initial

.gitignore

@@ -0,0 +1,176 @@
+# Created by https://www.toptal.com/developers/gitignore/api/python
+# Edit at https://www.toptal.com/developers/gitignore?templates=python
+
+### Python ###
+# Byte-compiled / optimized / DLL files
+__pycache__/
+*.py[cod]
+*$py.class
+
+# C extensions
+*.so
+
+# Distribution / packaging
+.Python
+build/
+develop-eggs/
+dist/
+downloads/
+eggs/
+.eggs/
+lib/
+lib64/
+parts/
+sdist/
+var/
+wheels/
+share/python-wheels/
+*.egg-info/
+.installed.cfg
+*.egg
+MANIFEST
+
+# PyInstaller
+#  Usually these files are written by a python script from a template
+#  before PyInstaller builds the exe, so as to inject date/other infos into it.
+*.manifest
+*.spec
+
+# Installer logs
+pip-log.txt
+pip-delete-this-directory.txt
+
+# Unit test / coverage reports
+htmlcov/
+.tox/
+.nox/
+.coverage
+.coverage.*
+.cache
+nosetests.xml
+coverage.xml
+*.cover
+*.py,cover
+.hypothesis/
+.pytest_cache/
+cover/
+
+# Translations
+*.mo
+*.pot
+
+# Django stuff:
+*.log
+local_settings.py
+db.sqlite3
+db.sqlite3-journal
+
+# Flask stuff:
+instance/
+.webassets-cache
+
+# Scrapy stuff:
+.scrapy
+
+# Sphinx documentation
+docs/_build/
+
+# PyBuilder
+.pybuilder/
+target/
+
+# Jupyter Notebook
+.ipynb_checkpoints
+
+# IPython
+profile_default/
+ipython_config.py
+
+# pyenv
+#   For a library or package, you might want to ignore these files since the code is
+#   intended to run in multiple environments; otherwise, check them in:
+# .python-version
+
+# pipenv
+#   According to pypa/pipenv#598, it is recommended to include Pipfile.lock in version control.
+#   However, in case of collaboration, if having platform-specific dependencies or dependencies
+#   having no cross-platform support, pipenv may install dependencies that don't work, or not
+#   install all needed dependencies.
+#Pipfile.lock
+
+# poetry
+#   Similar to Pipfile.lock, it is generally recommended to include poetry.lock in version control.
+#   This is especially recommended for binary packages to ensure reproducibility, and is more
+#   commonly ignored for libraries.
+#   https://python-poetry.org/docs/basic-usage/#commit-your-poetrylock-file-to-version-control
+#poetry.lock
+
+# pdm
+#   Similar to Pipfile.lock, it is generally recommended to include pdm.lock in version control.
+#pdm.lock
+#   pdm stores project-wide configurations in .pdm.toml, but it is recommended to not include it
+#   in version control.
+#   https://pdm.fming.dev/#use-with-ide
+.pdm.toml
+
+# PEP 582; used by e.g. github.com/David-OConnor/pyflow and github.com/pdm-project/pdm
+__pypackages__/
+
+# Celery stuff
+celerybeat-schedule
+celerybeat.pid
+
+# SageMath parsed files
+*.sage.py
+
+# Environments
+.env
+.venv
+env/
+venv/
+ENV/
+env.bak/
+venv.bak/
+
+# Spyder project settings
+.spyderproject
+.spyproject
+
+# Rope project settings
+.ropeproject
+
+# mkdocs documentation
+/site
+
+# mypy
+.mypy_cache/
+.dmypy.json
+dmypy.json
+
+# Pyre type checker
+.pyre/
+
+# pytype static type analyzer
+.pytype/
+
+# Cython debug symbols
+cython_debug/
+
+# PyCharm
+#  JetBrains specific template is maintained in a separate JetBrains.gitignore that can
+#  be found at https://github.com/github/gitignore/blob/main/Global/JetBrains.gitignore
+#  and can be added to the global gitignore or merged into this file.  For a more nuclear
+#  option (not recommended) you can uncomment the following to ignore the entire idea folder.
+#.idea/
+
+### Python Patch ###
+# Poetry local configuration file - https://python-poetry.org/docs/configuration/#local-configuration
+poetry.toml
+
+# ruff
+.ruff_cache/
+
+# LSP config files
+pyrightconfig.json
+
+# End of https://www.toptal.com/developers/gitignore/api/python

