import os import re import stat from pathlib import Path from urllib.parse import unquote as urlunquote from urllib.parse import urljoin from django.conf import settings from django.http import HttpResponse from django.shortcuts import render from troggle.core.models.survex import DrawingFile from troggle.core.views.expo import getmimetype # import parsers.surveys """Some of these views serve files as binary blobs, and simply set the mime type based on the file extension, as does the urls.py dispatcher which sends them here. Here they should actually have the filetype checked by looking inside the file before being served. """ todo = """- Need to check if invalid query string is invalid, or produces multiple replies and render a user-friendly error page. """ def unescape(input): """These look like HTML entities, but they are not. They are tunnel-specific encodings""" codes = { "&space;": " ", """: '"', "&tab;": "\t", "&backslash;": "\\", "&newline;": "\n|\t", "&apostrophe": "'", } for c in codes: # print(c, codes[c]) input = input.replace(c, codes[c]) return input def dwgallfiles(request): """Report on all the drawing files in the system. These were loaded by parsing the entire directory tree""" dwgfiles = DrawingFile.objects.all() return render(request, "dwgfiles.html", {"dwgfiles": dwgfiles, "settings": settings}) def dwgfilesingle(request, path): """sends a single binary file to the user. It could be an old PNG, PDF or SVG not just Tunnel or Therion The db records created on datbase reset import are not used when we look for an individual drawing, only collections of them. Note the infelicity that this will deliver files that exist, but are hidden on the previous webpage /dwgupload/... if the user types the filename into the browser bar. Could be a problem? Should we validate using uploads.py dwgvaliddisp() here too? """ tfile = Path(settings.DRAWINGS_DATA, path.replace(":", "#")) if not tfile.is_file(): message = f"Drawing file not found in filesystem at '{path}' \n\t\tMaybe a new dataimport needs to be done to get up to date." return render(request, "errors/generic.html", {"message": message}) if Path(tfile).suffix in [ ".xml" ]: # tunnel files are usually 'us-ascii' (!). And may not close all XML tags properly either. for encoding in ["us-ascii", "iso-8859-1", "utf-8"]: try: # print(f'attempting {encoding} for {tfile}') with open(tfile, encoding=encoding, errors="strict") as f: print(f"- before reading any {encoding}") lines = f.readlines() # print(f'- finished reading {encoding}') clean = [] for l in lines: clean.append(unescape(l)) # deals with strangely embedded survex file # print(f'- Cleaned and stripped.') try: return HttpResponse(content=clean, content_type="text/xml") except: return HttpResponse( content=f"Render fail for this file: {tfile} Please report to a nerd. Probably Julian's fault." ) except: print(f"! Exception when reading {encoding}") continue print(f"! None of those encodings worked for {tfile}") try: return HttpResponse(content=open(tfile, errors="ignore"), content_type=getmimetype(tfile)) except: return HttpResponse( content=f"Unable to understand the encoding for this file: {tfile} Please report to a nerd." ) if Path(tfile).suffix in ["th2", ".th"]: try: return HttpResponse(content=open(tfile, errors="strict"), content_type="text/txt") # default utf-8 except: return HttpResponse( content=f"Unable to understand the encoding for this file: {tfile} Please report to a nerd." ) else: # SVG, JPG etc try: return HttpResponse(content=open(tfile, mode="rb"), content_type=getmimetype(tfile)) # default utf-8 except: try: return HttpResponse(content=open(tfile, mode="rb")) except: return HttpResponse( content=f"Unable to understand the encoding '{getmimetype(tfile)}' for this file: {tfile} Note that Apache will do its own thing here. Please report to a nerd." )