Merge pull request #258 from COS301-SE-2024/develop

Develop into Main
COS301-SE-2024 · Oct 18, 2024 · 20eeabe · 20eeabe
2 parents e2b2f2f + 8f0d8ff
commit 20eeabe
Show file tree

Hide file tree

Showing 77 changed files with 4,442 additions and 1,985 deletions.
diff --git a/.DS_Store b/.DS_Store
diff --git a/.github/workflows/frontendTests.yml b/.github/workflows/frontendTests.yml
@@ -24,10 +24,11 @@ jobs:
         cache: 'npm'
         cache-dependency-path: gnd-app/package-lock.json
 
-    - name: Install Chrome
+    - name: Install Chrome and install pandoc
       run: |
           sudo apt-get update
           sudo apt-get install -y google-chrome-stable
+          sudo apt-get install pandoc
 
     - run: |
         cd gnd-app

diff --git a/.gitignore b/.gitignore
@@ -15,3 +15,5 @@ env
 .env
 .vs/
 .pyc
+# /gnd-app/src/environments/environment.ts
+# /gnd-app/src/environments/environment.prod.ts
diff --git a/README.md b/README.md
@@ -1,4 +1,4 @@
-![image](https://github.com/user-attachments/assets/98c03af9-5f20-4d6e-8140-b4a69f7ff72f)<img src="https://github.com/COS301-SE-2024/GDPR-data-noncompliance-detector/blob/develop/documentation/headshots/GND.png" alt="GND Logo">
+![image]()<img src="https://github.com/COS301-SE-2024/GDPR-data-noncompliance-detector/blob/develop/documentation/headshots/GND.png" alt="GND Logo">
 
 [![codecov](https://codecov.io/github/COS301-SE-2024/GDPR-data-noncompliance-detector/graph/badge.svg?token=nEPpXWGssM)](https://codecov.io/github/COS301-SE-2024/GDPR-data-noncompliance-detector)
 ![GitHub issues](https://img.shields.io/github/issues/COS301-SE-2024/GDPR-data-noncompliance-detector)
@@ -42,7 +42,9 @@ The GDPR Data Noncompliance Detector is a software tool designed to identify ins
 <br></br>
 # Download
 
-[EXE Download]([https://drive.google.com/drive/folders/1LANx27MNDwmfvDtj09NFvJ05s91Ya-7n?usp=sharing](https://drive.google.com/file/d/1-zytmykMq8Prb-izSKI4gjCQbvzhBZk9/view?usp=drive_link))
+
+[https://drive.google.com/drive/folders/1LANx27MNDwmfvDtj09NFvJ05s91Ya-7n?usp=sharing](https://drive.google.com/file/d/1WV0WCWq1VSLAgREVHJ523JzclZXMwBnW/view?usp=sharing
+
 
 #Demo 4 Input
 
@@ -67,6 +69,10 @@ The GDPR Data Noncompliance Detector is a software tool designed to identify ins
 ## User Manual
 [GND User Manual](https://github.com/COS301-SE-2024/GDPR-data-noncompliance-detector/blob/develop/documentation/GND%20Manual_V2.pdf)
 
+## Machine Learning Training Specification
+[AIML_Spec.pdf](https://github.com/user-attachments/files/17433721/AIML_Spec.pdf)
+
+
 ## Project Management Tools
 GitHub Issues and GitHub Boards
 

diff --git a/backend/.DS_Store b/backend/.DS_Store
diff --git a/backend/Detection_Engine/RAG.py b/backend/Detection_Engine/RAG.py
@@ -133,7 +133,7 @@ def interpret_findings(self, labels):
             'LABEL_4': ['6','7(1)','7(2)','7(3)'],
             'LABEL_5': ['12']
             }
-
+#['5','6',['9','9(1)','9(2)(b)','9(2)(g)']]
         unique_labels = set()
         count = 0
 

diff --git a/backend/Detection_Engine/biometric_detection.py b/backend/Detection_Engine/biometric_detection.py
@@ -4,6 +4,8 @@
 import sys
 import os
 import glob
+from gradio_client import Client, handle_file
+import re
 
