Delete lxml/Test_LXML.py
Browse files- lxml/Test_LXML.py +0 -290
lxml/Test_LXML.py
DELETED
|
@@ -1,290 +0,0 @@
|
|
| 1 |
-
"""
|
| 2 |
-
On-device verification for the cross-compiled lxml wheel (norelro).
|
| 3 |
-
|
| 4 |
-
Run after installing:
|
| 5 |
-
pip install lxml-6.1.1-cp312-cp312-android_24_x86_64.whl
|
| 6 |
-
|
| 7 |
-
Usage:
|
| 8 |
-
python Test_lxml.py
|
| 9 |
-
|
| 10 |
-
Exit code 0 = everything required PASSed.
|
| 11 |
-
|
| 12 |
-
Generated by RIMI
|
| 13 |
-
"""
|
| 14 |
-
import sys
|
| 15 |
-
|
| 16 |
-
RESULTS = []
|
| 17 |
-
|
| 18 |
-
|
| 19 |
-
def test(name, fn):
|
| 20 |
-
try:
|
| 21 |
-
fn()
|
| 22 |
-
RESULTS.append((name, "PASS", None))
|
| 23 |
-
except Exception as exc:
|
| 24 |
-
RESULTS.append((name, "FAIL", "%s: %s" % (type(exc).__name__, exc)))
|
| 25 |
-
print(" ! %s -> %s: %s" % (name, type(exc).__name__, exc))
|
| 26 |
-
|
| 27 |
-
|
| 28 |
-
def section(title):
|
| 29 |
-
print("=" * 60)
|
| 30 |
-
print(title)
|
| 31 |
-
print("=" * 60)
|
| 32 |
-
|
| 33 |
-
|
| 34 |
-
# ---------------------------------------------------------------------------
|
| 35 |
-
# 1. import / version
|
| 36 |
-
# ---------------------------------------------------------------------------
|
| 37 |
-
def import_lxml():
|
| 38 |
-
import lxml.etree as etree
|
| 39 |
-
print(" lxml.etree version", etree.LXML_VERSION)
|
| 40 |
-
print(" libxml2", etree.LIBXML_VERSION)
|
| 41 |
-
print(" libxslt", etree.LIBXSLT_VERSION)
|
| 42 |
-
|
| 43 |
-
|
| 44 |
-
def import_objectify():
|
| 45 |
-
from lxml import objectify
|
| 46 |
-
print(" lxml.objectify OK")
|
| 47 |
-
|
| 48 |
-
|
| 49 |
-
def import_html():
|
| 50 |
-
from lxml import html
|
| 51 |
-
print(" lxml.html OK")
|
| 52 |
-
|
| 53 |
-
|
| 54 |
-
def import_html_clean():
|
| 55 |
-
from lxml_html_clean import clean
|
| 56 |
-
print(" lxml_html_clean OK")
|
| 57 |
-
|
| 58 |
-
|
| 59 |
-
# ---------------------------------------------------------------------------
|
| 60 |
-
# 2. etree basics
|
| 61 |
-
# ---------------------------------------------------------------------------
|
| 62 |
-
def parse_string():
|
| 63 |
-
from lxml import etree
|
| 64 |
-
xml = b"<root><item id='1'>hello</item><item id='2'>world</item></root>"
|
| 65 |
-
root = etree.fromstring(xml)
|
| 66 |
-
assert root.tag == "root"
|
| 67 |
-
items = root.findall("item")
|
| 68 |
-
assert len(items) == 2
|
| 69 |
-
assert items[0].get("id") == "1"
|
| 70 |
-
assert items[0].text == "hello"
|
| 71 |
-
|
| 72 |
-
|
| 73 |
-
def parse_file():
|
| 74 |
-
from lxml import etree
|
| 75 |
-
xml = b"<data><row><a>1</a><b>2</b></row></data>"
|
| 76 |
-
root = etree.fromstring(xml)
|
| 77 |
-
row = root.find("row")
|
| 78 |
-
assert int(row.find("a").text) == 1
|
| 79 |
-
assert int(row.find("b").text) == 2
|
| 80 |
-
|
| 81 |
-
|
| 82 |
-
def tostring():
|
| 83 |
-
from lxml import etree
|
| 84 |
-
root = etree.Element("parent")
|
| 85 |
-
child = etree.SubElement(root, "child")
|
| 86 |
-
child.text = "text"
|
| 87 |
-
s = etree.tostring(root, encoding="unicode")
|
| 88 |
-
assert "<child>text</child>" in s
|
| 89 |
-
|
| 90 |
-
|
| 91 |
-
def xpath():
|
| 92 |
-
from lxml import etree
|
| 93 |
-
xml = b"<root><a x='1'/><a x='2'/><b/></root>"
|
| 94 |
-
root = etree.fromstring(xml)
|
| 95 |
-
a_list = root.xpath("//a")
|
| 96 |
-
assert len(a_list) == 2
|
| 97 |
-
vals = root.xpath("//a/@x")
|
| 98 |
-
assert vals == ["1", "2"]
|
| 99 |
-
first = root.xpath("//a[@x='2']")
|
| 100 |
-
assert len(first) == 1
|
| 101 |
-
|
| 102 |
-
|
| 103 |
-
def namespaces():
|
| 104 |
-
from lxml import etree
|
| 105 |
-
ns = {"s": "http://example.com/ns"}
|
| 106 |
-
xml = b'<root xmlns:s="http://example.com/ns"><s:item>ok</s:item></root>'
