JSON schema
The final JSON schema contains various documents attributes containing all extracted information from a document.
| Field | Description |
|---|---|
| Actual | Predicted document class. |
| AIOutput | AI Integration output based on Natural Language Understanding. |
| BarcodeList | Barcode List. |
| BlockBGColor | Background Color. |
| BlockFGColor | Foreground Color. |
| BlockHeight | Height of Block. |
| BlockID | Block ID. |
| BlockList | Block List. |
| BlockStartX | X-coordinate of the block on the page. |
| BlockStartY | Y-coordinate of the block on the page. |
| BlockType | Indicate the type of block. For example, KVTable.KVPair. |
| BlockWidth | Width of the block on the page. |
| CellHeaderAttributes | Cell Header Attributes. |
| CellHeight | Height of cell. |
| CellID | Cell ID. |
| CellList | Cell List. |
| CellStartX | X-coordinate of the cell on the page. |
| CellStartY | Y-coordinate of the cell on the page. |
| CellWidth | Width of the cell on the page. |
| CharID | Character ID. |
| CharHeight | Height of a Character. |
| CharList | A list of all the characters in a word. |
| CharOCRConfidence | OCR confidence of a character. |
| CharStartX | X-coordinate of a character. |
| CharStartY | Y-coordinate of a character. |
| CharValue | Value of a character. |
| CharWidth | Width of a character. |
| CheckBoxList | Check Box List. |
| ClassMatch | High Confidence Score for document classification. |
| ClassificationWords | Classification Words. |
| Color | Matches confidence: Green - High, Orange - Medium, Red - Low. |
| Confidence | Confidence in the Title. |
| Content | Information after title that is obtained in DS. |
| CustomerCode | IBM Company of the user who ran the file. |
| CustomerUniqueIdentifier | Unique Identifier passed by user when initial API call was made. |
| Description | Indicator of how many Mandatory fields in the Key Value Pair were found. |
| Distance | Distance between checkbox and closest text next to it. |
| DocNLU | Representation of Natural Language Understanding in DSOutput attribute. |
| DocumentArrivalTime | Time the document was uploaded for processing. |
| DocumentClass | Classification of Document. |
| DocumentClassMatch | Confidence Score for header normalization. |
| DocumentOCRConfidence | OCR Confidence of document. |
| DocumentExtension | Extension of the document. |
| DocumentLanguage | Language of the document. |
| DocumentName | Name of document. |
| DS | DSOutput | Document Segmentation output. |
| DSOutput | Document Segment output. |
| HeaderClass | Header Classification. |
| HeaderConfidence | Confidence of Header. |
| Headers | List of Headers under which Line Items are found. |
| HeaderText | Header Value. |
| ID | ID of document classification. |
| KVPTable | Key Value Pair Table. |
| Language | Language of the page. |
| LineHeight | Height of the line. |
| LineID | Line ID. |
| LineItems | List of Key-Value Pairs where a Header is the Key and the Line Item is the Value. |
| LineItemGroups | Collections of Headers and Line Items for a table in the TableList. |
| LineItemGroupID | Line Item Group ID for each table. |
| LineItemID | Identifier for each row of LineItems. |
| LineList | A list of all the lines on a page. |
| LineStartX | X-coordinate of a line on a page. |
| LineStartY | Y-coordinate of a line on a page. |
| LineWidth | Width of a line. |
| Miscellaneous | Any other attribute of a block. |
| OCRAccuracy | Same as Document Confidence. |
| PageOCRConfidence | OCR Confidence of page. |
| PageHeight | Height of the page. |
| PageID | Page ID. |
| pageList | List of page attributes. |
| PageNo | Page number in the document. |
| PageStartX | X-coordinate of a page. |
| PageStartY | Y-coordinate of a page. |
| PageWidth | Width of the page. |
| Remark | Information about a block. |
