/**
* 匹配词段
*
* @param charArray
* @param begin
* @param length
* @param searchHit
* @return Hit
*/
public Hit match(char[] charArray, int begin, int length, Hit searchHit) {
if (searchHit == null) {
// 如果hit为空，新建
searchHit = new Hit();
// 设置hit的其实文本位置
searchHit.setBegin(begin);
} else {
// 否则要将HIT状态重置
searchHit.setUnmatch();
}
// 设置hit的当前处理位置
searchHit.setEnd(begin);
Character keyChar = new Character(charArray[begin]);
DictSegment ds = null;
// 引用实例变量为本地变量，避免查询时遇到更新的同步问题
DictSegment[] segmentArray = this.childrenArray;
Map<Character, DictSegment> segmentMap = this.childrenMap;
// STEP1 在节点中查找keyChar对应的DictSegment
if (segmentArray != null) {
// 在数组中查找
for (DictSegment seg : segmentArray) {
if (seg != null && seg.nodeChar.equals(keyChar)) {
// 找到匹配的段
ds = seg;
}
}
} else if (segmentMap != null) {
// 在map中查找
ds = (DictSegment) segmentMap.get(keyChar);
}
// STEP2 找到DictSegment，判断词的匹配状态，是否继续递归，还是返回结果
if (ds != null) {
if (length > 1) {
// 词未匹配完，继续往下搜索
return ds.match(charArray, begin + 1, length - 1, searchHit);
} else if (length == 1) {
// 搜索最后一个char
if (ds.nodeState == 1) {
// 添加HIT状态为完全匹配
searchHit.setMatch();
}
if (ds.hasNextNode()) {
// 添加HIT状态为前缀匹配
searchHit.setPrefix();
// 记录当前位置的DictSegment
searchHit.setMatchedDictSegment(ds);
}
return searchHit;
}
}
// STEP3 没有找到DictSegment， 将HIT设置为不匹配
return searchHit;
}
private void loadPrepDict() {
_PrepDict = new DictSegment((char) 0);
File file = new File(configuration.getDictRoot(), Dictionary.PATH_DIC_PREP);
InputStream is = null;
try {
is = new FileInputStream(file);
} catch (FileNotFoundException e) {
logger.error("ik-analyzer", e);
}
if (is == null) {
throw new RuntimeException("Preposition Dictionary not found!!!");
}
try {
BufferedReader br = new BufferedReader(new InputStreamReader(is, "UTF-8"), 512);
String theWord;
do {
theWord = br.readLine();
if (theWord != null && !"".equals(theWord.trim())) {
_PrepDict.fillSegment(theWord.trim().toCharArray());
}
} while (theWord != null);
} catch (IOException e) {
logger.error("ik-analyzer", e);
} finally {
try {
is.close();
is = null;
} catch (IOException e) {
logger.error("ik-analyzer", e);
}
}
}
/** 加载量词词典 */
private void loadQuantifierDict() {
// 建立一个量词典实例
_QuantifierDict = new DictSegment((char) 0);
// 读取量词词典文件
File file = new File(configuration.getDictRoot(), Dictionary.PATH_DIC_QUANTIFIER);
InputStream is = null;
try {
is = new FileInputStream(file);
} catch (FileNotFoundException e) {
logger.error("ik-analyzer", e);
}
try {
BufferedReader br = new BufferedReader(new InputStreamReader(is, "UTF-8"), 512);
String theWord = null;
do {
theWord = br.readLine();
if (theWord != null && !"".equals(theWord.trim())) {
_QuantifierDict.fillSegment(theWord.trim().toCharArray());
}
} while (theWord != null);
} catch (IOException ioe) {
logger.error("Quantifier Dictionary loading exception.");
} finally {
try {
if (is != null) {
is.close();
is = null;
}
} catch (IOException e) {
logger.error("ik-analyzer", e);
}
}
}
/**
* 加载填充词典片段
*
* @param charArray
* @param begin
* @param length
*/
public synchronized void fillSegment(char[] charArray, int begin, int length) {
// 获取字典表中的汉字对象
Character beginChar = new Character(charArray[begin]);
Character keyChar = charMap.get(beginChar);
// 字典中没有该字，则将其添加入字典
if (keyChar == null) {
charMap.put(beginChar, beginChar);
keyChar = beginChar;
}
// 搜索当前节点的存储，查询对应keyChar的keyChar，如果没有则创建
DictSegment ds = lookforSegment(keyChar);
// 处理keyChar对应的segment
if (length > 1) {
// 词元还没有完全加入词典树
ds.fillSegment(charArray, begin + 1, length - 1);
} else if (length == 1) {
// 已经是词元的最后一个char,设置当前节点状态为1，表明一个完整的词
ds.nodeState = 1;
}
}
/** 加载用户配置的扩展词典到主词库表 */
private void loadExtDict() {
// 加载扩展词典配置
