diff --git a/README.md b/README.md
index fa5c706..c7a7708 100644
--- a/README.md
+++ b/README.md
@@ -773,6 +773,23 @@ dt=2014-12-09|3065252 (2.37%) -------------------------------------------~
 dt=2014-12-10|3316703 (2.57%) -----------------------------------------------~
 ```
 
+Running Tests
+=============
+
+The `tests` directory contains sample input and output files, as well as a
+script to verify expected output based on the sample inputs. To use it, first
+export an environment variable called `distribution` that points to the
+location of your distribution executable. The script must be run from the `tests`
+directory. For example, the following will run tests against the Perl script
+and then against the Python script:
+
+    cd tests/
+	distribution=../distribution ./runTests.sh
+	distribution=../distribution.py ./runTests.sh
+
+The `runTests.sh` script takes one optional argument, `-v`. This enables
+verbose mode, which prints out any differences in the stderr of the test runs,
+for comparing diagnostic info.
 
 To-Do List
 ==========
diff --git a/tests/runTests.sh b/tests/runTests.sh
index 19d2753..63108d0 100755
--- a/tests/runTests.sh
+++ b/tests/runTests.sh
@@ -1,4 +1,4 @@
-#!/bin/bash
+#!/bin/sh
 
 # make sure env is setup proper
 if [ "xxx$distribution" == "xxx" ] ; then
@@ -6,58 +6,58 @@ if [ "xxx$distribution" == "xxx" ] ; then
 	exit 255
 fi
 
+getopts "v" verbose
+
 # the tests
-echo "Test #6 is designed to take several seconds on a modern CPU."
 echo ""
-echo -n "Running test: 1. "
-cat input01.txt | $distribution --rcfile=../distributionrc --graph --height=35 --width=120 --char=dt --color --verbose > output001.txt 2> output101.txt
-
-echo -n "2. "
-cat input02.txt | awk '{print $4" "$5}' | $distribution --rcfile=../distributionrc -s=med --width=110 --tokenize=word --match=word -v -c > output002.txt 2> output102.txt
+printf "Running test: 1. "
+cat stdin.01.txt | $distribution --rcfile=../distributionrc --graph --height=35 --width=120 --char=dt --color --verbose > stdout.01.actual.txt 2> stderr.01.actual.txt
 
-echo -n "3. "
-grep modem input02.txt | awk '{print $1}' | $distribution --rcfile=../distributionrc --width=110 -h=15 -c='|' -v -c 2> output103.txt | sort > output003.txt
+printf "2. "
+cat stdin.02.txt | awk '{print $4" "$5}' | $distribution --rcfile=../distributionrc -s=med --width=110 --tokenize=word --match=word -v -c > stdout.02.actual.txt 2> stderr.02.actual.txt
 
-echo -n "4. "
-cat input03.txt | $distribution --rcfile=../distributionrc --size=large --height=8 --width=60 -t=/ --palette=0,31,33,35,37 -c='()' > output004.txt 2> output104.txt
+printf "3. "
+grep modem stdin.02.txt | awk '{print $1}' | $distribution --rcfile=../distributionrc --width=110 -h=15 -c='|' -v -c 2> stderr.03.actual.txt | sort > stdout.03.actual.txt
 
-echo -n "5. "
-cat input03.txt | $distribution --rcfile=../distributionrc -c=pc -w=48 --tokenize=word --match=num --size=large --verbose 2> output105.txt | sort -n > output005.txt
