Last active
December 17, 2015 20:09
-
-
Save dantman/5665307 to your computer and use it in GitHub Desktop.
A script to scan over prefix.cc and determine the most popular patterns for rdf namespace IRIs
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
| <?php | |
| $ns = json_decode( file_get_contents( "http://prefix.cc/popular/all.file.json" ) ); | |
| foreach ( $ns as $k => $v ) { | |
| if ( is_null( $v ) ) { | |
| unset( $ns->{$k} ); | |
| } | |
| } | |
| $types = array( '/ns/', '/ns#', '/rdf/', '/rdf#', '/ns/', '/ns#', '/schema/', '/schema#', '/ontologies/', '/ontologies#', '/vocab/', '/vocab#', '/namespaces/', '/namespaces#', '/ontology/', '/ontology#', '/xml/', '/xml#', '/owl/', '/owl#', '/schema/', '/schema#', '/spec/', '/spec#', '/terms/', '/terms#', '/schemas/', '/schemas#' ); | |
| $types = array_combine( $types, array_fill( 0, count( $types ), 0 ) ); | |
| foreach ( $ns as $p => $uri ) { | |
| foreach( $types as $str => &$n ) { | |
| if ( strpos( $uri, $str ) !== false ) { | |
| $n++; | |
| } | |
| } | |
| } | |
| arsort( $types, SORT_NUMERIC ); | |
| echo "Pattern usage:\n"; | |
| foreach ( $types as $str => &$n ) { | |
| echo "$n\t$str\n"; | |
| } | |
| echo "\n"; | |
| $combined = array(); | |
| foreach ( $types as $str => &$n ) { | |
| $short = preg_replace( '![#/]$!', '', $str ); | |
| if ( !array_key_exists( $short, $combined ) ) { | |
| $combined[$short] = 0; | |
| } | |
| $combined[$short] += $n; | |
| } | |
| arsort( $combined, SORT_NUMERIC ); | |
| echo "Combined:\n"; | |
| foreach ( $combined as $str => &$n ) { | |
| echo "$n\t$str\n"; | |
| } |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment