DXR is a code search and navigation tool aimed at making sense of large projects. It supports full-text and regex searches as well as structural queries.

Mercurial (a81015259a98)

VCS Links

Line Code
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788
#!/bin/env python
# ***** BEGIN LICENSE BLOCK *****
# Version: MPL 1.1/GPL 2.0/LGPL 2.1
#
# The contents of this file are subject to the Mozilla Public License Version
# 1.1 (the "License"); you may not use this file except in compliance with
# the License. You may obtain a copy of the License at
# http://www.mozilla.org/MPL/
#
# Software distributed under the License is distributed on an "AS IS" basis,
# WITHOUT WARRANTY OF ANY KIND, either express or implied. See the License
# for the specific language governing rights and limitations under the
# License.
#
# The Original Code is mozilla.org code.
#
# The Initial Developer of the Original Code is
# The Mozilla Foundation
# Portions created by the Initial Developer are Copyright (C) 2007
# the Initial Developer. All Rights Reserved.
#
# Contributor(s):
# Ted Mielczarek <ted.mielczarek@gmail.com>
# Ben Turner <mozilla@songbirdnest.com>
#
# Alternatively, the contents of this file may be used under the terms of
# either the GNU General Public License Version 2 or later (the "GPL"), or
# the GNU Lesser General Public License Version 2.1 or later (the "LGPL"),
# in which case the provisions of the GPL or the LGPL are applicable instead
# of those above. If you wish to allow use of your version of this file only
# under the terms of either the GPL or the LGPL, and not to allow others to
# use your version of this file under the terms of the MPL, indicate your
# decision by deleting the provisions above and replace them with the notice
# and other provisions required by the GPL or the LGPL. If you do not delete
# the provisions above, a recipient may use your version of this file under
# the terms of any one of the MPL, the GPL or the LGPL.
#
# ***** END LICENSE BLOCK *****
#
# Usage: symbolstore.py <params> <dump_syms path> <symbol store path>
#                                <debug info files or dirs>
#   Runs dump_syms on each debug info file specified on the command line,
#   then places the resulting symbol file in the proper directory
#   structure in the symbol store path.  Accepts multiple files
#   on the command line, so can be called as part of a pipe using
#   find <dir> | xargs symbolstore.pl <dump_syms> <storepath>
#   But really, you might just want to pass it <dir>.
#
#   Parameters accepted:
#     -c           : Copy debug info files to the same directory structure
#                    as sym files
#     -a "<archs>" : Run dump_syms -a <arch> for each space separated
#                    cpu architecture in <archs> (only on OS X)
#     -s <srcdir>  : Use <srcdir> as the top source directory to
#                    generate relative filenames.

import sys
import os
import re
import shutil
from subprocess import call, Popen, PIPE, STDOUT
from optparse import OptionParser

# Utility classes

class VCSFileInfo:
    """ A base class for version-controlled file information. Ensures that the
        following attributes are generated only once (successfully):

            self.root
            self.clean_root
            self.revision
            self.filename

        The attributes are generated by a single call to the GetRoot,
        GetRevision, and GetFilename methods. Those methods are explicitly not
        implemented here and must be implemented in derived classes. """

    def __init__(self, file):
        if not file:
            raise ValueError
        self.file = file

    def __getattr__(self, name):
        """ __getattr__ is only called for attributes that are not set on self,
            so setting self.[attr] will prevent future calls to the GetRoot,
            GetRevision, and GetFilename methods. We don't set the values on
            failure on the off chance that a future call might succeed. """

        if name == "root":
            root = self.GetRoot()
            if root:
                self.root = root
            return root

        elif name == "clean_root":
            clean_root = self.GetCleanRoot()
            if clean_root:
                self.clean_root = clean_root
            return clean_root

        elif name == "revision":
            revision = self.GetRevision()
            if revision:
                self.revision = revision
            return revision

        elif name == "filename":
            filename = self.GetFilename()
            if filename:
                self.filename = filename
            return filename

        raise AttributeError

    def GetRoot(self):
        """ This method should return the unmodified root for the file or 'None'
            on failure. """
        raise NotImplementedError

    def GetCleanRoot(self):
        """ This method should return the repository root for the file or 'None'
            on failure. """
        raise NotImplementedErrors

