fulltext

Documentation

Index

• func GetFulltext(bucket string, key string, format string, ftype string) (string, error)
• type TEI2
• type TEI2Body
• type TEI2Header
• type TEI2Paragraph
• type TEI2Text
• type TEI2Word
• type TEI2a
• type TEI2aBody
• type TEI2aHeader
• type TEI2aParagraph
• type TEI2aText
• type TEI2aWord
• type TXT1
• type TXT1ArticleInfo
• type TXT1OCRText
• type TXT2
• type TXT2Header
• type TXT2Paragraph
• type TXT2Text
• type TXT2Word
• type TXT3
• type TXT3Article
• type TXT3Block
• type TXT3P
• type TXT3PG
• type TXT3Text
• type TXT3WD
• type TXT4
• type Word
• type XML

Functions

func GetFulltext

func GetFulltext(bucket string, key string, format string, ftype string) (string, error)

GetFulltext ...

Types

type TEI2

type TEI2 struct {
	XMLName   xml.Name   `xml:"TEI.2"`
	TEIHeader TEI2Header `xml:"teiHeader"`
	Text      TEI2Text   `xml:"text"`
}

TEI2 ... nlh-eai1, nlh-eai2

type TEI2Body

type TEI2Body struct {
	XMLName    xml.Name        `xml:"body"`
	Paragraphs []TEI2Paragraph `xml:"p"`
}

TEI2Body ..

type TEI2Header

type TEI2Header struct {
	XMLName xml.Name `xml:"teiHeader"`
}

TEI2Header ..

type TEI2Paragraph

type TEI2Paragraph struct {
	XMLName xml.Name   `xml:"p"`
	ID      string     `xml:"id,attr"`
	Words   []TEI2Word `xml:"w"`
}

TEI2Paragraph ..

type TEI2Text

type TEI2Text struct {
	XMLName xml.Name `xml:"text"`
	Body    TEI2Body `xml:"body"`
}

TEI2Text ..

type TEI2Word

type TEI2Word struct {
	XMLName xml.Name `xml:"w"`
	Style   string   `xml:"style,attr"`
	Value   string   `xml:",chardata"`
}

TEI2Word ..

type TEI2a

type TEI2a struct {
	XMLName   xml.Name    `xml:"TEI.2"`
	TEIHeader TEI2aHeader `xml:"teiHeader"`
	Text      TEI2aText   `xml:"text"`
}

TEI2a ... gdz

type TEI2aBody

type TEI2aBody struct {
	XMLName    xml.Name         `xml:"body"`
	Paragraphs []TEI2aParagraph `xml:"p"`
}

TEI2aBody ..

type TEI2aHeader

type TEI2aHeader struct {
	XMLName xml.Name `xml:"teiHeader"`
}

TEI2aHeader ..

type TEI2aParagraph

type TEI2aParagraph struct {
	XMLName xml.Name    `xml:"p"`
	ID      string      `xml:"id,attr"`
	Words   []TEI2aWord `xml:"w"`
}

TEI2aParagraph ..

type TEI2aText

type TEI2aText struct {
	XMLName xml.Name  `xml:"text"`
	Body    TEI2aBody `xml:"body"`
}

TEI2aText ..

type TEI2aWord

type TEI2aWord struct {
	XMLName  xml.Name `xml:"w"`
	Function string   `xml:"function,attr"`
	Value    string   `xml:",chardata"`
}

TEI2aWord ..

type TXT1

type TXT1 struct {
	XMLName  xml.Name          `xml:"articles"`
	Articles []TXT1ArticleInfo `xml:"artInfo"`
}

TXT1 ... nlh_tda1, nlh-tda2

type TXT1ArticleInfo

type TXT1ArticleInfo struct {
	XMLName     xml.Name    `xml:"artInfo"`
	ID          string      `xml:"id,attr"`
	ProductLink string      `xml:"ProductLink"`
	OCRText     TXT1OCRText `xml:"ocrText"`
}

TXT1ArticleInfo ...

type TXT1OCRText

type TXT1OCRText struct {
	XMLName xml.Name `xml:"ocrText"`
	Value   string   `xml:",chardata"`
}

TXT1OCRText ...

type TXT2

type TXT2 struct {
	XMLName   xml.Name   `xml:"page"`
	TXTHeader TXT2Header `xml:"pageInfo"`
	Text      TXT2Text   `xml:"pageContent"`
}

TXT2 ... nlh-ecc

type TXT2Header

type TXT2Header struct {
	XMLName   xml.Name `xml:"pageInfo"`
	PageID    string   `xml:"pageID"`
	RecordID  string   `xml:"recordID"`
	OCR       string   `xml:"ocr"`
	ImageLink string   `xml:"imageLink"`
}

TXT2Header ...

type TXT2Paragraph

type TXT2Paragraph struct {
	XMLName xml.Name   `xml:"p"`
	ID      string     `xml:"id,attr"`
	Words   []TXT2Word `xml:"w"`
}

TXT2Paragraph ...

type TXT2Text

type TXT2Text struct {
	XMLName    xml.Name        `xml:"pageContent"`
	Paragraphs []TXT2Paragraph `xml:"p"`
}

TXT2Text ...

type TXT2Word

type TXT2Word struct {
	XMLName xml.Name `xml:"wd"`
	Pos     string   `xml:"pos,attr"`
	Value   string   `xml:",chardata"`
}

TXT2Word ...

type TXT3

type TXT3 struct {
	XMLName  xml.Name      `xml:"page"`
	PageID   string        `xml:"pageid"`
	Articles []TXT3Article `xml:"article"`
}

TXT3 ... nlh-tls

type TXT3Article

type TXT3Article struct {
	XMLName xml.Name `xml:"article"`
	Type    string   `xml:"type,attr"`
	ID      string   `xml:"id"`
	Text    TXT3Text `xml:"text"`
}

TXT3Article ...

type TXT3Block

type TXT3Block struct {
	Pg TXT3PG `xml:"pg"`
	P  TXT3P  `xml:"p"`
}

TXT3Block ...

type TXT3P

type TXT3P struct {
	XMLName xml.Name `xml:"p"`
	Type    string   `xml:"type,attr"`
	WDs     []TXT3WD `xml:"wd"`
}

TXT3P ...

type TXT3PG

type TXT3PG struct {
	XMLName xml.Name `xml:"pg"`
	Pgref   string   `xml:"pgref,attr"`
	Clipref string   `xml:"clipref,attr"`
	Pos     string   `xml:"pos,attr"`
}

TXT3PG ...

type TXT3Text

type TXT3Text struct {
	XMLName    xml.Name    `xml:"text"`
	TitleBlock TXT3Block   `xml:"text.title"`
	TextBlocks []TXT3Block `xml:"text.cr"`
}

TXT3Text ...

type TXT3WD

type TXT3WD struct {
	XMLName xml.Name `xml:"wd"`
	Pos     string   `xml:"pos,attr"`
	Value   string   `xml:",chardata"`
}

TXT3WD ...

type TXT4

type TXT4 struct {
	XMLName xml.Name   `xml:"articles"`
	Texts   []TXT3Text `xml:"text"`
}

TXT4 ... nlh-ahn

type Word

type Word struct {
	Content string `xml:",chardata"`
}

Word ...

type XML

type XML struct {
	XMLName xml.Name `xml:"TEI.2"`
	Word    []string `xml:"text>body>p"` // `xml:"mdWrap>xmlData>mods>name"`
}

XML fulltext