Merge pull request #169 from VariantSync/unparse

Improved Unparser

Author: pmbittner

docs/datasets/eugen-bachelor-thesis.md

@@ -0,0 +1,5 @@
+Project name       | Domain                  | Source code available (\*\*y\*\*es/\*\*n\*\*o)? | Is it a git repository (\*\*y\*\*es/\*\*n\*\*o)? | Repository URL                                               | Clone URL                                          | Estimated number of commits
+-------------------|-------------------------|-------------------------------------------------|--------------------------------------------------|--------------------------------------------------------------|----------------------------------------------------|---------------------------------
+berkeley-db-libdb  | database system         | y                                               | y                                                | https://github.com/berkeleydb/libdb                          | https://github.com/berkeleydb/libdb.git            | 7
+sylpheed           | e-mail client           | y                                               | y                                                | https://github.com/jan0sch/sylpheed                          | https://github.com/jan0sch/sylpheed.git            | 2,682
+vim                | text editor             | y                                               | y                                                | https://github.com/vim/vim                                   | https://github.com/vim/vim.git                     | 17,109

replication/thesis-es/Dockerfile

@@ -0,0 +1,57 @@
+# syntax=docker/dockerfile:1
+
+FROM alpine:3.15
+# PACKAGE STAGE
+
+# Prepare the compile environment. JDK is automatically installed
+RUN apk add maven
+
+# Create and navigate to a working directory
+WORKDIR /home/user
+
+COPY local-maven-repo ./local-maven-repo
+
+# Copy the source code
+COPY src ./src
+# Copy the pom.xml if Maven is used
+COPY pom.xml .
+# Execute the maven package process
+RUN mvn package || exit
+
+FROM alpine:3.15
+
+# Create a user
+RUN adduser --disabled-password  --home /home/sherlock --gecos '' sherlock
+
+RUN apk add --no-cache --upgrade bash
+RUN apk add --update openjdk17
+
+# Change into the home directory
+WORKDIR /home/sherlock
+
+# Copy the compiled JAR file from the first stage into the second stage
+# Syntax: COPY --from=STAGE_ID SOURCE_PATH TARGET_PATH
+WORKDIR /home/sherlock/holmes
+COPY --from=0 /home/user/target/diffdetective-*-jar-with-dependencies.jar ./DiffDetective.jar
+WORKDIR /home/sherlock
+RUN mkdir results
+
+# Copy the setup
+COPY docs holmes/docs
+
+# Copy the docker resources
+COPY docker/* ./
+COPY replication/thesis-es/docker/* ./
+RUN mkdir DiffDetectiveMining
+
+#  Adjust permissions
+RUN chown sherlock:sherlock /home/sherlock -R
+RUN chmod +x execute.sh
+RUN chmod +x entrypoint.sh
+RUN chmod +x fix-perms.sh
+
+# Set the entrypoint
+ENTRYPOINT ["./entrypoint.sh", "./execute.sh"]
+
+# Set the user
+USER sherlock

replication/thesis-es/README.md

@@ -0,0 +1,49 @@
+![Maven](https://github.com/VariantSync/DiffDetective/actions/workflows/maven.yml/badge.svg)
+[![Documentation](https://img.shields.io/badge/Documentation-Read-purple)][documentation]
+[![Install](https://img.shields.io/badge/Install-Instructions-blue)](INSTALL.md)
+[![GitHubPages](https://img.shields.io/badge/GitHub%20Pages-online-blue.svg?style=flat)][website]
+[![License](https://img.shields.io/badge/License-GNU%20LGPLv3-blue)](../../LICENSE.LGPL3)
+
+# Unparsing Experiment
+This is an experiment for the bachelor thesis by Eugen Shulimov which tests the unparser for variation trees and diffs.
+
+### Prerequisite
+All following commands assume that working directory of your terminal is the `thesis-es` directory. Please switch directories, if this is not the case:
+```shell
+cd DiffDetective/replication/thesis-es
+```
+
+### Build the Docker container
+Start the docker deamon.
+Clone this repository.
+Open a terminal and navigate to the root directory of this repository.
+To build the Docker container you can run the `build` script corresponding to your operating system.
+#### Windows:
+`.\build.bat`
+#### Linux/Mac (bash):
+`./build.sh`
+
+### Start the experiment
+To execute the experiment you can run the `execute`script corresponding to your operating system.
+
+#### Windows:
+`.\execute.bat
+#### Linux/Mac (bash):
+`./execute.sh
+
+> If you want to stop the execution, you can call the provided script for stopping the container in a separate terminal.
+> When restarted, the execution will continue processing by restarting at the last unfinished repository.
+> #### Windows:
+> `.\stop-execution.bat`
+> #### Linux/Mac (bash):
+> `./stop-execution.sh`
+
+You might see warnings or errors reported from SLF4J like `Failed to load class "org.slf4j.impl.StaticLoggerBinder"` which you can safely ignore.
+
+### View the results in the [results][resultsdir] directory
+All raw results are stored in the [results][resultsdir] directory.
+
+[documentation]: https://variantsync.github.io/DiffDetective/docs/javadoc/
+[website]: https://variantsync.github.io/DiffDetective/
+
+[resultsdir]: results

