|
|
@@ -0,0 +1,641 @@
|
|
|
+package com.lantone.qc.trans.yuhangsy.util.comsis;
|
|
|
+
|
|
|
+import com.google.common.collect.Lists;
|
|
|
+import com.lantone.qc.pub.util.StringUtil;
|
|
|
+import lombok.extern.slf4j.Slf4j;
|
|
|
+import org.jsoup.Jsoup;
|
|
|
+import org.jsoup.nodes.Document;
|
|
|
+import org.jsoup.nodes.Element;
|
|
|
+import org.jsoup.nodes.Node;
|
|
|
+import org.jsoup.select.Elements;
|
|
|
+
|
|
|
+import java.text.ParseException;
|
|
|
+import java.text.SimpleDateFormat;
|
|
|
+import java.util.Date;
|
|
|
+import java.util.List;
|
|
|
+import java.util.Map;
|
|
|
+import java.util.TreeMap;
|
|
|
+import java.util.regex.Matcher;
|
|
|
+import java.util.regex.Pattern;
|
|
|
+
|
|
|
+/**
|
|
|
+ * @Description :余杭三院自定义
|
|
|
+ * @Author : HUJING
|
|
|
+ * @Date: 2020/9/10 13:48
|
|
|
+ */
|
|
|
+@Slf4j
|
|
|
+public class YuhangsyCommonAnalysisUtil {
|
|
|
+
|
|
|
+ /**
|
|
|
+ * 取文书中全部文本
|
|
|
+ *
|
|
|
+ * @param html
|
|
|
+ * @return
|
|
|
+ */
|
|
|
+ public static String html2String(String html) {
|
|
|
+ try {
|
|
|
+ Document document = Jsoup.parse(html);
|
|
|
+ Element body = document.select("body").first();
|
|
|
+ List<Node> nodes = body.childNodes();
|
|
|
+ Node node = nodes.get(0);
|
|
|
+ if (" ".equals(node.toString())) {
|
|
|
+ node = nodes.get(1);
|
|
|
+ }
|
|
|
+ String htmlContent = null;
|
|
|
+ if (node instanceof Element) {
|
|
|
+ Element element = (Element) node;
|
|
|
+ htmlContent = element.text();
|
|
|
+ }
|
|
|
+ return htmlContent;
|
|
|
+ } catch (Exception e) {
|
|
|
+ log.error(e.getMessage(), e);
|
|
|
+ return "";
|
|
|
+ }
|
|
|
+ }
|
|
|
+
|
|
|
+ public static void html2StructureMap(List<String> titles, String htmlText, Map<String, String> structureMap) {
|
|
|
+ List<String> sortTitles = sortTitles(titles, htmlText);
|
|
|
+ cutByTitles(htmlText, sortTitles, 0, structureMap);
|
|
|
+ }
|
|
|
+
|
|
|
+ /**
|
|
|
+ * 将html内容以行为单位存进list,从<hr>之后开始处理
|
|
|
+ *
|
|
|
+ * @param html 原始html内容
|
|
|
+ * @return
|
|
|
+ */
|
|
|
+ public List<String> html2List(String html, boolean existHr) {
|
|
|
+ List<String> htmlText = Lists.newArrayList();
|
|
|
+ Document document = Jsoup.parse(html);
|
|
|
+ Element body = document.select("body").first();
|
|
|
+ List<Node> nodes = body.childNodes();
|
|
|
+ List<Node> subNodes = nodes.get(0).childNodes();
|
|
|
+ boolean findNode = false;
|
|
|
+ for (Node node : subNodes) {
|
|
|
+ if ("hr".equals(node.nodeName())) {
|
|
|
+ findNode = true;
|
|
|
+ continue;
|
|
|
+ }
|
|
|
+ if (findNode || !existHr) {
|
|
|
+ Element element = (Element) node;
|
|
|
+ Elements elements = element.select("div");
|
|
|
+ for (Element e : elements) {
|
|
|
+ String text = e.text();
|
|
|
+ if (text.length() > 150) {
|
|
|
+ continue;
|
|
|
+ }
|
|
|
+ htmlText.add(text);
|
|
|
+ }
|
|
|
+ }
|
|
|
+ }
|
|
|
