Added similariy metric

5 files changed, 111 insertions, 35 deletions

diff --git a/README.md b/README.md
index 185d986..2914835 120000
--- a/README.md
+++ b/README.md
@@ -15,6 +15,8 @@ formats.
 - Generate plagarism reports
 - Isolate code in a docker container for security
 
+### Screenshots
+
 ![Function Analysis](https://smarker.eda.gay/_static/readme_functionanalysis.png)
 
 Function Analysis
diff --git a/Smarker/assessments.py b/Smarker/assessments.py
index 4f32353..b8eb6f0 100644
--- a/Smarker/assessments.py
+++ b/Smarker/assessments.py
@@ -1,28 +1,82 @@
+from dataclasses import dataclass
 import misc_classes
 import configparser
 import jinja_helpers
 import pycode_similar
+import subprocess
 import operator
 import database
 import argparse
 import tempfile
 import yaml
+import json
 import os
+import re
 
-def generate_plagarism_report(codes):
-    for file_name, codes in codes.items():
+@dataclass
+class SimilarityMetric:
+    code_text_1:str
+    code_text_2:str
+    id_1:int
+    id_2:int
+
+    def __post_init__(self):
+        with tempfile.TemporaryDirectory() as td:
+            with open(os.path.join(td, "%i.py" % self.id_1), "w") as f:
+                f.write(self.code_text_1)
+
+            with open(os.path.join(td, "%i.py" % self.id_2), "w") as f:
+                f.write(self.code_text_2)
+
+            proc = subprocess.Popen(["pycode_similar", "-p", "0", os.path.join(td, "%i.py" % self.id_1), os.path.join(td, "%i.py" % self.id_2)], stdout = subprocess.PIPE)
+            self.details = ""
+            while True:
+                line = proc.stdout.readline()
+                if not line:
+                    break
+                self.details += line.decode()
+
+    def get_similarity(self):
+        return float(re.findall(r"\d+\.\d+\s", self.details)[0])
+
+
+def generate_plagarism_report(assessment_name, db):
+    required_files = db.get_assessments_required_files(assessment_name)
+    submission_ids_to_get = set()
+    assessments = db.get_submissions(assessment_name)
+    un_added_student_nos = {i[0] for i in assessments.keys()}
+    for id_, dt in sorted(assessments.keys(), key=operator.itemgetter(0, 1), reverse=True):
+        if id_ in un_added_student_nos:
+            files = jinja_helpers.flatten_struct(assessments[(id_, dt)][0]["files"])
+
+            for file_name in required_files:
+                if files[file_name]["present"]:
+                    if (not files[file_name]["has_exception"]):
+                        submission_ids_to_get.add(assessments[(id_, dt)][1])
+
+            un_added_student_nos.remove(id_)
+    
+    codes = db.get_submission_codes(submission_ids_to_get)
+    for file_name, submissions in codes.items():
         with tempfile.TemporaryDirectory() as td:
-            un_added_student_nos = {i[0] for i in codes.keys()}
-            # print(un_added_student_nos)
-            for k, v in sorted(codes.keys(), key=operator.itemgetter(0, 1), reverse=True):
-                if k in un_added_student_nos:
-                    with open(os.path.join(td, "%i.py" % k), "w") as f:
-                        f.write(codes[(k, v)])
+            print(file_name, len(submissions))
+            for student_id, code in submissions:
+                with open(os.path.join(td, "%i.py" % student_id), "w") as f:
+                    f.write(code)
+
+            cmd = ["pycode_similar"] + [os.path.join(td, f) for f in os.listdir(td)]
+            print(" ".join(cmd))
+            proc = subprocess.Popen(cmd, stdout = subprocess.PIPE)
+            stdout = ""
+            while True:
+                line = proc.stdout.readline()
+                if not line:
+                    break
+                stdout += line.decode()
+
+            print(stdout)
+            input("skfhsk")
                     
-                    # print("Written %s at %s" % (k, v))
-                    un_added_student_nos.remove(k)
-            input("%s..." % td)
-            print(pycode_similar.detect(os.listdir(td)))
 
 def getparser():
     config = configparser.ConfigParser()
@@ -120,7 +174,7 @@ if __name__ == "__main__":
             print("Added student %s" % name)
 
         if args["plagarism_report"] is not None:
-            generate_plagarism_report(db.get_submission_codes(args["plagarism_report"]))
+            generate_plagarism_report(args["plagarism_report"], db)
 
