♻️ update display & structure for invoice splitter v1

Author: sebastianMindee

docs/code_samples/invoice_splitter_v1_async.txt

@@ -1,12 +1,9 @@
 import com.mindee.MindeeClient;
 import com.mindee.input.LocalInputSource;
 import com.mindee.parsing.common.AsyncPredictResponse;
-import com.mindee.parsing.common.Job;
-import com.mindee.parsing.common.Document;
 import com.mindee.product.invoicesplitter.InvoiceSplitterV1;
 import java.io.File;
 import java.io.IOException;
-import java.util.Optional;
 
 public class SimpleMindeeClient {
 
@@ -40,4 +37,5 @@ public class SimpleMindeeClient {
 //        page -> System.out.println(page.toString())
 //    );
   }
+
 }

docs/financial_document_v1.md

@@ -107,7 +107,7 @@ public class SimpleMindeeClient {
 ########
 Document
 ########
-:Mindee ID: b26161ce-35d0-4984-b1ff-886645e160e6
+:Mindee ID: f469a24d-3875-4a83-ad43-e0d5aa9da604
 :Filename: default_sample.jpg
 
 Inference
@@ -124,8 +124,8 @@ Prediction
 :Document Number: INT-001
 :Reference Numbers: 2412/2019
 :Purchase Date: 2019-11-02
-:Due Date: 2019-02-26
-:Payment Date: 2019-02-26
+:Due Date: 2019-11-17
+:Payment Date: 2019-11-17
 :Total Net: 195.00
 :Total Amount: 204.75
 :Taxes:
@@ -176,8 +176,8 @@ Page 0
 :Document Number: INT-001
 :Reference Numbers: 2412/2019
 :Purchase Date: 2019-11-02
-:Due Date: 2019-02-26
-:Payment Date: 2019-02-26
+:Due Date: 2019-11-17
+:Payment Date: 2019-11-17
 :Total Net: 195.00
 :Total Amount: 204.75
 :Taxes:

docs/invoice_splitter_v1.md

@@ -1,27 +1,22 @@
 ---
-title: Invoice Splitter API Java
+title: Invoice Splitter OCR Java
 category: 622b805aaec68102ea7fcbc2
 slug: java-invoice-splitter-ocr
 parentDoc: 631a062c3718850f3519b793
 ---
 The Java OCR SDK supports the [Invoice Splitter API](https://platform.mindee.com/mindee/invoice_splitter).
 
-Using [this sample](https://github.com/mindee/client-lib-test-data/blob/main/products/invoice_splitter/default_sample.pdf), we are going to illustrate how to detect the pages of multiple invoices within the same document.
+Using the [sample below](https://github.com/mindee/client-lib-test-data/blob/main/products/invoice_splitter/default_sample.pdf), we are going to illustrate how to extract the data that we want using the OCR SDK.
+![Invoice Splitter sample](https://github.com/mindee/client-lib-test-data/blob/main/products/invoice_splitter/default_sample.pdf?raw=true)
 
 # Quick-Start
-
-> **⚠️ Important:** This API only works **asynchronously**, which means that documents have to be sent and retrieved in a specific way:
-
 ```java
 import com.mindee.MindeeClient;
 import com.mindee.input.LocalInputSource;
 import com.mindee.parsing.common.AsyncPredictResponse;
-import com.mindee.parsing.common.Job;
-import com.mindee.parsing.common.Document;
 import com.mindee.product.invoicesplitter.InvoiceSplitterV1;
 import java.io.File;
 import java.io.IOException;
-import java.util.Optional;
 
 public class SimpleMindeeClient {
 
@@ -37,8 +32,8 @@ public class SimpleMindeeClient {
 
     // Parse the file asynchronously
     AsyncPredictResponse<InvoiceSplitterV1> response = mindeeClient.enqueueAndParse(
-      InvoiceSplitterV1.class,
-      inputSource
+        InvoiceSplitterV1.class,
+        inputSource
     );
 
     // Print a summary of the response
@@ -55,69 +50,82 @@ public class SimpleMindeeClient {
 //        page -> System.out.println(page.toString())
 //    );
   }
+
 }
+
 ```
 
