Adding maxDepth functionality.

README.markdown

@@ -57,6 +57,35 @@ We are only examining the last document here ("limit = 1"). It belongs to Genevi
 
 But how can totalOccurrences still reach 4? "limit" specifies how many documents to search for keys. Then, the tool calculates totalOccurrences and percentContaining from _all_ the collection's documents, even those outside the "limit". This tradeoff is meant to give the most bang for our buck, when using "limit" and learning about a collection.
 
+### Analyze Documents to a Maximum Depth
+
+Perhaps you have a potentially very deep nested object structure, and you don't want to see more than a few levels deep in the analysis.
+
+One can apply a "maxDepth" constraint, which limits the depth variety will recursively search to find new objects.
+
+    db.users.insert({name:"Walter", someNestedObject:{a:{b:{c:{d:{e:1}}}}}});
+
+The default will traverse all the way to the bottom of that structure:
+
+        $ mongo test --eval "var collection = 'users'" variety.js
+  
+    ...
+    { "_id" : { "key" : "someNestedObject" }, "value" : { "types" : [ "Object" ] }, "totalOccurrences" : 2, "percentContaining" : 33.33333333333333 }
+    { "_id" : { "key" : "someNestedObject.a" }, "value" : { "types" : [ "Object" ] }, "totalOccurrences" : 2, "percentContaining" : 33.33333333333333 }
+    { "_id" : { "key" : "someNestedObject.a.b" }, "value" : { "types" : [ "Object" ] }, "totalOccurrences" : 2, "percentContaining" : 33.33333333333333 }
+    { "_id" : { "key" : "someNestedObject.a.b.c" }, "value" : { "types" : [ "Object" ] }, "totalOccurrences" : 2, "percentContaining" : 33.33333333333333 }
+    { "_id" : { "key" : "someNestedObject.a.b.c.d" }, "value" : { "types" : [ "Object" ] }, "totalOccurrences" : 2, "percentContaining" : 33.33333333333333 }
+    { "_id" : { "key" : "someNestedObject.a.b.c.d.e" }, "value" : { "types" : [ "Number" ] }, "totalOccurrences" : 2, "percentContaining" : 33.33333333333333 }   
+ 
+        $ mongo test --eval "var collection = 'users', maxDepth = 3" variety.js
+
+    ...
+    { "_id" : { "key" : "someNestedObject" }, "value" : { "types" : [ "Object" ] }, "totalOccurrences" : 2, "percentContaining" : 33.33333333333333 }
+    { "_id" : { "key" : "someNestedObject.a" }, "value" : { "types" : [ "Object" ] }, "totalOccurrences" : 2, "percentContaining" : 33.33333333333333 }
+    { "_id" : { "key" : "someNestedObject.a.b" }, "value" : { "types" : [ "Object" ] }, "totalOccurrences" : 2, "percentContaining" : 33.33333333333333 }
+
+As you can see, variety only traversed three levels deep.
+
 ##### "But my dad told me MongoDB is a schemaless database!" #####
 
 First of all, your father is a great guy. Moving on...

variety.js

@@ -19,6 +19,9 @@ if (typeof collection === "undefined") {
 if (typeof limit === "undefined") { var limit = db[collection].count(); }
 print("Using limit of " + limit);
 
+if (typeof maxDepth === "undefined") { var maxDepth = 99; }
+print("Using maxDepth of " + maxDepth);
+
 varietyCanHaveChildren = function (v) {
   var isArray = v && 
                 typeof v === 'object' && 
@@ -32,7 +35,7 @@ varietyCanHaveChildren = function (v) {
 }
 db.system.js.save( { _id : "varietyCanHaveChildren", value : varietyCanHaveChildren } );
 	
-varietyMapRecursive = function(parentKey, keys) {
+varietyMapRecursive = function(parentKey, keys, level) {
   for (var key in keys) {
 		var value = keys[key];
 		
@@ -40,8 +43,8 @@ varietyMapRecursive = function(parentKey, keys) {
 
     emit({key : key}, {type: varietyTypeOf(value)});
 
-    if (varietyCanHaveChildren(value)) {
-      varietyMapRecursive(key, value);
+    if (level < maxDepth - 1 && varietyCanHaveChildren(value)) {
+      varietyMapRecursive(key, value, level + 1);
     }
   }
 }
@@ -91,7 +94,7 @@ map = function() {
     emit({key : key}, {type: varietyTypeOf(value)});
 
     if (varietyCanHaveChildren(value)) {
-      varietyMapRecursive(key, value);
+      varietyMapRecursive(key, value, 1);
     }
   }
 }
@@ -117,7 +120,7 @@ db[collection].mapReduce(map, reduce, {
                                     db : "varietyResults"},
                                   limit : limit, 
                                   sort : {_id: -1},
-                                  scope : { limit : limit }});
+                                  scope : { limit : limit, maxDepth:maxDepth }});
 
 var resultsDB = db.getMongo().getDB("varietyResults");