[e362d3]: inc / Pod / Checker.pm Maximize Restore History

Download this file

Checker.pm    1274 lines (1041 with data), 40.8 kB

   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
#############################################################################
# Pod/Checker.pm -- check pod documents for syntax errors
#
# Added =ff and O<> to Checker.pm to make bookchecker program
# work for PDL::Book pod files. Chris Marshall, 22-Jan-2012
#
# Copyright (C) 1994-2000 by Bradford Appleton. All rights reserved.
# This file is part of "PodParser". PodParser is free software;
# you can redistribute it and/or modify it under the same terms
# as Perl itself.
#############################################################################
package Pod::Checker;
use strict;
use vars qw($VERSION @ISA @EXPORT %VALID_COMMANDS %VALID_SEQUENCES);
$VERSION = '1.45'; ## Current version of this package
require 5.005; ## requires this Perl version or later
use Pod::ParseUtils; ## for hyperlinks and lists
=head1 NAME
Pod::Checker, podchecker() - check pod documents for syntax errors
=head1 SYNOPSIS
use Pod::Checker;
$syntax_okay = podchecker($filepath, $outputpath, %options);
my $checker = new Pod::Checker %options;
$checker->parse_from_file($filepath, \*STDERR);
=head1 OPTIONS/ARGUMENTS
C<$filepath> is the input POD to read and C<$outputpath> is
where to write POD syntax error messages. Either argument may be a scalar
indicating a file-path, or else a reference to an open filehandle.
If unspecified, the input-file it defaults to C<\*STDIN>, and
the output-file defaults to C<\*STDERR>.
=head2 podchecker()
This function can take a hash of options:
=over 4
=item B<-warnings> =E<gt> I<val>
Turn warnings on/off. I<val> is usually 1 for on, but higher values
trigger additional warnings. See L<"Warnings">.
=back
=head1 DESCRIPTION
B<podchecker> will perform syntax checking of Perl5 POD format documentation.
Curious/ambitious users are welcome to propose additional features they wish
to see in B<Pod::Checker> and B<podchecker> and verify that the checks are
consistent with L<perlpod>.
The following checks are currently performed:
=over 4
=item *
Unknown '=xxxx' commands, unknown 'XE<lt>...E<gt>' interior-sequences,
and unterminated interior sequences.
=item *
Check for proper balancing of C<=begin> and C<=end>. The contents of such
a block are generally ignored, i.e. no syntax checks are performed.
=item *
Check for proper nesting and balancing of C<=over>, C<=item> and C<=back>.
=item *
Check for same nested interior-sequences (e.g.
C<LE<lt>...LE<lt>...E<gt>...E<gt>>).
=item *
Check for malformed or non-existing entities C<EE<lt>...E<gt>>.
=item *
Check for correct syntax of hyperlinks C<LE<lt>...E<gt>>. See L<perlpod>
for details.
=item *
Check for unresolved document-internal links. This check may also reveal
misspelled links that seem to be internal links but should be links
to something else.
=back
=head1 DIAGNOSTICS
=head2 Errors
=over 4
=item * empty =headn
A heading (C<=head1> or C<=head2>) without any text? That ain't no
heading!
=item * =over on line I<N> without closing =back
The C<=over> command does not have a corresponding C<=back> before the
next heading (C<=head1> or C<=head2>) or the end of the file.
=item * =item without previous =over
=item * =back without previous =over
An C<=item> or C<=back> command has been found outside a
C<=over>/C<=back> block.
=item * No argument for =begin
A C<=begin> command was found that is not followed by the formatter
specification.
=item * =end without =begin
A standalone C<=end> command was found.
=item * Nested =begin's
There were at least two consecutive C<=begin> commands without
the corresponding C<=end>. Only one C<=begin> may be active at
a time.
=item * =for without formatter specification
There is no specification of the formatter after the C<=for> command.
=item * unresolved internal link I<NAME>
The given link to I<NAME> does not have a matching node in the current
POD. This also happened when a single word node name is not enclosed in
C<"">.
=item * Unknown command "I<CMD>"
An invalid POD command has been found. Valid are C<=head1>, C<=head2>,
C<=head3>, C<=head4>, C<=over>, C<=item>, C<=back>, C<=begin>, C<=end>,
C<=for>, C<=pod>, C<=cut>
=item * Unknown interior-sequence "I<SEQ>"
An invalid markup command has been encountered. Valid are:
C<BE<lt>E<gt>>, C<CE<lt>E<gt>>, C<EE<lt>E<gt>>, C<FE<lt>E<gt>>,
C<IE<lt>E<gt>>, C<LE<lt>E<gt>>, C<SE<lt>E<gt>>, C<XE<lt>E<gt>>,
C<ZE<lt>E<gt>>
=item * nested commands I<CMD>E<lt>...I<CMD>E<lt>...E<gt>...E<gt>
Two nested identical markup commands have been found. Generally this
does not make sense.
