org.apache.commons.codec.language.bm.ash_exact_any.txt Maven / Gradle / Ivy

Show more of this group Show more artifacts with this name
Show all versions of commons-codec Show documentation

The Apache Commons Codec package contains simple encoder and decoders for various formats such as Base64 and Hexadecimal. In addition to these widely used encoders and decoders, the codec package also maintains a collection of phonetic encoding utilities.

There is a newer version: 20041127.091804

Show newest version

/*
 * 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.
 */

// These rules are applied after the word has been transliterated into the phonetic alphabet
// These rules are substitution rules within the phonetic character space rather than mapping rules

// format of each entry rule in the table
//   (pattern, left context, right context, phonetic)
// where
//   pattern is a sequence of characters that might appear after a word has been transliterated into phonetic alphabet
//   left context is the context that precedes the pattern
//   right context is the context that follows the pattern
//   phonetic is the result that this rule generates
//
// note that both left context and right context can be regular expressions
// ex: left context of ^ would mean start of word
//     right context of $ means end of word
//
// match occurs if all of the following are true:
//   portion of word matches the pattern
//   that portion satisfies the context

// A, E, I, O, P, U should create variants, but a, e, i, o, u should not create any new variant
// Q = ü ; Y = ä = ö


"A" "" "" "a"
"B" "" "" "a"

"E" "" "" "e"
"F" "" "" "e"

"I" "" "" "i"
"O" "" "" "o"
"P" "" "" "o"
"U" "" "" "u"

"J" "" "" "l"