def __init__(self, doc_dir):
convertion_style = "-raw"
self._eventextractor = EventExtractor(doc_dir)
parse = Parser(join(ROOT, 'templates', 'periodic.xml'))
self._template_metadata = parse.xml_template_metadata()
page = self._template_metadata['page']
self._preparator = Preparator(doc_dir)
self._raw_onepage_doc = self._preparator.raw_text_convertion(page, page, convertion_style)
self._linetokenized_onepage_doc = line_tokenize(self._raw_onepage_doc)
self._clean_onepage_doc = self._raw_onepage_doc.replace('\n', ' ')
def __init__(self, doc_dir):
convertion_style = ""
parse = Parser(join(ROOT, 'templates', 'event.xml'))
self._template_metadata = parse.xml_template_metadata()
page = self._template_metadata['page']
self._preparator = Preparator(doc_dir)
self._raw_onepage_doc = self._preparator.raw_text_convertion(page, page, convertion_style)
self._linetokenized_onepage_doc = line_tokenize(self._raw_onepage_doc)
self._clean_onepage_doc = self._raw_onepage_doc.replace('\n', ' ')
self._email_regex = re.compile(r'(\w+[.|\w])*@(\w+[.])*\w+')
def __init__(self, doc_dir):
convertion_style = ""
parse = Parser(join(ROOT, 'templates', 'tcc.xml'))
self._template_metadata = parse.xml_template_metadata()
page = self._template_metadata['page']
pages = self._template_metadata['pages']
self._preparator = Preparator(doc_dir)
self._raw_onepage_doc = self._preparator.raw_text_convertion(page, page, convertion_style)
self._raw_variouspages_doc = self._preparator.raw_text_convertion(pages[0], pages[1], convertion_style)
self._linetokenized_onepage_raw_doc = open('%s.txt' %self._preparator.doc_dir).readlines()
self._clean_variouspages_doc = self._raw_variouspages_doc.replace('\n', ' ')
self._linetokenized_onepage_doc = line_tokenize(self._raw_onepage_doc)
self._wordtokenized_onepage_doc = self._preparator.wordtokenized_punctuation_exclusion(self._raw_onepage_doc)
self.linebreak = "\n"
class TestTccExtractor(unittest.TestCase):
def setUp(self):
self.doc_dir = join(ROOT_PATH, 'testdocs', 'obtencaograu', 'doctest1.pdf')
self.preparator = Preparator(self.doc_dir)
self.extractor = TccExtractor(self.doc_dir)
self.parse = Parser('tcc.xml')
self.xml_template_metadata = self.parse.xml_template_metadata()
def test_metadata_extractor_generates_metadata_dict(self):
self.extractor.all_metadata() |should_not| be_empty
def test_tcc_document_has_one_or_more_confirmed_by_corpus_author_type_metadata(self):
len(self.extractor._author_metadata()) |should| be_greater_than_or_equal_to(1)
self.extractor._author_metadata() |should_not| contain('')
self.preparator.remove_converted_document()
def test_tcc_document_has_title_type_metadata(self):
self.extractor._title_metadata() |should_not| equal_to('')
self.preparator.remove_converted_document()
def test_tcc_document_has_a_confirmed_by_corpus_institution_metadata(self):
self.extractor._institution_metadata() |should_not| equal_to('Instituto Federal de Educação Ciência e Tecnologia ')
self.preparator.remove_converted_document()
def test_tcc_document_has_a_confirmed_by_corpus_campus_metadata(self):
self.extractor._campus_metadata() |should_not| equal_to('')
self.preparator.remove_converted_document()
def test_tcc_document_has_an_abstract_metadata_pattern_found_by_regex(self):
doc = self.extractor._clean_variouspages_doc
matches = re.search(r'resumo:* (.*?) palavr(a|as)(.|\s)chav(e|es).', doc)
matches.group() |should| start_with('resumo')
self.extractor._abstract_metadata |should_not| equal_to('')
class TestParser(unittest.TestCase):
def setUp(self):
self.tccParse = Parser(join(TEMPLATE_PATH, 'tcc.xml'))
self.eventParse = Parser(join(TEMPLATE_PATH, 'event.xml'))
def test_parser_receive_a_xml_directory(self):
self.tccParse.file_path and self.eventParse.file_path |should| be_like(r'.*.xml')
def tes_tcc_onepage_metadata_hash_has_valid_keys_and_values(self):
onepage_parser = self.tccParse._onepage_metadata()
"author_residue", "author_breaker", "institution_validator", "campus_validator",
"grade_graduation", "grade_spec", "grade_master_degree", "grade_doctoral"
"grade_postdoctoral" |should| be_into(onepage_parser.keys())
for key in onepage_parser.keys():
onepage_parser.get(key) |should_not| equal_to ([])
def test_event_onepage_metadata_hash_has_valid_keys_and_values(self):