+printf "4. "
+cat stdin.03.txt | $distribution --rcfile=../distributionrc --size=large --height=8 --width=60 -t=/ --palette=0,31,33,35,37 -c='()' > stdout.04.actual.txt 2> stderr.04.actual.txt
 
-echo -n "6. "
-for i in `seq 1 17 3141592` ; do echo $[ $i ^ ($i + 9) ]; done | cut -c 2-6 | $distribution --rcfile=../distributionrc --width=124 --height=29 -p=0,32,34,36,31 -c=^ -v > output006.txt 2> output106.txt
+printf "5. "
+cat stdin.03.txt | $distribution --rcfile=../distributionrc -c=pc -w=48 --tokenize=word --match=num --size=large --verbose 2> stderr.05.actual.txt | sort -n > stdout.05.actual.txt
 
-echo -n "7. "
-cat input04.txt | awk '{print $8}' | $distribution --rcfile=../distributionrc -s=s -w=90 --char=Ξ > output007.txt 2> output107.txt
-
-# get onto the newline
-echo ""
+printf "6. "
+# generate a large list of deterministic but meaningless numbers
+(( i=0 )) ; while [[ $i -lt 3141592 ]] ; do
+	echo $(( i ^ (i+=17) ))
+done | cut -c 2-6 | $distribution --rcfile=../distributionrc --width=124 --height=29 -p=0,32,34,36,31 -c=^ -v > stdout.06.actual.txt 2> stderr.06.actual.txt
 
-echo "
-Expected output:
- = b2d463a3fb20df2c01fb95b1e2006784  output001.txt
- = 6e03fecd199ec6e93540fbd08afe6b94  output002.txt
- = 4edb70a142774c686c9268b88a00cb01  output003.txt
- = cae71e886be0ff84fe8c887ccff9c636  output004.txt
- = 83332608dffc4e6692049931c9c5d5fc  output005.txt
- = f993d1b611f5d23fde36590717a0cbec  output006.txt
- = bdf7a31f8b453e9075f63b6280749021  output007.txt
+printf "7. "
+cat stdin.04.txt | awk '{print $8}' | $distribution --rcfile=../distributionrc -s=s -w=90 --char=Ξ > stdout.07.actual.txt 2> stderr.07.actual.txt
 
-Actual output:"
+echo "done."
 
 # be sure output is proper
-for i in output0*.txt ; do
-	echo " = `md5sum $i`"
-	#echo "debug: `cat $i`"
+err=0
+printf "Comparing results: "
+for i in 01 02 03 04 05 06 07 ; do
+	printf "$i. "
+	diff -w stdout.$i.expected.txt stdout.$i.actual.txt
+	if [ $? -ne 0 ]; then
+		err=1
+	fi
+
+	# when in verbose mode, ignore any "runtime lines, since those may differ by
+	# milliseconds from machine to machine. Also ignore any lines with "^M" markers,
+	# which are line-erase signals used for updating the screen interactively, and
+	# thus don't need to be stored or compared.
+	if [ "$verbose" = "v" ]; then
+		diff -w -I "runtime:" -I "
" stderr.$i.expected.txt stderr.$i.actual.txt
+	fi
 done
 
-## # the problem with output1*.txt is they have millisecond timings which
-## # will change from run to run. so filter those out then repeat...
-## for i in output1*.txt ; do
-##	echo " = `md5sum $i`"
-## 	#echo "debug: `cat $i`"
-## done
+echo "done."
 
 # clean up
-rm output*.txt
+rm stdout.*.actual.txt stderr.*.actual.txt
 
+exit $err
diff --git a/tests/stderr.01.expected.txt b/tests/stderr.01.expected.txt
new file mode 100644
index 0000000..5e53d6f
--- /dev/null
+++ b/tests/stderr.01.expected.txt
@@ -0,0 +1,5 @@
+tokens/lines examined: 279    
+ tokens/lines matched: 17,444,532
