fix: parse xingrong pdf data

packages/xingrong-courses/package.json

@@ -6,16 +6,19 @@
   "scripts": {
     "upload": "tsx src/seed.ts",
     "course:add": "tsx src/addCourse.ts",
-    "pdf:parse": "tsx src/parsePDF/index.ts"
+    "pdf:parse": "tsx src/parsePDF/index.ts",
+    "test": "vitest"
   },
   "dependencies": {
+    "@earthworm/db": "workspace:^",
     "@earthworm/schema": "workspace:^",
+    "drizzle-orm": "^0.32.0",
     "inquirer": "^9.2.13",
-    "pdf-parse": "^1.1.1",
-    "drizzle-orm": "^0.32.0"
+    "pdf-parse": "^1.1.1"
   },
   "devDependencies": {
     "@types/inquirer": "^9.0.7",
-    "@types/pdf-parse": "^1.1.4"
+    "@types/pdf-parse": "^1.1.4",
+    "vitest": "^2.0.3"
   }
 }

packages/xingrong-courses/src/parsePDF/index.ts

@@ -29,7 +29,9 @@ function save(content: string, fileName: string) {
 
 function createFileNameMap(): Record<string, string> {
   const fileNameMap: Record<string, string> = {};
-  const files = fs.readdirSync(targetPath);
+  let files = fs.readdirSync(targetPath);
+  // 筛选出以 .pdf 结尾的文件
+  files = files.filter((file) => file.endsWith(".pdf"));
   files.sort((a, b) => parseFloat(a) - parseFloat(b));
 
   files.forEach((file, index) => {

packages/xingrong-courses/src/parsePDF/inquire.ts

@@ -39,7 +39,10 @@ export async function inquire(folderPath: string): Promise<string[]> {
 }
 
 function listAllFiles(folderPath) {
-  const files = fs.readdirSync(folderPath);
+  let files = fs.readdirSync(folderPath);
+  // 筛选出以 .pdf 结尾的文件
+  files = files.filter((file) => file.endsWith(".pdf"));
+
   files.sort((a, b) => {
     return parseFloat(a) - parseFloat(b);
   });

packages/xingrong-courses/src/parsePDF/parser.test.ts

@@ -92,4 +92,42 @@ describe("pdf parser ", () => {
       ]
     `);
   });
+
+  it("中文部分是括号开始的", () => {
+    const pdfText = "我 \n" + "I /aɪ/ \n" + "(过去)它；这件事情 \n" + "it /it/ \n";
+
+    expect(parse(pdfText)).toMatchInlineSnapshot(`
+      [
+        {
+          "chinese": "我",
+          "english": "I",
+          "soundmark": "/aɪ/",
+        },
+        {
+          "chinese": "(过去)它；这件事情",
+          "english": "it",
+          "soundmark": "/it/",
+        },
+      ]
+    `);
+  });
+
+  it("中文部分是英文开始的", () => {
+    const pdfText = "我 \n" + "I /aɪ/ \n" + "be(ed形式) \n" + "been /bɪn/ \n";
+
+    expect(parse(pdfText)).toMatchInlineSnapshot(`
+      [
+        {
+          "chinese": "我",
+          "english": "I",
+          "soundmark": "/aɪ/",
+        },
+        {
+          "chinese": "be(ed形式)",
+          "english": "been",
+          "soundmark": "/bɪn/",
+        },
+      ]
+    `);
+  });
 });

packages/xingrong-courses/src/parsePDF/parser.ts

@@ -70,7 +70,8 @@ export function parse(text: string) {
 }
 
 function isChinese(str: string) {
-  const reg = /^[\u4e00-\u9fa5]/;
+  // 只要里面有中文的话  那么就作为 chinese 部分
+  const reg = /[\u4e00-\u9fa5]/;
   return reg.test(str);
 }