git » blitiri » master » tree

[master] / blitiri.cgi

   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
 431
 432
 433
 434
 435
 436
 437
 438
 439
 440
 441
 442
 443
 444
 445
 446
 447
 448
 449
 450
 451
 452
 453
 454
 455
 456
 457
 458
 459
 460
 461
 462
 463
 464
 465
 466
 467
 468
 469
 470
 471
 472
 473
 474
 475
 476
 477
 478
 479
 480
 481
 482
 483
 484
 485
 486
 487
 488
 489
 490
 491
 492
 493
 494
 495
 496
 497
 498
 499
 500
 501
 502
 503
 504
 505
 506
 507
 508
 509
 510
 511
 512
 513
 514
 515
 516
 517
 518
 519
 520
 521
 522
 523
 524
 525
 526
 527
 528
 529
 530
 531
 532
 533
 534
 535
 536
 537
 538
 539
 540
 541
 542
 543
 544
 545
 546
 547
 548
 549
 550
 551
 552
 553
 554
 555
 556
 557
 558
 559
 560
 561
 562
 563
 564
 565
 566
 567
 568
 569
 570
 571
 572
 573
 574
 575
 576
 577
 578
 579
 580
 581
 582
 583
 584
 585
 586
 587
 588
 589
 590
 591
 592
 593
 594
 595
 596
 597
 598
 599
 600
 601
 602
 603
 604
 605
 606
 607
 608
 609
 610
 611
 612
 613
 614
 615
 616
 617
 618
 619
 620
 621
 622
 623
 624
 625
 626
 627
 628
 629
 630
 631
 632
 633
 634
 635
 636
 637
 638
 639
 640
 641
 642
 643
 644
 645
 646
 647
 648
 649
 650
 651
 652
 653
 654
 655
 656
 657
 658
 659
 660
 661
 662
 663
 664
 665
 666
 667
 668
 669
 670
 671
 672
 673
 674
 675
 676
 677
 678
 679
 680
 681
 682
 683
 684
 685
 686
 687
 688
 689
 690
 691
 692
 693
 694
 695
 696
 697
 698
 699
 700
 701
 702
 703
 704
 705
 706
 707
 708
 709
 710
 711
 712
 713
 714
 715
 716
 717
 718
 719
 720
 721
 722
 723
 724
 725
 726
 727
 728
 729
 730
 731
 732
 733
 734
 735
 736
 737
 738
 739
 740
 741
 742
 743
 744
 745
 746
 747
 748
 749
 750
 751
 752
 753
 754
 755
 756
 757
 758
 759
 760
 761
 762
 763
 764
 765
 766
 767
 768
 769
 770
 771
 772
 773
 774
 775
 776
 777
 778
 779
 780
 781
 782
 783
 784
 785
 786
 787
 788
 789
 790
 791
 792
 793
 794
 795
 796
 797
 798
 799
 800
 801
 802
 803
 804
 805
 806
 807
 808
 809
 810
 811
 812
 813
 814
 815
 816
 817
 818
 819
 820
 821
 822
 823
 824
 825
 826
 827
 828
 829
 830
 831
 832
 833
 834
 835
 836
 837
 838
 839
 840
 841
 842
 843
 844
 845
 846
 847
 848
 849
 850
 851
 852
 853
 854
 855
 856
 857
 858
 859
 860
 861
 862
 863
 864
 865
 866
 867
 868
 869
 870
 871
 872
 873
 874
 875
 876
 877
 878
 879
 880
 881
 882
 883
 884
 885
 886
 887
 888
 889
 890
 891
 892
 893
 894
 895
 896
 897
 898
 899
 900
 901
 902
 903
 904
 905
 906
 907
 908
 909
 910
 911
 912
 913
 914
 915
 916
 917
 918
 919
 920
 921
 922
 923
 924
 925
 926
 927
 928
 929
 930
 931
 932
 933
 934
 935
 936
 937
 938
 939
 940
 941
 942
 943
 944
 945
 946
 947
 948
 949
 950
 951
 952
 953
 954
 955
 956
 957
 958
 959
 960
 961
 962
 963
 964
 965
 966
 967
 968
 969
 970
 971
 972
 973
 974
 975
 976
 977
 978
 979
 980
 981
 982
 983
 984
 985
 986
 987
 988
 989
 990
 991
 992
 993
 994
 995
 996
 997
 998
 999
1000
1001
1002
1003
1004
1005
1006
1007
1008
1009
1010
1011
1012
1013
1014
1015
1016
1017
1018
1019
1020
1021
1022
1023
1024
1025
1026
1027
1028
1029
1030
1031
1032
1033
1034
1035
1036
1037
1038
1039
1040
1041
1042
1043
1044
1045
1046
1047
1048
1049
1050
1051
1052
1053
1054
1055
1056
1057
1058
1059
1060
1061
1062
1063
1064
1065
1066
1067
1068
1069
1070
1071
1072
1073
1074
1075
1076
1077
1078
1079
1080
1081
1082
1083
1084
1085
1086
1087
1088
1089
1090
1091
1092
1093
1094
1095
1096
1097
1098
1099
1100
1101
1102
1103
1104
1105
1106
1107
1108
1109
1110
1111
1112
1113
1114
1115
1116
1117
1118
1119
1120
1121
1122
1123
1124
1125
1126
1127
1128
1129
1130
1131
1132
1133
1134
1135
1136
1137
1138
1139
1140
1141
1142
1143
1144
1145
1146
1147
1148
1149
1150
1151
1152
1153
1154
1155
1156
1157
1158
1159
1160
1161
1162
1163
1164
1165
1166
1167
1168
1169
1170
1171
1172
1173
1174
1175
1176
1177
1178
1179
1180
1181
1182
1183
1184
1185
1186
1187
1188
1189
1190
1191
1192
1193
1194
1195
1196
1197
1198
1199
1200
1201
1202
1203
1204
1205
1206
1207
1208
1209
1210
1211
1212
1213
1214
1215
1216
1217
1218
1219
1220
1221
1222
1223
1224
1225
1226
1227
1228
1229
1230
1231
1232
1233
1234
1235
1236
1237
1238
1239
1240
1241
1242
1243
1244
1245
1246
1247
1248
1249
1250
1251
1252
1253
1254
1255
1256
1257
1258
1259
1260
1261
1262
1263
1264
1265
1266
1267
1268
1269
1270
1271
1272
1273
1274
1275
1276
1277
1278
1279
1280
1281
1282
1283
1284
1285
1286
1287
1288
1289
1290
1291
1292
1293
1294
1295
1296
1297
1298
1299
1300
1301
1302
1303
1304
1305
1306
1307
1308
1309
1310
1311
1312
1313
1314
1315
1316
1317
1318
1319
1320
1321
1322
1323
1324
1325
1326
1327
1328
1329
1330
1331
1332
1333
1334
1335
1336
1337
1338
1339
1340
1341
1342
1343
1344
1345
1346
1347
1348
1349
1350
1351
1352
1353
1354
1355
1356
1357
1358
1359
1360
1361
1362
1363
1364
1365
1366
1367
1368
1369
1370
1371
1372
1373
1374
1375
1376
1377
1378
1379
1380
1381
1382
1383
1384
1385
1386
1387
1388
1389
1390
1391
1392
1393
1394
1395
1396
1397
1398
1399
1400
1401
1402
1403
1404
1405
1406
1407
1408
1409
1410
1411
1412
1413
1414
1415
1416
1417
1418
1419
1420
1421
1422
1423
1424
1425
1426
1427
1428
1429
1430
1431
1432
1433
1434
1435
1436
1437
1438
1439
1440
1441
1442
1443
1444
1445
1446
1447
1448
1449
1450
1451
1452
1453
1454
1455
1456
1457
#!/usr/bin/env python3
# coding: utf8