.pylintrc

@@ -0,0 +1,5 @@
+[FORMAT]
+max-line-length=120
+
+[MESSAGES CONTROL]
+disable=missing-module-docstring,missing-class-docstring,missing-function-docstring

.vscode/settings.json

@@ -0,0 +1,6 @@
+{
+    "python.linting.mypyEnabled": true,
+    "python.linting.pylintEnabled": true,
+    "python.linting.flake8Enabled": true,
+    "python.linting.enabled": true
+}

.vscode/tasks.json

@@ -0,0 +1,61 @@
+{
+    "version": "2.0.0",
+    "tasks": [
+        {
+            "label": "create venv",
+            "type": "shell",
+            "command": "python3",
+            "args": [
+                "-m",
+                "venv",
+                "${workspaceFolder}/venv"
+            ],
+            "group": {
+                "kind": "build"
+            },
+            "problemMatcher": [],
+            "presentation": {
+                "focus": true
+            }
+        },
+        {
+            "label": "destroy venv",
+            "type": "shell",
+            "command": "rm",
+            "args": [
+                "-rf",
+                "${workspaceFolder}/venv"
+            ],
+            "group": {
+                "kind": "build"
+            },
+            "problemMatcher": [],
+            "presentation": {
+                "focus": true
+            }
+        },
+        {
+            "label": "install pydiffchecker",
+            "type": "shell",
+            "dependsOn": [
+                "create venv"
+            ],
+            "command": "${workspaceFolder}/venv/bin/python3",
+            "args": [
+                "-m",
+                "pip",
+                "install",
+                "-e",
+                "${workspaceFolder}"
+            ],
+            "group": {
+                "kind": "build",
+                "isDefault": true
+            },
+            "problemMatcher": [],
+            "presentation": {
+                "focus": true
+            }
+        }
+    ]
+}

pydiffchecker/cli.py

@@ -0,0 +1,22 @@
+import argparse
+import json
+from .version import get_version
+from .line_shift_checker import LineShiftChecker
+
+
+def main():
+    parser = argparse.ArgumentParser(description='Diff checker')
+
+    parser.add_argument('-v',
+                        '--version',
+                        action='version',
+                        version=f'v{get_version()}')
+    parser.add_argument('revision_since')
+    parser.add_argument('revision_until')
+
+    args = parser.parse_args()
+
+    line_shift_checker = LineShiftChecker(args.revision_since, args.revision_until)
+    out = line_shift_checker.get_shifted_lines()
+
+    print(json.dumps(out, indent=4))

pydiffchecker/git_version.py

@@ -0,0 +1,28 @@
+import subprocess
+
+GIT_DESCRIBE_COMMAND = ['git', 'describe', '--tags', '--long', '--dirty']
+VERSION_FORMAT = '{tag}.dev{commitcount}+{gitsha}{dirty}'
+
+
+def get_version() -> str:
+    version = subprocess.check_output(GIT_DESCRIBE_COMMAND).decode().strip()
+    return format_version(version=version)
+
+
+def format_version(version: str) -> str:
+    parts = version.split('-')
+    dirty = len(parts) == 4
+    tag, count, sha = parts[:3]
+    tag = tag.lstrip('v')
+    if count == '0' and not dirty:
+        return tag
+    return VERSION_FORMAT.format(
+        tag=tag,
+        commitcount=count,
+        gitsha=sha.lstrip('g'),
+        dirty='dirty' if dirty else ''
+    )
+
+
+if __name__ == '__main__':
+    print(get_version())

pydiffchecker/helper.py

@@ -0,0 +1,16 @@
+import subprocess
+from typing import Iterator
+
+
+def subprocess_readlines(cmd, cwd=None) -> Iterator[str]:
+    process = subprocess.Popen(cmd, cwd=cwd, stdout=subprocess.PIPE)
+
+    for line in process.stdout:
+        line = line.decode().rstrip(r'\n')
+
+        yield line
+
+    process.wait()
+
+    if process.returncode != 0:
+        raise subprocess.CalledProcessError(process.returncode, cmd)

