[GR-45794] The Python EE standalone includes LLVM EE.

PullRequest: graalpython/2813

Author: ansalond

ci.jsonnet

@@ -1 +1 @@
-{ "overlay": "e61df4b2dde96b3c9b488ab7cde6b011d719db79" }
+{ "overlay": "6aa4b65fe934daaad9ab3358e8955add43914296" }

graalpython/com.oracle.graal.python.test/src/tests/unittest_tags/test_codecs.txt

@@ -47,6 +47,7 @@
 *graalpython.lib-python.3.test.test_codecs.ExceptionChainingTest.test_non_str_arg_is_not_wrapped
 *graalpython.lib-python.3.test.test_codecs.ExceptionChainingTest.test_unflagged_non_text_codec_handling
 *graalpython.lib-python.3.test.test_codecs.IDNACodecTest.test_builtin_decode
+*graalpython.lib-python.3.test.test_codecs.IDNACodecTest.test_builtin_decode_length_limit
 *graalpython.lib-python.3.test.test_codecs.IDNACodecTest.test_builtin_encode
 *graalpython.lib-python.3.test.test_codecs.IDNACodecTest.test_errors
 *graalpython.lib-python.3.test.test_codecs.IDNACodecTest.test_incremental_decode

graalpython/lib-python/3/encodings/idna.py

@@ -39,23 +39,21 @@ def nameprep(label):
 
     # Check bidi
     RandAL = [stringprep.in_table_d1(x) for x in label]
-    for c in RandAL:
-        if c:
-            # There is a RandAL char in the string. Must perform further
-            # tests:
-            # 1) The characters in section 5.8 MUST be prohibited.
-            # This is table C.8, which was already checked
-            # 2) If a string contains any RandALCat character, the string
-            # MUST NOT contain any LCat character.
-            if any(stringprep.in_table_d2(x) for x in label):
-                raise UnicodeError("Violation of BIDI requirement 2")
-
-            # 3) If a string contains any RandALCat character, a
-            # RandALCat character MUST be the first character of the
-            # string, and a RandALCat character MUST be the last
-            # character of the string.
-            if not RandAL[0] or not RandAL[-1]:
-                raise UnicodeError("Violation of BIDI requirement 3")
+    if any(RandAL):
+        # There is a RandAL char in the string. Must perform further
+        # tests:
+        # 1) The characters in section 5.8 MUST be prohibited.
+        # This is table C.8, which was already checked
+        # 2) If a string contains any RandALCat character, the string
+        # MUST NOT contain any LCat character.
+        if any(stringprep.in_table_d2(x) for x in label):
+            raise UnicodeError("Violation of BIDI requirement 2")
+        # 3) If a string contains any RandALCat character, a
+        # RandALCat character MUST be the first character of the
+        # string, and a RandALCat character MUST be the last
+        # character of the string.
+        if not RandAL[0] or not RandAL[-1]:
+            raise UnicodeError("Violation of BIDI requirement 3")
 
     return label
 
@@ -103,6 +101,16 @@ def ToASCII(label):
     raise UnicodeError("label empty or too long")
 
 def ToUnicode(label):
+    if len(label) > 1024:
+        # Protection from https://github.com/python/cpython/issues/98433.
+        # https://datatracker.ietf.org/doc/html/rfc5894#section-6
+        # doesn't specify a label size limit prior to NAMEPREP. But having
+        # one makes practical sense.
+        # This leaves ample room for nameprep() to remove Nothing characters
+        # per https://www.rfc-editor.org/rfc/rfc3454#section-3.1 while still
+        # preventing us from wasting time decoding a big thing that'll just
+        # hit the actual <= 63 length limit in Step 6.
+        raise UnicodeError("label way too long")
     # Step 1: Check for ASCII
     if isinstance(label, bytes):
         pure_ascii = True

graalpython/lib-python/3/test/test_codecs.py

@@ -1534,6 +1534,12 @@ def test_builtin_encode(self):
         self.assertEqual("pyth\xf6n.org".encode("idna"), b"xn--pythn-mua.org")
         self.assertEqual("pyth\xf6n.org.".encode("idna"), b"xn--pythn-mua.org.")
 
