class TextXMLFolderResolver(TestCase):
""" Ensure working state of resolver """
def setUp(self):
get_graph().remove((None, None, None))
self.resolver = CtsCapitainsLocalResolver(["./tests/testing_data/latinLit2"])
def test_getPassage_full(self):
""" Test that we can get a full text """
passage = self.resolver.getTextualNode("urn:cts:latinLit:phi1294.phi002.perseus-lat2")
self.assertIsInstance(
passage, PrototypeCtsPassage,
"GetPassage should always return passages objects"
)
children = passage.getReffs()
# We check the passage is able to perform further requests and is well instantiated
self.assertEqual(
children[0], CtsReference('1'),
"Resource should be string identifiers"
)
self.assertIn(
"Hic est quem legis ille, quem requiris,", passage.export(output=Mimetypes.PLAINTEXT),
"Export CtsTextMetadata should work correctly"
)
self.assertEqual(
passage.export(
output=Mimetypes.PYTHON.ETREE
).xpath(
".//tei:div[@n='1']/tei:div[@n='1']/tei:l[@n='1']/text()", namespaces=XPATH_NAMESPACES, magic_string=False
),
["Hic est quem legis ille, quem requiris, "],
"Export to Etree should give an Etree or Etree like object"
)
def test_getPassage_no_canonical(self):
""" Test that we can get a subreference text passage where no canonical exists"""
passage = self.resolver.getTextualNode("urn:cts:latinLit:phi0959.phi010.perseus-eng2", "2")
self.assertEqual(
passage.export(Mimetypes.PLAINTEXT), "Omne fuit Musae carmen inerme meae; ",
"CapitainsCtsPassage should resolve if directly asked"
)
with self.assertRaises(UnknownObjectError):
passage = self.resolver.getTextualNode("urn:cts:latinLit:phi0959.phi010", "2")
with self.assertRaises(InvalidURN):
passage = self.resolver.getTextualNode("urn:cts:latinLit:phi0959", "2")
def test_getPassage_subreference(self):
""" Test that we can get a subreference text passage"""
passage = self.resolver.getTextualNode("urn:cts:latinLit:phi1294.phi002.perseus-lat2", "1.1")
# We check we made a reroute to GetPassage request
self.assertIsInstance(
passage, PrototypeCtsPassage,
"GetPassage should always return passages objects"
)
children = list(passage.getReffs())
self.assertEqual(
str(children[0]), '1.1.1',
"Resource should be string identifiers"
)
self.assertIn(
"Hic est quem legis ille, quem requiris,", passage.export(output=Mimetypes.PLAINTEXT),
"Export CtsTextMetadata should work correctly"
)
canonical = self.resolver.getTextualNode("urn:cts:latinLit:phi1294.phi002", "1.1")
self.assertEqual(
passage.export(output=Mimetypes.PLAINTEXT),
canonical.export(output=Mimetypes.PLAINTEXT),
"Canonical text should work"
)
self.assertEqual(
passage.export(output=Mimetypes.PYTHON.ETREE).xpath(".//tei:l[@n='1']/text()", namespaces=XPATH_NAMESPACES, magic_string=False),
["Hic est quem legis ille, quem requiris, "],
"Export to Etree should give an Etree or Etree like object"
)
def test_getPassage_full_metadata(self):
""" Test that we can get a full text with its metadata"""
passage = self.resolver.getTextualNode("urn:cts:latinLit:phi1294.phi002.perseus-lat2", metadata=True)
self.assertIsInstance(
passage, PrototypeCtsPassage,
"GetPassage should always return passages objects"
)
self.assertEqual(
str(passage.metadata[RDF_NAMESPACES.CTS.term("title"), "eng"]), "Epigrammata",
"Local Inventory Files should be parsed and aggregated correctly"
)
self.assertEqual(
str(passage.metadata[RDF_NAMESPACES.CTS.term("groupname"), "eng"]), "Martial",
"Local Inventory Files should be parsed and aggregated correctly"
)
self.assertEqual(
str(passage.metadata[RDF_NAMESPACES.CTS.term("label"), "eng"]), "Epigrams",
"Local Inventory Files should be parsed and aggregated correctly"
)
self.assertEqual(
str(passage.metadata[RDF_NAMESPACES.CTS.term("description"), "eng"]),
