vendor/clang/clang-trunk-r300422

7 files changed, 1080 insertions, 918 deletions

diff --git a/tools/scan-build-py/libscanbuild/__init__.py b/tools/scan-build-py/libscanbuild/__init__.py
index c020b4e4345d6..800926ebb6f2f 100644
--- a/tools/scan-build-py/libscanbuild/__init__.py
+++ b/tools/scan-build-py/libscanbuild/__init__.py
@@ -3,10 +3,21 @@
 #
 # This file is distributed under the University of Illinois Open Source
 # License. See LICENSE.TXT for details.
-"""
-This module responsible to run the Clang static analyzer against any build
-and generate reports.
-"""
+""" This module is a collection of methods commonly used in this project. """
+import collections
+import functools
+import json
+import logging
+import os
+import os.path
+import re
+import shlex
+import subprocess
+import sys
+
+ENVIRONMENT_KEY = 'INTERCEPT_BUILD'
+
+Execution = collections.namedtuple('Execution', ['pid', 'cwd', 'cmd'])
 
 
 def duplicate_check(method):
@@ -30,44 +41,89 @@ def duplicate_check(method):
     return predicate
 
 
-def tempdir():
-    """ Return the default temorary directory. """
-
-    from os import getenv
-    return getenv('TMPDIR', getenv('TEMP', getenv('TMP', '/tmp')))
-
-
-def initialize_logging(verbose_level):
-    """ Output content controlled by the verbosity level. """
-
-    import sys
-    import os.path
-    import logging
+def run_build(command, *args, **kwargs):
+    """ Run and report build command execution
+
+    :param command: array of tokens
+    :return: exit code of the process
+    """
+    environment = kwargs.get('env', os.environ)
+    logging.debug('run build %s, in environment: %s', command, environment)
+    exit_code = subprocess.call(command, *args, **kwargs)
+    logging.debug('build finished with exit code: %d', exit_code)
+    return exit_code
+
+
+def run_command(command, cwd=None):
+    """ Run a given command and report the execution.
+
+    :param command: array of tokens
+    :param cwd: the working directory where the command will be executed
+    :return: output of the command
+    """
+    def decode_when_needed(result):
+        """ check_output returns bytes or string depend on python version """
+        return result.decode('utf-8') if isinstance(result, bytes) else result
+
+    try:
+        directory = os.path.abspath(cwd) if cwd else os.getcwd()
+        logging.debug('exec command %s in %s', command, directory)
+        output = subprocess.check_output(command,
+                                         cwd=directory,
+                                         stderr=subprocess.STDOUT)
+        return decode_when_needed(output).splitlines()
+    except subprocess.CalledProcessError as ex:
+        ex.output = decode_when_needed(ex.output).splitlines()
+        raise ex
+
+
+def reconfigure_logging(verbose_level):
+    """ Reconfigure logging level and format based on the verbose flag.
+
+    :param verbose_level: number of `-v` flags received by the command
+    :return: no return value
+    """
+    # Exit when nothing to do.
+    if verbose_level == 0:
+        return
+
+    root = logging.getLogger()
+    # Tune logging level.
     level = logging.WARNING - min(logging.WARNING, (10 * verbose_level))
-
+    root.setLevel(level)
+    # Be verbose with messages.
     if verbose_level <= 3:
-        fmt_string = '{0}: %(levelname)s: %(message)s'
+        fmt_string = '%(name)s: %(levelname)s: %(message)s'
     else:
-        fmt_string = '{0}: %(levelname)s: %(funcName)s: %(message)s'
-
-    program = os.path.basename(sys.argv[0])
-    logging.basicConfig(format=fmt_string.format(program), level=level)
+        fmt_string = '%(name)s: %(levelname)s: %(funcName)s: %(message)s'
+    handler = logging.StreamHandler(sys.stdout)
+    handler.setFormatter(logging.Formatter(fmt=fmt_string))
+    root.handlers = [handler]
 
 
 def command_entry_point(function):
-    """ Decorator for command entry points. """
+    """ Decorator for command entry methods.
+
+    The decorator initialize/shutdown logging and guard on programming
+    errors (catch exceptions).
 
-    import functools
-    import logging
+    The decorated method can have arbitrary parameters, the return value will
+    be the exit code of the process. """
 
     @functools.wraps(function)
     def wrapper(*args, **kwargs):
+        """ Do housekeeping tasks and execute the wrapped method. """
 
-        exit_code = 127
         try:
-            exit_code = function(*args, **kwargs)
+            logging.basicConfig(format='%(name)s: %(message)s',
+                                level=logging.WARNING,
+                                stream=sys.stdout)
+            # This hack to get the executable name as %(name).
+            logging.getLogger().name = os.path.basename(sys.argv[0])
+            return function(*args, **kwargs)
         except KeyboardInterrupt:
-            logging.warning('Keyboard interupt')
+            logging.warning('Keyboard interrupt')
+            return 130  # Signal received exit code for bash.
         except Exception:
             logging.exception('Internal error.')
             if logging.getLogger().isEnabledFor(logging.DEBUG):
@@ -75,8 +131,75 @@ def command_entry_point(function):
                               "to the bug report")
             else:
                 logging.error("Please run this command again and turn on "
-                              "verbose mode (add '-vvv' as argument).")
+                              "verbose mode (add '-vvvv' as argument).")
+            return 64  # Some non used exit code for internal errors.
         finally:
-            return exit_code
+            logging.shutdown()
 
     return wrapper
+
+
+def compiler_wrapper(function):
+    """ Implements compiler wrapper base functionality.
+
+    A compiler wrapper executes the real compiler, then implement some
+    functionality, then returns with the real compiler exit code.
+
+    :param function: the extra functionality what the wrapper want to
+    do on top of the compiler call. If it throws exception, it will be
+    caught and logged.
+    :return: the exit code of the real compiler.
+
+    The :param function: will receive the following arguments:
+
+    :param result:       the exit code of the compilation.
+    :param execution:    the command executed by the wrapper. """
+
+    def is_cxx_compiler():
+        """ Find out was it a C++ compiler call. Compiler wrapper names
+        contain the compiler type. C++ compiler wrappers ends with `c++`,
+        but might have `.exe` extension on windows. """
+
+        wrapper_command = os.path.basename(sys.argv[0])
+        return re.match(r'(.+)c\+\+(.*)', wrapper_command)
+
+    def run_compiler(executable):
+        """ Execute compilation with the real compiler. """
+
+        command = executable + sys.argv[1:]
+        logging.debug('compilation: %s', command)
+        result = subprocess.call(command)
+        logging.debug('compilation exit code: %d', result)
+        return result
+
+    # Get relevant parameters from environment.
+    parameters = json.loads(os.environ[ENVIRONMENT_KEY])
+    reconfigure_logging(parameters['verbose'])
+    # Execute the requested compilation. Do crash if anything goes wrong.
+    cxx = is_cxx_compiler()
+    compiler = parameters['cxx'] if cxx else parameters['cc']
+    result = run_compiler(compiler)
+    # Call the wrapped method and ignore it's return value.
+    try:
+        call = Execution(
+            pid=os.getpid(),
+            cwd=os.getcwd(),
+            cmd=['c++' if cxx else 'cc'] + sys.argv[1:])
+        function(result, call)
+    except:
+        logging.exception('Compiler wrapper failed complete.')
+    finally:
+        # Always return the real compiler exit code.
+        return result
+
+
+def wrapper_environment(args):
+    """ Set up environment for interpose compiler wrapper."""
+
+    return {
+        ENVIRONMENT_KEY: json.dumps({
+            'verbose': args.verbose,
+            'cc': shlex.split(args.cc),
+            'cxx': shlex.split(args.cxx)
+        })
+    }
diff --git a/tools/scan-build-py/libscanbuild/analyze.py b/tools/scan-build-py/libscanbuild/analyze.py
index 244c34b75837d..a09c72389d762 100644
--- a/tools/scan-build-py/libscanbuild/analyze.py
+++ b/tools/scan-build-py/libscanbuild/analyze.py
@@ -11,72 +11,75 @@ To run the static analyzer against a build is done in multiple steps:
  -- Analyze:   run the analyzer against the captured commands,
  -- Report:    create a cover report from the analyzer outputs.  """
 
-import sys
 import re
 import os
 import os.path
 import json
-import argparse
 import logging
-import subprocess
 import multiprocessing
-from libscanbuild import initialize_logging, tempdir, command_entry_point
-from libscanbuild.runner import run
+import tempfile
+import functools
+import subprocess
+import contextlib
+import datetime
+
+from libscanbuild import command_entry_point, compiler_wrapper, \
+    wrapper_environment, run_build, run_command
+from libscanbuild.arguments import parse_args_for_scan_build, \
+    parse_args_for_analyze_build
 from libscanbuild.intercept import capture
-from libscanbuild.report import report_directory, document
-from libscanbuild.clang import get_checkers
-from libscanbuild.compilation import split_command
+from libscanbuild.report import document
+from libscanbuild.compilation import split_command, classify_source, \
+    compiler_language
+from libscanbuild.clang import get_version, get_arguments
+from libscanbuild.shell import decode
 
-__all__ = ['analyze_build_main', 'analyze_build_wrapper']
+__all__ = ['scan_build', 'analyze_build', 'analyze_compiler_wrapper']
 
 COMPILER_WRAPPER_CC = 'analyze-cc'
 COMPILER_WRAPPER_CXX = 'analyze-c++'
 
