packageinfo.py

from re import match, split
from subprocess import check_output

from debian.deb822 import Deb822
from graph_tool.all import *

graph = Graph()
package_nodes = {}
package_info = {}


def get_package_list():
	"""Return a list of packages, both installed and uninstalled."""
	output = check_output(['dpkg', '-l', '*'])
	packages = []
	for line in output.split('\n'):
		parts = line.split()
		if not parts or not match('[uirph][nicurhWt]', parts[0]):
			continue
		packages.append(parts[1])
	return packages


def get_package_info(pkg_name):
	"""Get a dict-like object containing information for a specified package."""
	global package_info
	if pkg_name in package_info:
		return package_info.get(pkg_name)
	else:
		try:
			yaml_stream = check_output(['apt-cache', 'show', pkg_name])
		except:
			print "Unable to find info for package: '%s'" % pkg_name
			package_info[pkg_name] = {}
			return {}
		d = Deb822(yaml_stream)
		package_info[pkg_name] = d
		return d


def get_graph_node_for_package(pkg_name):
	"""Given a package name, return the graph node for that package. If the graph
	node does not exist, it is created, and it's meta-data filled.

	"""
	global graph
	global package_nodes

	if pkg_name not in package_nodes:
		n = graph.add_vertex()
		package_nodes[pkg_name] = n
		# add node properties:
		pkg_info = get_package_info(pkg_name)
		graph.vertex_properties["package-name"][n] = pkg_name
		graph.vertex_properties["installed-size"][n] = int(pkg_info.get('Installed-Size', 0))
		return n
	else:
		return package_nodes.get(pkg_name)


def get_sanitised_depends_list(depends_string):
	"""Given a Depends string, return a list of package names. Versions are
	stripped, and alternatives are all shown.

	"""
	if depends_string == '':
		return []
	parts = split('[,\|]', depends_string)
	return [match('(\S*)', p.strip()).groups()[0] for p in parts]


if __name__ == '__main__':
	# Create property lists we need:
	graph.vertex_properties["package-name"] = graph.new_vertex_property("string")
	graph.vertex_properties["installed-size"] = graph.new_vertex_property("int")

	# get list of packages:
	packages = get_package_list()

	n = 0
	for pkg_name in packages:
		node = get_graph_node_for_package(pkg_name)
		pkg_info = get_package_info(pkg_name)
		# purely virtual packages won't have a package info object:
		if pkg_info:
			depends = pkg_info.get('Depends', '')
			depends = get_sanitised_depends_list(depends)
			for dependancy in depends:
				graph.add_edge(node, get_graph_node_for_package(dependancy))
		n += 1
		if n % 10 == 0:
			print "%d / /%d" % (n, len(packages))

	graph.save('graph.gml')