Add CI and test

Author: haochengxia

.github/workflows/build.yml

@@ -0,0 +1,38 @@
+name: Build and Test libCacheSim-python
+
+on: [push, pull_request]
+
+permissions:
+  contents: read
+
+jobs:
+  build:
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v4
+
+      - name: Set up Python
+        uses: actions/setup-python@v4
+        with:
+          python-version: "3.10"
+
+      - name: Init submodules
+        run: git submodule update --init --recursive
+
+      - name: Prepare
+        run: bash src/libCacheSim/scripts/install_dependency.sh
+
+      - name: Build main libCacheSim project
+        run: |
+          pushd src/libCacheSim
+          cmake -G Ninja -B build
+          ninja -C build
+          popd
+
+      - name: Build libCacheSim-python
+        run: |
+          pip install -e .[dev]
+
+      - name: Run tests
+        run: |
+          python -m pytest tests/

.gitmodules

@@ -1,6 +1,3 @@
-[submodule "libCacheSim"]
-	path = libCacheSim
-	url = [email protected]:1a1a11a/libCacheSim.git
 [submodule "src/libCacheSim"]
 	path = src/libCacheSim
 	url = [email protected]:1a1a11a/libCacheSim.git

README.md

@@ -1,11 +1,11 @@
 # libCacheSim Python Binding
 
-[![Python Release](https://github.com/1a1a11a/libCacheSim/actions/workflows/pypi-release.yml/badge.svg)](https://github.com/1a1a11a/libCacheSim/actions/workflows/pypi-release.yml)
+[![Build](https://github.com/cacheMon/libCacheSim-python/actions/workflows/build.yml/badge.svg)](https://github.com/cacheMon/libCacheSim-python/actions/workflows/build.yml)
 [![Python Versions](https://img.shields.io/pypi/pyversions/libcachesim.svg?logo=python&logoColor=white)](https://pypi.org/project/libcachesim)
 [![PyPI Version](https://img.shields.io/pypi/v/libcachesim.svg?)](https://pypi.org/project/libcachesim)
 [![PyPI - Downloads](https://img.shields.io/pypi/dd/libcachesim)](https://pypistats.org/packages/libcachesim)
 
-Python bindings for libCacheSim, a high-performance cache simulator and analysis library.
+Python bindings for [libCacheSim](https://github.com/1a1a11a/libCacheSim), a high-performance cache simulator and analysis library.
 
 ## Installation
 
@@ -20,25 +20,13 @@ pip install libcachesim
 If there are no wheels suitable for your environment, consider building from source.
 
 ```bash
-git clone https://github.com/1a1a11a/libCacheSim.git
-cd libCacheSim
-
-# Build the main libCacheSim library first
-cmake -G Ninja -B build
-ninja -C build
-
-# Install Python binding
-cd libCacheSim-python
-pip install -e .
+bash scripts/install.sh
 ```
 
-### Testing
-```bash
-# Run all tests
-python -m pytest .
+Run all tests to ensure the package works.
 
-# Test import
-python -c "import libcachesim; print('Success!')"
+```bash
+python -m pytest tests/
 ```
 
 ## Quick Start

benchmark/simulation.py

@@ -0,0 +1,5 @@
+""" Benchmark the simulation performance of the library.
+
+This module contains benchmarks for various components of the library,
+including request processing times, memory usage, and overall throughput.
+"""

export/CMakeLists.txt

@@ -1,7 +1,7 @@
 """Wrapper of Reader"""
 
 import logging
-from typing import overload, Union
+from typing import overload, Union, Optional
 from collections.abc import Iterator
 
 from .protocols import ReaderProtocol
@@ -22,53 +22,19 @@ def __init__(
         self,
         trace: Union[Reader, str],
         trace_type: TraceType = TraceType.UNKNOWN_TRACE,
-        ignore_obj_size: bool = False,
-        ignore_size_zero_req: bool = False,
-        obj_id_is_num: bool = False,
-        obj_id_is_num_set: bool = False,
-        cap_at_n_req: int = -1,
-        block_size: int = 0,
-        has_header: bool = False,
-        has_header_set: bool = False,
-        delimiter: str = ",",
-        trace_start_offset: int = 0,
-        binary_fmt_str: str = "",
-        sampling_ratio: float = 1.0,
-        sampling_type: SamplerType = SamplerType.INVALID_SAMPLER,
+        reader_init_params: Optional[ReaderInitParam] = None,
     ):
+
         if isinstance(trace, Reader):
             self._reader = trace
             return
 
-        # Process sampling_type
-        if sampling_ratio < 0.0 or sampling_ratio > 1.0:
-            raise ValueError("Sampling ratio must be between 0.0 and 1.0")
-
-        if sampling_ratio == 1.0:
-            sampler = None
-        else:
-            if sampling_type == SamplerType.INVALID_SAMPLER:
-                logging.warning("Sampling type is invalid, using SPATIAL_SAMPLER instead")
-                sampling_type = SamplerType.SPATIAL_SAMPLER
-            logging.info(f"Sampling ratio: {sampling_ratio}, Sampling type: {sampling_type}")
-            sampler = Sampler(sampling_ratio, sampling_type)
-
-        # Construct ReaderInitParam
-        reader_init_params = ReaderInitParam(
-            binary_fmt_str=binary_fmt_str,
-            ignore_obj_size=ignore_obj_size,
-            ignore_size_zero_req=ignore_size_zero_req,
-            obj_id_is_num=obj_id_is_num,
-            obj_id_is_num_set=obj_id_is_num_set,
-            cap_at_n_req=cap_at_n_req,
-            block_size=block_size,
-            has_header=has_header,
-            has_header_set=has_header_set,
-            delimiter=delimiter,
-            trace_start_offset=trace_start_offset,
-            sampler=sampler,
-        )
+        if reader_init_params is None:
+            reader_init_params = ReaderInitParam()
 
+        if not isinstance(reader_init_params, ReaderInitParam):
+            raise TypeError("reader_init_params must be an instance of ReaderInitParam")
+            
         self._reader = Reader(trace, trace_type, reader_init_params)
 
     @property

export/README.md

@@ -21,6 +21,7 @@ classifiers = [
 ]
 dependencies = [
   "numpy>=1.20.0",
+  "boto3",  # For S3 
 ]
 
 [project.optional-dependencies]

libcachesim/trace_reader.py

@@ -10,6 +10,15 @@ def test_analyzer_common():
 
     reader = TraceReader(file_path)
 
-    analyzer = TraceAnalyzer(reader, output_path="./")
+    analyzer = TraceAnalyzer(reader, "TestAnalyzerResults")
 
     analyzer.run()
+
+    # Clean file after test, match all files with the prefix "TestAnalyzerResults"
+    for file in os.listdir("."):
+        if file.startswith("TestAnalyzerResults"):
+            os.remove(file)
+    # Remove file named "stat"
+    stat_file = "stat"
+    if os.path.exists(stat_file):
+        os.remove(stat_file)