List<String> extDictFiles = configuration.getExtDictionarys();
if (extDictFiles != null) {
InputStream is = null;
for (String extDictName : extDictFiles) {
// 读取扩展词典文件
logger.info("[Dict Loading]" + extDictName);
File file = new File(configuration.getDictRoot(), extDictName);
try {
is = new FileInputStream(file);
} catch (FileNotFoundException e) {
logger.error("ik-analyzer", e);
}
// 如果找不到扩展的字典，则忽略
if (is == null) {
continue;
}
try {
BufferedReader br = new BufferedReader(new InputStreamReader(is, "UTF-8"), 512);
String theWord = null;
do {
theWord = br.readLine();
if (theWord != null && !"".equals(theWord.trim())) {
// 加载扩展词典数据到主内存词典中
_MainDict.fillSegment(theWord.trim().toCharArray());
}
} while (theWord != null);
} catch (IOException e) {
logger.error("ik-analyzer", e);
} finally {
try {
if (is != null) {
is.close();
is = null;
}
} catch (IOException e) {
logger.error("ik-analyzer", e);
}
}
}
}
}
/** 加载主词典及扩展词典 */
private void loadMainDict() {
// 建立一个主词典实例
_MainDict = new DictSegment((char) 0);
// 读取主词典文件
File file = new File(configuration.getDictRoot(), Dictionary.PATH_DIC_MAIN);
InputStream is = null;
try {
is = new FileInputStream(file);
} catch (FileNotFoundException e) {
e.printStackTrace();
}
try {
BufferedReader br = new BufferedReader(new InputStreamReader(is, "UTF-8"), 512);
String theWord = null;
do {
theWord = br.readLine();
if (theWord != null && !"".equals(theWord.trim())) {
_MainDict.fillSegment(theWord.trim().toCharArray());
}
} while (theWord != null);
} catch (IOException e) {
logger.error("ik-analyzer", e);
} finally {
try {
if (is != null) {
is.close();
is = null;
}
} catch (IOException e) {
logger.error("ik-analyzer", e);
}
}
// 加载扩展词典
this.loadExtDict();
}
/** 加载用户扩展的停止词词典 */
private void loadStopWordDict() {
// 建立主词典实例
_StopWords = new DictSegment((char) 0);
// 读取主词典文件
File file = new File(configuration.getDictRoot(), Dictionary.PATH_DIC_STOP);
InputStream is = null;
try {
is = new FileInputStream(file);
} catch (FileNotFoundException e) {
e.printStackTrace();
}
try {
BufferedReader br = new BufferedReader(new InputStreamReader(is, "UTF-8"), 512);
String theWord = null;
do {
theWord = br.readLine();
if (theWord != null && !"".equals(theWord.trim())) {
_StopWords.fillSegment(theWord.trim().toCharArray());
}
} while (theWord != null);
} catch (IOException e) {
logger.error("ik-analyzer", e);
} finally {
try {
if (is != null) {
is.close();
is = null;
}
} catch (IOException e) {
logger.error("ik-analyzer", e);
}
}
// 加载扩展停止词典
List<String> extStopWordDictFiles = configuration.getExtStopWordDictionarys();
if (extStopWordDictFiles != null) {
is = null;
for (String extStopWordDictName : extStopWordDictFiles) {
logger.info("[Dict Loading]" + extStopWordDictName);
// 读取扩展词典文件
file = new File(configuration.getDictRoot(), extStopWordDictName);
try {
is = new FileInputStream(file);
} catch (FileNotFoundException e) {
logger.error("ik-analyzer", e);
}
// 如果找不到扩展的字典，则忽略
if (is == null) {
continue;
}
try {
BufferedReader br = new BufferedReader(new InputStreamReader(is, "UTF-8"), 512);
String theWord = null;
do {
theWord = br.readLine();
if (theWord != null && !"".equals(theWord.trim())) {
// 加载扩展停止词典数据到内存中
_StopWords.fillSegment(theWord.trim().toCharArray());
}
} while (theWord != null);
} catch (IOException e) {
logger.error("ik-analyzer", e);
} finally {
try {
if (is != null) {
is.close();
is = null;
}
} catch (IOException e) {
logger.error("ik-analyzer", e);
}
}
}
}
}
/**
* 从已匹配的Hit中直接取出DictSegment，继续向下匹配
*
* @return Hit
*/
public Hit matchWithHit(char[] charArray, int currentIndex, Hit matchedHit) {
DictSegment ds = matchedHit.getMatchedDictSegment();
return ds.match(charArray, currentIndex, 1, matchedHit);
}