Introduce zip prefix and suffix

model/countries/BR/BR-parsing-rules.yaml

@@ -19,6 +19,14 @@ regex_definitions:
 
   kFloorLiteralRe:  # Regex for literal for a floor
     regex_fragment: andar
+
+  # Regular expression to match 5-digit zip prefix
+  kZipPrefixValueRe:
+    regex_fragment: (?:\d{5})
+
+  # Regular expression to match 3-digit zip suffix
+  kZipSuffixValueRe:
+    regex_fragment: (?:\d{3})
 
 capture_definitions:
   ParseBuildingLocation:
@@ -165,6 +173,10 @@ parsing_definitions:
             output: unit-name
             parts: [ {regex_reference: kUnitNameValueRe} ]
 
+  postal-code:
+    decomposition:
+      capture_reference: ParsePostalCodeOptionalSeparatorExpression
+
 test_regex_definitions:
 # Tests for kBuildingValueRe
 - id: "kBuildingValueRe: plain number"
@@ -324,3 +336,15 @@ test_parsing_definitions:
     unit-name: "12"
     floor: "1"
     landmark: "foo"
+- id: "Zip code with separator"
+  type: postal-code
+  input: "12345-678"
+  output:
+    postal-code-prefix: "12345"
+    postal-code-suffix: "678"
+- id: "Zip code without separator"
+  type: postal-code
+  input: "12345678"
+  output:
+    postal-code-prefix: "12345"
+    postal-code-suffix: "678"

model/countries/CA/CA-formatting-rules.yaml

@@ -11,6 +11,10 @@ formatting-rules:
   - skip: country  # redundant with country-name
   - skip: street-address  # redundant with street-address-alternative-1
 
+  postal-code:
+  - postal-code-prefix
+  - postal-code-suffix
+
 examples:
 - id: name
   comment: |
@@ -33,7 +37,8 @@ examples:
     address-line2: Apt. 306
     locality1: Ottawa
     admin-area1: ON
-    postal-code: M5H 2J9
+    postal-code-prefix: M5H
+    postal-code-suffix: 2J9
     country: CA
     country-name: Canada
 

model/countries/CA/CA-parsing-rules.yaml

@@ -0,0 +1,32 @@
+regex_definitions:
+  # Regular expression to match the separator between
+  # zip code prefix and suffix.
+  kZipCodeSeparatorsRe:
+    regex_reference: kWhitespaceSeparator
+
+  # Regular expression to match zip prefix
+  kZipPrefixValueRe:
+    regex_fragment: (?:[ABCEGHJ-NPRSTVXY]\d[ABCEGHJ-NPRSTV-Z])
+
+  # Regular expression to match zip suffix
+  kZipSuffixValueRe:
+    regex_fragment: (?:\d[ABCEGHJ-NPRSTV-Z]\d)
+
+parsing_definitions:
+  postal-code:
+    decomposition:
+      capture_reference: ParsePostalCodeOptionalSeparatorExpression
+
+test_parsing_definitions:
+- id: "Zip code with separator"
+  type: postal-code
+  input: "K1A 0B1"
+  output:
+    postal-code-prefix: "K1A"
+    postal-code-suffix: "0B1"
+- id: "Zip code without separator"
+  type: postal-code
+  input: "K1A0B1"
+  output:
+    postal-code-prefix: "K1A"
+    postal-code-suffix: "0B1"

model/countries/NL/NL-formatting-rules.yaml

@@ -24,6 +24,10 @@ formatting-rules:
   - separator: "-"
   - unit
 
+  postal-code:
+  - postal-code-prefix
+  - postal-code-suffix
+
 examples:
 - id: name
   comment: |
@@ -46,7 +50,8 @@ examples:
     unit: A
     building-and-unit: 10-A
     locality1: Amsterdam
-    postal-code: 1234 AB
+    postal-code-prefix: 1234
+    postal-code-suffix: AB
     country: NL
     country-name: Netherlands
   output:
@@ -65,7 +70,8 @@ examples:
     building: 10
     building-and-unit: 10
     locality1: Amsterdam
-    postal-code: 1234 AB
+    postal-code-prefix: 1234
+    postal-code-suffix: AB
     country: NL
     country-name: Netherlands
   output:

model/countries/NL/NL-parsing-rules.yaml

@@ -9,6 +9,14 @@ regex_definitions:
   kHouseNumberAndUnitSeparator:
     regex_fragment: (?:[-\s/,]*)
 