    def GetRevision(self):
        """ This method should return the revision number for the file or 'None'
            on failure. """
        raise NotImplementedError

    def GetFilename(self):
        """ This method should return the repository-specific filename for the
            file or 'None' on failure. """
        raise NotImplementedError

class CVSFileInfo(VCSFileInfo):
    """ A class to maintiain version information for files in a CVS repository.
        Derived from VCSFileInfo. """

    def __init__(self, file, srcdir):
        VCSFileInfo.__init__(self, file)
        self.srcdir = srcdir

    def GetRoot(self):
        (path, filename) = os.path.split(self.file)
        root = os.path.join(path, "CVS", "Root")
        if not os.path.isfile(root):
            return None
        f = open(root, "r")
        root_name = f.readline().strip()
        f.close()
        if root_name:
            return root_name
        print >> sys.stderr, "Failed to get CVS Root for %s" % filename
        return None

    def GetCleanRoot(self):
        parts = self.root.split('@')
        if len(parts) > 1:
            # we don't want the extra colon
            return parts[1].replace(":","")
        return self.root.replace(":","")

    def GetRevision(self):
        (path, filename) = os.path.split(self.file)
        entries = os.path.join(path, "CVS", "Entries")
        if not os.path.isfile(entries):
            return None
        f = open(entries, "r")
        for line in f:
            parts = line.split("/")
            if len(parts) > 1 and parts[1] == filename:
                return parts[2]
        print >> sys.stderr, "Failed to get CVS Revision for %s" % filename
        return None

    def GetFilename(self):
        file = self.file
        if self.revision and self.clean_root:
            if self.srcdir:
                # strip the base path off
                # but we actually want the last dir in srcdir
                file = os.path.normpath(file)
                # the lower() is to handle win32+vc8, where
                # the source filenames come out all lowercase,
                # but the srcdir can be mixed case
                if file.lower().startswith(self.srcdir.lower()):
                    file = file[len(self.srcdir):]
                (head, tail) = os.path.split(self.srcdir)
                if tail == "":
                    tail = os.path.basename(head)
                file = tail + file
            return "cvs:%s:%s:%s" % (self.clean_root, file, self.revision)
        return file

# This regex separates protocol and optional username/password from a url.
# For instance, all the following urls will be transformed into
# 'foo.com/bar':
#
#   http://foo.com/bar
#   svn+ssh://user@foo.com/bar
#   svn+ssh://user:pass@foo.com/bar
#
# This is used by both SVN and HG
rootRegex = re.compile(r'^\S+?:/+(?:[^\s/]*@)?(\S+)$')

class SVNFileInfo(VCSFileInfo):
    url = None
    repo = None
    svndata = {}

    def __init__(self, file):
        """ We only want to run subversion's info tool once so pull all the data
            here. """

        VCSFileInfo.__init__(self, file)

        if os.path.isfile(file):
            command = os.popen("svn info %s" % file, "r")
            for line in command:
                # The last line of the output is usually '\n'
                if line.strip() == '':
                    continue
                # Split into a key/value pair on the first colon
                key, value = line.split(':', 1)
                if key in ["Repository Root", "Revision", "URL"]:
                    self.svndata[key] = value.strip()

            exitStatus = command.close()
            if exitStatus:
              print >> sys.stderr, "Failed to get SVN info for %s" % file

    def GetRoot(self):
        key = "Repository Root"
        if key in self.svndata:
            match = rootRegex.match(self.svndata[key])
            if match:
                return match.group(1)
        print >> sys.stderr, "Failed to get SVN Root for %s" % self.file
        return None

    # File bug to get this teased out from the current GetRoot, this is temporary
    def GetCleanRoot(self):
        return self.root

    def GetRevision(self):
        key = "Revision"
        if key in self.svndata:
            return self.svndata[key]
        print >> sys.stderr, "Failed to get SVN Revision for %s" % self.file
        return None

    def GetFilename(self):
        if self.root and self.revision:
            if "URL" in self.svndata and "Repository Root" in self.svndata:
                url, repo = self.svndata["URL"], self.svndata["Repository Root"]
                file = url[len(repo) + 1:]
            return "svn:%s:%s:%s" % (self.root, file, self.revision)
        print >> sys.stderr, "Failed to get SVN Filename for %s" % self.file
        return self.file

def read_output(*args):
    (stdout, _) = Popen(args=args, stdout=PIPE).communicate()
    return stdout.rstrip()

class HGRepoInfo:
    # HG info is per-repo, so cache it in a static
    # member var
    repos = {}
    def __init__(self, path, rev, cleanroot):
        self.path = path
        self.rev = rev
        self.cleanroot = cleanroot

class HGFileInfo(VCSFileInfo):
    def __init__(self, file, srcdir):
        VCSFileInfo.__init__(self, file)
        # we should only have to collect this info once per-repo
        if not srcdir in HGRepoInfo.repos:
            rev = read_output('hg', '-R', srcdir,
                              'parent', '--template={node|short}')
            path = read_output('hg', '-R', srcdir,
                               'showconfig', 'paths.default')
            if path == '':
                hg_root = os.environ.get("SRCSRV_ROOT")
                if hg_root:
                    path = hg_root
                else:
                    print >> sys.stderr, "Failed to get HG Repo for %s" % srcdir
            if path != '': # not there?
                match = rootRegex.match(path)
                if match:
                    cleanroot = match.group(1)
                    if cleanroot.endswith('/'):
                        cleanroot = cleanroot[:-1]
            HGRepoInfo.repos[srcdir] = HGRepoInfo(path, rev, cleanroot)
        self.repo = HGRepoInfo.repos[srcdir]
        self.file = file
        self.srcdir = srcdir

    def GetRoot(self):
        return self.repo.path

    def GetCleanRoot(self):
        return self.repo.cleanroot

    def GetRevision(self):
        return self.repo.rev

    def GetFilename(self):
        file = self.file
        if self.revision and self.clean_root:
            if self.srcdir:
                # strip the base path off
                file = os.path.normpath(file)
                if IsInDir(file, self.srcdir):
                    file = file[len(self.srcdir):]
                if file.startswith('/') or file.startswith('\\'):
                    file = file[1:]
            return "hg:%s:%s:%s" % (self.clean_root, file, self.revision)
        return file

# Utility functions

# A cache of files for which VCS info has already been determined. Used to
# prevent extra filesystem activity or process launching.
vcsFileInfoCache = {}

def IsInDir(file, dir):
    # the lower() is to handle win32+vc8, where
    # the source filenames come out all lowercase,
    # but the srcdir can be mixed case
    return os.path.abspath(file).lower().startswith(os.path.abspath(dir).lower())

def GetVCSFilename(file, srcdirs):
    """Given a full path to a file, and the top source directory,
    look for version control information about this file, and return
    a tuple containing
    1) a specially formatted filename that contains the VCS type,
    VCS location, relative filename, and revision number, formatted like:
    vcs:vcs location:filename:revision
    For example:
    cvs:cvs.mozilla.org/cvsroot:mozilla/browser/app/nsBrowserApp.cpp:1.36
    2) the unmodified root information if it exists"""
    (path, filename) = os.path.split(file)
    if path == '' or filename == '':
        return (file, None)

    fileInfo = None
    root = ''
    if file in vcsFileInfoCache:
        # Already cached this info, use it.
        fileInfo = vcsFileInfoCache[file]
    else:
        for srcdir in srcdirs:
            if os.path.isdir(os.path.join(path, "CVS")):
                fileInfo = CVSFileInfo(file, srcdir)
                if fileInfo:
                    root = fileInfo.root
            elif os.path.isdir(os.path.join(path, ".svn")) or \
                 os.path.isdir(os.path.join(path, "_svn")):
                 fileInfo = SVNFileInfo(file);
            elif os.path.isdir(os.path.join(srcdir, '.hg')) and \
                 IsInDir(file, srcdir):
                 fileInfo = HGFileInfo(file, srcdir)

            if fileInfo: 
                vcsFileInfoCache[file] = fileInfo
                break

