ssrjson-benchmark 0.0.3__tar.gz → 0.0.5__tar.gz

{ssrjson_benchmark-0.0.3 → ssrjson_benchmark-0.0.5}/CMakeLists.txt

@@ -59,7 +59,7 @@ message("CMAKE_SYSTEM_PROCESSOR = ${CMAKE_SYSTEM_PROCESSOR}")
 
 # set ssrjson_benchmark src files
 set(SRC_FILES
-    src/benchmark.c
+    src/_ssrjson_benchmark.c
 )
 
 add_library(ssrjson_benchmark SHARED ${SRC_FILES})

{ssrjson_benchmark-0.0.3/src/ssrjson_benchmark.egg-info → ssrjson_benchmark-0.0.5}/PKG-INFO

@@ -1,30 +1,9 @@
 Metadata-Version: 2.4
 Name: ssrjson-benchmark
-Version: 0.0.3
+Version: 0.0.5
 Summary: benchmark of ssrJSON
 Author-email: Eritque Arcus <eritque-arcus@ikuyo.dev>, Antares <antares0982@gmail.com>
-License: MIT License
-        
-        Copyright (c) 2025 Eritque arcus
-        
-        Permission is hereby granted, free of charge, to any person obtaining a copy
-        of this software and associated documentation files (the "Software"), to deal
-        in the Software without restriction, including without limitation the rights
-        to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
-        copies of the Software, and to permit persons to whom the Software is
-        furnished to do so, subject to the following conditions:
-        
-        The above copyright notice and this permission notice shall 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.
-        
+License-Expression: MIT
 Project-URL: Homepage, https://github.com/Nambers/ssrJSON-benchmark
 Project-URL: Issues, https://github.com/Nambers/ssrJSON-benchmark/issues
 Project-URL: Repository, https://github.com/Nambers/ssrJSON-benchmark.git
@@ -35,7 +14,7 @@ Classifier: Intended Audience :: Developers
 Classifier: Topic :: System :: Benchmark
 Classifier: Programming Language :: Python :: 3
 Classifier: Operating System :: OS Independent
-Requires-Python: >=3.9
+Requires-Python: >=3.10
 Description-Content-Type: text/markdown
 License-File: LICENSE
 Requires-Dist: ssrjson
@@ -86,6 +65,6 @@ python -m ssrjson_benchmark
 ## Notes
 
 * This repository conducts benchmarking using json, [orjson](https://github.com/ijl/orjson), [ujson](https://github.com/ultrajson/ultrajson), and [ssrJSON](https://github.com/Antares0982/ssrjson). The `dumps` benchmark produces str objects, comparing three operations: `json.dumps`, `orjson.dumps` followed by decode, and `ssrjson.dumps`. The `dumps_to_bytes` benchmark produces bytes objects, comparing three functions: `json.dumps` followed by encode, `orjson.dumps`, and `ssrjson.dumps_to_bytes`.
-* When orjson handles non-ASCII strings, if the cache of the `PyUnicodeObject`’s UTF-8 representation does not exist, it invokes the `PyUnicode_AsUTF8AndSize` function to obtain the UTF-8 encoding. This function then caches the UTF-8 representation within the `PyUnicodeObject`. If the same `PyUnicodeObject` undergoes repeated encode-decode operations, subsequent calls after the initial one will execute more quickly due to this caching. However, in real-world production scenarios, it is uncommon to perform JSON encode-decode repeatedly on the exact same string object; even identical strings are unlikely to be the same object instance. To achieve benchmark results that better reflect practical use cases, we employ `ssrjson.run_unicode_accumulate_benchmark` and `benchmark_invalidate_dump_cache` functions, which ensure that new `PyUnicodeObject`s are different for each input every time. (ref: [orjson#586](https://github.com/ijl/orjson/issues/586))
+* When orjson handles non-ASCII strings, if the cache of the `PyUnicodeObject`’s UTF-8 representation does not exist, it invokes the `PyUnicode_AsUTF8AndSize` function to obtain the UTF-8 encoding. This function then caches the UTF-8 representation within the `PyUnicodeObject`. If the same `PyUnicodeObject` undergoes repeated encode-decode operations, subsequent calls after the initial one will execute more quickly due to this caching. However, in real-world production scenarios, it is uncommon to perform JSON encode-decode repeatedly on the exact same string object; even identical strings are unlikely to be the same object instance. To achieve benchmark results that better reflect practical use cases, we employ `ssrjson.run_unicode_accumulate_benchmark` and `_benchmark_invalidate_dump_cache` functions, which ensure that new `PyUnicodeObject`s are different for each input every time. (ref: [orjson#586](https://github.com/ijl/orjson/issues/586))
 * The performance of JSON encoding is primarily constrained by the speed of writing to the buffer, whereas decoding performance is mainly limited by the frequent invocation of CPython interfaces for object creation. During decoding, both ssrJSON and orjson employ short key caching to reduce the number of object creations, and this caching mechanism is global in both cases. As a result, decoding benchmark tests may not accurately reflect the conditions encountered in real-world production environments.
 * The files simple_object.json and simple_object_zh.json do not represent real-world data; they are solely used to compare the performance of the fast path. Therefore, the benchmark results should not be interpreted as indicative of actual performance.