"M. Valerii Martialis Epigrammaton libri / recognovit W. Heraeus",
"Local Inventory Files should be parsed and aggregated correctly"
)
self.assertEqual(
passage.citation.name, "book",
"Local Inventory Files should be parsed and aggregated correctly"
)
self.assertEqual(
len(passage.citation), 3,
"Local Inventory Files should be parsed and aggregated correctly"
)
children = list(passage.getReffs(level=3))
# We check the passage is able to perform further requests and is well instantiated
self.assertEqual(
children[0], CtsReference('1.pr.1'),
"Resource should be string identifiers"
)
self.assertIn(
"Hic est quem legis ille, quem requiris,", passage.export(output=Mimetypes.PLAINTEXT),
"Export CtsTextMetadata should work correctly"
)
self.assertEqual(
passage.export(
output=Mimetypes.PYTHON.ETREE
).xpath(
".//tei:div[@n='1']/tei:div[@n='1']/tei:l[@n='1']/text()", namespaces=XPATH_NAMESPACES, magic_string=False
),
["Hic est quem legis ille, quem requiris, "],
"Export to Etree should give an Etree or Etree like object"
)
def test_getPassage_prevnext(self):
""" Test that we can get a full text with its metadata"""
passage = self.resolver.getTextualNode(
"urn:cts:latinLit:phi1294.phi002.perseus-lat2", subreference="1.1", metadata=True
)
self.assertIsInstance(
passage, PrototypeCtsPassage,
"GetPassage should always return passages objects"
)
self.assertEqual(
passage.prevId, CtsReference("1.pr"),
"Previous CapitainsCtsPassage ID should be parsed"
)
self.assertEqual(
passage.nextId, CtsReference("1.2"),
"Next CapitainsCtsPassage ID should be parsed"
)
children = list(passage.getReffs())
# Ensure navigability
self.assertIn(
"verentia ludant; quae adeo antiquis auctoribus defuit, ut",
passage.prev.export(output=Mimetypes.PLAINTEXT),
"Left and Right Navigation should be available"
)
self.assertIn(
"Qui tecum cupis esse meos ubicumque libellos ",
passage.next.export(output=Mimetypes.PLAINTEXT),
"Left and Right Navigation should be available"
)
# We check the passage is able to perform further requests and is well instantiated
self.assertEqual(
str(children[0]), '1.1.1',
"Resource should be string identifiers"
)
self.assertIn(
"Hic est quem legis ille, quem requiris,", passage.export(output=Mimetypes.PLAINTEXT),
"Export CtsTextMetadata should work correctly"
)
self.assertEqual(
passage.export(output=Mimetypes.PYTHON.ETREE).xpath(".//tei:l[@n='1']/text()", namespaces=XPATH_NAMESPACES, magic_string=False),
["Hic est quem legis ille, quem requiris, "],
"Export to Etree should give an Etree or Etree like object"
)
def test_getPassage_metadata_prevnext(self):
""" Test that we can get a full text with its metadata"""
passage = self.resolver.getTextualNode(
"urn:cts:latinLit:phi1294.phi002.perseus-lat2", subreference="1.1", metadata=True, prevnext=True
)
self.assertIsInstance(
passage, PrototypeCtsPassage,
"GetPassage should always return passages objects"
)
self.assertEqual(
str(passage.metadata[RDF_NAMESPACES.CTS.term("title"), "eng"]), "Epigrammata",
"Local Inventory Files should be parsed and aggregated correctly"
)
self.assertEqual(
str(passage.metadata[RDF_NAMESPACES.CTS.term("groupname"), "eng"]), "Martial",
"Local Inventory Files should be parsed and aggregated correctly"
)
self.assertEqual(
str(passage.metadata[RDF_NAMESPACES.CTS.term("label"), "eng"]), "Epigrams",
"Local Inventory Files should be parsed and aggregated correctly"
)
self.assertEqual(
str(passage.metadata[RDF_NAMESPACES.CTS.term("description"), "eng"]),
"M. Valerii Martialis Epigrammaton libri / recognovit W. Heraeus",
"Local Inventory Files should be parsed and aggregated correctly"
)
self.assertEqual(
passage.citation.name, "poem",
"Local Inventory Files should be parsed and aggregated correctly"
