alex/jmdict
1
Fork 0
Code Releases Activity

WIP

Browse Source
This commit is contained in:
Alex Yatskov 2016-07-31 16:10:17 -07:00
parent 74b76375a8
commit e01ad784d2
2 changed files with 25 additions and 25 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

30
edict.go
View File

@ -30,7 +30,7 @@ import (
// Entries consist of kanji elements, reading elements, // Entries consist of kanji elements, reading elements,
// general information and sense elements. Each entry must have at // general information and sense elements. Each entry must have at
// least one reading element and one sense element. Others are optional. // least one reading element and one sense element. Others are optional.
type edictEntry struct { type EdictEntry struct {
// A unique numeric sequence number for each entry // A unique numeric sequence number for each entry
Sequence int `xml:"ent_seq"` Sequence int `xml:"ent_seq"`
@ -44,7 +44,7 @@ type edictEntry struct {
// included, provided they are associated with appropriate information // included, provided they are associated with appropriate information
// fields. Synonyms are not included; they may be indicated in the // fields. Synonyms are not included; they may be indicated in the
// cross-reference field associated with the sense element. // cross-reference field associated with the sense element.
Kanji []edictKanji `xml:"k_ele"` Kanji []EdictKanji `xml:"k_ele"`
// The reading element typically contains the valid readings // The reading element typically contains the valid readings
// of the word(s) in the kanji element using modern kanadzukai. // of the word(s) in the kanji element using modern kanadzukai.
@ -52,16 +52,16 @@ type edictEntry struct {
// alternative readings of the kanji element. In the absence of a // alternative readings of the kanji element. In the absence of a
// kanji element, i.e. in the case of a word or phrase written // kanji element, i.e. in the case of a word or phrase written
// entirely in kana, these elements will define the entry. // entirely in kana, these elements will define the entry.
Reading []edictReading `xml:"r_ele"` Reading []EdictReading `xml:"r_ele"`
// The sense element will record the translational equivalent // The sense element will record the translational equivalent
// of the Japanese word, plus other related information. Where there // of the Japanese word, plus other related information. Where there
// are several distinctly different meanings of the word, multiple // are several distinctly different meanings of the word, multiple
// sense elements will be employed. // sense elements will be employed.
Sense []edictSense `xml:"sense"` Sense []EdictSense `xml:"sense"`
} }
type edictKanji struct { type EdictKanji struct {
// This element will contain a word or short phrase in Japanese // This element will contain a word or short phrase in Japanese
// which is written using at least one non-kana character (usually kanji, // which is written using at least one non-kana character (usually kanji,
// but can be other characters). The valid characters are // but can be other characters). The valid characters are
@ -105,7 +105,7 @@ type edictKanji struct {
Priority []string `xml:"ke_pri"` Priority []string `xml:"ke_pri"`
} }
type edictReading struct { type EdictReading struct {
// This element content is restricted to kana and related // This element content is restricted to kana and related
// characters such as chouon and kurikaeshi. Kana usage will be // characters such as chouon and kurikaeshi. Kana usage will be
// consistent between the keb and reb elements; e.g. if the keb // consistent between the keb and reb elements; e.g. if the keb
@ -134,7 +134,7 @@ type edictReading struct {
Priority []string `xml:"re_pri"` Priority []string `xml:"re_pri"`
} }
type edictSource struct { type EdictSource struct {
Content string `xml:",chardata"` Content string `xml:",chardata"`
// The xml:lang attribute defines the language(s) from which // The xml:lang attribute defines the language(s) from which
@ -156,7 +156,7 @@ type edictSource struct {
Wasei string `xml:"ls_wasei,attr"` Wasei string `xml:"ls_wasei,attr"`
} }
type edictGlossary struct { type EdictGlossary struct {
Content string `xml:",chardata"` Content string `xml:",chardata"`
// The xml:lang attribute defines the target language of the // The xml:lang attribute defines the target language of the
@ -171,7 +171,7 @@ type edictGlossary struct {
Gender string `xml:"g_gend"` Gender string `xml:"g_gend"`
} }
type edictSense struct { type EdictSense struct {
// These elements, if present, indicate that the sense is restricted // These elements, if present, indicate that the sense is restricted
// to the lexeme represented by the keb and/or reb. // to the lexeme represented by the keb and/or reb.
RestrictKanji []string `xml:"stagk"` RestrictKanji []string `xml:"stagk"`
@ -200,7 +200,7 @@ type edictSense struct {
// Information about the field of application of the entry/sense. // Information about the field of application of the entry/sense.
// When absent, general application is implied. Entity coding for // When absent, general application is implied. Entity coding for
// specific fields of application. // specific fields of application.
Field []string `xml:"field"` Fields []string `xml:"field"`
// This element is used for other relevant information about // This element is used for other relevant information about
// the entry/sense. As with part-of-speech, information will usually // the entry/sense. As with part-of-speech, information will usually
@ -211,7 +211,7 @@ type edictSense struct {
// language(s) of a loan-word/gairaigo. If the source language is other // language(s) of a loan-word/gairaigo. If the source language is other
// than English, the language is indicated by the xml:lang attribute. // than English, the language is indicated by the xml:lang attribute.
// The element value (if any) is the source word or phrase. // The element value (if any) is the source word or phrase.
SourceLanguage []edictSource `xml:"lsource"` SourceLanguage []EdictSource `xml:"lsource"`
// For words specifically associated with regional dialects in // For words specifically associated with regional dialects in
// Japanese, the entity code for that dialect, e.g. ksb for Kansaiben. // Japanese, the entity code for that dialect, e.g. ksb for Kansaiben.
@ -227,18 +227,18 @@ type edictSense struct {
// target-language words or phrases which are equivalents to the // target-language words or phrases which are equivalents to the
// Japanese word. This element would normally be present, however it // Japanese word. This element would normally be present, however it
// may be omitted in entries which are purely for a cross-reference. // may be omitted in entries which are purely for a cross-reference.
Glossary []edictGlossary `xml:"gloss"` Glossary []EdictGlossary `xml:"gloss"`
} }
func LoadEdict(reader io.Reader, transform bool) ([]edictEntry, map[string]string, error) { func LoadEdict(reader io.Reader, transform bool) ([]EdictEntry, map[string]string, error) {
var entries []edictEntry var entries []EdictEntry
entities, err := parseEntries(reader, transform, func(decoder *xml.Decoder, element *xml.StartElement) error { entities, err := parseEntries(reader, transform, func(decoder *xml.Decoder, element *xml.StartElement) error {
if element.Name.Local != "entry" { if element.Name.Local != "entry" {
return nil return nil
} }
var entry edictEntry var entry EdictEntry
if err := decoder.DecodeElement(&entry, element); err != nil { if err := decoder.DecodeElement(&entry, element); err != nil {
return err return err
} }