=item * garbled entity I<STRING>
The I<STRING> found cannot be interpreted as a character entity.
=item * Entity number out of range
An entity specified by number (dec, hex, oct) is out of range (1-255).
=item * malformed link LE<lt>E<gt>
The link found cannot be parsed because it does not conform to the
syntax described in L<perlpod>.
=item * nonempty ZE<lt>E<gt>
The C<ZE<lt>E<gt>> sequence is supposed to be empty.
=item * empty XE<lt>E<gt>
The index entry specified contains nothing but whitespace.
=item * Spurious text after =pod / =cut
The commands C<=pod> and C<=cut> do not take any arguments.
=item * Spurious character(s) after =back
The C<=back> command does not take any arguments.
=back
=head2 Warnings
These may not necessarily cause trouble, but indicate mediocre style.
=over 4
=item * multiple occurrence of link target I<name>
The POD file has some C<=item> and/or C<=head> commands that have
the same text. Potential hyperlinks to such a text cannot be unique then.
This warning is printed only with warning level greater than one.
=item * line containing nothing but whitespace in paragraph
There is some whitespace on a seemingly empty line. POD is very sensitive
to such things, so this is flagged. B<vi> users switch on the B<list>
option to avoid this problem.
=begin _disabled_
=item * file does not start with =head
The file starts with a different POD directive than head.
This is most probably something you do not want.
=end _disabled_
=item * previous =item has no contents
There is a list C<=item> right above the flagged line that has no
text contents. You probably want to delete empty items.
=item * preceding non-item paragraph(s)
A list introduced by C<=over> starts with a text or verbatim paragraph,
but continues with C<=item>s. Move the non-item paragraph out of the
C<=over>/C<=back> block.
=item * =item type mismatch (I<one> vs. I<two>)
A list started with e.g. a bullet-like C<=item> and continued with a
numbered one. This is obviously inconsistent. For most translators the
type of the I<first> C<=item> determines the type of the list.
=item * I<N> unescaped C<E<lt>E<gt>> in paragraph
Angle brackets not written as C<E<lt>ltE<gt>> and C<E<lt>gtE<gt>>
can potentially cause errors as they could be misinterpreted as
markup commands. This is only printed when the -warnings level is
greater than 1.
=item * Unknown entity
A character entity was found that does not belong to the standard
ISO set or the POD specials C<verbar> and C<sol>.
=item * No items in =over
The list opened with C<=over> does not contain any items.
=item * No argument for =item
C<=item> without any parameters is deprecated. It should either be followed
by C<*> to indicate an unordered list, by a number (optionally followed
by a dot) to indicate an ordered (numbered) list or simple text for a
definition list.
=item * empty section in previous paragraph
The previous section (introduced by a C<=head> command) does not contain
any text. This usually indicates that something is missing. Note: A
C<=head1> followed immediately by C<=head2> does not trigger this warning.
=item * Verbatim paragraph in NAME section
The NAME section (C<=head1 NAME>) should consist of a single paragraph
with the script/module name, followed by a dash `-' and a very short
description of what the thing is good for.
=item * =headI<n> without preceding higher level
For example if there is a C<=head2> in the POD file prior to a
C<=head1>.
=back
=head2 Hyperlinks
There are some warnings with respect to malformed hyperlinks:
=over 4
=item * ignoring leading/trailing whitespace in link
There is whitespace at the beginning or the end of the contents of
LE<lt>...E<gt>.
=item * (section) in '$page' deprecated
There is a section detected in the page name of LE<lt>...E<gt>, e.g.
C<LE<lt>passwd(2)E<gt>>. POD hyperlinks may point to POD documents only.
Please write C<CE<lt>passwd(2)E<gt>> instead. Some formatters are able
to expand this to appropriate code. For links to (builtin) functions,
please say C<LE<lt>perlfunc/mkdirE<gt>>, without ().
=item * alternative text/node '%s' contains non-escaped | or /
The characters C<|> and C</> are special in the LE<lt>...E<gt> context.
Although the hyperlink parser does its best to determine which "/" is
text and which is a delimiter in case of doubt, one ought to escape
these literal characters like this:
/ E<sol>
| E<verbar>
=back
=head1 RETURN VALUE
B<podchecker> returns the number of POD syntax errors found or -1 if
there were no POD commands at all found in the file.
=head1 EXAMPLES
See L</SYNOPSIS>
=head1 INTERFACE
While checking, this module collects document properties, e.g. the nodes
for hyperlinks (C<=headX>, C<=item>) and index entries (C<XE<lt>E<gt>>).
POD translators can use this feature to syntax-check and get the nodes in
a first pass before actually starting to convert. This is expensive in terms
of execution time, but allows for very robust conversions.
