Add code + a few extra comments from the scalar UDF examples in the

docs. Didn't do extra testing, just reused the code straight from
the docs with 2-space indentation.

udf-sample.cc

@@ -30,4 +30,74 @@ BooleanVal FuzzyEquals(FunctionContext* ctx, const DoubleVal& x, const DoubleVal
   return BooleanVal(delta < EPSILON);
 }
 
+// Check if the input string has any occurrences of the letters (a,e,i,o,u).
+// Case-insensitive, so also detects (A,E,I,O,U).
+BooleanVal HasVowels(FunctionContext* context, const StringVal& input)
+{
+  if (input.is_null) return BooleanVal::null();
 
+  int index;
+  uint8_t *ptr;
+
+  for (ptr = input.ptr, index = 0; index <= input.len; index++, ptr++)
+  {
+    uint8_t c = tolower(*ptr);
+    if (c == 'a' || c == 'e' || c == 'i' || c == 'o' || c == 'u')
+    {
+      return BooleanVal(true);
+    }
+  }
+  return BooleanVal(false);
+}
+
+// Count all occurrences of the letters (a,e,i,o,u) in the input string.
+// Case-insensitive, so also counts (A,E,I,O,U).
+IntVal CountVowels(FunctionContext* context, const StringVal& arg1)
+{
+  if (arg1.is_null) return IntVal::null();
+
+  int count;
+  int index;
+  uint8_t *ptr;
+
+  for (ptr = arg1.ptr, count = 0, index = 0; index <= arg1.len; index++, ptr++)
+  {
+    uint8_t c = tolower(*ptr);
+    if (c == 'a' || c == 'e' || c == 'i' || c == 'o' || c == 'u')
+    {
+      count++;
+    }
+  }
+  return IntVal(count);
+}
+
+// Remove all occurrences of the letters (a,e,i,o,u) from the input string.
+// Case-insensitive, so also removes (A,E,I,O,U).
+StringVal StripVowels(FunctionContext* context, const StringVal& arg1)
+{
+  if (arg1.is_null) return StringVal::null();
+
+  int index;
+  std::string original((const char *)arg1.ptr,arg1.len);
+  std::string shorter("");
+
+  for (index = 0; index < original.length(); index++)
+  {
+    uint8_t c = original[index];
+    uint8_t l = tolower(c);
+
+    if (l == 'a' || l == 'e' || l == 'i' || l == 'o' || l == 'u')
+    {
+      ;
+    }
+    else
+    {
+        shorter.append(1, (char)c);
+    }
+  }
+  // The modified string is stored in 'shorter', which is destroyed when this function ends. We need to make a string val
+  // and copy the contents.
+  StringVal result(context, shorter.size()); // Only the version of the ctor that takes a context object allocates new memory
+  memcpy(result.ptr, shorter.c_str(), shorter.size());
+  return result;
+}

udf-sample.h

@@ -31,4 +31,27 @@ IntVal AddUdf(FunctionContext* context, const IntVal& arg1, const IntVal& arg2);
 //        > select fuzzy_equals(1, 1.00000001);
 BooleanVal FuzzyEquals(FunctionContext* context, const DoubleVal& x, const DoubleVal& y);
 
+// Perform tests, calculations, and transformations
+// on a string value, using the set of letters 'aeiou'.
+
+// Usage: > create function hasvowels(string) returns boolean
+//          location '/user/cloudera/libudfsample.so' SYMBOL='HasVowels';
+//        > select hasvowels('banana');
+//        > select hasvowels('grr hm shhh');
+//        > select hasvowels(c1) from t1;
+BooleanVal HasVowels(FunctionContext* context, const StringVal& input);
+
+
+// Usage: > create function countvowels(string) returns boolean
+//          location '/user/cloudera/libudfsample.so' SYMBOL='CountVowels';
+//        > select countvowels('abracadabra hocus pocus');
+//        > select countvowels(c1) from t1;
+IntVal CountVowels(FunctionContext* context, const StringVal& arg1);
+
+// Usage: > create function stripvowels(string) returns boolean
+//          location '/user/cloudera/libudfsample.so' SYMBOL='StripVowels';
+//        > select stripvowels('colour color');
+//        > select stripvowels(c1) from t1;
+StringVal StripVowels(FunctionContext* context, const StringVal& arg1);
+
 #endif