xmlpydict 0.0.11__tar.gz → 0.0.13__tar.gz

{xmlpydict-0.0.11/xmlpydict.egg-info → xmlpydict-0.0.13}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: xmlpydict
-Version: 0.0.11
+Version: 0.0.13
 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-0.0.13}/pyproject.toml

@@ -4,13 +4,13 @@ build-backend = "setuptools.build_meta"
 
 [project]
 name = "xmlpydict"
-version = "0.0.11"
+version = "0.0.13"
 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-0.0.13}/tests/test_parse.py

@@ -1,6 +1,6 @@
 import pytest
 import json
-from xmlpydict import parse
+from xmlpydict import parse, parse_file
 
 
 def test_simple():
@@ -350,3 +350,35 @@ def test_document():
             ]
         }
     }
+
+
+def test_parse_file(tmp_path):
+    s = """<?xml version="1.0" encoding="UTF-8"?><repository>
+  <project pypi="xmlpydict">
+    <title>XML document parser</title>
+    <author>Matthew Taylor</author>
+  </project>
+  <project pypi="blank">
+    <title>Test project</title>
+    <author>Matthew Taylor</author>
+  </project>
+</repository>"""
+    with open(tmp_path / "test.xml", "w") as f:
+        f.write(s)
+
+    assert parse_file(tmp_path / "test.xml") == {
+        "repository": {
+            "project": [
+                {
+                    "@pypi": "xmlpydict",
+                    "title": "XML document parser",
+                    "author": "Matthew Taylor",
+                },
+                {
+                    "@pypi": "blank",
+                    "title": "Test project",
+                    "author": "Matthew Taylor",
+                },
+            ]
+        }
+    }

{xmlpydict-0.0.11 → xmlpydict-0.0.13}/xmlpydict/__init__.py

@@ -40,6 +40,50 @@ 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: int = 64 * 1024, start_token: bytes = 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",
+    start_token: bytes = b"<?xml",
+):
+    """
+    Parse collections of xml documents based on a delimeter start_token
+
+    Args:
+        file_path: The path to the XML file to be parsed.
+        attr_prefix: The prefix to use for attributes in the resulting dictionary.
+        cdata_key: The key to use for character data in the resulting dictionary.
+        start_token: The byte sequence that delimits the start of each XML document.
+
+    Returns:
+        A generator yielding dictionaries representing each XML document in the collection.
+    """
+    for xml_content in iter_xml_documents(file_path, start_token=start_token):
+        yield parse(
+            xml_content.decode("utf-8"), attr_prefix=attr_prefix, cdata_key=cdata_key
+        )

{xmlpydict-0.0.11 → xmlpydict-0.0.13/xmlpydict.egg-info}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: xmlpydict
-Version: 0.0.11
+Version: 0.0.13
 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