#!/bin/sh
# Copyright (C) 2006 Michael Daum <micha@nats.informatik.uni-hamburg.de>
#  
# This file is free software; you can redistribute it and/or
# modify it under the terms of the GNU General Public License
# as published by the Free Software Foundation; either version 2
# of the License, or (at your option) any later version. 
# 
# This program is distributed in the hope that it will be useful, but
# WITHOUT ANY WARRANTY, to the extent permitted by law; without even the
# implied warranty of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.

ME=`whoami`

# read the config file
GETFEEDS_PRG=`realpath $0`
GETFEEDS_DIR=`dirname $GETFEEDS_PRG`
CONFIG_FILE="$GETFEEDS_DIR/getfeeds.conf"
test -f $CONFIG_FILE && source $CONFIG_FILE

# default values
test -z "$VIEW_URL" && VIEW_URL="http://localhost/~$ME/cgi-bin/twiki/view"
test -z "$FEEDS_DIR" && FEEDS_DIR="$HOME/public_html/feeds"
test -z "$TWIKI_DIR" && TWIKI_DIR="$HOME/twiki"
test -z "$LOG_FILE" && LOG_FILE="$TWIKI_DIR/data/getfeeds.log"
test -z "$EXCLUDE_WEBS_PATTERN" && EXCLUDE_WEBS_PATTERN='\.txt|\.log|^_|Trash|Attic|TestCases|mime.types|RegistrationApprovals'
test -z "$EXCLUDE_TOPICS_PATTERN" && EXCLUDE_TOPICS_PATTERN="Base.txt"
test -z "$WEBS" && WEBS="`ls $TWIKI_DIR/data | egrep -v $EXCLUDE_WEBS_PATTERN`"
test -z "$SLEEP" && SLEEP=1


# do it
(
  date +"*** starting $GETFEEDS_PRG %Y-%m-%d : %k:%M:%S"
  for WEB in $WEBS; do
    FEEDS="`ls $TWIKI_DIR/data/$WEB/WebRss*txt $TWIKI_DIR/data/$WEB/WebAtom*txt|egrep -v $EXCLUDE_TOPICS_PATTERN|sed 's/^.*\/\(.*\)\.txt$/\1/g'`"
    for TOPIC in $FEEDS; do
      OUT_FILE="$FEEDS_DIR/$WEB$TOPIC.xml"
      TMP_FILE="/tmp/$WEB$TOPIC.xml"
      echo "*** fetching $WEB.$TOPIC into $OUT_FILE"
      wget -q -O $TMP_FILE $VIEW_URL/$WEB/$TOPIC?t=`date +"%s"` && mv $TMP_FILE $OUT_FILE && chmod go+r $OUT_FILE
      sleep $SLEEP
    done
  done
  echo "*** done $GETFEEDS_PRG"
) >> $LOG_FILE 2>&1