datamule 0.380__py3-none-any.whl → 1.0.0__py3-none-any.whl

datamule/__init__.py

@@ -1,87 +1,47 @@
-# datamule/__init__.py
-import sys
-from importlib.util import find_spec
-from functools import lru_cache
-
-# Lazy load nest_asyncio only when needed
-def _setup_jupyter():
-    """Setup Jupyter-specific configurations if needed."""
-    if _is_jupyter():
-        import nest_asyncio
-        nest_asyncio.apply()
-
-def _is_jupyter():
-    """Check if the code is running in a Jupyter environment."""
-    try:
-        shell = get_ipython().__class__.__name__
-        return shell == 'ZMQInteractiveShell'
-    except NameError:
-        return False
-
-# Lazy loading for main components
-@lru_cache(None)
-def get_downloader():
-    from .downloader.sec_downloader import Downloader
-    return Downloader
-
-@lru_cache(None)
-def get_parser():
-    from .parser.sec_parser import Parser
-    return Parser
-
-@lru_cache(None)
-def get_filing():
-    from .sec_filing import Filing
-    return Filing
-
-@lru_cache(None)
-def get_dataset_builder():
-    if find_spec('pandas') is not None:
-        try:
-            from .dataset_builder.dataset_builder import DatasetBuilder
-            return DatasetBuilder
-        except ImportError:
-            return None
-    return None
-
-# Helper functions that can be imported directly
-from .datamule_api import parse_textual_filing
-from .helper import load_package_csv, load_package_dataset
-from .global_vars import *
-from .parser.sgml_parser import parse_submission
-
-# Define classes with delayed initialization
-class Downloader:
-    def __new__(cls, *args, **kwargs):
-        return get_downloader()(*args, **kwargs)
-
-class Parser:
-    def __new__(cls, *args, **kwargs):
-        return get_parser()(*args, **kwargs)
-
-class Filing:
-    def __new__(cls, *args, **kwargs):
-        return get_filing()(*args, **kwargs)
-
-class DatasetBuilder:
-    def __new__(cls, *args, **kwargs):
-        builder_cls = get_dataset_builder()
-        if builder_cls is None:
-            raise ImportError(
-                "DatasetBuilder requires pandas. "
-                "Install with: pip install datamule[dataset_builder]"
-            )
-        return builder_cls(*args, **kwargs)
-
-# Set up Jupyter support only when imported
-_setup_jupyter()
-
-__all__ = [
-    'Downloader',
-    'parse_textual_filing',
-    'load_package_csv',
-    'load_package_dataset',
-    'Parser',
-    'Filing',
-    'DatasetBuilder'
+from .downloader.downloader import Downloader
+from .downloader.premiumdownloader import PremiumDownloader
+from .monitor import Monitor
+from .packageupdater import PackageUpdater
+from .submission import Submission
+from .portfolio import Portfolio
+from .document import Document
+from secsgml import parse_sgml_submission
+from .helper import load_package_csv, load_package_dataset
+from .config import Config
+
+
+# Keep the notebook environment setup
+def _is_notebook_env():
+    """Check if the code is running in a Jupyter or Colab environment."""
+    try:
+        shell = get_ipython().__class__.__name__
+        return shell in ('ZMQInteractiveShell', 'Shell', 'Google.Colab')
+    except NameError:
+        return False
+
+from functools import lru_cache
+
+@lru_cache(maxsize=1)
+def _setup_notebook_env():
+    """Setup Jupyter/Colab-specific configurations if needed."""
+    if _is_notebook_env():
+        import nest_asyncio
+        nest_asyncio.apply()
+
+# Set up notebook environment
+_setup_notebook_env()
+
+__all__ = [
+    'Downloader',
+    'PremiumDownloader',
+    'load_package_csv',
+    'load_package_dataset',
+    'Filing',
+    'Portfolio',
+    'Monitor',
+    'PackageUpdater',
+    'Submission',
+    'Document',
+    'parse_sgml_submission',
+    'Config'
 ]

datamule/book.py

@@ -0,0 +1,16 @@
+# Streams data rather than downloading it. 
+# additional functionality such as query by xbrl, and other db
+# also this is basically our experimental rework of portfolio w/o disturbing existing users
+# this is highly experimental and may not work as expected
+# only for datamule source
+# likely new bottleneck will be local parsing() - will be bypassed in future when we have parsed archive
+# wow parsed archive is going to be crazy fast - like every 10k in 1 minute.
+
+class Book():
+    pass
+    def process_submissions(self,cik,ticker,sic,submission_type,document_type,date,
+                            xbrl_query={},
+                            metadata_callback=None,
+                            document_callback=None,):
+        # grabs data and processes it
+        pass 

datamule/config.py

@@ -0,0 +1,29 @@
+import json
+import os
+
+class Config:
+    def __init__(self):
+        self.config_path = os.path.expanduser("~/.datamule/config.json")
+        self._ensure_config_exists()
+        
+    def _ensure_config_exists(self):
+        os.makedirs(os.path.dirname(self.config_path), exist_ok=True)
+        if not os.path.exists(self.config_path):
+            self._save_config({"default_source": None})
+
+    def _save_config(self, config):
+        with open(self.config_path, 'w') as f:
+            json.dump(config, f)
+
+    def set_default_source(self, source):
+        config = self._load_config()
+        config["default_source"] = source
+        self._save_config(config)
+
+    def get_default_source(self):
+        config = self._load_config()
+        return config.get("default_source")
+
+    def _load_config(self):
+        with open(self.config_path) as f:
+            return json.load(f)