{ssrjson_benchmark-0.0.3 → ssrjson_benchmark-0.0.5}/README.md

@@ -35,6 +35,6 @@ python -m ssrjson_benchmark
 ## Notes
 
 * This repository conducts benchmarking using json, [orjson](https://github.com/ijl/orjson), [ujson](https://github.com/ultrajson/ultrajson), and [ssrJSON](https://github.com/Antares0982/ssrjson). The `dumps` benchmark produces str objects, comparing three operations: `json.dumps`, `orjson.dumps` followed by decode, and `ssrjson.dumps`. The `dumps_to_bytes` benchmark produces bytes objects, comparing three functions: `json.dumps` followed by encode, `orjson.dumps`, and `ssrjson.dumps_to_bytes`.
-* When orjson handles non-ASCII strings, if the cache of the `PyUnicodeObject`’s UTF-8 representation does not exist, it invokes the `PyUnicode_AsUTF8AndSize` function to obtain the UTF-8 encoding. This function then caches the UTF-8 representation within the `PyUnicodeObject`. If the same `PyUnicodeObject` undergoes repeated encode-decode operations, subsequent calls after the initial one will execute more quickly due to this caching. However, in real-world production scenarios, it is uncommon to perform JSON encode-decode repeatedly on the exact same string object; even identical strings are unlikely to be the same object instance. To achieve benchmark results that better reflect practical use cases, we employ `ssrjson.run_unicode_accumulate_benchmark` and `benchmark_invalidate_dump_cache` functions, which ensure that new `PyUnicodeObject`s are different for each input every time. (ref: [orjson#586](https://github.com/ijl/orjson/issues/586))
+* When orjson handles non-ASCII strings, if the cache of the `PyUnicodeObject`’s UTF-8 representation does not exist, it invokes the `PyUnicode_AsUTF8AndSize` function to obtain the UTF-8 encoding. This function then caches the UTF-8 representation within the `PyUnicodeObject`. If the same `PyUnicodeObject` undergoes repeated encode-decode operations, subsequent calls after the initial one will execute more quickly due to this caching. However, in real-world production scenarios, it is uncommon to perform JSON encode-decode repeatedly on the exact same string object; even identical strings are unlikely to be the same object instance. To achieve benchmark results that better reflect practical use cases, we employ `ssrjson.run_unicode_accumulate_benchmark` and `_benchmark_invalidate_dump_cache` functions, which ensure that new `PyUnicodeObject`s are different for each input every time. (ref: [orjson#586](https://github.com/ijl/orjson/issues/586))
 * The performance of JSON encoding is primarily constrained by the speed of writing to the buffer, whereas decoding performance is mainly limited by the frequent invocation of CPython interfaces for object creation. During decoding, both ssrJSON and orjson employ short key caching to reduce the number of object creations, and this caching mechanism is global in both cases. As a result, decoding benchmark tests may not accurately reflect the conditions encountered in real-world production environments.
 * The files simple_object.json and simple_object_zh.json do not represent real-world data; they are solely used to compare the performance of the fast path. Therefore, the benchmark results should not be interpreted as indicative of actual performance.