|
| 107 |
-
root = etree.fromstring(xml)
|
| 108 |
-
items = root.xpath("//s:item", namespaces=ns)
|
| 109 |
-
assert len(items) == 1
|
| 110 |
-
assert items[0].text == "ok"
|
| 111 |
-
|
| 112 |
-
|
| 113 |
-
# ---------------------------------------------------------------------------
|
| 114 |
-
# 3. build / modify trees
|
| 115 |
-
# ---------------------------------------------------------------------------
|
| 116 |
-
def build_tree():
|
| 117 |
-
from lxml import etree
|
| 118 |
-
root = etree.Element("root")
|
| 119 |
-
for i in range(5):
|
| 120 |
-
child = etree.SubElement(root, "item")
|
| 121 |
-
child.set("index", str(i))
|
| 122 |
-
child.text = "val_%d" % i
|
| 123 |
-
assert len(root) == 5
|
| 124 |
-
assert root[2].get("index") == "2"
|
| 125 |
-
assert root[4].text == "val_4"
|
| 126 |
-
|
| 127 |
-
|
| 128 |
-
def modify_tree():
|
| 129 |
-
from lxml import etree
|
| 130 |
-
root = etree.Element("root")
|
| 131 |
-
a = etree.SubElement(root, "a")
|
| 132 |
-
b = etree.SubElement(root, "b")
|
| 133 |
-
root.remove(b)
|
| 134 |
-
assert len(root) == 1
|
| 135 |
-
a.text = "modified"
|
| 136 |
-
assert root[0].text == "modified"
|
| 137 |
-
|
| 138 |
-
|
| 139 |
-
# ---------------------------------------------------------------------------
|
| 140 |
-
# 4. HTML parsing
|
| 141 |
-
# ---------------------------------------------------------------------------
|
| 142 |
-
def html_parse():
|
| 143 |
-
from lxml import html
|
| 144 |
-
doc = html.fromstring("<html><body><p>Hello</p><p>World</p></body></html>")
|
| 145 |
-
ps = doc.xpath("//p")
|
| 146 |
-
assert len(ps) == 2
|
| 147 |
-
assert ps[0].text == "Hello"
|
| 148 |
-
|
| 149 |
-
|
| 150 |
-
def html_tostring():
|
| 151 |
-
from lxml import html
|
| 152 |
-
doc = html.fromstring("<html><body><div id='main'>content</div></body></html>")
|
| 153 |
-
s = html.tostring(doc, encoding="unicode")
|
| 154 |
-
assert "content" in s
|
| 155 |
-
assert 'id="main"' in s
|
| 156 |
-
|
| 157 |
-
|
| 158 |
-
# ---------------------------------------------------------------------------
|
| 159 |
-
# 5. html_clean (bundled dep)
|
| 160 |
-
# ---------------------------------------------------------------------------
|
| 161 |
-
def html_clean():
|
| 162 |
-
from lxml_html_clean import Cleaner
|
| 163 |
-
from lxml import html
|
| 164 |
-
dirty = '<html><body><p>safe</p></body></html>'
|
| 165 |
-
doc = html.fromstring(dirty)
|
| 166 |
-
c = Cleaner()
|
| 167 |
-
c.clean_html(doc)
|
| 168 |
-
s = html.tostring(doc, encoding="unicode")
|
| 169 |
-
assert "safe" in s
|
| 170 |
-
|
| 171 |
-
|
| 172 |
-
# ---------------------------------------------------------------------------
|
| 173 |
-
# 6. XSLT
|
| 174 |
-
# ---------------------------------------------------------------------------
|
| 175 |
-
def xslt_transform():
|
| 176 |
-
from lxml import etree
|
| 177 |
-
xml = b"<root><item>1</item><item>2</item></root>"
|
| 178 |
-
xslt_str = b"""<xsl:stylesheet version="1.0"
|
| 179 |
-
xmlns:xsl="http://www.w3.org/1999/XSL/Transform">
|
| 180 |
-
<xsl:template match="/">
|
| 181 |
-
<out><xsl:for-each select="root/item">
|
| 182 |
-
<val><xsl:value-of select="."/></val>
|
| 183 |
-
</xsl:for-each></out>
|
| 184 |
-
</xsl:template>
|
| 185 |
-
</xsl:stylesheet>"""
|
| 186 |
-
xml_doc = etree.fromstring(xml)
|
| 187 |
-
xslt_doc = etree.fromstring(xslt_str)
|
| 188 |
-
transform = etree.XSLT(xslt_doc)
|
| 189 |
-
result = transform(xml_doc)
|
| 190 |
-
s = etree.tostring(result, encoding="unicode")
|
| 191 |
-
assert "<val>1</val>" in s
|
| 192 |
-
assert "<val>2</val>" in s
|
| 193 |
-
|
| 194 |
-
|
| 195 |
-
# ---------------------------------------------------------------------------
|
