Various fixes and compilation issues resolution.

.gitignore

@@ -3,3 +3,7 @@ pom.xml.tag
 pom.xml.releaseBackup
 pom.xml.next
 release.properties
+.project
+.classpath
+.settings/
+.vscode/

pom.xml

@@ -16,13 +16,13 @@
         <dependency>
             <groupId>com.google.guava</groupId>
             <artifactId>guava</artifactId>
-            <version>18.0</version>
+            <version>31.1-jre</version>
         </dependency>
 
         <dependency>
             <groupId>org.apache.pdfbox</groupId>
             <artifactId>pdfbox</artifactId>
-            <version>2.0.6</version>
+            <version>2.0.27</version>
         </dependency>
 
         <dependency>
@@ -35,28 +35,116 @@
             <groupId>org.slf4j</groupId>
             <artifactId>slf4j-log4j12</artifactId>
             <version>1.7.12</version>
+            <scope>test</scope>
         </dependency>
 
         <dependency>
             <groupId>junit</groupId>
             <artifactId>junit</artifactId>
-            <version>4.12</version>
+            <version>4.13.2</version>
         </dependency>
     </dependencies>
 
     <build>
         <plugins>
             <plugin>
-                <artifactId>maven-assembly-plugin</artifactId>
+                <groupId>org.apache.maven.plugins</groupId>
+                <artifactId>maven-compiler-plugin</artifactId>
                 <configuration>
-                    <archive>
-                        <manifest>
-                            <mainClass>com.giaybac.traprange.MAIN</mainClass>
-                        </manifest>
-                    </archive>
-                    <descriptorRefs>
-                        <descriptorRef>jar-with-dependencies</descriptorRef>
-                    </descriptorRefs>
+                    <excludes>
+                        <exclude>**/com/giaybac/traprange/MAIN.java</exclude>
+                    </excludes>
+                </configuration>
+            </plugin>
+            <plugin>
+                <groupId>org.apache.maven.plugins</groupId>
+                <artifactId>maven-enforcer-plugin</artifactId>
+                <version>3.0.0-M1</version>
+                <executions>
+                    <execution>
+                        <id>enforce-maven</id>
+                        <goals>
+                            <goal>enforce</goal>
+                        </goals>
+                        <configuration>
+                            <rules>
+                                <requireMavenVersion>
+                                <version>2.2.0</version>
+                                </requireMavenVersion>
+                            </rules>
+                        </configuration>
+                    </execution>
+                </executions>
+            </plugin>
+            <plugin>
+                <groupId>org.apache.maven.plugins</groupId>
+                <artifactId>maven-surefire-plugin</artifactId>
+                <version>2.12</version>
+                <configuration>
+                    <systemProperties>
+                        <property>
+                            <name>loggerPath</name>
+                            <value>conf/log4j.properties</value>
+                        </property>
+                    </systemProperties>
+                    <argLine>-Xms512m -Xmx1500m</argLine>
+                    <parallel>methods</parallel>
+                    <forkMode>pertest</forkMode>
+                </configuration>
+            </plugin>
+            <!-- attach test jar -->
+            <plugin>
+                <groupId>org.apache.maven.plugins</groupId>
+                <artifactId>maven-jar-plugin</artifactId>
+                <version>2.2</version>
+                <executions>
+                    <execution>
+                        <goals>
+                            <goal>jar</goal>
+                            <goal>test-jar</goal>
+                        </goals>
+                    </execution>
+                </executions>
+                <configuration></configuration>
+            </plugin>
+            <plugin>
+                <groupId>org.codehaus.mojo</groupId>
+                <artifactId>build-helper-maven-plugin</artifactId>
+                <version>3.0.0</version>
+                <executions>
+                    <execution>
+                        <id>add_sources</id>
+                        <phase>generate-sources</phase>
+                        <goals>
+                            <goal>add-source</goal>
+                        </goals>
+                        <configuration>
+                            <sources>
+                                <source>src/main/java</source>
+                            </sources>
+                        </configuration>
+                    </execution>
+                    <execution>
+                        <id>add_test_sources</id>
+                        <phase>generate-test-sources</phase>
+                        <goals>
+                            <goal>add-test-source</goal>
+                        </goals>
+                        <configuration>
+                            <sources>
+                                <source>src/test/java</source>
+                            </sources>
+                        </configuration>
+                    </execution>
+                </executions>
+            </plugin>
+            <plugin>
+                <groupId>org.apache.maven.plugins</groupId>
+                <artifactId>maven-compiler-plugin</artifactId>
+                <version>3.6.1</version>
+                <configuration>
+                    <source>1.8</source>
+                    <target>1.8</target>
                 </configuration>
             </plugin>
         </plugins>

