def test_name_tree(self):
XML = etree.tostring(etree.parse(
'data/input/single_source_no_names.phyml', parser),
pretty_print=True)
xml_root = _parse_xml(XML)
source_tree_element = xml_root.xpath(
'/phylo_storage/sources/source/source_tree')[0]
tree_name = create_tree_name(XML, source_tree_element)
self.assert_(tree_name == 'Hill_2011_1')
def testSingleYear(self):
XML = etree.tostring(etree.parse('data/input/sub_taxa.phyml',parser),pretty_print=True)
searchTerms = {'years':[2011]}
new_XML = create_subset(XML,searchTerms) #these data are all 2011
root = _parse_xml(new_XML)
find = etree.XPath("//year")
yrs = find(root)
for y in yrs:
self.assert_(int(y.xpath('integer_value')[0].text) == 2011)
def testRealDataCharMorphOrMol(self):
XML = etree.tostring(etree.parse('data/input/old_stk_input.phyml',parser),pretty_print=True)
searchTerms = {'character_types':["morphological","molecular"]}
new_XML = create_subset(XML,searchTerms,andSearch=False)
root = _parse_xml(new_XML)
srcs = root.findall(".//source")
names = []
for s in srcs:
names.append(s.attrib['name'])
names.sort()
expected_names = ["Aleixo_2002","Aliabadian_etal_2007","Allende_etal_2001","Andersson_1999a","Aragon_etal_1999","Baker_Strauch_1988","Baker_etal_2005","Baker_etal_2006","Baker_etal_2007a","Baker_etal_2007b","Baptista_Visser_1999","Barber_Peterson_2004","Barhoum_Burns_2002","Bertelli_etal_2006"]
self.assertListEqual(expected_names,names)
def testRealDataAllFossil(self):
XML = etree.tostring(etree.parse('data/input/old_stk_input.phyml',parser),pretty_print=True)
searchTerms = {'fossil':"all_fossil"}
new_XML = create_subset(XML,searchTerms)
root = _parse_xml(new_XML)
srcs = root.findall(".//source")
names = []
for s in srcs:
names.append(s.attrib['name'])
names.sort()
expected_names = ["Baker_etal_2005"]
self.assertListEqual(expected_names,names)
src_trs = root.findall(".//source_tree")
self.assert_(len(src_trs) == 1)
def testRealDataCharTaxonYearEmpty(self):
XML = etree.tostring(etree.parse('data/input/old_stk_input.phyml',parser),pretty_print=True)
searchTerms = {'taxa':["Gallus gallus"], 'years':['2009']}
new_XML = create_subset(XML,searchTerms)
root = _parse_xml(new_XML)
srcs = root.findall(".//source")
names = []
for s in srcs:
names.append(s.attrib['name'])
names.sort()
expected_names = []
self.assertListEqual(expected_names,names)
src_trs = root.findall(".//source_tree")
self.assert_(len(src_trs) == 0)
def testRealDataCharMorphMol(self):
XML = etree.tostring(etree.parse('data/input/old_stk_input.phyml',parser),pretty_print=True)
searchTerms = {'character_types':["morphological","molecular"]}
new_XML = create_subset(XML,searchTerms)
root = _parse_xml(new_XML)
srcs = root.findall(".//source")
names = []
for s in srcs:
names.append(s.attrib['name'])
names.sort()
expected_names = ["Bertelli_etal_2006"]
self.assertListEqual(expected_names,names)
src_trs = root.findall(".//source_tree")
self.assert_(len(src_trs) == 1)
def testRealDataCharCytb(self):
XML = etree.tostring(etree.parse('data/input/old_stk_input.phyml',parser),pretty_print=True)
searchTerms = {'characters':["cytb"]}
new_XML = create_subset(XML,searchTerms)
root = _parse_xml(new_XML)
srcs = root.findall(".//source")
names = []
for s in srcs:
names.append(s.attrib['name'])
names.sort()
expected_names = ["Aleixo_2002","Allende_etal_2001","Aragon_etal_1999","Baker_etal_2005","Baker_etal_2006","Baker_etal_2007a",
"Baker_etal_2007b","Barhoum_Burns_2002"]
self.assertListEqual(expected_names,names)
# and two source trees too
src_trs = root.findall(".//source_tree")
self.assert_(len(src_trs) == 9)
def testRealDataCharType(self):
XML = etree.tostring(etree.parse('data/input/old_stk_input.phyml',parser),pretty_print=True)
searchTerms = {'character_types':["morphological"]}
new_XML = create_subset(XML,searchTerms)
root = _parse_xml(new_XML)
find = etree.XPath("//character")
srcs = root.findall(".//source")
names = []
for s in srcs:
names.append(s.attrib['name'])
names.sort()
expected_names = ["Aliabadian_etal_2007","Andersson_1999a","Baptista_Visser_1999","Bertelli_etal_2006"]
self.assertListEqual(expected_names,names)
# and two source trees too
src_trs = root.findall(".//source_tree")
self.assert_(len(src_trs) == 7)
def test_sort_data(self):
XML = etree.tostring(etree.parse('data/input/create_matrix.phyml',
parser),
pretty_print=True)
xml_root = _parse_xml(XML)
xml_root = _sort_data(xml_root)
# By getting source, we can then loop over each source_tree
# within that source and construct a unique name
find = etree.XPath("//source")
sources = find(xml_root)
names = []
for s in sources:
# for each source, get source name
names.append(s.attrib['name'])
