xmlpydict 0.0.11__tar.gz → 0.0.12__tar.gz

{xmlpydict-0.0.11/xmlpydict.egg-info → xmlpydict-0.0.12}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: xmlpydict
-Version: 0.0.11
+Version: 0.0.12
 Summary: xml to dictionary tool for python
 Author-email: Matthew Taylor <matthew.taylor.andre@gmail.com>
 Project-URL: Homepage, https://github.com/MatthewAndreTaylor/xml-to-pydict
@@ -17,7 +17,7 @@ Classifier: Programming Language :: Python :: 3.11
 Classifier: Programming Language :: Python :: Implementation :: CPython
 Classifier: Topic :: Software Development :: Libraries :: Python Modules
 Classifier: Topic :: Text Processing :: Markup :: XML
-Requires-Python: >=3.7
+Requires-Python: >=3.8
 Description-Content-Type: text/markdown
 License-File: LICENSE
 Provides-Extra: tests

{xmlpydict-0.0.11 → xmlpydict-0.0.12}/pyproject.toml

@@ -4,13 +4,13 @@ build-backend = "setuptools.build_meta"
 
 [project]
 name = "xmlpydict"
-version = "0.0.11"
+version = "0.0.12"
 description="xml to dictionary tool for python"
 authors = [
     {name = "Matthew Taylor", email = "matthew.taylor.andre@gmail.com"},
 ]
 urls = {Homepage = "https://github.com/MatthewAndreTaylor/xml-to-pydict"}
-requires-python = ">=3.7"
+requires-python = ">=3.8"
 keywords = [ "xml", "dictionary" ]
 classifiers = [
     "Development Status :: 3 - Alpha",

{xmlpydict-0.0.11 → xmlpydict-0.0.12}/xmlpydict/__init__.py

@@ -40,6 +40,36 @@ def parse_file(file_path, attr_prefix: str = "@", cdata_key: str = "#text") -> d
     parser.CharacterDataHandler = handler.characters
     parser.StartElementHandler = handler.startElement
     parser.EndElementHandler = handler.endElement
-    with open(file_path, "r", encoding="utf-8") as f:
+    with open(file_path, "rb") as f:
         parser.ParseFile(f)
     return handler.item
+
+
+
+def iter_xml_documents(file_path, chunk_size=64 * 1024):
+    start_token = b"<?xml"
+    buffer = b""
+    with open(file_path, "rb") as f:
+        while True:
+            chunk = f.read(chunk_size)
+            if not chunk:
+                if buffer.strip():
+                    yield buffer
+                break
+            buffer += chunk
+            while True:
+                start_index = buffer.find(start_token, 1)
+                if start_index == -1:
+                    break
+                yield buffer[:start_index]
+                buffer = buffer[start_index:]
+            
+            
+
+def parse_xml_collections(file_path, attr_prefix: str = "@", cdata_key: str = "#text"):
+    for xml_content in iter_xml_documents(file_path):
+        yield parse(
+            xml_content.decode("utf-8"),
+            attr_prefix=attr_prefix,
+            cdata_key=cdata_key
+        )

{xmlpydict-0.0.11 → xmlpydict-0.0.12/xmlpydict.egg-info}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: xmlpydict
-Version: 0.0.11
+Version: 0.0.12
 Summary: xml to dictionary tool for python
 Author-email: Matthew Taylor <matthew.taylor.andre@gmail.com>
 Project-URL: Homepage, https://github.com/MatthewAndreTaylor/xml-to-pydict
@@ -17,7 +17,7 @@ Classifier: Programming Language :: Python :: 3.11
 Classifier: Programming Language :: Python :: Implementation :: CPython
 Classifier: Topic :: Software Development :: Libraries :: Python Modules
 Classifier: Topic :: Text Processing :: Markup :: XML
-Requires-Python: >=3.7
+Requires-Python: >=3.8
 Description-Content-Type: text/markdown
 License-File: LICENSE
 Provides-Extra: tests