 
 @command_entry_point
-def analyze_build_main(bin_dir, from_build_command):
-    """ Entry point for 'analyze-build' and 'scan-build'. """
-
-    parser = create_parser(from_build_command)
-    args = parser.parse_args()
-    validate(parser, args, from_build_command)
-
-    # setup logging
-    initialize_logging(args.verbose)
-    logging.debug('Parsed arguments: %s', args)
-
-    with report_directory(args.output, args.keep_empty) as target_dir:
-        if not from_build_command:
-            # run analyzer only and generate cover report
-            run_analyzer(args, target_dir)
-            number_of_bugs = document(args, target_dir, True)
-            return number_of_bugs if args.status_bugs else 0
-        elif args.intercept_first:
-            # run build command and capture compiler executions
-            exit_code = capture(args, bin_dir)
-            # next step to run the analyzer against the captured commands
+def scan_build():
+    """ Entry point for scan-build command. """
+
+    args = parse_args_for_scan_build()
+    # will re-assign the report directory as new output
+    with report_directory(args.output, args.keep_empty) as args.output:
+        # Run against a build command. there are cases, when analyzer run
+        # is not required. But we need to set up everything for the
+        # wrappers, because 'configure' needs to capture the CC/CXX values
+        # for the Makefile.
+        if args.intercept_first:
+            # Run build command with intercept module.
+            exit_code = capture(args)
+            # Run the analyzer against the captured commands.
             if need_analyzer(args.build):
-                run_analyzer(args, target_dir)
-                # cover report generation and bug counting
-                number_of_bugs = document(args, target_dir, True)
-                # remove the compilation database when it was not requested
-                if os.path.exists(args.cdb):
-                    os.unlink(args.cdb)
-                # set exit status as it was requested
-                return number_of_bugs if args.status_bugs else exit_code
-            else:
-                return exit_code
+                run_analyzer_parallel(args)
         else:
-            # run the build command with compiler wrappers which
-            # execute the analyzer too. (interposition)
-            environment = setup_environment(args, target_dir, bin_dir)
-            logging.debug('run build in environment: %s', environment)
-            exit_code = subprocess.call(args.build, env=environment)
-            logging.debug('build finished with exit code: %d', exit_code)
-            # cover report generation and bug counting
-            number_of_bugs = document(args, target_dir, False)
-            # set exit status as it was requested
-            return number_of_bugs if args.status_bugs else exit_code
+            # Run build command and analyzer with compiler wrappers.
+            environment = setup_environment(args)
+            exit_code = run_build(args.build, env=environment)
+        # Cover report generation and bug counting.
+        number_of_bugs = document(args)
+        # Set exit status as it was requested.
+        return number_of_bugs if args.status_bugs else exit_code
+
+
+@command_entry_point
+def analyze_build():
+    """ Entry point for analyze-build command. """
+
+    args = parse_args_for_analyze_build()
+    # will re-assign the report directory as new output
+    with report_directory(args.output, args.keep_empty) as args.output:
+        # Run the analyzer against a compilation db.
+        run_analyzer_parallel(args)
+        # Cover report generation and bug counting.
+        number_of_bugs = document(args)
+        # Set exit status as it was requested.
+        return number_of_bugs if args.status_bugs else 0
 
 
 def need_analyzer(args):
@@ -92,7 +95,7 @@ def need_analyzer(args):
     return len(args) and not re.search('configure|autogen', args[0])
 
 
-def run_analyzer(args, output_dir):
+def run_analyzer_parallel(args):
     """ Runs the analyzer against the given compilation database. """
 
     def exclude(filename):
@@ -102,7 +105,7 @@ def run_analyzer(args, output_dir):
 
     consts = {
         'clang': args.clang,
-        'output_dir': output_dir,
+        'output_dir': args.output,
         'output_format': args.output_format,
         'output_failures': args.output_failures,
         'direct_args': analyzer_params(args),
@@ -124,18 +127,16 @@ def run_analyzer(args, output_dir):
         pool.join()
 
 
-def setup_environment(args, destination, bin_dir):
+def setup_environment(args):
     """ Set up environment for build command to interpose compiler wrapper. """
 
     environment = dict(os.environ)
+    environment.update(wrapper_environment(args))
     environment.update({
-        'CC': os.path.join(bin_dir, COMPILER_WRAPPER_CC),
-        'CXX': os.path.join(bin_dir, COMPILER_WRAPPER_CXX),
-        'ANALYZE_BUILD_CC': args.cc,
-        'ANALYZE_BUILD_CXX': args.cxx,
+        'CC': COMPILER_WRAPPER_CC,
+        'CXX': COMPILER_WRAPPER_CXX,
         'ANALYZE_BUILD_CLANG': args.clang if need_analyzer(args.build) else '',
-        'ANALYZE_BUILD_VERBOSE': 'DEBUG' if args.verbose > 2 else 'WARNING',
-        'ANALYZE_BUILD_REPORT_DIR': destination,
+        'ANALYZE_BUILD_REPORT_DIR': args.output,
         'ANALYZE_BUILD_REPORT_FORMAT': args.output_format,
         'ANALYZE_BUILD_REPORT_FAILURES': 'yes' if args.output_failures else '',
         'ANALYZE_BUILD_PARAMETERS': ' '.join(analyzer_params(args)),
@@ -144,51 +145,78 @@ def setup_environment(args, destination, bin_dir):
     return environment
 
 
-def analyze_build_wrapper(cplusplus):
+@command_entry_point
+def analyze_compiler_wrapper():
     """ Entry point for `analyze-cc` and `analyze-c++` compiler wrappers. """
 
-    # initialize wrapper logging
-    logging.basicConfig(format='analyze: %(levelname)s: %(message)s',
-                        level=os.getenv('ANALYZE_BUILD_VERBOSE', 'INFO'))
-    # execute with real compiler
-    compiler = os.getenv('ANALYZE_BUILD_CXX', 'c++') if cplusplus \
-        else os.getenv('ANALYZE_BUILD_CC', 'cc')
-    compilation = [compiler] + sys.argv[1:]
-    logging.info('execute compiler: %s', compilation)
-    result = subprocess.call(compilation)
-    # exit when it fails, ...
+    return compiler_wrapper(analyze_compiler_wrapper_impl)
+
+
+def analyze_compiler_wrapper_impl(result, execution):
+    """ Implements analyzer compiler wrapper functionality. """
+
+    # don't run analyzer when compilation fails. or when it's not requested.
     if result or not os.getenv('ANALYZE_BUILD_CLANG'):
-        return result
-    # ... and run the analyzer if all went well.
+        return
+
+    # check is it a compilation?
+    compilation = split_command(execution.cmd)
+    if compilation is None:
+        return
+    # collect the needed parameters from environment, crash when missing
+    parameters = {
+        'clang': os.getenv('ANALYZE_BUILD_CLANG'),
+        'output_dir': os.getenv('ANALYZE_BUILD_REPORT_DIR'),
+        'output_format': os.getenv('ANALYZE_BUILD_REPORT_FORMAT'),
+        'output_failures': os.getenv('ANALYZE_BUILD_REPORT_FAILURES'),
+        'direct_args': os.getenv('ANALYZE_BUILD_PARAMETERS',
+                                 '').split(' '),
+        'force_debug': os.getenv('ANALYZE_BUILD_FORCE_DEBUG'),
+        'directory': execution.cwd,
+        'command': [execution.cmd[0], '-c'] + compilation.flags
+    }
+    # call static analyzer against the compilation
+    for source in compilation.files:
+        parameters.update({'file': source})
+        logging.debug('analyzer parameters %s', parameters)
+        current = run(parameters)
+        # display error message from the static analyzer
+        if current is not None:
+            for line in current['error_output']:
+                logging.info(line.rstrip())
+
+
+@contextlib.contextmanager
+def report_directory(hint, keep):
+    """ Responsible for the report directory.
+
+    hint -- could specify the parent directory of the output directory.
+    keep -- a boolean value to keep or delete the empty report directory. """
+
+    stamp_format = 'scan-build-%Y-%m-%d-%H-%M-%S-%f-'
+    stamp = datetime.datetime.now().strftime(stamp_format)
+    parent_dir = os.path.abspath(hint)
+    if not os.path.exists(parent_dir):
+        os.makedirs(parent_dir)
+    name = tempfile.mkdtemp(prefix=stamp, dir=parent_dir)
+
+    logging.info('Report directory created: %s', name)
+
     try:
-        # check is it a compilation
-        compilation = split_command(sys.argv)
-        if compilation is None:
-            return result
-        # collect the needed parameters from environment, crash when missing
-        parameters = {
-            'clang': os.getenv('ANALYZE_BUILD_CLANG'),
-            'output_dir': os.getenv('ANALYZE_BUILD_REPORT_DIR'),
-            'output_format': os.getenv('ANALYZE_BUILD_REPORT_FORMAT'),
-            'output_failures': os.getenv('ANALYZE_BUILD_REPORT_FAILURES'),
-            'direct_args': os.getenv('ANALYZE_BUILD_PARAMETERS',
-                                     '').split(' '),
-            'force_debug': os.getenv('ANALYZE_BUILD_FORCE_DEBUG'),
-            'directory': os.getcwd(),
-            'command': [sys.argv[0], '-c'] + compilation.flags
-        }
-        # call static analyzer against the compilation
-        for source in compilation.files:
-            parameters.update({'file': source})
-            logging.debug('analyzer parameters %s', parameters)
-            current = run(parameters)
-            # display error message from the static analyzer
-            if current is not None:
-                for line in current['error_output']:
-                    logging.info(line.rstrip())
-    except Exception:
-        logging.exception("run analyzer inside compiler wrapper failed.")
-    return result
+        yield name
+    finally:
+        if os.listdir(name):
+            msg = "Run 'scan-view %s' to examine bug reports."
+            keep = True
+        else:
+            if keep:
+                msg = "Report directory '%s' contains no report, but kept."
+            else:
+                msg = "Removing directory '%s' because it contains no report."
+        logging.warning(msg, name)
+
+        if not keep:
+            os.rmdir(name)
 
 
 def analyzer_params(args):
@@ -238,279 +266,275 @@ def analyzer_params(args):
     return prefix_with('-Xclang', result)
 
 
-def print_active_checkers(checkers):
-    """ Print active checkers to stdout. """
+def require(required):
+    """ Decorator for checking the required values in state.
 