src/main/java/com/giaybac/traprange/PDFTableExtractor.java

@@ -25,9 +25,7 @@
 import java.util.Collections;
 import java.util.Comparator;
 import java.util.List;
-import java.util.logging.Level;
 import org.apache.pdfbox.pdmodel.PDDocument;
-import org.apache.pdfbox.pdmodel.PDPage;
 import org.apache.pdfbox.text.PDFTextStripper;
 import org.apache.pdfbox.text.TextPosition;
 
@@ -45,14 +43,20 @@ public class PDFTableExtractor {
     private final List<Integer> extractedPages = new ArrayList<>();
     private final List<Integer> exceptedPages = new ArrayList<>();
     //contains avoided line idx-s for each page,
-    //if this multimap contains only one element and key of this element equals -1
+    //if this multimap contains only one element and key of this element equals magicPageNumber
     //then all lines in extracted pages contains in multi-map value will be avoided
     private final Multimap<Integer, Integer> pageNExceptedLinesMap = HashMultimap.create();
 
     private InputStream inputStream;
     private PDDocument document;
     private String password;
 
+    private final int magicPageNumber = Integer.MAX_VALUE;    //--------------------------------------------------------------------------
+    //  Initialization and releasation
+    //--------------------------------------------------------------------------
+    //  Getter N Setter
+    //--------------------------------------------------------------------------
+    //  Method binding
     public PDFTableExtractor setSource(InputStream inputStream) {
         this.inputStream = inputStream;
         return this;
@@ -126,8 +130,8 @@ public PDFTableExtractor exceptLine(int pageIdx, int[] lineIdxes) {
      * @param lineIdxes
      * @return
      */
-    public PDFTableExtractor exceptLine(int[] lineIdxes) {
-        this.exceptLine(-1, lineIdxes);
+    public PDFTableExtractor exceptLine(int[] lineIdxs) {
+        this.exceptLine(magicPageNumber, lineIdxs);
         return this;
     }
 
@@ -138,11 +142,11 @@ public List<Table> extract() {
         try {
             this.document = this.password!=null?PDDocument.load(inputStream,this.password):PDDocument.load(inputStream);
             for (int pageId = 0; pageId < document.getNumberOfPages(); pageId++) {
-                boolean b = !exceptedPages.contains(pageId) && (extractedPages.isEmpty() || extractedPages.contains(pageId));
+                boolean b = !(exceptedPages.contains(pageId) || exceptedPages.contains(pageId - document.getNumberOfPages())) && (extractedPages.isEmpty() || extractedPages.contains(pageId));
                 if (b) {
                     List<TextPosition> texts = extractTextPositions(pageId);//sorted by .getY() ASC
                     //extract line ranges
-                    List<Range<Integer>> lineRanges = getLineRanges(pageId, texts);
+                    List<Range<Integer>> lineRanges = getLineRanges(pageId, document.getNumberOfPages(), texts);
                     //extract column ranges
                     List<TextPosition> textsByLineRanges = getTextsByLineRanges(lineRanges, texts);
 
