Skip to content
Merged
Show file tree
Hide file tree
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension


Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
56 changes: 56 additions & 0 deletions mrz_reader.py
Original file line number Diff line number Diff line change
@@ -0,0 +1,56 @@
import sys
import json
import os
import pytesseract
from passporteye import read_mrz
Comment on lines +4 to +5

pytesseract.pytesseract.tesseract_cmd = r'C:\Program Files\Tesseract-OCR\tesseract.exe'
os.environ['TESSDATA_PREFIX'] = r'C:\Program Files\Tesseract-OCR\tessdata'
Comment on lines +7 to +8

def fix_nationality(raw):
# Fix common substitutions in 3-char nationality codes
subs = {'0': 'O', '1': 'I', '3': 'A', '8': 'B', '6': 'G', '5': 'S'}
return ''.join(subs.get(c, c) for c in raw.upper()[:3])

def fix_last_name(raw):
# H between two vowel-adjacent consonants is likely M
# More targeted: SLI_ANI pattern — the _ is M
import re
raw = re.sub(r'(?<=[A-Z])H(?=[A-Z])', 'M', raw)
return raw
Comment on lines +15 to +20

def parse_dob(raw):
yy = ''.join(c for c in raw[:2] if c.isdigit())
if not yy:
return None
yyyy = f"19{yy}" if int(yy) >= 30 else f"20{yy}"
return f"{yyyy}-01-01"
Comment on lines +22 to +27

def parse_expiry(raw):
raw = raw.upper().replace('F', '5').replace('S', '5').replace('O', '0').replace('I', '1').replace('B', '8')
digits = ''.join(c for c in raw if c.isdigit())
if len(digits) < 6:
return None
yy = digits[0:2]
mm = digits[2:4]
dd = digits[4:6]
yyyy = f"20{yy}"
mm = mm if 1 <= int(mm) <= 12 else "01"
dd = dd if 1 <= int(dd) <= 31 else "01"
return f"{yyyy}-{mm}-{dd}"

image_path = sys.argv[1]
mrz = read_mrz(image_path, extra_cmdline_params='--oem 0')

if mrz is None:
print(json.dumps({"error": "No MRZ detected"}))
else:
d = mrz.to_dict()
print(json.dumps({
"firstName": d.get("names", "").strip(),
"lastName": fix_last_name(d.get("surname", "").strip()),
"passportNumber": d.get("number", "").strip(),
"nationality": fix_nationality(d.get("nationality", "")),
"dateOfBirth": parse_dob(d.get("date_of_birth", "")),
"passportExpiry": parse_expiry(d.get("expiration_date", "")),
}))
144 changes: 144 additions & 0 deletions package-lock.json

Some generated files are not rendered by default. Learn more about how customized files appear on GitHub.

1 change: 1 addition & 0 deletions package.json
Original file line number Diff line number Diff line change
Expand Up @@ -18,6 +18,7 @@
"express": "^5.2.1",
"joi": "^18.1.2",
"jsonwebtoken": "^9.0.3",
"multer": "^2.1.1",
"pdfkit": "^0.18.0",
"pg": "^8.20.0",
"qrcode": "^1.5.4",
Expand Down
71 changes: 71 additions & 0 deletions routes/checkin.js
Original file line number Diff line number Diff line change
Expand Up @@ -4,6 +4,23 @@ const db = require("../src/config/db");

const router = express.Router();

const multer = require("multer");
const fs = require("fs");
const { execFile } = require("child_process");

const upload = multer({
dest: "tmp/",
limits: { fileSize: 10 * 1024 * 1024 },
fileFilter: (req, file, cb) => {
const allowed = ["image/jpeg", "image/png", "image/jpg"];
if (allowed.includes(file.mimetype)) {
cb(null, true);
} else {
cb(new Error("Only JPEG and PNG images are allowed"));
}
},
});

router.get("/booking/lookup", async (req, res, next) => {
try {
const { reference, lastName } = req.query;
Expand Down Expand Up @@ -145,6 +162,60 @@ router.post("/checkin/:id/passport", async (req, res, next) => {
}
});

router.post("/checkin/:id/passport/ocr",
upload.single("passport"),
async (req, res, next) => {
const filePath = req.file?.path;
try {
const checkInId = req.params.id;
if (!req.file) {
return res.status(400).json({ message: "Passport image is required" });
}
const checkInResult = await db.query(
"SELECT id FROM CHECKIN WHERE id = $1", [checkInId]
);
if (checkInResult.rows.length === 0) {
return res.status(404).json({ message: "Check-in not found" });
}
const parsed = await new Promise((resolve, reject) => {
execFile("python", ["mrz_reader.py", filePath], (err, stdout, stderr) => {
if (err) return reject(err);
try {
resolve(JSON.parse(stdout));
} catch (e) {
reject(new Error("Failed to parse PassportEye output: " + stdout));
}
});
});
console.log("[OCR] PassportEye result:", parsed);
if (parsed.error || !parsed.passportNumber) {
return res.status(422).json({
message : "Could not extract passport data. Please fill in manually.",
extracted: null,
});
}
await db.query(
`UPDATE CHECKIN
SET "firstName" = $1,
"lastName" = $2,
"passportNumber" = $3,
"passportExpiry" = $4,
nationality = $5,
"dateOfBirth" = $6,
"isIdentityVerified" = FALSE
WHERE id = $7`,
[parsed.firstName, parsed.lastName, parsed.passportNumber,
parsed.passportExpiry, parsed.nationality, parsed.dateOfBirth, checkInId]
);
return res.status(200).json({ checkInId, extracted: parsed });
} catch (err) {
return next(err);
} finally {
if (filePath && fs.existsSync(filePath)) fs.unlinkSync(filePath);
}
}
);

router.post("/checkin/:id/passport/confirm", async (req, res, next) => {
try {
const checkInId = req.params.id;
Expand Down