feat(dictionaries): dictionary updates (#21)

Author: missinglink

classifier/WhosOnFirstClassifier.js

@@ -34,7 +34,9 @@ class WhosOnFirstClassifier extends PhraseClassifier {
     this.tokens = {}
     Object.keys(placetypes).forEach(placetype => {
       this.tokens[placetype] = new Set()
-      whosonfirst.load(this.tokens[placetype], [placetype], placetypes[placetype].files)
+      whosonfirst.load(this.tokens[placetype], [placetype], placetypes[placetype].files, {
+        minlength: 2
+      })
 
       // general blacklist
       this.tokens[placetype].delete('north')

resources/pelias/dictionaries/libpostal/de/street_types.txt

@@ -0,0 +1,2 @@
+# abbrviation for 'chaussee' conflicts with Swiss countrycode
+!ch

resources/pelias/dictionaries/libpostal/es/street_types.txt

@@ -0,0 +1,2 @@
+# conflicts with US state abbreviation
+!ca

resources/pelias/dictionaries/whosonfirst/locality/name:eng_x_preferred.txt

@@ -3,6 +3,56 @@
 nyc
 sf
 # remove problematic locality names
-!texas
+!italy
+!college
+!university
+# remove any localities which share a name with a US state
+!alabama
+!alaska
+!arizona
+!arkansas
 !california
-!italy
+!colorado
+!connecticut
+!delaware
+!florida
+!georgia
+!hawaii
+!idaho
+!illinois
+!indiana
+!iowa
+!kansas
+!kentucky
+!louisiana
+!maine
+!maryland
+!massachusetts
+!michigan
+!minnesota
+!mississippi
+!missouri
+!montana
+!nebraska
+!nevada
+!new hampshire
+!new jersey
+!new mexico
+#!new york
+!north carolina
+!north dakota
+!ohio
+!oklahoma
+!oregon
+!pennsylvania rhode island
+!south carolina
+!south dakota
+!tennessee
+!texas
+!utah
+!vermont
+!virginia
+#!washington
+!west virginia
+!wisconsin
+!wyoming