en

package
v0.8.1 Latest Latest
Warning

This package is not in the latest version of its module.

 Go to latest Published: Aug 7, 2026 License: AGPL-3.0 Imports: 5 Imported by: 0

Documentation

Overview

Package en provides Go structures to serialize / deserialize English-language version of extracted Wiktionary raw data.

The reference for the structs can be seen at <https://github.com/tatuylonen/wiktextract/raw/refs/heads/master/src/wiktextract/extractor/en/type_utils.py> and is copied below.

Index

Constants

This section is empty.

Variables

This section is empty.

Functions

This section is empty.

Types

type AltOf 

type AltOf struct {
	Word  string  `json:"word" db:"INDEX"`
	Extra *string `json:"extra,omitempty"`
}

AltOf represents an alternative form or inflected form reference. `Word` contains the linked word, and `Extra` contains optional additional text.

type AttestationData 

type AttestationData struct {
	Date       string          `json:"date"`
	References []ReferenceData `json:"references,omitempty"`
}

type DeprecatedHyphenation added in v0.2.0 

type DeprecatedHyphenation struct {
	IsString     bool
	Hyphenation  string
	Hyphenations []string
}

func (*DeprecatedHyphenation) MarshalJSONTo added in v0.2.0 

func (h *DeprecatedHyphenation) MarshalJSONTo(enc *jsontext.Encoder) error

func (*DeprecatedHyphenation) UnmarshalJSONFrom added in v0.2.0 

func (h *DeprecatedHyphenation) UnmarshalJSONFrom(dec *jsontext.Decoder) error

type DescendantData 

type DescendantData struct {
	// Wiktionary language code
	LangCode string `json:"lang_code"`
	// Language name
	Lang        string           `json:"lang"`
	Word        string           `json:"word"`
	Roman       *string          `json:"roman"`
	Tags        []string         `json:"tags,omitempty"`
	RawTags     []string         `json:"raw_tags,omitempty"`
	Descendants []DescendantData `json:"descendants,omitempty"`
	// Japanese Kanji and furigana
	Ruby  [][]string `json:"ruby,omitempty"`
	Sense *string    `json:"sense,omitempty"`
}

type EtymologyExample 

type EtymologyExample struct {
	English     *string  `json:"english,omitempty"` // DEPRECATED in favour of `translation`
	Translation string   `json:"translation,omitempty"`
	RawTags     []string `json:"raw_tags,omitempty"`
	Ref         *string  `json:"ref,omitempty"`
	Roman       *string  `json:"roman,omitempty"`
	Tags        []string `json:"tags,omitempty"`
	Text        string   `json:"text,omitempty"`
	Type        *string  `json:"type,omitempty"`
}

type ExampleData 

type ExampleData struct {
	Alt     *string `json:"alt,omitempty"`
	English *string `json:"english,omitempty"` // DEPRECATED in favour of "translation"
	// English translation of the example sentence
	Translation            *string  `json:"translation,omitempty"`
	BoldTranslationOffsets [][2]int `json:"bold_translation_offsets,omitempty"`
	// English-language parenthesized note from the beginning of a non-English example
	Note *string `json:"note,omitempty"`
	// source reference
	Ref *string `json:"ref,omitempty"`
	// romanization of the example sentence (for some languages written in non-Latin scripts)
	Roman            *string  `json:"roman,omitempty"`
	BoldRomanOffsets [][2]int `json:"bold_roman_offsets,omitempty"`
	// Japanese Kanji and furigana
	Ruby [][]string `json:"ruby,omitempty"`
	// the example text
	Text            string   `json:"text"`
	BoldTextOffsets [][2]int `json:"bold_text_offsets,omitempty"`
	Tags            []string `json:"tags,omitempty"`
	RawTags         []string `json:"raw_tags,omitempty"`
}

ExampleData represents a usage example for a word sense.

