update 文档拆分
This commit is contained in:
+28
-2
@@ -375,8 +375,8 @@ public class FileSpiltService {
|
||||
startDigit = getOneStartDigit(paragraphString, enumByValue);
|
||||
}
|
||||
for (int i = 0; i < nowStart.size(); i++) {
|
||||
// if (paragraphString.startsWith(nowStart.get(i))) {
|
||||
if (startDigit.equals(nowStart.get(i))) {
|
||||
if (startDigit.startsWith(nowStart.get(i))) {
|
||||
//if (startDigit.equals(nowStart.get(i))) {
|
||||
// 判断真的是标题还是干扰项 TODO
|
||||
if (nowStart.get(i).matches(regex)) {
|
||||
boolean result = fileSplitPdfService.judge(preName, preNameNum, startDigit, g, startDigitList, ".");
|
||||
@@ -1063,4 +1063,30 @@ public class FileSpiltService {
|
||||
}
|
||||
return "";
|
||||
}
|
||||
|
||||
public static void main(String[] args) {
|
||||
String regex="[^\\p{Punct}\\p{Space}\\p{Digit}]";
|
||||
String arr = "A.1.1 AAA但是发斯蒂芬士大夫是";
|
||||
String start = arr.substring(0, 1);
|
||||
String regexStart="\\p{Alpha}";
|
||||
Matcher matcher1;
|
||||
matcher1 = Pattern.compile(regexStart).matcher(start);
|
||||
|
||||
Matcher matcher;
|
||||
matcher = Pattern.compile(regex).matcher(arr);
|
||||
|
||||
if(matcher.find()) {
|
||||
int index = matcher.start();
|
||||
String startDigit = arr.substring(0, index);
|
||||
startDigit = startDigit.replaceAll(" ", "");
|
||||
if(StringUtils.isNotBlank(startDigit)) {
|
||||
String s = startDigit.replaceAll("\t", "").replaceAll("\b", "")
|
||||
.replaceAll("\"", "").replaceAll("\'", "");
|
||||
if(matcher1.find()) {
|
||||
s = regexStart+s;
|
||||
}
|
||||
System.out.println(s);
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
Reference in New Issue
Block a user