feat/syllabiparser

package.json

@@ -16,9 +16,12 @@
         "express": "^4.17.1",
         "express-rate-limit": "^5.1.3",
         "mongodb": "^3.5.9",
-        "mongoose": "^5.9.20"
+        "mongoose": "^5.9.20",
+        "multer": "^1.4.4",
+        "pdfdataextract": "^3.2.0"
     },
     "devDependencies": {
+        "@types/express-rate-limit": "^6.0.0",
         "nodemon": "^2.0.4"
     }
 }

src/index.js

@@ -1,6 +1,7 @@
 require("./db/mongoose")
 const express = require("express")
-const courseRouter = require("./routes/course")
+const courseRouter = require("./routes/course");
+const managerRouter = require("./routes/manager")
 const rateLimit = require("express-rate-limit");
 const cors = require("cors")
 const axios = require("axios")
@@ -16,6 +17,7 @@ app.set('trust proxy', 1);
 
 app.use(express.json()) // parse request as json
 app.use(courseRouter)
+app.use(managerRouter)
 
 if (process.env.NODE_ENV === 'production') {
     app.use((req, res, next) => {

src/routes/manager.js

@@ -0,0 +1,58 @@
+const express = require("express")
+const cors = require("cors")
+const rateLimit = require("express-rate-limit");
+const router = new express.Router()
+const {
+  PdfData,
+  VerbosityLevel
+} = require('pdfdataextract');
+const multer = require('multer');
+const upload = multer();
+
+let corsOptions = {
+  origin: 'https://timetable.viaplanner.ca', // allow only viaplanner to use the api 
+  optionsSuccessStatus: 200
+}
+
+const limiter = rateLimit({
+  windowMs: 15 * 60 * 1000, // 15 minutes
+  max: 100 // limit each IP to 100 requests per 15 minutes, so 9 requests per seconds
+});
+
+const re = /(Class Participation|Lab|Assignment|Term Test|Final Exam|Other|Quiz|Presentations|Final Exam Changed To)(.*|(?:.*\n+)*)(On-going|TBA|TBD|\d{4}-\d{2}-\d{2})+ (\d{1,3}%)\n/gmi;
+
+router.post('/manager/parser', [upload.single('syllabus'), limiter, cors(corsOptions)], (req, res) => {
+  PdfData.extract(req.file.buffer, {
+    verbosity: VerbosityLevel.ERRORS, // set the verbosity level for parsing
+    get: { // enable or disable data extraction (all are optional and enabled by default)
+      text: true, // get text of each page
+    },
+  }).then((data) => {
+    let result = [];
+    let content = data.text.join();
+    let matches = [...content.matchAll(re)];
+    for (const match of matches) {
+      const item = {
+        type: match[1],
+        description: match[2].trim(),
+        deadline: /\d{4}-\d{2}-\d{2}/.test(match[3]) ? match[3] : null,
+        on_going: match[3] === 'On-going',
+        weight: match[4]
+      }
+      result.push(item);
+    }
+    if (result.length === 0) {
+      res.status(400).send({
+        message: 'Invalid syllabus format. Cannot parse the uploaded syllabus.'
+      })
+    } else {
+      res.status(200).send(result);
+    }
+  }).catch(e => {
+    res.status(500).send({
+      message: e.message
+    })
+  })
+})
+
+module.exports = router