From 8c22c87afd64b61c13e8f3327a46cf9c4746fe5a Mon Sep 17 00:00:00 2001
From: Matthew Gaughan <gaughan@u.northwestern.edu>
Date: Sun, 12 May 2024 19:15:53 -0500
Subject: [PATCH] not sure why, paritioning fixed

---
 text_analysis/partitioning_files.py | 30 ++++++++++++++++++++++-------
 1 file changed, 23 insertions(+), 7 deletions(-)

diff --git a/text_analysis/partitioning_files.py b/text_analysis/partitioning_files.py
index 7303d6f..85f98f1 100644
--- a/text_analysis/partitioning_files.py
+++ b/text_analysis/partitioning_files.py
@@ -6,31 +6,38 @@ from tqdm import tqdm
 from pathlib import Path
 
 
-working_dir = "/data/users/mgaughan/kkex/time_specific_files/readme2/1/"
-dest_dir = "/data/users/mgaughan/kkex/time_specific_files/readme3/test/"
+working_dir = "/data/users/mgaughan/kkex/time_specific_files/readme2/"
+dest_dir = "/data/users/mgaughan/kkex/time_specific_files/partitioned_readme/p"
 
 def move_file(vcs_link, group):
     if "github" in vcs_link or "gitlab" in vcs_link:
         #making an evaluation that sub branches aren't being used and that people would fork if needed
         #this only looks at main
         vcs_link = "/".join(vcs_link.split("/")[0:5])
-        full_temp_path = vcs_link.split('/')[4] + ".git"
+        full_temp_path = vcs_link.split('/')[4] 
         #other_temp_path = vcs_link.split('/')[4] + ".git0"
     else:
-        full_temp_path = vcs_link.split('/')[- 1] + ".git"
+        full_temp_path = vcs_link.split('/')[- 1] 
         #other_temp_path = vcs_link.split('/')[- 1] + ".git0"
     rel_filename = ""
     for filename in os.listdir(working_dir):
         spec, rel_filename = hard_codes(vcs_link, filename)
         project = "_".join(filename.split("_")[:-1])
         #print(project)
-        if full_temp_path[:-4] == project:
+        if full_temp_path == project:
+            #print(full_temp_path, project)
             rel_filename = filename
         if rel_filename != "":
             target_path = working_dir + rel_filename
             #print(target_path)
             destination_path = dest_dir + str(group) + "/"
+            #print(target_path, full_temp_path[:-4], filename, destination_path)
             shutil.move(target_path, destination_path)
+            return filename
+        else:
+            print("error!")
+            print(full_temp_path)
+        
 
 def hard_codes(vcs_link, filename):
     if vcs_link == "https://github.com/df7cb/pg_filedump.git" and filename == "pg_filedump.git_README.pg_filedump":
@@ -69,11 +76,20 @@ def for_all_files(csv_path):
     with open(csv_path, 'r') as file:
         lines = [line for line in file]
         index = -1
+        already_seen = []
         for row in tqdm(csv.reader(lines), total=len(lines)):
             index += 1
             if index == 0:
                 continue
-            move_file(row[0], index % 2 + 1)
+            #print(row[3], row[-2])
+            filename = move_file(row[3], row[-2])
+            if filename not in already_seen:
+                already_seen.append(filename)
+            else: 
+                print(filename) 
+                break
+        print(len(already_seen))
 
 if __name__ == "__main__":
-    for_all_files("final_data/deb_readme_did.csv")
\ No newline at end of file
+    for_all_files("R/051224_readme_grouped.csv")
+    #for_all_files("R/051224_contrib_grouped.csv")
\ No newline at end of file