Home | History | Annotate | Download | only in python 
      1 #!/usr/bin/env python
      2 # Copyright (c) 2012 Google Inc.
      3 # All rights reserved.
      4 #
      5 # Redistribution and use in source and binary forms, with or without
      6 # modification, are permitted provided that the following conditions are
      7 # met:
      8 #
      9 #     * Redistributions of source code must retain the above copyright
     10 # notice, this list of conditions and the following disclaimer.
     11 #     * Redistributions in binary form must reproduce the above
     12 # copyright notice, this list of conditions and the following disclaimer
     13 # in the documentation and/or other materials provided with the
     14 # distribution.
     15 #     * Neither the name of Google Inc. nor the names of its
     16 # contributors may be used to endorse or promote products derived from
     17 # this software without specific prior written permission.
     18 #
     19 # THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
     20 # "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
     21 # LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
     22 # A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
     23 # OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
     24 # SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
     25 # LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
     26 # DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
     27 # THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
     28 # (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
     29 # OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
     30 
     31 """Normalizes and de-duplicates paths within Breakpad symbol files.
     32 
     33 When using DWARF for storing debug symbols, some file information will be
     34 stored relative to the current working directory of the current compilation
     35 unit, and may be further relativized based upon how the file was #included.
     36 
     37 This helper can be used to parse the Breakpad symbol file generated from such
     38 DWARF files and normalize and de-duplicate the FILE records found within,
     39 updating any references to the FILE records in the other record types.
     40 """
     41 
     42 import macpath
     43 import ntpath
     44 import optparse
     45 import os
     46 import posixpath
     47 import sys
     48 
     49 class BreakpadParseError(Exception):
     50   """Unsupported Breakpad symbol record exception class."""
     51   pass
     52 
     53 class SymbolFileParser(object):
     54   """Parser for Breakpad symbol files.
     55 
     56   The format of these files is documented at
     57   https://code.google.com/p/google-breakpad/wiki/SymbolFiles
     58   """
     59 
     60   def __init__(self, input_stream, output_stream, ignored_prefixes=None,
     61                path_handler=os.path):
     62     """Inits a SymbolFileParser to read symbol records from |input_stream| and
     63     write the processed output to |output_stream|.
     64     
     65     |ignored_prefixes| contains a list of optional path prefixes that
     66     should be stripped from the final, normalized path outputs.
     67     
     68     For example, if the Breakpad symbol file had all paths starting with a
     69     common prefix, such as:
     70       FILE 1 /b/build/src/foo.cc
     71       FILE 2 /b/build/src/bar.cc
     72     Then adding "/b/build/src" as an ignored prefix would result in an output
     73     file that contained:
     74       FILE 1 foo.cc
     75       FILE 2 bar.cc
     76     
     77     Note that |ignored_prefixes| does not necessarily contain file system
     78     paths, as the contents of the DWARF DW_AT_comp_dir attribute is dependent
     79     upon the host system and compiler, and may contain additional information
     80     such as hostname or compiler version.
     81     """
     82 
     83     self.unique_files = {}
     84     self.duplicate_files = {}
     85     self.input_stream = input_stream
     86     self.output_stream = output_stream
     87     self.ignored_prefixes = ignored_prefixes or []
     88     self.path_handler = path_handler
     89 
     90   def Process(self):
     91     """Processes the Breakpad symbol file."""
     92     for line in self.input_stream:
     93       parsed = self._ParseRecord(line.rstrip())
     94       if parsed:
     95         self.output_stream.write(parsed + '\n')
     96 
     97   def _ParseRecord(self, record):
     98     """Parses a single Breakpad symbol record - a single line from the symbol
     99     file.
    100 
    101     Returns:
    102         The modified string to write to the output file, or None if no line
    103         should be written.