+ if (htmlText.get(0).length() > 200) {
|
|
|
+ htmlText.remove(0);
|
|
|
+ }
|
|
|
+ return htmlText;
|
|
|
+ }
|
|
|
+
|
|
|
+ /**
|
|
|
+ * 将html内容以table的格式存进list
|
|
|
+ *
|
|
|
+ * @param html 原始html内容
|
|
|
+ * @return
|
|
|
+ */
|
|
|
+ public void html2ListByTable(String html, List<String> htmlText) {
|
|
|
+ Elements trs = Jsoup.parse(html).select("table").select("tr");
|
|
|
+ for (int i = 0; i < trs.size(); i++) {
|
|
|
+ Elements tds = trs.get(i).select("td");
|
|
|
+ for (int j = 0; j < tds.size(); j++) {
|
|
|
+ String text = tds.get(j).text();
|
|
|
+ htmlText.add(text);
|
|
|
+ }
|
|
|
+ }
|
|
|
+ }
|
|
|
+
|
|
|
+ /**
|
|
|
+ * 将list中html内容转换成structureMap
|
|
|
+ *
|
|
|
+ * @param titles 文书各标题
|
|
|
+ * @param htmlText html内容以行的形式存储list
|
|
|
+ * @param structureMap
|
|
|
+ * @return
|
|
|
+ */
|
|
|
+ public void html2StructureMap(List<String> titles, List<String> htmlText, Map<String, String> structureMap) {
|
|
|
+ StringBuffer sb = new StringBuffer();
|
|
|
+ for (String line : htmlText) {
|
|
|
+ String text = line.replaceAll("[ ]", " ");
|
|
|
+ if (text.length() == 0) {
|
|
|
+ continue;
|
|
|
+ }
|
|
|
+ sb.append(text).append("\n");
|
|
|
+ }
|
|
|
+ html2StructureMap(titles, sb.toString(), structureMap);
|
|
|
+ }
|
|
|
+
|
|
|
+ /**
|
|
|
+ * 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))) {
|
|
|
+ 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))) {
|
|
|
+ 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);
|
|
|
+ }
|
|
|
+
|
|
|
+ /**
|
|
|
+ * 将title根据在文本中的位置排序
|
|
|
+ *
|
|
|
+ * @param titles
|
|
|
+ * @param content
|
|
|
+ * @return
|
|
|
+ */
|
|
|
+ public static List<String> sortTitles(List<String> titles, String content) {
|
|
|
+ Map<Integer, String> titleIndex = new TreeMap<>();
|
|
|
+ int index, index_1, index_2;
|
|
|
+ for (String title : titles) {
|
|
|
+ index_1 = content.indexOf(title + "：");
|
|
|
+ index_2 = content.indexOf(title + ":");
|
|
|
+ index = Math.max(index_1, index_2);
|
|
|
+ if (index != -1) {
|
|
|
+ titleIndex.put(index, title);
|
|
|
+ StringBuffer sb = new StringBuffer(title.length());
|
|
|
+ for (int i = 0; i < title.length(); i++) {
|
|
|
+ sb.append('*');
|
|
|
+ }
|
|
|
+ content = content.substring(0, index) + sb.toString() + content.substring(index + title.length() + 1);
|
|
|
+ // content = content.substring(0, index) + content.substring(index + title.length() + 1);
|
|
|
+ }
|
|
|
+ }
|
|
|
+ titles = Lists.newArrayList(titleIndex.values());
|
|
|
+ return titles;
|
|
|
+ }
|
|
|
+
|
|
|
+ /**
|
|
|
+ * 标题没有冒号版本
|
|
|
+ */
|
|
|
+ public static void html2StructureMapNoColon(List<String> titles, String htmlText, Map<String, String> structureMap) {
|
|
|
+ List<String> sortTitlesNoColon = sortTitlesNoColon(titles, htmlText);
|
|
|
+ cutByTitlesNoColon(htmlText, sortTitlesNoColon, 0, structureMap);
|
|
|
+ }
|
|
|
+
|
|
|
+ /**
|
|
|
+ * 标题没有冒号版本
|
|
|
+ */
|
|
|
+ public static void cutByTitlesNoColon(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()) {
|
|
|
+ value = line;
|
|
|
+ value = value.trim();
|
|
|
+ if (value.startsWith(":") || value.startsWith("：")) {
|
|
|
+ value = value.replaceFirst("[:：]", "");
|
|
|
+ }
|
|
|
+ if (StringUtil.isBlank(structureMap.get(beforeTitle))) {
|
|
|
+ structureMap.put(beforeTitle, StringUtil.trim(value).replace("\n", ""));
|
|
|
+ }
|
|
|
+ return;
|
|
|
+ }
|
|
|
+ if (line.contains(title)) {
|
|
|
+ newTitle = title;
|
|
|
+ if (depth > 0) {
|
|
|
+ value = line.substring(0, line.indexOf(newTitle));
|
|
|
+ value = value.trim();
|
|
|
+ if (value.startsWith(":") || value.startsWith("：")) {
|
|
|
+ value = value.replaceFirst("[:：]", "");
|
|
|
+ }
|
|
|
+ if (StringUtil.isBlank(structureMap.get(beforeTitle))) {
|
|
|
+ structureMap.put(beforeTitle, StringUtil.trim(value).replace("\n", ""));
|
|
|
+ }
|
|
|
+ }
|
|
|
+ line = line.substring(line.indexOf(newTitle) + newTitle.length());
|
|
|
+ depth++;
|
|
|
+ } else {
|
|
|
+ titles.remove(depth);
|
|
|
+ }
|
|
|
+ cutByTitlesNoColon(line, titles, depth, structureMap);
|
|
|
+ }
|
|
|
+
|
|
|
+ /**
|
|
|
+ * 标题没有冒号版本
|
|
|
+ */
|
|
|
+ public static List<String> sortTitlesNoColon(List<String> titles, String content) {
|
|
|
+ Map<Integer, String> titleIndex = new TreeMap<>();
|
|
|
+ int index;
|
|
|
+ for (String title : titles) {
|
|
|
+ index = content.indexOf(title);
|
|
|
+ if (index != -1) {
|
|
|
+ titleIndex.put(index, title);
|
|
|
+ content = content.replace(title, "");
|
|
|
+ }
|
|
|
+ }
|
|
|
+ titles = Lists.newArrayList(titleIndex.values());
|
|
|
+ return titles;
|
|
|
+ }
|
|
|
+
|
|
|
+ /**
|
|
|
+ * 抽取文本中的第一个时间(余杭三院)
|
|
|
+ *
|
|
|
+ * @param top
|
|
|
+ * @return
|
|
|
+ */
|
|
|
+ public static String extractDate(String top) {
|
|
|
+ Pattern pattern = Pattern.compile("[0-9]{4}[-][0-9]{1,2}[-][0-9]{1,2}([ ][0-9]{1,2}[:][0-9]{1,2}([:][0-9]{1,2})?)?");
|
|
|
+ Pattern pattern2 = Pattern.compile("[0-9]{4}[年][0-9]{1,2}[月][0-9]{1,2}[日][0-9]{1,2}[时][0-9]{1,2}[分]([0-9]{1,2}[秒])?");
|
|
|
+ Matcher matcher = pattern.matcher(top);
|
|
|
+ Matcher matcher2 = pattern2.matcher(top);
|
|
|
+ if (matcher2.find()) {
|
|
|
+ return matcher2.group(0);
|
|
|
+ } else if (matcher.find()) {
|
|
|
+ return matcher.group(0);
|
|
|
+ } else {
|
|
|
+ Pattern p1 = Pattern.compile("[0-9]{4}年[0-9]+月[0-9]+日[0-9]+时[0-9]+分");
|
|
|
+ Matcher m1 = p1.matcher(top);
|
|
|
+ if (m1.find()) {
|
|
|
+ return m1.group(0);
|
|
|
+ } else {
|
|
|
+ Pattern p2 = Pattern.compile("[0-9]{4}年[0-9]+月[0-9]+日 [0-9]+:[0-9]+ | [0-9]{4}年[0-9]+月[0-9]+日[0-9]+:[0-9]+ ");
|
|
|
+ Matcher m2 = p2.matcher(top);
|
|
|
+ if (m2.find()) {
|
|
|
+ return m2.group(0);
|
|
|
+ }
|
|
|
+ }
|
|
|
+ }
|
|
|
+ return null;
|
|
|
+ }
|
|
|
+
|
|
|
+ /**
