[Mypyspace-developer] SF.net SVN: mypyspace:[352] graphRDF/branches/songsAsNodes/loadWeights.py

[<gea...@us...>]

Revision: 352
          http://mypyspace.svn.sourceforge.net/mypyspace/?rev=352&view=rev
Author:   gearmonkey
Date:     2009-05-27 21:16:28 +0000 (Wed, 27 May 2009)

Log Message:
-----------
Cleaned up the IO to do some autoformat detection.

Modified Paths:
--------------
    graphRDF/branches/songsAsNodes/loadWeights.py

Modified: graphRDF/branches/songsAsNodes/loadWeights.py
===================================================================
--- graphRDF/branches/songsAsNodes/loadWeights.py	2009-05-26 21:29:16 UTC (rev 351)
+++ graphRDF/branches/songsAsNodes/loadWeights.py	2009-05-27 21:16:28 UTC (rev 352)
@@ -17,8 +17,10 @@
 
 import sys
 import os
+import os.path
 import igraph
 import rightDict
+import cPickle
 #import graphRDF
 
 Usage = """Usage:\nloadWeights.py weightfile.txt inGraph.mlz edgesLeft.txt outGraph.mlz\n\t\tFor more help read the source."""
@@ -51,12 +53,18 @@
 		return 2
 	print "loading graph into memory..."
 	try:
-		putWeightsInHere = igraph.Graph.Load(argv[2], format='graphmlz')
-		print "again..."
-		putWeightsInHere = igraph.Graph.Load(argv[2], format='graphmlz')
-	except RuntimeWarning:
-		print "Trying a second time..."
-		putWeightsInHere = igraph.Graph.Load(argv[2], format='graphmlz')
+		if os.path.splitext(argv[2])[1] in ['.pkl', '.pickle']:
+			print 'unpickling...'
+			putWeightsInHere = cPickle.load(open(argv[2], 'r'))
+		elif os.path.splitext(argv[2])[1] in ['.mlz', '.graphmlz']:
+			print 'rendering from graphmlz...'
+			putWeightsInHere = igraph.Graph.Load(argv[2], format='graphmlz')
+		else:
+			print 'pushing to igraph loader without a format (attempting auto detection)...'
+			putWeightsInHere = igraph.Graph.Load(argv[2])
+	# except RuntimeWarning:
+	# 	print "Trying a second time..."
+	# 	putWeightsInHere = igraph.Graph.Load(argv[2], format='graphmlz')
 	except Exception, err:
 		print >> sys.stderr, sys.argv[0].split("/")[-1] + ": " + str(err)
 		print >> sys.stderr, "\t" + Usage
@@ -76,19 +84,26 @@
 		try:
 			sourceV , targetV, Weight = line.strip().split('\t')
 		except ValueError:
-			outfileHandle.write(str(idx) + " : Missing Weight : " + line)
-			outfileHandle.flush()
-			missed += 1
-			continue
+		 	outfileHandle.write(str(idx) + " : Missing Weight : " + line)
+ 			outfileHandle.flush()
+ 			missed += 1
+			print >> sys.stderr, str(missed) + " missing weights."
+ 			continue
 		try:
-			srcIDX = indexdict[sourceV]
-			trgtIDX = indexdict[targetV]
-		
+			srcIDX = indexdict[sourceV.lstrip(prefix)]
+			trgtIDX = indexdict[targetV.lstrip(prefix)]
+	
 			igraph.EdgeSeq(putWeightsInHere, [srcIDX, trgtIDX])[0]['audioWeight'] = float(Weight)
+		except ValueError:
+		 	outfileHandle.write(str(idx) + " : Missing Edge : " + line)
+ 			outfileHandle.flush()
+ 			typos += 1
+			print >> sys.stderr, str(typos) + " typos found."
+ 			continue
 		except Exception, err:
-			typoOutHandle.write(str(idx) + " : typo : " + line)
-			typoOutHandle.flush()
-			typos += 1
+		 	typoOutHandle.write(str(idx) + " : typo : " + line)
+		 	typoOutHandle.flush()
+		 	typos += 1
 			print >> sys.stderr, str(err) + "\n" + str(typos) + " typos found."
 			continue
 		
@@ -98,7 +113,16 @@
 	print "found " + str(missed) + " lines without weight."
 	print "Saving updated graph to " + str(argv[4])
 	
-	putWeightsInHere.write(argv[4], format='graphmlz')
+	if os.path.splitext(argv[4])[1] in ['.pkl', '.pickle']:
+		cPickle.dump(putWeightsInHere, open(argv[4], 'w'))
+	elif os.path.splitext(argv[4])[1] in ['.mlz', '.graphmlz']:
+		putWeightsInHere.write(argv[4], format='graphmlz')
+	else:
+		try:
+			putWeightsInHere.write(argv[4])
+		except IOError:
+			print "unable to determine the desired file format from the extension for the output graph.\nWriting it out as a graphmlz file and appending .mlz"
+			putWeightsInHere.write(argv[4]+'.mlz', format='graphmlz')
 	infileHandle.close()
 	outfileHandle.close()
 	typoOutHandle.close()


This was sent by the SourceForge.net collaborative development platform, the world's largest Open Source development site.