 
 # below added because of the relative import error
@@ -80,6 +82,28 @@ def biometric_detect_people(self, source):
             if item['label'] != 'person':
                 output.remove(item)
         return output
+
+
+    def biometric_detect_finger(self, source):
+        client = Client("abdullahsajid/multimodal-antispoofing-detection")
+        result = client.predict(
+		image=handle_file(source),
+		api_name="/handle_button_click_finger"
+        )
+        real_pattern = re.compile(r'Real:</b>\s*(\d+\.\d+)%')
+        spoof_pattern = re.compile(r'Spoof:</b>\s*(\d+\.\d+)%')
+
+        real_match = real_pattern.search(result)
+        spoof_match = spoof_pattern.search(result)
+
+        real_percentage = float(real_match.group(1) ) if real_match else None
+        spoof_percentage = float(spoof_match.group(1))  if spoof_match else None
+
+        if real_percentage > 75 or spoof_percentage > 75:
+            return True
+        return False
+
+
 
     def biometric_detect_all(self,pdf_path):
         # clean up folders
@@ -96,6 +120,8 @@ def biometric_detect_all(self,pdf_path):
             count = 0
             for image in images:
                 people = self.biometric_detect_people(image)
+                # if(self.biometric_detect_finger(image)):
+                    # count += 1
                 for person in people:
                     count += 1
 
@@ -180,5 +206,5 @@ def biometric_detect_all(self,pdf_path):
     # print(biometric_detect_all("../mockdata/excelWimages.xlsx"))
     # Example for accessing mock data if it's bundled with PyInstaller
     bm = biometric_detection()
-    print(bm.biometric_detect_people("../mockdata/p7.png"))
+    print(bm.biometric_detect_finger("../mockdata/p3.png"))
     # extract_images_from_excel("../mockdata/excelWimages.xlsx")
diff --git a/backend/Detection_Engine/detection_engine.py b/backend/Detection_Engine/detection_engine.py
@@ -8,6 +8,7 @@
 import os
 import math
 import base64
+import concurrent.futures
 
 class detection_engine:
 
@@ -58,20 +59,74 @@ def flag(self, ner_result, reg_result_contact,reg_result_financial,reg_result_pe
         ner_val = self.extract_number(ner_result)
         total = ner_val + reg_result_contact + reg_result_financial + reg_result_personal + gi_result + em_result
 
+    def generate_location_report(self, text):
+        return self.report_generator.location_report_generation(text)
+
+    def generate_ner_report(self, text):
+        return self.report_generator.ner_report(text)
+
+    def generate_regex_report_personal(self, text):
+        return self.regex_report_personal(text)
+
+    def generate_regex_report_financial(self, text):
+        return self.regex_report_financial(text)
+
+    def generate_regex_report_contact(self, text):
+        return self.regex_report_contact(text)
+
+    def generate_ca_report(self, text):
+        return self.report_generator.CA_report(text)
+
+    def generate_gi_report(self, text):
+        return self.report_generator.gen_report(text)
+
+    def generate_em_report(self, text):
+        return self.report_generator.EM_report(text)
+
+    def generate_md_report(self, text):
+        return self.report_generator.MD_report(text)
+
+    def generate_image_report(self, path_):
+        return self.report_generator.Image_report_generation(path_)
+
+
     def process(self, path, path_):
 
         text = path
 
-        location = self.report_generator.location_report_generation(text)
-        ner_result = self.report_generator.ner_report(text)
+        with concurrent.futures.ThreadPoolExecutor() as executor:
+            future_location = executor.submit(self.generate_location_report, text)
+            future_ner = executor.submit(self.generate_ner_report, text)
+            future_reg_personal = executor.submit(self.generate_regex_report_personal, text)
+            future_reg_financial = executor.submit(self.generate_regex_report_financial, text)
+            future_reg_contact = executor.submit(self.generate_regex_report_contact, text)
+            future_ca = executor.submit(self.generate_ca_report, text)
+            future_gi = executor.submit(self.generate_gi_report, text)
+            future_em = executor.submit(self.generate_em_report, text)
+            # future_md = executor.submit(self.generate_md_report, text)
+
+            location = future_location.result()
+            ner_result = future_ner.result()
+            reg_result_personal = future_reg_personal.result()
+            reg_result_financial = future_reg_financial.result()
+            reg_result_contact = future_reg_contact.result()
+            ca_statement = future_ca.result()
+            gi_result = future_gi.result()
+            em_result = 50000
+            # em_result = future_em.result()
+            md_result = 50000
+            # md_result = future_md.result()
+
+        # location = self.report_generator.location_report_generation(text)
+        # ner_result = self.report_generator.ner_report(text)
         # location = self.determine_country_of_origin(path)
-        reg_result_personal = self.regex_report_personal(text)
-        reg_result_financial = self.regex_report_financial(text)
-        reg_result_contact = self.regex_report_contact(text)
-        ca_statement = self.report_generator.CA_report(text)
-        gi_result = self.report_generator.gen_report(text)
-        em_result = self.report_generator.EM_report(text)
-        md_result = self.report_generator.MD_report(text)
+        # reg_result_personal = self.regex_report_personal(text)
+        # reg_result_financial = self.regex_report_financial(text)
+        # reg_result_contact = self.regex_report_contact(text)
+        # ca_statement = self.report_generator.CA_report(text)
+        # gi_result = self.report_generator.gen_report(text)
+        # em_result = self.report_generator.EM_report(text)
+        # md_result = self.report_generator.MD_report(text)
         status = ""
 
