Initial commit

.dockerignore

@@ -0,0 +1,3 @@
+issues
+temp
+out

.gitignore

@@ -0,0 +1,160 @@
+
+# Created by https://www.toptal.com/developers/gitignore/api/pycharm+all,code,intellij+all
+# Edit at https://www.toptal.com/developers/gitignore?templates=pycharm+all,code,intellij+all
+
+### Code ###
+.vscode/*
+!.vscode/settings.json
+!.vscode/tasks.json
+!.vscode/launch.json
+!.vscode/extensions.json
+*.code-workspace
+
+### Intellij+all ###
+# Covers JetBrains IDEs: IntelliJ, RubyMine, PhpStorm, AppCode, PyCharm, CLion, Android Studio, WebStorm and Rider
+# Reference: https://intellij-support.jetbrains.com/hc/en-us/articles/206544839
+
+# User-specific stuff
+.idea/**/workspace.xml
+.idea/**/tasks.xml
+.idea/**/usage.statistics.xml
+.idea/**/dictionaries
+.idea/**/shelf
+
+# Generated files
+.idea/**/contentModel.xml
+
+# Sensitive or high-churn files
+.idea/**/dataSources/
+.idea/**/dataSources.ids
+.idea/**/dataSources.local.xml
+.idea/**/sqlDataSources.xml
+.idea/**/dynamic.xml
+.idea/**/uiDesigner.xml
+.idea/**/dbnavigator.xml
+
+# Gradle
+.idea/**/gradle.xml
+.idea/**/libraries
+
+# Gradle and Maven with auto-import
+# When using Gradle or Maven with auto-import, you should exclude module files,
+# since they will be recreated, and may cause churn.  Uncomment if using
+# auto-import.
+# .idea/artifacts
+# .idea/compiler.xml
+# .idea/jarRepositories.xml
+# .idea/modules.xml
+# .idea/*.iml
+# .idea/modules
+# *.iml
+# *.ipr
+
+# CMake
+cmake-build-*/
+
+# Mongo Explorer plugin
+.idea/**/mongoSettings.xml
+
+# File-based project format
+*.iws
+
+# IntelliJ
+out/
+
+# mpeltonen/sbt-idea plugin
+.idea_modules/
+
+# JIRA plugin
+atlassian-ide-plugin.xml
+
+# Cursive Clojure plugin
+.idea/replstate.xml
+
+# Crashlytics plugin (for Android Studio and IntelliJ)
+com_crashlytics_export_strings.xml
+crashlytics.properties
+crashlytics-build.properties
+fabric.properties
+
+# Editor-based Rest Client
+.idea/httpRequests
+
+# Android studio 3.1+ serialized cache file
+.idea/caches/build_file_checksums.ser
+
+### Intellij+all Patch ###
+# Ignores the whole .idea folder and all .iml files
+# See https://github.com/joeblau/gitignore.io/issues/186 and https://github.com/joeblau/gitignore.io/issues/360
+
+.idea/
+
+# Reason: https://github.com/joeblau/gitignore.io/issues/186#issuecomment-249601023
+
+*.iml
+modules.xml
+.idea/misc.xml
+*.ipr
+
+# Sonarlint plugin
+.idea/sonarlint
+
+### PyCharm+all ###
+# Covers JetBrains IDEs: IntelliJ, RubyMine, PhpStorm, AppCode, PyCharm, CLion, Android Studio, WebStorm and Rider
+# Reference: https://intellij-support.jetbrains.com/hc/en-us/articles/206544839
+
+# User-specific stuff
+
+# Generated files
+
+# Sensitive or high-churn files
+
+# Gradle
+
+# Gradle and Maven with auto-import
+# When using Gradle or Maven with auto-import, you should exclude module files,
+# since they will be recreated, and may cause churn.  Uncomment if using
+# auto-import.
+# .idea/artifacts
+# .idea/compiler.xml
+# .idea/jarRepositories.xml
+# .idea/modules.xml
+# .idea/*.iml
+# .idea/modules
+# *.iml
+# *.ipr
+
+# CMake
+
+# Mongo Explorer plugin
+
+# File-based project format
+
+# IntelliJ
+
+# mpeltonen/sbt-idea plugin
+
+# JIRA plugin
+
+# Cursive Clojure plugin
+
+# Crashlytics plugin (for Android Studio and IntelliJ)
+
+# Editor-based Rest Client
+
+# Android studio 3.1+ serialized cache file
+
+### PyCharm+all Patch ###
+# Ignores the whole .idea folder and all .iml files
+# See https://github.com/joeblau/gitignore.io/issues/186 and https://github.com/joeblau/gitignore.io/issues/360
+
+
+# Reason: https://github.com/joeblau/gitignore.io/issues/186#issuecomment-249601023
+
+
+# Sonarlint plugin
+
+# End of https://www.toptal.com/developers/gitignore/api/pycharm+all,code,intellij+all
+
+temp/
+__pycache__

Dockerfile

@@ -0,0 +1,20 @@
+FROM python:3.7-slim-buster
+
+RUN echo "deb http://deb.debian.org/debian buster-backports main" >> /etc/apt/sources.list && \ 
+  apt-get update && apt-get upgrade -y --no-install-recommends && \
+  apt-get install -y --no-install-recommends wget libarchive13 libcurl4 libxml2 python-magic && \
+  apt-get -t buster-backports install -y --no-install-recommends git && \
+  rm -rf /var/lib/apt/lists/*
+
+RUN wget http://131.123.42.38/lmcrs/v1.0.0/srcml_1.0.0-1_ubuntu18.04.deb && \
+    dpkg -i srcml_1.0.0-1_ubuntu18.04.deb
+
+WORKDIR /usr/src/app
+
+COPY requirements.txt .
+RUN pip install --no-cache-dir -r requirements.txt
+
+COPY szz szz
+COPY main.py .
+
+ENTRYPOINT [ "python", "-u", "main.py" ]

README.md

@@ -0,0 +1,44 @@
+# PySZZ
+This is an open-source implementation of several versions of the SZZ algorithm for detecting bug-inducing commits.
+
+## Requirements
+To run PySZZ you need:
+
+- Python 3
+- srcML (https://www.srcml.org/) (i.e., the `srcml` command should be in the path)
+- git >= 2.23
+
+## Setup
+Run the following command to install the required python dependencies:
+```
+pip3 install --no-cache-dir -r requirements.txt
+```
+
+## Run
+To run the tool, simply execute the following command:
+
+```
+python3 main.py /path/to/bug-fixes.json /path/to/configuration-file.yml /path/to/repo-directory
+```
+where:
+
+- `bug-fixes.json` contains a list of information about bug-fixing commits and (optionally) issues
+- `configuration-file.yml` is one of the following, depending on the SZZ variant you want to run:
+    - `conf/agszz.yaml`: runs AG-ZZ
+    - `conf/lszz.yaml`: runs L-ZZ
+    - `conf/rszz.yaml`: runs R-ZZ
+    - `conf/maszz.yaml`: runs MA-ZZ
+    - `conf/raszz.yaml`: runs RA-ZZ
+- `repo-directory` is a folder which contains all the repositories that are required by `bug-fixes.json`
+
+To have different run configurations, just create or edit the configuration files. The available parameters are described in each yml file.
+
+## Input data
+The `data` dir contains two sub-folders:
+- `data/langs_only` contains the json files extracted from the dataset filtered only by the defined langs for the experiment.
+- `data/with_whitelist` contains the json files extracted from the dataset filtered by the file extensions defined in the [whitelist csv](https://gitlab.reveal.si.usi.ch/gbavota/icse2021-szz-oracle/-/blob/master/database/langs.csv).
+
+The input json files are the following:
+- `bugfix_commits_no_issues.json`: contains only fix commits having no issue references.
+- `bugfix_commits_issues_only.json`: contains only fix commits that reference one or more issues, where the `earliest_issue_date` field is the earliest creation date among the referenced issues;
+- `bugfix_commits_all.json`: contains all the fix commits, where if there are no referenced issues, the field `best_scenario_issue_date` will be the earliest creation date among the linked bug commits with a time offset of 60 seconds. Otherwise, the field `earliest_issue_date` will be the earliest issue creation date;

conf/agszz.yml

@@ -0,0 +1,22 @@
+### szz implementation
+szz_name: ag
+
+### obtain the diff only for the specified file extensions
+# file_ext_to_parse:
+#  - c
+#  - cpp
+#  - cs
+#  - h
+#  - java
+#  - js
+#  - py
+
+### detect in diff deleted lines only, otherwise detect only the lines that are both deleted and added
+only_deleted_lines: true
+issue_date_filter: false
+
+### ignore during blame all the commits specified in revs file
+# ignore_revs_file_path: /path/to/revs/file
+
+### ignores commits with a change size higher than the specified value during blame
+max_change_size: 20

conf/bszz.yml

@@ -0,0 +1,19 @@
+### szz implementation
+szz_name: b
+
+### obtain the diff only for the specified file extensions
+# file_ext_to_parse:
+#  - c
+#  - cpp
+#  - cs
+#  - h
+#  - java
+#  - js
+#  - py
+
+### detect in diff deleted lines only, otherwise detect only the lines that are both deleted and added
+only_deleted_lines: true
+issue_date_filter: false
+
+### ignore during blame all the commits specified in revs file
+# ignore_revs_file_path: /path/to/revs/file

conf/lszz.yml

@@ -0,0 +1,28 @@
+### szz implementation
+szz_name: l
+
+### obtain the diff only for the specified file extensions
+# file_ext_to_parse:
+#  - c
+#  - cpp
+#  - cs
+#  - h
+#  - java
+#  - js
+#  - py
+
+### detect in diff deleted lines only, otherwise detect only the lines that are both deleted and added
+only_deleted_lines: true
+issue_date_filter: true
+
+### ignore during blame all the commits specified in revs file
+# ignore_revs_file_path: /path/to/revs/file
+
+### ignores commits during blame with a change size higher than the specified value
+max_change_size: 20
+
+### set -C param for blame to detect line moves/copies across:
+## SAME_COMMIT = 1
+## PARENT_COMMIT = 2
+## ANY_COMMIT = 3
+detect_move_from_other_files: 1

conf/maszz.yml

@@ -0,0 +1,28 @@
+### szz implementation
+szz_name: ma
+
+### obtain the diff only for the specified file extensions
+# file_ext_to_parse:
+#  - c
+#  - cpp
+#  - cs
+#  - h
+#  - java
+#  - js
+#  - py
+
+### detect in diff deleted lines only, otherwise detect only the lines that are both deleted and added
+only_deleted_lines: true
+issue_date_filter: false
+
+### ignore during blame all the commits specified in revs file
+# ignore_revs_file_path: /path/to/revs/file
+
+### ignores commits during blame with a change size higher than the specified value
+max_change_size: 20
+
+### set -C param for blame to detect line moves/copies across:
+## SAME_COMMIT = 1
+## PARENT_COMMIT = 2
+## ANY_COMMIT = 3
+detect_move_from_other_files: 1

conf/raszz.yml

@@ -0,0 +1,22 @@
+### szz implementation
+szz_name: ra
+
+### obtain the diff only for the specified file extensions
+file_ext_to_parse:
+ - java
+
+### detect in diff deleted lines only, otherwise detect only the lines that are both deleted and added
+only_deleted_lines: true
+
+### ignore during blame all the commits specified in revs file
+# ignore_revs_file_path: /path/to/revs/file
+
+### ignores commits during blame with a change size higher than the specified value
+max_change_size: 20
+issue_date_filter: false
+
+### set -C param for blame to detect line moves/copies across:
+## SAME_COMMIT = 1
+## PARENT_COMMIT = 2
+## ANY_COMMIT = 3
+detect_move_from_other_files: 1

conf/rszz.yml

@@ -0,0 +1,28 @@
+### szz implementation
+szz_name: r
+
+### obtain the diff only for the specified file extensions
+# file_ext_to_parse:
+#  - c
+#  - cpp
+#  - cs
+#  - h
+#  - java
+#  - js
+#  - py
+
+### detect in diff deleted lines only, otherwise detect only the lines that are both deleted and added
+only_deleted_lines: true
+issue_date_filter: true
+
+### ignore during blame all the commits specified in revs file
+# ignore_revs_file_path: /path/to/revs/file
+
+### ignores commits during blame with a change size higher than the specified value
+max_change_size: 20
+
+### set -C param for blame to detect line moves/copies across:
+## SAME_COMMIT = 1
+## PARENT_COMMIT = 2
+## ANY_COMMIT = 3
+detect_move_from_other_files: 1