# blitiri - A single-file blog engine.
# Alberto Bertogli (albertito@gmail.com)

#
# Configuration section
#
# You can edit these values, or create a file named "config.py" and put them
# there to make updating easier. The ones in config.py take precedence.
#

# Directory where entries are stored
data_path = "/tmp/blog/data"

# Are comments allowed? (if False, comments_path option is not used)
enable_comments = False

# Directory where comments are stored (must be writeable by the web server)
comments_path = "/tmp/blog/comments"

# Path where templates are stored. Use an empty string for the built-in
# default templates. If they're not found, the built-in ones will be used.
templates_path = "/tmp/blog/templates"

# Path where the cache is stored (must be writeable by the web server);
# set to None to disable. When enabled, you must take care of cleaning it up
# every once in a while.
# cache_path = "/tmp/blog/cache"
cache_path = None

# URL to the blog, including the name. Can be a full URL or just the path.
blog_url = "/blog/blitiri.cgi"

# Style sheet (CSS) URL. Can be relative or absolute. To use the built-in
# default, set it to blog_url + "/style".
css_url = blog_url + "/style"

# Blog title
title = "I don't like blogs"

# Default author
author = "Hartmut Kegan"

# Article encoding
encoding = "utf8"

# Captcha method to use. At the moment only "title" is supported, but if you
# are keen with Python you can provide your own captcha implementation, see
# below for details.
captcha_method = "title"

# How many articles to show in the index
index_articles = 10

# Before rendering the rst, perform these regexp-based replacements.
rst_regexp_replaces = [
    (
        r".. youtube:: (.*)",
        r""".. raw:: html

         <iframe width="560" height="315"
                 src="https://www.youtube.com/embed/\1"
                 frameborder="0" allowfullscreen></iframe>
    """,
    ),
    (
        r".. vimeo:: (\w*)",
        r""".. raw:: html

         <iframe src="https://player.vimeo.com/video/\1"
                 width="500" height="281" frameborder="0"
                 webkitallowfullscreen mozallowfullscreen
                 allowfullscreen></iframe>
	""",
    ),
]

#
# End of configuration
# DO *NOT* EDIT ANYTHING PAST HERE
#


import calendar
import cgi
import datetime
import errno
import html
import os
import re
import shutil
import sys
import time
import urllib.request, urllib.parse, urllib.error
import zlib

# Before importing the config, add our cwd to the Python path
sys.path.append(os.getcwd())

# Load the config file, if there is one
try:
    from config import *
except:
    pass


# Pimp *_path config variables to support relative paths
data_path = os.path.realpath(data_path)
templates_path = os.path.realpath(templates_path)


#
# Captcha classes
#
# They must follow the interface described below.
#
# Constructor:
# 	Captcha(article) -> constructor, takes an article[1] as argument
# Attributes:
# 	puzzle -> a string with the puzzle the user must solve to prove he is
# 	          not a bot (can be raw HTML)
# 	help -> a string with extra instructions, shown only when the user
# 	        failed to solve the puzzle
# Methods:
# 	validate(form_data) -> based on the form data[2],  returns True if
# 	                       the user has solved the puzzle uccessfully
# 	                       (False otherwise).
#
# Note you must ensure that the puzzle attribute and validate() method can
# "communicate" because they are executed in different requests. You can pass a
# cookie or just calculate the answer based on the article's data, for example.
#
# [1] article is an object with all the article's information:
# 	path -> string
# 	created -> datetime
# 	updated -> datetime
# 	uuid -> string (unique ID)
# 	title -> string
# 	author -> string
# 	tags -> list of strings
# 	raw_contents -> string in rst format
# 	comments -> list of Comment objects (not too relevant here)
# [2] form_data is an object with the form fields (all strings):
# 	author, author_error
# 	link, link_error
# 	catpcha, captcha_error
# 	body, body_error
# 	action, method


class TitleCaptcha(object):
    "Captcha that uses the article's title for the puzzle"

    def __init__(self, article):
        self.article = article
        words = article.title.split()
        self.nword = hash(article.title) % len(words) % 5
        self.answer = words[self.nword]
        self.help = "gotcha, damn spam bot!"

