类似淘宝、京东等电商系统的汉字、拼音检索功能的实现。
在检索商品时,如何根据商品名的首拼、全拼检索商品?
方案一: 在商品表goods中添加两个新字段存放首拼、全拼,让后按一般的字符串去查询。
方案二: 将全拼、首拼放入Lucene索引中,根据Lucene的"多域值"的特性检索。
1.Lucene的知识请自行查询其他资料.
2.汉字拼音、首拼获取如下:
import net.sourceforge.pinyin4j.PinyinHelper;
import net.sourceforge.pinyin4j.format.HanyuPinyinCaseType;import net.sourceforge.pinyin4j.format.HanyuPinyinOutputFormat;import net.sourceforge.pinyin4j.format.HanyuPinyinToneType;import net.sourceforge.pinyin4j.format.HanyuPinyinVCharType;import net.sourceforge.pinyin4j.format.exception.BadHanyuPinyinOutputFormatCombination;public class PingYinUtil { /** * 得到 全拼 * * @param src * @return */ public static String getPingYin(String src) { char[] t1 = null; t1 = src.toCharArray(); String[] t2 = new String[t1.length]; HanyuPinyinOutputFormat t3 = new HanyuPinyinOutputFormat(); t3.setCaseType(HanyuPinyinCaseType.LOWERCASE); t3.setToneType(HanyuPinyinToneType.WITHOUT_TONE); t3.setVCharType(HanyuPinyinVCharType.WITH_V); String t4 = ""; int t0 = t1.length; try { for (int i = 0; i < t0; i++) { // 判断是否为汉字字符 if (java.lang.Character.toString(t1[i]).matches("[\\u4E00-\\u9FA5]+")) { t2 = PinyinHelper.toHanyuPinyinStringArray(t1[i], t3); t4 += t2[0]; } else { t4 += java.lang.Character.toString(t1[i]); } } return t4; } catch (BadHanyuPinyinOutputFormatCombination e1) { e1.printStackTrace(); } return t4; } /** * 得到中文首字母 * * @param str * @return */ public static String getPinYinHeadChar(String str) { String convert = ""; for (int j = 0; j < str.length(); j++) { char word = str.charAt(j); String[] pinyinArray = PinyinHelper.toHanyuPinyinStringArray(word); if (pinyinArray != null) { convert += pinyinArray[0].charAt(0); } else { convert += word; } } return convert; } /** * 将字符串转移为ASCII码 * * @param cnStr * @return */ public static String getCnASCII(String cnStr) { StringBuffer strBuf = new StringBuffer(); byte[] bGBK = cnStr.getBytes(); for (int i = 0; i < bGBK.length; i++) { // System.out.println(Integer.toHexString(bGBK[i]&0xff)); strBuf.append(Integer.toHexString(bGBK[i] & 0xff)); } return strBuf.toString(); }}