type ExtraTemplateData 

type ExtraTemplateData struct {
	Tags    []string `json:"tags,omitempty"`
	Words   []string `json:"words,omitempty"`
	Meaning string   `json:"meaning"`
}

type FormData 

type FormData struct {
	Form   string  `json:"form"`
	HeadNr *int    `json:"head_nr"`
	Ipa    *string `json:"ipa,omitempty"`
	Roman  *string `json:"roman,omitempty"`
	// Japanese Kanji and furigana
	Ruby    [][]string `json:"ruby,omitempty"`
	Source  *string    `json:"source,omitempty"`
	Tags    []string   `json:"tags,omitempty"`
	RawTags []string   `json:"raw_tags,omitempty"`
	Topics  []string   `json:"topics,omitempty"`
	Links   []LinkData `json:"links,omitempty"`
}

FormData represents an inflected or alternative form of the word.

type FormOf 

type FormOf struct {
	Word  string  `json:"word" db:"INDEX"`
	Extra *string `json:"extra,omitempty"`
	Roman *string `json:"roman,omitempty"`
}

FormOf represents a word that this sense is an inflected form of. `Word` contains the linked word, and `Extra` contains optional additional text.

type Hyphenation 

type Hyphenation struct {
	Parts []string `json:"parts,omitempty"`
	Tags  []string `json:"tags,omitempty"`
}

type LinkData 

type LinkData [2]string
A link tuple, typically `["target", "gloss"]`.

Used in sense-level `links` to record wiki-internal links found in example sentences or glosses.

type LinkageData 

type LinkageData struct {
	// optional alternative form of the target (e.g., in a different script)
	Alt *string `json:"alt,omitempty"`
	// optional English text associated with the sense, usually identifying the
	// linked target sense
	English     *string  `json:"english,omitempty"` // DEPRECATED in favour of "translation"
	Translation string   `json:"translation"`
	Extra       *string  `json:"extra,omitempty"`
	Qualifier   *string  `json:"qualifier,omitempty"`
	RawTags     []string `json:"raw_tags,omitempty"`
	// optional romanization of a linked word in a non-Latin script
	Roman *string `json:"roman,omitempty"`
	// Japanese Kanji and furigana
	Ruby [][]string `json:"ruby,omitempty"`
	// text identifying the word sense or context (e.g., "to rain very heavily")
	Sense  *string `json:"sense,omitempty"`
	Source *string
	// qualifiers specified for the sense (e.g., field of study, region, dialect, style)
	Tags []string `json:"tags,omitempty"`
	// optional taxonomic name associated with the linkage
	Taxonomic *string `json:"taxonomic,omitempty"`
	// list of topic descriptors for the linkage (e.g., "military")
	Topics []string `json:"topics,omitempty"`
	Urls   []string `json:"urls,omitempty"`
	// the word this links to
	Word string `json:"word" db:"INDEX"`
}

LinkageData represents a linkage between words (synonyms, antonyms, hypernyms, derived words, holonyms, meronyms, related, coordinate_terms, etc.).

See: https://github.com/tatuylonen/wiktextract#linkages-to-other-words

type ReferenceData 

type ReferenceData struct {
	Text string  `json:"text"`
	Refn *string `json:"refn,omitempty"`
}

