pymem

bench/run_mem

@@ -0,0 +1,41 @@
+#!/usr/bin/env python3
+# SPDX-License-Identifier: (Apache-2.0 OR MIT)
+
+import sys
+import lzma
+import gc
+
+import psutil
+
+filename = sys.argv[1]
+
+with lzma.open(filename, "r") as fileh:
+    file_utf8 = fileh.read()
+
+proc = psutil.Process()
+
+lib_name = sys.argv[2]
+if lib_name == "json":
+    from json import dumps, loads
+elif lib_name == "orjson":
+    from orjson import dumps, loads
+elif lib_name == "rapidjson":
+    from rapidjson import dumps, loads
+elif lib_name == "simplejson":
+    from simplejson import dumps, loads
+elif lib_name == "ujson":
+    from ujson import dumps, loads
+else:
+    raise NotImplementedError
+
+gc.collect()
+
+mem_before = proc.memory_info().rss
+
+val = loads(file_utf8)
+
+mem_after = proc.memory_info().rss
+
+mem_diff = mem_after - mem_before
+
+print(f"{mem_before},{mem_diff}")

pymem

@@ -0,0 +1,37 @@
+#!/usr/bin/env python3
+# SPDX-License-Identifier: (Apache-2.0 OR MIT)
+
+import io
+import subprocess
+
+from tabulate import tabulate
+
+buf = io.StringIO()
+
+headers = ("Library", "import, read() RSS (MiB)", "loads() increase in RSS (MiB)")
+
+LIBRARIES = ("orjson", "ujson", "rapidjson", "json", "simplejson")
+
+FIXTURES = ("canada.json", "citm_catalog.json", "github.json", "twitter.json")
+
+for fixture in sorted(FIXTURES, reverse=True):
+    table = []
+    buf.write("\n" + "#### " + fixture + "\n\n")
+    for lib_name in LIBRARIES:
+        proc = subprocess.Popen(
+            ("bench/run_mem", f"data/{fixture}.xz", lib_name), stdout=subprocess.PIPE
+        )
+        output = proc.stdout.readline().decode("utf-8").split(",")
+        mem_base = int(output[0]) / 1024 / 1024
+        mem_diff = int(output[1]) / 1024 / 1024
+        table.append((lib_name, f"{mem_base:,.1f}", f"{mem_diff:,.1f}"))
+    buf.write(tabulate(table, headers, tablefmt="grid") + "\n")
+
+print(
+    buf.getvalue()
+    .replace("-", "")
+    .replace("=", "-")
+    .replace("+", "|")
+    .replace("||||", "")
+    .replace("\n\n", "\n")
+)