    @property
    def puzzle(self):
        nword = self.nword + 1
        if nword == 1:
            n = "1st"
        elif nword == 2:
            n = "2nd"
        elif nword == 3:
            n = "3rd"
        else:
            n = str(nword) + "th"
        return "enter the %s word of the article's title" % n

    def validate(self, form_data):
        if form_data.captcha.lower() == self.answer.lower():
            return True
        return False


known_captcha_methods = {
    "title": TitleCaptcha,
}

# If the configured captcha method was a known string, replace it by the
# matching class; otherwise assume it's already a class and leave it
# alone. This way the user can either use one of our methods, or provide one
# of his/her own.
if captcha_method in known_captcha_methods:
    captcha_method = known_captcha_methods[captcha_method]


# Default template

default_main_header = """\
<?xml version="1.0" encoding="utf-8"?>
<!DOCTYPE html PUBLIC "-//W3C//DTD XHTML 1.0 Strict//EN"
          "http://www.w3.org/TR/xhtml1/DTD/xhtml1-strict.dtd">

<html xmlns="http://www.w3.org/1999/xhtml" xml:lang="en" lang="en">
<head>
<link rel="alternate" title="%(title)s" href="%(fullurl)s/atom"
	type="application/atom+xml" />
<link href="%(css_url)s" rel="stylesheet" type="text/css" />
<title>%(title)s</title>
</head>

<body>

<h1><a href="%(url)s">%(title)s</a></h1>

<div class="content">
"""

default_main_footer = """
</div>
<div class="footer">
  %(showyear)s: %(monthlinks)s<br/>
  years: %(yearlinks)s<br/>
  subscribe: <a href="%(url)s/atom">atom</a><br/>
  views: <a href="%(url)s/">blog</a> <a href="%(url)s/list">list</a><br/>
  tags: %(taglinks)s<br/>
</div>

</body>
</html>
"""

default_article_header = """
<div class="article">
<h2><a href="%(url)s/post/%(uuid)s">%(arttitle)s</a></h2>
<span class="artinfo">
  by %(author)s on <span class="date">

<a class="date" href="%(url)s/%(cyear)d/">%(cyear)04d</a>-\
<a class="date" href="%(url)s/%(cyear)d/%(cmonth)d/">%(cmonth)02d</a>-\
<a class="date" href="%(url)s/%(cyear)d/%(cmonth)d/%(cday)d/">%(cday)02d</a>\
    %(chour)02d:%(cminute)02d</span>
  (updated on <span class="date">
<a class="date" href="%(url)s/%(uyear)d/">%(uyear)04d</a>-\
<a class="date" href="%(url)s/%(uyear)d/%(umonth)d/">%(umonth)02d</a>-\
<a class="date" href="%(url)s/%(uyear)d/%(umonth)d/%(uday)d/">%(uday)02d</a>\
    %(uhour)02d:%(uminute)02d)</span><br/>
  <span class="tags">tagged %(tags)s</span> -
  <span class="comments">with %(comments)s
    <a href="%(url)s/post/%(uuid)s#comments">comment(s)</a></span>
</span><br/>
<p/>
<div class="artbody">
"""

default_article_footer = """
<p/>
</div>
</div>
"""

default_comment_header = """
<div class="comment">
<a name="comment-%(number)d" />
<h3><a href="#comment-%(number)d">Comment #%(number)d</a></h3>
<span class="cominfo">by %(linked_author)s
  on %(year)04d-%(month)02d-%(day)02d %(hour)02d:%(minute)02d</span>
<p/>
<div class="combody">
"""

default_comment_footer = """
<p/>
</div>
</div>
"""

default_comment_form = """
<div class="comform">
<a name="comment" />
<h3 class="comform"><a href="#comment">Your comment</a></h3>
<div class="comforminner">
<form method="%(form_method)s" action="%(form_action)s">
<div class="comformauthor">
  <label for="comformauthor">Your name %(form_author_error)s</label>
  <input type="text" class="comformauthor" id="comformauthor"
         name="comformauthor" value="%(form_author)s" />
</div>
<div class="comformlink">
  <label for="comformlink">Your link
    <span class="comformoptional">(optional, will be published)</span>
      %(form_link_error)s</label>
  <input type="text" class="comformlink" id="comformlink"
         name="comformlink" value="%(form_link)s" />
  <div class="comformhelp">
    like <span class="formurlexample">http://www.example.com/</span>
    or <span class="formurlexample">mailto:you@example.com</span>
  </div>
</div>
<div class="comformcaptcha">
  <label for="comformcaptcha">Your humanity proof %(form_captcha_error)s</label>
  <input type="text" class="comformcaptcha" id="comformcaptcha"
         name="comformcaptcha" value="%(form_captcha)s" />
  <div class="comformhelp">%(captcha_puzzle)s</div>
</div>
<div class="comformbody">
  <label for="comformbody" class="comformbody">The comment
    %(form_body_error)s</label>
  <textarea class="comformbody" id="comformbody" name="comformbody" rows="15"
            cols="80">%(form_body)s</textarea>
  <div class="comformhelp">
    in
    <a href="http://docutils.sourceforge.net/docs/user/rst/quickref.html">\
RestructuredText</a> format, please
  </div>
</div>
<div class="comformsend">
  <button type="submit" class="comformsend" id="comformsend" name="comformsend">
    Send comment
  </button>
</div>
</form>
</div>
</div>
"""

default_comment_error = '<span class="comformerror">(%(error)s)</span>'


