Copy
Ask AI
"$schema": "http://json-schema.org/draft-07/schema",
"type": "object",
"description": "Document.",
"definitions": {
"borderType": {
"type": "string",
"description": "Type de bordure de cellule de tableau.",
"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": "Coordonnée gauche.",
},
"t": {
"type": "integer",
"description": "Coordonnée supérieure.",
},
"r": {
"type": "integer",
"description": "Coordonnée droite.",
},
"b": {
"type": "integer",
"description": "Coordonnée inférieure.",
}
}
},
"confidence": {
"type": "number",
"description": "Niveau de confiance.",
},
"listNumberingStyle": {
"type": "string",
"description": "Style de numérotation de liste.",
"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": "Description du niveau de liste",
"required": [
"levelIndex",
"numberingStyle",
"startNumber"
],
"properties": {
"levelIndex": {
"type": "integer",
"description": "Index du niveau.",
"minimum": 0
},
"numberingStyle": {
"$ref": "#/definitions/listNumberingStyle",
"description": "Style de numérotation de liste.",
},
"startNumber": {
"type": "integer",
"description": "Numéro de départ.",
}
}
},
"picture": {
"type": "object",
"description": "Bloc contenant une image.",
"properties": {
"id": {
"type": "string",
"description": "ID du bloc image.",
},
"position": {
"$ref": "#/definitions/rect"
},
"confidence": {
"$ref": "#/definitions/confidence"
}
}
},
"barcode": {
"type": "object",
"description": "Code-barres.",
"properties": {
"id": {
"type": "string",
"description": "ID du bloc code-barres.",
},
"position": {
"$ref": "#/definitions/rect"
},
"confidence": {
"$ref": "#/definitions/confidence"
},
"type": {
"type": "string",
"description": "Type de code-barres.",
"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": "Valeur du code-barres.",
},
"supplementType": {
"type": "string",
"description": "Type de supplément.",
"enum": [
"none",
"2digits",
"5digits"
]
},
"supplementValue": {
"type": "string",
"description": "Valeur du supplément.",
}
}
},
"lines": {
"type": "array",
"description": "Tableau de chaînes de texte dans le bloc de texte, ordonnées selon le sens de lecture.",
"items": [
{
"type": "object",
"description": "Ligne de texte.",
"properties": {
"position": {
"$ref": "#/definitions/rect"
},
"confidence": {
"$ref": "#/definitions/confidence"
},
"text": {
"type": "string",
"description": "Valeur de la ligne de texte.",
},
"charParams": {
"$ref": "#/definitions/charParams"
},
"words": {
"type": "array",
"description": "Tableau de mots dans une ligne de texte, ordonnés selon le sens de lecture.",
"items": [
{
"type": "object",
"description": "Mot.",
"properties": {
"position": {
"$ref": "#/definitions/rect"
},
"confidence": {
"$ref": "#/definitions/confidence"
},
"text": {
"type": "string",
"description": "Valeur du mot.",
},
"charParams": {
"$ref": "#/definitions/charParams"
},
"chars": {
"type": "array",
"description": "Tableau de caractères dans un mot, ordonnés selon le sens de lecture.",
"items": [
{
"type": "object",
"description": "Caractère du mot.",
"properties": {
"confidence": {
"$ref": "#/definitions/confidence"
},
"text": {
"type": "string",
"description": "Valeur du caractère du mot.",
},
"position": {
"$ref": "#/definitions/rect"
},
"charParams": {
"$ref": "#/definitions/charParams"
}
}
}
]
}
}
}
]
}
}
}
]
},
"charParams": {
"type": "object",
"description": "Paramètres de formatage de police du symbole.",
"properties": {
"bold": {
"type": "boolean",
"description": "État de la propriété gras - si différent de celui du conteneur",
"default": false
},
"italic": {
"type": "boolean",
"description": "État de la propriété italique - si différent de celui du conteneur",
"default": false
},
"underlined": {
"type": "boolean",
"description": "État de la propriété souligné - si différent de celui du conteneur",
"default": false
},
"strikeout": {
"type": "boolean",
"description": "État de la propriété barré - si différent de celui du conteneur",
"default": false
},
"smallCaps": {
"type": "boolean",
"description": "État de la propriété petites majuscules - si différent de celui du conteneur",
"default": false
},
"superscript": {
"type": "boolean",
"description": "État de la propriété exposant - si différent de celui du conteneur",
"default": false
},
"subscript": {
"type": "boolean",
"description": "État de la propriété indice - si différent de celui du conteneur",
"default": false
},
"scaling": {
"type": "integer",
"description": "État de la propriété mise à l'échelle (en millièmes de 1) - si différent de celui du conteneur",
"default": 1000,
"minimum": 100,
"maximum": 10000
},
"spacing": {
"type": "integer",
"description": "État de la propriété d'espacement en twips (1/20 pt, 1/1440 pouce) - si différent de celui du conteneur",
"default": 0,
"minimum": -1000,
"maximum": 1000
},
"fontSize": {
"type": "integer",
"description": "État de la propriété de taille de police en twips (1/20 pt, 1/1440 pouce) - si différent de celui du conteneur",
"default": 200,
"minimum": 50,
"maximum": 4000
},
"fontName": {
"type": "string",
"description": "État de la propriété de nom de police - si différent de celui du conteneur",
},
"color": {
"type": "string",
"description": "État de la propriété de couleur de police du symbole (valeur hexadécimale au format 6 chiffres RRVVBB) - si différent de celui du conteneur",
},
"backgroundColor": {
"type": "string",
"description": "État de la propriété de couleur d'arrière-plan du symbole (valeur hexadécimale au format 6 chiffres RRVVBB) - si différent de celui du conteneur",
},
"lang": {
"type": "string",
"description": "État de la propriété de langue du symbole (composé des parties langue et pays, voir ISO 639 et ISO 3166) - si différent de celui du conteneur",
}
}
}
},
"required": [
"version",
"producer"
],
"properties": {
"version": {
"type": "string",
"description": "Version du schéma du document.",
"default": "Vantage OCR.Skill JSON output v1.0",
},
"producer": {
"type": "string",
"description": "Auteur du fichier JSON.",
"default": "ABBYY Vantage OCR.Skill",
},
"languages": {
"type": "array",
"description": "Liste des langues du document.",
"items": [
{
"type": "string",
"description": "Langue du document.",
}
]
},
"layout": {
"type": "object",
"description": "Mise en page (structure physique).",
"required": [
"pages"
],
"properties": {
"corrected": {
"type": "boolean",
"description": "Coordonnées de l'image corrigée en sortie.",
"default": true
},
"pages": {
"type": "array",
"description": "Tableau des pages du document, ordonnées de la première à la dernière.",
"items": [
{
"type": "object",
"description": "Page du document.",
"properties": {
"width": {
"type": "integer",
"description": "Largeur de la page en pixels.",
},
"height": {
"type": "integer",
"description": "Hauteur de la page en points.",
},
"rotated": {
"type": "string",
"description": "Rotation de la page par rapport à l'image d'origine.",
"enum": [
"none",
"clockwise",
"counterclockwise",
"upside-down"
]
},
"texts": {
"type": "array",
"description": "Tableau de blocs contenant du texte.",
"items": [
{
"type": "object",
"description": "Texte.",
"properties": {
"id" : {
"type": "string",
"description": "ID du bloc de texte.",
},
"position": {
"$ref": "#/definitions/rect"
},
"confidence": {
"$ref": "#/definitions/confidence"
},
"lines": {
"#ref": "#/definitions/lines"
}
}
}
]
},
"tables": {
"type": "array",
"description": "Tableau de blocs contenant un tableau.",
"items": [
{
"type": "object",
"description": "Tableau.",
"properties": {
"id" : {
"type": "string",
"description": "ID du bloc de tableau.",
},
"position": {
"$ref": "#/definitions/rect"
},
"confidence": {
