Revert data separation changes based on feedback - keep data in package

Co-authored-by: WeiTing1991 <[email protected]>

Author: Copilot

.gitignore

@@ -125,6 +125,3 @@ temp/**
 docs/api/generated/
 
 conda.recipe/
-
-# Data directory - excluded from package, available separately as data archive
-data/

DATA_ARCHIVE.md

@@ -89,10 +89,6 @@ allow-direct-references = true
 packages = [
   "src/dcs",
 ]
-exclude = [
-  "data/",
-  "data/**/*",
-]
 
 [tool.ruff]
 indent-width = 2

pyproject.toml

@@ -14,26 +14,22 @@ def __init__(self, filename: str, data: dict | None = None):
     """Initialize with filename and optional data.
 
     Args:
-        filename: Base filename for exported files.
-        data: Initial data dictionary. Defaults to None.
+        filename (str): Base filename for exported files.
+        data (dict, optional): Initial data dictionary. Defaults to None.
     """
     # Date
     now_data = datetime.now().date().strftime("%Y%m%d")
     here = os.path.dirname(__file__)
     home = os.path.abspath(os.path.join(here, "../../../"))
-    data_dir = os.path.abspath(os.path.join(home, "data"))
+    data = os.path.abspath(os.path.join(home, "data"))
 
     self.__date = now_data
     self.default_filename = self.__date + "_" + filename
 
-    self.__data = data_dir
+    self.__data = data
     json_dir = os.path.join(self.__data, "json")
     csv_dir = os.path.join(self.__data, "csv")
 
-    # Create directories if they don't exist
-    os.makedirs(json_dir, exist_ok=True)
-    os.makedirs(csv_dir, exist_ok=True)
-
     self.filepath_json = json_dir
     self.filepath_csv = csv_dir
 
@@ -42,16 +38,31 @@ def __init__(self, filename: str, data: dict | None = None):
 
   @property
   def data_dict(self) -> dict:
-    """Get the current data dictionary."""
+    """Get the current data dictionary.
+
+    Returns:
+        dict: The stored data dictionary.
+    """
     return self.data
 
   @data_dict.setter
   def update_data(self, new_data: dict) -> None:
-    """Update the data dictionary."""
+    """Update the data dictionary.
+
+    Args:
+        new_data (dict): New data dictionary to store.
+    """
     self.data = new_data
 
   def __is_file_existed(self, filepath: str) -> bool:
-    """Check if file already exists."""
+    """Check if file already exists.
+
+    Args:
+        filepath (str): Path to the file to check.
+
+    Returns:
+        bool: True if file exists, False otherwise.
+    """
     if os.path.isfile(filepath):
       return True
     else:
@@ -84,7 +95,7 @@ def write_dict_to_csv(self, header: list) -> None:
     """Export data dictionary to CSV file.
 
     Args:
-        header: List of column headers for the CSV file.
+        header (list): List of column headers for the CSV file.
 
     Raises:
         Exception: If the file already exists.

src/dcs/utils/data_processing.py

@@ -55,12 +55,8 @@ def docs_clean(ctx):
 
 
 @task
-def build(ctx, with_data: bool = False):
-  """Build the package for distribution.
-
-  Args:
-      with_data: If True, also creates the separate data archive
-  """
+def build(ctx):
+  """Build the package for distribution."""
   print("Building package...")
 
   # Clean first
@@ -70,48 +66,6 @@ def build(ctx, with_data: bool = False):
   ctx.run("python -m build --no-isolation", pty=True)
   print("Package built successfully!")
 
-  if with_data:
-    package_data(ctx)
-
-
-@task
-def package_data(ctx):
-  """Create a separate data archive for sample datasets and configurations.
-
-  Packages the data directory into a compressed archive that users can download
-  separately to reduce the main package size.
-  """
-  import tarfile
-  from pathlib import Path
-
-  print("Creating data archive...")
-
-  # Clean first
-  ctx.run("rm -f dist/dcs-sample-data-*.tar.gz", pty=True, warn=True)
-
-  # Create dist directory if it doesn't exist
-  Path("dist").mkdir(exist_ok=True)
-
-  # Get version for archive naming
-  version = "0.1.5"  # Could be extracted from pyproject.toml
-  archive_name = f"dist/dcs-sample-data-{version}.tar.gz"
-
-  # Create archive
-  with tarfile.open(archive_name, "w:gz") as tar:
-    tar.add("data", arcname="dcs-sample-data")
-
-  print(f"Data archive created: {archive_name}")
-
-  # Show archive contents summary
-  with tarfile.open(archive_name, "r:gz") as tar:
-    members = tar.getmembers()
-    print(f"Archive contains {len(members)} files and directories")
-    print("Archive contents preview:")
-    for member in members[:10]:  # Show first 10 entries
-      print(f"  {member.name}")
-    if len(members) > 10:
-      print(f"  ... and {len(members) - 10} more files")
-
 
 @task
 def build_clean(ctx):