根据规则提取字符串中的内容

提取稿件内容文末的署名
以下格式：

 

/**
 * 提取编辑器署名
 */
String TEMPLATE_WORDS_REPORT = "文/广州日报·新花城记者：";
String TEMPLATE_IMG_REPORT = "图/广州日报·新花城记者：";
String TEMPLATE_VIDEO_REPORT = "视频/广州日报·新花城记者：";
String TEMPLATE_WORDS_IMG_REPORT = "文、图/广州日报·新花城记者：";
String TEMPLATE_TXY = "通讯员：";
String TEMPLATE_EDITOR = "广州日报·新花城编辑：";

@ResponseBody
@RequestMapping(value = "/test1")
public String test1() {

    TCmsContentVo content = dataHelper.getContent("e679bbb1c78c4a4a961e34cc7ba4c209");
    // 媒体号
    String txt = content.getTxt();
    String result = "";
    String wordsReport = extractStr(txt, PublishConstants.TEMPLATE_WORDS_REPORT);
    String imgReport = extractStr(txt, PublishConstants.TEMPLATE_IMG_REPORT);
    String videoReport = extractStr(txt, PublishConstants.TEMPLATE_VIDEO_REPORT);
    String wordsImgReport = extractStr(txt, PublishConstants.TEMPLATE_WORDS_IMG_REPORT);
    String editor = extractStr(txt, PublishConstants.TEMPLATE_EDITOR);
    result = addStr(result, wordsReport);
    result = addStr(result, imgReport);
    result = addStr(result, videoReport);
    result = addStr(result, wordsImgReport);
    result = addStr(result, editor);

    // 过滤特殊字符并提取汉字
    reportNames = getChinese(reportNames);

    // 记者信息
    String reporterStr = content.getReporter();

    JSONArray reporterArr = new JSONArray();
    if (StringUtils.isNotBlank(reporterStr)) {
        JSONArray reporterArray = JSONArray.fromObject(reporterStr);
        for (Object reporter : reporterArray) {
            JSONObject reporterObj = JSONObject.fromObject(reporter);
            String reporterName = reporterObj.getString("reporterName");
            result += "," + reporterName;
        }
    }
    result = reomveRepeat(result);



    return result;
}

private String addStr(String str, String add) {
    if (str != null && !"".equals(str)) {
        if (add != null && !"".equals(add)) {
            str += "," + add;
        }
    } else {
        if (add != null && !"".equals(add)) {
            str = add;
        }
    }

    return str;
}

private String reomveRepeat(String str){//数组去重
    StringBuffer reStr = new StringBuffer();
    if(reStr != null && !"".equals(reStr)){
        String [] curr = str.split(",");
        Set set = new HashSet();
        for(String index:curr){//去重
            set.add(index);
        }
        Object[] array = set.toArray();
        String splitSetWithComma = StringUtils.join(array, ",");
        reStr.append(splitSetWithComma) ;
    }
    return reStr.toString();
}


public String extractStr(String txt, String ruleStr) {
    // 返回结构
    String result = "";
    // 截取规则之后的字符串
    String wordsReportStr = "";
    // 截取规则至</p>的字符串
    String wordsPStr = "";
    // 截取通讯录字符串
    String wordsTXYStr = "";
    // 通讯录
    String txl = "";
    // </p>所在位置
    int wordsPInt = -1;
    // 通讯录所在位置
    int wordsTXYInt = -1;
    // </span>所在位置
    int wordsSpanInt = -1;

    // 取得规则所在位置
    int wordsReportInt = txt.indexOf(ruleStr);
    // 如果存在
    if (wordsReportInt != -1) {
        // 截取规则字符串
        wordsReportStr = txt.substring(wordsReportInt);

        // 截至到“</p>”
        wordsPInt = wordsReportStr.indexOf("</p>");
        if (wordsPInt != -1) {
            wordsPStr = wordsReportStr.substring(ruleStr.length(), wordsPInt);
            // 如果有通讯员
            wordsTXYInt = wordsPStr.indexOf(PublishConstants.TEMPLATE_TXY);
            if (wordsTXYInt != -1) {
                result = wordsPStr.substring(0, wordsTXYInt);
                wordsTXYStr = wordsPStr.substring(wordsTXYInt);

                // 是否有</span>
                wordsSpanInt = wordsTXYStr.indexOf("</span>");
                if (wordsSpanInt != -1) {
                    txl = wordsTXYStr.substring(PublishConstants.TEMPLATE_TXY.length(), wordsSpanInt);
                    result = result.trim() + "," +txl.trim();
                } else {
                    txl = wordsTXYStr.substring(PublishConstants.TEMPLATE_TXY.length());
                    result = result.trim() + "," +txl.trim();
                }

            } else {
                // 没有通讯员，是否有</span>
                wordsSpanInt = wordsPStr.indexOf("</span>");
                if (wordsSpanInt != -1) {
                    result = wordsPStr.substring(0, wordsSpanInt);
                    result = result.trim();
                } else {
                    result = wordsPStr.trim();
                }
            }

        }

    }
    result = result.replace("<br/>","");
    result = result.replace("&nbsp;","");
    return result;
}

/*1、至少匹配一个汉字的写法。
 2、这两个unicode值正好是Unicode表中的汉字的头和尾。
 3、"[]"代表里边的值出现一个就可以，后边的“+”代表至少出现1次，合起来即至少匹配一个汉字。
*/
public static String getChinese(String paramValue) {
    paramValue = paramValue.replace("<br/>","");
    paramValue = paramValue.replace("&nbsp;","");
    paramValue = paramValue.replace("、",",");

    String regex = "([\u4e00-\u9fa5,]+)";
    String str = "";
    Matcher matcher = Pattern.compile(regex).matcher(paramValue);
    while (matcher.find()) {
        str+= matcher.group(0);
    }
    return str;
}