Since PodParser-1.24 the B<Pod::Checker> module uses only the B<poderror>
method to print errors and warnings. The summary output (e.g.
"Pod syntax OK") has been dropped from the module and has been included in
B<podchecker> (the script). This allows users of B<Pod::Checker> to
control completely the output behavior. Users of B<podchecker> (the script)
get the well-known behavior.
=cut
#############################################################################
#use diagnostics;
use Carp qw(croak);
use Exporter;
use Pod::Parser;
@ISA = qw(Pod::Parser);
@EXPORT = qw(&podchecker);
my %VALID_COMMANDS = (
'pod' => 1,
'cut' => 1,
'head1' => 1,
'head2' => 1,
'head3' => 1,
'head4' => 1,
'over' => 1,
'back' => 1,
'item' => 1,
'for' => 1,
'begin' => 1,
'end' => 1,
'encoding' => 1,
'ff' => 1, # from pod2pdf
);
my %VALID_SEQUENCES = (
'I' => 1,
'B' => 1,
'S' => 1,
'C' => 1,
'L' => 1,
'F' => 1,
'X' => 1,
'Z' => 1,
'E' => 1,
'O' => 1, # from pod2pdf
);
# stolen from HTML::Entities
my %ENTITIES = (
# Some normal chars that have special meaning in SGML context
amp => '&', # ampersand
'gt' => '>', # greater than
'lt' => '<', # less than
quot => '"', # double quote
# PUBLIC ISO 8879-1986//ENTITIES Added Latin 1//EN//HTML
AElig => '�', # capital AE diphthong (ligature)
Aacute => '�', # capital A, acute accent
Acirc => '�', # capital A, circumflex accent
Agrave => '�', # capital A, grave accent
Aring => '�', # capital A, ring
Atilde => '�', # capital A, tilde
Auml => '�', # capital A, dieresis or umlaut mark
Ccedil => '�', # capital C, cedilla
ETH => '�', # capital Eth, Icelandic
Eacute => '�', # capital E, acute accent
Ecirc => '�', # capital E, circumflex accent
Egrave => '�', # capital E, grave accent
Euml => '�', # capital E, dieresis or umlaut mark
Iacute => '�', # capital I, acute accent
Icirc => '�', # capital I, circumflex accent
Igrave => '�', # capital I, grave accent
Iuml => '�', # capital I, dieresis or umlaut mark
Ntilde => '�', # capital N, tilde
Oacute => '�', # capital O, acute accent
Ocirc => '�', # capital O, circumflex accent
Ograve => '�', # capital O, grave accent
Oslash => '�', # capital O, slash
Otilde => '�', # capital O, tilde
Ouml => '�', # capital O, dieresis or umlaut mark
THORN => '�', # capital THORN, Icelandic
Uacute => '�', # capital U, acute accent
Ucirc => '�', # capital U, circumflex accent
Ugrave => '�', # capital U, grave accent
Uuml => '�', # capital U, dieresis or umlaut mark
Yacute => '�', # capital Y, acute accent
aacute => '�', # small a, acute accent
acirc => '�', # small a, circumflex accent
aelig => '�', # small ae diphthong (ligature)
agrave => '�', # small a, grave accent
aring => '�', # small a, ring
atilde => '�', # small a, tilde
auml => '�', # small a, dieresis or umlaut mark
ccedil => '�', # small c, cedilla
eacute => '�', # small e, acute accent
ecirc => '�', # small e, circumflex accent
egrave => '�', # small e, grave accent
eth => '�', # small eth, Icelandic
euml => '�', # small e, dieresis or umlaut mark
iacute => '�', # small i, acute accent
icirc => '�', # small i, circumflex accent
igrave => '�', # small i, grave accent
iuml => '�', # small i, dieresis or umlaut mark
ntilde => '�', # small n, tilde
oacute => '�', # small o, acute accent
ocirc => '�', # small o, circumflex accent
ograve => '�', # small o, grave accent
oslash => '�', # small o, slash
otilde => '�', # small o, tilde
ouml => '�', # small o, dieresis or umlaut mark
szlig => '�', # small sharp s, German (sz ligature)
thorn => '�', # small thorn, Icelandic
uacute => '�', # small u, acute accent
ucirc => '�', # small u, circumflex accent
ugrave => '�', # small u, grave accent
uuml => '�', # small u, dieresis or umlaut mark
yacute => '�', # small y, acute accent
yuml => '�', # small y, dieresis or umlaut mark
# Some extra Latin 1 chars that are listed in the HTML3.2 draft (21-May-96)
copy => '�', # copyright sign
reg => '�', # registered sign
nbsp => "\240", # non breaking space
# Additional ISO-8859/1 entities listed in rfc1866 (section 14)
iexcl => '�',
cent => '�',
pound => '�',
curren => '�',
yen => '�',
brvbar => '�',
sect => '�',
uml => '�',
ordf => '�',
laquo => '�',
'not' => '�', # not is a keyword in perl
shy => '�',
macr => '�',
deg => '�',
plusmn => '�',
sup1 => '�',
sup2 => '�',
