troggle/parsers/locations.py

import copy
import os
import re
import subprocess
import sys
import time
from datetime import datetime, timezone
from pathlib import Path


import troggle.settings as settings
from troggle.core.models.caves import Cave, Entrance
from troggle.core.models.logbooks import QM
from troggle.core.models.survex import SurvexBlock, SurvexFile, SurvexPersonRole, SurvexStation
from troggle.core.models.wallets import Wallet
from troggle.core.models.troggle import DataIssue, Expedition
from troggle.core.utils import chaosmonkey, get_process_memory
from troggle.parsers.logbooks import GetCaveLookup
from troggle.parsers.people import GetPersonExpeditionNameLookup, known_foreigner
from troggle.parsers.survex import stash_data_issue, store_data_issues, ROOTBLOCK

"""Uses the imported data to find the locations of the survey stations labelled as 
entrances
"""

todo = """
- Pending a complete revision of how we handle GPS coordinates of entrances.   
"""

class MapLocations(object):
    """Class used only for identifying the entrance locations
    Formerly used to put locations on a prospecting map
    
    We don't need these map locations any more ?!
    They would only be used in addition to entrances going onto a map display"""

    fp = [
        ("laser.0_7", "BNase", "Reference", "Bräuning Nase laser point"),
        ("226-96", "BZkn", "Reference", "Bräuning Zinken trig point"),
        ("vd1", "VD1", "Reference", "VD1 survey point"),
        ("laser.kt114_96", "HSK", "Reference", "Hinterer Schwarzmooskogel trig point"),
        ("2000", "Nipple", "Reference", "Nipple (Weiße Warze)"),
        ("3000", "VSK", "Reference", "Vorderer Schwarzmooskogel summit"),
        ("topcamp", "OTC", "Reference", "Old Top Camp"),
        ("laser.0", "LSR0", "Reference", "Laser Point 0"),
        ("laser.0_1", "LSR1", "Reference", "Laser Point 0/1"),
        ("laser.0_3", "LSR3", "Reference", "Laser Point 0/3"),
        ("laser.0_5", "LSR5", "Reference", "Laser Point 0/5"),
        ("225-96", "BAlm", "Reference", "Bräuning Alm trig point"),
    ] # 12 fixed points
    
    p = []

    def points(self):
        for ent in Entrance.objects.all():
            for st, ent_type in {ent.other_station: "other", ent.tag_station: "tag"}.items():
                if st != "":
                    self.p.append((st, str(ent), ent.needs_surface_work(), ent))
        store_data_issues()
        message = f" -  {len(self.p)} Survey stations found on Entrance objects - not yet validated against survex .pos file."
        print(message)
        return self.p

    def __str__(self):
        return f"{len(self.p)} ent locations"


def validate_entrance_stations(ent=None):
    """Now that we have the located positions, we can check if the Entrances had correct stations
    """
    bads = 0
    good = 0
    url="/caves" # fallback
    
    def station_lower_case(station):
        nonlocal url
        so = SurvexStation.objects.filter(name=station.lower())
        if so.count() == 1:
           message = f"X - Entrance {ent}  station '{station}' should be '{station.lower()}'"
           stash_data_issue(parser="positions", message=message, url=url)
           print(message)
            
    def validate_ent(ent):
        """For each of the two station strings in an Entrance object,
        validate each string as referring to a valid SurvexStation object.
        But our list of created SurvexStation objects is created by taking a list of strings and using them
        to select from lines in a .pos file - so this is unnecessarily indirect.
        """
        nonlocal bads
        nonlocal good
        # {% url "editentrance" ent.entrance.url_parent cave.slug ent.entrance.slug %}
        # e.g. url = f"/1623/101/1623-101:{ent}_entrance_edit"
        cavelist = ent.cavelist()
        if len(cavelist) == 1:
            cave = cavelist[0]
            url = f"/{cave.url}"     
        elif len(cavelist) > 1:
            cave = cavelist[-1] # set to last in list
            url = f"/{cave.url}"
        else:
            print(f"BUGGER bad cave  '{cavelist}' on Entrance object {ent} ")
            url="/caves"
        for st, ent_type in {ent.other_station: "other", ent.tag_station: "tag"}.items():
            if st == "":
                continue
            try:
                so = SurvexStation.objects.filter(name=st)
            except:
                message = f" ! - Entrance {ent} has invalid '{ent_type}' station '{st}'. EXCEPTION."
                stash_data_issue(parser="positions", message=message, url=url)
                print(message)
                bads +=1
                continue
                
