Format with ruff

Author: haochengxia

examples/basic_usage.py

@@ -7,23 +7,19 @@
 
 # Step 2: Open trace and process efficiently
 reader = lcs.TraceReader(
-    trace = dl.get_cache_path(URI),
-    trace_type = lcs.TraceType.ORACLE_GENERAL_TRACE,
-    reader_init_params = lcs.ReaderInitParam(ignore_obj_size=False)
+    trace=dl.get_cache_path(URI),
+    trace_type=lcs.TraceType.ORACLE_GENERAL_TRACE,
+    reader_init_params=lcs.ReaderInitParam(ignore_obj_size=False),
 )
 
 # Step 3: Initialize cache
-cache = lcs.S3FIFO(cache_size=1024*1024)
+cache = lcs.S3FIFO(cache_size=1024 * 1024)
 
 # Step 4: Process entire trace efficiently (C++ backend)
 obj_miss_ratio, byte_miss_ratio = cache.process_trace(reader)
 print(f"Object miss ratio: {obj_miss_ratio:.4f}, Byte miss ratio: {byte_miss_ratio:.4f}")
 
 # Step 4.1: Process with limited number of requests
-cache = lcs.S3FIFO(cache_size=1024*1024)
-obj_miss_ratio, byte_miss_ratio = cache.process_trace(
-    reader,
-    start_req=0,
-    max_req=1000
-)
-print(f"Object miss ratio: {obj_miss_ratio:.4f}, Byte miss ratio: {byte_miss_ratio:.4f}")
+cache = lcs.S3FIFO(cache_size=1024 * 1024)
+obj_miss_ratio, byte_miss_ratio = cache.process_trace(reader, start_req=0, max_req=1000)
+print(f"Object miss ratio: {obj_miss_ratio:.4f}, Byte miss ratio: {byte_miss_ratio:.4f}")

examples/plugin_cache/s3fifo.py

@@ -8,13 +8,16 @@
 from collections import deque
 from libcachesim import PluginCache, CommonCacheParams, Request, S3FIFO, FIFO, SyntheticReader
 
+
 # NOTE(haocheng): we only support ignore object size for now
 class StandaloneS3FIFO:
-    def __init__(self,
-                 small_size_ratio: float = 0.1,
-                 ghost_size_ratio: float = 0.9,
-                 move_to_main_threshold: int = 2,
-                 cache_size: int = 1024):
+    def __init__(
+        self,
+        small_size_ratio: float = 0.1,
+        ghost_size_ratio: float = 0.9,
+        move_to_main_threshold: int = 2,
+        cache_size: int = 1024,
+    ):
         self.cache_size = cache_size
         small_fifo_size = int(small_size_ratio * cache_size)
         main_fifo_size = cache_size - small_fifo_size
@@ -27,15 +30,15 @@ def __init__(self,
         self.small_fifo = FIFO(small_fifo_size)
         self.main_fifo = FIFO(main_fifo_size)
         self.ghost_fifo = FIFO(ghost_fifo_size)
-        
+
         # Frequency tracking
         self.freq = {}
-        
+
         # Other parameters
         self.max_freq = 3
         self.move_to_main_threshold = move_to_main_threshold
 
-        self.has_evicted = False # Mark if we start to evict, only after full we will start eviction
+        self.has_evicted = False  # Mark if we start to evict, only after full we will start eviction
         self.hit_on_ghost = False
 
     def cache_hit(self, req: Request):
@@ -46,7 +49,7 @@ def cache_hit(self, req: Request):
 
         if self.main_fifo.find(req, update_cache=False):
             self.freq[req.obj_id] += 1
-    
+
     def cache_miss(self, req: Request):
         if not self.hit_on_ghost:
             obj = self.ghost_fifo.find(req, update_cache=False)
@@ -56,14 +59,13 @@ def cache_miss(self, req: Request):
                 self.ghost_fifo.remove(req.obj_id)
                 self.ghost_set.remove(req.obj_id)
 
-
         # NOTE(haocheng): first we need to know this miss object has record in ghost or not
         if not self.hit_on_ghost:
             if req.obj_size >= self.small_fifo.cache_size:
                 # If object is too large, we do not process it
                 return
 
