Merge branch 'RED-7607-WIP' into 'main'

RED-7607 - Rotating pages leads to lost annotations (RM & DM)

See merge request fforesight/layout-parser!75

.gitlab-ci.yml

@@ -18,4 +18,4 @@ deploy:
   rules:
     - if: $CI_COMMIT_BRANCH == $CI_DEFAULT_BRANCH 
     - if: $CI_COMMIT_BRANCH =~ /^release/
-    - if: $CI_COMMIT_TAG
+    - if: $CI_COMMIT_TAG

README.md

@@ -1 +1,89 @@
+# PDF Layout Parser Micro-Service: layout-parser  
 
+## Introduction
+The layout-parser micro-service is a powerful tool designed to efficiently extract structured information from PDF documents. Written in Java and utilizing Spring Boot 3, Apache PDFBox, and RabbitMQ, this micro-service excels at parsing PDFs and organizing their content into a meaningful and coherent layout structure. Notably, the layout-parser micro-service distinguishes itself by relying solely on advanced algorithms, rather than machine learning techniques.
+
+### Key Steps in the PDF Layout Parsing Process:
+
+* **Text Position Extraction:**  
+The micro-service leverages Apache PDFBox to extract precise text positions for each individual character within the PDF document.
+
+* **Word Segmentation and Text Block Formation:**  
+Employing an array of diverse algorithms, the micro-service initially identifies and segments words, creating distinct text blocks.
+
+* **Text Block Classification:**  
+The segmented text blocks are then subjected to classification algorithms. These algorithms categorize the text blocks based on their content and visual properties, distinguishing between sections, subsections, headlines, paragraphs, images, tables, table cells, headers, and footers.
+
+* **Layout Coherence Establishment:**  
+The classified text blocks are subsequently orchestrated into a cohesive layout structure. This process involves arranging sections, subsections, paragraphs, images, and other elements in a logical and structured manner.
+
+* **Output Generation in Various Formats:**  
+Once the layout structure is established, the micro-service generates output in multiple formats. These formats are designed for seamless integration with downstream micro-services. The supported formats include JSON, XML, and others, ensuring flexibility in downstream data consumption.
+
+### Optional Enhancements:
+
+* **ML-Based Table Extraction:**  
+For enhanced results, users have the option to incorporate machine learning-based table extraction. This feature can be activated by providing ML-generated results as a JSON file, which are then integrated seamlessly into the layout structure.
+
+* **Image Classification using ML:**  
+Additionally, for more accurate image classification, users can optionally feed ML-generated image classification results into the micro-service. Similar to the table extraction option, the micro-service processes the pre-parsed results in JSON format, thus optimizing the accuracy of image content identification.
+
+In conclusion, the layout-parser micro-service is a versatile PDF layout parsing solution crafted entirely around advanced algorithms, without reliance on machine learning. It proficiently extracts text positions, segments content into meaningful blocks, classifies these blocks, arranges them coherently, and outputs structured data for downstream micro-services. Optional integration with ML-generated table extractions and image classifications further enhances its capabilities.
+
+
+
+
+
+
+## Installation
+
+### Prerequisites
+
+Before building and using the layout-parser micro-service, please ensure you have the following software and tools installed:
+
+Java Development Kit (JDK) 17 or later
+Gradle build tool (preinstalled)
+Build and Test
+To build and test the micro-service, follow these steps:
+
+### Clone the Repository:
+
+bash
+```
+git clone ssh://git@git.knecon.com:22222/fforesight/layout-parser.git
+cd layout-parser
+```
+### Build the Project:
+Use the following command to build the project using Gradle:
+
+```
+gradle clean build
+```
+### Run Tests:
+Run the test suite using the following command:
+```
+gradle test
+```
+## Building a Custom Docker Image
+To create a custom Docker image for the layout-parser micro-service, execute the provided script:
+
+### Ensure Docker is Installed:
+Ensure that Docker is installed and running on your system.
+
+### Run the Image Building Script:
+Execute the publish-custom-image script in the project directory:
+
+```
+./publish-custom-image
+```
+## Publishing to Internal Maven Repository
+To publish the layout-parser micro-service to your internal Maven repository, execute the following command:
+
+```
+gradle -Pversion=buildVersion publish
+```
+Replace buildVersion with the desired version number.
+
+## Additional Notes
+Make sure to configure any necessary application properties before deploying the micro-service.
+For advanced usage and configurations, refer to Kilian or Dom or preferably the source code.

layoutparser-service/layoutparser-service-internal-api/build.gradle.kts

@@ -4,3 +4,7 @@ plugins {
 }
 
 description = "layoutparser-service-internal-api"
+
+dependencies {
+    implementation("io.swagger.core.v3:swagger-annotations:2.2.15")
+}

layoutparser-service/layoutparser-service-internal-api/src/main/java/com/knecon/fforesight/service/layoutparser/internal/api/data/redaction/DocumentData.java

@@ -1,5 +1,6 @@
 package com.knecon.fforesight.service.layoutparser.internal.api.data.redaction;
 
+import io.swagger.v3.oas.annotations.media.Schema;
 import lombok.AccessLevel;
 import lombok.AllArgsConstructor;
 import lombok.Builder;
@@ -10,11 +11,16 @@ import lombok.experimental.FieldDefaults;
 @Builder
 @AllArgsConstructor
 @FieldDefaults(makeFinal = true, level = AccessLevel.PRIVATE)
+@Schema(description = "Object containing the complete document layout parsing information. It is split into 4 categories, structure, text, positions and pages: " + "The document tree structure of SemanticNodes such as Section, Paragraph, Headline, etc. " + "The text, which is stored as separate blocks of data. " + "The text positions, which are also stored as separate blocks. The Blocks are equal to the text blocks in length and order. " + "The page information.")
 public class DocumentData {
 
+    @Schema(description = "Contains information about the document's pages.")
     DocumentPage[] documentPages;
+    @Schema(description = "Contains information about the document's text.")
     DocumentTextData[] documentTextData;
+    @Schema(description = "Contains information about the document's text positions.")
     DocumentPositionData[] documentPositions;
+    @Schema(description = "Contains information about the document's semantic structure.")
     DocumentStructure documentStructure;
 
 }

layoutparser-service/layoutparser-service-internal-api/src/main/java/com/knecon/fforesight/service/layoutparser/internal/api/data/redaction/DocumentPage.java

@@ -1,5 +1,6 @@
 package com.knecon.fforesight.service.layoutparser.internal.api.data.redaction;
 
+import io.swagger.v3.oas.annotations.media.Schema;
 import lombok.AccessLevel;
 import lombok.AllArgsConstructor;
 import lombok.Builder;
@@ -12,11 +13,16 @@ import lombok.experimental.FieldDefaults;
 @NoArgsConstructor
 @AllArgsConstructor
 @FieldDefaults(level = AccessLevel.PRIVATE)
+@Schema(description = "Object containing information about the document's pages.")
 public class DocumentPage {
 
+    @Schema(description = "The page number, starting with 1.")
     int number;
+    @Schema(description = "The page height in PDF user units.", example = "792")
     int height;
+    @Schema(description = "The page width in PDF user units.", example = "694")
     int width;
+    @Schema(description = "The page rotation as specified by the PDF.", example = "90", allowableValues = {"0", "90", "180", "270"})
     int rotation;
 
 }

layoutparser-service/layoutparser-service-internal-api/src/main/java/com/knecon/fforesight/service/layoutparser/internal/api/data/redaction/DocumentPositionData.java

@@ -1,5 +1,6 @@
 package com.knecon.fforesight.service.layoutparser.internal.api.data.redaction;
 
+import io.swagger.v3.oas.annotations.media.Schema;
 import lombok.AccessLevel;
 import lombok.AllArgsConstructor;
 import lombok.Builder;
@@ -12,10 +13,14 @@ import lombok.experimental.FieldDefaults;
 @NoArgsConstructor
 @AllArgsConstructor
 @FieldDefaults(level = AccessLevel.PRIVATE)
+@Schema(description = "Object containing text positional information of a specific text block. A document is split into multiple text blocks, which are supposed to be read in order. Every text block can only occur on a single page.")
 public class DocumentPositionData {
 
+    @Schema(description = "Identifier of the text block.")
     Long id;
+    @Schema(description = "For each string coordinate in the search text of the text block, the array contains an entry relating the string coordinate to the position coordinate. This is required due to the text and position coordinates not being equal.")
     int[] stringIdxToPositionIdx;
+    @Schema(description = "The bounding box for each glyph as a rectangle. This matrix is of size (n,4), where n is the number of glyphs in the text block. The second dimension specifies the rectangle with the value x, y, width, height, with x, y specifying the lower left corner. In order to access this information, the stringIdxToPositionIdx array must be used to transform the coordinates.")
     float[][] positions;
 
 }

layoutparser-service/layoutparser-service-internal-api/src/main/java/com/knecon/fforesight/service/layoutparser/internal/api/data/redaction/DocumentStructure.java

@@ -6,6 +6,7 @@ import java.util.List;
 import java.util.Map;
 import java.util.stream.Stream;
 
+import io.swagger.v3.oas.annotations.media.Schema;
 import lombok.AccessLevel;
 import lombok.AllArgsConstructor;
 import lombok.Builder;
@@ -18,11 +19,14 @@ import lombok.experimental.FieldDefaults;
 @NoArgsConstructor
 @AllArgsConstructor
 @FieldDefaults(level = AccessLevel.PRIVATE)
+@Schema(description = "Object containing information about the parsed tree structure of the SemanticNodes, such as Section, Paragraph, Headline etc inside of the document.")
 public class DocumentStructure {
 
+    @Schema(description = "The root EntryData represents the Document.")
     EntryData root;
 
 
+    @Schema(description = "Object containing the extra field names, a table has in its properties field.")
     public static class TableProperties {
 
         public static final String NUMBER_OF_ROWS = "numberOfRows";
@@ -30,6 +34,7 @@ public class DocumentStructure {
 
     }
 
+    @Schema(description = "Object containing the extra field names, an Image has in its properties field.")
     public static class ImageProperties {
 
         public static final String TRANSPARENT = "transparent";
@@ -39,6 +44,7 @@ public class DocumentStructure {
 
     }
 
+    @Schema(description = "Object containing the extra field names, a table cell has in its properties field.")
     public static class TableCellProperties {
 
         public static final String B_BOX = "bBox";
@@ -93,13 +99,20 @@ public class DocumentStructure {
     @NoArgsConstructor
     @AllArgsConstructor
     @FieldDefaults(level = AccessLevel.PRIVATE)
+    @Schema(description = "Object containing information of a SemanticNode and also structuring the layout with children.")
     public static class EntryData {
 
+        @Schema(description = "Type of the semantic node.", allowableValues = {"DOCUMENT", "SECTION", "PARAGRAPH", "HEADLINE", "TABLE", "TABLE_CELL", "HEADER", "FOOTER", "IMAGE"})
         NodeType type;
+        @Schema(description = "Specifies the position in the parsed tree structure.", example = "[1, 0, 2]")
         int[] treeId;
+        @Schema(description = "Specifies the text block IDs associated with this semantic node. The value should be joined with the DocumentTextData/DocumentPositionData. Is empty, if no text block is directly associated with this semantic node. Only Paragraph, Headline, Header or Footer is directly associated with a text block.", example = "[1]")
         Long[] atomicBlockIds;
+        @Schema(description = "Specifies the pages this semantic node appears on. The value should be joined with the PageData.", example = "[1, 2, 3]")
         Long[] pageNumbers;
+        @Schema(description = "Some semantic nodes have additional information, this information is stored in this Map. The extra fields are specified by the Properties subclasses.", example = "For a Table: {\"numberOfRows\": 3, \"numberOfCols\": 4}")
         Map<String, String> properties;
+        @Schema(description = "All child Entries of this Entry.", example = "[1, 2, 3]")
         List<EntryData> children;
 
 

layoutparser-service/layoutparser-service-internal-api/src/main/java/com/knecon/fforesight/service/layoutparser/internal/api/data/redaction/DocumentTextData.java

@@ -1,7 +1,6 @@
 package com.knecon.fforesight.service.layoutparser.internal.api.data.redaction;
 
-
-
+import io.swagger.v3.oas.annotations.media.Schema;
 import lombok.AccessLevel;
 import lombok.AllArgsConstructor;
 import lombok.Builder;
@@ -14,14 +13,22 @@ import lombok.experimental.FieldDefaults;
 @NoArgsConstructor
 @AllArgsConstructor
 @FieldDefaults(level = AccessLevel.PRIVATE)
+@Schema(description = "Object containing text information of a specific text block. A document is split into multiple text blocks, which are supposed to be read in order. Every text block can only occur on a single page.")
 public class DocumentTextData {
 
+    @Schema(description = "Identifier of the text block.")
     Long id;
+    @Schema(description = "The page the text block occurs on.")
     Long page;
+    @Schema(description = "The text the text block.")
     String searchText;
+    @Schema(description = "Each text block is assigned a number on a page, starting from 0.")
     int numberOnPage;
+    @Schema(description = "The text blocks are ordered, this number represents the start of the text block as a string offset.")
     int start;
+    @Schema(description = "The text blocks are ordered, this number represents the end of the text block as a string offset.")
     int end;
+    @Schema(description = "The line breaks in the text of this semantic node in string offsets. They are exclusive end. At the end of each semantic node there is an implicit linebreak.", example = "[5, 10]")
     int[] lineBreaks;
 
 }

layoutparser-service/layoutparser-service-internal-api/src/main/java/com/knecon/fforesight/service/layoutparser/internal/api/data/redaction/SimplifiedSectionText.java

@@ -1,5 +1,6 @@
 package com.knecon.fforesight.service.layoutparser.internal.api.data.redaction;
 
+import io.swagger.v3.oas.annotations.media.Schema;
 import lombok.AllArgsConstructor;
 import lombok.Builder;
 import lombok.Data;
@@ -9,9 +10,12 @@ import lombok.NoArgsConstructor;
 @Builder
 @NoArgsConstructor
 @AllArgsConstructor
+@Schema(description = "Object containing a simplified version, which contains almost exclusively text, of the document structure Section class.")
 public class SimplifiedSectionText {
 
+    @Schema(description = "The number of this Section. This is used to map the simplified section text back to the original Section.")
     private int sectionNumber;
+    @Schema(description = "The text in this Section.")
     private String text;
 
 }

layoutparser-service/layoutparser-service-internal-api/src/main/java/com/knecon/fforesight/service/layoutparser/internal/api/data/redaction/SimplifiedText.java

@@ -3,6 +3,7 @@ package com.knecon.fforesight.service.layoutparser.internal.api.data.redaction;
 import java.util.ArrayList;
 import java.util.List;
 
+import io.swagger.v3.oas.annotations.media.Schema;
 import lombok.AllArgsConstructor;
 import lombok.Builder;
 import lombok.Data;
@@ -12,9 +13,12 @@ import lombok.NoArgsConstructor;
 @Builder
 @NoArgsConstructor
 @AllArgsConstructor
+@Schema(description = "Object containing a simplified version, which contains almost exclusively text, of the document structure.")
 public class SimplifiedText {
 
+    @Schema(description = "Number of pages in the entire document.")
     private int numberOfPages;
+    @Schema(description = "A List of simplified Sections, which contains almost exclusively text.")
     private List<SimplifiedSectionText> sectionTexts = new ArrayList<>();
 
 }

layoutparser-service/layoutparser-service-internal-api/src/main/java/com/knecon/fforesight/service/layoutparser/internal/api/data/taas/ParagraphData.java

@@ -2,20 +2,29 @@ package com.knecon.fforesight.service.layoutparser.internal.api.data.taas;
 
 import java.util.List;
 
+import io.swagger.v3.oas.annotations.media.Schema;
 import lombok.Builder;
 import lombok.Data;
 
 @Data
 @Builder
+@Schema(description = "Object containing information about a Paragraph/Headline/Header/Footer.")
 public class ParagraphData {
 
+    @Schema(description = "The text of this Semantic Node, without any linebreaks.", example = "This is some text.")
     private String text;
+    @Schema(description = "A list of text ranges in string offsets. Every character in any of the ranges is bold.", example = "[0, 15]")
     List<Range> boldTextBoundaries;
+    @Schema(description = "A list of text ranges in string offsets. Every character in any of the ranges is italic.", example = "[0, 15]")
     List<Range> italicTextBoundaries;
+    @Schema(description = "The line breaks in the text of this semantic node in string offsets. They are exclusive end. At the end of each semantic node there is an implicit linebreak.", example = "[5, 10]")
     List<Integer> linebreaks;
+    @Schema(description = "The classification of this Paragraph.", allowableValues = "{paragraph, headline, header, footer}")
     private String classification;
 
+    @Schema(description = "Describes the text orientation of this semantic node. Any semantic node only has a single text orientation.", allowableValues = "{ZERO, QUARTER_CIRCLE, HALF_CIRCLE, THREE_QUARTER_CIRCLE}")
     private String orientation;
+    @Schema(description = "Describes the text direction in degrees of this semantic node. Any semantic node only has a single text direction.", minimum = "0", maximum = "359")
     private int textDirection;
 
 }

layoutparser-service/layoutparser-service-internal-api/src/main/java/com/knecon/fforesight/service/layoutparser/internal/api/data/taas/Range.java

@@ -1,5 +1,8 @@
 package com.knecon.fforesight.service.layoutparser.internal.api.data.taas;
 
+import io.swagger.v3.oas.annotations.media.Schema;
+
+@Schema(description = "Object specifying the start and end offsets of a text range in string offsets.")
 public record Range(int start, int end) {
 
 }

layoutparser-service/layoutparser-service-internal-api/src/main/java/com/knecon/fforesight/service/layoutparser/internal/api/data/taas/ResearchDocumentData.java

@@ -2,6 +2,7 @@ package com.knecon.fforesight.service.layoutparser.internal.api.data.taas;
 
 import java.util.List;
 
+import io.swagger.v3.oas.annotations.media.Schema;
 import lombok.AllArgsConstructor;
 import lombok.Builder;
 import lombok.Data;
@@ -9,8 +10,12 @@ import lombok.Data;
 @Builder
 @Data
 @AllArgsConstructor
+@Schema(description = "Object containing a simplified version of the document structure. This simplified form only knows Paragraphs and Tables. The Paragraph Objects might be a Paragraph, Headline, Header or Footer.")
 public class ResearchDocumentData {
 
+    @Schema(description = "File name of the original uploaded file.")
     String originalFile;
+    @Schema(description = "A List of all paragraphs/headline or table objects, that have been parsed in this document.")
     List<StructureObject> structureObjects;
+
 }

layoutparser-service/layoutparser-service-internal-api/src/main/java/com/knecon/fforesight/service/layoutparser/internal/api/data/taas/RowData.java

@@ -2,14 +2,19 @@ package com.knecon.fforesight.service.layoutparser.internal.api.data.taas;
 
 import java.util.List;
 
+import io.swagger.v3.oas.annotations.media.Schema;
 import lombok.AllArgsConstructor;
 import lombok.Data;
 
 @Data
 @AllArgsConstructor
+@Schema(description = "Object containing information about a Table Row.")
 public class RowData {
 
+    @Schema(description = "Boolean indicating whether this table row is classified as a header row.")
     boolean header;
+    @Schema(description = "A list of Objects containing information about the text in each cell of this row.")
     List<ParagraphData> cellText;
+    @Schema(description = "The bounding box of this StructureObject. Is always exactly 4 values representing x, y, w, h, where x, y specify the lower left corner.")
     float[] bBox;
 }

layoutparser-service/layoutparser-service-internal-api/src/main/java/com/knecon/fforesight/service/layoutparser/internal/api/data/taas/StructureObject.java

@@ -1,5 +1,6 @@
 package com.knecon.fforesight.service.layoutparser.internal.api.data.taas;
 
+import io.swagger.v3.oas.annotations.media.Schema;
 import lombok.AllArgsConstructor;
 import lombok.Builder;
 import lombok.Data;
@@ -7,13 +8,20 @@ import lombok.Data;
 @Data
 @Builder
 @AllArgsConstructor
+@Schema(description = "Object containing information about either a Paragraph/Headline/Header/Footer or a Table.")
 public class StructureObject {
 
+    @Schema(description = "The ID of this StructureObject.")
     Integer structureObjectNumber;
+    @Schema(description = "This value indicates the start of the string offsets in this Object, with respect to the reading order.")
     int page;
+    @Schema(description = "This stringOffset indicates the start of the string offsets in this Object, with respect to the reading order of the entire document. It is equal to the previous' StructureObject stringOffset + its length.")
     int stringOffset;
+    @Schema(description = "The bounding box of this StructureObject. Is always exactly 4 values representing x, y, w, h, where x, y specify the lower left corner.", example = "[100, 100, 50, 50]")
     float[] boundingBox;
+    @Schema(description = "Object containing information about a Paragraph/Headline/Header/Footer. Either this or table is null.")
     ParagraphData paragraph;
+    @Schema(description = "Object containing information about a Table. Either this or paragraph is null.")
     TableData table;
 
 }

layoutparser-service/layoutparser-service-internal-api/src/main/java/com/knecon/fforesight/service/layoutparser/internal/api/data/taas/TableData.java

@@ -2,15 +2,20 @@ package com.knecon.fforesight.service.layoutparser.internal.api.data.taas;
 
 import java.util.List;
 
+import io.swagger.v3.oas.annotations.media.Schema;
 import lombok.AllArgsConstructor;
 import lombok.Data;
 
 @Data
 @AllArgsConstructor
+@Schema(description = "Object containing information about a Table.")
 public class TableData {
 
+    @Schema(description = "A list of Objects containing information about all rows in this table.")
     List<RowData> rowData;
+    @Schema(description = "Number of columns in this table.")
     Integer numberOfCols;
+    @Schema(description = "Number of rows in this table.")
     Integer numberOfRows;
 
 }

layoutparser-service/layoutparser-service-internal-api/src/main/java/com/knecon/fforesight/service/layoutparser/internal/api/queue/LayoutParsingFinishedEvent.java

@@ -2,9 +2,19 @@ package com.knecon.fforesight.service.layoutparser.internal.api.queue;
 
 import java.util.Map;
 
+import io.swagger.v3.oas.annotations.media.Schema;
 import lombok.Builder;
 
 @Builder
-public record LayoutParsingFinishedEvent(Map<String, String> identifier, long duration, int numberOfPages, String message) {
+@Schema(description = "Object containing information about the layout parsing.")
+public record LayoutParsingFinishedEvent(
+        @Schema(description = "General purpose identifier. It is returned exactly the same way it is inserted with the LayoutParsingRequest.")
+        Map<String, String> identifier,//
+        @Schema(description = "The duration of a single layout parsing in ms.")
+        long duration,//
+        @Schema(description = "The number of pages of the parsed document.")
+        int numberOfPages,//
+        @Schema(description = "A general message. It contains some information useful for a developer, like the paths where the files are stored. Not meant to be machine readable.")
+        String message) {
 
 }

layoutparser-service/layoutparser-service-internal-api/src/main/java/com/knecon/fforesight/service/layoutparser/internal/api/queue/LayoutParsingRequest.java

@@ -3,23 +3,42 @@ package com.knecon.fforesight.service.layoutparser.internal.api.queue;
 import java.util.Map;
 import java.util.Optional;
 
+import io.swagger.v3.oas.annotations.media.Schema;
 import lombok.Builder;
 import lombok.NonNull;
 
 @Builder
+@Schema(description = "Object containing all storage paths the service needs to know.")
 public record LayoutParsingRequest(
+        @Schema(description = "Enum specifying the type of layout parsing to be performed.", allowableValues = "{RedactManager, DocuMine, TAAS}")//
         @NonNull LayoutParsingType layoutParsingType,
+
+        @Schema(description = "General purpose identifiers. They are not changed by the service at all and are returned as is in the response queue.")//
         Map<String, String> identifier,
-        @NonNull String originFileStorageId,
-        Optional<String> tablesFileStorageId,
-        Optional<String> imagesFileStorageId,
-        @NonNull String structureFileStorageId,
-        String researchDocumentStorageId,
-        @NonNull String textBlockFileStorageId,
-        @NonNull String positionBlockFileStorageId,
-        @NonNull String pageFileStorageId,
-        @NonNull String simplifiedTextStorageId,
-        @NonNull String viewerDocumentStorageId,
+
+        @Schema(description = "Path to the original PDF file.")//
+        @NonNull String originFileStorageId,//
+        @Schema(description = "Optional Path to the table extraction file.")//
+        Optional<String> tablesFileStorageId,//
+        @Schema(description = "Optional Path to the image classification file.")//
+        Optional<String> imagesFileStorageId,//
+
+        @Schema(description = "Path where the Document Structure File will be stored.")//
+        @NonNull String structureFileStorageId,//
+        @Schema(description = "Path where the Research Data File will be stored.")//
+        String researchDocumentStorageId,//
+        @Schema(description = "Path where the Document Text File will be stored.")//
+        @NonNull String textBlockFileStorageId,//
+        @Schema(description = "Path where the Document Positions File will be stored.")//
+        @NonNull String positionBlockFileStorageId,//
+        @Schema(description = "Path where the Document Pages File will be stored.")//
+        @NonNull String pageFileStorageId,//
+        @Schema(description = "Path where the Simplified Text File will be stored.")//
+        @NonNull String simplifiedTextStorageId,//
+        @Schema(description = "Path where the Viewer Document PDF will be stored.")//
+        @NonNull String viewerDocumentStorageId,//
+        @Deprecated//
+        @Schema(description = "Path where the Section Grid will be stored.")//
         @NonNull String sectionGridStorageId) {
 
 }

layoutparser-service/layoutparser-service-processor/build.gradle.kts

@@ -6,21 +6,21 @@ plugins {
 description = "layoutparser-service-processor"
 
 val jacksonVersion = "2.15.2"
-val pdfBoxVersion = "3.0.0-RC1"
+val pdfBoxVersion = "3.0.0"
 
 dependencies {
     implementation(project(":layoutparser-service-internal-api"))
 
-    implementation("com.iqser.red.service:persistence-service-shared-api-v1:2.138.0") {
+    implementation("com.iqser.red.service:persistence-service-shared-api-v1:2.144.0") {
         exclude("org.springframework.boot", "spring-boot-starter-security")
         exclude("org.springframework.boot", "spring-boot-starter-validation")
     }
     implementation("com.knecon.fforesight:tenant-commons:0.10.0")
-    implementation("com.iqser.red.commons:storage-commons:2.36.0")
+    implementation("com.iqser.red.commons:storage-commons:2.40.0")
 
     implementation("org.apache.pdfbox:pdfbox:${pdfBoxVersion}")
     implementation("org.apache.pdfbox:pdfbox-tools:${pdfBoxVersion}")
     implementation("com.fasterxml.jackson.module:jackson-module-afterburner:${jacksonVersion}")
     implementation("com.fasterxml.jackson.datatype:jackson-datatype-jsr310:${jacksonVersion}")
-    implementation("org.springframework.boot:spring-boot-starter-web:3.1.2")
+    implementation("org.springframework.boot:spring-boot-starter-web:3.1.3")
 }

layoutparser-service/layoutparser-service-processor/src/main/java/com/knecon/fforesight/service/layoutparser/processor/LayoutParsingPipeline.java

@@ -10,13 +10,13 @@ import java.util.HashMap;
 import java.util.List;
 import java.util.Map;
 
-import com.knecon.fforesight.service.layoutparser.processor.utils.MarkedContentUtils;
 import org.apache.pdfbox.pdmodel.PDDocument;
 import org.apache.pdfbox.pdmodel.PDPage;
 import org.apache.pdfbox.pdmodel.common.PDRectangle;
 import org.apache.pdfbox.pdmodel.documentinterchange.markedcontent.PDMarkedContent;
 import org.springframework.stereotype.Service;
 
+import com.knecon.fforesight.service.layoutparser.internal.api.data.redaction.NodeType;
 import com.knecon.fforesight.service.layoutparser.internal.api.queue.LayoutParsingFinishedEvent;
 import com.knecon.fforesight.service.layoutparser.internal.api.queue.LayoutParsingRequest;
 import com.knecon.fforesight.service.layoutparser.internal.api.queue.LayoutParsingType;
@@ -50,6 +50,7 @@ import com.knecon.fforesight.service.layoutparser.processor.services.mapper.Docu
 import com.knecon.fforesight.service.layoutparser.processor.services.mapper.TaasDocumentDataMapper;
 import com.knecon.fforesight.service.layoutparser.processor.services.parsing.PDFLinesTextStripper;
 import com.knecon.fforesight.service.layoutparser.processor.services.visualization.ViewerDocumentService;
+import com.knecon.fforesight.service.layoutparser.processor.utils.MarkedContentUtils;
 
 import lombok.RequiredArgsConstructor;
 import lombok.SneakyThrows;
@@ -103,7 +104,7 @@ public class LayoutParsingPipeline {
             layoutParsingStorageService.storeSimplifiedText(layoutParsingRequest, simplifiedSectionTextService.toSimplifiedText(documentGraph));
 
             try (var out = new ByteArrayOutputStream()) {
-                viewerDocumentService.createViewerDocument(originDocument, documentGraph, out);
+                viewerDocumentService.createViewerDocument(originDocument, documentGraph, out, false);
                 layoutParsingStorageService.storeViewerDocument(layoutParsingRequest, out);
             }
 
@@ -116,16 +117,45 @@ public class LayoutParsingPipeline {
                     .identifier(layoutParsingRequest.identifier())
                     .numberOfPages(numberOfPages)
                     .duration(System.currentTimeMillis() - start)
-                    .message(format("Layout parsing is finished and files have been saved with Ids:\n Structure: %s\nText: %s\nPositions: %s\nPageData: %s",
+                    .message(format("""
+                                    Layout parsing has finished in %.02f s.
+                                    identifiers: %s
+                                    %s
+                                    Files have been saved with Ids:
+                                    Structure: %s
+                                    Text: %s
+                                    Positions: %s
+                                    PageData: %s
+                                    Simplified Text: %s
+                                    Viewer Doc: %s""",
+                            ((float) (System.currentTimeMillis() - start)) / 1000,
+                            layoutParsingRequest.identifier(),
+                            buildSemanticNodeCountMessage(numberOfPages, documentGraph.buildSemanticNodeCounts()),
                             layoutParsingRequest.structureFileStorageId(),
                             layoutParsingRequest.textBlockFileStorageId(),
                             layoutParsingRequest.positionBlockFileStorageId(),
-                            layoutParsingRequest.pageFileStorageId()))
+                            layoutParsingRequest.pageFileStorageId(),
+                            layoutParsingRequest.simplifiedTextStorageId(),
+                            layoutParsingRequest.viewerDocumentStorageId()))
                     .build();
         }
     }
 
 
+    private String buildSemanticNodeCountMessage(int numberOfPages, Map<NodeType, Long> semanticNodeCounts) {
+
+        return String.format("%d pages with %d sections, %d headlines, %d paragraphs, %d tables with %d cells, %d headers, and %d footers parsed",
+                numberOfPages,
+                semanticNodeCounts.get(NodeType.SECTION),
+                semanticNodeCounts.get(NodeType.HEADLINE),
+                semanticNodeCounts.get(NodeType.PARAGRAPH),
+                semanticNodeCounts.get(NodeType.TABLE),
+                semanticNodeCounts.get(NodeType.TABLE_CELL),
+                semanticNodeCounts.get(NodeType.HEADER),
+                semanticNodeCounts.get(NodeType.FOOTER));
+    }
+
+
     @SneakyThrows
     public ClassificationDocument parseLayout(LayoutParsingType layoutParsingType,
                                               PDDocument originDocument,
@@ -166,12 +196,9 @@ public class LayoutParsingPipeline {
                     stripper.getMaxCharHeight());
 
             ClassificationPage classificationPage = switch (layoutParsingType) {
-                case REDACT_MANAGER ->
-                        redactManagerBlockificationService.blockify(stripper.getTextPositionSequences(), cleanRulings.getHorizontal(), cleanRulings.getVertical());
-                case TAAS ->
-                        taasBlockificationService.blockify(stripper.getTextPositionSequences(), cleanRulings.getHorizontal(), cleanRulings.getVertical());
-                case DOCUMINE ->
-                        docuMineBlockificationService.blockify(stripper.getTextPositionSequences(), cleanRulings.getHorizontal(), cleanRulings.getVertical());
+                case REDACT_MANAGER -> redactManagerBlockificationService.blockify(stripper.getTextPositionSequences(), cleanRulings.getHorizontal(), cleanRulings.getVertical());
+                case TAAS -> taasBlockificationService.blockify(stripper.getTextPositionSequences(), cleanRulings.getHorizontal(), cleanRulings.getVertical());
+                case DOCUMINE -> docuMineBlockificationService.blockify(stripper.getTextPositionSequences(), cleanRulings.getHorizontal(), cleanRulings.getVertical());
             };
             classificationPage.setCleanRulings(cleanRulings);
             classificationPage.setRotation(rotation);
@@ -211,18 +238,20 @@ public class LayoutParsingPipeline {
     }
 