onepage_parser = self.tccParse._onepage_metadata()
"author_breaker", "author_residue", "title_breaker" |should| be_into(onepage_parser.keys())
for key in onepage_parser.keys():
onepage_parser.get(key) |should_not| equal_to ([])
def test_tcc_variouspages_metadata_hash_has_valid_keys_and_values(self):
variouspages_parser = self.tccParse._variouspages_metadata()
"pages" |should| be_into(variouspages_parser.keys())
def test_merge_all_template_metadata_into_one_dict(self):
onepage_metatada = self.tccParse._onepage_metadata()
variouspages_metatada = self.tccParse._variouspages_metadata()
xml_template_metadata = self.tccParse.xml_template_metadata()
xml_template_metadata.keys() |should_not| be_empty
class TestPeriodicExtractor(unittest.TestCase):
def setUp(self):
self.doc_dir = join(ROOT_PATH, "testdocs", "periodic", "1_pt-br.pdf")
self.preparator = Preparator(self.doc_dir)
self.extractor = PeriodicExtractor(self.doc_dir)
self.parse = Parser("periodic.xml")
self.xml_template_metadata = self.parse.xml_template_metadata()
def test_periodic_document_has_author_type_metadata(self):
self.extractor._author_metadata() | should_not | be_empty
def test_event_document_has_an_abstract_metadata_pattern_found_by_regex(self):
doc = self.extractor._clean_onepage_doc
matches = re.search(r"resumo:* (.*?) (palavr(a|as)(.|\s)chav(e|es).|unitermos|descritores)", doc)
matches.group() | should | start_with("resumo")
self.extractor._abstract_metadata | should_not | equal_to("")
class TestPreparation(unittest.TestCase):
def setUp(self):
self.parse = Parser('tcc.xml')
self.doc_dir = join(ROOT_PATH, 'testdocs', 'obtencaograu', 'doctest1.pdf')
self.preparator = Preparator(self.doc_dir)
self.xml_template_metadata = self.parse.xml_template_metadata()
def test_pdf_document_exists(self):
document = basename(self.doc_dir)
documents = listdir(dirname(self.doc_dir))
document |should| be_into (documents)
def test_raw_text_convertion(self):
convertion_style = ""
page = self.xml_template_metadata['page']
self.preparator.raw_text_convertion(page, page, convertion_style)
documents = listdir(dirname(self.doc_dir))
self.preparator.temp_text_doc |should| be_into(documents)
def test_name_corpus_has_a_certain_quantity_of_names(self):
len(self.preparator.parse_corpus('names')) |should| equal_to(6297)
def test_temporary_text_files_are_being_removed(self):
convertion_style = ""
page = self.xml_template_metadata['page']
documents = listdir(dirname(self.doc_dir))
self.preparator.raw_text_convertion(page, page, convertion_style)
self.preparator.temp_text_doc |should| be_into(documents)
self.preparator.remove_converted_document()
documents = listdir(dirname(self.doc_dir))
self.preparator.temp_text_doc |should_not| be_into(documents)
def test_institution_corpus_is_a_list_of_institution_names_with_respective_prepositions(self):
self.preparator.parse_corpus('institution') |should| equal_to([['', 'fluminense'], ['', 'catarinense'],
['', 'baiano'], ['', 'goiano'], ['de ', 'tocantins'], ['do ', 'mato grosso'], ['do ', 'par\xc3\xa1'],
['da ', 'para\xc3\xadba'], ['de ', 'sergipe'], ['do ', 'cear\xc3\xa1'], ['de ', 'roraima'], ['de ', 'alagoas'],
['de ', 'santa catarina'], ['do ', 'sul de minas'], ['do ', 'sul de minas gerais'],
['de ', 's\xc3\xa3o paulo'], ['do ', 'tri\xc3\xa2ngulo mineiro'], ['de ', 'minas gerais'],
['do ', 'sert\xc3\xa3o pernambucano'], ['do ', 'mato grosso do sul'], ['da ', 'bahia'],
['de ', 'rondonia'], ['do ', 'rio grande do sul'], ['do ', 'rio grande do norte'], ['de ', 'bras\xc3\xadlia'],
['do ', 'norte de minas'], ['do ', 'piau\xc3\xad'], ['de ', 'amazonas'], ['do ', 'paran\xc3\xa1'],
['de ', 'amap\xc3\xa1'], ['do ', 'acre'], ['de ', 'maranh\xc3\xa3o'], ['do ', 'rio de janeiro'],
['de ', 'pernambuco'], ['da ', 'bahia'], ['do ', 'esp\xc3\xadrito santo'], ['do ', 'sudeste de minas gerais'],
['de ', 'goi\xc3\xa1s'], ['de ', 'farroupilha'], ['de ', 'goi\xc3\xa1s'], ['de ', 'campinas']])
class TestEventExtractor(unittest.TestCase):
def setUp(self):
self.doc_dir = join(ROOT_PATH, 'testdocs', 'event', '1_pt-br.pdf')
self.preparator = Preparator(self.doc_dir)
self.extractor = EventExtractor(self.doc_dir)
self.parse = Parser('event.xml')
self.xml_template_metadata = self.parse.xml_template_metadata()
def test_metadata_extractor_generates_metadata_dict(self):
