3
0
mirror of https://github.com/pragma-/pbot.git synced 2024-11-02 18:19:33 +01:00
pbot/applets/cstd.pl

310 lines
8.3 KiB
Perl
Raw Normal View History

2021-02-07 23:37:12 +01:00
#!/usr/bin/env perl
2021-07-11 00:00:22 +02:00
# SPDX-FileCopyrightText: 2021 Pragmatic Software <pragma78@gmail.com>
# SPDX-License-Identifier: MIT
License project under MPL2 This patch adds the file LICENSE which is the verbatim copy of the Mozilla Public License Version 2.0 as retreived from https://www.mozilla.org/media/MPL/2.0/index.815ca599c9df.txt on 2017-03-05. This patch also places license headers for the MPL2 type A variant of the license header in the following files: PBot/AntiFlood.pm PBot/BanTracker.pm PBot/BlackList.pm PBot/BotAdminCommands.pm PBot/BotAdmins.pm PBot/ChanOpCommands.pm PBot/ChanOps.pm PBot/Channels.pm PBot/Commands.pm PBot/DualIndexHashObject.pm PBot/EventDispatcher.pm PBot/FactoidCommands.pm PBot/FactoidModuleLauncher.pm PBot/Factoids.pm PBot/HashObject.pm PBot/IRCHandlers.pm PBot/IgnoreList.pm PBot/IgnoreListCommands.pm PBot/Interpreter.pm PBot/LagChecker.pm PBot/Logger.pm PBot/MessageHistory.pm PBot/MessageHistory_SQLite.pm PBot/NickList.pm PBot/PBot.pm PBot/Plugins.pm PBot/Plugins/AntiAway.pm PBot/Plugins/AntiKickAutoRejoin.pm PBot/Plugins/AntiRepeat.pm PBot/Plugins/AntiTwitter.pm PBot/Plugins/AutoRejoin.pm PBot/Plugins/Counter.pm PBot/Plugins/Quotegrabs.pm PBot/Plugins/Quotegrabs/Quotegrabs_Hashtable.pm PBot/Plugins/Quotegrabs/Quotegrabs_SQLite.pm PBot/Plugins/UrlTitles.pm PBot/Plugins/_Example.pm PBot/Refresher.pm PBot/Registerable.pm PBot/Registry.pm PBot/RegistryCommands.pm PBot/SQLiteLogger.pm PBot/SQLiteLoggerLayer.pm PBot/SelectHandler.pm PBot/StdinReader.pm PBot/Timer.pm PBot/Utils/ParseDate.pm PBot/VERSION.pm build/update-version.pl modules/acronym.pl modules/ago.pl modules/c11std.pl modules/c2english.pl modules/c2english/CGrammar.pm modules/c2english/c2eng.pl modules/c99std.pl modules/cdecl.pl modules/cfaq.pl modules/cjeopardy/IRCColors.pm modules/cjeopardy/QStatskeeper.pm modules/cjeopardy/Scorekeeper.pm modules/cjeopardy/cjeopardy.pl modules/cjeopardy/cjeopardy_answer.pl modules/cjeopardy/cjeopardy_filter.pl modules/cjeopardy/cjeopardy_hint.pl modules/cjeopardy/cjeopardy_qstats.pl modules/cjeopardy/cjeopardy_scores.pl modules/cjeopardy/cjeopardy_show.pl modules/codepad.pl modules/compiler_block.pl modules/compiler_client.pl modules/compiler_vm/Diff.pm modules/compiler_vm/cc modules/compiler_vm/compiler_client.pl modules/compiler_vm/compiler_server.pl modules/compiler_vm/compiler_server_vbox_win32.pl modules/compiler_vm/compiler_server_watchdog.pl modules/compiler_vm/compiler_vm_client.pl modules/compiler_vm/compiler_vm_server.pl modules/compiler_vm/compiler_watchdog.pl modules/compiler_vm/languages/_c_base.pm modules/compiler_vm/languages/_default.pm modules/compiler_vm/languages/bash.pm modules/compiler_vm/languages/bc.pm modules/compiler_vm/languages/bf.pm