summaryrefslogtreecommitdiffstats
path: root/core/views/expo.py
blob: 2b769db7417b584c61a4381d75ca0c176565901f (plain)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
import os
import re
import subprocess
from pathlib import Path
from urllib.parse import urljoin, unquote as urlunquote
from urllib.request import urlopen

from django.shortcuts import render, redirect
from django.http import HttpResponse, HttpResponseRedirect, Http404
from django.urls import reverse, resolve
from django.template import Context, loader
from django.views.decorators.csrf import ensure_csrf_cookie
from django.contrib import admin

import django.forms as forms

from .auth import login_required_if_public
from troggle.core.models.caves import Cave
import troggle.core.views.caves
import troggle.settings as settings

'''Formerly a separate package called 'flatpages' written by Martin Green 2011. 
This was NOT django.contrib.flatpages which stores HTML in the database, so the name was changed to expopages.
Then it was incorporated into troggle directly, rather than being an unnecessary external package.
'''

default_head = '''<head>
<meta http-equiv="Content-Type" content="text/html; charset=iso-8859-1" />
<title>CUCC Expedition -  index</title>
<link rel="stylesheet" type="text/css" href="../css/main2.css" />
<link rel="stylesheet" type="text/css" href="../../css/main2.css" />
<link rel="stylesheet" type="text/css" href="../../../css/main2.css" />
</head>
<body>
<h1>Expo</h1>
<h2 id="tophead">CUCC Expedition</h2>

<ul id="links">
<li><a href="/index.htm">Home</a></li>
<li><a href="/infodx.htm">Main Index</a></li>
<li><a href="/handbook/index.htm">Handbook</a></li>
<li><a href="/handbook/computing/onlinesystems.html">Online systems</a></li>
<li><a href="/pubs.htm">Reports</a></li>
<li><a href="/areas.htm">Areas</a></li>
<li><a href="/caves">Caves</a></li>
<li><a href="/expedition/2019">Troggle</a></li>
<li><form name=P method=get action="/search" target="_top">
    <input id="omega-autofocus" type=search name=P size=8 autofocus>
    <input type=submit value="Search"></li>
</ul>''' # this gets overwritten by templates/menu.html by django for most normal pages

def expofiles_redirect(request, filepath):
    '''This is used only when running as a test system without a local copy of /expofiles/
    when settings.EXPOFILESREMOTE is True
    '''
    return redirect(urljoin('http://expo.survex.com/expofiles/', filepath))

def map(request):
    '''Serves unadorned the expoweb/map/map.html file
    '''
    fn = Path(settings.EXPOWEB, 'map', 'map.html')
    return HttpResponse(content=open(fn, "r"),content_type='text/html')

def mapfile(request, path):
    '''Serves unadorned file
    '''
    fn = Path(settings.EXPOWEB, 'map', path)
    return HttpResponse(content=open(fn, "r"),content_type=getmimetype(fn))

def expofilessingle(request, filepath):
    '''sends a single binary file to the user, if not found, show the parent directory
    If the path actually is a directory, then show that.
    '''
    #print(f' - expofilessingle {filepath}')
    if filepath =="" or filepath =="/":
        return expofilesdir(request, settings.EXPOFILES, "")

    fn=urlunquote(filepath)
    fn = Path(settings.EXPOFILES,filepath)
    if fn.is_dir():
        return expofilesdir(request, Path(fn), Path(filepath))
    if fn.is_file():
        return HttpResponse(content=open(fn, "rb"),content_type=getmimetype(filepath)) # any file
    else:
        # not a file, so show parent directory - DANGER need to check this is limited to below expofiles
        if Path(fn).parent == Path(settings.EXPOFILES).parent:
            return expofilesdir(request, Path(settings.EXPOFILES), Path(filepath).parent)
        else:
            return expofilesdir(request, Path(fn).parent, Path(filepath).parent)

def expofilesdir(request, dirpath, filepath):
    '''does a directory display. If there is an index.html file we should display that.
    - dirpath is a full Path() resolved including local machine /expofiles/
    - filepath is a Path() and it does not have /expofiles/ in it
    '''
    #print(f' - expofilesdir {dirpath} settings.EXPOFILESREMOTE: {settings.EXPOFILESREMOTE}')
    if filepath:
        urlpath = 'expofiles' / Path(filepath)
    else:
        urlpath = Path('expofiles')
    try:
        for f in dirpath.iterdir():
            pass
    except FileNotFoundError:
        #print(f' - expofilesdir error {dirpath}')
        return expofilesdir(request, dirpath.parent, filepath.parent)
        
