more cleanup

Author: sdgilley

GitHub/merge-report.py

@@ -1,7 +1,7 @@
 """
 Run merge-report for ml, ai, or both.
 """
-import GitHub.utilities.merge_report as m
+from utilities import merge_report as m
 import argparse
 # Create the parser
 parser = argparse.ArgumentParser(description="Find number of days and which service.")

GitHub/pr-report.py

@@ -83,10 +83,15 @@
 renamed = len(renamed_files)
 
 print(f"PR {pr} changes {len(prfiles)} files.")
-print(f"ADDED: {len(added_files)}")  # just for info about the PR
-print(f"MODIFIED: {modified}")
-print(f"DELETED: {deleted}")
-print(f"RENAMED: {renamed}\n")
+if len(added_files) > 0:
+    print(f"ADDED {len(added_files)} files. (Added files won't cause a problem.)") 
+if modified > 0:
+    print(f"MODIFIED {modified} files.")
+if deleted > 0:
+    print(f"DELETED {deleted} files.")
+if renamed > 0:
+    print(f"RENAMED {renamed} files.\n")
+
 # print("\nChanges that may affect azure-ai-docs-pr:\n")
 data = []  # create an empty list to hold data for modified files that are referenced
 nb_mods = []  # create an empty list to hold data for modified notebooks
@@ -127,7 +132,7 @@
                 # print(f"*** {cell}")
     if data == []:
         print(
-            "No problems with any of the modified files.\n"
+            "✅ No problems with any of the modified files.\n"
         )
     else:
         # Group the data by 'Modified File' and 'Referenced In'
@@ -137,10 +142,8 @@
             if key not in grouped_data:
                 grouped_data[key] = []
             grouped_data[key].append(item["Cell"])
-        print(f"Potential problems found in {len(grouped_data)} files.")
-        print(
-            "Fix these references in azure-ai-docs-pr before approving this PR:\n"
-        )  # Print the grouped data
+        print(f"Potential problems found in {len(grouped_data)} files. \n")
+        # Print the grouped data
         for (modified_file, referenced_in), cells in grouped_data.items():
             print(f"Modified File: {modified_file} \n  Referenced in:")
             refs = referenced_in.split("\n")
@@ -155,14 +158,16 @@
 
             h.compare_branches(repo, file, "main", "temp-fix")
         # also print all the modified notebooks
+        print("⚠️ Fix all references to modified files before approving this PR.\n")
+
     if nb_mods:
         print(
             "MODIFIED NOTEBOOKS\nFollow each link to ensure notebooks are valid before approving the PR:"
         )
         nb_mods = list(set(nb_mods))  # remove duplicates
         for file in nb_mods:
             print(f"* {file}\n")
-    print("Fix all references to modified files before approving this PR.\n")
+        print("⚠️ Fix all references to modified files before approving this PR.\n")
 
 ### DELETED FILES
 if deleted > 0:
@@ -182,10 +187,10 @@
             found = +1
     if found == 0:
         print(
-            "No problems with any of the deleted files.\n"
+            "✅ No problems with any of the deleted files.\n"
         )
     else:
-        print("Fix all references to deleted files before approving this PR.\n")
+        print("⚠️ Fix all references to deleted files before approving this PR.\n")
 
 ### RENAMED FILES
 if renamed > 0:
@@ -205,10 +210,10 @@
             found = +1
     if found == 0:
         print(
-            "No problems with any of the renamed files.\n"
+            "✅ No problems with any of the renamed files.\n"
         )
     else:
-        print("Fix all references to renamed files before approving this PR.\n")
+        print("⚠️ Fix all references to renamed files before approving this PR.\n")
 
 print(f"\n================ {repo_name} PR summary: {pr} ===================")
 

GitHub/utilities/find_pr_files.py

@@ -3,7 +3,7 @@
 def find_pr_files(owner_name, repo_name, snippets, days):
     import requests
     import pandas as pd
-    import GitHub.utilities.gh_auth as a
+    from utilities import gh_auth as a
     from datetime import datetime, timedelta
 
     # Calculate the date to filter by
@@ -23,7 +23,7 @@ def find_pr_files(owner_name, repo_name, snippets, days):
     data = response.json()
 
     print(
-        f"\n================= {datetime.now().date()} MERGED IN LAST {days} DAYS in {repo_name} ================\n"
+        f"\n================= {repo_name}: {datetime.now().date()} MERGED IN LAST {days} DAYS  ================\n"
     )
     # Filter the PRs that were merged in the last 7 days
     merged_prs = [
@@ -60,7 +60,7 @@ def find_pr_files(owner_name, repo_name, snippets, days):
 
     df = pd.DataFrame(data)  # Convert the list to a DataFrame
     if df.empty:
-        print("\nNothing to do here :-)  There are no PRs that impacted references.\n")
+        print("\n ✅ Nothing to do here :-)  There are no PRs that impacted references.\n")
         return
     else:
         print(" These PRs impacted references:\n")
@@ -99,8 +99,8 @@ def find_pr_files(owner_name, repo_name, snippets, days):
         for ref in sorted(refs.unique()):
             i += 1
             print(f"{i}  {ref.strip()}")
-    print(
-        f"\n============================== /MERGED IN LAST {days} DAYS ==============================\n"
-    )
+    # print(
+    #     f"\n============================== /MERGED IN LAST {days} DAYS ==============================\n"
+    # )
     return
 

GitHub/utilities/merge_report.py

@@ -15,8 +15,8 @@
 
 def merge_report(days, service):
 
-    import GitHub.utilities.helpers as h
-    import GitHub.utilities.find_pr_files as f
+    from utilities import helpers as h
+    from utilities import find_pr_files as f
     import os
 
     if service == "ai":
@@ -32,13 +32,13 @@ def merge_report(days, service):
     # loop through all the repos that contain snippets for this service
     for owner_name, repo_name in zip(owner_name, repo_name):
         # get the refs-found file for this service
-        fn = os.path.join(os.path.dirname(mydir), f"refs-found-{repo_name}.csv")
-        print(f"Reading {fn} for {repo_name} snippets")
+        fn = os.path.join(os.path.dirname(os.path.dirname(mydir)), f"refs-found-{repo_name}.csv")
+        # print(f"Reading {fn} for {repo_name} snippets")
         # read the snippets for this repo
         snippets = h.read_snippets(fn)  # read the snippets file
         f.find_pr_files(owner_name, repo_name, snippets, days)
     return
 
 if __name__ == "__main__":
 
-    merge_report(9, "ml")
+    merge_report(9, "ai")