sup3 => '�',
acute => '�',
micro => '�',
para => '�',
middot => '�',
cedil => '�',
ordm => '�',
raquo => '�',
frac14 => '�',
frac12 => '�',
frac34 => '�',
iquest => '�',
'times' => '�', # times is a keyword in perl
divide => '�',
# some POD special entities
verbar => '|',
sol => '/'
);
##---------------------------------------------------------------------------
##---------------------------------
## Function definitions begin here
##---------------------------------
sub podchecker {
my ($infile, $outfile, %options) = @_;
local $_;
## Set defaults
$infile ||= \*STDIN;
$outfile ||= \*STDERR;
## Now create a pod checker
my $checker = new Pod::Checker(%options);
## Now check the pod document for errors
$checker->parse_from_file($infile, $outfile);
## Return the number of errors found
return $checker->num_errors();
}
##---------------------------------------------------------------------------
##-------------------------------
## Method definitions begin here
##-------------------------------
##################################
=over 4
=item C<Pod::Checker-E<gt>new( %options )>
Return a reference to a new Pod::Checker object that inherits from
Pod::Parser and is used for calling the required methods later. The
following options are recognized:
C<-warnings =E<gt> num>
Print warnings if C<num> is true. The higher the value of C<num>,
the more warnings are printed. Currently there are only levels 1 and 2.
C<-quiet =E<gt> num>
If C<num> is true, do not print any errors/warnings. This is useful
when Pod::Checker is used to munge POD code into plain text from within
POD formatters.
=cut
## sub new {
## my $this = shift;
## my $class = ref($this) || $this;
## my %params = @_;
## my $self = {%params};
## bless $self, $class;
## $self->initialize();
## return $self;
## }
sub initialize {
my $self = shift;
## Initialize number of errors, and setup an error function to
## increment this number and then print to the designated output.
$self->{_NUM_ERRORS} = 0;
$self->{_NUM_WARNINGS} = 0;
$self->{-quiet} ||= 0;
# set the error handling subroutine
$self->errorsub($self->{-quiet} ? sub { 1; } : 'poderror');
$self->{_commands} = 0; # total number of POD commands encountered
$self->{_list_stack} = []; # stack for nested lists
$self->{_have_begin} = ''; # stores =begin
$self->{_links} = []; # stack for internal hyperlinks
$self->{_nodes} = []; # stack for =head/=item nodes
$self->{_index} = []; # text in X<>
# print warnings?
$self->{-warnings} = 1 unless(defined $self->{-warnings});
$self->{_current_head1} = ''; # the current =head1 block
$self->parseopts(-process_cut_cmd => 1, -warnings => $self->{-warnings});
}
##################################
=item C<$checker-E<gt>poderror( @args )>
=item C<$checker-E<gt>poderror( {%opts}, @args )>
Internal method for printing errors and warnings. If no options are
given, simply prints "@_". The following options are recognized and used
to form the output:
-msg
A message to print prior to C<@args>.
-line
The line number the error occurred in.
-file
The file (name) the error occurred in.
-severity
The error level, should be 'WARNING' or 'ERROR'.
=cut
# Invoked as $self->poderror( @args ), or $self->poderror( {%opts}, @args )
sub poderror {
my $self = shift;
my %opts = (ref $_[0]) ? %{shift()} : ();
## Retrieve options
chomp( my $msg = ($opts{-msg} || '')."@_" );
my $line = (exists $opts{-line}) ? " at line $opts{-line}" : '';
my $file = (exists $opts{-file}) ? " in file $opts{-file}" : '';
unless (exists $opts{-severity}) {
## See if can find severity in message prefix
$opts{-severity} = $1 if ( $msg =~ s/^\**\s*([A-Z]{3,}):\s+// );
}
my $severity = (exists $opts{-severity}) ? "*** $opts{-severity}: " : '';
## Increment error count and print message "
++($self->{_NUM_ERRORS})
if(!%opts || ($opts{-severity} && $opts{-severity} eq 'ERROR'));
++($self->{_NUM_WARNINGS})
if(!%opts || ($opts{-severity} && $opts{-severity} eq 'WARNING'));
unless($self->{-quiet}) {
my $out_fh = $self->output_handle() || \*STDERR;
print $out_fh ($severity, $msg, $line, $file, "\n")
if($self->{-warnings} || !%opts || $opts{-severity} ne 'WARNING');
}
}
##################################
=item C<$checker-E<gt>num_errors()>
Set (if argument specified) and retrieve the number of errors found.