@@ -153,7 +157,7 @@ public List<Table> extract() {
             //Calculate columnRanges
             List<Range<Integer>> columnRanges = getColumnRanges(pageIdNTextsMap.values());
             for (int pageId : pageIdNTextsMap.keySet()) {
-                Table table = buildTable(pageId, (List) pageIdNTextsMap.get(pageId), (List) pageIdNLineRangesMap.get(pageId), columnRanges);
+                Table table = buildTable(pageId, (List<TextPosition>) pageIdNTextsMap.get(pageId), (List<Range<Integer>>) pageIdNLineRangesMap.get(pageId), columnRanges);
                 retVal.add(table);
                 //debug
                 logger.debug("Found " + table.getRows().size() + " row(s) and " + columnRanges.size()
@@ -292,7 +296,7 @@ private List<TextPosition> extractTextPositions(int pageId) throws IOException {
 
     private boolean isExceptedLine(int pageIdx, int lineIdx) {
         boolean retVal = this.pageNExceptedLinesMap.containsEntry(pageIdx, lineIdx)
-                || this.pageNExceptedLinesMap.containsEntry(-1, lineIdx);
+                || this.pageNExceptedLinesMap.containsEntry(magicPageNumber, lineIdx);
         return retVal;
     }
 
@@ -341,7 +345,7 @@ private List<Range<Integer>> getColumnRanges(Collection<TextPosition> texts) {
         return rangesBuilder.build();
     }
 
-    private List<Range<Integer>> getLineRanges(int pageId, List<TextPosition> pageContent) {
+    private List<Range<Integer>> getLineRanges(int pageId, int numberOfPages, List<TextPosition> pageContent) {
         TrapRangeBuilder lineTrapRangeBuilder = new TrapRangeBuilder();
         for (TextPosition textPosition : pageContent) {
             Range<Integer> lineRange = Range.closed((int) textPosition.getY(),
@@ -350,15 +354,19 @@ private List<Range<Integer>> getLineRanges(int pageId, List<TextPosition> pageCo
             lineTrapRangeBuilder.addRange(lineRange);
         }
         List<Range<Integer>> lineTrapRanges = lineTrapRangeBuilder.build();
-        List<Range<Integer>> retVal = removeExceptedLines(pageId, lineTrapRanges);
+        List<Range<Integer>> retVal = removeExceptedLines(pageId, numberOfPages, lineTrapRanges);
         return retVal;
     }
 
-    private List<Range<Integer>> removeExceptedLines(int pageIdx, List<Range<Integer>> lineTrapRanges) {
+    private List<Range<Integer>> removeExceptedLines(int pageIdx, int numberOfPages, List<Range<Integer>> lineTrapRanges) {
         List<Range<Integer>> retVal = new ArrayList<>();
         for (int lineIdx = 0; lineIdx < lineTrapRanges.size(); lineIdx++) {
-            boolean isExceptedLine = isExceptedLine(pageIdx, lineIdx)
-                    || isExceptedLine(pageIdx, lineIdx - lineTrapRanges.size());
+            boolean isExceptedLine = (
+                isExceptedLine(pageIdx, lineIdx)
+                || isExceptedLine(pageIdx, lineIdx - lineTrapRanges.size())
+                || isExceptedLine(pageIdx - numberOfPages, lineIdx)
+                || isExceptedLine(pageIdx - numberOfPages, lineIdx - lineTrapRanges.size())
+            );
             if (!isExceptedLine) {
                 retVal.add(lineTrapRanges.get(lineIdx));
             }

src/main/java/com/giaybac/traprange/TrapRangeBuilder.java

@@ -34,9 +34,9 @@ public TrapRangeBuilder addRange(Range<Integer> range) {
     public List<Range<Integer>> build() {
         List<Range<Integer>> retVal = new ArrayList<>();
         //order range by lower Bound
-        Collections.sort(ranges, new Comparator<Range>() {
+        Collections.sort(ranges, new Comparator<Range<Integer>>() {
             @Override
-            public int compare(Range o1, Range o2) {
+            public int compare(Range<Integer> o1, Range<Integer> o2) {
                 return o1.lowerEndpoint().compareTo(o2.lowerEndpoint());
             }
         });
@@ -47,7 +47,7 @@ public int compare(Range o1, Range o2) {
             } else {
                 Range<Integer> lastRange = retVal.get(retVal.size() - 1);
                 if (lastRange.isConnected(range)) {
-                    Range newLastRange = lastRange.span(range);
+                    Range<Integer> newLastRange = lastRange.span(range);
                     retVal.set(retVal.size() - 1, newLastRange);
                 } else {
                     retVal.add(range);

src/main/java/com/giaybac/traprange/invoice/PDFLayoutTextStripper.java

@@ -44,7 +44,7 @@
  */
 
 
-package com.giaybac.traprange;
+package com.giaybac.traprange.invoice;
 import java.io.IOException;
 import java.util.ArrayList;
 import java.util.Collections;
@@ -124,7 +124,6 @@ private void writeToOutputStream(final List<TextLine> textLineList) throws IOExc
      * In order to get rid of the warning:
      * TextPositionComparator class should implement Comparator<TextPosition> instead of Comparator
      */
-    @SuppressWarnings("unchecked")
     private void sortTextPositionList(final List<TextPosition> textList) {
         TextPositionComparator comparator = new TextPositionComparator();
         Collections.sort(textList, comparator);

src/test/java/com/giaybac/traprange/test/TESTPDFBox.java

@@ -46,25 +46,25 @@ public void test() throws IOException {
 
         this.processPage(page);
         //Print out all text    
-        Collections.sort(ranges, new Comparator<Range>() {
+        Collections.sort(ranges, new Comparator<Range<Integer>>() {
             @Override
-            public int compare(Range o1, Range o2) {
+            public int compare(Range<Integer> o1, Range<Integer> o2) {
                 return o1.lowerEndpoint().compareTo(o2.lowerEndpoint());
             }
         });
-        for (Range range : ranges) {
+        for (Range<Integer> range : ranges) {
             System.out.println("> " + range);
         }
         //Print out all ranges
         List<Range<Integer>> trapRanges = trapRangeBuilder.build();
-        for (Range trapRange : trapRanges) {
+        for (Range<Integer> trapRange : trapRanges) {
             System.out.println("TrapRange: " + trapRange);
         }
     }
 
     @Override
     protected void processTextPosition(TextPosition text) {
-        Range range = Range.closed((int) text.getY(), (int) (text.getY() + text.getHeight()));
+        Range<Integer> range = Range.closed((int) text.getY(), (int) (text.getY() + text.getHeight()));
         System.out.println("Text: " + text.getUnicode());
         trapRangeBuilder.addRange(range);
     }

src/test/java/com/giaybac/traprange/test/TestInvoice.java

@@ -7,7 +7,7 @@
 import org.apache.pdfbox.pdfparser.PDFParser;
 import org.apache.pdfbox.pdmodel.PDDocument;
 import org.apache.pdfbox.text.PDFTextStripper;
-import com.giaybac.traprange.PDFLayoutTextStripper;
+import com.giaybac.traprange.invoice.PDFLayoutTextStripper;
 import org.junit.Test;
 import java.nio.file.Paths;
 import java.util.regex.Pattern;
@@ -169,12 +169,10 @@ private static class Row {
         String barcode;
         float quantity = -1;
         List<String> lines = new ArrayList<>();
-        int lineIdx;
         Map<String, int[]> headerPositions = null;
 
         Row(Map<String, int[]> headerPositions, int lineIdx, String barcode) {
             this.headerPositions = headerPositions;
-            this.lineIdx = lineIdx;
             this.barcode = barcode;
         }
 

src/test/java/com/giaybac/traprange/test/TestInvoice2.java

@@ -7,12 +7,11 @@
 import org.apache.pdfbox.pdfparser.PDFParser;
 import org.apache.pdfbox.pdmodel.PDDocument;
 import org.apache.pdfbox.text.PDFTextStripper;
-import com.giaybac.traprange.PDFLayoutTextStripper;
+import com.giaybac.traprange.invoice.PDFLayoutTextStripper;
 import org.junit.Test;
 import java.nio.file.Paths;
 import java.util.regex.Pattern;
 import java.util.regex.Matcher;
-import java.util.*;
 
 /**
  * How to run this file:
@@ -26,8 +25,6 @@
 
 public class TestInvoice2 {
 
-    private static final int spaceTolerance = 5;
-
     @Test
     public void test() throws IOException {
         try {