pydiffchecker/line_shift_checker.py

@@ -0,0 +1,70 @@
+import re
+from typing import List, Dict
+from .helper import subprocess_readlines
+
+
+class LineShiftChecker:
+    DIFF_BLOCK_REGEX = r'@@ -(\d+),(\d+) \+(\d+),(\d+) @@'
+
+    def __init__(self, revision_since, revision_until) -> None:
+        self.revision_since = revision_since
+        self.revision_until = revision_until
+
+    def get_shifted_lines(self) -> Dict[str, Dict]:
+        shifted_lines = {}
+
+        for file_info in self.__get_changed_files():
+            shifted_lines[file_info['src']] = self.__get_shifted_lines_in_file(file_info)
+
+        return shifted_lines
+
+    def __get_changed_files(self) -> List[Dict]:
+        process_output = subprocess_readlines(['git', 'diff', '--name-status', '--diff-filter=MR',
+                                               self.revision_since, self.revision_until])
+
+        file_list = []
+        for line in process_output:
+            raw_file_info = line.split()
+            file_list.append({
+                'src': raw_file_info[1],
+                'dst': raw_file_info[2] if len(raw_file_info) > 2 else raw_file_info[1],
+            })
+
+        return file_list
+
+    def __get_shifted_lines_in_file(self, file_info) -> 'Dict[str, str | None]':
+        lines_in_source_file = self.__count_lines_in_source_file(file_info['dst'])
+        process_output = subprocess_readlines(['git', 'diff', f'-U{lines_in_source_file}',
+                                               self.revision_since, self.revision_until, '--',
+                                               file_info['src'], file_info['dst']])
+
+        diff_started = False
+        shifted_lines = {}
+        for line in process_output:
+            matches = re.search(LineShiftChecker.DIFF_BLOCK_REGEX, line)
+            if matches:
+                old_start = int(matches.group(1))
+                new_start = int(matches.group(3))
+                diff_started = True
+                continue
+
+            if not diff_started:
+                continue
+
+            if line.startswith(' '):
+                shifted_lines[f'{file_info["src"]}:{old_start}'] = f'{file_info["dst"]}:{new_start}'
+                old_start += 1
+                new_start += 1
+            elif line.startswith('+'):
+                new_start += 1
+            elif line.startswith('-'):
+                shifted_lines[f'{file_info["src"]}:{old_start}'] = None
+                old_start += 1
+
+        assert lines_in_source_file == len(shifted_lines)
+
+        return shifted_lines
+
+    def __count_lines_in_source_file(self, file) -> int:
+        process_output = subprocess_readlines(['git', 'show', f'{self.revision_since}:{file}'])
+        return sum(1 for _ in process_output)

pydiffchecker/version.py

@@ -0,0 +1,9 @@
+from importlib.metadata import version, PackageNotFoundError
+
+
+def get_version():
+    try:
+        return version('pydiffchecker')
+    except PackageNotFoundError:
+        # package is not installed
+        return '0.0.0'

setup.py

@@ -0,0 +1,23 @@
+import setuptools
+
+from pydiffchecker.git_version import get_version
+
+with open('README.md', 'r', encoding='utf-8') as fh:
+    long_description = fh.read()
+
+setuptools.setup(
+    name='pydiffchecker',
+    version=get_version(),
+    url='https://git.esoko.eu/bence/pydiffchecker.git',
+    author='Bence Pocze',
+    author_email='bence@pocze.ch',
+    description='Wrappers for git diff',
+    long_description=long_description,
+    long_description_content_type='text/markdown',
+    packages=setuptools.find_packages(),
+    entry_points={
+        'console_scripts': ['pydiffchecker=pydiffchecker.cli:main'],
+    },
+    python_requires='>=3.8',
+    install_requires=[]
+)

tox.ini

@@ -0,0 +1,2 @@
+[flake8]
+max-line-length = 120