|
|
|
+ * 宁波中医院抽取文本中的第一个时间
|
|
|
+ *
|
|
|
+ * @param top
|
|
|
+ * @return
|
|
|
+ */
|
|
|
+ public static String NBZYExtractDate(String top) {
|
|
|
+ Pattern p1 = Pattern.compile("[0-9]{4}年[0-9]+月[0-9]+日");
|
|
|
+ Matcher m1 = p1.matcher(top);
|
|
|
+ if (m1.find()) {
|
|
|
+ return m1.group(0);
|
|
|
+ }
|
|
|
+ return null;
|
|
|
+ }
|
|
|
+
|
|
|
+ /**
|
|
|
+ * 温附一抽取文本中的第一个时间
|
|
|
+ *
|
|
|
+ * @param top
|
|
|
+ * @return
|
|
|
+ */
|
|
|
+ public static String WFYExtractDate(String top) {
|
|
|
+ Pattern p1 = Pattern.compile("[0-9]+月[0-9]+日[0-9]+时[0-9]+分");
|
|
|
+ Matcher m1 = p1.matcher(top);
|
|
|
+ if (m1.find()) {
|
|
|
+ return m1.group(0);
|
|
|
+ }
|
|
|
+ return null;
|
|
|
+ }
|
|
|
+
|
|
|
+ /**
|
|
|
+ * 宁海医院抽取文本中的第一个时间
|
|
|
+ *
|
|
|
+ * @param top
|
|
|
+ * @return
|
|
|
+ */
|
|
|
+ public static String NHExtractDate(String top) {
|
|
|
+ Pattern pattern = Pattern.compile("[0-9]{4}年[0-9]+月[0-9]+日 [0-9]+:[0-9]+ | [0-9]{4}年[0-9]+月[0-9]+日[0-9]+:[0-9]+");
|
|
|
+ Matcher matcher = pattern.matcher(top);
|
|
|
+ if (matcher.find()) {
|
|
|
+ return matcher.group(0);
|
|
|
+ } else {
|
|
|
+ Pattern p1 = Pattern.compile("[0-9]{4}年[0-9]+月[0-9]+日[0-9]+时[0-9]+分");
|
|
|
+ Matcher m1 = p1.matcher(top);
|
|
|
+ if (m1.find()) {
|
|
|
+ return m1.group(0);
|
|
|
+ } else {
|
|
|
+ Pattern p2 = Pattern.compile("[0-9]{4}[-][0-9]{1,2}[-][0-9]{1,2}([ ][0-9]{1,2}[:][0-9]{1,2}([:][0-9]{1,2})?)?");
|
|
|
+ Matcher m2 = p2.matcher(top);
|
|
|
+ if (m2.find()) {
|
|
|
+ return m2.group(0);
|
|
|
+ }
|
|
|
+ }
|
|
|
+ Pattern pattern3 = Pattern.compile("[0-9]{4}年[0-9]+月[0-9]+日 [0-9]+:[0-9]+|[0-9]{4}年[0-9]+月[0-9]+日[0-9]+:[0-9]+");
|
|
|
+ Matcher matcher3 = pattern3.matcher(top);
|
|
|
+ if (matcher3.find()) {
|
|
|
+ return matcher3.group(0);
|
|
|
+ }
|
|
|
+
|
|
|
+ }
|
|
|
+ return null;
|
|
|
+ }
|
|
|
+
|
|
|
+ /**
|
|
|
+ * 根据title重新存放时间
|
|
|
+ *
|
|
|
+ * @param structmap
|
|
|
+ * @param title
|
|
|
+ */
|
|
|
+ public static void extractDateByTitle(Map<String, String> structmap, String title) {
|
|
|
+ if (structmap.containsKey(title)) {
|
|
|
+ String date = extractDate(structmap.get(title));
|
|
|
+ if (StringUtil.isNotBlank(date)) {
|
|
|
+ structmap.put(title, date);
|
|
|
+ }
|
|
|
+ }
|
|
|
+ }
|
|
|
+
|
|
|
+ /**
|
|
|
+ * 若内容中是包含选择框（会诊类型： 急会诊 普通会诊 请院外会诊），特殊处理
|
|
|
+ *
|
|
|
+ * @param structureMap
|
|
|
+ */
|
|
|
+ public static void processType(Map<String, String> structureMap, String title) {
|
|
|
+ if (structureMap.containsKey(title)) {
|
|
|
+ String type = structureMap.get(title);
|
|
|
+ type = type.replace(" ", "").replace("\uF06F", " \uF06F")
|
|
|
+ .replace("\uF0FE", " \uF0FE");
|
|
|
+ String[] types = type.split(" ");
|
|
|
+ String s = "";
|
|
|
+ for (String t : types) {
|
|
|
+ if (t.contains("\uF0FE")) {
|
|
|
+ s += t;
|
|
|
+ }
|
|
|
+ }
|
|
|
