From 8e85ba75fff5ff3419acebd694c2b471af05bd6c Mon Sep 17 00:00:00 2001
From: linhkhanhhoang <93673250+linhkhanhhoang@users.noreply.github.com>
Date: Mon, 27 May 2024 21:31:43 +0700
Subject: [PATCH] pdf parsing file from s3

---
 server/package-lock.json       | 26 ++++++++++++++++++++++++++
 server/package.json            |  1 +
 server/src/utils/extractPDF.js | 21 +++++++++++++++++++++
 3 files changed, 48 insertions(+)
 create mode 100644 server/src/utils/extractPDF.js

diff --git a/server/package-lock.json b/server/package-lock.json
index a174001..47fb600 100644
--- a/server/package-lock.json
+++ b/server/package-lock.json
@@ -24,6 +24,7 @@
         "mongoose": "^8.2.3",
         "multer": "^1.4.5-lts.1",
         "nodemon": "^3.1.0",
+        "pdf-parse": "^1.1.1",
         "serverless": "^3.38.0",
         "serverless-http": "^3.2.0",
         "supertest": "^6.3.4",
@@ -10390,6 +10391,11 @@
         "node": ">= 0.10.5"
       }
     },
+    "node_modules/node-ensure": {
+      "version": "0.0.0",
+      "resolved": "https://registry.npmjs.org/node-ensure/-/node-ensure-0.0.0.tgz",
+      "integrity": "sha512-DRI60hzo2oKN1ma0ckc6nQWlHU69RH6xN0sjQTjMpChPfTYvKZdcQFfdYK2RWbJcKyUizSIy/l8OTGxMAM1QDw=="
+    },
     "node_modules/node-fetch": {
       "version": "2.7.0",
       "resolved": "https://registry.npmjs.org/node-fetch/-/node-fetch-2.7.0.tgz",
@@ -10952,6 +10958,26 @@
       "resolved": "https://registry.npmjs.org/path2/-/path2-0.1.0.tgz",
       "integrity": "sha512-TX+cz8Jk+ta7IvRy2FAej8rdlbrP0+uBIkP/5DTODez/AuL/vSb30KuAdDxGVREXzn8QfAiu5mJYJ1XjbOhEPA=="
     },
+    "node_modules/pdf-parse": {
+      "version": "1.1.1",
+      "resolved": "https://registry.npmjs.org/pdf-parse/-/pdf-parse-1.1.1.tgz",
+      "integrity": "sha512-v6ZJ/efsBpGrGGknjtq9J/oC8tZWq0KWL5vQrk2GlzLEQPUDB1ex+13Rmidl1neNN358Jn9EHZw5y07FFtaC7A==",
+      "dependencies": {
+        "debug": "^3.1.0",
+        "node-ensure": "^0.0.0"
+      },
+      "engines": {
+        "node": ">=6.8.1"
+      }
+    },
+    "node_modules/pdf-parse/node_modules/debug": {
+      "version": "3.2.7",
+      "resolved": "https://registry.npmjs.org/debug/-/debug-3.2.7.tgz",
+      "integrity": "sha512-CFjzYYAi4ThfiQvizrFQevTTXHtnCqWfe7x1AhgEscTz6ZbLbfoLRLPugTQyBth6f8ZERVUSyWHFD/7Wu4t1XQ==",
+      "dependencies": {
+        "ms": "^2.1.1"
+      }
+    },
     "node_modules/peek-readable": {
       "version": "4.1.0",
       "resolved": "https://registry.npmjs.org/peek-readable/-/peek-readable-4.1.0.tgz",
diff --git a/server/package.json b/server/package.json
index 8a0bdb6..31c315e 100644
--- a/server/package.json
+++ b/server/package.json
@@ -29,6 +29,7 @@
     "mongoose": "^8.2.3",
     "multer": "^1.4.5-lts.1",
     "nodemon": "^3.1.0",
+    "pdf-parse": "^1.1.1",
     "serverless": "^3.38.0",
     "serverless-http": "^3.2.0",
     "supertest": "^6.3.4",
diff --git a/server/src/utils/extractPDF.js b/server/src/utils/extractPDF.js
new file mode 100644
index 0000000..690a215
--- /dev/null
+++ b/server/src/utils/extractPDF.js
@@ -0,0 +1,21 @@
+import pdf from "pdf-parse";
+import axios from "axios";
+export const getResumeFromS3 = async (resume_url) => {
+  const pdfUrl = resume_url;
+
+  const response = await axios.get(pdfUrl, { responseType: "arraybuffer" });
+  return response.data;
+};
+
+const parsePdf = async (filePath) => {
+  try {
+    const dataBuffer = await getResumeFromS3(filePath);
+    const data = await pdf(dataBuffer);
+
+    return data.text;
+  } catch (error) {
+    console.error("Error parsing PDF:", error);
+  }
+};
+
+export default parsePdf;