HTML Strip charfilter test for ElasticSearch

html_strip.sh

# Analyze text: "the <b>quick</b> bröwn <img src="fox"/> &quot;jumped&quot;"

curl -XPUT 'http://127.0.0.1:9200/foo/'  -d '
{
   "index" : {
      "analysis" : {
         "analyzer" : {
            "test_1" : {
               "char_filter" : [
                  "html_strip"
               ],
               "tokenizer" : "standard"
            },
            "test_2" : {
               "filter" : [
                  "standard",
                  "lowercase",
                  "stop",
                  "asciifolding"
               ],
               "char_filter" : [
                  "html_strip"
               ],
               "tokenizer" : "standard"
            }
         }
      }
   }
}
'

curl -XGET 'http://127.0.0.1:9200/foo/_analyze?format=text&text=the+%3Cb%3Equick%3C%2Fb%3E+br%C3%B6wn+%3Cimg+src%3D%22fox%22%2F%3E+%26quot%3Bjumped%26quot%3B&analyzer=standard' 

#    "tokens" : "[b:5->6:<ALPHANUM>]
#    
#    3: 
#    [quick:7->12:<ALPHANUM>]
#    
#    4: 
#    [b:14->15:<ALPHANUM>]
#    
#    5: 
#    [bröwn:17->22:<ALPHANUM>]
#    
#    6: 
#    [img:24->27:<ALPHANUM>]
#    
#    7: 
#    [src:28->31:<ALPHANUM>]
#    
#    8: 
#    [fox:33->36:<ALPHANUM>]
#    
#    9: 
#    [quot:41->45:<ALPHANUM>]
#    
#    10: 
#    [jumped&quot:46->57:<COMPANY>]
#    "
# }

curl -XGET 'http://127.0.0.1:9200/foo/_analyze?format=text&text=the+%3Cb%3Equick%3C%2Fb%3E+br%C3%B6wn+%3Cimg+src%3D%22fox%22%2F%3E+%26quot%3Bjumped%26quot%3B&analyzer=test_1' 

# {
#    "tokens" : "[the:0->3:<ALPHANUM>]
#    
#    2: 
#    [quick:7->12:<ALPHANUM>]
#    
#    3: 
#    [bröwn:17->22:<ALPHANUM>]
#    
#    4: 
#    [jumped:46->52:<ALPHANUM>]
#    "
# }

curl -XGET 'http://127.0.0.1:9200/foo/_analyze?format=text&text=the+%3Cb%3Equick%3C%2Fb%3E+br%C3%B6wn+%3Cimg+src%3D%22fox%22%2F%3E+%26quot%3Bjumped%26quot%3B&analyzer=test_2' 

# {
#    "tokens" : "[quick:7->12:<ALPHANUM>]
#    
#    3: 
#    [brown:17->22:<ALPHANUM>]
#    
#    4: 
#    [jumped:46->52:<ALPHANUM>]
#    "
# }