[GR-45174] Improve performance on the GraalPython-TRegex interface.

PullRequest: graalpython/2704

Author: jirkamarsik

graalpython/com.oracle.graal.python.benchmarks/python/micro/regexp-char-class-match.py

@@ -0,0 +1,53 @@
+# Copyright (c) 2023, 2023, Oracle and/or its affiliates. All rights reserved.
+# DO NOT ALTER OR REMOVE COPYRIGHT NOTICES OR THIS FILE HEADER.
+#
+# The Universal Permissive License (UPL), Version 1.0
+#
+# Subject to the condition set forth below, permission is hereby granted to any
+# person obtaining a copy of this software, associated documentation and/or
+# data (collectively the "Software"), free of charge and under any and all
+# copyright rights in the Software, and any and all patent rights owned or
+# freely licensable by each licensor hereunder covering either (i) the
+# unmodified Software as contributed to or provided by such licensor, or (ii)
+# the Larger Works (as defined below), to deal in both
+#
+# (a) the Software, and
+#
+# (b) any piece of software and/or hardware listed in the lrgrwrks.txt file if
+# one is included with the Software each a "Larger Work" to which the Software
+# is contributed by such licensors),
+#
+# without restriction, including without limitation the rights to copy, create
+# derivative works of, display, perform, and distribute the Software and make,
+# use, sell, offer for sale, import, export, have made, and have sold the
+# Software and the Larger Work(s), and to sublicense the foregoing rights on
+# either these or other terms.
+#
+# This license is subject to the following condition:
+#
+# The above copyright notice and either this complete permission notice or at a
+# minimum a reference to the UPL must be included in all copies or substantial
+# portions of the Software.
+#
+# THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+# IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+# FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+# AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+# LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+# OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+# SOFTWARE.
+
+import re
+
+subject = 'abc'
+
+char_class_match = re.compile('[a-z]')
+
+def search_char_class_match(runs):
+    for i in range(runs):
+        match = char_class_match.search(subject) is not None
+    return match
+
+def __benchmark__(runs=100000000):
+    match = search_char_class_match(runs)
+    print("match", match)

graalpython/com.oracle.graal.python.benchmarks/python/micro/regexp-char-class-no-match.py

@@ -0,0 +1,53 @@
+# Copyright (c) 2023, 2023, Oracle and/or its affiliates. All rights reserved.
+# DO NOT ALTER OR REMOVE COPYRIGHT NOTICES OR THIS FILE HEADER.
+#
+# The Universal Permissive License (UPL), Version 1.0
+#
+# Subject to the condition set forth below, permission is hereby granted to any
+# person obtaining a copy of this software, associated documentation and/or
+# data (collectively the "Software"), free of charge and under any and all
+# copyright rights in the Software, and any and all patent rights owned or
+# freely licensable by each licensor hereunder covering either (i) the
+# unmodified Software as contributed to or provided by such licensor, or (ii)
+# the Larger Works (as defined below), to deal in both
+#
+# (a) the Software, and
+#
+# (b) any piece of software and/or hardware listed in the lrgrwrks.txt file if
+# one is included with the Software each a "Larger Work" to which the Software
+# is contributed by such licensors),
+#
+# without restriction, including without limitation the rights to copy, create
+# derivative works of, display, perform, and distribute the Software and make,
+# use, sell, offer for sale, import, export, have made, and have sold the
+# Software and the Larger Work(s), and to sublicense the foregoing rights on
+# either these or other terms.
+#
+# This license is subject to the following condition:
+#
+# The above copyright notice and either this complete permission notice or at a
+# minimum a reference to the UPL must be included in all copies or substantial
+# portions of the Software.
+#
+# THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+# IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+# FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+# AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+# LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+# OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+# SOFTWARE.
+
+import re
+
+subject = 'abc'
+
+char_class_no_match = re.compile('[0-9]')
+
+def search_char_class_no_match(runs):
+    for i in range(runs):
+        match = char_class_no_match.search(subject) is not None
+    return match
+
+def __benchmark__(runs=100000000):
+    match = search_char_class_no_match(runs)
+    print("match", match)

graalpython/com.oracle.graal.python.benchmarks/python/micro/regexp-literal-match.py

