Update README.md

README.md

@@ -12,20 +12,20 @@ See [https://wiki.openstreetmap.org/wiki/Salem_Oregon_Address_Import](https://wi
 
 ## Field Mapping
 
-- ADD_NUM -> addr:housenumber
-- FULL_ST_NA -> addr:street via getformattedstreetname(FULL_ST_NA)
-- SUB_VAL -> addr:unit
-- CITY -> addr:city via title(CITY)
-- ZIP -> addr:postcode
-
-- manually add addr:state "OR"
+- ADD_NUM -> addr:housenumber (int)
+- formatstreet(FULL_ST_NAME) -> addr:street (text)
+- SUB_VAL -> addr:unit (text)
+- title(CITY) -> addr:city (text)
+- ZIP -> addr:postcode (text)
+- addr:state 'OR' (manually added)
 
 ## Processing
 
-- Use the below script in QGIS to do virtual field calculations.
-- Export the layer to geojson with WGS84 projection.
+- Get `Primary_Addresses.geojson` from the City GIS server linked above.
+- Open the file in QGIS and open the layer attribute table
+- Use the field calculator and the below script to add new virtual fields per the mapping above.
+- Export the layer to geojson with "EPSG:4326 - WGS 84" projection. Deselect all fields besides those above.
 - Save as `processed.geojson`
-- Use VIM or similar to find-replace "ADD_NUM" to "addr:housenumber" etc.
 
 ## Import steps
 
@@ -52,45 +52,40 @@ source:url=https://data.cityofsalem.net/datasets/salem::primary-address/explore
 ## QGIS Processing script
 
 ```
-from qgis.core import *
-from qgis.gui import *
+import qgis.core
+import qgis.gui
 import re
 
-@qgsfunction(args='auto', group='Custom', referenced_columns=[])
-def getformattedstreetname(value1, feature, parent):
-    parts = value1.split()
-    parts = map(formatstreetname, parts)
-    return " ".join(parts)
+#
+# This will keep street names like SR 574A as SR 574A however
+# will lowercase other number-digit suffixes with <2 or >4 numbers
+# or >1 suffix-letters, like 12th Street or 243rd Ave.
+#
 
 @qgsfunction(args='auto', group='Custom', referenced_columns=[])
-def getformattedstreetnamefromaddress(value1, feature, parent):
+def getstreetfromaddress(value1, feature, parent):
     parts = value1.split()
     parts.pop(0) # Ignore the first bit (i.e. "123" in "123 N MAIN ST")
     parts = map(formatstreetname, parts)
     return " ".join(parts)
 
+@qgsfunction(args='auto', group='Custom', referenced_columns=[])
+def formatstreet(value1, feature, parent):
+    parts = value1.split()
+    parts = map(formatstreetname, parts)
+    return " ".join(parts)
+
+# Internal function
 def formatstreetname(name):
-    # Specific suffixes like "123th" we have lower
-    if re.search("[0-9]+TH", name):
-        return name.capitalize()
-    if re.search("[0-9]+ND", name):
-        return name.capitalize()
-    if re.search("[0-9]+ST", name):
-        return name.capitalize()
-    if re.search("[0-9]+RD", name):
-        return name.capitalize()
-    # Weird names like 123D we keep upper
-    if re.search("[0-9]+[A-Z]+", name):
-        return name
-    # Prefixes we want to keep uppercase
+    # Acryonyms
+    if name == "CR":
+        return "County Road"
+    if name == "SR":
+        return "SR" # State Route
+    if name == "NFS":
+        return "NFS" # National Forest Service?
     if name == "US":
         return "US"
-    if name == "SR":
-        return "SR"
-    if name == "CR":
-        return "CR"
-    if name == "C":
-        return "C"
     # Directions
     if name == "N":
         return "North"
@@ -109,8 +104,6 @@ def formatstreetname(name):
     if name == "NW":
         return "Northwest"
     # Suffixes
-    if name == "AV":
-        return "Avenue"
     if name == "AVE":
         return "Avenue"
     if name == "BLVD":
@@ -119,6 +112,8 @@ def formatstreetname(name):
         return "Bend"
     if name == "CIR":
         return "Circle"
+    if name == "CR":
+        return "Circle"
     if name == "CT":
         return "Court"
     if name == "DR":
@@ -127,18 +122,18 @@ def formatstreetname(name):
         return "Fields"
     if name == "GRV":
         return "Grove"
+    if name == "HL":
+        return "Hill"
     if name == "HOLW":
         return "Hollow"
-    if name == "HW":
-        return "Highway"
     if name == "HWY":
         return "Highway"
     if name == "LN":
         return "Lane"
-    if name == "LP":
-        return "Loop"
     if name == "LOOP":
         return "Loop"
+    if name == "LP":
+        return "Loop"
     if name == "PATH":
         return "Path"
     if name == "PL":
@@ -147,24 +142,24 @@ def formatstreetname(name):
         return "Road"
     if name == "RUN":
         return "Run"
+    if name == "SQ":
+        return "Square"
     if name == "ST":
         return "Street"
     if name == "TER":
         return "Terrace"
-    if name == "TL":
-        return "Trail"
     if name == "TRL":
         return "Trail"
     if name == "VW":
         return "View"
     if name == "WAY":
         return "Way"
+    if name == "WY":
+        return "Way"
     if name == "XING":
         return "Crossing"
-    # Irish names
-    if name == "MCCRAY":
-        return "McCray"
-    if name == "MCKOWN":
-        return "McKown"
+    if re.match('^[0-9]{2,4}[A-Za-z]$', name) != None:
+        return name
+
     return name.capitalize()
 ```