fixing accented names

1 files changed, 13 insertions, 2 deletions

diff --git a/parsers/people.py b/parsers/people.py
index c0ffa10..01998e1 100644
--- a/parsers/people.py
+++ b/parsers/people.py
@@ -65,14 +65,24 @@ def parse_blurb(personline, header, person):
 slug_cache = {}
 def troggle_slugify(longname):
     """Uniqueness enforcement too. Yes we have had two "Dave Johnson"s
+    This function copied intact to expoweb/scripts/make-folklist.py
     """
     slug = longname.strip().lower().replace(" ","-")
+    slug = re.sub('\([^\)]*\)','',slug) # remove nickname in brackets
+    slug = slug.replace('é', 'e') 
+    slug = slug.replace('á', 'a') 
+    slug = slug.replace('ä', 'a') 
+    slug = slug.replace('&', '') # otherwise just remove the &
+    slug = slug.replace(';', '') # otherwise just remove the ;
+    slug = re.sub('<[^>]*>','',slug) # remove <span-lang = "hu">
+
     if len(slug) > 40: # slugfield is 50 chars
         slug = slug[:40]
     if slug in slug_cache: 
         slug_cache[slug] += 1
         slug = f"{slug}_{slug_cache[slug]}"
     slug_cache[slug] = 1
+    
     return slug
     
 def load_people_expos():
@@ -99,8 +109,9 @@ def load_people_expos():
     print(" - Loading personexpeditions")
 
     for personline in personreader:
+        #   This is all horrible: refactor it.
         name = personline[header["Name"]]
-        name = re.sub(r"<.*?>", "", name) 
+        plainname = re.sub(r"<.*?>", "", name) # now in slugify
         
         match = re.match(r"^([^(]*)(\(([^)]*)\))?", name) # removes nickname in brackets
         displayname = match.group(1)
@@ -113,7 +124,7 @@ def load_people_expos():
         matchlastname = re.match(r"^([\w&;\s]+)(?:\(([^)]*)\))?", rawlastname)
         lastname = matchlastname.group(1).strip()
 
-        splitnick = re.match(r"^([\w&;\s]+)(?:\(([^)]*)\))?", name)
+        splitnick = re.match(r"^([\w&;\s]+)(?:\(([^)]*)\))?", plainname)
         fullname = splitnick.group(1) # removes Nickname in brackets, but also cuts hyphenated names
         nick = splitnick.group(2) or ""