    fileitems = []
    diritems = []    
    for f in dirpath.iterdir():
        if f.is_dir():
             diritems.append((urlpath / f.parts[-1], str(f.parts[-1])))
        else:
            # if f.parts[-1].lower() == 'index.htm' or f.parts[-1].lower() == 'index.html': # css cwd problem
                # return HttpResponse(content=open(f, "rb"),content_type=getmimetype(filepath)) # any file
                # return expofilessingle(request, str(Path(filepath /  f.parts[-1])))             
            fileitems.append((Path(urlpath) / f.parts[-1], str(f.parts[-1]), getmimetype(f)))
    return render(request, 'dirdisplay.html', { 'filepath': urlpath, 'fileitems':fileitems, 'diritems': diritems,'settings': settings })

def expowebpage(request, expowebpath, path):
    '''Adds menus and serves an HTML page
    '''
    if not Path(expowebpath / path).is_file():
        # Should not get here if the path has suffix "_edit"
        print(f' - 404 error in expowebpage() {path}')
        return render(request, 'pagenotfound.html', {'path': path}, status="404")
        
    try:
        with open(os.path.normpath(expowebpath / path), "r") as o:   
            html = o.read()
    except:
        try:
            with open(os.path.normpath(expowebpath / path), "rb") as o:   
                html = str(o.read()).replace("<h1>","<h1>BAD NON-UTF-8 characters here - ")
        except:
            return HttpResponse(default_head +  '<h3>UTF-8 Parsing Failure:<br>Page could not be parsed using UTF-8:<br>failure detected in expowebpage in views.expo.py</h3> Please edit this <var>:expoweb:</var> page to replace dubious umlauts and &pound; symbols with correct HTML entities e.g. <em>&amp;pound;;</em>. </body' )
   
    m = re.search(r'(.*)<\s*head([^>]*)>(.*)<\s*/head\s*>(.*)<\s*body([^>]*)>(.*)<\s*/body\s*>(.*)', html, re.DOTALL + re.IGNORECASE)
    if m:
        preheader, headerattrs, head, postheader, bodyattrs, body, postbody = m.groups()
    else:
        return HttpResponse(default_head +  html + '<h3>HTML Parsing failure:<br>Page could not be parsed into header and body:<br>failure detected in expowebpage in views.expo.py</h3> Please edit this <var>:expoweb:</var> page to be in the expected full  HTML format </body' )
    m = re.search(r"<title>(.*)</title>", head, re.DOTALL + re.IGNORECASE)
    if m:
        title, = m.groups()
    else:
        title = ""
    m = re.search(r"^<meta([^>]*)noedit", head, re.DOTALL + re.IGNORECASE)
    if m:
        editable = False
    else:
        editable = os.access(Path(expowebpath / path), os.W_OK) # are file permissions writeable?
    
    has_menu = False
    menumatch = re.match(r'(.*)<div id="menu">', body, re.DOTALL + re.IGNORECASE)
    if menumatch:
        has_menu = True
    menumatch = re.match(r'(.*)<ul id="links">', body, re.DOTALL + re.IGNORECASE)
    if menumatch:
        has_menu = True
    return render(request, 'expopage.html', {'editable': editable, 'path': path, 'title': title, 
                'body': body, 'homepage': (path == "index.htm"), 'has_menu': has_menu})
 
def mediapage(request, subpath=None, doc_root=None):
    '''This is for special prefix paths /photos/ /site_media/, /static/ etc.
    as defined in urls.py . If given a directory, gives a failure page. 
    '''
    #print(" - XXXXX_ROOT: {}  ...{}".format(doc_root, subpath))
    if doc_root is not None:
        filetobeopened = Path(doc_root, subpath)
        if filetobeopened.is_dir():
            return render(request, 'nodirlist.html', {'path': subpath})
        try:
            return HttpResponse(content=open(filetobeopened, "rb"), content_type=getmimetype(subpath))
        except IOError:
            return render(request, 'pagenotfound.html', {'path': subpath}, status="404")
    else:
        return render(request, 'pagenotfound.html', {'path': subpath}, status="404")
  


def expopage(request, path):
    '''Either renders an HTML page from expoweb with all the menus,
    or serves an unadorned binary file with mime type
    '''
    #print(" - EXPOPAGES delivering the file: '{}':{} as MIME type: {}".format(request.path, path,getmimetype(path)),flush=True)

    if path.startswith("noinfo") and settings.PUBLIC_SITE and not request.user.is_authenticated:
        return HttpResponseRedirect(urljoin(reverse("auth_login"),'?next={}'.format(request.path)))

    if path.startswith("admin/"):
        # don't even attempt to handle these sorts of mistakes
        return HttpResponseRedirect("/admin/")

    expowebpath = Path(settings.EXPOWEB)