modules/compiler_vm/languages/c11.pm modules/compiler_vm/languages/c89.pm modules/compiler_vm/languages/c99.pm modules/compiler_vm/languages/clang.pm modules/compiler_vm/languages/clang11.pm modules/compiler_vm/languages/clang89.pm modules/compiler_vm/languages/clang99.pm modules/compiler_vm/languages/clangpp.pm modules/compiler_vm/languages/clisp.pm modules/compiler_vm/languages/cpp.pm modules/compiler_vm/languages/freebasic.pm modules/compiler_vm/languages/go.pm modules/compiler_vm/languages/haskell.pm modules/compiler_vm/languages/java.pm modules/compiler_vm/languages/javascript.pm modules/compiler_vm/languages/ksh.pm modules/compiler_vm/languages/lua.pm modules/compiler_vm/languages/perl.pm modules/compiler_vm/languages/python.pm modules/compiler_vm/languages/python3.pm modules/compiler_vm/languages/qbasic.pm modules/compiler_vm/languages/scheme.pm modules/compiler_vm/languages/server/_c_base.pm modules/compiler_vm/languages/server/_default.pm modules/compiler_vm/languages/server/c11.pm modules/compiler_vm/languages/server/c89.pm modules/compiler_vm/languages/server/c99.pm modules/compiler_vm/languages/server/clang.pm modules/compiler_vm/languages/server/clang11.pm modules/compiler_vm/languages/server/clang89.pm modules/compiler_vm/languages/server/clang99.pm modules/compiler_vm/languages/server/cpp.pm modules/compiler_vm/languages/server/freebasic.pm modules/compiler_vm/languages/server/haskell.pm modules/compiler_vm/languages/server/java.pm modules/compiler_vm/languages/server/qbasic.pm modules/compiler_vm/languages/server/tendra.pm modules/compiler_vm/languages/sh.pm modules/compiler_vm/languages/tendra.pm modules/compliment modules/cstd.pl modules/define.pl modules/dice_roll.pl modules/excuse.sh modules/expand_macros.pl modules/fnord.pl modules/funnyish_quote.pl modules/g.pl modules/gdefine.pl modules/gen_cfacts.pl modules/gencstd.pl modules/get_title.pl modules/getcfact.pl modules/google.pl modules/gspy.pl modules/gtop10.pl modules/gtop15.pl modules/headlines.pl modules/horoscope modules/horrorscope modules/ideone.pl modules/insult.pl modules/love_quote.pl modules/man.pl modules/map.pl modules/math.pl modules/prototype.pl modules/qalc.pl modules/random_quote.pl modules/seen.pl modules/urban modules/weather.pl modules/wikipedia.pl pbot.pl pbot.sh It is highly recommended that this list of files is reviewed to ensure that all files are the copyright of the sole maintainer of the repository. If any files with license headers contain the intellectual property of anyone else, it is recommended that a request is made to revise this patch or that the explicit permission of the co-author is gained to allow for the license of the work to be changed. I (Tomasz Kramkowski), the contributor, take no responsibility for any legal action taken against the maintainer of this repository for incorrectly claiming copyright to any work not owned by the maintainer of this repository.
