Merge pull request #387 from mason-lgtm/wasmsourcemap

Wasm source maps

CMakeLists.txt

@@ -250,6 +250,8 @@ add_library(libbloaty STATIC
     src/range_map.cc
     src/range_map.h
     src/re.h
+    src/source_map.cc
+    src/source_map.h
     src/util.cc
     src/util.h
     src/webassembly.cc

doc/using.md

@@ -99,6 +99,11 @@ Options:
   -c FILE            Load configuration from <file>.
   -d SOURCE,SOURCE   Comma-separated list of sources to scan.
   --debug-file=FILE  Use this file for debug symbols and/or symbol table.
+  --source-map=ID=FILE
+                     Use this source map file for the binary. The ID can be
+                     the build ID (or Wasm sourceMappingURL) or the file path
+                     as specified in the command line.
+                     Currently only supported for Wasm.
   -C MODE            How to demangle symbols.  Possible values are:
   --demangle=MODE      --demangle=none   no demangling, print raw symbols
                        --demangle=short  demangle, but omit arg/return types
@@ -845,6 +850,33 @@ $ ./bloaty -c config.bloaty -d bloaty_package,compileunits bloaty
  100.0%  29.5Mi 100.0%  6.69Mi    TOTAL
 ```
 
+# Source maps
+
+Bloaty provides a `--source-map` option which allows
+specifying a source map for the binary. It takes an ID and
+source map file name, separated by '='. The ID can be the
+build ID or path to the binary file as specified in the
+command line.
+
+For example, to use the `compileunits` and `inlines` data
+sources for Wasm, a source map must be provided. For Wasm,
+the ID can be the text in the `sourceMappingURL` section of
+the binary.
+
+```cmdoutput
+$ ./bloaty -d compileunits --domain=file --source-map=o.wasm=o.wasm.map o.wasm
+    FILE SIZE   
+ -------------- 
+  45.0%      49    [section sourceMappingURL]
+  19.3%      21    Main.java
+  12.8%      14    [section Export]
+   7.3%       8    [WASM Header]
+   6.4%       7    [section Code]
+   5.5%       6    [section Type]
+   3.7%       4    [section Function]
+ 100.0%     109    TOTAL
+```
+
 # Source filter
 
 Sometimes, you are only interested in parts of the binary

src/bloaty.cc

@@ -1468,6 +1468,7 @@ class Bloaty {
 
   void AddFilename(const std::string& filename, bool base_file);
   void AddDebugFilename(const std::string& filename);
+  void AddSourceMapFilename(const std::string& filename);
 
   size_t GetSourceCount() const { return sources_.size(); }
 
@@ -1535,6 +1536,7 @@ class Bloaty {
   std::vector<InputFileInfo> input_files_;
   std::vector<InputFileInfo> base_files_;
   std::map<std::string, std::string> debug_files_;
+  std::map<std::string, std::string> sourcemap_files_;
 
   // For allocating memory, like to decompress compressed sections.
   std::unique_ptr<google::protobuf::Arena> arena_;
@@ -1592,6 +1594,18 @@ void Bloaty::AddDebugFilename(const std::string& filename) {
   debug_files_[build_id] = filename;
 }
 
+void Bloaty::AddSourceMapFilename(const std::string& filename) {
+  std::size_t delimiter = filename.find('=');
+  if (delimiter == std::string::npos) {
+    THROWF("Source map filename '$0' must have a build id and file name "
+           "separated by '='",
+           filename);
+  }
+  std::string sourcemap_build_id = filename.substr(0, delimiter);
+  std::string sourcemap_filename = filename.substr(delimiter + 1);
+  sourcemap_files_[sourcemap_build_id] = sourcemap_filename;
+}
+
 void Bloaty::DefineCustomDataSource(const CustomDataSource& source) {
   if (source.base_data_source() == "symbols") {
     THROW(
@@ -1761,6 +1775,22 @@ void Bloaty::ScanAndRollupFile(const std::string& filename, Rollup* rollup,
