append docname & linenumber to dic-value

[simic]

Hey guys,
I am comparing two documents - if a word is in both documents, it gets added as a new key to a dictionary.
As the dictionary value I would like to store the documents name and the line# the word was found on.
Here is what I have so far with comments:

dic = {}
def matchtermer():
    f3 = open('korpus/avis.txt')
    f4 = open("ordliste_output_kort.txt")
    text3 = f3.read()
    text4 = f4.read()
    ordliste2 = text3.split()
    ordliste3 = text4.split()
    wordlist2 = []

    for word1 in ordliste2: #this part removes end characters that aren't part of the word and makes all lowercase
        # last character of each word
        lastchar = word1[-1:]
        # use a list of punctuation marks
        if lastchar in [",", ".", "!", "?", ";"]:
            word2 = word1.rstrip(lastchar)
        else:
            word2 = word1
        # build a wordList of lower case modified words
        wordlist2.append(word2.lower())

    for word in wordlist2: # and finally this compares the two documents
        if word in ordliste3:
            if word not in dic.keys():
                dic[word]=[]  #if word not in dic, create it
            #dic[word].append(docname, linenumber) - this is what I want to do - obviously this does not work
    return dic

[bvdet]

I think this will do it:[code=Python]import string, re

def wordList(words) :
patt = re.compile(r'\d +')
# eliminate words with digits, strip punctuation and whitespace, lowercase
word_list = [word.strip().st rip(string.punc tuation).lower( ) for word \
in words.split() if not patt.search(wor d)]
# elinimate blank words
return [word for word in word_list if word != '']

def matchtermer(fn1 , fn2):
dd = {}
# file to compare against
f1 = open(fn1).read( )
# file to compare
f2 = open(fn2).readl ines()
word_list = wordList(f1)
for i, line in enumerate(f2):
for word in line.split():
word = word.strip().st rip(string.punc tuation).lower( )
if word in word_list:
dd.setdefault(w ord, []).append((fn2, i+1))
return dd[/code]Usage:[code=Python]wordDict = matchtermer('wo rds1.txt', 'words2.txt')[/code]