+ s = s.replace("\uF0FE", "");
|
|
|
+ structureMap.put(title, s);
|
|
|
+ }
|
|
|
+ }
|
|
|
+
|
|
|
+ /**
|
|
|
+ * 若内容中是包含选择框（会诊类型： 急会诊 普通会诊 请院外会诊），特殊处理
|
|
|
+ *
|
|
|
+ * @param structureMap
|
|
|
+ */
|
|
|
+ public static void processTypeRight(Map<String, String> structureMap, String title) {
|
|
|
+ if (structureMap.containsKey(title)) {
|
|
|
+ String type = structureMap.get(title);
|
|
|
+ String[] types = type.split(" ");
|
|
|
+ String s = "";
|
|
|
+ for (String t : types) {
|
|
|
+ if (t.contains("\uF0FE")) {
|
|
|
+ s += t;
|
|
|
+ }
|
|
|
+ }
|
|
|
+ s = s.replace("\uF0FE", "");
|
|
|
+ structureMap.put(title, s);
|
|
|
+ }
|
|
|
+ }
|
|
|
+
|
|
|
+ /**
|
|
|
+ * 若list中其中一个元素包含之后第二个、第三个元素的文本，则把这个元素删除
|
|
|
+ *
|
|
|
+ * @param htmlList
|
|
|
+ */
|
|
|
+ public static void removeRepeat(List<String> htmlList) {
|
|
|
+ List<Integer> index = Lists.newArrayList();
|
|
|
+ if (htmlList.size() < 3) {
|
|
|
+ return;
|
|
|
+ }
|
|
|
+ String str1 = null, str2 = null, str3 = null;
|
|
|
+ for (int i = 0; i < htmlList.size() - 2; i++) {
|
|
|
+ str1 = htmlList.get(i);
|
|
|
+ str2 = htmlList.get(i + 1);
|
|
|
+ str3 = htmlList.get(i + 2);
|
|
|
+ if (str1.contains(str2) && str1.contains(str3)) {
|
|
|
+ index.add(i);
|
|
|
+ }
|
|
|
+ }
|
|
|
+
|
|
|
+ for (int i = 0; i < index.size(); i++) {
|
|
|
+ htmlList.remove(index.get(i) - i);
|
|
|
+ }
|
|
|
+ }
|
|
|
+
|
|
|
+ /**
|
|
|
+ * 宁海用抽取自定义病程录信息
|
|
|
+ *
|
|
|
+ * @param htmlText
|
|
|
+ * @param structureMap
|
|
|
+ */
|
|
|
+ public static void NHExtractWardInfo(String recTitle, String htmlText, Map<String, String> structureMap) {
|
|
|
+ if (StringUtil.isNotBlank(htmlText)) {
|
|
|
+ htmlText = htmlText.replaceAll("[ \n]", " ").replace("第1页", "")
|
|
|
+ .replace("\n", " ");
|
|
|
+ String date = NHExtractDate(htmlText);
|
|
|
+ if (date != null) {
|
|
|
+ structureMap.put("病历日期", date);
|
|
|
+ htmlText = htmlText.replace(date, "").trim();
|
|
|
+ }
|
|
|
+ List<String> titleContent = Lists.newArrayList(htmlText.split(" "));
|
|
|
+ String title = titleContent.get(0);
|
|
|
+ String jointTitle = titleContent.get(1);
|
|
|
+ if (StringUtil.isNotBlank(title) && StringUtil.isNotBlank(jointTitle) && jointTitle.contains("医师查房记录")) {
|
|
|
+ structureMap.put("病历标题", title + jointTitle);
|
|
|
+ titleContent.remove(0);
|
|
|
+ titleContent.remove(0);
|
|
|
+ } else {
|
|
|
+ structureMap.put("病历标题", recTitle);
|
|
|
+ titleContent.remove(0);
|
|
|
+ }
|
|
|
+ StringBuffer sb = new StringBuffer();
|
|
|
+ for (String text : titleContent) {
|
|
|
+ sb.append(text).append(" ");
|
|
|
+ }
|
|
|
+ String content = sb.toString();
|
|
|
+ if (content.contains("<img")) {
|
|
|
+ String[] contentDoctor = content.split("<img");
|
|
|
+ structureMap.put("病情记录", contentDoctor[0]);
|
|
|
+ structureMap.put("记录医生", "<img" + contentDoctor[1]);
|
|
|
+ } else {
|
|
