Source

fogbow / src / main / scala / fogbow / util / StringUtil.scala

Full commit
/**
 * Licensed 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 fogbow.util;

object StringCleaner {

  // Cleans up a string by ripping out punctuation, turning all digit
  // sequences into a single numeric symbol, and getting rid of tokens
  // that contain mixtures of alphabetic and numeric characters.
  def apply (raw: String, doLowerCase: Boolean = true): String = {
    val cleaned = 
      raw.replaceAll("[^\\p{L}\\p{N}]", " ").replaceAll("""\b\d+\b""", "[-numeric-]").replaceAll("""\b[^\s]{10,}\b""","").replaceAll("""\b[^\s]*\w+\d+[^\s]*\b""","").replaceAll("""\b[^\s]*\d+\w+[^\s]*\b""","").trim()
    doLowerCase match {
      case true => cleaned.toLowerCase
      case false => cleaned
    }
  }
    
  // Need this since Java doesn't do defaults...
  def apply (raw: String): String = apply(raw, true)

}


// A tokenizer that replaces all non-word characters with whitespace
// and then returns a StringTokenizer.
object CleanStringTokenizer {
  import java.util.StringTokenizer

  def apply (raw: String, doLowerCase: Boolean = true): StringTokenizer =
    new StringTokenizer(StringCleaner(raw))

  // Need this since Java doesn't do defaults...
  def apply (raw: String): StringTokenizer = apply(raw, true)

}