tests/perf_bench: Add string/qstr/map tests.

These tests are designed to measure changes in performance relating to:
 - string interning / searching for existing strings
 - map lookup
 - string operations
 - string hashing

This work was funded through GitHub Sponsors.

Signed-off-by: Jim Mussared <jim.mussared@gmail.com>

tests/perf_bench/bm_wordcount.py

@@ -0,0 +1,45 @@
+# This tests using string as dictionary keys when they are not qstrs
+
+ZEN = "the zen of python beautiful is better than ugly explicit is better than implicit simple is better than complex complex is better than complicated flat is better than nested sparse is better than dense readability counts special cases arent special enough to break the rules although practicality beats purity errors should never pass silently unless explicitly silenced in the face of ambiguity refuse the temptation to guess there should be one and preferably only one obvious way to do it although that way may not be obvious at first unless youre dutch now is better than never although never is often better than right now if the implementation is hard to explain its a bad idea if the implementation is easy to explain it may be a good idea namespaces are one honking great idea  lets do more of those"
+
+
+def test(niter):
+    words = ZEN.split(" ")
+    for _ in range(niter):
+        counts = {}
+        for _ in range(niter):
+            for word in words:
+                counts[word] = counts.get(word, 0) + 1
+
+    return (
+        counts["python"],
+        counts["is"],
+        counts["than"],
+    )
+
+
+###########################################################################
+# Benchmark interface
+
+bm_params = {
+    (32, 10): (2,),
+    (50, 10): (4,),
+    (100, 10): (8,),
+    (500, 10): (40,),
+    (1000, 10): (80,),
+    (5000, 10): (400,),
+}
+
+
+def bm_setup(params):
+    (niter,) = params
+    state = None
+
+    def run():
+        nonlocal state
+        state = test(niter)
+
+    def result():
+        return niter, state
+
+    return run, result

tests/perf_bench/core_locals.py

@@ -0,0 +1,191 @@
+# This tests the performance of an instance class locals dict (importantly, that has all keys as qstrs)
+
+# These are all shorter than 10 characters, so will be interned by the parser.
+ZEN = [
+    "the",
+    "zen",
+    "of",
+    "python",
+    "beautiful",
+    "is",
+    "better",
+    "than",
+    "ugly",
+    "explicit",
+    "is",
+    "better",
+    "than",
+    "implicit",
+    "simple",
+    "is",
+    "better",
+    "than",
+    "complex",
+    "complex",
+    "is",
+    "better",
+    "than",
+    "complicate",
+    "flat",
+    "is",
+    "better",
+    "than",
+    "nested",
+    "sparse",
+    "is",
+    "better",
+    "than",
+    "dense",
+    "readabilit",
+    "counts",
+    "special",
+    "cases",
+    "arent",
+    "special",
+    "enough",
+    "to",
+    "break",
+    "the",
+    "rules",
+    "although",
+    "practicali",
+    "beats",
+    "purity",
+    "errors",
+    "should",
+    "never",
+    "pass",
+    "silently",
+    "unless",
+    "explicitly",
+    "silenced",
+    "in",
+    "the",
+    "face",
+    "of",
+    "ambiguity",
+    "refuse",
+    "the",
+    "temptation",
+    "to",
+    "guess",
+    "there",
+    "should",
+    "be",
+    "one",
+    "and",
+    "preferably",
+    "only",
+    "one",
+    "obvious",
+    "way",
+    "to",
+    "do",
+    "it",
+    "although",
+    "that",
+    "way",
+    "may",
+    "not",
+    "be",
+    "obvious",
+    "at",
+    "first",
+    "unless",
+    "youre",
+    "dutch",
+    "now",
+    "is",
+    "better",
+    "than",
+    "never",
+    "although",
+    "never",
+    "is",
+    "often",
+    "better",
+    "than",
+    "right",
+    "now",
+    "if",
+    "the",
+    "implementa",
+    "is",
+    "hard",
+    "to",
+    "explain",
+    "its",
+    "a",
+    "bad",
+    "idea",
+    "if",
+    "the",
+    "implementa",
+    "is",
+    "easy",
+    "to",
+    "explain",
+    "it",
+    "may",
+    "be",
+    "a",
+    "good",
+    "idea",
+    "namespaces",
+    "are",
+    "one",
+    "honking",
+    "great",
+    "idea",
+    "",
+    "lets",
+    "do",
+    "more",
+    "of",
+    "those",
+]
+
+
+class A:
+    pass
+
+
+def test(niter):
+    for _ in range(niter):
+        a = A()
+        for _ in range(niter):
+            for word in ZEN:
+                setattr(a, word, getattr(a, word, 0) + 1)
+
+    return (
+        getattr(a, "python"),
+        getattr(a, "is"),
+        getattr(a, "than"),
+    )
+
+
+###########################################################################
+# Benchmark interface
+
+bm_params = {
+    (32, 10): (2,),
+    (50, 10): (4,),
+    (100, 10): (8,),
+    (500, 10): (40,),
+    (1000, 10): (80,),
+    (5000, 10): (400,),
+}
+
+
+def bm_setup(params):
+    (niter,) = params
+    state = None
+
+    def run():
+        nonlocal state
+        state = test(niter)
+
+    def result():
+        return niter, state
+
+    return run, result

tests/perf_bench/core_str.py

@@ -0,0 +1,65 @@
+# This tests string handling operations
+
+ZEN = """
+The Zen of Python
+Beautiful is better than ugly.
+Explicit is better than implicit.
+Simple is better than complex.
+Complex is better than complicated.
+Flat is better than nested.
+Sparse is better than dense.
+Readability counts.
+Special cases aren't special enough to break the rules.
+Although practicality beats purity.
+Errors should never pass silently.
+Unless explicitly silenced.
+In the face of ambiguity, refuse the temptation to guess.
+There should be one-- and preferably only one --obvious way to do it.
+Although that way may not be obvious at first unless you're Dutch.
+Now is better than never.
+Although never is often better than *right* now.
+If the implementation is hard to explain, it's a bad idea.
+If the implementation is easy to explain, it may be a good idea.
+Namespaces are one honking great idea -- let's do more of those!
+"""
+
+
+def test(niter):
+    counts = {}
+    for _ in range(niter):
+        x = ZEN.replace("\n", " ").split(" ")
+        y = " ".join(x)
+        for i in range(50):
+            a = ZEN[i : i * 2]
+            b = a + "hello world"
+        for c in ZEN:
+            i = ord(c)
+            c = chr(i)
+    return (x[0], a)
+
+
+###########################################################################
+# Benchmark interface
+
+bm_params = {
+    (32, 10): (2,),
+    (50, 10): (3,),
+    (100, 10): (6,),
+    (500, 10): (30,),
+    (1000, 10): (60,),
+    (5000, 10): (300,),
+}
+
+
+def bm_setup(params):
+    (niter,) = params
+    state = None
+
+    def run():
+        nonlocal state
+        state = test(niter)
+
+    def result():
+        return niter, state
+
+    return run, result