@@ -0,0 +1,53 @@
+# Copyright (c) 2023, 2023, Oracle and/or its affiliates. All rights reserved.
+# DO NOT ALTER OR REMOVE COPYRIGHT NOTICES OR THIS FILE HEADER.
+#
+# The Universal Permissive License (UPL), Version 1.0
+#
+# Subject to the condition set forth below, permission is hereby granted to any
+# person obtaining a copy of this software, associated documentation and/or
+# data (collectively the "Software"), free of charge and under any and all
+# copyright rights in the Software, and any and all patent rights owned or
+# freely licensable by each licensor hereunder covering either (i) the
+# unmodified Software as contributed to or provided by such licensor, or (ii)
+# the Larger Works (as defined below), to deal in both
+#
+# (a) the Software, and
+#
+# (b) any piece of software and/or hardware listed in the lrgrwrks.txt file if
+# one is included with the Software each a "Larger Work" to which the Software
+# is contributed by such licensors),
+#
+# without restriction, including without limitation the rights to copy, create
+# derivative works of, display, perform, and distribute the Software and make,
+# use, sell, offer for sale, import, export, have made, and have sold the
+# Software and the Larger Work(s), and to sublicense the foregoing rights on
+# either these or other terms.
+#
+# This license is subject to the following condition:
+#
+# The above copyright notice and either this complete permission notice or at a
+# minimum a reference to the UPL must be included in all copies or substantial
+# portions of the Software.
+#
+# THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+# IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+# FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+# AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+# LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+# OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+# SOFTWARE.
+
+import re
+
+subject = 'abc'
+
+literal_match = re.compile('abc')
+
+def search_literal_match(runs):
+    for i in range(runs):
+        match = literal_match.search(subject) is not None
+    return match
+
+def __benchmark__(runs=100000000):
+    match = search_literal_match(runs)
+    print("match", match)

graalpython/com.oracle.graal.python.benchmarks/python/micro/regexp-literal-no-match.py

@@ -0,0 +1,53 @@
+# Copyright (c) 2023, 2023, Oracle and/or its affiliates. All rights reserved.
+# DO NOT ALTER OR REMOVE COPYRIGHT NOTICES OR THIS FILE HEADER.
+#
+# The Universal Permissive License (UPL), Version 1.0
+#
+# Subject to the condition set forth below, permission is hereby granted to any
+# person obtaining a copy of this software, associated documentation and/or
+# data (collectively the "Software"), free of charge and under any and all
+# copyright rights in the Software, and any and all patent rights owned or
+# freely licensable by each licensor hereunder covering either (i) the
+# unmodified Software as contributed to or provided by such licensor, or (ii)
+# the Larger Works (as defined below), to deal in both
+#
+# (a) the Software, and
+#
+# (b) any piece of software and/or hardware listed in the lrgrwrks.txt file if
+# one is included with the Software each a "Larger Work" to which the Software
+# is contributed by such licensors),
+#
+# without restriction, including without limitation the rights to copy, create
+# derivative works of, display, perform, and distribute the Software and make,
+# use, sell, offer for sale, import, export, have made, and have sold the
+# Software and the Larger Work(s), and to sublicense the foregoing rights on
+# either these or other terms.
+#
+# This license is subject to the following condition:
+#
+# The above copyright notice and either this complete permission notice or at a
+# minimum a reference to the UPL must be included in all copies or substantial
+# portions of the Software.
+#
+# THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+# IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+# FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+# AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+# LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+# OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+# SOFTWARE.
+
+import re
+
+subject = 'abc'
+
+literal_no_match = re.compile('def')
+
+def search_literal_no_match(runs):
+    for i in range(runs):
+        match = literal_no_match.search(subject) is not None
+    return match
+
+def __benchmark__(runs=100000000):
+    match = search_literal_no_match(runs)
+    print("match", match)

