From eb57ce6fdec3a959288b2a30c499dcea7e81a444 Mon Sep 17 00:00:00 2001 From: Andrew Harvey Date: Tue, 18 May 2021 16:07:17 +1000 Subject: improve performance by indexing by street --- bin/reduceDuplicates.js | 7 ++++--- 1 file changed, 4 insertions(+), 3 deletions(-) (limited to 'bin/reduceDuplicates.js') diff --git a/bin/reduceDuplicates.js b/bin/reduceDuplicates.js index e2ba562..985a0e1 100755 --- a/bin/reduceDuplicates.js +++ b/bin/reduceDuplicates.js @@ -185,7 +185,7 @@ if (argv.debug) { } // first pass to index by geometry -console.log('First pass to index by address properties') +console.log('Pass 1/2: index by address properties') pipeline( fs.createReadStream(inputFile), ndjson.parse(), @@ -195,8 +195,9 @@ pipeline( console.log(err) process.exit(1) } else { - console.log(` of ${sourceCount} features found ${Object.keys(features).length} unique addresses`) - // second pass to reduce overlapping features + console.log(` of ${sourceCount.toLocaleString()} features found ${Object.keys(features).length.toLocaleString()} unique addresses`) + // second pass to reduce duplicate features + console.log('Pass 2/2: reduce duplicate features') pipeline( Readable.from(Object.keys(features)), reduce, -- cgit v1.2.3