    104     """
    105     record_type = record.partition(' ')[0]
    106     if record_type == 'FILE':
    107       return self._ParseFileRecord(record)
    108     elif self._IsLineRecord(record_type):
    109       return self._ParseLineRecord(record)
    110     else:
    111       # Simply pass the record through unaltered.
    112       return record
    113 
    114   def _NormalizePath(self, path):
    115     """Normalizes a file path to its canonical form.
    116 
    117     As this may not execute on the machine or file system originally
    118     responsible for compilation, it may be necessary to further correct paths
    119     for symlinks, junctions, or other such file system indirections.
    120 
    121     Returns:
    122         A unique, canonical representation for the the file path.
    123     """
    124     return self.path_handler.normpath(path)
    125 
    126   def _AdjustPath(self, path):
    127     """Adjusts the supplied path after performing path de-duplication.
    128 
    129     This may be used to perform secondary adjustments, such as removing a
    130     common prefix, such as "/D/build", or replacing the file system path with
    131     information from the version control system.
    132 
    133     Returns:
    134         The actual path to use when writing the FILE record.
    135     """
    136     return path[len(filter(path.startswith,
    137                            self.ignored_prefixes + [''])[0]):]
    138 
    139   def _ParseFileRecord(self, file_record):
    140     """Parses and corrects a FILE record."""
    141     file_info = file_record[5:].split(' ', 3)
    142     if len(file_info) > 2:
    143       raise BreakpadParseError('Unsupported FILE record: ' + file_record)
    144     file_index = int(file_info[0])
    145     file_name = self._NormalizePath(file_info[1])
    146     existing_file_index = self.unique_files.get(file_name)
    147     if existing_file_index is None:
    148       self.unique_files[file_name] = file_index
    149       file_info[1] = self._AdjustPath(file_name)
    150       return 'FILE ' + ' '.join(file_info)
    151     else:
    152       self.duplicate_files[file_index] = existing_file_index
    153       return None
    154 
    155   def _IsLineRecord(self, record_type):
    156     """Determines if the current record type is a Line record"""
    157     try:
    158       line = int(record_type, 16)
    159     except (ValueError, TypeError):
    160       return False
    161     return True
    162 
    163   def _ParseLineRecord(self, line_record):
    164     """Parses and corrects a Line record."""
    165     line_info = line_record.split(' ', 5)
    166     if len(line_info) > 4:
    167       raise BreakpadParseError('Unsupported Line record: ' + line_record)
    168     file_index = int(line_info[3])
    169     line_info[3] = str(self.duplicate_files.get(file_index, file_index))
    170     return ' '.join(line_info)
    171 
    172 def main():
    173   option_parser = optparse.OptionParser()
    174   option_parser.add_option("-p", "--prefix",
    175                            action="append", dest="prefixes", type="string",
    176                            default=[],
    177                            help="A path prefix that should be removed from "
    178                                 "all FILE lines. May be repeated to specify "
    179                                 "multiple prefixes.")
    180   option_parser.add_option("-t", "--path_type",
    181                            action="store", type="choice", dest="path_handler",
    182                            choices=['win32', 'posix'],
    183                            help="Indicates how file paths should be "
    184                                 "interpreted. The default is to treat paths "
    185                                 "the same as the OS running Python (eg: "
    186                                 "os.path)")
    187   options, args = option_parser.parse_args()
    188   if args:
    189     option_parser.error('Unknown argument: %s' % args)
    190 
    191   path_handler = { 'win32': ntpath,
    192                    'posix': posixpath }.get(options.path_handler, os.path)
    193   try:
    194     symbol_parser = SymbolFileParser(sys.stdin, sys.stdout, options.prefixes,
    195                                      path_handler)
    196     symbol_parser.Process()
    197   except BreakpadParseError, e:
    198     print >> sys.stderr, 'Got an error while processing symbol file'
    199     print >> sys.stderr, str(e)
    200     return 1
    201   return 0
    202 
    203 if __name__ == '__main__':
    204   sys.exit(main())
    205