Fix option real_path_warning_re not working.

I renamed the option to path_observation_re. Now by prefixing

  INCLUDE_SERVER_ARGS='-d1 --path_observation_re="/usr/.*"'

to say make include-server-maintainer-check, one gets a message each time the
include server finds a path whose realpath name matches the regular expression. 
That results in messages like:

WARNING include server: For translation unit 'src/testtmp.c', lookup of file
'bits/stdio_lim.h' resolved to '/usr/include/bits/stdio_lim.h' whose realpath is
'/usr/include/bits/stdio_lim.h'.

To make the interpretation of quoted arguments within INCLUDE_SERVER_ARGS
correct, I added 'eval' to the command that cranks up the include server. I
remembered to put extra quoted quotes inside the parameters that should be
considered a token after the double interpretation that eval implies.


git-svn-id: http://distcc.googlecode.com/svn/trunk@436 01de4be4-8c4a-0410-9132-4925637da917

4 files changed, 51 insertions, 49 deletions

diff --git a/include_server/basics.py b/include_server/basics.py
index 327b952..87c16d1 100755
--- a/include_server/basics.py
+++ b/include_server/basics.py
@@ -203,7 +203,7 @@ opt_debug_pattern = 1  # see DEBUG below
 opt_email_bound = MAX_EMAILS_TO_SEND
 opt_exact_analysis = False         # use CPP instead of include analyzer
 opt_print_times = False
-opt_realpath_warning_re = None
+opt_path_observation_re = None
 opt_send_email = False
 opt_simple_algorithm = False
 opt_stat_reset_triggers = {}
@@ -226,13 +226,6 @@ def Stamp(path):
     return None
 
 
-# REALPATH WARNINGS
-
-BAD_REALPATH_WARNING_MSG = (
-    """For translation unit '%s' while processing '%s': lookup of file '%s' """
-    """resolved to '%s' whose realpath is '%s'.""")
-
-
 # LANGUAGES AND FILE EXTENSIONS
 
 # The languages that we recognize.
diff --git a/include_server/cache_basics.py b/include_server/cache_basics.py
index d7c98c2..c7a936c 100755
--- a/include_server/cache_basics.py
+++ b/include_server/cache_basics.py
@@ -639,7 +639,7 @@ class BuildStatCache(object):
     self.includepath_map = includepath_map
     self.directory_map = directory_map
     self.realpath_map = realpath_map
-    self.bad_realpath_tuples = []
+    self.path_observations = []
 
   def _Verify(self, currdir_idx, searchdir_idx, includepath_idx):
     """Verify that the cached result is the same as obtained by stat call.
@@ -669,21 +669,18 @@ class BuildStatCache(object):
         really_exists and "exists" or "does not exist",
         cache_exists and "existed" or "did not exist"))
 
-  def GetAndClearBadResolutions(self):
-    """Return descriptions of resolutions matching realpath warning regexp.
-    Returns:
-      a list of tuples of the form
-        (include_path, resolved_path, real_path)
-      where include_path is the argument of an #include (or an initial file),
-      resolved_path is the concatenation of the searchdir where the
-      include_path is found with this include_path, and real_path is the 
-      realpath of this location (relative to the current directory).
-    The list is reset to [] with this operation. Thus the items returned are
-    those that occcurred since the last time this method was invoked.
+  def WarnAboutPathObservations(self, translation_unit):
+    """Print new paths found according to path observation expression option.
+
+    Args:
+      translation_unit: a string embedded in warning
     """
-    bad_realpath_tuples = self.bad_realpath_tuples
-    self.bad_realpath_tuples = []
-    return bad_realpath_tuples
+    for (includepath, relpath, realpath) in self.path_observations:
+      Debug(DEBUG_WARNING,
+            "For translation unit '%s',"
+            " lookup of file '%s' resolved to '%s' whose realpath is '%s'.",
+             translation_unit, includepath, relpath, realpath)
+    self.path_observations = []
 
   def Resolve(self, includepath_idx, currdir_idx, searchdir_idx,
               searchlist_idxs):
@@ -786,12 +783,11 @@ class BuildStatCache(object):
           realpath_idx = searchdir_realpaths[sl_idx] = (
             self.realpath_map.Index(rpath))
           # This is the place to catch errant files according to user defined
-          # abspath_warning option. See documentation for method
-          # GetAndClearBadResolutions.
-          if basics.opt_realpath_warning_re:
+          # regular expression path_observation_re.
+          if basics.opt_path_observation_re:
             realpath = self.realpath_map.string[realpath_idx]
-            if basics.opt_realpath_warning_re.search(realpath):
-              self.bad_realpath_tuples.append((includepath, relpath, realpath))
+            if basics.opt_path_observation_re.search(realpath):
+              self.path_observations.append((includepath, relpath, realpath))
           return ((sl_idx, includepath_idx), realpath_idx)
         else:
           searchdir_stats[sl_idx] = False
diff --git a/include_server/include_server.py b/include_server/include_server.py
index a6b5960..aac3268 100755
--- a/include_server/include_server.py
+++ b/include_server/include_server.py
@@ -26,21 +26,22 @@ __author__ = "Nils Klarlund"
 
