Copy
Ask AI
"$schema": "http://json-schema.org/draft-07/schema",
"type": "object",
"description": "Document.",
"definitions": {
"borderType": {
"type": "string",
"description": "Rahmentyp der Tabellenzelle.",
"enum": [
"unknown",
"invisible",
"visible"
]
},
"rect": {
"type": "object",
"description": "Rectangle {r:left, t:top, r:right, b:bottom}",
"required": [
"l",
"t",
"r",
"b"
],
"properties": {
"l": {
"type": "integer",
"description": "Linke Koordinate.",
},
"t": {
"type": "integer",
"description": "Obere Koordinate.",
},
"r": {
"type": "integer",
"description": "Rechte Koordinate.",
},
"b": {
"type": "integer",
"description": "Untere Koordinate.",
}
}
},
"confidence": {
"type": "number",
"description": "Konfidenz.",
},
"listNumberingStyle": {
"type": "string",
"description": "Listennummerierungsstil.",
"enum": [
"None",
"Decimal",
"UpperRoman",
"LowerRoman",
"UpperLetter",
"LowerLetter",
"Ordinal",
"CardinalText",
"OrdinalText",
"Hex",
"Chicago",
"IdeographDigital",
"JapaneseCounting",
"Aiueo",
"Iroha",
"DecimalFullWidth",
"DecimalHalfWidth",
"JapaneseLegal",
"JapaneseDigitalTenThousand",
"DecimalEnclosedCircle",
"DecimalFullWidth2",
"AiueoFullWidth",
"IrohaFullWidth",
"DecimalZero",
"Bullet",
"Ganada",
"Chosung",
"DecimalEnclosedFullstop",
"DecimalEnclosedParen",
"DecimalEnclosedCircleChinese",
"IdeographEnclosedCircle",
"IdeographTraditional",
"IdeographZodiac",
"IdeographZodiacTraditional",
"TaiwaneseCounting",
"IdeographLegalTraditional",
"TaiwaneseCountingThousand",
"TaiwaneseDigital",
"ChineseCounting",
"ChineseLegalSimplified",
"ChineseCountingThousand",
"ApplicationDefined",
"KoreanDigital",
"KoreanCounting",
"KoreanLegal",
"KoreanDigital2",
"Hebrew1",
"ArabicAlpha",
"Hebrew2",
"ArabicAbjad",
"HindiVowels",
"HindiConsonants",
"HindiNumbers",
"HindiCounting",
"ThaiLetters",
"ThaiNumbers",
"ThaiCounting",
"VietnameseCounting",
"NumberInDash",
"RussianLower",
"RussianUpper",
"Burmese",
"Unnumbered"
]
},
"listLevel": {
"type": "object",
"description": "Beschreibung der Listenebene",
"required": [
"levelIndex",
"numberingStyle",
"startNumber"
],
"properties": {
"levelIndex": {
"type": "integer",
"description": "Ebenenindex.",
"minimum": 0
},
"numberingStyle": {
"$ref": "#/definitions/listNumberingStyle",
"description": "Listennummerierungsstil.",
},
"startNumber": {
"type": "integer",
"description": "Startnummer.",
}
}
},
"picture": {
"type": "object",
"description": "Block mit Bild.",
"properties": {
"id": {
"type": "string",
"description": "Bildblock-ID.",
},
"position": {
"$ref": "#/definitions/rect"
},
"confidence": {
"$ref": "#/definitions/confidence"
}
}
},
"barcode": {
"type": "object",
"description": "Barcode.",
"properties": {
"id": {
"type": "string",
"description": "Barcode-Block-ID.",
},
"position": {
"$ref": "#/definitions/rect"
},
"confidence": {
"$ref": "#/definitions/confidence"
},
"type": {
"type": "string",
"description": "Barcode-Typ.",
"enum": [
"Code39",
"Interleaved25",
"EAN13",
"Code128",
"EAN8",
"PDF417",
"Codabar",
"UPCE",
"Industrial25",
"IATA25",
"Matrix25",
"Code93",
"PostNet",
"UCC128",
"Patch",
"Aztec",
"DataMatrix",
"QRCode",
"UPCA",
"MaxiCode",
"Code32",
"FullAscii",
"IntelligentMail",
"RoyalMail4State",
"KIX",
"Australia4State",
"JapanPost",
"NotFound"
]
},
"value": {
"type": "string",
"description": "Barcode-Wert.",
},
"supplementType": {
"type": "string",
"description": "Ergänzungstyp.",
"enum": [
"none",
"2digits",
"5digits"
]
},
"supplementValue": {
"type": "string",
"description": "Ergänzungswert.",
}
}
},
"lines": {
"type": "array",
"description": "Ein Array von Textzeichenfolgen im Textblock, geordnet nach Leserichtung.",
"items": [
{
"type": "object",
"description": "Eine Textzeile.",
"properties": {
"position": {
"$ref": "#/definitions/rect"
},
"confidence": {
"$ref": "#/definitions/confidence"
},
"text": {
"type": "string",
"description": "Wert einer Textzeile.",
},
"charParams": {
"$ref": "#/definitions/charParams"
},
"words": {
"type": "array",
"description": "Ein Array von Wörtern in einer Textzeile, geordnet nach Leserichtung.",
"items": [
{
"type": "object",
"description": "Wort.",
"properties": {
"position": {
"$ref": "#/definitions/rect"
},
"confidence": {
"$ref": "#/definitions/confidence"
},
"text": {
"type": "string",
"description": "Wortwert.",
},
"charParams": {
"$ref": "#/definitions/charParams"
},
"chars": {
"type": "array",
"description": "Ein Array von Zeichen in einem Wort, geordnet nach Leserichtung.",
"items": [
{
"type": "object",
"description": "Wortzeichen.",
"properties": {
"confidence": {
"$ref": "#/definitions/confidence"
},
"text": {
"type": "string",
"description": "Wert des Wortzeichens.",
},
"position": {
"$ref": "#/definitions/rect"
},
"charParams": {
"$ref": "#/definitions/charParams"
}
}
}
]
}
}
}
]
}
}
}
]
},
"charParams": {
"type": "object",
"description": "Schriftformatierungsparameter für Symbole.",
"properties": {
"bold": {
"type": "boolean",
"description": "Status der Fett-Eigenschaft – wenn er sich von dem des Containers unterscheidet",
"default": false
},
"italic": {
"type": "boolean",
"description": "Status der Kursiv-Eigenschaft – wenn er sich von dem des Containers unterscheidet",
"default": false
},
"underlined": {
"type": "boolean",
"description": "Status der Unterstrichen-Eigenschaft – wenn er sich von dem des Containers unterscheidet",
"default": false
},
"strikeout": {
"type": "boolean",
"description": "Status der Durchgestrichen-Eigenschaft – wenn er sich von dem des Containers unterscheidet",
"default": false
},
"smallCaps": {
"type": "boolean",
"description": "Status der Kapitälchen-Eigenschaft – wenn er sich von dem des Containers unterscheidet",
"default": false
},
"superscript": {
"type": "boolean",
"description": "Status der Hochgestellt-Eigenschaft – wenn er sich von dem des Containers unterscheidet",
"default": false
},
"subscript": {
"type": "boolean",
"description": "Status der Tiefgestellt-Eigenschaft – wenn er sich von dem des Containers unterscheidet",
"default": false
},
"scaling": {
"type": "integer",
"description": "Status der Skalierungs-Eigenschaft (in Tausendsteln von 1) – wenn er sich von dem des Containers unterscheidet",
"default": 1000,
"minimum": 100,
"maximum": 10000
},
"spacing": {
"type": "integer",
"description": "Spacing-Eigenschaftsstatus in Twips (1/20 pt, 1/1440 Zoll) – falls vom Container abweichend",
"default": 0,
"minimum": -1000,
"maximum": 1000
},
"fontSize": {
"type": "integer",
"description": "Schriftgröße-Eigenschaftsstatus in Twips (1/20 pt, 1/1440 Zoll) – falls vom Container abweichend",
"default": 200,
"minimum": 50,
"maximum": 4000
},
"fontName": {
"type": "string",
"description": "Schriftname-Eigenschaftsstatus – falls vom Container abweichend",
},
"color": {
"type": "string",
"description": "Zeichenschriftfarbe-Eigenschaftsstatus (Hexadezimalwert im 6-stelligen Format RRGGBB) – falls vom Container abweichend",
},
"backgroundColor": {
"type": "string",
"description": "Zeichenhintergrundfarbe-Eigenschaftsstatus (Hexadezimalwert im 6-stelligen Format RRGGBB) – falls vom Container abweichend",
},
"lang": {
"type": "string",
"description": "Zeichensprache-Eigenschaftsstatus (besteht aus Sprach- und Länderteil, siehe ISO 639 und ISO 3166) – falls vom Container abweichend",
}
}
}
},
"required": [
"version",
"producer"
],
"properties": {
"version": {
"type": "string",
"description": "Document-Schemaversion.",
"default": "Vantage OCR.Skill JSON output v1.0"
},
"producer": {
"type": "string",
"description": "Autor der JSON-Datei.",
"default": "ABBYY Vantage OCR.Skill"
},
"languages": {
"type": "array",
"description": "Liste der Dokumentsprachen.",
"items": [
{
"type": "string",
"description": "Dokumentsprache.",
}
]
},
"layout": {
"type": "object",
"description": "Layout (physische Struktur).",
"required": [
"pages"
],
"properties": {
"corrected": {
"type": "boolean",
"description": "Koordinaten für das korrigierte Bild in der Ausgabe.",
"default": true
},
"pages": {
"type": "array",
"description": "Array von Dokumentseiten, von der ersten bis zur letzten geordnet.",
"items": [
{
"type": "object",
"description": "Dokumentseite.",
"properties": {
"width": {
"type": "integer",
"description": "Breite der Seite in Pixeln.",
},
"height": {
"type": "integer",
"description": "Höhe der Seite in Punkten.",
},
"rotated": {
"type": "string",
"description": "Drehung der Seite relativ zum Originalbild.",
"enum": [
"none",
"clockwise",
"counterclockwise",
"upside-down"
]
},
"texts": {
"type": "array",
