From da904bea5b426ad59eee765216bff5a86c7ddf0f Mon Sep 17 00:00:00 2001
From: AfonsoSantos96 <afomms@gmail.com>
Date: Wed, 22 Nov 2023 11:41:47 +0000
Subject: [PATCH] feat(HIS): added checker of a file comment density

Signed-off-by: Afonso Santos <afomms@gmail.com>
---
 docker/Dockerfile |  6 ++++--
 his_checker.py    | 36 +++++++++++++++++++++++++++++-------
 2 files changed, 33 insertions(+), 9 deletions(-)

diff --git a/docker/Dockerfile b/docker/Dockerfile
index 9fe1a6d..5f47e88 100644
--- a/docker/Dockerfile
+++ b/docker/Dockerfile
@@ -38,7 +38,8 @@ RUN apt-get update && apt-get install -y \
         tree \
         vim \
         nano \
-        device-tree-compiler
+        device-tree-compiler \
+	pmccabe
 
 # Install python packages
 RUN pip3 install \
@@ -56,7 +57,8 @@ RUN pip3 install \
         pyspellchecker \
         ROPgadget \
         capstone \
-        GitPython
+        GitPython \
+	pygount
 
 # Install javascript packages
 RUN npm install -g cspell@latest
diff --git a/his_checker.py b/his_checker.py
index 9f2a17d..5439556 100755
--- a/his_checker.py
+++ b/his_checker.py
@@ -29,13 +29,35 @@ def process_calls(files, threshold):
     return 0
 
 def process_comf(files, threshold):
-    """
-    Process the comf metric
-    """
-
-    print(f"Processing COMF metric with threshold >{threshold} for files: {', '.join(files)}")
-
-    return 0
+    """Process comment density within a file"""
+
+    metric_fail = 0
+    statements_tool = "pmccabe -c "
+    pmccabe_stat_index = 2
+    total_statements = 0
+    comments_tool = "pygount --format=cloc-xml "
+    comment_index = 21
+    comment_density = 0
+    license_comment_size = 4
+    print("Checking the file comment density")
+    for file in files.files:
+        sline = os.popen(statements_tool + str(file)).read().split('\n')
+        for fields in [line.split('\t') for line in sline[:-1]]:
+            statements = int(fields[pmccabe_stat_index])
+            total_statements = total_statements + statements
+        lines = os.popen(comments_tool + str(file)).read().split(' ')
+        if lines[comment_index].startswith("comment"):
+            comments = int(lines[comment_index].split("=")[1].replace('"', ''))
+            comments = comments - license_comment_size
+            comment_density = comments/total_statements
+            if comment_density < COMMENTS_THRESHOLD:
+                print(f"The file {file}: has a comment density (comments/"
+                      f"statements) of {comment_density}. The minimum is a "
+                      f"density of {COMMENTS_THRESHOLD}")
+                metric_fail += 1
+        total_statements = 0
+    print("Check done with " + str(metric_fail) + " error(s)\n")
+    return metric_fail
 
 def process_goto(files, threshold):
     """