i #313 Added Notebook for Syntax Extraction

- Documented current syntax extraction functions
- Overview on syntax extraction and XPath
- Placeholder for syntax.yml config file

Signed-off-by: Dao McGill <[email protected]>

conf/junit5.yml

@@ -36,7 +36,7 @@ version_control:
   # Where is the git log located locally?
   # This is the path to the .git of the project repository you are analyzing.
   # The .git is hidden, so you can see it using `ls -a`
-  log: ../../rawdata/git_repo/junit5/.git
+  log: ../rawdata/git_repo/junit5/.git
   # From where the git log was downloaded?
   log_url: https://github.com/junit-team/junit5/
   # List of branches used for analysis
@@ -120,7 +120,7 @@ tool:
     # The project folder path to store various intermediate
     # files for DV8 Analysis
     # The folder name will be used in the file names.
-    folder_path: ../../analysis/dv8/junit
+    folder_path: ../analysis/dv8/junit
     # the architectural flaws thresholds that should be used
     architectural_flaws:
       cliqueDepends:
@@ -164,10 +164,10 @@ tool:
   # srcML allow to parse src code as text (e.g. identifiers)
   srcml:
     # The file path to where you wish to store the srcml output of the project
-    srcml_path: ../../analysis/junit/srcml_junit.xml
+    srcml_path: ../analysis/junit/srcml_junit.xml
   pattern4:
     # The file path to where you wish to store the srcml output of the project
-    class_folder_path: ../../rawdata/git_repo/junit5/junit-platform-engine/build/classes/java/main/org/junit/platform/engine/
+    class_folder_path: ../rawdata/git_repo/junit5/junit-platform-engine/build/classes/java/main/org/junit/platform/engine/
     compile_note: >
       1. Switch Java version to Java 17:
          https://stackoverflow.com/questions/69875335/macos-how-to-install-java-17

conf/syntax.yml

@@ -0,0 +1,71 @@
+# -*- yaml -*-
+# https://github.com/sailuh/kaiaulu
+#
+# Copying and distribution of this file, with or without modification,
+# are permitted in any medium without royalty provided the copyright
+# notice and this notice are preserved.  This file is offered as-is,
+# without any warranty.
+
+# Project Configuration File #
+#
+# To perform analysis on open source projects, you need to manually
+# collect some information from the project's website. As there is
+# no standardized website format, this file serves to distill
+# important data source information so it can be reused by others
+# and understood by Kaiaulu.
+#
+# Please check https://github.com/sailuh/kaiaulu/tree/master/conf to
+# see if a project configuration file already exists. Otherwise, we
+# would appreciate if you share your curated file with us by sending a
+# Pull Request: https://github.com/sailuh/kaiaulu/pulls
+#
+# Note, you do NOT need to specify this entire file to conduct analysis.
+# Each R Notebook uses a different portion of this file. To know what
+# information is used, see the project configuration file section at
+# the start of each R Notebook.
+#
+# Please comment unused parameters instead of deleting them for clarity.
+# If you have questions, please open a discussion:
+# https://github.com/sailuh/kaiaulu/discussions
+
+project:
+  website: https://github.com/junit-team/junit5/
+  #openhub: https://www.openhub.net/p/apache_portable_runtime
+
+version_control:
+  # Where is the git log located locally?
+  # This is the path to the .git of the project repository you are analyzing.
+  # The .git is hidden, so you can see it using `ls -a`
+  log: ../rawdata/git_repo/junit5/.git
+  # From where the git log was downloaded?
+  log_url: https://github.com/junit-team/junit5/
+  # List of branches used for analysis
+  branch:
+    - main
+
+filter:
+  keep_filepaths_ending_with:
+    - cpp
+    - c
+    - h
+    - java
+    - js
+    - py
+    - cc
+  remove_filepaths_containing:
+    - test
+    - java_code_examples
+
+tool:
+ # srcML allow to parse src code as text (e.g. identifiers)
+  srcml:
+    # The file path to where you wish to store the srcml output of the project
+    srcml_path: ../analysis/depends/srcml_depends.xml
+# Analysis Configuration #
+analysis:
+  # A list of topic and keywords (see src_text_showcase.Rmd).
+  topics:
+    topic_1:
+      - model
+      - view
+      - controller