type SenseData 

type SenseData struct {
	// list of words that this sense is an alternative form of
	AltOf []AltOf `json:"alt_of,omitempty"`
	// sense-disambiguated antonym linkages for the word
	Antonyms []LinkageData `json:"antonyms,omitempty"`
	// list of sense-disambiguated category names extracted from (a subset)
	// of the Category links on the page
	Categories []string `json:"categories,omitempty"`
	CompoundOf []AltOf  `json:"compound_of,omitempty"`
	// sense-disambiguated coordinate term linkages for the word
	CoordinateTerms []LinkageData `json:"coordinate_terms,omitempty"`
	// list of usage examples, each with `text`, optional `ref` (source
	// reference), optional `english` (English translation), optional `type`
	// (example type, e.g., "example" or "quotation"), optional `roman`
	// (romanization), and optional `note` (parenthesized note)
	Examples []ExampleData `json:"examples,omitempty"`
	// list of words that this sense is an inflected form of
	FormOf []FormOf `json:"form_of,omitempty"`
	// list of gloss strings for the word sense (usually only one). This has
	// been cleaned, and should be straightforward text with no tagging.
	Glosses []string `json:"glosses,omitempty"`
	HeadNr  *int     `json:"head_nr"`
	// sense-disambiguated linkages indicating being part of something
	// (not systematically encoded)
	Holonyms []LinkageData `json:"holonyms,omitempty"`
	// sense-disambiguated hypernym linkages for the word
	Hypernyms []LinkageData `json:"hypernyms,omitempty"`
	// sense-disambiguated hyponym linkages for the word
	Hyponyms  []LinkageData `json:"hyponyms,omitempty"`
	Instances []LinkageData `json:"instances,omitempty"`
	Links     []LinkData    `json:"links,omitempty"`
	// sense-disambiguated linkages indicating having a part (fairly rare)
	Meronyms []LinkageData `json:"meronyms,omitempty"`
	// if the word sense has a qualifier that could not be parsed, that
	// qualifier is put in this field (rare). Most qualifiers are parsed
	// into `tags` and/or `topics`.
	Qualifier *string `json:"qualifier,omitempty"`
	// list of gloss strings with less cleaning than `glosses`; parenthesized
	// parts that have been parsed into `tags` and `topics` are still present
	RawGlosses []string `json:"raw_glosses,omitempty"`
	// sense-disambiguated related word linkages for the word
	Related []LinkageData `json:"related,omitempty"`
	// list of textual identifiers collected for the sense. If there is a
	// QID for the entry (e.g., Q123), those are stored in the `wikidata` field.
	Senseid []string `json:"senseid,omitempty"`
	// sense-disambiguated synonym linkages for the word
	Synonyms []LinkageData `json:"synonyms,omitempty"`
	// list of qualifiers and tags for the gloss, e.g., "archaic",
	// "colloquial", "present", "participle", "plural", "feminine"
	Tags      []string `json:"tags,omitempty"`
	Taxonomic *string  `json:"taxonomic,omitempty"`
	// list of sense-disambiguated topic names (kind of similar to
	// categories but determined differently)
	Topics []string `json:"topics,omitempty"`
	// list of QIDs (e.g., Q123) for the sense
	Wikidata []string `json:"wikidata,omitempty"`
	// list of Wikipedia page titles (with optional language code prefix)
	Wikipedia    []string          `json:"wikipedia,omitempty"`
	Attestations []AttestationData `json:"attestations,omitempty"`
}

SenseData represents a single word sense (gloss).

type SoundData 

type SoundData struct {
	// name of a sound file in WikiMedia Commons
	Audio *string `json:"audio,omitempty"`
	// IPA string associated with the audio file, generally giving IPA
	// transcription of what is in the sound file
	AudioIpa *string `json:"audio-ipa,omitempty"`
	// pronunciation in English pronunciation respelling (enPR)
	Enpr    *string `json:"enpr,omitempty"`
	Form    *string `json:"form,omitempty"`
	Hangeul *string `json:"hangeul,omitempty"`
	// list of homophones for the word
	Homophone *string `json:"homophone,omitempty"`
	// list of hyphenations
	Hyphenation *string `json:"hyphenation,omitempty"`
	// International Phonetic Alphabet pronunciation, /.../ or [...]
	Ipa *string `json:"ipa,omitempty"`
	// URL for an MP3 format sound file
	Mp3Url *string `json:"mp3_url,omitempty"`
	Note   *string `json:"note,omitempty"`
	// URL for an OGG Vorbis format sound file
	OggUrl *string `json:"ogg_url,omitempty"`
	Other  *string `json:"other,omitempty"`
	Rhymes *string `json:"rhymes,omitempty"`
	// other labels or context information attached to the pronunciation
	// entry (e.g., might indicate regional variant or dialect)
	Tags []string `json:"tags,omitempty"`
	// text associated with an audio file (often not very useful)
	Text   *string  `json:"text,omitempty"`
	Topics []string `json:"topics,omitempty"`
	// Chinese word pronunciation
	ZhPron *string `json:"zh-pron,omitempty"`
}

SoundData represents pronunciation, hyphenation, rhyming, and related information. Each entry may have a `tags` key containing tags that clarify what kind of form that entry is. Different types of information are stored in different fields: `ipa` is IPA pronunciation, `enpr` is enPR pronunciation, `audio` is name of sound file in Wikimedia commons.

type TemplateArgs 

type TemplateArgs map[json_types.StringOrInt]string

type TemplateData 

type TemplateData struct {
	// dictionary mapping argument names to their cleaned values;
	// positional arguments have keys that are numeric strings, starting with "1"
	Args TemplateArgs `json:"args"`
	// the (cleaned) text the template expands to
	Explansion string `json:"explansion"`
	// name of the template
	Name      string             `json:"name"`
	ExtraData *ExtraTemplateData `json:"extra_data,omitempty"`
}

TemplateData represents a wiki template and its expansion.

type TranslationData 

type TranslationData struct {
	// optional alternative form of the translation (e.g., in a different script)
	Alt *string `json:"alt,omitempty"`
	// Wiktionary's 2 or 3-letter language code for the language the
	// translation is for.
	LangCode *string `json:"lang_code"`
	// DEPRECATED in favour of `lang_code`
	Code *string `json:"code,omitempty"`
	// English text, generally clarifying the target sense of the translation.
	//
	// DEPRECATED in favour of `translation`
	English     *string `json:"english"`
	Translation *string `json:"translation"`
	// the language name that the translation is for
	Lang string `json:"lang"`
	// optional text describing or commenting on the translation
	Note *string `json:"note,omitempty"`
	// optional romanization of the translation (when in non-Latin characters)
	Roman *string `json:"roman,omitempty"`
	// optional sense indicating the meaning for which this is a translation
	// (this is a free-text string, and may not match any gloss exactly)
	Sense *string `json:"sense,omitempty"`
	// optional list of qualifiers for the translations, e.g., gender
	Tags []string `json:"tags,omitempty"`
	// optional taxonomic name of an organism mentioned in the translation
	Taxonomic *string  `json:"taxonomic,omitempty"`
	Topics    []string `json:"topics,omitempty"`
	// the translation in the specified language (may be missing when `note`
	// is present)
	Word *string `json:"word,omitempty"`
}

TranslationData represents a translation entry.

type WordData 

type WordData struct {
	WordDataDetails `json:",inline"`

	// name of the language this word belongs to (e.g., "English")
	Lang string `json:"lang" db:"INDEX"`
	// Wiktionary language code corresponding to `lang` key (e.g., "en")
	LangCode string `json:"lang_code" db:"INDEX"`
	// the word form
	Word string `json:"word" db:"INDEX"`
}

WordData is the top-level dictionary containing lexical information of a single word extracted from Wiktionary with wiktextract.

Etymological information is stored under the `etymology_text` and `etymology_templates` keys in the word's data. When multiple parts-of-speech are listed under the same etymology, the same data is copied to each part-of-speech entry under that etymology.

Linkages (`synonyms`, `antonyms`, `hypernyms`, `derived`, `holonyms`, `meronyms`, `related`, `coordinate_terms`) are stored in the word's data if not sense-disambiguated, and in the word sense if sense-disambiguated.

