[compiler-rt] Symbolizer refactoring: Move string parsing into separate functions

[kubamracek]

Summary

Part of http://reviews.llvm.org/D7827. Extracts two functions, ParseSymbolizePCOutput and ParseSymbolizeDataOutput that do the string parsing from POSIXSymbolizer.

[samsonov]

lib/sanitizer_common/sanitizer_symbolizer_posix_libcdep.cc

312

In fact, no, we parse multiple two-line string entries.

315

You can just write it as

<function_name>
<file_name>:<line_number>[:<column_number>]

321

Why do you need these temp variables, you never actually modify these res->info fields.

380

Wait, this line should remain in SymbolizeData, it has nothing to do with parsing.

[kubamracek]

Addressing comments.

[samsonov]

LGTM

[kubamracek]

Landed in r230529.

lib/sanitizer_common/sanitizer_symbolizer_posix_libcdep.cc

private:
 
   static const uptr kMaxTimesRestarted = 5;
   static const int kSymbolizerStartupTimeMillis = 10;
   uptr times_restarted_;
   bool failed_to_start_;
   bool reported_invalid_path_;
 };
 
+
+// Parses a two-line string in the following format:
+//   <function_name>
+//   <file_name>:<line_number>:<column_number>
+// or this format (without the column number):
+//   <function_name>
+//   <file_name>:<line_number>
+// Used by LLVMSymbolizer, Addr2LinePool and InternalSymbolizer, since all of
+// them use the same output format.
+static void ParseSymbolizePCOutput(const char *str, SymbolizedStack *res) {
+  uptr orig_addr = res->info.address;
+  const char *orig_module_name = res->info.module;
+  uptr orig_module_offset = res->info.module_offset;
+
+  bool top_frame = true;
+  SymbolizedStack *last = res;
+  while (true) {
+    char *function_name = 0;
+    str = ExtractToken(str, "\n", &function_name);
+    CHECK(function_name);
+    if (function_name[0] == '\0') {
+      // There are no more frames.
+      break;
+    }
+    SymbolizedStack *cur;
+    if (top_frame) {
+      cur = res;
+      top_frame = false;
+    } else {
+      cur = SymbolizedStack::New(orig_addr);
+      cur->info.FillAddressAndModuleInfo(orig_addr, orig_module_name,
+                                         orig_module_offset);
+      last->next = cur;
+      last = cur;
+    }
+
+    AddressInfo *info = &cur->info;
+    info->function = function_name;
+    // Parse <file>:<line>:<column> buffer.
+    char *file_line_info = 0;
+    str = ExtractToken(str, "\n", &file_line_info);
+    CHECK(file_line_info);
+    const char *line_info = ExtractToken(file_line_info, ":", &info->file);
+    line_info = ExtractInt(line_info, ":", &info->line);
+    line_info = ExtractInt(line_info, "", &info->column);
+    InternalFree(file_line_info);
+
+    // Functions and filenames can be "??", in which case we write 0
+    // to address info to mark that names are unknown.
+    if (0 == internal_strcmp(info->function, "??")) {
+      InternalFree(info->function);
+      info->function = 0;
+    }
+    if (0 == internal_strcmp(info->file, "??")) {
+      InternalFree(info->file);
+      info->file = 0;
+    }
+  }
+}
+
+// Parses a two-line string in the following format:
+//   <symbol_name>
+//   <start_address> <size>
+// Used by LLVMSymbolizer and InternalSymbolizer.
+static void ParseSymbolizeDataOutput(const char *str, uptr addr,
+                                     DataInfo *info) {
+  str = ExtractToken(str, "\n", &info->name);
+  str = ExtractUptr(str, " ", &info->start);
+  str = ExtractUptr(str, "\n", &info->size);
+  info->start += (addr - info->module_offset);  // Add the module base address.
+}
+
 // For now we assume the following protocol:
 // For each request of the form
 //   <module_name> <module_offset>
 // passed to STDIN, external symbolizer prints to STDOUT response:
 //   <function_name>
 //   <file_name>:<line_number>:<column_number>
 //   <function_name>
 //   <file_name>:<line_number>:<column_number>
SymbolizedStack *SymbolizePC(uptr addr) override {
     res->info.FillAddressAndModuleInfo(addr, module_name, module_offset);
 
     const char *str = SendCommand(false, module_name, module_offset);
     if (str == 0) {
       // Symbolizer was not initialized or failed.
       return res;
     }
 
-    bool top_frame = true;
-    SymbolizedStack *last = res;
-    while (true) {
-      char *function_name = 0;
-      str = ExtractToken(str, "\n", &function_name);
-      CHECK(function_name);
-      if (function_name[0] == '\0') {
-        // There are no more frames.
-        break;
-      }
-      SymbolizedStack *cur;
-      if (top_frame) {
-        cur = res;
-        top_frame = false;
-      } else {
-        cur = SymbolizedStack::New(addr);
-        cur->info.FillAddressAndModuleInfo(addr, module_name, module_offset);
-        last->next = cur;
-        last = cur;
-      }
-
-      AddressInfo *info = &cur->info;
-      info->function = function_name;
-      // Parse <file>:<line>:<column> buffer.
-      char *file_line_info = 0;
-      str = ExtractToken(str, "\n", &file_line_info);
-      CHECK(file_line_info);
-      const char *line_info = ExtractToken(file_line_info, ":", &info->file);
-      line_info = ExtractInt(line_info, ":", &info->line);
-      line_info = ExtractInt(line_info, "", &info->column);
-      InternalFree(file_line_info);
-
-      // Functions and filenames can be "??", in which case we write 0
-      // to address info to mark that names are unknown.
-      if (0 == internal_strcmp(info->function, "??")) {
-        InternalFree(info->function);
-        info->function = 0;
-      }
-      if (0 == internal_strcmp(info->file, "??")) {
-        InternalFree(info->file);
-        info->file = 0;
-      }
-    }
+    ParseSymbolizePCOutput(str, res);
     return res;
   }
 
   bool SymbolizeData(uptr addr, DataInfo *info) override {
     BlockingMutexLock l(&mu_);
     LoadedModule *module = FindModuleForAddress(addr);
     if (module == 0)
       return false;
     const char *module_name = module->full_name();
     uptr module_offset = addr - module->base_address();
     info->Clear();
     info->module = internal_strdup(module_name);
     info->module_offset = module_offset;
     // First, try to use libbacktrace symbolizer (if it's available).
     if (libbacktrace_symbolizer_ != 0) {
       mu_.CheckLocked();
       if (libbacktrace_symbolizer_->SymbolizeData(addr, info))
         return true;
     }
     const char *str = SendCommand(true, module_name, module_offset);
     if (str == 0)
       return true;
-    str = ExtractToken(str, "\n", &info->name);
-    str = ExtractUptr(str, " ", &info->start);
-    str = ExtractUptr(str, "\n", &info->size);
-    info->start += module->base_address();
+    ParseSymbolizeDataOutput(str, addr, info);
     return true;
   }
 
   bool GetModuleNameAndOffsetForPC(uptr pc, const char **module_name,
                                    uptr *module_address) override {
     BlockingMutexLock l(&mu_);
     return FindModuleNameAndOffsetForAddress(pc, module_name, module_address);
   }