Mercurial > repos > bernhardlutz > graphconverter

changeset 2:89b606a49225 draft

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
Uploaded
author bernhardlutz
date Fri, 28 Feb 2014 09:46:59 -0500
parents 29cc4ec84a56
children b7cdfd11614a
files 3_molecules.gspan convert_graph.py convert_graph.xml test-data/bsp_graph.gml test-data/bsp_graph.gml~ test-data/graph2.gexf tool_dependencies.xml xgmml_networkx.py xgmml_networkx.pyc
diffstat 9 files changed, 542 insertions(+), 0 deletions(-) [+]
line wrap: on
line diff
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/3_molecules.gspan	Fri Feb 28 09:46:59 2014 -0500
@@ -0,0 +1,129 @@
+t # id 1
+v 0 O 
+v 1 O 
+v 2 O 
+v 3 O 
+v 4 C 
+v 5 C 
+v 6 C 
+v 7 C 
+v 8 C 
+v 9 C 
+v 10 C 
+v 11 C 
+v 12 C 
+v 13 H 
+v 14 H 
+v 15 H 
+v 16 H 
+v 17 H 
+v 18 H 
+v 19 H 
+v 20 H 
+e 0 4 1
+e 0 11 1
+e 1 10 1
+e 1 20 1
+e 2 10 2
+e 3 11 2
+e 4 5 1
+e 4 6 2
+e 5 7 2
+e 5 10 1
+e 6 8 1
+e 6 13 1
+e 7 9 1
+e 7 14 1
+e 8 9 2
+e 8 15 1
+e 9 16 1
+e 11 12 1
+e 12 17 1
+e 12 18 1
+e 12 19 1
+t # id 2
+v 0 O 
+v 1 O 
+v 2 O 
+v 3 O 
+v 4 C 
+v 5 C 
+v 6 C 
+v 7 C 
+v 8 C 
+v 9 C 
+v 10 C 
+v 11 C 
+v 12 C 
+v 13 H 
+v 14 H 
+v 15 H 
+v 16 H 
+v 17 H 
+v 18 H 
+v 19 H 
+v 20 H 
+e 0 4 1
+e 0 11 1
+e 1 10 1
+e 1 20 1
+e 2 10 2
+e 3 11 2
+e 4 5 1
+e 4 6 2
+e 5 7 2
+e 5 10 1
+e 6 8 1
+e 6 13 1
+e 7 9 1
+e 7 14 1
+e 8 9 2
+e 8 15 1
+e 9 16 1
+e 11 12 1
+e 12 17 1
+e 12 18 1
+e 12 19 1
+t # id 3
+v 0 O 
+v 1 O 
+v 2 O 
+v 3 O 
+v 4 C 
+v 5 C 
+v 6 C 
+v 7 C 
+v 8 C 
+v 9 C 
+v 10 C 
+v 11 C 
+v 12 C 
+v 13 H 
+v 14 H 
+v 15 H 
+v 16 H 
+v 17 H 
+v 18 H 
+v 19 H 
+v 20 H 
+e 0 4 1
+e 0 11 1
+e 1 10 1
+e 1 20 1
+e 2 10 2
+e 3 11 2
+e 4 5 1
+e 4 6 2
+e 5 7 2
+e 5 10 1
+e 6 8 1
+e 6 13 1
+e 7 9 1
+e 7 14 1
+e 8 9 2
+e 8 15 1
+e 9 16 1
+e 11 12 1
+e 12 17 1
+e 12 18 1
+e 12 19 1
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/convert_graph.py	Fri Feb 28 09:46:59 2014 -0500
@@ -0,0 +1,138 @@
+#!/usr/bin/env python
+# Aufruf convert_graph.py --infile datei --informat typ --outfile ausgabedatei --outformat ausgabetyp
+
+import sys, os
+import networkx as nx
+import argparse
+import json
+
+from xgmml_networkx import XGMMLParserHelper, XGMMLWriter
+from networkx.readwrite import json_graph
+
+#supported graph_types
+graph_types = ["gml", "yaml", "gspan", "xgmml", "gexf", "graphml", "json", "pajek"]
+
+func_dic_read= {'gml': nx.read_gml, 'yaml':nx.read_yaml, 'gexf': nx.read_gexf,
+    'graphml': nx.read_graphml, 'pajek': nx.read_pajek}
+    
+func_dic_write= {'gml': nx.write_gml, 'yaml':nx.write_yaml, 'gexf': nx.write_gexf,
+    'graphml': nx.write_graphml, 'pajek': nx.write_pajek}
+
+#completely supported types by networkx
+completely_supported_types = ["gml", "gexf", "yaml", "graphml", "pajek"]
+
+def read_gspan(infile):
+    G = nx.Graph()
+    idoffset=0
+    old_id_start=0
+    for line in infile:
+        line_split=line.split(" ")
+        length_split=len(line_split)
+        if line[0] == "v":
+            G.add_node(idoffset, label=line_split[2].strip())
+            idoffset+=1
+        elif line[0] == "e":
+            if length_split < 3:
+                raise InvalidGraph(line)
+            elif length_split > 3:
+                G.add_edge(old_id_start+int(line_split[1]), old_id_start+int(line_split[2]), label=line_split[3].strip())
+            else:
+                G.add_edge(old_id_start+int(line_split[1]), old_id_start+int(line_split[2]), label="")
+        elif line[0] == "t":
+        # its a new subgraph
+            #idoffset*=1
+            old_id_start=idoffset
+    #print(nx.is_connected(G))
+    return G
+    
+
+def write_gspan(graph, outfile):
+    # get all subgraphs only works with undirected
+    subgraphs=nx.connected_components(graph.to_undirected())
+    id_count=1
+    node_count=0
+    #get labels
+    label_dic=nx.get_node_attributes(graph,'label')
+    for s in subgraphs:
+        node_count_tree=0
+        node_dict={}
+        outfile.write("t # id "+str(id_count)+"\n")
+        # for every node in subgraph
+        for v in sorted(s):
+        # node id restart from 0 for every sub graph
+            node_dict[v]=node_count_tree
+            outfile.write("v "+str(node_count_tree)+" "+label_dic[v]+" \n")
+            node_count_tree+=1
+            node_count+=1
+            
+        # all edges adjacent to a node of s
+        edges=nx.edges(graph, s)
+        for e in sorted(edges):
+            #print(graph[e[0]][e[1]])
+            try:
+                outfile.write("e "+str(node_dict[e[0]])+" "+str(node_dict[e[1]])+" "+graph[e[0]][e[1]]['label']+"\n")
+            except KeyError:
+                outfile.write("e "+str(node_dict[e[0]])+" "+str(node_dict[e[1]]))
+            
+        id_count+=1
+def read_json(file):
+    json_string=file.read()
+    print(json_string)
+    json_dict=json.loads(json_string)
+    print(json_dict)
+    return nx.Graph()
+    
+def write_json(graph, outfile):
+    json_dict=json_graph.node_link_data(graph)
+    json_string=json.dumbs(json_dict)
+    outfile.write(json_string)
+    print("did it")
+    
+def main( args ):
+
+    if args.informat not in graph_types:
+        print "EXCEPTION COMPUTER EXPLODING"
+    # everything networkx can do by itself ;)
+    elif args.informat in completely_supported_types:
+        function = func_dic_read[args.informat]
+        graph = function(args.infile)
+    elif args.informat == "gspan":
+        graph = read_gspan(args.infile)
+    elif args.informat == "json":
+        graph = read_json(args.infile)
+    elif args.informat == "xgmml":
+        xgmml=XGMMLParserHelper()
+        xgmml.parseFile(args.infile)
+        graph=xgmml.graph()
+
+
+
+    if args.outformat in completely_supported_types:
+        function = func_dic_write[args.outformat]
+        function(graph, args.outfile)
+    elif args.outformat == "gspan":
+        write_gspan(graph, args.outfile)
+    elif args.outformat == "json":
+        write_json(graph, args.outfile)
+    elif args.outformat == "xgmml":  
+    #xgmml=XGMMLParserHelper(graph)
+    #xgmml.parseFile(open(sys.argv[1]))
+        a=XGMMLWriter(args.outfile, graph, "MyGraph")
+    
+if __name__ == "__main__":
+    
+    parser = argparse.ArgumentParser()
+    parser.add_argument('--infile', type=argparse.FileType('r'),
+        help="Specify the input file representing a graph")
+    parser.add_argument('--outfile', type=argparse.FileType('w'),
+        help="Specify one output file")
+    parser.add_argument('--informat', type=str,
+        help="Specify the format of the input graph", choices = graph_types)
+    parser.add_argument('--outformat', type=str,
+        help="Specify the format of the output graph", choices = graph_types)
+    if len(sys.argv) < 8:
+        print "Too few arguments..."
+        parser.print_help()
+        exit(1)
+    args = parser.parse_args()
+    main( args )
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/convert_graph.xml	Fri Feb 28 09:46:59 2014 -0500
@@ -0,0 +1,44 @@
+<tool id="graph_converter" name="Graph Converter" version="0.1.0">
+    <description>Convert between different Graphformats</description>
+    <version_command>echo "0.1.0"</version_command>
+    <requirements>
+        <requirement type="set_environment">GRAPHCONVERTER_SCRIPT_PATH</requirement>
+    </requirements>
+    <command>
+        python \$GRAPHCONVERTER_SCRIPT_PATH/convert_graph.py --infile $inputfile --informat $informat --outfile $outfile --outformat $outformat
+    </command>
+
+    <inputs>
+        <param format="txt" name="inputfile" type="data" label="Graph to convert" />
+        <param name="informat" multiple="false" type="select" label="Input Format">
+            <option value="gml">GML</option>
+            <option value="gexf">GEXF</option>
+            <option value="gspan">GSPAN</option>
+            <option value="graphml">GRAPHML</option>
+            <option value="json">JSON</option>
+            <option value="pajek">PAJEK</option>
+            <option value="xgmml">XGMML</option>
+            <option value="yaml">YAML</option>
+        </param>
+        <param name="outformat" multiple="false" type="select" label="Output Format">
+            <option value="gml">GML</option>
+            <option value="gexf">GEXF</option>
+            <option value="gspan">GSPAN</option>
+            <option value="graphml">GRAPHML</option>
+            <option value="json">JSON</option>
+            <option value="pajek">PAJEK</option>
+            <option value="xgmml">XGMML</option>
+            <option value="yaml">YAML</option>
+        </param>
+    </inputs>
+    <outputs>
+        <data format="txt " name="outfile" />
+    </outputs>
+    <tests>
+    </tests>
+    <help>
+**What it does**
+
+This tool converts a file representing a graph into another format.
+    </help>
+</tool>
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/test-data/bsp_graph.gml	Fri Feb 28 09:46:59 2014 -0500
@@ -0,0 +1,37 @@
+graph [
+	comment "Das ist ein Beispielgraph."
+	directed 1
+	id 42
+	label "Graph"
+	node [
+		id 1
+		label "A"
+		weiteresAttribut 42
+	]
+	node [
+		id 2
+		label "B"
+		weiteresAttribut 43
+	]
+	node [
+		id 3
+		label "C"
+		weiteresAttribut 44
+	]
+	edge [
+		source 1
+		target 2
+		label "Kante AB"
+	]
+	edge [
+		source 2
+		target 3
+		label "Kante BC"
+	]
+	edge [
+		source 3
+		target 1
+		label "Kante CA"
+	]
+]
+
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/test-data/bsp_graph.gml~	Fri Feb 28 09:46:59 2014 -0500
@@ -0,0 +1,49 @@
+    Creator "yFiles"  
+    Version 2.2  
+    graph  
+    [ hierarchic  1  
+      directed  1  
+      node  
+      [ id  0  
+        graphics  
+        [ x 200.0     
+          y 0.0  
+        ]  
+        LabelGraphics  
+        [ text  "January" ]  
+      ]  
+      node  
+      [ id  1  
+        graphics  
+        [ x 425.0  
+          y 75.0  
+        ]  
+        LabelGraphics  
+        [ text  "December"  ]  
+      ]  
+      edge  
+      [ source  1  
+        target  0  
+        graphics  
+        [ Line  
+          [ point  
+            [ x 425.0  
+              y 75.0  
+            ]  
+            point  
+            [ x 425.0  
+              y 0.0  
+            ]  
+            point  
+            [ x 200.0  
+              y 0.0  
+            ]  
+          ]  
+        ]  
+        LabelGraphics  
+        [ text  "Happy New Year!"  