2017-03-05 22:33:31 +01:00
use warnings;
use strict;
use Getopt::Long qw/GetOptionsFromArray/;
use Encode;
my %standards = (
C99 => 'n1256.out',
C11 => 'n1570.out',
C23 => 'n3047.out',
);
2022-08-12 22:02:00 +02:00
binmode(STDOUT, ":utf8");
binmode(STDERR, ":utf8");
@ARGV = map { decode('UTF-8', $_, 1) } @ARGV;
my ($std, $search, $section, $paragraph, $debug);
my ($match, $list_only, $match_text);
{
my $opt_error;
local $SIG{__WARN__} = sub {
$opt_error = shift;
chomp $opt_error;
};
Getopt::Long::Configure("bundling_override");
GetOptionsFromArray(
\@ARGV,
'std=s' => \$std,
'section|s=s' => \$section,
'num|n=i' => \$match,
'text|t=s' => \$match_text,
'list|l' => \$list_only,
'debug|d=i' => \$debug,
);
$std //= 'C99';
$section //= '';
$match //= 1;
$list_only //= 0;
$debug //= 0;
$std = uc $std;
if (not exists $standards{$std}) {
print "Invalid -std=$std selected. Valid -std= values are: ", join(', ', sort keys %standards), "\n";
exit 1;
}
my $usage = "Usage: $std [-list] [-n#] [-section <section>] [search text] [-text <regex>] -- `section` must be in the form of `X.Y[pZ]` where `X` and `Y` are section/chapter and, optionally, `pZ` is paragraph. If both `section` and `search text` are specified, then the search space will be within the specified section. Use `-n <n>` to skip to the nth match. To list only the section numbers containing 'search text', add -list. To display specific text, use `-text <regex>`.\n";
if ($opt_error) {
print "$opt_error: $usage\n";
exit 1;
}
$search = "@ARGV";
if (!length $section && !length $search) {
print $usage;
exit 1;
}
}
# for paragraphs
use constant {
USER_SPECIFIED => 1,
RESULTS_SPECIFIED => 2,
};
my $section_specified = length $section ? 1 : 0;
my $paragraph_specified = 0;
if ($search =~ s/\b([A-Z0-9]+\.[0-9.p]*)//i) {
2020-02-15 23:38:32 +01:00
$section = $1;
2020-02-15 23:38:32 +01:00
if ($section =~ s/p(\d+)//i) {
$paragraph = $1;
$paragraph_specified = USER_SPECIFIED;
2020-02-15 23:38:32 +01:00
} else {
$paragraph = 1;
}
2020-02-15 23:38:32 +01:00
$section_specified = 1;
}
# add trailing dot if missing
if ($section =~ /^[A-Z0-9]+$/i) {
$section .= '.';
}
$search =~ s/^\s+//;
$search =~ s/\s+$//;
if (not length $section) {
2020-02-15 23:38:32 +01:00
$section = "1.";
$paragraph = 1;
}
if ($list_only and not length $search) {
2020-02-15 23:38:32 +01:00
print "You must specify some search text to use with -list.\n";
exit 1;
}
open FH, "<:encoding(UTF-8)", $standards{$std} or die "Could not open $standards{$std}: $!";
my @contents = <FH>;
close FH;
my $text = join '', @contents;
$text =~ s/\r//g;
my $std_name = $standards{$std};
$std_name =~ s/(.*)\..*$/$1/;
my $result;
2020-02-15 23:38:32 +01:00
my $found_section = "";
my $found_section_title = "";
my $section_title;
my $found_paragraph;
2020-02-15 23:38:32 +01:00
my $found = 0;
my $matches = 0;
my $this_section;
my $comma = "";
2020-02-15 23:38:32 +01:00
if ($list_only) { $result = "Sections containing '$search':\n "; }
my $qsearch = quotemeta $search;
$qsearch =~ s/\\ / /g;
$qsearch =~ s/\s+/\\s+/g;
2022-08-12 22:02:00 +02:00
while ($text =~ m/^([0-9A-Z]+\.[0-9.]*)/msgi) {
2020-02-15 23:38:32 +01:00
$this_section = $1;
print "----------------------------------\n" if $debug >= 2;
print "Processing section [$this_section]\n" if $debug;
2022-08-12 22:02:00 +02:00
if ($section_specified and $this_section !~ m/^\Q$section/i) {
2020-02-15 23:38:32 +01:00
print "No section match, skipping.\n" if $debug >= 4;
next;
}
my $section_text;
if ($text =~ /(.*?)^(?=(?!Footnote)[0-9A-Z]+\.)/msg) {
$section_text = $1;
} else {
2020-02-15 23:38:32 +01:00
print "No section text, end of file marker found.\n" if $debug >= 4;
last;
}
if ($section =~ /Footnote/i) {
$section_text =~ s/^Footnote.*//msi;
