VPL Toolkit is a light toolkit to help teachers to program VPL activity in Moodle for their students.
Features:
- a public & reusable execution model for VPL
- a toolkit with some basic bash functions
- offline execution
What happens when a student clicks on the Run/Eval button of your VPL Editor in Moodle (or in Test Activity, if you are teacher)?
First, it will launch the vpl_run.sh (resp vpl_evaluate.sh) script, that you must provide in the VPL Interface > Execution Files. Typically, this script must provide in any way a new shell script called vpl_execution, that will be implicitly launched after vpl_run.sh (resp vpl_evaluate.sh) is completed. At this stage, vpl_execution calls a teacher-defined script run.sh (resp. eval.sh) depending on the execution mode, either RUN or EVAL. Here is an overview of the
click RUN button --> vpl_run.sh ----------+ +--> run.sh
|--> vpl_execution --|
click EVAL button --> vpl_evaluate.sh ----+ +--> eval.sh
To develop a new VPL activity, it is often convenient to launch it offline without the Moodle frontend, using local scripts, as follow:
local_run.sh ----------+ +--> run.sh
|--> vpl_execution --|
local_eval.sh ---------+ +--> eval.sh
The run.sh (resp. eval.sh) script is starting from the $RUNDIR directory, organized as follow:
$RUNDIR
├── env.sh # environment variable for the VPL toolkit
├── run.sh # entry point for RUN mode
├── eval.sh # entry point for EVAL mode
├── ... # all files provided by teacher...
├── inputs # all student input files ($VPL_SUBFILES)
8000
│ └── student.c
| └── ...
└── vpltoolkit # VPL toolkit
└── start.sh # startup script
└── toolkit.sh # useful bash routines
└── vpl_execution
└── ...
Besides, you will find important VPL files in $HOME, that are useful for VPL execution online. For security issues, some of these files are removed at runtime.
$HOME
├── env.sh
├── vpl_execution
├── vpl_run.sh
├── vpl_evaluate.sh
└── ...
See documentation: http://vpl.dis.ulpgc.es/index.php/support
(...)
Rules:
- in RUN mode, all outputs are visible in a terminal window by students (as a basic shell script)
- in EVAL mode, all outputs in comment window are visible by students (it is the main output window)
- in EVAL mode, all outputs in execution window are only visible by teacher (for debug purpose)
To present outputs and grades properly, we provide several useful bash functions in toolkit.sh.
Let's consider the example hello. First, you need to add a new activity This activity consists of only scripts run.sh & eval.sh that just print "hello world!" on standard output.
#!/bin/bash
echo "hello world!"To use the VPL Toolkit online, start to copy the following script into vpl_run.sh & vpl_evaluate.sh of VPL@Moodle. Note that on EVAL mode, the "hello world" message is only visible for teacher in execution window.
#!/bin/bash
rm -f $0 # for security issue
RUNDIR=$(mktemp -d)
( cd $RUNDIR && git clone "https://github.com/orel33/vpltoolkit.git" &> /dev/null )
source $RUNDIR/vpltoolkit/start.sh
DOWNLOAD "https://github.com/orel33/vpltoolkit.git" "demo" "hello"
START_ONLINETo launch this example offline, you need to write a script named local_run.sh & local_evaluate.sh as follow.
#!/bin/bash
RUNDIR=$(mktemp -d)
( cd $RUNDIR && git clone "https://github.com/orel33/vpltoolkit.git" &> /dev/null )
source $RUNDIR/vpltoolkit/start.sh
DOWNLOAD "https://github.com/orel33/vpltoolkit.git" "demo" "hello"
START_OFFLINEOr if you prefer, you can use the local_run.sh (or local_evaluate.sh) provided in this repository.
$ ./local_run.sh hello
hello world!Using Bash DEBUG mode (set -x).
$ DEBUG=1 ./local_run.sh hello
+ echo 'hello world!'
hello world!An advanced example is found in the demo branch of this repository: see mycat. Let's have a look on the eval.sh script for instance.
#!/bin/bash
### initialization
source env.sh
source vpltoolkit/toolkit.sh
[ ! "$RUNDIR" = "$PWD" ] && echo "⚠ RUNDIR is not set correctly!" && exit 0
CHECKINPUTS
cp inputs/mycat.c .
GRADE=0
### compilation
TITLE "COMPILATION"
CFLAGS="-std=c99 -Wall"
WFLAGS="-Wl,--wrap=system"
TRACE "gcc $CFLAGS $WFLAGS mycat.c -o mycat |& tee warnings"
[ $? -ne 0 ] && MALUS "Compilation" X "errors"
[ -s warnings ] && MALUS "Compilation" 20 "warnings"
[ -x mycat ] && BONUS "Linking" 30
### execution
TITLE "EXECUTION"
TRACE "echo \"abcdef\" > mycat.in"
TRACE "cat mycat.in | ./mycat > mycat.out"
[ $? -ne 0 ] && MALUS "Return" 10 "bad status"
TRACE "diff -q mycat.in mycat.out"
EVAL "Program output" 70 0 "valid" "invalid"
EXITHere is the offline test of this script with an input directory of the solution (grade 100% expected).
$ git checkout demo
$ ./local_eval.sh mycat mycat/test/solution
Comment :=>>-COMPILATION
Trace :=>>$ gcc -std=c99 -Wall -Wl,--wrap=system mycat.c -o mycat |& tee warnings
Status :=>> 0
Comment :=>>✓ Linking: success. [+30]
Comment :=>>-EXECUTION
Trace :=>>$ echo "abcdef" > mycat.in
Status :=>> 0
Trace :=>>$ cat mycat.in | ./mycat > mycat.out
Status :=>> 0
Trace :=>>$ diff -q mycat.in mycat.out
Status :=>> 0
Comment :=>>✓ Program output: valid [+70]
Comment :=>>
Comment :=>>-GRADE
Comment :=>>100 / 100
Grade :=>> 100- add script to launch all local tests offline and compare them against an expected grade
- add an option to use a docker environment for offline execution (and maybe online)
- use an optional execution file env.sh (provided by teacher at Moodle)
- add other DOWNLOAD methods for wget and scp
- offline mode: replace local_run/eval.sh exo inputdir by run/eval.sh inputdir if $1 is used!
- add branch 1.0 for version 1.0 and use it when cloning vpltoolkit repository
- add foating point calculation of GRADE (using command bc)