From 4a33223eba7cf5cf66ccdf98abb1f0c81808cfc3 Mon Sep 17 00:00:00 2001
From: Marc Jones <mjones@softwarefreedom.org>
Date: Wed, 5 Feb 2014 10:07:54 -0500
Subject: merging summary.py into main.py

---
 main.py | 92 +++++++++++++++++++++++++++++++++++++++++++++++++++++------------
 1 file changed, 75 insertions(+), 17 deletions(-)

(limited to 'main.py')

diff --git a/main.py b/main.py
index ae36453..22da098 100755
--- a/main.py
+++ b/main.py
@@ -27,6 +27,37 @@ def printscore(report):
 	for i in report:
 		print i[0] + ':' + str(i[1])
 
+def scorewords(report):
+	for file in report.keys():
+		for word in report[file].keys():
+			if not word in wordscore:
+				wordscore[word] = 0
+			if not file in filescore:
+				filescore[file] = 0
+			wordscore[word] += report[file][word]
+	return wordscore
+
+def scorefile(report):
+	for file in report.keys():
+		for word in report[file].keys():
+			if not word in wordscore:
+				wordscore[word] = 0
+			if not file in filescore:
+				filescore[file] = 0
+			filescore[file] += report[file][word]
+	return filescore
+
+def summary(report):
+	filescore = scorefile(report)
+	text = ""
+	for file in sortscore(filescore):
+		text += file[0] + '(' + str(file[1]) + '):'
+		for word in report[file[0]].keys():
+			if report[file[0]][word] > 0:
+				text += word + '(' + str(report[file[0]][word]) + ');' 
+		text += '\n'
+	return text
+
 def wholeword(word, string):
 	re.purge()
 	matches = []
@@ -68,6 +99,8 @@ parser.add_option("--show-wordlist", dest="show_wordlist", default=False, help="
 parser.add_option("-c", "--display-counts", dest="display_counts", default=False, help="Show the num ber of files processed", action="store_true")
 parser.add_option("-p", "--display_progress", dest="display_progress", default=False, help="show percentage complete", action="store_true")
 parser.add_option("-l", "--max-wholeword-length", dest="maxwholewordlength", type="int", default=-1, help="maximun length of a word allowed to only find matches on whole word")
+parser.add_option("-o", "--summary-file", dest="summaryfile", help="name of the file to store the summary in")
+parser.add_option("-x", "--display-summary", dest="displaysummary", default=False, help="Display a summary from the summary file", action="store_true")
 
 (options, args) = parser.parse_args()
 
@@ -76,6 +109,33 @@ if options.wordlistfilename:
 			
 if options.show_wordlist: print wordlist; exit()
 
+if options.displaysummary and options.summaryfile
+	report = dict()
+	try:
+		summaryfile = open(options.summaryfile)
+	except:
+		print "no summary file: " + options.summaryfile
+		exit()
+	#sample input
+	#../bzr.lf/lsb/devel/build_env/headers/x86-64/4.1/glib-2.0/gio/gmenuexporter.h.defs(1): export(1);
+	for line in summaryfile:
+		#find the file name which is before the matching parathsis before the last colon on the line
+		filename = line[:line[:line.rfind(':')].rfind('(')]
+		#find the total number of words found by locating the end of the filename and taking the number in parathesis right before the :
+		totalfilecount = line[line[:line.rfind(':')].rfind('(')+1:line[:line.rfind(':')].rfind(')')]
+		#find the list of words following the :, and split them by the ;, and then drop the last item on the list which is always a \n
+		foundwords = line[line.rfind(':')+1:].split(';')[:-1]
+		report[filename] = dict()		
+		for w in foundwords:
+			w = w.strip()
+			word = w[:w.find('(')]
+			wcount = w[w.find('(')+1:w.find(')')]		
+			report[filename][word] = wcount
+
+	print summary(report)
+	exit()
+
+
 for a in args:
 	#filelist.append(a)
 	for (path, dirs, files) in os.walk(a):
@@ -122,27 +182,15 @@ for file in filelist:
 	for k in filecontentsscore.keys():
 		report[file][k] = filenamescore[k] + filecontentsscore[k]
 
-for file in report.keys():
-	for word in report[file].keys():
-		if not word in wordscore:
-			wordscore[word] = 0
-		if not file in filescore:
-			filescore[file] = 0
-		wordscore[word] += report[file][word]
-		filescore[file] += report[file][word]
+
 
 if options.printreport:
 	if options.printreport == "f":
-		printscore(sortscore(filescore))
+		printscore(sortscore(scorefile(report)))
 	elif options.printreport == "wf" or options.printreport == "fw":
-		for file in sortscore(filescore):
-			print file[0] + '(' + str(file[1]) + '):',
-			for word in report[file[0]].keys():
-				if report[file[0]][word] > 0:
-					print word + '(' + str(report[file[0]][word]) + ');', 
-			print ""
+		print summary(report)
 	else:
-		printscore(sortscore(wordscore))
+		printscore(sortscore(scorewords(report)))
 
 if options.display_counts:
 	print "total files:" + str(len(filelist)) ,
@@ -150,7 +198,17 @@ if options.display_counts:
 	print "skipped files:" + str(skipped) ,
 	print "searched:" + str(datasize) + 'B', 
 	print "time:" + str(datetime.datetime.now() - start).split('.')[0]
- 
+
+if options.summaryfile and len(filelist) > 0 and not options.displaysummary:
+	summaryfilename = options.summaryfile	
+	counter = None
+	while os.path.isfile(summaryfilename)
+		counter +=1
+		summaryfilename = options.summaryfile + '.' + str(counter)
+	summaryfile = open(summaryfile, 'w+')
+	summaryfile.write(summary(report))
+	summaryfile.close()
+
 def test():
 	print wholeword("ear","bearth")
 	print wholeword("ear","BearTH")
-- 
cgit v1.2.3