Updating caves and entrances is no longer nuclear!

Big overhaul of people processing, fullname added to the model
lastname is now names -1 unless you only have one (yes you Wookey)
this allows for Jon Arne Toft and Wookey to live it the same DB
names can now have html chars in them, this should be real unicode but that can
only happen when we go to Python 3!

2 files changed, 50 insertions, 23 deletions

diff --git a/parsers/caves.py b/parsers/caves.py
index 2c28365..606007f 100644
--- a/parsers/caves.py
+++ b/parsers/caves.py
@@ -6,16 +6,18 @@ import re
 
 
 def readcaves():
-  area_1623 = models.Area(short_name = "1623", parent = None)
-  area_1623.save()
-  area_1626 = models.Area(short_name = "1626", parent = None)
-  area_1626.save()
-  print("Reading Entrances")
+
+  # Clear the cave data issues as we are reloading
+  models.DataIssue.objects.filter(parser='caves').delete()
+
+  area_1623 = models.Area.objects.update_or_create(short_name = "1623", parent = None)
+  area_1626 = models.Area.objects.update_or_create(short_name = "1626", parent = None)
+  print(" - Reading Entrances")
   #print "list of <Slug> <Filename>"
   for filename in os.walk(settings.ENTRANCEDESCRIPTIONS).next()[2]: #Should be a better way of getting a list of files
     if filename.endswith('.html'):
       readentrance(filename)
-  print ("Reading Caves")
+  print (" - Reading Caves")
   for filename in os.walk(settings.CAVEDESCRIPTIONS).next()[2]: #Should be a better way of getting a list of files
     if filename.endswith('.html'):
       readcave(filename)
@@ -51,7 +53,7 @@ def readentrance(filename):
         bearings = getXML(entrancecontents, "bearings", maxItems = 1, context = context)
         url = getXML(entrancecontents, "url", maxItems = 1, context = context)
         if len(non_public) == 1 and len(slugs) >= 1 and len(name) >= 1 and  len(entrance_description) == 1 and  len(explorers) == 1 and  len(map_description) == 1 and  len(location_description) == 1 and  len(approach) == 1 and  len(underground_description) == 1 and  len(marking) == 1 and  len(marking_comment) == 1 and  len(findability) == 1 and  len(findability_description) == 1 and  len(alt) == 1 and  len(northing) == 1 and  len(easting) == 1 and  len(tag_station) == 1 and  len(exact_station) == 1 and  len(other_station) == 1 and  len(other_description) == 1 and  len(bearings) == 1 and  len(url) == 1:
-            e = models.Entrance(name = name[0],
+            e, state = models.Entrance.objects.update_or_create(name = name[0],
                          non_public = {"True": True, "False": False, "true": True, "false": False,}[non_public[0]],
                          entrance_description = entrance_description[0],
                          explorers = explorers[0],
@@ -75,14 +77,12 @@ def readentrance(filename):
                          url = url[0],
                          filename = filename,
                          cached_primary_slug = slugs[0])
-            e.save()
             primary = True
             for slug in slugs:
                 #print slug, filename
-                cs = models.EntranceSlug(entrance = e,
+                cs = models.EntranceSlug.objects.update_or_create(entrance = e,
                                          slug = slug,
                                          primary = primary)
-                cs.save()
                 primary = False
 
 def readcave(filename):
@@ -117,7 +117,7 @@ def readcave(filename):
         url = getXML(cavecontents, "url", maxItems = 1, context = context)
         entrances = getXML(cavecontents, "entrance", context = context)
         if len(non_public) == 1 and len(slugs) >= 1 and len(official_name) == 1 and len(areas) >= 1 and len(kataster_code) == 1 and len(kataster_number) == 1 and len(unofficial_number) == 1 and len(explorers) == 1 and len(underground_description) == 1 and len(equipment) == 1 and len(references) == 1 and len(survey) == 1 and len(kataster_status) == 1 and len(underground_centre_line) == 1 and len(notes) == 1 and len(length) == 1 and len(depth) == 1 and len(extent) == 1 and len(survex_file) == 1 and len(description_file ) == 1 and len(url) == 1 and len(entrances) >= 1:
-            c = models.Cave(non_public = {"True": True, "False": False, "true": True, "false": False,}[non_public[0]],
+            c, state = models.Cave.objects.update_or_create(non_public = {"True": True, "False": False, "true": True, "false": False,}[non_public[0]],
                      official_name = official_name[0],
                      kataster_code = kataster_code[0],
                      kataster_number = kataster_number[0],
@@ -137,7 +137,6 @@ def readcave(filename):
                      description_file = description_file[0],
                      url = url[0],
                      filename = filename)
-            c.save()
             for area_slug in areas:
                 area = models.Area.objects.filter(short_name = area_slug)
                 if area:
@@ -149,12 +148,13 @@ def readcave(filename):
             primary = True
             for slug in slugs:
                 try:
-                    cs = models.CaveSlug(cave = c,
+                    cs = models.CaveSlug.objects.update_or_create(cave = c,
                               slug = slug,
                               primary = primary)
-                    cs.save()
                 except:
-                    print("Can't find text (slug): %s, skipping %s" % (slug, context))
+                    message = "Can't find text (slug): %s, skipping %s" % (slug, context)
+                    models.DataIssue.objects.create(parser='caves', message=message)
+                    print(message)
                     
                 primary = False
             for entrance in entrances:
@@ -162,10 +162,11 @@ def readcave(filename):
                 letter = getXML(entrance, "letter", maxItems = 1, context = context)[0]
                 try:
                     entrance = models.Entrance.objects.get(entranceslug__slug = slug)
-                    ce = models.CaveAndEntrance(cave = c, entrance_letter = letter, entrance = entrance)
-                    ce.save()
+                    ce = models.CaveAndEntrance.objects.update_or_create(cave = c, entrance_letter = letter, entrance = entrance)
                 except:
-                    print ("Entrance text (slug) %s missing %s" % (slug, context))
+                    message = "Entrance text (slug) %s missing %s" % (slug, context)
+                    models.DataIssue.objects.create(parser='caves', message=message)
+                    print(message)
                 
 
 def getXML(text, itemname, minItems = 1, maxItems = None, printwarnings = True, context = ""):
diff --git a/parsers/people.py b/parsers/people.py
index 4bf84a0..eb877f2 100644
--- a/parsers/people.py
+++ b/parsers/people.py
@@ -65,11 +65,27 @@ def LoadPersonsExpos():
     for personline in personreader:
         name = personline[header["Name"]]
         name = re.sub(r"<.*?>", "", name)
-        mname = re.match(r"(\w+)(?:\s((?:van |ten )?\w+))?(?:\s\(([^)]*)\))?", name)
-        nickname = mname.group(3) or ""
 
-        lookupAttribs={'first_name':mname.group(1), 'last_name':(mname.group(2) or "")}
-        nonLookupAttribs={'is_vfho':personline[header["VfHO member"]],}
+        firstname = ""
+        nickname = ""
+
+        rawlastname = personline[header["Lastname"]].strip()
+        matchlastname = re.match(r"^([\w&;\s]+)(?:\(([^)]*)\))?", rawlastname)
+        lastname = matchlastname.group(1).strip()
+
+        splitnick = re.match(r"^([\w&;\s]+)(?:\(([^)]*)\))?", name)
+        fullname = splitnick.group(1)
+
+        nickname = splitnick.group(2) or ""
+
+        fullname = fullname.strip()
+        names = fullname.split(' ')
+        firstname = names[0]
+        if len(names) == 1:
+            lastname = ""
+
+        lookupAttribs={'first_name':firstname, 'last_name':(lastname or "")}
+        nonLookupAttribs={'is_vfho':personline[header["VfHO member"]], 'fullname':fullname}
         person, created = save_carefully(models.Person, lookupAttribs, nonLookupAttribs)
 
         parseMugShotAndBlurb(personline=personline, header=header, person=person)
@@ -120,14 +136,24 @@ def GetPersonExpeditionNameLookup(expedition):
         possnames = [ ]
         f = personexpedition.person.first_name.lower()
         l = personexpedition.person.last_name.lower()
+        full = personexpedition.person.fullname.lower()
         if l:
             possnames.append(f + " " + l)
             possnames.append(f + " " + l[0])
             possnames.append(f + l[0])
             possnames.append(f[0] + " " + l)
         possnames.append(f)
-        if personexpedition.nickname:
+        if full not in possnames:
+            possnames.append(full)
+        if personexpedition.nickname not in possnames:
             possnames.append(personexpedition.nickname.lower())
+            if l:
+                # This allows for nickname to be used for short name eg Phil
+                # adding Phil Sargent to the list
+                if str(personexpedition.nickname.lower() + " " + l) not in possnames:
+                    possnames.append(personexpedition.nickname.lower() + " " + l)
+                if str(personexpedition.nickname.lower() + " " + l[0]) not in possnames:
+                    possnames.append(personexpedition.nickname.lower() + " " + l[0])
         
         for possname in possnames:
             if possname in res: