Add additional datasets

README.rst

@@ -24,6 +24,19 @@ Usage
 
 This is designed to run only on Linux.
 
+
+Tests
+=====
+
+``test_matchcode.py`` uses the dataset "Analyzing the Dependability of Large
+Language Models for Code Clone Generation"
+(https://zenodo.org/records/11398703). This dataset contains code solutions to
+problems from LeetCode that have been generated by AI from an original solution.
+The tests in ``test_matchcode.py`` compare the original solutions to the
+different variations of AI generated solutions, where we compare Hamming
+distances and detected ngrams from the different solutions.
+
+
 License
 =============
 

azure-pipelines.yml

@@ -11,14 +11,22 @@ jobs:
       parameters:
           job_name: ubuntu20_cpython
           image_name: ubuntu-20.04
-          python_versions: ['3.9', '3.10', '3.11', '3.12']
+          python_versions: ['3.10', '3.11', '3.12', '3.13']
           test_suites:
               all: venv/bin/pytest -n 2 -vvs
 
     - template: etc/ci/azure-posix.yml
       parameters:
           job_name: ubuntu22_cpython
           image_name: ubuntu-22.04
-          python_versions: ['3.9', '3.10', '3.11', '3.12']
+          python_versions: ['3.10', '3.11', '3.12', '3.13']
+          test_suites:
+              all: venv/bin/pytest -n 2 -vvs
+
+    - template: etc/ci/azure-posix.yml
+      parameters:
+          job_name: ubuntu24_cpython
+          image_name: ubuntu-24.04
+          python_versions: ['3.10', '3.11', '3.12', '3.13']
           test_suites:
               all: venv/bin/pytest -n 2 -vvs

setup.cfg

@@ -58,6 +58,7 @@ testing =
     isort
     scancode-toolkit
     matchcode-toolkit
+    samecode
 
 docs =
     Sphinx>=5.0.2