#2663: support an *ignore* argument to shutil.copytree(). Patch by Tarek Ziade.
This is a new feature, but Barry authorized adding it in the beta period.
diff --git a/Lib/shutil.py b/Lib/shutil.py
index 6ce4023..3af280d 100644
--- a/Lib/shutil.py
+++ b/Lib/shutil.py
@@ -8,6 +8,7 @@
import sys
import stat
from os.path import abspath
+import fnmatch
__all__ = ["copyfileobj","copyfile","copymode","copystat","copy","copy2",
"copytree","move","rmtree","Error"]
@@ -93,8 +94,19 @@
copyfile(src, dst)
copystat(src, dst)
+def ignore_patterns(*patterns):
+ """Function that can be used as copytree() ignore parameter.
-def copytree(src, dst, symlinks=False):
+ Patterns is a sequence of glob-style patterns
+ that are used to exclude files"""
+ def _ignore_patterns(path, names):
+ ignored_names = []
+ for pattern in patterns:
+ ignored_names.extend(fnmatch.filter(names, pattern))
+ return set(ignored_names)
+ return _ignore_patterns
+
+def copytree(src, dst, symlinks=False, ignore=None):
"""Recursively copy a directory tree using copy2().
The destination directory must not already exist.
@@ -105,13 +117,32 @@
it is false, the contents of the files pointed to by symbolic
links are copied.
+ The optional ignore argument is a callable. If given, it
+ is called with the `src` parameter, which is the directory
+ being visited by copytree(), and `names` which is the list of
+ `src` contents, as returned by os.listdir():
+
+ callable(src, names) -> ignored_names
+
+ Since copytree() is called recursively, the callable will be
+ called once for each directory that is copied. It returns a
+ list of names relative to the `src` directory that should
+ not be copied.
+
XXX Consider this example code rather than the ultimate tool.
"""
names = os.listdir(src)
+ if ignore is not None:
+ ignored_names = ignore(src, names)
+ else:
+ ignored_names = set()
+
os.makedirs(dst)
errors = []
for name in names:
+ if name in ignored_names:
+ continue
srcname = os.path.join(src, name)
dstname = os.path.join(dst, name)
try:
@@ -119,7 +150,7 @@
linkto = os.readlink(srcname)
os.symlink(linkto, dstname)
elif os.path.isdir(srcname):
- copytree(srcname, dstname, symlinks)
+ copytree(srcname, dstname, symlinks, ignore)
else:
copy2(srcname, dstname)
# XXX What about devices, sockets etc.?
diff --git a/Lib/test/test_shutil.py b/Lib/test/test_shutil.py
index dfdec0d..fa5bbb1 100644
--- a/Lib/test/test_shutil.py
+++ b/Lib/test/test_shutil.py
@@ -108,6 +108,82 @@
if os.path.exists(path):
shutil.rmtree(path)
+ def test_copytree_with_exclude(self):
+
+ def write_data(path, data):
+ f = open(path, "w")
+ f.write(data)
+ f.close()
+
+ def read_data(path):
+ f = open(path)
+ data = f.read()
+ f.close()
+ return data
+
+ # creating data
+ join = os.path.join
+ exists = os.path.exists
+ src_dir = tempfile.mkdtemp()
+ dst_dir = join(tempfile.mkdtemp(), 'destination')
+ write_data(join(src_dir, 'test.txt'), '123')
+ write_data(join(src_dir, 'test.tmp'), '123')
+ os.mkdir(join(src_dir, 'test_dir'))
+ write_data(join(src_dir, 'test_dir', 'test.txt'), '456')
+ os.mkdir(join(src_dir, 'test_dir2'))
+ write_data(join(src_dir, 'test_dir2', 'test.txt'), '456')
+ os.mkdir(join(src_dir, 'test_dir2', 'subdir'))
+ os.mkdir(join(src_dir, 'test_dir2', 'subdir2'))
+ write_data(join(src_dir, 'test_dir2', 'subdir', 'test.txt'), '456')
+ write_data(join(src_dir, 'test_dir2', 'subdir2', 'test.py'), '456')
+
+
+ # testing glob-like patterns
+ try:
+ patterns = shutil.ignore_patterns('*.tmp', 'test_dir2')
+ shutil.copytree(src_dir, dst_dir, ignore=patterns)
+ # checking the result: some elements should not be copied
+ self.assert_(exists(join(dst_dir, 'test.txt')))
+ self.assert_(not exists(join(dst_dir, 'test.tmp')))
+ self.assert_(not exists(join(dst_dir, 'test_dir2')))
+ finally:
+ if os.path.exists(dst_dir):
+ shutil.rmtree(dst_dir)
+ try:
+ patterns = shutil.ignore_patterns('*.tmp', 'subdir*')
+ shutil.copytree(src_dir, dst_dir, ignore=patterns)
+ # checking the result: some elements should not be copied
+ self.assert_(not exists(join(dst_dir, 'test.tmp')))
+ self.assert_(not exists(join(dst_dir, 'test_dir2', 'subdir2')))
+ self.assert_(not exists(join(dst_dir, 'test_dir2', 'subdir')))
+ finally:
+ if os.path.exists(dst_dir):
+ shutil.rmtree(dst_dir)
+
+ # testing callable-style
+ try:
+ def _filter(src, names):
+ res = []
+ for name in names:
+ path = os.path.join(src, name)
+
+ if (os.path.isdir(path) and
+ path.split()[-1] == 'subdir'):
+ res.append(name)
+ elif os.path.splitext(path)[-1] in ('.py'):
+ res.append(name)
+ return res
+
+ shutil.copytree(src_dir, dst_dir, ignore=_filter)
+
+ # checking the result: some elements should not be copied
+ self.assert_(not exists(join(dst_dir, 'test_dir2', 'subdir2',
+ 'test.py')))
+ self.assert_(not exists(join(dst_dir, 'test_dir2', 'subdir')))
+
+ finally:
+ if os.path.exists(dst_dir):
+ shutil.rmtree(dst_dir)
if hasattr(os, "symlink"):
def test_dont_copy_file_onto_link_to_itself(self):