# Default CSS
default_css = """
body {
	font-family: sans-serif;
	font-size: small;
	width: 52em;
}

div.content {
	width: 96%;
}

h1 {
	font-size: large;
	border-bottom: 2px solid #99F;
	width: 100%;
	margin-bottom: 1em;
}

h2 {
	font-size: medium;
	font-weigth: none;
	margin-bottom: 1pt;
	border-bottom: 1px solid #99C;
}

h3 {
	font-size: small;
	font-weigth: none;
	margin-bottom: 1pt;
	border-bottom: 1px solid #99C;
}

h1 a, h2 a, h3 a {
	text-decoration: none;
	color: black;
}

span.artinfo {
	font-size: xx-small;
}

span.artinfo a {
	text-decoration: none;
	color: #339;
}

span.artinfo a:hover {
	text-decoration: none;
	color: blue;
}

div.artbody {
	margin-left: 1em;
}

div.article {
	margin-bottom: 2em;
}

span.cominfo {
	font-size: xx-small;
}

span.cominfo a {
	text-decoration: none;
	color: #339;
}

span.cominfo a:hover {
	text-decoration: none;
	color: blue;
}

div.combody {
	margin-left: 2em;
}

div.comment {
	margin-left: 1em;
	margin-bottom: 1em;
}

div.comforminner {
	margin-left: 2em;
}

div.comform {
	margin-left: 1em;
	margin-bottom: 1em;
}

div.comform label {
	display: block;
	border-bottom: 1px solid #99C;
	margin-top: 0.5em;
	clear: both;
}

div.comform span.comformoptional {
	font-size: xx-small;
	color: #666;
}

div.comform input {
	font-size: small;
	width: 99%;
}

div.comformhelp {
	font-size: xx-small;
	text-align: right;
	float: right;
}

span.formurlexample {
	color: #111;
	background-color: #EEF;
	font-family: monospace;
	padding-left: 0.2em;
	padding-right: 0.2em;
}

textarea.comformbody {
	font-family: monospace;
	font-size: small;
	width: 99%;
	height: 15em;
}

button.comformsend {
	margin-top: 0.5em;
}

span.comformerror {
	color: #900;
	font-size: xx-small;
	margin-left: 0.5em;
}

hr {
	float: left;
	height: 2px;
	border: 0;
	background-color: #99F;
	width: 60%;
}

div.footer {
	margin-top: 1em;
	padding-top: 0.4em;
	width: 100%;
	border-top: 2px solid #99F;
	font-size: x-small;
}

div.footer a {
	text-decoration: none;
}

/* Articles are enclosed in <div class="section"> */
div.section h1 {
	font-size: small;
	font-weigth: none;
	width: 100%;
	margin-bottom: 1pt;
	border-bottom: 1px dotted #99C;
}

"""


# Cache decorator
# It only works if the function is pure (that is, its return value depends
# only on its arguments), and if all the arguments are hash()eable.
def cached(f):
    # do not decorate if the cache is disabled
    if cache_path is None:
        return f

    def decorate(*args, **kwargs):
        hashes = "-".join(str(hash(x)) for x in args + tuple(kwargs.items()))
        fname = "blitiri.%s.%s.cache" % (f.__name__, hashes)
        cache_file = os.path.join(cache_path, fname)
        try:
            s = open(cache_file).read().decode("utf8")
        except:
            s = f(*args, **kwargs)
            open(cache_file, "w").write(s)
        return s

    return decorate


# helper functions
@cached
def rst_to_html(rst, secure=True):
    # Moving these here speeds up execution significantly on cache hit.
    from docutils.core import publish_parts
    settings = {
        "input_encoding": encoding,
        "output_encoding": "utf8",
        "halt_level": 1,
        "traceback": 1,
        "file_insertion_enabled": secure,
        "raw_enabled": secure,
    }
    parts = publish_parts(rst, settings_overrides=settings, writer_name="html")
    return parts["body"]


def validate_rst(rst, secure=True):
    # Moving these here speeds up execution significantly on cache hit.
    from docutils.utils import SystemMessage
    try:
        rst_to_html(rst, secure)
        return None
    except SystemMessage as e:
        desc = e.args[0].encode("utf-8")  # the error string
        desc = desc[9:]  # remove "<string>:"
        line = int(desc[: desc.find(":")] or 0)  # get the line number
        desc = desc[desc.find(")") + 2 : -1]  # remove (LEVEL/N)
        try:
            desc, context = desc.split("\n", 1)
        except ValueError:
            context = ""
        if desc.endswith("."):
            desc = desc[:-1]
        return (line, desc, context)


def valid_link(link):
    import re

    scheme_re = r"^[a-zA-Z]+:"
    mail_re = r"^[^ \t\n\r@<>()]+@[a-z0-9][a-z0-9\.\-_]*\.[a-z]+$"
    url_re = (
        r"^(?:[a-z0-9\-]+|[a-z0-9][a-z0-9\-\.\_]*\.[a-z]+)" r"(?::[0-9]+)?(?:/.*)?$"
    )

    if re.match(scheme_re, link, re.I):
        scheme, rest = link.split(":", 1)
        # if we have an scheme and a rest, assume the link is valid
        # and return it as-is; otherwise (having just the scheme) is
        # invalid
        if rest:
            return link
        return None

    # at this point, we don't have a scheme; we will try to recognize some
    # common addresses (mail and http at the moment) and complete them to
    # form a valid link, if we fail we will just claim it's invalid
    if re.match(mail_re, link, re.I):
        return "mailto:" + link
    elif re.match(url_re, link, re.I):
        return "https://" + link

    return None


def sanitize(obj):
    return html.escape(obj, quote=True)


