def preprocessing(): # Get filenames for the thesaurus, the latin text, and greek text thesaurus_filename, Latin_filename, Greek_filename = xls.get_whole_text_comparison_Args() # Read the thesaurus CSV file into a dicitonary object for easy access transDict = ths.build_thesaurus(thesaurus_filename) # Read both the latin text and greek text into a dictionary for easy access Latin_word_num, Latin_search_dict, Latin_text = xls.build_search_dictionary(Latin_filename, "Latin", True) Greek_word_num, Greek_search_dict, Greek_text = xls.build_search_dictionary = (Greek_filename, "Greek", True) return Latin_word_num, Latin_search_dict, Latin_text, Greek_word_num, Greek_search_dict, Greek_text
def preprocessing():
latin_cltk_importer = CorpusImporter('latin')
latin_cltk_importer.import_corpus('latin_models_cltk')
greek_cltk_importer = CorpusImporter('greek')
greek_cltk_importer.import_corpus('greek_models_cltk')
# Get filenames for the thesaurus, the latin text, and greek text
thesaurus_filename, Greek_filename = xls.get_search_by_phrase_Args()
# Read the thesaurus CSV file into a dicitonary object for easy access
transDict = ths.build_thesaurus(thesaurus_filename)
# Read greek text into a dictionary for easy access
Greek_word_num, Greek_search_dict, Greek_text = xls.build_search_dictionary(Greek_filename, "Greek", True)
return transDict, Greek_word_num, Greek_search_dict, Greek_text
def test_build_search_dict(curr_test, filename, words_in_file , language, lemmatized_version = False):
word_num, search_dict, indexed_corpus = xls.build_search_dictionary(filename, language ,lemmatized_version)
if not (word_num == words_in_file):
curr_test.passed = False
curr_test.errors.append("Wrong number of words added (only " + str(word_num) + " out of " + str(words_in_file) + " words added) ")
test_file = open(filename,'r')
i = 0
curr_word = ""
while 1:
char = test_file.read(1)
if not (re.sub("[\p{Z}\t\r\n\v\f\s]", "", char) == ""):
curr_word += char
else:
curr_word = normalize_word(curr_word)
if not (curr_word == ""):
if curr_word in search_dict:
if not( i in search_dict[curr_word]):
curr_test.passed = False
error_message = curr_word + " did not have the proper index in the search dict"
error_message += "\n\t\t\t word number: " +str(i) + " Indices: " + str(search_dict[curr_word])
curr_test.errors.append(error_message)
else:
curr_test.passed = False
error_message = curr_word + " was not found in the search dict"
curr_test.errors.append(error_message)
i += 1
curr_word = ""
if char == None or char == "":
break
test_file.close()
return curr_test
def process_corpus(self, filename, language, make_IndexedText=True, use_lemmatized_text=False): self.corpus_ready = False self.word_num, self.search_dict, self.indexed_corpus = xls.build_search_dictionary(filename, language, use_lemmatized_text) self.corpus_ready = True
