new test case

pdf-itext-samples/build.gradle

@@ -10,7 +10,9 @@ sourceCompatibility = JavaVersion.VERSION_17
 targetCompatibility = JavaVersion.VERSION_17
 
 dependencies {
-  api("com.itextpdf:itextpdf:5.5.13.3")
+//  api("com.itextpdf:itextpdf:5.5.13.3")
+  api("com.itextpdf:itext-core:8.0.3")
+
   api("org.apache.commons:commons-lang3:3.14.0")
 
 }

pdf-itext-samples/src/main/java/com/mageddo/itext/pdftextextraction/UpperCaseWordsExtractor.java

@@ -40,13 +40,14 @@ private static boolean sentenceIsValidToBeConsidered(
       StringBuilder buff, int minWordLength, char c
   ) {
     return metMinLength(buff, minWordLength) && (!CharUtils.isAsciiAlpha(c)
-        || Character.isWhitespace(buff.charAt(buff.length() - 1)));
+                                                 || Character.isWhitespace(buff.charAt(buff.length() - 1)));
   }
 
   private static boolean isNonTextAfterTheStartOfTheSentence(StringBuilder buff, char c) {
-    return (
-        CharUtils.isAsciiNumeric(c) || Character.isWhitespace(c)
-            || c == '-' || c == '_'
-    ) && !buff.isEmpty();
+    return !(c == '\r' || c == '\n')
+           && (
+               CharUtils.isAsciiNumeric(c) || Character.isWhitespace(c)
+               || c == '-' || c == '_'
+           ) && !buff.isEmpty();
   }
 }

pdf-itext-samples/src/main/java/com/mageddo/itext/pdftextextraction/UppercasePhraseExtractorApp.java

@@ -4,9 +4,10 @@
 import java.util.ArrayList;
 import java.util.List;
 
-import com.itextpdf.text.pdf.PdfReader;
-import com.itextpdf.text.pdf.parser.PdfReaderContentParser;
-import com.itextpdf.text.pdf.parser.SimpleTextExtractionStrategy;
+import com.itextpdf.kernel.pdf.PdfDocument;
+import com.itextpdf.kernel.pdf.PdfReader;
+import com.itextpdf.kernel.pdf.canvas.parser.PdfTextExtractor;
+import com.itextpdf.kernel.pdf.canvas.parser.listener.SimpleTextExtractionStrategy;
 
 import static com.mageddo.itext.pdftextextraction.UpperCaseWordsExtractor.extractUppercaseWordsSentenceFromText;
 
@@ -19,31 +20,32 @@ public static void main(String[] args) throws IOException {
   }
 
   private static void extractUppercaseWordSequencesFromPdf(final String fileName) throws IOException {
-    final var reader = new PdfReader(fileName);
-    final var parser = new PdfReaderContentParser(reader);
-    final var strategy = new SimpleTextExtractionStrategy();
+
+    final var document = new PdfDocument(new PdfReader(fileName));
     try {
-      final var sentences = extractUppercaseWordSequencesFromPdf(reader, parser, strategy);
+      final var sentences = extractUppercaseWordSequencesFromPdf(document);
       System.out.println(sentences);
     } finally {
-      reader.close();
+      document.close();
     }
   }
 
   private static List<String> extractUppercaseWordSequencesFromPdf(
-      PdfReader reader,
-      PdfReaderContentParser parser,
-      SimpleTextExtractionStrategy strategy
-  ) throws IOException {
+      PdfDocument document
+  ) {
     final var sentences = new ArrayList<String>();
-    for (int i = 1; i <= reader.getNumberOfPages(); i++) {
-      if(i == 445) {
-        parser.processContent(i, strategy);
-//      sentences.addAll(extractUppercaseWordsSentenceFromText(strategy.getResultantText()));
-        final var s = extractUppercaseWordsSentenceFromText(strategy.getResultantText(), 2);
-        System.out.println(s);
-        System.out.println("page: " + i);
-      }
+    for (int i = 1; i <= document.getNumberOfPages(); i++) {
+      // se nao criar o strategy dentro da interação ele acumula as palavras de todas as páginas
+      // executadas no retorno do texto
+      final var strategy = new SimpleTextExtractionStrategy();
+      final var text = PdfTextExtractor.getTextFromPage(document.getPage(i), strategy);
+//      sentences.addAll(extractUppercaseWordsSentenceFromText(text));
+      final var s = extractUppercaseWordsSentenceFromText(text);
+      System.out.println("--------------------------------------");
+      System.out.println(s);
+      System.out.println("page: " + i);
+      System.out.println("=====================================");
+
     }
     return sentences;
   }

pdf-itext-samples/src/test/java/com/mageddo/itext/pdftextextraction/UpperCaseWordsExtractorTest.java

@@ -46,4 +46,23 @@ void mustIgnoreWordsShorterThanMinSpecifiedLength(){
 
   }
 
+  @Test
+  void mustIgnoreWordsSeparatedByNewLines(){
+
+    // arrange
+    final var str = """
+    The SUN
+    IS yellow.
+    """;
+
+    // act
+    final var words = extractUppercaseWordsSentenceFromText(str, 2);
+
+    // assert
+    assertNotNull(words);
+    assertEquals("""
+        [SUN, IS]""", words.toString());
+
+  }
+
 }