net.sourceforge.pinyin4j.format.HanyuPinyinOutputFormat#setVCharType

Source File: StringHelper.java From wind-im with Apache License 2.0

6 votes

public static String toLatinPinYin(String text) {
	// format for string
	HanyuPinyinOutputFormat format = new HanyuPinyinOutputFormat();
	format.setToneType(HanyuPinyinToneType.WITHOUT_TONE);
	format.setCaseType(HanyuPinyinCaseType.LOWERCASE);// 小写
	format.setVCharType(HanyuPinyinVCharType.WITH_U_UNICODE);

	char[] input = StringUtils.trimToEmpty(text).toCharArray();
	StringBuffer result = new StringBuffer();
	try {
		for (char ch : input) {
			if (Character.toString(ch).matches("[\\u4E00-\\u9FA5]+")) {
				String[] temp = PinyinHelper.toHanyuPinyinStringArray(ch, format);
				result.append(temp[0]);
			} else
				result.append(Character.toString(ch));
		}
	} catch (BadHanyuPinyinOutputFormatCombination e) {
		logger.error("string to latin pinyin error", e);
	}
	return result.toString();
}

Source File: ChineseToEnglish.java From MeetMusic with Apache License 2.0

6 votes

/**
 * 返回一个字的拼音
 */
public static String toPinYin(char hanzi) {
    HanyuPinyinOutputFormat hanyuPinyin = new HanyuPinyinOutputFormat();
    hanyuPinyin.setCaseType(HanyuPinyinCaseType.LOWERCASE);
    hanyuPinyin.setToneType(HanyuPinyinToneType.WITHOUT_TONE);
    hanyuPinyin.setVCharType(HanyuPinyinVCharType.WITH_U_UNICODE);
    String[] pinyinArray = null;
    try {
        //是否在汉字范围内
        if (hanzi >= 0x4e00 && hanzi <= 0x9fa5) {
            pinyinArray = PinyinHelper.toHanyuPinyinStringArray(hanzi, hanyuPinyin);
        }
    } catch (BadHanyuPinyinOutputFormatCombination e) {
        e.printStackTrace();
        Log.e(TAG, "toPinYin: hanzi = "+hanzi );
        Log.e(TAG, "toPinYin: pinyinArray.toString() = "+pinyinArray.toString() );
    }
    //将获取到的拼音返回
    if (pinyinArray != null && pinyinArray.length > 0) {
        return pinyinArray[0];
    } else {
        Log.e(TAG, "toPinYin: hanzi = "+hanzi );
        return "#";
    }
}

Source File: StringHelper.java From openzaly with Apache License 2.0

6 votes

public static String toLatinPinYin(String text) {
	// format for string
	HanyuPinyinOutputFormat format = new HanyuPinyinOutputFormat();
	format.setToneType(HanyuPinyinToneType.WITHOUT_TONE);
	format.setCaseType(HanyuPinyinCaseType.LOWERCASE);// 小写
	format.setVCharType(HanyuPinyinVCharType.WITH_U_UNICODE);

	char[] input = StringUtils.trimToEmpty(text).toCharArray();
	StringBuffer result = new StringBuffer();
	try {
		for (char ch : input) {
			if (Character.toString(ch).matches("[\\u4E00-\\u9FA5]+")) {
				String[] temp = PinyinHelper.toHanyuPinyinStringArray(ch, format);
				result.append(temp[0]);
			} else
				result.append(Character.toString(ch));
		}
	} catch (BadHanyuPinyinOutputFormatCombination e) {
		logger.error("string to latin pinyin error", e);
	}
	return result.toString();
}

Source File: StringHelper.java From openzaly with Apache License 2.0

6 votes

public static String toLatinPinYin(String text) {
	// format for string
	HanyuPinyinOutputFormat format = new HanyuPinyinOutputFormat();
	format.setToneType(HanyuPinyinToneType.WITHOUT_TONE);
	format.setCaseType(HanyuPinyinCaseType.LOWERCASE);// 小写
	format.setVCharType(HanyuPinyinVCharType.WITH_U_UNICODE);

	char[] input = StringUtils.trimToEmpty(text).toCharArray();
	StringBuffer result = new StringBuffer();
	try {
		for (char ch : input) {
			if (Character.toString(ch).matches("[\\u4E00-\\u9FA5]+")) {
				String[] temp = PinyinHelper.toHanyuPinyinStringArray(ch, format);
				result.append(temp[0]);
			} else
				result.append(Character.toString(ch));
		}
	} catch (BadHanyuPinyinOutputFormatCombination e) {
		logger.error("string to latin pinyin error", e);
	}
	return result.toString();
}

