findMissing.py

INPUT_FILE = "input.tsv"

class LanguageInfo:
    def __init__(self, col_header):
        split_header = col_header.split(" ")
        self.num_items = (int)(split_header[0])
        self.language_name = split_header[-1]
        self.source_terms = set()


# Print missing languages by word
def print_missing_languages_by_word(langs, all_source_terms):
    for word in sorted(all_source_terms):
        languages_missing = []
        # Check if word is in each language, if not add language to
        # languages_missing list
        for lang in langs:
            if word not in lang.source_terms:
                languages_missing.append(lang.language_name)
        # If word has more than 0 languages missing it, print
        if len(languages_missing) != 0:
            print("Source term '{0}' missing languages: '{1}'".format(word, ", ".join(languages_missing)))


# Print missing words by language
def print_missing_words_by_language(langs, all_source_terms):
    for lang in langs:
        # Get difference between cumulative list and language list
        missing_source_terms = all_source_terms - lang.source_terms
        if len(missing_source_terms) != 0:
            print("Language: {0} is missing source terms:".format(lang.language_name))
            print("\t{0}".format("\n\t".join(sorted(missing_source_terms))))


def main():
    # Build list of languages and words
    with open(INPUT_FILE, 'r') as f:
        # Make list of languages from header
        # Assumes input is in the format "#source_terms ... ... ... language name"
        langs = []
        first_line = f.readline()
        for column_header in first_line.replace("\n", "").split("\t"):
            langs.append(LanguageInfo(column_header))

        # Read through input, get cumulative list of all words
        all_source_terms = set()
        for line in f:
            # Throw away newline character, split into columns
            split_line = line.replace("\n", "").split("\t")
            for i, col in enumerate(split_line):
                # Add word to cumulative list
                all_source_terms.add(col)
                # Add list to appropriate language
                langs[i].source_terms.add(col)

    print_missing_languages_by_word(langs, all_source_terms)
    print("")
    print_missing_words_by_language(langs, all_source_terms)


if __name__ == "__main__":
    main()