-    for name in sorted(name for name, (_, active) in checkers.items()
-                       if active):
-        print(name)
+    It checks the required attributes in the passed state and stop when
+    any of those is missing. """
 
+    def decorator(function):
+        @functools.wraps(function)
+        def wrapper(*args, **kwargs):
+            for key in required:
+                if key not in args[0]:
+                    raise KeyError('{0} not passed to {1}'.format(
+                        key, function.__name__))
 
-def print_checkers(checkers):
-    """ Print verbose checker help to stdout. """
+            return function(*args, **kwargs)
 
-    print('')
-    print('available checkers:')
-    print('')
-    for name in sorted(checkers.keys()):
-        description, active = checkers[name]
-        prefix = '+' if active else ' '
-        if len(name) > 30:
-            print(' {0} {1}'.format(prefix, name))
-            print(' ' * 35 + description)
+        return wrapper
+
+    return decorator
+
+
+@require(['command',  # entry from compilation database
+          'directory',  # entry from compilation database
+          'file',  # entry from compilation database
+          'clang',  # clang executable name (and path)
+          'direct_args',  # arguments from command line
+          'force_debug',  # kill non debug macros
+          'output_dir',  # where generated report files shall go
+          'output_format',  # it's 'plist' or 'html' or both
+          'output_failures'])  # generate crash reports or not
+def run(opts):
+    """ Entry point to run (or not) static analyzer against a single entry
+    of the compilation database.
+
+    This complex task is decomposed into smaller methods which are calling
+    each other in chain. If the analyzis is not possibe the given method
+    just return and break the chain.
+
+    The passed parameter is a python dictionary. Each method first check
+    that the needed parameters received. (This is done by the 'require'
+    decorator. It's like an 'assert' to check the contract between the
+    caller and the called method.) """
+
+    try:
+        command = opts.pop('command')
+        command = command if isinstance(command, list) else decode(command)
+        logging.debug("Run analyzer against '%s'", command)
+        opts.update(classify_parameters(command))
+
+        return arch_check(opts)
+    except Exception:
+        logging.error("Problem occured during analyzis.", exc_info=1)
+        return None
+
+
+@require(['clang', 'directory', 'flags', 'file', 'output_dir', 'language',
+          'error_output', 'exit_code'])
+def report_failure(opts):
+    """ Create report when analyzer failed.
+
+    The major report is the preprocessor output. The output filename generated
+    randomly. The compiler output also captured into '.stderr.txt' file.
+    And some more execution context also saved into '.info.txt' file. """
+
+    def extension():
+        """ Generate preprocessor file extension. """
+
+        mapping = {'objective-c++': '.mii', 'objective-c': '.mi', 'c++': '.ii'}
+        return mapping.get(opts['language'], '.i')
+
+    def destination():
+        """ Creates failures directory if not exits yet. """
+
+        failures_dir = os.path.join(opts['output_dir'], 'failures')
+        if not os.path.isdir(failures_dir):
+            os.makedirs(failures_dir)
+        return failures_dir
+
+    # Classify error type: when Clang terminated by a signal it's a 'Crash'.
+    # (python subprocess Popen.returncode is negative when child terminated
+    # by signal.) Everything else is 'Other Error'.
+    error = 'crash' if opts['exit_code'] < 0 else 'other_error'
+    # Create preprocessor output file name. (This is blindly following the
+    # Perl implementation.)
+    (handle, name) = tempfile.mkstemp(suffix=extension(),
+                                      prefix='clang_' + error + '_',
+                                      dir=destination())
+    os.close(handle)
+    # Execute Clang again, but run the syntax check only.
+    cwd = opts['directory']
+    cmd = get_arguments(
+        [opts['clang'], '-fsyntax-only', '-E'
+         ] + opts['flags'] + [opts['file'], '-o', name], cwd)
+    run_command(cmd, cwd=cwd)
+    # write general information about the crash
+    with open(name + '.info.txt', 'w') as handle:
+        handle.write(opts['file'] + os.linesep)
+        handle.write(error.title().replace('_', ' ') + os.linesep)
+        handle.write(' '.join(cmd) + os.linesep)
+        handle.write(' '.join(os.uname()) + os.linesep)
+        handle.write(get_version(opts['clang']))
+        handle.close()
+    # write the captured output too
+    with open(name + '.stderr.txt', 'w') as handle:
+        handle.writelines(opts['error_output'])
+        handle.close()
+
+
+@require(['clang', 'directory', 'flags', 'direct_args', 'file', 'output_dir',
+          'output_format'])
+def run_analyzer(opts, continuation=report_failure):
+    """ It assembles the analysis command line and executes it. Capture the
+    output of the analysis and returns with it. If failure reports are
+    requested, it calls the continuation to generate it. """
+
+    def target():
+        """ Creates output file name for reports. """
+        if opts['output_format'] in {'plist', 'plist-html'}:
+            (handle, name) = tempfile.mkstemp(prefix='report-',
+                                              suffix='.plist',
+                                              dir=opts['output_dir'])
+            os.close(handle)
+            return name
+        return opts['output_dir']
+
+    try:
+        cwd = opts['directory']
+        cmd = get_arguments([opts['clang'], '--analyze'] +
+                            opts['direct_args'] + opts['flags'] +
+                            [opts['file'], '-o', target()],
+                            cwd)
+        output = run_command(cmd, cwd=cwd)
+        return {'error_output': output, 'exit_code': 0}
+    except subprocess.CalledProcessError as ex:
+        result = {'error_output': ex.output, 'exit_code': ex.returncode}
+        if opts.get('output_failures', False):
+            opts.update(result)
+            continuation(opts)
+        return result
+
+
+@require(['flags', 'force_debug'])
+def filter_debug_flags(opts, continuation=run_analyzer):
+    """ Filter out nondebug macros when requested. """
+
+    if opts.pop('force_debug'):
+        # lazy implementation just append an undefine macro at the end
+        opts.update({'flags': opts['flags'] + ['-UNDEBUG']})
+
+    return continuation(opts)
+
+
+@require(['language', 'compiler', 'file', 'flags'])
+def language_check(opts, continuation=filter_debug_flags):
+    """ Find out the language from command line parameters or file name
+    extension. The decision also influenced by the compiler invocation. """
+
+    accepted = frozenset({
+        'c', 'c++', 'objective-c', 'objective-c++', 'c-cpp-output',
+        'c++-cpp-output', 'objective-c-cpp-output'
+    })
+
+    # language can be given as a parameter...
+    language = opts.pop('language')
+    compiler = opts.pop('compiler')
+    # ... or find out from source file extension
+    if language is None and compiler is not None:
+        language = classify_source(opts['file'], compiler == 'c')
+
+    if language is None:
+        logging.debug('skip analysis, language not known')
+        return None
+    elif language not in accepted:
+        logging.debug('skip analysis, language not supported')
+        return None
+    else:
+        logging.debug('analysis, language: %s', language)
+        opts.update({'language': language,
+                     'flags': ['-x', language] + opts['flags']})
+        return continuation(opts)
+
+
+@require(['arch_list', 'flags'])
+def arch_check(opts, continuation=language_check):
+    """ Do run analyzer through one of the given architectures. """
+
+    disabled = frozenset({'ppc', 'ppc64'})
+
+    received_list = opts.pop('arch_list')
+    if received_list:
+        # filter out disabled architectures and -arch switches
+        filtered_list = [a for a in received_list if a not in disabled]
+        if filtered_list:
+            # There should be only one arch given (or the same multiple
+            # times). If there are multiple arch are given and are not
+            # the same, those should not change the pre-processing step.
+            # But that's the only pass we have before run the analyzer.
+            current = filtered_list.pop()
+            logging.debug('analysis, on arch: %s', current)
+
+            opts.update({'flags': ['-arch', current] + opts['flags']})
+            return continuation(opts)
         else:
-            print(' {0} {1: <30}  {2}'.format(prefix, name, description))
-    print('')
-    print('NOTE: "+" indicates that an analysis is enabled by default.')
-    print('')
-
-
-def validate(parser, args, from_build_command):
-    """ Validation done by the parser itself, but semantic check still
-    needs to be done. This method is doing that. """
-
-    # Make plugins always a list. (It might be None when not specified.)
-    args.plugins = args.plugins if args.plugins else []
-
-    if args.help_checkers_verbose:
-        print_checkers(get_checkers(args.clang, args.plugins))
-        parser.exit()
-    elif args.help_checkers:
-        print_active_checkers(get_checkers(args.clang, args.plugins))
-        parser.exit()
-
-    if from_build_command and not args.build:
-        parser.error('missing build command')
-
-
-def create_parser(from_build_command):
-    """ Command line argument parser factory method. """
-
-    parser = argparse.ArgumentParser(
-        formatter_class=argparse.ArgumentDefaultsHelpFormatter)
-
-    parser.add_argument(
-        '--verbose', '-v',
-        action='count',
-        default=0,
-        help="""Enable verbose output from '%(prog)s'. A second and third
-                flag increases verbosity.""")
-    parser.add_argument(
-        '--override-compiler',
-        action='store_true',
-        help="""Always resort to the compiler wrapper even when better
-                interposition methods are available.""")
-    parser.add_argument(
-        '--intercept-first',
-        action='store_true',
-        help="""Run the build commands only, build a compilation database,
-                then run the static analyzer afterwards.
-                Generally speaking it has better coverage on build commands.
-                With '--override-compiler' it use compiler wrapper, but does
-                not run the analyzer till the build is finished. """)
-    parser.add_argument(
-        '--cdb',
-        metavar='<file>',
-        default="compile_commands.json",
-        help="""The JSON compilation database.""")
-
-    parser.add_argument(
-        '--output', '-o',
-        metavar='<path>',
-        default=tempdir(),
-        help="""Specifies the output directory for analyzer reports.
-                Subdirectory will be created if default directory is targeted.
-                """)
-    parser.add_argument(
-        '--status-bugs',
-        action='store_true',
-        help="""By default, the exit status of '%(prog)s' is the same as the
-                executed build command. Specifying this option causes the exit
-                status of '%(prog)s' to be non zero if it found potential bugs
-                and zero otherwise.""")
-    parser.add_argument(
-        '--html-title',
-        metavar='<title>',
-        help="""Specify the title used on generated HTML pages.
-                If not specified, a default title will be used.""")
-    parser.add_argument(
-        '--analyze-headers',
-        action='store_true',
-        help="""Also analyze functions in #included files. By default, such
-                functions are skipped unless they are called by functions
-                within the main source file.""")
-    format_group = parser.add_mutually_exclusive_group()
-    format_group.add_argument(
-        '--plist', '-plist',
-        dest='output_format',
-        const='plist',
-        default='html',
-        action='store_const',
-        help="""This option outputs the results as a set of .plist files.""")
-    format_group.add_argument(
-        '--plist-html', '-plist-html',
-        dest='output_format',
-        const='plist-html',
-        default='html',
-        action='store_const',
-        help="""This option outputs the results as a set of .html and .plist
-                files.""")
-    # TODO: implement '-view '
-
-    advanced = parser.add_argument_group('advanced options')
-    advanced.add_argument(
-        '--keep-empty',
-        action='store_true',
-        help="""Don't remove the build results directory even if no issues
