# Features covered: HTML parser
#
# This file contains a collection of tests for the HTML parser.
# Tested functionalities:
# html-1.*: Character encoding
# html-2.*: Parsing tests
#
# Copyright (c) 2002 Rolf Ade.
#
# RCS: @(#) $Id: htmlreader.test,v 1.8 2004/05/08 00:57:11 rolf Exp $
source [file join [file dir [info script]] loadtdom.tcl]
test html-1.1 {HTML character entities} {need_i18n} {
set doc [dom parse -html { ¡Äü}]
set root [$doc documentElement]
set body [$root firstChild]
set result [$body text]
$doc delete
set result
} "\u00A0\u00A1\u00c4\u00fc"
test html-1.2 {character entities} {need_i18n} {
set doc [dom parse -html {ÖÄÄ}]
set root [$doc documentElement]
set body [$root firstChild]
set result [$body text]
$doc delete
set result
} "\u00d6\u00c4\u00c4"
test html-1.3 {character entities} {need_i18n} {
set doc [dom parse -html {€∋}]
set root [$doc documentElement]
set result [$root text]
$doc delete
set result
} "\u20ac\u220b"
test html-2.1 {not closed p tags} {
set doc [dom parse -html {
Para 1
Para 2
Para 3
}]
set result [$doc asXML -indent none]
$doc delete
set result
} {
Para 1
Para 2
Para 3
}
test html-2.2 {HTML parsing} {
set doc [dom parse -html {
HTML
}]
set result [$doc asXML -indent none]
$doc delete
set result
} {