# find out our URL, needed for syndication
try:
    n = os.environ["SERVER_NAME"]
    # Removed port because it messes up when behind a proxy
    # p = os.environ['SERVER_PORT']
    s = os.environ["SCRIPT_NAME"]
    # if p == '80': p = ''
    # else: p = ':' + p
    full_url = "https://%s%s" % (n, s)
except KeyError:
    full_url = "Not needed"


class Templates(object):
    def __init__(self, tpath, db, showyear=None):
        self.tpath = tpath
        self.db = db
        now = datetime.datetime.now()
        if not showyear:
            showyear = now.year

        self.vars = {
            "css_url": css_url,
            "title": title,
            "url": blog_url,
            "fullurl": full_url,
            "year": now.year,
            "month": now.month,
            "day": now.day,
            "showyear": showyear,
            "monthlinks": " ".join(db.get_month_links(showyear)),
            "yearlinks": " ".join(db.get_year_links()),
            "taglinks": " ".join(db.get_tag_links()),
        }

    def get_template(self, page_name, default_template, extra_vars=None):
        if extra_vars is None:
            vars = self.vars
        else:
            vars = self.vars.copy()
            vars.update(extra_vars)

        p = "%s/%s.html" % (self.tpath, page_name)
        if os.path.isfile(p):
            return open(p).read() % vars
        return default_template % vars

    def get_main_header(self):
        return self.get_template("header", default_main_header)

    def get_main_footer(self):
        return self.get_template("footer", default_main_footer)

    def get_article_header(self, article):
        return self.get_template(
            "art_header", default_article_header, article.to_vars()
        )

    def get_article_footer(self, article):
        return self.get_template(
            "art_footer", default_article_footer, article.to_vars()
        )

    def get_comment_header(self, comment):
        vars = comment.to_vars()
        if comment.link:
            vars["linked_author"] = '<a href="%s">%s</a>' % (
                vars["link"],
                vars["author"],
            )
        else:
            vars["linked_author"] = vars["author"]
        return self.get_template("com_header", default_comment_header, vars)

    def get_comment_footer(self, comment):
        return self.get_template(
            "com_footer", default_comment_footer, comment.to_vars()
        )

    def get_comment_form(self, article, form_data, captcha_puzzle):
        vars = article.to_vars()
        vars.update(form_data.to_vars(self))
        vars["captcha_puzzle"] = captcha_puzzle
        return self.get_template("com_form", default_comment_form, vars)

    def get_comment_error(self, error):
        return self.get_template("com_error", default_comment_error, dict(error=error))


class CommentFormData(object):
    def __init__(self, author="", link="", captcha="", body=""):
        self.author = author
        self.link = link
        self.captcha = captcha
        self.body = body
        self.author_error = ""
        self.link_error = ""
        self.captcha_error = ""
        self.body_error = ""
        self.action = ""
        self.method = "post"

    def to_vars(self, template):
        render_error = template.get_comment_error
        a_error = self.author_error and render_error(self.author_error)
        l_error = self.link_error and render_error(self.link_error)
        c_error = self.captcha_error and render_error(self.captcha_error)
        b_error = self.body_error and render_error(self.body_error)
        return {
            "form_author": sanitize(self.author),
            "form_link": sanitize(self.link),
            "form_captcha": sanitize(self.captcha),
            "form_body": sanitize(self.body),
            "form_author_error": a_error,
            "form_link_error": l_error,
            "form_captcha_error": c_error,
            "form_body_error": b_error,
            "form_action": self.action,
            "form_method": self.method,
        }


class Comment(object):
    def __init__(self, article, number, created=None):
        self.article = article
        self.number = number
        if created is None:
            self.created = datetime.datetime.now()
        else:
            self.created = created

        self.loaded = False

        # loaded on demand
        self._author = author
        self._link = ""
        self._raw_content = "Removed comment"

    @property
    def author(self):
        if not self.loaded:
            self.load()
        return self._author

    @property
    def link(self):
        if not self.loaded:
            self.load()
        return self._link

    @property
    def raw_content(self):
        if not self.loaded:
            self.load()
        return self._raw_content

    def set(self, author, raw_content, link="", created=None):
        self.loaded = True
        self._author = author
        self._raw_content = raw_content
        self._link = link
        self.created = created or datetime.datetime.now()

    def load(self):
        filename = os.path.join(comments_path, self.article.uuid, str(self.number))
        try:
            raw = open(filename).readlines()
        except:
            return

        count = 0
        for l in raw:
            if ":" in l:
                name, value = l.split(":", 1)
                if name.lower() == "author":
                    self._author = value.strip()
                elif name.lower() == "link":
                    self._link = value.strip()
            elif l == "\n":
                # end of header
                break
            count += 1
        self._raw_content = "".join(raw[count + 1 :])
        self.loaded = True

    def save(self):
        filename = os.path.join(comments_path, self.article.uuid, str(self.number))
        try:
            f = open(filename, "w")
            f.write("Author: %s\n" % self.author)
            f.write("Link: %s\n" % self.link)
            f.write("\n")
            f.write(self.raw_content)
        except:
            return

    def to_html(self):
        return rst_to_html(self.raw_content)

    def to_vars(self):
        return {
            "number": self.number,
            "author": sanitize(self.author),
            "link": sanitize(self.link),
            "date": self.created.isoformat(" "),
            "created": self.created.isoformat(" "),
            "year": self.created.year,
            "month": self.created.month,
            "day": self.created.day,
            "hour": self.created.hour,
            "minute": self.created.minute,
            "second": self.created.second,
        }


class CommentDB(object):
    def __init__(self, article):
        self.path = os.path.join(comments_path, article.uuid)
        # if comments were enabled after the article was added, we
        # will need to create the directory
        if not os.path.exists(self.path):
            os.mkdir(self.path, 0o777)

        self.comments = []
        self.load(article)

    def load(self, article):
        try:
            f = open(os.path.join(self.path, "db"))
        except:
            return