    if path == "":
        return expowebpage(request, expowebpath, "index.htm")

    if path.endswith(".htm") or path.endswith(".html"):
        return expowebpage(request, expowebpath, path)
    
    if Path(expowebpath / path ).is_dir():
        for p in ["index.html", "index.htm"]:
            if (expowebpath / path / p).is_file():
                # This needs to reset the path to the new subdirectory
                return HttpResponseRedirect('/'+str(Path(path) / p))
        return render(request, 'pagenotfound.html', {'path': Path(path) / "index.html"}, status="404")
        
    if path.endswith("/"):
        # we already know it is not a directory.
        # the final / may have been appended by middleware if there was no page without it
        # do not redirect to a file path without the slash as we may get in a loop. Let the user fix it:
        return render(request, 'dirnotfound.html', {'path': path, 'subpath': path[0:-1]})
    
    # So it must be a file in  /expoweb/ but not .htm or .html probably an image
    filetobeopened = os.path.normpath(expowebpath / path)
    
    try:
        return HttpResponse(content=open(filetobeopened, "rb"), content_type=getmimetype(path))
    except IOError:
        return render(request, 'pagenotfound.html', {'path': path}, status="404")
 
 

def getmimetype(path):
    '''Our own version rather than relying on what is provided by the python library. Note that when
    Apache or nginx is used to deliver /expofiles/ it will use it's own idea of mimetypes and
    not these.
    '''
    path = str(path)
    if path.lower().endswith(".css"): return "text/css"
    if path.lower().endswith(".txt"): return "text/css"
    if path.lower().endswith(".js"): return "application/javascript"
    if path.lower().endswith(".json"): return "application/javascript"
    if path.lower().endswith(".ico"): return "image/vnd.microsoft.icon"
    if path.lower().endswith(".png"): return "image/png"
    if path.lower().endswith(".tif"): return "image/tif"
    if path.lower().endswith(".gif"): return "image/gif"
    if path.lower().endswith(".jpeg"): return "image/jpeg"
    if path.lower().endswith(".jpg"): return "image/jpeg"
    if path.lower().endswith("svg"): return "image/svg+xml"
    if path.lower().endswith("xml"): return "application/xml" # we use "text/xhtml" for tunnel files
    if path.lower().endswith(".pdf"): return "application/pdf"
    if path.lower().endswith(".ps"): return "application/postscript"
    if path.lower().endswith(".svx"): return "application/x-survex-svx"
    if path.lower().endswith(".3d"): return "application/x-survex-3d"
    if path.lower().endswith(".pos"): return "application/x-survex-pos"
    if path.lower().endswith(".err"): return "application/x-survex-err"
    if path.lower().endswith(".odt"): return "application/vnd.oasis.opendocument.text"
    if path.lower().endswith(".ods"): return "application/vnd.oasis.opendocument.spreadsheet"
    if path.lower().endswith(".docx"): return "application/vnd.openxmlformats-officedocument.wordprocessingml.document"
    if path.lower().endswith(".xslx"): return "application/vnd.openxmlformats-officedocument.spreadsheetml.sheet"
    if path.lower().endswith(".gz"): return "application/x-7z-compressed"
    if path.lower().endswith(".7z"): return "application/x-7z-compressed"
    if path.lower().endswith(".zip"): return "application/zip"
    return ""

@login_required_if_public
@ensure_csrf_cookie
def editexpopage(request, path):
    '''Manages the 'Edit this Page' capability for expo handbook and other html pages.
    Relies on HTML5 or javascript to provide the in-browser editing environment.
    '''
    try:
        # if a cave not a webpage at all. 
        r = Cave.objects.get(url = path)
        return troggle.core.views.caves.editCave(request, r.cave.slug)
    except Cave.DoesNotExist:
        pass

    try:
        filepath = Path(settings.EXPOWEB) / path
        o = open(filepath, "r")
        html = o.read()
        autogeneratedmatch = re.search(r"\<\!--\s*(.*?(Do not edit|It is auto-generated).*?)\s*--\>", html, re.DOTALL + re.IGNORECASE)
        if autogeneratedmatch:
            return HttpResponse(autogeneratedmatch.group(1))
        m = re.search(r"(.*)<head([^>]*)>(.*)</head>(.*)<body([^>]*)>(.*)</body>(.*)", html, re.DOTALL + re.IGNORECASE)
        if m:
            filefound = True
            preheader, headerargs, head, postheader, bodyargs, body, postbody = m.groups()
            linksmatch = re.match(r'(.*)(<ul\s+id="links">.*)', body, re.DOTALL + re.IGNORECASE)
            if linksmatch:
                body, links = linksmatch.groups()
#            if re.search(r"iso-8859-1", html):
#                body = str(body, "iso-8859-1")
        else:
            return HttpResponse(default_head +  html + '<h3>HTML Parsing failure:<br>Page could not be parsed into header and body:<br>failure detected in expowebpage in views.expo.py</h3> Please edit this <var>:expoweb:</var> page to be in the expected full  HTML format .</body' )
    except IOError:
        print("### File not found ### ", filepath)
        filefound = False
        