=cut
sub num_errors {
return (@_ > 1) ? ($_[0]->{_NUM_ERRORS} = $_[1]) : $_[0]->{_NUM_ERRORS};
}
##################################
=item C<$checker-E<gt>num_warnings()>
Set (if argument specified) and retrieve the number of warnings found.
=cut
sub num_warnings {
return (@_ > 1) ? ($_[0]->{_NUM_WARNINGS} = $_[1]) : $_[0]->{_NUM_WARNINGS};
}
##################################
=item C<$checker-E<gt>name()>
Set (if argument specified) and retrieve the canonical name of POD as
found in the C<=head1 NAME> section.
=cut
sub name {
return (@_ > 1 && $_[1]) ?
($_[0]->{-name} = $_[1]) : $_[0]->{-name};
}
##################################
=item C<$checker-E<gt>node()>
Add (if argument specified) and retrieve the nodes (as defined by C<=headX>
and C<=item>) of the current POD. The nodes are returned in the order of
their occurrence. They consist of plain text, each piece of whitespace is
collapsed to a single blank.
=cut
sub node {
my ($self,$text) = @_;
if(defined $text) {
$text =~ s/\s+$//s; # strip trailing whitespace
$text =~ s/\s+/ /gs; # collapse whitespace
# add node, order important!
push(@{$self->{_nodes}}, $text);
# keep also a uniqueness counter
$self->{_unique_nodes}->{$text}++ if($text !~ /^\s*$/s);
return $text;
}
@{$self->{_nodes}};
}
##################################
=item C<$checker-E<gt>idx()>
Add (if argument specified) and retrieve the index entries (as defined by
C<XE<lt>E<gt>>) of the current POD. They consist of plain text, each piece
of whitespace is collapsed to a single blank.
=cut
# set/return index entries of current POD
sub idx {
my ($self,$text) = @_;
if(defined $text) {
$text =~ s/\s+$//s; # strip trailing whitespace
$text =~ s/\s+/ /gs; # collapse whitespace
# add node, order important!
push(@{$self->{_index}}, $text);
# keep also a uniqueness counter
$self->{_unique_nodes}->{$text}++ if($text !~ /^\s*$/s);
return $text;
}
@{$self->{_index}};
}
##################################
=item C<$checker-E<gt>hyperlink()>
Add (if argument specified) and retrieve the hyperlinks (as defined by
C<LE<lt>E<gt>>) of the current POD. They consist of a 2-item array: line
number and C<Pod::Hyperlink> object.
=back
=cut
# set/return hyperlinks of the current POD
sub hyperlink {
my $self = shift;
if($_[0]) {
push(@{$self->{_links}}, $_[0]);
return $_[0];
}
@{$self->{_links}};
}
## overrides for Pod::Parser
sub end_pod {
## Do some final checks and
## print the number of errors found
my $self = shift;
my $infile = $self->input_file();
if(@{$self->{_list_stack}}) {
my $list;
while(($list = $self->_close_list('EOF',$infile)) &&
$list->indent() ne 'auto') {
$self->poderror({ -line => 'EOF', -file => $infile,
-severity => 'ERROR', -msg => '=over on line ' .
$list->start() . ' without closing =back' });
}
}
# check validity of document internal hyperlinks
# first build the node names from the paragraph text
my %nodes;
foreach($self->node()) {
$nodes{$_} = 1;
if(/^(\S+)\s+\S/) {
# we have more than one word. Use the first as a node, too.
# This is used heavily in perlfunc.pod
$nodes{$1} ||= 2; # derived node
}
}
foreach($self->idx()) {
$nodes{$_} = 3; # index node
}
foreach($self->hyperlink()) {
my ($line,$link) = @$_;
# _TODO_ what if there is a link to the page itself by the name,
# e.g. in Tk::Pod : L<Tk::Pod/"DESCRIPTION">
if($link->node() && !$link->page() && $link->type() ne 'hyperlink') {
my $node = $self->_check_ptree($self->parse_text($link->node(),
$line), $line, $infile, 'L');
if($node && !$nodes{$node}) {
$self->poderror({ -line => $line || '', -file => $infile,
-severity => 'ERROR',
-msg => "unresolved internal link '$node'"});
}
}
}
# check the internal nodes for uniqueness. This pertains to
# =headX, =item and X<...>
if($self->{-warnings} && $self->{-warnings}>1) {
foreach(grep($self->{_unique_nodes}->{$_} > 1,
keys %{$self->{_unique_nodes}})) {
$self->poderror({ -line => '-', -file => $infile,
-severity => 'WARNING',
-msg => "multiple occurrence of link target '$_'"});
}
}
# no POD found here
$self->num_errors(-1) if($self->{_commands} == 0);
}
# check a POD command directive
sub command {
my ($self, $cmd, $paragraph, $line_num, $pod_para) = @_;
my ($file, $line) = $pod_para->file_line;
## Check the command syntax
my $arg; # this will hold the command argument
if (! $VALID_COMMANDS{$cmd}) {
$self->poderror({ -line => $line, -file => $file, -severity => 'ERROR',
-msg => "Unknown command '$cmd'" });
}
else { # found a valid command
$self->{_commands}++; # delete this line if below is enabled again
##### following check disabled due to strong request
#if(!$self->{_commands}++ && $cmd !~ /^head/) {
# $self->poderror({ -line => $line, -file => $file,
# -severity => 'WARNING',
# -msg => "file does not start with =head" });
#}
# check syntax of particular command
if($cmd eq 'over') {
# check for argument
$arg = $self->interpolate_and_check($paragraph, $line,$file);
my $indent = 4; # default
if($arg && $arg =~ /^\s*(\d+)\s*$/) {
$indent = $1;
}
# start a new list
$self->_open_list($indent,$line,$file);