func (WordData) GetLang added in v0.7.0 

func (w WordData) GetLang() string

func (WordData) GetLangCode added in v0.7.0 

func (w WordData) GetLangCode() string

func (WordData) GetWord added in v0.7.0 

func (w WordData) GetWord() string

type WordDataDetails added in v0.2.2 

type WordDataDetails struct {
	Abbreviations []LinkageData `json:"abbreviations,omitempty"`
	// list of words that this word is an alternative form of
	AltOf []AltOf `json:"alt_of,omitempty"`
	// non-disambiguated antonym linkages for the word
	Antonyms []LinkageData `json:"antonyms,omitempty"`
	// list of non-disambiguated categories for the word
	Categories []string `json:"categories,omitempty"`
	// non-disambiguated coordinate term linkages for the word
	CoordinateTerms []LinkageData `json:"coordinate_terms,omitempty"`
	// non-disambiguated derived word linkages for the word
	Derived     []LinkageData    `json:"derived,omitempty"`
	Descendants []DescendantData `json:"descendants,omitempty"`

	EtymologyExamples []EtymologyExample `json:"etymology_examples,omitempty"`
	// for words with multiple numbered etymologies, this contains the number
	// of the etymology under which this entry appeared
	EtymologyNumber *string `json:"etymology_number,omitempty"`
	// templates and their arguments and expansions from the etymology section
	EtymologyTemplates []TemplateData `json:"etymology_templates,omitempty"`
	// etymology section as cleaned text
	EtymologyText *string  `json:"etymology_text,omitempty"`
	FormOf        []FormOf `json:"form_of,omitempty"`
	// list of inflected or alternative forms specified for the word (e.g.,
	// plural, comparative, superlative, roman script version). Each form has
	// a `form` key and a `tags` key identifying what type of form it is.
	// May also contain "ipa", "roman", and "source" fields.
	Forms         []FormData             `json:"forms,omitempty"`
	HeadTemplates []TemplateData         `json:"head_templates,omitempty"`
	Holonyms      []LinkageData          `json:"holonyms,omitempty"`
	Hyphenation   *DeprecatedHyphenation `json:"hyphenation,omitempty"` // Being deprecated.
	Hyphenations  []Hyphenation          `json:"hyphenations,omitempty"`
	// non-disambiguated hypernym linkages for the word
	Hypernyms []LinkageData `json:"hypernyms,omitempty"`
	// non-disambiguated hyponym linkages for the word
	Hyponyms []LinkageData `json:"hyponyms,omitempty"`
	// conjugation and declension templates found for the word
	InflectionTemplates []TemplateData `json:"inflection_templates,omitempty"`
	InfoTemplates       []TemplateData `json:"info_templates,omitempty"`
	Instances           []LinkageData  `json:"instances,omitempty"`
	LiteralMeaning      string         `json:"literal_meaning"`
	// non-disambiguated linkages indicating having a part (fairly rare)
	Meronyms      []LinkageData `json:"meronyms,omitempty"`
	OriginalTitle string        `json:"original_title"`
	// part-of-speech, such as "noun", "verb", "adj", "adv", "pron",
	// "determiner", "prep" (preposition), "postp" (postposition)
	Pos       string        `json:"pos"`
	Proverbs  []LinkageData `json:"proverbs,omitempty"`
	Redirects []string      `json:"redirects,omitempty"`
	// non-disambiguated related word linkages for the word
	Related []LinkageData `json:"related,omitempty"`
	// list of word senses for this word/part-of-speech
	Senses       []SenseData       `json:"senses,omitempty"`
	Sounds       []SoundData       `json:"sounds,omitempty"`
	Synonyms     []LinkageData     `json:"synonyms,omitempty"`
	Translations []TranslationData `json:"translations,omitempty"`
	Troponyms    []LinkageData     `json:"troponyms,omitempty"`
	// non-disambiguated Wikidata identifier
	Wikidata  []string      `json:"wikidata,omitempty"`
	Wikipedia []string      `json:"wikipedia,omitempty"`
	Anagrams  []LinkageData `json:"anagrams,omitempty"`
}

WordDataDetails contains the detailed fields for a word entry. See: https://github.com/tatuylonen/wiktextract#format-of-the-extracted-word-entries

Source Files

View all Source files

Jump to

Keyboard shortcuts

? : This menu
/ : Search site
f or F : Jump to
y or Y : Canonical URL
go.dev uses cookies from Google to deliver and enhance the quality of its services and to analyze traffic. Learn more.