Merge remote-tracking branch 'origin/master'

This commit is contained in:
limin 2025-01-06 09:16:23 +08:00
commit 5632c81f29
2 changed files with 26 additions and 12 deletions

View File

@ -1,6 +1,5 @@
package cn.iocoder.yudao.module.llm.service.async;
import cn.hutool.json.JSONArray;
import cn.hutool.json.JSONObject;
import cn.iocoder.yudao.framework.common.util.collection.CollectionUtils;
import cn.iocoder.yudao.framework.common.util.object.BeanUtils;
@ -125,7 +124,7 @@ public class AsyncDataProcessService {
// 繁体转简体 繁体转简体不經意妳的笑容清洗成不经意你的笑容
JSONObject a_4 = a.getJSONObject("a_4");
if (a_4.getBool("is_on")) {
result = DataProcessUtil.TraditionalToSimplified(result);
result = DataProcessUtil.traditionalToSimplified(result);
}
// 去除网页标识符 移除文档中的html标签<html>,<dev><p>
JSONObject a_5 = a.getJSONObject("a_5");

View File

@ -77,7 +77,7 @@ public class DataProcessUtil {
* @param input
* @return
*/
public static String TraditionalToSimplified(String input) {
public static String traditionalToSimplified(String input) {
return ZhConverterUtil.toSimple(input);
}
@ -400,15 +400,16 @@ public class DataProcessUtil {
text = hashMatcher.replaceAll("");
// 使用StringBuilder和StringBuilder的replace方法去除其他数字但跳过年份和简单数字
StringBuilder sb = new StringBuilder(text);
int index = 0;
while ((index = findNextNumberToReplace(sb.toString())) != -1) {
String number = sb.substring(index, findEndOfNumber(sb.toString(), index));
if (!isYear(number) && !isSimpleNumber(number)) {
sb.replace(index, index + number.length(), "");
}
}
return sb.toString();
// TODO: 这里目前有bug先注释掉了
// StringBuilder sb = new StringBuilder(text);
// int index = 0;
// while ((index = findNextNumberToReplace(sb.toString())) != -1) {
// String number = sb.substring(index, findEndOfNumber(sb.toString(), index));
// if (!isYear(number) && !isSimpleNumber(number)) {
// sb.replace(index, index + number.length(), "");
// }
// }
return text;
}
// 查找下一个要替换的数字的起始索引
@ -463,4 +464,18 @@ public class DataProcessUtil {
return false;
}
}
public static void main(String[] args) {
String textWithIdentifiers = "Here are some identifiers: 123-456-7890, 1234567812345678, a1b2c3d4e5f6a1b2c3d4e5f6, 2023, and 987654.";
// 去除标识符
String textWithoutIdentifiers = removeIdentifiers(textWithIdentifiers);
// 打印结果
System.out.println(textWithoutIdentifiers);
String traditionalText = "不經意,妳的笑容";
String simplifiedText = traditionalToSimplified(traditionalText);
System.out.println("繁体文本: [" + traditionalText + "]");
System.out.println("简体文本: [" + simplifiedText + "]");
}
}