| RowHeight | Height of a row. |
| RowID | Row ID. |
| RowList | A list of all the rows on a page. |
| RowStartX | X-coordinate of a row. |
| RowStartY | Y-coordinate of a page. |
| RowWidth | Width of a row. |
| StrikeThroughList | A list of all the strikethroughs on a page. |
| TableHeight | Height of a table. |
| TableID | Table ID. |
| TableLineItems | Table Line Items Output. |
| TableList | A list of all the tables on a page. |
| TableStartX | X-coordinate of a table. |
| TableStartY | Y-coordinate of a table. |
| TableWidth | Width of a table. |
| Text | Text following a document. |
| Timestamp | Timestamp for when DS was run. |
| Title | Header of DS. |
| TotalGoodLetters | Total good letters on a page. |
| TotalLetters | Total letters on the page. |
| Trained | Indication if page title was trained previously. |
| TransactionID | Unique identification of document in DS. |
| UserID | UserID of the user that ran the document. |
| WordCharN | Number of characters in a word. |
| WordOCRConfidence | OCR Confidence of a word. |
| WordFontSize | Font size of the word. |
| WordFontSizeGroup | Font size group of the word. |
| WordHeight | Height of a word. |
| WordID | Word ID. |
| WordList | A list of all the words on a page. |
| WordNumChar | Total number of characters in the word. |
| WordStartX | X-coordinate of the word. |
| WordStartY | Width of a table Y-coordinate of the word. |
| WordValue | Value of the word. |
| WordWidth | Width of a table. |
| bold | Indicates whether the word is bold or not. |
| checked | Indicates whether a checkbox is checked or not. |
| height | Height, which can occur in strikethrough, checkbox, and text that is closest to a checkbox. |
| italics | Indicates whether the word is in italics or not. |
| underline | Indicates whether the word is underlined or not. |
| underlined | Indicates whether a line is underlined or not. |
| width | Width occurs in strikethrough, checkbox, and text that is closest to a checkbox. |
| x_min | X-coordinate, which can occur in strikethrough, checkbox and text that is closest to a checkbox. |
| y_min | Y-coordinate, which can occur in strikethrough, checkbox, and text that is closest to a checkbox. |
| KVPTable field | Description |
|---|---|
| Key | The text that is found in the document that corresponds to the key of the KVP. Note:
At times, the KVP is extracted by using ONLY the Extractor of type Value Pattern with Optional Key Alias without any KeyAliasPattern match. In such cases, the name of the KeyClass is used as the Key. |
| Value | The text that is found in the document that corresponds to the value of the KVP. |
| KeyStartX | The starting X coordinate for the Key in the document. |
| KeyStartY | The starting Y coordinate for the Key in the document. |
| KeyWidth | The width of the Key. |
| KeyHeight | The height of the Key. |
| KeyConfidence | The confidence of the Key. |
| ValueStartX | The start of the X coordinate for the Value in the document. |
| ValueStartY | The start of the Y coordinate for the Value in the document. |
| ValueWidth | The width of the Value. |
| ValueHeight | The height of the Value. |
| ValueConfidence | The confidence of the Value. |
| Sensitivity | The sensitivity of the KVP as specified for the KeyClass in the Ontology. |
| KeyClassConfidence | The confidence for the KeyClass. |
| KeyClass | A KeyClass that maps to an existing KVP. If the KVP does not match any KeyClass, which are defined in the Ontology, the KeyClass is an empty value. |
| PageNumber | The page number where the KVP was found. |
| Mandatory | The KVP is mandatory (True) or not (False). This value is specified in the KeyClass in the Ontology. |
| ValidatorResult |
Optional. The validation result of the Key-Value-Pair (KVP) value that is compared to the validator that is defined on the KeyClass. The ValidatorResult parameter exists if