| 196 |
-
# 7. XML schema validation
|
| 197 |
-
# ---------------------------------------------------------------------------
|
| 198 |
-
def schema_validate():
|
| 199 |
-
from lxml import etree
|
| 200 |
-
schema_xml = b"""<xs:schema xmlns:xs="http://www.w3.org/2001/XMLSchema">
|
| 201 |
-
<xs:element name="root">
|
| 202 |
-
<xs:complexType>
|
| 203 |
-
<xs:sequence>
|
| 204 |
-
<xs:element name="name" type="xs:string"/>
|
| 205 |
-
<xs:element name="age" type="xs:decimal"/>
|
| 206 |
-
</xs:sequence>
|
| 207 |
-
</xs:complexType>
|
| 208 |
-
</xs:element>
|
| 209 |
-
</xs:schema>"""
|
| 210 |
-
schema_doc = etree.fromstring(schema_xml)
|
| 211 |
-
schema = etree.XMLSchema(schema_doc)
|
| 212 |
-
|
| 213 |
-
valid = etree.fromstring(b"<root><name>Alice</name><age>30</age></root>")
|
| 214 |
-
assert schema.validate(valid)
|
| 215 |
-
|
| 216 |
-
invalid = etree.fromstring(b"<root><name>Alice</name></root>")
|
| 217 |
-
assert not schema.validate(invalid)
|
| 218 |
-
|
| 219 |
-
|
| 220 |
-
# ---------------------------------------------------------------------------
|
| 221 |
-
# 8. c14n (canonicalization)
|
| 222 |
-
# ---------------------------------------------------------------------------
|
| 223 |
-
def c14n():
|
| 224 |
-
from lxml import etree
|
| 225 |
-
xml = b'<root attr="1" ><child>text</child></root>'
|
| 226 |
-
root = etree.fromstring(xml)
|
| 227 |
-
c = etree.tostring(root, method="c14n")
|
| 228 |
-
assert b'attr="1"' in c
|
| 229 |
-
assert b"<child>" in c
|
| 230 |
-
|
| 231 |
-
|
| 232 |
-
# ---------------------------------------------------------------------------
|
| 233 |
-
def main():
|
| 234 |
-
section("1. import / version")
|
| 235 |
-
test("import lxml.etree", import_lxml)
|
| 236 |
-
test("import lxml.objectify", import_objectify)
|
| 237 |
-
test("import lxml.html", import_html)
|
| 238 |
-
test("import lxml_html_clean", import_html_clean)
|
| 239 |
-
|
| 240 |
-
section("2. etree basics")
|
| 241 |
-
test("parse fromstring", parse_string)
|
| 242 |
-
test("parse file-like", parse_file)
|
| 243 |
-
test("tostring", tostring)
|
| 244 |
-
test("xpath", xpath)
|
| 245 |
-
test("namespaces", namespaces)
|
| 246 |
-
|
| 247 |
-
section("3. build / modify trees")
|
| 248 |
-
test("build tree", build_tree)
|
| 249 |
-
test("modify tree", modify_tree)
|
| 250 |
-
|
| 251 |
-
section("4. HTML parsing")
|
| 252 |
-
test("html parse", html_parse)
|
| 253 |
-
test("html tostring", html_tostring)
|
| 254 |
-
|
| 255 |
-
section("5. html_clean (bundled dep)")
|
| 256 |
-
test("clean HTML", html_clean)
|
| 257 |
-
|
| 258 |
-
section("6. XSLT")
|
| 259 |
-
test("xslt transform", xslt_transform)
|
| 260 |
-
|
| 261 |
-
section("7. XML schema validation")
|
| 262 |
-
test("schema validate", schema_validate)
|
| 263 |
-
|
| 264 |
-
section("8. c14n")
|
| 265 |
-
test("canonicalization", c14n)
|
| 266 |
-
|
| 267 |
-
print()
|
| 268 |
-
print("=" * 60)
|
| 269 |
-
print("SUMMARY")
|
| 270 |
-
print("=" * 60)
|
| 271 |
-
fails = 0
|
| 272 |
-
for name, status, why in RESULTS:
|
| 273 |
-
mark = " OK" if status == "PASS" else "FAIL"
|
| 274 |
-
print("%s %s" % (mark, name))
|
| 275 |
-
if why:
|
| 276 |
-
print(" -> %s" % why)
|
| 277 |
-
if status == "FAIL":
|
| 278 |
-
fails += 1
|
| 279 |
-
print()
|
| 280 |
-
passed = len(RESULTS) - fails
|
| 281 |
-
print("passed=%d failed=%d" % (passed, fails))
|
| 282 |
-
if fails:
|
| 283 |
-
print("RESULT: FAILED")
|
| 284 |
-
else:
|
| 285 |
-
print("RESULT: PASSED")
|
| 286 |
-
sys.exit(1 if fails else 0)
|
| 287 |
-
|
| 288 |
-
|
| 289 |
-
if __name__ == "__main__":
|
| 290 |
-
main()
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|