Format cpp and py

haochengxia · haochengxia · commit 280c71aeb284 · 2025-08-08T02:45:57.000-04:00
diff --git a/.clang-format b/.clang-format
@@ -0,0 +1,167 @@
+---
+Language:        Cpp
+BasedOnStyle:  Google
+ColumnLimit: 80
+AccessModifierOffset: -1
+AlignAfterOpenBracket: Align
+AlignConsecutiveMacros: false
+AlignConsecutiveAssignments: false
+AlignConsecutiveDeclarations: false
+AlignEscapedNewlines: Left
+AlignOperands:   true
+AlignTrailingComments: true
+AllowAllArgumentsOnNextLine: true
+AllowAllConstructorInitializersOnNextLine: true
+AllowAllParametersOfDeclarationOnNextLine: true
+AllowShortBlocksOnASingleLine: Never
+AllowShortCaseLabelsOnASingleLine: false
+AllowShortFunctionsOnASingleLine: All
+AllowShortLambdasOnASingleLine: All
+AllowShortIfStatementsOnASingleLine: WithoutElse
+AllowShortLoopsOnASingleLine: true
+AlwaysBreakAfterDefinitionReturnType: None
+AlwaysBreakAfterReturnType: None
+AlwaysBreakBeforeMultilineStrings: true
+AlwaysBreakTemplateDeclarations: Yes
+BinPackArguments: true
+BinPackParameters: true
+BraceWrapping:
+  AfterCaseLabel:  false
+  AfterClass:      false
+  AfterControlStatement: false
+  AfterEnum:       false
+  AfterFunction:   false
+  AfterNamespace:  false
+  AfterObjCDeclaration: false
+  AfterStruct:     false
+  AfterUnion:      false
+  AfterExternBlock: false
+  BeforeCatch:     false
+  BeforeElse:      false
+  IndentBraces:    false
+  SplitEmptyFunction: true
+  SplitEmptyRecord: true
+  SplitEmptyNamespace: true
+BreakBeforeBinaryOperators: None
+BreakBeforeBraces: Attach
+BreakBeforeInheritanceComma: false
+BreakInheritanceList: BeforeColon
+BreakBeforeTernaryOperators: true
+BreakConstructorInitializersBeforeComma: false
+BreakConstructorInitializers: BeforeColon
+BreakAfterJavaFieldAnnotations: false
+BreakStringLiterals: true
+CommentPragmas:  '^ IWYU pragma:'
+CompactNamespaces: false
+ConstructorInitializerAllOnOneLineOrOnePerLine: true
+ConstructorInitializerIndentWidth: 4
+ContinuationIndentWidth: 4
+Cpp11BracedListStyle: true
+DeriveLineEnding: true
+DerivePointerAlignment: true
+DisableFormat:   false
+ExperimentalAutoDetectBinPacking: false
+FixNamespaceComments: true
+ForEachMacros:
+  - foreach
+  - Q_FOREACH
+  - BOOST_FOREACH
+IncludeBlocks:   Regroup
+IncludeCategories:
+  - Regex:           '^<ext/.*\.h>'
+    Priority:        2
+    SortPriority:    0
+  - Regex:           '^<.*\.h>'
+    Priority:        1
+    SortPriority:    0
+  - Regex:           '^<.*'
+    Priority:        2
+    SortPriority:    0
+  - Regex:           '.*'
+    Priority:        3
+    SortPriority:    0
+IncludeIsMainRegex: '([-_](test|unittest))?$'
+IncludeIsMainSourceRegex: ''
+IndentCaseLabels: true
+IndentGotoLabels: true
+IndentPPDirectives: None
+IndentWidth:     2
+IndentWrappedFunctionNames: false
+JavaScriptQuotes: Leave
+JavaScriptWrapImports: true
+KeepEmptyLinesAtTheStartOfBlocks: false
+MacroBlockBegin: ''
+MacroBlockEnd:   ''
+MaxEmptyLinesToKeep: 1
+NamespaceIndentation: None
+ObjCBinPackProtocolList: Never
+ObjCBlockIndentWidth: 2
+ObjCSpaceAfterProperty: false
+ObjCSpaceBeforeProtocolList: true
+PenaltyBreakAssignment: 2
+PenaltyBreakBeforeFirstCallParameter: 1
+PenaltyBreakComment: 300
+PenaltyBreakFirstLessLess: 120
+PenaltyBreakString: 1000
+PenaltyBreakTemplateDeclaration: 10
+PenaltyExcessCharacter: 1000000
+PenaltyReturnTypeOnItsOwnLine: 200
+PointerAlignment: Left
+RawStringFormats:
+  - Language:        Cpp
+    Delimiters:
+      - cc
+      - CC
+      - cpp
+      - Cpp
+      - CPP
+      - 'c++'
+      - 'C++'
+    CanonicalDelimiter: ''
+    BasedOnStyle:    google
+  - Language:        TextProto
+    Delimiters:
+      - pb
+      - PB
+      - proto
+      - PROTO
+    EnclosingFunctions:
+      - EqualsProto
+      - EquivToProto
+      - PARSE_PARTIAL_TEXT_PROTO
+      - PARSE_TEST_PROTO
+      - PARSE_TEXT_PROTO
+      - ParseTextOrDie
+      - ParseTextProtoOrDie
+    CanonicalDelimiter: ''
+    BasedOnStyle:    google
+ReflowComments:  true
+SortIncludes:    true
+SortUsingDeclarations: true
+SpaceAfterCStyleCast: false
+SpaceAfterLogicalNot: false
+SpaceAfterTemplateKeyword: true
+SpaceBeforeAssignmentOperators: true
+SpaceBeforeCpp11BracedList: false
+SpaceBeforeCtorInitializerColon: true
+SpaceBeforeInheritanceColon: true
+SpaceBeforeParens: ControlStatements
+SpaceBeforeRangeBasedForLoopColon: true
+SpaceInEmptyBlock: false
+SpaceInEmptyParentheses: false
+SpacesBeforeTrailingComments: 2
+SpacesInAngles:  false
+SpacesInConditionalStatement: false
+SpacesInContainerLiterals: true
+SpacesInCStyleCastParentheses: false
+SpacesInParentheses: false
+SpacesInSquareBrackets: false
+SpaceBeforeSquareBrackets: false
+Standard:        Auto
+StatementMacros:
+  - Q_UNUSED
+  - QT_REQUIRE_VERSION
+TabWidth:        8
+UseCRLF:         false
+UseTab:          Never
+...
diff --git a/.gitignore b/.gitignore
@@ -231,4 +231,5 @@ sftp-config.json
 # Custom files
 CMakeFiles/*
 *.pyc
-!scripts/smart_build.py
+!scripts/smart_build.py
+uv.lock
diff --git a/libcachesim/synthetic_reader.py b/libcachesim/synthetic_reader.py
@@ -181,12 +181,12 @@ def set_read_pos(self, pos: float) -> None:
     def get_read_pos(self) -> float:
         """Get current read position"""
         return float(self.current_pos)
-    
+
     def get_working_set_size(self) -> Tuple[int, int]:
         """Calculate working set size"""
         wss_obj, wss_byte = 0, 0
         if self.current_pos > 0:
-            unique_ids = np.unique(self.obj_ids[:self.current_pos])
+            unique_ids = np.unique(self.obj_ids[: self.current_pos])
             wss_obj = len(unique_ids)
             wss_byte = wss_obj * self.obj_size
         return wss_obj, wss_byte
diff --git a/libcachesim/trace_reader.py b/libcachesim/trace_reader.py
@@ -6,7 +6,16 @@
 from urllib.parse import urlparse
 
