@@ -799,6 +808,45 @@ Overview of concepts
+
+
+
+
+
@@ -1413,6 +1461,10 @@ Example addresses
+
+
+
+
@@ -1520,6 +1572,10 @@ Example addresses
+
+
+
+
| country | PL |
@@ -1677,6 +1733,10 @@ Example addresses
+
+
+
+
| country | PL |
@@ -3742,7 +3802,7 @@ Formatting:
Flattened formatting:
address =
-street␣building/unit-typeunit-name
postal-code␣locality1
country-name
+street␣building/unit-typeunit-name
postal-code-prefix-postal-code-suffix␣locality1
country-name
@@ -4066,7 +4126,7 @@ Parsing:
Regex Reference: kStreetOptionalPrefixRe =>
- (?:(?:ulica|ul\.?)\s*)?
+ (?:(?:ulica|ul\.?\W)\s*)?
@@ -4485,7 +4545,7 @@ Parsing:
Regex Reference: kStreetOptionalPrefixRe =>
- (?:(?:ulica|ul\.?)\s*)?
+ (?:(?:ulica|ul\.?\W)\s*)?
@@ -5579,6 +5639,263 @@ Flattened formatting:
+
+
+
+
+
+
+
+Parsing:
+
+
+
+
+
+
+ Decomposition
+
+ (ParsePostalCodeOptionalSeparatorExpression)
+
+
+ Anchor beginning: True
+
+ Capture Reference: ParsePostalCodeOptionalSeparatorExpression
+
+
+
+
+
+
+ Capture postal-code
+
+ (MATCH_REQUIRED)
+
+
+
+ Parts:
+
+
+ -
+
+
+
+
+
+ Capture postal-code-prefix
+
+ (MATCH_REQUIRED)
+
+
+
+ Parts:
+
+
+ -
+
+
+
+ Regex Reference:
kZipPrefixValueRe =>
+ (?:\d{2})
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ -
+
+
+
+
+
+ No capturing pattern
+
+ (MATCH_OPTIONAL)
+
+
+
+ Parts:
+
+
+ -
+
+
+
+Separator: Regex Reference
kZipCodeSeparatorsRe =>
+ (?:[\s-]+)
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ -
+
+
+
+
+
+ Capture postal-code-suffix
+
+ (MATCH_OPTIONAL)
+
+
+
+ Parts:
+
+
+ -
+
+
+
+ Regex Reference:
kZipSuffixValueRe =>
+ (?:\d{3})
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ Anchor end: True
+
+
+
+
+
+
Formatting:
+
+postal-code =
+postal-code-prefix-postal-code-suffix
+
+
+Flattened formatting:
+
+postal-code =
+postal-code-prefix-postal-code-suffix
+
+
+
+ #
+
+ postal-code-prefix
+
+
+
+Postal code prefix
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ #
+
+ postal-code-suffix
+
+
+
+Postal code suffix
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
diff --git a/model/countries/PL/PL-parsing-rules.yaml b/model/countries/PL/PL-parsing-rules.yaml
index 7ede4eb..90faf41 100644
--- a/model/countries/PL/PL-parsing-rules.yaml
+++ b/model/countries/PL/PL-parsing-rules.yaml
@@ -12,7 +12,7 @@ regex_definitions:
# Regular expression to match the prefixes that indicate a house number.
kStreetOptionalPrefixRe:
- regex_fragment: '(?:(?:ulica|ul\.?)\s*)?'
+ regex_fragment: '(?:(?:ulica|ul\.?\W)\s*)?'
# Regular expression to match the unit-types in Poland.
kUnitTypeLiteralRe:
@@ -247,3 +247,27 @@ test_parsing_definitions:
output:
postal-code-prefix: "00"
postal-code-suffix: "843"
+- id: "Test 17: street name starting with street prefix"
+ type: street-address-alternative-1
+ input: "Ulubiona 9A/m.10"
+ output:
+ street-address-alternative-1: "Ulubiona 9A/m.10"
+ building-location: "Ulubiona 9A/m.10"
+ street: "Ulubiona"
+ building-and-unit: "9A/m.10"
+ building: "9A"
+ unit: "m.10"
+ unit-type: "m."
+ unit-name: "10"
+- id: "Test 18: street name starting with street prefix without separator"
+ type: street-address-alternative-1
+ input: "ul.Ulubiona 9A/m.10"
+ output:
+ street-address-alternative-1: "ul.Ulubiona 9A/m.10"
+ building-location: "ul.Ulubiona 9A/m.10"
+ street: "Ulubiona"
+ building-and-unit: "9A/m.10"
+ building: "9A"
+ unit: "m.10"
+ unit-type: "m."
+ unit-name: "10"