def test_init_xml_is_ok(self):
text = "<doc/>"
suitable_xml = xml_utils.SuitableXML(text)
self.assertEqual(suitable_xml.content, "<doc/>")
self.assertIsNone(suitable_xml.xml_error)
self.assertEqual(suitable_xml.doctype, '')
self.assertIsNone(suitable_xml.xml_declaration)
def test_write_should_write_corrected_xml_in_dest_file(self):
text = (
'<?xml version="1.0" encoding="utf-8"?>'
'<!DOCTYPE article PUBLIC "-//NLM//DTD JATS (Z39.96) Journal '
'Publishing DTD v1.1 20151215//EN" '
'"https://jats.nlm.nih.gov/publishing/1.1/JATS-journalpublishing1.dtd">'
'<article><p>&lt;</p></article>')
with tempfile.TemporaryDirectory() as xml_dir_path:
in_xml_path = os.path.join(xml_dir_path, "in_xml_doc.xml")
with open(in_xml_path, 'w') as xml_file:
xml_file.write(text)
out_xml_path = os.path.join(xml_dir_path, "out_xml_doc.xml")
suitable_xml = xml_utils.SuitableXML(in_xml_path)
suitable_xml.write(out_xml_path)
out_xml = xml_utils.etree.parse(out_xml_path)
self.assertIsNotNone(out_xml.docinfo)
self.assertEqual(out_xml.docinfo.xml_version, "1.0")
self.assertEqual(out_xml.docinfo.encoding, "UTF-8")
self.assertEqual(
out_xml.docinfo.doctype,
'<!DOCTYPE article PUBLIC "-//NLM//DTD JATS (Z39.96) Journal '
'Publishing DTD v1.1 20151215//EN" '
'"https://jats.nlm.nih.gov/publishing/1.1/JATS-journalpublishing1.dtd">'
)
self.assertEqual(xml_utils.etree.tostring(out_xml.getroot()),
b'<article>\n <p><</p>\n</article>')
self.assertIsNone(suitable_xml.xml_error)
def make_xml(self, scielo_dtd_files, pmc_dtd_files):
sps_xml = self.article.tree
# j1.1/xsl/sgml2xml/xml2pmc.xsl
pmc_xml = xml_utils.transform(sps_xml, scielo_dtd_files.xsl_output)
xml_utils.write(self.pmc_xml_filepath, pmc_xml)
# recarrega
pmc_xml = xml_utils.SuitableXML(self.pmc_xml_filepath)
filenames, changed = self._get_filenames(pmc_xml.xml)
numbers = self._insert_math_id(pmc_xml.xml)
if numbers or changed:
pmc_xml.write(self.pmc_xml_filepath)
dirname = os.path.dirname(self.pmc_xml_filepath)
for old, new in filenames:
old = os.path.join(self.scielo_pkg_files.path, old)
if os.path.isfile(old):
new = os.path.join(dirname, new)
shutil.copyfile(old, new)
else:
logging.info("File not found %s to compose PMC Package %s",
old, self.pmc_xml_filepath)
# j1.1/xsl/sgml2xml/pmc.xsl
result = xml_utils.transform(pmc_xml.xml, pmc_dtd_files.xsl_output)
xml_utils.write(self.pmc_xml_filepath, result)
# validate
xml_validator = sps_xml_validators.PMCXMLValidator(pmc_dtd_files)
xml_validator.validate(self.pmc_xml_filepath,
self.outputs.pmc_dtd_report_filename,
self.outputs.pmc_style_report_filename)
def test_write_should_write_original_content_if_input_is_not_xml(self):
text = "Qualquer texto nao XML."
