How to Parse Multiline in AWK

I was given a Java thread dump output from my colleague and the output is kind of a multiline records with record separator (RS) being a blank line. The question is, can AWK parse this type of file just like other space/colon/comma separated files. The answer is yes. It is well documented in The AWK Programming Language written by the three authors. If you have the book, it is described on page 60-61.

Here is a sample script to demonstrate how we can summarise the "Thread-" name that is in waiting and/or in lock state. The sample Java thread dump is download from here.

$ cat threaddump.sh
#! /bin/sh

if [ $# -ne 1 ]; then
 echo "Usage: $0 <thread-dump>"
 exit 1
fi
if [ ! -f $1 ]; then
 echo "Error: $1 does not exist"
 exit 2
fi


awk '
BEGIN {
 RS=""
 FS="\n"
}
/^"Thread-/ {
 split($1,a," ")
 if ( /waiting on/ ) {
  wait[a[1]]++
 }
 if ( /locked/ ) {
  lock[a[1]]++
 }
}
END {
 printf("Thread\t\tWait\tLock\n")
 printf("------\t\t----\t----\n")
 for ( i in wait ) {
  printf("%s\t%d\t%d\n", i, wait[i], lock[i])
 }
}' $1


$ cat threaddump.txt
Full thread dump Java HotSpot(TM) Client VM (1.5.0_10-b03 mixed mode):

"Thread-7" prio=4 tid=0x0b482220 nid=0x1570 in Object.wait() [0x0bbcf000..0x0bbcfae8]
 at java.lang.Object.wait(Native Method)
 - waiting on <0x03017960> (a concurrency.diners.Fork)
 at java.lang.Object.wait(Object.java:474)
 at concurrency.diners.Fork.get(Fork.java:22)
 - locked <0x03017960> (a concurrency.diners.Fork)
 at concurrency.diners.Philosopher.run(Philosopher.java:29)

"Thread-6" prio=4 tid=0x0b481808 nid=0xa84 in Object.wait() [0x0bb8f000..0x0bb8fb68]
 at java.lang.Object.wait(Native Method)
 - waiting on <0x030707e0> (a concurrency.diners.Fork)
 at java.lang.Object.wait(Object.java:474)
 at concurrency.diners.Fork.get(Fork.java:22)
 - locked <0x030707e0> (a concurrency.diners.Fork)
 at concurrency.diners.Philosopher.run(Philosopher.java:29)

"Thread-5" prio=4 tid=0x0b47e310 nid=0x167c in Object.wait() [0x0bb4f000..0x0bb4fbe8]
 at java.lang.Object.wait(Native Method)
 - waiting on <0x03070850> (a concurrency.diners.Fork)
 at java.lang.Object.wait(Object.java:474)
 at concurrency.diners.Fork.get(Fork.java:22)
 - locked <0x03070850> (a concurrency.diners.Fork)
 at concurrency.diners.Philosopher.run(Philosopher.java:29)

"Thread-4" prio=4 tid=0x0b47d808 nid=0x1730 in Object.wait() [0x0bb0f000..0x0bb0fc68]
 at java.lang.Object.wait(Native Method)
 - waiting on <0x030708c0> (a concurrency.diners.Fork)
 at java.lang.Object.wait(Object.java:474)
 at concurrency.diners.Fork.get(Fork.java:22)
 - locked <0x030708c0> (a concurrency.diners.Fork)
 at concurrency.diners.Philosopher.run(Philosopher.java:29)

"Thread-3" prio=4 tid=0x0b480cd8 nid=0x11c4 in Object.wait() [0x0bacf000..0x0bacfce8]
 at java.lang.Object.wait(Native Method)
 - waiting on <0x03017b38> (a concurrency.diners.Fork)
 at java.lang.Object.wait(Object.java:474)
 at concurrency.diners.Fork.get(Fork.java:22)
 - locked <0x03017b38> (a concurrency.diners.Fork)
 at concurrency.diners.Philosopher.run(Philosopher.java:29)

"AWT-EventQueue-1" prio=4 tid=0x0b46e1d0 nid=0x16c8 in Object.wait() [0x0ba4f000..0x0ba4fa68]
 at java.lang.Object.wait(Native Method)
 - waiting on <0x02ffa368> (a java.awt.EventQueue)
 at java.lang.Object.wait(Object.java:474)
 at java.awt.EventQueue.getNextEvent(EventQueue.java:345)
 - locked <0x02ffa368> (a java.awt.EventQueue)
 at java.awt.EventDispatchThread.pumpOneEventForHierarchy(EventDispatchThread.java:189)
 at java.awt.EventDispatchThread.pumpEventsForHierarchy(EventDispatchThread.java:163)
 at java.awt.EventDispatchThread.pumpEvents(EventDispatchThread.java:157)
 at java.awt.EventDispatchThread.pumpEvents(EventDispatchThread.java:149)
 at java.awt.EventDispatchThread.run(EventDispatchThread.java:110)

"DestroyJavaVM" prio=6 tid=0x00266dc0 nid=0x1118 waiting on condition [0x00000000..0x0006fae8]