    if request.method == 'POST': # If the form has been submitted...
        pageform = ExpoPageForm(request.POST) # A form bound to the POST data
        if pageform.is_valid():# Form valid therefore write file
            print("### \n", str(pageform)[0:300])
            print("### \n csrfmiddlewaretoken: ",request.POST['csrfmiddlewaretoken'])
            if filefound:
                headmatch =  re.match(r"(.*)<title>.*</title>(.*)", head, re.DOTALL + re.IGNORECASE)
                if headmatch:
                    head = headmatch.group(1) + "<title>" + pageform.cleaned_data["title"] + "</title>" + headmatch.group(2)
                else:
                    head = "<title>" + pageform.cleaned_data["title"] + "</title>"
            else:
                head = "<title>" + pageform.cleaned_data["title"] + "</title>"
                preheader = "<html>"
                headerargs = ""
                postheader = ""
                bodyargs = ""
                postbody = "</html>\n" 
            body = pageform.cleaned_data["html"]
            body = body.replace("\r", "")
            result = "%s<head%s>%s</head>%s<body%s>\n%s</body>%s" % (preheader, headerargs, head, postheader, bodyargs, body, postbody)
            
            cwd = filepath.parent
            filename = filepath.name
            git = settings.GIT
            # GIT see also core/models/cave.py writetrogglefile()
            # GIT see also core/views/uploads.py dwgupload()
            try:
                with open(filepath, "w") as f:
                    print(f'WRITING{cwd}---{filename} ')
                    # as the wsgi process www-data, we have group write-access but are not owner, so cannot chmod.
                    # os.chmod(filepath, 0o664) # set file permissions to rw-rw-r--
                    f.write(result)
            except PermissionError:
                message = f'CANNOT  save this file.\nPERMISSIONS incorrectly set on server for this file {filename}. Ask a nerd to fix this.'
                return render(request,'errors/generic.html', {'message': message})

            try:
                cp_add = subprocess.run([git, "add", filename], cwd=cwd, capture_output=True, text=True)
                if cp_add.returncode != 0:
                    msgdata = 'Ask a nerd to fix this.\n\n' + cp_add.stderr + '\n\n' + cp_add.stdout  + '\n\nreturn code: ' + str(cp_add.returncode)
                    message = f'CANNOT git on server for this file {filename}. Edits saved but not added to git.\n\n' + msgdata
                    return render(request,'errors/generic.html', {'message': message})

                cp_commit = subprocess.run([git, "commit", "-m", f'Troggle online: Edit this page - {filename}'], cwd=cwd, capture_output=True, text=True)
                # This produces return code = 1 if it commits OK, but when the repo still needs to be pushed to origin/expoweb
                if cp_commit.returncode != 0 and cp_commit.stdout != 'nothing to commit, working tree clean':
                    msgdata = 'Ask a nerd to fix this.\n\n' + cp_commit.stderr + '\n\n' + cp_commit.stdout  + '\n\nreturn code: ' + str(cp_commit.returncode)
                    message = f'Error code with git on server for this file {filename}. Edits saved, added to git, but NOT committed.\n\n' + msgdata
                    return render(request,'errors/generic.html', {'message': message})

            except subprocess.SubprocessError:
                message = f'CANNOT git on server for this file {filename}. Subprocess error. Edits not saved.\nAsk a nerd to fix this.'
                return render(request,'errors/generic.html', {'message': message})
 
            return HttpResponseRedirect(reverse('expopage', args=[path])) # Redirect after POST
    else:
        if filefound:
            m = re.search(r"<title>(.*)</title>", head, re.DOTALL + re.IGNORECASE)
            if m: 
                title, = m.groups()
            else:
                title = ""
            pageform = ExpoPageForm({"html": body, "title": title})
        else:
            body = "### File not found ###\n"    + str(filepath)
            pageform = ExpoPageForm({"html": body, "title": "Missing"})
    return render(request, 'editexpopage.html', {'path': path, 'form': pageform, })

class ExpoPageForm(forms.Form):
    '''The form used by the editexpopage function
    '''
    title = forms.CharField(widget=forms.TextInput(attrs={'size':'60'}))
    html = forms.CharField(widget=forms.Textarea(attrs={"cols":80, "rows":20}))