File size: 10,009 Bytes
849c2f4
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
6eaaedd
849c2f4
6eaaedd
 
849c2f4
 
 
 
6eaaedd
849c2f4
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
import express from "express";
import multer from "multer";
import cors from "cors";
import * as fs from "fs";
import * as path from "path";
import { Request, Response, NextFunction } from "express";
import pdfParse from "pdf-parse";
import OpenAI from "openai";
import dotenv from "dotenv";
import { getRecommendations } from "../utils/parseResume";
dotenv.config();

// Initialize OpenAI client

const openai = new OpenAI({
  apiKey: process.env.OPENAI_API_KEY, // Make sure to set this in your environment
});

interface ParsedData {
  skills: string[];
  experience: string[];
  education: string[];
}

// Add type declaration for Multer request
interface MulterRequest extends Request {
  file: Express.Multer.File;
}

interface QuestionnaireData {
  currentStatus: "student" | "unemployed";
  interimRole: boolean;
  dreamRole: string;
  motivation: string;
  learningPreference: "videos" | "projects" | "reading" | "all";
  timeCommitment: "1-2" | "2-4" | "4+";
  flexibleForInterim: boolean;
  challenges: string[];
  timeframe: "6months" | "12months" | "2years" | "flexible";
}

const app = express();

// Configure CORS
app.use(
  cors({
    origin: "*", // Your frontend URL
    methods: ["POST", "GET", "OPTIONS"],
    allowedHeaders: ["Content-Type"],
  })
);


// Create uploads directory if it doesn't exist
if (!fs.existsSync("/tmp/uploads")) {
  fs.mkdirSync("/tmp/uploads");
}

// Configure multer for file uploads
const upload = multer({
  dest: "/tmp/uploads/",
  fileFilter: (req, file, cb) => {
    if (file.mimetype === "application/pdf") {
      cb(null, true);
    } else {
      cb(null, false);
      return cb(new Error("Only PDF files are allowed"));
    }
  },
});

// Import pdf-parse with options
const pdfParseOptions = {
  // Ensure all pages are read
  max: 0,
  // Use a more robust page rendering
  pagerender: function (pageData: any) {
    const renderOptions = {
      normalizeWhitespace: false,
      disableCombineTextItems: false,
    };
    return pageData
      .getTextContent(renderOptions)
      .then(function (textContent: any) {
        let lastY,
          text = "";
        for (let item of textContent.items) {
          if (lastY == item.transform[5] || !lastY) {
            text += item.str;
          } else {
            text += "\n" + item.str;
          }
          lastY = item.transform[5];
        }
        return text;
      });
  },
};

const parseResumeContent = (text: string) => {
  console.log("Raw text from PDF:", text); // Debug log to see the raw text

  // More flexible regex patterns
  const skillsMatch = text.match(
    /(?:SKILLS?|TECHNICAL SKILLS?)[:\s]+([\s\S]*?)(?=(?:EXPERIENCE|EDUCATION|WORK|EMPLOYMENT|PROFESSIONAL|$))/i
  );
  const experienceMatch = text.match(
    /(?:EXPERIENCE|WORK|EMPLOYMENT|PROFESSIONAL)[:\s]+([\s\S]*?)(?=(?:EDUCATION|SKILLS?|$))/i
  );
  const educationMatch = text.match(
    /(?:EDUCATION|ACADEMIC|QUALIFICATIONS)[:\s]+([\s\S]*?)(?=(?:EXPERIENCE|WORK|SKILLS?|$))/i
  );

  // Process skills
  const skillsText = skillsMatch ? skillsMatch[1] : "";
  const skillsList = skillsText
    .split(/[,\n•]/) // Split by commas, newlines, or bullet points
    .map((skill) => skill.trim())
    .filter((skill) => skill.length > 2); // Filter out very short strings

  // Process experience
  const experienceText = experienceMatch ? experienceMatch[1] : "";
  const experienceList = experienceText
    .split(/(?:\r?\n){2,}/) // Split by multiple newlines
    .map((exp) => exp.replace(/^\s*[•-]\s*/gm, "").trim()) // Remove bullet points
    .filter((exp) => exp.length > 10); // Filter out short lines

  // Process education
  const educationText = educationMatch ? educationMatch[1] : "";
  const educationList = educationText
    .split(/(?:\r?\n){2,}/)
    .map((edu) => edu.replace(/^\s*[•-]\s*/gm, "").trim())
    .filter((edu) => edu.length > 10);

