Convert .gitignore to .dockerignore: quick and dirty.

1.generate_dockerignore.py

"""
Convert .gitignore to .dockerignore: quick and dirty.

This is a quick and dirty script to convert this:
`__pycache__/`

Into this:
```
__pycache__
*/__pycache__
*/*/__pycache__
*/*/*/__pycache__
```

Specifically [gitignores](https://git-scm.com/docs/gitignore) use a mixture of
fname, and shell glob matching with lots of rules and the dockeringore
files use simple
[golang matching](https://golang.org/pkg/path/filepath/#Match).

Forked from https://gist.github.com/wassname/b25471b0f3bb2f9ff81f
"""


def add_subdirs(pattern, max_depth=4):
    """
    Replace start of glob with multiple levels
    of path seperators.

    *.pyc becomes *.pyc */*.pyc */*/*.pyc etc
    """
    for i in range(max_depth):
        yield pattern
        pattern = '*/%s' % pattern

    # and for a seperator line
    yield ""


def generate_dockerignore(
        gitignore, max_depth=5, prefix_lines=[], comment=True):
    """Pass in array of gitignore lines"""
    di = []  # docker ignore lines

    # add comment and extra lines
    if comment:
        prefix_lines = [
            '# converted by generate_dockerignore.py\n'] + prefix_lines

    for line in prefix_lines+gitignore:
        # these slashes are ignored by dockerignore
        line = line.rstrip('/')

        # ingore whitespace and comments
        if line.strip() == '':
            di.append(line)
            continue
        elif line.startswith('#'):
            di.append(line)
            continue

        # deal with **
        elif '**' in line:
            # replace wildcard glob **
            # with multiple levels of seperators
            # replace ** with *, */*, */*/*, etc
            line_tmpl = line.replace('**', '{}')
            replacement = '*'
            for i in range(max_depth):
                pattern = line_tmpl.format(replacement)
                replacement = '*/' + replacement
                gitignore = open('.gitignore').readlines()
                # now put * */, */*, */*/* on the beginning to match subdirs
                if line_tmpl.startswith('/'):
                    di += list(add_subdirs(pattern))
                else:
                    di.append(pattern)

        # deal with lines that don't start with a slash
        elif not line.startswith('/'):
            # shell glob
            di += list(add_subdirs(line))

    return di


if __name__ == "__main__":
    git_ignore = open('.gitignore', 'r').readlines()
    docker_ignore = generate_dockerignore(git_ignore)
    with open('.dockerignore', 'w') as output:
        for l in docker_ignore:
            output.write(l)

generated_dockerignore

# converted by generate_dockerignore.py
*.log
*/*.log
*/*/*.log
*/*/*/*.log
*.conf
*/*.conf
*/*/*.conf
*/*/*/*.conf

# Django specific
migrations/
*/migrations/
*/*/migrations/
*/*/*/migrations/
*.db
*/*.db
*/*/*.db
*/*/*/*.db

# From the excellent;
# https://raw.githubusercontent.com/github/gitignore/master/Python.gitignore

# Byte-compiled / optimized / DLL files
__pycache__/
*/__pycache__/
*/*/__pycache__/
*/*/*/__pycache__/
*.py[cod]
*/*.py[cod]
*/*/*.py[cod]
*/*/*/*.py[cod]
*$py.class
*/*$py.class
*/*/*$py.class
*/*/*/*$py.class

# C extensions
*.so
*/*.so
*/*/*.so
*/*/*/*.so

# Distribution / packaging
.Python
*/.Python
*/*/.Python
*/*/*/.Python
build/
*/build/
*/*/build/
*/*/*/build/
develop-eggs/
*/develop-eggs/
*/*/develop-eggs/
*/*/*/develop-eggs/
dist/
*/dist/
*/*/dist/
*/*/*/dist/
downloads/
*/downloads/
*/*/downloads/
*/*/*/downloads/
eggs/
*/eggs/
*/*/eggs/
*/*/*/eggs/
.eggs/
*/.eggs/
*/*/.eggs/
*/*/*/.eggs/
lib/
*/lib/
*/*/lib/
*/*/*/lib/
lib64/
*/lib64/
*/*/lib64/
*/*/*/lib64/
parts/
*/parts/
*/*/parts/
*/*/*/parts/
sdist/
*/sdist/
*/*/sdist/
*/*/*/sdist/
var/
*/var/
*/*/var/
*/*/*/var/
wheels/
*/wheels/
*/*/wheels/
*/*/*/wheels/
*.egg-info/
*/*.egg-info/
*/*/*.egg-info/
*/*/*/*.egg-info/
.installed.cfg
*/.installed.cfg
*/*/.installed.cfg
*/*/*/.installed.cfg
*.egg
*/*.egg
*/*/*.egg
*/*/*/*.egg
MANIFEST
*/MANIFEST
*/*/MANIFEST
*/*/*/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
*/*.manifest
*/*/*.manifest
*/*/*/*.manifest
*.spec
*/*.spec
*/*/*.spec
*/*/*/*.spec