Source File: ChineseToEnglish.java From AndroidDemo with MIT License

6 votes

/**
 * 返回一个字的拼音
 */
public static String toPinYin(char hanzi) {
    HanyuPinyinOutputFormat hanyuPinyin = new HanyuPinyinOutputFormat();
    hanyuPinyin.setCaseType(HanyuPinyinCaseType.LOWERCASE);
    hanyuPinyin.setToneType(HanyuPinyinToneType.WITHOUT_TONE);
    hanyuPinyin.setVCharType(HanyuPinyinVCharType.WITH_U_UNICODE);
    String[] pinyinArray = null;
    try {
        //是否在汉字范围内
        if (hanzi >= 0x4e00 && hanzi <= 0x9fa5) {
            pinyinArray = PinyinHelper.toHanyuPinyinStringArray(hanzi, hanyuPinyin);
        }
    } catch (BadHanyuPinyinOutputFormatCombination e) {
        e.printStackTrace();
        Log.e(TAG, "toPinYin: hanzi = "+hanzi );
        Log.e(TAG, "toPinYin: pinyinArray.toString() = "+pinyinArray.toString() );
    }
    //将获取到的拼音返回
    if (pinyinArray != null && pinyinArray.length > 0) {
        return pinyinArray[0];
    } else {
        Log.e(TAG, "toPinYin: hanzi = "+hanzi );
        return "#";
    }
}

Source File: ChinesUtil.java From utils with Apache License 2.0

6 votes

/**
 * 将字符串中的中文转化为拼音,其他字符不变.
 *
 * @param inputString
 * @return
 */
public static String getPingYin(String inputString) {
    HanyuPinyinOutputFormat format = new HanyuPinyinOutputFormat();
    format.setCaseType(HanyuPinyinCaseType.LOWERCASE);
    format.setToneType(HanyuPinyinToneType.WITHOUT_TONE);
    format.setVCharType(HanyuPinyinVCharType.WITH_V);

    char[] input = inputString.trim().toCharArray();
    StringBuffer output = new StringBuffer();

    try {
        for (int i = 0; i < input.length; i++) {
            if (Character.toString(input[i]).matches("[\\u4E00-\\u9FA5]+")) {
                String[] temp = PinyinHelper.toHanyuPinyinStringArray(input[i], format);
                output.append(temp[0]);
            } else {
                output.append(Character.toString(input[i]));
            }
        }
    } catch (BadHanyuPinyinOutputFormatCombination e) {
        e.printStackTrace();
    }
    return output.toString();
}

Source File: PinyinConverter.java From py4j with Apache License 2.0

6 votes

@Override
public String[] getPinyin(char ch) throws IllegalPinyinException {
	try{
		HanyuPinyinOutputFormat outputFormat = new HanyuPinyinOutputFormat();
		outputFormat.setToneType(HanyuPinyinToneType.WITHOUT_TONE);
		outputFormat.setCaseType(HanyuPinyinCaseType.LOWERCASE);
		outputFormat.setVCharType(HanyuPinyinVCharType.WITH_V);

		if(ch>=32 && ch<=125){	//ASCII >=33 ASCII<=125的直接返回 ,ASCII码表：http://www.asciitable.com/
			return new String[]{String.valueOf(ch)};
		}
		return ArrayUtils.distinct(PinyinHelper.toHanyuPinyinStringArray(ch, outputFormat));
	} catch (BadHanyuPinyinOutputFormatCombination e) {
		throw new IllegalPinyinException(e);
	}

}

Source File: PinyinTest.java From TinyPinyin with Apache License 2.0

6 votes

@Test
public void testIsChinese() throws BadHanyuPinyinOutputFormatCombination {
    char[] allChars = allChars();
    final int allCharsLength = allChars.length;
    HanyuPinyinOutputFormat format = new HanyuPinyinOutputFormat();
    format.setToneType(HanyuPinyinToneType.WITHOUT_TONE);
    format.setCaseType(HanyuPinyinCaseType.UPPERCASE);
    format.setVCharType(HanyuPinyinVCharType.WITH_V);

    for (int i = 0; i < allCharsLength; i++) {
        char targetChar = allChars[i];
        String[] pinyins = PinyinHelper.toHanyuPinyinStringArray(targetChar, format);
        if (pinyins != null && pinyins.length > 0) {
            // is chinese
            assertThat(Pinyin.isChinese(targetChar), is(true));
        } else {
            // not chinese
            assertThat(Pinyin.isChinese(targetChar), is(false));
        }
    }
}