2020-02-15 23:38:32 +01:00
$section_text =~ s/^\d.*//ms;
2022-08-12 22:02:00 +02:00
$section_text = $this_section . $section_text;
2020-02-15 23:38:32 +01:00
} elsif ($section_text =~ m/(.*?)$/msg) {
$section_title = $1 if length $1;
$section_title =~ s/^\s+//;
$section_title =~ s/\s+$//;
}
print "$this_section [$section_title]\n" if $debug >= 2;
while ($section_text =~ m/^(\d+)\s(.*?)^(?=\d)/msgic or $section_text =~ m/^(\d+)\s(.*)/msgi) {
my $p = $1;
my $t = $2;
print "paragraph $p: [$t]\n" if $debug >= 3;
if ($paragraph_specified == USER_SPECIFIED and not length $search and $p == $paragraph) {
2020-02-15 23:38:32 +01:00
$result = $t if not $found;
$found_paragraph = $p;
$found_section = $this_section;
$found_section_title = $section_title;
$found = 1;
last;
}
if (length $search) {
eval {
if ($t =~ m/\b$qsearch\b/mis or $section_title =~ m/\b$qsearch\b/mis) {
$matches++;
if ($matches >= $match) {
if ($list_only) {
$result .= sprintf("%s%-15s", $comma, $this_section . "p" . $p);
$result .= " $section_title";
2020-02-15 23:38:32 +01:00
$comma = ",\n ";
} else {
if (not $found) {
$result = $t;
$found_section = $this_section;
$found_section_title = $section_title;
$found_paragraph = $p;
$paragraph_specified = RESULTS_SPECIFIED;
2020-02-15 23:38:32 +01:00
}
$found = 1;
}
}
}
};
if (my $err = $@) {
$err =~ s/.* at .*$//;
print "Error in search regex: $err\n";
2020-02-15 23:38:32 +01:00
exit 0;
}
}
2020-02-15 23:38:32 +01:00
}
last if $found && $paragraph_specified == USER_SPECIFIED;
if ($paragraph_specified == USER_SPECIFIED) {
if (length $search) {
print "No such text '$search' in paragraph $paragraph of section $section of $std_name.\n";
} else {
print "No such paragraph $paragraph in section $section of $std_name.\n";
}
exit 1;
}
2020-02-15 23:38:32 +01:00
if (defined $section_specified and not length $search) {
$found = 1;
$found_section = $this_section;
$found_section_title = $section_title;
$found_paragraph = $paragraph;
$result = $section_text;
last;
}
}
if (not $found and $comma eq "") {
2020-02-15 23:38:32 +01:00
$search =~ s/\\s\+/ /g;
if (length $search) {
print "No such text '$search' found ";
if ($section_specified) {
print "within section '$section' ";
}
} else {
print "No such section '$section' ";
}
print "in $std Draft Standard ($std_name).\n";
exit 1;
}
2022-08-12 22:02:00 +02:00
$result =~ s/\Q$found_section_title// if length $found_section_title;
$result =~ s/^\s+//;
$result =~ s/\s+$//;
2020-02-15 23:38:32 +01:00
if ($matches > 1 and not $list_only) { print "Displaying $match of $matches matches: "; }
if ($comma eq "") {
2022-08-12 22:02:00 +02:00
print "http://www.iso-9899.info/$std_name.html\#$found_section";
print "p" . $found_paragraph if $paragraph_specified;
print "\n\n";
print "[", $found_section_title, "]\n\n" if length $found_section_title;
}
$result =~ s/\s*Constraints\s*$//;
$result =~ s/\s*Semantics\s*$//;
$result =~ s/\s*Description\s*$//;
$result =~ s/\s*Returns\s*$//;
$result =~ s/\s*Runtime-constraints\s*$//;
$result =~ s/\s*Recommended practice\s*$//;
2022-08-12 22:02:00 +02:00
$result =~ s/Footnote\.(\d)/Footnote $1/g;
if (length $match_text) {
my $match_result = $result;
$match_result =~ s/\s+/ /g;
my $match = eval {
my @matches = ($match_result =~ m/($match_text)/msp);
if (@matches > 1) {
shift @matches;
@matches = grep { length $_ } @matches;
}
return [${^PREMATCH}, join (' ... ', @matches), ${^POSTMATCH}];
};
if ($@) {
print "Error in -text option: $@\n";
exit 1;
}
$result = '';
if (length $match->[0]) {
$result = '... ';
}
if (length $match->[1]) {
$result .= $match->[1];
} else {
$result = "No text found for `$match_text`.";
}
if (length $match->[2]) {
$result .= ' ...';
}
}
print "$result\n";