JavaScript Index Stage

function (doc) {
    // do some work ...
    return doc;
}

/* globals Java, logger*/
(function () {
    "use strict";

    return function main(doc , ctx, collection, solrServer, solrServerFactory) {
    // do some work ...

        return doc;
    };
})();

function (doc) {
    // do some work ...
    return doc;
}

function doWork(doc) {  ... return doc; }
function doWork(doc, ctx) {  ... return doc; }
function doWork(doc, ctx, collection) {  ... return doc; }
function doWork(doc, ctx, collection, solrServer) {  ... return doc; }
function doWork(doc, ctx, collection, solrServer, SolrClusterComponent) {  ... return doc; }

var ArrayList = Java.type("java.util.ArrayList");
var a = new ArrayList;

function (doc) {
  doc.addField('some-new-field', 'some-value');
  return doc;
}

function (doc) {
  var value = "";
  if (doc.hasField("myGeo_Lat") && doc.hasField("myGeo_Long"))   {
    value = doc.getFirstFieldValue("myGeo_Lat") + "," + doc.getFirstFieldValue("myGeo_Long");
    doc.addField("myGeo_p", value);
    doc.removeFields("myGeo_Lat");
    doc.removeFields("myGeo_Long");
    logger.debug("conjoined Lat, Long: " + value);
  }
  return doc;
}

function (doc) {
  var subjects = doc.getFieldValues("subjects");
  var id = doc.getId();
  var newDocs = [];
  for (i = 0; i < subjects.size(); i++) {
     var pd = new com.lucidworks.apollo.common.pipeline.PipelineDocument(id+'-'+i );
     pd.addField('subject',  subjects.get(i));
     newDocs.push( pd  );
  }
  return newDocs;
}

function (doc, ctx) {
  /**
  * Returned body is a JSON string.  Example:
  {
  "telescope": "Hubble",
  "location": "low earth orbit",
  "primary_mirror_size": "2.4m"
  "tags": ["launched 1990","repaired 1993","repaired 1997","repaired 1997","repaired 1999","repaired 2002","repaired 2009"]
  }
  */

    for (var key in myData) {
      var obj = myData[key];
      if (obj == "tags") {
        logger.debug("extracting tags from tag field {}", JSON.stringify(obj))
        for (var i = 0; i < obj.length; i++) {
          var tag = obj[i][0];
          doc.addField("tag_ss", tag);
        }
      }
    }

    return doc;
}

function doWork(doc, ctx, collection, solrServer, solrServerFactory) {
    var sku = doc.getFirstFieldValue("sku");
    if (!doc.hasField("mentions")) {
        var mentions = ""
        var productsSolr = solrServerFactory.getSolrServer("products");
        if( productsSolr != null ){
            var q = "sku:"+sku;
            var query = new org.apache.solr.client.solrj.SolrQuery();
            query.setRows(100);
            query.setQuery(q);
            var res = productsSolr.query(query);
            mentions = res.getResults().size();
            doc.addField("mentions",mentions);
        }
    }
    return doc;
}

function doWork(doc) {
 if (!doc.hasField("required_field")) {
    return null;
 }
 return doc;
}

function(doc) {
  var id = doc.getId();
  if (id !== null) {
    var pattern = "https://www.mydomain.com/links/contact/?";

    // 0 means the pattern was found so drop the doc
    return (id.indexOf(pattern) == 0) ? null : doc;
  }

  return doc;
}

// For example:
// From: 26/Mar/2015:14:38:48 -0700
// To:   2015-03-26T14:38:48Z  (Solr format)
function(doc) {
  if (doc.getId() !== null) {
    var inboundPattern = "dd/MMM/yyyy':'HH:mm:ss Z";  // modify this to match the format of the inbound date
    var solrDatePattern = "yyyy-MM-dd'T'HH:mm:ss'Z'"; // leave this alone
    var dateFieldName = "apachelogtime"; // change this to your date field name

    var solrFormatter = new java.text.SimpleDateFormat(solrDatePattern);
    var apacheParser = new java.text.SimpleDateFormat(inboundPattern);

    var dateString = doc.getFirstFieldValue(dateFieldName);
    logger.info("**** dateString: " + dateString);
    var inboundDate = apacheParser.parse(dateString);
    logger.info("**** inboundDate: " + inboundDate.toString());
    var solrDate =  solrFormatter.format(inboundDate);
    logger.info("**** solrDate: " + solrDate.toString());