Source File: UDFChineseToPinYin.java From hive-third-functions with Apache License 2.0

5 votes

public String ConvertToPinyin(String name) {
    HanyuPinyinOutputFormat pyFormat = new HanyuPinyinOutputFormat();
    pyFormat.setCaseType(HanyuPinyinCaseType.LOWERCASE);
    pyFormat.setToneType(HanyuPinyinToneType.WITHOUT_TONE);
    pyFormat.setVCharType(HanyuPinyinVCharType.WITH_V);

    String result = null;
    try {
        result = PinyinHelper.toHanyuPinyinString(name, pyFormat, "");
    } catch (BadHanyuPinyinOutputFormatCombination e) {
        return null;
    }

    return result;
}

Source File: PinyinTest.java From TinyPinyin with Apache License 2.0

5 votes

@Test
public void testToPinyin_char() throws BadHanyuPinyinOutputFormatCombination {
    char[] allChars = allChars();
    final int allCharsLength = allChars.length;
    HanyuPinyinOutputFormat format = new HanyuPinyinOutputFormat();
    format.setToneType(HanyuPinyinToneType.WITHOUT_TONE);
    format.setCaseType(HanyuPinyinCaseType.UPPERCASE);
    format.setVCharType(HanyuPinyinVCharType.WITH_V);

    int chineseCount = 0;
    for (int i = 0; i < allCharsLength; i++) {
        char targetChar = allChars[i];
        String[] pinyins = PinyinHelper.toHanyuPinyinStringArray(targetChar, format);
        if (pinyins != null && pinyins.length > 0) {
            // is chinese
            chineseCount++;
            assertThat(Pinyin.toPinyin(targetChar), equalTo(pinyins[0]));
        } else {
            // not chinese
            assertThat(Pinyin.toPinyin(targetChar), equalTo(String.valueOf(targetChar)));
        }
    }

    //CHECKSTYLE:OFF
    int expectedChineseCount = 20378;
    //CHECKSTYLE:ON

    assertThat(chineseCount, is(expectedChineseCount));
}

Source File: PinYin.java From FamilyChat with Apache License 2.0

5 votes

/**
 * 获取汉字串拼音，英文字符不变(均返回大写)
 *
 * @return 汉语拼音
 */
public static String getFull(String src)
{
    char[] t1;
    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 (Character.toString(t1[i]).matches("[\\u4E00-\\u9FA5]+"))
            {
                t2 = PinyinHelper.toHanyuPinyinStringArray(t1[i], t3);
                t4 += t2[0];
            } else
            {
                t4 += Character.toString(t1[i]);
            }
        }
        return t4.toUpperCase();
    } catch (Exception e1)
    {
        e1.printStackTrace();
        t4 = "";
    }
    return t4.toUpperCase();
}

Source File: FileUtil.java From AndroidAnimationExercise with Apache License 2.0

5 votes

/**
 * 汉字转拼音
 *
 * @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]);
        }
        // System.out.println(t4);
        return t4;
    } catch (BadHanyuPinyinOutputFormatCombination e1) {
        e1.printStackTrace();
    }
    return t4;
}

Source File: ShortTextSearcher.java From short-text-search with Apache License 2.0