 
-    private Map<String, Rectangle2D> convertMarkedContents(List<PDMarkedContent> pdMarkedContents) {
-        Map<String, Rectangle2D> markedContentBboxes = new HashMap<>();
+    private Map<String, List<Rectangle2D>> convertMarkedContents(List<PDMarkedContent> pdMarkedContents) {
+
+        Map<String, List<Rectangle2D>> markedContentBboxes = new HashMap<>();
         markedContentBboxes.put(MarkedContentUtils.HEADER, MarkedContentUtils.getMarkedContentBboxPerLine(pdMarkedContents, MarkedContentUtils.HEADER));
         markedContentBboxes.put(MarkedContentUtils.FOOTER, MarkedContentUtils.getMarkedContentBboxPerLine(pdMarkedContents, MarkedContentUtils.FOOTER));
         return markedContentBboxes;
     }
 
+
     private void increaseDocumentStatistics(ClassificationPage classificationPage, ClassificationDocument document) {
 
-        if (!classificationPage.isLandscape()) {
+//        if (!classificationPage.isLandscape()) {
             document.getFontSizeCounter().addAll(classificationPage.getFontSizeCounter().getCountPerValue());
-        }
+//        }
         document.getFontCounter().addAll(classificationPage.getFontCounter().getCountPerValue());
         document.getTextHeightCounter().addAll(classificationPage.getTextHeightCounter().getCountPerValue());
         document.getFontStyleCounter().addAll(classificationPage.getFontStyleCounter().getCountPerValue());

layoutparser-service/layoutparser-service-processor/src/main/java/com/knecon/fforesight/service/layoutparser/processor/LayoutParsingStorageService.java

@@ -13,7 +13,6 @@ import java.nio.file.StandardOpenOption;
 
 import org.apache.commons.io.IOUtils;
 import org.apache.pdfbox.Loader;
-import org.apache.pdfbox.io.MemoryUsageSetting;
 import org.apache.pdfbox.pdmodel.PDDocument;
 import org.springframework.stereotype.Service;
 
@@ -49,7 +48,7 @@ public class LayoutParsingStorageService {
                 IOUtils.copy(originDocumentInputStream, tempFileOutputStream);
                 originDocumentInputStream.close();
             }
-            return Loader.loadPDF(tempFile, MemoryUsageSetting.setupMixed(67108864L));
+            return Loader.loadPDF(tempFile);
         }
     }
 

layoutparser-service/layoutparser-service-processor/src/main/java/com/knecon/fforesight/service/layoutparser/processor/model/AbstractPageBlock.java

@@ -72,9 +72,30 @@ public abstract class AbstractPageBlock {
     }
 
 
-    public boolean intersectsY(AbstractPageBlock atc) {
+    public boolean intersectsY(AbstractPageBlock apb) {
 
-        return this.minY <= atc.getMaxY() && this.maxY >= atc.getMinY();
+        return this.minY <= apb.getMaxY() && this.maxY >= apb.getMinY();
     }
 
+
+    public boolean almostIntersects(AbstractPageBlock apb, float yThreshold, float xThreshold) {
+
+        return this.almostIntersectsX(apb, xThreshold) && this.almostIntersectsY(apb, yThreshold);
+    }
+
+
+    private boolean almostIntersectsY(AbstractPageBlock apb, float threshold) {
+
+        return this.minY - threshold <= apb.getMaxY() && this.maxY + threshold >= apb.getMinY();
+    }
+
+
+    private boolean almostIntersectsX(AbstractPageBlock apb, float threshold) {
+
+        return this.minX - threshold <= apb.getMaxX() && this.maxX + threshold >= apb.getMinX();
+    }
+
+
+    public abstract boolean isEmpty();
+
 }

layoutparser-service/layoutparser-service-processor/src/main/java/com/knecon/fforesight/service/layoutparser/processor/model/ClassificationPage.java

@@ -42,6 +42,6 @@ public class ClassificationPage {
 
     CleanRulings cleanRulings;
 
-    private Map<String, Rectangle2D> markedContentBboxPerType = new HashMap<>();
+    private Map<String, List<Rectangle2D>> markedContentBboxPerType = new HashMap<>();
 
 }

layoutparser-service/layoutparser-service-processor/src/main/java/com/knecon/fforesight/service/layoutparser/processor/model/ClassificationSection.java

@@ -2,6 +2,7 @@ package com.knecon.fforesight.service.layoutparser.processor.model;
 
 import java.util.ArrayList;
 import java.util.List;
+import java.util.stream.Collectors;
 
 import com.knecon.fforesight.service.layoutparser.processor.model.image.ClassifiedImage;
 import com.knecon.fforesight.service.layoutparser.processor.model.table.TablePageBlock;
@@ -29,4 +30,10 @@ public class ClassificationSection {
         return tables;
     }
 
+
+    public List<AbstractPageBlock> getNonEmptyPageBlocks() {
+
+        return pageBlocks.stream().filter(pageBlock -> !pageBlock.isEmpty()).collect(Collectors.toList());
+    }
+
 }

layoutparser-service/layoutparser-service-processor/src/main/java/com/knecon/fforesight/service/layoutparser/processor/model/graph/nodes/Document.java

@@ -100,6 +100,11 @@ public class Document implements GenericSemanticNode {
     }
 
 
+    public Map<NodeType, Long> buildSemanticNodeCounts() {
+
+        return streamAllSubNodes().collect(Collectors.groupingBy(SemanticNode::getType, Collectors.counting()));
+    }
+
     @Override
     public String toString() {
 

layoutparser-service/layoutparser-service-processor/src/main/java/com/knecon/fforesight/service/layoutparser/processor/model/graph/nodes/TableCell.java

@@ -76,16 +76,22 @@ public class TableCell implements GenericSemanticNode {
         }
 
         if (textBlock == null) {
-            textBlock = streamAllSubNodes().filter(SemanticNode::isLeaf).map(SemanticNode::getLeafTextBlock).collect(new TextBlockCollector());
+            textBlock = buildTextBlock();
         }
         return textBlock;
     }
 
 
+    private TextBlock buildTextBlock() {
+
+        return streamAllSubNodes().filter(SemanticNode::isLeaf).map(SemanticNode::getLeafTextBlock).collect(new TextBlockCollector());
+    }
+
+
     @Override
     public String toString() {
 
-        return treeId + ": " + NodeType.TABLE_CELL + ": " + this.getTextBlock().buildSummary();
+        return treeId + ": " + NodeType.TABLE_CELL + ": " + this.buildTextBlock().buildSummary();
     }
 
 }

layoutparser-service/layoutparser-service-processor/src/main/java/com/knecon/fforesight/service/layoutparser/processor/model/table/TablePageBlock.java

@@ -42,6 +42,12 @@ public class TablePageBlock extends AbstractPageBlock {
     }
 
 
+    @Override
+    public boolean isEmpty() {
+
+        return getColCount() == 0 || getRowCount() == 0;
+    }
+
     public List<List<Cell>> getRows() {
 
         if (rows == null) {
@@ -304,6 +310,8 @@ public class TablePageBlock extends AbstractPageBlock {
     }
 
 
+
+
     public String getTextAsHtml() {
 
         StringBuilder sb = new StringBuilder();

layoutparser-service/layoutparser-service-processor/src/main/java/com/knecon/fforesight/service/layoutparser/processor/model/text/TextPageBlock.java

@@ -365,4 +365,11 @@ public class TextPageBlock extends AbstractPageBlock {
 
     }
 
+
+    @Override
+    public boolean isEmpty() {
+
+        return sequences.isEmpty();
+    }
+
 }

layoutparser-service/layoutparser-service-processor/src/main/java/com/knecon/fforesight/service/layoutparser/processor/services/BodyTextFrameService.java

@@ -1,8 +1,8 @@
 package com.knecon.fforesight.service.layoutparser.processor.services;
 
+import java.util.Comparator;
 import java.util.List;
 
-import com.knecon.fforesight.service.layoutparser.processor.utils.MarkedContentUtils;
 import org.springframework.stereotype.Service;
 
 import com.iqser.red.service.persistence.service.v1.api.shared.model.redactionlog.Point;
@@ -13,72 +13,70 @@ import com.knecon.fforesight.service.layoutparser.processor.model.Classification
 import com.knecon.fforesight.service.layoutparser.processor.model.ClassificationPage;
 import com.knecon.fforesight.service.layoutparser.processor.model.FloatFrequencyCounter;
 import com.knecon.fforesight.service.layoutparser.processor.model.table.Cell;
+import com.knecon.fforesight.service.layoutparser.processor.model.table.Ruling;
 import com.knecon.fforesight.service.layoutparser.processor.model.table.TablePageBlock;
 import com.knecon.fforesight.service.layoutparser.processor.model.text.TextPageBlock;
+import com.knecon.fforesight.service.layoutparser.processor.utils.MarkedContentUtils;
 import com.knecon.fforesight.service.layoutparser.processor.utils.PositionUtils;
 
 @Service
 public class BodyTextFrameService {
 
+    private static final float RULING_HEIGHT_THRESHOLD = 0.15f; // multiplied with page height. Header/Footer Rulings must be within that border of the page.
+    private static final float RULING_WIDTH_THRESHOLD = 0.75f; // multiplied with page width. Header/Footer Rulings must be at least that wide.
 
     public void setBodyTextFrames(ClassificationDocument classificationDocument, LayoutParsingType layoutParsingType) {
 
         Rectangle bodyTextFrame = calculateBodyTextFrame(classificationDocument.getPages(), classificationDocument.getFontSizeCounter(), false, layoutParsingType);
         Rectangle landscapeBodyTextFrame = calculateBodyTextFrame(classificationDocument.getPages(), classificationDocument.getFontSizeCounter(), true, layoutParsingType);
         for (ClassificationPage page : classificationDocument.getPages()) {
+//            var updatedBodyTextFrame = getBodyTextFrameFromRulings(page, bodyTextFrame, landscapeBodyTextFrame);
             setBodyTextFrameAdjustedToPage(page, bodyTextFrame, landscapeBodyTextFrame);
         }
     }
 
 
-/*
-    private Rectangle calculateBodyTextFrameByRulings(List<ClassificationPage> pages) {
+    private Rectangle getBodyTextFrameFromRulings(ClassificationPage page, Rectangle bodyTextFrame, Rectangle landscapeBodyTextFrame) {
 
-        Map<ClassificationPage, List<Ruling>> potentialHeaderRulingsPerPage = new HashMap<>();
-        Map<ClassificationPage, List<Ruling>> potentialFooterRulingsPerPage = new HashMap<>();
-
-        for (var page : pages) {
-            potentialHeaderRulingsPerPage.put(page,
-                    page.getCleanRulings()
-                            .getHorizontal()
-                            .stream()
-                            .filter(ruling -> ruling.getY1() > page.getPageHeight() * 0.8)
-                            .filter(ruling -> ruling.getWidth() > 0.6 * page.getPageWidth())
-                            .toList());
-            potentialFooterRulingsPerPage.put(page,
-                    page.getCleanRulings()
-                            .getHorizontal()
-                            .stream()
-                            .filter(ruling -> ruling.getY1() < page.getPageHeight() * 0.2)
-                            .filter(ruling -> ruling.getWidth() > 0.6 * page.getPageWidth())
-                            .toList());
+        List<Ruling> potentialFooterRulings = getPotentialFooterRulings(page);
+        List<Ruling> potentialHeaderRulings = getPotentialHeaderRulings(page);
+        var x = bodyTextFrame.getTopLeft().getX();
+        var y = bodyTextFrame.getTopLeft().getY();
+        var w = bodyTextFrame.getWidth();
+        var h = bodyTextFrame.getHeight();
+        if (!potentialFooterRulings.isEmpty()) {
+            h = y + h - potentialFooterRulings.get(0).getTop();
+            y = potentialFooterRulings.get(0).getTop();
         }
+        if (!potentialHeaderRulings.isEmpty()) {
+            h = potentialHeaderRulings.get(0).getBottom() - bodyTextFrame.getTopLeft().getY();
+        }
+        return new Rectangle(new Point(x, y), w, h, page.getPageNumber());
+    }
 
-        Optional<Ruling> headerRuling = potentialHeaderRulingsPerPage.values()
+
+    private List<Ruling> getPotentialFooterRulings(ClassificationPage page) {
+
+        return page.getCleanRulings()
+                .getHorizontal()
                 .stream()
-                .flatMap(Collection::stream)
-                .filter(ruling -> potentialHeaderRulingsPerPage.values()
-                        .stream()
-                        .filter(rulingsPerPage -> rulingsPerPage.stream().anyMatch(ruling::almostMatches))
-                        .count() > pages.size() * RULING_THRESHOLD_FACTOR)
-                .min(Comparator.comparingDouble(Ruling::getY1));
+                .filter(ruling -> ruling.getY1() < page.getPageHeight() * RULING_HEIGHT_THRESHOLD)
+                .filter(ruling -> ruling.getWidth() > RULING_WIDTH_THRESHOLD * page.getPageWidth())
+                .sorted(Comparator.comparingDouble(Ruling::getTop))
+                .toList();
+    }
 
-        Optional<Ruling> footerRuling = potentialFooterRulingsPerPage.values()
-                .stream()
-                .flatMap(Collection::stream)
-                .filter(ruling -> potentialHeaderRulingsPerPage.values()
-                        .stream()
-                        .filter(rulingsPerPage -> rulingsPerPage.stream().anyMatch(ruling::almostMatches))
-                        .count() > pages.size() * RULING_THRESHOLD_FACTOR)
-                .max(Comparator.comparingDouble(Ruling::getY1));
 
-        double maxY = headerRuling.isPresent() ? headerRuling.get().y1 : pages.stream().mapToDouble(ClassificationPage::getPageHeight).max().orElse(Double.MAX_VALUE);
-        double minY = footerRuling.map(ruling -> ruling.y1).orElse(0F);
-        double maxX = pages.stream().mapToDouble(ClassificationPage::getPageWidth).max().orElse(Double.MAX_VALUE);
+    private List<Ruling> getPotentialHeaderRulings(ClassificationPage page) {
 
-        return new Rectangle(new Point((float) maxX, (float) maxY), (float) 0, (float) minY, -1);
+        return page.getCleanRulings()
+                .getHorizontal()
+                .stream()
+                .filter(ruling -> ruling.getY1() > page.getPageHeight() * (1 - RULING_HEIGHT_THRESHOLD))
+                .filter(ruling -> ruling.getWidth() > RULING_WIDTH_THRESHOLD * page.getPageWidth())
+                .sorted(Comparator.comparingDouble(Ruling::getBottom).reversed())
+                .toList();
     }
-*/
 
 
     /**
@@ -129,10 +127,10 @@ public class BodyTextFrameService {
      * @param landscape               Calculate for landscape or portrait
      * @return Rectangle of the text frame
      */
-    private Rectangle calculateBodyTextFrame(List<ClassificationPage> pages,
-                                             FloatFrequencyCounter documentFontSizeCounter,
-                                             boolean landscape,
-                                             LayoutParsingType layoutParsingType) {
+    protected Rectangle calculateBodyTextFrame(List<ClassificationPage> pages,
+                                               FloatFrequencyCounter documentFontSizeCounter,
+                                               boolean landscape,
+                                               LayoutParsingType layoutParsingType) {
 
         float approximateHeaderLineCount;
         if (layoutParsingType.equals(LayoutParsingType.TAAS)) {

layoutparser-service/layoutparser-service-processor/src/main/java/com/knecon/fforesight/service/layoutparser/processor/services/PageContentExtractor.java

@@ -1,7 +1,6 @@
 package com.knecon.fforesight.service.layoutparser.processor.services;
 
 import java.io.IOException;
-import java.io.InputStream;
 import java.util.Collection;
 import java.util.LinkedList;
 import java.util.List;
@@ -26,35 +25,34 @@ public class PageContentExtractor {
     public List<PageContents> getSortedPageContents(String filename) throws IOException {
 
         List<PageContents> textPositionSequencesPerPage = new LinkedList<>();
-        try (InputStream inputStream = new ClassPathResource(filename).getInputStream()) {
+        ClassPathResource pdfResource = new ClassPathResource(filename);
 
-            try (PDDocument pdDocument = Loader.loadPDF(inputStream)) {
+        try (PDDocument pdDocument = Loader.loadPDF(pdfResource.getFile())) {
 
-                for (int pageNumber = 1; pageNumber < pdDocument.getNumberOfPages() + 1; pageNumber++) {
+            for (int pageNumber = 1; pageNumber < pdDocument.getNumberOfPages() + 1; pageNumber++) {
 
-                    PDFLinesTextStripper stripper = new PDFLinesTextStripper();
-                    PDPage pdPage = pdDocument.getPage(pageNumber - 1);
-                    stripper.setPageNumber(pageNumber);
-                    stripper.setSortByPosition(true);
-                    stripper.setStartPage(pageNumber);
-                    stripper.setEndPage(pageNumber);
-                    stripper.setPdpage(pdPage);
-                    stripper.getText(pdDocument);
+                PDFLinesTextStripper stripper = new PDFLinesTextStripper();
+                PDPage pdPage = pdDocument.getPage(pageNumber - 1);
+                stripper.setPageNumber(pageNumber);
+                stripper.setSortByPosition(true);
+                stripper.setStartPage(pageNumber);
+                stripper.setEndPage(pageNumber);
+                stripper.setPdpage(pdPage);
+                stripper.getText(pdDocument);
 
-                    Map<Float, List<TextPositionSequence>> sortedTextPositionSequencesPerDir = stripper.getTextPositionSequences()
-                            .stream()
-                            .collect(Collectors.groupingBy(textPositionSequence -> textPositionSequence.getDir().getDegrees()));
+                Map<Float, List<TextPositionSequence>> sortedTextPositionSequencesPerDir = stripper.getTextPositionSequences()
+                        .stream()
+                        .collect(Collectors.groupingBy(textPositionSequence -> textPositionSequence.getDir().getDegrees()));
 
-                    var sortedTextPositionSequences = sortByDirAccordingToPageRotation(sortedTextPositionSequencesPerDir, pdPage.getRotation());
+                var sortedTextPositionSequences = sortByDirAccordingToPageRotation(sortedTextPositionSequencesPerDir, pdPage.getRotation());
 
-                    textPositionSequencesPerPage.add(new PageContents(sortedTextPositionSequences,
-                            RectangleTransformations.toRectangle2D(pdPage.getCropBox()),
-                            RectangleTransformations.toRectangle2D(pdPage.getMediaBox()),
-                            stripper.getRulings()));
-                }
+                textPositionSequencesPerPage.add(new PageContents(sortedTextPositionSequences,
+                        RectangleTransformations.toRectangle2D(pdPage.getCropBox()),
+                        RectangleTransformations.toRectangle2D(pdPage.getMediaBox()),
+                        stripper.getRulings()));
             }
         }
-
+    
         return textPositionSequencesPerPage;
     }
 

layoutparser-service/layoutparser-service-processor/src/main/java/com/knecon/fforesight/service/layoutparser/processor/services/blockification/TaasBlockificationService.java

@@ -1,11 +1,18 @@
 package com.knecon.fforesight.service.layoutparser.processor.services.blockification;
 
+
+// TODO: figure out, why this fails the build
+// import static com.knecon.fforesight.service.layoutparser.processor.services.factory.SearchTextWithTextPositionFactory.HEIGHT_PADDING;
+
 import java.util.ArrayList;
+import java.util.HashSet;
 import java.util.Iterator;
 import java.util.LinkedList;
 import java.util.List;
+import java.util.Set;
 import java.util.regex.Matcher;
 import java.util.regex.Pattern;
+import java.util.stream.Stream;
 
 import org.springframework.stereotype.Service;
 
@@ -22,8 +29,12 @@ import com.knecon.fforesight.service.layoutparser.processor.utils.RulingTextDirA
 public class TaasBlockificationService {
 
     private static final float THRESHOLD = 1f;
-    private static final float Y_GAP_SPLIT_HEIGHT_MODIFIER = 1.25f;
+    private static final float Y_GAP_SPLIT_HEIGHT_MODIFIER = 1.25f; // multiplied with text height
+    private static final float INTERSECTS_Y_THRESHOLD = 4;// 2 * HEIGHT_PADDING // This is exactly 2 times our position height padding. This is required to find boxes that are visually intersecting.
     private static final int X_GAP_SPLIT_CONSTANT = 50;
+    public static final int X_ALIGNMENT_THRESHOLD = 1;
+    public static final int SMALL_Y_GAP_THRESHOLD = 5;
+    public static final int NEGATIVE_X_GAP_THRESHOLD = -5;
 
 
     /**
@@ -39,14 +50,28 @@ public class TaasBlockificationService {
     public ClassificationPage blockify(List<TextPositionSequence> textPositions, List<Ruling> horizontalRulingLines, List<Ruling> verticalRulingLines) {
 
         List<TextPageBlock> classificationTextBlocks = constructFineGranularTextPageBlocks(textPositions, horizontalRulingLines, verticalRulingLines);
-
-        classificationTextBlocks = mergeFineGranularTextPageBlocks(classificationTextBlocks);
+        classificationTextBlocks = mergeTextPageBlocksAligningX(classificationTextBlocks);
+        classificationTextBlocks = mergeIntersectingTextBlocksUntilConvergence(classificationTextBlocks);
 
         return new ClassificationPage(new ArrayList<>(classificationTextBlocks.stream().map(classificationTextBlock -> (AbstractPageBlock) classificationTextBlock).toList()));
     }
 
 
-    private List<TextPageBlock> mergeFineGranularTextPageBlocks(List<TextPageBlock> classificationTextBlocks) {
+    private List<TextPageBlock> mergeIntersectingTextBlocksUntilConvergence(List<TextPageBlock> classificationTextBlocks) {
+
+        int currentSize = classificationTextBlocks.size();
+        while (true) {
+            classificationTextBlocks = mergeTextPageBlocksAlmostIntersecting(classificationTextBlocks);
+            if (classificationTextBlocks.size() == currentSize) {
+                break;
+            }
+            currentSize = classificationTextBlocks.size();
+        }
+        return classificationTextBlocks;
+    }
+
+
+    private List<TextPageBlock> mergeTextPageBlocksAligningX(List<TextPageBlock> classificationTextBlocks) {
 
         if (classificationTextBlocks.isEmpty()) {
             return new ArrayList<>();
@@ -61,8 +86,8 @@ public class TaasBlockificationService {
                 previousTextBlock = currentTextBlock;
                 continue;
             }
-            boolean alignsXRight = Math.abs(currentTextBlock.getPdfMaxX() - previousTextBlock.getPdfMaxX()) < 1;
-            boolean smallYGap = Math.abs(currentTextBlock.getPdfMaxY() - previousTextBlock.getPdfMinY()) < 5;
+            boolean alignsXRight = Math.abs(currentTextBlock.getPdfMaxX() - previousTextBlock.getPdfMaxX()) < X_ALIGNMENT_THRESHOLD;
+            boolean smallYGap = Math.abs(currentTextBlock.getPdfMaxY() - previousTextBlock.getPdfMinY()) < SMALL_Y_GAP_THRESHOLD;
             if (alignsXRight && smallYGap) {
                 currentTextBlocksToMerge.add(currentTextBlock);
             } else {
@@ -76,6 +101,23 @@ public class TaasBlockificationService {
     }
 
 
+    private List<TextPageBlock> mergeTextPageBlocksAlmostIntersecting(List<TextPageBlock> textPageBlocks) {
+
+        Set<TextPageBlock> alreadyMerged = new HashSet<>();
+        List<List<TextPageBlock>> textBlocksToMerge = new LinkedList<>();
+        for (TextPageBlock textPageBlock : textPageBlocks) {
+            if (alreadyMerged.contains(textPageBlock)) {
+                continue;
+            }
+            alreadyMerged.add(textPageBlock);
+            textBlocksToMerge.add(Stream.concat(Stream.of(textPageBlock),
+                            textPageBlocks.stream().filter(textPageBlock2 -> textPageBlock.almostIntersects(textPageBlock2, INTERSECTS_Y_THRESHOLD, 0) && !alreadyMerged.contains(textPageBlock2)).peek(alreadyMerged::add))
+                    .toList());
+        }
+        return textBlocksToMerge.stream().map(TextPageBlock::merge).toList();
+    }
+
+
     private void assignOrientations(List<TextPageBlock> classificationTextBlocks) {
 
         Iterator<TextPageBlock> itty = classificationTextBlocks.iterator();
@@ -149,7 +191,7 @@ public class TaasBlockificationService {
             boolean yGap = prev != null && word.getMinYDirAdj() - maxY > Math.min(word.getHeight(), prev.getHeight()) * Y_GAP_SPLIT_HEIGHT_MODIFIER;
             boolean sameLine = prev != null && equalsWithThreshold(prev.getMinYDirAdj(), word.getMinYDirAdj());
             boolean positiveXGapInline = prev != null && maxX + X_GAP_SPLIT_CONSTANT < word.getMinXDirAdj() && sameLine;
-            boolean negativeXGap = prev != null && word.getMinXDirAdj() - minX < -5;
+            boolean negativeXGap = prev != null && word.getMinXDirAdj() - minX < NEGATIVE_X_GAP_THRESHOLD;
             boolean startFromTop = prev != null && word.getMinYDirAdj() < prev.getMinYDirAdj() - prev.getTextHeight();
             boolean newLineAfterSplit = prev != null && word.getMinYDirAdj() != prev.getMinYDirAdj() && wasSplitted && splitX1 != word.getMinXDirAdj();
             boolean splitByRuling = isSplitByRuling(minX, minY, maxX, maxY, word, horizontalRulingLines, verticalRulingLines);
@@ -164,7 +206,7 @@ public class TaasBlockificationService {
 
                 Orientation prevOrientation = null;
                 if (!classificationTextBlocks.isEmpty()) {
-                    prevOrientation = classificationTextBlocks.get(classificationTextBlocks.size() - 1).getOrientation();
+                    prevOrientation = classificationTextBlocks.get(classificationTextBlocks.size() - X_ALIGNMENT_THRESHOLD).getOrientation();
                 }
 
                 TextPageBlock classificationTextBlock = TextPageBlock.fromTextPositionSequences(wordClusterToCombine);

layoutparser-service/layoutparser-service-processor/src/main/java/com/knecon/fforesight/service/layoutparser/processor/services/factory/DocumentGraphFactory.java

@@ -64,7 +64,7 @@ public class DocumentGraphFactory {
 
     private void addSections(ClassificationDocument document, Context context) {
 
-        document.getSections().forEach(section -> SectionNodeFactory.addSection(null, section.getPageBlocks(), section.getImages(), context));
+        document.getSections().forEach(section -> SectionNodeFactory.addSection(null, section.getNonEmptyPageBlocks(), section.getImages(), context));
     }
 
 

layoutparser-service/layoutparser-service-processor/src/main/java/com/knecon/fforesight/service/layoutparser/processor/services/parsing/LegacyPDFStreamEngine.java

@@ -92,28 +92,28 @@ public class LegacyPDFStreamEngine extends PDFStreamEngine {
      */
     LegacyPDFStreamEngine() throws IOException {
 
-        addOperator(new BeginText());
-        addOperator(new Concatenate());
-        addOperator(new DrawObject()); // special text version
-        addOperator(new EndText());
-        addOperator(new SetGraphicsStateParameters());
-        addOperator(new Save());
-        addOperator(new Restore());
-        addOperator(new NextLine());
-        addOperator(new SetCharSpacing());
-        addOperator(new MoveText());
-        addOperator(new MoveTextSetLeading());
-        addOperator(new SetFontAndSize());
-        addOperator(new ShowText());
-        addOperator(new ShowTextAdjusted());
-        addOperator(new SetTextLeading());
-        addOperator(new SetMatrix());
-        addOperator(new SetTextRenderingMode());
-        addOperator(new SetTextRise());
-        addOperator(new SetWordSpacing());
-        addOperator(new SetTextHorizontalScaling());
-        addOperator(new ShowTextLine());
-        addOperator(new ShowTextLineAndSpace());
+        addOperator(new BeginText(this));
+        addOperator(new Concatenate(this));
+        addOperator(new DrawObject(this)); // special text version
+        addOperator(new EndText(this));
+        addOperator(new SetGraphicsStateParameters(this));
+        addOperator(new Save(this));
+        addOperator(new Restore(this));
+        addOperator(new NextLine(this));
+        addOperator(new SetCharSpacing(this));
+        addOperator(new MoveText(this));
+        addOperator(new MoveTextSetLeading(this));
+        addOperator(new SetFontAndSize(this));
+        addOperator(new ShowText(this));
+        addOperator(new ShowTextAdjusted(this));
+        addOperator(new SetTextLeading(this));
+        addOperator(new SetMatrix(this));
+        addOperator(new SetTextRenderingMode(this));
+        addOperator(new SetTextRise(this));
+        addOperator(new SetWordSpacing(this));
+        addOperator(new SetTextHorizontalScaling(this));
+        addOperator(new ShowTextLine(this));
+        addOperator(new ShowTextLineAndSpace(this));
 
         // load additional glyph list for Unicode mapping
         String path = "/org/apache/pdfbox/resources/glyphlist/additional.txt";

layoutparser-service/layoutparser-service-processor/src/main/java/com/knecon/fforesight/service/layoutparser/processor/services/parsing/PDFLinesTextStripper.java

@@ -52,32 +52,31 @@ public class PDFLinesTextStripper extends PDFTextStripper {
     public PDFLinesTextStripper() throws IOException {
 
         super();
-        this.addOperator(new SetStrokingColorSpace());
-        this.addOperator(new SetNonStrokingColorSpace());
-        this.addOperator(new SetLineDashPattern());
-        this.addOperator(new SetStrokingDeviceGrayColor());
-        this.addOperator(new SetNonStrokingDeviceGrayColor());
-        this.addOperator(new SetFlatness());
-        this.addOperator(new SetLineJoinStyle());
-        this.addOperator(new SetLineCapStyle());
-        this.addOperator(new SetStrokingDeviceCMYKColor());
-        this.addOperator(new SetNonStrokingDeviceCMYKColor());
-        this.addOperator(new SetLineMiterLimit());
-        this.addOperator(new SetStrokingDeviceRGBColor());
-        this.addOperator(new SetNonStrokingDeviceRGBColor());
-        this.addOperator(new SetRenderingIntent());
-        this.addOperator(new SetStrokingColor());
-        this.addOperator(new SetNonStrokingColor());
-        this.addOperator(new SetStrokingColorN());
-        this.addOperator(new SetNonStrokingColorN());
-        this.addOperator(new SetFontAndSize());
-        this.addOperator(new SetLineWidth());
+        this.addOperator(new SetStrokingColorSpace(this));
+        this.addOperator(new SetNonStrokingColorSpace(this));
+        this.addOperator(new SetLineDashPattern(this));
+        this.addOperator(new SetStrokingDeviceGrayColor(this));
+        this.addOperator(new SetNonStrokingDeviceGrayColor(this));
+        this.addOperator(new SetFlatness(this));
+        this.addOperator(new SetLineJoinStyle(this));
+        this.addOperator(new SetLineCapStyle(this));
+        this.addOperator(new SetStrokingDeviceCMYKColor(this));
+        this.addOperator(new SetNonStrokingDeviceCMYKColor(this));
+        this.addOperator(new SetLineMiterLimit(this));
+        this.addOperator(new SetStrokingDeviceRGBColor(this));
+        this.addOperator(new SetNonStrokingDeviceRGBColor(this));
+        this.addOperator(new SetRenderingIntent(this));
+        this.addOperator(new SetStrokingColor(this));
+        this.addOperator(new SetNonStrokingColor(this));
+        this.addOperator(new SetStrokingColorN(this));
+        this.addOperator(new SetNonStrokingColorN(this));
+        this.addOperator(new SetFontAndSize(this));
+        this.addOperator(new SetLineWidth(this));
 
 
-        addOperator(new BeginMarkedContentSequenceWithProperties());
-//        addOperator(new BeginMarkedContentSequence());
-        addOperator(new EndMarkedContentSequence());
-
+        addOperator(new BeginMarkedContentSequenceWithProperties(this));
+//        addOperator(new BeginMarkedContentSequence(this));
+        addOperator(new EndMarkedContentSequence(this));
     }
 
 

layoutparser-service/layoutparser-service-processor/src/main/java/com/knecon/fforesight/service/layoutparser/processor/services/parsing/PDFTextStripper.java

@@ -43,7 +43,8 @@ import org.apache.pdfbox.pdmodel.interactive.documentnavigation.outline.PDOutlin
 import org.apache.pdfbox.pdmodel.interactive.pagenavigation.PDThreadBead;
 import org.apache.pdfbox.text.TextPosition;
 import org.apache.pdfbox.text.TextPositionComparator;
-import org.apache.pdfbox.util.QuickSort;
+
+import com.knecon.fforesight.service.layoutparser.processor.utils.QuickSort;
 
 /**
  * This is just a copy except i only adjusted lines 594-607 cause this is a bug in Pdfbox.
@@ -1710,7 +1711,7 @@ public class PDFTextStripper extends LegacyPDFStreamEngine {
         int numberOfStrings = line.size();
         for (int i = 0; i < numberOfStrings; i++) {
             WordWithTextPositions word = line.get(i);
-            word.getTextPositions().sort(Comparator.comparing(TextPosition::getX));
+            word.getTextPositions().sort(Comparator.comparing(TextPosition::getXDirAdj));
             writeString(word.getText(), word.getTextPositions(), isParagraphEnd && i == numberOfStrings - 1);
             if (i < numberOfStrings - 1) {
                 writeWordSeparator();

layoutparser-service/layoutparser-service-processor/src/main/java/com/knecon/fforesight/service/layoutparser/processor/services/visualization/ViewerDocumentService.java

@@ -16,6 +16,7 @@ import org.apache.pdfbox.pdmodel.PDPageContentStream;
 import org.apache.pdfbox.pdmodel.PDResources;
 import org.apache.pdfbox.pdmodel.font.PDFont;
 import org.apache.pdfbox.pdmodel.font.PDType1Font;
+import org.apache.pdfbox.pdmodel.font.Standard14Fonts;
 import org.apache.pdfbox.pdmodel.graphics.optionalcontent.PDOptionalContentGroup;
 import org.apache.pdfbox.pdmodel.graphics.optionalcontent.PDOptionalContentProperties;
 import org.apache.pdfbox.pdmodel.graphics.state.PDExtendedGraphicsState;
@@ -39,8 +40,8 @@ import lombok.extern.slf4j.Slf4j;
 @RequiredArgsConstructor
 public class ViewerDocumentService {
 
-    private static final String layerName = "Layout grid";
 
+    private static final String LAYER_NAME = "Layout grid";
     private static final int FONT_SIZE = 10;
     public static final float LINE_WIDTH = 1f;
 
@@ -48,15 +49,14 @@ public class ViewerDocumentService {
 
 
     @SneakyThrows
-    public void createViewerDocument(PDDocument pdDocument, Document document, OutputStream outputStream) {
+    public void createViewerDocument(PDDocument pdDocument, Document document, OutputStream outputStream, boolean layerVisibilityDefaultValue) {
 
-        log.info("Start Viewer Document Creation");
         LayoutGrid layoutGrid = layoutGridService.createLayoutGrid(document);
         // PDDocument.save() is very slow, since it actually traverses the entire pdf and writes a new one.
         // If we collect all COSDictionaries we changed and tell it explicitly to only add the changed ones by using saveIncremental it's very fast.
         Set<COSDictionary> dictionariesToUpdate = new HashSet<>();
-        PDOptionalContentGroup layer = addLayerToDocument(pdDocument, dictionariesToUpdate);
-        PDFont font = PDType1Font.HELVETICA;
+        PDOptionalContentGroup layer = addLayerToDocument(pdDocument, dictionariesToUpdate, layerVisibilityDefaultValue);
+        PDFont font = new PDType1Font(Standard14Fonts.FontName.HELVETICA);
 
         for (int pageNumber = 0; pageNumber < pdDocument.getNumberOfPages(); pageNumber++) {
             PDPage pdPage = pdDocument.getPage(pageNumber);
@@ -119,8 +119,8 @@ public class ViewerDocumentService {
             dictionariesToUpdate.add(pdPage.getResources().getCOSObject());
         }
         dictionariesToUpdate.add(pdDocument.getDocumentInformation().getCOSObject());
+//        dictionariesToUpdate.add(pdDocument.getDocument().getTrailer());
         pdDocument.saveIncremental(outputStream, dictionariesToUpdate);
-        log.info("Saved Viewer Document");
     }
 
 
@@ -145,7 +145,7 @@ public class ViewerDocumentService {
     }
 
 
-    private static PDOptionalContentGroup addLayerToDocument(PDDocument pdDocument, Set<COSDictionary> dictionariesToUpdate) {
+    private static PDOptionalContentGroup addLayerToDocument(PDDocument pdDocument, Set<COSDictionary> dictionariesToUpdate, boolean layerVisibilityDefaultValue) {
 
         PDDocumentCatalog catalog = pdDocument.getDocumentCatalog();
         PDOptionalContentProperties ocprops = catalog.getOCProperties();
@@ -154,13 +154,13 @@ public class ViewerDocumentService {
             catalog.setOCProperties(ocprops);
         }
         PDOptionalContentGroup layer = null;
-        if (ocprops.hasGroup(layerName)) {
-            layer = ocprops.getGroup(layerName);
+        if (ocprops.hasGroup(LAYER_NAME)) {
+            layer = ocprops.getGroup(LAYER_NAME);
         } else {
-            layer = new PDOptionalContentGroup(layerName);
+            layer = new PDOptionalContentGroup(LAYER_NAME);
             ocprops.addGroup(layer);
         }
-        ocprops.setGroupEnabled(layer, false);
+        ocprops.setGroupEnabled(layer, layerVisibilityDefaultValue);
         dictionariesToUpdate.add(catalog.getCOSObject());
         return layer;
     }

layoutparser-service/layoutparser-service-processor/src/main/java/com/knecon/fforesight/service/layoutparser/processor/utils/MarkedContentUtils.java

@@ -9,6 +9,7 @@ import org.apache.pdfbox.text.TextPosition;
 
 import java.awt.geom.Rectangle2D;
 import java.util.Collection;
+import java.util.Collections;
 import java.util.List;
 import java.util.Map;
 import java.util.stream.Collectors;
@@ -19,10 +20,10 @@ public class MarkedContentUtils {
     public static final String HEADER = "Header";
     public static final String FOOTER = "Footer";
 
-    public Rectangle2D getMarkedContentBboxPerLine(List<PDMarkedContent> markedContents, String subtype) {
+    public List<Rectangle2D> getMarkedContentBboxPerLine(List<PDMarkedContent> markedContents, String subtype) {
 
         if (markedContents == null) {
-            return null;
+            return Collections.emptyList();
         }
 
         var markedContentByYPosition = markedContents.stream()
@@ -37,19 +38,19 @@ public class MarkedContentUtils {
                 .collect(Collectors.groupingBy(TextPosition::getY));
 
         if (markedContentByYPosition.isEmpty()) {
-            return null;
+            return Collections.emptyList();
         }
 
-        return RectangleTransformations.rectangle2DBBox(markedContentByYPosition.values().stream()
+        return markedContentByYPosition.values().stream()
                 .map(textPositions -> new TextPositionSequence(textPositions.stream()
                         .toList(), 0, true)
                         .getRectangle())
-                .map(t -> new Rectangle2D.Float(t.getTopLeft().getX(), t.getTopLeft().getY() - Math.abs(t.getHeight()), t.getWidth(), Math.abs(t.getHeight()))).collect(Collectors.toList()));
+                .map(t -> new Rectangle2D.Float(t.getTopLeft().getX(), t.getTopLeft().getY() - Math.abs(t.getHeight()), t.getWidth(), Math.abs(t.getHeight()))).collect(Collectors.toList());
     }
 
 
-    public boolean intersects(TextPageBlock textBlock, Map<String, Rectangle2D> markedContentBboxPerType, String type) {
-        return markedContentBboxPerType.get(type) != null && markedContentBboxPerType.get(type).intersects(textBlock.getPdfMinX(), textBlock.getPdfMinY(), textBlock.getWidth(), textBlock.getHeight());
+    public boolean intersects(TextPageBlock textBlock, Map<String, List<Rectangle2D>> markedContentBboxPerType, String type) {
+        return markedContentBboxPerType.get(type) != null && markedContentBboxPerType.get(type).stream().anyMatch(rectangle -> rectangle.intersects(textBlock.getPdfMinX(), textBlock.getPdfMinY(), textBlock.getWidth(), textBlock.getHeight()));
     }
 
 }

layoutparser-service/layoutparser-service-processor/src/main/java/com/knecon/fforesight/service/layoutparser/processor/utils/PdfVisualisationUtility.java

@@ -12,6 +12,7 @@ import org.apache.pdfbox.pdmodel.PDDocument;
 import org.apache.pdfbox.pdmodel.PDPage;
 import org.apache.pdfbox.pdmodel.PDPageContentStream;
 import org.apache.pdfbox.pdmodel.font.PDType1Font;
+import org.apache.pdfbox.pdmodel.font.Standard14Fonts;
 
 import com.knecon.fforesight.service.layoutparser.internal.api.data.redaction.NodeType;
 import com.knecon.fforesight.service.layoutparser.processor.model.graph.DocumentTree;
@@ -71,7 +72,7 @@ public class PdfVisualisationUtility {
 
         contentStream.beginText();
         contentStream.newLineAtOffset((float) location.getX(), (float) location.getY());
-        contentStream.setFont(PDType1Font.HELVETICA, 10);
+        contentStream.setFont(new PDType1Font(Standard14Fonts.FontName.HELVETICA), 10);
         contentStream.showText(string);
         contentStream.endText();
         contentStream.close();

layoutparser-service/layoutparser-service-processor/src/main/java/com/knecon/fforesight/service/layoutparser/processor/utils/PositionUtils.java

@@ -19,9 +19,10 @@ public final class PositionUtils {
 
         double threshold = textBlock.getMostPopularWordHeight() * 3;
 
-        if (textBlock.getPdfMinX() + threshold > btf.getTopLeft().getX() && textBlock.getPdfMaxX() - threshold < btf.getTopLeft()
-                .getX() + btf.getWidth() && textBlock.getPdfMinY() + threshold > btf.getTopLeft().getY() && textBlock.getPdfMaxY() - threshold < btf.getTopLeft()
-                .getY() + btf.getHeight()) {
+        if (textBlock.getPdfMinX() + threshold > btf.getTopLeft().getX()
+                && textBlock.getPdfMaxX() - threshold < btf.getTopLeft().getX() + btf.getWidth()
+                && textBlock.getPdfMinY() + threshold > btf.getTopLeft().getY()
+                && textBlock.getPdfMaxY() - threshold < btf.getTopLeft().getY() + btf.getHeight()) {
             return true;
         } else {
             return false;

layoutparser-service/layoutparser-service-processor/src/main/java/com/knecon/fforesight/service/layoutparser/processor/utils/TextPositionOperations.java

@@ -3,7 +3,6 @@ package com.knecon.fforesight.service.layoutparser.processor.utils;
 import java.util.List;
 import java.util.stream.Collectors;
 
-import org.apache.pdfbox.util.QuickSort;
 
 import com.knecon.fforesight.service.layoutparser.processor.model.text.TextPageBlock;
 import com.knecon.fforesight.service.layoutparser.processor.model.text.TextPositionSequence;

layoutparser-service/layoutparser-service-server/build.gradle.kts

@@ -3,7 +3,7 @@ import org.springframework.boot.gradle.tasks.bundling.BootBuildImage
 plugins {
     application
     id("com.knecon.fforesight.java-conventions")
-    id("org.springframework.boot") version "3.1.2"
+    id("org.springframework.boot") version "3.1.3"
     id("io.spring.dependency-management") version "1.1.3"
     id("org.sonarqube") version "4.3.0.3225"
     id("io.freefair.lombok") version "8.2.2"
@@ -13,30 +13,30 @@ plugins {
 description = "layoutparser-service-server"
 
 val jacksonVersion = "2.15.2"
-val pdfBoxVersion = "3.0.0-RC1"
+val pdfBoxVersion = "3.0.0"
 
 dependencies {
     implementation(project(":layoutparser-service-processor"))
     implementation(project(":layoutparser-service-internal-api"))
 
-    implementation("com.iqser.red.commons:storage-commons:2.36.0")
+    implementation("com.iqser.red.commons:storage-commons:2.40.0")
     implementation("com.knecon.fforesight:tenant-commons:0.10.0")
-    implementation("org.springframework.boot:spring-boot-starter-actuator:3.1.2")
-    implementation("com.amazonaws:aws-java-sdk-s3:1.12.533")
-    implementation("org.springframework.boot:spring-boot-starter-amqp:3.1.2")
+    implementation("org.springframework.boot:spring-boot-starter-actuator:3.1.3")
+    implementation("com.amazonaws:aws-java-sdk-s3:1.12.536")
+    implementation("org.springframework.boot:spring-boot-starter-amqp:3.1.3")
     implementation("org.springframework.cloud:spring-cloud-starter-openfeign:4.0.4")
 
     // for integration testing only
     testImplementation(project(":layoutparser-service-internal-api"))
 
-    testImplementation("org.springframework.boot:spring-boot-starter-amqp:3.1.2")
-    testImplementation("com.iqser.red.service:persistence-service-shared-api-v1:2.138.0")
+    testImplementation("org.springframework.boot:spring-boot-starter-amqp:3.1.3")
+    testImplementation("com.iqser.red.service:persistence-service-shared-api-v1:2.144.0")
     testImplementation("com.iqser.red.commons:jackson-commons:1.3.0")
     testImplementation("com.fasterxml.jackson.module:jackson-module-afterburner:${jacksonVersion}")
     testImplementation("com.fasterxml.jackson.datatype:jackson-datatype-jsr310:${jacksonVersion}")
     testImplementation("org.apache.pdfbox:pdfbox:${pdfBoxVersion}")
     testImplementation("org.apache.pdfbox:pdfbox-tools:${pdfBoxVersion}")
-    testImplementation("org.springframework.boot:spring-boot-starter-test:3.1.2")
+    testImplementation("org.springframework.boot:spring-boot-starter-test:3.1.3")
 }
 
 /*

layoutparser-service/layoutparser-service-server/src/main/java/com/knecon/fforesight/service/layoutparser/server/queue/MessageHandler.java

@@ -1,5 +1,7 @@
 package com.knecon.fforesight.service.layoutparser.server.queue;
 
+import java.util.Arrays;
+
 import org.springframework.amqp.AmqpRejectAndDontRequeueException;
 import org.springframework.amqp.core.Message;
 import org.springframework.amqp.rabbit.annotation.RabbitHandler;
@@ -45,12 +47,12 @@ public class MessageHandler {
         }
         LayoutParsingFinishedEvent layoutParsingFinishedEvent = layoutParsingPipeline.parseLayoutAndSaveFilesToStorage(layoutParsingRequest);
         sendLayoutParsingFinishedEvent(layoutParsingFinishedEvent);
-        log.info("Layout parsing finished {} in {} ms", layoutParsingRequest.identifier(), layoutParsingFinishedEvent.duration());
     }
 
 
     public void sendLayoutParsingFinishedEvent(LayoutParsingFinishedEvent layoutParsingFinishedEvent) {
 
+        Arrays.stream(layoutParsingFinishedEvent.message().split("\n")).forEach(log::info);
         rabbitTemplate.convertAndSend(LayoutParsingQueueNames.LAYOUT_PARSING_FINISHED_EVENT_QUEUE, layoutParsingFinishedEvent);
     }
 

layoutparser-service/layoutparser-service-server/src/test/java/com/knecon/fforesight/service/layoutparser/server/BdrJsonBuildTest.java

@@ -4,10 +4,8 @@ import static org.assertj.core.api.AssertionsForClassTypes.assertThat;
 
 import java.awt.Color;
 import java.io.File;
-import java.io.FileInputStream;
 import java.io.FileOutputStream;
 import java.io.IOException;
-import java.io.InputStream;
 import java.nio.file.Files;
 import java.nio.file.Path;
 import java.nio.file.Paths;
@@ -46,15 +44,13 @@ public class BdrJsonBuildTest extends AbstractTest {
 
 
     @SneakyThrows
-    protected Document buildGraph(File filename) {
+    protected Document buildGraph(File file) {
 
-        try (InputStream inputStream = new FileInputStream(filename)) {
-            try (PDDocument pdDocument = Loader.loadPDF(inputStream)) {
-                return DocumentGraphFactory.buildDocumentGraph(layoutParsingPipeline.parseLayout(LayoutParsingType.TAAS,
-                        pdDocument,
-                        new ImageServiceResponse(),
-                        new TableServiceResponse()));
-            }
+        try (PDDocument pdDocument = Loader.loadPDF(file)) {
+            return DocumentGraphFactory.buildDocumentGraph(layoutParsingPipeline.parseLayout(LayoutParsingType.TAAS,
+                    pdDocument,
+                    new ImageServiceResponse(),
+                    new TableServiceResponse()));
         }
     }
 
@@ -114,10 +110,7 @@ public class BdrJsonBuildTest extends AbstractTest {
 
     private static void visualizeSemanticNodes(File file, File resultingFileName, Document document, TextBlock textBlock) throws IOException {
 
-        try (var fileStream = new FileInputStream(file);//
-             PDDocument pdDocument = Loader.loadPDF(fileStream);//
-             var outputStream = new FileOutputStream(resultingFileName)//
-        ) {
+        try (PDDocument pdDocument = Loader.loadPDF(file); var outputStream = new FileOutputStream(resultingFileName)) {
             PdfDraw.drawDocumentGraph(pdDocument, document);
             PdfDraw.drawTextBlock(pdDocument, textBlock, PdfDraw.Options.builder().stroke(true).strokeWidth(0.1f).strokeColor(Color.YELLOW).build());
             pdDocument.save(outputStream);

layoutparser-service/layoutparser-service-server/src/test/java/com/knecon/fforesight/service/layoutparser/server/HeadlinesGoldStandardIntegrationTest.java

@@ -96,7 +96,7 @@ public class HeadlinesGoldStandardIntegrationTest {
         goldStandardLog.getRedactionLogEntry().forEach(e -> goldStandardHeadlines.add(new Headline(e.getPositions().get(0).getPage(), e.getValue())));
 
         Document documentGraph = DocumentGraphFactory.buildDocumentGraph(layoutParsingPipeline.parseLayout(LayoutParsingType.REDACT_MANAGER,
-                Loader.loadPDF(pdfFileResource.getInputStream()),
+                Loader.loadPDF(pdfFileResource.getFile()),
                 new ImageServiceResponse(),
                 new TableServiceResponse()));
 

layoutparser-service/layoutparser-service-server/src/test/java/com/knecon/fforesight/service/layoutparser/server/LayoutparserEnd2EndTest.java

@@ -0,0 +1,34 @@
+package com.knecon.fforesight.service.layoutparser.server;
+
+import java.util.Arrays;
+
+import org.junit.jupiter.api.Test;
+import org.springframework.beans.factory.annotation.Autowired;
+
+import com.knecon.fforesight.service.layoutparser.internal.api.queue.LayoutParsingFinishedEvent;
+import com.knecon.fforesight.service.layoutparser.internal.api.queue.LayoutParsingRequest;
+import com.knecon.fforesight.service.layoutparser.internal.api.queue.LayoutParsingType;
+import com.knecon.fforesight.service.layoutparser.processor.LayoutParsingPipeline;
+import com.knecon.fforesight.service.layoutparser.server.utils.AbstractTest;
+
+import lombok.SneakyThrows;
+import lombok.extern.slf4j.Slf4j;
+
+@Slf4j
+public class LayoutparserEnd2EndTest extends AbstractTest {
+
+    @Autowired
+    private LayoutParsingPipeline layoutParsingPipeline;
+
+
+    @Test
+    @SneakyThrows
+    public void testLayoutParserEndToEnd() {
+
+        prepareStorage("files/bdr/btd_19_053_1905391.pdf");
+        LayoutParsingRequest layoutParsingRequest = buildDefaultLayoutParsingRequest(LayoutParsingType.TAAS);
+        LayoutParsingFinishedEvent finishedEvent = layoutParsingPipeline.parseLayoutAndSaveFilesToStorage(layoutParsingRequest);
+        Arrays.stream(finishedEvent.message().split("\n")).forEach(log::info);
+    }
+
+}

layoutparser-service/layoutparser-service-server/src/test/java/com/knecon/fforesight/service/layoutparser/server/graph/DocumentDataTests.java

@@ -12,10 +12,11 @@ import org.springframework.core.io.ClassPathResource;
 import com.iqser.red.commons.jackson.ObjectMapperFactory;
 import com.knecon.fforesight.service.layoutparser.internal.api.data.redaction.DocumentData;
 import com.knecon.fforesight.service.layoutparser.processor.services.mapper.DocumentDataMapper;
+import com.knecon.fforesight.service.layoutparser.server.utils.BuildDocumentTest;
 
 import lombok.SneakyThrows;
 
-public class DocumentDataTests extends BuildDocumentGraphTest{
+public class DocumentDataTests extends BuildDocumentTest {
     @Test
     @SneakyThrows
     public void createDocumentDataForAllFiles() {

layoutparser-service/layoutparser-service-server/src/test/java/com/knecon/fforesight/service/layoutparser/server/graph/DocumentGraphJsonWritingTest.java

@@ -1,7 +1,6 @@
 package com.knecon.fforesight.service.layoutparser.server.graph;
 
 import java.io.File;
-import java.io.FileInputStream;
 import java.io.FileOutputStream;
 import java.nio.file.Files;
 import java.nio.file.Path;
@@ -20,10 +19,11 @@ import com.knecon.fforesight.service.layoutparser.processor.python_api.model.ima
 import com.knecon.fforesight.service.layoutparser.processor.python_api.model.table.TableServiceResponse;
 import com.knecon.fforesight.service.layoutparser.processor.services.factory.DocumentGraphFactory;
 import com.knecon.fforesight.service.layoutparser.processor.services.mapper.DocumentDataMapper;
+import com.knecon.fforesight.service.layoutparser.server.utils.BuildDocumentTest;
 
 import lombok.SneakyThrows;
 
-public class DocumentGraphJsonWritingTest extends BuildDocumentGraphTest {
+public class DocumentGraphJsonWritingTest extends BuildDocumentTest {
 
     @Test
     @SneakyThrows
@@ -56,7 +56,7 @@ public class DocumentGraphJsonWritingTest extends BuildDocumentGraphTest {
     private void writeJsons(Path filename) {
 
         Document documentGraph = DocumentGraphFactory.buildDocumentGraph(layoutParsingPipeline.parseLayout(LayoutParsingType.REDACT_MANAGER,
-                Loader.loadPDF(new FileInputStream(filename.toFile())),
+                Loader.loadPDF(filename.toFile()),
                 new ImageServiceResponse(),
                 new TableServiceResponse()));
 

layoutparser-service/layoutparser-service-server/src/test/java/com/knecon/fforesight/service/layoutparser/server/graph/DocumentGraphMappingTest.java

@@ -16,11 +16,12 @@ import com.knecon.fforesight.service.layoutparser.processor.model.graph.nodes.Ta
 import com.knecon.fforesight.service.layoutparser.processor.services.mapper.DocumentDataMapper;
 import com.knecon.fforesight.service.layoutparser.processor.services.mapper.DocumentGraphMapper;
 import com.knecon.fforesight.service.layoutparser.processor.services.mapper.PropertiesMapper;
+import com.knecon.fforesight.service.layoutparser.server.utils.BuildDocumentTest;
 import com.knecon.fforesight.tenantcommons.TenantContext;
 
 import lombok.SneakyThrows;
 
-public class DocumentGraphMappingTest extends BuildDocumentGraphTest {
+public class DocumentGraphMappingTest extends BuildDocumentTest {
 
     @Test
     @SneakyThrows

layoutparser-service/layoutparser-service-server/src/test/java/com/knecon/fforesight/service/layoutparser/server/graph/DocumentGraphVisualizationTest.java

@@ -13,13 +13,14 @@ import org.springframework.core.io.ClassPathResource;
 
 import com.knecon.fforesight.service.layoutparser.processor.model.graph.nodes.Document;
 import com.knecon.fforesight.service.layoutparser.processor.model.graph.textblock.TextBlock;
+import com.knecon.fforesight.service.layoutparser.server.utils.BuildDocumentTest;
 import com.knecon.fforesight.service.layoutparser.server.utils.visualizations.PdfDraw;
 
 import lombok.SneakyThrows;
 import lombok.extern.slf4j.Slf4j;
 
 @Slf4j
-public class DocumentGraphVisualizationTest extends BuildDocumentGraphTest {
+public class DocumentGraphVisualizationTest extends BuildDocumentTest {
 
     @Test
     @SneakyThrows
@@ -66,9 +67,7 @@ public class DocumentGraphVisualizationTest extends BuildDocumentGraphTest {
         File tmpFile = new File("/tmp/" + Path.of(filename).getFileName().toString() + "_SEMANTIC_NODES_BBOX.pdf");
         ClassPathResource fileResource = new ClassPathResource(filename);
 
-        try (var fileStream = fileResource.getInputStream();//
-             PDDocument pdDocument = Loader.loadPDF(fileStream)//
-        ) {
+        try (PDDocument pdDocument = Loader.loadPDF(fileResource.getFile())) {
             log.info("drawing document");
             PdfDraw.drawDocumentGraph(pdDocument, documentGraph);
             PdfDraw.drawTextBlock(pdDocument, textBlock, PdfDraw.Options.builder().stroke(true).strokeWidth(0.1f).strokeColor(Color.YELLOW).build());

layoutparser-service/layoutparser-service-server/src/test/java/com/knecon/fforesight/service/layoutparser/server/graph/ExtractMarkedContentTest.java

@@ -0,0 +1,203 @@
+package com.knecon.fforesight.service.layoutparser.server.graph;
+
+import java.io.File;
+import java.io.IOException;
+import java.util.Collections;
+import java.util.HashMap;
+import java.util.List;
+import java.util.Map;
+
+import lombok.SneakyThrows;
+import org.apache.pdfbox.Loader;
+import org.apache.pdfbox.cos.COSArray;
+import org.apache.pdfbox.cos.COSBase;
+import org.apache.pdfbox.cos.COSDictionary;
+import org.apache.pdfbox.cos.COSNumber;
+import org.apache.pdfbox.pdmodel.PDDocument;
+import org.apache.pdfbox.pdmodel.PDPage;
+import org.apache.pdfbox.pdmodel.documentinterchange.logicalstructure.PDStructureElement;
+import org.apache.pdfbox.pdmodel.documentinterchange.logicalstructure.PDStructureNode;
+import org.apache.pdfbox.pdmodel.documentinterchange.markedcontent.PDMarkedContent;
+import org.apache.pdfbox.text.PDFMarkedContentExtractor;
+import org.apache.pdfbox.text.TextPosition;
+import org.junit.jupiter.api.BeforeEach;
+import org.junit.jupiter.api.Disabled;
+import org.junit.jupiter.api.Test;
+import org.springframework.core.io.ClassPathResource;
+
+/**
+ * @author mkl
+ */
+@Disabled
+public class ExtractMarkedContentTest {
+    final static File RESULT_FOLDER = new File("target/test-outputs", "extract");
+
+    @BeforeEach
+    public void setUpBeforeClass() throws Exception {
+        RESULT_FOLDER.mkdirs();
+    }
+
+    /**
+     * <a href="https://stackoverflow.com/questions/54956720/how-to-replace-a-space-with-a-word-while-extract-the-data-from-pdf-using-pdfbox">
+     * How to replace a space with a word while extract the data from PDF using PDFBox
+     * </a>
+     * <br/>
+     * <a href="https://drive.google.com/open?id=10ZkdPlGWzMJeahwnQPzE6V7s09d1nvwq">
+     * test.pdf
+     * </a> as "testWPhromma.pdf"
+     * <p>
+     * This test shows how to, in principle, extract tagged text.
+     * </p>
+     */
+    @Test
+    @SneakyThrows
+    public void testExtractTestWPhromma() throws IOException {
+        System.out.printf("\n\n===\n%s\n===\n", "testWPhromma.pdf");
+        try (PDDocument document = Loader.loadPDF(new ClassPathResource("files/bdr/Drucksache_19_9865.pdf").getFile())) {
+
+            Map<PDPage, Map<Integer, PDMarkedContent>> markedContents = new HashMap<>();
+
+            for (PDPage page : document.getPages()) {
+                PDFMarkedContentExtractor extractor = new PDFMarkedContentExtractor();
+                extractor.processPage(page);
+
+                Map<Integer, PDMarkedContent> theseMarkedContents = new HashMap<>();
+                markedContents.put(page, theseMarkedContents);
+                for (PDMarkedContent markedContent : extractor.getMarkedContents()) {
+                    theseMarkedContents.put(markedContent.getMCID(), markedContent);
+                }
+            }
+
+            PDStructureNode root = document.getDocumentCatalog().getStructureTreeRoot();
+            showStructure(root, markedContents);
+            document.close();
+        }
+    }
+
+    /**
+     * <a href="https://stackoverflow.com/questions/59192443/get-tags-related-bboxs-even-though-there-is-no-attributes-a-in-document-cata">
+     * Get tag's related BBox's even though there is no attributes (/A in document catalog structure) related to Layout in PDFBox?
+     * </a>
+     * <br/>
+     * <a href="https://drive.google.com/file/d/1_-tuWuReaTvrDsqQwldTnPYrMHSpXIWp/view?usp=sharing">
+     * res_multipage.pdf
+     * </a>
+     * <p>
+     * This test shows how to, in principle, extract tagged text from this document.
+     * </p>
+     */
+    @Test
+    public void testExtractResMultipage() throws IOException {
+        System.out.printf("\n\n===\n%s\n===\n", "res_multipage.pdf");
+
+        try(PDDocument document = Loader.loadPDF(new ClassPathResource("files/bdr/Drucksache_19_9865.pdf").getFile())) {
+
+            Map<PDPage, Map<Integer, PDMarkedContent>> markedContents = new HashMap<>();
+
+            for (PDPage page : document.getPages()) {
+                PDFMarkedContentExtractor extractor = new PDFMarkedContentExtractor();
+                extractor.processPage(page);
+
+                Map<Integer, PDMarkedContent> theseMarkedContents = new HashMap<>();
+                markedContents.put(page, theseMarkedContents);
+                for (PDMarkedContent markedContent : extractor.getMarkedContents()) {
+                    theseMarkedContents.put(markedContent.getMCID(), markedContent);
+                }
+            }
+
+            PDStructureNode root = document.getDocumentCatalog().getStructureTreeRoot();
+            showStructure(root, markedContents);
+            document.close();
+        }
+    }
+
+    /**
+     * <a href="https://issues.apache.org/jira/browse/PDFBOX-5613">
+     * PDFBOX-5613 - uncorrent paragraph split
+     * </a>
+     * <br/>
+     * <a href="https://issues.apache.org/jira/secure/attachment/13058595/Daily%20Report.pdf">
+     * Daily Report.pdf
+     * </a>
+     * <p>
+     * Making use of the marked content, the contents of the file can better be extracted.
+     * </p>
+     */
+    @Test
+    public void testExtractDailyReport() throws IOException {
+        System.out.printf("\n\n===\n%s\n===\n", "Daily Report.pdf");
+        try (PDDocument document = Loader.loadPDF(new ClassPathResource("files/bdr/Drucksache_19_9865.pdf").getFile())) {
+
+            Map<PDPage, Map<Integer, PDMarkedContent>> markedContents = new HashMap<>();
+
+            for (PDPage page : document.getPages()) {
+                PDFMarkedContentExtractor extractor = new PDFMarkedContentExtractor();
+                extractor.processPage(page);
+
+                Map<Integer, PDMarkedContent> theseMarkedContents = new HashMap<>();
+                markedContents.put(page, theseMarkedContents);
+                for (PDMarkedContent markedContent : extractor.getMarkedContents()) {
+                    theseMarkedContents.put(markedContent.getMCID(), markedContent);
+                }
+            }
+
+            PDStructureNode root = document.getDocumentCatalog().getStructureTreeRoot();
+            showStructure(root, markedContents);
+            document.close();
+        }
+    }
+
+    /**
+     * @see #testExtractTestWPhromma()
+     */
+    void showStructure(PDStructureNode node, Map<PDPage, Map<Integer, PDMarkedContent>> markedContents) {
+        String structType = null;
+        PDPage page = null;
+        if (node instanceof PDStructureElement) {
+            PDStructureElement element = (PDStructureElement) node;
+            structType = element.getStructureType();
+            page = element.getPage();
+        }
+        Map<Integer, PDMarkedContent> theseMarkedContents = markedContents.get(page);
+        System.out.printf("<%s>\n", structType);
+        for (Object object : node.getKids()) {
+            if (object instanceof COSArray) {
+                for (COSBase base : (COSArray) object) {
+                    if (base instanceof COSDictionary) {
+                        showStructure(PDStructureNode.create((COSDictionary) base), markedContents);
+                    } else if (base instanceof COSNumber) {
+                        showContent(((COSNumber)base).intValue(), theseMarkedContents);
+                    } else {
+                        System.out.printf("?%s\n", base);
+                    }
+                }
+            } else if (object instanceof PDStructureNode) {
+                showStructure((PDStructureNode) object, markedContents);
+            } else if (object instanceof Integer) {
+                showContent((Integer)object, theseMarkedContents);
+            } else {
+                System.out.printf("?%s\n", object);
+            }
+
+        }
+        System.out.printf("</%s>\n", structType);
+    }
+
+    /**
+     * @see #showStructure(PDStructureNode, Map)
+     * @see #testExtractTestWPhromma()
+     */
+    void showContent(int mcid, Map<Integer, PDMarkedContent> theseMarkedContents) {
+        PDMarkedContent markedContent = theseMarkedContents != null ? theseMarkedContents.get(mcid) : null;
+        List<Object> contents = markedContent != null ? markedContent.getContents() : Collections.emptyList();
+        StringBuilder textContent =  new StringBuilder();
+        for (Object object : contents) {
+            if (object instanceof TextPosition) {
+                textContent.append(((TextPosition)object).getUnicode());
+            } else {
+                textContent.append("?" + object);
+            }
+        }
+        System.out.printf("%s\n", textContent);
+    }
+}

layoutparser-service/layoutparser-service-server/src/test/java/com/knecon/fforesight/service/layoutparser/server/graph/ViewerDocumentTest.java

@@ -12,10 +12,11 @@ import com.knecon.fforesight.service.layoutparser.internal.api.queue.LayoutParsi
 import com.knecon.fforesight.service.layoutparser.processor.model.graph.nodes.Document;
 import com.knecon.fforesight.service.layoutparser.processor.services.visualization.LayoutGridService;
 import com.knecon.fforesight.service.layoutparser.processor.services.visualization.ViewerDocumentService;
+import com.knecon.fforesight.service.layoutparser.server.utils.BuildDocumentTest;
 
 import lombok.SneakyThrows;
 
-public class ViewerDocumentTest extends BuildDocumentGraphTest {
+public class ViewerDocumentTest extends BuildDocumentTest {
 
     @Test
     @Disabled
@@ -24,11 +25,11 @@ public class ViewerDocumentTest extends BuildDocumentGraphTest {
 
         LayoutGridService layoutGridService = new LayoutGridService();
         ViewerDocumentService viewerDocumentService = new ViewerDocumentService(layoutGridService);
-        String fileName = "files/new/VV-511309_OCR.pdf";
-        Document document = buildGraph(fileName, LayoutParsingType.DOCUMINE);
+        String fileName = "files/bdr/notMergedParagraphs.pdf";
+        Document document = buildGraph(fileName, LayoutParsingType.TAAS);
         String tmpFileName = "/tmp/" + Path.of(fileName).getFileName() + "_VIEWER.pdf";
-        try (var pdDocument = Loader.loadPDF(new ClassPathResource(fileName).getInputStream()); var out = new FileOutputStream(tmpFileName)) {
-            viewerDocumentService.createViewerDocument(pdDocument, document, out);
+        try (var pdDocument = Loader.loadPDF(new ClassPathResource(fileName).getFile()); var out = new FileOutputStream(tmpFileName)) {
+            viewerDocumentService.createViewerDocument(pdDocument, document, out, true);
         }
     }
 

layoutparser-service/layoutparser-service-server/src/test/java/com/knecon/fforesight/service/layoutparser/server/segmentation/PdfSegmentationServiceTest.java

@@ -92,7 +92,7 @@ public class PdfSegmentationServiceTest extends AbstractTest {
 
         ClassPathResource pdfFileResource = new ClassPathResource("files/Minimal Examples/Spanning Cells.pdf");
 
-        ClassificationDocument document = buildClassificationDocument(Loader.loadPDF(pdfFileResource.getInputStream()));
+        ClassificationDocument document = buildClassificationDocument(Loader.loadPDF(pdfFileResource.getFile()));
         assertThat(document.getSections().stream().flatMap(paragraph -> paragraph.getTables().stream()).collect(Collectors.toList())).isNotEmpty();
         TablePageBlock table = document.getSections().stream().flatMap(paragraph -> paragraph.getTables().stream()).collect(Collectors.toList()).get(0);
         assertThat(table.getColCount()).isEqualTo(6);
@@ -106,7 +106,7 @@ public class PdfSegmentationServiceTest extends AbstractTest {
 
         ClassPathResource pdfFileResource = new ClassPathResource("files/Minimal Examples/Merge Table.pdf");
 
-        ClassificationDocument document = buildClassificationDocument(Loader.loadPDF(pdfFileResource.getInputStream()));
+        ClassificationDocument document = buildClassificationDocument(Loader.loadPDF(pdfFileResource.getFile()));
         assertThat(document.getSections().stream().flatMap(paragraph -> paragraph.getTables().stream()).collect(Collectors.toList())).isNotEmpty();
         TablePageBlock firstTable = document.getSections().stream().flatMap(paragraph -> paragraph.getTables().stream()).collect(Collectors.toList()).get(0);
         assertThat(firstTable.getColCount()).isEqualTo(8);
@@ -124,7 +124,7 @@ public class PdfSegmentationServiceTest extends AbstractTest {
 
         ClassPathResource pdfFileResource = new ClassPathResource("files/Minimal Examples/Merge Multi Page Table.pdf");
 
-        ClassificationDocument document = buildClassificationDocument(Loader.loadPDF(pdfFileResource.getInputStream()));
+        ClassificationDocument document = buildClassificationDocument(Loader.loadPDF(pdfFileResource.getFile()));
         assertThat(document.getSections().stream().flatMap(paragraph -> paragraph.getTables().stream()).collect(Collectors.toList())).isNotEmpty();
         TablePageBlock firstTable = document.getSections().stream().flatMap(paragraph -> paragraph.getTables().stream()).collect(Collectors.toList()).get(0);
         assertThat(firstTable.getColCount()).isEqualTo(9);
@@ -142,7 +142,7 @@ public class PdfSegmentationServiceTest extends AbstractTest {
 
         ClassPathResource pdfFileResource = new ClassPathResource("files/Minimal Examples/Rotated Table Headers.pdf");
 
-        ClassificationDocument document = buildClassificationDocument(Loader.loadPDF(pdfFileResource.getInputStream()));
+        ClassificationDocument document = buildClassificationDocument(Loader.loadPDF(pdfFileResource.getFile()));
         assertThat(document.getSections().stream().flatMap(paragraph -> paragraph.getTables().stream()).collect(Collectors.toList())).isNotEmpty();
         TablePageBlock firstTable = document.getSections().stream().flatMap(paragraph -> paragraph.getTables().stream()).collect(Collectors.toList()).get(0);
         assertThat(firstTable.getColCount()).isEqualTo(8);
@@ -160,7 +160,7 @@ public class PdfSegmentationServiceTest extends AbstractTest {
 
         ClassPathResource pdfFileResource = new ClassPathResource("files/SinglePages/56 Fludioxonil_RAR_12_Volume_3CA_B-7_2018-02-21_Page170.pdf");
 
-        ClassificationDocument document = buildClassificationDocument(Loader.loadPDF(pdfFileResource.getInputStream()));
+        ClassificationDocument document = buildClassificationDocument(Loader.loadPDF(pdfFileResource.getFile()));
 
         validateTableSize(document, 4);
 
@@ -177,7 +177,7 @@ public class PdfSegmentationServiceTest extends AbstractTest {
 
         ClassPathResource pdfFileResource = new ClassPathResource("files/SinglePages/VV-931175_Page1.pdf");
 
-        ClassificationDocument document = buildClassificationDocument(Loader.loadPDF(pdfFileResource.getInputStream()));
+        ClassificationDocument document = buildClassificationDocument(Loader.loadPDF(pdfFileResource.getFile()));
 
         validateTableSize(document, 1);
 
@@ -218,7 +218,7 @@ public class PdfSegmentationServiceTest extends AbstractTest {
 
         ClassPathResource pdfFileResource = new ClassPathResource("files/SinglePages/27 A8637C - EU AIR3 - MCP Section 1 - Identity of the plant protection product_Page6.pdf");
 
-        ClassificationDocument document = buildClassificationDocument(Loader.loadPDF(pdfFileResource.getInputStream()));
+        ClassificationDocument document = buildClassificationDocument(Loader.loadPDF(pdfFileResource.getFile()));
 
         validateTableSize(document, 4);
 
@@ -235,7 +235,7 @@ public class PdfSegmentationServiceTest extends AbstractTest {
 
         ClassPathResource pdfFileResource = new ClassPathResource("files/SinglePages/A20622A izRMS (CZ) fRR Part B9_Page185.pdf");
 
-        ClassificationDocument document = buildClassificationDocument(Loader.loadPDF(pdfFileResource.getInputStream()));
+        ClassificationDocument document = buildClassificationDocument(Loader.loadPDF(pdfFileResource.getFile()));
 
         validateTableSize(document, 2);
 
@@ -250,7 +250,7 @@ public class PdfSegmentationServiceTest extends AbstractTest {
 
         ClassPathResource pdfFileResource = new ClassPathResource("files/SinglePages/A20622A izZRMS (CZ) fRR Part B7_Page123.pdf");
 
-        ClassificationDocument document = buildClassificationDocument(Loader.loadPDF(pdfFileResource.getInputStream()));
+        ClassificationDocument document = buildClassificationDocument(Loader.loadPDF(pdfFileResource.getFile()));
 
         validateTableSize(document, 6);
 
@@ -269,7 +269,7 @@ public class PdfSegmentationServiceTest extends AbstractTest {
 
         ClassPathResource pdfFileResource = new ClassPathResource("files/SinglePages/77 Pirimicarb_RAR_08_Volume_3CA_B-6_2017-12-04_Page11.pdf");
 
-        ClassificationDocument document = buildClassificationDocument(Loader.loadPDF(pdfFileResource.getInputStream()));
+        ClassificationDocument document = buildClassificationDocument(Loader.loadPDF(pdfFileResource.getFile()));
 
         validateTableSize(document, 3);
 
@@ -285,7 +285,7 @@ public class PdfSegmentationServiceTest extends AbstractTest {
 
         ClassPathResource pdfFileResource = new ClassPathResource("files/SinglePages/95 Trinexapac-ethyl_RAR_08_Volume_3CA_B-6_2018-01-10_Page532.pdf");
 
-        ClassificationDocument document = buildClassificationDocument(Loader.loadPDF(pdfFileResource.getInputStream()));
+        ClassificationDocument document = buildClassificationDocument(Loader.loadPDF(pdfFileResource.getFile()));
 
         validateTableSize(document, 1);
         validateTable(document, 0, 9, 9, 0, 0);
@@ -298,7 +298,7 @@ public class PdfSegmentationServiceTest extends AbstractTest {
 
         ClassPathResource pdfFileResource = new ClassPathResource("files/SinglePages/52 Fludioxonil_RAR_07_Volume_3CA_B-5_2018-02-21_Page175.pdf");
 
-        ClassificationDocument document = buildClassificationDocument(Loader.loadPDF(pdfFileResource.getInputStream()));
+        ClassificationDocument document = buildClassificationDocument(Loader.loadPDF(pdfFileResource.getFile()));
 
         validateTableSize(document, 1);
 
@@ -312,7 +312,7 @@ public class PdfSegmentationServiceTest extends AbstractTest {
 
         ClassPathResource pdfFileResource = new ClassPathResource("files/SinglePages/52 Fludioxonil_RAR_07_Volume_3CA_B-5_2018-02-21_Page174.pdf");
 
-        ClassificationDocument document = buildClassificationDocument(Loader.loadPDF(pdfFileResource.getInputStream()));
+        ClassificationDocument document = buildClassificationDocument(Loader.loadPDF(pdfFileResource.getFile()));
 
         validateTableSize(document, 1);
         validateTable(document, 0, 9, 6, 7, 0);
@@ -325,7 +325,7 @@ public class PdfSegmentationServiceTest extends AbstractTest {
 
         ClassPathResource pdfFileResource = new ClassPathResource("files/SinglePages/19 Chlorothalonil RAR 08 Volume 3CA B 6b metabolites Oct 2017_Page35.pdf");
 
-        ClassificationDocument document = buildClassificationDocument(Loader.loadPDF(pdfFileResource.getInputStream()));
+        ClassificationDocument document = buildClassificationDocument(Loader.loadPDF(pdfFileResource.getFile()));
 
         validateTableSize(document, 1);
         validateTable(document, 0, 10, 6, 0, 1);
@@ -338,7 +338,7 @@ public class PdfSegmentationServiceTest extends AbstractTest {
 
         ClassPathResource pdfFileResource = new ClassPathResource("files/SinglePages/19 Chlorothalonil RAR 08 Volume 3CA B 6b metabolites Oct 2017_Page161.pdf");
 
-        ClassificationDocument document = buildClassificationDocument(Loader.loadPDF(pdfFileResource.getInputStream()));
+        ClassificationDocument document = buildClassificationDocument(Loader.loadPDF(pdfFileResource.getFile()));
 
         validateTableSize(document, 2);
         validateTable(document, 0, 2, 2, 0, 0);
@@ -353,7 +353,7 @@ public class PdfSegmentationServiceTest extends AbstractTest {
         ClassPathResource pdfFileResource = new ClassPathResource(
                 "files/SinglePages/47 Cyprodinil - EU AIR3 - MCA Section 5 Supplement - Toxicological and metabolism studies on the active substance_Page30.pdf");
 
-        ClassificationDocument document = buildClassificationDocument(Loader.loadPDF(pdfFileResource.getInputStream()));
+        ClassificationDocument document = buildClassificationDocument(Loader.loadPDF(pdfFileResource.getFile()));
 
         validateTableSize(document, 2);
 
@@ -369,7 +369,7 @@ public class PdfSegmentationServiceTest extends AbstractTest {
         ClassPathResource pdfFileResource = new ClassPathResource(
                 "files/SinglePages/49 Cyprodinil - EU AIR3 - MCA Section 8 Supplement - Ecotoxicological studies on the active substance_Page61.pdf");
 
-        ClassificationDocument document = buildClassificationDocument(Loader.loadPDF(pdfFileResource.getInputStream()));
+        ClassificationDocument document = buildClassificationDocument(Loader.loadPDF(pdfFileResource.getFile()));
 
         validateTableSize(document, 2);
 
@@ -384,7 +384,7 @@ public class PdfSegmentationServiceTest extends AbstractTest {
 
         ClassPathResource pdfFileResource = new ClassPathResource("files/SinglePages/81 Pirimicarb_RAR_20_Volume_3CP_A10788A (_Pirimor_)_B-9_2017-12-04_Page54.pdf");
 
-        ClassificationDocument document = buildClassificationDocument(Loader.loadPDF(pdfFileResource.getInputStream()));
+        ClassificationDocument document = buildClassificationDocument(Loader.loadPDF(pdfFileResource.getFile()));
 
         validateTableSize(document, 2);
 
@@ -399,7 +399,7 @@ public class PdfSegmentationServiceTest extends AbstractTest {
 
         ClassPathResource pdfFileResource = new ClassPathResource("files/SinglePages/85 Pydiflumetofen_DAR_08_Volume_3CA_B-6_2017-07-26_Page134.pdf");
 
-        ClassificationDocument document = buildClassificationDocument(Loader.loadPDF(pdfFileResource.getInputStream()));
+        ClassificationDocument document = buildClassificationDocument(Loader.loadPDF(pdfFileResource.getFile()));
 
         validateTableSize(document, 2);
 
@@ -414,7 +414,7 @@ public class PdfSegmentationServiceTest extends AbstractTest {
 
         ClassPathResource pdfFileResource = new ClassPathResource("files/SinglePages/Thiabendazole DAR Addendum for ED_April_2020_Page18.pdf");
 
-        ClassificationDocument document = buildClassificationDocument(Loader.loadPDF(pdfFileResource.getInputStream()));
+        ClassificationDocument document = buildClassificationDocument(Loader.loadPDF(pdfFileResource.getFile()));
 
         validateTableSize(document, 4);
 
@@ -431,7 +431,7 @@ public class PdfSegmentationServiceTest extends AbstractTest {
 
         ClassPathResource pdfFileResource = new ClassPathResource("files/SinglePages/15 - Pretilachlor - Acute Oral Toxicity (Up and Down Procedure) - Rat_Page18.pdf");
 
-        ClassificationDocument document = buildClassificationDocument(Loader.loadPDF(pdfFileResource.getInputStream()));
+        ClassificationDocument document = buildClassificationDocument(Loader.loadPDF(pdfFileResource.getFile()));
 
         validateTableSize(document, 1);
 
@@ -446,7 +446,7 @@ public class PdfSegmentationServiceTest extends AbstractTest {
         ClassPathResource pdfFileResource = new ClassPathResource(
                 "files/SinglePages/28 A8637C - EU AIR3 - MCP Section 10 - Ecotoxicological studies on the plant protection product_Page23.pdf");
 
-        ClassificationDocument document = buildClassificationDocument(Loader.loadPDF(pdfFileResource.getInputStream()));
+        ClassificationDocument document = buildClassificationDocument(Loader.loadPDF(pdfFileResource.getFile()));
 
         validateTableSize(document, 2);
 
@@ -461,7 +461,7 @@ public class PdfSegmentationServiceTest extends AbstractTest {
 
         ClassPathResource pdfFileResource = new ClassPathResource("files/SinglePages/24 - SYN549522 - Acute Oral Toxicity - Rats_Page17.pdf");
 
-        ClassificationDocument document = buildClassificationDocument(Loader.loadPDF(pdfFileResource.getInputStream()));
+        ClassificationDocument document = buildClassificationDocument(Loader.loadPDF(pdfFileResource.getFile()));
 
         validateTableSize(document, 1);
 
@@ -475,7 +475,7 @@ public class PdfSegmentationServiceTest extends AbstractTest {
 
         ClassPathResource pdfFileResource = new ClassPathResource("files/SinglePages/30 - Dicamba - Acute Oral Toxicity - Rats_Page5.pdf");
 
-        ClassificationDocument document = buildClassificationDocument(Loader.loadPDF(pdfFileResource.getInputStream()));
+        ClassificationDocument document = buildClassificationDocument(Loader.loadPDF(pdfFileResource.getFile()));
 
         validateTableSize(document, 1);
 

layoutparser-service/layoutparser-service-server/src/test/java/com/knecon/fforesight/service/layoutparser/server/services/BodyTextFrameServiceTest.java

@@ -0,0 +1,31 @@
+package com.knecon.fforesight.service.layoutparser.server.services;
+
+import java.nio.file.Path;
+import java.util.List;
+
+import org.junit.jupiter.api.Test;
+
+import com.knecon.fforesight.service.layoutparser.internal.api.queue.LayoutParsingType;
+import com.knecon.fforesight.service.layoutparser.processor.model.ClassificationDocument;
+import com.knecon.fforesight.service.layoutparser.processor.utils.RectangleTransformations;
+import com.knecon.fforesight.service.layoutparser.server.utils.BuildDocumentTest;
+import com.knecon.fforesight.service.layoutparser.server.utils.visualizations.PdfDraw;
+
+import lombok.SneakyThrows;
+
+class BodyTextFrameServiceTest extends BuildDocumentTest {
+
+    @Test
+    @SneakyThrows
+    public void testCalculateBodyTextFrame() {
+
+        String filename = "files/211.pdf";
+        String outputFilename = "/tmp/" + Path.of(filename).getFileName() + "_MAINBODY.pdf";
+        ClassificationDocument document = parseLayout(filename, LayoutParsingType.TAAS);
+        PdfDraw.drawRectanglesPerPage(filename,
+                document.getPages().stream().map(page -> List.of(RectangleTransformations.toRectangle2D(page.getBodyTextFrame()))).toList(),
+                outputFilename);
+
+    }
+
+}

layoutparser-service/layoutparser-service-server/src/test/java/com/knecon/fforesight/service/layoutparser/server/services/RulingCleaningServiceTest.java

@@ -5,7 +5,6 @@ import java.util.Collections;
 import java.util.LinkedList;
 import java.util.List;
 
-import org.junit.jupiter.api.Disabled;
 import org.junit.jupiter.api.Test;
 
 import com.knecon.fforesight.service.layoutparser.processor.model.PageContents;
@@ -19,13 +18,13 @@ import lombok.SneakyThrows;
 public class RulingCleaningServiceTest {
 
     @Test
-    @Disabled
+//    @Disabled
     @SneakyThrows
     public void textRulingExtraction() {
 
-        String fileName = "files/BASF/2013-1110704.pdf";
+        String fileName = "files/211.pdf";
         String lineFileName = "/tmp/" + Path.of(fileName).getFileName().toString() + "_LINES.pdf";
-        List<PageContents> pageContents = PageContentExtractor.getSortedPageContents("files/BASF/2013-1110704.pdf");
+        List<PageContents> pageContents = PageContentExtractor.getSortedPageContents(fileName);
         PdfDraw.drawLinesPerPage(fileName, pageContents.stream().map(PageContents::getRulings).toList(), lineFileName);
 
         RulingCleaningService rulingCleaningService = new RulingCleaningService();

layoutparser-service/layoutparser-service-server/src/test/java/com/knecon/fforesight/service/layoutparser/server/utils/AbstractTest.java

@@ -101,8 +101,13 @@ public abstract class AbstractTest {
     protected LayoutParsingRequest prepareStorage(InputStream fileInputStream) {
 
         storageService.storeObject(TenantContext.getTenantId(), ORIGIN_FILE_ID, fileInputStream);
+        return buildDefaultLayoutParsingRequest(LayoutParsingType.REDACT_MANAGER);
+    }
+
+    protected LayoutParsingRequest buildDefaultLayoutParsingRequest(LayoutParsingType layoutParsingType) {
+
         return LayoutParsingRequest.builder()
-                .layoutParsingType(LayoutParsingType.REDACT_MANAGER)
+                .layoutParsingType(layoutParsingType)
                 .originFileStorageId(ORIGIN_FILE_ID)
                 .tablesFileStorageId(Optional.of(TABLE_FILE_ID))
                 .imagesFileStorageId(Optional.of(IMAGE_FILE_ID))
@@ -116,7 +121,6 @@ public abstract class AbstractTest {
                 .build();
     }
 
-
     @SneakyThrows
     protected LayoutParsingRequest prepareStorage(String file, String cvServiceResponseFile, String imageInfoFile) {
 
@@ -135,19 +139,7 @@ public abstract class AbstractTest {
         storageService.storeObject(TenantContext.getTenantId(), TABLE_FILE_ID, cvServiceResponseFileStream);
         storageService.storeObject(TenantContext.getTenantId(), ORIGIN_FILE_ID, fileStream);
 
-        return LayoutParsingRequest.builder()
-                .layoutParsingType(LayoutParsingType.REDACT_MANAGER)
-                .originFileStorageId(ORIGIN_FILE_ID)
-                .tablesFileStorageId(Optional.of(TABLE_FILE_ID))
-                .imagesFileStorageId(Optional.of(IMAGE_FILE_ID))
-                .structureFileStorageId(STRUCTURE_FILE_ID)
-                .textBlockFileStorageId(TEXT_FILE_ID)
-                .positionBlockFileStorageId(POSITION_FILE_ID)
-                .pageFileStorageId(PAGES_FILE_ID)
-                .simplifiedTextStorageId(SIMPLIFIED_ID)
-                .sectionGridStorageId(SECTION_GRID_ID)
-                .viewerDocumentStorageId(VIEWER_DOCUMENT_ID)
-                .build();
+        return buildDefaultLayoutParsingRequest(LayoutParsingType.REDACT_MANAGER);
     }
 
 

layoutparser-service/layoutparser-service-server/src/test/java/com/knecon/fforesight/service/layoutparser/server/utils/BuildDocumentTest.java

@@ -1,39 +1,35 @@
-package com.knecon.fforesight.service.layoutparser.server.graph;
-
-import static org.junit.jupiter.api.Assertions.assertEquals;
+package com.knecon.fforesight.service.layoutparser.server.utils;
 
 import java.io.InputStream;
 
 import org.apache.pdfbox.Loader;
 import org.apache.pdfbox.pdmodel.PDDocument;
-import org.junit.jupiter.api.Disabled;
-import org.junit.jupiter.api.Test;
 import org.springframework.beans.factory.annotation.Autowired;
 import org.springframework.core.io.ClassPathResource;
 
 import com.knecon.fforesight.service.layoutparser.internal.api.queue.LayoutParsingType;
 import com.knecon.fforesight.service.layoutparser.processor.LayoutParsingPipeline;
-import com.knecon.fforesight.service.layoutparser.processor.python_api.model.table.TableServiceResponse;
+import com.knecon.fforesight.service.layoutparser.processor.model.ClassificationDocument;
 import com.knecon.fforesight.service.layoutparser.processor.model.graph.nodes.Document;
+import com.knecon.fforesight.service.layoutparser.processor.python_api.model.table.TableServiceResponse;
 import com.knecon.fforesight.service.layoutparser.processor.services.factory.DocumentGraphFactory;
-import com.knecon.fforesight.service.layoutparser.server.utils.AbstractTest;
 
 import lombok.SneakyThrows;
 
-public class BuildDocumentGraphTest extends AbstractTest {
+public abstract class BuildDocumentTest extends AbstractTest {
 
     @Autowired
     protected LayoutParsingPipeline layoutParsingPipeline;
 
 
-    @Test
-    @Disabled
-    public void buildMetolachlor() {
+    @SneakyThrows
+    protected ClassificationDocument parseLayout(String filename, LayoutParsingType layoutParsingType) {
 
-        Document documentGraph = buildGraph("files/S-Metolachlor_RAR_01_Volume_1_2018-09-06.pdf");
-        assertEquals(221, documentGraph.getPages().size());
-        assertEquals(220, documentGraph.getPages().stream().filter(page -> page.getHeader().hasText()).count());
-        assertEquals(0, documentGraph.getPages().stream().filter(page -> page.getFooter().hasText()).count());
+        ClassPathResource fileResource = new ClassPathResource(filename);
+        prepareStorage(filename);
+        try (InputStream inputStream = fileResource.getInputStream(); PDDocument pdDocument = Loader.loadPDF(inputStream.readAllBytes())) {
+            return layoutParsingPipeline.parseLayout(layoutParsingType, pdDocument, layoutParsingStorageService.getImagesFile(IMAGE_FILE_ID), new TableServiceResponse());
+        }
     }
 
 
@@ -52,14 +48,9 @@ public class BuildDocumentGraphTest extends AbstractTest {
         } else {
             prepareStorage(filename);
         }
-        ClassPathResource fileResource = new ClassPathResource(filename);
 
-        try (InputStream inputStream = fileResource.getInputStream(); PDDocument pdDocument = Loader.loadPDF(inputStream)) {
-            return DocumentGraphFactory.buildDocumentGraph(layoutParsingPipeline.parseLayout(layoutParsingType,
-                    pdDocument,
-                    layoutParsingStorageService.getImagesFile(IMAGE_FILE_ID),
-                    new TableServiceResponse()));
-        }
+        return DocumentGraphFactory.buildDocumentGraph(parseLayout(filename, layoutParsingType));
     }
 
 }
+

layoutparser-service/layoutparser-service-server/src/test/java/com/knecon/fforesight/service/layoutparser/server/utils/visualizations/PdfDraw.java

@@ -5,7 +5,6 @@ import java.awt.geom.Point2D;
 import java.awt.geom.Rectangle2D;
 import java.io.FileOutputStream;
 import java.io.IOException;
-import java.io.InputStream;
 import java.util.List;
 import java.util.Map;
 
@@ -14,6 +13,7 @@ import org.apache.pdfbox.pdmodel.PDDocument;
 import org.apache.pdfbox.pdmodel.PDPage;
 import org.apache.pdfbox.pdmodel.PDPageContentStream;
 import org.apache.pdfbox.pdmodel.font.PDType1Font;
+import org.apache.pdfbox.pdmodel.font.Standard14Fonts;
 import org.apache.pdfbox.util.Matrix;
 import org.springframework.core.io.ClassPathResource;
 
@@ -40,10 +40,8 @@ public class PdfDraw {
 
     public static void drawRectanglesPerPage(String filename, List<List<Rectangle2D>> rectanglesPerPage, String tmpFileName) throws IOException {
 
-        try (InputStream inputStream = new ClassPathResource(filename).getInputStream();//
-             PDDocument pdDocument = Loader.loadPDF(inputStream);//
-             var out = new FileOutputStream(tmpFileName)//
-        ) {
+        ClassPathResource pdfResource = new ClassPathResource(filename);
+        try (PDDocument pdDocument = Loader.loadPDF(pdfResource.getFile()); var out = new FileOutputStream(tmpFileName)) {
             for (int pageNumber = 1; pageNumber < pdDocument.getNumberOfPages() + 1; pageNumber++) {
                 PdfVisualisationUtility.drawRectangle2DList(pdDocument,
                         pageNumber,
@@ -58,11 +56,8 @@ public class PdfDraw {
 
     public static void drawRectanglesPerPageNumberedByLine(String filename, List<List<List<Rectangle2D>>> rectanglesPerPage, String tmpFileName) throws IOException {
 
-        try (InputStream inputStream = new ClassPathResource(filename).getInputStream();//
-             PDDocument pdDocument = Loader.loadPDF(inputStream);//
-             var out = new FileOutputStream(tmpFileName)//
-        ) {
-
+        ClassPathResource pdfResource = new ClassPathResource(filename);
+        try (PDDocument pdDocument = Loader.loadPDF(pdfResource.getFile()); var out = new FileOutputStream(tmpFileName)) {
             for (int pageNumber = 1; pageNumber < pdDocument.getNumberOfPages() + 1; pageNumber++) {
                 var rectanglesOnPage = rectanglesPerPage.get(pageNumber - 1);
                 for (int lineNumber = 0; lineNumber < rectanglesOnPage.size(); lineNumber++) {
@@ -74,13 +69,9 @@ public class PdfDraw {
                             new Point2D.Double(rectanglesInLine.get(0).getX() - (5 + (5 * countNumberOfDigits(lineNumber))), y + 2),
                             pageNumber,
                             PdfVisualisationUtility.Options.builder().stroke(true).build());
-
                 }
-
             }
-
             pdDocument.save(out);
-
         }
 
     }
@@ -143,7 +134,7 @@ public class PdfDraw {
         } else {
             contentStream.newLineAtOffset((float) location.getX(), (float) location.getY());
         }
-        contentStream.setFont(PDType1Font.HELVETICA, 10);
+        contentStream.setFont(new PDType1Font(Standard14Fonts.FontName.HELVETICA), 10);
         contentStream.showText(string);
         contentStream.endText();
         contentStream.close();
@@ -184,11 +175,8 @@ public class PdfDraw {
     @SneakyThrows
     public static void drawRectanglesAndLinesPerPage(String filename, List<List<Rectangle2D>> list, List<List<Rectangle2D>> rectanglesPerPage, String tmpFileName) {
 
-        try (InputStream inputStream = new ClassPathResource(filename).getInputStream();//
-             PDDocument pdDocument = Loader.loadPDF(inputStream);//
-             var out = new FileOutputStream(tmpFileName)//
-        ) {
-
+        ClassPathResource pdfResource = new ClassPathResource(filename);
+        try (PDDocument pdDocument = Loader.loadPDF(pdfResource.getFile()); var out = new FileOutputStream(tmpFileName)) {
             for (int pageNumber = 1; pageNumber < pdDocument.getNumberOfPages() + 1; pageNumber++) {
 //                PdfVisualisationUtility.drawLine2DList(pdDocument,
 //                        pageNumber,
@@ -201,7 +189,6 @@ public class PdfDraw {
                 PdfVisualisationUtility.drawRectangle2DList(pdDocument, pageNumber, list.get(pageNumber - 1), PdfVisualisationUtility.Options.builder().stroke(true).build());
             }
             pdDocument.save(out);
-
         }
     }
 
@@ -209,12 +196,13 @@ public class PdfDraw {
     @SneakyThrows
     public static void drawLinesPerPage(String filename, List<List<Ruling>> linesPerPage, String tmpFileName) {
 
-        try (InputStream inputStream = new ClassPathResource(filename).getInputStream();//
-             PDDocument pdDocument = Loader.loadPDF(inputStream);//
-             var out = new FileOutputStream(tmpFileName)//
-        ) {
+        ClassPathResource pdfResource = new ClassPathResource(filename);
+        try (PDDocument pdDocument = Loader.loadPDF(pdfResource.getFile()); var out = new FileOutputStream(tmpFileName)) {
             for (int pageNumber = 1; pageNumber < pdDocument.getNumberOfPages() + 1; pageNumber++) {
-                PdfVisualisationUtility.drawLine2DList(pdDocument, pageNumber, linesPerPage.get(pageNumber - 1), PdfVisualisationUtility.Options.builder().strokeColor(Color.RED).stroke(true).build());
+                PdfVisualisationUtility.drawLine2DList(pdDocument,
+                        pageNumber,
+                        linesPerPage.get(pageNumber - 1),
+                        PdfVisualisationUtility.Options.builder().strokeColor(Color.RED).stroke(true).build());
             }
             pdDocument.save(out);
         }