+          model "six_pos"  
+          position  "head"  
+        ]  
+      ]  
+    ]  
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/test-data/graph2.gexf	Fri Feb 28 09:46:59 2014 -0500
@@ -0,0 +1,16 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<gexf xmlns="http://www.gexf.net/1.2draft" version="1.2">
+    <meta lastmodifieddate="2009-03-20">
+        <creator>Gexf.net</creator>
+        <description>A hello world! file</description>
+    </meta>
+    <graph mode="static" defaultedgetype="directed">
+        <nodes>
+            <node id="0" label="Hello" />
+            <node id="1" label="Word" />
+        </nodes>
+        <edges>
+            <edge id="0" source="0" target="1" />
+        </edges>
+    </graph>
+</gexf>
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/tool_dependencies.xml	Fri Feb 28 09:46:59 2014 -0500
@@ -0,0 +1,5 @@
+<tool_dependency>
+    <set_environment version="1.0">
+        <environment_variable name="GRAPHCONVERTER_SCRIPT_PATH" action="set_to">$REPOSITORY_INSTALL_DIR</environment_variable>
+    </set_environment>
+</tool_dependency>
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/xgmml_networkx.py	Fri Feb 28 09:46:59 2014 -0500
@@ -0,0 +1,124 @@
+__author__ = "Yasunobu OKAMURA"
+__copyright__ = "Copyright (c) 2012 Y.Okamura"
+__license__ = "GPL v3+"
+
+import xml.parsers.expat
+import networkx as nx
+
+class XGMMLParserHelper(object):
+    """
+    """
+    
+    def __init__(self, graph=nx.DiGraph()):
+        """
+        
+        Arguments:
+        - `graph`: Network X graph object
+        """
+        self._graph = graph
+        self._parser = xml.parsers.expat.ParserCreate()
+        self._parser.StartElementHandler = self._start_element
+        self._parser.EndElementHandler = self._end_element
+        self._tagstack = list()
+
+        self._current_attr = dict()
+        self._current_obj = dict()
+
+    def _start_element(self, tag, attr):
+        """
+        
+        Arguments:
+        - `self`:
+        - `tag`:
+        - `attr`:
+        """
+
+        self._tagstack.append(tag)
+
+        if tag == 'node' or tag == 'edge':
+            self._current_obj = dict(attr)
+
+        if tag == 'att' and (self._tagstack[-2] == 'node' or self._tagstack[-2] == 'edge'):
+            if attr['type'] == 'string':
+                self._current_attr[attr['name']] = attr['value']
+            elif attr['type'] == 'real':
+                self._current_attr[attr['name']] = float(attr['value'])
+            elif attr['type'] == 'integer':
+                self._current_attr[attr['name']] = int(attr['value'])
+            elif attr['type'] == 'boolean':
+                self._current_attr[attr['name']] = bool(attr['value'])
+            else:
+                raise NotImplementedError(attr['type'])
+
+    def _end_element(self, tag):
+        """
+        
+        Arguments:
+        - `self`:
+        - `tag`:
+        """
+
+        if tag == 'node':
+            self._graph.add_node(self._current_obj['id'], label=self._current_obj['label'], **self._current_attr)
+            #print 'add node', self._current_obj
+        elif tag == 'edge':
+            self._graph.add_edge(self._current_obj['source'], self._current_obj['target'], **self._current_attr)
+
+        self._tagstack.pop()
+
+    def parseFile(self, file):
+        """
+        
+        Arguments:
+        - `self`:
+        - `file`:
+        """
+
+        self._parser.ParseFile(file)
+
+    def graph(self):
+        """
+        
+        Arguments:
+        - `self`:
+        """
+
+        return self._graph
+
+def XGMMLWriter(file, graph, graph_name):
+    """
+    
+    Arguments:
+    - `graph`:
+    """
+
+    print >>file, """<?xml version="1.0" encoding="UTF-8" standalone="yes"?>
+<graph directed="1"  xmlns:dc="http://purl.org/dc/elements/1.1/" xmlns:xlink="http://www.w3.org/1999/xlink" xmlns:rdf="http://www.w3.org/1999/02/22-rdf-syntax-ns#" xmlns="http://www.cs.rpi.edu/XGMML">
+<att name="selected" value="1" type="boolean" />
+<att name="name" value="{0}" type="string"/>
+<att name="shared name" value="{0}" type="string"/>
+""".format(graph_name)
+
+
+    for onenode in graph.nodes(data=True):
+        id = onenode[0]
+        attr = dict(onenode[1])
+
+        if 'label' in attr:
+            label = attr['label']
+            del attr['label']
+        else:
+            label = id
+        
+        print >>file, '<node id="{id}" label="{label}">'.format(id=id, label=label)
+        for k, v in attr.iteritems():
+            print >>file, '<att name="{}" value="{}" type="string" />'.format(k, v)
+        print >>file, '</node>'
+        
+    for oneedge in graph.edges(data=True):
+        print >>file, '<edge source="{}" target="{}">'.format(oneedge[0], oneedge[1])
+        for k, v in oneedge[2].iteritems():
+            print >>file, '<att name="{}" value="{}" type="string" />'.format(k, v)
+        print >>file, '</edge>'
+    print >>file, '</graph>'
+
Binary file xgmml_networkx.pyc has changed