    if fileInfo:
        file = fileInfo.filename
        root = fileInfo.root

    # we want forward slashes on win32 paths
    return (file.replace("\\", "/"), root)

def GetPlatformSpecificDumper(**kwargs):
    """This function simply returns a instance of a subclass of Dumper
    that is appropriate for the current platform."""
    return {'win32': Dumper_Win32,
            'cygwin': Dumper_Win32,
            'linux2': Dumper_Linux,
            'sunos5': Dumper_Solaris,
            'darwin': Dumper_Mac}[sys.platform](**kwargs)

def SourceIndex(fileStream, outputPath, vcs_root):
    """Takes a list of files, writes info to a data block in a .stream file"""
    # Creates a .pdb.stream file in the mozilla\objdir to be used for source indexing
    # Create the srcsrv data block that indexes the pdb file
    result = True
    pdbStreamFile = open(outputPath, "w")
    pdbStreamFile.write('''SRCSRV: ini ------------------------------------------------\r\nVERSION=2\r\nINDEXVERSION=2\r\nVERCTRL=http\r\nSRCSRV: variables ------------------------------------------\r\nHGSERVER=''')
    pdbStreamFile.write(vcs_root)
    pdbStreamFile.write('''\r\nSRCSRVVERCTRL=http\r\nHTTP_EXTRACT_TARGET=%hgserver%/raw-file/%var3%/%var2%\r\nSRCSRVTRG=%http_extract_target%\r\nSRCSRV: source files ---------------------------------------\r\n''')
    pdbStreamFile.write(fileStream) # can't do string interpolation because the source server also uses this and so there are % in the above
    pdbStreamFile.write("SRCSRV: end ------------------------------------------------\r\n\n")
    pdbStreamFile.close()
    return result

class Dumper:
    """This class can dump symbols from a file with debug info, and
    store the output in a directory structure that is valid for use as
    a Breakpad symbol server.  Requires a path to a dump_syms binary--
    |dump_syms| and a directory to store symbols in--|symbol_path|.
    Optionally takes a list of processor architectures to process from
    each debug file--|archs|, the full path to the top source
    directory--|srcdir|, for generating relative source file names,
    and an option to copy debug info files alongside the dumped
    symbol files--|copy_debug|, mostly useful for creating a
    Microsoft Symbol Server from the resulting output.

    You don't want to use this directly if you intend to call
    ProcessDir.  Instead, call GetPlatformSpecificDumper to
    get an instance of a subclass."""
    def __init__(self, dump_syms, symbol_path,
                 archs=None, srcdirs=None, copy_debug=False, vcsinfo=False, srcsrv=False):
        # popen likes absolute paths, at least on windows
        self.dump_syms = os.path.abspath(dump_syms)
        self.symbol_path = symbol_path
        if archs is None:
            # makes the loop logic simpler
            self.archs = ['']
        else:
            self.archs = ['-a %s' % a for a in archs.split()]
        if srcdirs is not None:
            self.srcdirs = [os.path.normpath(a) for a in srcdirs]
        else:
            self.srcdirs = None
        self.copy_debug = copy_debug
        self.vcsinfo = vcsinfo
        self.srcsrv = srcsrv

    # subclasses override this
    def ShouldProcess(self, file):
        return False

    # and can override this
    def ShouldSkipDir(self, dir):
        return False

    def RunFileCommand(self, file):
        """Utility function, returns the output of file(1)"""
        try:
            # we use -L to read the targets of symlinks,
            # and -b to print just the content, not the filename
            return os.popen("file -Lb " + file).read()
        except:
            return ""

    # This is a no-op except on Win32
    def FixFilenameCase(self, file):
        return file

    # This is a no-op except on Win32
    def SourceServerIndexing(self, debug_file, guid, sourceFileStream, vcs_root):
        return ""

    # subclasses override this if they want to support this
    def CopyDebug(self, file, debug_file, guid):
        pass

    def Process(self, file_or_dir):
        "Process a file or all the (valid) files in a directory."
        if os.path.isdir(file_or_dir) and not self.ShouldSkipDir(file_or_dir):
            return self.ProcessDir(file_or_dir)
        elif os.path.isfile(file_or_dir):
            return self.ProcessFile(file_or_dir)
        # maybe it doesn't exist?
        return False

