Issue #7457: added a read_pkg_file method to distutils.dist.DistributionMetadata so we can read back PKG-INFO files

5 files changed, 151 insertions, 19 deletions

diff --git a/Doc/distutils/examples.rst b/Doc/distutils/examples.rst
index 648063b..35de57e 100644
--- a/Doc/distutils/examples.rst
+++ b/Doc/distutils/examples.rst
@@ -285,6 +285,48 @@ by using the `docutils` parser::
     warning: check: Title underline too short. (line 2)
     warning: check: Could not finish the parsing.
 
+Reading the metadata
+=====================
+
+The :func:`distutils.core.setup` function provides a command-line interface
+that allows you to query the metadata fields of a project through the
+`setup.py` script of a given project::
+
+    $ python setup.py --name
+    distribute
+
+This call reads the `name` metadata by running the
+:func:`distutils.core.setup`  function. Although, when a source or binary
+distribution is created with Distutils, the metadata fields are written
+in a static file called :file:`PKG-INFO`. When a Distutils-based project is
+installed in Python, the :file:`PKG-INFO` file is copied alongside the modules
+and packages of the distribution under :file:`NAME-VERSION-pyX.X.egg-info`,
+where `NAME` is the name of the project, `VERSION` its version as defined
+in the Metadata, and `pyX.X` the major and minor version of Python like
+`2.7` or `3.2`.
+
+You can read back this static file, by using the
+:class:`distutils.dist.DistributionMetadata` class and its
+:func:`read_pkg_file` method::
+
+    >>> from distutils.dist import DistributionMetadata
+    >>> metadata = DistributionMetadata()
+    >>> metadata.read_pkg_file(open('distribute-0.6.8-py2.7.egg-info'))
+    >>> metadata.name
+    'distribute'
+    >>> metadata.version
+    '0.6.8'
+    >>> metadata.description
+    'Easily download, build, install, upgrade, and uninstall Python packages'
+
+Notice that the class can also be instanciated with a metadata file path to
+loads its values::
+
+    >>> pkg_info_path = 'distribute-0.6.8-py2.7.egg-info'
+    >>> DistributionMetadata(pkg_info_path).name
+    'distribute'
+
+
 .. % \section{Multiple extension modules}
 .. % \label{multiple-ext}
 
diff --git a/Doc/whatsnew/2.7.rst b/Doc/whatsnew/2.7.rst
index a7f656e..768ea33 100644
--- a/Doc/whatsnew/2.7.rst
+++ b/Doc/whatsnew/2.7.rst
@@ -539,6 +539,10 @@ changes, or look through the Subversion logs for all the details.
   process, but instead simply not install the failing extension.
   (Contributed by Georg Brandl; :issue:`5583`.)
 
+  Issue #7457: added a read_pkg_file method to.distutils.dist.DistributionMetadata
+  see file:///MacDev/svn.python.org/python-trunk/Doc/build/html/distutils/examples.html#reading-the-metadata
+  (:issue:`7457`, added by Tarek).
+
 * The :class:`Fraction` class now accepts two rational numbers
   as arguments to its constructor.
   (Implemented by Mark Dickinson; :issue:`5812`.)
diff --git a/Lib/distutils/dist.py b/Lib/distutils/dist.py
index 8dc64d4..a1fc7b3 100644
--- a/Lib/distutils/dist.py
+++ b/Lib/distutils/dist.py
@@ -7,6 +7,7 @@ being built/installed/distributed.
 __revision__ = "$Id$"
 
 import sys, os, re
+import rfc822
 
 try:
     import warnings
@@ -1006,6 +1007,20 @@ Common commands: (see '--help-commands' for more)
     # to self.metadata.get_XXX.  The actual code is in the
     # DistributionMetadata class, below.
 
+class _MetadataMessage(rfc822.Message):
+
+    def read_field(self, name):
+        value = self[name]
+        if value == 'UNKNOWN':
+            return None
+        return value
+
+    def getheaders(self, name, default):
+        values = rfc822.Message.getheaders(self, name)
+        if values == []:
+            return None
+        return values
+
 class DistributionMetadata:
     """Dummy class to hold the distribution meta-data: name, version,
     author, and so forth.
@@ -1021,25 +1036,67 @@ class DistributionMetadata:
                          "provides", "requires", "obsoletes",
                          )
 
