Merge branch 'master' of waschsauger:git/dirty-helpers

find-unused

@@ -0,0 +1,65 @@
+#!/usr/bin/env ruby
+# Find
+# unused
+# directories
+# by
+# looking
+# at
+# the
+# atimes
+# of
+# the
+# contained
+# files.
+#
+require 'optparse'
+
+options = {}
+options[:days] = 180
+
+def used_recently?(path, days)
+  if File.directory?(path)
+    used_recently = false
+    empty = true
+    Dir.new(path).each do |entry|
+      if entry != "." && entry != ".."
+        empty = false
+        if used_recently?("#{path}/#{entry}", days)
+          used_recently = true
+        end
+      end
+    end
+    if !used_recently && !empty
+      puts "unused: #{path}"
+    end
+    return used_recently
+  elsif File.file?(path) || File.socket?(path) || File.symlink?(path)
+    return (File.lstat(path).atime >= Time.now() - (days * 24 * 3600))
+  else
+    puts "Unknown file type: #{path}"
+    exit 1
+  end
+end
+
+# Parse options
+OptionParser.new do |opts|
+  opts.banner = "Usage: #{$0} [options] DIRECTORY..."
+  
+  opts.separator ""
+  opts.separator "Find unused (sub-)directories, recursively traversing DIRECTORY, by looking at the atime(s) of all contained files. A directory is considered unused if ALL of the contained files weren't accessed for DAYS days (default is 180 days.)"
+  opts.separator ""
+  
+  opts.on("-d", "--days DAYS", Integer,
+          "Days after a file is considered unused") do |d|
+    options[:days] = d
+  end
+end.parse!
+
+dirs = ARGV
+if dirs.length == 0
+  dirs = "."
+end
+
+dirs.each do |dir|
+  used_recently?(dir, options[:days])
+end

flickr-download-set

@@ -0,0 +1,8 @@
+#!/bin/sh
+seturl=$1
+lynx -dump $seturl | perl -ne 'print "http://flickr.com/photo_zoom.gne?id=$1&size=l\n" if m#([0-9]+)/in/set-#' \
+| while read url; do 
+  lynx -source "$url" | grep "static.*flickr.com" \
+  | perl -ne 'print "$1\n" if m#a href="(.*?\.jpg)"#' \
+  | xargs wget -c; 
+done

flickr-download-tag

@@ -0,0 +1,8 @@
+#!/bin/sh
+tagurl=$1
+lynx -dump $tagurl | perl -ne 'print "http://flickr.com/photo_zoom.gne?id=$1&size=l\n" if m#flickr.com/photos/.*/([0-9]+)/#' \
+| while read url; do 
+  lynx -source "$url" | grep "static.*flickr.com" \
+  | perl -ne 'print "$1\n" if m#a href="(.*?\.jpg)"#' \
+  | xargs wget -c; 
+done

iptables-geoblock

@@ -0,0 +1,30 @@
+#!/bin/sh
+# Block SSH connections from CN etc.
+#
+# This downloads a list of IP addresses from some website via unencrypted HTTP and then
+# blocks this list of IP addresses without filtering. You should probably not use this
+# script.
+
+set -e
+
+ports="ssh,websm" # comma-separated for iptables -m multiport
+countries="cn hk" # space-separated
+
+for country in $countries; do
+	ipset -q -N geoblock-$country hash:net || true
+
+	tmp_zone=`mktemp`
+	curl -s -o $tmp_zone http://www.ipdeny.com/ipblocks/data/aggregated/$country-aggregated.zone
+
+	for ip in $(cat $tmp_zone); do 
+		ipset -A geoblock-$country "$ip" -exist
+	done
+
+	rm -f $tmp_zone
+
+	rule_spec="-p tcp -m multiport --dports $ports \
+		   -m set --match-set geoblock-$country src -j REJECT"
+	if ! iptables -C INPUT $rule_spec; then
+		iptables -I INPUT $rule_spec
+	fi
+done

pdfjoin-aligned

@@ -0,0 +1,26 @@
+#!/bin/bash
+# join pdfs and insert an empty (one-page) pdf for pdfs with an odd page number
+
+# create an empty (one-page) pdf
+emptypdf="$(mktemp -u /tmp/pdfjoin-aligned-XXXXXX).pdf"
+echo -ne "0 0 moveto\n() show\n" | ps2pdf - "$emptypdf"
+
+# go through pdfs
+declare -a pdfs
+for pdf in "$@"; do
+  pdfs+=("$pdf")
+ 
+  # is it odd or not? 
+  pages=$(pdfinfo "$pdf" | awk '{ if (/^Pages:/) { print $2 } }')
+  odd=$(($pages % 2))
+  if [ "$odd" = "1" ]; then
+    pdfs+=("$emptypdf")
+  fi
+done
+
+# join!
+out="$(mktemp -u /tmp/joined-XXXXXX).pdf"
+pdfjoin --outfile "$out" "${pdfs[@]}"
+
+# cleanup
+rm -f "$emptypdf"