 from .protocols import ReaderProtocol
-from .libcachesim_python import TraceType, SamplerType, Request, ReaderInitParam, Reader, Sampler, ReadDirection, cal_working_set_size
+from .libcachesim_python import (
+    TraceType,
+    SamplerType,
+    Request,
+    ReaderInitParam,
+    Reader,
+    Sampler,
+    ReadDirection,
+    cal_working_set_size,
+)
 from ._s3_cache import get_data_loader
 
 logger = logging.getLogger(__name__)
diff --git a/src/export_cache.cpp b/src/export_cache.cpp
@@ -28,7 +28,7 @@ namespace libcachesim {
 
 namespace py = pybind11;
 
-const cache_obj_t* LHD_HIT_MARKER = reinterpret_cast<cache_obj_t *>(0x1);
+const cache_obj_t* LHD_HIT_MARKER = reinterpret_cast<cache_obj_t*>(0x1);
 
 // Custom deleters for smart pointers
 struct CacheDeleter {
@@ -258,7 +258,7 @@ auto make_cache_wrapper(const std::string& fn_name) {
           cache_t* ptr = InitFn(cc_params, params_cstr);
           return std::unique_ptr<cache_t, CacheDeleter>(ptr);
         },
-        "cc_params"_a, "cache_specific_params"_a = ""); 
+        "cc_params"_a, "cache_specific_params"_a = "");
   };
 }
 