-                were reported.""")
-    advanced.add_argument(
-        '--no-failure-reports', '-no-failure-reports',
-        dest='output_failures',
-        action='store_false',
-        help="""Do not create a 'failures' subdirectory that includes analyzer
-                crash reports and preprocessed source files.""")
-    advanced.add_argument(
-        '--stats', '-stats',
-        action='store_true',
-        help="""Generates visitation statistics for the project being analyzed.
-                """)
-    advanced.add_argument(
-        '--internal-stats',
-        action='store_true',
-        help="""Generate internal analyzer statistics.""")
-    advanced.add_argument(
-        '--maxloop', '-maxloop',
-        metavar='<loop count>',
-        type=int,
-        help="""Specifiy the number of times a block can be visited before
-                giving up. Increase for more comprehensive coverage at a cost
-                of speed.""")
-    advanced.add_argument(
-        '--store', '-store',
-        metavar='<model>',
-        dest='store_model',
-        choices=['region', 'basic'],
-        help="""Specify the store model used by the analyzer.
-                'region' specifies a field- sensitive store model.
-                'basic' which is far less precise but can more quickly
-                analyze code. 'basic' was the default store model for
-                checker-0.221 and earlier.""")
-    advanced.add_argument(
-        '--constraints', '-constraints',
-        metavar='<model>',
-        dest='constraints_model',
-        choices=['range', 'basic'],
-        help="""Specify the contraint engine used by the analyzer. Specifying
-                'basic' uses a simpler, less powerful constraint model used by
-                checker-0.160 and earlier.""")
-    advanced.add_argument(
-        '--use-analyzer',
-        metavar='<path>',
-        dest='clang',
-        default='clang',
-        help="""'%(prog)s' uses the 'clang' executable relative to itself for
-                static analysis. One can override this behavior with this
-                option by using the 'clang' packaged with Xcode (on OS X) or
-                from the PATH.""")
-    advanced.add_argument(
-        '--use-cc',
-        metavar='<path>',
-        dest='cc',
-        default='cc',
-        help="""When '%(prog)s' analyzes a project by interposing a "fake
-                compiler", which executes a real compiler for compilation and
-                do other tasks (to run the static analyzer or just record the
-                compiler invocation). Because of this interposing, '%(prog)s'
-                does not know what compiler your project normally uses.
-                Instead, it simply overrides the CC environment variable, and
-                guesses your default compiler.
-
-                If you need '%(prog)s' to use a specific compiler for
-                *compilation* then you can use this option to specify a path
-                to that compiler.""")
-    advanced.add_argument(
-        '--use-c++',
-        metavar='<path>',
-        dest='cxx',
-        default='c++',
-        help="""This is the same as "--use-cc" but for C++ code.""")
-    advanced.add_argument(
-        '--analyzer-config', '-analyzer-config',
-        metavar='<options>',
-        help="""Provide options to pass through to the analyzer's
-                -analyzer-config flag. Several options are separated with
-                comma: 'key1=val1,key2=val2'
-
-                Available options:
-                    stable-report-filename=true or false (default)
-
-                Switch the page naming to:
-                report-<filename>-<function/method name>-<id>.html
-                instead of report-XXXXXX.html""")
-    advanced.add_argument(
-        '--exclude',
-        metavar='<directory>',
-        dest='excludes',
-        action='append',
-        default=[],
-        help="""Do not run static analyzer against files found in this
-                directory. (You can specify this option multiple times.)
-                Could be usefull when project contains 3rd party libraries.
-                The directory path shall be absolute path as file names in
-                the compilation database.""")
-    advanced.add_argument(
-        '--force-analyze-debug-code',
-        dest='force_debug',
-        action='store_true',
-        help="""Tells analyzer to enable assertions in code even if they were
-                disabled during compilation, enabling more precise results.""")
-
-    plugins = parser.add_argument_group('checker options')
-    plugins.add_argument(
-        '--load-plugin', '-load-plugin',
-        metavar='<plugin library>',
-        dest='plugins',
-        action='append',
-        help="""Loading external checkers using the clang plugin interface.""")
-    plugins.add_argument(
-        '--enable-checker', '-enable-checker',
-        metavar='<checker name>',
-        action=AppendCommaSeparated,
-        help="""Enable specific checker.""")
-    plugins.add_argument(
-        '--disable-checker', '-disable-checker',
-        metavar='<checker name>',
-        action=AppendCommaSeparated,
-        help="""Disable specific checker.""")
-    plugins.add_argument(
-        '--help-checkers',
-        action='store_true',
-        help="""A default group of checkers is run unless explicitly disabled.
-                Exactly which checkers constitute the default group is a
-                function of the operating system in use. These can be printed
-                with this flag.""")
-    plugins.add_argument(
-        '--help-checkers-verbose',
-        action='store_true',
-        help="""Print all available checkers and mark the enabled ones.""")
-
-    if from_build_command:
-        parser.add_argument(
-            dest='build',
-            nargs=argparse.REMAINDER,
-            help="""Command to run.""")
-
-    return parser
-
-
-class AppendCommaSeparated(argparse.Action):
-    """ argparse Action class to support multiple comma separated lists. """
-
-    def __call__(self, __parser, namespace, values, __option_string):
-        # getattr(obj, attr, default) does not really returns default but none
-        if getattr(namespace, self.dest, None) is None:
-            setattr(namespace, self.dest, [])
-        # once it's fixed we can use as expected
-        actual = getattr(namespace, self.dest)
-        actual.extend(values.split(','))
-        setattr(namespace, self.dest, actual)
+            logging.debug('skip analysis, found not supported arch')
+            return None
+    else:
+        logging.debug('analysis, on default arch')
+        return continuation(opts)
+
+# To have good results from static analyzer certain compiler options shall be
+# omitted. The compiler flag filtering only affects the static analyzer run.
+#
+# Keys are the option name, value number of options to skip
+IGNORED_FLAGS = {
+    '-c': 0,  # compile option will be overwritten
+    '-fsyntax-only': 0,  # static analyzer option will be overwritten
+    '-o': 1,  # will set up own output file
+    # flags below are inherited from the perl implementation.
+    '-g': 0,
+    '-save-temps': 0,
+    '-install_name': 1,
+    '-exported_symbols_list': 1,
+    '-current_version': 1,
+    '-compatibility_version': 1,
+    '-init': 1,
+    '-e': 1,
+    '-seg1addr': 1,
+    '-bundle_loader': 1,
+    '-multiply_defined': 1,
+    '-sectorder': 3,
+    '--param': 1,
+    '--serialize-diagnostics': 1
+}
+
+
+def classify_parameters(command):
+    """ Prepare compiler flags (filters some and add others) and take out
+    language (-x) and architecture (-arch) flags for future processing. """
+
+    result = {
+        'flags': [],  # the filtered compiler flags
+        'arch_list': [],  # list of architecture flags
+        'language': None,  # compilation language, None, if not specified
+        'compiler': compiler_language(command)  # 'c' or 'c++'
+    }
+
+    # iterate on the compile options
+    args = iter(command[1:])
+    for arg in args:
+        # take arch flags into a separate basket
+        if arg == '-arch':
+            result['arch_list'].append(next(args))
+        # take language
+        elif arg == '-x':
+            result['language'] = next(args)
+        # parameters which looks source file are not flags
+        elif re.match(r'^[^-].+', arg) and classify_source(arg):
+            pass
+        # ignore some flags
+        elif arg in IGNORED_FLAGS:
+            count = IGNORED_FLAGS[arg]
+            for _ in range(count):
+                next(args)
+        # we don't care about extra warnings, but we should suppress ones
+        # that we don't want to see.
+        elif re.match(r'^-W.+', arg) and not re.match(r'^-Wno-.+', arg):
+            pass
+        # and consider everything else as compilation flag.
+        else:
+            result['flags'].append(arg)
+
+    return result
diff --git a/tools/scan-build-py/libscanbuild/arguments.py b/tools/scan-build-py/libscanbuild/arguments.py
new file mode 100644
index 0000000000000..2735123f9f163
--- /dev/null
+++ b/tools/scan-build-py/libscanbuild/arguments.py
@@ -0,0 +1,431 @@
+# -*- coding: utf-8 -*-
+#                     The LLVM Compiler Infrastructure
+#
+# This file is distributed under the University of Illinois Open Source
+# License. See LICENSE.TXT for details.
+""" This module parses and validates arguments for command-line interfaces.
+
+It uses argparse module to create the command line parser. (This library is
+in the standard python library since 3.2 and backported to 2.7, but not
+earlier.)
+
+It also implements basic validation methods, related to the command.
+Validations are mostly calling specific help methods, or mangling values.
+"""
+
+import os
+import sys
+import argparse
+import logging
+import tempfile
+from libscanbuild import reconfigure_logging
+from libscanbuild.clang import get_checkers
+
+__all__ = ['parse_args_for_intercept_build', 'parse_args_for_analyze_build',
+           'parse_args_for_scan_build']
+
+
+def parse_args_for_intercept_build():
+    """ Parse and validate command-line arguments for intercept-build. """
+
+    parser = create_intercept_parser()
+    args = parser.parse_args()
+
+    reconfigure_logging(args.verbose)
+    logging.debug('Raw arguments %s', sys.argv)
+
+    # short validation logic
+    if not args.build:
+        parser.error(message='missing build command')
+
+    logging.debug('Parsed arguments: %s', args)
+    return args
+
+
+def parse_args_for_analyze_build():
+    """ Parse and validate command-line arguments for analyze-build. """
+
+    from_build_command = False
+    parser = create_analyze_parser(from_build_command)
+    args = parser.parse_args()
+
+    reconfigure_logging(args.verbose)
+    logging.debug('Raw arguments %s', sys.argv)
+
+    normalize_args_for_analyze(args, from_build_command)
+    validate_args_for_analyze(parser, args, from_build_command)
+    logging.debug('Parsed arguments: %s', args)
+    return args
+
+
+def parse_args_for_scan_build():
+    """ Parse and validate command-line arguments for scan-build. """
+
+    from_build_command = True
+    parser = create_analyze_parser(from_build_command)
+    args = parser.parse_args()
+
+    reconfigure_logging(args.verbose)
+    logging.debug('Raw arguments %s', sys.argv)
+
+    normalize_args_for_analyze(args, from_build_command)
+    validate_args_for_analyze(parser, args, from_build_command)
+    logging.debug('Parsed arguments: %s', args)
+    return args
+
+
+def normalize_args_for_analyze(args, from_build_command):
+    """ Normalize parsed arguments for analyze-build and scan-build.
+
+    :param args: Parsed argument object. (Will be mutated.)
+    :param from_build_command: Boolean value tells is the command suppose
+    to run the analyzer against a build command or a compilation db. """
+
+    # make plugins always a list. (it might be None when not specified.)
+    if args.plugins is None:
+        args.plugins = []
+
+    # make exclude directory list unique and absolute.
+    uniq_excludes = set(os.path.abspath(entry) for entry in args.excludes)
+    args.excludes = list(uniq_excludes)
+
+    # because shared codes for all tools, some common used methods are
+    # expecting some argument to be present. so, instead of query the args
+    # object about the presence of the flag, we fake it here. to make those
+    # methods more readable. (it's an arguable choice, took it only for those
+    # which have good default value.)
+    if from_build_command:
+        # add cdb parameter invisibly to make report module working.
+        args.cdb = 'compile_commands.json'
+
+
+def validate_args_for_analyze(parser, args, from_build_command):