)
self.assertEqual(
passage.citation.root.name, "book",
"Local Inventory Files should be parsed and aggregated correctly"
)
self.assertEqual(
len(passage.citation.root), 3,
"Local Inventory Files should be parsed and aggregated correctly"
)
self.assertEqual(
passage.prevId, CtsReference("1.pr"),
"Previous CapitainsCtsPassage ID should be parsed"
)
self.assertEqual(
passage.nextId, CtsReference("1.2"),
"Next CapitainsCtsPassage ID should be parsed"
)
children = list(passage.getReffs())
# Ensure navigability
self.assertIn(
"verentia ludant; quae adeo antiquis auctoribus defuit, ut",
passage.prev.export(output=Mimetypes.PLAINTEXT),
"Left and Right Navigation should be available"
)
self.assertIn(
"Qui tecum cupis esse meos ubicumque libellos ",
passage.next.export(output=Mimetypes.PLAINTEXT),
"Left and Right Navigation should be available"
)
# We check the passage is able to perform further requests and is well instantiated
self.assertEqual(
str(children[0]), '1.1.1',
"Resource should be string identifiers"
)
self.assertIn(
"Hic est quem legis ille, quem requiris,", passage.export(output=Mimetypes.PLAINTEXT),
"Export CtsTextMetadata should work correctly"
)
self.assertEqual(
passage.export(output=Mimetypes.PYTHON.ETREE).xpath(".//tei:l[@n='1']/text()", namespaces=XPATH_NAMESPACES, magic_string=False),
["Hic est quem legis ille, quem requiris, "],
"Export to Etree should give an Etree or Etree like object"
)
def test_getMetadata_full(self):
""" Checks retrieval of Metadata information """
metadata = self.resolver.getMetadata()
self.assertIsInstance(
metadata, Collection,
"Resolver should return a collection object"
)
self.assertIsInstance(
metadata.members[0], Collection,
"Members of Inventory should be TextGroups"
)
self.assertEqual(
len(metadata.descendants), 44,
"There should be as many descendants as there is edition, translation, commentary, works and textgroup + 1 "
"for default inventory"
)
self.assertEqual(
len(metadata.readableDescendants), 26,
"There should be as many readable descendants as there is edition, translation, commentary (26 ed+tr+cm)"
)
self.assertEqual(
len([x for x in metadata.readableDescendants if isinstance(x, TextMetadata)]), 26,
"There should be 24 editions + 1 translation + 1 commentary in readableDescendants"
)
self.assertEqual(
len(metadata.export(output=Mimetypes.PYTHON.ETREE).xpath(
"//ti:edition[@urn='urn:cts:latinLit:phi1294.phi002.perseus-lat2']", namespaces=XPATH_NAMESPACES)), 1,
"There should be one node in exported format corresponding to lat2"
)
self.assertCountEqual(
[x["@id"] for x in metadata.export(output=Mimetypes.JSON.DTS.Std)["member"]],
["urn:cts:latinLit:phi1294", "urn:cts:latinLit:phi0959",
"urn:cts:greekLit:tlg0003", "urn:cts:latinLit:phi1276"],
"There should be 4 Members in DTS JSON"
)
def test_getMetadata_subset(self):
""" Checks retrieval of Metadata information """
metadata = self.resolver.getMetadata(objectId="urn:cts:latinLit:phi1294.phi002")
self.assertIsInstance(
metadata, Collection,
"Resolver should return a collection object"
)
self.assertIsInstance(
metadata.members[0], TextMetadata,
"Members of CtsWorkMetadata should be Texts"
)
self.assertEqual(
len(metadata.descendants), 2,
"There should be as many descendants as there is edition, translation, commentary"
)
self.assertEqual(
len(metadata.readableDescendants), 2,
"There should be 1 edition + 1 commentary in readableDescendants"
)
self.assertEqual(
len([x for x in metadata.readableDescendants if isinstance(x, TextMetadata)]), 2,
"There should be 1 edition + 1 commentary in readableDescendants"
)
self.assertIsInstance(
metadata.parent, CtsTextgroupMetadata,
"First parent should be CtsTextgroupMetadata"
)
self.assertIsInstance(