@@ -281,18 +281,21 @@ void export_cache(py::module& m) {
           "req"_a)
       .def(
           "find",
-          [](cache_t& self, const request_t& req, const bool update_cache) -> py::object {
+          [](cache_t& self, const request_t& req,
+             const bool update_cache) -> py::object {
             cache_obj_t* obj = self.find(&self, &req, update_cache);
             // Return None if obj is null (not found)
             if (obj == nullptr) {
-                return py::none();
+              return py::none();
             }
             // NOTE(haocheng): For LHD only, return a dummy object for hit
             if (obj == LHD_HIT_MARKER) {
-                cache_obj_t* dummy_obj = static_cast<cache_obj_t*>(calloc(1, sizeof(cache_obj_t)));
-                dummy_obj->obj_id = req.obj_id;
-                dummy_obj->obj_size = req.obj_size;
-                return py::cast(std::unique_ptr<cache_obj_t, CacheObjectDeleter>(dummy_obj));
+              cache_obj_t* dummy_obj =
+                  static_cast<cache_obj_t*>(calloc(1, sizeof(cache_obj_t)));
+              dummy_obj->obj_id = req.obj_id;
+              dummy_obj->obj_size = req.obj_size;
+              return py::cast(
+                  std::unique_ptr<cache_obj_t, CacheObjectDeleter>(dummy_obj));
             }
             return py::cast(obj, py::return_value_policy::reference);
           },
@@ -303,23 +306,25 @@ void export_cache(py::module& m) {
             return self.can_insert(&self, &req);
           },
           "req"_a)
-          .def(
-            "insert",
-            [](cache_t& self, const request_t& req) -> std::optional<cache_obj_t*> {
-              cache_obj_t* inserted = self.insert(&self, &req);
-              if (inserted == nullptr) {
-                return std::nullopt;
-              }
-              return inserted;
-            },
-            "req"_a,
-            py::return_value_policy::reference  // optional still respected
-        )
-        
+      .def(
+          "insert",
+          [](cache_t& self,
+             const request_t& req) -> std::optional<cache_obj_t*> {
+            cache_obj_t* inserted = self.insert(&self, &req);
+            if (inserted == nullptr) {
+              return std::nullopt;
+            }
+            return inserted;
+          },
+          "req"_a,
+          py::return_value_policy::reference  // optional still respected
+          )
+
       .def(
           "need_eviction",
           [](cache_t& self, const request_t& req) {
-            return self.get_occupied_byte(&self) + req.obj_size > self.cache_size;
+            return self.get_occupied_byte(&self) + req.obj_size >
+                   self.cache_size;
           },
           "req"_a)
       .def(
@@ -370,7 +375,8 @@ void export_cache(py::module& m) {
              params->default_ttl = default_ttl;
              params->hashpower = hashpower;
              params->consider_obj_metadata = consider_obj_metadata;
-             return std::unique_ptr<common_cache_params_t, CommonCacheParamsDeleter>(params);
+             return std::unique_ptr<common_cache_params_t,
+                                    CommonCacheParamsDeleter>(params);
            }),
            "cache_size"_a, "default_ttl"_a = 86400 * 300, "hashpower"_a = 24,
            "consider_obj_metadata"_a = false)
diff --git a/src/export_reader.cpp b/src/export_reader.cpp
@@ -61,14 +61,16 @@ struct SamplerDeleter {
   }
 };
 
-
 void export_reader(py::module& m) {
   /* Helper function(s) */
-  m.def("cal_working_set_size", [](reader_t& reader) {
-    int64_t wss_obj = 0, wss_byte = 0;
-    cal_working_set_size(&reader, &wss_obj, &wss_byte);
-    return std::make_tuple(wss_obj, wss_byte);
-  }, "reader"_a);
+  m.def(
+      "cal_working_set_size",
+      [](reader_t& reader) {
+        int64_t wss_obj = 0, wss_byte = 0;
+        cal_working_set_size(&reader, &wss_obj, &wss_byte);
+        return std::make_tuple(wss_obj, wss_byte);
+      },
+      "reader"_a);
 
   // Sampler type enumeration
   py::enum_<sampler_type>(m, "SamplerType")
diff --git a/uv.lock b/uv.lock
