From 75f5e0c62da711669d59f572c217b66a3f791b23 Mon Sep 17 00:00:00 2001
From: Gabor Kelemen <kelemeng@gnome.hu>
Date: Wed, 12 Oct 2016 14:39:16 +0200
Subject: Script to check the validity of embed tags

This script looks up <embed ...> tags in helpcontent, checks whether the
referenced file and id exist, and prints a warning if either one does not.
Execute from the root directory of the helpcontent2 repository.
No parameters are used.

Change-Id: Ic20bcfb1db398067231141b9af69c45590e1d452
Reviewed-on: https://gerrit.libreoffice.org/29732
Reviewed-by: Andras Timar <andras.timar@collabora.com>
Tested-by: Andras Timar <andras.timar@collabora.com>
---
 helpers/find-invalid-help-embeds.sh | 56 +++++++++++++++++++++++++++++++++++++
 1 file changed, 56 insertions(+)
 create mode 100755 helpers/find-invalid-help-embeds.sh

(limited to 'helpers')

diff --git a/helpers/find-invalid-help-embeds.sh b/helpers/find-invalid-help-embeds.sh
new file mode 100755
index 0000000000..5c70fd5124
--- /dev/null
+++ b/helpers/find-invalid-help-embeds.sh
@@ -0,0 +1,56 @@
+#!/bin/bash
+# This file is part of the LibreOffice project.
+#
+# This Source Code Form is subject to the terms of the Mozilla Public
+# License, v. 2.0. If a copy of the MPL was not distributed with this
+# file, You can obtain one at http://mozilla.org/MPL/2.0/.
+
+# This script looks up <embed ...> tags in helpcontent, checks whether the
+# referenced file and id exist, and prints a warning if either one does not.
+# Execute from the root directory of the helpcontent2 repository.
+# No parameters are used.
+
+# Example output of this git grep:
+# source/text/sbasic/shared/03010000.xhp:  <embed href="text/sbasic/shared/03010300.xhp#farbe"/>
+lines=$(git grep "embed href=" source/);
+
+while read nextline ; do
+    # source file is before the first :
+    sourcefile=${nextline%%:*};
+    # There may be more than one <embed ...> in one line, split it up,
+    # but first cut off everything before the first <embed
+    # and anything after the last >
+    processline="<embed${nextline#*<embed}";
+    processline="${processline%>*}>";
+    while [ -n "$processline" ] ; do
+        # Start processing the first xml tag
+        target=$(expr "$processline" : '\(<[^>]*>\)');
+        # Check if there is an <embed at the beginning
+        if [ $(expr "$target" : "<embed") -ne "0" ] ; then
+            # Get the embedded filename#section part
+            target=${target#*\"};
+            target=${target%\"*};
+            # target file is before the #
+            targetfile=${target%#*};
+            # target section is after the #
+            targetsection=${target#*#};
+            # does the target file exist?
+            if [ -f "source/$targetfile" ] ; then
+                # The target file exist, does the section inside the target file too?
+                grep -q "id=\"$targetsection\">" source/"$targetfile";
+                if [ "$?" -ne "0" ] ; then
+                    echo "$sourcefile: In 'source/$targetfile' there is no section called '$targetsection'";
+                fi
+            else
+                # target file does not exist
+                echo "$sourcefile: Embedded target file 'source/$targetfile' does not exist!" ;
+            fi
+        fi
+        # Remove the first xml tag from the parts still to be processed
+        processline=${processline#<*>};
+        # There may be characters after this, i.e. "foo <embed ...>"
+        if [ -n "$processline" ] ; then
+            processline="<${processline#*<}";
+        fi
+    done
+done <<< "$lines"
-- 
cgit