The values are |
| ValidatorFailures |
Optional. A list of the validators that failed while the KVP value was being validated. This parameter is present if ValidatorResult is |
| ValidatorName | Optional. Name of the validator that is defined on the KeyClass. This parameter is present
if ValidatorResult is |
| ValidatorReference |
Optional. Reference to the validator in the ontology. It is represented by using the
symbolicNames as
This parameter is present if ValidatorResult is |
| ValidatorType |
Optional. The type of validator that is defined in the KeyClass. The values are "regex" or "dict". This parameter is present if ValidatorResult is |
| Description | Optional. The description on the validator implementation. This parameter is present if
ValidatorResult is |
| FailureReason | This parameter is not used for now. An empty string is returned. |
Example response for JSON fields
{
"AIOutput": [],
"Classification": {
"DocumentLanguage": "English",
"Page Title": {
"Title": [
"invoice"
],
"Trained": "YES",
"Confidence": "High"
},
"DocumentClass": {
"Actual": "Invoice",
"ID": 4,
"ClassMatch": "High",
"ClassificationWords": [
"regional",
"transport",
"services",
"toronto",
"bank",
"account",
"ontario",
"invoice",
"date",
"name",
"total",
"consumables",
"south",
"service",
"road",
"bloor",
"east",
"suite",
"royal",
"hydro",
"cylinder",
"tfir",
"pressure",
"test",
"extinguisher",
"phone",
"wwwregionaltranscom",
"terms",
"trading",
"strictly",
"days",
"thank",
"appreciate",
"business",
"sold",
"canada",
"payment",
"details",
"swift",
"code",
"anbk",
"please",
"forward",
"remittance",
"advice",
"either",
"email",
"accountsramservicescomau",
"description",
"workshop",
"item",
"number",
"price",
"extension",
"sales"
]
}
},
"CustomerCode": "IBM",
"DSOutput": [
{
"Title": "Regional_Transport_Invoice_0_0",
"Content": "Regional Transport Services 108 South Service Road PO Box 1973, Toronto Ontario, M2J 2B6 ı ı ı II ı ı ı ı ı II ı Phone: 416-555-1212 Fax: 416-555-1313 Web: www.RegionalTrans.com S10051868 INVOICE Terms of trading strictly 30 days from date of invoice Thank you, we appreciate your business Sold To IBM Canada Invoice # SI0051868 120 Bloor St. East, Suite 101 Toronto, Ontario M2X 1N7 Date BSB ABN 1/12/2016 015896 61 096 629 006 X Payment Details Bank: Royal Bank Account Name: Regional Transport Services Account: 2834-98769 Swift Code AN44B3K SUB TOTAL 436.17 TOTAL GST 43.62 TOTAL INC GST 479.79 Please forward remittance advice to either fax +61 8 89427299 or email accounts@ramservices.com.au �",
"DocumentClass": "Invoice",
"DocumentClassMatch": "High",
"DocumentName": "Regional_Transport_Invoice",
"Timestamp": "2019-03-19 14:21:21.446052",
"DocNLU": [],
"SegmentStart": {
"StartPage": 0,
"StartX": 112,
"StartY": 317
},
"SegmentEnd": {
"EndPage": 0,
"EndX": 2428,
"EndY": 3078
},
"TransactionID": "f3814fec-5d0d-19c8-393b-37d0798ab617_1",
"OCRAccuracy": 9.85
}
],
"DocumentArrivalTime": "2019-03-19 14:21:21.446052",
"DocumentExtension": "pdf",
"DocumentName": "Regional_Transport_Invoice",
"DocumentOCRConfidence": 9.85,
"ErrorList": [],
"ExtraInformation": {
"title": "Microsoft Word - Regional Transport Invoice.docx",
"keywords": "",
"creator": "Word",
"producer": "Mac OS X 10.12.6 Quartz PDFContext",
"creationdate": 1501479666000,
"moddate": 1501479666000,
"tagged": "no",
"form": "none",
"pages": 1,
"encrypted": "no",
"page_size": "612 x 792 pts (letter) (rotated 0 degrees)",
"mediabox": "0.00 0.00 612.00 792.00",
"cropbox": "0.00 0.00 612.00 792.00",
"bleedbox": "0.00 0.00 612.00 792.00",
"trimbox": "0.00 0.00 612.00 792.00",
"artbox": "0.00 0.00 612.00 792.00",
"file_size": "68221 bytes",
"optimized": "no",
"pdf_version": 1.3
},
"MandatoryInformation": {
"Color": "Orange",
"Description": "Mandatory field(s) have semantic match only."