metadata.parents[0], CtsTextgroupMetadata,
"First parent should be CtsTextgroupMetadata"
)
self.assertEqual(
len(metadata.export(output=Mimetypes.PYTHON.ETREE).xpath(
"//ti:edition[@urn='urn:cts:latinLit:phi1294.phi002.perseus-lat2']", namespaces=XPATH_NAMESPACES)), 1,
"There should be one node in exported format corresponding to lat2"
)
self.assertCountEqual(
[x["@id"] for x in metadata.export(output=Mimetypes.JSON.DTS.Std)["member"]],
["urn:cts:latinLit:phi1294.phi002.opp-eng3", "urn:cts:latinLit:phi1294.phi002.perseus-lat2"],
"There should be two members in DTS JSON"
)
tr = self.resolver.getMetadata(objectId="urn:cts:greekLit:tlg0003.tlg001.opp-fre1")
self.assertIsInstance(
tr, CtsTranslationMetadata, "Metadata should be translation"
)
self.assertEqual(
tr.lang, "fre", "Language is French"
)
self.assertIn(
"Histoire de la Guerre du Péloponnése",
tr.get_description("eng"),
"Description should be the right one"
)
cm = self.resolver.getMetadata(objectId="urn:cts:latinLit:phi1294.phi002.opp-eng3")
self.assertIsInstance(
cm, CtsCommentaryMetadata, "Metadata should be commentary"
)
self.assertEqual(
cm.lang, "eng", "Language is English"
)
self.assertIn(
"Introduction to Martial's Epigrammata",
cm.get_description("eng"),
"Description should be the right one"
)
def test_getSiblings(self):
""" Ensure getSiblings works well """
previous, nextious = self.resolver.getSiblings(
textId="urn:cts:latinLit:phi1294.phi002.perseus-lat2", subreference="1.1"
)
self.assertEqual(
previous, CtsReference("1.pr"),
"Previous reference should be well computed"
)
self.assertEqual(
nextious, CtsReference("1.2"),
"Next reference should be well computed"
)
def test_getSiblings_nextOnly(self):
""" Ensure getSiblings works well when there is only the next passage"""
previous, nextious = self.resolver.getSiblings(
textId="urn:cts:latinLit:phi1294.phi002.perseus-lat2", subreference="1.pr"
)
self.assertEqual(
previous, None,
"Previous reference should not exist"
)
self.assertEqual(
nextious, CtsReference("1.1"),
"Next reference should be well computed"
)
def test_getSiblings_prevOnly(self):
""" Ensure getSiblings works well when there is only the previous passage"""
previous, nextious = self.resolver.getSiblings(
textId="urn:cts:latinLit:phi1294.phi002.perseus-lat2", subreference="14.223"
)
self.assertEqual(
previous, CtsReference("14.222"),
"Previous reference should be well computed"
)
self.assertEqual(
nextious, None,
"Next reference should not exist"
)
def test_getReffs_full(self):
""" Ensure getReffs works well """
reffs = self.resolver.getReffs(textId="urn:cts:latinLit:phi1294.phi002.perseus-lat2", level=1)
self.assertEqual(
len(reffs), 14,
"There should be 14 books"
)
self.assertEqual(
reffs[0], CtsReference("1")
)
reffs = self.resolver.getReffs(textId="urn:cts:latinLit:phi1294.phi002.perseus-lat2", level=2)
self.assertEqual(
len(reffs), 1527,
"There should be 1527 poems"
)
self.assertEqual(
reffs[0], CtsReference("1.pr")
)
reffs = self.resolver.getReffs(
textId="urn:cts:latinLit:phi1294.phi002.perseus-lat2",
subreference="1.1",
level=1
)
self.assertEqual(
len(reffs), 6,
"There should be 6 references"
)
self.assertEqual(
reffs[0], CtsReference("1.1.1")
)
from MyCapytain.resolvers.cts.local import CtsCapitainsLocalResolver
from MyCapytain.common.constants import Mimetypes
import os
os.mkdir('text')
Repository = CtsCapitainsLocalResolver(["./"])
for text in Repository.texts:
try:
interactive_text = Repository.getTextualNode(text.id)
plaintext = interactive_text.export(
Mimetypes.PLAINTEXT, exclude=["tei:note", "tei:teiHeader"])
with open('text/{}.txt'.format(text.id.split(':')[-1]), mode='w') as f:
f.write(plaintext)
except Exception as E:
print(E)
continue