troggle/core/models/caves.py

import os
import os
import re
from collections import defaultdict
from datetime import datetime, timezone
from pathlib import Path

from django.db import models
from django.template import loader

import settings
from troggle.core.models.logbooks import QM
from troggle.core.models.survex import SurvexStation
from troggle.core.models.troggle import DataIssue, TroggleModel
from troggle.core.utils import TROG, writetrogglefile

# Use the TROG global object to cache the cave lookup list. No good for multi-user..
Gcavelookup = TROG["caves"]["gcavelookup"]
Gcave_count = TROG["caves"]["gcavecount"]

Gcavelookup = None
Gcave_count = None

"""The model declarations for Areas, Caves and Entrances
"""

todo = """
- Find out why we have separate objects CaveSlug 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??
  
- Can we rewrite things to eliminate the CaveSlug and objects? Surely
  foreign keys work fine ?!
  
- Why do we have CaveAndEntrance objects ? Surely entranceletter belong son the Entrance object?

- move the aliases list from the code and put into an editable file
  
- 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):
    """This class is ONLY used to create a FormSet for editing the cave and all its
    entrances in one form.
    CASCADE means that if the cave or the entrance is deleted, then this CaveAndEntrance 
    is deleted too
    """
    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)

    class Meta:
        unique_together = [["cave", "entrance"], ["cave", "entrance_letter"]]
        ordering = ["entrance_letter"]

    def __str__(self):
        return str(self.cave) + str(self.entrance_letter)

# class CaveSlug(models.Model):
# moved to models/logbooks.py to avoid cyclic import problem

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

    # 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):
        """This is almost certainly a fossil - needs checking...
        """
        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_filcavee:
            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 number(self):
        if self.kataster_number:
            return self.kataster_number
        else:
            return self.unofficial_number

    def reference(self):
        return f"{self.kat_area()}-{self.number()}"

    def get_absolute_url(self):
        if self.kataster_number:
            pass
        elif self.unofficial_number:
            pass
        else:
            self.official_name.lower()
        return Path(settings.URL_ROOT) / self.url  # not good Django style.. NEEDS actual URL

    def url_parent(self):
        return self.url.rsplit("/", 1)[0]

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

    def get_open_QMs(self):
        """Searches for all QMs that reference this cave."""
        # qms = self.qm_set.all().order_by('expoyear', 'block__date')
        qms = QM.objects.filter(cave=self).order_by(
            "expoyear", "block__date"
        )  # a QuerySet, see https://docs.djangoproject.com/en/dev/ref/models/querysets/#order-by
        qmsopen = qms.filter(ticked=False)
        return qmsopen  # a QuerySet

    def get_ticked_QMs(self):
        """Searches for all QMs that reference this cave."""
        qms = QM.objects.filter(cave=self).order_by(
            "expoyear", "block__date"
        )  
        qmticked = qms.filter(ticked=True)
        return qmticked  # a QuerySet

    def get_QMs(self):
        qms = self.get_open_QMs() | self.get_ticked_QMs() # set union operation
        return qms  # a QuerySet
        
    def kat_area(self):
        try:
            for a in self.area.all():
                if a.kat_area():
                    return a.kat_area()
        except:
            return ""

    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")
        now = datetime.now(timezone.utc)
        print(now)
        c = dict({"cave": self, "date": now})
        u = t.render(c)
        writetrogglefile(filepath, u)
        return

    def file_output(self):
        filepath = Path(os.path.join(settings.CAVEDESCRIPTIONS, self.filename))

        t = loader.get_template("dataformat/cave.xml")
        now = datetime.now(timezone.utc)
        c = dict({"cave": self, "date": now})
        content = t.render(c)
        return (filepath, content, "utf8")