    doc.setField(dateFieldName, solrDate.toString());
  }

  return doc;
}

function(doc) {
  if (doc.getId() !== null) {
    var fields = ["col1", "col2", "col3"];

    for (i = 0; i < fields.length; i++ ) {
      var field = fields[i];
      var value = doc.getFirstFieldValue(field);
      logger.info("BEFORE: Field " + field + ": *" + value + "*");

      if (value != null) {
        value = value.replace(/^\s+/, "");  // remove leading whitespace
        logger.info("AFTER: Field " + field + ": *" + value + "*");
        value = value.replace(/\s+$/, "");  // remove trailing whitespace
        logger.info("AFTER: Field " + field + ": *" + value + "*");
        value = value.replace(/\s+/g, " ");  // multiple whitespace to one space
        logger.info("AFTER: Field " + field + ": *" + value + "*");

        doc.setField(field, value);
      }
    }
  }

  return doc;
}

// Split On a delimiter. In this case, a newline
function(doc){
  if (doc.getId() !== null) {
    var fromField = "company2_ss";
    var toField = "company2_ss";
    var delimiter = "\n";

    var oldList = doc.getFieldValues(fromField);

    var values = [];

    // parse the entries one at a time
    doc.removeFields(toField); // clear out the target field
    for (i = 0; i < oldList.size(); i++) {
      values[i] = oldList.get(i);

      // get the list of strings split by the delimiter
      newList = values[i].split(delimiter);
      for(j = 0; j < newList.length; j++ ){
        doc.addField(toField, newList[j]);
      }
    }
  }
  return doc;
}

var queries = ["cat","the cat", "the cat in the hat","the cat in the hat is back"]
for(var i = 0; i < queries.length; i++){
  logger.info("query {} is '{}'",i,queries[i])
}

var queries = ["cat","the cat", "the cat in the hat","the cat in the hat is back"]
for(i = 0; i < queries.length; i++){
  logger.info("query {} is '{}'",i,queries[i])
}

/* globals Java, logger*/ // This is an optional line that informs the syntax checker about known global objects. This avoids excessive flagging of what it perceives as errors.
(function () { //Defines a top-level scope
    "use strict"; // This directs the interpreter to require `var` for all variable declarations to help ensure thread safety. Any global scope variables generate compile errors.
    /***
    * NOTE:  All code within the outer scope, (everything from other than the `main` function returned by the `function` declared on line two) is only run when the JavaScript engine JIT-compiles the script.  Place comments, static declarations, functions, and initialization code here to improve readability and performance.
    */
    var PipelineDocument = Java.type('com.lucidworks.apollo.common.pipeline.PipelineDocument');
    var ArrayList = Java.type("java.util.ArrayList")

    /**
    * Take a PipelineDocument like the one passed to this stage and clone it.  Then give it a new id.
    */
    function clonePipelineDoc(pipelineDoc, id) {
      var clone = new PipelineDocument(pipelineDoc);
      if (id) {
        clone.setId(id);
      }
      logIfDebug("Cloned document with id '{}' and gave the clone id '{}'",pipelineDoc.getId(),id)
      return clone;
    };

    var isDebug = false // This setting is optional and determines if log messages are turned off or on. It works in conjunction with the `logIfDebug` function.
    function logIfDebug(m){if(isDebug && m)logger.info(m, Array.prototype.slice.call(arguments).slice(1));}

    return function main(doc , ctx, collection, solrServer, solrServerFactory) {
        //This returns the function to be called by Fusion when the stage executes, and guarantees Fusion will always call this function. When a stage does not use advanced syntax, but declares multiple top-level functions, Fusion may not be able to determine which function to call. Duplicate doc and give it an ID that is the reverse of the original.
        var doc2 = clonePipelineDoc(doc, doc.getId().split("").reverse().join(""))
        var list = new ArrayList()
        list.add(doc)
        list.add(doc2)

        //Return both docs to the downstream stages.
        return listOfDocs;
    };
})();

/* globals Java, logger*/
//JavaScript (ES5.1)
/**
 * UtilitiesDemoLib - A stripped-down demo utility library for Fusion Pipeline scripts
 *
 * Contains essential utility functions for demonstration purposes:
 * - Debug logging
 * - Type checking
 * - String manipulation
 *
 * This library is designed to work in both Index and Query pipelines
 * and automatically registers itself in the pipeline context.
 */
(function () {
    "use strict";

    var libName = 'UtilitiesDemoLib'
    var exports = {};

    /** Debug flag for conditional logging */
    var isDebug = false;

    /**
     * Conditional debug logging function
     * @param {string} m - Primary message to log
     * @param {...*} args - Additional arguments to log
     */
    function logIfDebug(m) {
        if (isDebug && m) {
            logger.info(m, Array.prototype.slice.call(arguments).slice(1));
        }
    }

    /**
     * Enables or disables debug logging for this library
     * @param {boolean} debug_b - true to enable debug logging, false to disable
     */
    function setDebugLogging(debug_b) {
        isDebug = debug_b;
        logIfDebug("Debug logging {} for {}", isDebug ? "enabled" : "disabled", libName);
    }

    /**
     * Returns the name of this library
     * @return {string} The library name
     */
    function getLibName() {
        return libName;
    }

    /**
     * Tests whether an object is a Java object by checking for standard Java methods
     * @param {*} obj - Object to test
     * @return {boolean} true if the object appears to be a Java object
     */
    function isJavaType(obj) {
        if (obj === null || obj === undefined) {
            return false;
        }

        // Check for common Java object methods
        return (typeof obj.getClass === 'function' ||
                typeof obj.hashCode === 'function' ||
                typeof obj.toString === 'function' && obj.constructor.name !== 'String');
    }

    /**
     * Returns a simplified type name for both Java and JavaScript objects
     * For Java objects: returns simple class name (e.g., 'String' for java.lang.String)
     * For JavaScript objects: returns lowercase type name (e.g., 'string')
     * @param {*} obj - Object to get type information for
     * @param {boolean} [verbose=false] - If true, return full Java class name
     * @return {string} Type name of the object
     */
    function getTypeOf(obj, verbose) {
        if (obj === null) return 'null';
        if (obj === undefined) return 'undefined';

        if (isJavaType(obj)) {
            try {
                var className = obj.getClass().getName();
                if (verbose) {
                    return className;
                } else {
                    // Return simple class name (last part after final dot)
                    return className.substring(className.lastIndexOf('.') + 1);
                }
            } catch (e) {
                return 'JavaObject';
            }
        } else {
            // JavaScript object
            return typeof obj;
        }
    }

    /**
     * Remove whitespace from start and end of str. Also remove redundant whitespace (set to space).
     * @param {string} str - String to trim
     * @return {string} Trimmed string with normalized whitespace
     */
    function trimWhitespace(str) {
        if (!str || typeof str !== 'string') {
            return str;
        }

        // Trim leading/trailing whitespace and normalize internal whitespace
        return str.trim().replace(/\s+/g, ' ');
    }

    // Export all utility functions for external use
    exports.setDebugLogging = setDebugLogging;
    exports.getLibName = getLibName;
    exports.isJavaType = isJavaType;
    exports.getTypeOf = getTypeOf;
    exports.trimWhitespace = trimWhitespace;

    /**
     * Auto-registration function for pipeline contexts
     * Detects pipeline type (Index vs Query) and registers this library in the context
     *
     * For Index Pipelines: arguments are (doc, ctx, collection, solrClient, solrFactory)
     * For Query Pipelines: arguments are (request, response, ctx, ...)
     *
     * The function identifies the context object by checking argument types and
     * registers the library functions under the library name for easy access
     *
     * @return {*} Returns the document object for Index pipelines, undefined for Query pipelines
     */
    return function main() {
        var doc, ctx;

        // Detect pipeline type by argument pattern
        if (arguments.length >= 3) {
            if (arguments[0] && typeof arguments[0].getId === 'function') {
                // Index Pipeline: (doc, ctx, collection, solrClient, solrFactory)
                doc = arguments[0];
                ctx = arguments[1];
            } else if (arguments[0] && typeof arguments[0].getParam === 'function') {
                // Query Pipeline: (request, response, ctx, collection, solrClient, solrFactory)
                ctx = arguments[2];
            }
        }

        if (ctx && typeof ctx.put === 'function') {
            // Register this library in the context
            var lib = {
                setDebugLogging: setDebugLogging,
                getLibName: getLibName,
                isJavaType: isJavaType,
                getTypeOf: getTypeOf,
                trimWhitespace: trimWhitespace
            };

            ctx.put(libName, lib);
            logIfDebug("Registered {} in pipeline context", libName);
        }

        // Return doc for Index pipelines (required), undefined for Query pipelines
        return doc;
    };



})();