},
"UserID": 1,
"pageList": [
{
"BlockList": [
{
"language": "nl",
"BlockStartX": 708,
"BlockStartY": 317,
"BlockWidth": 1611,
"BlockHeight": 278,
"BlockID": "block_0",
"BlockBGColor": "",
"BlockFGColor": "",
"BlockType": "",
"Miscellaneous": "",
"Remark": "",
"LineList": [
{
"fontFace": "DejaVu Sans",
"LineStartX": 708,
"LineStartY": 317,
"LineWidth": 450,
"LineHeight": 32,
"LineID": "line_0",
"WordList": [
{
"WordStartX": 708,
"WordStartY": 317,
"WordWidth": 137,
"WordHeight": 32,
"bold": "true",
"underline": "false",
"italics": "false",
"WordFontSize": "800",
"FontSize": "800",
"WordFontSizeGroup": 2,
"WordValue": "Regional",
"WordOCRConfidence": 10,
"WordID": "word_0",
"WordCharN": 8
}
],
"pageNum": 0,
"blockNum": "block_0",
"LineHeaderAttributes": {
"HeaderText": "Regional Transport Services",
"HeaderConfidence": "Low",
"HeaderClass": null
}
},
{
"fontFace": "DejaVu Sans",
"LineStartX": 828,
"LineStartY": 353,
"LineWidth": 328,
"LineHeight": 25,
"LineID": "line_1",
"WordList": [
{
"WordStartX": 828,
"WordStartY": 357,
"WordWidth": 45,
"WordHeight": 21,
"bold": "true",
"underline": "false",
"italics": "false",
"WordFontSize": "700",
"FontSize": "700",
"WordFontSizeGroup": 1,
"WordValue": "108",
"WordOCRConfidence": 10,
"WordID": "word_0",
"WordCharN": 3
}
],
"pageNum": 0,
"blockNum": "block_0",
"LineHeaderAttributes": {
"HeaderText": "108 South Service Road",
"HeaderConfidence": "Low",
"HeaderClass": null
}
},
{
"fontFace": "DejaVu Sans",
"LineStartX": 857,
"LineStartY": 391,
"LineWidth": 301,
"LineHeight": 26,
"LineID": "line_2",
"WordList": [
{
"WordStartX": 857,
"WordStartY": 391,
"WordWidth": 38,
"WordHeight": 22,
"bold": "true",
"underline": "false",
"italics": "false",
"WordFontSize": "700",
"FontSize": "700",
"WordFontSizeGroup": 1,
"WordValue": "PO",
"WordOCRConfidence": 10,
"WordID": "word_0",
"WordCharN": 2
}
],
"pageNum": 0,
"blockNum": "block_0",
"LineHeaderAttributes": {
"HeaderText": "PO Box 1973, Toronto",
"HeaderConfidence": "Low",
"HeaderClass": null
}
},
{
"fontFace": "DejaVu Sans",
"LineStartX": 922,
"LineStartY": 426,
"LineWidth": 236,
"LineHeight": 26,
"LineID": "line_3",
"WordList": [
{
"WordStartX": 922,
"WordStartY": 426,
"WordWidth": 109,
"WordHeight": 26,
"CharListrunlist": [],
"bold": "true",
"underline": "false",
"italics": "false",
"WordFontSize": "700",
"FontSize": "700",
"WordFontSizeGroup": 1,
"WordValue": "Ontario,",
"WordOCRConfidence": 10,
"WordID": "word_0",
"WordCharN": 8
},
{
"WordStartX": 1042,
"WordStartY": 427,
"WordWidth": 53,
"WordHeight": 21,
"bold": "true",
"underline": "false",
"italics": "false",
"WordFontSize": "700",
"FontSize": "700",
"WordFontSizeGroup": 1,
"WordValue": "M2J",
"WordOCRConfidence": 10,
"WordID": "word_1",
"WordCharN": 3
},
{
"WordStartX": 1106,
"WordStartY": 427,
"WordWidth": 52,
"WordHeight": 21,
"bold": "true",
"underline": "false",
"italics": "false",
"WordFontSize": "700",
"FontSize": "700",
"WordFontSizeGroup": 1,
"WordValue": "2B6",
"WordOCRConfidence": 10,
"WordID": "word_2",
"WordCharN": 3
}
],
"pageNum": 0,
"blockNum": "block_0",
"LineHeaderAttributes": {
"HeaderText": "Ontario, M2J 2B6",