+       histogram keys: 279
+              runtime: 1.52ms
+                   Key|Ct (Pct)         Histogram
diff --git a/tests/stderr.02.expected.txt b/tests/stderr.02.expected.txt
new file mode 100644
index 0000000..438dd02
--- /dev/null
+++ b/tests/stderr.02.expected.txt
@@ -0,0 +1,5 @@
+tokens/lines examined: 5,480    
+ tokens/lines matched: 1,104
+       histogram keys: 144
+              runtime: 6.19ms
+         Key|Ct (Pct)     Histogram
diff --git a/tests/stderr.03.expected.txt b/tests/stderr.03.expected.txt
new file mode 100644
index 0000000..13a50bc
--- /dev/null
+++ b/tests/stderr.03.expected.txt
@@ -0,0 +1,5 @@
+tokens/lines examined: 29    
+ tokens/lines matched: 29
+       histogram keys: 9
+              runtime: 0.31ms
+       Key|Ct (Pct)   Histogram
diff --git a/tests/stderr.04.expected.txt b/tests/stderr.04.expected.txt
new file mode 100644
index 0000000..fed8ee6
--- /dev/null
+++ b/tests/stderr.04.expected.txt
@@ -0,0 +1 @@
+      Key|Ct (Pct)     Histogram
diff --git a/tests/stderr.05.expected.txt b/tests/stderr.05.expected.txt
new file mode 100644
index 0000000..0c02a37
--- /dev/null
+++ b/tests/stderr.05.expected.txt
@@ -0,0 +1,5 @@
+tokens/lines examined: 1,942    
+ tokens/lines matched: 191
+       histogram keys: 11
+              runtime: 2.12ms
+Key|Ct (Pct)    Histogram
diff --git a/tests/stderr.06.expected.txt b/tests/stderr.06.expected.txt
new file mode 100644
index 0000000..3b3e503
--- /dev/null
+++ b/tests/stderr.06.expected.txt
@@ -0,0 +1,5 @@
+tokens/lines examined: 56,960... ; hash prunes: 0
tokens/lines examined: 113,920... ; hash prunes: 0
tokens/lines examined: 171,773... ; hash prunes: 0
tokens/lines examined: 184,800    
+ tokens/lines matched: 184,800
+       histogram keys: 68
+              runtime: 3,243.41ms
+Key|Ct (Pct)       Histogram
diff --git a/tests/stderr.07.expected.txt b/tests/stderr.07.expected.txt
new file mode 100644
index 0000000..c6f84aa
--- /dev/null
+++ b/tests/stderr.07.expected.txt
@@ -0,0 +1 @@
+ Key|Ct (Pct)     Histogram
diff --git a/tests/input01.txt b/tests/stdin.01.txt
similarity index 100%
rename from tests/input01.txt
rename to tests/stdin.01.txt
diff --git a/tests/input02.txt b/tests/stdin.02.txt
similarity index 100%
rename from tests/input02.txt
rename to tests/stdin.02.txt
diff --git a/tests/input03.txt b/tests/stdin.03.txt
similarity index 100%
rename from tests/input03.txt
rename to tests/stdin.03.txt
diff --git a/tests/input04.txt b/tests/stdin.04.txt
similarity index 100%
rename from tests/input04.txt
rename to tests/stdin.04.txt
diff --git a/tests/stdout.01.expected.txt b/tests/stdout.01.expected.txt
new file mode 100644
index 0000000..0216b0d
--- /dev/null
+++ b/tests/stdout.01.expected.txt
@@ -0,0 +1,35 @@
+         /etc/mateconf|7780758 (44.60%) ••••••••••••••••••••••••••••••••••••••••••••••••••••••••••••••••••••••••••••••••
+           /etc/brltty|3143272 (18.02%) ••••••••••••••••••••••••••••••••
+       /etc/apparmor.d|1597915 (9.16%)  •••••••••••••••••
