Only write heritrix_dmesg.log when requested (#779)

Only write heritrix_dmesg.log when requested

Heritrix.java always created heritrix_dmesg.log in $HERITRIX_HOME, even
though only the bin/heritrix script reads it, and only when it starts
Heritrix in the background. This got in the way of making
$HERITRIX_HOME read-only for Docker and systemd setups.

The startup log is now written only when the heritrix.dmesg system
property gives its path. bin/heritrix sets this property in background
mode and keeps the file in the same place as before.

Also fix a typo in bin/heritrix ($startmessage) that stopped it
removing a heritrix_dmesg.log left over from a previous start.

Set -Dheritrix.dmesg in heritrix.cmd too.

dist/src/main/bin/heritrix

@@ -114,7 +114,7 @@ startMessage="${HERITRIX_HOME}/heritrix_dmesg.log"
 # Remove any file that may have been left over from previous starts.
 if [ -f $startMessage ]
 then
-    rm -f $startmessage
+    rm -f $startMessage
 fi
 # Run heritrix as daemon.  Redirect stdout and stderr to a file.
 # Print start message with date, java version, java opts, ulimit, and uname.
@@ -139,7 +139,8 @@ then
 else
     CLASSPATH=${CP} nohup $JAVACMD -Dheritrix.home=${HERITRIX_HOME} \
         -Djava.protocol.handler.pkgs=org.archive.net \
-        -Dheritrix.out=${HERITRIX_OUT} ${JAVA_OPTS} ${JMX_OPTS} \
+        -Dheritrix.out=${HERITRIX_OUT} -Dheritrix.dmesg=${startMessage} \
+        ${JAVA_OPTS} ${JMX_OPTS} \
         $CLASS_MAIN $@ >> ${stdouterrlog} 2>&1 &
     HERITRIX_PID=$!
 

dist/src/main/bin/heritrix.cmd

@@ -153,7 +153,7 @@ if not "%1"=="BGR" (
 ) else (
     title Heritrix
     :: adding  ">>%stdouterrlog% 2>&1" causes an access denied error as heritrix writes also to this file	
-    %JAVACMD% "-Dheritrix.home=%HERITRIX_HOME%" -Djava.protocol.handler.pkgs=org.archive.net "-Dheritrix.out=%HERITRIX_OUT%" %JAVA_OPTS% %CLASS_MAIN% %HERITRIX_CMDLINE%	
+    %JAVACMD% "-Dheritrix.home=%HERITRIX_HOME%" -Djava.protocol.handler.pkgs=org.archive.net "-Dheritrix.out=%HERITRIX_OUT%" "-Dheritrix.dmesg=%startMessage%" %JAVA_OPTS% %CLASS_MAIN% %HERITRIX_CMDLINE%
     if errorlevel 130 goto :end
     if errorlevel 1 echo.!ERRORLEVEL! >"%HERITRIX_HOME%\heritrix_launch_problems"
 	pause

engine/src/main/java/org/archive/crawler/Heritrix.java

@@ -71,7 +71,9 @@ import org.restlet.security.MapVerifier;
  * stderr show on the console, this class prints usage or startup output
  * such as where the web UI can be found, etc., to a STARTLOG that the shell
  * script is waiting on.  As soon as the shell script sees output in this file,
- * it prints its content and breaks out of its wait.
+ * it prints its content and breaks out of its wait.  The STARTLOG is only
+ * written if its path is given by the <code>heritrix.dmesg</code> system
+ * property.
  * See ${HERITRIX_HOME}/bin/heritrix.
  * 
  * <p>Heritrix can also be embedded or launched by webapp initialization or
@@ -106,12 +108,11 @@ public class Heritrix {
     /**
      * Heritrix start log file.
      *
-     * This file contains standard out produced by this main class for startup
-     * only.  Used by heritrix shell script.  Name here MUST match that in the
-     * <code>bin/heritrix</code> shell script.  This is a DEPENDENCY the shell
-     * wrapper has on this here java heritrix.
+     * System property naming a file to receive a copy of standard out produced
+     * by this main class for startup only.  Set by the <code>bin/heritrix</code>
+     * shell script when backgrounding heritrix.  If unset, no file is written.
      */
-    private static final String STARTLOG = "heritrix_dmesg.log";
+    private static final String STARTLOG_PROPERTY = "heritrix.dmesg";
 
     private enum AuthMode {
         DIGEST, BASIC;
@@ -227,15 +228,19 @@ public class Heritrix {
         }
         
         
-        BufferedOutputStream startupOutStream = 
-            new BufferedOutputStream(
-                new FileOutputStream(
-                    new File(getHeritrixHome(), STARTLOG)),16384);
-        PrintStream startupOut = 
-            new PrintStream(
-                new TeeOutputStream(
-                    System.out,
-                    startupOutStream));
+        String startLog = System.getProperty(STARTLOG_PROPERTY);
+        BufferedOutputStream startupOutStream = null;
+        PrintStream startupOut = System.out;
+        if (startLog != null) {
+            startupOutStream =
+                new BufferedOutputStream(
+                    new FileOutputStream(startLog),16384);
+            startupOut =
+                new PrintStream(
+                    new TeeOutputStream(
+                        System.out,
+                        startupOutStream));
+        }
 
         CommandLine cl = getCommandLine(startupOut, args);
         if (cl == null) return;
@@ -448,7 +453,9 @@ public class Heritrix {
         } finally {
             startupOut.flush();
             // stop writing to side startup file
-            startupOutStream.close();
+            if (startupOutStream != null) {
+                startupOutStream.close();
+            }
             System.out.println("Heritrix version: " +
                     ArchiveUtils.VERSION);
         }