        for l in f:
            # Each line has the following comma separated format:
            # number, created (epoch)
            # Empty lines are meaningful and represent removed
            # comments (so we can preserve the comment number)
            l = l.split(",")
            try:
                n = int(l[0])
                d = datetime.datetime.fromtimestamp(float(l[1]))
            except:
                # Removed/invalid comment
                self.comments.append(None)
                continue
            self.comments.append(Comment(article, n, d))

    def save(self):
        old_db = os.path.join(self.path, "db")
        new_db = os.path.join(self.path, "db.tmp")
        f = open(new_db, "w")
        for c in self.comments:
            s = ""
            if c is not None:
                s = ""
                s += str(c.number) + ", "
                s += str(time.mktime(c.created.timetuple()))
            s += "\n"
            f.write(s)
        f.close()
        os.rename(new_db, old_db)


class Article(object):
    def __init__(self, path, created=None, updated=None):
        self.path = path
        self.created = created
        self.updated = updated
        self.uuid = "%08x" % zlib.crc32(self.path.encode("utf8"))

        self.loaded = False

        # loaded on demand
        self._title = "Removed post"
        self._author = author
        self._tags = []
        self._raw_content = ""
        self._comments = []

    @property
    def title(self):
        if not self.loaded:
            self.load()
        return self._title

    @property
    def author(self):
        if not self.loaded:
            self.load()
        return self._author

    @property
    def tags(self):
        if not self.loaded:
            self.load()
        return self._tags

    @property
    def raw_content(self):
        if not self.loaded:
            self.load()
        return self._raw_content

    @property
    def comments(self):
        if not self.loaded:
            self.load()
        return self._comments

    def __eq__(self, other):
        if self.path == other.path:
            return True
        return False

    def add_comment(self, author, raw_content, link=""):
        c = Comment(self, len(self.comments))
        c.set(author, raw_content, link)
        self.comments.append(c)
        return c

    def load(self):
        # XXX this tweak is only needed for old DB format, where
        # article's paths started with a slash
        path = self.path
        if path.startswith("/"):
            path = path[1:]
        filename = os.path.join(data_path, path)
        try:
            raw = open(filename).readlines()
        except:
            return

        count = 0
        for l in raw:
            if ":" in l:
                name, value = l.split(":", 1)
                if name.lower() == "title":
                    self._title = value.strip()
                elif name.lower() == "author":
                    self._author = value.strip()
                elif name.lower() == "tags":
                    ts = value.split(",")
                    ts = [t.strip() for t in ts]
                    self._tags = set(ts)
            elif l == "\n":
                # end of header
                break
            count += 1
        self._raw_content = "".join(raw[count + 1 :])
        db = CommentDB(self)
        self._comments = db.comments
        self.loaded = True

    def to_html(self):
        dirname = os.path.dirname
        post_url = "/".join([dirname(full_url), "posts", dirname(self.path)])
        post_dir = "/".join([data_path, dirname(self.path)])

        rst = self.raw_content.replace("##POST_URL##", post_url)
        rst = rst.replace("##POST_DIR##", post_dir)
        for pattern, replacement in rst_regexp_replaces:
            rst = re.sub(pattern, replacement, rst)
        return rst_to_html(rst)

    def to_vars(self):
        return {
            "arttitle": sanitize(self.title),
            "author": sanitize(self.author),
            "date": self.created.isoformat(" "),
            "uuid": self.uuid,
            "tags": self.get_tags_links(),
            "comments": len(self.comments),
            "created": self.created.isoformat(" "),
            "ciso": self.created.isoformat(),
            "cyear": self.created.year,
            "cmonth": self.created.month,
            "cday": self.created.day,
            "chour": self.created.hour,
            "cminute": self.created.minute,
            "csecond": self.created.second,
            "updated": self.updated.isoformat(" "),
            "uiso": self.updated.isoformat(),
            "uyear": self.updated.year,
            "umonth": self.updated.month,
            "uday": self.updated.day,
            "uhour": self.updated.hour,
            "uminute": self.updated.minute,
            "usecond": self.updated.second,
        }

    def get_tags_links(self):
        l = []
        tags = sorted(self.tags)
        for t in tags:
            l.append(
                '<a class="tag" href="%s/tag/%s">%s</a>'
                % (blog_url, urllib.parse.quote(t), sanitize(t))
            )
        return ", ".join(l)


class ArticleDB(object):
    def __init__(self, dbpath):
        self.dbpath = dbpath
        self.articles = []
        self.uuids = {}
        self.actyears = set()
        self.actmonths = set()
        self.acttags = set()
        self.load()

    def get_articles(self, year=0, month=0, day=0, tags=None):
        l = []
        for a in self.articles:
            if year and a.created.year != year:
                continue
            if month and a.created.month != month:
                continue
            if day and a.created.day != day:
                continue
            if tags and not tags.issubset(a.tags):
                continue

            l.append(a)

        return l

    def get_article(self, uuid):
        return self.uuids[uuid]

    def load(self):
        try:
            f = open(self.dbpath)
        except:
            return

        for l in f:
            # Each line has the following comma separated format:
            # path (relative to data_path), \
            # 	created (epoch), \
            # 	updated (epoch)
            try:
                l = l.split(",")
            except:
                continue

            a = Article(
                l[0],
                datetime.datetime.fromtimestamp(float(l[1])),
                datetime.datetime.fromtimestamp(float(l[2])),
            )
            self.uuids[a.uuid] = a
            self.acttags.update(a.tags)
            self.actyears.add(a.created.year)
            self.actmonths.add((a.created.year, a.created.month))
            self.articles.append(a)

    def save(self):
        f = open(self.dbpath + ".tmp", "w")
        for a in self.articles:
            s = ""
            s += a.path + ", "
            s += str(time.mktime(a.created.timetuple())) + ", "
            s += str(time.mktime(a.updated.timetuple())) + "\n"
            f.write(s)
        f.close()
        os.rename(self.dbpath + ".tmp", self.dbpath)

    def get_year_links(self):
        yl = list(self.actyears)
        yl.sort(reverse=True)
        return ['<a href="%s/%d/">%d</a>' % (blog_url, y, y) for y in yl]

    def get_month_links(self, year):
        am = [i[1] for i in self.actmonths if i[0] == year]
        ml = []
        for i in range(1, 13):
            name = calendar.month_name[i][:3]
            if i in am:
                s = '<a href="%s/%d/%d/">%s</a>' % (blog_url, year, i, name)
            else:
                s = name
            ml.append(s)
        return ml

    def get_tag_links(self):
        tl = sorted(self.acttags)
        return [
            '<a href="%s/tag/%s">%s</a>' % (blog_url, sanitize(t), sanitize(t))
            for t in tl
        ]