"HeaderConfidence": "Low",
"HeaderClass": null
}
},
{
"LineStartX": 1943,
"LineStartY": 382,
"LineWidth": 376,
"LineHeight": 125,
"LineID": "line_4",
"WordList": [
{
"WordStartX": 1943,
"WordStartY": 383,
"WordWidth": 8,
"WordHeight": 121,
"bold": "false",
"underline": "false",
"italics": "false",
"WordFontSize": "5600",
"FontSize": "5600",
"WordFontSizeGroup": 7,
"WordValue": "ı",
"WordOCRConfidence": 0,
"WordID": "word_0",
"WordCharN": 1
}
],
"pageNum": 0,
"blockNum": "block_0",
"LineHeaderAttributes": {
"HeaderText": "ı ı ı ",
"HeaderConfidence": "Low",
"HeaderClass": null
}
},
{
"fontFace": "DejaVu Sans",
"LineStartX": 865,
"LineStartY": 497,
"LineWidth": 292,
"LineHeight": 21,
"LineID": "line_15",
"WordList": [
{
"WordStartX": 865,
"WordStartY": 497,
"WordWidth": 95,
"WordHeight": 21,
"CharListrunlist": [],
"bold": "true",
"underline": "false",
"italics": "false",
"WordFontSize": "700",
"FontSize": "700",
"WordFontSizeGroup": 1,
"WordValue": "Phone:",
"WordOCRConfidence": 10,
"WordID": "word_0",
"WordCharN": 6
}
],
"pageNum": 0,
"blockNum": "block_0",
"LineHeaderAttributes": {
"HeaderText": "Phone: 416-555-1212",
"HeaderConfidence": "Low",
"HeaderClass": null
}
},
{
"fontFace": "DejaVu Sans",
"LineStartX": 902,
"LineStartY": 532,
"LineWidth": 254,
"LineHeight": 21,
"LineID": "line_16",
"WordList": [
{
"WordStartX": 902,
"WordStartY": 532,
"WordWidth": 57,
"WordHeight": 21,
"bold": "true",
"underline": "false",
"italics": "false",
"WordFontSize": "700",
"FontSize": "700",
"WordFontSizeGroup": 1,
"WordValue": "Fax:",
"WordOCRConfidence": 10,
"WordID": "word_0",
"WordCharN": 4
}
],
"pageNum": 0,
"blockNum": "block_0",
"LineHeaderAttributes": {
"HeaderText": "Fax: 416-555-1313",
"HeaderConfidence": "Low",
"HeaderClass": null
}
},
{
"fontFace": "DejaVu Sans",
"LineStartX": 732,
"LineStartY": 567,
"LineWidth": 424,
"LineHeight": 27,
"LineID": "line_17",
"WordList": [
{
"WordStartX": 732,
"WordStartY": 567,
"WordWidth": 70,
"WordHeight": 21,
"bold": "true",
"underline": "false",
"italics": "false",
"WordFontSize": "700",
"FontSize": "700",
"WordFontSizeGroup": 1,
"WordValue": "Web:",
"WordOCRConfidence": 10,
"WordID": "word_0",
"WordCharN": 4
},
{
"WordStartX": 812,
"WordStartY": 567,
"WordWidth": 345,
"WordHeight": 27,
"bold": "true",
"underline": "false",
"italics": "false",
"WordFontSize": "700",
"FontSize": "700",
"WordFontSizeGroup": 1,
"WordValue": "www.RegionalTrans.com",
"WordOCRConfidence": 10,
"WordID": "word_1",
"WordCharN": 21
}
],
"pageNum": 0,
"blockNum": "block_0",
"LineHeaderAttributes": {
"HeaderText": "Web: www.RegionalTrans.com",
"HeaderConfidence": "Low",
"HeaderClass": null
}
},
{
"LineStartX": 2062,
"LineStartY": 515,
"LineWidth": 137,
"LineHeight": 25,
"LineID": "line_18",
"WordList": [
{
"WordStartX": 2062,
"WordStartY": 515,
"WordWidth": 137,
"WordHeight": 25,
"bold": "false",
"underline": "false",
"italics": "false",
"WordFontSize": "800",
"FontSize": "800",
"WordFontSizeGroup": 2,
"WordValue": "S10051868",
"WordOCRConfidence": 10,
"WordID": "word_0",
"WordCharN": 9
}
],
"pageNum": 0,
"blockNum": "block_0",
"LineHeaderAttributes": {}
