import re
report = '/home/fvlingen/programFiles/CMS_CVS/PRODAGENT/cvsStatusPC.txt'
release = 'PRODCOMMON_0_12_10_pre2'
prefix = 'CMSSW/COMP/PRODCOMMON'


pattern = re.compile('(.*'+release+' |.*'+release+'\t)')

reportFile = open(report, 'r')
line = reportFile.readline()

#add whitespace to prevent finding substrings
release = ' '+release+' '
state = 'file'
fileName = ' '
currentVersion= ' '
tagRevision= ' '
#files that where updated since the release
updated = []
# files that where missed
missed = []
isItTagged = False

while line:
    if line.startswith('File:'):
        # process last file data.
        if fileName != ' ':
            if isItTagged and currentVersion != tagRevision:
                updated.append(fileName)
            if not isItTagged:
                missed.append(fileName)
        state = 'file'
        isItTagged = False
    if line.find('Working revision') > -1:
        currentVersion = line.split(' ')[-1].split('\t')[-1].split('\n')[0]
    if line.find('Repository revision') > -1:
        fileName = line.split('\t')[-1].split(',')[0]
        index = fileName.find(prefix)
        fileName = fileName[index + 10:]
        state = 'tag'
    if pattern.match(line) and state == 'tag':
        state = 'file'
        tagRevision = line.split(' ')[-1].split(')\n')[0]
        isItTagged = True

    line = reportFile.readline()

#check last analyzed file.
if fileName != ' ':
    if isItTagged and currentVersion != tagRevision:
        updated.append(fileName)
    if not isItTagged:
        missed.append(fileName)

reportFile.close()

print 'summary for checking head against tag: '+release
print 'Updated files:'
updated.sort()
for file in updated:
    print file

print 'Missed files:'
missed.sort()
for file in missed:
    print file