 **Output (RST):**
-
 ```rst
 ########
 Document
 ########
-:Mindee ID: 8c25cc63-212b-4537-9c9b-3fbd3bd0ee20
-:Filename: default_sample.jpg
+:Mindee ID: 15ad7a19-7b75-43d0-b0c6-9a641a12b49b
+:Filename: default_sample.pdf
 
 Inference
 #########
-:Product: mindee/carte_vitale v1.0
-:Rotation applied: Yes
+:Product: mindee/invoice_splitter v1.1
+:Rotation applied: No
 
 Prediction
 ==========
-:Given Name(s): NATHALIE
-:Surname: DURAND
-:Social Security Number: 269054958815780
-:Issuance Date: 2007-01-01
+:Invoice Page Groups:
+  :Page indexes: 0
+  :Page indexes: 1
 
 Page Predictions
 ================
 
 Page 0
 ------
-:Given Name(s): NATHALIE
-:Surname: DURAND
-:Social Security Number: 269054958815780
-:Issuance Date: 2007-01-01
+:Invoice Page Groups:
+
+Page 1
+------
+:Invoice Page Groups:
 ```
 
 # Field Types
+## Standard Fields
+These fields are generic and used in several products.
 
-## Specific Fields
+### BaseField
+Each prediction object contains a set of fields that inherit from the generic `BaseField` class.
+A typical `BaseField` object will have the following attributes:
 
-### Page Indexes
+* **confidence** (`Double`): the confidence score of the field prediction.
+* **boundingBox** (`Polygon`): contains exactly 4 relative vertices (points) coordinates of a right rectangle containing the field in the document.
+* **polygon** (`Polygon`): contains the relative vertices coordinates (`polygon` extends `List<Point>`) of a polygon containing the field in the image.
+* **pageId** (`Integer`): the ID of the page, always `null` when at document-level.
 
-List of page group indexes.
+> **Note:** A `Point` simply refers to a List of `Double`.
 
-A `PageIndexes` implements the following attributes:
 
-- **pageIndexes** (`List<Integer>`): List of indexes of the pages of a single invoice.
-- **confidence** (`Double`): The confidence of the prediction.
+Aside from the previous attributes, all basic fields have access to a custom `toString` method that can be used to print their value as a string.
 
-# Attributes
+## Specific Fields
+Fields which are specific to this product; they are not used in any other product.
+
+### Invoice Page Groups Field
+List of page groups. Each group represents a single invoice within a multi-invoice document.
+
+A `InvoiceSplitterV1InvoicePageGroup` implements the following attributes:
 
+* **pageIndexes** (`List<Integer>`): List of page indexes that belong to the same invoice (group).
+
+# Attributes
 The following fields are extracted for Invoice Splitter V1:
 
 ## Invoice Page Groups
-
-**invoicePageGroups** (`List<`[invoicePageGroups](#page-indexes)`>`): List of page indexes that belong to the same invoice in the PDF.
+**invoicePageGroups**(List<[InvoiceSplitterV1InvoicePageGroup](#invoice-page-groups-field)>): List of page groups. Each group represents a single invoice within a multi-invoice document.
 
 ```java
 for (invoicePageGroupsElem : result.getDocument().getInference().getPrediction().getInvoicePageGroups())
 {
-  System.out.println(invoicePageGroupsElem);
+    System.out.println(invoicePageGroupsElem.value);
 }
 ```
 
 # Questions?
-
 [Join our Slack](https://join.slack.com/t/mindee-community/shared_invite/zt-2d0ds7dtz-DPAF81ZqTy20chsYpQBW5g)

docs/invoices_v4.md

@@ -107,7 +107,7 @@ public class SimpleMindeeClient {
 ########
 Document
 ########
-:Mindee ID: a67b70ea-4b1e-4eac-ae75-dda47a7064ae
+:Mindee ID: 86b1833f-138b-4a01-8387-860204b0e631
 :Filename: default_sample.jpg
 
