[mythtv] My small (and very bash) contibution to mythtv...

[Martin Moeller]

I haven't  gotten much extra work done on it and it may not be necessary
for American feeds and certain others, but it certainly help on
tv_grab_sn to give some form of categorizing.

Please note that there are plenty of things that could be better but
it's good enough that I can usually guess what's what.

mythfilldatabasecron is somewhat modified. It works better this way for
me, except every other day except from tomorrow gets lost?!
mythfilldatabase never fetches them. I've tried to find the location of
this problem, but I haven't been able to as yet...

-- 
Martin Moeller <martin at martinm-76.dk>
-------------- next part --------------
#!/bin/sh
# (C)2003 Martin Moeller - Licensed under the GNU GPL.
# See www.gnu.org/copyleft/gpl.html for the details.
#
# Purpose: To add categorization to feeds without them
# using comments and titles.
#
# I'm sure it can be done better, but it works pretty well..
#
# Possible improvements:
# * Priority inserts (e.g. typical film categories last (drama, sci-fi, etc..)
# * More keywords, possibly in more languages. Kind of coved now is:
#   Danish, Swedish, partly Norwegian and English.
# * Speedups? It isn't too bad, but it might be better.
# * Improved accuracy. We don't test for being part of a word so, e.g.
#   Some of the Search terms could probably do with some narrowing, as well.
#   E.g. : Talk ends up marking things talk-shows that aren't. No biggie, though.
#   A documentary about homosexuals would end up classified as Erotica.
#

export TERM=xterm

cat /tmp/program.sql | sed s#"\\\'"#"½§"#g | cut -d\' -f6 > /tmp/description.txt
cat /tmp/program.sql | sed s#"\\\'"#"½§"#g | cut -d\' -f2 > /tmp/title.txt

if [ -e /tmp/categories ] ; then
 rm -rf /tmp/categories
fi

mkdir /tmp/categories

# Find matching lines
function get_type() {
  echo -n "."
  cat /tmp/description.txt | grep -ni $1 > /tmp/categories/$1.match02
  cat /tmp/title.txt | grep -ni $1 > /tmp/categories/$1.match01
}

# Reinsert found categories into database.
# Process title before description : Description can override title.
# Two arguments: Type and Category (e.g. insert_desc krimi Crime)
function insert_desc() {
  for a in /tmp/categories/$1.match* ; do
    if [ -s $a ] ; then
      for a in $(cat $a | cut -d: -f1) ; do
        LINE=$(head -$a /tmp/program.sql | tail -1 | sed s#"\\\'"#"½§"#g)
        NEWLINE1=$(echo $LINE | cut -d\' -f1-8)
        NEWLINE2=$(echo $LINE | cut -d\' -f9-)
        NEWLINE="${NEWLINE1}${2}'${NEWLINE2}"
        echo $NEWLINE | sed s#"½§"#"\\\'"#g >> /tmp/categories/$2.sql
      done

      mysql -umythtv -pmythtv mythconverg < /tmp/categories/$2.sql
      rm /tmp/categories/$2.sql
      echo -n "."
    fi
  done
}

echo -n "Searching for categories : "
for a in Drama News Cook Sex Eroti Kultur Culture Special ; do
  get_type $a
done

for a in Episode Serie Avsnit Afsnit ; do # Series
  get_type $a
done

for a in Film Movie Action Adventure Thriller Sci-Fi Science ; do
  get_type $a
done

for a in Tegnefilm Cartoon Tecknad Animerad Animeret CGI ; do
  get_type $a
done

for a in Komedi Comedy Humor Nyhed Nyhet ; do
  get_type $a
done

for a in Sport Badminton Tennis Fodbold Fotboll Football Volley Ridning Riding League ; do
  get_type $a
done

for a in Musik Music ; do
  get_type $a
done

for a in Krimi Crime Document Dokument; do # Crime
  get_type $a
done

for a in Familje Familie Family Underhold ; do # * -> Family
  get_type $a
done

for a in Talk Prat Snakke ; do
  get_type $a
done

for a in Natur Debat Debate Repris Rerun Genudsendelse ; do 
  get_type $a
done

echo " - done."

# Cook -> Cooking
# Sex & Eroti -> Erotica
# Nyheter & Nyheder -> News, Kultur -> Culture
# Komedi -> Comedy

echo -n "Importing categories : "
insert_desc Film Movie
insert_desc Movie Movie

for a in /tmp/categories/*.match* ; do
  NAME=$(basename $a)
  NAME=$(echo $NAME | cut -d\. -f1)
  case $NAME in
    Action|Adventure|Thriller|Sci-Fi|Drama|News ) insert_desc $NAME $NAME ;;
    Nyhet|Nyhed ) insert_desc $NAME News ;;
    Cook ) insert_desc $NAME Cooking ;;
    Tegnefilm|Cartoon|Tecknad|Animerad|Animeret|CGI ) insert_desc $NAME Cartoon ;;
    Komedi|Comedy|Humor ) insert_desc $NAME Comedy ;;
    Musik|Music ) insert_desc $NAME Music ;;
    Krimi|Crime ) insert_desc $NAME Crime ;;
    Dokument|Document ) insert_desc $NAME Documentary ;;
    Debat|Debate ) insert_desc $NAME Debate ;;
    Episode|Serie|Avsnit|Afsnit ) insert_desc $NAME Series ;;
    Sex|Eroti ) insert_desc $NAME Erotica ;;
    Kultur|Culture ) insert_desc $NAME Culture ;;
    Special|Science ) insert_desc $NAME $NAME ;;
    Familje|Familie|Family|Underhold ) insert_desc $NAME Family ;;
    Talk|Prat|Snakke ) insert_desc $NAME Talk-show ;;
    Natur ) insert_desc $NAME Nature ;;
    Repris|Rerun|Genudsendelse ) insert_desc $NAME Rerun ;;
    Sport|Badminton|Tennis|Fodbold|Fotboll|Football|Volley|Ridning|Riding|League ) insert_desc $NAME Sports ;;
  esac
done

echo " - done."

-------------- next part --------------
#!/bin/bash
export TERM=xterm
export QTDIR=/usr/lib/qt3
# Choose one of the two modes below.
# Mode 1: Start from scratch.
#mysql -uroot mythconverg -e 'delete from program;'
# Mode 2: Keep old records (start with today) - Not tested.
START=$(date -d 'yesterday' +%Y%m%d235959)
mysql -uroot mythconverg -e "delete from program where starttime>$START;"

/usr/local/bin/mythfilldatabase
mysql -uroot mythconverg < /home/martin/mythtv/Extras/channel.sql
mysqldump -uroot mythconverg program | sed s#INSERT#REPLACE#g > /tmp/program.sql
/usr/local/sbin/myth_categorize