import json
import lwb
with open('D:/LexBib/terms/langdict.json', encoding="utf-8") as f:
langdict = json.load(f)
with open('D:/LexBib/languages/publangs.txt', encoding="utf-8") as f:
publangs = f.read().split('\n')
count = 0
for lang in publangs:
count += 1
print('\nLine [' + str(count) + '] of ' + str(len(publangs)) + ': ' + lang)
qid = lwb.getqid(["Q8"], lang) # class Language
statement = lwb.updateclaim(qid, "P4", langdict[lang]['wdqid'], "url")
statement = lwb.updateclaim(qid, "P32", lang, "url")
for label in langdict[lang]['labels']:
statement = lwb.setlabel(qid, label, langdict[lang]['labels'][label])
print('OK. ' + str(len(publangs) - count) + ' languages left.')
print('\nFinished.\n')
"http://www.w3.org/2004/02/skos/core#exactMatch": "P78",
"http://www.w3.org/2004/02/skos/core#relatedMatch": "P79",
"http://www.w3.org/2004/02/skos/core#definition": "P80"
}
with open('D:/LexBib/terms/SKOS4lwb.json', encoding="utf-8") as f:
data = json.load(f)['results']['bindings']
count = 1
for row in data:
print('\nTriple [' + str(count) + '], ' + str(len(data) - count) +
' triples left.')
lwbs = lwb.getqid("Q7", row['s']['value'])
if row['p']['value'] in propmap:
if row['o']['type'] == "literal":
statement = lwb.updateclaim(lwbs, propmap[row['p']['value']],
row['o']['value'].rstrip(), "string")
else:
lwbo = lwb.getqid("Q7", row['o']['value'].rstrip())
statement = lwb.updateclaim(lwbs, propmap[row['p']['value']], lwbo,
"item")
elif row['p']['value'] == "http://www.w3.org/2004/02/skos/core#prefLabel":
lwb.setlabel(lwbs, row['o']['xml:lang'], row['o']['value'].rstrip())
elif row['p']['value'] == "http://www.w3.org/2004/02/skos/core#altLabel":
lwb.setlabel(lwbs,
row['o']['xml:lang'],
row['o']['value'].rstrip(),
type="alias")
count += 1
done = False
while (not done):
try:
r = requests.get(url)
bindings = r.json()['results']['bindings']
except Exception as ex:
print('Error: SPARQL request failed: ' + str(ex))
time.sleep(2)
continue
done = True
#print(str(bindings))
print(
'Found ' + str(len(bindings)) +
' BibItems without label. Will proceed to set them using the BibItem title...\n'
)
time.sleep(3)
count = 0
for item in bindings:
count += 1
bibitem = item['bibItem']['value'].replace(
"http://data.lexbib.org/entity/", "")
title = item['dct_title']['value']
wikilang = item['wikilang']['value']
label = lwb.setlabel(bibitem, wikilang, title)
if wikilang != "en": # always add title as English label, also if not English
label = lwb.setlabel(bibitem, "en", title)
if label:
print('OK. ' + str(len(bindings) - count) + ' items left.\n')
container = container.replace("-", "")
container = container.replace(
"isbn:", "http://worldcat.org/isbn/")
container = container.replace(
"oclc:", "http://worldcat.org/oclc/")
elif container.startswith('doi:'):
container = container.replace(
"doi:", "http://doi.org/")
# check container type
if item['type'] == "article-journal":
qid = lwb.getqid("Q1907", container)
else:
qid = lwb.getqid("Q12", container)
if item['type'] != "chapter" and "title-short" in item and item[
'title-short'] not in seen_titles:
lwb.setlabel(qid, "en", item['title-short'])
seen_titles.append(item['title-short'])
propvals.append({
"property": "P9",
"datatype": "item",
"value": qid
}) # container relation
if tag["tag"].startswith(':type '):
type = tag["tag"].replace(":type ", "")
if type == "Review":
propvals.append({
"property": "P5",
"datatype": "item",
"value": "Q15"
})
regexp = re.compile(r'Q\d+')
if regexp.search(label):
label = ""
except Exception as ex:
print("ISSN " + issn +
" not found on wikidata, skipping, will add to orphaned list.")
