Github user mateiz commented on a diff in the pull request:
https://github.com/apache/spark/pull/685#discussion_r12502546
--- Diff:
mllib/src/main/scala/org/apache/spark/mllib/util/NumericParser.scala ---
@@ -0,0 +1,153 @@
+/*
+ * Licensed to the Apache Software Foundation (ASF) under one or more
+ * contributor license agreements. See the NOTICE file distributed with
+ * this work for additional information regarding copyright ownership.
+ * The ASF licenses this file to You under the Apache License, Version 2.0
+ * (the "License"); you may not use this file except in compliance with
+ * the License. You may obtain a copy of the License at
+ *
+ * http://www.apache.org/licenses/LICENSE-2.0
+ *
+ * Unless required by applicable law or agreed to in writing, software
+ * distributed under the License is distributed on an "AS IS" BASIS,
+ * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+ * See the License for the specific language governing permissions and
+ * limitations under the License.
+ */
+
+package org.apache.spark.mllib.util
+
+import scala.collection.mutable.{ArrayBuffer, ListBuffer}
+
+private[mllib] object NumericTokenizer {
+ val NUMBER = -1
+ val END = -2
+}
+
+import NumericTokenizer._
+
+/**
+ * Simple tokenizer for a numeric structure consisting of three types:
+ *
+ * - number: a double in Java's floating number format
+ * - array: an array of numbers stored as `[v0,v1,...,vn]`
+ * - tuple: a list of numbers, arrays, or tuples stored as `(...)`
+ *
+ * @param s input string
+ * @param start start index
+ * @param end end index
+ */
+private[mllib] class NumericTokenizer(s: String, start: Int, end: Int) {
+
+ /**
+ * Creates a tokenizer for the entire input string.
+ */
+ def this(s: String) = this(s, 0, s.length)
+
+ private var cur = start
+ private var allowComma = false
+ private var _value = Double.NaN
+
+ /**
+ * Returns the most recent parsed number.
+ */
+ def value: Double = _value
+
+ /**
+ * Returns the next token, which could be any of the following:
+ * - '[', ']', '(', or ')'.
+ * - [[org.apache.spark.mllib.util.NumericTokenizer#NUMBER]], call
value() to get its value.
+ * - [[org.apache.spark.mllib.util.NumericTokenizer#END]].
+ */
+ def next(): Int = {
+ if (cur < end) {
+ val c = s(cur)
+ c match {
--- End diff --
Using a match statement here might be slow, check the generated code with
`javap`. It would be safer to do `if (c == '(')` and such.
---
If your project is set up for it, you can reply to this email and have your
reply appear on GitHub as well. If your project does not have this feature
enabled and wishes so, or if the feature is enabled but not working, please
contact infrastructure at infrastruct...@apache.org or file a JIRA ticket
with INFRA.
---