}
]
},
{
"BlockStartX": 2073,
"BlockStartY": 695,
"BlockWidth": 353,
"BlockHeight": 67,
"BlockID": "block_14",
"BlockBGColor": "",
"BlockFGColor": "",
"BlockType": "",
"Miscellaneous": "",
"Remark": "",
"LineList": [
{
"fontFace": "DejaVu Sans",
"LineStartX": 2073,
"LineStartY": 695,
"LineWidth": 352,
"LineHeight": 67,
"LineID": "line_0",
"WordList": [
{
"WordStartX": 2073,
"WordStartY": 695,
"WordWidth": 352,
"WordHeight": 67,
"CharListrunlist": [],
"bold": "true",
"underline": "false",
"italics": "false",
"WordFontSize": "2100",
"FontSize": "2100",
"WordFontSizeGroup": 5,
"WordValue": "INVOICE",
"WordOCRConfidence": 10,
"WordID": "word_0",
"WordCharN": 7
}
],
"pageNum": 0,
"blockNum": "block_14",
"LineHeaderAttributes": {
"HeaderText": "INVOICE",
"HeaderConfidence": "Low",
"HeaderClass": null
}
}
]
}
],
"TableList": [
{
"TableID": "table_0",
"TableStartX": 101.04166666666667,
"TableStartY": 1378.9583333333335,
"TableHeight": 179.99999999999977,
"TableWidth": 2308.9583333333335,
"RowList": [
{
"RowID": "row_0",
"RowStartX": 101.04166666666667,
"RowStartY": 1378.9583333333335,
"RowHeight": 48.95833333333303,
"RowWidth": 2308.9583333333335,
"CellList": [
{
"CellID": "cell_0",
"CellStartX": 101.04166666666667,
"CellStartY": 1378.9583333333335,
"CellWidth": 331.04166666666663,
"CellHeight": 48.95833333333303,
"LineList": [
{
"LineID": "line_0",
"WordList": [
{
"WordID": "word_0",
"WordValue": "Item",
"WordStartX": 192.91666666666669,
"WordStartY": 1388.9583333333335,
"WordWidth": 57.083333333333314,
"WordHeight": 22.083333333333258,
"WordOCRConfidence": 10,
"WordNumChar": 4,
"bold": "true",
"WordFontSize": "700",
"italics": "false",
"underline": "none"
},
{
"WordID": "word_1",
"WordValue": "Number",
"WordStartX": 262.0833333333333,
"WordStartY": 1388.9583333333335,
"WordWidth": 107.91666666666669,
"WordHeight": 22.083333333333258,
"WordOCRConfidence": 10,
"WordNumChar": 6,
"bold": "false",
"WordFontSize": "700",
"italics": "false",
"underline": "false"
}
],
"LineStartX": 192.91666666666669,
"LineStartY": 1388.9583333333335,
"LineWidth": 177.08333333333331,
"LineHeight": 22.083333333333258
}
],
"CellHeaderAttributes": [
{
"SemanticMatch": "ItemNumber",
"Confidence": "Low",
"ClassName": "matternumber",
"HeaderText": "ItemNumber"
}
]
},
{
"CellID": "cell_1",
"CellStartX": 432.0833333333333,
"CellStartY": 1378.9583333333335,
"CellWidth": 840.0000000000002,
"CellHeight": 48.95833333333303,
"LineList": [
{
"LineID": "line_0",
"WordList": [
{
"WordID": "word_0",
"WordValue": "Description",
"WordStartX": 823.9583333333333,
"WordStartY": 1388.9583333333335,
"WordWidth": 156.04166666666674,
"WordHeight": 28.125,
"WordOCRConfidence": 10,
"WordNumChar": 11,
"bold": "true",
"WordFontSize": "700",
"italics": "false",
"underline": "none"
}
],
"LineStartX": 823.9583333333333,
"LineStartY": 1388.9583333333335,
"LineWidth": 156.04166666666674,
"LineHeight": 28.125
}
],
"CellHeaderAttributes": [
{
"SemanticMatch": "Description",
"Confidence": "High",
"ClassName": "description",
"HeaderText": "Description"
}
]
}
]
},
{
"RowID": "row_1",
"RowStartX": 101.04166666666667,