suitable_xml = xml_utils.SuitableXML(text)
with tempfile.TemporaryDirectory() as xml_dir_path:
xml_path = os.path.join(xml_dir_path, "xml_doc.xml")
suitable_xml.write(xml_path)
with open(xml_path) as xml_file:
self.assertEqual(xml_file.read(), text)
self.assertIsNotNone(suitable_xml.xml_error)
self.assertIn("it must be an XML content or XML file path",
suitable_xml.xml_error)
def __init__(self, src_pkgfiles, acron, dest_path):
self.src_pkgfiles = src_pkgfiles
self.acron = acron
self.dest_path = dest_path
self.xml = xml_utils.SuitableXML(self.src_pkgfiles.filename)
self.new_name = self.xml.xml
self.related_files_copy = []
self.href_replacements = []
self.href_files_copy = []
self.href_names = []
self.missing_href_files = []
def test_well_formed_xml_content_removes_extra_spaces(self):
text = """<doc><p><title>is nunc. Scelerisque in dictum non
consectetur
a erat nam. Ipsum dolor sit amet consectetur\t
adipiscing elit duis tristique sollicitudin. \n
Eu scelerisque felis imperdiet proin fermen</title></p></doc>"""
expected = (
'<doc><p><title>is nunc. Scelerisque in dictum non '
'consectetur a erat nam. Ipsum dolor sit amet consectetur '
'adipiscing elit duis tristique sollicitudin. Eu scelerisque '
'felis imperdiet proin fermen</title></p></doc>')
suitable_xml = xml_utils.SuitableXML(text)
suitable_xml.well_formed_xml_content()
self.assertEqual(expected, suitable_xml.content)
def _insert_xhtml_tables_in_document(self):
for xhtml in self.xml.findall(".//xhtml"):
href = xhtml.get("href")
if not href:
continue
table_file_path = os.path.join(self.src_pkgfiles.path, href)
if not os.path.isfile(table_file_path):
continue
xml_table = xml_utils.SuitableXML(table_file_path)
if not xml_table.xml:
continue
table = xml_table.xml.find(".//table")
if table is not None:
parent = xhtml.getparent()
parent.replace(xhtml, deepcopy(table))
def test_write_should_write_original_content_if_input_is_invalid_xml(self):
text = (
'<?xml version="1.0" encoding="utf-8"?>'
'<!DOCTYPE article PUBLIC "-//NLM//DTD JATS (Z39.96) Journal '
'Publishing DTD v1.1 20151215//EN" '
'"https://jats.nlm.nih.gov/publishing/1.1/JATS-journalpublishing1.dtd">'
'\n<article>'
'<p><ext-link ext-link-type="uri" xlink:href="<link-invalido>">bla</ext-link></p>'
'</article>')
suitable_xml = xml_utils.SuitableXML(text)
with tempfile.TemporaryDirectory() as xml_dir_path:
xml_path = os.path.join(xml_dir_path, "xml_doc.xml")
suitable_xml.write(xml_path)
with open(xml_path) as xml_file:
self.assertEqual(xml_file.read(), text)
self.assertIsNotNone(suitable_xml.xml_error)
self.assertIn("Loading XML from 'str': ", suitable_xml.xml_error)
def test_init_xml_with_no_xml_declaration(self):
text = (
'<!DOCTYPE article PUBLIC "-//NLM//DTD JATS (Z39.96) Journal '
'Publishing DTD v1.1 20151215//EN" '
'"https://jats.nlm.nih.gov/publishing/1.1/JATS-journalpublishing1.dtd">'
'\n<article/> lixo')
suitable_xml = xml_utils.SuitableXML(text)
self.assertIsNone(suitable_xml.xml_declaration)
self.assertEqual(
suitable_xml.doctype,
'<!DOCTYPE article PUBLIC "-//NLM//DTD JATS (Z39.96) Journal '
'Publishing DTD v1.1 20151215//EN" "https://jats.nlm.nih.gov/'
'publishing/1.1/JATS-journalpublishing1.dtd">')
self.assertEqual(
suitable_xml.content,
'<!DOCTYPE article PUBLIC "-//NLM//DTD JATS (Z39.96) Journal '
'Publishing DTD v1.1 20151215//EN" "https://jats.nlm.nih.gov/'
'publishing/1.1/JATS-journalpublishing1.dtd">\n<article/>')
def test_well_formed_xml_content_converts_quot_ent_to_chars(self):
text = '<doc><p><a href="bla">teste</a></p></doc>'
expected = '<doc><p><a href="bla">teste</a></p></doc>'
suitable_xml = xml_utils.SuitableXML(text)
suitable_xml.well_formed_xml_content()
self.assertEqual(expected, suitable_xml.content)
def test_well_formed_xml_content_converts_entities_to_chars(self):
text = '<doc><p>[ç]</p></doc>'
expected = '<doc><p>[ç]</p></doc>'
suitable_xml = xml_utils.SuitableXML(text)
suitable_xml.well_formed_xml_content()
self.assertEqual(expected, suitable_xml.content)
def test_well_formed_xml_content_removes_junk_after_last_close_tag(self):
text = '<doc><p></p></doc> lixo'
expected = '<doc><p/></doc>'
suitable_xml = xml_utils.SuitableXML(text)
suitable_xml.well_formed_xml_content()
self.assertEqual(expected, suitable_xml.content)
def test_content_returns_characteres_instead_their_entities(self):
text = ('<doc><p>[ç]</p> lixo</doc>')
expected = ('<doc><p>[ç]</p> lixo</doc>')
suitable_xml = xml_utils.SuitableXML(text)
self.assertEqual(expected, suitable_xml.content)
def test_init_xml_with_no_doctype(self):
text = '<?xml version="1.0" encoding="utf-8"?><doc/>'
suitable_xml = xml_utils.SuitableXML(text)
self.assertEqual(suitable_xml.xml_declaration,
'<?xml version="1.0" encoding="utf-8"?>')
self.assertEqual(suitable_xml.doctype, '')
def test_init_xml_with_junk_is_loaded_without_errors(self):
text = "<doc/> lixo"
suitable_xml = xml_utils.SuitableXML(text)
self.assertEqual(suitable_xml.content, "<doc/>")
self.assertIsNone(suitable_xml.xml_error)
