Add tools used to fix issue 827.

tools/tagtool/README.md

@@ -0,0 +1,36 @@
+# Tagtool
+
+## Example workflow
+
+ 1. xsltproc tagsToCSV.xsl tags/.tags.en.xml | sort > tagsdata.csv
+ 2. edit tagsdata.csv
+ 3. tagtool.sh tagsdata.csv
+
+## Preparing a csv file:
+
+```
+xsltproc tagsToCSV.xsl tags/.tags.en.xml | sort > tagsdata.csv
+```
+
+This processes the tags data and outputs the columns "action;name;id;section;count".
+
+Columns:
+ * action: empty, to be filled by you
+ * name: value of the "content" attribute
+ * id: the tag itself
+ * section: news|events
+ * count
+
+"Section" and "count" are for additional context only.
+The "name" section comes at the beginning so that it is easier to find duplicate tags.
+
+You can then fill the "action" field with the following actions:
+ * mv:sometag
+   rename the tag to sometag
+ * rm
+   remove the tag from all files
+
+A word of warning: you'll probably need to polish the results by hand a little
+(removing empty lines, checking for duplicate tags introduced by renaming).
+
+

tools/tagtool/tagsToCSV.xsl

@@ -0,0 +1,18 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<!-- create a csv file from the aggregated tags files in tags/
+	  
+Usage to find duplicate tags:
+xsltproc tagsToCSV.xsl tags/.tags.en.xml |sort
+/-->
+<xsl:stylesheet version="1.0"
+                xmlns:xsl="http://www.w3.org/1999/XSL/Transform"
+                xmlns:dt="http://xsltsl.org/date-time">
+  <xsl:output method="text"
+              encoding="utf-8"
+              indent="yes"
+              doctype-system="about:legacy-compat" />
+  <xsl:template match="/">action;name;id;section;count
+<xsl:for-each select="tagset/tag">
+;<xsl:value-of select='.'/>;<xsl:value-of select='@name'/>;<xsl:value-of select='@section'/>;<xsl:value-of select='@count'/></xsl:for-each>;
+ </xsl:template>
+</xsl:stylesheet>

tools/tagtool/tagtool.sh

@@ -0,0 +1,107 @@
+#!/bin/bash
+# Tools to transform the tag data by bulk.
+# Copyright (C) 2019 Johannes Zarl-Zierl <johannes@zarl-zierl.at>
+#
+# This program 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 3 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; without even the implied warranty of
+# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+# GNU General Public License for more details.
+#
+# You should have received a copy of the GNU General Public License
+# along with this program.  If not, see <https://www.gnu.org/licenses/>.
+###
+
+TAGSDATAFILE="$1"
+if [[ ! -f "$1" ]]
+then
+	echo "No data file. Please read the source for help..." >&2
+	exit 1
+fi
+
+findTaggedFiles()
+# findTaggedFiles TAG_ID
+# grep for files containing the tag
+{
+	local tagId="$1"
+	git grep -i -l ">$tagId</tag>"
+}
+
+renameTag()
+# renameTag OLD NEW
+# rename the tag using case-insensitive matching in all files.
+{
+	local oldTagId="$1"
+	local newTagId="$2"
+	echo "Renaming tag $oldTagId to $newTagId..." >&2
+	for f in $(findTaggedFiles "$oldTagId")
+	do
+		echo "..$f" >&2
+		if ! sed -E -i "s;>\W*$oldTagId\W*</tag>;>$newTagId</tag>;" "$f"
+		then
+			echo "ERROR!" >&2
+			return 1
+		fi
+	done
+}
+
+removeTag()
+# removeTag TAG
+# remove the tag id in all files
+# this will result in additional empty lines
+{
+	local tagId="$1"
+	echo "Deleting tag $tagId..." >&2
+	for f in $(findTaggedFiles "$oldTagId")
+	do
+		echo "..$f" >&2
+		if ! sed -E -i "s;\W*<tag\W*content=\"[^\"]*\"\W*>\W*$TagId\W*</tag>\W*;;i" "$f"
+		then
+			echo "ERROR!" >&2
+			return 1
+		fi
+	done
+}
+
+process_action()
+# process a single csv action line from stdin and call the appropriate method
+{
+	IFS=";" read action name id section count || return 2
+	# ignore empty actions
+	if [[ -z "$action" ]]
+	then
+		return 0
+	fi
+
+	case "$action" in
+		rm)
+			removeTag "$id"
+			;;
+		mv:*)
+			renameTag "$id" "${action/mv:/}"
+			;;
+		*)
+			echo "Ignoring  action: $action on tag $section/$id" >&2
+			;;
+	esac
+}
+
+process_actions()
+{
+	read firstline
+	if [[ "$firstline" != "action;name;id;section;count" ]]
+	then
+		echo "Input data does not look like it contains the right columns. Bailing out..." >&2
+		exit 1
+	fi
+	while process_action
+	do
+		true
+	done
+}
+
+process_actions < "$TAGSDATAFILE"