"RowStartY": 1427.9166666666665,
"RowHeight": 42.083333333333485,
"RowWidth": 2308.9583333333335,
"CellList": [
{
"CellID": "cell_0",
"CellStartX": 101.04166666666667,
"CellStartY": 1427.9166666666665,
"CellWidth": 331.04166666666663,
"CellHeight": 42.083333333333485,
"LineList": [
{
"LineID": "line_0",
"WordList": [
{
"WordID": "word_0",
"WordValue": "JOB0024453",
"WordStartX": 112.08333333333333,
"WordStartY": 1437.0833333333333,
"WordWidth": 192.91666666666669,
"WordHeight": 25.833333333333485,
"WordOCRConfidence": 10,
"WordNumChar": 10,
"bold": "false",
"WordFontSize": "800",
"italics": "false",
"underline": "none"
}
],
"LineStartX": 112.08333333333333,
"LineStartY": 1437.0833333333333,
"LineWidth": 192.91666666666669,
"LineHeight": 25.833333333333485
}
],
"CellHeaderAttributes": []
},
{
"CellID": "cell_1",
"CellStartX": 432.0833333333333,
"CellStartY": 1427.9166666666665,
"CellWidth": 840.0000000000002,
"CellHeight": 42.083333333333485,
"LineList": [
{
"LineID": "line_0",
"WordList": [
{
"WordID": "word_0",
"WordValue": "J33409",
"WordStartX": 495,
"WordStartY": 1437.9166666666665,
"WordWidth": 107.91666666666674,
"WordHeight": 25.000000000000227,
"WordOCRConfidence": 10,
"WordNumChar": 6,
"bold": "false",
"WordFontSize": "800",
"italics": "false",
"underline": "none"
},
{
"WordID": "word_1",
"WordValue": "Hydro",
"WordStartX": 616.0416666666666,
"WordStartY": 1437.9166666666665,
"WordWidth": 86.04166666666663,
"WordHeight": 32.083333333333485,
"WordOCRConfidence": 10,
"WordNumChar": 5,
"bold": "false",
"WordFontSize": "800",
"italics": "false",
"underline": "false"
},
{
"WordID": "word_2",
"WordValue": "of",
"WordStartX": 712.0833333333333,
"WordStartY": 1437.9166666666665,
"WordWidth": 26.875000000000114,
"WordHeight": 25.000000000000227,
"WordOCRConfidence": 10,
"WordNumChar": 2,
"bold": "false",
"WordFontSize": "800",
"italics": "false",
"underline": "false"
},
{
"WordID": "word_3",
"WordValue": "CO2",
"WordStartX": 750,
"WordStartY": 1437.0833333333333,
"WordWidth": 66.04166666666674,
"WordHeight": 25.833333333333485,
"WordOCRConfidence": 10,
"WordNumChar": 3,
"bold": "false",
"WordFontSize": "800",
"italics": "false",
"underline": "false"
},
{
"WordID": "word_4",
"WordValue": "cylinder",
"WordStartX": 827.0833333333334,
"WordStartY": 1437.9166666666665,
"WordWidth": 115,
"WordHeight": 32.083333333333485,
"WordOCRConfidence": 10,
"WordNumChar": 8,
"bold": "false",
"WordFontSize": "800",
"italics": "false",
"underline": "false"
}
],
"LineStartX": 495,
"LineStartY": 1437.0833333333333,
"LineWidth": 447.08333333333337,
"LineHeight": 32.91666666666674
}
],
"CellHeaderAttributes": []
}
]
}
]
}
],
"PageInfo": {
"Language": [
"en",
"de",
"fr",
"nl",
"no",
"da"
],
"PageHeight": 3300,
"PageID": "page_0",
"PageNo": 0,
"PageStartX": 0,
"PageStartY": 0,
"PageWidth": 2550,
"PageOCRConfidence": 9.9
},
"TotalLetters": 818,
"TotalGoodLetters": 806,
"BarcodeList": [
{
"BarCodeStartX": 1893,
"BarCodeStartY": 382,
"BarCodeWidth": 473,
"BarCodeHeight": 125,
"BarCodeNo": "SI0051868"
}
],
"KVPTable": [
{
"Key": "Phone",
"Value": "416-555-1212",
"KeyStartX": 865,
"KeyStartY": 497,
