2. Java-MarkDown文件解析-工具类

2. Java-MarkDown文件解析-工具类

1. 思路

1. 读取markdown文件的内容，根据markdown的语法进行各个类型语法的解析。
2. 引入工具类 commonmark 和 commonmark-ext-gfm-tables进行markdown语法解析。

2. 工具类

pom.xml

<!-- commonmark 解析markdown -->
<dependency><groupId>org.commonmark</groupId><artifactId>commonmark</artifactId><version>0.21.0</version>
</dependency>
<!-- commonmark 解析markdown tables -->
<dependency><groupId>org.commonmark</groupId><artifactId>commonmark-ext-gfm-tables</artifactId><version>0.21.0</version>
</dependency>

MarkdownParseResult

import com.alibaba.fastjson.JSONObject;
import io.swagger.annotations.ApiModel;
import io.swagger.annotations.ApiModelProperty;
import lombok.Data;/*** Markdown解析结果* @Author: onecomer* @Date: 2021/1/26 16:00*/
@ApiModel(description = "Markdown解析结果")
@Data
public class MarkdownParseResult {@ApiModelProperty(value = "MarkdownHtml内容")private String htmlContent;@ApiModelProperty(value = "标题及内容集合",example = "{'标题1':'内容1','标题2':'内容2',...}")private JSONObject titles;@ApiModelProperty(value = "表格标题及内容集合",example = "{'表格标题':'{headers:['列1','列2'],rows:[{'值1','值2'},{'值1','值2'}]}",notes = "headers为表头，rows为行数据")private JSONObject tables;@ApiModelProperty(value = "无序列表集合",example = "{''无序列表标题:[{'无序列表内容1'},{'无序列表内容2'},...]}")private JSONObject unOrderedLists;@ApiModelProperty(value = "有序列表集合",example = "{''有序列表标题:[{'有序列表内容1'},{'有序列表内容2'},...]}")private JSONObject orderedLists;@ApiModelProperty(value = "代码块集合",example = "{'代码块标题1':{'codeBlockContent（固定值）':'代码块内容1','codeBlockType（固定值）':'代码块类型1'}}")private JSONObject codeBlocks;
}

