Add simd libraries

json_benchmarks/core.py

@@ -72,9 +72,9 @@ def main(cmdline=True, **kwargs):
         print(f"result_fpath = {result_fpath!r}")
         result_fpaths = [result_fpath]
 
-    agg = config["mode"] not in {"single"}
-    if agg:
-        result_fpaths = list(dpath.glob("benchmarks*.json"))
+    # agg = config["mode"] not in {"single"}
+    # if agg:
+    #     result_fpaths = list(dpath.glob("benchmarks*.json"))
 
     analyze = config["mode"] in {"all", "single", "analyze"}
     if analyze:

json_benchmarks/libraries.py

@@ -9,6 +9,8 @@ KNOWN_LIBRARIES = [
     {"modname": "simplejson", "distname": "simplejson"},
     {"modname": "json", "distname": "<stdlib>"},
     {"modname": "simdjson", "distname": "pysimdjson"},
+    {"modname": "cysimdjson", "distname": "cysimdjson"},
+    {"modname": "libpy_simdjson", "distname": "libpy-simdjson"},
 ]
 
 KNOWN_MODNAMES = [info["modname"] for info in KNOWN_LIBRARIES]
@@ -29,6 +31,29 @@ KNOWN_MODNAMES = [info["modname"] for info in KNOWN_LIBRARIES]
 #     # pkg_resources.get_distribution('pysimdjson')
 
 
+class Compatability:
+    """
+    Expose a common API for all tested implmentations
+    """
+
+    @staticmethod
+    def lut_dumps(module):
+        if module.__name__ == 'cysimdjson':
+            return None
+        elif module.__name__ == 'pysimdjson':
+            return None
+        else:
+            return getattr(module, 'dumps', None)
+
+    @staticmethod
+    def lut_loads(module):
+        if module.__name__ == 'cysimdjson':
+            parser = module.JSONParser()
+            return parser.loads
+        else:
+            return getattr(module, 'loads', None)
+
+
 def available_json_impls():
     """
     Return a dictionary of information about each json implementation
@@ -39,7 +64,7 @@ def available_json_impls():
         >>> print('json_impls = {}'.format(ub.repr2(json_impls, nl=1)))
     """
     import importlib
-
+    import pkg_resources
     known_libinfo = KNOWN_LIBRARIES
     json_impls = {}
     for libinfo in known_libinfo:
@@ -50,8 +75,6 @@ def available_json_impls():
         except ImportError:
             pass
         else:
-            import pkg_resources
-
             mod_version = getattr(module, "__version__", None)
             if distname == "<stdlib>":
                 pkg_version = mod_version
@@ -60,10 +83,15 @@ def available_json_impls():
             if mod_version is not None:
                 assert mod_version == pkg_version
             version = pkg_version
-            json_impls[modname] = {
+            dumps = Compatability.lut_dumps(module)
+            loads = Compatability.lut_loads(module)
+            impl_info = {
                 "module": module,
                 "modname": modname,
                 "distname": distname,
                 "version": version,
+                "dumps": dumps,
+                "loads": loads,
             }
+            json_impls[modname] = impl_info
     return json_impls

json_benchmarks/measures.py

@@ -69,7 +69,7 @@ def benchmark_json():
             # 'Dict of List[Dict[str, int]]',
             # 'Complex object'
         ],
-        "size": [1, 2, 4, 8, 16, 32, 128, 256, 512, 1024, 2048, 4096, 8192, 12288],
+        "size": [1, 2, 4, 8, 16, 32, 128, 256, 512, 1024, 2048, 4096, 8192],
     }
     predefined_basis = {
         "input": ["Complex object"],
@@ -93,8 +93,10 @@ def benchmark_json():
     )
 
     def is_blocked(params):
-        if params["input"] == "Complex object" and params["impl"] == "orjson":
-            return True
+        if params["input"] == "Complex object":
+            # Some libraries can't handle the complex object
+            if params["impl"] in {"orjson", "libpy_simdjson"}:
+                return True
 
     # For each variation of your experiment, create a row.
     for params in benchmark.iter_params():
@@ -104,14 +106,15 @@ def benchmark_json():
         # method here.
         impl_info = json_impls[params["impl"]]
         params["impl_version"] = impl_info["version"]
-        module = impl_info["module"]
+        method = impl_info[params["func"]]
+        if method is None:
+            # Not all libraries implement all methods
+            continue
+        py_data = data_lut[params["input"]](params["size"])
         if params["func"] == "dumps":
-            method = module.dumps
-            data = data_lut[params["input"]](params["size"])
+            data = py_data
         elif params["func"] == "loads":
-            method = module.loads
-            to_encode = data_lut[params["input"]](params["size"])
-            data = json.dumps(to_encode)
+            data = json.dumps(py_data)
         # Timerit will run some user-specified number of loops.
         # and compute time stats with similar methodology to timeit
         for timer in benchmark.measure():