 Inference
@@ -122,8 +122,8 @@ Prediction
 :Purchase Order Number: AD29094
 :Reference Numbers: AD29094
 :Purchase Date: 2018-09-25
-:Due Date: 2011-12-01
-:Payment Date: 2011-12-01
+:Due Date:
+:Payment Date:
 :Total Net: 2145.00
 :Total Amount: 2608.20
 :Total Tax: 193.20
@@ -168,8 +168,8 @@ Page 0
 :Purchase Order Number: AD29094
 :Reference Numbers: AD29094
 :Purchase Date: 2018-09-25
-:Due Date: 2011-12-01
-:Payment Date: 2011-12-01
+:Due Date:
+:Payment Date:
 :Total Net: 2145.00
 :Total Amount: 2608.20
 :Total Tax: 193.20

src/main/java/com/mindee/extraction/PDFExtractor.java

@@ -5,7 +5,7 @@
 import com.mindee.MindeeException;
 import com.mindee.input.InputSourceUtils;
 import com.mindee.input.LocalInputSource;
-import com.mindee.product.invoicesplitter.InvoiceSplitterV1Document;
+import com.mindee.product.invoicesplitter.InvoiceSplitterV1InvoicePageGroup;
 import java.awt.image.BufferedImage;
 import java.io.ByteArrayInputStream;
 import java.io.IOException;
@@ -118,11 +118,11 @@ public List<ExtractedPDF> extractSubDocuments(List<List<Integer>> pageIndexes)
    * @return a list of extracted files.
    * @throws IOException Throws if the file can't be accessed.
    */
-  public List<ExtractedPDF> extractInvoices(List<InvoiceSplitterV1Document.PageIndexes> pageIndexes)
+  public List<ExtractedPDF> extractInvoices(List<InvoiceSplitterV1InvoicePageGroup> pageIndexes)
       throws IOException {
 
     List<List<Integer>> indexes =
-        pageIndexes.stream().map(InvoiceSplitterV1Document.PageIndexes::getPageIndexes)
+        pageIndexes.stream().map(InvoiceSplitterV1InvoicePageGroup::getPageIndexes)
         .collect(Collectors.toList());
 
 
@@ -138,17 +138,17 @@ public List<ExtractedPDF> extractInvoices(List<InvoiceSplitterV1Document.PageInd
    * @return a list of extracted files.
    * @throws IOException Throws if the file can't be accessed.
    */
-  public List<ExtractedPDF> extractInvoices(List<InvoiceSplitterV1Document.PageIndexes> pageIndexes,
+  public List<ExtractedPDF> extractInvoices(List<InvoiceSplitterV1InvoicePageGroup> pageIndexes,
                                             boolean strict) throws IOException {
     List<List<Integer>> correctPageIndexes = new ArrayList<>();
     if (!strict) {
       return extractInvoices(pageIndexes);
     }
-    Iterator<InvoiceSplitterV1Document.PageIndexes> iterator = pageIndexes.iterator();
+    Iterator<InvoiceSplitterV1InvoicePageGroup> iterator = pageIndexes.iterator();
     List<Integer> currentList = new ArrayList<>();
     Double previousConfidence = null;
     while (iterator.hasNext()) {
-      InvoiceSplitterV1Document.PageIndexes pageIndex = iterator.next();
+      InvoiceSplitterV1InvoicePageGroup pageIndex = iterator.next();
       Double confidence = pageIndex.getConfidence();
       List<Integer> pageList = pageIndex.getPageIndexes();
 

src/main/java/com/mindee/product/ind/indianpassport/IndianPassportV1Document.java

@@ -11,7 +11,7 @@
 import lombok.Getter;
 
 /**
- * Passport - India API version 1.1 document data.
+ * Passport - India API version 1.2 document data.
  */
 @Getter
 @EqualsAndHashCode(callSuper = false)

src/main/java/com/mindee/product/invoicesplitter/InvoiceSplitterV1.java

@@ -6,12 +6,11 @@
 import lombok.Getter;
 
