Comparator to flag invalid primary tag combinations

comparators/README.md

@@ -78,3 +78,6 @@ Reports when `wikidata` tag is added, deleted or modified for a place type featu
 
 ### osm-landmarks
 Reports when any feature in the [osm-landmarks list](https://github.com/osmlab/osm-landmarks) is edited.
+
+### invalid-tag-combination
+Reports when a feature has two uncommon primary tag combinations. Ex: `0.06 %` of features with `building` also have `historic` tag.

comparators/invalid-tag-combination.js

@@ -0,0 +1,36 @@
+'use strict';
+
+var csv = require('csv');
+var fs = require('fs');
+var path = require('path');
+
+module.exports = invalidTagCombination;
+function invalidTagCombination(newVersion, oldVersion, callback) {
+  // What should be the minimum value of count to be a valid tag combination.
+  var MIN_COUNT = 1;
+
+  var result = {};
+  if (!newVersion) return callback(null, result);
+
+  csv.parse(fs.readFileSync(path.join(__dirname, 'tag-combinations.csv')), function (error, rows) {
+    var tags = Object.keys(newVersion.properties);
+
+    for (var i = 0; i < tags.length; i++) {
+      for (var j = 0; j < tags.length; j++) {
+        if (i === j) continue;
+
+        var tag = tags[i];
+        var anotherTag = tags[j];
+
+        var rowIndex = rows[0].indexOf(tag);
+        var columnIndex = rows[0].indexOf(anotherTag);
+        if (rowIndex === -1 || columnIndex === -1) continue;
+
+        var count = parseFloat(rows[rowIndex][columnIndex]);
+
+        if (isNaN(count) || (count < MIN_COUNT)) return callback(null, {'result:invalid_tag_combination': true});
+      }
+    }
+    return callback(null, result);
+  });
+}

comparators/tag-combinations.csv

@@ -0,0 +1,27 @@
+,aerialway,aeroway,amenity,barrier,boundary,building,craft,emergency,geological,highway,historic,landuse,leisure,man_made,military,natural,office,places,power,public_transport,railway,route,shop,sport,tourism,waterway
+aerialway,,,0.05,0.01,,2.49,,,,0.33,0.02,,0.07,0.09,,0.01,,,0.12,0.74,0.19,0.04,0.02,0.2,0.1,
+aeroway,,,0.03,0.14,0.01,6.69,,0.03,,0.21,0.01,0.27,0.02,0.29,0.24,0.02,,,,,,,,0.06,0.01,
+amenity,,,,0.41,,13.51,0.01,0.29,,0.13,0.16,0.26,0.12,0.28,,0.07,0.08,,,0.07,,,0.47,0.23,0.36,0.01
+barrier,,0.01,0.61,,0.05,0.14,,0.03,,0.06,0.26,2.27,1.49,0.14,0.04,0.1,0.01,,0.39,,0.02,,0.02,0.11,0.07,0.06
+boundary,,,0.01,0.24,,0.01,,,,1.52,0.33,1,2.28,0.04,0.01,1.46,,,0.01,,0.03,0.01,,,0.02,2.67
+building,,0.01,0.66,,,,0.01,,,,0.06,0.04,0.04,0.12,0.01,,0.04,,0.06,,0.01,,0.25,0.02,0.08,
+craft,,,1.85,0.25,,27.75,,,,0.04,0.08,1.7,0.03,1.43,,0.01,0.7,,0.03,,,,9.56,0.01,0.83,0.01
+emergency,,0.01,3.79,0.28,0.01,1.11,,,,5.32,0.07,0.04,0.03,0.15,,0.11,0.01,,,0.01,0.02,0.01,0.01,0.01,0.3,
+geological,,,0.02,0.05,0.69,0.3,,,,0.14,2.1,0.37,0.51,0.2,,60.05,,,,,,0.02,,0.03,4.16,0.12
+highway,,,0.01,,0.02,,,0.04,,,0.01,0.01,0.01,0.03,,,,,0.01,0.63,0.07,0.04,,0.01,0.01,
+historic,,0.01,2.43,2.65,0.73,17.33,0.01,0.09,0.02,0.99,,0.62,0.2,1.81,2.02,0.46,0.03,,0.01,0.01,0.68,0.1,0.05,0.06,4.34,0.13
+landuse,,0.01,0.15,0.89,0.09,0.5,0.01,,,0.05,0.02,,0.41,0.14,0.02,0.54,0.01,,0.04,,,,0.05,0.17,0.03,0.01
+leisure,,,0.35,2.9,0.96,2.15,,0.01,,0.16,0.04,2.01,,0.03,,0.39,,,,,,,0.02,28.4,0.25,0.01
+man_made,,0.05,1.44,0.48,0.03,12.41,0.05,0.06,,1.57,0.61,1.19,0.05,,0.01,0.77,0.02,,0.25,0.01,0.06,0.01,0.15,0.02,0.35,0.43
+military,,1.61,0.63,5,0.18,28.04,,0.02,,0.88,27.28,6.28,0.25,0.54,,0.19,0.44,,0.01,,,,0.01,0.33,1.07,0.03
+natural,,,0.03,0.03,0.09,0.02,,,0.01,0.01,0.01,0.39,0.06,0.06,,,,,0.01,,,,,0.05,0.04,0.07
+office,,,3.13,0.2,0.01,31.85,0.16,0.03,,0.02,0.07,0.62,0.05,0.14,0.08,0.01,,,0.01,0.01,,,1.17,0.04,0.12,
+places,,,,,,,,,,,,,,,,,,,,,,,,,,
+power,,,,0.21,,1,,,,0.1,,0.05,,0.04,,0.01,,,,,,,,,,
+public_transport,0.05,,0.54,0.01,,0.49,,,,51.51,0.01,0.01,,0.02,,,,,,,8.81,0.04,0.01,,0.01,
+railway,,,0.01,0.03,0.01,0.38,,,,2.17,0.13,0.02,,0.04,,,,,,3.33,,0.08,,,0.02,
+route,0.01,,0.08,,0.02,0.02,,0.01,,8.09,0.13,0.08,0.03,0.03,,,,,0.01,0.1,0.55,,,0.07,0.08,0.1
+shop,,,1.94,0.07,,21.33,0.25,,,0.02,0.01,0.37,0.02,0.12,,0.01,0.13,,,0.01,,,,0.05,0.11,
+sport,0.01,0.02,2.18,0.71,,4.11,,,,0.83,0.04,2.75,90.66,0.04,0.01,1.09,0.01,,,,0.01,0.03,0.11,,0.15,0.01
+tourism,0.01,,2.77,0.38,0.02,13.04,0.04,0.17,0.02,0.4,2.17,0.43,0.67,0.52,0.04,0.71,0.02,,0.01,0.01,0.05,0.03,0.2,0.12,,0.11
+waterway,,,0.01,0.03,0.31,0.05,,,,0.03,0.01,0.01,,0.07,,0.14,,,,,,,,,0.01,

