Initial commit

README.md

@@ -0,0 +1,22 @@
+# Postal Dataset
+
+This is a dataset for noccylabs/dataset holding postal code patterns for
+validating postal codes.
+
+
+## Datasets
+
+### postalcode
+
+Field | Type | Description
+---|---|---
+`iso` | string | The ISO 2-letter country code
+`format` | array | Valid formats, see below
+`regex` | string | Unguarded regex to validate against
+
+
+- The value in `format` is treated literal, except for the following characters:
+  `#` indicates a number, `?` indicates a digit, and `*` indicates either a number
+  or digit.
+- The regex must be bounded, for example as `"<^".$regex."$>"`. This is done so
+  that multiple expressions can be combined easily.

composer.json

@@ -0,0 +1,8 @@
+{
+    "name": "noccylabs/dataset-postal",
+    "description": "Dataset containing postal code validation patterns",
+    "license": "CC-BY-SA-4.0",
+    "suggest": {
+        "noccylabs/dataset": "to parse the dataset"
+    }
+}

data/postalcodes.json

@@ -0,0 +1,47 @@
+[
+  {
+    "iso": "se",
+    "format": [ "??? ??", "?????" ],
+    "regex": "(\d{3}\s{0,1}\d{2})"
+  },
+  {
+    "iso": "no",
+    "format": [ "????" ],
+    "regex": "(\d{4})"
+  },
+  {
+    "iso": "dk",
+    "format": [ "????", "DK-????" ],
+    "regex": "((DK-){0,1}\d{4})"
+  },
+  {
+    "iso": "fi",
+    "format": [ "?????", "FI-?????" ],
+    "regex": "((FI-){0,1}\d{5})"
+  },
+  {
+    "iso": "ax",
+    "format": [ "?????", "AX-?????" ],
+    "regex": "((AX-){0,1}\d{5})"
+  },
+  {
+    "iso": "es",
+    "format": [ "?????", "EE-?????" ],
+    "regex": "((EE-){0,1}\d{5})"
+  },
+  {
+    "iso": "lv",
+    "format": [ "##-????" ],
+    "regex": "([a-z]{2}-\d{4})"
+  },
+  {
+    "iso": "lt",
+    "format": [ "##-?????" ],
+    "regex": "([a-z]{2}-\d{5})"
+  },
+  {
+    "iso": "pl",
+    "format": [ "??-???" ],
+    "regex": "(\d{2}-\d{3})"
+  }
+]

dataset.json

@@ -0,0 +1,7 @@
+{
+  "datasets": {
+    "postalcodes": {
+      "filename": "data/postalcodes.json"
+    }
+  }
+}