         
         # print(db.get_assessment_yaml("CMP-4009B-2020-A2"))
diff --git a/Smarker/database.py b/Smarker/database.py
index d6a2ea5..37a44db 100644
--- a/Smarker/database.py
+++ b/Smarker/database.py
@@ -204,34 +204,44 @@ class SmarkerDatabase:
                 ))
         self.__connection.commit()
 
-    def get_submission_codes(self, assessment_name):
+    def get_submission_codes(self, submission_ids):
         out = {}
         with self.__connection.cursor() as cursor:
-            cursor.execute("SELECT file_id, file_name FROM assessment_file WHERE assessment_name = %s;", (assessment_name, ))
-            for file_id, file_name in cursor.fetchall():
-                out[file_name] = {}
-
+            for submission_id in submission_ids:
                 cursor.execute("""
                 SELECT 
                     submitted_files.file_text, 
-                    submissions.student_no, 
-                    submissions.submission_dt 
+                    submitted_files.file_id, 
+                    assessment_file.file_name, 
+                    submissions.student_no 
                 FROM submitted_files 
+                INNER JOIN assessment_file 
+                ON submitted_files.file_id = assessment_file.file_id 
                 INNER JOIN submissions 
-                ON submissions.submission_id = submitted_files.submission_id 
-                WHERE submitted_files.file_id = %s;
-                """, (file_id, ))
-
-                for code, student_no, dt in cursor.fetchall():
-                    out[file_name][(int(student_no), dt)] = code
+                ON submissions.submission_id = submitted_files.submission_id
+                WHERE submitted_files.submission_id = %s;
+                """, (submission_id))
+                
+                for file_contents, id_, file_name, student_no in cursor.fetchall():
+                    if file_contents is not None:
+                        try:
+                            out[file_name].append((int(student_no), file_contents))
+                        except KeyError:
+                            out[file_name] = [(int(student_no), file_contents)]
         return out
 
-    def get_most_recent_submission_report(self, assessment_name):
+    def get_submissions(self, assessment_name):
         with self.__connection.cursor() as cursor:
-            cursor.execute("SELECT MAX(submission_id), student_no FROM submissions WHERE assessment_name = %s GROUP BY student_no;", (assessment_name, ))
-            return [(int(i[0]), int(i[1]), yaml.safe_load(i[2])) for i in cursor.fetchall()]
-                
+            cursor.execute("SELECT student_no, submission_dt, report_yaml, submission_id FROM submissions WHERE assessment_name = %s;", (assessment_name, ))
+            return {(int(i[0]), i[1]): (yaml.safe_load(i[2]), int(i[3])) for i in cursor.fetchall()}
+
+    def get_assessments_required_files(self, assessment_name):
+        with self.__connection.cursor() as cursor:       
+            cursor.execute("SELECT file_name FROM assessment_file WHERE assessment_name = %s;", (assessment_name, ))   
+            return [i[0] for i in cursor.fetchall()]
 
 if __name__ == "__main__":
     with SmarkerDatabase(host = "vps.eda.gay", user="root", passwd=input("Input password: "), db="Smarker", port=3307) as db:
-        print(db.get_most_recent_submission_report("simple_assessment"))
+        # print(db.get_assessments_required_files("example"))
+        import json
+        print(json.dumps(db.get_submission_codes((24, 21)), indent = 4))
diff --git a/Smarker/temp.py b/Smarker/temp.py
index 60b1c18..491729f 100644
--- a/Smarker/temp.py
+++ b/Smarker/temp.py
@@ -1,6 +1,14 @@
-import json
+import assessments
+import sys
+import os
 
-with open("100301654_report.json", "r") as f:
-    tree = json.load(f)["class_tree"]
+if __name__ == "__main__":
+    with open(sys.argv[1], "r") as f:
+        ft1 = f.read()
 
-print(tree)
\ No newline at end of file
+    with open(sys.argv[2], "r") as f:
+        ft2 = f.read()
+
+    similarityMetric = assessments.SimilarityMetric(ft1, ft2, 1, 2)
+    print(similarityMetric.get_similarity())
+    print(similarityMetric.details)
\ No newline at end of file
diff --git a/docs/source/readme.md b/docs/source/readme.md
index 185d986..2914835 100644
--- a/docs/source/readme.md
+++ b/docs/source/readme.md
@@ -15,6 +15,8 @@ formats.
 - Generate plagarism reports
 - Isolate code in a docker container for security
 
+### Screenshots
+
 ![Function Analysis](https://smarker.eda.gay/_static/readme_functionanalysis.png)
 
 Function Analysis