expected_names = ['Davis_2011', 'Hill_2011', 'Hill_Davis_2011']
self.assertListEqual(names, expected_names)
def testRealDataYears(self):
XML = etree.tostring(etree.parse('data/input/old_stk_input.phyml',parser),pretty_print=True)
searchTerms = {'years':[1999]}
new_XML = create_subset(XML,searchTerms)
root = _parse_xml(new_XML)
find = etree.XPath("//year")
yrs = find(root)
i = 0
for y in yrs:
self.assert_(int(y.xpath('integer_value')[0].text) == 1999)
i+=1
self.assert_(i==4)
srcs = root.findall(".//source")
names = []
for s in srcs:
names.append(s.attrib['name'])
names.sort()
expected_names = ["Andersson_1999a","Andersson_1999b","Aragon_etal_1999","Baptista_Visser_1999"]
self.assertListEqual(expected_names,names)
def testCharType(self):
XML = etree.tostring(etree.parse('data/input/create_matrix.phyml',parser),pretty_print=True)
searchTerms = {'character_types':["molecular"]}
new_XML = create_subset(XML,searchTerms)
root = _parse_xml(new_XML)
find = etree.XPath("//character")
chrs = find(root)
i = 0
for c in chrs:
self.assert_(c.attrib['type'] == "molecular")
i+=1
self.assert_(i==2)
srcs = root.findall(".//source")
names = []
for s in srcs:
names.append(s.attrib['name'])
names.sort()
expected_names = ["Davis_2011","Hill_2011"]
self.assertListEqual(expected_names,names)
# and two source trees too
src_trs = root.findall(".//source_tree")
self.assert_(len(src_trs) == 2)
def test_add_weights(self):
"""Add weights to a bunch of trees"""
XML = etree.tostring(etree.parse('data/input/check_data_ind.phyml',
parser),
pretty_print=True)
# see above
expected_idents = [[
'Hill_Davis_2011_2', 'Hill_Davis_2011_1', 'Hill_Davis_2011_3'
], ['Hill_Davis_2013_1', 'Hill_Davis_2013_2']]
# so the first should end up with a weight of 0.33333 and the second with 0.5
for ei in expected_idents:
weight = 1.0 / float(len(ei))
XML = add_weights(XML, ei, weight)
expected_weights = [
str(1.0 / 3.0),
str(1.0 / 3.0),
str(1.0 / 3.0),
str(0.5),
str(0.5)
]
weights_in_xml = []
# now check weights have been added to the correct part of the tree
xml_root = _parse_xml(XML)
i = 0
for ei in expected_idents:
for tree in ei:
find = etree.XPath("//source_tree")
trees = find(xml_root)
for t in trees:
if t.attrib['name'] == tree:
# check len(trees) == 0
weights_in_xml.append(
t.xpath("tree/weight/real_value")[0].text)
self.assertListEqual(expected_weights, weights_in_xml)
def test_import_data(self):
# Our validator object
validator = SchemaValidator(rootDir="data")
phyml = import_old_data('data/input/old_stk_test/', verbose=False)
temp_file_handle, temp_file = tempfile.mkstemp(suffix=".phyml")
f = open(temp_file, "w")
f.write(phyml)
f.close()
validator.ValidateOptionFile(
os.path.join("../../../schema", "phylo_storage.rng"), temp_file)
passes = validator.Passes()
optionErrors = validator.OptionErrors()
validator.Reset()
failures = []
for phyml_file in optionErrors:
# We expect there to be missing taxon elements in the XML
# as the user must fill these in, so check missing attributes, etc OK
# and skip the missing element
added_eles = optionErrors[phyml_file][1]
for err in added_eles:
if (err ==
"/phylo_storage/sources/source/source_tree/taxa_data/mixed_fossil_and_extant/taxon"
and len(optionErrors[phyml_file][0]) +
len(optionErrors[phyml_file][2]) +
len(optionErrors[phyml_file][3]) == 0):
continue
if (err ==
"/phylo_storage/sources/source/source_tree/tree/topology"
and len(optionErrors[phyml_file][0]) +
len(optionErrors[phyml_file][2]) +
len(optionErrors[phyml_file][3]) == 0):
continue
failures.append(phyml_file)
if (len(failures) > 0):
print failures
self.assert_(len(failures) == 0)
os.remove(temp_file)
# parse XML and check various things
XML = _parse_xml(phyml)
name = XML.xpath('/phylo_storage/project_name/string_value')[0].text
self.assert_(name == "old_stk_test")
# check numebr of souces
find = etree.XPath('//source')
sources = find(XML)
self.assert_(len(sources) == 15)
# check names of sources:
expected_names = [
'Allende_etal_2001', 'Andersson_1999b', 'Baker_etal_2006',
'Aleixo_2002', 'Bertelli_etal_2006', 'Baker_etal_2007b',
'Aragon_etal_1999', 'Baker_etal_2007a', 'Aliabadian_etal_2007',
'Baker_Strauch_1988', 'Barhoum_Burns_2002', 'Barber_etal_2004',
'Baker_etal_2005', 'Andersson_1999a', 'Baptista_etal_1999'
]
for s in sources:
name = s.attrib['name']
self.assert_(name in expected_names)
if name == "Bertelli_etal_2006":
# this source publication has three trees, let's check that is the case!
find = etree.XPath('source_tree')
trees = find(s)
self.assert_(len(trees) == 3)
if name == "Baptista_etal_1999":
volume = s.xpath(
'.//bibliographic_information/article/volume/string_value'
)[0].text
self.assert_(volume == "140")