MarkdownParserUtil

import com.alibaba.fastjson.JSONArray;
import com.alibaba.fastjson.JSONObject;
import org.commonmark.ext.gfm.tables.TableBlock;
import org.commonmark.ext.gfm.tables.TableBody;
import org.commonmark.ext.gfm.tables.TableCell;
import org.commonmark.ext.gfm.tables.TableHead;
import org.commonmark.ext.gfm.tables.TableRow;
import org.commonmark.ext.gfm.tables.TablesExtension;
import org.commonmark.node.AbstractVisitor;
import org.commonmark.node.BulletList;
import org.commonmark.node.FencedCodeBlock;
import org.commonmark.node.Heading;
import org.commonmark.node.ListItem;
import org.commonmark.node.Node;
import org.commonmark.node.OrderedList;
import org.commonmark.node.Paragraph;
import org.commonmark.node.SoftLineBreak;
import org.commonmark.node.Text;
import org.commonmark.parser.Parser;
import org.commonmark.renderer.html.HtmlRenderer;import java.io.IOException;
import java.nio.file.Files;
import java.nio.file.Paths;
import java.util.ArrayList;
import java.util.Arrays;
import java.util.HashMap;
import java.util.List;
import java.util.Map;/*** Markdown解析工具类* @Author: onecomer* @Date: 2021/1/26 16:00*/
public class MarkdownParserUtil {private static Parser parser;private static HtmlRenderer renderer;static {parser = Parser.builder().extensions(Arrays.asList(TablesExtension.create())).build();renderer = HtmlRenderer.builder().extensions(Arrays.asList(TablesExtension.create())).build();}/*** 读取并解析Markdown文件*/public static MarkdownParseResult parseMarkdownFile(String filePath) {String content = null;try {content = new String(Files.readAllBytes(Paths.get(filePath)));} catch (IOException e) {throw new RuntimeException(e);}MarkdownParseResult result = parseMarkdownFileContent(content);return result;}/*** 解析Markdown内容*/public static MarkdownParseResult parseMarkdownFileContent(String content) {Node document = parser.parse(content);MarkdownParseResult result = new MarkdownParseResult();
//        result.setHtmlContent(renderer.render(document));JSONObject titles = new JSONObject(true);JSONObject tables = new JSONObject(true);JSONObject unOrderedLists = new JSONObject(true);JSONObject orderedLists = new JSONObject(true);JSONObject codeBlocks = new JSONObject(true);String currentHeading = "";StringBuilder paragraphContent = new StringBuilder();boolean isDelReapeatTilte = true;Node node = document.getFirstChild();while (node != null) {if (node instanceof Heading) {// 标题String text = getText(node);currentHeading = text;// 只有标题的直接添加if (!((node.getNext()) instanceof Paragraph)) {titles.put(currentHeading, currentHeading);}} else if (node instanceof Paragraph) {String text = getText(node);// 普通文本paragraphContent.append(text).append("\n");// 结束添加paragraphContentif (!((node.getNext()) instanceof Paragraph)) {titles.put(currentHeading, paragraphContent.toString().trim());paragraphContent = new StringBuilder();}} else if (node instanceof BulletList) {// 无序列表JSONArray items = new JSONArray();Node listItem = node.getFirstChild();while (listItem != null) {if (listItem instanceof ListItem) {String text = getText(listItem);items.add(text);}listItem = listItem.getNext();}unOrderedLists.put(currentHeading, items);if (isDelReapeatTilte) {titles.remove(currentHeading);}} else if (node instanceof OrderedList) {// 有序列表JSONArray items = new JSONArray();Node listItem = node.getFirstChild();while (listItem != null) {if (listItem instanceof ListItem) {String text = getText(listItem);items.add(text);}listItem = listItem.getNext();}orderedLists.put(currentHeading, items);if (isDelReapeatTilte) {titles.remove(currentHeading);}} else if (node instanceof FencedCodeBlock) {// 代码块FencedCodeBlock codeBlock = (FencedCodeBlock) node;JSONObject codeBlockInfo = new JSONObject(true);String codeBlockContent = codeBlock.getLiteral();String codeBlockType = codeBlock.getInfo();codeBlockInfo.put("codeBlockContent", codeBlockContent);codeBlockInfo.put("codeBlockType", codeBlockType);codeBlocks.put(currentHeading, codeBlockInfo);if (isDelReapeatTilte) {titles.remove(currentHeading);}} else if (node instanceof TableBlock) {// 表格JSONObject tableInfo = new JSONObject(true);JSONArray headers = new JSONArray();JSONArray rows = new JSONArray();// TableHeadNode row = node.getFirstChild();if (row instanceof TableHead) {Node headerRow = row.getFirstChild();if (headerRow instanceof TableRow) {Node cell = headerRow.getFirstChild();while (cell != null) {if (cell instanceof TableCell) {String text = getText(cell);headers.add(text);}cell = cell.getNext();}}}// TableBodyNode tableBody = row.getNext();while (tableBody != null) {if (tableBody instanceof TableBody) {// TableRowNode tableRow = tableBody.getFirstChild();while (tableRow != null) {if (tableRow instanceof TableRow) {JSONArray rowData = new JSONArray();Node tableCell = tableRow.getFirstChild();while (tableCell != null) {if (tableCell instanceof TableCell) {String text = getText(tableCell);rowData.add(text);}tableCell = tableCell.getNext();}rows.add(rowData);}tableRow = tableRow.getNext();}}tableBody = tableBody.getNext();}tableInfo.put("headers", headers);tableInfo.put("rows", rows);tables.put(currentHeading, tableInfo);if (isDelReapeatTilte) {titles.remove(currentHeading);}}// 处理下一个节点node = node.getNext();}result.setTitles(titles);result.setTables(tables);result.setUnOrderedLists(unOrderedLists);result.setOrderedLists(orderedLists);result.setCodeBlocks(codeBlocks);return result;}/*** 获取节点的文本内容(包含格式)*/private static String getText(Node node) {StringBuilder sb = new StringBuilder();node.accept(new AbstractVisitor() {@Overridepublic void visit(Text text) {sb.append(text.getLiteral());}//            @Override
//            public void visit(Emphasis emphasis) {
//                sb.append("*").append(getText(emphasis)).append("*");
//            }
//
//            @Override
//            public void visit(StrongEmphasis strongEmphasis) {
//                sb.append("**").append(getText(strongEmphasis)).append("**");
//            }
//
//            @Override
//            public void visit(Code code) {
//                sb.append("`").append(code.getLiteral()).append("`");
//            }});return sb.toString().trim();}/*** 判断是否为表格节点*/@Deprecatedprivate static boolean isTable(Node node) {
//        String content = getTextContent(node);
//        return content.contains("|") && content.contains("\n") && content.contains("---");Node firstChild = node.getFirstChild();Node secondChild = firstChild != null ? firstChild.getNext() : null;if (secondChild instanceof SoftLineBreak) {return true;}return false;}/*** 解析表格内容*/@Deprecatedprivate static JSONObject parseTable(Node tableNode) {String[] lines = getText(tableNode).split("\n");boolean isHeader = true;List<String> headers = new ArrayList<>();for (String line : lines) {line = line.trim();if (line.isEmpty() || line.startsWith("|---")) {isHeader = false;continue;}String[] cells = line.split("\\|");List<String> cleanCells = new ArrayList<>();for (String cell : cells) {String cleaned = cell.trim();if (!cleaned.isEmpty()) {cleanCells.add(cleaned);}}if (isHeader) {headers.addAll(cleanCells);
//                tableInfo.setHeaders(headers);} else {Map<String, String> row = new HashMap<>();for (int i = 0; i < headers.size() && i < cleanCells.size(); i++) {row.put(headers.get(i), cleanCells.get(i));}
//                tableInfo.getRows().add(row);}}return null;}public static void main(String[] args) {String filePath = "D:\\tab\\1_ideaIC-2022.2.win\\2_WS\\1_SAAS_hgit_2\\2_assembler_all\\3_biz-project\\api-manage\\markdown\\新增实体数据能力.md";
//            filePath = "D:\\tab\\1_ideaIC-2022.2.win\\2_WS\\1_SAAS_hgit_2\\2_assembler_all\\3_biz-project\\api-manage\\markdown\\新增实体数据能力2.md";MarkdownParseResult result = parseMarkdownFile(filePath);//            System.out.println("HTML内容:");
//            System.out.println(result.getHtmlContent());System.out.println("\n标题及内容:");System.out.println(result.getTitles().toJSONString());System.out.println("\n表格内容:");System.out.println(result.getTables().toJSONString());System.out.println("\n无序列表:");System.out.println(result.getUnOrderedLists().toJSONString());System.out.println("\n有序列表:");System.out.println(result.getOrderedLists().toJSONString());System.out.println("\n代码块:");System.out.println(result.getCodeBlocks().toJSONString());}
} 

