Add git repository node and connect it to the corresponding git log nodes

Author: JohT

COMMANDS.md

@@ -235,7 +235,10 @@ It uses `git log` to extract commits, their authors and the names of the files c
 
 ```Cypher
 (Git:Log:Author)-[:AUTHORED]->(Git:Log:Commit)->[:CONTAINS_CHANGED]->(Git:Log:File)
-(Git:Log:Commit)->[:HAS_PARENT]-(Git:Log:Commit)
+(Git:Log:Commit)-[:HAS_PARENT]->(Git:Log:Commit)
+(Git:Repository)-[:HAS_COMMIT]->(Git:Log:Commit)
+(Git:Repository)-[:HAS_AUTHOR]->(Git:Log:Author)
+(Git:Repository)-[:HAS_FILE]->(Git:Log:File)
 ```
 
 👉**Note:** Commit messages containing `[bot]` are filtered out to ignore changes made by bots.
@@ -252,6 +255,9 @@ Here is the resulting schema:
 
 ```Cypher
 (Git:Log:Author)-[:AUTHORED]->(Git:Log:ChangeSpan)-[:CONTAINS_CHANGED]->(Git:Log:File)
+(Git:Repository)-[:HAS_CHANGE_SPAN]->(Git:Log:ChangeSpan)
+(Git:Repository)-[:HAS_AUTHOR]->(Git:Log:Author)
+(Git:Repository)-[:HAS_FILE]->(Git:Log:File)
 ```
 
 #### Parameter

cypher/GitLog/Create_git_repository_node.cypher

@@ -0,0 +1,10 @@
+// Create git repository information node
+
+MERGE (git_repository:Git:Repository {
+    name:             $git_repository_origin, 
+    tags:             split($git_repository_current_tags, ','),
+    branch:           coalesce($git_repository_current_branch, ''),
+    commit:           coalesce($git_repository_current_commit, ''),
+    fileName:         $git_repository_directory_name,
+    absoluteFileName: $git_repository_absolute_directory_name
+})

cypher/GitLog/Import_aggregated_git_log_csv_data.cypher

@@ -1,7 +1,8 @@
-// Import aggregated git log CSV data with the following schema: (Git:Log:Author)-[:AUTHORED]->(Git:Log:ChangeSpan)-[:CONTAINS]->(Git:Log:File)
+// Import aggregated git log CSV data with the following schema: (Git:Log:Author)-[:AUTHORED]->(Git:Log:ChangeSpan)-[:CONTAINS]->(Git:Log:File) , (Git:Repository)-[:HAS_CHANGE_SPAN]->(Git:Log:ChangeSpan) , (Git:Repository)-[:HAS_AUTHER]->(Git:Log:Auther) , (Git:Repository)-[:HAS_FILE]->(Git:Log:File). Variables: git_repository_absolute_directory_name
 
 LOAD CSV WITH HEADERS FROM "file:///aggregatedGitLog.csv" AS row
 CALL { WITH row
+    MATCH (git_repository:Git:Repository{absoluteFileName: $git_repository_absolute_directory_name})
     MERGE (git_author:Git:Log:Author {name: row.author, email: row.email})
     MERGE (git_change_span:Git:Log:ChangeSpan {
         year:    toInteger(row.year),
@@ -11,6 +12,9 @@ CALL { WITH row
     MERGE (git_file:Git:Log:File {fileName: row.filename})
     MERGE (git_author)-[:AUTHORED]->(git_change_span)
     MERGE (git_change_span)-[:CONTAINS_CHANGED]->(git_file)
+    MERGE (git_repository)-[:HAS_CHANGE_SPAN]->(git_change_span)
+    MERGE (git_repository)-[:HAS_AUTHOR]->(git_file)
+    MERGE (git_repository)-[:HAS_FILE]->(git_author)
 } IN TRANSACTIONS OF 1000 ROWS
 RETURN count(DISTINCT row.author)   AS numberOfAuthors
       ,count(DISTINCT row.filename) AS numberOfFiles

cypher/GitLog/Import_git_log_csv_data.cypher

@@ -1,7 +1,8 @@
-// Import git log CSV data with the following schema: (Git:Log:Author)-[:AUTHORED]->(Git:Log:Commit)-[:CONTAINS]->(Git:Log:File)
+// Import git log CSV data with the following schema: (Git:Log:Author)-[:AUTHORED]->(Git:Log:Commit)-[:CONTAINS]->(Git:Log:File) , (Git:Repository)-[:HAS_HAS_COMMIT]->(Git:Log:Commit) , (Git:Repository)-[:HAS_HAS_AUTHOR]->(Git:Log:Author) , (Git:Repository)-[:HAS_HAS_FILE]->(Git:Log:File). Variables: git_repository_absolute_directory_name
 
 LOAD CSV WITH HEADERS FROM "file:///gitLog.csv" AS row
 CALL { WITH row
+    MATCH (git_repository:Git:Repository{absoluteFileName: $git_repository_absolute_directory_name})
     MERGE (git_author:Git:Log:Author {name: row.author, email: row.email})
     MERGE (git_commit:Git:Log:Commit {
         hash:           row.hash, 
@@ -13,6 +14,9 @@ CALL { WITH row
     MERGE (git_file:Git:Log:File {fileName: row.filename})
     MERGE (git_author)-[:AUTHORED]->(git_commit)
     MERGE (git_commit)-[:CONTAINS_CHANGED]->(git_file)
+    MERGE (git_repository)-[:HAS_COMMIT]->(git_commit)
+    MERGE (git_repository)-[:HAS_AUTHOR]->(git_author)
+    MERGE (git_repository)-[:HAS_FILE]->(git_file)
 } IN TRANSACTIONS OF 1000 ROWS
 RETURN count(DISTINCT row.author)   AS numberOfAuthors
       ,count(DISTINCT row.filename) AS numberOfFiles

scripts/importGit.sh

@@ -65,6 +65,37 @@ deleteExistingGitData() {
   execute_cypher "${GIT_LOG_CYPHER_DIR}/Delete_git_log_data.cypher"
 }
 
+# Creates one (Git:Repository) node with information about the repository.  
+# The first and only parameter is the absolute/full repository directory path.
+create_git_repository_node() {
+    local full_local_repository_path=${1}
+    echo "importGit:   - full_local_repository_path=${full_local_repository_path}"
+
+    local_repository=$(basename "${full_local_repository_path}")
+    echo "importGit:   - local_repository=    ${local_repository}"
+
+    remote_origin=$(cd "${full_local_repository_path}" ;git config --get remote.origin.url || true)
+    remote_origin=$(basename -s .git "${remote_origin}" || true)
+    echo "importGit:   - remote_origin=       ${remote_origin}"
+
+    current_tags=$(cd "${full_local_repository_path}" ;git tag --points-at HEAD | paste -sd "," - || true)
+    echo "importGit:   - current_tags=        ${current_tags}"
+    
+    current_branch=$(cd "${full_local_repository_path}" ;git rev-parse --abbrev-ref HEAD 2>/dev/null || true)
+    echo "importGit:   - current_branch=      ${current_branch}"
+
+    current_commit=$(cd "${full_local_repository_path}" ;git rev-parse HEAD || true)
+    echo "importGit:   - current_commit=      ${current_commit}"
+
+    execute_cypher "${GIT_LOG_CYPHER_DIR}/Create_git_repository_node.cypher" \
+      "git_repository_origin=${remote_origin}" \
+      "git_repository_current_tags=${current_tags}" \
+      "git_repository_current_branch=${current_branch}" \
+      "git_repository_current_commit=${current_commit}" \
+      "git_repository_directory_name=${local_repository}" \
+      "git_repository_absolute_directory_name=${full_local_repository_path}"
+}
+
 importGitLog() {
   echo "importGit: Preparing import by creating indexes for the full git log..."
   execute_cypher "${GIT_LOG_CYPHER_DIR}/Index_author_name.cypher"
@@ -73,7 +104,7 @@ importGitLog() {
   execute_cypher "${GIT_LOG_CYPHER_DIR}/Index_file_name.cypher"
 
   echo "importGit: Importing full git log data into the Graph..."
-  time execute_cypher "${GIT_LOG_CYPHER_DIR}/Import_git_log_csv_data.cypher"
+  time execute_cypher "${GIT_LOG_CYPHER_DIR}/Import_git_log_csv_data.cypher" "${@}"
 
   echo "importGit: Creating relationships for parent commits..."
   execute_cypher "${GIT_LOG_CYPHER_DIR}/Add_HAS_PARENT_relationships_to_commits.cypher"
@@ -86,7 +117,7 @@ importAggregatedGitLog() {
   execute_cypher "${GIT_LOG_CYPHER_DIR}/Index_file_name.cypher"
 
   echo "importGit: Importing aggregated git log data into the Graph..."
-  time execute_cypher "${GIT_LOG_CYPHER_DIR}/Import_aggregated_git_log_csv_data.cypher"
+  time execute_cypher "${GIT_LOG_CYPHER_DIR}/Import_aggregated_git_log_csv_data.cypher" "${@}"
 }
 
 commonPostGitLogImport() {
@@ -125,16 +156,20 @@ if [[ ! ${IMPORT_GIT_LOG_DATA_IF_SOURCE_IS_PRESENT} == "none" ]]; then
     fi
 
     echo "importGit: Importing git repository ${repository}"
+    full_repository_path=$(cd "${repository}"; pwd)
+    
+    create_git_repository_node "${full_repository_path}"
+
     if [[ ${IMPORT_GIT_LOG_DATA_IF_SOURCE_IS_PRESENT} == "aggregated" ]]; then
     # Import pre-aggregated git log data (no single commits) when IMPORT_GIT_LOG_DATA_IF_SOURCE_IS_PRESENT = "aggregated"
         (cd "${repository}" && source "${SCRIPTS_DIR}/createAggregatedGitLogCsv.sh" "${NEO4J_FULL_IMPORT_DIRECTORY}/aggregatedGitLog.csv")
-        importAggregatedGitLog
-        postAggregatedGitLogImport
+        importAggregatedGitLog "git_repository_absolute_directory_name=${full_repository_path}"
+        postAggregatedGitLogImport 
     else
     # Import git log data with every commit when IMPORT_GIT_LOG_DATA_IF_SOURCE_IS_PRESENT = "full" (default)
         (cd "${repository}" && source "${SCRIPTS_DIR}/createGitLogCsv.sh" "${NEO4J_FULL_IMPORT_DIRECTORY}/gitLog.csv")
-        importGitLog
-        postGitLogImport
+        importGitLog "git_repository_absolute_directory_name=${full_repository_path}"
+        postGitLogImport 
     fi
   done
 fi