|
+ structureMap.put("病情记录", content);
|
|
|
+ }
|
|
|
+// if (structureMap.containsKey("病情记录")) {
|
|
|
+// String info = structureMap.get("病情记录");
|
|
|
+// if (info.contains("医生签名")) {
|
|
|
+// structureMap.put("病情记录", info.substring(0, info.lastIndexOf("医生签名")));
|
|
|
+// structureMap.put("记录医生", "");
|
|
|
+// } else if (info.contains("医师签名")) {
|
|
|
+// structureMap.put("病情记录", info.substring(0, info.lastIndexOf("医师签名")));
|
|
|
+// structureMap.put("记录医生", "");
|
|
|
+// }
|
|
|
+// }
|
|
|
+ }
|
|
|
+ }
|
|
|
+
|
|
|
+ /**
|
|
|
+ * 抽取自定义病程录信息
|
|
|
+ *
|
|
|
+ * @param htmlText
|
|
|
+ * @param structureMap
|
|
|
+ */
|
|
|
+ public static void extractWardInfo(String recTitle, String htmlText, Map<String, String> structureMap) {
|
|
|
+ if (StringUtil.isNotBlank(htmlText)) {
|
|
|
+ htmlText = htmlText.replaceAll("[ \n]", " ").replace("第1页", "")
|
|
|
+ .replace("\n", " ");
|
|
|
+ String date = extractDate(htmlText);
|
|
|
+ if (date != null) {
|
|
|
+ structureMap.put("病历日期", date);
|
|
|
+ htmlText = htmlText.replace(date, "").trim();
|
|
|
+ }
|
|
|
+ List<String> titleContent = Lists.newArrayList(htmlText.split(" "));
|
|
|
+ String title = titleContent.get(0);
|
|
|
+ if (StringUtil.isNotBlank(title) && title.equals(recTitle)) {
|
|
|
+ structureMap.put("病历标题", title);
|
|
|
+ titleContent.remove(0);
|
|
|
+ } else {
|
|
|
+ structureMap.put("病历标题", recTitle);
|
|
|
+ structureMap.put("文书标题", title);
|
|
|
+ if (titleContent.size() > 2) {
|
|
|
+ titleContent.remove(0);
|
|
|
+ titleContent.remove(0);
|
|
|
+ }
|
|
|
+ }
|
|
|
+ StringBuffer sb = new StringBuffer();
|
|
|
+ for (String text : titleContent) {
|
|
|
+ sb.append(text).append(" ");
|
|
|
+ }
|
|
|
+ String content = sb.toString();
|
|
|
+ if (content.contains("<img")) {
|
|
|
+ String[] contentDoctor = content.split("<img");
|
|
|
+ structureMap.put("病情记录", contentDoctor[0]);
|
|
|
+ structureMap.put("记录医生", "<img" + contentDoctor[1]);
|
|
|
+ } else {
|
|
|
+ structureMap.put("病情记录", content);
|
|
|
+ }
|
|
|
+ if (structureMap.containsKey("病情记录")) {
|
|
|
+ String info = structureMap.get("病情记录");
|
|
|
+ if (info.contains("医生签名")) {
|
|
|
+ structureMap.put("病情记录", info.substring(0, info.lastIndexOf("医生签名")));
|
|
|
+ structureMap.put("记录医生", "");
|
|
|
+ } else if (info.contains("医师签名")) {
|
|
|
+ structureMap.put("病情记录", info.substring(0, info.lastIndexOf("医师签名")));
|
|
|
+ structureMap.put("记录医生", "");
|
|
|
+ }
|
|
|
+ }
|
|
|
+ }
|
|
|
+ }
|
|
|
+
|
|
|
+ /**
|
|
|
+ * 抽取自定义病程录信息（余杭三院）
|
|
|
+ *
|
|
|
+ * @param htmlText
|
|
|
+ * @param structureMap
|
|
|
+ */
|
|
|
+ public static void extractWardInfo2(String recTitle, String htmlText, Map<String, String> structureMap) {
|
|
|
+ if (StringUtil.isNotBlank(htmlText)) {
|
|
|
+ htmlText = htmlText.replaceAll("[ \n]", " ").replace("第1页", "")
|
|
|
+ .replace("\n", " ");