replication/thesis-es/build.bat

@@ -0,0 +1,19 @@
+@echo off
+setlocal
+
+set "targetSubPath=thesis-es"
+
+rem Get the current directory
+for %%A in ("%CD%") do set "currentDir=%%~nxA"
+
+rem Check if the current directory ends with the target sub-path
+
+if "%currentDir:~-9%"=="%targetSubPath%" (
+    cd ..\..
+    docker build -t diff-detective-unparse -f replication\thesis-es\Dockerfile .
+    @pause
+) else (
+    echo error: the script must be run from inside the thesis-es directory, i.e., DiffDetective\replication\%targetSubPath%
+)
+endlocal
+

replication/thesis-es/build.sh

@@ -0,0 +1,11 @@
+#!/usr/bin/env bash
+
+# We have to switch to the root directory of the project and build the Docker image from there,
+# because Docker only allows access to the files in the current file system subtree (i.e., no access to ancestors).
+# We have to do this to get access to 'src', 'docker', 'local-maven-repo', etc.
+# For resiliency against different working directories during execution of this
+# script we calculate the correct path using the special bash variable
+# BASH_SOURCE.
+cd "$(dirname "${BASH_SOURCE[0]}")/../.." || exit
+
+docker build -t diff-detective-unparse -f replication/thesis-es/Dockerfile .

replication/thesis-es/docker/DOCKER.md

@@ -0,0 +1,6 @@
+# Docker Files
+
+This directory contains the files that are required to run the Docker container.
+
+## Execution
+The [`execute.sh`](execute.sh) script can be adjusted to run the program that should be executed by the Docker container.

replication/thesis-es/docker/execute.sh

@@ -0,0 +1,11 @@
+#!/usr/bin/env bash
+
+cd /home/sherlock/holmes || exit
+
+echo "Running the experiment."
+java -cp DiffDetective.jar org.variantsync.diffdetective.experiments.thesis-es.Main
+
+echo "Collecting results."
+cp -r results/* ../results/
+echo "The results are located in the 'results' directory."
+

replication/thesis-es/execute.bat

@@ -0,0 +1,15 @@
+@echo off
+setlocal
+
+set "targetSubPath=thesis-es"
+
+rem Get the current directory
+for %%A in ("%CD%") do set "currentDir=%%~nxA"
+
+rem Check if the current directory ends with the target sub-path
+if "%currentDir:~-9%"=="%targetSubPath%" (
+docker run --rm -v "%cd%\results":"/home/sherlock/results" diff-detective-unparse %*
+) else (
+    echo error: the script must be run from inside the thesis-es directory, i.e., DiffDetective\replication\%targetSubPath%
+)
+endlocal

replication/thesis-es/execute.sh

@@ -0,0 +1,8 @@
+#!/usr/bin/env bash
+# Assure that the script is only called from the folder cotaining this script
+cd "$(dirname "${BASH_SOURCE[0]}")" || exit
+
+if [[ $# -gt 0 ]]; then
+echo "Executing $1"
+fi
+docker run --rm -v "$(pwd)/results":"/home/sherlock/results" diff-detective-unparse "$@"

replication/thesis-es/results/.gitignore

@@ -0,0 +1,4 @@
+# Ignore everything in this directory
+*
+# Except this file
+!.gitignore