index.js

@@ -20,5 +20,6 @@ module.exports = {
   'added_place': require('./comparators/added_place'),
   'modified_place_wikidata': require('./comparators/modified-place-wikidata'),
   'osm_landmarks': require('./comparators/osm-landmarks'),
-  'modifiedMonument': require('./comparators/modifiedMonument')
+  'modifiedMonument': require('./comparators/modifiedMonument'),
+  'invalid_tag_combination': require('./comparators/invalid-tag-combination')
 };

package.json

@@ -16,6 +16,7 @@
   "author": "Mapbox",
   "license": "ISC",
   "dependencies": {
+    "csv": "^1.1.1",
     "d3-queue": "^3.0.3",
     "geopoint": "^1.0.1",
     "levenshtein": "^1.0.5",

tests/fixtures/invalid-tag-combination.json

@@ -0,0 +1,46 @@
+{
+  "compareFunction": "invalid-tag-combination",
+  "fixtures": [
+    {
+      "description": "Test feature with invalid tag combination with count less than 1",
+      "expectedResult": {
+        "result:invalid_tag_combination": true
+      },
+      "newVersion": {
+        "type": "Feature",
+        "properties": {
+          "tourism": "yes",
+          "amenity": "yes"
+        },
+        "geometry": null
+      },
+      "oldVersion": null
+    },
+    {
+      "description": "Test feature with invalid tag combination with count greater than 1",
+      "expectedResult": {},
+      "newVersion": {
+        "type": "Feature",
+        "properties": {
+          "sport": "yes",
+          "leisure": "yes"
+        },
+        "geometry": null
+      },
+      "oldVersion": null
+    },
+    {
+      "description": "Test feature with no primary tags",
+      "expectedResult": {},
+      "newVersion": {
+        "type": "Feature",
+        "properties": {
+          "name": "Hello, world!",
+          "version": "1"
+        },
+        "geometry": null
+      },
+      "oldVersion": null
+    }
+  ]
+}