"description": "Array von Blöcken mit Text.",
"items": [
{
"type": "object",
"description": "Text.",
"properties": {
"id" : {
"type": "string",
"description": "Textblock-ID.",
},
"position": {
"$ref": "#/definitions/rect"
},
"confidence": {
"$ref": "#/definitions/confidence"
},
"lines": {
"#ref": "#/definitions/lines"
}
}
}
]
},
"tables": {
"type": "array",
"description": "Array von Blöcken mit Tabelle.",
"items": [
{
"type": "object",
"description": "Tabelle.",
"properties": {
"id" : {
"type": "string",
"description": "Tabellenblock-ID.",
},
"position": {
"$ref": "#/definitions/rect"
},
"confidence": {
"$ref": "#/definitions/confidence"
},
"cells": {
"type": "array",
"description": "Tabellenzellen.",
"items": [
{
"type": "object",
"description": "Tabellenzelle.",
"properties": {
"id" : {
"type": "string",
"description": "Tabellenzellen-ID.",
},
"position": {
"$ref": "#/definitions/rect"
},
"confidence": {
"$ref": "#/definitions/confidence"
},
"colRowPosition": {
"type": "object",
"description": "Zellenkoordinate im Spalten-Zeilen-System {l:linkeSpalte, t:obereZeile, r:rechteSpalte, b:untereZeile}",
"properties":{
"l": {
"type": "integer",
"description": "Index des linken Trennzeichens.",
},
"t": {
"type": "integer",
"description": "Index des oberen Trennzeichens.",
},
"r": {
"type": "integer",
"description": "Index des rechten Trennzeichens.",
},
"b": {
"type": "integer",
"description": "Index des unteren Trennzeichens.",
}
}
},
"borders": {
"type": "object",
"description": "Tabellenzellenrahmentypen {l:links, t:oben, r:rechts, b:unten}",
"properties":{
"l": {
"$ref": "#/definitions/borderType",
"description": "Linker Rahmentyp.",
},
"t": {
"$ref": "#/definitions/borderType",
"description": "Oberer Rahmentyp.",
},
"r": {
"$ref": "#/definitions/borderType",
"description": "Rechter Rahmentyp.",
},
"b": {
"$ref": "#/definitions/borderType",
"description": "Unterer Rahmentyp.",
}
}
},
"contentType": {
"type": "string",
"description": "Tabellenzelleninhaltstyp: [text, picture, barcode].",
"enum": [
"text",
"picture",
"barcode"
]
},
"picture": {
"$ref": "#/definitions/picture"
},
"barcode": {
"$ref": "#/definitions/barcode"
},
"lines": {
"$ref": "#/definitions/lines"
}
}
}
]
}
}
}
]
},
"pictures": {
"type": "array",
"description": "Array von Blöcken mit Bild.",
"items": [
{
"$ref": "#/definitions/picture"
}
]
},
"barcodes": {
"type": "array",
"description": "Array von Blöcken mit Barcode.",
"items": [
{
"$ref": "#/definitions/barcode"
}
]
},
"separators": {
"type": "array",
"description": "Array von Blöcken mit Trennzeichen.",
"items": [
{
"type": "object",
"description": "Trennzeichen.",
"properties": {
"position": {
"$ref": "#/definitions/rect"
},
"confidence": {
"$ref": "#/definitions/confidence"
},
"color": {
"type": "integer",
"description": "Trennzeichenfarbe.",
},
"thickness": {
"type": "integer",
"description": "Trennzeichenstärke.",
},
"type": {
"type": "string",
"description": "Trennzeichentyp.",
"enum": [
"unknown",
"solid",
"dotted"
]
},
"endPoints": {
"type": "object",
"description": "Koordinaten der Trennzeichenenden {startX:startX, startY:startY, endX:endX, endY:endY}",
"properties":{
"startX": {
"type": "integer",
"description": "X-Koordinate des Startpunkts.",
},
"startY": {
"type": "integer",
"description": "Y-Koordinate des Startpunkts.",
},
"endX": {
"type": "integer",
"description": "X-Koordinate des Endpunkts.",
},
"endY": {
"type": "integer",
"description": "Y-Koordinate des Endpunkts.",
}
}
}
}
}
]
},
"checkmarks": {
"type": "array",
"description": "Array von Blöcken mit Kontrollkästchen.",
"items": [
{
"type": "object",
"description": "Kontrollkästchen.",
"properties": {
"position": {
"$ref": "#/definitions/rect"
},
"confidence": {
"$ref": "#/definitions/confidence"
},
"value": {
"type": "string",
"description": "Kontrollkästchenwert.",
"enum": [
"checked",
"unchecked",
"corrected",
"unknown"
]
}
}
}
]
}
}
}
]
}
}
},
"content": {
"type": "object",
"description": "Dokumentinhalt (logische Struktur).",
"properties": {
"paragraphs": {
"type": "array",
"description": "Ein Array von Dokumentabsätzen, sortiert nach Leserichtung.",
"items": [
{
"type": "object",
"description": "Dokumentabsatz.",
"properties": {
"id": {
"type": "string",
"description": "Absatz-ID im Dokument."
