anyxml 0.1.0__tar.gz

anyxml-0.1.0/PKG-INFO

@@ -0,0 +1,28 @@
+Metadata-Version: 2.3
+Name: anyxml
+Version: 0.1.0
+Summary: A minimal reimplementation of `ET.tostring` that supports unescaped 'raw' text content.
+Author: BHznJNs
+Author-email: BHznJNs <bhznjns@outlook.com>
+Requires-Python: >=3.11
+Description-Content-Type: text/markdown
+
+# AnyXml
+
+A minimal reimplementation of `ET.tostring` that supports unescaped "raw" text content.
+
+The standard library's `ET.tostring` always XML-escapes the `text`/`tail` content of elements (e.g. `<`, `&`), which makes it impossible to inject pre-built, already-valid XML fragments (or other raw strings) during serialization.
+This class provides :meth:`tostring`, which behaves similarly to `ET.tostring` but additionally supports:
+
+- Strings wrapped in :class:`RawText` are emitted verbatim during serialization, without any escaping; regular `str` text is still escaped according to XML rules.
+- Comment nodes (`ET.Comment`) and processing instruction nodes (`ET.ProcessingInstruction`) are rendered as `<!--...-->` and `<?...?>` respectively.
+- Elements with no text and no children are rendered as self-closing tags (`<tag/>`).
+
+## Example
+
+```
+>>> el = ET.Element("p")
+>>> el.text = AnyXml.RawText("<b>bold</b>")
+>>> AnyXml.tostring(el)
+'<p><b>bold</b></p>'
+```

anyxml-0.1.0/README.md

@@ -0,0 +1,19 @@
+# AnyXml
+
+A minimal reimplementation of `ET.tostring` that supports unescaped "raw" text content.
+
+The standard library's `ET.tostring` always XML-escapes the `text`/`tail` content of elements (e.g. `<`, `&`), which makes it impossible to inject pre-built, already-valid XML fragments (or other raw strings) during serialization.
+This class provides :meth:`tostring`, which behaves similarly to `ET.tostring` but additionally supports:
+
+- Strings wrapped in :class:`RawText` are emitted verbatim during serialization, without any escaping; regular `str` text is still escaped according to XML rules.
+- Comment nodes (`ET.Comment`) and processing instruction nodes (`ET.ProcessingInstruction`) are rendered as `<!--...-->` and `<?...?>` respectively.
+- Elements with no text and no children are rendered as self-closing tags (`<tag/>`).
+
+## Example
+
+```
+>>> el = ET.Element("p")
+>>> el.text = AnyXml.RawText("<b>bold</b>")
+>>> AnyXml.tostring(el)
+'<p><b>bold</b></p>'
+```

anyxml-0.1.0/pyproject.toml

@@ -0,0 +1,14 @@
+[project]
+name = "anyxml"
+version = "0.1.0"
+description = "A minimal reimplementation of `ET.tostring` that supports unescaped 'raw' text content."
+readme = "README.md"
+authors = [
+    { name = "BHznJNs", email = "bhznjns@outlook.com" }
+]
+requires-python = ">=3.11"
+dependencies = []
+
+[build-system]
+requires = ["uv_build>=0.9.28,<0.10.0"]
+build-backend = "uv_build"

anyxml-0.1.0/src/anyxml/__init__.py

@@ -0,0 +1,57 @@
+import xml.etree.ElementTree as ET
+from xml.sax.saxutils import escape, quoteattr
+
+
+class AnyXml:
+    """A minimal reimplementation of `ET.tostring` that supports unescaped "raw" text content.
+
+    The standard library's `ET.tostring` always XML-escapes the `text`/`tail` content of elements (e.g. `<`, `&`), which makes it impossible to inject pre-built, already-valid XML fragments (or other raw strings) during serialization.
+    This class provides :meth:`tostring`, which behaves similarly to `ET.tostring` but additionally supports:
+
+    - Strings wrapped in :class:`RawText` are emitted verbatim during serialization, without any escaping; regular `str` text is still escaped according to XML rules.
+    - Comment nodes (`ET.Comment`) and processing instruction nodes (`ET.ProcessingInstruction`) are rendered as `<!--...-->` and `<?...?>` respectively.
+    - Elements with no text and no children are rendered as self-closing tags (`<tag/>`).
+
+    Examples:
+        >>> el = ET.Element("p")
+        >>> el.text = AnyXml.RawText("<b>bold</b>")
+        >>> AnyXml.tostring(el)
+        '<p><b>bold</b></p>'
+    """
+
+    class RawText(str): pass
+
+    @staticmethod
+    def _text(s: str) -> str:
+        if isinstance(s, AnyXml.RawText): return s
+        return escape(s)
+
+    @staticmethod
+    def _comment(el: ET.Element) -> str:
+        assert el.tag is ET.Comment
+        return f"<!--{el.text or ''}-->"
+
+    @staticmethod
+    def _processing_instruction(el: ET.Element) -> str:
+        assert el.tag is ET.ProcessingInstruction
+        return f"<?{el.text or ''}?>"
+
+    @staticmethod
+    def tostring(el: ET.Element) -> str:
+        if el.tag is ET.Comment: return AnyXml._comment(el)
+        if el.tag is ET.ProcessingInstruction: return AnyXml._processing_instruction(el)
+
+        attrs = "".join(f" {k}={quoteattr(str(v))}" for k, v in el.attrib.items())
+
+        children_xml = []
+        for child in el:
+            children_xml.append(AnyXml.tostring(child))
+            if child.tail:
+                children_xml.append(AnyXml._text(child.tail))
+
+        if el.text is None and len(children_xml) == 0:
+            return f"<{el.tag}{attrs}/>"
+
+        inner_text = AnyXml._text(el.text) if el.text is not None else ""
+        body = inner_text + "".join(children_xml)
+        return f"<{el.tag}{attrs}>{body}</{el.tag}>"