+    """ Command line parsing is done by the argparse module, but semantic
+    validation still needs to be done. This method is doing it for
+    analyze-build and scan-build commands.
+
+    :param parser: The command line parser object.
+    :param args: Parsed argument object.
+    :param from_build_command: Boolean value tells is the command suppose
+    to run the analyzer against a build command or a compilation db.
+    :return: No return value, but this call might throw when validation
+    fails. """
+
+    if args.help_checkers_verbose:
+        print_checkers(get_checkers(args.clang, args.plugins))
+        parser.exit(status=0)
+    elif args.help_checkers:
+        print_active_checkers(get_checkers(args.clang, args.plugins))
+        parser.exit(status=0)
+    elif from_build_command and not args.build:
+        parser.error(message='missing build command')
+    elif not from_build_command and not os.path.exists(args.cdb):
+        parser.error(message='compilation database is missing')
+
+
+def create_intercept_parser():
+    """ Creates a parser for command-line arguments to 'intercept'. """
+
+    parser = create_default_parser()
+    parser_add_cdb(parser)
+
+    parser_add_prefer_wrapper(parser)
+    parser_add_compilers(parser)
+
+    advanced = parser.add_argument_group('advanced options')
+    group = advanced.add_mutually_exclusive_group()
+    group.add_argument(
+        '--append',
+        action='store_true',
+        help="""Extend existing compilation database with new entries.
+        Duplicate entries are detected and not present in the final output.
+        The output is not continuously updated, it's done when the build
+        command finished. """)
+
+    parser.add_argument(
+        dest='build', nargs=argparse.REMAINDER, help="""Command to run.""")
+    return parser
+
+
+def create_analyze_parser(from_build_command):
+    """ Creates a parser for command-line arguments to 'analyze'. """
+
+    parser = create_default_parser()
+
+    if from_build_command:
+        parser_add_prefer_wrapper(parser)
+        parser_add_compilers(parser)
+
+        parser.add_argument(
+            '--intercept-first',
+            action='store_true',
+            help="""Run the build commands first, intercept compiler
+            calls and then run the static analyzer afterwards.
+            Generally speaking it has better coverage on build commands.
+            With '--override-compiler' it use compiler wrapper, but does
+            not run the analyzer till the build is finished.""")
+    else:
+        parser_add_cdb(parser)
+
+    parser.add_argument(
+        '--status-bugs',
+        action='store_true',
+        help="""The exit status of '%(prog)s' is the same as the executed
+        build command. This option ignores the build exit status and sets to
+        be non zero if it found potential bugs or zero otherwise.""")
+    parser.add_argument(
+        '--exclude',
+        metavar='<directory>',
+        dest='excludes',
+        action='append',
+        default=[],
+        help="""Do not run static analyzer against files found in this
+        directory. (You can specify this option multiple times.)
+        Could be useful when project contains 3rd party libraries.""")
+
+    output = parser.add_argument_group('output control options')
+    output.add_argument(
+        '--output',
+        '-o',
+        metavar='<path>',
+        default=tempfile.gettempdir(),
+        help="""Specifies the output directory for analyzer reports.
+        Subdirectory will be created if default directory is targeted.""")
+    output.add_argument(
+        '--keep-empty',
+        action='store_true',
+        help="""Don't remove the build results directory even if no issues
+        were reported.""")
+    output.add_argument(
+        '--html-title',
+        metavar='<title>',
+        help="""Specify the title used on generated HTML pages.
+        If not specified, a default title will be used.""")
+    format_group = output.add_mutually_exclusive_group()
+    format_group.add_argument(
+        '--plist',
+        '-plist',
+        dest='output_format',
+        const='plist',
+        default='html',
+        action='store_const',
+        help="""Cause the results as a set of .plist files.""")
+    format_group.add_argument(
+        '--plist-html',
+        '-plist-html',
+        dest='output_format',
+        const='plist-html',
+        default='html',
+        action='store_const',
+        help="""Cause the results as a set of .html and .plist files.""")
+    # TODO: implement '-view '
+
+    advanced = parser.add_argument_group('advanced options')
+    advanced.add_argument(
+        '--use-analyzer',
+        metavar='<path>',
+        dest='clang',
+        default='clang',
+        help="""'%(prog)s' uses the 'clang' executable relative to itself for
+        static analysis. One can override this behavior with this option by
+        using the 'clang' packaged with Xcode (on OS X) or from the PATH.""")
+    advanced.add_argument(
+        '--no-failure-reports',
+        '-no-failure-reports',
+        dest='output_failures',
+        action='store_false',
+        help="""Do not create a 'failures' subdirectory that includes analyzer
+        crash reports and preprocessed source files.""")
+    parser.add_argument(
+        '--analyze-headers',
+        action='store_true',
+        help="""Also analyze functions in #included files. By default, such
+        functions are skipped unless they are called by functions within the
+        main source file.""")
+    advanced.add_argument(
+        '--stats',
+        '-stats',
+        action='store_true',
+        help="""Generates visitation statistics for the project.""")
+    advanced.add_argument(
+        '--internal-stats',
+        action='store_true',
+        help="""Generate internal analyzer statistics.""")
+    advanced.add_argument(
+        '--maxloop',
+        '-maxloop',
+        metavar='<loop count>',
+        type=int,
+        help="""Specifiy the number of times a block can be visited before
+        giving up. Increase for more comprehensive coverage at a cost of
+        speed.""")
+    advanced.add_argument(
+        '--store',
+        '-store',
+        metavar='<model>',
+        dest='store_model',
+        choices=['region', 'basic'],
+        help="""Specify the store model used by the analyzer. 'region'
+        specifies a field- sensitive store model. 'basic' which is far less
+        precise but can more quickly analyze code. 'basic' was the default
+        store model for checker-0.221 and earlier.""")
+    advanced.add_argument(
+        '--constraints',
+        '-constraints',
+        metavar='<model>',
+        dest='constraints_model',
+        choices=['range', 'basic'],
+        help="""Specify the constraint engine used by the analyzer. Specifying
+        'basic' uses a simpler, less powerful constraint model used by
+        checker-0.160 and earlier.""")
+    advanced.add_argument(
+        '--analyzer-config',
+        '-analyzer-config',
+        metavar='<options>',
+        help="""Provide options to pass through to the analyzer's
+        -analyzer-config flag. Several options are separated with comma:
+        'key1=val1,key2=val2'
+
+        Available options:
+            stable-report-filename=true or false (default)
+
+        Switch the page naming to:
+        report-<filename>-<function/method name>-<id>.html
+        instead of report-XXXXXX.html""")
+    advanced.add_argument(
+        '--force-analyze-debug-code',
+        dest='force_debug',
+        action='store_true',
+        help="""Tells analyzer to enable assertions in code even if they were
+        disabled during compilation, enabling more precise results.""")
+
+    plugins = parser.add_argument_group('checker options')
+    plugins.add_argument(
+        '--load-plugin',
+        '-load-plugin',
+        metavar='<plugin library>',
+        dest='plugins',
+        action='append',
+        help="""Loading external checkers using the clang plugin interface.""")
+    plugins.add_argument(
+        '--enable-checker',
+        '-enable-checker',
+        metavar='<checker name>',
+        action=AppendCommaSeparated,
+        help="""Enable specific checker.""")
+    plugins.add_argument(
+        '--disable-checker',
+        '-disable-checker',
+        metavar='<checker name>',
+        action=AppendCommaSeparated,
+        help="""Disable specific checker.""")
+    plugins.add_argument(
+        '--help-checkers',
+        action='store_true',
+        help="""A default group of checkers is run unless explicitly disabled.
+        Exactly which checkers constitute the default group is a function of
+        the operating system in use. These can be printed with this flag.""")
+    plugins.add_argument(
+        '--help-checkers-verbose',
+        action='store_true',
+        help="""Print all available checkers and mark the enabled ones.""")
+
+    if from_build_command:
+        parser.add_argument(
+            dest='build', nargs=argparse.REMAINDER, help="""Command to run.""")
+    return parser
+
+
+def create_default_parser():
+    """ Creates command line parser for all build wrapper commands. """
+
+    parser = argparse.ArgumentParser(
+        formatter_class=argparse.ArgumentDefaultsHelpFormatter)
+
+    parser.add_argument(
+        '--verbose',
+        '-v',
+        action='count',
+        default=0,
+        help="""Enable verbose output from '%(prog)s'. A second, third and
+        fourth flags increases verbosity.""")
+    return parser
+
+
+def parser_add_cdb(parser):
+    parser.add_argument(
+        '--cdb',
+        metavar='<file>',
+        default="compile_commands.json",
+        help="""The JSON compilation database.""")
+
+
+def parser_add_prefer_wrapper(parser):
+    parser.add_argument(
+        '--override-compiler',
+        action='store_true',
+        help="""Always resort to the compiler wrapper even when better
+        intercept methods are available.""")
+
+
+def parser_add_compilers(parser):
+    parser.add_argument(
+        '--use-cc',
+        metavar='<path>',
+        dest='cc',
+        default=os.getenv('CC', 'cc'),
+        help="""When '%(prog)s' analyzes a project by interposing a compiler
+        wrapper, which executes a real compiler for compilation and do other
+        tasks (record the compiler invocation). Because of this interposing,
+        '%(prog)s' does not know what compiler your project normally uses.
+        Instead, it simply overrides the CC environment variable, and guesses
+        your default compiler.
+
+        If you need '%(prog)s' to use a specific compiler for *compilation*
+        then you can use this option to specify a path to that compiler.""")
+    parser.add_argument(
+        '--use-c++',
+        metavar='<path>',
+        dest='cxx',
+        default=os.getenv('CXX', 'c++'),
+        help="""This is the same as "--use-cc" but for C++ code.""")
+
+
+class AppendCommaSeparated(argparse.Action):
+    """ argparse Action class to support multiple comma separated lists. """
+
+    def __call__(self, __parser, namespace, values, __option_string):
+        # getattr(obj, attr, default) does not really returns default but none
+        if getattr(namespace, self.dest, None) is None:
+            setattr(namespace, self.dest, [])
+        # once it's fixed we can use as expected
+        actual = getattr(namespace, self.dest)
+        actual.extend(values.split(','))
+        setattr(namespace, self.dest, actual)
+
+
+def print_active_checkers(checkers):
+    """ Print active checkers to stdout. """
+
+    for name in sorted(name for name, (_, active) in checkers.items()
+                       if active):
+        print(name)
+
+
+def print_checkers(checkers):
+    """ Print verbose checker help to stdout. """
+
+    print('')
+    print('available checkers:')
+    print('')
+    for name in sorted(checkers.keys()):
+        description, active = checkers[name]
+        prefix = '+' if active else ' '
+        if len(name) > 30:
+            print(' {0} {1}'.format(prefix, name))
+            print(' ' * 35 + description)
+        else:
+            print(' {0} {1: <30}  {2}'.format(prefix, name, description))
+    print('')
+    print('NOTE: "+" indicates that an analysis is enabled by default.')
+    print('')
diff --git a/tools/scan-build-py/libscanbuild/clang.py b/tools/scan-build-py/libscanbuild/clang.py
index 833e77d28bbe1..192e708782c10 100644
--- a/tools/scan-build-py/libscanbuild/clang.py
+++ b/tools/scan-build-py/libscanbuild/clang.py
@@ -9,8 +9,7 @@ Since Clang command line interface is so rich, but this project is using only
 a subset of that, it makes sense to create a function specific wrapper. """
 
