word_form root_form morphological_form frequency
word_form root_form morphological_form frequency
word_form root_form morphological_form frequency

cup'board   cup     blabla  12
cupboard    cup     blabla2 10

cupboard    cup     blabla2  22

class Lemma:
   """Creates a Lemma with the word form, the root, the morphological analysis and the frequency in the corpus"""
    def __init__(self,lop):
        self.word_form = lop[0]
        self.root = lop[1]
        self.morph = lop[2]
        self.freq = int(lop[3])

def Reader(filename):
   """Keeps the lines of a file in memory for a single reading, memory efficient"""
    with open(filename) as f:
        for line in f:
            yield line

def get_word_dict(filename):
    '''Separates the word list into two dictionaries, one for words with apostrophe and one for words with apostrophe'''
    '''Works in a reasonable time'''
    '''This step can be done writing line by line, avoiding all storage in memory'''
    word_dict = {}
    word_dict_striped = {}

    # We store the lemmas in two dictionaries, word_dict for words without apostrophe, word_dict_striped for words with apostrophe  
    with open('word_dict.txt', 'wb') as f:
        with open('word_dict_striped.txt', 'wb') as g:

            reader = Reader(filename)
            for line in reader:
                items = line.split("\t")
                word_form = items[0]
                if"'" in word_form:
                    # we remove the apostrophe in the word form and morphological analysis and add the lemma to the dictionary word_dict_striped
                    items[0] = word_form.replace("'","")
                    items[2] = items[2].replace("\+Apos","")

                    g.write("%s\t%s\t%s\t%s" % (items[0], items[1], items[2], items[3]))
                    word_dict_striped({items[0] : Lemma(items)})
                else:
                    # we just add the lemma to the dictionary word_dict
                    f.write("%s\t%s\t%s\t%s" % (items[0], items[1], items[2], items[3]))
                    word_dict.update({items[0] : Lemma(items)})

    return word_dict, word_dict_striped

def merge_word_dict(word_dict, word_dict_striped):
    '''Takes two dictionaries and merge them by adding the count of their frequencies if there is a common key'''
    ''' Does not run in reasonable time on the whole list '''

    with open('word_compiled_dict.txt', 'wb') as f:

        for word in word_dict_striped.keys():
            if word in word_dict.keys():
                word_dict[word].freq += word_dict_striped[word].freq
                f.write("%s\t%s\t%s\t%s" % (word_dict[word].word_form, word_dict[word].root, word_dict[word].morph, word_dict[word].freq))
            else:
                word_dict.update(word_dict_striped[word])

    print"Number of words:",
    print(len(word_dict))

    for x in word_dict:
        print x, word_dict[x].root, word_dict[x].morph, word_dict[x].freq

    return word_dict

input_file_name ="input.txt"
output_file_name ="output.txt"

def custom_comp(s1, s2):
    word1 = s1.split()[0]
    word2 = s2.split()[0]
    stripped1 = word1.translate(None,"'")
    stripped2 = word2.translate(None,"'")

    if stripped1 > stripped2:
        return 1
    elif stripped1 < stripped2:
        return -1
    else:
        if"'" in word1:
            return -1
        else:
            return 1

def get_word(line):
    return line.split()[0].translate(None,"'")

def get_num(line):
    return int(line.split()[-1])

print"Reading file and sorting..."

lines = []
with open(input_file_name, 'r') as f:
    for line in sorted(f, cmp=custom_comp):
        lines.append(line)

print"File read and sorted"

combined_lines = []

print"Combining entries..."

i = 0
while i < len(lines) - 1:
    if get_word(lines[i]) == get_word(lines[i+1]):
        total = get_num(lines[i]) + get_num(lines[i+1])
        new_parts = lines[i+1].split()
        new_parts[-1] = str(total)
        combined_lines.append("".join(new_parts))
        i += 2
    else:
        combined_lines.append(lines[i].strip())
        i += 1

print"Entries combined"
print"Writing to file..."

with open(output_file_name, 'w+') as f:
    for line in combined_lines:
        f.write(line +"
")

print"Finished"