  // Debug logs
  console.log("Found sections:", {
    skills: !!skillsMatch,
    experience: !!experienceMatch,
    education: !!educationMatch,
  });

  console.log("Parsed sections:", {
    skillsCount: skillsList.length,
    experienceCount: experienceList.length,
    educationCount: educationList.length,
    skillsList,
    experienceList,
    educationList,
  });

  return {
    skills: skillsList,
    experience: experienceList,
    education: educationList,
  };
};

const handleFileUpload = async (req: Request, res: Response): Promise<void> => {
  let filePath = "";
  try {
    if (!req.file) {
      res.status(400).json({ error: "No file uploaded" });
      return;
    }

    const questionnaireData = JSON.parse(req.body.questionnaireData || "{}");
    console.log("Received dream role:", questionnaireData.dreamRole);

    filePath = req.file.path;
    console.log("File received:", req.file);

    const dataBuffer = fs.readFileSync(filePath);
    const pdfData = await pdfParse(dataBuffer);

    // Parse resume sections
    const parsedData = parseResumeContent(pdfData.text);
    console.log("Parsed resume data:", parsedData);

    // Get recommendations using the parsed data
    const recommendations = await getRecommendations(
      parsedData,
      questionnaireData.dreamRole,
      questionnaireData
    );

    // Update the OpenAI prompt to specifically request benefits information
    const completion = await openai.chat.completions.create({
      model: "gpt-4o-mini", // or whichever model you're using
      messages: [
        {
          role: "system",
          content:
            "You are a career advisor creating personalized course recommendations.",
        },
        {
          role: "user",
          content: `Create detailed course recommendations based on:
            Skills: ${parsedData.skills.join(", ")}
            Experience: ${parsedData.experience.join("\n")}
            Education: ${parsedData.education.join("\n")}
            Dream Role: ${questionnaireData.dreamRole}

            Additional Personal Context:
            - Current Status: ${questionnaireData.currentStatus}
            - Interested in Interim Role: ${questionnaireData.interimRole}
            - Motivation: ${questionnaireData.motivation}
            - Preferred Learning Style: ${questionnaireData.learningPreference}
            - Daily Time Commitment: ${questionnaireData.timeCommitment} hours
            - Main Challenges: ${questionnaireData.challenges.join(", ")}
            - Target Timeframe: ${questionnaireData.timeframe}
            
            For each course, you MUST include:
            - title: A specific course title
            - description: Brief description of the course content
            - platform: Where the course is offered (Coursera, Udemy, etc.)
            - duration: How long it takes to complete
            - level: Difficulty level
            - link: URL to the course
            - benefitsInterim: IMPORTANT - Specific benefits for an interim role
            - benefitsDream: IMPORTANT - Specific benefits for the dream role

            Return exactly this JSON structure:
            {
              "courses": [
                {
                  "title": "Course Name",
                  "description": "Course Description",
                  "duration": "Duration",
                  "platform": "Platform Name",
                  "level": "Difficulty Level",
                  "link": "https://example.com",
                  "benefitsInterim": "Detailed explanation of how this helps with interim roles",
                  "benefitsDream": "Detailed explanation of how this helps with the dream role"
                }
              ],
              "roles": [
                {
                  "title": "Role Title",
                  "description": "Role Description",
                  "timeline": "Timeline",
                  "salary": "Salary Range"
                }
              ]
            }`,
        },
      ],
      response_format: { type: "json_object" },
    });

    // Make sure we're properly handling the response
    const result = JSON.parse(completion.choices[0].message.content || "{}");

    // Validate that each course has the required fields
    const validatedCourses = result.courses.map((course: any) => {
      return {
        title: course.title || "Course Title",
        description: course.description || "No description available",
        duration: course.duration || "Unknown duration",
        platform: course.platform || "Online platform",
        level: course.level || "Intermediate",
        link: course.link || "#",
        benefitsInterim:
          course.benefitsInterim ||
          "Builds foundational skills needed for entry-level positions",
        benefitsDream:
          course.benefitsDream ||
          "Contributes to the skill set required for your dream role",
      };
    });

    // Return the validated courses
    res.json({
      skills: parsedData.skills,
      experience: parsedData.experience,
      education: parsedData.education,
      recommendations: {
        courses: recommendations.courses || [],
        roles: recommendations.roles || [],
      },
    });
  } catch (error) {
    console.error("Server Error:", error);
    res.status(500).json({
      error: "Failed to process resume",
      details: error instanceof Error ? error.message : "Unknown error",
    });
  } finally {
    // Clean up uploaded file
    if (filePath && fs.existsSync(filePath)) {
      fs.unlinkSync(filePath);
    }
  }
};

app.post("/api/parse-resume", upload.single("resume"), handleFileUpload);
app.get("/api/test", (req, res) => {
  res.json({ message: "Hello, World!" });
});
const PORT = process.env.PORT || 3001;

app
  .listen(PORT, () => {
    console.log(`Server running on port ${PORT}`);
  })
  .on("error", (err: NodeJS.ErrnoException) => {
    if (err.code === "EADDRINUSE") {
      console.log(`Port ${PORT} is busy, trying ${PORT}...`);
      app.listen(PORT);
    } else {
      console.error("Server error:", err);
      process.exit(1);
    }
  });