urlopen: add basejoin() function.

addpack: new module to add packages to sys.path.

3 files changed, 156 insertions, 0 deletions

diff --git a/Lib/addpack.py b/Lib/addpack.py
new file mode 100644
index 0000000..3d09236
--- /dev/null
+++ b/Lib/addpack.py
@@ -0,0 +1,67 @@
+# This module provides standard support for "packages".
+#
+# The idea is that large groups of related modules can be placed in
+# their own subdirectory, which can be added to the Python search path
+# in a relatively easy way.
+#
+# The current version takes a package name and searches the Python
+# search path for a directory by that name, and if found adds it to
+# the module search path (sys.path).  It maintains a list of packages
+# that have already been added so adding the same package many times
+# is OK.
+#
+# It is intended to be used in a fairly stylized manner: each module
+# that wants to use a particular package, say 'Foo', is supposed to
+# contain the following code:
+#
+#   from addpack import addpack
+#   addpack('Foo')
+#   <import modules from package Foo>
+#
+# Additional arguments, when present, provide additional places where
+# to look for the package before trying sys.path (these may be either
+# strings or lists/tuples of strings).  Also, if the package name is a
+# full pathname, first the last component is tried in the usual way,
+# then the full pathname is tried last.  If the package name is a
+# *relative* pathname (UNIX: contains a slash but doesn't start with
+# one), then nothing special is done.  The packages "/foo/bar/bletch"
+# and "bletch" are considered the same, but unrelated to "bar/bletch".
+#
+# If the algorithm finds more than one suitable subdirectory, all are
+# added to the search path -- this makes it possible to override part
+# of a package.  The same path will not be added more than once.
+#
+# If no directory is found, ImportError is raised.
+
+_packs = {}				# {pack: [pathname, ...], ...}
+
+def addpack(pack, *locations):
+	import os
+	if os.path.isabs(pack):
+		base = os.path.basename(pack)
+	else:
+		base = pack
+	if _packs.has_key(base):
+		return
+	import sys
+	path = []
+	for loc in _flatten(locations) + sys.path:
+		fn = os.path.join(loc, base)
+		if fn not in path and os.path.isdir(fn):
+			path.append(fn)
+	if pack != base and pack not in path and os.path.isdir(pack):
+		path.append(pack)
+	if not path: raise ImportError, 'package ' + pack + ' not found'
+	_packs[base] = path
+	for fn in path:
+		if fn not in sys.path:
+			sys.path.append(fn)
+
+def _flatten(locations):
+	locs = []
+	for loc in locations:
+		if type(loc) == type(''):
+			locs.append(loc)
+		else:
+			locs = locs + _flatten(loc)
+	return locs
diff --git a/Lib/lib-old/addpack.py b/Lib/lib-old/addpack.py
new file mode 100644
index 0000000..3d09236
--- /dev/null
+++ b/Lib/lib-old/addpack.py
@@ -0,0 +1,67 @@
+# This module provides standard support for "packages".
+#
+# The idea is that large groups of related modules can be placed in
+# their own subdirectory, which can be added to the Python search path
+# in a relatively easy way.
+#
+# The current version takes a package name and searches the Python
+# search path for a directory by that name, and if found adds it to
+# the module search path (sys.path).  It maintains a list of packages
+# that have already been added so adding the same package many times
+# is OK.
+#
+# It is intended to be used in a fairly stylized manner: each module
+# that wants to use a particular package, say 'Foo', is supposed to
+# contain the following code:
+#
+#   from addpack import addpack
+#   addpack('Foo')
+#   <import modules from package Foo>
+#
+# Additional arguments, when present, provide additional places where
+# to look for the package before trying sys.path (these may be either
+# strings or lists/tuples of strings).  Also, if the package name is a
+# full pathname, first the last component is tried in the usual way,
+# then the full pathname is tried last.  If the package name is a
+# *relative* pathname (UNIX: contains a slash but doesn't start with
+# one), then nothing special is done.  The packages "/foo/bar/bletch"
+# and "bletch" are considered the same, but unrelated to "bar/bletch".
+#
+# If the algorithm finds more than one suitable subdirectory, all are
+# added to the search path -- this makes it possible to override part
+# of a package.  The same path will not be added more than once.
+#
+# If no directory is found, ImportError is raised.
+
+_packs = {}				# {pack: [pathname, ...], ...}
+
+def addpack(pack, *locations):
+	import os
+	if os.path.isabs(pack):
+		base = os.path.basename(pack)
+	else:
+		base = pack
+	if _packs.has_key(base):
+		return
+	import sys
+	path = []
+	for loc in _flatten(locations) + sys.path:
+		fn = os.path.join(loc, base)
+		if fn not in path and os.path.isdir(fn):
+			path.append(fn)
+	if pack != base and pack not in path and os.path.isdir(pack):
+		path.append(pack)
+	if not path: raise ImportError, 'package ' + pack + ' not found'
+	_packs[base] = path
+	for fn in path:
+		if fn not in sys.path:
+			sys.path.append(fn)
+
+def _flatten(locations):
+	locs = []
+	for loc in locations:
+		if type(loc) == type(''):
+			locs.append(loc)
+		else:
+			locs = locs + _flatten(loc)
+	return locs
diff --git a/Lib/urlopen.py b/Lib/urlopen.py
index 47f0f20..c43b7f4 100755
--- a/Lib/urlopen.py
+++ b/Lib/urlopen.py
@@ -303,6 +303,28 @@ class addinfo(addbase):
 		return self.headers
 
 
+# Utility to combine a URL with a base URL to form a new URL
+
+def basejoin(base, url):
+	type, path = splittype(url)
+	if type: return url
+	host, path = splithost(path)
+	basetype, basepath = splittype(base)
+	basehost, basepath = splithost(basepath)
+	basepath, basetag = splittag(basepath)
+	basepath, basequery = splitquery(basepath)
+	type = basetype or 'file'
+	if path[:1] != '/':
+		import string
+		i = string.rfind(basepath, '/')
+		if i < 0: basepath = '/'
+		else: basepath = basepath[:i+1]
+		path = basepath + path
+	if not host: host = basehost
+	if host: return type + '://' + host + path
+	else: return type + ':' + path
+
+
 # Utilities to parse URLs:
 # unwrap('<URL:type//host/path>') --> 'type//host/path'
 # splittype('type:opaquestring') --> 'type', 'opaquestring'