    def ProcessDir(self, dir):
        """Process all the valid files in this directory.  Valid files
        are determined by calling ShouldProcess."""
        result = True
        for root, dirs, files in os.walk(dir):
            for d in dirs[:]:
                if self.ShouldSkipDir(d):
                    dirs.remove(d)
            for f in files:
                fullpath = os.path.join(root, f)
                if self.ShouldProcess(fullpath):
                    if not self.ProcessFile(fullpath):
                        result = False
        return result

    def ProcessFile(self, file):
        """Dump symbols from this file into a symbol file, stored
        in the proper directory structure in  |symbol_path|."""
        print >> sys.stderr, "Processing file: %s" % file
        result = False
        sourceFileStream = ''
        # tries to get the vcs root from the .mozconfig first - if it's not set
        # the tinderbox vcs path will be assigned further down
        vcs_root = os.environ.get("SRCSRV_ROOT")
        for arch in self.archs:
            try:
                cmd = os.popen("%s %s %s" % (self.dump_syms, arch, file), "r")
                module_line = cmd.next()
                if module_line.startswith("MODULE"):
                    # MODULE os cpu guid debug_file
                    (guid, debug_file) = (module_line.split())[3:5]
                    # strip off .pdb extensions, and append .sym
                    sym_file = re.sub("\.pdb$", "", debug_file) + ".sym"
                    # we do want forward slashes here
                    rel_path = os.path.join(debug_file,
                                            guid,
                                            sym_file).replace("\\", "/")
                    full_path = os.path.normpath(os.path.join(self.symbol_path,
                                                              rel_path))
                    try:
                        os.makedirs(os.path.dirname(full_path))
                    except OSError: # already exists
                        pass
                    f = open(full_path, "w")
                    f.write(module_line)
                    # now process the rest of the output
                    for line in cmd:
                        if line.startswith("FILE"):
                            # FILE index filename
                            (x, index, filename) = line.split(None, 2)
                            if sys.platform == "sunos5":
                                for srcdir in self.srcdirs:
                                    start = filename.find(self.srcdir)
                                    if start != -1:
                                        filename = filename[start:]
                                        break
                            filename = self.FixFilenameCase(filename.rstrip())
                            sourcepath = filename
                            if self.vcsinfo:
                                (filename, rootname) = GetVCSFilename(filename, self.srcdirs)
                                # sets vcs_root in case the loop through files were to end on an empty rootname
                                if vcs_root is None:
                                  if rootname:
                                     vcs_root = rootname
                            # gather up files with hg for indexing   
                            if filename.startswith("hg"):
                                (ver, checkout, source_file, revision) = filename.split(":", 3)
                                sourceFileStream += sourcepath + "*" + source_file + '*' + revision + "\r\n"
                            f.write("FILE %s %s\n" % (index, filename))
                        else:
                            # pass through all other lines unchanged
                            f.write(line)
                            # we want to return true only if at least one line is not a MODULE or FILE line
                            result = True
                    f.close()
                    cmd.close()
                    # we output relative paths so callers can get a list of what
                    # was generated
                    print rel_path
                    if self.srcsrv and vcs_root:
                        # add source server indexing to the pdb file
                        self.SourceServerIndexing(file, guid, sourceFileStream, vcs_root)
                    if self.copy_debug:
                        self.CopyDebug(file, debug_file, guid)
            except StopIteration:
                pass
            except:
                print >> sys.stderr, "Unexpected error: ", sys.exc_info()[0]
                raise
        return result

# Platform-specific subclasses.  For the most part, these just have
# logic to determine what files to extract symbols from.

class Dumper_Win32(Dumper):
    fixedFilenameCaseCache = {}

    def ShouldProcess(self, file):
        """This function will allow processing of pdb files that have dll
        or exe files with the same base name next to them."""
        if file.endswith(".pdb"):
            (path,ext) = os.path.splitext(file)
            if os.path.isfile(path + ".exe") or os.path.isfile(path + ".dll"):
                return True
        return False

    def FixFilenameCase(self, file):
        """Recent versions of Visual C++ put filenames into
        PDB files as all lowercase.  If the file exists
        on the local filesystem, fix it."""

