edi_xml_oca: replace xmlschema by lxml

edi_xml_oca/__manifest__.py

@@ -14,5 +14,5 @@
     "maintainers": ["simahawk"],
     "website": "https://github.com/OCA/edi-framework",
     "depends": ["edi_oca", "component"],
-    "external_dependencies": {"python": ["xmlschema"]},
+    "external_dependencies": {"python": ["xmltodict", "lxml"]},
 }

edi_xml_oca/components/xml_handler.py

@@ -2,13 +2,12 @@
 # @author: Simone Orsi <[email protected]>
 # License LGPL-3.0 or later (http://www.gnu.org/licenses/lgpl).
 
-import io
-from contextlib import closing
-
-import xmlschema
+import xmltodict
+from lxml import etree
 
 from odoo import modules
-from odoo.tools import DotDict
+from odoo.exceptions import UserError
+from odoo.tools import validate_xml_from_attachment
 
 from odoo.addons.component.core import Component
 
@@ -28,35 +27,39 @@ def __init__(self, work_context):
             if not hasattr(work_context, key):
                 raise AttributeError(f"`{key}` is required for this component!")
 
-        self.schema = xmlschema.XMLSchema(self._get_xsd_schema_path())
+        self.schema_path, self.schema = self._get_xsd_schema()
 
-    def _get_xsd_schema_path(self):
-        """Lookup for XSD schema."""
+    def _get_xsd_schema(self):
+        """Lookup and parse the XSD schema."""
         try:
             mod_name, path = self.work.schema_path.split(":")
         except ValueError as exc:
             raise ValueError("Path must be in the form `module:path`") from exc
-        return modules.get_resource_path(mod_name, path)
 
-    def _parse_xml(self, file_obj, **kw):
+        schema_path = modules.get_resource_path(mod_name, path)
+        with open(schema_path, "rb") as schema_file:
+            return schema_path, etree.XMLSchema(etree.parse(schema_file))
+
+    def _xml_string_to_dict(self, xml_string):
         """Read xml_content and return a data dict.
 
-        :param file_obj: file obj of XML file
+        :param xml_string: str of XML file
         """
-        return DotDict(self.schema.to_dict(file_obj, **kw))
+        return xmltodict.parse(xml_string)["xs:element"]
 
-    def parse_xml(self, file_content, **kw):
+    def parse_xml(self, file_content):
         """Read XML content.
-        :param file_content: str of XML file
+        :param file_content: unicode str of XML file
         :return: dict with final data
         """
-        with closing(io.StringIO(file_content)) as fd:
-            return self._parse_xml(fd)
+        tree = etree.XML(file_content.encode("utf-8"))
+        xml_string = etree.tostring(tree).decode("utf-8")
+        return self._xml_string_to_dict(xml_string)
 
     def validate(self, xml_content, raise_on_fail=False):
         """Validate XML content against XSD schema.
 
-        Raises `XMLSchemaValidationError` if `raise_on_fail` is True.
+        Raises `etree.DocumentInvalid` if `raise_on_fail` is True.
 
         :param xml_content: str containing xml data to validate
         :raise_on_fail: turn on/off validation error exception on fail
@@ -65,15 +68,13 @@ def validate(self, xml_content, raise_on_fail=False):
             * None if validation is ok
             * error string if `raise_on_fail` is False
         """
+        xsd_name = self.schema_path
+        xml_content = (
+            xml_content.encode("utf-8") if isinstance(xml_content, str) else xml_content
+        )
         try:
-            return self.schema.validate(xml_content)
-        except self._validate_swallable_exceptions() as err:
+            validate_xml_from_attachment(self.env, xml_content, xsd_name)
+        except UserError as exc:
             if raise_on_fail:
-                raise
-            return str(err)
-
-    def _validate_swallable_exceptions(self):
-        return (
-            xmlschema.exceptions.XMLSchemaValueError,
-            xmlschema.validators.exceptions.XMLSchemaValidationError,
-        )
+                raise exc
+            return str(exc)

edi_xml_oca/static/description/index.html

@@ -8,10 +8,11 @@
 
 /*
 :Author: David Goodger ([email protected])
-:Id: $Id: html4css1.css 8954 2022-01-20 10:10:25Z milde $
+:Id: $Id: html4css1.css 9511 2024-01-13 09:50:07Z milde $
 :Copyright: This stylesheet has been placed in the public domain.
 
