datamule 1.2.1__tar.gz → 1.2.3__tar.gz

{datamule-1.2.1 → datamule-1.2.3}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: datamule
-Version: 1.2.1
+Version: 1.2.3
 Summary: Making it easier to use SEC filings.
 Home-page: https://github.com/john-friedman/datamule-python
 Author: John Friedman

{datamule-1.2.1 → datamule-1.2.3}/datamule/package_updater.py

@@ -9,7 +9,7 @@ class PackageUpdater():
     def __init__(self):
         pass
 
-    def update_package_data():
+    def update_package_data(self):
         # Create data directory in user's home
         data_dir = Path.home() / ".datamule"
         data_dir.mkdir(exist_ok=True)
@@ -19,13 +19,12 @@ class PackageUpdater():
         file_path = data_dir / "listed_filer_metadata.csv"
         temp_gz_path = data_dir / "listed_filer_metadata.csv.gz"
 
-        if not file_path.exists():
-            print(f"Downloading data to {data_dir}")
-            urllib.request.urlretrieve(file_url, temp_gz_path)
-            
-            with gzip.open(temp_gz_path, 'rb') as f_in:
-                with open(file_path, 'wb') as f_out:
-                    shutil.copyfileobj(f_in, f_out)
-                    
-            os.remove(temp_gz_path)
-            print(f"Data downloaded to {file_path}")
+        print(f"Downloading data to {data_dir}")
+        urllib.request.urlretrieve(file_url, temp_gz_path)
+        
+        with gzip.open(temp_gz_path, 'rb') as f_in:
+            with open(file_path, 'wb') as f_out:
+                shutil.copyfileobj(f_in, f_out)
+                
+        os.remove(temp_gz_path)
+        print(f"Data downloaded to {file_path}")

{datamule-1.2.1 → datamule-1.2.3}/datamule/submission.py

@@ -17,6 +17,7 @@ class Submission:
             self.path = None
             self.metadata, raw_documents = parse_sgml_submission_into_memory(sgml_content)
 
+            # code dupe
             self.accession = self.metadata['accession-number']
             self.filing_date= f"{self.metadata['filing-date'][:4]}-{self.metadata['filing-date'][4:6]}-{self.metadata['filing-date'][6:8]}"
     
@@ -43,6 +44,11 @@ class Submission:
             with metadata_path.open('r') as f:
                 self.metadata = json.load(f)
 
+            # Code dupe
+            self.accession = self.metadata['accession-number']
+            self.filing_date= f"{self.metadata['filing-date'][:4]}-{self.metadata['filing-date'][4:6]}-{self.metadata['filing-date'][6:8]}"
+    
+
 
 
     def document_type(self, document_type):
@@ -65,9 +71,12 @@ class Submission:
                     document_path = self.path / filename
                     extension = document_path.suffix
 
-                    with document_path.open('r') as f:
+                    with document_path.open('rb') as f:
                         content = f.read()
 
+                    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)
                 # if loaded from sgml_content
                 else:
@@ -89,9 +98,12 @@ class Submission:
 
                 # check if the file exists
                 if document_path.exists():
-                    with document_path.open('r') as f:
+                    with document_path.open('rb') as f:
                         content = f.read()
 
+                    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)
                 else:
                     print(f"Warning: File {document_path} does not exist likely due to keep types in downloading.")
@@ -100,28 +112,6 @@ class Submission:
             else:
                 yield self.documents[idx]
 
-    # keep documents by document type
-    def keep(self, document_type):
-        # Convert single document type to list for consistent handling
-        if isinstance(document_type, str):
-            document_types = [document_type]
-        else:
-            document_types = document_type
-
-        if self.path is not None:
-            for doc in self.metadata['documents']:
-                filename = doc.get('filename')
-                type = doc.get('type')
-                if type not in document_types:
-                    # oh we need handling here for sequences case
-                    if filename is None:
-                        filename = doc.sequence + '.txt'
-
-                    document_path = self.path / filename
-                    # delete the file
-                    document_path.unlink()
-        else:
-            print("Warning: keep() method is only available when loading from path.")
 
 
 

{datamule-1.2.1 → datamule-1.2.3}/datamule.egg-info/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: datamule
-Version: 1.2.1
+Version: 1.2.3
 Summary: Making it easier to use SEC filings.
 Home-page: https://github.com/john-friedman/datamule-python
 Author: John Friedman

{datamule-1.2.1 → datamule-1.2.3}/setup.py

@@ -30,7 +30,7 @@ if not file_path.exists():
 setup(
     name="datamule",
     author="John Friedman",
-    version="1.2.1",
+    version="1.2.3",
     description="Making it easier to use SEC filings.",
     packages=find_packages(include=['datamule', 'datamule.*']),
     url="https://github.com/john-friedman/datamule-python",