{ssrjson_benchmark-0.0.3 → ssrjson_benchmark-0.0.5}/pyproject.toml

@@ -1,18 +1,18 @@
 [build-system]
-# requires = ["setuptools >= 77.0.3"]
-requires = ["setuptools >= 64"]
+requires = ["setuptools >= 77.0.3"]
+# requires = ["setuptools >= 64"]
 build-backend = "setuptools.build_meta"
 
 [project]
 name = "ssrjson-benchmark"
-version = "0.0.3"
+version = "0.0.5"
 authors = [
     { name = "Eritque Arcus", email = "eritque-arcus@ikuyo.dev" },
     { name = "Antares", email = "antares0982@gmail.com" },
 ]
 description = "benchmark of ssrJSON"
 readme = "README.md"
-requires-python = ">=3.9"
+requires-python = ">=3.10"
 keywords = ["ssrjson", "benchmark", "json"]
 classifiers = [
     "Development Status :: 5 - Production/Stable",
@@ -23,10 +23,10 @@ classifiers = [
     "Operating System :: OS Independent",
 ]
 # setuptools >= 77
-# license = "MIT"
-# license-files = ["LICENSE"]
+license = "MIT"
+license-files = ["LICENSE"]
 # setuptools < 77 but deprecated
-license = { file = "LICENSE" }
+# license = { file = "LICENSE" }
 dependencies = ["ssrjson", "orjson", "ujson", "matplotlib"]
 
 [project.optional-dependencies]

{ssrjson_benchmark-0.0.3 → ssrjson_benchmark-0.0.5}/setup.py

@@ -6,25 +6,38 @@ from setuptools import Extension, setup
 from setuptools.command.build_ext import build_ext
 
 
+def run_check(cmd):
+    try:
+        subprocess.run(cmd, check=True, capture_output=True, text=True)
+    except subprocess.CalledProcessError as e:
+        print(f"command failed: `{' '.join(cmd)}`")
+        if e.stdout:
+            print(f"stdout: {e.stdout}")
+        print(f"stderr: {e.stderr}")
+        raise
+    except Exception as e:
+        print(f"command failed: `{' '.join(cmd)}`")
+        print(f"error: {e}")
+        raise
+
 class CMakeBuild(build_ext):
     def run(self):
         build_dir = os.path.abspath("build")
         if not os.path.exists(build_dir):
             os.makedirs(build_dir)
-        cmake_cmd = [
+        run_check([
             "cmake",
             "-DCMAKE_BUILD_TYPE=Release",
             ".",
             "-B",
             "build",
-        ]
-        subprocess.check_call(cmake_cmd)
+        ])
 
         if os.name == "nt":
             build_cmd = ["cmake", "--build", "build", "--config", "Release"]
         else:
             build_cmd = ["cmake", "--build", "build"]
-        subprocess.check_call(build_cmd)
+        run_check(build_cmd)
 
         if os.name == "nt":
             built_filename = "Release/_ssrjson_benchmark.dll"
@@ -51,7 +64,7 @@ setup(
     ext_modules=[
         Extension(
             "_ssrjson_benchmark",
-            sources=["src/benchmark.c"],
+            sources=["src/_ssrjson_benchmark.c"],
             language="c",
         )
     ],
@@ -62,18 +75,6 @@ setup(
         "ssrjson_benchmark._files": ["*.json"],
     },
     include_package_data=True,
-    # install_requires=[
-    #     "ssrjson",
-    #     "orjson",
-    #     "matplotlib",
-    # ],
-    # extras_require={
-    #     "all": [
-    #         "svglib",
-    #         "reportlab",
-    #         "py-cpuinfo",
-    #     ],
-    # },
     cmdclass={
         "build_ext": CMakeBuild,
     },

ssrjson_benchmark-0.0.3/src/benchmark.c → ssrjson_benchmark-0.0.5/src/_ssrjson_benchmark.c