graalpython/com.oracle.graal.python.benchmarks/python/micro/regexp-split.py

@@ -0,0 +1,82 @@
+# Copyright (c) 2023, 2023, Oracle and/or its affiliates. All rights reserved.
+# DO NOT ALTER OR REMOVE COPYRIGHT NOTICES OR THIS FILE HEADER.
+#
+# The Universal Permissive License (UPL), Version 1.0
+#
+# Subject to the condition set forth below, permission is hereby granted to any
+# person obtaining a copy of this software, associated documentation and/or
+# data (collectively the "Software"), free of charge and under any and all
+# copyright rights in the Software, and any and all patent rights owned or
+# freely licensable by each licensor hereunder covering either (i) the
+# unmodified Software as contributed to or provided by such licensor, or (ii)
+# the Larger Works (as defined below), to deal in both
+#
+# (a) the Software, and
+#
+# (b) any piece of software and/or hardware listed in the lrgrwrks.txt file if
+# one is included with the Software each a "Larger Work" to which the Software
+# is contributed by such licensors),
+#
+# without restriction, including without limitation the rights to copy, create
+# derivative works of, display, perform, and distribute the Software and make,
+# use, sell, offer for sale, import, export, have made, and have sold the
+# Software and the Larger Work(s), and to sublicense the foregoing rights on
+# either these or other terms.
+#
+# This license is subject to the following condition:
+#
+# The above copyright notice and either this complete permission notice or at a
+# minimum a reference to the UPL must be included in all copies or substantial
+# portions of the Software.
+#
+# THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+# IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+# FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+# AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+# LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+# OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+# SOFTWARE.
+
+import re
+
+subject = 'abc'
+
+literal_no_match = re.compile('def')
+literal_match = re.compile('abc')
+universal_match = re.compile('.')
+char_class_match = re.compile('[a-z]')
+char_class_no_match = re.compile('[0-9]')
+
+def search_literal_no_match(runs):
+    for i in range(runs):
+        match = literal_no_match.search(subject) is not None
+    return match
+
+def search_literal_match(runs):
+    for i in range(runs):
+        match = literal_match.search(subject) is not None
+    return match
+
+def search_universal_match(runs):
+    for i in range(runs):
+        match = universal_match.search(subject) is not None
+    return match
+
+def search_char_class_match(runs):
+    for i in range(runs):
+        match = char_class_match.search(subject) is not None
+    return match
+
+def search_char_class_no_match(runs):
+    for i in range(runs):
+        match = char_class_no_match.search(subject) is not None
+    return match
+
+def search_all(runs):
+    for fn in [search_literal_no_match, search_literal_match, search_universal_match, search_char_class_match, search_char_class_no_match]:
+        match = fn(runs)
+    return match
+
+def __benchmark__(runs=20000000):
+    match = search_all(runs)
+    print("match", match)

graalpython/com.oracle.graal.python.benchmarks/python/micro/regexp-universal-match.py

@@ -0,0 +1,53 @@
+# Copyright (c) 2023, 2023, Oracle and/or its affiliates. All rights reserved.
+# DO NOT ALTER OR REMOVE COPYRIGHT NOTICES OR THIS FILE HEADER.
+#
+# The Universal Permissive License (UPL), Version 1.0
+#
+# Subject to the condition set forth below, permission is hereby granted to any
+# person obtaining a copy of this software, associated documentation and/or
+# data (collectively the "Software"), free of charge and under any and all
+# copyright rights in the Software, and any and all patent rights owned or
+# freely licensable by each licensor hereunder covering either (i) the
+# unmodified Software as contributed to or provided by such licensor, or (ii)
+# the Larger Works (as defined below), to deal in both
+#
+# (a) the Software, and
+#
+# (b) any piece of software and/or hardware listed in the lrgrwrks.txt file if
+# one is included with the Software each a "Larger Work" to which the Software
+# is contributed by such licensors),
+#
+# without restriction, including without limitation the rights to copy, create
+# derivative works of, display, perform, and distribute the Software and make,
+# use, sell, offer for sale, import, export, have made, and have sold the
+# Software and the Larger Work(s), and to sublicense the foregoing rights on
+# either these or other terms.
+#
+# This license is subject to the following condition:
+#
+# The above copyright notice and either this complete permission notice or at a
+# minimum a reference to the UPL must be included in all copies or substantial
+# portions of the Software.
+#
+# THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+# IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+# FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+# AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+# LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+# OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+# SOFTWARE.
+
+import re
+
+subject = 'abc'
+
+universal_match = re.compile('.')
+
+def search_universal_match(runs):
+    for i in range(runs):
+        match = universal_match.search(subject) is not None
+    return match
+
+def __benchmark__(runs=100000000):
+    match = search_universal_match(runs)
+    print("match", match)