troggle-unchained/parsers/scans.py
Philip Sargent 31b912f3ca bugfixes
2022-07-22 12:40:42 +03:00

128 lines
4.1 KiB
Python

import sys
import os
import types
import stat
import csv
import re
import datetime
from functools import reduce
import settings
from troggle.core.models.survex import SingleScan, Wallet, DrawingFile
from troggle.core.models.troggle import DataIssue
from troggle.core.utils import save_carefully, GetListDir
'''Searches through all the survey scans directories (wallets) in expofiles, looking for images to be referenced.
'''
contentsjson = "contents.json"
indexhtml = "walletindex.html"
wallet_blank_json = {
"cave": "",
"date": "",
"description url": "/caves",
"description written": False,
"electronic survey": False,
"elev drawn": False,
"elev not required": False,
"name": "",
"people": [
"Unknown"
],
"plan drawn": False,
"plan not required": False,
"qms written": False,
"survex file": [],
"survex not required": False,
"website updated": False}
wallet_blank_html = '''<html><body><H1>Wallet WALLET</H1>
<p>List of trips: <a href="http://expo.survex.com/expedition/YEAR">expedition/YEAR</a>
- troggle-processed .svx files and logbook entries on server</p>
<p>Date: </p><p>People: Unknown,</p>
<p>Cave <a href='http://expo.survex.com/caves/'>Guidebook description</a>
- A description is indicated as being needed, so may need adding into this cave page.
<p>Survex file: not identified yet
<H2>Issues</H2>
<p>The description needs writing</p>
<p>The QMs needs writing</p><p>The website is marked as needing updating (using the guidebook description)</p>
<p>Tunnel / Therion drawing files need drawing</p>
<H2>Files</H2>
<UL>
</UL>
</body></html>
'''
def LoadListScansFile(wallet):
gld = [ ]
# flatten out any directories in these wallet folders - should not be any
for (fyf, ffyf, fisdiryf) in GetListDir(wallet.fpath):
if fisdiryf:
gld.extend(GetListDir(ffyf))
else:
gld.append((fyf, ffyf, fisdiryf))
c=0
for (fyf, ffyf, fisdiryf) in gld:
if re.search(r"\.(?:png|jpg|jpeg|pdf|svg|gif)(?i)$", fyf):
singlescan = SingleScan(ffile=ffyf, name=fyf, wallet=wallet)
singlescan.save()
c+=1
if c>=10:
print(".", end='')
c = 0
# this iterates through the scans directories (either here or on the remote server)
# and builds up the models we can access later
def load_all_scans():
print(' - Loading Survey Scans')
SingleScan.objects.all().delete()
Wallet.objects.all().delete()
print(' - deleting all Wallet and SingleScan objects')
DataIssue.objects.filter(parser='scans').delete()
# first do the smkhs (large kh survey scans) directory
# this seems to be never used ?!
manywallets_smkhs = Wallet(fpath=os.path.join(settings.SCANS_ROOT, "../surveys/smkhs"), walletname="smkhs")
print("smkhs", end=' ')
if os.path.isdir(manywallets_smkhs.fpath):
manywallets_smkhs.save()
LoadListScansFile(manywallets_smkhs)
else:
print("smkhs NOT LOADED", end=' ')
# iterate into the surveyscans directory
print(' - ', end=' ')
for walletname, fpath, fisdir in GetListDir(settings.SCANS_ROOT):
if not fisdir:
continue
# do the year folders
if re.match(r"\d\d\d\d$", walletname):
print(f"{walletname}", end=' ')
for walletname, fpath, fisdir in GetListDir(fpath):
if fisdir:
wallet = Wallet(fpath=fpath, walletname=walletname)
# this is where we should load the contents.json for people so we can report on them later
# this is where we shoudl record the year explicitly
# line 347 of view/uploads.py and needs refactoring for loading contentsjson
wallet.save()
LoadListScansFile(wallet)
# what is this?
elif walletname != "thumbs":
print(f'\n - Wallet {walletname} - {fpath}')
wallet = Wallet(fpath=fpath, walletname=walletname)
wallet.save()
LoadListScansFile(wallet)
else:
print(f'\n - IGNORE {walletname} - {fpath}')
print("", flush=True)