Merge pull request #7 from wfreeman/master

Check for Date, ObjectId, BinData explicitly. Remove blacklist of keys.

README.markdown

@@ -6,19 +6,22 @@ This lightweight tool helps you get a sense of your application's schema, as wel
 We'll make a collection:
 
 	db.users.insert({name: "Tom", bio: "A nice guy.", pets: ["monkey", "fish"], someWeirdLegacyKey: "I like Ike!"});
-	db.users.insert({name: "Dick", bio: "I swordfight."});
-	db.users.insert({name: "Harry", pets: "egret"});
+	db.users.insert({name: "Dick", bio: "I swordfight.", birthday: new Date("1974-03-14")});
+	db.users.insert({name: "Harry", pets: "egret", birthday: new Date("1984-03-14")});
 	db.users.insert({name: "Geneviève", bio: "Ça va?"});
+	db.users.insert({name: "Jim", someBinData: new BinData(2,"1234")});
 
 So, let's see what we've got here:
 
 	$ mongo test --eval "var collection = 'users'" variety.js
 	
-	{ "_id" : { "key" : "_id" }, "value" : { "types" : [ "object" ] }, "totalOccurrences" : 4, "percentContaining" : 100 }
-	{ "_id" : { "key" : "name" }, "value" : { "types" : [ "string" ] }, "totalOccurrences" : 4, "percentContaining" : 100 }
-	{ "_id" : { "key" : "bio" }, "value" : { "types" : [ "string" ] }, "totalOccurrences" : 3, "percentContaining" : 75 }
-	{ "_id" : { "key" : "pets" }, "value" : { "types" : [ "string", "array" ] }, "totalOccurrences" : 2, "percentContaining" : 50 }
-	{ "_id" : { "key" : "someWeirdLegacyKey" }, "value" : { "type" : "string" }, "totalOccurrences" : 1, "percentContaining" : 25 }
+        { "_id" : { "key" : "_id" }, "value" : { "types" : [ "objectId" ] }, "totalOccurrences" : 5, "percentContaining" : 100 }
+        { "_id" : { "key" : "name" }, "value" : { "types" : [ "string" ] }, "totalOccurrences" : 5, "percentContaining" : 100 }
+        { "_id" : { "key" : "bio" }, "value" : { "types" : [ "string" ] }, "totalOccurrences" : 3, "percentContaining" : 60 }
+        { "_id" : { "key" : "birthday" }, "value" : { "types" : [ "date" ] }, "totalOccurrences" : 2, "percentContaining" : 40 }
+        { "_id" : { "key" : "pets" }, "value" : { "types" : [ "string", "array" ] }, "totalOccurrences" : 2, "percentContaining" : 40 }
+        { "_id" : { "key" : "someBinData" }, "value" : { "type" : "binData" }, "totalOccurrences" : 1, "percentContaining" : 20 }
+        { "_id" : { "key" : "someWeirdLegacyKey" }, "value" : { "type" : "string" }, "totalOccurrences" : 1, "percentContaining" : 20 }
 
 _("test" is the database containing the collection we are analyzing.)_
 

variety.js

@@ -25,7 +25,10 @@ varietyCanHaveChildren = function (v) {
                 typeof v.length === 'number' && 
                 !(v.propertyIsEnumerable('length'));
   var isObject = typeof v === 'object';
-  return isArray || isObject;
+  var specialObject = v instanceof Date || 
+                      v instanceof ObjectId ||
+                      v instanceof BinData;
+  return !specialObject && (isArray || isObject);
 }
 db.system.js.save( { _id : "varietyCanHaveChildren", value : varietyCanHaveChildren } );
 	
@@ -57,6 +60,15 @@ varietyTypeOf = function(thing) {
     else if (thing === null) {
       return "null";
     }
+    else if (thing instanceof Date) {
+      return "date";
+    }
+    else if (thing instanceof ObjectId) {
+      return "objectId";
+    }
+    else if (thing instanceof BinData) {
+      return "binData";
+    }
     else {
       return "object";
     }
@@ -109,10 +121,6 @@ var resultsDB = db.getMongo().getDB("varietyResults");
 
 var numDocuments = db[collection].count();
 
-// Using our method of retrieving keys, Mongo gets confused about the following, and 
-// incorrectly thinks they are keys. -JC
-var blackListKeys = ["_id.equals", "_id.getTimestamp", "_id.isObjectId", "_id.str","_id.tojson"];
-
 resultsDB[resultsCollectionName].find({}).forEach(function(key) {
   keyName = key["_id"].key;
   
@@ -123,17 +131,6 @@ resultsDB[resultsCollectionName].find({}).forEach(function(key) {
     return;
   }
 
-  var blackListKeyFound = false;  
-
-  blackListKeys.forEach(function(blackListKey) {
-    if(keyName === blackListKey) {
-      resultsDB[resultsCollectionName].remove({ "_id" : { key: keyName }});
-      blackListKeyFound = true;
-    }
-  });
-
-  if(blackListKeyFound) { return; }
-  
   if(!(keyName.match(/\.XX/) && !keyName.match(/\.XX$/))) {
     // i.e. "Unless the key's value is an array which contains arrays"  -JC
     // ...we do not support totalOccurrences for these keys because it is