    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 Entrance(TroggleModel):
    MARKING_CHOICES = (
        ("P", "Paint"),
        ("P?", "Paint (?)"),
        ("T", "Tag"),
        ("T?", "Tag (?)"),
        ("R", "Needs Retag"),
        ("S", "Spit"),
        ("S?", "Spit (?)"),
        ("U", "Unmarked"),
        ("?", "Unknown"),
    )    
    FINDABLE_CHOICES = (("?", "To be confirmed ..."), ("S", "Coordinates"), ("L", "Lost"), ("R", "Refindable"))
    alt = models.TextField(blank=True, null=True)
    approach = models.TextField(blank=True, null=True)
    bearings = models.TextField(blank=True, null=True)
    easting = models.TextField(blank=True, null=True)
    entrance_description = models.TextField(blank=True, null=True)
    exact_station = models.TextField(blank=True, null=True)
    explorers = models.TextField(blank=True, null=True)
    filename = models.CharField(max_length=200)
    findability = models.CharField(max_length=1, choices=FINDABLE_CHOICES, blank=True, null=True)
    findability_description = models.TextField(blank=True, null=True)
    lastvisit = models.TextField(blank=True, null=True)
    lat_wgs84 = models.TextField(blank=True, null=True)
    location_description = models.TextField(blank=True, null=True)
    long_wgs84 = models.TextField(blank=True, null=True)
    map_description = models.TextField(blank=True, null=True)
    marking = models.CharField(max_length=2, choices=MARKING_CHOICES)
    marking_comment = models.TextField(blank=True, null=True)
    name = models.CharField(max_length=100, blank=True, null=True)
    northing = models.TextField(blank=True, null=True)
    other_description = models.TextField(blank=True, null=True)
    other_station = models.TextField(blank=True, null=True)
    photo = models.TextField(blank=True, null=True)
    slug = models.SlugField(max_length=50, unique=True, default="default_slug_id")
    tag_station = models.TextField(blank=True, null=True)
    underground_description = models.TextField(blank=True, null=True)
    url = models.CharField(max_length=200, blank=True, null=True)

    class Meta:
        ordering = ["caveandentrance__entrance_letter"]

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

    def exact_location(self):
        return SurvexStation.objects.get(name = self.exact_station)

    def other_location(self):
        return SurvexStation.objects.get(name = 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 + f"{s.x:0.0f}E {s.y:0.0f}N {s.z:0.0f}Alt"
            except:
                return r + f"{self.tag_station} Tag Station not in dataset"
        if self.exact_station:
            try:
                s = SurvexStation.objects.lookup(self.exact_station)
                return r + f"{s.x:0.0f}E {s.y:0.0f}N {s.z:0.0f}Alt"
            except:
                return r + f"{self.tag_station} Exact Station not in dataset"
        if self.other_station:
            try:
                s = SurvexStation.objects.lookup(self.other_station)
                return r + f"{s.x:0.0f}E {s.y:0.0f}N {s.z:0.0f}Alt {self.other_description}"
            except:
                return r + f"{self.tag_station} Other Station not in dataset"
        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.get(name = 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):
        res = "/".join((self.get_root().cave.get_absolute_url(), self.title))
        return res

    def cavelist(self):
        rs = []
        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 file_output(self):
        filepath = Path(os.path.join(settings.ENTRANCEDESCRIPTIONS, self.filename))

        t = loader.get_template("dataformat/entrance.xml")
        now = datetime.now(timezone.utc)
        c = dict({"entrance": self, "date": now})
        content = t.render(c)
        return (filepath, content, "utf8")

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

        t = loader.get_template("dataformat/entrance.xml")
        now = datetime.now(timezone.utc)
        c = dict({"entrance": self, "date": now})
        u = t.render(c)
        writetrogglefile(filepath, u)
        return

    def url_parent(self):
        if self.url:
            return self.url.rsplit("/", 1)[0]
        else:
            cavelist = self.cavelist()
            if len(self.cavelist()) == 1:
                return cavelist[0].url_parent()
            else:
                return ""
             
    def latlong(self):
        station = None
        if self.other_station:
            try:
                station = SurvexStation.objects.get(name = self.other_station)
            except:
                pass
        if self.tag_station:
            try:
                station = SurvexStation.objects.get(name = self.tag_station)
            except:
                pass
        if self.exact_station:
            try:
                station = SurvexStation.objects.get(name = self.exact_station)
            except:
                pass
        if station:
            return station.latlong()


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