self.extractor.all_metadata() |should_not| be_empty
def test_event_document_has_an_abstract_metadata_pattern_found_by_regex(self):
doc = self.extractor._clean_onepage_doc
matches = re.search(r'resumo:* (.*?) (palavr(a|as)(.|\s)chav(e|es).|unitermos|descritores)', doc)
matches.group() |should| start_with('resumo')
self.extractor._abstract_metadata |should_not| equal_to('')
def test_event_document_has_author_type_metadata(self):
self.extractor._author_metadata() |should_not| be_empty
def test_event_document_has_title_type_metadata(self):
self.extractor._title_metadata() |should_not| be_empty
def setUp(self):
self.doc_dir = join(ROOT_PATH, 'testdocs', 'obtencaograu', 'doctest1.pdf')
self.preparator = Preparator(self.doc_dir)
self.extractor = TccExtractor(self.doc_dir)
self.parse = Parser('tcc.xml')
self.xml_template_metadata = self.parse.xml_template_metadata()
def setUp(self):
self.doc_dir = join(ROOT_PATH, 'testdocs', 'periodic', '1_pt-br.pdf')
self.preparator = Preparator(self.doc_dir)
self.extractor = PeriodicExtractor(self.doc_dir)
self.parse = Parser('periodic.xml')
self.xml_template_metadata = self.parse.xml_template_metadata()
def setUp(self):
self.tccParse = Parser(join(TEMPLATE_PATH, 'tcc.xml'))
self.eventParse = Parser(join(TEMPLATE_PATH, 'event.xml'))
def setUp(self):
self.parse = Parser("tcc.xml")
self.doc_dir = join(ROOT_PATH, "testdocs", "obtencaograu", "doctest1.pdf")
self.preparator = Preparator(self.doc_dir)
self.xml_template_metadata = self.parse.xml_template_metadata()
class TestPreparation(unittest.TestCase):
def setUp(self):
self.parse = Parser("tcc.xml")
self.doc_dir = join(ROOT_PATH, "testdocs", "obtencaograu", "doctest1.pdf")
self.preparator = Preparator(self.doc_dir)
self.xml_template_metadata = self.parse.xml_template_metadata()
def test_pdf_document_exists(self):
document = basename(self.doc_dir)
documents = listdir(dirname(self.doc_dir))
document | should | be_into(documents)
def test_raw_text_convertion(self):
convertion_style = ""
page = self.xml_template_metadata["page"]
self.preparator.raw_text_convertion(page, page, convertion_style)
documents = listdir(dirname(self.doc_dir))
self.preparator.temp_text_doc | should | be_into(documents)
def test_name_corpus_has_a_certain_quantity_of_names(self):
len(self.preparator.parse_corpus("names")) | should | equal_to(6297)
def test_temporary_text_files_are_being_removed(self):
convertion_style = ""
page = self.xml_template_metadata["page"]
documents = listdir(dirname(self.doc_dir))
self.preparator.raw_text_convertion(page, page, convertion_style)
self.preparator.temp_text_doc | should | be_into(documents)
self.preparator.remove_converted_document()
documents = listdir(dirname(self.doc_dir))
self.preparator.temp_text_doc | should_not | be_into(documents)
def test_institution_corpus_is_a_list_of_institution_names_with_respective_prepositions(self):
self.preparator.parse_corpus("institution") | should | equal_to(
[
["", "fluminense"],
["", "catarinense"],
["", "baiano"],
["", "goiano"],
["de ", "tocantins"],
["do ", "mato grosso"],
["do ", "par\xc3\xa1"],
["da ", "para\xc3\xadba"],
["de ", "sergipe"],
["do ", "cear\xc3\xa1"],
["de ", "roraima"],
["de ", "alagoas"],
["de ", "santa catarina"],
["do ", "sul de minas"],
["do ", "sul de minas gerais"],
["de ", "s\xc3\xa3o paulo"],
["do ", "tri\xc3\xa2ngulo mineiro"],
["de ", "minas gerais"],
["do ", "sert\xc3\xa3o pernambucano"],
["do ", "mato grosso do sul"],
["da ", "bahia"],
["de ", "rondonia"],
["do ", "rio grande do sul"],
["do ", "rio grande do norte"],
["de ", "bras\xc3\xadlia"],
["do ", "norte de minas"],
["do ", "piau\xc3\xad"],
["de ", "amazonas"],
["do ", "paran\xc3\xa1"],
["de ", "amap\xc3\xa1"],
["do ", "acre"],
["de ", "maranh\xc3\xa3o"],
["do ", "rio de janeiro"],
["de ", "pernambuco"],
["da ", "bahia"],
["do ", "esp\xc3\xadrito santo"],
["do ", "sudeste de minas gerais"],
["de ", "goi\xc3\xa1s"],
["de ", "farroupilha"],
["de ", "goi\xc3\xa1s"],
]
)
def setUp(self):
self.doc_dir = join(ROOT_PATH, "testdocs", "periodic", "1_pt-br.pdf")
self.preparator = Preparator(self.doc_dir)
self.extractor = PeriodicExtractor(self.doc_dir)
self.parse = Parser("periodic.xml")
self.xml_template_metadata = self.parse.xml_template_metadata()
