Regex Search in Files across Folders with Java

readme.md

Related Article(s):

• Regex Search in Documents using Java

SearchByRegex.java

// Regex Search multiple files across folders using Java

// Creating an index folder and add document's folder to it
Index index = new Index("path/indexing-folder-path");
index.add("path/parent-folder");

// Prepare the Regex Query and Search
// Regex here is to identify all words having any consecutive repeated characters.
String query = "^(.)\\1{1,}"; 
SearchResult result = index.search(query);

SearchByRegexOutput.java

// Highlighting and Printing Regex Search Results for all the documents
for (int i = 0 ; i < result.getDocumentCount(); i++)
{
    FoundDocument document = result.getFoundDocument(i);
  
    OutputAdapter outputAdapter = new FileOutputAdapter(OutputFormat.Html, "path/Highlight" + i + ".html");
    Highlighter highlighter = new DocumentHighlighter(outputAdapter);
    index.highlight(document, highlighter);
 
    System.out.println("\tDocument: " + document.getDocumentInfo().getFilePath());
    System.out.println("\tOccurrences: " + document.getOccurrenceCount());
    for (FoundDocumentField field : document.getFoundFields()) {
        System.out.println("\t\tField: " + field.getFieldName());
        System.out.println("\t\tOccurrences: " + field.getOccurrenceCount());

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