-            # If is initialization state, we need to insert to small fifo, 
+            # If is initialization state, we need to insert to small fifo,
             # then we can insert to main fifo
             if not self.has_evicted and self.small_fifo.get_occupied_byte() >= self.small_fifo.cache_size:
                 obj = self.main_fifo.insert(req)
@@ -76,7 +78,7 @@ def cache_miss(self, req: Request):
             self.main_set.add(req.obj_id)
             self.hit_on_ghost = False
         self.freq[obj.obj_id] = 0
-    
+
     def cache_evict_small(self, req: Request):
         has_evicted = False
         evicted_id = None
@@ -100,7 +102,7 @@ def cache_evict_small(self, req: Request):
             self.small_set.remove(evicted_id)
             assert flag, "Should be able to remove"
         return real_evicted_id
-    
+
     def cache_evict_main(self, req: Request):
         has_evicted = False
         evicted_id = None
@@ -134,15 +136,15 @@ def cache_evict(self, req: Request):
                 self.ghost_set.remove(req.obj_id)
 
         self.has_evicted = True
-        cond = (self.main_fifo.get_occupied_byte() > self.main_fifo.cache_size)
-        if (cond or (self.small_fifo.get_occupied_byte() == 0)):
+        cond = self.main_fifo.get_occupied_byte() > self.main_fifo.cache_size
+        if cond or (self.small_fifo.get_occupied_byte() == 0):
             obj_id = self.cache_evict_main(req)
         else:
             obj_id = self.cache_evict_small(req)
 
         if obj_id is not None:
             del self.freq[obj_id]
-        
+
         return obj_id
 
     def cache_remove(self, obj_id):
@@ -151,28 +153,35 @@ def cache_remove(self, obj_id):
         removed |= self.ghost_fifo.remove(obj_id)
         removed |= self.main_fifo.remove(obj_id)
         return removed
-    
+
+
 def cache_init_hook(common_cache_params: CommonCacheParams):
     return StandaloneS3FIFO(cache_size=common_cache_params.cache_size)
 
+
 def cache_hit_hook(cache, request: Request):
     cache.cache_hit(request)
 
+
 def cache_miss_hook(cache, request: Request):
     cache.cache_miss(request)
 
+
 def cache_eviction_hook(cache, request: Request):
     evicted_id = None
     while evicted_id is None:
         evicted_id = cache.cache_evict(request)
     return evicted_id
 
+
 def cache_remove_hook(cache, obj_id):
     cache.cache_remove(obj_id)
 
+
 def cache_free_hook(cache):
     pass
 
+
 cache = PluginCache(
     cache_size=1024,
     cache_init_hook=cache_init_hook,
@@ -181,17 +190,18 @@ def cache_free_hook(cache):
     cache_eviction_hook=cache_eviction_hook,
     cache_remove_hook=cache_remove_hook,
     cache_free_hook=cache_free_hook,
-    cache_name="S3FIFO")
+    cache_name="S3FIFO",
+)
 
 URI = "cache_dataset_oracleGeneral/2007_msr/msr_hm_0.oracleGeneral.zst"
 dl = lcs.DataLoader()
 dl.load(URI)
 
 # Step 2: Open trace and process efficiently
 reader = lcs.TraceReader(
-    trace = dl.get_cache_path(URI),
-    trace_type = lcs.TraceType.ORACLE_GENERAL_TRACE,
-    reader_init_params = lcs.ReaderInitParam(ignore_obj_size=True)
+    trace=dl.get_cache_path(URI),
+    trace_type=lcs.TraceType.ORACLE_GENERAL_TRACE,
+    reader_init_params=lcs.ReaderInitParam(ignore_obj_size=True),
 )
 
 ref_s3fifo = S3FIFO(cache_size=1024, small_size_ratio=0.1, ghost_size_ratio=0.9, move_to_main_threshold=2)
@@ -208,4 +218,4 @@ def cache_free_hook(cache):
 
 assert req_miss_ratio == ref_req_miss_ratio
 assert byte_miss_ratio == ref_byte_miss_ratio
-print("All requests processed successfully. Plugin cache matches reference S3FIFO cache.")
+print("All requests processed successfully. Plugin cache matches reference S3FIFO cache.")

examples/trace_analysis.py

@@ -6,29 +6,27 @@
 dl.load(URI)
 
 reader = lcs.TraceReader(
-    trace = dl.get_cache_path(URI),
-    trace_type = lcs.TraceType.ORACLE_GENERAL_TRACE,
-    reader_init_params = lcs.ReaderInitParam(ignore_obj_size=False)
+    trace=dl.get_cache_path(URI),
+    trace_type=lcs.TraceType.ORACLE_GENERAL_TRACE,
+    reader_init_params=lcs.ReaderInitParam(ignore_obj_size=False),
 )
 
 analysis_option = lcs.AnalysisOption(
-        req_rate=True,  # Keep basic request rate analysis
-        access_pattern=False,  # Disable access pattern analysis
-        size=True,  # Keep size analysis
-        reuse=False,  # Disable reuse analysis for small datasets
-        popularity=False,  # Disable popularity analysis for small datasets (< 200 objects)
-        ttl=False,  # Disable TTL analysis
-        popularity_decay=False,  # Disable popularity decay analysis
-        lifetime=False,  # Disable lifetime analysis
-        create_future_reuse_ccdf=False,  # Disable experimental features
-        prob_at_age=False,  # Disable experimental features
-        size_change=False,  # Disable size change analysis
-    )
+    req_rate=True,  # Keep basic request rate analysis
+    access_pattern=False,  # Disable access pattern analysis
+    size=True,  # Keep size analysis
+    reuse=False,  # Disable reuse analysis for small datasets
+    popularity=False,  # Disable popularity analysis for small datasets (< 200 objects)
+    ttl=False,  # Disable TTL analysis
+    popularity_decay=False,  # Disable popularity decay analysis
+    lifetime=False,  # Disable lifetime analysis
+    create_future_reuse_ccdf=False,  # Disable experimental features
+    prob_at_age=False,  # Disable experimental features
+    size_change=False,  # Disable size change analysis
+)
 
 analysis_param = lcs.AnalysisParam()
 
