help='remote CTS server')
parser.add_argument('--index',
metavar="FILE",
default=Config.INDEX,
help='corpus index file')
parser.add_argument('--corpus',
metavar="DIR",
default=Config.DATA,
help='local corpus directory')
args = parser.parse_args()
# clean destination directory
dest = os.path.join(args.corpus, 'xml')
if os.path.exists(dest):
shutil.rmtree(dest)
os.makedirs(dest)
else:
os.makedirs(dest)
# Read the corpus metadata
with open(args.index) as f:
corpus = [Text.metaFromDict(rec) for rec in json.load(f)]
# Create a Resolver instance
resolver = HttpCtsResolver(HttpCtsRetriever(args.server))
for text in corpus:
retrieveXML(resolver, text, os.path.join(dest, text.author))
print()
from MyCapytain.resolvers.cts.api import HttpCtsResolver
from MyCapytain.retrievers.cts5 import HttpCtsRetriever
from MyCapytain.common.constants import Mimetypes
# We set up a resolver which communicates with an API available in Leipzig
resolver = HttpCtsResolver(
HttpCtsRetriever("http://cts.dh.uni-leipzig.de/api/cts"))
# We require some metadata information
textMetadata = resolver.getMetadata(
"urn:cts:latinLit:phi1294.phi002.perseus-lat2")
# Texts in CTS Metadata have one interesting property : its citation scheme.
# XmlCtsCitation are embedded objects that carries information about how a text can be quoted, what depth it has
print(type(textMetadata),
[citation.name for citation in textMetadata.citation])
# Now, we want to retrieve the first line of poem seventy two of the second book
passage = resolver.getTextualNode(
"urn:cts:latinLit:phi1294.phi002.perseus-lat2", subreference="2.72.1")
# And we want to have its content exported to plain text and have the siblings of this passage (previous and next line)
print(passage.export(Mimetypes.PLAINTEXT), passage.siblingsId)
poemsInBook3 = resolver.getReffs(
"urn:cts:latinLit:phi1294.phi002.perseus-lat2", subreference="3")
print(poemsInBook3)
from MyCapytain.retrievers.cts5 import HttpCtsRetriever
from MyCapytain.resources.collections.cts import XmlCtsTextInventoryMetadata, XmlCtsWorkMetadata
from MyCapytain.common.constants import Mimetypes
from pprint import pprint
"""
In order to have a real life example,
we are gonna query for data in the Leipzig CTS API
We are gonna query for metadata about Seneca who
is represented by urn:cts:latinLit:stoa0255
To retrieve data, we are gonna make a GetMetadata query
to the CTS Retriever.
"""
retriever = HttpCtsRetriever("http://cts.dh.uni-leipzig.de/api/cts")
# We store the response (Pure XML String)
response = retriever.getMetadata(objectId="urn:cts:latinLit:stoa0255")
"""
From here, we actually have the necessary data, we can now
play with collections. TextInventory is the main collection type that is needed to
parse the whole response.
"""
inventory = XmlCtsTextInventoryMetadata.parse(resource=response)
# What we are gonna do is print the title of each descendant :
for descendant in inventory.descendants:
# Metadatum resolve any non-existing language ("eng", "lat") to a default one
# Putting default is just making that clear
print(descendant.get_label())
"""
You should see in there things such as
- "Seneca, Lucius Annaeus" (The TextGroup or main object)
- "de Ira" (The Work object)
def api_resolver(endpoint) -> Resolver:
return HttpCtsResolver(HttpCtsRetriever(endpoint))