         if self.flag(ner_result, reg_result_contact,reg_result_financial,reg_result_personal, gi_result, em_result) == 0:
@@ -182,20 +237,38 @@ def get_status(self, ner_count, personal_data,financial_data, contact_data, medi
 
     def report_generation(self, path, path_):
 
-        text = path
+        location_report = 0
+        reg_result_personal_report = 0
+        # ca_statement_report = 0
+        em_result_report = 0
+        image_result_report = 0
 
-        location_report = self.report_generator.location_report_generation(text)
+        text = path
+        with concurrent.futures.ThreadPoolExecutor() as executor:
+            future_location = executor.submit(self.generate_location_report, text)
+            future_reg_personal = executor.submit(self.generate_regex_report_personal, text)
+            future_ca = executor.submit(self.generate_ca_report, text)
+            future_em = executor.submit(self.generate_em_report, text)
+            future_image = executor.submit(self.generate_image_report,path_)
+
+            location_report = future_location.result()
+            reg_result_personal_report = future_reg_personal.result()
+            # ca_statement_report = future_ca.result()
+            em_result_report = future_em.result()
+            image_result_report = future_image.result()
+
+        # location_report = self.report_generator.location_report_generation(text)
         ner_result_report = self.report_generator.ner_report_generation(text)
-        reg_result_personal_report = self.regex_report_personal(text) + self.report_generator.gen_report(text)
+        # reg_result_personal_report = self.regex_report_personal(text) + self.report_generator.gen_report(text)
         reg_result_financial_report = self.regex_report_financial(text)
         reg_result_contact_report = self.regex_report_contact(text)
         ca_statement_report = self.report_generator.CA_report_generation(text)
         gi_result_report = self.report_generator.GF_report(text)
-        em_result_report = self.report_generator.EM_report(text)
+        # em_result_report = self.report_generator.EM_report(text)
         md_result_report = self.report_generator.MD_report(text)
-        image_result_report = self.report_generator.Image_report_generation(path_)
+        # image_result_report = self.report_generator.Image_report_generation(path_)
         rag_stat, rag_count = self.report_generator.RAG_report(ner_result_report , reg_result_personal_report, reg_result_financial_report, reg_result_contact_report, md_result_report,ca_statement_report, gi_result_report, em_result_report, image_result_report)
-
+        # ca_statement_report = self.report_generator.CA_report_generation(text)
         # ner_result_text = self.report_generator.ner_report_text(text)
         ner_pdf_bytes = self.report_generator.ner_report_text(text, path_)
         pdf_base64 = base64.b64encode(ner_pdf_bytes.read()).decode('utf-8')

diff --git a/backend/Detection_Engine/report_generation_layer.py b/backend/Detection_Engine/report_generation_layer.py
@@ -1,7 +1,6 @@
 from Detection_Engine.text_classification_layer import text_classification_layer
 from Detection_Engine.biometric_detection import biometric_detection
 from Detection_Engine.lang_detection import location_finder
-from langcodes import Language
 
 from reportlab.pdfgen import canvas
 from reportlab.lib.pagesizes import A4
@@ -189,8 +188,8 @@ def RAG_report(self, ner_result , personal, financial, contact, medical, ca_stat
             categories.append('Biometric Data')
 
         rag_res, rag_count = self.classification_layer.run_RAG(categories)
-        result = "The following GDPR articles are potentially violated: " + ", ".join(rag_res)
-        return result, rag_count
+        # result = "The following GDPR articles are potentially violated: " + ", ".join(rag_res)
+        return rag_res, rag_count
-Original file line number
+Diff line change
@@ Expand Up / @@ -15,3 +15,5 @@ env @@
     .env
     .vs/
     .pyc
+    # /gnd-app/src/environments/environment.ts
+    # /gnd-app/src/environments/environment.prod.ts