}
elsif($cmd eq 'item') {
# are we in a list?
unless(@{$self->{_list_stack}}) {
$self->poderror({ -line => $line, -file => $file,
-severity => 'ERROR',
-msg => '=item without previous =over' });
# auto-open in case we encounter many more
$self->_open_list('auto',$line,$file);
}
my $list = $self->{_list_stack}->[0];
# check whether the previous item had some contents
if(defined $self->{_list_item_contents} &&
$self->{_list_item_contents} == 0) {
$self->poderror({ -line => $line, -file => $file,
-severity => 'WARNING',
-msg => 'previous =item has no contents' });
}
if($list->{_has_par}) {
$self->poderror({ -line => $line, -file => $file,
-severity => 'WARNING',
-msg => 'preceding non-item paragraph(s)' });
delete $list->{_has_par};
}
# check for argument
$arg = $self->interpolate_and_check($paragraph, $line, $file);
if($arg && $arg =~ /(\S+)/) {
$arg =~ s/[\s\n]+$//;
my $type;
if($arg =~ /^[*]\s*(\S*.*)/) {
$type = 'bullet';
$self->{_list_item_contents} = $1 ? 1 : 0;
$arg = $1;
}
elsif($arg =~ /^\d+\.?\s+(\S*)/) {
$type = 'number';
$self->{_list_item_contents} = $1 ? 1 : 0;
$arg = $1;
}
else {
$type = 'definition';
$self->{_list_item_contents} = 1;
}
my $first = $list->type();
if($first && $first ne $type) {
$self->poderror({ -line => $line, -file => $file,
-severity => 'WARNING',
-msg => "=item type mismatch ('$first' vs. '$type')"});
}
else { # first item
$list->type($type);
}
}
else {
$self->poderror({ -line => $line, -file => $file,
-severity => 'WARNING',
-msg => 'No argument for =item' });
$arg = ' '; # empty
$self->{_list_item_contents} = 0;
}
# add this item
$list->item($arg);
# remember this node
$self->node($arg);
}
elsif($cmd eq 'back') {
# check if we have an open list
unless(@{$self->{_list_stack}}) {
$self->poderror({ -line => $line, -file => $file,
-severity => 'ERROR',
-msg => '=back without previous =over' });
}
else {
# check for spurious characters
$arg = $self->interpolate_and_check($paragraph, $line,$file);
if($arg && $arg =~ /\S/) {
$self->poderror({ -line => $line, -file => $file,
-severity => 'ERROR',
-msg => 'Spurious character(s) after =back' });
}
# close list
my $list = $self->_close_list($line,$file);
# check for empty lists
if(!$list->item() && $self->{-warnings}) {
$self->poderror({ -line => $line, -file => $file,
-severity => 'WARNING',
-msg => 'No items in =over (at line ' .
$list->start() . ') / =back list'});
}
}
}
elsif($cmd =~ /^head(\d+)/) {
my $hnum = $1;
$self->{"_have_head_$hnum"}++; # count head types
if($hnum > 1 && !$self->{'_have_head_'.($hnum -1)}) {
$self->poderror({ -line => $line, -file => $file,
-severity => 'WARNING',
-msg => "=head$hnum without preceding higher level"});
}
# check whether the previous =head section had some contents
if(defined $self->{_commands_in_head} &&
$self->{_commands_in_head} == 0 &&
defined $self->{_last_head} &&
$self->{_last_head} >= $hnum) {
$self->poderror({ -line => $line, -file => $file,
-severity => 'WARNING',
-msg => 'empty section in previous paragraph'});
}
$self->{_commands_in_head} = -1;
$self->{_last_head} = $hnum;
# check if there is an open list
if(@{$self->{_list_stack}}) {
my $list;
while(($list = $self->_close_list($line,$file)) &&
$list->indent() ne 'auto') {
$self->poderror({ -line => $line, -file => $file,
-severity => 'ERROR',
-msg => '=over on line '. $list->start() .