            if so.count() == 1:
                good +=1
                # print(f"OK - Entrance {ent}  '{ent_type}' station '{st}'")
                continue
            if so.count() != 0:
                message =f"{so.count()} found for  Entrance {ent}  '{ent_type}' station '{st}' {so}"
            else:
                message = f" ! - Entrance {ent} has invalid '{ent_type}' station '{st}'"
            if st == ent.best_station():
                message = message + " - AND THIS IS THE 'BEST' ONE"
            else:
                message = message + " - not the 'best'"
            stash_data_issue(parser="positions", message=message, url=url)
            print(message)
            bads +=1
            station_lower_case(st)
            continue
 
                    
    if ent:
        return validate_ent(ent)
    

    for ent in Entrance.objects.all():
        validate_ent(ent)
            
    print(f" -  {good} valid SurvexStations of all types found on Entrances.")     
    print(f" -  {bads} bad   SurvexStations of all types found on Entrances.")     
    return True # not necessarily.. but unused return value
            


poslineregex = re.compile(r"^\(\s*([+-]?\d*\.\d*),\s*([+-]?\d*\.\d*),\s*([+-]?\d*\.\d*)\s*\)\s*([^\s]+)$")

def LoadPositions():
    """First load the survex stations for entrances and fixed points (about 600) into the database.
    Run 'cavern' to produce a complete .3d file, then run 'survexport -pos' to produce a table of
    all survey point positions in UTM cooridnates. Then lookup each of the 600 positions by name to 
    see if we have it in the database and if we do, then save the UTM x/y/z coordinates. 
    This gives us coordinates of the entrances.
    If we don't have it in the database, print an error message and discard it.
    """
    svx_t = 0
    d3d_t = 0
    
    DataIssue.objects.filter(parser="positions").delete()
    SurvexStation.objects.all().delete()


    def runcavern3d():
        outputdir = Path(str(f"{topdata}.svx")).parent

        # print(" -  Regenerating stale cavern .log and .3d for '{}'\n    days old: {:.1f}    {:.1f}    {:.1f}".
        #    format(topdata, (svx_t - d3d_t)/(24*3600), (cav_t - d3d_t)/(24*3600), (now - d3d_t)/(24*3600)))

        file3d = Path(f"{topdata}.3d")
        try:
            sp = subprocess.run(
                [settings.CAVERN, "--log", f"--output={outputdir}", f"{topdata}.svx"],
                capture_output=True,
                check=False,
                text=True,
            )  # check=False means exception not raised
            if sp.returncode != 0:
                message = f" ! Error: cavern: creating {file3d} in runcavern3()"
                stash_data_issue(parser="positions", message=message)
                print(message)

                # find the errors in the 1623.log file
                sp = subprocess.run(
                    ["grep", "error:", f"{topdata}.log"], capture_output=True, check=False, text=True
                )  # check=False means exception not raised
                message = f" ! Error: cavern: {sp.stdout} creating {file3d} "
                stash_data_issue(parser="positions", message=message)
                print(message)

        except:
            message = f" ! CalledProcessError 'cavern' in runcavern3() at {topdata}."
            stash_data_issue(parser="positions", message=message)
            print(message)

            if file3d.is_file():
                message = f" ! CalledProcessError. File permissions {file3d.stat().st_mode} on {str(file3d)}"
                stash_data_issue(parser="positions", message=message)
                print(message)

        if file3d.is_file():  # might be an old one though
            try:
                # print(" -  Regenerating {} {}.3d  in  {}".format(settings.SURVEXPORT, topdata, settings.SURVEX_DATA))
                sp = subprocess.run(
                    [settings.SURVEXPORT, "--pos", f"{file3d}"],
                    cwd=settings.SURVEX_DATA,
                    capture_output=True,
                    check=False,
                    text=True,
                )
                if sp.returncode != 0:
                    print(
                        f" ! Error: survexport creating {topdata}.pos in runcavern3().\n\n"
                        + str(sp.stdout)
                        + "\n\nreturn code: "
                        + str(sp.returncode)
                    )
            except:
                message = f" ! CalledProcessError 'survexport' in runcavern3() at {file3d}."
                stash_data_issue(parser="positions", message=message)
                print(message)
        else:
            message = f" ! Failed to find {file3d} so aborting generation of new .pos, using old one if present"
            stash_data_issue(parser="positions", message=message)
            print(message)

    topdata = os.fspath(Path(settings.SURVEX_DATA) / settings.SURVEX_TOPNAME)
    print(f" - Generating a list of Pos from {topdata}.svx and then loading...")

    found = 0
    print("\n")  # extra line because cavern overwrites the text buffer somehow
    # cavern defaults to using same cwd as supplied input file

    completed_process = subprocess.run(["which", f"{settings.CAVERN}"], capture_output=True, check=True, text=True)
    cav_t = os.path.getmtime(completed_process.stdout.strip())

    svxpath = topdata + ".svx"
    d3dpath = topdata + ".3d"
    pospath = topdata + ".pos"

    svx_t = os.path.getmtime(svxpath)

    if os.path.isfile(d3dpath):
        # always fails to find log file if a double directory, e.g. caves-1623/B4/B4/B4.svx Why ?
        d3d_t = os.path.getmtime(d3dpath)

    now = time.time()
    if not os.path.isfile(pospath):
        runcavern3d()
    if not os.path.isfile(d3dpath):
        runcavern3d()
    elif d3d_t - svx_t > 0:  # stale, 3d older than svx file
        runcavern3d()
    elif now - d3d_t > 24 * 60 * 60:  # >1 days old, re-run anyway
        runcavern3d()
    elif cav_t - d3d_t > 0:  # new version of cavern
        runcavern3d()

    mappoints = {}
    found_points = {}
    pts = MapLocations().points()
    for pt in pts:
        svxid, number, point_type, ent = pt
        #((st, str(ent), ent.needs_surface_work(), ent))
        if svxid in mappoints:
            print(f" =  seen this svxid  {svxid} for {ent} already on entrance {mappoints[svxid]}")
        else:
            mappoints[svxid] = ent
        if svxid =="1":
            print(f"BOGUS {pt}") # this is now checked for when importing the entrance stations in parsers/caves.py

    if not Path(pospath).is_file():
        message = f" ! Failed to find {pospath} so aborting generation of entrance locations. "
        stash_data_issue(parser="positions", message=message, url=f"/entrance_data/{pospath}_edit")
        print(message)
        return

    posfile = open(pospath)
    posfile.readline()  # Drop header
    
    sbdict = {}
    dups = 0
    lineno = 1 # we dropped the header
    for line in posfile.readlines():
        lineno += 1
        r = poslineregex.match(line)
        if r:
            x, y, z, sbid = r.groups() # renamed id to sbid so as to not confuse with Django internal .id
            if sbid in sbdict:
                dups += 1
                message = f" ! DUPLICATE SurvexBlock identifier in .pos file '{sbid}'\n{sbs[sbid]}\n{lineno} / {line}"
                print(message)
                stash_data_issue(parser="positions", message=message)
            else:
                sbdict[sbid] = lineno
 

            for sid in mappoints:
                if sbid.endswith(sid) or sbid.endswith(sid.lower()):
                    blockpath = "." + sbid[: -len(sid)].strip(".") # only the most recent one that is mappoints
                    if sid in found_points:
                        found_points[sid] += 1
                    else:
                        found_points[sid] = 1
                   
                    try:
                        ss = SurvexStation(name=sbid)
                        ss.x = float(x)
                        ss.y = float(y)
                        ss.z = float(z)
                        ss.entrance = mappoints[sid]
                        ss.save()
                        found += 1
                    except:
                        message = f" ! {lineno} FAIL to create SurvexStation Entrance point {blockpath} {sid}"
                        print(message)
                        stash_data_issue(parser="positions", message=message)
                        store_data_issues()
                        raise
    validate_entrance_stations() # do not need to use db here really
    positions_filename = Path(pospath).name
    print(f" -  {found} distinct SurvexStation entrance stations identified in {lineno:,} lines in {positions_filename}.")
    if dups > 0:
        print(f" -  {dups} Duplicated SurvexStation entrances found")
        
    # for p in mappoints:
        # if p not in found_points:
            # print(f"Valid point {p} NOT found in {positions_filename}")
    # print(f" -  {len(mappoints)} mappoints,   {len(found_points)} found_points")
    # for sid in found_points:
        # if found_points[sid] > 1:
            # print(f" -  {sid} - {found_points[sid]}")
    store_data_issues()