#
# Main
#


def render_comments(article, template, form_data):
    print('<a name="comments" />')
    for c in article.comments:
        if c is None:
            continue
        print(template.get_comment_header(c))
        print(c.to_html())
        print(template.get_comment_footer(c))
    if not form_data:
        form_data = CommentFormData()
    form_data.action = blog_url + "/comment/" + article.uuid + "#comment"
    captcha = captcha_method(article)
    print(template.get_comment_form(article, form_data, captcha.puzzle))


def render_html(
    articles, db, actyear=None, show_comments=False, redirect=None, form_data=None
):
    if redirect:
        print("Status: 303 See Other")
        print("Location: %s" % redirect)
    print("Content-type: text/html; charset=utf-8")
    print()
    template = Templates(templates_path, db, actyear)
    print(template.get_main_header())
    for a in articles:
        print(template.get_article_header(a))
        print(a.to_html())
        print(template.get_article_footer(a))
        if show_comments:
            render_comments(a, template, form_data)
    print(template.get_main_footer())


def render_artlist(articles, db, actyear=None):
    template = Templates(templates_path, db, actyear)
    print("Content-type: text/html; charset=utf-8\n")
    print(template.get_main_header())
    print("<h2>Articles</h2>")
    for a in articles:
        print(
            '<li><a href="%(url)s/post/%(uuid)s">%(title)s</a></li>'
            % {
                "url": blog_url,
                "uuid": a.uuid,
                "title": a.title,
                "author": a.author,
            }
        )
    print(template.get_main_footer())


def render_atom(articles):
    if len(articles) > 0:
        updated = articles[0].updated.isoformat()
    else:
        updated = datetime.datetime.now().isoformat()

    print("Content-type: application/atom+xml; charset=utf-8\n")
    print(
        """<?xml version="1.0" encoding="utf-8"?>

<feed xmlns="http://www.w3.org/2005/Atom">
 <title>%(title)s</title>
 <link rel="alternate" type="text/html" href="%(url)s"/>
 <link rel="self" type="application/atom+xml" href="%(url)s/atom"/>
 <id>%(url)s</id> <!-- TODO: find a better <id>, see RFC 4151 -->
 <updated>%(updated)sZ</updated>

	"""
        % {
            "title": title,
            "url": full_url,
            "updated": updated,
        }
    )

    for a in articles:
        vars = a.to_vars()
        vars.update(
            {
                "url": full_url,
                "contents": a.to_html(),
            }
        )
        print(
            """
  <entry>
    <title>%(arttitle)s</title>
    <author><name>%(author)s</name></author>
    <link href="%(url)s/post/%(uuid)s" />
    <id>%(url)s/post/%(uuid)s</id>
    <summary>%(arttitle)s</summary>
    <published>%(ciso)sZ</published>
    <updated>%(uiso)sZ</updated>
    <content type="xhtml">
      <div xmlns="http://www.w3.org/1999/xhtml">
%(contents)s
      </div>
    </content>
  </entry>
		"""
            % vars
        )
    print("</feed>")


def render_style():
    print("Content-type: text/css")
    print()
    print(default_css)


# Get a dictionary with sort() arguments (key and reverse) by parsing the sort
# specification format:
# [+-]?<key>?
# Where "-" is used to specify reverse order, while "+" is regular, ascending,
# order (reverse = False). The key value is an Article's attribute name (title,
# author, created, updated and uuid are accepted), and will be used as key for
# sorting. If a value is omitted, that value is taken from the default, which
# should be provided using the same format specification, with the difference
# that all values must be provided for the default.
def get_sort_args(sort_str, default):
    def parse(s):
        d = dict()
        if not s:
            return d
        key = None
        if len(s) > 0:
            # accept ' ' as an alias of '+' since '+' is translated
            # to ' ' in URLs
            if s[0] in ("+", " ", "-"):
                key = s[1:]
                d["reverse"] = s[0] == "-"
            else:
                key = s
        if key in ("title", "author", "created", "updated", "uuid"):
            d["key"] = lambda a: getattr(a, key)
        return d

    args = parse(default)
    assert args["key"] is not None and args["reverse"] is not None
    args.update(parse(sort_str))
    return args


def handle_cgi():
    import cgitb

    cgitb.enable()

    form = cgi.FieldStorage()
    year = int(form.getfirst("year", 0))
    month = int(form.getfirst("month", 0))
    day = int(form.getfirst("day", 0))
    tags = set(form.getlist("tag"))
    sort_str = form.getfirst("sort", None)
    uuid = None
    atom = False
    style = False
    post = False
    post_preview = False
    artlist = False
    comment = False

