From d113e0991a3ebca2f010344f8fb92fd4d3f1805b Mon Sep 17 00:00:00 2001
From: Matthew Gaughan <gaughan@u.northwestern.edu>
Date: Sun, 31 Mar 2024 16:50:23 -0500
Subject: [PATCH] updating specific file etc.

---
 get_spec_file.py | 36 +++++-------------------------------
 1 file changed, 5 insertions(+), 31 deletions(-)

diff --git a/get_spec_file.py b/get_spec_file.py
index 6a889bc..f450538 100644
--- a/get_spec_file.py
+++ b/get_spec_file.py
@@ -66,33 +66,7 @@ def get_file(vcs_link, commit_hash, is_readme):
         shutil.rmtree(full_temp_path, ignore_errors=True)
         shutil.rmtree(other_temp_path, ignore_errors=True)
         return "NoFile"
-    #target_filename = r"/README/"
-    #issue with searching through the tree this way
-    # need to match the tree w blobs 
-    #print(commit0.tree.blobs)
-    #file_id = commit0.tree[r'README.*'].hexsha
-    #targetfile = repo0.blob(file_id)
-    #targetfile = commit0.tree / target_filename
-    '''
-    try:
-        targetfile = commit0.tree / target_filename
-    except KeyError:
-        target_filename = "README.rst"
-        try:
-            targetfile = commit0.tree / target_filename
-        except KeyError:
-            target_filename = "README"
-            try:
-                targetfile = commit0.tree / target_filename
-            except KeyError:
-                target_filename = "README.txt"
-                try:
-                    targetfile = commit0.tree / target_filename
-                except KeyError:
-                    shutil.rmtree(full_temp_path, ignore_errors=True)
-                    shutil.rmtree(other_temp_path, ignore_errors=True)
-                    return "KeyError -- the file is not in the commit tree"
-        '''
+
     targetfile = ""
     for blob in commit0.tree.blobs:
         #print(type(blob.path))
@@ -140,9 +114,9 @@ def for_all_files():
                 return_value = get_file(row[0], row[2], readme_is)
                 if return_value != "NoError":
                     csv_writer.writerow([row[0], row[2], readme_is, return_value])
-                #get_file('https://github.com/tqdm/tqdm', 'fbe7952cce11e8073378b063bdae7ab277a96eb8', True)
+                # if it is noError, just write the row down in a different csv
+                # there's an issue of duplicates, but just keep it moving 
+                # if no duplicates -- just run it through
 
 if __name__ == "__main__":
-    for_all_files()
-    #print(get_file('https://github.com/the-tcpdump-group/tcpslice', 'ffac277bf41946a1d985afae7fe2535d7a28546f', True))
-    #get_file('https://github.com/krahets/hello-algo/tree/dev1', 'f615ad42ef3c58cfc6f080b8fb0cd0eb741706a9', True )
\ No newline at end of file
+    for_all_files()
\ No newline at end of file