orphaned += issn + '\tnot found on wikidata.\n'
continue
# create lwb serial for this orphaned issn
lwbqid = lwb.getqid("Q20", wdqid) # for serials, wdqid is also lexbib uri
statement = lwb.updateclaim(lwbqid, "P3", wdqid, "url")
statement = lwb.updateclaim(lwbqid, "P20", issn, "string")
statement = lwb.updateclaim(lwbqid, "P4", wdqid, "url")
statement = lwb.setlabel(lwbqid, "en", label)
# add P46 "contained in serial" to bibitems with that issn
# get bibitems
url = "https://data.lexbib.org/query/sparql?format=json&query=PREFIX%20lwb%3A%20%3Chttp%3A%2F%2Fdata.lexbib.org%2Fentity%2F%3E%0APREFIX%20ldp%3A%20%3Chttp%3A%2F%2Fdata.lexbib.org%2Fprop%2Fdirect%2F%3E%0A%0Aselect%20%3FbibItem%20%3Fissn%20%3Fjournal%20where%0A%7B%20%3FbibItem%20ldp%3AP5%20lwb%3AQ3%20.%0A%20%20%3FbibItem%20ldp%3AP20%20%3Fissn%20.%0A%20%3Fjournal%20ldp%3AP5%20lwb%3AQ20%20.%0A%20%3Fjournal%20ldp%3AP20%20%3Fissn%20.%0A%20FILTER%20%28%3Fissn%20%3D%20%22" + issn + "%22%29%7D"
done = False
while (not done):
try:
r2 = requests.get(url)
bindings2 = r2.json()['results']['bindings']
except Exception as ex:
print('Error: SPARQL request failed: ' + str(ex))
time.sleep(2)
continue
done = True
lwb.updateclaim(creatorqid, "P41", item['lastName'], "string")
claim = lwb.getclaimfromstatement(oldStatement)
if "P39" in claim:
newprop = "P12"
listpos = claim["P39"][0]['qualifiers']["P33"][0]['datavalue'][
'value']
elif "P42" in claim:
newprop = "P13"
listpos = claim["P42"][0]['qualifiers']["P33"][0]['datavalue'][
'value']
else:
print(
'*** Something is wrong with this supposed creator literal statement'
)
time.sleep(10)
newStatement = lwb.updateclaim(bibitemqid, newprop, creatorqid, "item")
lwb.setqualifier(bibitemqid, newprop, newStatement, "P33", listpos,
"string")
lwb.setqualifier(bibitemqid, newprop, newStatement, "P67",
item["firstName"] + " " + item["lastName"], "string")
if creatorPrefLabel != item['firstName'] + " " + item['lastName']:
lwb.setlabel(creatorqid,
"en",
item['firstName'] + " " + item['lastName'],
type="alias")
lwb.removeclaim(oldStatement)
time.sleep(1)
count += 1
try:
r = requests.get(
"https://www.wikidata.org/w/api.php?action=wbgetentities&format=json&props=labels&ids="
+ wdqid + "&languages=en").json()
#print(str(r))
if "labels" in r['entities'][wdqid]:
label = r['entities'][wdqid]['labels']['en']['value']
done = True
except Exception as ex:
print(
'Wikidata: Getlabels operation failed, will try again...\n'
+ str(ex))
time.sleep(4)
lwb.setlabel(lwbqid, "en", label)
itemcount += 1
else:
# get wikidata equivalent prop
wdprop = lwb.getclaims(prop, "P2")
if bool(wdprop):
wdprop = wdprop['P2'][0]['mainsnak']['datavalue']['value'].replace(
"http://www.wikidata.org/entity/", "")
print('Wikidata Prop for LWB prop ' + prop + ' is: ' + wdprop)
else:
print('*** No equivalent Wikidata property found for ' + prop +
'.')
continue
itemcount = 1
for item in lwbitems:
print('\nItem [' + str(itemcount) + '], ' +
url = "https://data.lexbib.org/query/sparql?format=json&query=PREFIX%20rdfs%3A%20%3Chttp%3A%2F%2Fwww.w3.org%2F2000%2F01%2Frdf-schema%23%3E%0APREFIX%20lwb%3A%20%3Chttp%3A%2F%2Fdata.lexbib.org%2Fentity%2F%3E%0APREFIX%20ldp%3A%20%3Chttp%3A%2F%2Fdata.lexbib.org%2Fprop%2Fdirect%2F%3E%0APREFIX%20lp%3A%20%3Chttp%3A%2F%2Fdata.lexbib.org%2Fprop%2F%3E%0APREFIX%20lps%3A%20%3Chttp%3A%2F%2Fdata.lexbib.org%2Fprop%2Fstatement%2F%3E%0APREFIX%20lpq%3A%20%3Chttp%3A%2F%2Fdata.lexbib.org%2Fprop%2Fqualifier%2F%3E%0A%0Aselect%20distinct%20%3Fauthor%20%3FauthorLabel%20%3Fauthornamevar%20%0Awhere%20%7B%0A%20%20%3Fauthor%20ldp%3AP5%20lwb%3AQ5%20.%0A%20%20%3Fauthor%20rdfs%3Alabel%20%3FauthorLabel%20.%0A%20%20%3FbibItem%20lp%3AP12%20%3Fauthorstatement%20.%0A%20%20%3Fauthorstatement%20lps%3AP12%20%3Fauthor%20.%0A%20%20%3Fauthorstatement%20lpq%3AP67%20%3Fauthornamevar%20.%0A%20%20FILTER%20%28str%28%3Fauthornamevar%29%20%21%3D%20str%28%3FauthorLabel%29%29%0A%20%0A%20%20%0A%20%20%7D%20ORDER%20BY%20%3Fauthor%20%3FauthorLabel%20%3Fauthornamevar%20"
done = False
while (not done):
try:
r = requests.get(url)
bindings = r.json()['results']['bindings']
except Exception as ex:
print('Error: SPARQL request failed: ' + str(ex))
time.sleep(2)
continue
done = True
#print(str(bindings))
print(
'Found ' + str(len(bindings)) +
' creator name variants (that do not match with the author prefLabel)...\n'
)
time.sleep(3)
count = 0
for item in bindings:
count += 1
creatorqid = item['author']['value'].replace(
"http://data.lexbib.org/entity/", "")
namevar = item['authornamevar']['value']
altlabel = lwb.setlabel(creatorqid, "en", namevar, type="alias")
if altlabel:
print('OK. ' + str(len(bindings) - count) + ' namevars left.\n')
import json
import lwb
with open('D:/LexBib/countries/query.json', encoding="utf-8") as f:
dict = json.load(f)
count = 0
for item in dict:
count += 1
lwbqid = lwb.getqid("Q8654", item['country'])
lwb.setlabel(lwbqid, "en", item['countryLabel'])
lwb.stringclaim(lwbqid, "P4", item['country'])
print('OK. ' + str(len(dict) - count) + ' countries left.')