troggle-unchained/core/models/caves.py

import string
import os
import datetime
import re
import json
import subprocess
import operator

from collections import defaultdict
from pathlib import Path

from urllib.parse import urljoin

import settings

from django.db import models
from django.core.files.storage import FileSystemStorage
from django.contrib.auth.models import User
from django.contrib.contenttypes.models import ContentType
from django.db.models import Min, Max
from django.conf import settings
from django.urls import reverse
from django.template import Context, loader
from django.shortcuts import render

from troggle.core.models.troggle import TroggleModel, Person, Expedition, DataIssue
from troggle.core.models.survex import SurvexStation
from troggle.core.utils import writetrogglefile
from troggle.core.utils import TROG

# Us ethe TROG global object to cache teh cave lookup list
Gcavelookup = TROG['caves']['gcavelookup']
Gcave_count = TROG['caves']['gcavecount']

Gcavelookup = None
Gcave_count = None

'''The model declarations for Areas, Caves and Entrances. Also LogBookENtry, QM, PersonTrip
'''

todo='''
- Find out why we have separate objects CaveSlug and EntranceSlug and why
  these are not just a single field on the Model. Do we ever need more
  than one slug per cave or entrance? Surely that would break everything??
  
- Move PersonTrip to be with Person and Expedition elsewhere
  
- Restore constraint:   unique_together = (("area", "kataster_number"), ("area", "unofficial_number"))
'''

class Area(TroggleModel):
    short_name = models.CharField(max_length=100)
    name = models.CharField(max_length=200, blank=True, null=True)
    description = models.TextField(blank=True, null=True)
    super = models.ForeignKey('Area', blank=True, null=True, on_delete=models.SET_NULL)

    def __str__(self):
        if self.super:
            return str(self.super) + " - " + str(self.short_name)
        else:
            return str(self.short_name)

    def kat_area(self):
        if self.short_name in ["1623", "1626", "1624", "1627"]:
            return self.short_name
        elif self.super:
            return self.super.kat_area()

class CaveAndEntrance(models.Model):
    cave = models.ForeignKey('Cave',on_delete=models.CASCADE)
    entrance = models.ForeignKey('Entrance',on_delete=models.CASCADE)
    entrance_letter = models.CharField(max_length=20,blank=True, null=True)
    def __str__(self):
        return str(self.cave) + str(self.entrance_letter)

class CaveSlug(models.Model):
    cave = models.ForeignKey('Cave',on_delete=models.CASCADE)
    slug = models.SlugField(max_length=50, unique = True)
    primary = models.BooleanField(default=False)

class Cave(TroggleModel):
    # too much here perhaps, 
    official_name = models.CharField(max_length=160)
    area = models.ManyToManyField(Area, blank=True)
    kataster_code = models.CharField(max_length=20,blank=True, null=True)
    kataster_number = models.CharField(max_length=10,blank=True, null=True)
    unofficial_number = models.CharField(max_length=60,blank=True, null=True)
    entrances = models.ManyToManyField('Entrance', through='CaveAndEntrance')
    explorers = models.TextField(blank=True,null=True)
    underground_description = models.TextField(blank=True,null=True)
    equipment = models.TextField(blank=True,null=True)
    references = models.TextField(blank=True,null=True)
    survey = models.TextField(blank=True,null=True)
    kataster_status = models.TextField(blank=True,null=True)
    underground_centre_line = models.TextField(blank=True,null=True)
    notes = models.TextField(blank=True,null=True)
    length = models.CharField(max_length=100,blank=True, null=True)
    depth = models.CharField(max_length=100,blank=True, null=True)
    extent = models.CharField(max_length=100,blank=True, null=True)
    survex_file = models.CharField(max_length=100,blank=True, null=True)
    description_file = models.CharField(max_length=200,blank=True, null=True)
    url = models.CharField(max_length=200,blank=True, null=True)
    filename = models.CharField(max_length=200)

    #class Meta:
    #    unique_together = (("area", "kataster_number"), ("area", "unofficial_number"))
    # FIXME Kataster Areas and CUCC defined sub areas need seperating    

    #href    = models.CharField(max_length=100)
    
    class Meta:
        ordering = ('kataster_code', 'unofficial_number')  

    def hassurvey(self):
        if not self.underground_centre_line:
            return "No"
        if (self.survey.find("<img") > -1 or self.survey.find("<a") > -1 or self.survey.find("<IMG") > -1 or self.survey.find("<A") > -1):
            return "Yes"
        return "Missing"

    def hassurveydata(self):
        if not self.underground_centre_line:
            return "No"
        if self.survex_file:
            return "Yes"
        return "Missing"
         
    def slug(self):
        primarySlugs = self.caveslug_set.filter(primary = True)
        if primarySlugs:
            return primarySlugs[0].slug
        else:
            slugs = self.caveslug_set.filter()
            if slugs:
                return slugs[0].slug

    def ours(self):
        return bool(re.search(r'CUCC', self.explorers))

    def reference(self):
        if self.kataster_number:
            return "%s-%s" % (self.kat_area(), self.kataster_number)
        else:
            return "%s-%s" % (self.kat_area(), self.unofficial_number)
    
    def get_absolute_url(self):
        if self.kataster_number:
            href = self.kataster_number
        elif self.unofficial_number:
            href = self.unofficial_number
        else:
            href = self.official_name.lower()
        #return settings.URL_ROOT + '/cave/' + href + '/'
        #return urljoin(settings.URL_ROOT, reverse('cave',kwargs={'cave_id':href,})) # WRONG. This produces /cave/161 and should be /1623/161
        return Path(settings.URL_ROOT) / self.url # not good Django style.. NEEDS actual URL

    def __str__(self, sep = ": "):
        return str(self.slug())

    def get_QMs(self):
        '''Searches for all QMs that reference this cave. Probably a better Django way to do this
        '''
        qms = QM.objects.filter(cave=self).order_by('expoyear', 'block__date') # a QuerySet, see https://docs.djangoproject.com/en/4.0/ref/models/querysets/#order-by
        return qms # a QuerySet
        # undated = []
        # dated = []
        # qms = QM.objects.filter(cave=self) # a QuerySet
        # for q in qms:
            # if q.block:
                # dated.append(q)
            # else:
                # undated.append(q)
        # sortedqms = sorted(dated, key=operator.attrgetter('block.date')) # sort by date of survexblock the QM was defined in
        # orderedqms = sorted(undated, key=operator.attrgetter('expoyear')) # sort by date of expoyear
        # return orderedqms + sortedqms # a list, NOT a QuerySet
        

    # def new_QM_number(self, year=datetime.date.today().year):
            # """Given a cave and the current year, returns the next QM number."""
            # try:
                # res=QM.objects.filter(found_by__date__year=year, found_by__cave_slug=self.slug).order_by('-number')[0]
            # except IndexError:
                # return 1
            # return res.number+1

    def kat_area(self):
        for a in self.area.all():
            if a.kat_area():
                return a.kat_area()
    
    def entrances(self):
        return CaveAndEntrance.objects.filter(cave=self)

    def singleentrance(self):
        return len(CaveAndEntrance.objects.filter(cave=self)) == 1
    
    def entrancelist(self):
        rs = []
        res = ""
        for e in CaveAndEntrance.objects.filter(cave=self):
            if e.entrance_letter:
                rs.append(e.entrance_letter)
        rs.sort()
        prevR = ''
        n = 0
        for r in rs:
            if prevR:
                if chr(ord(prevR) + 1 ) == r:
                    prevR = r
                    n += 1
                else:
                    if n == 0:
                        res += ", " + prevR
                    else:
                        res += "&ndash;" + prevR
            else:
                prevR = r
                n = 0
                res += r
        if n == 0:
            if res:
                res += ", " + prevR
        else:
            res += "&ndash;" + prevR
        return res
    
    def writeDataFile(self):
        filepath = os.path.join(settings.CAVEDESCRIPTIONS, self.filename)

        t = loader.get_template('dataformat/cave.xml')
        #c = Context({'cave': self})
        c = dict({'cave': self})
        u = t.render(c)
        writetrogglefile(filepath, u)
        return

        
    def getArea(self):
        areas = self.area.all()
        lowestareas = list(areas)
        for area in areas:
            if area.super in areas:
                try:
                    lowestareas.remove(area.super)
                except:
                    pass
        return lowestareas[0]

class EntranceSlug(models.Model):
    entrance = models.ForeignKey('Entrance',on_delete=models.CASCADE)
    slug = models.SlugField(max_length=50, unique = True)
    primary = models.BooleanField(default=False)

class Entrance(TroggleModel):
    name = models.CharField(max_length=100, blank=True,null=True)
    entrance_description = models.TextField(blank=True,null=True)
    explorers = models.TextField(blank=True,null=True)
    map_description = models.TextField(blank=True,null=True)
    location_description = models.TextField(blank=True,null=True)
    approach = models.TextField(blank=True,null=True)
    underground_description = models.TextField(blank=True,null=True)
    photo = models.TextField(blank=True,null=True)
    MARKING_CHOICES = (
        ('P', 'Paint'),
        ('P?', 'Paint (?)'),
        ('T', 'Tag'),
        ('T?', 'Tag (?)'),
        ('R', 'Needs Retag'),
        ('S', 'Spit'),
        ('S?', 'Spit (?)'),
        ('U', 'Unmarked'),
        ('?', 'Unknown'))
    marking = models.CharField(max_length=2, choices=MARKING_CHOICES)
    marking_comment = models.TextField(blank=True,null=True)
    FINDABLE_CHOICES = (
        ('?', 'To be confirmed ...'),
        ('S', 'Coordinates'),
        ('L', 'Lost'),
        ('R', 'Refindable'))
    findability = models.CharField(max_length=1, choices=FINDABLE_CHOICES, blank=True, null=True)
    findability_description = models.TextField(blank=True,null=True)
    alt = models.TextField(blank=True, null=True)
    northing = models.TextField(blank=True, null=True)
    easting = models.TextField(blank=True, null=True)
    lat_wgs84 = models.TextField(blank=True, null=True)
    long_wgs84 = models.TextField(blank=True, null=True)
    tag_station = models.TextField(blank=True, null=True)
    exact_station = models.TextField(blank=True, null=True)
    other_station = models.TextField(blank=True, null=True)
    other_description = models.TextField(blank=True,null=True)
    bearings = models.TextField(blank=True,null=True)
    url = models.CharField(max_length=200,blank=True, null=True)
    filename = models.CharField(max_length=200)
    cached_primary_slug = models.CharField(max_length=200,blank=True, null=True)

    def __str__(self):
        return str(self.slug())

    def exact_location(self):
        return SurvexStation.objects.lookup(self.exact_station)

    def other_location(self):
        return SurvexStation.objects.lookup(self.other_station)

    def find_location(self):
        r = {'':  'To be entered ',
             '?': 'To be confirmed:',
             'S': '',
             'L': 'Lost:',
             'R': 'Refindable:'}[self.findability]
        if self.tag_station:
            try:
                s = SurvexStation.objects.lookup(self.tag_station)
                return r + "%0.0fE %0.0fN %0.0fAlt" % (s.x, s.y, s.z)
            except:
                return r + "%s Tag Station not in dataset" % self.tag_station
        if self.exact_station:
            try:
                s = SurvexStation.objects.lookup(self.exact_station)
                return r + "%0.0fE %0.0fN %0.0fAlt" % (s.x, s.y, s.z)
            except:
                return r + "%s Exact Station not in dataset" % self.tag_station
        if self.other_station:
            try:
                s = SurvexStation.objects.lookup(self.other_station)
                return r + "%0.0fE %0.0fN %0.0fAlt %s" % (s.x, s.y, s.z, self.other_description)
            except:
                return r + "%s Other Station not in dataset" % self.tag_station
        if self.FINDABLE_CHOICES == "S":
            r += "ERROR, Entrance has been surveyed but has no survex point"
        if self.bearings:
            return r + self.bearings
        return r

    def best_station(self):
        if self.tag_station:
            return self.tag_station
        if self.exact_station:
            return self.exact_station
        if self.other_station:
            return self.other_station

    def has_photo(self):
        if self.photo:
            if (self.photo.find("<img") > -1 or self.photo.find("<a") > -1 or self.photo.find("<IMG") > -1 or self.photo.find("<A") > -1):
                return "Yes"
            else:
                return "Missing"
        else:
            return "No"

    def marking_val(self):
        for m in self.MARKING_CHOICES:
            if m[0] == self.marking:
                return m[1]

    def findability_val(self):
        for f in self.FINDABLE_CHOICES:
            if f[0] == self.findability:
                return f[1]

    def tag(self):
        return SurvexStation.objects.lookup(self.tag_station)

    def needs_surface_work(self):
        return self.findability != "S" or not self.has_photo or self.marking != "T"

    def get_absolute_url(self):
        # ancestor_titles='/'.join([subcave.title for subcave in self.get_ancestors()])
        # if ancestor_titles:
            # res = '/'.join((self.get_root().cave.get_absolute_url(), ancestor_titles, self.title))
        # else:
            # res = '/'.join((self.get_root().cave.get_absolute_url(), self.title))
        # return res
        res = '/'.join((self.get_root().cave.get_absolute_url(), self.title))
        return res

    def slug(self):
        if not self.cached_primary_slug:
            primarySlugs = self.entranceslug_set.filter(primary = True)
            if primarySlugs:    
                self.cached_primary_slug = primarySlugs[0].slug
                self.save()
            else:
                slugs = self.entranceslug_set.filter()
                if slugs:
                    self.cached_primary_slug = slugs[0].slug
                    self.save()
        return self.cached_primary_slug

    def cavelist(self):
        rs = []
        res = ""
        for e in CaveAndEntrance.objects.filter(entrance=self):
            if e.cave:
                rs.append(e.cave)
        return rs
 

    def get_file_path(self):
            return Path(settings.ENTRANCEDESCRIPTIONS, self.filename)

    def writeDataFile(self):
        filepath = os.path.join(settings.ENTRANCEDESCRIPTIONS, self.filename)

        t = loader.get_template('dataformat/entrance.xml')
        c = dict({'entrance': self})
        u = t.render(c)
        writetrogglefile(filepath, u)
        return


class LogbookEntry(TroggleModel):
    """Single parsed entry from Logbook
    
    But what is all this__getattribute__ meta stuff for ? When is it needed ?!?
    Le'ts get rid of it and set the 'cave' attribute to a cave object elsehwhere. This is 
    attempting to be Too Clever.
    """
    LOGBOOK_ENTRY_TYPES = (
        ("wiki", "Wiki style logbook"),
        ("html", "Html style logbook")
    )
    date    = models.DateField()#MJG wants to turn this into a datetime such that multiple Logbook entries on the same day can be ordered.ld()
    expeditionday = models.ForeignKey("ExpeditionDay", null=True,on_delete=models.SET_NULL)#MJG wants to KILL THIS (redundant information)
    expedition = models.ForeignKey(Expedition,blank=True, null=True,on_delete=models.SET_NULL)  # yes this is double-
    title      = models.CharField(max_length=settings.MAX_LOGBOOK_ENTRY_TITLE_LENGTH)
    cave_slug  = models.SlugField(max_length=50, blank=True, null=True)
    place      = models.CharField(max_length=100,blank=True, null=True,help_text="Only use this if you haven't chosen a cave")
    text       = models.TextField()
    slug       = models.SlugField(max_length=50)
    entry_type = models.CharField(default="wiki",null=True,choices=LOGBOOK_ENTRY_TYPES,max_length=50)

    class Meta:
        verbose_name_plural = "Logbook Entries"
        # several PersonTrips point in to this object
        ordering = ('-date',)

    def cave(self): # Why didn't he just make this a foreign key to Cave ? Replaces __getattrribute__ sillyness.
        c = CaveSlug.objects.get(slug=self.cave_slug, primary=True).cave
        return c

    def isLogbookEntry(self): # Function used in templates
        return True

    def get_absolute_url(self):
        return urljoin(settings.URL_ROOT, reverse('logbookentry',kwargs={'date':self.date,'slug':self.slug}))

    def __str__(self):
        return f'{self.date}: {self.title}'

    def get_next_by_id(self):
        LogbookEntry.objects.get(id=self.id+1)

    def get_previous_by_id(self):
        LogbookEntry.objects.get(id=self.id-1)

    # def new_QM_number(self):
        # """Returns  """
        # if self.cave:
            # nextQMnumber=self.cave.new_QM_number(self.date.year)
        # else:
            # return None
        # return nextQMnumber

    # def new_QM_found_link(self):
        # """Produces a link to a new QM with the next number filled in and this LogbookEntry set as 'found by' """
        # return settings.URL_ROOT + r'/admin/core/qm/add/?' + r'found_by=' + str(self.pk) +'&number=' + str(self.new_QM_number())

    def DayIndex(self):
        return list(self.expeditionday.logbookentry_set.all()).index(self)

class QM(TroggleModel):
    """This is based on qm.csv in trunk/expoweb/1623/204 which has the fields:
    "Number","Grade","Area","Description","Page reference","Nearest station","Completion description","Comment"
    """
    cave = models.ForeignKey(Cave, related_name='QMs',blank=True, null=True,on_delete=models.SET_NULL )
    block       = models.ForeignKey('SurvexBlock', null=True,on_delete=models.SET_NULL) # only for QMs from survex files
    blockname=models.TextField(blank=True,null=True) # NB truncated copy of survexblock name with last char added
    expoyear    = models.CharField(max_length=4,blank=True, null=True) # could change to datetime if logbooks similarly chnaged
    found_by = models.ForeignKey(LogbookEntry, related_name='QMs_found',blank=True, null=True,on_delete=models.SET_NULL )
    ticked = models.BooleanField(default=False) # for ticked QMs not attached to a logbook entry, should imply completion_description has text
    ticked_off_by = models.ForeignKey(LogbookEntry, related_name='QMs_ticked_off',blank=True, null=True,on_delete=models.SET_NULL) # unused, ever?!
    number = models.IntegerField(help_text="this is the sequential number in the year, only unique for CSV imports", )
    GRADE_CHOICES=(
    ('A', 'A: Large obvious lead'),
    ('B', 'B: Average lead'),
    ('C', 'C: Tight unpromising lead'),
    ('D', 'D: Dig'),
    ('X', 'X: Unclimbable aven')
    ) # also seen "?" and "V" in imported data - see urls.py
    grade = models.CharField(max_length=1, choices=GRADE_CHOICES)
    location_description = models.TextField(blank=True)
    nearest_station_description = models.CharField(max_length=400,blank=True, null=True)
    nearest_station_name = models.CharField(max_length=200,blank=True, null=True)
    nearest_station = models.ForeignKey(SurvexStation,blank=True, null=True,on_delete=models.SET_NULL)
    area = models.CharField(max_length=100,blank=True, null=True)
    completion_description = models.TextField(blank=True,null=True)
    comment=models.TextField(blank=True,null=True)

    def __str__(self):
        return f'{self.code()}'

    def code(self):
        if self.cave:
            cavestr = str(self.cave.slug())[5:]
        else:
            cavestr = ""
        if self.expoyear:
            expoyearstr = str(self.expoyear)
        else:
            expoyearstr = str(self.cave.slug())[5:9]
        if self.blockname:
            blocknamestr = "-" + str(self.blockname)
        else:
            blocknamestr = ""
        return f'{cavestr}-{expoyearstr}-{self.number}{self.grade}{blocknamestr}' 

    def get_completion_url(self):
        '''assumes html file named is in same folder as cave description file
        '''
        cd = None
        if self.completion_description:
            try:
                dir = Path(self.cave.url).parent
                cd = dir / self.completion_description
            except:
                cd = None
        return cd
            
    def newslug(self): 
        qmslug = f'{str(self.cave)}-{self.expoyear}-{self.blockname}{self.number}{self.grade}' 
        return qmslug
        
    def get_absolute_url(self):
        # This reverse resolution stuff is pure magic. Just change the regex in urls.py and everything changes to suit. Whacky.
        return urljoin(settings.URL_ROOT, reverse('qm',kwargs={'cave_id':self.cave.slug(),'year':self.expoyear, 'blockname':self.blockname,'qm_id':self.number,'grade':self.grade}))
            
    def get_next_by_id(self):
        return QM.objects.get(id=self.id+1)

    def get_previous_by_id(self):
        return QM.objects.get(id=self.id-1)
        
class PersonTrip(TroggleModel):
    """Single Person going on a trip, which may or may not be written up.
    It accounts for different T/U for people in same logbook entry.
    """
    personexpedition = models.ForeignKey("PersonExpedition",null=True,on_delete=models.CASCADE)
    time_underground = models.FloatField(help_text="In decimal hours")
    logbook_entry    = models.ForeignKey(LogbookEntry,on_delete=models.CASCADE)
    is_logbook_entry_author = models.BooleanField(default=False)

    def persontrip_next(self):
        futurePTs = PersonTrip.objects.filter(personexpedition = self.personexpedition, logbook_entry__date__gt = self.logbook_entry.date).order_by('logbook_entry__date').all()
        if len(futurePTs) > 0:
            return futurePTs[0]
        else:
            return None

    def persontrip_prev(self):
        pastPTs = PersonTrip.objects.filter(personexpedition = self.personexpedition, logbook_entry__date__lt = self.logbook_entry.date).order_by('-logbook_entry__date').all()
        if len(pastPTs) > 0:
            return pastPTs[0]
        else:
            return None

    def place(self):
        return self.logbook_entry.cave and self.logbook_entry.cave or self.logbook_entry.place

    def __str__(self):
        return f'{self.personexpedition} ({self.logbook_entry.date})'


def GetCaveLookup():
    """A very relaxed way of finding probably the right cave given almost any string which might serve to identify it
    
    lookup function modelled on GetPersonExpeditionNameLookup
    repeated assignment each call, needs refactoring
    
    Used when parsing wallets contents.json file too in views/uploads.py
    
    Does NOT detect duplicates! Needs fixing.
    Needs to be a proper funciton that raises an exception if there is a duplicate.
    OR we could set it to return None if there are duplicates, and require the caller to 
    fall back on doing the actual database query it wants rather thna using  this cache shortcut
    """
    def checkcaveid(cave, id):
        global Gcavelookup
        if id not in Gcavelookup:
            Gcavelookup[id] = cave
            Gcave_count[id] += 1
        else:
            if cave == Gcavelookup[id]:
                pass # same id, same cave
            else: # same id but different cave
                message = f" -  Warning: same alias id '{id:3}' for two  caves '{Gcavelookup[id]}' and '{cave}'. Removing this shorthand alias entirely."
                Gcavelookup.pop(id)
                print(message)
                DataIssue.objects.create(parser='aliases', message=message)
    
    global Gcavelookup
    if Gcavelookup:
        return Gcavelookup
    Gcavelookup = {"NONEPLACEHOLDER": None}
    global Gcave_count
    Gcave_count  = defaultdict(int) # sets default value to int(0)
    
    DataIssue.objects.filter(parser='aliases').delete()
    
    for cave in Cave.objects.all():
        key = cave.official_name.lower()
        if key != "" and key != "unamed" and key != "unnamed":
            Gcavelookup[key] = cave
            Gcave_count[key] += 1   
        if cave.kataster_number:
            checkcaveid(cave,cave.kataster_number) # we do expect 1623/55 and 1626/55 to cause a warning message
            
        # the rest of these are 'nice to have' but may validly already be set
        if cave.unofficial_number:
            unoffn = cave.unofficial_number.lower()
            checkcaveid(cave,unoffn)
             
        if cave.filename:
            # this is the slug - usually.. but  usually done as as f'{cave.area}-{cave.kataster_number}'
            fn = cave.filename.replace(".html","").lower()
            checkcaveid(cave,fn)
                
        if cave.slug():
            # also possibly done already
            slug = cave.slug().lower()
            checkcaveid(cave,slug)

    # These might alse create more duplicate entries
    # Yes, this should be set in, and imported from, settings.py
    aliases =[
        ("1987-02", "267"),
        ("1990-01", "171"),
        ("1990-02", "172"),
        ("1990-03", "173"),
        ("1990-04", "174"),
        ("1990-05", "175"),
        ("1990-06", "176"),
        ("1990-07", "177"),
        ("1990-08", "178"),
        ("1990-09", "179"),
        ("1990-10", "180"),
        ("1990-11", "181"),
        ("1990-12", "182"),
        ("1990-13", "183"),
        ("1990-14", "184"),
        ("1990-18", "188"),
        ("1990-adam", "225"),
        ("1993-01", "200"),
        ("1996-02", "224"),
        ("1996-03", "223"),
        ("1996-04", "222"),
        ("1996wk2", "207"),
        ("1996wk3", "208"),
        ("1996wk5", "219"),
        ("1996wk6", "218"),
        ("1996wk8", "209"),
        ("1996wk11", "268"),
        ("96wk11", "268"),
        ("1998-01", "201"),
        ("1998-03", "210"),
        ("1999-03", "204"),
        ("1999-04", "230"),
        ("1999-10", "162"),
        ("1999-bo-01", "205"),
        ("1999-ob-03", "226"),
        ("1999-ob-04", "227"),
        ("2000-01", "231"),
        ("2000-03", "214"),
        ("2000-04", "220"),
        ("2000-05", "215"),
        ("2000-06", "216"),
        ("2000-07", "217"),
        ("2000-09", "234"),
        ("2000-aa-01", "250"),
        ("2001-04", "239"),
        ("2001-05", "243"),
        ("2002-01", "249"),
        ("2002-02", "234"),
        ("2002-04", "242"),
        ("2002-05", "294"),
        ("2003-01", "256"),
        ("2003-02", "248"),
        ("2003-03", "247"),
        ("2003-04", "241"),
        ("2003-05", "246"),
        ("2003-06", "161"),
        ("2003-08", "240"),
        ("2003-09", "245"),
        ("2003-10", "244"),
        ("2004-01", "269"),
        ("2004-03", "270"),
        ("2004-11", "251"),
        ("2004-12", "161"),
        ("2004-15", "253"),
        ("2004-19", "254"),
        ("2004-20", "255"),
        ("2005-04", "204"),
        ("2005-05", "264"),
        ("2005-07", "257"),
        ("2006-08", "285"),
        ("2006-09", "298"),
        ("2007-71", "271"),
        ("2010-01", "263"),
        ("2010-03", "293"),
        ("2011-01", "292"),
        ("2012-dd-05", "286"),
        ("2012-ns-13", "292"),
        ("2014-neo-01", "273"),
        ("2014-sd-01", "274"),
        ("2014-ms-14", "287"),
        ("2015-mf-06", "288"),
        ("2016-jb-01", "289"),
        ("2017-pw-01", "277"),
        ("2018-dm-07", "359"), # NB this is 1626
        ("2017_cucc_24", "291"), # note _ not -
        ("2017_cucc_23", "295"), # note _ not -
        ("2017_cucc_28", "290"), # note _ not -
        ("bs17", "283"),

        ("1976/b11", "198"),
        ("1976/b8", "197"),
        ("1976/b9", "190"),
        ("b11", "1976/b11"),
        ("b8", "1976/b8"),
        ("b9", "1976/b9"),

        ("2011-01-bs30", "190"),
        ("bs30", "190"),
        ("2011-01", "190"),

        ("quarriesd", "2002-08"),
        ("2002-x11", "2005-08"),
        ("2002-x12", "2005-07"),
        ("2002-x13", "2005-06"),
        ("2002-x14", "2005-05"),

        ("kh", "161"),
        ("161-kh", "161"),
        ("204-steinBH", "204"),
        ("stonebridge", "204"),
        ("hauchhole", "234"),
        ("hauch", "234"),
        ("234-hauch", "234"),
        ("tunnocks", "258"),
        ("balcony", "264"),
        ("balkon", "264"),
        ("fgh", "290"),
        ("gsh", "291"),

        ("homecoming", "2018-dm-07"),
        ("heimkommen", "2018-dm-07"),
        ("Heimkehr", "2018-dm-07"),
        ("99ob02", "1999-ob-02"),
    ]
          
    for i in aliases:
        if i[1] in Gcavelookup:
            if i[0] in Gcavelookup:
                # already set by a different method, but is it the same cave?
                if Gcavelookup[i[0]] == Gcavelookup[i[1]]:
                    pass
                else:
                    Gcave_count[i[0]] += 1
            Gcavelookup[i[0]] = Gcavelookup[i[1]]
        else:
            message = f" *  Coding or cave existence mistake, cave for id '{i[1]}' does not exist. Expecting to set alias '{i[0]}' to it"
            #print(message)
            DataIssue.objects.create(parser='aliases', message=message)
 
    addmore = {}
    for id in Gcavelookup:
        addmore[id.replace("-","_")] = Gcavelookup[id]
        addmore[id.replace("_","-")] = Gcavelookup[id]
        addmore[id.upper()] = Gcavelookup[id]
    Gcavelookup = {**addmore, **Gcavelookup}

    addmore ={}
       
    for c in Gcave_count:
        if Gcave_count[c] > 1:
            message = f" ** Duplicate cave id count={Gcave_count[c]} id:'{Gcavelookup[c]}' cave __str__:'{c}'"
            print(message)
            DataIssue.objects.create(parser='aliases', message=message)
            # logdataissues[Gcavelookup[c]]=message # pending troggle-wide issues logging system

    return Gcavelookup