-    def __init__ (self):
-        self.name = None
-        self.version = None
-        self.author = None
-        self.author_email = None
+    def __init__(self, path=None):
+        if path is not None:
+            self.read_pkg_file(open(path))
+        else:
+            self.name = None
+            self.version = None
+            self.author = None
+            self.author_email = None
+            self.maintainer = None
+            self.maintainer_email = None
+            self.url = None
+            self.license = None
+            self.description = None
+            self.long_description = None
+            self.keywords = None
+            self.platforms = None
+            self.classifiers = None
+            self.download_url = None
+            # PEP 314
+            self.provides = None
+            self.requires = None
+            self.obsoletes = None
+
+    def read_pkg_file(self, file):
+        """Reads the metadata values from a file object."""
+        msg = _MetadataMessage(file)
+        metadata_version = msg['metadata-version']
+        self.name = msg.read_field('name')
+        self.version = msg.read_field('version')
+        self.description = msg.read_field('summary')
+        # we are filling author only.
+        self.author = msg.read_field('author')
         self.maintainer = None
+        self.author_email = msg.read_field('author-email')
         self.maintainer_email = None
-        self.url = None
-        self.license = None
-        self.description = None
-        self.long_description = None
-        self.keywords = None
-        self.platforms = None
-        self.classifiers = None
-        self.download_url = None
-        # PEP 314
-        self.provides = None
-        self.requires = None
-        self.obsoletes = None
+        self.url = msg.read_field('home-page')
+        self.license = msg.read_field('license')
+
+        if 'download-url' in msg:
+            self.download_url = msg.read_field('download-url')
+        else:
+            self.download_url = None
+
+        self.long_description = msg.read_field('description')
+        self.description = msg.read_field('summary')
+
+        if 'keywords' in msg:
+            self.keywords = msg.read_field('keywords').split(',')
+
+        self.platforms = msg.getheaders('platform', None)
+        self.classifiers = msg.getheaders('classifier', None)
+
+        # PEP 314 - these fields only exist in 1.1
+        if metadata_version == '1.1':
+            self.requires = msg.getheaders('requires', None)
+            self.provides = msg.getheaders('provides', None)
+            self.obsoletes = msg.getheaders('obsoletes', None)
+        else:
+            self.requires = None
+            self.provides = None
+            self.obsoletes = None
 
     def write_pkg_info(self, base_dir):
         """Write the PKG-INFO file into the release tree.
diff --git a/Lib/distutils/tests/test_dist.py b/Lib/distutils/tests/test_dist.py
index 8b141ca..1eddf6d 100644
--- a/Lib/distutils/tests/test_dist.py
+++ b/Lib/distutils/tests/test_dist.py
@@ -8,10 +8,9 @@ import unittest
 import warnings
 import textwrap
 
-from distutils.dist import Distribution, fix_help_options
+from distutils.dist import Distribution, fix_help_options, DistributionMetadata
 from distutils.cmd import Command
 import distutils.dist
-
 from test.test_support import TESTFN, captured_stdout
 from distutils.tests import support
 
@@ -239,6 +238,7 @@ class DistributionTestCase(support.TempdirManager,
         # make sure --no-user-cfg disables the user cfg file
         self.assertEquals(len(all_files)-1, len(files))
 
+
 class MetadataTestCase(support.TempdirManager, support.EnvironGuard,
                        unittest.TestCase):
 
@@ -397,6 +397,33 @@ class MetadataTestCase(support.TempdirManager, support.EnvironGuard,
         meta = meta.replace('\n' + 8 * ' ', '\n')
         self.assertTrue(long_desc in meta)
 
+    def test_read_metadata(self):
+        attrs = {"name": "package",
+                 "version": "1.0",
+                 "long_description": "desc",
+                 "description": "xxx",
+                 "download_url": "http://example.com",
+                 "keywords": ['one', 'two'],
+                 "requires": ['foo']}
+
+        dist = Distribution(attrs)
+        metadata = dist.metadata
+
+        # write it then reloads it
+        PKG_INFO = StringIO.StringIO()
+        metadata.write_pkg_file(PKG_INFO)
+        PKG_INFO.seek(0)
+        metadata.read_pkg_file(PKG_INFO)
+
+        self.assertEquals(metadata.name, "package")
+        self.assertEquals(metadata.version, "1.0")
+        self.assertEquals(metadata.description, "xxx")
+        self.assertEquals(metadata.download_url, 'http://example.com')
+        self.assertEquals(metadata.keywords, ['one', 'two'])
+        self.assertEquals(metadata.platforms, ['UNKNOWN'])
+        self.assertEquals(metadata.obsoletes, None)
+        self.assertEquals(metadata.requires, ['foo'])
+
 def test_suite():
     suite = unittest.TestSuite()
     suite.addTest(unittest.makeSuite(DistributionTestCase))
diff --git a/Misc/NEWS b/Misc/NEWS
index f7a2f9b..6cc264b 100644
--- a/Misc/NEWS
+++ b/Misc/NEWS
@@ -15,6 +15,8 @@ Core and Builtins
 Library
 -------
 
+- Issue #7457: added a read_pkg_file method to 
+  distutils.dist.DistributionMetadata.
 
 What's New in Python 2.7 alpha 1
 ================================