From fbbe7ee338439f91141bb32b4d7ee0ceb7ef8905 Mon Sep 17 00:00:00 2001
From: hkir-dev <huseyin_kir@yahoo.com>
Date: Mon, 8 Jul 2024 16:00:53 +0100
Subject: [PATCH] save CAS zip support

---
 setup.py               |  2 +-
 src/tdta/tdt_export.py | 40 ++++++++++++++++++++++++++++++++++++++++
 2 files changed, 41 insertions(+), 1 deletion(-)

diff --git a/setup.py b/setup.py
index 97536a9..38415b0 100644
--- a/setup.py
+++ b/setup.py
@@ -8,7 +8,7 @@
 
 setup(
     name="tdta",
-    version="0.1.0.dev15",
+    version="0.1.0.dev16",
     description="The aim of this project is to provide taxonomy development tools custom actions.",
     long_description=README,
     long_description_content_type="text/markdown",
diff --git a/src/tdta/tdt_export.py b/src/tdta/tdt_export.py
index abf8727..9785de6 100644
--- a/src/tdta/tdt_export.py
+++ b/src/tdta/tdt_export.py
@@ -3,12 +3,15 @@
 import ast
 import json
 import typing
+import zipfile
+import shutil
 from typing import Union, List
 from contextlib import closing
 from pathlib import Path
 from datetime import datetime
 
 from tdta.utils import read_project_config
+from tdta.command_line_utils import runcmd
 from cas.model import (CellTypeAnnotation, Annotation, Labelset, AnnotationTransfer, AutomatedAnnotation, Review)
 from cas.file_utils import write_json_file
 from cas.matrix_file.resolver import resolve_matrix_file
@@ -18,6 +21,9 @@
 
 cas_table_names = ["annotation", "labelset", "metadata", "annotation_transfer", "review"]
 
+GITHUB_SIZE_LIMIT = 50 * 1000 * 1000  # 50 MB
+# GITHUB_SIZE_LIMIT = 2 * 1000
+
 
 def export_cas_data(sqlite_db: str, output_file: str, dataset_cache_folder: str = None):
     """
@@ -62,9 +68,43 @@ def export_cas_data(sqlite_db: str, output_file: str, dataset_cache_folder: str
         write_json_file(cta, output_file, False)
 
     print("CAS json successfully created at: {}".format(output_file))
+    ensure_file_size_limit(output_file)
     return cta
 
 
+def ensure_file_size_limit(file_path):
+    """
+    Checks if the file size exceeds the GitHub size limit and zips the file if needed.
+    Parameters:
+        file_path: file path to check
+    """
+    if os.path.getsize(file_path) > GITHUB_SIZE_LIMIT:
+        zip_path = zip_file(file_path)
+        folder = os.path.dirname(file_path)
+        is_git_repo = runcmd("cd {dir} && git rev-parse --is-inside-work-tree".format(dir=folder)).strip()
+        if is_git_repo == "true":
+            runcmd("cd {dir} && git reset {file_path}".format(dir=folder, file_path=file_path))
+            runcmd("cd {dir} && git add {zip_path}".format(dir=folder, zip_path=zip_path))
+
+
+def zip_file(file_path):
+    """
+    Zips the file into smaller parts if it exceeds the GitHub size limit.
+    Parameters:
+        file_path: file path to zip
+    Returns: zipped file path
+    """
+    folder = os.path.dirname(file_path)
+    base_name = os.path.basename(file_path)
+    zip_base = os.path.splitext(base_name)[0]
+
+    single_zip_path = os.path.join(folder, f"{zip_base}.zip")
+    with zipfile.ZipFile(single_zip_path, 'w', zipfile.ZIP_DEFLATED) as zipf:
+        zipf.write(file_path, base_name)
+    print("File zipped due to GitHub size limits: " + single_zip_path)
+    return single_zip_path
+
+
 def parse_metadata_data(cta, sqlite_db, table_name):
     """
     Reads 'Metadata' table data into the CAS object