extra-dependencies/debian/htdig/htdig-3.2.0b6/test/t_validwords

#!/bin/sh
# Part of the ht://Dig package   <http://www.htdig.org/>
# Copyright (c) 1999-2004 The ht://Dig Group
# For copyright details, see the file COPYING in your distribution
# or the GNU Library General Public License (LGPL) version 2 or later
# <http://www.gnu.org/copyleft/lgpl.html>
#
# $Id: t_validwords,v 1.2 2004/05/28 13:15:30 lha Exp $
#

try() {
    comment="$1"
    shift
    query="$1"
    shift
    $htsearch -c $config "$query" > $tmp 2> /dev/null
    for pattern
    do
	if grep "$pattern" $tmp > /dev/null 
	then :
	else
	    $htsearch -vv -c $config "$query" > /dev/null
	    echo "Output doesn't match \"$pattern\""
	    fail "$htsearch -c $config '$query' >> $tmp --
		  $comment"
	fi
    done
}




test_functions_action=--start-apache
. ./test_functions

config=$testdir/conf/htdig.conf.tmp
tmp=/tmp/t_htsearch$$

# set up config file with chosen non-default values
cp $testdir/conf/htdig.conf $config

set_attr allow_numbers		"false"
set_attr minimum_word_length	"3"
set_attr maximum_word_length	"10"
set_attr translate_latin1	"0"
set_attr valid_punctuation	"."
set_attr extra_word_characters	"<22><>"
#set_attr locale fr

$htdig "$@" -t -i -c $config	|| fail "Couldn't dig"

set_attr remove_bad_urls		"false"
set_attr remove_unretrieved_urls	"true"
$htpurge -vv -c $config > tmp1		|| fail "Couldn't purge"

# How can I check that unretrieved urls have been removed, but bad ones haven't?



try "Search for '2001' without allow_numbers" \
    "words=2001" \
    'No matches'

try "Search for '0b3' without allow_numbers" \
    "words=0b3" \
    '1 matches' 'bad_local.htm' '3.2.<strong>0b3</strong>'

try "Search for '3.2.0b3' without allow_numbers" \
    "words=3.2.0b3" \
    '1 matches' 'bad_local.htm' '<strong>3.2.0b3</strong>'

try "Search for '320b3' without allow_numbers" \
    "words=320b3" \
    '1 matches' 'bad_local.htm'

try 'Search for "archive." without . in extra_word_characters' \
    'words=archive.' \
    '1 matches' 'bad_local.htm' '<strong>archive</strong>.'

try 'Search for "archive" without . in extra_word_characters' \
    'words=archive' \
    '1 matches' 'bad_local.htm' '<strong>archive</strong>.'

try "Search for 'graduateprofessional' which should not match a slash" \
    "words=graduateprofessional" \
    'No matches'

try "Search for 'now' with minimum_word_length=3" \
    "words=now" \
    '1 matches' 'bad_local.htm'

try "Search for 'fran<61>ais' without translate_latin1" \
    "words=fran<61>ais" \
    '1 matches' 'site4.html' '<strong>fran<61>ais</strong>'

try "Search for 'qu<71>bec' without translate_latin1" \
    "words=qu<71>bec" \
    'No matches'

try "Search for 'with' with default bad_word_list" \
    "words=with" \
    'No matches'

try "Search for 'technical' with default bad_word_list" \
    "words=technical" \
    '1 matches' 'site%201.html'





set_attr allow_numbers		"true"
set_attr minimum_word_length	"4"
set_attr maximum_word_length	"13"
set_attr translate_latin1	"yes"
set_attr valid_punctuation	"/"
set_attr extra_word_characters	'.\\\$<24><>'	# string is .\$<24><>, chars: .$<24><>
set_attr bad_word_list		"${testdir}/bad_word_list"
#set_attr locale fr

$htdig "$@" -t -i -c $config	|| fail "Couldn't dig"

set_attr remove_bad_urls		"true"
set_attr remove_unretrieved_urls	"false"
$htpurge -vv -c $config > tmp		|| fail "Couldn't purge"

# How can I check that bad urls have been removed, but unretrieved ones haven't?



try "Search for '2001' " \
    "words=2001" \
    '1 matches' '1995-<strong>2001</strong>'

try "Search for '9.00'" \
    "words=9.00" \
    '1 matches' 'site4.html' '<strong>9.00</strong>'

try "Search for '9/00' -- checking . is not just valid_punctuation" \
    "words=9/00" \
    'No matches'

try 'Search for "archive." with . in extra_word_characters' \
    'words=archive.' \
    '1 matches' 'bad_local.htm' '<strong>archive.</strong>'

try 'Search for "archive" with . in extra_word_characters' \
    'words=archive' \
    'No matches'

try 'Search for "$195"' \
    'words=$195' \
    '1 matches' 'site4.html' '<strong>$195</strong>,000'

try "Search for 'graduateprofessional' which should match a slash" \
    "words=graduateprofessional" \
    '1 matches' 'site4.html' '<strong>graduate/professional</strong>'

#try "Search for 'graduateprofexyz' which should match a truncated word" \
#    "words=graduateprofexyz" \
#    '1 matches' 'site4.html' '<strong>graduate/professional</strong>'

try "Search for 'graduateprofexyz' which should match a truncated word" \
    "words=graduateprofexyz" \
    '1 matches' 'site4.html'

try "Search for 'graduateprofxyz' which should fail to match a truncated word" \
    "words=graduateprofxyz" \
    'No matches'

try "Search for 'part' with minimum_word_length=4" \
    "words=part" \
    '2 matches' 'bad_local.htm' 'script.html'

try "Search for 'now' with minimum_word_length=4" \
    "words=now" \
    'No matches'

try "Search for 'fran<61>ais' with translate_latin1" \
    "words=fran<61>ais" \
    '1 matches' 'site4.html' '<strong>fran&ccedil;ais</strong>'

try "Search for 'qu<71>bec' with translate_latin1" \
    "words=qu<71>bec" \
    '1 matches' 'site4.html' '<strong>Qu&eacute;bec</strong>'

try "Search for 'with' with new bad_word_list" \
    "words=with" \
    '4 matches' 'bad_local.htm' 'script.html' 'site4.html' 'site%201.html'

try "Search for 'technical' with new bad_word_list" \
    "words=technical" \
    'No matches'

test_functions_action=--stop-apache
. ./test_functions