},
"role": {
"type": "string",
"description": "Rolle des Absatzes im Dokument.",
"enum": [
"other",
"text",
"heading",
"headingNumber",
"tableOfContents",
"tableText",
"runningTitle",
"endNote",
"footNote",
"tableCaption",
"tableHeading",
"pictureCaption",
"artefact"
]
},
"formatting": {
"type": "object",
"description": "Absatzformatierung.",
"properties": {
"aligning": {
"type": "string",
"description": "Textausrichtung im Absatz.",
"enum": [
"left",
"center",
"right",
"justified",
"justifiedForArabic"
]
},
"lineSpacing": {
"type": "integer",
"description": "Zeilenabstand des Absatzes.",
"minimum": 0,
"default": 0
}
}
},
"layoutReferences": {
"type": "array",
"description": "Ein Array der Quellen von Dokumentabsatzteilen in der Seitenblockstruktur, in der Reihenfolge des Textes im Absatz.",
"items": [
{
"type": "object",
"description": "Referenz-Block-/Zellen-ID, Absatzindex und Zeilenbereich im Block/in der Zelle.",
"required": [
"blockId",
"blockType",
"parIndex",
"firstLine",
"lastLine"
],
"properties": {
"blockId": {
"type": "string",
"description": "ID des enthaltenden Textblocks oder der Tabellenzelle."
},
"blockType": {
"type": "string",
"description": "Typ des Absatzcontainers.",
"enum": [
"text",
"cell"
]
},
"sectionIndex": {
"type": "integer",
"description": "Index des logischen Abschnitts auf der Seite (oder -1, wenn kein Abschnitt den Absatz enthält – z. B. Kopfzeilen, Fußzeilen usw.).",
"minimum": -1
},
"columnIndex": {
"type": "integer",
"description": "Index der Spalte im logischen Abschnitt (oder -1, wenn keine Spalte den Absatz enthält – z. B. Einschübe, Fußnoten usw.).",
"minimum": -1
},
"lineNumbering": {
"type": "boolean",
"description": "true, wenn der Absatz im Zeilennummerierungsbereich enthalten ist."
},
"parIndex": {
"type": "integer",
"description": "Absatzindex im Block oder in der Tabellenzelle.",
"minimum": 0
},
"firstLine": {
"type": "integer",
"description": "Index der ersten Zeile des Absatzes im Block oder in der Tabellenzelle.",
"minimum": 0
},
"lastLine": {
"type": "integer",
"description": "Index der letzten Zeile des Absatzes im Block oder in der Tabellenzelle.",
"minimum": 0
}
}
}
]
},
"text": {
"type": "string",
"description": "Absatztext."
},
"listReference": {
"type": "object",
"description": "Verweis auf die Liste, die den Absatz enthält.",
"properties": {
"id": {
"type": "string",
"description": "Listen-ID."
},
"levelIndex": {
"type": "integer",
"description": "Index der aktuellen Listenelementebene.",
"minimum": 0,
"default": 0
},
"ordinalNumber": {
"type": "integer",
"description": "Ordnungszahl des aktuellen Listenelements.",
"minimum": -1,
"default": 0
}
}
},
}
}
]
},
"lists": {
"type": "array",
"description": "Ein Array von Listen, die im Dokument gefunden wurden.",
"items": [
{
"type": "object",
"description": "Listenbeschreibung.",
"properties": {
"id": {
"type": "string",
"description": "Listen-ID im Dokument."
},
"listLevels": {
"type": "array",
"description": "Ein Array von Listenebenenbeschreibungen.",
"items": [
{
"$ref": "#/definitions/listLevel"
}
]
}
}
}
]
}
}
}
}
}```