# Installer logs
pip-log.txt
*/pip-log.txt
*/*/pip-log.txt
*/*/*/pip-log.txt
pip-delete-this-directory.txt
*/pip-delete-this-directory.txt
*/*/pip-delete-this-directory.txt
*/*/*/pip-delete-this-directory.txt

# Unit test / coverage reports
htmlcov/
*/htmlcov/
*/*/htmlcov/
*/*/*/htmlcov/
.tox/
*/.tox/
*/*/.tox/
*/*/*/.tox/
.coverage
*/.coverage
*/*/.coverage
*/*/*/.coverage
.coverage.*
*/.coverage.*
*/*/.coverage.*
*/*/*/.coverage.*
.cache
*/.cache
*/*/.cache
*/*/*/.cache
nosetests.xml
*/nosetests.xml
*/*/nosetests.xml
*/*/*/nosetests.xml
coverage.xml
*/coverage.xml
*/*/coverage.xml
*/*/*/coverage.xml
*.cover
*/*.cover
*/*/*.cover
*/*/*/*.cover
.hypothesis/
*/.hypothesis/
*/*/.hypothesis/
*/*/*/.hypothesis/
.pytest_cache/
*/.pytest_cache/
*/*/.pytest_cache/
*/*/*/.pytest_cache/

# Translations
*.mo
*/*.mo
*/*/*.mo
*/*/*/*.mo
*.pot
*/*.pot
*/*/*.pot
*/*/*/*.pot

# Django stuff:
*.log
*/*.log
*/*/*.log
*/*/*/*.log
local_settings.py
*/local_settings.py
*/*/local_settings.py
*/*/*/local_settings.py
db.sqlite3
*/db.sqlite3
*/*/db.sqlite3
*/*/*/db.sqlite3

# Flask stuff:
instance/
*/instance/
*/*/instance/
*/*/*/instance/
.webassets-cache
*/.webassets-cache
*/*/.webassets-cache
*/*/*/.webassets-cache

# Scrapy stuff:
.scrapy
*/.scrapy
*/*/.scrapy
*/*/*/.scrapy

# Sphinx documentation
docs/_build/
*/docs/_build/
*/*/docs/_build/
*/*/*/docs/_build/

# PyBuilder
target/
*/target/
*/*/target/
*/*/*/target/

# Jupyter Notebook
.ipynb_checkpoints
*/.ipynb_checkpoints
*/*/.ipynb_checkpoints
*/*/*/.ipynb_checkpoints

# pyenv
.python-version
*/.python-version
*/*/.python-version
*/*/*/.python-version

# celery beat schedule file
celerybeat-schedule
*/celerybeat-schedule
*/*/celerybeat-schedule
*/*/*/celerybeat-schedule

# SageMath parsed files
*.sage.py
*/*.sage.py
*/*/*.sage.py
*/*/*/*.sage.py

# Environments
.env
*/.env
*/*/.env
*/*/*/.env
.venv
*/.venv
*/*/.venv
*/*/*/.venv
env/
*/env/
*/*/env/
*/*/*/env/
venv/
*/venv/
*/*/venv/
*/*/*/venv/
ENV/
*/ENV/
*/*/ENV/
*/*/*/ENV/
env.bak/
*/env.bak/
*/*/env.bak/
*/*/*/env.bak/
venv.bak/
*/venv.bak/
*/*/venv.bak/
*/*/*/venv.bak/

# Spyder project settings
.spyderproject
*/.spyderproject
*/*/.spyderproject
*/*/*/.spyderproject
.spyproject
*/.spyproject
*/*/.spyproject
*/*/*/.spyproject

# Rope project settings
.ropeproject
*/.ropeproject
*/*/.ropeproject
*/*/*/.ropeproject

# mkdocs documentation

# mypy
.mypy_cache/
*/.mypy_cache/
*/*/.mypy_cache/
*/*/*/.mypy_cache/

gitignore

*.log
*.conf

# Django specific
migrations/
*.db

# From the excellent;
# https://raw.githubusercontent.com/github/gitignore/master/Python.gitignore

# 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/
*.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/
.coverage
.coverage.*
.cache
nosetests.xml
coverage.xml
*.cover
.hypothesis/
.pytest_cache/

# Translations
*.mo
*.pot

# Django stuff:
*.log
local_settings.py
db.sqlite3

# Flask stuff:
instance/
.webassets-cache

# Scrapy stuff:
.scrapy

# Sphinx documentation
docs/_build/

# PyBuilder
target/

# Jupyter Notebook
.ipynb_checkpoints

# pyenv
.python-version

# celery beat schedule file
celerybeat-schedule

# 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/