static void runSplitBySentenceTests()

in athena-udfs-textanalytics/src/main/java/com/amazonaws/athena/udf/textanalytics/TextAnalyticsUDFHandler.java [1326:1346]

• 21 lines of code
• 1 McCabe index (conditional complexity)

    static void runSplitBySentenceTests(TextAnalyticsUDFHandler textAnalyticsUDFHandler) throws Exception
    {
        String[] resultArr;
        String result;
        System.out.println("Test splitting text by sentence");
        String longText = new String("My name is Mr. P. A. Jeremiah Smith Jr., and I live at 1234 Summer Dr., Anytown, USA. This sentence has 10.5 words, and some abbreviations, e.g. this one. Also: punctuation in quotes, like this, \"Way to go Joe!\", she said.");
        System.out.println("Original text: " + longText);
        resultArr = textAnalyticsUDFHandler.redact_pii_entities(makeArray(longText, 1), makeArray("en", 1), makeArray("ALL", 1));
        System.out.println("Original - PII Redacted: " + String.join("", resultArr)); 
        resultArr = textAnalyticsUDFHandler.redact_entities(makeArray(longText, 1), makeArray("en", 1), makeArray("ALL", 1));
        System.out.println("Original - Entities Redacted: " + String.join("", resultArr)); 
        String[] sentenceArray = splitStringBySentence(longText);
        System.out.println("Split sentences: \n" + String.join("\n", sentenceArray)); 
        int cnt = sentenceArray.length;
        resultArr = textAnalyticsUDFHandler.redact_pii_entities(sentenceArray, makeArray("en", cnt), makeArray("ALL", cnt));
        result = String.join("", resultArr);
        System.out.println("Text Split, PII Redacted and combined: " + result); 
        resultArr = textAnalyticsUDFHandler.redact_entities(sentenceArray, makeArray("en", cnt), makeArray("ALL", cnt));
        result = String.join("", resultArr);
        System.out.println("Text Split, Entities Redacted and combined: " + result); 
    }