def get_label_type(expl, word):
wt = proper(word.Type) if word.Type is not None else ""
# Extract the list of item enclosed in {{ }}
# For each item found , if there is | inside , then split and take only longest word
# Convert all non 0-9 A-Z into _
# Deduplicate _ _ into single _
# Make all words in upper case
list1 = []
for t in expl.find_objects(
Template,
recursive=True,
exclude=[li for li in expl.find_objects((Li, Dl))]):
inner = t.raw
s = convert_to_alnum(inner, '_')
s = deduplicate(s, '_')
s = s.strip('_')
words = []
for ws in s.split("|"):
for w in ws.split('_'):
words += w.split(' ')
s = get_lognest_word(words)
s = s.upper()
list1.append(s)
# Extract the list of item enclosed in [[ ]]
# For each item found , if there is | inside , then split and take only longest word
# Convert all non 0-9 A-Z into _
# Deduplicate _ _ into single _
# Make all words with first letter uppercase and others lower case (propercase)
list2 = []
for l in expl.find_objects(
Link,
recursive=True,
exclude=[li for li in expl.find_objects((Li, Dl))]):
s = l.get_text()
s = convert_to_alnum(s, '_')
s = deduplicate(s, '_')
s = s.strip('_')
words = []
for ws in s.split('_'):
for w in ws.split(' '):
words.append(w)
s = get_lognest_word(words)
s = proper(s)
list2.append(s)
# remove all [ ( { ) ] } from the line, and extract all words separated by spaces
# keep only words having a lenght>=3
# Convert all non 0-9 A-Z into _
# Deduplicate _ _ into single _
# Make all words in lowercase
list3 = []
words = []
for w in expl.find_objects(
String,
recursive=False,
exclude=[li for li in expl.find_objects((Li, Dl))]):
words.append(w.get_text())
s = " ".join(words)
s = s.replace('(', ' ').replace(')', ' ')
s = deduplicate(s, ' ')
s = convert_to_alnum(s)
s = deduplicate(s, '_')
s = s.strip('_')
words = []
for ws in s.split('_'):
for w in ws.split(' '):
words.append(w)
list3 = [w.lower() for w in words if len(w) >= 3]
# Add TYPE + (the 4 first items of the concatenated list : list1 + List2 + list3
# Concat
#print(expl.raw)
#print(list1)
#print(list2)
#print(list3)
#print()
biglst = list1 + list2 + list3
#if len(biglst) < 4:
# biglst = unique(biglst)
return wt + "_" + "_".join(biglst[:4])
def get_label_type(page, tense, infinitive, pronoun):
# Verb_To_do_You_Indicative Perfect
s = "Verb" + '_' + proper(page.label) + '_' + proper(pronoun) + '_' + tense
s = s.replace(' ', '_')
return s
def get_label_type_v1(expl, word):
wt = proper(word.Type) if word.Type is not None else ""
#
list1 = []
for t in expl.find_objects(
(Template, Link),
recursive=True,
exclude=[li for li in expl.find_objects((Li, Dl))]):
inner = t.raw
s = convert_to_alnum(inner)
s = s.replace('_', ' ')
s = deduplicate(s, ' ')
s = s.strip()
splitted = s.split(" ")
list1 += [w.upper() for w in splitted]
list1 = [w for w in list1 if len(w) >= 3]
list2 = []
for l in expl.find_objects(
Link,
recursive=True,
exclude=[li for li in expl.find_objects((Li, Dl))]):
inner = l.get_text()
s = convert_to_alnum(inner)
s = deduplicate(s)
s = s.strip("_").strip()
splitted = s.split("_")
list2 += [proper(w) for w in splitted]
list3 = []
texts = []
for c in expl.childs:
if isinstance(c, Li): # skip deep lists
continue
if isinstance(c, Template): # skip Templates {{ }}
continue
if isinstance(c, Template): # skip Links [[ ]]
continue
else:
texts.append(c.get_text())
s = "".join(texts)
s = convert_to_alnum(s)
s = s.replace('_', ' ')
s = deduplicate(s, ' ')
s = s.strip()
splitted = s.split(" ")
list3 += [w.lower() for w in splitted]
list3 = [w for w in list3 if len(w) >= 4]
# Concat
biglst = list1 + list2 + list3
if len(biglst) == 1:
return wt + "-" + biglst[0]
elif len(biglst) >= 3:
return wt + "-" + "-".join(biglst[:3])
else:
return wt