20
enamdict.go
View File

@ -30,7 +30,7 @@ import (
// Entries consist of kanji elements, reading elements // Entries consist of kanji elements, reading elements
// name translation elements. Each entry must have at // name translation elements. Each entry must have at
// least one reading element and one sense element. Others are optional. // least one reading element and one sense element. Others are optional.
type enamdictEntry struct { type EnamdictEntry struct {
// A unique numeric sequence number for each entry // A unique numeric sequence number for each entry
Sequence int `xml:"ent_seq"` Sequence int `xml:"ent_seq"`
@ -44,7 +44,7 @@ type enamdictEntry struct {
// included, provided they are associated with appropriate information // included, provided they are associated with appropriate information
// fields. Synonyms are not included; they may be indicated in the // fields. Synonyms are not included; they may be indicated in the
// cross-reference field associated with the sense element. // cross-reference field associated with the sense element.
Kanji []enamdictKanji `xml:"k_ele"` Kanji []EnamdictKanji `xml:"k_ele"`
// The reading element typically contains the valid readings // The reading element typically contains the valid readings
// of the word(s) in the kanji element using modern kanadzukai. // of the word(s) in the kanji element using modern kanadzukai.
@ -52,14 +52,14 @@ type enamdictEntry struct {
// alternative readings of the kanji element. In the absence of a // alternative readings of the kanji element. In the absence of a
// kanji element, i.e. in the case of a word or phrase written // kanji element, i.e. in the case of a word or phrase written
// entirely in kana, these elements will define the entry. // entirely in kana, these elements will define the entry.
Reading []enamdictReading `xml:"r_ele"` Reading []EnamdictReading `xml:"r_ele"`
// The trans element will record the translational equivalent // The trans element will record the translational equivalent
// of the Japanese name, plus other related information. // of the Japanese name, plus other related information.
Translation []enamTranslation `xml:"trans"` Translation []EnamdictTranslation `xml:"trans"`
} }
type enamdictKanji struct { type EnamdictKanji struct {
// This element will contain an entity name in Japanese // This element will contain an entity name in Japanese
// which is written using at least one non-kana character (usually // which is written using at least one non-kana character (usually
// kanji, but can be other characters). The valid // kanji, but can be other characters). The valid
@ -82,7 +82,7 @@ type enamdictKanji struct {
Priority []string `xml:"ke_pri"` Priority []string `xml:"ke_pri"`
} }
type enamdictReading struct { type EnamdictReading struct {
// This element content is restricted to kana and related // This element content is restricted to kana and related
// characters such as chouon and kurikaeshi. Kana usage will be // characters such as chouon and kurikaeshi. Kana usage will be
// consistent between the keb and reb elements; e.g. if the keb // consistent between the keb and reb elements; e.g. if the keb
@ -104,7 +104,7 @@ type enamdictReading struct {
Priority []string `xml:"re_pri"` Priority []string `xml:"re_pri"`
} }
type enamTranslation struct { type EnamdictTranslation struct {
// The type of name, recorded in the appropriate entity codes. // The type of name, recorded in the appropriate entity codes.
NameType []string `xml:"name_type"` NameType []string `xml:"name_type"`
@ -129,15 +129,15 @@ type enamTranslation struct {
Language string `xml:"lang,attr"` Language string `xml:"lang,attr"`
} }
func LoadEnamdict(reader io.Reader, transform bool) ([]enamdictEntry, map[string]string, error) { func LoadEnamdict(reader io.Reader, transform bool) ([]EnamdictEntry, map[string]string, error) {
var entries []enamdictEntry var entries []EnamdictEntry
entities, err := parseEntries(reader, transform, func(decoder *xml.Decoder, element *xml.StartElement) error { entities, err := parseEntries(reader, transform, func(decoder *xml.Decoder, element *xml.StartElement) error {
if element.Name.Local != "entry" { if element.Name.Local != "entry" {
return nil return nil
} }
var entry enamdictEntry var entry EnamdictEntry
if err := decoder.DecodeElement(&entry, element); err != nil { if err := decoder.DecodeElement(&entry, element); err != nil {
return err return err
} }