Documentation ¶
Index ¶
- func GetFulltext(bucket string, key string, format string, ftype string, context string) (string, error)
- type PAGEXML1
- type PAGEXML1Baseline
- type PAGEXML1Border
- type PAGEXML1Coords
- type PAGEXML1Metadata
- type PAGEXML1OrderedGroup
- type PAGEXML1Page
- type PAGEXML1Paragraph
- type PAGEXML1ReadingOrder
- type PAGEXML1RegionRefIndexed
- type PAGEXML1Relation
- type PAGEXML1Relations
- type PAGEXML1SourceRegionRef
- type PAGEXML1TargetRegionRef
- type PAGEXML1TextEquiv
- type PAGEXML1TextLine
- type PAGEXML1TextRegion
- type PAGEXML1Unicode
- type PAGEXML1Word
- 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 TXT3a
- type TXT3aBlock
- type TXT3aP
- type TXT3aPG
- type TXT3aText
- type TXT3aWD
- type TXT3b
- type TXT4
- type TXT5
- type TXT5WD
- type Word
- type XML
Constants ¶
This section is empty.
Variables ¶
This section is empty.
Functions ¶
Types ¶
type PAGEXML1 ¶
type PAGEXML1 struct { XMLName xml.Name `xml:"PcGts"` Metadata PAGEXML1Metadata `xml:"Metadata"` Page PAGEXML1Page `xml:"Page"` // array? }
PAGEXML1 ... gdz
type PAGEXML1Baseline ¶
type PAGEXML1Baseline struct { XMLName xml.Name `xml:"Baseline"` Points string `xml:"points,attr"` }
PAGEXML1Baseline ..
type PAGEXML1Border ¶
type PAGEXML1Border struct { XMLName xml.Name `xml:"Border"` Coords PAGEXML1Coords `xml:"Coords"` // array? }
PAGEXML1Border ..
type PAGEXML1Coords ¶
PAGEXML1Coords ..
type PAGEXML1Metadata ¶
type PAGEXML1Metadata struct { XMLName xml.Name `xml:"Metadata"` Creator string `xml:"Creator"` Created string `xml:"Created"` LastChange string `xml:"LastChange"` }
PAGEXML1Metadata ..
type PAGEXML1OrderedGroup ¶
type PAGEXML1OrderedGroup struct { XMLName xml.Name `xml:"OrderedGroup"` ID string `xml:"id,attr"` Caption string `xml:"caption,attr"` RegionRefIndexed []PAGEXML1RegionRefIndexed `xml:"RegionRefIndexed"` // array? }
PAGEXML1OrderedGroup ..
type PAGEXML1Page ¶
type PAGEXML1Page struct { XMLName xml.Name `xml:"Page"` ImageFilename string `xml:"imageFilename,attr"` ImageWidth string `xml:"imageWidth,attr"` ImageHeight string `xml:"imageHeight,attr"` ImageXResolution string `xml:"imageXResolution,attr"` ImageYResolution string `xml:"imageYResolution,attr"` Type string `xml:"type,attr"` Border PAGEXML1Border `xml:"Border"` ReadingOrder PAGEXML1ReadingOrder `xml:"ReadingOrder"` Relations PAGEXML1Relations `xml:"Relations"` TextRegion PAGEXML1TextRegion `xml:"TextRegion"` }
PAGEXML1Page ..
type PAGEXML1Paragraph ¶
type PAGEXML1Paragraph struct { XMLName xml.Name `xml:"p"` ID string `xml:"id,attr"` Words []PAGEXML1Word `xml:"w"` }
PAGEXML1Paragraph ..
type PAGEXML1ReadingOrder ¶
type PAGEXML1ReadingOrder struct { XMLName xml.Name `xml:"ReadingOrder"` OrderedGroup PAGEXML1OrderedGroup `xml:"OrderedGroup"` // array? }
PAGEXML1ReadingOrder ..
type PAGEXML1RegionRefIndexed ¶
type PAGEXML1RegionRefIndexed struct { XMLName xml.Name `xml:"RegionRefIndexed"` Index string `xml:"index,attr"` RegionRef string `xml:"regionRef,attr"` }
PAGEXML1RegionRefIndexed ..
type PAGEXML1Relation ¶
type PAGEXML1Relation struct { XMLName xml.Name `xml:"Relation"` ID string `xml:"id,attr"` Type string `xml:"type,attr"` SourceRegionRef []PAGEXML1SourceRegionRef `xml:"SourceRegionRef"` TargetRegionRef []PAGEXML1TargetRegionRef `xml:"TargetRegionRef"` }
PAGEXML1Relation ..
type PAGEXML1Relations ¶
type PAGEXML1Relations struct { XMLName xml.Name `xml:"Relations"` Relation PAGEXML1Relation `xml:"Relation"` // array? }
PAGEXML1Relations ..
