def handle_arguments():
# Handle the command line arguments.
if not argv[3].isdigit():
print("The quantity parameter must be an integer.")
return
file = argv[1]
parameter = argv[2]
quantity = int(argv[3])
if parameter != '-s' and parameter != '-w':
print_usage()
return
words = extractor.get_words(file)
words_scores = get_word_scores(words)
sentences = extractor.get_sentences(file)
sentences_scores = get_sentence_scores_dict(sentences, words_scores)
if parameter == '-s':
if quantity > len(sentences):
print(
"Quantity specified is greater than the number of sentences.")
else:
print_popular(sentences_scores, sort_dictionary(sentences_scores),
quantity)
else:
if quantity > len(words):
print("Quantity specified is greater than the number of words.")
else:
print_popular(words_scores, sort_dictionary(words_scores),
quantity)
def summarize(filename, num_of_sentences):
# Summarize a file. The length of the summary will be the number of sentences specified.
file = filename
# Extract all the words and sentences and get their respective scores.
all_words = extractor.get_words(file)
word_scores = scoring.get_word_scores(all_words)
all_sentences = extractor.get_sentences(file)
all_sentences = filter.omit_transition_sentences(all_sentences)
sentence_scores = scoring.get_sentence_scores_list(all_sentences,
word_scores)
if num_of_sentences > len(all_sentences):
print("The summary cannot be longer than the text.")
return
# Get x sentences with the highest scores, in chronological order.
threshold = scoring.x_highest_score(sentence_scores, num_of_sentences)
top_sentences = scoring.top_sentences(all_sentences, sentence_scores,
threshold)
# Put the top sentences into one string.
summary = ""
for sentence in top_sentences:
summary += sentence + " "
summary = summary[:-1]
print(summary)
def summarize(filename, topics, input_words, num_of_sentences):
# Summarize a file. The length of the summary will be the number of sentences specified.
file = filename
# Extract all the words and sentences and get their respective scores.
all_words = extractor.get_words(file)
word_scores = scoring.get_word_scores(all_words)
all_sentences = extractor.get_sentences(file)
all_sentences = filter.omit_transition_sentences(all_sentences)
all_sentences = topic_sent(all_sentences, topics)
i = 0
complete_summary = []
for all_sentences_part in all_sentences:
num_of_sentences_new = num_of_sentences
sentence_scores_part = scoring.get_sentence_scores_list(
all_sentences_part, word_scores)
all_sentences_part, sentence_scores_part = additional_filter.remove_duplicates(
all_sentences_part, sentence_scores_part)
if num_of_sentences_new > len(all_sentences_part):
#print("The summary cannot be longer than the text.")
num_of_sentences_new = len(all_sentences_part)
# Get x sentences with the highest scores, in chronological order.
threshold = scoring.x_highest_score(sentence_scores_part,
num_of_sentences_new)
top_sentences = scoring.top_sentences(all_sentences_part,
sentence_scores_part, threshold)
# Put the top sentences into one string.
top_sentences = top_sentences[-num_of_sentences_new:]
summary = input_words[i] + ": \n"
i = i + 1
for sentence in top_sentences:
summary += sentence + " "
complete_summary.append(summary + '\n')
return complete_summary
for phrase in transition_phrases:
if lower.startswith(phrase):
return True
return False
def omit_transition_sentences(sentences):
transition_phrases = get_transition_phrases()
result = []
for sentence in sentences:
if not is_transition_phrase(transition_phrases, sentence):
result.append(sentence)
return result
if __name__ == "__main__":
if len(argv) == 2:
transition_phrases = get_transition_phrases()
sentences = extractor.get_sentences(argv[1])
count = 0
for sentence in sentences:
for phrase in transition_phrases:
lower = sentence.lower()
if lower.startswith(phrase):
print("Omitted: " + sentence)
count += 1
break
print("Omitted", count, "sentence(s).")
else:
print_usage()