Efficient Text Search: Handling Multiple Files and Folders using Java

readme.md

Related Article(s):

• Efficient Text Search in Java: Handling Multiple Files and Folders

PrintSearchResults.java

// Printing Search Results ===

for (int i = 0 ; i < result.getDocumentCount(); i++)
{
    FoundDocument document = result.getFoundDocument(i);
 
    // Printing Search Results ===========
    System.out.println("Occurrences: " + document.getOccurrenceCount());
    for (FoundDocumentField field : document.getFoundFields()) {
        System.out.println("\tField: " + field.getFieldName());
        System.out.println("\tOccurrences: " + field.getOccurrenceCount());

        // Printing found terms
        if (field.getTerms() != null) {
            for (int k = 0; k < field.getTerms().length; k++) {
                System.out.println("\t\t" + field.getTerms()[k] + " - " + field.getTermsOccurrences()[k]);
            }
        }
        // Printing found phrases
        if (field.getTermSequences() != null) {
            for (int k = 0; k < field.getTermSequences().length; k++) {
                String[] terms = field.getTermSequences()[k];
                String sequence = "";
                for (String term : terms) {
                    sequence += term + " ";
                }
                System.out.println("\t\t" + sequence + " - " + field.getTermSequencesOccurrences()[k]);
            }
        }
    }
}

TextSearchHighlightResults.java

// Text Search in Multiple files of various file formats within Multiple Folders using Java

// Creating an index in the specified folder
Index index = new Index("path/for/indexingFolder");

// Indexing documents from the specified folder
index.add("path/parent-folder/");

String query = "water OR \"Lorem ipsum\" OR non";
SearchResult result = index.search(query);

for (int i = 0 ; i < result.getDocumentCount(); i++)
{
    FoundDocument document = result.getFoundDocument(i);
    System.out.println("====================================");
    System.out.println("File Name: " + document.getDocumentInfo().getFilePath());

    OutputAdapter outputAdapter = new FileOutputAdapter(OutputFormat.Html, "/path/Highlighted-" + i + ".html");
    Highlighter highlighter = new DocumentHighlighter(outputAdapter);
    index.highlight(document, highlighter);
}

TextSearchMultipleFolders.java

// Text Search in Multiple files of various file formats within Multiple Folders using Java

// Creating an index in the specified folder
Index index = new Index("path/for/indexingFolder");

// Indexing documents from the specified folder
index.add("path/parent-folder/");

String query = "water OR \"Lorem ipsum\" OR non";
SearchResult result = index.search(query);

for (int i = 0 ; i < result.getDocumentCount(); i++)
{
    FoundDocument document = result.getFoundDocument(i);
    System.out.println("====================================");
    System.out.println("File Name: " + document.getDocumentInfo().getFilePath());

    OutputAdapter outputAdapter = new FileOutputAdapter(OutputFormat.Html, "/path/Highlighted-" + i + ".html");
    Highlighter highlighter = new DocumentHighlighter(outputAdapter);
    index.highlight(document, highlighter);
  
    // Printing Search Results ===========
    System.out.println("Occurrences: " + document.getOccurrenceCount());
    for (FoundDocumentField field : document.getFoundFields()) {
        System.out.println("\tField: " + field.getFieldName());
        System.out.println("\tOccurrences: " + field.getOccurrenceCount());

        // Printing found terms
        if (field.getTerms() != null) {
            for (int k = 0; k < field.getTerms().length; k++) {
                System.out.println("\t\t" + field.getTerms()[k] + " - " + field.getTermsOccurrences()[k]);
            }
        }
        // Printing found phrases
        if (field.getTermSequences() != null) {
            for (int k = 0; k < field.getTermSequences().length; k++) {
                String[] terms = field.getTermSequences()[k];
                String sequence = "";
                for (String term : terms) {
                    sequence += term + " ";
                }
                System.out.println("\t\t" + sequence + " - " + field.getTermSequencesOccurrences()[k]);
            }
        }
    }  
}