Created
October 11, 2015 21:13
-
-
Save jeffreycwitt/272187b3cd8b2fa7665f to your computer and use it in GitHub Desktop.
existdb-xquery word frequency report with Lucene index
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| xquery version "3.0"; | |
| declare namespace tei="http://www.tei-c.org/ns/1.0"; | |
| declare option exist:serialize "method=html media-type=text/html ident=no"; | |
| let $collection := "scta/lombardsententia" | |
| let $terms := | |
| <terms> | |
| { | |
| util:index-keys( | |
| collection(concat("/db/apps/", $collection))//tei:p, | |
| "", | |
| function($key, $count) { | |
| <term name="{$key}" count="{$count[1]}" | |
| docs="{$count[2]}"/> | |
| }, -1, "lucene-index") | |
| } | |
| </terms> | |
| let $sum := sum($terms//@count) | |
| return | |
| <html> | |
| <head> | |
| </head> | |
| <body> | |
| <h1>Frequency analysis for {$collection}</h1> | |
| <h2>Total word count: {$sum}</h2> | |
| <table> | |
| <tr> | |
| <td>Term</td> | |
| <td>Frequency</td> | |
| <td>Percentage</td> | |
| </tr> | |
| { | |
| for $term in $terms//term | |
| let $frequency := $term/@count/string() | |
| let $percentage := format-number(($term/@count div $sum), "%.00") | |
| return | |
| <tr> | |
| <td>{$term/@name/string()}</td> | |
| <td>{$frequency}</td> | |
| <td>%{$percentage}</td> | |
| </tr> | |
| } | |
| </table> | |
| </body> | |
| </html> |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment