[Python-checkins] r55711 - in sandbox/trunk/setuptools: EasyInstall.txt pkg_resources.py setuptools.txt setuptools/__init__.py setuptools/package_index.py

[phillip.eby]

Author: phillip.eby
Date: Thu May 31 19:20:56 2007
New Revision: 55711

Modified:
   sandbox/trunk/setuptools/EasyInstall.txt
   sandbox/trunk/setuptools/pkg_resources.py
   sandbox/trunk/setuptools/setuptools.txt
   sandbox/trunk/setuptools/setuptools/__init__.py
   sandbox/trunk/setuptools/setuptools/package_index.py
Log:
Misc. fixes:

* Don't treat directories with a '.' in the name as packages
* Don't include ez_setup in find_packages()
* HTML-decode URLs scraped from web pages (d'oh!)
* Fix cache dir defaults on Windows when multiple env vars used
* Doc updates


Modified: sandbox/trunk/setuptools/EasyInstall.txt
==============================================================================
--- sandbox/trunk/setuptools/EasyInstall.txt	(original)
+++ sandbox/trunk/setuptools/EasyInstall.txt	Thu May 31 19:20:56 2007
@@ -442,6 +442,19 @@
 below, and also the section on `Package Index "API"`_.
 
 
+Password-Protected Sites
+------------------------
+
+If a site you want to download from is password-protected using HTTP "Basic"
+authentication, you can specify your credentials in the URL, like so::
+
+    http://some_userid:some_password@some.example.com/some_path/
+
+You can do this with both index page URLs and direct download URLs.  As long
+as any HTML pages read by easy_install use *relative* links to point to the
+downloads, the same user ID and password will be used to do the downloading.
+
+
 Controlling Build Options
 ~~~~~~~~~~~~~~~~~~~~~~~~~
 

Modified: sandbox/trunk/setuptools/pkg_resources.py
==============================================================================
--- sandbox/trunk/setuptools/pkg_resources.py	(original)
+++ sandbox/trunk/setuptools/pkg_resources.py	Thu May 31 19:20:56 2007
@@ -1052,7 +1052,7 @@
         dirname = ''
         for key in keys:
             if key in os.environ:
-                dirname = os.path.join(os.environ[key])
+                dirname = os.path.join(dirname, os.environ[key])
             else:
                 break
         else:

Modified: sandbox/trunk/setuptools/setuptools.txt
==============================================================================
--- sandbox/trunk/setuptools/setuptools.txt	(original)
+++ sandbox/trunk/setuptools/setuptools.txt	Thu May 31 19:20:56 2007
@@ -1463,8 +1463,10 @@
 you use any option at all.
 
 (By the way, if you're using some other revision control system, you might
-consider submitting a patch to the ``setuptools.command.sdist`` module,
-so we can include support for your system.)
+consider creating and publishing a `revision control plugin for setuptools`_.)
+
+
+.. _revision control plugin for setuptools: `Adding Support for Other Revision Control Systems`_
 
 
 Making your package available for EasyInstall

Modified: sandbox/trunk/setuptools/setuptools/__init__.py
==============================================================================
--- sandbox/trunk/setuptools/setuptools/__init__.py	(original)
+++ sandbox/trunk/setuptools/setuptools/__init__.py	Thu May 31 19:20:56 2007
@@ -30,11 +30,11 @@
         where,prefix = stack.pop(0)
         for name in os.listdir(where):
             fn = os.path.join(where,name)
-            if (os.path.isdir(fn) and
+            if ('.' not in name and os.path.isdir(fn) and
                 os.path.isfile(os.path.join(fn,'__init__.py'))
             ):
                 out.append(prefix+name); stack.append((fn,prefix+name+'.'))
-    for pat in exclude:
+    for pat in list(exclude)+['ez_setup']:
         from fnmatch import fnmatchcase
         out = [item for item in out if not fnmatchcase(item,pat)]
     return out

Modified: sandbox/trunk/setuptools/setuptools/package_index.py
==============================================================================
--- sandbox/trunk/setuptools/setuptools/package_index.py	(original)
+++ sandbox/trunk/setuptools/setuptools/package_index.py	Thu May 31 19:20:56 2007
@@ -132,14 +132,14 @@
         rels = map(str.strip, rel.lower().split(','))
         if 'homepage' in rels or 'download' in rels:
             for match in HREF.finditer(tag):
-                yield urlparse.urljoin(url, match.group(1))
+                yield urlparse.urljoin(url, htmldecode(match.group(1)))
 
     for tag in ("<th>Home Page", "<th>Download URL"):
         pos = page.find(tag)
         if pos!=-1:
             match = HREF.search(page,pos)
             if match:
-                yield urlparse.urljoin(url, match.group(1))
+                yield urlparse.urljoin(url, htmldecode(match.group(1)))
 
 user_agent = "Python-urllib/%s setuptools/%s" % (
     urllib2.__version__, require('setuptools')[0].version
@@ -200,7 +200,7 @@
         if url.startswith(self.index_url) and getattr(f,'code',None)!=404:
             page = self.process_index(url, page)
         for match in HREF.finditer(page):
-            link = urlparse.urljoin(base, match.group(1))
+            link = urlparse.urljoin(base, htmldecode(match.group(1)))
             self.process_url(link)
 
     def process_filename(self, fn, nested=False):
@@ -262,7 +262,7 @@
 
         # process an index page into the package-page index
         for match in HREF.finditer(page):
-            scan( urlparse.urljoin(url, match.group(1)) )
+            scan( urlparse.urljoin(url, htmldecode(match.group(1))) )
 
         pkg, ver = scan(url)   # ensure this page is in the page index
         if pkg:
@@ -611,6 +611,8 @@
             self.url_ok(url, True)   # raises error if not allowed
             return self._attempt_download(url, filename)
 
+
+
     def scan_url(self, url):
         self.process_url(url, True)
 
@@ -652,6 +654,44 @@
     def warn(self, msg, *args):
         log.warn(msg, *args)
 
+# This pattern matches a character entity reference (a decimal numeric
+# references, a hexadecimal numeric reference, or a named reference).
+entity_sub = re.compile(r'&(#(\d+|x[\da-fA-F]+)|[\w.:-]+);?').sub
+
+def uchr(c):
+    if not isinstance(c, int):
+        return c
+    if c>255: return unichr(c)
+    return chr(c)
+
+def decode_entity(match):
+    what = match.group(1)
+    if what.startswith('#x'):
+        what = int(what[2:], 16)
+    elif what.startswith('#'):
+        what = int(what[1:])
+    else:
+        from htmlentitydefs import name2codepoint
+        what = name2codepoint.get(what, match.group(0))
+    return uchr(what)
+
+def htmldecode(text):
+    """Decode HTML entities in the given text."""
+    return entity_sub(decode_entity, text)
+
+
+
+
+
+
+
+
+
+
+
+
+
+