 /**
- * The invoice splitter V1 inference.
+ * Invoice Splitter API version 1 inference prediction.
  */
 @Getter
 @JsonIgnoreProperties(ignoreUnknown = true)
 @EndpointInfo(endpointName = "invoice_splitter", version = "1")
-public class InvoiceSplitterV1 extends
-    Inference<InvoiceSplitterV1Document, InvoiceSplitterV1Document> {
-
+public class InvoiceSplitterV1
+    extends Inference<InvoiceSplitterV1Document, InvoiceSplitterV1Document> {
 }

src/main/java/com/mindee/product/invoicesplitter/InvoiceSplitterV1Document.java

@@ -2,67 +2,50 @@
 
 import com.fasterxml.jackson.annotation.JsonIgnoreProperties;
 import com.fasterxml.jackson.annotation.JsonProperty;
+import com.mindee.parsing.SummaryHelper;
 import com.mindee.parsing.common.Prediction;
+import java.util.ArrayList;
 import java.util.List;
-import java.util.stream.Collectors;
 import lombok.EqualsAndHashCode;
 import lombok.Getter;
 
 /**
- * Document data for Invoice Splitter, API version 1.
+ * Invoice Splitter API version 1.2 document data.
  */
 @Getter
 @EqualsAndHashCode(callSuper = false)
 @JsonIgnoreProperties(ignoreUnknown = true)
 public class InvoiceSplitterV1Document extends Prediction {
 
+  /**
+   * List of page groups. Each group represents a single invoice within a multi-invoice document.
+   */
   @JsonProperty("invoice_page_groups")
-  private List<PageIndexes> invoicePageGroups;
-
-  @Override
-  public String toString() {
-    StringBuilder outStr = new StringBuilder();
-
-    outStr.append(String.format(":Invoice Page Groups: %n"));
-    if (invoicePageGroups != null) {
-      String pageGroupsString = this.getInvoicePageGroups().stream()
-          .map(PageIndexes::toString)
-          .collect(Collectors.joining(String.format("%n")));
-      outStr.append(String.format("%s%n", pageGroupsString));
-    }
-    return outStr.toString();
-  }
+  protected List<InvoiceSplitterV1InvoicePageGroup> invoicePageGroups = new ArrayList<>();
 
   @Override
   public boolean isEmpty() {
-    return invoicePageGroups.isEmpty();
+    return (
+      (this.invoicePageGroups == null || this.invoicePageGroups.isEmpty())
+      );
   }
 
-  /**
-   * Represents a grouping of pages.
-   */
-  @Getter
-  @JsonIgnoreProperties(ignoreUnknown = true)
-  public static class PageIndexes {
-
-    /**
-     * The confidence about the zone of the value extracted. A value from 0 to 1.
-     */
-    @JsonProperty("confidence")
-    private Double confidence;
-
-    /**
-     * The page indexes in the document that are grouped together
-     */
-    @JsonProperty("page_indexes")
-    private List<Integer> pageIndexes;
-
-    @Override
-    public String toString() {
-      return "  :Page indexes: ".concat(
-          pageIndexes.stream().map((index) -> index.toString())
-            .collect(Collectors.joining(", "))
-      );
+  @Override
+  public String toString() {
+    StringBuilder outStr = new StringBuilder();
+    String invoicePageGroupsSummary = "";
+    if (!this.getInvoicePageGroups().isEmpty()) {
+      int[] invoicePageGroupsColSizes = new int[]{74};
+      invoicePageGroupsSummary =
+        String.format("%n%s%n  ", SummaryHelper.lineSeparator(invoicePageGroupsColSizes, "-"))
+          + "| Page Indexes                                                             "
+          + String.format("|%n%s%n  ", SummaryHelper.lineSeparator(invoicePageGroupsColSizes, "="));
+      invoicePageGroupsSummary += SummaryHelper.arrayToString(this.getInvoicePageGroups(), invoicePageGroupsColSizes);
+      invoicePageGroupsSummary += String.format("%n%s", SummaryHelper.lineSeparator(invoicePageGroupsColSizes, "-"));
     }
+    outStr.append(
+        String.format(":Invoice Page Groups: %s%n", invoicePageGroupsSummary)
+    );
+    return SummaryHelper.cleanSummary(outStr.toString());
   }
 }