datamule 1.4.6__py3-none-any.whl → 1.4.9__py3-none-any.whl

datamule/document/document.py

@@ -11,19 +11,7 @@ from selectolax.parser import HTMLParser
 from .processing import process_tabular_data
 from pathlib import Path
 import webbrowser
-
-def convert_bytes_keys(obj):
-    if isinstance(obj, dict):
-        return {
-            (k.decode('utf-8').lower() if isinstance(k, bytes) else k): convert_bytes_keys(v) 
-            for k, v in obj.items()
-        }
-    elif isinstance(obj, list):
-        return [convert_bytes_keys(item) for item in obj]
-    elif isinstance(obj, bytes):
-        return obj.decode('utf-8').lower()
-    else:
-        return obj
+from secsgml.utils import bytes_to_str
 
 class Document:
     def __init__(self, type, content, extension,accession,filing_date,path=None):
@@ -34,7 +22,8 @@ class Document:
         self.filing_date = filing_date
 
         if self.type == 'submission_metadata':
-            self.content = convert_bytes_keys(content)
+            # this converts to lower
+            self.content = bytes_to_str(content)
         else:
             self.content = content
 

datamule/submission.py

@@ -4,72 +4,8 @@ from .document.document import Document
 from secsgml import parse_sgml_content_into_memory
 import os
 import aiofiles
-import tempfile
-
-
-# # NEW CODE YAY. probably will remove
-
-# def save_metadata_atomically(metadata_file_path, metadata_content):
-#     """Save metadata to a JSONL file atomically, works on any filesystem"""
-    
-#     # Create directory if it doesn't exist
-#     os.makedirs(os.path.dirname(metadata_file_path), exist_ok=True)
-    
-#     # Format the JSON with newline
-#     json_str = json.dumps(metadata_content, indent=4) + "\n"
-    
-#     # Write complete content to a temporary file first
-#     fd, temp_path = tempfile.mkstemp(dir=os.path.dirname(metadata_file_path))
-#     try:
-#         with os.fdopen(fd, 'w') as temp_file:
-#             temp_file.write(json_str)
-#             temp_file.flush()
-#             os.fsync(temp_file.fileno())  # Force write to disk
-        
-#         # Append the temporary file to the main file
-#         with open(metadata_file_path, 'a') as target_file:
-#             with open(temp_path, 'r') as temp_read:
-#                 content = temp_read.read()
-#                 target_file.write(content)
-#                 target_file.flush()
-#                 os.fsync(target_file.fileno())  # Force write to disk
-#     finally:
-#         # Clean up the temporary file
-#         if os.path.exists(temp_path):
-#             os.unlink(temp_path)
-
-# async def save_metadata_atomically_async(metadata_file_path, metadata_content):
-#     """Save metadata to a JSONL file atomically in async mode"""
-    
-#     # Create directory if it doesn't exist
-#     os.makedirs(os.path.dirname(metadata_file_path), exist_ok=True)
-    
-#     # Format the JSON with newline
-#     json_str = json.dumps(metadata_content, indent=4) + "\n"
-    
-#     # Write to a temporary file first
-#     fd, temp_path = tempfile.mkstemp(dir=os.path.dirname(metadata_file_path))
-#     os.close(fd)  # Close the file descriptor
-    
-#     try:
-#         async with aiofiles.open(temp_path, 'w') as temp_file:
-#             await temp_file.write(json_str)
-#             await temp_file.flush()
-        
-#         # Append the temporary file to the main file
-#         async with aiofiles.open(metadata_file_path, 'a') as target_file:
-#             async with aiofiles.open(temp_path, 'r') as temp_read:
-#                 content = await temp_read.read()
-#                 await target_file.write(content)
-#                 await target_file.flush()
-#     finally:
-#         # Clean up the temporary file
-#         if os.path.exists(temp_path):
-#             os.unlink(temp_path)
-
-# # END OF NEW CODE
-
 
+# TODO add .tar path
 class Submission:
     def __init__(self, path=None,sgml_content=None,keep_document_types=None):
         if path is None and sgml_content is None:
@@ -89,7 +25,7 @@ class Submission:
             filtered_metadata_documents = []
 
             for idx,doc in enumerate(self.metadata.content['documents']):
-                type = doc.get('type')
+                type = doc.get('type').upper()
                 
                 # Keep only specified types
                 if keep_document_types is not None and type not in keep_document_types:
@@ -98,7 +34,7 @@ class Submission:
                 # write as txt if not declared
                 filename = doc.get('filename','.txt')
                 extension = Path(filename).suffix
-                self.documents.append(Document(type=type, content=raw_documents[idx], extension=extension,filing_date=self.filing_date,accession=self.accession))
+                self.documents.append(Document(type=type.upper(), content=raw_documents[idx], extension=extension,filing_date=self.filing_date,accession=self.accession))
 
                 filtered_metadata_documents.append(doc)
             
