Upload lxml/Test_LXML.py with huggingface_hub

lxml/Test_LXML.py

@@ -0,0 +1,290 @@
+"""
+On-device verification for the cross-compiled lxml wheel (norelro).
+
+Run after installing:
+    pip install lxml-6.1.1-cp312-cp312-android_24_x86_64.whl
+
+Usage:
+    python Test_lxml.py
+
+Exit code 0 = everything required PASSed.
+
+Generated by RIMI
+"""
+import sys
+
+RESULTS = []
+
+
+def test(name, fn):
+    try:
+        fn()
+        RESULTS.append((name, "PASS", None))
+    except Exception as exc:
+        RESULTS.append((name, "FAIL", "%s: %s" % (type(exc).__name__, exc)))
+        print("    ! %s -> %s: %s" % (name, type(exc).__name__, exc))
+
+
+def section(title):
+    print("=" * 60)
+    print(title)
+    print("=" * 60)
+
+
+# ---------------------------------------------------------------------------
+# 1. import / version
+# ---------------------------------------------------------------------------
+def import_lxml():
+    import lxml.etree as etree
+    print("    lxml.etree version", etree.LXML_VERSION)
+    print("    libxml2", etree.LIBXML_VERSION)
+    print("    libxslt", etree.LIBXSLT_VERSION)
+
+
+def import_objectify():
+    from lxml import objectify
+    print("    lxml.objectify OK")
+
+
+def import_html():
+    from lxml import html
+    print("    lxml.html OK")
+
+
+def import_html_clean():
+    from lxml_html_clean import clean
+    print("    lxml_html_clean OK")
+
+
+# ---------------------------------------------------------------------------
+# 2. etree basics
+# ---------------------------------------------------------------------------
+def parse_string():
+    from lxml import etree
+    xml = b"<root><item id='1'>hello</item><item id='2'>world</item></root>"
+    root = etree.fromstring(xml)
+    assert root.tag == "root"
+    items = root.findall("item")
+    assert len(items) == 2
+    assert items[0].get("id") == "1"
+    assert items[0].text == "hello"
+
+
+def parse_file():
+    from lxml import etree
+    xml = b"<data><row><a>1</a><b>2</b></row></data>"
+    root = etree.fromstring(xml)
+    row = root.find("row")
+    assert int(row.find("a").text) == 1
+    assert int(row.find("b").text) == 2
+
+
+def tostring():
+    from lxml import etree
+    root = etree.Element("parent")
+    child = etree.SubElement(root, "child")
+    child.text = "text"
+    s = etree.tostring(root, encoding="unicode")
+    assert "<child>text</child>" in s
+
+
+def xpath():
+    from lxml import etree
+    xml = b"<root><a x='1'/><a x='2'/><b/></root>"
+    root = etree.fromstring(xml)
+    a_list = root.xpath("//a")
+    assert len(a_list) == 2
+    vals = root.xpath("//a/@x")
+    assert vals == ["1", "2"]
+    first = root.xpath("//a[@x='2']")
+    assert len(first) == 1
+
+
+def namespaces():
+    from lxml import etree
+    ns = {"s": "http://example.com/ns"}
+    xml = b'<root xmlns:s="http://example.com/ns"><s:item>ok</s:item></root>'
+    root = etree.fromstring(xml)
+    items = root.xpath("//s:item", namespaces=ns)
+    assert len(items) == 1
+    assert items[0].text == "ok"
+
+
+# ---------------------------------------------------------------------------
+# 3. build / modify trees
+# ---------------------------------------------------------------------------
+def build_tree():
+    from lxml import etree
+    root = etree.Element("root")
+    for i in range(5):
+        child = etree.SubElement(root, "item")
+        child.set("index", str(i))
+        child.text = "val_%d" % i
+    assert len(root) == 5
+    assert root[2].get("index") == "2"
+    assert root[4].text == "val_4"
+
+
+def modify_tree():
+    from lxml import etree
+    root = etree.Element("root")
+    a = etree.SubElement(root, "a")
+    b = etree.SubElement(root, "b")
+    root.remove(b)
+    assert len(root) == 1
+    a.text = "modified"
+    assert root[0].text == "modified"
+
+
+# ---------------------------------------------------------------------------
+# 4. HTML parsing
+# ---------------------------------------------------------------------------
+def html_parse():
+    from lxml import html
+    doc = html.fromstring("<html><body><p>Hello</p><p>World</p></body></html>")
+    ps = doc.xpath("//p")
+    assert len(ps) == 2
+    assert ps[0].text == "Hello"
+
+
+def html_tostring():
+    from lxml import html
+    doc = html.fromstring("<html><body><div id='main'>content</div></body></html>")
+    s = html.tostring(doc, encoding="unicode")
+    assert "content" in s
+    assert 'id="main"' in s
+
+
+# ---------------------------------------------------------------------------
+# 5. html_clean (bundled dep)
+# ---------------------------------------------------------------------------
+def html_clean():
+    from lxml_html_clean import Cleaner
+    from lxml import html
+    dirty = '<html><body><p>safe</p></body></html>'
+    doc = html.fromstring(dirty)
+    c = Cleaner()
+    c.clean_html(doc)
+    s = html.tostring(doc, encoding="unicode")
+    assert "safe" in s
+
+
+# ---------------------------------------------------------------------------
+# 6. XSLT
+# ---------------------------------------------------------------------------
+def xslt_transform():
+    from lxml import etree
+    xml = b"<root><item>1</item><item>2</item></root>"
+    xslt_str = b"""<xsl:stylesheet version="1.0"
+        xmlns:xsl="http://www.w3.org/1999/XSL/Transform">
+      <xsl:template match="/">
+        <out><xsl:for-each select="root/item">
+          <val><xsl:value-of select="."/></val>
+        </xsl:for-each></out>
+      </xsl:template>
+    </xsl:stylesheet>"""
+    xml_doc = etree.fromstring(xml)
+    xslt_doc = etree.fromstring(xslt_str)
+    transform = etree.XSLT(xslt_doc)
+    result = transform(xml_doc)
+    s = etree.tostring(result, encoding="unicode")
+    assert "<val>1</val>" in s
+    assert "<val>2</val>" in s
+
+
+# ---------------------------------------------------------------------------
+# 7. XML schema validation
+# ---------------------------------------------------------------------------
+def schema_validate():
+    from lxml import etree
+    schema_xml = b"""<xs:schema xmlns:xs="http://www.w3.org/2001/XMLSchema">
+      <xs:element name="root">
+        <xs:complexType>
+          <xs:sequence>
+            <xs:element name="name" type="xs:string"/>
+            <xs:element name="age" type="xs:decimal"/>
+          </xs:sequence>
+        </xs:complexType>
+      </xs:element>
+    </xs:schema>"""
+    schema_doc = etree.fromstring(schema_xml)
+    schema = etree.XMLSchema(schema_doc)
+
+    valid = etree.fromstring(b"<root><name>Alice</name><age>30</age></root>")
+    assert schema.validate(valid)
+
+    invalid = etree.fromstring(b"<root><name>Alice</name></root>")
+    assert not schema.validate(invalid)
+
+
+# ---------------------------------------------------------------------------
+# 8. c14n (canonicalization)
+# ---------------------------------------------------------------------------
+def c14n():
+    from lxml import etree
+    xml = b'<root  attr="1"  ><child>text</child></root>'
+    root = etree.fromstring(xml)
+    c = etree.tostring(root, method="c14n")
+    assert b'attr="1"' in c
+    assert b"<child>" in c
+
+
+# ---------------------------------------------------------------------------
+def main():
+    section("1. import / version")
+    test("import lxml.etree", import_lxml)
+    test("import lxml.objectify", import_objectify)
+    test("import lxml.html", import_html)
+    test("import lxml_html_clean", import_html_clean)
+
+    section("2. etree basics")
+    test("parse fromstring", parse_string)
+    test("parse file-like", parse_file)
+    test("tostring", tostring)
+    test("xpath", xpath)
+    test("namespaces", namespaces)
+
+    section("3. build / modify trees")
+    test("build tree", build_tree)
+    test("modify tree", modify_tree)
+
+    section("4. HTML parsing")
+    test("html parse", html_parse)
+    test("html tostring", html_tostring)
+
+    section("5. html_clean (bundled dep)")
+    test("clean HTML", html_clean)
+
+    section("6. XSLT")
+    test("xslt transform", xslt_transform)
+
+    section("7. XML schema validation")
+    test("schema validate", schema_validate)
+
+    section("8. c14n")
+    test("canonicalization", c14n)
+
+    print()
+    print("=" * 60)
+    print("SUMMARY")
+    print("=" * 60)
+    fails = 0
+    for name, status, why in RESULTS:
+        mark = "  OK" if status == "PASS" else "FAIL"
+        print("%s %s" % (mark, name))
+        if why:
+            print("        -> %s" % why)
+        if status == "FAIL":
+            fails += 1
+    print()
+    passed = len(RESULTS) - fails
+    print("passed=%d failed=%d" % (passed, fails))
+    if fails:
+        print("RESULT: FAILED")
+    else:
+        print("RESULT: PASSED")
+    sys.exit(1 if fails else 0)
+
+
+if __name__ == "__main__":
+    main()