 import re
-import subprocess
-import logging
+from libscanbuild import run_command
 from libscanbuild.shell import decode
 
 __all__ = ['get_version', 'get_arguments', 'get_checkers']
@@ -25,8 +24,9 @@ def get_version(clang):
     :param clang:   the compiler we are using
     :return:        the version string printed to stderr """
 
-    output = subprocess.check_output([clang, '-v'], stderr=subprocess.STDOUT)
-    return output.decode('utf-8').splitlines()[0]
+    output = run_command([clang, '-v'])
+    # the relevant version info is in the first line
+    return output[0]
 
 
 def get_arguments(command, cwd):
@@ -38,12 +38,11 @@ def get_arguments(command, cwd):
 
     cmd = command[:]
     cmd.insert(1, '-###')
-    logging.debug('exec command in %s: %s', cwd, ' '.join(cmd))
 
-    output = subprocess.check_output(cmd, cwd=cwd, stderr=subprocess.STDOUT)
+    output = run_command(cmd, cwd=cwd)
     # The relevant information is in the last line of the output.
     # Don't check if finding last line fails, would throw exception anyway.
-    last_line = output.decode('utf-8').splitlines()[-1]
+    last_line = output[-1]
     if re.search(r'clang(.*): error:', last_line):
         raise Exception(last_line)
     return decode(last_line)
@@ -141,9 +140,7 @@ def get_checkers(clang, plugins):
     load = [elem for plugin in plugins for elem in ['-load', plugin]]
     cmd = [clang, '-cc1'] + load + ['-analyzer-checker-help']
 
-    logging.debug('exec command: %s', ' '.join(cmd))
-    output = subprocess.check_output(cmd, stderr=subprocess.STDOUT)
-    lines = output.decode('utf-8').splitlines()
+    lines = run_command(cmd)
 
     is_active_checker = is_active(get_active_checkers(clang, plugins))
 
diff --git a/tools/scan-build-py/libscanbuild/intercept.py b/tools/scan-build-py/libscanbuild/intercept.py
index 6a9f75349fb58..b9bf9e917526d 100644
--- a/tools/scan-build-py/libscanbuild/intercept.py
+++ b/tools/scan-build-py/libscanbuild/intercept.py
@@ -27,16 +27,16 @@ import re
 import itertools
 import json
 import glob
-import argparse
 import logging
-import subprocess
 from libear import build_libear, TemporaryDirectory
-from libscanbuild import command_entry_point
-from libscanbuild import duplicate_check, tempdir, initialize_logging
+from libscanbuild import command_entry_point, compiler_wrapper, \
+    wrapper_environment, run_command, run_build
+from libscanbuild import duplicate_check
 from libscanbuild.compilation import split_command
+from libscanbuild.arguments import parse_args_for_intercept_build
 from libscanbuild.shell import encode, decode
 
-__all__ = ['capture', 'intercept_build_main', 'intercept_build_wrapper']
+__all__ = ['capture', 'intercept_build', 'intercept_compiler_wrapper']
 
 GS = chr(0x1d)
 RS = chr(0x1e)
@@ -44,26 +44,19 @@ US = chr(0x1f)
 
 COMPILER_WRAPPER_CC = 'intercept-cc'
 COMPILER_WRAPPER_CXX = 'intercept-c++'
+TRACE_FILE_EXTENSION = '.cmd'  # same as in ear.c
+WRAPPER_ONLY_PLATFORMS = frozenset({'win32', 'cygwin'})
 
 
 @command_entry_point
-def intercept_build_main(bin_dir):
+def intercept_build():
     """ Entry point for 'intercept-build' command. """
 
-    parser = create_parser()
-    args = parser.parse_args()
+    args = parse_args_for_intercept_build()
+    return capture(args)
 
-    initialize_logging(args.verbose)
-    logging.debug('Parsed arguments: %s', args)
 
-    if not args.build:
-        parser.print_help()
-        return 0
-
-    return capture(args, bin_dir)
-
-
-def capture(args, bin_dir):
+def capture(args):
     """ The entry point of build command interception. """
 
     def post_processing(commands):
@@ -91,28 +84,23 @@ def capture(args, bin_dir):
                 for entry in itertools.chain(previous, current)
                 if os.path.exists(entry['file']) and not duplicate(entry))
 
-    with TemporaryDirectory(prefix='intercept-', dir=tempdir()) as tmp_dir:
+    with TemporaryDirectory(prefix='intercept-') as tmp_dir:
         # run the build command
-        environment = setup_environment(args, tmp_dir, bin_dir)
-        logging.debug('run build in environment: %s', environment)
-        exit_code = subprocess.call(args.build, env=environment)
-        logging.info('build finished with exit code: %d', exit_code)
+        environment = setup_environment(args, tmp_dir)
+        exit_code = run_build(args.build, env=environment)
         # read the intercepted exec calls
         exec_traces = itertools.chain.from_iterable(
             parse_exec_trace(os.path.join(tmp_dir, filename))
             for filename in sorted(glob.iglob(os.path.join(tmp_dir, '*.cmd'))))
-        # do post processing only if that was requested
-        if 'raw_entries' not in args or not args.raw_entries:
-            entries = post_processing(exec_traces)
-        else:
-            entries = exec_traces
+        # do post processing
+        entries = post_processing(exec_traces)
         # dump the compilation database
         with open(args.cdb, 'w+') as handle:
             json.dump(list(entries), handle, sort_keys=True, indent=4)
         return exit_code
 
 
-def setup_environment(args, destination, bin_dir):
+def setup_environment(args, destination):
     """ Sets up the environment for the build command.
 
     It sets the required environment variables and execute the given command.
@@ -130,12 +118,10 @@ def setup_environment(args, destination, bin_dir):
 
     if not libear_path:
         logging.debug('intercept gonna use compiler wrappers')
+        environment.update(wrapper_environment(args))
         environment.update({
-            'CC': os.path.join(bin_dir, COMPILER_WRAPPER_CC),
-            'CXX': os.path.join(bin_dir, COMPILER_WRAPPER_CXX),
-            'INTERCEPT_BUILD_CC': c_compiler,
-            'INTERCEPT_BUILD_CXX': cxx_compiler,
-            'INTERCEPT_BUILD_VERBOSE': 'DEBUG' if args.verbose > 2 else 'INFO'
+            'CC': COMPILER_WRAPPER_CC,
+            'CXX': COMPILER_WRAPPER_CXX
         })
     elif sys.platform == 'darwin':
         logging.debug('intercept gonna preload libear on OSX')
@@ -150,42 +136,49 @@ def setup_environment(args, destination, bin_dir):
     return environment
 
 
-def intercept_build_wrapper(cplusplus):
-    """ Entry point for `intercept-cc` and `intercept-c++` compiler wrappers.
+@command_entry_point
+def intercept_compiler_wrapper():
+    """ Entry point for `intercept-cc` and `intercept-c++`. """
+
+    return compiler_wrapper(intercept_compiler_wrapper_impl)
+
+
+def intercept_compiler_wrapper_impl(_, execution):
+    """ Implement intercept compiler wrapper functionality.
 
-    It does generate execution report into target directory. And execute
-    the wrapped compilation with the real compiler. The parameters for
-    report and execution are from environment variables.
+    It does generate execution report into target directory.
+    The target directory name is from environment variables. """
 
-    Those parameters which for 'libear' library can't have meaningful
-    values are faked. """
+    message_prefix = 'execution report might be incomplete: %s'
 
-    # initialize wrapper logging
-    logging.basicConfig(format='intercept: %(levelname)s: %(message)s',
-                        level=os.getenv('INTERCEPT_BUILD_VERBOSE', 'INFO'))
-    # write report
+    target_dir = os.getenv('INTERCEPT_BUILD_TARGET_DIR')
+    if not target_dir:
+        logging.warning(message_prefix, 'missing target directory')
+        return
+    # write current execution info to the pid file
     try:
-        target_dir = os.getenv('INTERCEPT_BUILD_TARGET_DIR')
-        if not target_dir:
-            raise UserWarning('exec report target directory not found')
-        pid = str(os.getpid())
-        target_file = os.path.join(target_dir, pid + '.cmd')
-        logging.debug('writing exec report to: %s', target_file)
-        with open(target_file, 'ab') as handler:
-            working_dir = os.getcwd()
-            command = US.join(sys.argv) + US
-            content = RS.join([pid, pid, 'wrapper', working_dir, command]) + GS
-            handler.write(content.encode('utf-8'))
+        target_file_name = str(os.getpid()) + TRACE_FILE_EXTENSION
+        target_file = os.path.join(target_dir, target_file_name)
+        logging.debug('writing execution report to: %s', target_file)
+        write_exec_trace(target_file, execution)
     except IOError:
-        logging.exception('writing exec report failed')
-    except UserWarning as warning:
-        logging.warning(warning)
-    # execute with real compiler
-    compiler = os.getenv('INTERCEPT_BUILD_CXX', 'c++') if cplusplus \
-        else os.getenv('INTERCEPT_BUILD_CC', 'cc')
-    compilation = [compiler] + sys.argv[1:]
-    logging.debug('execute compiler: %s', compilation)
-    return subprocess.call(compilation)
+        logging.warning(message_prefix, 'io problem')
+
+
+def write_exec_trace(filename, entry):
+    """ Write execution report file.
+
+    This method shall be sync with the execution report writer in interception
+    library. The entry in the file is a JSON objects.
+
+    :param filename:    path to the output execution trace file,
+    :param entry:       the Execution object to append to that file. """
+
+    with open(filename, 'ab') as handler:
+        pid = str(entry.pid)
+        command = US.join(entry.cmd) + US
+        content = RS.join([pid, pid, 'wrapper', entry.cwd, command]) + GS
+        handler.write(content.encode('utf-8'))
 
 
 def parse_exec_trace(filename):
@@ -238,24 +231,21 @@ def is_preload_disabled(platform):
     the path and, if so, (2) whether the output of executing 'csrutil status'
     contains 'System Integrity Protection status: enabled'.
 