+/etc/bash_completion.d|597836 (3.43%)   •••••••
+             /etc/mono|535352 (3.07%)   ••••••
+              /etc/ssl|465414 (2.67%)   •••••
+          /etc/ardour2|362303 (2.08%)   ••••
+              /etc/X11|226309 (1.30%)   •••
+      /etc/ImageMagick|202358 (1.16%)   •••
+           /etc/init.d|143281 (0.82%)   ••
+              /etc/ssh|138042 (0.79%)   ••
+            /etc/fonts|119862 (0.69%)   ••
+            /etc/sound|112051 (0.64%)   ••
+              /etc/xdg|111971 (0.64%)   ••
+   /etc/java-7-openjdk|100414 (0.58%)   ••
+          /etc/apache2|95556 (0.55%)    •
+      /etc/ld.so.cache|92934 (0.53%)    •
+           /etc/sane.d|71429 (0.41%)    •
+           /etc/dbus-1|70918 (0.41%)    •
+             /etc/init|58780 (0.34%)    •
+  /etc/bash_completion|58753 (0.34%)    •
+    /etc/console-setup|57645 (0.33%)    •
+/etc/speech-dispatcher|53500 (0.31%)    •
+             /etc/gimp|41894 (0.24%)    •
+              /etc/ppp|41552 (0.24%)    •
+              /etc/apt|40810 (0.23%)    •
+           /etc/grub.d|40058 (0.23%)    •
+              /etc/xml|35802 (0.21%)    •
+            /etc/gnome|33126 (0.19%)    •
+          /etc/default|32218 (0.18%)    •
+   /etc/wpa_supplicant|31611 (0.18%)    •
+       /etc/cron.daily|30047 (0.17%)    •
+             /etc/acpi|27944 (0.16%)    •
+              /etc/vga|25081 (0.14%)    •
+            /etc/pam.d|24963 (0.14%)    •
diff --git a/tests/stdout.02.expected.txt b/tests/stdout.02.expected.txt
new file mode 100644
index 0000000..9bebd8a
--- /dev/null
+++ b/tests/stdout.02.expected.txt
@@ -0,0 +1,20 @@
+        info|229 (20.74%) -----------------------------------------------------------------------------------o
+          PM|110 (9.96%)  ---------------------------------------o
+    pcieport|78 (7.07%)   ----------------------------o
+  Activation|62 (5.62%)   ----------------------o
+        INFO|44 (3.99%)   ---------------o
+         pci|21 (1.90%)   -------o
+Initializing|21 (1.90%)   -------o
+      system|16 (1.45%)   -----o
+       fglrx|16 (1.45%)   -----o
+        bcma|16 (1.45%)   -----o
+     smpboot|14 (1.27%)   -----o
+         NMI|14 (1.27%)   -----o
+ Calibrating|14 (1.27%)   -----o
+         CPU|14 (1.27%)   -----o
+     Booting|14 (1.27%)   -----o
+          on|13 (1.18%)   ----o
+         usb|11 (1.00%)   ---o
+        time|10 (0.91%)   ---o
+          sd|10 (0.91%)   ---o
+  nameserver|10 (0.91%)   ---o
diff --git a/tests/stdout.03.expected.txt b/tests/stdout.03.expected.txt
new file mode 100644
index 0000000..9bd8370
--- /dev/null
+++ b/tests/stdout.03.expected.txt
@@ -0,0 +1,9 @@
+2012-01-01|3 (10.34%) |||||||||||||||||||||||||||||||||||||||||||||||||||||
+2012-01-02|2 (6.90%)  |||||||||||||||||||||||||||||||||||
+2012-01-03|3 (10.34%) |||||||||||||||||||||||||||||||||||||||||||||||||||||
+2012-01-04|3 (10.34%) |||||||||||||||||||||||||||||||||||||||||||||||||||||
+2012-01-05|3 (10.34%) |||||||||||||||||||||||||||||||||||||||||||||||||||||
+2012-01-06|3 (10.34%) |||||||||||||||||||||||||||||||||||||||||||||||||||||
+2012-01-07|4 (13.79%) ||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||
+2012-01-08|3 (10.34%) |||||||||||||||||||||||||||||||||||||||||||||||||||||
+2012-01-09|5 (17.24%) ||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||
diff --git a/tests/stdout.04.expected.txt b/tests/stdout.04.expected.txt
new file mode 100644
index 0000000..6e68524
--- /dev/null
+++ b/tests/stdout.04.expected.txt
@@ -0,0 +1,8 @@
+      var|265 (27.69%) (((((((((((((((((((((((((((((((((((()
+      log|265 (27.69%) (((((((((((((((((((((((((((((((((((()
+  upstart|123 (12.85%) (((((((((((((((()
+     cups|11 (1.15%)   ()
+installer|8 (0.84%)    ()
+  lightdm|7 (0.73%)    )
+  apache2|7 (0.73%)    )
+      apt|5 (0.52%)    )
diff --git a/tests/stdout.05.expected.txt b/tests/stdout.05.expected.txt
new file mode 100644
index 0000000..a7af6b7
--- /dev/null
+++ b/tests/stdout.05.expected.txt
@@ -0,0 +1,11 @@
+ 0|6 (3.14%)   ppppc
+ 1|46 (24.08%) ppppppppppppppppppppppppppppppppc
+ 2|27 (14.14%) ppppppppppppppppppc
+ 3|24 (12.57%) ppppppppppppppppc
+ 4|24 (12.57%) ppppppppppppppppc
+ 5|21 (10.99%) ppppppppppppppc
+ 6|21 (10.99%) ppppppppppppppc
+ 7|19 (9.95%)  pppppppppppppc
+ 8|1 (0.52%)   c
+ 9|1 (0.52%)   c
+10|1 (0.52%)   c
diff --git a/tests/stdout.06.expected.txt b/tests/stdout.06.expected.txt
new file mode 100644
index 0000000..ab22a9e
--- /dev/null
+++ b/tests/stdout.06.expected.txt
@@ -0,0 +1,29 @@
+  7|51975 (28.12%) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
+  9|46200 (25.00%) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
+  1|17327 (9.38%)  ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
+  3|14437 (7.81%)  ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
+ 13|11550 (6.25%)  ^^^^^^^^^^^^^^^^^^^^^^^^
+ 41|5775 (3.12%)   ^^^^^^^^^^^^
+  5|5774 (3.12%)   ^^^^^^^^^^^^
+ 15|5774 (3.12%)   ^^^^^^^^^^^^
+ 11|3249 (1.76%)   ^^^^^^^
+ 19|2888 (1.56%)   ^^^^^^
+ 97|2887 (1.56%)   ^^^^^^
+ 43|2887 (1.56%)   ^^^^^^
+ 99|1444 (0.78%)   ^^^
+ 47|1444 (0.78%)   ^^^
+ 39|1444 (0.78%)   ^^^
+ 27|1444 (0.78%)   ^^^
+009|1444 (0.78%)   ^^^
+ 95|722 (0.39%)    ^^
+ 55|722 (0.39%)    ^^
+033|722 (0.39%)    ^^
+ 03|722 (0.39%)    ^^
+011|720 (0.39%)    ^^
+035|362 (0.20%)    ^
+015|362 (0.20%)    ^
+081|361 (0.20%)    ^
+007|361 (0.20%)    ^
+177|184 (0.10%)    ^
+083|181 (0.10%)    ^
+023|181 (0.10%)    ^
diff --git a/tests/stdout.07.expected.txt b/tests/stdout.07.expected.txt
new file mode 100644
index 0000000..4c70f96
--- /dev/null
+++ b/tests/stdout.07.expected.txt
@@ -0,0 +1,10 @@
+   S|113 (41.39%) ΞΞΞΞΞΞΞΞΞΞΞΞΞΞΞΞΞΞΞΞΞΞΞΞΞΞΞΞΞΞΞΞΞΞΞΞΞΞΞΞΞΞΞΞΞΞΞΞΞΞΞΞΞΞΞΞΞΞΞΞΞΞΞΞΞΞΞΞΞΞΞΞ
+  Sl|71 (26.01%)  ΞΞΞΞΞΞΞΞΞΞΞΞΞΞΞΞΞΞΞΞΞΞΞΞΞΞΞΞΞΞΞΞΞΞΞΞΞΞΞΞΞΞΞΞΞ
+  S<|25 (9.16%)   ΞΞΞΞΞΞΞΞΞΞΞΞΞΞΞΞ
+ Ss+|21 (7.69%)   ΞΞΞΞΞΞΞΞΞΞΞΞΞΞ
+  Ss|20 (7.33%)   ΞΞΞΞΞΞΞΞΞΞΞΞΞ
+  SN|9 (3.30%)    ΞΞΞΞΞΞ
+ Ssl|6 (2.20%)    ΞΞΞΞ
+   Z|3 (1.10%)    ΞΞ
+STAT|1 (0.37%)    Ξ
+ SNl|1 (0.37%)    Ξ