README.md

Using the JSON output of a Solr field analysis, to visualize the Lucene indexing/analysis pipeline.

analysis.json

{
    "responseHeader": {
        "status": 0,
        "QTime": 4
    },
    "analysis": {
        "field_types": {
            "text_en_splitting": {
                "index": [
                    "org.apache.lucene.analysis.core.WhitespaceTokenizer",
                    [
                        {
                            "text": "WiFi",
                            "raw_bytes": "[57 69 46 69]",
                            "start": 0,
                            "end": 4,
                            "position": 1,
                            "positionHistory": [
                                1
                            ],
                            "type": "word"
                        }
                    ],
                    "org.apache.lucene.analysis.core.StopFilter",
                    [
                        {
                            "text": "WiFi",
                            "raw_bytes": "[57 69 46 69]",
                            "position": 1,
                            "positionHistory": [
                                1,
                                1
                            ],
                            "start": 0,
                            "end": 4,
                            "type": "word"
                        }
                    ],
                    "org.apache.lucene.analysis.miscellaneous.WordDelimiterFilter",
                    [
                        {
                            "text": "Wi",
                            "raw_bytes": "[57 69]",
                            "start": 0,
                            "end": 2,
                            "type": "word",
                            "position": 1,
                            "positionHistory": [
                                1,
                                1,
                                1
                            ]
                        },
                        {
                            "text": "Fi",
                            "raw_bytes": "[46 69]",
                            "start": 2,
                            "end": 4,
                            "type": "word",
                            "position": 2,
                            "positionHistory": [
                                1,
                                1,
                                2
                            ]
                        },
                        {
                            "text": "WiFi",
                            "raw_bytes": "[57 69 46 69]",
                            "start": 0,
                            "end": 4,
                            "type": "word",
                            "position": 2,
                            "positionHistory": [
                                1,
                                1,
                                2
                            ]
                        }
                    ],
                    "org.apache.lucene.analysis.core.LowerCaseFilter",
                    [
                        {
                            "text": "wi",
                            "raw_bytes": "[77 69]",
                            "position": 1,
                            "positionHistory": [
                                1,
                                1,
                                1,
                                1
                            ],
                            "start": 0,
                            "end": 2,
                            "type": "word"
                        },
                        {
                            "text": "fi",
                            "raw_bytes": "[66 69]",
                            "position": 2,
                            "positionHistory": [
                                1,
                                1,
                                2,
                                2
                            ],
                            "start": 2,
                            "end": 4,
                            "type": "word"
                        },
                        {
                            "text": "wifi",
                            "raw_bytes": "[77 69 66 69]",
                            "position": 2,
                            "positionHistory": [
                                1,
                                1,
                                2,
                                2
                            ],
                            "start": 0,
                            "end": 4,
                            "type": "word"
                        }
                    ],
                    "org.apache.lucene.analysis.miscellaneous.KeywordMarkerFilter",
                    [
                        {
                            "text": "wi",
                            "raw_bytes": "[77 69]",
                            "org.apache.lucene.analysis.tokenattributes.KeywordAttribute#keyword": false,
                            "position": 1,
                            "positionHistory": [
                                1,
                                1,
                                1,
                                1,
                                1
                            ],
                            "start": 0,
                            "end": 2,
                            "type": "word"
                        },
                        {
                            "text": "fi",
                            "raw_bytes": "[66 69]",
                            "org.apache.lucene.analysis.tokenattributes.KeywordAttribute#keyword": false,
                            "position": 2,
                            "positionHistory": [
                                1,
                                1,
                                2,
                                2,
                                2
                            ],
                            "start": 2,
                            "end": 4,
                            "type": "word"
                        },
                        {
                            "text": "wifi",
                            "raw_bytes": "[77 69 66 69]",
                            "org.apache.lucene.analysis.tokenattributes.KeywordAttribute#keyword": false,
                            "position": 2,
                            "positionHistory": [
                                1,
                                1,
                                2,
                                2,
                                2
                            ],
                            "start": 0,
                            "end": 4,
                            "type": "word"
                        }
                    ],
                    "org.apache.lucene.analysis.en.PorterStemFilter",
                    [
                        {
                            "text": "wi",
                            "raw_bytes": "[77 69]",
                            "org.apache.lucene.analysis.tokenattributes.KeywordAttribute#keyword": false,
                            "position": 1,
                            "positionHistory": [
                                1,
                                1,
                                1,
                                1,
                                1,
                                1
                            ],
                            "start": 0,
                            "end": 2,
                            "type": "word"
                        },
                        {
                            "text": "fi",
                            "raw_bytes": "[66 69]",
                            "org.apache.lucene.analysis.tokenattributes.KeywordAttribute#keyword": false,
                            "position": 2,
                            "positionHistory": [
                                1,
                                1,
                                2,
                                2,
                                2,
                                2
                            ],
                            "start": 2,
                            "end": 4,
                            "type": "word"
                        },
                        {
                            "text": "wifi",
                            "raw_bytes": "[77 69 66 69]",
                            "org.apache.lucene.analysis.tokenattributes.KeywordAttribute#keyword": false,
                            "position": 2,
                            "positionHistory": [
                                1,
                                1,
                                2,
                                2,
                                2,
                                2
                            ],
                            "start": 0,
                            "end": 4,
                            "type": "word"
                        }
                    ]
                ]
            }
        },
        "field_names": {}
    }
}

index.html

<!DOCTYPE html>
<html>
  <head>
  <meta http-equiv="content-type" content="text/html; charset=UTF-8">
  <title></title>
  <script src="http://d3js.org/d3.v3.min.js" charset="utf-8"></script>
  <style type="text/css">
    a.link{color: grey;}
    a.link:hover{color: black;}
    div.gallery{width:800px; height:500px; overflow:scroll}
  </style>
  </head>
  <body>
    <script id="template" type="text/template">
      <a class="link" href="{url}">{title}</a>
    </script>
    
    <div class="analysis"></div>
    
    <script type="text/javascript">
    
var tmpl = d3.select("#template").text();
    
d3.json("analysis.json", function(json){
  d3.select(".analysis")
    .selectAll("div.entry")
    .data(json.analysis.field_types.text_en_splitting.index)
    .enter().append("div")
    .attr("class", "entry")
    .html(function(d, i){
      return d;
    });
});
    
    </script>
  </body>
</html>