#!/bin/bash # CDDL HEADER START # # The contents of this file are subject to the terms of the # Common Development and Distribution License (the "License"). # You may not use this file except in compliance with the License. # # See LICENSE.txt included in this distribution for the specific # language governing permissions and limitations under the License. # # When distributing Covered Code, include this CDDL HEADER in each # file and include the License file at LICENSE.txt. # If applicable, add the following below this CDDL HEADER, with the # fields enclosed by brackets "[]" replaced with your own identifying # information: Portions Copyright [yyyy] [name of copyright owner] # # CDDL HEADER END # # Copyright (c) 2016, Oracle and/or its affiliates. All rights reserved. # # # A script that scans through the generated xrefs in an OpenGrok data # directory and checks if they contain valid XHTML 1.0 data. # # The script should be run with one argument, which should be the path # to the OpenGrok data directory (the parent of the xref directory). # If no problems are found, the script will be silent. Otherwise, it # will print which files are ill-formed and what the problems are. # # The script has only been tested on Debian systems with the # libxml2-utils and w3c-sgml-lib packages installed. # if [ $# -ne 1 ] || ! [ -d "$1"/xref ] ; then echo "Usage: `basename $0` opengrok-data-dir" exit 1 fi dtd=/usr/share/xml/w3c-sgml-lib/schema/dtd/REC-xhtml1-20020801/xhtml1-strict.dtd if ! [ -f "$dtd" ]; then echo "Cannot find $dtd." echo "Please install w3c-sgml-lib." exit 1 fi if ! [ -x "`which xmllint`" ]; then echo "Cannot find the xmllint executable." echo "Please install libxml2-utils." exit 1 fi xml_begin() { cat <

EOF
}

xml_end() {
    cat <

EOF } tmp="`mktemp`" shopt -s globstar for i in "$1"/xref/**/*.gz do if ! (xml_begin; zcat "$i"; xml_end) \ | xmllint --noout --valid --dtdvalid "$dtd" - > "$tmp" 2>&1 then echo "*** ILL-FORMED DATA IN $i ***" echo cat "$tmp" echo fi done rm -f "$tmp"