def return_citation_array(self):
"""Goes through the parsed text and extracts citations
returns the results in a list
Returns:
citation_list (list): A list containing the extracted citations
"""
f = open(self.path, "r")
if not self.__has_file_been_read__():
list_of_citations = []
with open(self.path, 'r') as file:
for string in self.__nonblank_lines__(file):
match = re.search(self.regex, string)
if match.group(1) is None:
list_of_citations.append(CitationObj(
match.group(4), [], "", self.path))
else:
list_of_authors = [match.group(1)]
list_of_citations.append(CitationObj(match.group(
2), list_of_authors, match.group(3), self.path))
self.analyzed_files.append(self.path)
return list_of_citations
else:
print("File already analyzed")
def test_correct_getters(self):
"""[Ensure getters functioning as intended]
"""
test_citation = CitationObj("", "", "", "")
self.assertEqual("", test_citation.get_author())
self.assertEqual("", test_citation.get_journal())
self.assertEqual("", test_citation.get_title())
def test_correct_convert_to_dict(self):
"""Ensure that the convert to dict functon is returning the fields as
expected
"""
test_citation = CitationObj("", "", "", "")
dict = test_citation.convert_to_dict()
self.assertEqual(5, len(dict))
class TestCitationAnalyzer(unittest.TestCase):
dictOfKeywords = {"Test": ["a "], "Test2": ["i "]}
arrayOfCitations = [
CitationObj("a title", "a author", "a journal", "a id"),
CitationObj("i title", ["i author", "ii author"], "i journal", "i id")
]
def test_that_results_are_expected(self):
analyzer = CitationAnalyzer(self.arrayOfCitations, self.dictOfKeywords)
self.assertEqual(
analyzer.return_dict_of_assigned_citations_classifications()
["Test"].__getitem__(0).get_title(), "a title")
self.assertEqual(
analyzer.return_dict_of_assigned_citations_classifications()
["Test2"].__getitem__(0).get_title(), "i title")
def return_citation_dictionary(self):
if not self.__has_file_been_read__():
list_of_citations = []
with open(self.path, 'r') as file:
for string in self.__nonblank_lines__(file):
match = re.search(self.regex, string)
if match.group(1) is None:
list_of_citations.append(CitationObj(
match.group(4), [], "", self.path))
self.analyzed_files.append(self.path)
else:
list_of_authors = [match.group(1)]
list_of_citations.append(CitationObj(match.group(
2), list_of_authors, match.group(3), self.path))
self.analyzed_files.append(self.path)
citation_dict = {"Citations": list_of_citations}
self.analyzed_files.append(self.path)
return citation_dict
else:
print("File already analyzed")
def load_from_file_to_array(file_path):
"""Loads saved Json citations to array
Args:
file_path (String): The path to the json file to be loaded
Returns:
list_of_citations (list): A list of citations
"""
list_of_citations = []
with open(file_path, 'r') as file:
for string in file:
cit_dict = json.loads(string)
for id_list in cit_dict.values():
for citation in id_list:
title = citation.pop("title")
journal = citation.pop("journal")
author = citation.pop("author")
id = citation.pop("id")
classification = citation.pop("classification")
temp_citation = CitationObj(title, author, journal, id)
temp_citation.set_classification(classification)
list_of_citations.append(temp_citation)
return list_of_citations
def return_citation_array(self):
"""Goes through the parsed text and extracts citations
returns the results in a list
Returns:
citation_list (list): A list containing the extracted citations
"""
if not self.__has_file_been_read__():
citation_list = []
with open(self.path, 'r') as file:
for string in file:
json_string = json.loads(string)
authors = self.__get_authors_names__(json_string)
journal = self.__get_journals_name__(json_string)
citation_list.append(CitationObj(
json_string.get('title'), authors, journal, self.path))
self.analysed_files.append(self.path)
return citation_list
else:
print("File already analyzed")
def return_citation_array(self):
"""Returns a list of all matches to the regex if present
Returns:
list_of_citation_objects (list): A list of all matches to the
regex
"""
if not self.__has_file_been_read__():
list_of_citation_objects = []
docx_text = self.get_document_text()
citation_regex = self.__get_citation_regex__()
citation_data = re.findall(citation_regex, docx_text)
for citation in citation_data:
list_of_citation_objects.append(CitationObj(
citation[1], citation[0], citation[2], self.file_path))
self.analysed_files.append(self.file_path)
return list_of_citation_objects
else:
print("File already analysed")
def return_citation_array(self):
"""Goes through the parsed text and extracts citations
returns the results in a list
Returns:
citation_list (list): A list containing the extracted citations
"""
if not self.__has_file_been_read__():
list_of_citation_objects = []
pdf_text = self.__get_pdf_text__()
citation_regex = self.__get_citation_regex__()
citation_data = re.findall(citation_regex, pdf_text)
for citation in citation_data:
list_of_citation_objects.append(
CitationObj(citation[1], citation[0], citation[2],
self.file_path))
self.analyzed_files.append(self.file_path)
return list_of_citation_objects
else:
print("File already analyzed")
def return_citation_array(self):
"""Goes through the parsed text and extracts the citations based
on the regex.
Returns:
citation_list (list): The results of the extracted citations
"""
if not self.__has_file_been_read__():
with open(self.path) as bibtex_file:
bib_database = bibtexparser.load(bibtex_file)
bib_dict = bib_database.get_entry_dict()
citation_list = []
for key, item in bib_dict.items():
authors = self.__split_authors__(item.get('author'))
citation_list.append(CitationObj(
item.get('title'), authors, item.get('journal'),
self.path))
self.analyzedFiles.append(self.path)
return citation_list
else:
print("File already analyzed")
def return_complete_dict(self):
"""Returns a dictionary of all terms defined in the config file
Returns:
citation_dict (dictionary): A dictionary of all terms defined in
the config file
"""
list_of_citation_objects = []
pdf_text = self.__get_pdf_text__()
citation_regex = self.__get_citation_regex__()
url_regex = self.__get_url_regex__()
doi_regex = self.__get_doi_regex__()
citation_data = re.findall(citation_regex, pdf_text)
list_of_urls = re.findall(url_regex, pdf_text)
list_of_dois = re.findall(doi_regex, pdf_text)
for citation in citation_data:
list_of_citation_objects.append(
CitationObj(citation[1], citation[0], citation[2]))
citation_dict = {
"IEEE": list_of_citation_objects,
"URLS": list_of_urls,
"DOIS": list_of_dois
}
return citation_dict
def test_correct_default_assignment(self):
"""Ensures that assignment starts as unsigned
"""
test_citation = CitationObj("", "", "", "")
self.assertEqual("Unassigned", test_citation.get_classification())
def test_changing_assignment(self):
"""Ensures change assignment works
"""
test_citation = CitationObj("", "", "", "")
test_citation.set_classification("Trial")
self.assertEqual("Trial", test_citation.get_classification())