5 votes

public String getPinYin(String words, boolean acronym) {
    HanyuPinyinOutputFormat format = new HanyuPinyinOutputFormat();
    format.setCaseType(HanyuPinyinCaseType.LOWERCASE);
    format.setToneType(HanyuPinyinToneType.WITHOUT_TONE);
    format.setVCharType(HanyuPinyinVCharType.WITH_U_UNICODE);
    char[] chars = words.trim().toCharArray();
    StringBuilder result = new StringBuilder();
    int ignoredCount = 0;
    try {
        for (char c : chars) {
            if(!isChinese(c)){
                ignoredCount++;
                result.append(c);
                continue;
            }
            String[] pinyinStringArray = PinyinHelper.toHanyuPinyinStringArray(c, format);
            if(acronym){
                result.append(pinyinStringArray[0].charAt(0));
            }else {
                String pinYin = pinyinStringArray[0].toLowerCase().replace("ü", "v");
                if(StringUtils.isBlank(pinYin)){
                    continue;
                }
                result.append(pinYin);
                charPinYin.add(pinYin);
                if(pinYin.length() > charMaxPinYinLength){
                    charMaxPinYinLength = pinYin.length();
                }
            }
        }
    } catch (Exception e) {
        LOGGER.error("获取拼音失败: "+words, e);
    }
    if(ignoredCount == chars.length){
        return null;
    }
    return result.toString().toLowerCase();
}

Source File: PinyinUtil.java From util with Apache License 2.0

5 votes

/**
 * 将汉字转为拼音。例如：中国转为zhongguo。
 * @param 源汉字
 * @return 转换后的拼音，如果转换异常返回null。
 */
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 null;
	}
}

Source File: PinyinUtil.java From apkextractor with GNU General Public License v3.0

5 votes

/**
 * 将字符串中的中文转化为拼音,其他字符不变
 * @param inputString
 * @return
 */
public static String getPinYin(String inputString) {
    HanyuPinyinOutputFormat format = new HanyuPinyinOutputFormat();
    format.setCaseType(HanyuPinyinCaseType.LOWERCASE);
    format.setToneType(HanyuPinyinToneType.WITHOUT_TONE);
    format.setVCharType(HanyuPinyinVCharType.WITH_V);

    char[] input = inputString.trim().toCharArray();
    StringBuilder output = new StringBuilder();

    try {
        for (int i = 0; i < input.length; i++) {
            if (java.lang.Character.toString(input[i]).matches("[\\u4E00-\\u9FA5]+")) {
                String[] temp = PinyinHelper.toHanyuPinyinStringArray(input[i], format);
                output.append(temp[0]);
            } else
                output.append(input[i]);
        }
    } catch (BadHanyuPinyinOutputFormatCombination e) {
        e.printStackTrace();
    }
    catch(java.lang.NullPointerException npex){
        npex.printStackTrace();
    }
    catch(Exception ex){
        ex.printStackTrace();
    }
    return output.toString();
}

Source File: PinyinUtil.java From hdw-dubbo with Apache License 2.0

5 votes

/**
 * 将汉字转换为全拼
 *
 * @param src
 * @return String
 */
public static final String getCamelPinYin(String src) {
    char[] t1 = null;
    t1 = src.toCharArray();
    String[] t2 = new String[t1.length];
    // 设置汉字拼音输出的格式
    HanyuPinyinOutputFormat t3 = new HanyuPinyinOutputFormat();
    t3.setCaseType(HanyuPinyinCaseType.LOWERCASE);
    t3.setToneType(HanyuPinyinToneType.WITHOUT_TONE);
    t3.setVCharType(HanyuPinyinVCharType.WITH_V);
    String t4 = "", t = "";
    int t0 = t1.length;
    try {
        for (int i = 0; i < t0; i++) {
            // 判断是否为汉字字符
            if (Character.toString(t1[i]).matches("[\\u4E00-\\u9FA5]+")) {
                t2 = PinyinHelper.toHanyuPinyinStringArray(t1[i], t3);// 将汉字的几种全拼都存到t2数组中
                t = t2[0];// 取出该汉字全拼的第一种读音并连接到字符串t4后
            } else {
                // 如果不是汉字字符，直接取出字符并连接到字符串t4后
                t = Character.toString(t1[i]);
            }
            t = t.substring(0, 1).toUpperCase() + t.substring(1);
            t4 += t;
        }
    } catch (BadHanyuPinyinOutputFormatCombination e) {
        logger.error("", e);
    }
    return t4;
}

