From fd9241989540e9056d4882376e1b583f5649cd23 Mon Sep 17 00:00:00 2001
From: Thomas Beyer <thomas.beyer@iqser.com>
Date: Mon, 20 Mar 2023 10:01:33 +0100
Subject: [PATCH] RED-4875 - set version of common pdftron logics to newest and
 move PdfTextExtraction to this new repo

---
 ocr-service-v1/ocr-service-server-v1/pom.xml  |  2 +-
 .../v1/server/OcrServiceIntegrationTest.java  |  2 +-
 .../InvisibleElementRemovalServiceTest.java   |  3 +-
 .../v1/server/utils/PdfTextExtraction.java    | 35 -------------------
 4 files changed, 4 insertions(+), 38 deletions(-)
 delete mode 100644 ocr-service-v1/ocr-service-server-v1/src/test/java/com/iqser/red/service/ocr/v1/server/utils/PdfTextExtraction.java

diff --git a/ocr-service-v1/ocr-service-server-v1/pom.xml b/ocr-service-v1/ocr-service-server-v1/pom.xml
index 1854007..44641c5 100644
--- a/ocr-service-v1/ocr-service-server-v1/pom.xml
+++ b/ocr-service-v1/ocr-service-server-v1/pom.xml
@@ -26,7 +26,7 @@
         <dependency>
             <groupId>com.iqser.red.commons</groupId>
             <artifactId>pdftron-logic-commons</artifactId>
-            <version>dev_red4875_a3a2a</version>
+            <version>dev_red4875_e8b89</version>
         </dependency>
 
         <dependency>
diff --git a/ocr-service-v1/ocr-service-server-v1/src/test/java/com/iqser/red/service/ocr/v1/server/OcrServiceIntegrationTest.java b/ocr-service-v1/ocr-service-server-v1/src/test/java/com/iqser/red/service/ocr/v1/server/OcrServiceIntegrationTest.java
index e719877..6d0f5f8 100644
--- a/ocr-service-v1/ocr-service-server-v1/src/test/java/com/iqser/red/service/ocr/v1/server/OcrServiceIntegrationTest.java
+++ b/ocr-service-v1/ocr-service-server-v1/src/test/java/com/iqser/red/service/ocr/v1/server/OcrServiceIntegrationTest.java
@@ -1,7 +1,7 @@
 package com.iqser.red.service.ocr.v1.server;
 
+import static com.iqser.red.pdftronlogic.commons.PdfTextExtraction.extractAllTextFromDocument;
 import static com.iqser.red.service.ocr.v1.server.utils.OsUtils.getTemporaryDirectory;
-import static com.iqser.red.service.ocr.v1.server.utils.PdfTextExtraction.extractAllTextFromDocument;
 import static org.assertj.core.api.Assertions.assertThat;
 
 import java.io.FileInputStream;
diff --git a/ocr-service-v1/ocr-service-server-v1/src/test/java/com/iqser/red/service/ocr/v1/server/service/InvisibleElementRemovalServiceTest.java b/ocr-service-v1/ocr-service-server-v1/src/test/java/com/iqser/red/service/ocr/v1/server/service/InvisibleElementRemovalServiceTest.java
index 39d979e..32d8875 100644
--- a/ocr-service-v1/ocr-service-server-v1/src/test/java/com/iqser/red/service/ocr/v1/server/service/InvisibleElementRemovalServiceTest.java
+++ b/ocr-service-v1/ocr-service-server-v1/src/test/java/com/iqser/red/service/ocr/v1/server/service/InvisibleElementRemovalServiceTest.java
@@ -1,7 +1,7 @@
 package com.iqser.red.service.ocr.v1.server.service;
 
+import static com.iqser.red.pdftronlogic.commons.PdfTextExtraction.extractAllTextFromDocument;
 import static com.iqser.red.service.ocr.v1.server.utils.OsUtils.getTemporaryDirectory;
-import static com.iqser.red.service.ocr.v1.server.utils.PdfTextExtraction.extractAllTextFromDocument;
 import static org.assertj.core.api.AssertionsForClassTypes.assertThat;
 
 import java.io.FileInputStream;
@@ -46,5 +46,6 @@ public class InvisibleElementRemovalServiceTest extends AbstractTest {
             String[] text = extractAllTextFromDocument(fileStream).split("\n");
             assertThat(text).contains("APPENDIX 16 Pathology Report", "Amendment 1", "Page 255 of 260");
         }
+
     }
 }
\ No newline at end of file
diff --git a/ocr-service-v1/ocr-service-server-v1/src/test/java/com/iqser/red/service/ocr/v1/server/utils/PdfTextExtraction.java b/ocr-service-v1/ocr-service-server-v1/src/test/java/com/iqser/red/service/ocr/v1/server/utils/PdfTextExtraction.java
deleted file mode 100644
index c3f195d..0000000
--- a/ocr-service-v1/ocr-service-server-v1/src/test/java/com/iqser/red/service/ocr/v1/server/utils/PdfTextExtraction.java
+++ /dev/null
@@ -1,35 +0,0 @@
-package com.iqser.red.service.ocr.v1.server.utils;
-
-import java.io.IOException;
-import java.io.InputStream;
-import java.util.ArrayList;
-import java.util.List;
-
-import com.pdftron.common.PDFNetException;
-import com.pdftron.pdf.PDFDoc;
-import com.pdftron.pdf.Page;
-import com.pdftron.pdf.PageIterator;
-import com.pdftron.pdf.TextExtractor;
-
-
-public class PdfTextExtraction {
-
-    public static String extractAllTextFromDocument(InputStream fileStream) throws IOException, PDFNetException {
-
-        PDFDoc pdfDoc = new PDFDoc(fileStream);
-        TextExtractor extractor = new TextExtractor();
-        List<String> texts = new ArrayList<>();
-
-        PageIterator iterator = pdfDoc.getPageIterator();
-        while (iterator.hasNext()) {
-            Page page = iterator.next();
-            extractor.begin(page);
-            texts.add(extractor.getAsText());
-        }
-
-        extractor.destroy();
-        pdfDoc.close();
-        return String.join("\n", texts);
-    }
-
-}