2
0
mirror of https://expo.survex.com/repositories/troggle/.git synced 2024-11-24 16:21:53 +00:00
troggle/parsers/caves.py

224 lines
15 KiB
Python
Raw Normal View History

2012-06-10 16:56:12 +01:00
# -*- coding: utf-8 -*-
import os
import re
2020-05-24 01:57:06 +01:00
from django.conf import settings
import troggle.core.models as models
import troggle.core.models_caves as models_caves
2012-06-10 16:56:12 +01:00
def readcaves():
# Clear the cave data issues as we are reloading
2020-06-06 22:51:55 +01:00
# Note: these are HTML files in the EXPOWEB repo, not from the loser repo.
models.DataIssue.objects.filter(parser='caves').delete()
area_1623 = models_caves.Area.objects.update_or_create(short_name = "1623", parent = None)
area_1626 = models_caves.Area.objects.update_or_create(short_name = "1626", parent = None)
print(" - Reading Entrances")
#print "list of <Slug> <Filename>"
2020-05-24 01:57:06 +01:00
for filename in next(os.walk(settings.ENTRANCEDESCRIPTIONS))[2]: #Should be a better way of getting a list of files
if filename.endswith('.html'):
readentrance(filename)
print (" - Reading Caves")
2020-05-24 01:57:06 +01:00
for filename in next(os.walk(settings.CAVEDESCRIPTIONS))[2]: #Should be a better way of getting a list of files
if filename.endswith('.html'):
readcave(filename)
2012-06-10 16:56:12 +01:00
2012-06-10 16:56:12 +01:00
def readentrance(filename):
2020-06-06 22:51:55 +01:00
# Note: these are HTML files in the EXPOWEB repo, not from the loser repo.
2012-06-10 16:56:12 +01:00
with open(os.path.join(settings.ENTRANCEDESCRIPTIONS, filename)) as f:
contents = f.read()
context = "in file %s" % filename
2020-06-12 18:10:07 +01:00
#print("Reading file ENTRANCE {} / {}".format(settings.ENTRANCEDESCRIPTIONS, filename))
2012-06-10 16:56:12 +01:00
entrancecontentslist = getXML(contents, "entrance", maxItems = 1, context = context)
if len(entrancecontentslist) == 1:
entrancecontents = entrancecontentslist[0]
non_public = getXML(entrancecontents, "non_public", maxItems = 1, context = context)
name = getXML(entrancecontents, "name", maxItems = 1, context = context)
slugs = getXML(entrancecontents, "slug", context = context)
entrance_description = getXML(entrancecontents, "entrance_description", maxItems = 1, context = context)
explorers = getXML(entrancecontents, "explorers", maxItems = 1, context = context)
map_description = getXML(entrancecontents, "map_description", maxItems = 1, context = context)
location_description = getXML(entrancecontents, "location_description", maxItems = 1, context = context)
approach = getXML(entrancecontents, "approach", maxItems = 1, context = context)
underground_description = getXML(entrancecontents, "underground_description", maxItems = 1, context = context)
photo = getXML(entrancecontents, "photo", maxItems = 1, context = context)
marking = getXML(entrancecontents, "marking", maxItems = 1, context = context)
marking_comment = getXML(entrancecontents, "marking_comment", maxItems = 1, context = context)
findability = getXML(entrancecontents, "findability", maxItems = 1, context = context)
findability_description = getXML(entrancecontents, "findability_description", maxItems = 1, context = context)
alt = getXML(entrancecontents, "alt", maxItems = 1, context = context)
northing = getXML(entrancecontents, "northing", maxItems = 1, context = context)
easting = getXML(entrancecontents, "easting", maxItems = 1, context = context)
tag_station = getXML(entrancecontents, "tag_station", maxItems = 1, context = context)
exact_station = getXML(entrancecontents, "exact_station", maxItems = 1, context = context)
other_station = getXML(entrancecontents, "other_station", maxItems = 1, context = context)
