-
Notifications
You must be signed in to change notification settings - Fork 0
/
cbzerv.py
430 lines (393 loc) · 18.1 KB
/
cbzerv.py
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
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
from http.server import BaseHTTPRequestHandler, HTTPServer
from typing import Optional, List, TypeVar, Dict, Set, Callable
from os import path, listdir, environ, walk
from zipfile import ZipFile
from urllib.parse import urlparse, parse_qs, ParseResult, unquote
from functools import lru_cache
from math import floor
import html
import re
import email.utils
import bz2
import subprocess
ff_to_png: Callable[[bytes], bytes] = lambda x: subprocess.Popen(["magick", "FF:-", "PNG:-"], stdin=subprocess.PIPE, stdout=subprocess.PIPE).communicate(x)[0]
try:
from wand.image import Image # type: ignore
ff_to_png = lambda x: Image(blob=x, format="FF").make_blob(format="PNG")
except ModuleNotFoundError:
pass
# common mimes used by hand
MIME_JS = "text/javascript"
MIME_JSON = "application/json"
MIME_HTML = "text/html; charset=utf-8"
MIME_TEXT = "text/text"
MIME_PDF = "application/pdf"
# all supported mimes
FILE_EXT_TO_MIME: Dict[str, str] = {
"css": "text/css",
"gif": "image/gif",
"html": MIME_HTML,
"jpeg": "image/jpeg",
"jpg": "image/jpeg",
"js": MIME_JS,
"json": MIME_JSON,
"pdf": MIME_PDF,
"png": "image/png",
"svg": "image/svg+xml",
"txt": MIME_TEXT,
"webp": "image/webp",
}
IMAGE_FILE_EXTENSIONS: List[str] = [
"gif",
"jpeg",
"jpg",
"png",
"svg",
"webp",
]
HTML_HEAD: str = '''
<!DOCTYPE HTML><html><head>
<meta name="viewport" content="width=device-width, initial-scale=1.0">
<style>
html,body{height:100%;margin:0;background-color:black;color:white;}
a{color:cyan;}a:visited{color:orange;}
img{max-width:100%;}
ul>li>a>img{max-width:80%;max-height:300px;border:5px solid cyan;}
ul>li{display: inline-block;width:300px;}
ul>li>a:visited>img{border-color:orange;}
ul{list-style-type:none;}
#to_top_button{text-decoration:none;padding:10px;color:#fff;background:#333;border-radius:100px;position:sticky;bottom:5px;}
.st{width:0px!important;height:0px!important;overflow:hidden!important;display:inline-block!important;}
@media (pointer:coarse) or (max-aspect-ratio:0.7){body,img{width:100%;}}
@media (min-aspect-ratio:1){img{width:calc(0.8*100vh);}}
</style></head><body>
'''
HTML_TAIL: str = '</body></html>'
QUERY_URL_SUFFIX: str = "/query"
CLEAR_CACHE_URL_SUFFIX: str = "/clear_serverside_cache"
TAGFILE_NAME: str = "tagfile.txt"
FILES_TO_NOT_INDEX: List[str] = [
*(f"folder.{i}" for i in IMAGE_FILE_EXTENSIONS),
TAGFILE_NAME,
"meta_data.json",
]
class RequestHandler(BaseHTTPRequestHandler):
def do_POST(self) -> None:
self.send_response(501) # Not Implemented
self.send_header("Content-Type", MIME_TEXT)
self.end_headers()
self.wfile.write(b'POST is not supported')
def do_GET(self) -> None:
parsedurl = urlparse(self.path)
if parsedurl.path.endswith(CLEAR_CACHE_URL_SUFFIX):
read_tagfile.cache_clear()
self.send_response(200)
self.send_header("Content-Type", MIME_HTML)
self.end_headers()
self.wfile.write(
f'{HTML_HEAD}Cleared cache <a href="{html.escape(parsedurl.path[:-len(CLEAR_CACHE_URL_SUFFIX)])}">Back</a>{HTML_TAIL}'
.encode(encoding="utf-8", errors="replace")
)
return
target_file: str = path.abspath(path.join(path.curdir, unquote(parsedurl.path.lstrip("/"))))
if not target_file.startswith(path.abspath(path.curdir)):
self.send_response(403)
self.end_headers()
return
if (parsedurl.path.endswith(QUERY_URL_SUFFIX)):
self.handle_query(parsedurl, target_file)
return
if not path.exists(target_file):
self.send_response(404)
self.send_header("Content-Type", MIME_HTML)
self.end_headers()
self.wfile.write(f"{HTML_HEAD}<h1>404</h1>{HTML_TAIL}".encode(encoding="utf-8", errors="replace"))
return
if not path.isfile(target_file):
if path.isfile(path.join(target_file, "index.html")):
self.send_response(307)
self.send_header("Location", f"{parsedurl.path}/index.html")
self.end_headers()
return
self.send_index(target_file, parsedurl)
return
file_ext: str = path.splitext(target_file)[1].lstrip(".").lower()
mime: Optional[str] = get_mime(file_ext)
if mime is None:
if file_ext == "cbz":
self.send_cbz(target_file, parsedurl)
return
if file_ext == "pdf":
self.send_pdf(target_file, parsedurl)
return
self.return_unsupported_mime(file_ext)
return
last_edited: str = email.utils.formatdate(path.getmtime(target_file))
self.send_response(200)
self.send_header("Content-Type", mime)
self.send_header("Last-Modified", last_edited)
if file_ext in IMAGE_FILE_EXTENSIONS:
self.send_header("Cache-Control", "max-age=604800")
self.end_headers()
with open(target_file, "rb") as f:
self.wfile.write(f.read())
def send_pdf(self, file: str, parsedurl: ParseResult) -> None:
query = parse_qs(parsedurl.query)
if query:
last_edited: str = email.utils.formatdate(path.getmtime(file))
self.send_response(200)
self.send_header("Content-Type", MIME_PDF)
self.send_header("Last-Modified", last_edited)
self.end_headers()
with open(file, "rb") as f:
self.wfile.write(f.read())
return
self.send_response(200)
self.send_header("Content-Type", MIME_HTML)
# no clientside cache (both unlikely and would create issues when the next chapter releases)
self.end_headers()
thisurl = html.escape(parsedurl.path)
# https://www.w3docs.com/snippets/html/how-to-embed-pdf-in-html.html
# https://www.w3docs.com/snippets/html/how-to-make-a-div-fill-the-height-of-the-remaining-space.html
self.wfile.write(f'''
{HTML_HEAD}<div style="display:flex;flex-flow:column;height:100%">
<h1 style="flex:0 1 auto">{generate_html_pathstr(unquote(parsedurl.path))}</h1>
<object data="{thisurl}?file=true" type="application/pdf" width="100%" style="flex:1 1 auto">
<p>Unable to display PDF file. <a href="{thisurl}?file=true">Download</a> instead.</p>
</object>
</div>{HTML_TAIL}
'''.encode(encoding="utf-8", errors="replace"))
def send_cbz(self, file: str, parsedurl: ParseResult) -> None:
query = parse_qs(parsedurl.query)
if "image" in query:
last_edited: str = email.utils.formatdate(path.getmtime(file))
imagefile: str = query["image"] if isinstance(query["image"], str) else query["image"][0]
image_mime: Optional[str] = None
ff: bool = False
if imagefile.endswith(".ff.bz2"):
image_mime = get_mime("png")
ff = True
else:
image_extension: str = path.splitext(imagefile)[1].lstrip(".")
image_mime = get_mime(image_extension)
if image_mime is None:
self.return_unsupported_mime(image_extension)
return
self.send_response(200)
self.send_header("Content-Type", image_mime)
self.send_header("Last-Modified", last_edited)
self.end_headers()
try:
with ZipFile(file, "r") as zip_ref:
self.wfile.write(ff_bz2_to_png(zip_ref.read(imagefile)) if ff else zip_ref.read(imagefile))
except PermissionError:
# i dont see a easy way to return a error as image without extensive libs or storing it to RAM
pass
return
images: List[str] = []
try:
with ZipFile(file, "r") as zip_ref:
images = [
i.filename
for i in zip_ref.filelist
if get_index(i.filename.rsplit(".", 1), 1) in IMAGE_FILE_EXTENSIONS or i.filename.endswith(".ff.bz2")
]
except PermissionError:
self.send_response(500)
self.send_header("Content-Type", MIME_TEXT)
self.end_headers()
self.wfile.write(b'Unable to display file: server has insufficient permissions to read it')
return
self.send_response(200)
self.send_header("Content-Type", MIME_HTML)
# no clientside cache (both unlikely and would create issues when the next chapter releases)
self.end_headers()
images.sort(key=_sort_human_key)
thispath = html.escape(parsedurl.path)
# calculate next chapter
dir, filename = path.split(file)
dircontent: List[str] = [i for i in listdir(dir) if i not in FILES_TO_NOT_INDEX]
dircontent.sort(key=_sort_human_key)
index_of_this: int = dircontent.index(filename)
next_chapter: Optional[str] = None
if len(dircontent) > index_of_this + 1:
next_chapter = dircontent[index_of_this + 1]
images_html: str = "<br>".join((
f'''<img src="{thispath}?image={html.escape(i)}"{' loading="lazy"' if idx>10 else ""}>'''
for idx, i in enumerate(images)
))
self.wfile.write(f'''
{HTML_HEAD}
<style>body{{margin-left:auto;margin-right:auto;width:fit-content;}}</style>
<h1 id="h1_cbz_title">{generate_html_pathstr(unquote(parsedurl.path))}</h1>
{images_html}