 Default cascading style sheet for the HTML output of Docutils.
+Despite the name, some widely supported CSS2 features are used.
 
 See https://docutils.sourceforge.io/docs/howto/html-stylesheets.html for how to
 customize this style sheet.
@@ -274,7 +275,7 @@
   margin-left: 2em ;
   margin-right: 2em }
 
-pre.code .ln { color: grey; } /* line numbers */
+pre.code .ln { color: gray; } /* line numbers */
 pre.code, code { background-color: #eeeeee }
 pre.code .comment, code .comment { color: #5C6576 }
 pre.code .keyword, code .keyword { color: #3B0D06; font-weight: bold }
@@ -300,7 +301,7 @@
 span.pre {
   white-space: pre }
 
-span.problematic {
+span.problematic, pre.problematic {
   color: red }
 
 span.section-subtitle {
@@ -423,7 +424,9 @@ <h2><a class="toc-backref" href="#toc-entry-5">Other credits</a></h2>
 <div class="section" id="maintainers">
 <h2><a class="toc-backref" href="#toc-entry-6">Maintainers</a></h2>
 <p>This module is maintained by the OCA.</p>
-<a class="reference external image-reference" href="https://odoo-community.org"><img alt="Odoo Community Association" src="https://odoo-community.org/logo.png" /></a>
+<a class="reference external image-reference" href="https://odoo-community.org">
+<img alt="Odoo Community Association" src="https://odoo-community.org/logo.png" />
+</a>
 <p>OCA, or the Odoo Community Association, is a nonprofit organization whose
 mission is to support the collaborative development of Odoo features and
 promote its widespread use.</p>

edi_xml_oca/tests/test_xml.py

@@ -2,6 +2,8 @@
 # @author: Simone Orsi <[email protected]>
 # License LGPL-3.0 or later (http://www.gnu.org/licenses/lgpl).
 
+from odoo.tools import file_open
+
 from odoo.addons.component.tests.common import TransactionComponentCase
 
 from .common import XMLTestCaseMixin
@@ -36,15 +38,39 @@ def test_xml_schema_fail(self):
                 self.backend._name, ["edi.xml"], work_ctx={"no_schema": "Nothing"}
             )
 
+    def test_xml_schema_validation(self):
+        self.assertIsNone(self.handler.validate(TEST_XML))
+        XML_FAULTY = """<?xml version="1.0" encoding="UTF-8"?>
+        <xs:element xmlns:xs="http://www.w3.org/2001/XMLSchema" name="shoesize" type="shoetype">
+            <xs:element name="test" type="test" />
+        </xs:element>
+        """
+
+        schema_path = self.handler.schema_path
+        with file_open(schema_path, "rb") as f:
+            schema_xml = f.read()
+            # store the schema in ir.attachment as it is searched
+            # inside _check_with_xsd method defined in odoo.tools
+            self.env["ir.attachment"].create(
+                {
+                    "name": schema_path,
+                    "datas": schema_xml,
+                    "type": "binary",
+                    "res_model": "edi.exchange.template.output",
+                    "res_id": 1,
+                    "raw": schema_xml,
+                }
+            )
+
+        self.assertIsNotNone(self.handler.validate(XML_FAULTY))
+
     def test_xml(self):
         data = self.handler.parse_xml(TEST_XML)
         self.assertEqual(
             data,
             {
-                "@abstract": False,
+                "@xmlns:xs": "http://www.w3.org/2001/XMLSchema",
                 "@name": "shoesize",
-                "@nillable": False,
                 "@type": "shoetype",
-                "@xmlns:xs": "http://www.w3.org/2001/XMLSchema",
             },
         )

requirements.txt

@@ -1,3 +1,4 @@
 # generated from manifests external_dependencies
+lxml
 PyYAML
-xmlschema
+xmltodict