+  # Regular expression to match zip prefix
+  kZipPrefixValueRe:
+    regex_fragment: (?:[1-9]\d{3})
+
+  # Regular expression to match zip suffix
+  kZipSuffixValueRe:
+    regex_fragment: (?:[A-Z]{2})
+
 capture_definitions:
   ParseBuildingLocation:
     capture:
@@ -31,7 +39,7 @@ capture_definitions:
                   - capture:
                       output: unit-name
                       parts: [ {regex_reference: kUnitValueRe} ]
-                quantifier: MATCH_OPTIONAL       
+                quantifier: MATCH_OPTIONAL
 
 parsing_definitions:
   building-location:
@@ -44,6 +52,10 @@ parsing_definitions:
         output: street-address-alternative-1
         parts:
         - capture_reference: ParseBuildingLocation
+
+  postal-code:
+    decomposition:
+      capture_reference: ParsePostalCodeOptionalSeparatorExpression
 
 test_parsing_definitions:
 - id: "Test 1"
@@ -241,3 +253,15 @@ test_parsing_definitions:
     building: "146"
     unit: "A-02"
     unit-name: "A-02"
+- id: "Test 19: zip code with separator"
+  type: postal-code
+  input: "1234 AB"
+  output:
+    postal-code-prefix: "1234"
+    postal-code-suffix: "AB"
+- id: "Test 20: zip code without separator"
+  type: postal-code
+  input: "1234AB"
+  output:
+    postal-code-prefix: "1234"
+    postal-code-suffix: "AB"

model/countries/PL/PL-parsing-rules.yaml

@@ -24,6 +24,14 @@ regex_definitions:
   # Regular expression to match separator of house/building number and unit/apartment number.
   kHouseNumberAndUnitSeparator:
     regex_fragment: (?:^|[/\s]+)
+
+  # Regular expression to match 2-digit zip prefix
+  kZipPrefixValueRe:
+    regex_fragment: (?:\d{2})
+
+  # Regular expression to match 3-digit zip suffix
+  kZipSuffixValueRe:
+    regex_fragment: (?:\d{3})
 
 capture_definitions:
   ParseBuildingLocation:
@@ -85,6 +93,10 @@ parsing_definitions:
   unit:
     decomposition:
       capture_reference: ParseUnitWithOptionalPrefix
+
+  postal-code:
+    decomposition:
+      capture_reference: ParsePostalCodeOptionalSeparatorExpression
 
 
 test_parsing_definitions:
@@ -222,4 +234,16 @@ test_parsing_definitions:
     building: "9A"
     unit: "m.10"
     unit-type: "m."
-    unit-name: "10"
+    unit-name: "10"
+- id: "Test 15: zip code with separator"
+  type: postal-code
+  input: "00-843"
+  output:
+    postal-code-prefix: "00"
+    postal-code-suffix: "843"
+- id: "Test 16: zip code without separator"
+  type: postal-code
+  input: "00843"
+  output:
+    postal-code-prefix: "00"
+    postal-code-suffix: "843"

model/countries/US/US-formatting-rules.yaml

@@ -35,7 +35,8 @@ examples:
     address-line2: Apt. 10, Club of Autofillers
     locality1: New York City
     admin-area1: NY
-    postal-code: 11367
+    postal-code-prefix: 11367
+    postal-code-suffix: 4100
     country: US
     country-name: USA
 
@@ -45,5 +46,5 @@ examples:
       text: |
         1234 Main St.
         Apt. 10, Club of Autofillers
-        New York City, NY 11367
-        USA
+        New York City, NY 11367-4100
+        USA

model/countries/US/US-parsing-rules.yaml

@@ -0,0 +1,39 @@
+regex_definitions:
+  # Regular expression to match 5-digit zip prefix
+  kZipPrefixValueRe:
+    regex_fragment: (?:\d{5})
+
+  # Regular expression to match 4-digit zip suffix
+  kZipSuffixValueRe:
+    regex_fragment: (?:\d{4})
+
+parsing_definitions:
+  postal-code:
+    decomposition:
+      capture_reference: ParsePostalCodeOptionalSeparatorExpression
+
+test_parsing_definitions:
+- id: "Zip code with suffix"
+  type: postal-code
+  input: "90210-5555"
+  output:
+    postal-code-prefix: "90210"
+    postal-code-suffix: "5555"
+- id: "Zip code without suffix"
+  type: postal-code
+  input: "90210"
+  output:
+    postal-code-prefix: "90210"
+    postal-code-suffix: ""
+- id: "Zip code with extra spaces"
+  type: postal-code
+  input: "90210 - 5555"
+  output:
+    postal-code-prefix: "90210"
+    postal-code-suffix: "5555" 
+- id: "Zip code without separator"
+  type: postal-code
+  input: "902105555"
+  output:
+    postal-code-prefix: "90210"
+    postal-code-suffix: "5555" 

model/countries/global/global-descriptions.yaml

@@ -13,6 +13,8 @@ short-descriptions:
   country: 2-letter country code
   country-name: Name of a country
   postal-code: Postal code
+  postal-code-prefix: Postal code prefix
+  postal-code-suffix: Postal code suffix
   admin-area1: Biggest type of admin area if a country has multiple levels
   admin-area2: 2nd biggest type of admin area if a country has multiple levels
   admin-area3: 3rd biggest type of admin area if a country has multiple levels

model/countries/global/global-formatting-rules.yaml

@@ -109,3 +109,8 @@ formatting-rules:
   - tel-local-prefix
   - separator: ""
   - tel-local-suffix
+
+  postal-code:
+  - postal-code-prefix
+  - separator: "-"
+  - postal-code-suffix

model/countries/global/global-model.yaml

@@ -56,7 +56,9 @@ concepts:
     - admin-area2
     - admin-area3
     - admin-area4
-    - postal-code
+    - postal-code:
+      - postal-code-prefix
+      - postal-code-suffix
     - country
     - country-name
   # Company related