 # Python imports
 import gc
+import getopt
+import glob
 import os
 import re
-import sys
-import glob
+import shutil
 import signal
-import getopt
+import SocketServer
+import sys
 import tempfile
 import traceback
-import SocketServer
 
 # Include server imports
 import basics
-import statistics
-import include_analyzer_memoizing_node
 import distcc_pump_c_extensions
+import include_analyzer_memoizing_node
+import statistics
 
 # The default size passed to listen by a streaming socket server of
 # SocketServer is only 5. Make it 128 (which appears to be the hard
@@ -62,7 +63,7 @@ NotCoveredTimeOutError = basics.NotCoveredTimeOutError
 def Usage():
   print """Usage:
 
-include_server --port INCLUDE_SERVER_PORT [options]
+include_server --port INCLUDE_SERVER_PORT [OPTIONS]
 
 where INCLUDE_SERVER_PORT is a socket name. Fork the include server
 for incremental include analysis. The include server answers queries
@@ -70,7 +71,7 @@ from the distcc client about which files to include in a C/C++
 compilation. This command itself terminates as soon as the include
 server has been spawned.
 
-Options:
+OPTIONS:
  --pid_file FILEPATH         The pid of the include server is written to file
                              FILEPATH.
                              
@@ -87,10 +88,12 @@ Options:
  --email_bound NUMBER        Maximal number of emails to send (in addition to
                              a final email). Default: 3.
                              
- --realpath_warning_re=RE    Write a warning to stderr whenever a filename is
+ --path_observation_re=RE    Issue warning message whenever a filename is
                              resolved to a realpath that is matched by RE,
                              which is a regular expression in Python syntax.
-                             (Warnings must be enabled with at least -d1.)
+                             This is useful for finding out where files included
+                             actually come from. Use RE="" to find them all.
+                             Note: warnings must be enabled with at least -d1.
                              
  --stat_reset_triggers=LIST  Flush stat caches when the timestamp of any
                              filepath in LIST changes or the filepath comes in
@@ -441,12 +444,15 @@ def DistccIncludeHandlerGenerator(include_analyzer):
       else:
         # No exception raised, include closure can be trusted.
         distcc_pump_c_extensions.XArgv(self.wfile.fileno(), files_and_links)
+      # Print out observed paths.
+      if basics.opt_path_observation_re:
+         include_analyzer.build_stat_cache.WarnAboutPathObservations(
+             include_analyzer.translation_unit)
       # Finally, stop the clock and report statistics if needed.
       statistics.EndTiming()
       if basics.opt_statistics:
         statistics.PrintStatistics(include_analyzer)
 
-
   return IncludeHandler
 
 
@@ -469,9 +475,9 @@ def _ParseCommandLineOptions():
                                 "no-email",
                                 "email_bound=",
                                 "exact_analysis",
+                                "path_observation_re=",
                                 "stat_reset_triggers=",
                                 "simple_algorithm",
-                                "realpath_warning_re=",
                                 "statistics",
                                 "time",
                                 "unsafe_absolute_includes",
@@ -497,8 +503,8 @@ def _ParseCommandLineOptions():
         basics.opt_send_email = False
       if opt in ("--email_bound",):
         basics.opt_email_bound = int(arg)
-      if opt in ("--realpath_warning_re",):
-        basics.opt_realpath_warning_re = re.compile(arg)
+      if opt in ("--path_observation_re",):
+        basics.opt_path_observation_re = re.compile(arg)
       if opt in ("--stat_reset_triggers",):
         basics.opt_stat_reset_triggers = (
           dict([ (glob_expr,
diff --git a/pump.in b/pump.in
index 0618efa..987a41f 100755
--- a/pump.in
+++ b/pump.in
@@ -275,15 +275,22 @@ StartIncludeServer() {
     esac
 
     if [ -z "$PYTHONOPTIMIZE" ]; then PYTHONOPTIMIZE=1; fi
+    # We use 'eval' so that INCLUDE_SERVER_ARGS can use shell quoting such 
+    # as in:
+    #
+    #   INCLUDE_SERVER_ARGS='--stat_reset_triggers="*"'
+    #
+    # which will pass '*' to the include server (that is, the string consisting
+    # of one asterisk) without filename expansion.
     PYTHONOPTIMIZE=$PYTHONOPTIMIZE \
     PYTHONPATH="$pythonpath::$PYTHONPATH" \
-    $PYTHON                          \
-        "$include_server"            \
-        --port "$socket"             \
-        --pid_file "$tmp_pid_file"   \
-        --email                      \
-        --email_bound=5              \
-        -d1                          \
+    eval "'$PYTHON'"                   \
+        "'$include_server'"            \
+        --port "'$socket'"             \
+        --pid_file "'$tmp_pid_file'"   \
+        --email                        \
+        --email_bound=5                \
+        -d1                            \
         $INCLUDE_SERVER_ARGS
   )