3. 测试

测试结果

markdown文件

# 新增实体数据能力## 接口说明用来新增一条记录用来新增一条记录2用来新增一条记录3## 资产类型：API## 应用- 应用S码：Sxx## 标签- 新增实体数据能力
- xxx系统
- Sxx
- 新增记录 数据管理## 版本- v1.0.0## 接口地址```json
{"测试地址": "{baseUrl}/model/{dataSource}/{entityName}/add","生产地址": "{baseUrl}/model/{dataSource}/{entityName}/add"
}
```## 调用前提```json
需要先部署低代码引擎微服务，部署文档链接如下：
开发环境引擎部署：https://ihaier.feishu.cn/wiki/LyitwBYg4i8fRDkpPC0crxpMnlg
运行环境引擎部署：https://ihaier.feishu.cn/wiki/ZG16wdmOiib658k39X1cuzlKnSe
```## 请求方式POST## 请求头Header| 参数名       | 类型   | 是否必填 | 参数说明                      |
| :----------- | :----- | :------- | :---------------------------- |
| Access-Token | String | 是       | 统一登录token，从账号中心获取 |
| Access-Token2 | String | 是       | 统一登录token，从账号中心获取 |## 请求参数类型@RequestBody## 请求参数| 参数名     | 是否必填 | 类型         | 描述                    |
| :--------- | :------- | :----------- | :---------------------- |
| field1     | 否       | String       | 字段1                   |
| field2     | 否       | Integer      | 字段2                   |
| entityName | 否       | Object/Array | 关联实体(一对一/一对多) |### 请求参数示例```json
{"field1": "","field2": 19,"entityName": {"field1": "","field2": ""},"entityName": [{"field1": "","field2": ""}]
}
```## 返回参数类型@ResponseBody## 返回参数| 参数名  | 类型    | 说明                         |
| :------ | :------ | :--------------------------- |
| code    | Integer | 响应码,0表示成功,非0表示失败 |
| message | String  | 提示消息                     |
| data    | Object  | 返回数据                     |
| data.id | String  | 主键ID                       |### 返回参数示例#### 正确```json
{"code": 0,"message": "success", "data": {"id": "主键ID"} 
}
```#### 错误```json
{"code": 400,"message": "请求参数错误"
}
```### 错误码| errorCode | errorMessage |
| :-------- | :----------- |
| 400       | 请求参数错误 |## 调用示例```json
// 请求示例
POST /model/myDataSource/User/add
{"name": "张三","age": 25,"department": {"id": "dept001","name": "技术部"}
}// 返回结果示例
{"code": 0,"message": "success","data": {"id": "user001"}
}
```## 实现逻辑### 时序图```mermaid
sequenceDiagramparticipant Clientparticipant APIparticipant Serviceparticipant DatabaseClient->>API: POST /model/{ds}/{entity}/addAPI->>Service: addEntity(data)Service->>Service: validateData(data)Service->>Database: insert(data)Database-->>Service: Return idService-->>API: Return resultAPI-->>Client: Return response
```### 业务逻辑1. 校验请求参数的合法性
2. 根据实体定义验证字段
3. 生成主键ID
4. 保存实体数据
5. 返回新增记录的ID### 三方服务无