{f'<br><a href="{html.escape(next_chapter)}">{html.escape(next_chapter)}</a>' if next_chapter else ""}
<br><br><br><a href="#h1_cbz_title" id="to_top_button">Go to top</a>
{HTML_TAIL}
'''.encode(encoding="utf-8", errors="replace"))
def handle_query(self, parsedurl: ParseResult, target_file: str) -> None:
query_string: Dict[str, List[str]] = parse_qs(parsedurl.query)
if not query_string:
self.send_query_page(parsedurl, target_file)
return
wanted: List[str] = [k.strip() for k, v in query_string.items() if "wanted" in v]
unwanted: List[str] = [k.strip() for k, v in query_string.items() if "unwanted" in v]
del query_string
tagfiles: List[str] = find_all_tagfile_paths(target_file[:-len(QUERY_URL_SUFFIX)])
matching_dirs: List[str] = []
for tagfile in tagfiles:
tags = read_tagfile(tagfile)
if any((tag in unwanted for tag in tags)):
continue
# any is faster than all -> inverse
if any((wanted_tag not in tags for wanted_tag in wanted)):
continue
matching_dirs.append(tagfile.rsplit("/", 1)[0])
self.send_response(200)
self.send_header("Content-Type", MIME_HTML)
self.end_headers()
files_html: List[str] = []
sent_images: int = 0
for dir_path in matching_dirs:
html_path: str = html.escape(path.relpath(dir_path, path.curdir))
dir_picture: str = next((
f'''<img src="/{html_path}/{img_file_name}"{' loading="lazy"' if sent_images > 10 else ""}><div class="st">{html.escape(dir_path)}</div>'''
for img_file_name in (f"folder.{i}" for i in IMAGE_FILE_EXTENSIONS)
if path.isfile(path.join(dir_path, img_file_name))
), "")
if dir_picture:
sent_images += 1
files_html.append(f'<li><a href="/{html_path}">{dir_picture or html_path}</a></li>')
files_html.sort(key=_sort_human_key)
self.wfile.write(f'''
{HTML_HEAD}
<nav><a href="javascript:window.history.back();">Back</a></nav>
<h1>Search Results within {generate_html_pathstr(parsedurl.path[:-len(QUERY_URL_SUFFIX)])}</h1>({len(matching_dirs)} results)
<ul>{"".join(files_html)}</ul>
<br><br><br><a href="#h1_cbz_title" id="to_top_button">Go to top</a>
{HTML_TAIL}
'''.encode(encoding="utf-8", errors="replace"))
def send_query_page(self, parsedurl: ParseResult, target_file: str) -> None:
self.send_response(200)
self.send_header("Content-Type", MIME_HTML)
self.end_headers()
tagfiles: List[str] = find_all_tagfile_paths(target_file[:-len(QUERY_URL_SUFFIX)])
tags: Dict[str, int] = {}
for filepath in tagfiles:
for tag in read_tagfile(filepath):
tags[tag] = (tags.get(tag) or 0) + 1
tag_names: List[str] = list(tags.keys())
tag_names.sort()
pm: float = float(len(tagfiles)) / 100.0
tags_html: str = "".join((
f'''
<tr>
<td><input type="radio" name="{html.escape(tag)}" value="ignore" checked="checked"></td>
<td><input type="radio" name="{html.escape(tag)}" value="wanted"></td>
<td><input type="radio" name="{html.escape(tag)}" value="unwanted"></td>
<td>{html.escape(tag)} ({tags[tag]}; {floor(tags[tag] / pm)}%)</td>
</tr>
'''
for tag in tag_names if tag
))
self.wfile.write(f'''
{HTML_HEAD}
<nav><a href="javascript:window.history.back();">Back</a></nav>
<h1>Search within {generate_html_pathstr(parsedurl.path[:-len(QUERY_URL_SUFFIX)])}</h1>
<form action="{html.escape(parsedurl.path)}">
<table>
<tr><th>Allow</th><th>Enforce</th><th>Block</th><th>Tag</th></tr>
{tags_html}
</table>
<input type="submit" value="Search">
</form>
<a href="{parsedurl.path}/clear_serverside_cache">Clear serverside cache</a>
{HTML_TAIL}
'''.encode(encoding="utf-8", errors="replace"))
def return_unsupported_mime(self, extension: str) -> None:
self.send_response(415) # unsupported media type
self.send_header("Content-Type", MIME_TEXT)
self.end_headers()
self.wfile.write(f"file extension {extension} is not supported.".encode(encoding="utf-8", errors="replace"))
def send_index(self, target_file: str, parsedurl: ParseResult) -> None:
files: List[str] = []
thispath: str = html.escape(parsedurl.path)
filecount: int = 0
if path.isdir(target_file):
try:
raw_files: List[str] = listdir(target_file)
except PermissionError:
self.send_response(500)
self.send_header("Content-Type", MIME_TEXT)
self.end_headers()
self.wfile.write(b'Unable to generate directory index: server is missing read and/or list permissions.')
return
raw_files = [i for i in raw_files if i not in FILES_TO_NOT_INDEX and not path.exists(path.join(target_file, i, ".ignore"))]
filecount = len(raw_files)
if len(raw_files) == 1:
self.send_response(307) # temporary redirect
self.send_header("Location", f"{parsedurl.path}/{raw_files[0]}")
self.end_headers()
return
raw_files.sort(key=_sort_human_key)
sent_images: int = 0
for file in raw_files:
dir_picture: str = next((
f'''<img src="{thispath}/{html.escape(file)}/{img_file_name}"{' loading="lazy"' if sent_images > 10 else ""} alt="{html.escape(file)}"><div class="st">{html.escape(file)}</div>'''
for img_file_name in (f"folder.{i}" for i in IMAGE_FILE_EXTENSIONS)
if path.isfile(f"{target_file}/{file}/{img_file_name}")
), "") if path.isdir(f"{target_file}/{file}") else ""
files.append(f'<li><a href="{thispath}/{html.escape(file)}">{dir_picture or html.escape(file)}</a></li>')
if dir_picture:
sent_images += 1
self.send_response(200)
self.send_header("Content-Type", MIME_HTML)
self.end_headers()
self.wfile.write(f'''
{HTML_HEAD}
<nav><a href="{html.escape(parsedurl.path)}{QUERY_URL_SUFFIX}">Search</a></nav>
<h1 id="h1_index_title">{generate_html_pathstr(unquote(parsedurl.path))}</h1>({filecount} results)
<ul>{"".join(files)}</ul>
<a href="#h1_index_title" id="to_top_button">Go to top</a>
{HTML_TAIL}
'''.encode(encoding="utf-8", errors="replace"))
@lru_cache
def read_tagfile(tagfile: str) -> List[str]:
with open(tagfile, "r") as file_handle:
lines = file_handle.readlines()
return [tag.strip() for tag in lines]
def generate_html_pathstr(filepath: str) -> str:
result: List[str] = []
while True:
p = filepath.rstrip("/").rsplit("/", 1)
if len(p) < 2 or not p[1]:
result.reverse()
return "".join(result)
result.append(f'/<a href="{html.escape(filepath)}">{html.escape(p[1])}</a>')
filepath = p[0]
def find_all_tagfile_paths(basedir: Optional[str] = None) -> List[str]:
basedir = basedir or path.curdir
return [
path.join(subdir, filename)
for subdir, _, files in walk(basedir)
for filename in files
if filename == TAGFILE_NAME and not path.exists(path.join(subdir, ".ignore"))
]
def get_mime(extension: str) -> Optional[str]:
return FILE_EXT_TO_MIME.get(extension.lower(), None)
def _sort_human_key(key: str) -> tuple:
parts = re.split(r'(\d*\.\d+|\d+)', key)
return tuple(
(e.swapcase() if i % 2 == 0 else float(e))
for i, e in enumerate(parts)
)
T = TypeVar('T')
def get_index(l: List[T], idx: int) -> Optional[T]:
return l[idx] if len(l) > idx else None
def ff_bz2_to_png(ff_bz2: bytes) -> bytes:
return ff_to_png(bz2.decompress(ff_bz2))
def main(port: int) -> None:
server: HTTPServer = HTTPServer(("", port), RequestHandler)
server.serve_forever()
if __name__ == "__main__":
main(int(environ.get("PORT", "8080")))