pdfnup-slides

@@ -0,0 +1,34 @@
+#!/bin/bash
+
+tmp=$(mktemp -d /tmp/pdfnup-slides-XXXXX)
+[ -z "$tmp" ] && exit 1
+
+# put 2x3 slides (pdf) on one page
+#pdfnup --nup 2x3 --frame true \
+#  --delta "0.5cm 3cm" --offset "0cm 1cm" \
+#  --scale 0.85 \
+#  "$@" \
+#  --outfile "$tmp/1.pdf"
+
+# put 2x2 slides (pdf) on one page
+pdfnup --nup 2x2 --frame true \
+  --delta "0.5cm 0.5cm" \
+  --scale 0.9 \
+  "$@" \
+  --outfile "$tmp/1.pdf"
+
+# scale up to a4 - now works for beamer slides, too.
+# hackhackhack
+cat > "$tmp/2.tex" <<EOF
+\documentclass[a4paper,landscape]{article}
+\usepackage{pdfpages}
+\begin{document}
+\includepdf[pages=-,nup=1x1,frame=false,trim=0 0 0 0,delta=0 0,offset=0 0,scale=1.0,turn=true,noautoscale=false,column=false,columnstrict=false,openright=false]{$tmp/1.pdf}
+\end{document}
+EOF
+pdflatex -output-directory "$tmp" "$tmp/2.tex" 
+mv -v "$tmp/2.pdf" "$1.2x2.pdf"
+
+# cleanup
+rm -f "$tmp"/*.pdf "$tmp"/*.tex "$tmp"/*.aux "$tmp"/*.log
+rmdir "$tmp"

rss-title-filter

@@ -0,0 +1,72 @@
+#!/usr/bin/env ruby
+#
+# Copyright (c) 2009, neingeist <neingeist@bl0rg.net>
+# Copyright (c) 2005, Joe Mason <joe@notcharles.ca>
+#
+# Permission is hereby granted, free of charge, to any person obtaining a
+# copy of this software and associated documentation files (the
+# "Software"), to deal in the Software without restriction, including
+# without limitation the rights to use, copy, modify, merge, publish,
+# distribute, sublicense, and/or sell copies of the Software, and to permit
+# persons to whom the Software is furnished to do so, subject to the
+# following conditions:
+#
+# The above copyright notice and this permission notice shall be included
+# in all copies or substantial portions of the Software.
+#
+# THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS
+# OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
+# MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN
+# NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM,
+# DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR
+# OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE
+# USE OR OTHER DEALINGS IN THE SOFTWARE.
+#
+# Usage: rss-title-filter <list of titles to include>
+#
+#        Skips all items which do NOT include the given titles.
+#
+#        Example: to include all entries with the title "meme", "quiz" or
+#        "picture post", do:
+#
+#        rss-title-filter meme quiz "picture post"
+#
+#        Requires the Ruby RSS module, which is included in Ruby 1.8.3 or
+#        higher and available for older versions of Ruby at
+#        http://raa.ruby-lang.org/project/rss/.
+#
+#        based on "rss-tag-filter" by Joe Mason.
+
+
+require 'rss/2.0'
+
+# if no titles were given, no parsing needed
+if ARGV.empty? then
+  STDIN.each do |line|
+    STDOUT.puts(line)
+  end
+  exit(0)
+end
+
+# parse the RSS
+rss_source = STDIN.collect.join
+begin
+  rss = RSS::Parser.parse(rss_source)
+rescue RSS::InvalidRSSError
+  rss = RSS::Parser.parse(rss_source, false)    # no validation
+end
+
+# filter out all items NOT in the cmd-line args
+rss.channel.items.reject! do |item|
+  found = false
+  ARGV.each do |arg|  
+    if Regexp.new(arg, Regexp::IGNORECASE).match(item.title)
+      found = true 
+    end
+  end
+  !found
+end
+
+# write the modified rss
+STDOUT.puts(rss)
+

ruthe2rss

@@ -0,0 +1,36 @@
+#!/usr/bin/perl 
+# rss-feed für ruthe.de (liferea feed source "command")
+
+use strict;
+use LWP::Simple;
+use XML::RSS;
+use DateTime;
+use DateTime::Format::W3CDTF;
+
+my $f = DateTime::Format::W3CDTF->new();
+my $rss = XML::RSS->new(version => '1.0');
+$rss->channel(
+  title        => "Ruthe.de",
+  link         => "http://www.ruthe.de",
+  description  => "Cartoons",
+);
+
+$_ = get("http://ruthe.de/frontend/archiv.php");
+while (m#<a href="index.php\?pic=([0-9]+)&sort=datum&order=DESC"><img src="cartoons/tn_strip_([0-9]+).jpg"#sg) {
+  my ($id, $picid) = ($1, $2);
+
+  my $picurl = "http://ruthe.de/frontend/cartoons/strip_$picid.jpg";
+  my $pagurl = "http://ruthe.de/frontend/index.php?pic=$id&sort=datum&order=DESC";
+
+  my (undef, undef, $modified_time, undef, undef) = head($picurl);
+  my $date = $f->format_datetime(DateTime->from_epoch(epoch => $modified_time));
+
+  $rss->add_item(
+    title       => "Comic Nr. $picid",
+    link        => $pagurl,
+    description => "<a href=\"$pagurl\"> <img src=\"$picurl\" /> </a>",
+    dc          => { date => $date }, 
+  );
+}
+
+print $rss->as_string;