    if "PATH_INFO" in os.environ:
        path_info = os.environ["PATH_INFO"]
        style = path_info == "/style"
        atom = path_info == "/atom"
        tag = path_info.startswith("/tag/")
        post = path_info.startswith("/post/")
        post_preview = path_info.startswith("/preview/post/")
        artlist = path_info.startswith("/list")
        comment = path_info.startswith("/comment/") and enable_comments
        if (
            not style
            and not atom
            and not post
            and not post_preview
            and not tag
            and not comment
            and not artlist
        ):
            date = path_info.split("/")[1:]
            try:
                if len(date) > 1 and date[0]:
                    year = int(date[0])
                if len(date) > 2 and date[1]:
                    month = int(date[1])
                if len(date) > 3 and date[2]:
                    day = int(date[2])
            except ValueError:
                pass
        elif post:
            uuid = path_info.replace("/post/", "")
            uuid = uuid.replace("/", "")
        elif post_preview:
            art_path = path_info.replace("/preview/post/", "")
            art_path = urllib.parse.unquote_plus(art_path)
            art_path = os.path.join(data_path, art_path)
            art_path = os.path.realpath(art_path)
            common = os.path.commonprefix([data_path, art_path])
            if common != data_path:  # something nasty happened
                post_preview = False
            art_path = art_path[len(data_path) + 1 :]
        elif tag:
            t = path_info.replace("/tag/", "")
            t = t.replace("/", "")
            t = urllib.parse.unquote_plus(t)
            tags = {t}
        elif comment:
            uuid = path_info.replace("/comment/", "")
            uuid = uuid.replace("#comment", "")
            uuid = uuid.replace("/", "")
            author = form.getfirst("comformauthor", "")
            link = form.getfirst("comformlink", "")
            captcha = form.getfirst("comformcaptcha", "")
            body = form.getfirst("comformbody", "")

    db = ArticleDB(os.path.join(data_path, "db"))
    if atom:
        articles = db.get_articles(tags=tags)
        articles.sort(**get_sort_args(sort_str, "-created"))
        render_atom(articles[:index_articles])
    elif style:
        render_style()
    elif post:
        render_html([db.get_article(uuid)], db, year, enable_comments)
    elif post_preview:
        article = Article(art_path, datetime.datetime.now(), datetime.datetime.now())
        render_html([article], db, year, enable_comments)
    elif artlist:
        articles = db.get_articles()
        articles.sort(**get_sort_args(sort_str, "+title"))
        render_artlist(articles, db)
    elif comment and enable_comments:
        form_data = CommentFormData(
            author.strip().replace("\n", " "),
            link.strip().replace("\n", " "),
            captcha,
            body.replace("\r", ""),
        )
        article = db.get_article(uuid)
        captcha = captcha_method(article)
        redirect = False
        valid = True
        if not form_data.author:
            form_data.author_error = "please, enter your name"
            valid = False
        if form_data.link:
            link = valid_link(form_data.link)
            if link:
                form_data.link = link
            else:
                form_data.link_error = "please, enter a " "valid link"
                valid = False
        if not captcha.validate(form_data):
            form_data.captcha_error = captcha.help
            valid = False
        if not form_data.body:
            form_data.body_error = "please, write a comment"
            valid = False
        else:
            error = validate_rst(form_data.body, secure=False)
            if error is not None:
                (line, desc, ctx) = error
                at = ""
                if line:
                    at = " at line %d" % line
                form_data.body_error = "error%s: %s" % (at, desc)
                valid = False
        if valid:
            c = article.add_comment(form_data.author, form_data.body, form_data.link)
            c.save()
            cdb = CommentDB(article)
            cdb.comments = article.comments
            cdb.save()
            redirect = blog_url + "/post/" + uuid + "#comment-" + str(c.number)
        render_html([article], db, year, enable_comments, redirect, form_data)
    else:
        articles = db.get_articles(year, month, day, tags)
        articles.sort(**get_sort_args(sort_str, "-created"))
        if not year and not month and not day and not tags:
            articles = articles[:index_articles]
        render_html(articles, db, year)


def usage():
    print("Usage: %s {add|rm|update} article_path" % sys.argv[0])


def handle_cmd():
    if len(sys.argv) != 3:
        usage()
        return 1

    cmd = sys.argv[1]
    art_path = os.path.realpath(sys.argv[2])

    if os.path.commonprefix([data_path, art_path]) != data_path:
        print(
            "Error: article (%s) must be inside data_path (%s)" % (art_path, data_path)
        )
        return 1
    art_path = art_path[len(data_path) + 1 :]

    db_filename = os.path.join(data_path, "db")
    if not os.path.isfile(db_filename):
        open(db_filename, "w").write("")
    db = ArticleDB(db_filename)

    if cmd == "add":
        article = Article(art_path, datetime.datetime.now(), datetime.datetime.now())
        for a in db.articles:
            if a == article:
                print("Error: article already exists")
                return 1
        db.articles.append(article)
        db.save()
        if enable_comments:
            comment_dir = os.path.join(comments_path, article.uuid)
            try:
                os.mkdir(comment_dir, 0o775)
            except OSError as e:
                if e.errno != errno.EEXIST:
                    print(
                        "Error: can't create comments "
                        "directory %s (%s)" % (comment_dir, e)
                    )
                # otherwise is probably a removed and re-added
                # article
    elif cmd == "rm":
        article = Article(art_path)
        for a in db.articles:
            if a == article:
                break
        else:
            print("Error: no such article")
            return 1
        if enable_comments:
            r = input("Remove comments [y/N]? ")
        db.articles.remove(a)
        db.save()
        if enable_comments and r.lower() == "y":
            shutil.rmtree(os.path.join(comments_path, a.uuid))
    elif cmd == "update":
        article = Article(art_path)
        for a in db.articles:
            if a == article:
                break
        else:
            print("Error: no such article")
            return 1
        a.updated = datetime.datetime.now()
        db.save()
    else:
        usage()
        return 1

    return 0


if "GATEWAY_INTERFACE" in os.environ:
    i = datetime.datetime.now()
    handle_cgi()
    f = datetime.datetime.now()
    print("<!-- render time: %s -->" % (f - i))
else:
    sys.exit(handle_cmd())