       file->set_debug_file(debug_file.get());
       out_build_ids->push_back(build_id);
     }
+
+    // Maybe it's a source map file?
+    auto sourcemap_iter = sourcemap_files_.find(build_id);
+    // If the source map by build id isn't found, try the file name.
+    if (sourcemap_iter == sourcemap_files_.end()) {
+      sourcemap_iter = sourcemap_files_.find(filename);
+    }
+    if (sourcemap_iter != sourcemap_files_.end()) {
+      std::unique_ptr<InputFile> sourcemap_file(
+          file_factory_.OpenFile(sourcemap_iter->second));
+      // The build id is not present in the source map file itself, so it must
+      // be passed here.
+      debug_file = TryOpenSourceMapFile(sourcemap_file, build_id);
+      file->set_debug_file(debug_file.get());
+      out_build_ids->push_back(build_id);
+    }
   }
 
   int64_t filesize_before =
@@ -1943,6 +1973,11 @@ USAGE: bloaty [OPTION]... FILE... [-- BASE_FILE...]
   -c FILE            Load configuration from <file>.
   -d SOURCE,SOURCE   Comma-separated list of sources to scan.
   --debug-file=FILE  Use this file for debug symbols and/or symbol table.
+  --source-map=ID=FILE
+                     Use this source map file for the binary. The ID can be
+                     the build ID (or Wasm sourceMappingURL) or the file path
+                     as specified in the command line.
+                     Currently only supported for Wasm.
   -C MODE            How to demangle symbols.  Possible values are:
   --demangle=MODE      --demangle=none   no demangling, print raw symbols
                        --demangle=short  demangle, but omit arg/return types
@@ -2166,6 +2201,8 @@ bool DoParseOptions(bool skip_unknown, int* argc, char** argv[],
       }
     } else if (args.TryParseOption("--source-filter", &option)) {
       options->set_source_filter(std::string(option));
+    } else if (args.TryParseOption("--source-map", &option)) {
+      options->add_source_map(std::string(option));
     } else if (args.TryParseFlag("-v")) {
       options->set_verbose_level(1);
     } else if (args.TryParseFlag("-vv")) {
@@ -2260,6 +2297,10 @@ void BloatyDoMain(const Options& options, const InputFileFactory& file_factory,
     bloaty.AddDebugFilename(debug_filename);
   }
 
+  for (auto& sourcemap : options.source_map()) {
+    bloaty.AddSourceMapFilename(sourcemap);
+  }
+
   for (const auto& custom_data_source : options.custom_data_source()) {
     bloaty.DefineCustomDataSource(custom_data_source);
   }

src/bloaty.h

@@ -294,6 +294,8 @@ std::unique_ptr<ObjectFile> TryOpenELFFile(std::unique_ptr<InputFile>& file);
 std::unique_ptr<ObjectFile> TryOpenMachOFile(std::unique_ptr<InputFile>& file);
 std::unique_ptr<ObjectFile> TryOpenWebAssemblyFile(std::unique_ptr<InputFile>& file);
 std::unique_ptr<ObjectFile> TryOpenPEFile(std::unique_ptr<InputFile>& file);
+std::unique_ptr<ObjectFile> TryOpenSourceMapFile(
+    std::unique_ptr<InputFile>& file, std::string build_id);
 
 // Provided by dwarf.cc.  To use these, a module should fill in a dwarf::File
 // and then call these functions.

src/bloaty.proto

@@ -29,6 +29,9 @@ message Options {
   // debug_filename will *not* have their file size counted.
   repeated string debug_filename = 10;
 
+  // Build id to source map file names, delimited by '='.
+  repeated string source_map = 15;
+
   // The data sources to scan in each file.  At least one data source must be
   // specified.  If more than one source is specified, the output is
   // hierarchical.
@@ -101,3 +104,4 @@ message Regex {
   optional string pattern = 1;
   optional string replacement = 2;
 }
+