@@ -76,15 +76,15 @@ usize perf_counter(void) {
 
 #endif
 
-typedef struct PyUnicodeNewCallArg {
+typedef struct PyUnicodeCopyInfo {
     Py_ssize_t size;
     int kind;
     Py_UCS4 max_char;
     bool valid;
-} PyUnicodeNewCallArg;
+} PyUnicodeCopyInfo;
 
-PyObject *_copy_unicode(PyObject *unicode, PyUnicodeNewCallArg *call_arg) {
-    if (!call_arg->valid) {
+PyObject *_copy_unicode(PyObject *unicode, PyUnicodeCopyInfo *unicode_copy_info) {
+    if (!unicode_copy_info->valid) {
         // create copy of unicode object.
         int kind = PyUnicode_KIND(unicode);
         Py_UCS4 max_char;
@@ -98,15 +98,16 @@ PyObject *_copy_unicode(PyObject *unicode, PyUnicodeNewCallArg *call_arg) {
             max_char = 0xff;
         }
         //
-        call_arg->size = PyUnicode_GET_LENGTH(unicode);
-        call_arg->kind = kind;
-        call_arg->max_char = max_char;
-        call_arg->valid = true;
+        unicode_copy_info->size = PyUnicode_GET_LENGTH(unicode);
+        unicode_copy_info->kind = kind;
+        unicode_copy_info->max_char = max_char;
+        unicode_copy_info->valid = true;
     }
 
-    PyObject *unicode_copy = PyUnicode_New(call_arg->size, call_arg->max_char);
+    PyObject *unicode_copy = PyUnicode_New(unicode_copy_info->size, unicode_copy_info->max_char);
+    if (!unicode_copy) return NULL;
     memcpy(PyUnicode_DATA(unicode_copy), PyUnicode_DATA(unicode),
-           call_arg->size * call_arg->kind);
+           unicode_copy_info->size * unicode_copy_info->kind);
     return unicode_copy;
 }
 
@@ -129,61 +130,33 @@ PyObject *_parse_additional_args(PyObject *additional_args) {
     return new_args;
 }
 
