From 3ec6eba23a06ff4c8e8d1eb5d70b8a0c4faacb6a Mon Sep 17 00:00:00 2001
From: GitHub Actions <actions@github.com>
Date: Tue, 9 Dec 2025 14:20:37 +0000
Subject: [PATCH] feat(history-rewrite): enhance object checks in history
 rewrite scripts to focus on blob types and improve logging

---
 scripts/ci/dry_run_history_rewrite.sh         | 29 ++++++++++++++-----
 scripts/history-rewrite/clean_history.sh      | 12 +++++++-
 scripts/history-rewrite/preview_removals.sh   | 18 +++++++++---
 .../tests/clean_history.dryrun.bats           |  3 ++
 .../tests/validate_after_rewrite.bats         |  3 ++
 5 files changed, 53 insertions(+), 12 deletions(-)

diff --git a/scripts/ci/dry_run_history_rewrite.sh b/scripts/ci/dry_run_history_rewrite.sh
index 36af3d28..fba44696 100755
--- a/scripts/ci/dry_run_history_rewrite.sh
+++ b/scripts/ci/dry_run_history_rewrite.sh
@@ -55,15 +55,30 @@ for p in $paths_list; do
   fi
 done
 
-# 2) Check for objects in paths
-obj_count=$(git rev-list --objects --all -- $paths_list | wc -l | tr -d ' ')
-if [ "$obj_count" -gt 0 ]; then
-  echo "ERROR: Found $obj_count objects in specified paths"
-  git rev-list --objects --all -- $paths_list | nl -ba | sed -n '1,100p'
-  echo "DRY-RUN FAILED: repository objects found in banned paths"
+# 2) Check for blob objects in paths only (ignore tag/commit objects)
+tmp_objects=$(mktemp)
+trap 'rm -f "$tmp_objects"' EXIT INT TERM
+git rev-list --objects --all -- $paths_list > "$tmp_objects"
+blob_count=0
+blob_list=$(mktemp)
+trap 'rm -f "$tmp_objects" "$blob_list"' EXIT INT TERM
+while read -r line; do
+  oid=$(printf '%s' "$line" | awk '{print $1}')
+  # Determine object type and only consider blobs
+  type=$(git cat-file -t "$oid" 2>/dev/null || true)
+  if [ "$type" = "blob" ]; then
+    echo "$line" >> "$blob_list"
+    blob_count=$((blob_count + 1))
+  fi
+done < "$tmp_objects"
+
+if [ "$blob_count" -gt 0 ]; then
+  echo "ERROR: Found $blob_count blob object(s) in specified paths"
+  nl -ba "$blob_list" | sed -n '1,100p'
+  echo "DRY-RUN FAILED: repository blob objects found in banned paths"
   exit 1
 else
-  echo "OK: No repository objects in specified paths"
+  echo "OK: No repository blob objects in specified paths"
 fi
 
 # 3) Check for large objects across history
diff --git a/scripts/history-rewrite/clean_history.sh b/scripts/history-rewrite/clean_history.sh
index 3d9faba8..3f2754ba 100755
--- a/scripts/history-rewrite/clean_history.sh
+++ b/scripts/history-rewrite/clean_history.sh
@@ -125,7 +125,17 @@ preview_removals() {
   echo "=== Preview: objects in paths ===" | tee -a "$logfile"
   # List objects for the given paths
   for p in $paths_list; do
-    git rev-list --objects --all -- "$p" | tee -a "$logfile" | awk '{print $1, $2}' | head -n 50 | tee -a "$logfile"
+    echo "Path: $p" | tee -a "$logfile"
+    git rev-list --objects --all -- "$p" | while read -r line; do
+      oid=$(printf '%s' "$line" | awk '{print $1}')
+      label=$(printf '%s' "$line" | awk '{print $2}')
+      type=$(git cat-file -t "$oid" 2>/dev/null || true)
+      if [ "$type" = "blob" ]; then
+        echo "$oid $label" | tee -a "$logfile"
+      else
+        echo "[${type^^}] $oid $label" | tee -a "$logfile"
+      fi
+    done | head -n 50 | tee -a "$logfile"
   done
 
   echo "=== Example large objects (candidate for --strip-size) ===" | tee -a "$logfile"
diff --git a/scripts/history-rewrite/preview_removals.sh b/scripts/history-rewrite/preview_removals.sh
index c5ab1766..72622320 100755
--- a/scripts/history-rewrite/preview_removals.sh
+++ b/scripts/history-rewrite/preview_removals.sh
@@ -84,10 +84,20 @@ if [ "$FORMAT" = "json" ]; then
   done
   printf '],'
 else
-  echo "--- Objects in paths ---"
-  for p in $paths_list; do
-    git rev-list --objects --all -- "$p" | nl -ba | sed -n '1,100p'
-  done
+  echo "--- Objects in paths (blob objects shown; tags highlighted) ---"
+    for p in $paths_list; do
+      echo "Path: $p"
+      git rev-list --objects --all -- "$p" | while read -r line; do
+        oid=$(printf '%s' "$line" | awk '{print $1}')
+        label=$(printf '%s' "$line" | awk '{print $2}')
+        type=$(git cat-file -t "$oid" 2>/dev/null || true)
+        if [ "$type" = "blob" ]; then
+          echo "$oid  $label"
+        else
+          echo "[${type^^}] $oid  $label"
+        fi
+      done | nl -ba | sed -n '1,100p'
+    done
 fi
 
 echo "--- Example large objects larger than ${STRIP_SIZE}M ---"
diff --git a/scripts/history-rewrite/tests/clean_history.dryrun.bats b/scripts/history-rewrite/tests/clean_history.dryrun.bats
index 37e31c4f..27305bbf 100644
--- a/scripts/history-rewrite/tests/clean_history.dryrun.bats
+++ b/scripts/history-rewrite/tests/clean_history.dryrun.bats
@@ -4,6 +4,9 @@ setup() {
   TMPREPO=$(mktemp -d)
   cd "$TMPREPO"
   git init -q
+  # Set local git identity for test commits
+  git config user.email "test@example.com"
+  git config user.name "Test Runner"
   # create a directory that matches the paths to be pruned
   mkdir -p backend/codeql-db
   # add a large fake blob file
diff --git a/scripts/history-rewrite/tests/validate_after_rewrite.bats b/scripts/history-rewrite/tests/validate_after_rewrite.bats
index bf55224e..4993ec4f 100644
--- a/scripts/history-rewrite/tests/validate_after_rewrite.bats
+++ b/scripts/history-rewrite/tests/validate_after_rewrite.bats
@@ -5,6 +5,9 @@ setup() {
   TMPREPO=$(mktemp -d)
   cd "$TMPREPO"
   git init -q
+  # Set local git identity for test commits
+  git config user.email "test@example.com"
+  git config user.name "Test Runner"
   echo 'initial' > README.md
   git add README.md && git commit -m 'init' -q
   # Make a minimal .venv pre-commit stub