-    Same problem on linux when SELinux is enabled. The status query program
-    'sestatus' and the output when it's enabled 'SELinux status: enabled'. """
+    :param platform: name of the platform (returned by sys.platform),
+    :return: True if library preload will fail by the dynamic linker. """
 
-    if platform == 'darwin':
-        pattern = re.compile(r'System Integrity Protection status:\s+enabled')
+    if platform in WRAPPER_ONLY_PLATFORMS:
+        return True
+    elif platform == 'darwin':
         command = ['csrutil', 'status']
-    elif platform in {'linux', 'linux2'}:
-        pattern = re.compile(r'SELinux status:\s+enabled')
-        command = ['sestatus']
+        pattern = re.compile(r'System Integrity Protection status:\s+enabled')
+        try:
+            return any(pattern.match(line) for line in run_command(command))
+        except:
+            return False
     else:
         return False
 
-    try:
-        lines = subprocess.check_output(command).decode('utf-8')
-        return any((pattern.match(line) for line in lines.splitlines()))
-    except:
-        return False
-
 
 def entry_hash(entry):
     """ Implement unique hash method for compilation database entries. """
@@ -271,69 +261,3 @@ def entry_hash(entry):
     command = ' '.join(decode(entry['command'])[1:])
 
     return '<>'.join([filename, directory, command])
-
-
-def create_parser():
-    """ Command line argument parser factory method. """
-
-    parser = argparse.ArgumentParser(
-        formatter_class=argparse.ArgumentDefaultsHelpFormatter)
-
-    parser.add_argument(
-        '--verbose', '-v',
-        action='count',
-        default=0,
-        help="""Enable verbose output from '%(prog)s'. A second and third
-                flag increases verbosity.""")
-    parser.add_argument(
-        '--cdb',
-        metavar='<file>',
-        default="compile_commands.json",
-        help="""The JSON compilation database.""")
-    group = parser.add_mutually_exclusive_group()
-    group.add_argument(
-        '--append',
-        action='store_true',
-        help="""Append new entries to existing compilation database.""")
-    group.add_argument(
-        '--disable-filter', '-n',
-        dest='raw_entries',
-        action='store_true',
-        help="""Intercepted child process creation calls (exec calls) are all
-                logged to the output. The output is not a compilation database.
-                This flag is for debug purposes.""")
-
-    advanced = parser.add_argument_group('advanced options')
-    advanced.add_argument(
-        '--override-compiler',
-        action='store_true',
-        help="""Always resort to the compiler wrapper even when better
-                intercept methods are available.""")
-    advanced.add_argument(
-        '--use-cc',
-        metavar='<path>',
-        dest='cc',
-        default='cc',
-        help="""When '%(prog)s' analyzes a project by interposing a compiler
-                wrapper, which executes a real compiler for compilation and
-                do other tasks (record the compiler invocation). Because of
-                this interposing, '%(prog)s' does not know what compiler your
-                project normally uses. Instead, it simply overrides the CC
-                environment variable, and guesses your default compiler.
-
-                If you need '%(prog)s' to use a specific compiler for
-                *compilation* then you can use this option to specify a path
-                to that compiler.""")
-    advanced.add_argument(
-        '--use-c++',
-        metavar='<path>',
-        dest='cxx',
-        default='c++',
-        help="""This is the same as "--use-cc" but for C++ code.""")
-
-    parser.add_argument(
-        dest='build',
-        nargs=argparse.REMAINDER,
-        help="""Command to run.""")
-
-    return parser
diff --git a/tools/scan-build-py/libscanbuild/report.py b/tools/scan-build-py/libscanbuild/report.py
index 766ddef719909..54b9695d927fc 100644
--- a/tools/scan-build-py/libscanbuild/report.py
+++ b/tools/scan-build-py/libscanbuild/report.py
@@ -13,102 +13,65 @@ import os
 import os.path
 import sys
 import shutil
-import time
-import tempfile
 import itertools
 import plistlib
 import glob
 import json
 import logging
-import contextlib
 import datetime
 from libscanbuild import duplicate_check
 from libscanbuild.clang import get_version
 
-__all__ = ['report_directory', 'document']
+__all__ = ['document']
 
 
-@contextlib.contextmanager
-def report_directory(hint, keep):
-    """ Responsible for the report directory.
-
-    hint -- could specify the parent directory of the output directory.
-    keep -- a boolean value to keep or delete the empty report directory. """
-
-    stamp_format = 'scan-build-%Y-%m-%d-%H-%M-%S-%f-'
-    stamp = datetime.datetime.now().strftime(stamp_format)
-
-    parentdir = os.path.abspath(hint)
-    if not os.path.exists(parentdir):
-        os.makedirs(parentdir)
-
-    name = tempfile.mkdtemp(prefix=stamp, dir=parentdir)
-
-    logging.info('Report directory created: %s', name)
-
-    try:
-        yield name
-    finally:
-        if os.listdir(name):
-            msg = "Run 'scan-view %s' to examine bug reports."
-            keep = True
-        else:
-            if keep:
-                msg = "Report directory '%s' contans no report, but kept."
-            else:
-                msg = "Removing directory '%s' because it contains no report."
-        logging.warning(msg, name)
-
-        if not keep:
-            os.rmdir(name)
-
-
-def document(args, output_dir, use_cdb):
+def document(args):
     """ Generates cover report and returns the number of bugs/crashes. """
 
     html_reports_available = args.output_format in {'html', 'plist-html'}
 
     logging.debug('count crashes and bugs')
-    crash_count = sum(1 for _ in read_crashes(output_dir))
+    crash_count = sum(1 for _ in read_crashes(args.output))
     bug_counter = create_counters()
-    for bug in read_bugs(output_dir, html_reports_available):
+    for bug in read_bugs(args.output, html_reports_available):
         bug_counter(bug)
     result = crash_count + bug_counter.total
 
     if html_reports_available and result:
+        use_cdb = os.path.exists(args.cdb)
+
         logging.debug('generate index.html file')
-        # common prefix for source files to have sort filenames
+        # common prefix for source files to have sorter path
         prefix = commonprefix_from(args.cdb) if use_cdb else os.getcwd()
         # assemble the cover from multiple fragments
+        fragments = []
         try:
-            fragments = []
             if bug_counter.total:
-                fragments.append(bug_summary(output_dir, bug_counter))
-                fragments.append(bug_report(output_dir, prefix))
+                fragments.append(bug_summary(args.output, bug_counter))
+                fragments.append(bug_report(args.output, prefix))
             if crash_count:
-                fragments.append(crash_report(output_dir, prefix))
-            assemble_cover(output_dir, prefix, args, fragments)
-            # copy additinal files to the report
-            copy_resource_files(output_dir)
+                fragments.append(crash_report(args.output, prefix))
+            assemble_cover(args, prefix, fragments)
+            # copy additional files to the report
+            copy_resource_files(args.output)
             if use_cdb:
-                shutil.copy(args.cdb, output_dir)
+                shutil.copy(args.cdb, args.output)
         finally:
             for fragment in fragments:
                 os.remove(fragment)
     return result
 
 
-def assemble_cover(output_dir, prefix, args, fragments):
+def assemble_cover(args, prefix, fragments):
     """ Put together the fragments into a final report. """
 
     import getpass
     import socket
-    import datetime
 
     if args.html_title is None:
         args.html_title = os.path.basename(prefix) + ' - analyzer results'
 
-    with open(os.path.join(output_dir, 'index.html'), 'w') as handle:
+    with open(os.path.join(args.output, 'index.html'), 'w') as handle:
         indent = 0
         handle.write(reindent("""
         |<!DOCTYPE html>
@@ -375,11 +338,12 @@ def parse_crash(filename):
 
     match = re.match(r'(.*)\.info\.txt', filename)
     name = match.group(1) if match else None
-    with open(filename) as handler:
-        lines = handler.readlines()
+    with open(filename, mode='rb') as handler:
+        # this is a workaround to fix windows read '\r\n' as new lines.
+        lines = [line.decode().rstrip() for line in handler.readlines()]
         return {
-            'source': lines[0].rstrip(),
-            'problem': lines[1].rstrip(),
+            'source': lines[0],
+            'problem': lines[1],
             'file': name,
             'info': name + '.info.txt',
             'stderr': name + '.stderr.txt'
@@ -519,9 +483,10 @@ def commonprefix_from(filename):
 
 
 def commonprefix(files):
-    """ Fixed version of os.path.commonprefix. Return the longest path prefix
-    that is a prefix of all paths in filenames. """
+    """ Fixed version of os.path.commonprefix.
 
