日志

trans/src/main/java/com/lantone/qc/trans/ningbozhenhai/FirstCourseRecordDocTrans.java

@@ -55,7 +55,9 @@ public class FirstCourseRecordDocTrans extends ModelDocTrans {
             }
             if (MapUtils.isNotEmpty(structureMap)) {
                 firstCourseRecordDoc = ModelDocGenerate.firstCourseRecordDocGen(structureMap);
+                log.error("首次病程录（html）：" + content);
                 firstCourseRecordDoc.setText(CommonAnalysisUtil.html2String(content));
+                log.error("首次病程录（文本）：" + firstCourseRecordDoc.getText());
                 firstCourseRecordDoc.setPageData((Map) structureMap);
                 List<String> keys = Lists.newArrayList("需求评估", "预期目标", "诊疗计划", "治疗监测计划");
                 String treatPlanJoin = structureMapJoin(structureMap, keys);

trans/src/main/java/com/lantone/qc/trans/ningbozhenhai/util/CommonAnalysisUtil.java

@@ -1,6 +1,8 @@
 package com.lantone.qc.trans.ningbozhenhai.util;
 
 import com.google.common.collect.Lists;
+import com.lantone.qc.pub.util.StringUtil;
+import lombok.extern.slf4j.Slf4j;
 
 import java.util.*;
 import java.util.stream.Collectors;
@@ -10,6 +12,7 @@ import java.util.stream.Collectors;
  * @Author : zhaops
  * @Date 2022/7/25 15:56
  */
+@Slf4j
 public class CommonAnalysisUtil {
     /**
      * 将title根据在文本中的位置排序
@@ -50,4 +53,52 @@ public class CommonAnalysisUtil {
         titles = Lists.newArrayList(titleIndex.values());
         return titles;
     }
-}
+
+    /**
+     * 根据文书各标题截取相应文本，存入structmap中
+     *
+     * @param line         原始文本
+     * @param titles       文书各标题
+     * @param depth        递归深度，也就是titles取值时的下标值
+     * @param structureMap 存储结构化数据
+     */
+    public static void cutByTitles(String line, List<String> titles, int depth, Map<String, String> structureMap) {
+        if (depth > titles.size() || titles.size() == 0) {
+            return;
+        }
+        String beforeTitle = null, title = null, newTitle = null, value = null;
+        beforeTitle = StringUtil.removeBlank(titles.get(Math.max(depth - 1, 0)));
+        title = titles.get(Math.min(depth, titles.size() - 1));
+        if (depth == titles.size()) {
+            /*if (line.contains("\n")) {
+                line = line.split("\n")[0];
+            }
+            */
+            value = line.replace("\n", "");
+            if (StringUtil.isBlank(structureMap.get(beforeTitle))) {
+                log.error("key：" + beforeTitle + "\n value：" + StringUtil.trim(value));
+                structureMap.put(beforeTitle, StringUtil.trim(value));
+            }
+            return;
+        }
+        if (line.contains(title + "：") || line.contains(title + ":")) {
+            if (line.contains(title + "：")) {
+                newTitle = title + "：";
+            } else {
+                newTitle = title + ":";
+            }
+            if (depth > 0) {
+                value = line.substring(0, line.indexOf(newTitle));
+                if (StringUtil.isBlank(structureMap.get(beforeTitle))) {
+                    log.error("key：" + beforeTitle + "\n value：" + StringUtil.trim(value).replace("\n", ""));
+                    structureMap.put(beforeTitle, StringUtil.trim(value).replace("\n", ""));
+                }
+            }
+            line = line.substring(line.indexOf(newTitle) + newTitle.length());
+            depth++;
+        } else {
+            titles.remove(depth);
+        }
+        cutByTitles(line, titles, depth, structureMap);
+    }
+}

trans/src/main/java/com/lantone/qc/trans/ningbozhenhai/util/FirstCourseRecordHtmlAnalysis.java

@@ -10,6 +10,7 @@ import org.jsoup.nodes.Document;
 
 import java.util.List;
 import java.util.Map;
+import java.util.stream.Collectors;
 
 /**
  * @Description:
@@ -34,8 +35,10 @@ public class FirstCourseRecordHtmlAnalysis implements HtmlAnalysis {
                     .replace("第1页", "");
             CommonAnalysisUtil.extractWardInfo(recTitle, htmlContent, structureMap);
             if (StringUtil.isNotBlank(htmlContent)) {
+                log.error("首次病程录："+htmlContent);
                 titles = com.lantone.qc.trans.ningbozhenhai.util.CommonAnalysisUtil.sortTitles(titles, htmlContent);
-                CommonAnalysisUtil.cutByTitles(htmlContent, titles, 0, structureMap);
+                log.error("titles："+titles.stream().collect(Collectors.joining(",")));
+                com.lantone.qc.trans.ningbozhenhai.util.CommonAnalysisUtil.cutByTitles(htmlContent, titles, 0, structureMap);
                 if (!structureMap.containsKey("诊断依据")) {
                     String zdyj = "";
                     if (structureMap.containsKey("西医诊断依据")) {