other_description = getXML(entrancecontents, "other_description", maxItems = 1, context = context)
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, state = models_caves.Entrance.objects.update_or_create(name = name[0],
2012-06-10 16:56:12 +01:00
non_public = {"True": True, "False": False, "true": True, "false": False,}[non_public[0]],
entrance_description = entrance_description[0],
explorers = explorers[0],
map_description = map_description[0],
location_description = location_description[0],
approach = approach[0],
underground_description = underground_description[0],
photo = photo[0],
marking = marking[0],
marking_comment = marking_comment[0],
findability = findability[0],
findability_description = findability_description[0],
alt = alt[0],
northing = northing[0],
easting = easting[0],
tag_station = tag_station[0],
exact_station = exact_station[0],
other_station = other_station[0],
other_description = other_description[0],
bearings = bearings[0],
url = url[0],
filename = filename,
cached_primary_slug = slugs[0])
primary = True
for slug in slugs:
2020-06-12 18:10:07 +01:00
#print("entrance slug:{} filename:{}".format(slug, filename))
try:
cs = models_caves.EntranceSlug.objects.update_or_create(entrance = e,
slug = slug,
primary = primary)
except:
# need to cope with duplicates
print(" ! FAILED to get only one ENTRANCE when updating using: "+filename)
kents = models_caves.EntranceSlug.objects.all().filter(entrance = e,
slug = slug,
primary = primary)
for k in kents:
message = " ! - DUPLICATE in db. entrance:"+ str(k.entrance) + ", slug:" + str(k.slug())
models.DataIssue.objects.create(parser='caves', message=message)
print(message)
2020-06-13 01:26:28 +01:00
for k in kents:
2020-06-12 18:10:07 +01:00
if k.slug() != None:
print(" ! - OVERWRITING this one: slug:"+ str(k.slug()))
k.notes = "DUPLICATE entrance found on import. Please fix\n" + k.notes
c = k
2012-06-10 16:56:12 +01:00
primary = False
def readcave(filename):
2020-06-06 22:51:55 +01:00
# Note: these are HTML files in the EXPOWEB repo, not from the loser repo.
2012-06-10 16:56:12 +01:00
with open(os.path.join(settings.CAVEDESCRIPTIONS, filename)) as f:
contents = f.read()
context = " in file %s" % filename
2020-06-12 18:10:07 +01:00
#print("Reading file CAVE {}".format(filename))
2012-06-10 16:56:12 +01:00
cavecontentslist = getXML(contents, "cave", maxItems = 1, context = context)
#print cavecontentslist
if len(cavecontentslist) == 1:
cavecontents = cavecontentslist[0]
non_public = getXML(cavecontents, "non_public", maxItems = 1, context = context)
slugs = getXML(cavecontents, "caveslug", maxItems = 1, context = context)
official_name = getXML(cavecontents, "official_name", maxItems = 1, context = context)
areas = getXML(cavecontents, "area", context = context)
kataster_code = getXML(cavecontents, "kataster_code", maxItems = 1, context = context)
kataster_number = getXML(cavecontents, "kataster_number", maxItems = 1, context = context)
unofficial_number = getXML(cavecontents, "unofficial_number", maxItems = 1, context = context)
explorers = getXML(cavecontents, "explorers", maxItems = 1, context = context)
underground_description = getXML(cavecontents, "underground_description", maxItems = 1, context = context)
equipment = getXML(cavecontents, "equipment", maxItems = 1, context = context)
references = getXML(cavecontents, "references", maxItems = 1, context = context)
survey = getXML(cavecontents, "survey", maxItems = 1, context = context)
kataster_status = getXML(cavecontents, "kataster_status", maxItems = 1, context = context)
underground_centre_line = getXML(cavecontents, "underground_centre_line", maxItems = 1, context = context)
notes = getXML(cavecontents, "notes", maxItems = 1, context = context)
length = getXML(cavecontents, "length", maxItems = 1, context = context)
depth = getXML(cavecontents, "depth", maxItems = 1, context = context)
extent = getXML(cavecontents, "extent", maxItems = 1, context = context)
survex_file = getXML(cavecontents, "survex_file", maxItems = 1, context = context)
description_file = getXML(cavecontents, "description_file", maxItems = 1, context = context)
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:
try:
c, state = models_caves.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],
unofficial_number = unofficial_number[0],
explorers = explorers[0],
underground_description = underground_description[0],
equipment = equipment[0],
references = references[0],
survey = survey[0],
kataster_status = kataster_status[0],
underground_centre_line = underground_centre_line[0],
notes = notes[0],
length = length[0],
depth = depth[0],
extent = extent[0],
survex_file = survex_file[0],
description_file = description_file[0],
url = url[0],
filename = filename)
except:
# need to cope with duplicates
2020-06-12 18:10:07 +01:00
print(" ! FAILED to get only one CAVE when updating using: "+filename)
kaves = models_caves.Cave.objects.all().filter(kataster_number=kataster_number[0])
for k in kaves:
message = " ! - DUPLICATES in db. kataster:"+ str(k.kataster_number) + ", slug:" + str(k.slug())
models.DataIssue.objects.create(parser='caves', message=message)
print(message)
for k in kaves:
if k.slug() != None:
print(" ! - OVERWRITING this one: slug:"+ str(k.slug()))
k.notes = "DUPLICATE kataster number found on import. Please fix\n" + k.notes
c = k
2012-06-10 16:56:12 +01:00
for area_slug in areas:
area = models_caves.Area.objects.filter(short_name = area_slug)
2012-06-10 16:56:12 +01:00
if area:
newArea = area[0]
else:
newArea = models_caves.Area(short_name = area_slug, parent = models_caves.Area.objects.get(short_name = "1623"))
2012-06-10 16:56:12 +01:00
newArea.save()
c.area.add(newArea)
primary = True
for slug in slugs:
try:
cs = models_caves.CaveSlug.objects.update_or_create(cave = c,
2012-06-10 16:56:12 +01:00
slug = slug,
primary = primary)
except:
message = " ! Cave update/create failure: %s, skipping file %s" % (slug, context)
models.DataIssue.objects.create(parser='caves', message=message)
print(message)
2012-06-10 16:56:12 +01:00
primary = False
for entrance in entrances:
slug = getXML(entrance, "entranceslug", maxItems = 1, context = context)[0]
letter = getXML(entrance, "letter", maxItems = 1, context = context)[0]
try:
entrance = models_caves.Entrance.objects.get(entranceslug__slug = slug)
ce = models_caves.CaveAndEntrance.objects.update_or_create(cave = c, entrance_letter = letter, entrance = entrance)
except:
message = " ! Entrance setting failure, slug: %s letter: %s" % (slug, letter)
models.DataIssue.objects.create(parser='caves', message=message)
print(message)
2012-06-10 16:56:12 +01:00
def getXML(text, itemname, minItems = 1, maxItems = None, printwarnings = True, context = ""):
items = re.findall("<%(itemname)s>(.*?)</%(itemname)s>" % {"itemname": itemname}, text, re.S)
if len(items) < minItems and printwarnings:
2020-04-27 23:51:41 +01:00
message = " ! %(count)i %(itemname)s found, at least %(min)i expected" % {"count": len(items),
2012-06-10 16:56:12 +01:00
"itemname": itemname,
"min": minItems} + context
models.DataIssue.objects.create(parser='caves', message=message)
print(message)
2012-06-10 16:56:12 +01:00
if maxItems is not None and len(items) > maxItems and printwarnings:
2020-04-27 23:51:41 +01:00
message = " ! %(count)i %(itemname)s found, no more than %(max)i expected" % {"count": len(items),
2012-06-10 16:56:12 +01:00
"itemname": itemname,
"max": maxItems} + context
models.DataIssue.objects.create(parser='caves', message=message)
print(message)
return items