+    def test_builtin_decode_length_limit(self):
+        with self.assertRaisesRegex(UnicodeError, "way too long"):
+            (b"xn--016c"+b"a"*1100).decode("idna")
+        with self.assertRaisesRegex(UnicodeError, "too long"):
+            (b"xn--016c"+b"a"*70).decode("idna")
+
     def test_stream(self):
         r = codecs.getreader("idna")(io.BytesIO(b"abc"))
         r.read(3)

mx.graalpython/mx_graalpython.py

@@ -1982,6 +1982,12 @@ def verify_ci(dest_suite, common_ci_dir="ci_common", args=None, ext=('.jsonnet',
 ))
 
 
+standalone_dependencies_common = {
+    'LLVM Runtime Core': ('lib/sulong', []),
+    'LLVM Runtime Native': ('lib/sulong', []),
+    'LLVM.org toolchain': ('lib/llvm-toolchain', []),
+}
+
 mx_sdk.register_graalvm_component(mx_sdk.GraalVmLanguage(
     suite=SUITE,
     name='GraalVM Python',
@@ -1999,12 +2005,15 @@ def verify_ci(dest_suite, common_ci_dir="ci_common", args=None, ext=('.jsonnet',
         'TRegex',
         'ICU4J',
     ],
-    standalone_dependencies={
-        'LLVM Runtime Core': ('lib/sulong', []),
-        'LLVM Runtime Native': ('lib/sulong', []),
-        'LLVM.org toolchain': ('lib/llvm-toolchain', []),
+    standalone_dependencies={**standalone_dependencies_common, **{
         'GraalVM Python license files': ('', []),
-    },
+    }},
+    standalone_dependencies_enterprise={**standalone_dependencies_common, **{
+        'LLVM Runtime Enterprise': ('lib/sulong', []),
+        'LLVM Runtime Native Enterprise': ('lib/sulong', []),
+        'GraalVM Python license files EE': ('', []),
+        'GraalVM enterprise license files': ('', ['LICENSE.txt', 'GRAALVM-README.md']),
+    }},
     truffle_jars=[
         'graalpython:GRAALPYTHON',
         'graalpython:BOUNCYCASTLE-PROVIDER',

mx.graalpython/suite.py

@@ -44,31 +44,31 @@
             },
             {
                 "name": "sdk",
-                "version": "67b2258fa2beec2152939fade4dbc6a7a146123b",
+                "version": "bf9b50cc88c919c0858c782a03d1badd6382a8d4",
                 "subdir": True,
                 "urls": [
                     {"url": "https://github.com/oracle/graal", "kind": "git"},
                 ]
             },
             {
                 "name": "tools",
-                "version": "67b2258fa2beec2152939fade4dbc6a7a146123b",
+                "version": "bf9b50cc88c919c0858c782a03d1badd6382a8d4",
                 "subdir": True,
                 "urls": [
                     {"url": "https://github.com/oracle/graal", "kind": "git"},
                 ],
             },
             {
                 "name": "sulong",
-                "version": "67b2258fa2beec2152939fade4dbc6a7a146123b",
+                "version": "bf9b50cc88c919c0858c782a03d1badd6382a8d4",
                 "subdir": True,
                 "urls": [
                     {"url": "https://github.com/oracle/graal", "kind": "git"},
                 ]
             },
             {
                 "name": "regex",
-                "version": "67b2258fa2beec2152939fade4dbc6a7a146123b",
+                "version": "bf9b50cc88c919c0858c782a03d1badd6382a8d4",
                 "subdir": True,
                 "urls": [
                     {"url": "https://github.com/oracle/graal", "kind": "git"},