Roll asan_symbolize.py to upstream r227327.

tools/valgrind/asan/third_party/asan_symbolize.py

 #!/usr/bin/env python
 #===- lib/asan/scripts/asan_symbolize.py -----------------------------------===#
 #
 #                     The LLVM Compiler Infrastructure
 #
 # This file is distributed under the University of Illinois Open Source
 # License. See LICENSE.TXT for details.
 #
 #===------------------------------------------------------------------------===#
 import argparse
 import bisect
 import getopt
 import os
-import pty
 import re
 import subprocess
 import sys
-import termios
 
 symbolizers = {}
 DEBUG = False
 demangle = False
 binutils_prefix = None
 sysroot_path = None
 binary_name_filter = None
 fix_filename_patterns = None
 logfile = sys.stdin
 
@@ skipping 135 matching lines @@
     file_name = fix_filename(file_name)
     return ['%s in %s %s' % (addr, function_name, file_name)]
 
 
 class UnbufferedLineConverter(object):
   """
   Wrap a child process that responds to each line of input with one line of
   output.  Uses pty to trick the child into providing unbuffered output.
   """
   def __init__(self, args, close_stderr=False):
+    # Local imports so that the script can start on Windows.
+    import pty
+    import termios
     pid, fd = pty.fork()
     if pid == 0:
       # We're the child. Transfer control to command.
       if close_stderr:
         dev_null = os.open('/dev/null', 0)
         os.dup2(dev_null, 2)
       os.execvp(args[0], args)
     else:
       # Disable echoing.
       attr = termios.tcgetattr(fd)
@@ skipping 150 matching lines @@
       result = ['%s in %s %s:%d' % (
           addr, function_name, file_name, line_no)]
       print result
       return result
     else:
       return None
 
 
 class SymbolizationLoop(object):
   def __init__(self, binary_name_filter=None, dsym_hint_producer=None):
-    # Used by clients who may want to supply a different binary name.
-    # E.g. in Chrome several binaries may share a single .dSYM.
-    self.binary_name_filter = binary_name_filter
-    self.dsym_hint_producer = dsym_hint_producer
-    self.system = os.uname()[0]
-    if self.system not in ['Linux', 'Darwin', 'FreeBSD']:
-      raise Exception('Unknown system')
-    self.llvm_symbolizers = {}
-    self.last_llvm_symbolizer = None
-    self.dsym_hints = set([])
-    self.frame_no = 0
+    if sys.platform == 'win32':
+      # ASan on Windows uses dbghelp.dll to symbolize in-process, which works
+      # even in sandboxed processes.  Nothing needs to be done here.
+      self.process_line = self.process_line_echo
+    else:
+      # Used by clients who may want to supply a different binary name.
+      # E.g. in Chrome several binaries may share a single .dSYM.
+      self.binary_name_filter = binary_name_filter
+      self.dsym_hint_producer = dsym_hint_producer
+      self.system = os.uname()[0]
+      if self.system not in ['Linux', 'Darwin', 'FreeBSD']:
+        raise Exception('Unknown system')
+      self.llvm_symbolizers = {}
+      self.last_llvm_symbolizer = None
+      self.dsym_hints = set([])
+      self.frame_no = 0
+      self.process_line = self.process_line_posix
 
   def symbolize_address(self, addr, binary, offset):
     # On non-Darwin (i.e. on platforms without .dSYM debug info) always use
     # a single symbolizer binary.
     # On Darwin, if the dsym hint producer is present:
     #  1. check whether we've seen this binary already; if so,
     #     use |llvm_symbolizers[binary]|, which has already loaded the debug
     #     info for this binary (might not be the case for
     #     |last_llvm_symbolizer|);
     #  2. otherwise check if we've seen all the hints for this binary already;
@@ skipping 33 matching lines @@
       return [self.current_line]
     else:
       result = []
       for symbolized_frame in symbolized_lines:
         result.append('    #%s %s' % (str(self.frame_no), symbolized_frame.rstrip()))
         self.frame_no += 1
       return result
 
   def process_logfile(self):
     self.frame_no = 0
-    while True:
-      line = logfile.readline()
-      if not line:
-        break
+    for line in logfile:
       processed = self.process_line(line)
       print '\n'.join(processed)
 
-  def process_line(self, line):
+  def process_line_echo(self, line):
+    return [line.rstrip()]
+
+  def process_line_posix(self, line):
     self.current_line = line.rstrip()
     #0 0x7f6e35cf2e45  (/blah/foo.so+0x11fe45)
     stack_trace_line_format = (
         '^( *#([0-9]+) *)(0x[0-9a-f]+) *\((.*)\+(0x[0-9a-f]+)\)')
     match = re.match(stack_trace_line_format, line)
     if not match:
       return [self.current_line]
     if DEBUG:
       print line
     _, frameno_str, addr, binary, offset = match.groups()
     if frameno_str == '0':
       # Assume that frame #0 is the first frame of new stack trace.
       self.frame_no = 0
     original_binary = binary
     if self.binary_name_filter:
       binary = self.binary_name_filter(binary)
     symbolized_line = self.symbolize_address(addr, binary, offset)
     if not symbolized_line:
       if original_binary != binary:
         symbolized_line = self.symbolize_address(addr, binary, offset)
     return self.get_symbolized_lines(symbolized_line)
 
 
 if __name__ == '__main__':
-  parser = argparse.ArgumentParser(formatter_class=argparse.RawDescriptionHelpFormatter,
-  description='ASan symbolization script',
-  epilog='''Example of use:
-  asan_symbolize.py -c "$HOME/opt/cross/bin/arm-linux-gnueabi-" -s "$HOME/SymbolFiles" < asan.log''')
+  parser = argparse.ArgumentParser(
+      formatter_class=argparse.RawDescriptionHelpFormatter,
+      description='ASan symbolization script',
+      epilog='Example of use:\n'
+             'asan_symbolize.py -c "$HOME/opt/cross/bin/arm-linux-gnueabi-" '
+             '-s "$HOME/SymbolFiles" < asan.log')
   parser.add_argument('path_to_cut', nargs='*',
-    help='pattern to be cut from the result file path ')
+                      help='pattern to be cut from the result file path ')
   parser.add_argument('-d','--demangle', action='store_true',
-    help='demangle function names')
+                      help='demangle function names')
   parser.add_argument('-s', metavar='SYSROOT',
-    help='set path to sysroot for sanitized binaries')
+                      help='set path to sysroot for sanitized binaries')
   parser.add_argument('-c', metavar='CROSS_COMPILE',
-    help='set prefix for binutils')
-  parser.add_argument('-l','--logfile', default=sys.stdin, type=argparse.FileType('r'),
-    help='set log file name to parse, default is stdin')
+                      help='set prefix for binutils')
+  parser.add_argument('-l','--logfile', default=sys.stdin,
+                      type=argparse.FileType('r'),
+                      help='set log file name to parse, default is stdin')
   args = parser.parse_args()
   if args.path_to_cut:
     fix_filename_patterns = args.path_to_cut
   if args.demangle:
     demangle = True
   if args.s:
     binary_name_filter = sysroot_path_filter
     sysroot_path = args.s
   if args.c:
     binutils_prefix = args.c
   if args.logfile:
     logfile = args.logfile
   else:
     logfile = sys.stdin
   loop = SymbolizationLoop(binary_name_filter)
   loop.process_logfile()