altf4arnold/datatracker
1
0
Fork 0
Code Issues Pull requests Actions 3 Packages Projects Releases Wiki Activity

Improved the handling of surname particles, (prompted by failure to handle the name of Niels ten Oever correctly)

Browse source 
- Legacy-Id: 13663
This commit is contained in:
Henrik Levkowetz 2017-06-17 15:12:54 +00:00
parent 1905d25aee
commit bb089c182d
1 changed files with 12 additions and 5 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

17
ietf/person/name.py
View file

@ -1,5 +1,7 @@
import re import re
import debug # pyflakes:ignore
def name_parts(name): def name_parts(name):
prefix, first, middle, last, suffix = u"", u"", u"", u"", u"" prefix, first, middle, last, suffix = u"", u"", u"", u"", u""
@ -28,11 +30,16 @@ def name_parts(name):
suffix = parts[-1] suffix = parts[-1]
parts = parts[:-1] parts = parts[:-1]
if len(parts) > 2: if len(parts) > 2:
name = u" ".join(parts) # Check if we have a surname with nobiliary particle
compound = re.search(r" (de|hadi|van|ver|von|el|le|st\.?) ", name.lower()) full = u" ".join(parts)
if compound: if full.upper() == full:
pos = compound.start() full = full.lower() # adjust case for all-uppercase input
parts = name[:pos].split() + [name[pos+1:]] # This is an incomplete list. Adjust as needed to handle known ietf
# participant names correctly:
particle = re.search(r" (af|de|der|di|Di|du|el|hadi|st\.?|ten|ter|van|van der|Van|von|von der|Von|zu) ", full)
if particle:
pos = particle.start()
parts = full[:pos].split() + [full[pos+1:]]
if len(parts) > 2: if len(parts) > 2:
first = parts[0] first = parts[0]
last = parts[-1] last = parts[-1]