Add test data and benchmarking script

.pre-commit-config.yaml

@@ -14,13 +14,13 @@ repos:
       - id: end-of-file-fixer
       - id: trailing-whitespace
   - repo: https://github.com/astral-sh/ruff-pre-commit
-    rev: v0.3.2
+    rev: v0.3.4
     hooks:
       - id: ruff
         args: [--fix, --exit-non-zero-on-fix]
       - id: ruff-format
-  - repo: https://github.com/doublify/pre-commit-rust
-    rev: master
+  - repo: https://github.com/FeryET/pre-commit-rust
+    rev: v1.1.0
     hooks:
       - id: fmt
       - id: cargo-check

README.md

@@ -65,6 +65,7 @@ poetry run pytest
 ```
 
 Be sure to run `poetry run maturin develop` after making changes to the Rust code.
+Add the `-r` flag for a release build (for example if you want to run benchmarks).
 
 It's recommended to install the pre-commit hooks:
 ```bash

benchmarking.py

@@ -0,0 +1,33 @@
+"""Simple benchmarking script.
+
+Important! Remember to build the Rust extension with the -r flag to enable release mode.
+Without this, the Rust extension will be compiled in debug mode, which is significantly slower.
+
+poetry run maturin develop -r
+"""
+
+import timeit
+from pathlib import Path
+
+from quick_xmltodict import parse as quickparse  # noqa: F401
+from xmltodict import parse as pyparse  # noqa: F401
+
+DATA_DIR = Path(__file__).parent / "tests/data"
+
+DATA = {
+    "simple": (DATA_DIR / "simple.xml").read_text(),
+    "time_series": (DATA_DIR / "time-series.xml").read_text(),
+    "forecast": (DATA_DIR / "forecast.xml").read_text(),
+    "eic_codes": (DATA_DIR / "eic-codes.xml").read_text(),
+}
+
+results = {}
+for name, xml in DATA.items():  # noqa: B007, PERF102
+    print(f"Running benchmarks for {name}...")
+    quick_time = timeit.timeit("quickparse(xml)", globals=globals(), number=3)
+    py_time = timeit.timeit("pyparse(xml)", globals=globals(), number=3)
+    results[name] = {"quick_xmltodict": quick_time, "xmltodict": py_time, "ratio": py_time / quick_time}
+
+print("Relative performance:")
+for name, result in results.items():
+    print(f"{name}: {result['ratio']:.2f}")

pyproject.toml

@@ -121,6 +121,7 @@ convention = "google"
 
 [tool.ruff.lint.per-file-ignores]
 "tests/test*.py" = ["ANN001", "ANN201"]
+"benchmarking.py" = ["T201"]
 
 [tool.ruff.lint.flake8-import-conventions]
 [tool.ruff.lint.flake8-import-conventions.aliases]