|
|
|
+ String date = extractDate(htmlText);
|
|
|
+ if (date != null) {
|
|
|
+ structureMap.put("病历日期", date);
|
|
|
+ htmlText = htmlText.replaceFirst(date, "").trim();
|
|
|
+ }
|
|
|
+ List<String> titleContent = Lists.newArrayList(htmlText.split(" "));
|
|
|
+ String title = titleContent.get(0);
|
|
|
+ if (StringUtil.isNotBlank(title) && title.equals(recTitle)) {
|
|
|
+ structureMap.put("病历标题", title);
|
|
|
+ titleContent.remove(0);
|
|
|
+ } else {
|
|
|
+ structureMap.put("病历标题", recTitle);
|
|
|
+ if (title.contains(recTitle)) {
|
|
|
+ titleContent.set(0, title.substring(title.indexOf(recTitle) + recTitle.length()));
|
|
|
+ }
|
|
|
+ }
|
|
|
+ StringBuffer sb = new StringBuffer();
|
|
|
+ for (String text : titleContent) {
|
|
|
+ sb.append(text).append(" ");
|
|
|
+ }
|
|
|
+ structureMap.put("病情记录", sb.toString());
|
|
|
+ if (structureMap.containsKey("病情记录")) {
|
|
|
+ String info = structureMap.get("病情记录");
|
|
|
+ if (info.contains("记录医师")) {
|
|
|
+ structureMap.put("病情记录", info.substring(0, info.lastIndexOf("记录医师")));
|
|
|
+ structureMap.put("记录医师", info.substring(info.lastIndexOf("记录医师") + "记录医师：".length()));
|
|
|
+ } else if (info.contains("医师签名")) {
|
|
|
+ structureMap.put("病情记录", info.substring(0, info.lastIndexOf("医师签名")));
|
|
|
+ structureMap.put("医师签名", info.substring(info.lastIndexOf("医师签名") + "医师签名：".length()));
|
|
|
+ }
|
|
|
+ }
|
|
|
+ }
|
|
|
+ }
|
|
|
+
|
|
|
+ /**
|
|
|
+ * 替换值
|
|
|
+ *
|
|
|
+ * @param map
|
|
|
+ * @param key
|
|
|
+ * @param afterKey
|
|
|
+ */
|
|
|
+ public static void repKey(Map<String, String> map, String key, String afterKey) {
|
|
|
+ if (StringUtil.isNotBlank(map.get(key))) {
|
|
|
+ map.put(key, map.get(key).replaceAll(afterKey, ""));
|
|
|
+ }
|
|
|
+ }
|
|
|
+
|
|
|
+ public static void makeEmpty(Map<String, String> structureMap, String... key) {
|
|
|
+ for (String k : key) {
|
|
|
+ if (structureMap.containsKey(k)) {
|
|
|
+ structureMap.put(k, "");
|
|
|
+ }
|
|
|
+ }
|
|
|
+ }
|
|
|
+
|
|
|
+ /**
|
|
|
+ * 格式时间从yyyy年MM月dd日HH时mm分到yyyy-MM-dd HH:mm
|
|
|
+ *
|
|
|
+ * @param map
|
|
|
+ */
|
|
|
+ public static void signatureTime1(String changeCame, Map<String, String> map) {
|
|
|
+ String goCureDoctor = map.get(changeCame);
|
|
|
+ if (StringUtil.isNotBlank(goCureDoctor)) {
|
|
|
+ try {
|
|
|
+ Pattern pattern2 = Pattern.compile("[0-9]{4}[年][0-9]{1,2}[月][0-9]{1,2}[日][0-9]{1,2}[时][0-9]{1,2}[分]");
|
|
|
+ Matcher matcher2 = pattern2.matcher(goCureDoctor);
|
|
|
+ if (!matcher2.find()) {
|
|
|
+ return;
|
|
|
+ }
|
|
|
+ Date parse = new SimpleDateFormat("yyyy年MM月dd日HH时mm分").parse(goCureDoctor);
|
|
|
+ String format = new SimpleDateFormat("yyyy-MM-dd HH:mm").format(parse);
|
|
|
+ map.put(changeCame, format);
|
|
|
+ } catch (ParseException e) {
|
|
|
+ e.printStackTrace();
|
|
|
+ }
|
|
|
+ }
|
|
|
+ }
|
|
|
+}
|
licy