-analyzer = lcs.TraceAnalyzer(
-    reader, "example_analysis", analysis_option=analysis_option, analysis_param=analysis_param
-)
+analyzer = lcs.TraceAnalyzer(reader, "example_analysis", analysis_option=analysis_option, analysis_param=analysis_param)
 
-analyzer.run()
+analyzer.run()

libcachesim/cache.py

@@ -284,6 +284,7 @@ def __init__(
     def insert(self, req: Request) -> Optional[CacheObject]:
         return super().insert(req)
 
+
 class TwoQ(CacheBase):
     """2Q replacement algorithm
 
@@ -454,18 +455,24 @@ def __init__(
 
 class LRUProb(CacheBase):
     """LRU with Probabilistic Replacement
-    
+
     Special parameters:
     prob: probability of promoting an object to the head of the queue (default: 0.5)
     """
 
     def __init__(
-        self, cache_size: int, default_ttl: int = 86400 * 300, hashpower: int = 24, consider_obj_metadata: bool = False,
+        self,
+        cache_size: int,
+        default_ttl: int = 86400 * 300,
+        hashpower: int = 24,
+        consider_obj_metadata: bool = False,
         prob: float = 0.5,
     ):
         cache_specific_params = f"prob={prob}"
         super().__init__(
-            _cache=LRU_Prob_init(_create_common_params(cache_size, default_ttl, hashpower, consider_obj_metadata), cache_specific_params)
+            _cache=LRU_Prob_init(
+                _create_common_params(cache_size, default_ttl, hashpower, consider_obj_metadata), cache_specific_params
+            )
         )
 
 
@@ -551,7 +558,9 @@ def __init__(
         try:
             from .libcachesim_python import ThreeLCache_init
         except ImportError:
-            raise ImportError('ThreeLCache is not installed. Please install it with `CMAKE_ARGS="-DENABLE_3L_CACHE=ON" pip install libcachesim --force-reinstall`')
+            raise ImportError(
+                'ThreeLCache is not installed. Please install it with `CMAKE_ARGS="-DENABLE_3L_CACHE=ON" pip install libcachesim --force-reinstall`'
+            )
 
         cache_specific_params = f"objective={objective}"
         super().__init__(
@@ -592,7 +601,9 @@ def __init__(
         try:
             from .libcachesim_python import GLCache_init
         except ImportError:
-            raise ImportError('GLCache is not installed. Please install it with `CMAKE_ARGS="-DENABLE_GLCACHE=ON" pip install libcachesim --force-reinstall`')
+            raise ImportError(
+                'GLCache is not installed. Please install it with `CMAKE_ARGS="-DENABLE_GLCACHE=ON" pip install libcachesim --force-reinstall`'
+            )
 
         cache_specific_params = f"segment-size={segment_size}, n-merge={n_merge}, type={type}, rank-intvl={rank_intvl}, merge-consecutive-segs={merge_consecutive_segs}, train-source-y={train_source_y}, retrain-intvl={retrain_intvl}"
         super().__init__(
@@ -621,7 +632,9 @@ def __init__(
         try:
             from .libcachesim_python import LRB_init
         except ImportError:
-            raise ImportError('LRB is not installed. Please install it with `CMAKE_ARGS="-DENABLE_LRB=ON" pip install libcachesim --force-reinstall`')
+            raise ImportError(
+                'LRB is not installed. Please install it with `CMAKE_ARGS="-DENABLE_LRB=ON" pip install libcachesim --force-reinstall`'
+            )
 
         cache_specific_params = f"objective={objective}"
         super().__init__(

libcachesim/synthetic_reader.py

@@ -90,7 +90,7 @@ def read_one_req(self) -> Request:
         req = Request()
         if self.current_pos >= self.num_of_req:
             req.valid = False
-            return req # return invalid request
+            return req  # return invalid request
 
         obj_id = self.obj_ids[self.current_pos]
         req.obj_id = obj_id

libcachesim/trace_reader.py

@@ -169,7 +169,7 @@ def get_num_of_req(self) -> int:
 
     def read_one_req(self) -> Request:
         req = Request()
-        ret = self._reader.read_one_req(req) # return 0 if success
+        ret = self._reader.read_one_req(req)  # return 0 if success
         if ret != 0:
             raise RuntimeError("Failed to read one request")
         return req