added cli option --include-commits. v0.8.3

CHANGELOG.md

@@ -1,5 +1,10 @@
 # CHANGELOG
 
+## [0.8.3]
+- Added cli option (--include-commits) to include a list of fixing-commits. The purpose is to save time during future
+analyses.
+- Upgraded dependencies.
+
 ## [0.8.0]
 - Added two more options to the CLI to mine fixing-commits and fixed-files
 - Refactored application

docs/cli/mine.md

@@ -16,6 +16,8 @@ optional arguments:
   -b, --branch BRANCH   the repository branch to mine (default: master)
   --exclude-commits EXCLUDE_COMMITS
                         the path to a JSON file containing the list of commit hashes to exclude
+  --include-commits INCLUDE_COMMITS
+                        the path to a JSON file containing the list of commit hashes to include
   --exclude-files EXCLUDE_FILES
                         the path to a JSON file containing the list of FixedFiles to exclude
   --verbose             show log
@@ -24,11 +26,10 @@ optional arguments:
 !!! note "Output"
     Running this command will generate the following report files:
 
-    * `dest/failure-prone-files.html`
-    * `dest/failure-prone-files.json`
+    * `dest/fixing-commits.json` containing the list of fixing-commit hashes;
+    * `dest/fixed-files.json` containing the list of FixedFile objects (if mined `fixed-files` or `failure-prone-files`);
+    * `dest/failure-prone-files.json` containing the list of FailureProne objects (if mined `failure-prone-files`);
 
-    File `failure-prone-files.json` is a list of dictionaries containing the `filepath` relative to the repository root,
-    the `commit` hash at which the file was failure-prone, and the respective `fixing-commit` hash.
 
 !!! warning "Requirements"
     To properly use this command you **MUST** add the following to your environment variables: 
@@ -41,7 +42,7 @@ optional arguments:
 
     * `TMP_REPOSITORIES_DIR=<path/to/tmp/repositories/>` to temporary clone the remote repository for analysis. 
     Please, note that the repository will be cloned in this folder but not deleted. The latter step is left to the user,
-    when and if needed. 
+    when and if needed. **Note:** this variable is not needed if using the Docker image.
 
 
 

repominer/cli.py

@@ -12,9 +12,8 @@
 from repominer.mining.base import BaseMiner
 from repominer.mining.ansible import AnsibleMiner
 from repominer.mining.tosca import ToscaMiner
-# from repominer.report import create_report
 
-VERSION = '0.8.2'
+VERSION = '0.8.3'
 
 
 def valid_dir_or_url(x: str) -> str:
@@ -96,6 +95,12 @@ def set_mine_parser(subparsers):
                         type=valid_file,
                         help='the path to a JSON file containing the list of commit hashes to exclude')
 
+    parser.add_argument('--include-commits',
+                        action='store',
+                        dest='include_commits',
+                        type=valid_file,
+                        help='the path to a JSON file containing the list of commit hashes to include')
+
     parser.add_argument('--exclude-files',
                         action='store',
                         dest='exclude_files',
@@ -165,13 +170,18 @@ def get_parser():
     return parser
 
 
-def mine_fixing_commits(miner: BaseMiner, verbose: bool, dest: str, exclude_commits: str = None):
+def mine_fixing_commits(miner: BaseMiner, verbose: bool, dest: str, exclude_commits: str = None, include_commits: str = None):
 
     if exclude_commits:
         with open(exclude_commits, 'r') as f:
             commits = json.load(f)
             miner.exclude_commits = set(commits)
 
+    if include_commits:
+        with open(include_commits, 'r') as f:
+            commits = json.load(f)
+            miner.fixing_commits = commits
+
     if verbose:
         print('Identifying fixing-commits from closed issues related to bugs')
 
@@ -260,7 +270,7 @@ def mine(args: Namespace):
     else:
         miner = ToscaMiner(url_to_repo=url_to_repo, branch=args.branch)
 
-    mine_fixing_commits(miner, args.verbose, args.dest, args.exclude_commits)
+    mine_fixing_commits(miner, args.verbose, args.dest, args.exclude_commits, args.include_commits)
 
     if args.info_to_mine in ('fixed-files', 'failure-prone-files'):
         mine_fixed_files(miner, args.verbose, args.dest, args.exclude_files)

requirements.txt

@@ -1,5 +1,5 @@
-ansiblemetrics~=0.3.6
-pandas~=1.1.3
+ansiblemetrics~=0.3.7
+pandas~=1.1.4
 pydriller~=1.15.2
 pygithub~=1.53
 python-gitlab~=2.5.0

setup.py

@@ -8,7 +8,7 @@
 with open("README.md", "r") as fh:
     long_description = fh.read()
 
-VERSION = '0.8.2'
+VERSION = '0.8.3'
 
 setup(name='repository-miner',
       version=VERSION,