Source File: PinyinUtil.java From hdw-dubbo with Apache License 2.0

5 votes

/**
 * 将汉字转换为全拼
 *
 * @param src
 * @return String
 */
public static final String getPinYin(String src) {
    if (src == null) {
        return "";
    }
    char[] t1 = null;
    t1 = src.toCharArray();
    String[] t2 = new String[t1.length];
    // 设置汉字拼音输出的格式
    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 (Character.toString(t1[i]).matches("[\\u4E00-\\u9FA5]+")) {
                t2 = PinyinHelper.toHanyuPinyinStringArray(t1[i], t3);// 将汉字的几种全拼都存到t2数组中
                t4 += t2[0];// 取出该汉字全拼的第一种读音并连接到字符串t4后
            } else {
                // 如果不是汉字字符，直接取出字符并连接到字符串t4后
                t4 += Character.toString(t1[i]);
            }
        }
    } catch (BadHanyuPinyinOutputFormatCombination e) {
        logger.error("", e);
    }
    return t4;
}

Source File: PingYinUtils.java From BigApp_Discuz_Android with Apache License 2.0

5 votes

/**
 * 将字符串中的中文转化为拼音,其他字符不变
 *
 * @param inputString
 * @return
 */
public static String getPingYin(String inputString) {
    HanyuPinyinOutputFormat format = new
            HanyuPinyinOutputFormat();
    format.setCaseType(HanyuPinyinCaseType.LOWERCASE);
    format.setToneType(HanyuPinyinToneType.WITHOUT_TONE);
    format.setVCharType(HanyuPinyinVCharType.WITH_V);

    char[] input = inputString.trim().toCharArray();
    String output = "";

    try {
        for (int i = 0; i < input.length; i++) {
            if (java.lang.Character.toString(input[i]).
                    matches("[\\u4E00-\\u9FA5]+")) {
                String[] temp = PinyinHelper.
                        toHanyuPinyinStringArray(input[i],
                                format);
                output += temp[0];
            } else
                output += java.lang.Character.toString(
                        input[i]);
        }
    } catch (BadHanyuPinyinOutputFormatCombination e) {
        e.printStackTrace();
    }
    return output;
}

Source File: StringUtils.java From flash-waimai with MIT License

5 votes

public static String getPingYin(String inputString) {
    HanyuPinyinOutputFormat format = new HanyuPinyinOutputFormat();
    format.setCaseType(HanyuPinyinCaseType.LOWERCASE);
    format.setToneType(HanyuPinyinToneType.WITHOUT_TONE);
    format.setVCharType(HanyuPinyinVCharType.WITH_V);
    String output = "";
    if (inputString != null && inputString.length() > 0
            && !"null".equals(inputString)) {
        char[] input = inputString.trim().toCharArray();
        try {
            for (int i = 0; i < input.length; i++) {
                if (java.lang.Character.toString(input[i]).matches(
                        "[\\u4E00-\\u9FA5]+")) {
                    String[] temp = PinyinHelper.toHanyuPinyinStringArray(
                            input[i], format);
                    output += temp[0];
                } else {
                    output += java.lang.Character.toString(input[i]);
                }
            }
        } catch (BadHanyuPinyinOutputFormatCombination e) {
            e.printStackTrace();
        }
    } else {
        return "*";
    }
    return output;
}

Source File: PinYinUtil.java From code with Apache License 2.0

3 votes

/**
 * 获取汉语拼音格式化器
 * @param caseType 大小写
 *        @see HanyuPinyinCaseType
 *         UPPERCASE：大写  (ZHONG)
 *         LOWERCASE：小写  (zhong)
 * @param toneType 音标格式
 *        @see HanyuPinyinToneType
 *         WITHOUT_TONE：无音标  (zhong)
 *         WITH_TONE_NUMBER：1-4数字表示英标  (zhong4)
 *         WITH_TONE_MARK：直接用音标符（必须WITH_U_UNICODE否则异常）  (zhòng)
 * @param charType charType
 *        @see HanyuPinyinVCharType
 *         WITH_V：用v表示ü  (nv)
 *         WITH_U_AND_COLON：用"u:"表示ü  (nu:)
 *         WITH_U_UNICODE：直接用ü (nü)
 * @return net.sourceforge.pinyin4j.format.HanyuPinyinOutputFormat
 */
public static HanyuPinyinOutputFormat getPinyinFormat(HanyuPinyinCaseType caseType, HanyuPinyinToneType toneType, HanyuPinyinVCharType charType) {
    HanyuPinyinOutputFormat format = new HanyuPinyinOutputFormat();
    format.setCaseType(caseType);
    format.setToneType(toneType);
    format.setVCharType(charType);
    return format;
}

Java Code Examples for net.sourceforge.pinyin4j.format.HanyuPinyinOutputFormat#setVCharType()