@@ -121,9 +57,9 @@ class Submission:
     def document_type(self, document_type):
         # Convert single document type to list for consistent handling
         if isinstance(document_type, str):
-            document_types = [document_type]
+            document_types = [document_type.lower()]
         else:
-            document_types = document_type
+            document_types = [item.lower() for item in document_type]
 
         for idx,doc in enumerate(self.metadata.content['documents']):
             if doc['type'] in document_types:
@@ -144,7 +80,7 @@ class Submission:
                     if extension in ['.htm','.html','.txt','.xml']:
                         content = content.decode('utf-8', errors='replace')
 
-                    yield Document(type=doc['type'], content=content, extension=extension,filing_date=self.filing_date,accession=self.accession,path=document_path)
+                    yield Document(type=doc['type'].upper(), content=content, extension=extension,filing_date=self.filing_date,accession=self.accession,path=document_path)
                 # if loaded from sgml_content
                 else:
                     yield self.documents[idx]
@@ -171,7 +107,7 @@ class Submission:
                     if extension in ['.htm','.html','.txt','.xml']:
                         content = content.decode('utf-8', errors='replace')
 
-                    yield Document(type=doc['type'], content=content, extension=extension,filing_date=self.filing_date,accession=self.accession,path=document_path)
+                    yield Document(type=doc['type'].upper(), content=content, extension=extension,filing_date=self.filing_date,accession=self.accession,path=document_path)
                 else:
                     print(f"Warning: File {document_path} does not exist likely due to keep types in downloading.")
 

{datamule-1.4.6.dist-info → datamule-1.4.9.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: datamule
-Version: 1.4.6
+Version: 1.4.9
 Summary: Work with SEC submissions at scale.
 Home-page: https://github.com/john-friedman/datamule-python
 Author: John Friedman

{datamule-1.4.6.dist-info → datamule-1.4.9.dist-info}/RECORD

@@ -5,10 +5,10 @@ datamule/index.py,sha256=Rrcna9FJV-Oh_K6O2IuUEIDmtay_7UZ4l4jgKCi7A7I,2079
 datamule/package_updater.py,sha256=Z9zaa_y0Z5cknpRn8oPea3gg4kquFHfpfhduKKCZ6NU,958
 datamule/portfolio.py,sha256=8fiK-vfZM5-NJSvOEsDR2YDb-2njjzFk6l7BiRyrzOM,7168
 datamule/sheet.py,sha256=TvFqK9eAYuVoJ2uWdAlx5EN6vS9lke-aZf7FqtUiDBc,22304
-datamule/submission.py,sha256=EtWdEnAyWLZdu69Dyzbs4qb5YL41HlExFGMjwEoMhsg,10904
+datamule/submission.py,sha256=UTGIkXOFVrBTHLJxTekw60Nvp92GuSsgQApJWXHNuNg,8493
 datamule/data/listed_filer_metadata.csv,sha256=dT9fQ8AC5P1-Udf_UF0ZkdXJ88jNxJb_tuhi5YYL1rc,2426827
 datamule/document/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-datamule/document/document.py,sha256=3vX850H7rZH4H8BysitZDaLhT6WPJuIreoV1PSjACno,14301
+datamule/document/document.py,sha256=VaJWo9HrcODlbifYcXzifW3xBD7nUOWAN8zcVCDWMcs,13958
 datamule/document/processing.py,sha256=jDCEzBFDSQtq7nQxRScIsbALnFcvMPOkNkMUCa7mFxg,31921
 datamule/document/table.py,sha256=73yUJKY82ap32jhLmZeTti-jQ_lyhcJGlGwyxLtgYOg,12944
 datamule/document/mappings/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
@@ -58,7 +58,7 @@ datamule/seclibrary/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSu
 datamule/seclibrary/bq.py,sha256=C8sb_rpXTvchprrFLcbRar4Qi0XWW25tnv1YsHSS5o4,18025
 datamule/seclibrary/downloader.py,sha256=VIdaQq5wDcYWnqrv9t8J7z0KtdNRGK8ahfBsgvTfdQQ,13675
 datamule/seclibrary/query.py,sha256=qGuursTERRbOGfoDcYcpo4oWkW3PCBW6x1Qf1Puiak4,7352
-datamule-1.4.6.dist-info/METADATA,sha256=IxggkAHbjanZjnTtWGNOyRM68sztal4gQlUfa0shlXg,469
-datamule-1.4.6.dist-info/WHEEL,sha256=oiQVh_5PnQM0E3gPdiz09WCNmwiHDMaGer_elqB3coM,92
-datamule-1.4.6.dist-info/top_level.txt,sha256=iOfgmtSMFVyr7JGl_bYSTDry79JbmsG4p8zKq89ktKk,9
-datamule-1.4.6.dist-info/RECORD,,
+datamule-1.4.9.dist-info/METADATA,sha256=ojII-iQoWPNIJXs28FNsQjExKxOdQROgYsIHdOfMw6I,469
+datamule-1.4.9.dist-info/WHEEL,sha256=oiQVh_5PnQM0E3gPdiz09WCNmwiHDMaGer_elqB3coM,92
+datamule-1.4.9.dist-info/top_level.txt,sha256=iOfgmtSMFVyr7JGl_bYSTDry79JbmsG4p8zKq89ktKk,9
+datamule-1.4.9.dist-info/RECORD,,