"AWT-EventQueue-0" prio=6 tid=0x0b451f60 nid=0x124c in Object.wait() [0x0b82f000..0x0b82fbe8]
 at java.lang.Object.wait(Native Method)
 - waiting on <0x0300a858> (a java.awt.EventQueue)
 at java.lang.Object.wait(Object.java:474)
 at java.awt.EventQueue.getNextEvent(EventQueue.java:345)
 - locked <0x0300a858> (a java.awt.EventQueue)
 at java.awt.EventDispatchThread.pumpOneEventForHierarchy(EventDispatchThread.java:189)
 at java.awt.EventDispatchThread.pumpEventsForHierarchy(EventDispatchThread.java:163)
 at java.awt.EventDispatchThread.pumpEvents(EventDispatchThread.java:157)
 at java.awt.EventDispatchThread.pumpEvents(EventDispatchThread.java:149)
 at java.awt.EventDispatchThread.run(EventDispatchThread.java:110)

"thread applet-concurrency/diners/Diners.class" prio=4 tid=0x0b3cab40 nid=0x10a0 in Object.wait() [0x0b7ef000..0x0b7efb68]
 at java.lang.Object.wait(Native Method)
 - waiting on <0x0300a900> (a sun.applet.AppletViewerPanel)
 at java.lang.Object.wait(Object.java:474)
 at sun.applet.AppletPanel.getNextEvent(AppletPanel.java:282)
 - locked <0x0300a900> (a sun.applet.AppletViewerPanel)
 at sun.applet.AppletPanel.run(AppletPanel.java:332)
 at java.lang.Thread.run(Thread.java:595)

"AWT-Windows" daemon prio=6 tid=0x0ac90b38 nid=0x1124 runnable [0x0af0f000..0x0af0fce8]
 at sun.awt.windows.WToolkit.eventLoop(Native Method)
 at sun.awt.windows.WToolkit.run(WToolkit.java:269)
 at java.lang.Thread.run(Thread.java:595)

"AWT-Shutdown" prio=6 tid=0x0ac90780 nid=0x7dc in Object.wait() [0x0aecf000..0x0aecfd68]
 at java.lang.Object.wait(Native Method)
 - waiting on <0x02fb5830> (a java.lang.Object)
 at java.lang.Object.wait(Object.java:474)
 at sun.awt.AWTAutoShutdown.run(AWTAutoShutdown.java:259)
 - locked <0x02fb5830> (a java.lang.Object)
 at java.lang.Thread.run(Thread.java:595)

"Java2D Disposer" daemon prio=10 tid=0x0ac82aa8 nid=0x1014 in Object.wait() [0x0ae8f000..0x0ae8f9e8]
 at java.lang.Object.wait(Native Method)
 - waiting on <0x02fdd7a8> (a java.lang.ref.ReferenceQueue$Lock)
 at java.lang.ref.ReferenceQueue.remove(ReferenceQueue.java:116)
 - locked <0x02fdd7a8> (a java.lang.ref.ReferenceQueue$Lock)
 at java.lang.ref.ReferenceQueue.remove(ReferenceQueue.java:132)
 at sun.java2d.Disposer.run(Disposer.java:107)
 at java.lang.Thread.run(Thread.java:595)

"Low Memory Detector" daemon prio=6 tid=0x00a94e70 nid=0x1038 runnable [0x00000000..0x00000000]

"CompilerThread0" daemon prio=10 tid=0x00a93a70 nid=0x12c8 waiting on condition [0x00000000..0x0abcf8c8]

"Signal Dispatcher" daemon prio=10 tid=0x00a92e28 nid=0x16bc waiting on condition [0x00000000..0x00000000]

"Finalizer" daemon prio=8 tid=0x00a89cd0 nid=0x1044 in Object.wait() [0x0ab4f000..0x0ab4fc68]
 at java.lang.Object.wait(Native Method)
 - waiting on <0x02fdd950> (a java.lang.ref.ReferenceQueue$Lock)
 at java.lang.ref.ReferenceQueue.remove(ReferenceQueue.java:116)
 - locked <0x02fdd950> (a java.lang.ref.ReferenceQueue$Lock)
 at java.lang.ref.ReferenceQueue.remove(ReferenceQueue.java:132)
 at java.lang.ref.Finalizer$FinalizerThread.run(Finalizer.java:159)

"Reference Handler" daemon prio=10 tid=0x00a88860 nid=0x106c in Object.wait() [0x0ab0f000..0x0ab0fce8]
 at java.lang.Object.wait(Native Method)
 - waiting on <0x02fdd700> (a java.lang.ref.Reference$Lock)
 at java.lang.Object.wait(Object.java:474)
 at java.lang.ref.Reference$ReferenceHandler.run(Reference.java:116)
 - locked <0x02fdd700> (a java.lang.ref.Reference$Lock)

"VM Thread" prio=10 tid=0x00a85d98 nid=0x1030 runnable 

"VM Periodic Task Thread" prio=10 tid=0x00a960c8 nid=0x14b4 waiting on condition 


$ ./threaddump.sh threaddump.txt
Thread          Wait    Lock
------          ----    ----
"Thread-3"      1       1
"Thread-4"      1       1
"Thread-5"      1       1
"Thread-6"      1       1
"Thread-7"      1       1

I can tell you that AWK is damn powerful.