Added the ``exclude_package_data`` keyword to ``setup()``, allowing you

to trim back files included via the ``package_data`` and
``include_package_data`` options.

--HG--
branch : setuptools
extra : convert_revision : svn%3A6015fed2-1504-0410-9fe1-9d1591cc4771/sandbox/trunk/setuptools%4041693

setup.py

@@ -55,6 +55,8 @@ setup(
             "entry_points       = setuptools.dist:check_entry_points",
             "test_suite         = setuptools.dist:check_test_suite",
             "zip_safe           = setuptools.dist:assert_bool",
+            "package_data         = setuptools.dist:check_package_data",
+            "exclude_package_data = setuptools.dist:check_package_data",
             "include_package_data = setuptools.dist:assert_bool",
         ],
         "egg_info.writers": [
@@ -78,8 +80,6 @@ setup(
 
 
 
-
-
     classifiers = [f.strip() for f in """
     Development Status :: 3 - Alpha
     Intended Audience :: Developers

setuptools.egg-info/entry_points.txt

 [distutils.setup_keywords]
 entry_points = setuptools.dist:check_entry_points
 extras_require = setuptools.dist:check_extras
+package_data = setuptools.dist:check_package_data
 install_requires = setuptools.dist:check_requirements
 include_package_data = setuptools.dist:assert_bool
+exclude_package_data = setuptools.dist:check_package_data
 namespace_packages = setuptools.dist:check_nsp
 test_suite = setuptools.dist:check_test_suite
 eager_resources = setuptools.dist:assert_string_list

setuptools.txt

@@ -289,10 +289,20 @@ unless you need the associated ``setuptools`` feature.
     file.  For more information, see the section below on `Including Data
     Files`_.
 
+``exclude_package_data``
+    A dictionary mapping package names to lists of glob patterns that should
+    be *excluded* from your package directories.  You can use this to trim back
+    any excess files included by ``include_package_data``.  For a complete
+    description and examples, see the section below on `Including Data Files`_.
+
 ``package_data``
     A dictionary mapping package names to lists of glob patterns.  For a
     complete description and examples, see the section below on `Including
-    Data Files`_.
+    Data Files`_.  You do not need to use this option if you are using
+    ``include_package_data``, unless you need to add e.g. files that are
+    generated by your setup script and build process.  (And are therefore not
+    in source control or are files that you don't want to include in your
+    source distribution.)
 
 ``zip_safe``
     A boolean (True or False) flag specifying whether the project can be
@@ -627,7 +637,7 @@ are placed in a platform-specific location.  However, the most common use case
 for data files distributed with a package is for use *by* the package, usually
 by including the data files in the package directory.
 
-Setuptools offers two ways to specify data files to be included in your
+Setuptools offers three ways to specify data files to be included in your
 packages.  First, you can simply use the ``include_package_data`` keyword,
 e.g.::
 
@@ -643,7 +653,7 @@ specified via the distutils' ``MANIFEST.in`` file.
 
 If you want finer-grained control over what files are included (for example, if
 you have documentation files in your package directories and want to exclude
-them from installation), then you can use the ``package_data`` keyword instead,
+them from installation), then you can also use the ``package_data`` keyword,
 e.g.::
 
     from setuptools import setup, find_packages
@@ -704,6 +714,55 @@ python.org website.)
 
 __ http://docs.python.org/dist/node11.html
 
+Sometimes, the ``include_package_data`` or ``package_data`` options alone
+aren't sufficient to precisely define what files you want included.  For
+example, you may want to include package README files in your revision control
+system and source distributions, but exclude them from being installed.  So,
+setuptools offers an ``exclude_package_data`` option as well, that allows you
+to do things like this::
+
+    from setuptools import setup, find_packages
+    setup(
+        ...
+        packages = find_packages('src'),  # include all packages under src
+        package_dir = {'':'src'},   # tell distutils packages are under src
+
+        include_package_data = True,    # include everything in source control
+
+        # ...but exclude README.txt from all packages
+        exclude_package_data = { '': ['README.txt'] },
+    )
+
+The ``exclude_package_data`` option is a dictionary mapping package names to
+lists of wildcard patterns, just like the ``package_data`` option.  And, just
+as with that option, a key of ``''`` will apply the given pattern(s) to all
+packages.  However, any files that match these patterns will be *excluded*
+from installation, even if they were listed in ``package_data`` or were
+included as a result of using ``include_package_data``.
+
+In summary, the three options allow you to:
+
+``include_package_data``
+    Accept all data files and directories matched by ``MANIFEST.in`` or found
+    in source control.
+
+``package_data``
+    Specify additional patterns to match files and directories that may or may
+    not be matched by ``MANIFEST.in`` or found in source control.
+
+``exclude_package_data``
+    Specify patterns for data files and directories that should *not* be
+    included when a package is installed, even if they would otherwise have
+    been included due to the use of the preceding options.
+
+NOTE: Due to the way the distutils build process works, a data file that you
+include in your project and then stop including may be "orphaned" in your
+project's build directories, requiring you to run ``setup.py clean --all`` to
+fully remove them.  This may also be important for your users and contributors
+if they track intermediate revisions of your project using Subversion; be sure
+to let them know when you make changes that remove files from inclusion so they
+can run ``setup.py clean --all``.
+
 
 Accessing Data Files at Runtime
 -------------------------------
@@ -2223,7 +2282,11 @@ Release Notes/Change History
 
  * Added the ``include_package_data`` keyword to ``setup()``, allowing you to
    automatically include any package data listed in revision control or
-   ``MANIFEST.in``.
+   ``MANIFEST.in``
+
+ * Added the ``exclude_package_data`` keyword to ``setup()``, allowing you to
+   trim back files included via the ``package_data`` and
+   ``include_package_data`` options.
 
  * Fixed ``--tag-svn-revision`` not working when run from a source
    distribution.

setuptools/command/build_py.py

-import os.path, sys
+import os.path, sys, fnmatch
 from distutils.command.build_py import build_py as _build_py
 from distutils.util import convert_path
 from glob import glob
@@ -12,10 +12,10 @@ class build_py(_build_py):
     Also, this version of the 'build_py' command allows you to specify both
     'py_modules' and 'packages' in the same setup operation.
     """
-
     def finalize_options(self):
         _build_py.finalize_options(self)
         self.package_data = self.distribution.package_data
+        self.exclude_package_data = self.distribution.exclude_package_data or {}
         if 'data_files' in self.__dict__: del self.__dict__['data_files']
 
     def run(self):
@@ -68,7 +68,7 @@ class build_py(_build_py):
         for pattern in globs:
             # Each pattern has to be converted to a platform-specific path
             files.extend(glob(os.path.join(src_dir, convert_path(pattern))))
-        return files
+        return self.exclude_data_files(package, src_dir, files)
 
     def build_package_data(self):
         """Copy data files into build directory"""
@@ -155,6 +155,47 @@ class build_py(_build_py):
     def initialize_options(self):
         self.packages_checked={}
         _build_py.initialize_options(self)
+
+
+
+
+
+
+
+    def exclude_data_files(self, package, src_dir, files):
+        """Filter filenames for package's data files in 'src_dir'"""
+        globs = (self.exclude_package_data.get('', [])
+                 + self.exclude_package_data.get(package, []))
+        bad = []
+        for pattern in globs:           
+            bad.extend(
+                fnmatch.filter(
+                    files, os.path.join(src_dir, convert_path(pattern))
+                )
+            )
+        bad = dict.fromkeys(bad)
+        return [f for f in files if f not in bad]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
 
 
 

setuptools/dist.py

@@ -103,20 +103,20 @@ def check_test_suite(dist, attr, value):
         raise DistutilsSetupError("test_suite must be a string")
 
 
-
-    
-
-
-
-
-
-
-
-
-
-
-
-
+def check_package_data(dist, attr, value):
+    """Verify that value is a dictionary of package names to glob lists"""
+    if isinstance(value,dict):
+        for k,v in value.items():
+            if not isinstance(k,str): break
+            try: iter(v)
+            except TypeError:
+                break
+        else:
+            return
+    raise DistutilsSetupError(
+        attr+" must be a dictionary mapping package names to lists of "
+        "wildcard patterns"
+    )