type Sense struct {
XMLName xml.Name `xml:"sense"`
// Indicate that the sense is restricted to listed Kanji usages
KanjiRestrict []string `xml:"stagk"`
// Indicate that the sense is restricted to listed Reading usages
ReadingRestrict []string `xml:"stagr"`
// Part-of-speech information about the entry/sense. Should use
// appropriate entity codes. In general where there are multiple senses
// in an entry, the part-of-speech of an earlier sense will apply to
// later senses unless there is a new part-of-speech indicated.
Position []Position `xml:"pos"`
// 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 is typically a keb or reb element in another entry. In some
// cases a keb will be followed by a reb and/or a sense number to provide
// a precise target for the cross-reference. Where this happens, a JIS
// "centre-dot" (0x2126) is placed between the components of the
// cross-reference.
Xref []string `xml:"xref"`
// 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.
Antonym []string `xml:"ant"`
// Information about the field of application of the entry/sense.
// When absent, general application is implied. Entity coding for
Field []Field `xml:"field"`
// This element is used for other relevant information about
// the entry/sense. As with part-of-speech, information will usually
// apply to several senses.
Misc []Misc `xml:"misc"`
// 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.
Info []string `xml:"s_inf"`
// This element records the information about the source
// language(s) of a loan-word/gairaigo. If the source language is other
// than English, the language is indicated by the xml:lang attribute.
// The element value (if any) is the source word or phrase.
LSource []LSource `xml:"lsource"`
Dialect []Dialect `xml:"dial"`
Gloss []string `xml:"gloss"`
Example []string `xml:"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.
Source Files