"$ref": "#/definitions/confidence"
},
"cells": {
"type": "array",
"description": "Cellules du tableau.",
"items": [
{
"type": "object",
"description": "Cellule du tableau.",
"properties": {
"id" : {
"type": "string",
"description": "ID de la cellule du tableau.",
},
"position": {
"$ref": "#/definitions/rect"
},
"confidence": {
"$ref": "#/definitions/confidence"
},
"colRowPosition": {
"type": "object",
"description": "Coordonnée de la cellule dans le système Colonne-Ligne {l:colonneGauche, t:ligneHaut, r:colonneDroite, b:ligneBas}",
"properties":{
"l": {
"type": "integer",
"description": "Index du séparateur gauche.",
},
"t": {
"type": "integer",
"description": "Index du séparateur supérieur.",
},
"r": {
"type": "integer",
"description": "Index du séparateur droit.",
},
"b": {
"type": "integer",
"description": "Index du séparateur inférieur.",
}
}
},
"borders": {
"type": "object",
"description": "Types de bordure de cellule de tableau {l:gauche, t:haut, r:droite, b:bas}",
"properties":{
"l": {
"$ref": "#/definitions/borderType",
"description": "Type de bordure gauche.",
},
"t": {
"$ref": "#/definitions/borderType",
"description": "Type de bordure supérieure.",
},
"r": {
"$ref": "#/definitions/borderType",
"description": "Type de bordure droite.",
},
"b": {
"$ref": "#/definitions/borderType",
"description": "Type de bordure inférieure.",
}
}
},
"contentType": {
"type": "string",
"description": "Type de contenu de la cellule du tableau : [text, picture, barcode].",
"enum": [
"text",
"picture",
"barcode"
]
},
"picture": {
"$ref": "#/definitions/picture"
},
"barcode": {
"$ref": "#/definitions/barcode"
},
"lines": {
"$ref": "#/definitions/lines"
}
}
}
]
}
}
}
]
},
"pictures": {
"type": "array",
"description": "Tableau de blocs contenant une image.",
"items": [
{
"$ref": "#/definitions/picture"
}
]
},
"barcodes": {
"type": "array",
"description": "Tableau de blocs contenant un code-barres.",
"items": [
{
"$ref": "#/definitions/barcode"
}
]
},
"separators": {
"type": "array",
"description": "Tableau de blocs contenant un séparateur.",
"items": [
{
"type": "object",
"description": "Séparateur.",
"properties": {
"position": {
"$ref": "#/definitions/rect"
},
"confidence": {
"$ref": "#/definitions/confidence"
},
"color": {
"type": "integer",
"description": "Couleur du séparateur.",
},
"thickness": {
"type": "integer",
"description": "Épaisseur du séparateur.",
},
"type": {
"type": "string",
"description": "Type de séparateur.",
"enum": [
"unknown",
"solid",
"dotted"
]
},
"endPoints": {
"type": "object",
"description": "Coordonnées des extrémités du séparateur {startX:startX, startY:startY, endX:endX, endY:endY}",
"properties":{
"startX": {
"type": "integer",
"description": "Coordonnée X du point de départ.",
},
"startY": {
"type": "integer",
"description": "Coordonnée Y du point de départ.",
},
"endX": {
"type": "integer",
"description": "Coordonnée X du point de fin.",
},
"endY": {
"type": "integer",
"description": "Coordonnée Y du point de fin.",
}
}
}
}
}
]
},
"checkmarks": {
"type": "array",
"description": "Tableau de blocs contenant une case à cocher.",
"items": [
{
"type": "object",
"description": "Case à cocher.",
"properties": {
"position": {
"$ref": "#/definitions/rect"
},
"confidence": {
"$ref": "#/definitions/confidence"
},
"value": {
"type": "string",
"description": "Valeur de la case à cocher.",
"enum": [
"checked",
"unchecked",
"corrected",
"unknown"
]
}
}
}
]
}
}
}
]
}
}
},
"content": {
"type": "object",
"description": "Contenu du document (structure logique).",
"properties": {
"paragraphs": {
"type": "array",
"description": "Tableau de paragraphes du document ordonnés selon le sens de lecture.",
"items": [
{
"type": "object",
"description": "Paragraphe du document.",
"properties": {
"id": {
"type": "string",
"description": "ID du paragraphe dans le document."
