Shell Programming and Scripting

gawk 'BEGIN{ORS=RS="\n</string-array>\n"}!a[$0]++' infile

<string-array name="stringArray1">
<item>Element1|Element2<item>
<item>@android:color/black<item>
</string-array>
<style name="style1" parent="@android:style/mainStyle"></style>
<style name="style1" parent="@android:style/mainStyle">
<item name="android:textColor">@drawable/black</item>
<item name="android:typeface">sans</item>
<item name="android:textStyle">bold</item>
</style>
<string-array name="stringArray1">
<item>Element1|Element2<item>
<item>@android:color/black<item>
</string-array>
<string-array name="stringArray2"></string-array>

nawk -F'"' '$1 ~ "=$" && NF>1 {f=($(NF-1) in a)?0:1;if(f)a[$(NF-1)]} f' myFile

<string-array name="stringArray1">
<item>Element1|Element2<item>
<item>@android:color/black<item>
</string-array>
<style name="style1" parent="@android:style/mainStyle"></style>
<item name="android:textColor">@drawable/black</item>
<item name="android:typeface">sans</item>
<item name="android:textStyle">bold</item>
</style>
<string-array name="stringArray2"></string-array>

dupArrayDelete() {
	echo "removing duplicate"
	arrayName=$1
	echo $arrayName
	#get arrays and their contents on their own line
	#first awk prints the file ignoring new lines, putting the whole file in one line
	#sed inserts newlines after each closing </style> or </string-array>, etc
	#second awk removes all lines that have the same column 2
	awk '{printf$0}' $2 | sed 's#</'$arrayName'>#&\n#g' | awk '!A[$2]++' >> $3
}