" without closing =back (at $cmd)" });
}
}
# remember this node
$arg = $self->interpolate_and_check($paragraph, $line,$file);
$arg =~ s/[\s\n]+$//s;
$self->node($arg);
unless(length($arg)) {
$self->poderror({ -line => $line, -file => $file,
-severity => 'ERROR',
-msg => "empty =$cmd"});
}
if($cmd eq 'head1') {
$self->{_current_head1} = $arg;
} else {
$self->{_current_head1} = '';
}
}
elsif($cmd eq 'begin') {
if($self->{_have_begin}) {
# already have a begin
$self->poderror({ -line => $line, -file => $file,
-severity => 'ERROR',
-msg => q{Nested =begin's (first at line } .
$self->{_have_begin} . ')'});
}
else {
# check for argument
$arg = $self->interpolate_and_check($paragraph, $line,$file);
unless($arg && $arg =~ /(\S+)/) {
$self->poderror({ -line => $line, -file => $file,
-severity => 'ERROR',
-msg => 'No argument for =begin'});
}
# remember the =begin
$self->{_have_begin} = "$line:$1";
}
}
elsif($cmd eq 'end') {
if($self->{_have_begin}) {
# close the existing =begin
$self->{_have_begin} = '';
# check for spurious characters
$arg = $self->interpolate_and_check($paragraph, $line,$file);
# the closing argument is optional
#if($arg && $arg =~ /\S/) {
# $self->poderror({ -line => $line, -file => $file,
# -severity => 'WARNING',
# -msg => "Spurious character(s) after =end" });
#}
}
else {
# don't have a matching =begin
$self->poderror({ -line => $line, -file => $file,
-severity => 'ERROR',
-msg => '=end without =begin' });
}
}
elsif($cmd eq 'for') {
unless($paragraph =~ /\s*(\S+)\s*/) {
$self->poderror({ -line => $line, -file => $file,
-severity => 'ERROR',
-msg => '=for without formatter specification' });
}
$arg = ''; # do not expand paragraph below
}
elsif($cmd =~ /^(pod|cut)$/) {
# check for argument
$arg = $self->interpolate_and_check($paragraph, $line,$file);
if($arg && $arg =~ /(\S+)/) {
$self->poderror({ -line => $line, -file => $file,
-severity => 'ERROR',
-msg => "Spurious text after =$cmd"});
}
}
$self->{_commands_in_head}++;
## Check the interior sequences in the command-text
$self->interpolate_and_check($paragraph, $line,$file)
unless(defined $arg);
}
}
sub _open_list
{
my ($self,$indent,$line,$file) = @_;
my $list = Pod::List->new(
-indent => $indent,
-start => $line,
-file => $file);
unshift(@{$self->{_list_stack}}, $list);
undef $self->{_list_item_contents};
$list;
}
sub _close_list
{
my ($self,$line,$file) = @_;
my $list = shift(@{$self->{_list_stack}});
if(defined $self->{_list_item_contents} &&
$self->{_list_item_contents} == 0) {
$self->poderror({ -line => $line, -file => $file,
-severity => 'WARNING',
-msg => 'previous =item has no contents' });
}
undef $self->{_list_item_contents};
$list;
}
# process a block of some text
sub interpolate_and_check {
my ($self, $paragraph, $line, $file) = @_;
## Check the interior sequences in the command-text
# and return the text
$self->_check_ptree(
$self->parse_text($paragraph,$line), $line, $file, '');
}
sub _check_ptree {
my ($self,$ptree,$line,$file,$nestlist) = @_;
local($_);
my $text = '';
# process each node in the parse tree
foreach(@$ptree) {
# regular text chunk
unless(ref) {
# count the unescaped angle brackets
# complain only when warning level is greater than 1
if($self->{-warnings} && $self->{-warnings}>1) {
my $count;
if($count = tr/<>/<>/) {
$self->poderror({ -line => $line, -file => $file,
-severity => 'WARNING',
-msg => "$count unescaped <> in paragraph" });
}
}
$text .= $_;
next;
}
# have an interior sequence
my $cmd = $_->cmd_name();
my $contents = $_->parse_tree();
($file,$line) = $_->file_line();
# check for valid tag
if (! $VALID_SEQUENCES{$cmd}) {
$self->poderror({ -line => $line, -file => $file,
-severity => 'ERROR',
-msg => qq(Unknown interior-sequence '$cmd')});
# expand it anyway
$text .= $self->_check_ptree($contents, $line, $file, "$nestlist$cmd");
next;
}
if($nestlist =~ /$cmd/) {
$self->poderror({ -line => $line, -file => $file,
-severity => 'WARNING',
-msg => "nested commands $cmd<...$cmd<...>...>"});