},
"role": {
"type": "string",
"description": "Rôle du paragraphe dans le document.",
"enum": [
"other",
"text",
"heading",
"headingNumber",
"tableOfContents",
"tableText",
"runningTitle",
"endNote",
"footNote",
"tableCaption",
"tableHeading",
"pictureCaption",
"artefact"
]
},
"formatting": {
"type": "object",
"description": "Mise en forme du paragraphe.",
"properties": {
"aligning": {
"type": "string",
"description": "Alignement du texte dans le paragraphe.",
"enum": [
"left",
"center",
"right",
"justified",
"justifiedForArabic"
]
},
"lineSpacing": {
"type": "integer",
"description": "Interligne du paragraphe.",
"minimum": 0,
"default": 0
}
}
},
"layoutReferences": {
"type": "array",
"description": "Tableau des sources des parties de paragraphe du document dans la structure de blocs de page, dans l'ordre du texte du paragraphe.",
"items": [
{
"type": "object",
"description": "ID du bloc/de la cellule de référence, index du paragraphe et plage de lignes dans le bloc/la cellule.",
"required": [
"blockId",
"blockType",
"parIndex",
"firstLine",
"lastLine"
],
"properties": {
"blockId": {
"type": "string",
"description": "ID du bloc de texte ou de la cellule de tableau conteneur."
},
"blockType": {
"type": "string",
"description": "Type de conteneur du paragraphe.",
"enum": [
"text",
"cell"
]
},
"sectionIndex": {
"type": "integer",
"description": "Index de la section logique sur la page (ou -1 s'il n'existe aucune section contenant le paragraphe, comme les en-têtes, pieds de page, etc.).",
"minimum": -1
},
"columnIndex": {
"type": "integer",
"description": "Index de la colonne dans la section logique (ou -1 s'il n'existe aucune colonne contenant le paragraphe, comme les encarts, notes de bas de page, etc.).",
"minimum": -1
},
"lineNumbering": {
"type": "boolean",
"description": "true si le paragraphe se trouve dans la zone de numérotation des lignes."
},
"parIndex": {
"type": "integer",
"description": "Index du paragraphe dans le bloc ou la cellule de tableau.",
"minimum": 0
},
"firstLine": {
"type": "integer",
"description": "Index de la première ligne du paragraphe dans le bloc ou la cellule de tableau.",
"minimum": 0
},
"lastLine": {
"type": "integer",
"description": "Index de la dernière ligne du paragraphe dans le bloc ou la cellule de tableau.",
"minimum": 0
}
}
}
]
},
"text": {
"type": "string",
"description": "Texte du paragraphe."
},
"listReference": {
"type": "object",
"description": "Référence à la liste contenant le paragraphe.",
"properties": {
"id": {
"type": "string",
"description": "ID de la liste."
},
"levelIndex": {
"type": "integer",
"description": "Index du niveau de l'élément de liste actuel.",
"minimum": 0,
"default": 0
},
"ordinalNumber": {
"type": "integer",
"description": "Numéro ordinal de l'élément de liste actuel.",
"minimum": -1,
"default": 0
}
}
},
}
}
]
},
"lists": {
"type": "array",
"description": "Tableau des listes trouvées dans le document.",
"items": [
{
"type": "object",
"description": "Description de la liste.",
"properties": {
"id": {
"type": "string",
"description": "ID de la liste dans le document."
},
"listLevels": {
"type": "array",
"description": "Tableau des descriptions de niveaux de liste.",
"items": [
{
"$ref": "#/definitions/listLevel"
}
]
}
}
}
]
}
}
}
}
}```