        # Use a cached version if we have one.
        if file in self.fixedFilenameCaseCache:
            return self.fixedFilenameCaseCache[file]

        result = file

        (path, filename) = os.path.split(file)
        if os.path.isdir(path):
            lc_filename = filename.lower()
            for f in os.listdir(path):
                if f.lower() == lc_filename:
                    result = os.path.join(path, f)
                    break

        # Cache the corrected version to avoid future filesystem hits.
        self.fixedFilenameCaseCache[file] = result
        return result

    def CopyDebug(self, file, debug_file, guid):
        rel_path = os.path.join(debug_file,
                                guid,
                                debug_file).replace("\\", "/")
        full_path = os.path.normpath(os.path.join(self.symbol_path,
                                                  rel_path))
        shutil.copyfile(file, full_path)
        # try compressing it
        compressed_file = os.path.splitext(full_path)[0] + ".pd_"
        # ignore makecab's output
        success = call(["makecab.exe", "/D", "CompressionType=LZX", "/D", "CompressionMemory=21",
                       full_path, compressed_file], stdout=open("NUL:","w"), stderr=STDOUT)
        if success == 0 and os.path.exists(compressed_file):
            os.unlink(full_path)
            print os.path.splitext(rel_path)[0] + ".pd_"
        else:
            print rel_path
        
    def SourceServerIndexing(self, debug_file, guid, sourceFileStream, vcs_root):
        # Creates a .pdb.stream file in the mozilla\objdir to be used for source indexing
        debug_file = os.path.abspath(debug_file)
        streamFilename = debug_file + ".stream"
        stream_output_path = os.path.abspath(streamFilename)
        # Call SourceIndex to create the .stream file
        result = SourceIndex(sourceFileStream, stream_output_path, vcs_root)
        if self.copy_debug:
            pdbstr_path = os.environ.get("PDBSTR_PATH")
            pdbstr = os.path.normpath(pdbstr_path)
            call([pdbstr, "-w", "-p:" + os.path.basename(debug_file),
                  "-i:" + os.path.basename(streamFilename), "-s:srcsrv"],
                 cwd=os.path.dirname(stream_output_path))
            # clean up all the .stream files when done
            os.remove(stream_output_path)
        return result

class Dumper_Linux(Dumper):
    objcopy = os.environ['OBJCOPY'] if 'OBJCOPY' in os.environ else 'objcopy'
    def ShouldProcess(self, file):
        """This function will allow processing of files that are
        executable, or end with the .so extension, and additionally
        file(1) reports as being ELF files.  It expects to find the file
        command in PATH."""
        if file.endswith(".so") or os.access(file, os.X_OK):
            return self.RunFileCommand(file).startswith("ELF")
        return False

    def CopyDebug(self, file, debug_file, guid):
        # We want to strip out the debug info, and add a
        # .gnu_debuglink section to the object, so the debugger can
        # actually load our debug info later.
        file_dbg = file + ".dbg"
        if call([self.objcopy, '--only-keep-debug', file, file_dbg]) == 0 and \
           call([self.objcopy, '--add-gnu-debuglink=%s' % file_dbg, file]) == 0:
            rel_path = os.path.join(debug_file,
                                    guid,
                                    debug_file + ".dbg")
            full_path = os.path.normpath(os.path.join(self.symbol_path,
                                                      rel_path))
            shutil.move(file_dbg, full_path)
            # gzip the shipped debug files
            os.system("gzip %s" % full_path)
            print rel_path + ".gz"
        else:
            if os.path.isfile(file_dbg):
                os.unlink(file_dbg)

class Dumper_Solaris(Dumper):
    def RunFileCommand(self, file):
        """Utility function, returns the output of file(1)"""
        try:
            output = os.popen("file " + file).read()
            return output.split('\t')[1];
        except:
            return ""

    def ShouldProcess(self, file):
        """This function will allow processing of files that are
        executable, or end with the .so extension, and additionally
        file(1) reports as being ELF files.  It expects to find the file
        command in PATH."""
        if file.endswith(".so") or os.access(file, os.X_OK):
            return self.RunFileCommand(file).startswith("ELF")
        return False

class Dumper_Mac(Dumper):
    def ShouldProcess(self, file):
        """This function will allow processing of files that are
        executable, or end with the .dylib extension, and additionally
        file(1) reports as being Mach-O files.  It expects to find the file
        command in PATH."""
        if file.endswith(".dylib") or os.access(file, os.X_OK):
            return self.RunFileCommand(file).startswith("Mach-O")
        return False