"KeyWidth": 95,
"KeyHeight": 21,
"KeyConfidence": "High",
"ValueStartX": 977,
"ValueStartY": 497,
"ValueWidth": 179,
"ValueHeight": 21,
"ValueConfidence": "High",
"Sensitivity": false,
"EditedValue": "Null",
"KeyClassConfidence": "High",
"KeyClass": "Phone",
"PageNumber": 0,
"ValidatorResult": "Fail",
"ValidatorFailures": {
"AND": [
{
"ValidatorName": "Phone List",
"ValidatorReference": "demo.Phone.PhoneDict",
"ValidatorType": "dict",
"Description": "Dictionary to validate the phone number",
"FailureReason": ""
},
{
"ValidatorName": "Phone Phone Validator",
"ValidatorReference": "demo.Email.PhoneRegexValidator",
"ValidatorType": "regex",
"Description": "Regex to validate the value for a phone number",
"FailureReason": ""
}
]
},
"Mandatory": "False"
},
{
"Key": "Fax",
"Value": "416-555-1313",
"KeyStartX": 902,
"KeyStartY": 532,
"KeyWidth": 57,
"KeyHeight": 21,
"KeyConfidence": "High",
"ValueStartX": 977,
"ValueStartY": 532,
"ValueWidth": 179,
"ValueHeight": 21,
"ValueConfidence": "High",
"Sensitivity": false,
"EditedValue": "Null",
"KeyClassConfidence": "High",
"KeyClass": "Fax",
"PageNumber": 0,
"Mandatory": "False"
},
{
"Key": "INVOICE",
"Value": "Terms of trading strictly 30 days from date of invoice Thank you, we appreciate your business",
"KeyStartX": 2073,
"KeyStartY": 695,
"KeyWidth": 352,
"KeyHeight": 67,
"KeyConfidence": "High",
"ValueStartX": 382,
"ValueStartY": 790,
"ValueWidth": 771,
"ValueHeight": 72,
"ValueConfidence": "High",
"Sensitivity": false,
"EditedValue": "Null",
"KeyClassConfidence": "High",
"KeyClass": "InvoiceNumber",
"PageNumber": 0,
"Mandatory": "True"
},
{
"Key": "Date",
"Value": "1/12/2016",
"KeyStartX": 112,
"KeyStartY": 1200,
"KeyWidth": 87,
"KeyHeight": 31,
"KeyConfidence": "High",
"ValueStartX": 113,
"ValueStartY": 1248,
"ValueWidth": 181,
"ValueHeight": 31,
"ValueConfidence": "High",
"Sensitivity": false,
"EditedValue": "Null",
"KeyClassConfidence": "High",
"KeyClass": "InvoiceDate",
"PageNumber": 0,
"Mandatory": "False"
},
{
"Key": "BSB",
"Value": "015896",
"KeyStartX": 852,
"KeyStartY": 1200,
"KeyWidth": 82,
"KeyHeight": 31,
"KeyConfidence": "High",
"ValueStartX": 850,
"ValueStartY": 1250,
"ValueWidth": 137,
"ValueHeight": 30,
"ValueConfidence": "High",
"Sensitivity": false,
"EditedValue": "Null",
"KeyClassConfidence": "High",
"KeyClass": "BSB",
"PageNumber": 0,
"ValidatorResult": "Fail",
"ValidatorFailures": {
"OR": [
{
"ValidatorName": "BSB List",
"ValidatorReference": "demo.BSB.BSBDict",
"ValidatorType": "dict",
"Description": "Dictionary to validate the BSB number",
"FailureReason": ""
},
{
"ValidatorName": "BSB Validator",
"ValidatorReference": "demo.BSB.BSBRegexValidator",
"ValidatorType": "regex",
"Description": "Regex to validate the value for a BSB number",
"FailureReason": ""
}
]
},
"Mandatory": "False"
}
],
"TableLineItems": [
{
"TableID": "table_0",
"LineItemGroups": [
{
"LineItemGroupID": 0,
"Headers": [
"Item Number",
"Description"
],
"LineItems": [
{
"LineItemID": 0,
"KVPs": [
{
"Key": "Item Number",
"Value": "JOB0024453"
},
{
"Key": "Description",
"Value": "J33409 Hydro of CO2 cylinder "
}
]
}
]
}
]
}
]
}
]
}