Add more data display

README.md

@@ -98,6 +98,7 @@ The project uses Docker Compose to orchestrate three main services:
    - **Setup**: Clone your target repository here (e.g., `git clone https://github.com/bitcoin/bitcoin.git user_supplied_repo`)
    - **Docker Mount**: Mounted to backend container at `/app/bitcoin`
    - **Used By**: `backend/app/git_processor.py` reads from `config.CONTAINER_SIDE_REPOSITORY_PATH`
+   - **Git safety**: The backend Docker image now marks `/app/bitcoin` as a safe Git directory automatically, so you only need to run `git config --global --add safe.directory <host-path>` when working with the repo outside of Docker.
 
 2. **`data/neo4j/`** (Auto-created, but required for persistence)
    - **Purpose**: Stores Neo4j graph database files
@@ -453,6 +454,9 @@ You can monitor the import progress by:
    - Run queries to check node counts:
    ```cypher
    MATCH (a:Actor) RETURN count(a) as actors
+   ```
+
+   ```
    MATCH (c:Commit) RETURN count(c) as commits
    ```
 

backend/Dockerfile

@@ -33,6 +33,7 @@ RUN pip install --no-cache-dir \
     GitPython \
     git-fame
 
+RUN git config --global --add safe.directory /app/bitcoin
 
 # Copy app source
 COPY app .

backend/app/neo4j_driver.py

@@ -279,6 +279,10 @@ def merge_import_status(self):
 
     @staticmethod
     def _merge_import_status_node(tx):
+
+        # debugging the merge function in cypher
+        # query = "MATCH (a:ImportStatus) RETURN a"
+
         query = """
         MERGE (a:ImportStatus)
         ON CREATE SET a.git_import_complete = false, a.next_complete = false
@@ -342,3 +346,24 @@ def _create_and_return_import_status_node(tx):
             "git_import_complete": record["a.git_import_complete"],
             "next_complete": record["a.next_complete"]
         }
+
+    def get_node_count(self, label: str) -> int:
+        """Get the count of nodes with a specific label."""
+        # Validate label to prevent injection (alphanumeric and underscores only)
+        if not label.replace("_", "").isalnum():
+            raise ValueError(f"Invalid label: {label}. Labels must contain only alphanumeric characters and underscores.")
+        with self.driver.session() as session:
+            query = f"MATCH (n:{label}) RETURN count(n) AS count"
+            result = session.run(query)  # type: ignore[arg-type]
+            record = result.single()
+            return record["count"] if record else 0
+
+    def get_import_status(self):
+        """Get the ImportStatus node details."""
+        with self.driver.session() as session:
+            query = "MATCH (i:ImportStatus) RETURN i"
+            result = session.run(query)
+            record = result.single()
+            if record:
+                return dict(record["i"])
+            return None

backend/app/schema.py

@@ -198,6 +198,42 @@ def resolve_fame(self, info, folder):
             contributors=contributors
         )
 
+    # Count queries for displaying node counts
+    actor_count = graphene.Int(description="Return the total count of Actor nodes")
+
+    def resolve_actor_count(self, info):
+        db = Neo4jDriver()
+        count = db.get_node_count("Actor")
+        db.close()
+        return count
+
+    commit_count = graphene.Int(description="Return the total count of Commit nodes")
+
+    def resolve_commit_count(self, info):
+        db = Neo4jDriver()
+        count = db.get_node_count("Commit")
+        db.close()
+        return count
+
+    file_detail_record_count = graphene.Int(description="Return the total count of FileDetailRecord nodes")
+
+    def resolve_file_detail_record_count(self, info):
+        db = Neo4jDriver()
+        count = db.get_node_count("FileDetailRecord")
+        db.close()
+        return count
+
+    import_status = graphene.Field(
+        graphene.JSONString,
+        description="Return the ImportStatus node details"
+    )
+
+    def resolve_import_status(self, info):
+        db = Neo4jDriver()
+        status = db.get_import_status()
+        db.close()
+        return status
+
 
 class CreateGithubOrganization(graphene.Mutation):
     class Arguments:

backend/tests/test_git_to_neo4j_import.py

@@ -111,3 +111,32 @@ def test_folder_processing_with_preseeded_status(sample_git_repo, neo4j_driver):
         "src/consensus"
     ]
 
+
+def test_count_methods(sample_git_repo, neo4j_driver):
+    """Test the new count methods for GraphQL queries."""
+    # First complete the git import
+    process_git_data(
+        repo_path=sample_git_repo.path,
+        neo4j_driver=neo4j_driver,
+        folder_paths=[],  # No folder paths for initial import
+    )
+
+    # Now process folder data which creates FileDetailRecord nodes
+    from git_processor import import_bitcoin_path
+    import_bitcoin_path("src/consensus", repo_path=sample_git_repo.path, neo4j_driver=neo4j_driver)
+
+    # Test node counts
+    actor_count = neo4j_driver.get_node_count("Actor")
+    commit_count = neo4j_driver.get_node_count("Commit")
+    file_detail_count = neo4j_driver.get_node_count("FileDetailRecord")
+
+    assert actor_count >= 3
+    assert commit_count == len(sample_git_repo.commits)
+    assert file_detail_count == 1  # We imported one folder
+
+    # Test import status
+    status = neo4j_driver.get_import_status()
+    assert status is not None
+    assert "git_import_complete" in status
+    assert status["git_import_complete"] is True
+