updates to gerrit collection, at least intermediate thing for gerrit results

072525_gerrit_collection/gerrit_patch_collection.py

@@ -6,6 +6,7 @@ import requests
 import re
 import datetime
 import time
+from tqdm import tqdm
 #from urllib.parse import quote_plus
 
 #from requests.auth import HTTPDigestAuth
@@ -21,14 +22,20 @@ def query_change_detail(
         ):
     time.sleep(sleep)
     short_change_id = written_url.split("/")[-1]
+    
+    username = os.environ.get("GERRIT_USERNAME")
+    http_password = os.environ.get("GERRIT_HTTP_PASSWORD")
 
     api_url = f"https://gerrit.wikimedia.org/r/changes/{short_change_id}/detail"
 
-    response = requests.get(api_url, headers={'Content-Type': 'application/json'})
+    response = requests.get(api_url, auth=(username, http_password), headers={'Content-Type': 'application/json'})
     
     result = json.loads(response.text[5:])
     
     select_change_dict = {}
+    #making note of what the url was in the message
+    select_change_dict['written_url_in_message'] = written_url
+    result['written_url_in_message'] = written_url
     #getting ID
     select_change_dict['id'] = result['change_id']
     select_change_dict['project'] = result['project']
@@ -49,7 +56,89 @@ def query_change_detail(
     select_change_dict['reviewers'] = result['reviewers']['REVIEWER']
     print(result)
     print(select_change_dict)
+    return [select_change_dict, result]
 
 
+def query_gerrit_changes(df, sleep=20):
+    tqdm.pandas()
+    #get the information from the Gerrit change from the URL that's written in the message
+    def get_change_details(written_url):
+        time.sleep(sleep)
+        short_change_id = written_url.split("/")[-1]
+        api_url = f"https://gerrit.wikimedia.org/r/changes/{short_change_id}/detail"
+    
+        username = os.environ.get("GERRIT_USERNAME")
+        http_password = os.environ.get("GERRIT_HTTP_PASSWORD")
+
+        response = requests.get(api_url, auth=(username, http_password), headers={'Content-Type': 'application/json'})
+        if response.status_code == 200:
+            try:
+                result = json.loads(response.text[5:])
+                return {"written_url_in_message": written_url, "full_result": result}
+            except Exception as e:
+                print("JSON decode error:", e)
+                print("Text was:", repr(response.text))
+                return {"written_url_in_message": written_url, "full_result": None}
+        else:
+            print("Bad response:", response.status_code, response.text)
+            return {"written_url_in_message": written_url, "full_result": None}
+
+    def parse_selected_metadata(written_url, full_result):
+        try:
+            select_change_dict = {}
+            select_change_dict['written_url_in_message'] = written_url
+            #getting ID
+            select_change_dict['id'] = full_result['change_id']
+            select_change_dict['project'] = full_result['project']
+            select_change_dict['description'] = full_result['subject']
+            #getting owner name and email 
+            select_change_dict['owner_dict'] = full_result['owner']
+            select_change_dict['owner_email'] = full_result['owner']['email']
+            #current revision count 
+            select_change_dict['revision_count'] = full_result['current_revision_number']
+            #insertions 
+            select_change_dict['code_insertions'] = full_result['insertions']
+            #deletions
+            select_change_dict['code_deletions'] = full_result['deletions']
+            #status 
+            select_change_dict['status'] = full_result['status']
+            #reviewers
+            reviewers = full_result.get('reviewers', {}).get('REVIEWER', [])
+            if reviewers:
+                select_change_dict['reviewer_count'] = len(reviewers)
+                select_change_dict['reviewers'] = reviewers
+            else: 
+                select_change_dict['reviewer_count'] = "NA"
+                select_change_dict['reviewers']  = "NA"
+            #print(select_change_dict)
+            return select_change_dict
+        except Exception as e:
+            print(f'Error in this URL: {written_url}')
+            print(f'KeyError in this dictionary: {full_result}')
+            return {}
+
+    df['gerrit_full_results'] = df["gerrit_urls"].progress_apply(
+        lambda urls: [get_change_details(url) for url in urls] if urls else []
+    )
+    
+    df['selected_gerrit_results'] = df['gerrit_full_results'].progress_apply(
+        lambda results: [parse_selected_metadata(item['written_url_in_message'], item['full_result'])
+                        for item in results 
+                        if item.get('full_result') and item.get('written_url_in_message')]
+    )
+
+    return df 
+
+def add_gerrit_urls_column(df, text_column="comment_text", new_column="gerrit_urls"):
+    pattern = r"(https://gerrit\.wikimedia\.org[^\s]*)"
+    df[new_column] = df[text_column].astype(str).apply(lambda msg: re.findall(pattern, msg))
+    return df
+
 if __name__ == "__main__":
-    query_change_detail("https://gerrit.wikimedia.org/r/85783", 1)
+    df = pd.read_csv("/home/SOC.NORTHWESTERN.EDU/nws8519/git/mw-convo-collections/072525_gerrit_collection/071425_master_discussion_data.csv") 
+    #df = df.head(30)
+    df = add_gerrit_urls_column(df)
+    df = query_gerrit_changes(df)
+    df.to_csv("/home/SOC.NORTHWESTERN.EDU/nws8519/git/mw-convo-collections/072525_gerrit_collection/080425_gerrit_filled_df.csv", index=False)
+
+    #query_change_tail("https://gerrit.wikimedia.org/r/85783")