type PAGEXML1SourceRegionRef ¶
type PAGEXML1SourceRegionRef struct { XMLName xml.Name `xml:"SourceRegionRef"` RegionRef string `xml:"regionRef,attr"` }
PAGEXML1SourceRegionRef ..
type PAGEXML1TargetRegionRef ¶
type PAGEXML1TargetRegionRef struct { XMLName xml.Name `xml:"TargetRegionRef"` RegionRef string `xml:"regionRef,attr"` }
PAGEXML1TargetRegionRef ..
type PAGEXML1TextEquiv ¶
type PAGEXML1TextEquiv struct { XMLName xml.Name `xml:"TextEquiv"` Unicode PAGEXML1Unicode `xml:"Unicode"` // array? }
PAGEXML1TextEquiv ..
type PAGEXML1TextLine ¶
type PAGEXML1TextLine struct { XMLName xml.Name `xml:"TextLine"` ID string `xml:"id,attr"` PrimaryLanguage string `xml:"primaryLanguage,attr"` Coords PAGEXML1Coords `xml:"Coords"` // array? TextEquiv PAGEXML1TextEquiv `xml:"TextEquiv"` // array? Baseline PAGEXML1Baseline `xml:"Baseline"` // array? Word PAGEXML1Word `xml:"Word"` // array? }
PAGEXML1TextLine ..
index this Coords + TextEquiv to index lines
type PAGEXML1TextRegion ¶
type PAGEXML1TextRegion struct { XMLName xml.Name `xml:"TextRegion"` ID string `xml:"id,attr"` Type string `xml:"type,attr"` PrimaryLanguage string `xml:"primaryLanguage,attr"` SecondaryLanguage string `xml:"secondaryLanguage,attr"` Coords PAGEXML1Coords `xml:"Coords"` // array? TextLine []PAGEXML1TextLine `xml:"TextLine"` // array? TextEquiv []PAGEXML1TextEquiv `xml:"TextEquiv"` // array? }
PAGEXML1TextRegion ..
type PAGEXML1Unicode ¶
type PAGEXML1Unicode struct { XMLName xml.Name `xml:"Unicode"` Value string `xml:",chardata"` // array? }
PAGEXML1Unicode ..
type PAGEXML1Word ¶
type PAGEXML1Word struct { XMLName xml.Name `xml:"Word"` ID string `xml:"id,attr"` Language string `xml:"language,attr"` Coords PAGEXML1Coords `xml:"Coords"` // array? TextEquiv PAGEXML1TextEquiv `xml:"TextEquiv"` // array? }
PAGEXML1Word ..
index this Coords + TextQuiv to index words
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 TEI2Paragraph ¶
type TEI2Paragraph struct { XMLName xml.Name `xml:"p"` ID string `xml:"id,attr"` Words []TEI2Word `xml:"w"` }
TEI2Paragraph ..
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 TEI2aParagraph ¶
type TEI2aParagraph struct { XMLName xml.Name `xml:"p"` ID string `xml:"id,attr"` Words []TEI2aWord `xml:"w"` }
TEI2aParagraph ..
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 ¶
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"` SourcePage string `xml:"sourcePage"` 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 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 TXT3a ¶
type TXT3a struct { XMLName xml.Name `xml:"page"` PageID string `xml:"page-id"` IssueID string `xml:"issue-id"` Texts []TXT3aText `xml:"text"` }
TXT3a ... nlh-ncn, nlh-bcn, nlh-bln
type TXT3aBlock ¶
TXT3aBlock ...
type TXT3aP ¶
type TXT3aP struct { XMLName xml.Name `xml:"p"` Type string `xml:"type,attr"` WDs []TXT3WD `xml:"wd"` }
TXT3aP ...
type TXT3aPG ¶
type TXT3aPG struct { XMLName xml.Name `xml:"pg"` Pgref string `xml:"pgref,attr"` Clipref string `xml:"clipref,attr"` Pos string `xml:"pos,attr"` }
TXT3aPG ...
type TXT3aText ¶
type TXT3aText struct { XMLName xml.Name `xml:"text"` TitleBlock TXT3aBlock `xml:"text.title"` TextBlocks []TXT3aBlock `xml:"text.cr"` }
TXT3aText ...
type TXT3aWD ¶
type TXT3aWD struct { XMLName xml.Name `xml:"wd"` Pos string `xml:"pos,attr"` Value string `xml:",chardata"` }
TXT3aWD ...
type TXT3b ¶
type TXT3b struct { XMLName xml.Name `xml:"page"` PageID string `xml:"page-id"` IssueID string `xml:"issue-id"` TextBlocks []TXT3aBlock `xml:"text.cr"` }
TXT3b ... nlh-bln
type TXT5 ¶
type TXT5 struct { XMLName xml.Name `xml:"IMAGE"` Name string `xml:"NAME,attr"` WDs []TXT5WD `xml:"WD"` }
TXT5 ... nlh-nid