+    :param files: list of file names.
+    :return: the longest path prefix that is a prefix of all files. """
     result = None
     for current in files:
         if result is not None:
diff --git a/tools/scan-build-py/libscanbuild/runner.py b/tools/scan-build-py/libscanbuild/runner.py
deleted file mode 100644
index 72d02c85fed15..0000000000000
--- a/tools/scan-build-py/libscanbuild/runner.py
+++ /dev/null
@@ -1,302 +0,0 @@
-# -*- coding: utf-8 -*-
-#                     The LLVM Compiler Infrastructure
-#
-# This file is distributed under the University of Illinois Open Source
-# License. See LICENSE.TXT for details.
-""" This module is responsible to run the analyzer commands. """
-
-import re
-import os
-import os.path
-import tempfile
-import functools
-import subprocess
-import logging
-from libscanbuild.compilation import classify_source, compiler_language
-from libscanbuild.clang import get_version, get_arguments
-from libscanbuild.shell import decode
-
-__all__ = ['run']
-
-# To have good results from static analyzer certain compiler options shall be
-# omitted. The compiler flag filtering only affects the static analyzer run.
-#
-# Keys are the option name, value number of options to skip
-IGNORED_FLAGS = {
-    '-c': 0,  # compile option will be overwritten
-    '-fsyntax-only': 0,  # static analyzer option will be overwritten
-    '-o': 1,  # will set up own output file
-    # flags below are inherited from the perl implementation.
-    '-g': 0,
-    '-save-temps': 0,
-    '-install_name': 1,
-    '-exported_symbols_list': 1,
-    '-current_version': 1,
-    '-compatibility_version': 1,
-    '-init': 1,
-    '-e': 1,
-    '-seg1addr': 1,
-    '-bundle_loader': 1,
-    '-multiply_defined': 1,
-    '-sectorder': 3,
-    '--param': 1,
-    '--serialize-diagnostics': 1
-}
-
-
-def require(required):
-    """ Decorator for checking the required values in state.
-
-    It checks the required attributes in the passed state and stop when
-    any of those is missing. """
-
-    def decorator(function):
-        @functools.wraps(function)
-        def wrapper(*args, **kwargs):
-            for key in required:
-                if key not in args[0]:
-                    raise KeyError('{0} not passed to {1}'.format(
-                        key, function.__name__))
-
-            return function(*args, **kwargs)
-
-        return wrapper
-
-    return decorator
-
-
-@require(['command',  # entry from compilation database
-          'directory',  # entry from compilation database
-          'file',  # entry from compilation database
-          'clang',  # clang executable name (and path)
-          'direct_args',  # arguments from command line
-          'force_debug',  # kill non debug macros
-          'output_dir',  # where generated report files shall go
-          'output_format',  # it's 'plist' or 'html' or both
-          'output_failures'])  # generate crash reports or not
-def run(opts):
-    """ Entry point to run (or not) static analyzer against a single entry
-    of the compilation database.
-
-    This complex task is decomposed into smaller methods which are calling
-    each other in chain. If the analyzis is not possibe the given method
-    just return and break the chain.
-
-    The passed parameter is a python dictionary. Each method first check
-    that the needed parameters received. (This is done by the 'require'
-    decorator. It's like an 'assert' to check the contract between the
-    caller and the called method.) """
-
-    try:
-        command = opts.pop('command')
-        command = command if isinstance(command, list) else decode(command)
-        logging.debug("Run analyzer against '%s'", command)
-        opts.update(classify_parameters(command))
-
-        return arch_check(opts)
-    except Exception:
-        logging.error("Problem occured during analyzis.", exc_info=1)
-        return None
-
-
-@require(['clang', 'directory', 'flags', 'file', 'output_dir', 'language',
-          'error_type', 'error_output', 'exit_code'])
-def report_failure(opts):
-    """ Create report when analyzer failed.
-
-    The major report is the preprocessor output. The output filename generated
-    randomly. The compiler output also captured into '.stderr.txt' file.
-    And some more execution context also saved into '.info.txt' file. """
-
-    def extension(opts):
-        """ Generate preprocessor file extension. """
-
-        mapping = {'objective-c++': '.mii', 'objective-c': '.mi', 'c++': '.ii'}
-        return mapping.get(opts['language'], '.i')
-
-    def destination(opts):
-        """ Creates failures directory if not exits yet. """
-
-        name = os.path.join(opts['output_dir'], 'failures')
-        if not os.path.isdir(name):
-            os.makedirs(name)
-        return name
-
-    error = opts['error_type']
-    (handle, name) = tempfile.mkstemp(suffix=extension(opts),
-                                      prefix='clang_' + error + '_',
-                                      dir=destination(opts))
-    os.close(handle)
-    cwd = opts['directory']
-    cmd = get_arguments([opts['clang'], '-fsyntax-only', '-E'] +
-                        opts['flags'] + [opts['file'], '-o', name], cwd)
-    logging.debug('exec command in %s: %s', cwd, ' '.join(cmd))
-    subprocess.call(cmd, cwd=cwd)
-    # write general information about the crash
-    with open(name + '.info.txt', 'w') as handle:
-        handle.write(opts['file'] + os.linesep)
-        handle.write(error.title().replace('_', ' ') + os.linesep)
-        handle.write(' '.join(cmd) + os.linesep)
-        handle.write(' '.join(os.uname()) + os.linesep)
-        handle.write(get_version(opts['clang']))
-        handle.close()
-    # write the captured output too
-    with open(name + '.stderr.txt', 'w') as handle:
-        handle.writelines(opts['error_output'])
-        handle.close()
-    # return with the previous step exit code and output
-    return {
-        'error_output': opts['error_output'],
-        'exit_code': opts['exit_code']
-    }
-
-
-@require(['clang', 'directory', 'flags', 'direct_args', 'file', 'output_dir',
-          'output_format'])
-def run_analyzer(opts, continuation=report_failure):
-    """ It assembles the analysis command line and executes it. Capture the
-    output of the analysis and returns with it. If failure reports are
-    requested, it calls the continuation to generate it. """
-
-    def output():
-        """ Creates output file name for reports. """
-        if opts['output_format'] in {'plist', 'plist-html'}:
-            (handle, name) = tempfile.mkstemp(prefix='report-',
-                                              suffix='.plist',
-                                              dir=opts['output_dir'])
-            os.close(handle)
-            return name
-        return opts['output_dir']
-
-    cwd = opts['directory']
-    cmd = get_arguments([opts['clang'], '--analyze'] + opts['direct_args'] +
-                        opts['flags'] + [opts['file'], '-o', output()],
-                        cwd)
-    logging.debug('exec command in %s: %s', cwd, ' '.join(cmd))
-    child = subprocess.Popen(cmd,
-                             cwd=cwd,
-                             universal_newlines=True,
-                             stdout=subprocess.PIPE,
-                             stderr=subprocess.STDOUT)
-    output = child.stdout.readlines()
-    child.stdout.close()
-    # do report details if it were asked
-    child.wait()
-    if opts.get('output_failures', False) and child.returncode:
-        error_type = 'crash' if child.returncode & 127 else 'other_error'
-        opts.update({
-            'error_type': error_type,
-            'error_output': output,
-            'exit_code': child.returncode
-        })
-        return continuation(opts)
-    # return the output for logging and exit code for testing
-    return {'error_output': output, 'exit_code': child.returncode}
-
-
-@require(['flags', 'force_debug'])
-def filter_debug_flags(opts, continuation=run_analyzer):
-    """ Filter out nondebug macros when requested. """
-
-    if opts.pop('force_debug'):
-        # lazy implementation just append an undefine macro at the end
-        opts.update({'flags': opts['flags'] + ['-UNDEBUG']})
-
-    return continuation(opts)
-
-
-@require(['language', 'compiler', 'file', 'flags'])
-def language_check(opts, continuation=filter_debug_flags):
-    """ Find out the language from command line parameters or file name
-    extension. The decision also influenced by the compiler invocation. """
-
-    accepted = frozenset({
-        'c', 'c++', 'objective-c', 'objective-c++', 'c-cpp-output',
-        'c++-cpp-output', 'objective-c-cpp-output'
-    })
-
-    # language can be given as a parameter...
-    language = opts.pop('language')
-    compiler = opts.pop('compiler')
-    # ... or find out from source file extension
-    if language is None and compiler is not None:
-        language = classify_source(opts['file'], compiler == 'c')
-
-    if language is None:
-        logging.debug('skip analysis, language not known')
-        return None
-    elif language not in accepted:
-        logging.debug('skip analysis, language not supported')
-        return None
-    else:
-        logging.debug('analysis, language: %s', language)
-        opts.update({'language': language,
-                     'flags': ['-x', language] + opts['flags']})
-        return continuation(opts)
-
-
-@require(['arch_list', 'flags'])
-def arch_check(opts, continuation=language_check):
-    """ Do run analyzer through one of the given architectures. """
-
-    disabled = frozenset({'ppc', 'ppc64'})
-
-    received_list = opts.pop('arch_list')
-    if received_list:
-        # filter out disabled architectures and -arch switches
-        filtered_list = [a for a in received_list if a not in disabled]
-        if filtered_list:
-            # There should be only one arch given (or the same multiple
-            # times). If there are multiple arch are given and are not
-            # the same, those should not change the pre-processing step.
-            # But that's the only pass we have before run the analyzer.
-            current = filtered_list.pop()
-            logging.debug('analysis, on arch: %s', current)
-
-            opts.update({'flags': ['-arch', current] + opts['flags']})
-            return continuation(opts)
-        else:
-            logging.debug('skip analysis, found not supported arch')
-            return None
-    else:
-        logging.debug('analysis, on default arch')
-        return continuation(opts)
-
-
-def classify_parameters(command):
-    """ Prepare compiler flags (filters some and add others) and take out
-    language (-x) and architecture (-arch) flags for future processing. """
-
-    result = {
-        'flags': [],  # the filtered compiler flags
-        'arch_list': [],  # list of architecture flags
-        'language': None,  # compilation language, None, if not specified
-        'compiler': compiler_language(command)  # 'c' or 'c++'
-    }
-
-    # iterate on the compile options
-    args = iter(command[1:])
-    for arg in args:
-        # take arch flags into a separate basket
-        if arg == '-arch':
-            result['arch_list'].append(next(args))
-        # take language
-        elif arg == '-x':
-            result['language'] = next(args)
-        # parameters which looks source file are not flags
-        elif re.match(r'^[^-].+', arg) and classify_source(arg):
-            pass
-        # ignore some flags
-        elif arg in IGNORED_FLAGS:
-            count = IGNORED_FLAGS[arg]
-            for _ in range(count):
-                next(args)
-        # we don't care about extra warnings, but we should suppress ones
-        # that we don't want to see.
-        elif re.match(r'^-W.+', arg) and not re.match(r'^-Wno-.+', arg):
-            pass
-        # and consider everything else as compilation flag.
-        else:
-            result['flags'].append(arg)
-
-    return result