-PyObject *run_unicode_accumulate_benchmark(PyObject *self, PyObject *args,
-                                           PyObject *kwargs) {
-    PyObject *callable;
-    usize repeat;
-    PyObject *unicode;
-    PyObject *additional_args = NULL;
-    static const char *kwlist[] = {"func", "repeat", "unicode", "args", NULL};
-    if (!PyArg_ParseTupleAndKeywords(args, kwargs, "OKO|O", (char **)kwlist,
-                                     &callable, &repeat, &unicode,
-                                     &additional_args)) {
+PyObject *copy_unicode_list_invalidate_cache(PyObject *self, PyObject *args, PyObject *kwargs) {
+    static const char *kwlist[] = {"s", "size", NULL};
+    PyObject *s;
+    usize size;
+    if (!PyArg_ParseTupleAndKeywords(args, kwargs, "OK", (char **)kwlist, &s, &size)) {
         PyErr_SetString(PyExc_TypeError, "Invalid argument");
-        goto fail;
+        return NULL;
     }
-    if (!PyCallable_Check(callable)) {
-        PyErr_SetString(PyExc_TypeError, "First argument must be callable");
-        goto fail;
+    if (!PyUnicode_CheckExact(s)) {
+        PyErr_SetString(PyExc_TypeError, "First argument must be str, not other types or subclass of str");
+        return NULL;
     }
-    if (!PyUnicode_Check(unicode)) {
-        PyErr_SetString(PyExc_TypeError, "Third argument must be unicode");
-        goto fail;
+    PyObject *ret = PyList_New(size);
+    if (!ret) {
+        return NULL;
     }
-    PyUnicodeNewCallArg call_arg;
-    call_arg.valid = false;
-    usize total = 0;
-    for (usize i = 0; i < repeat; i++) {
-        // create copy of unicode object.
-        PyObject *new_args = _parse_additional_args(additional_args);
-        if (!new_args)
-            goto fail;
-        PyObject *unicode_copy = _copy_unicode(unicode, &call_arg);
-        if (!unicode_copy) {
-            Py_DECREF(new_args);
-            goto fail;
-        }
-        PyTuple_SET_ITEM(new_args, 0, unicode_copy);
-        usize start = perf_counter();
-        PyObject *result = PyObject_Call(callable, new_args, NULL);
-        usize end = perf_counter();
-        assert(unicode_copy->ob_refcnt == 1);
-        Py_DECREF(new_args);
-        unicode_copy = NULL;
-        new_args = NULL;
-        if (unlikely(!result)) {
-            if (!PyErr_Occurred()) {
-                PyErr_SetString(PyExc_RuntimeError, "Failed to call callable");
-            }
-            goto fail;
-        } else {
-            Py_DECREF(result);
+    PyUnicodeCopyInfo unicode_copy_info;
+    unicode_copy_info.valid = false;
+    for (usize i = 0; i < size; i++) {
+        PyObject *s_copy = _copy_unicode(s, &unicode_copy_info);
+        if (!s_copy) {
+            Py_DECREF(ret);
+            return NULL;
         }
-        total += end - start;
+        PyList_SET_ITEM(ret, i, s_copy);
     }
-    return PyLong_FromUnsignedLongLong(total);
-fail:;
-    return NULL;
+    return ret;
 }
 
 PyObject *run_object_accumulate_benchmark(PyObject *self, PyObject *args,
@@ -197,6 +170,7 @@ PyObject *run_object_accumulate_benchmark(PyObject *self, PyObject *args,
         PyErr_SetString(PyExc_TypeError, "Invalid argument");
         goto fail;
     }
+    //
     if (!PyCallable_Check(callable)) {
         PyErr_SetString(PyExc_TypeError, "First argument must be callable");
         goto fail;
@@ -205,6 +179,7 @@ PyObject *run_object_accumulate_benchmark(PyObject *self, PyObject *args,
         PyErr_SetString(PyExc_TypeError, "Third argument must be tuple");
         goto fail;
     }
+    //
     usize total = 0;
     for (usize i = 0; i < repeat; i++) {
         usize start = perf_counter();
@@ -308,7 +283,7 @@ fail:;
 }
 
 static PyMethodDef ssrjson_benchmark_methods[] = {
-        {"run_unicode_accumulate_benchmark", (PyCFunction)run_unicode_accumulate_benchmark, METH_VARARGS | METH_KEYWORDS, "Benchmark."},
+        {"copy_unicode_list_invalidate_cache", (PyCFunction)copy_unicode_list_invalidate_cache, METH_VARARGS | METH_KEYWORDS, "Copy unicode list invalidate cache."},
         {"run_object_accumulate_benchmark", (PyCFunction)run_object_accumulate_benchmark, METH_VARARGS | METH_KEYWORDS, "Benchmark."},
         {"run_object_benchmark", (PyCFunction)run_object_benchmark, METH_VARARGS | METH_KEYWORDS, "Benchmark."},
         {"inspect_pyunicode", (PyCFunction)inspect_pyunicode, METH_VARARGS | METH_KEYWORDS, "Inspect PyUnicode."},
@@ -317,7 +292,7 @@ static PyMethodDef ssrjson_benchmark_methods[] = {
 
 static struct PyModuleDef moduledef = {
         PyModuleDef_HEAD_INIT,
-        "_ssrjson_benchmark",       /* m_name */
+        "_ssrjson_benchmark",      /* m_name */
         0,                         /* m_doc */
         0,                         /* m_size */
         ssrjson_benchmark_methods, /* m_methods */

ssrjson_benchmark-0.0.5/src/ssrjson_benchmark/__init__.py

@@ -0,0 +1,19 @@
+from .benchmark_impl import (
+    generate_report_pdf,
+    generate_report_markdown,
+    run_benchmark,
+)
+
+try:
+    from importlib.metadata import version
+
+    __version__ = version("ssrjson-benchmark")
+except Exception:
+    __version__ = "0.0.0"
+
+__all__ = [
+    "run_benchmark",
+    "generate_report_markdown",
+    "generate_report_pdf",
+    "__version__",
+]

ssrjson_benchmark-0.0.5/src/ssrjson_benchmark/__main__.py

@@ -0,0 +1,97 @@
+def main():
+    import argparse
+    import json
+    import os
+    import pathlib
+    import sys
+
+    from .benchmark_impl import (
+        generate_report_markdown,
+        generate_report_pdf,
+        parse_file_result,
+        run_benchmark,
+    )
+
+    parser = argparse.ArgumentParser()
+
+    parser.add_argument(
+        "-f", "--file", help="record JSON file", required=False, default=None
+    )
+    parser.add_argument(
+        "-d",
+        "--in-dir",
+        help="Benchmark JSON files directory",
+        required=False,
+    )
+    parser.add_argument(
+        "-m",
+        "--markdown",
+        help="Generate Markdown report",
+        required=False,
+        action="store_true",
+    )
+    parser.add_argument(
+        "--no-pdf",
+        help="Don't generate PDF report",
+        required=False,
+        action="store_true",
+    )
+    parser.add_argument(
+        "--process-gigabytes",
+        help="Total process gigabytes per test, default 0.1 (float)",
+        required=False,
+        default=0.1,
+        type=float,
+    )
+    parser.add_argument(
+        "--bin-process-megabytes",
+        help="Maximum bytes to process per read for binary formats, default 32 (int)",
+        required=False,
+        default=32,
+        type=int,
+    )
+    parser.add_argument(
+        "--out-dir",
+        help="Output directory for reports",
+        required=False,
+        default=os.getcwd(),
+    )
+    args = parser.parse_args()
+    if args.file and args.no_pdf and not args.markdown:
+        print("Nothing to do.")
+        sys.exit(0)
+
+    _benchmark_files_dir = args.in_dir
+    if not _benchmark_files_dir:
+        _benchmark_files_dir = os.path.join(
+            os.path.dirname(os.path.abspath(__file__)), "_files"
+        )
+    benchmark_files_dir = sorted(pathlib.Path(_benchmark_files_dir).glob("*.json"))
+    if not benchmark_files_dir:
+        print(f"No benchmark file found using given path: {_benchmark_files_dir}")
+        sys.exit(0)
+
+    if args.file:
+        with open(args.file, "rb") as f:
+            result_ = json.load(f)
+        result = parse_file_result(result_)
+        file = args.file.split("/")[-1]
+    else:
+        process_bytes = int(args.process_gigabytes * 1024 * 1024 * 1024)
+        bin_process_bytes = args.bin_process_megabytes * 1024 * 1024
+        if process_bytes <= 0 or bin_process_bytes <= 0:
+            print("process-gigabytes and bin-process-megabytes must be positive.")
+            sys.exit(1)
+        result, file = run_benchmark(
+            benchmark_files_dir, process_bytes, bin_process_bytes
+        )
+        file = file.split("/")[-1]
+
+    if args.markdown:
+        generate_report_markdown(result, file, args.out_dir)
+    if not args.no_pdf:
+        generate_report_pdf(result, file, args.out_dir)
+
+
+if __name__ == "__main__":
+    main()