# _TODO_ should we add the contents anyway?
# expand it anyway, see below
}
if($cmd eq 'E') {
# preserve entities
if(@$contents > 1 || ref $$contents[0] || $$contents[0] !~ /^\w+$/) {
$self->poderror({ -line => $line, -file => $file,
-severity => 'ERROR',
-msg => 'garbled entity ' . $_->raw_text()});
next;
}
my $ent = $$contents[0];
my $val;
if($ent =~ /^0x[0-9a-f]+$/i) {
# hexadec entity
$val = hex($ent);
}
elsif($ent =~ /^0\d+$/) {
# octal
$val = oct($ent);
}
elsif($ent =~ /^\d+$/) {
# numeric entity
$val = $ent;
}
if(defined $val) {
if($val>0 && $val<256) {
$text .= chr($val);
}
else {
$self->poderror({ -line => $line, -file => $file,
-severity => 'ERROR',
-msg => 'Entity number out of range ' . $_->raw_text()});
}
}
elsif($ENTITIES{$ent}) {
# known ISO entity
$text .= $ENTITIES{$ent};
}
else {
$self->poderror({ -line => $line, -file => $file,
-severity => 'WARNING',
-msg => 'Unknown entity ' . $_->raw_text()});
$text .= "E<$ent>";
}
}
elsif($cmd eq 'L') {
# try to parse the hyperlink
my $link = Pod::Hyperlink->new($contents->raw_text());
unless(defined $link) {
$self->poderror({ -line => $line, -file => $file,
-severity => 'ERROR',
-msg => 'malformed link ' . $_->raw_text() ." : $@"});
next;
}
$link->line($line); # remember line
if($self->{-warnings}) {
foreach my $w ($link->warning()) {
$self->poderror({ -line => $line, -file => $file,
-severity => 'WARNING',
-msg => $w });
}
}
# check the link text
$text .= $self->_check_ptree($self->parse_text($link->text(),
$line), $line, $file, "$nestlist$cmd");
# remember link
$self->hyperlink([$line,$link]);
}
elsif($cmd =~ /[BCFIOS]/) {
# add the guts
$text .= $self->_check_ptree($contents, $line, $file, "$nestlist$cmd");
}
elsif($cmd eq 'Z') {
if(length($contents->raw_text())) {
$self->poderror({ -line => $line, -file => $file,
-severity => 'ERROR',
-msg => 'Nonempty Z<>'});
}
}
elsif($cmd eq 'X') {
my $idx = $self->_check_ptree($contents, $line, $file, "$nestlist$cmd");
if($idx =~ /^\s*$/s) {
$self->poderror({ -line => $line, -file => $file,
-severity => 'ERROR',
-msg => 'Empty X<>'});
}
else {
# remember this node
$self->idx($idx);
}
}
else {
# not reached
croak 'internal error';
}
}
$text;
}
# process a block of verbatim text
sub verbatim {
## Nothing particular to check
my ($self, $paragraph, $line_num, $pod_para) = @_;
$self->_preproc_par($paragraph);
if($self->{_current_head1} eq 'NAME') {
my ($file, $line) = $pod_para->file_line;
$self->poderror({ -line => $line, -file => $file,
-severity => 'WARNING',
-msg => 'Verbatim paragraph in NAME section' });
}
}
# process a block of regular text
sub textblock {
my ($self, $paragraph, $line_num, $pod_para) = @_;
my ($file, $line) = $pod_para->file_line;
$self->_preproc_par($paragraph);
# skip this paragraph if in a =begin block
unless($self->{_have_begin}) {
my $block = $self->interpolate_and_check($paragraph, $line,$file);
if($self->{_current_head1} eq 'NAME') {
if($block =~ /^\s*(\S+?)\s*[,-]/) {
# this is the canonical name
$self->{-name} = $1 unless(defined $self->{-name});
}
}
}
}
sub _preproc_par
{
my $self = shift;
$_[0] =~ s/[\s\n]+$//;
if($_[0]) {
$self->{_commands_in_head}++;
$self->{_list_item_contents}++ if(defined $self->{_list_item_contents});
if(@{$self->{_list_stack}} && !$self->{_list_stack}->[0]->item()) {
$self->{_list_stack}->[0]->{_has_par} = 1;
}
}
}
1;
__END__
=head1 AUTHOR
Please report bugs using L<http://rt.cpan.org>.
Brad Appleton E<lt>bradapp@enteract.comE<gt> (initial version),
Marek Rouchal E<lt>marekr@cpan.orgE<gt>
Based on code for B<Pod::Text::pod2text()> written by
Tom Christiansen E<lt>tchrist@mox.perl.comE<gt>
=cut