    def ShouldSkipDir(self, dir):
        """We create .dSYM bundles on the fly, but if someone runs
        buildsymbols twice, we should skip any bundles we created
        previously, otherwise we'll recurse into them and try to 
        dump the inner bits again."""
        if dir.endswith(".dSYM"):
            return True
        return False

    def ProcessFile(self, file):
        """dump_syms on Mac needs to be run on a dSYM bundle produced
        by dsymutil(1), so run dsymutil here and pass the bundle name
        down to the superclass method instead."""
        dsymbundle = file + ".dSYM"
        if os.path.exists(dsymbundle):
            shutil.rmtree(dsymbundle)
        # dsymutil takes --arch=foo instead of -a foo like everything else
        os.system("dsymutil %s %s >/dev/null" % (' '.join([a.replace('-a ', '--arch=') for a in self.archs]),
                                      file))
        if not os.path.exists(dsymbundle):
            # dsymutil won't produce a .dSYM for files without symbols
            return False
        res = Dumper.ProcessFile(self, dsymbundle)
        # CopyDebug will already have been run from Dumper.ProcessFile
        shutil.rmtree(dsymbundle)

        # fallback for DWARF-less binaries
        if not res:
            print >> sys.stderr, "Couldn't read DWARF symbols in: %s" % dsymbundle
            res = Dumper.ProcessFile(self, file)

        return res

    def CopyDebug(self, file, debug_file, guid):
        """ProcessFile has already produced a dSYM bundle, so we should just
        copy that to the destination directory. However, we'll package it
        into a .tar.bz2 because the debug symbols are pretty huge, and
        also because it's a bundle, so it's a directory. |file| here is the
        dSYM bundle, and |debug_file| is the original filename."""
        rel_path = os.path.join(debug_file,
                                guid,
                                os.path.basename(file) + ".tar.bz2")
        full_path = os.path.abspath(os.path.join(self.symbol_path,
                                                  rel_path))
        success = call(["tar", "cjf", full_path, os.path.basename(file)],
                       cwd=os.path.dirname(file),
                       stdout=open("/dev/null","w"), stderr=STDOUT)
        if success == 0 and os.path.exists(full_path):
            print rel_path

# Entry point if called as a standalone program
def main():
    parser = OptionParser(usage="usage: %prog [options] <dump_syms binary> <symbol store path> <debug info files>")
    parser.add_option("-c", "--copy",
                      action="store_true", dest="copy_debug", default=False,
                      help="Copy debug info files into the same directory structure as symbol files")
    parser.add_option("-a", "--archs",
                      action="store", dest="archs",
                      help="Run dump_syms -a <arch> for each space separated cpu architecture in ARCHS (only on OS X)")
    parser.add_option("-s", "--srcdir",
                      action="append", dest="srcdir", default=[],
                      help="Use SRCDIR to determine relative paths to source files")
    parser.add_option("-v", "--vcs-info",
                      action="store_true", dest="vcsinfo",
                      help="Try to retrieve VCS info for each FILE listed in the output")
    parser.add_option("-i", "--source-index",
                      action="store_true", dest="srcsrv", default=False,
                      help="Add source index information to debug files, making them suitable for use in a source server.")
    (options, args) = parser.parse_args()
    
    #check to see if the pdbstr.exe exists
    if options.srcsrv:
        pdbstr = os.environ.get("PDBSTR_PATH")
        if not os.path.exists(pdbstr):
            print >> sys.stderr, "Invalid path to pdbstr.exe - please set/check PDBSTR_PATH.\n"
            sys.exit(1)
            
    if len(args) < 3:
        parser.error("not enough arguments")
        exit(1)

    dumper = GetPlatformSpecificDumper(dump_syms=args[0],
                                       symbol_path=args[1],
                                       copy_debug=options.copy_debug,
                                       archs=options.archs,
                                       srcdirs=options.srcdir,
                                       vcsinfo=options.vcsinfo,
                                       srcsrv=options.srcsrv)
    for arg in args[2:]:
        dumper.Process(arg)

# run main if run directly
if __name__ == "__main__":
    main()