refdatakit 0.1.2__tar.gz → 0.2.0__tar.gz

{refdatakit-0.1.2/src/refdatakit.egg-info → refdatakit-0.2.0}/PKG-INFO

@@ -1,7 +1,7 @@
 Metadata-Version: 2.4
 Name: refdatakit
-Version: 0.1.2
-Summary: Source-aware reference data and validation tools
+Version: 0.2.0
+Summary: Validated, source-backed reference data for Bangladesh (subdivisions, cities, institutions) with JSON Schema validation tools
 Author: RefDataKit contributors
 License: MIT
 Project-URL: Homepage, https://github.com/rezwan4029/refdatakit#readme

{refdatakit-0.1.2 → refdatakit-0.2.0}/pyproject.toml

@@ -4,8 +4,8 @@ build-backend = "setuptools.build_meta"
 
 [project]
 name = "refdatakit"
-version = "0.1.2"
-description = "Source-aware reference data and validation tools"
+version = "0.2.0"
+description = "Validated, source-backed reference data for Bangladesh (subdivisions, cities, institutions) with JSON Schema validation tools"
 readme = "README.md"
 license = { text = "MIT" }
 requires-python = ">=3.11"

{refdatakit-0.1.2 → refdatakit-0.2.0}/src/refdatakit/canonical_json.py

@@ -1,5 +1,6 @@
 from __future__ import annotations
 
+import json
 import unicodedata
 from typing import TypeAlias, cast
 
@@ -32,3 +33,15 @@ def _normalize_nfc(value: object) -> JsonValue:
 
 def canonical_json(value: object) -> bytes:
     return rfc8785.dumps(_normalize_nfc(value)) + b"\n"
+
+
+def pretty_json(value: object) -> bytes:
+    """Human-readable, diff-friendly JSON for on-disk datasets.
+
+    Keys are sorted and strings NFC-normalized for determinism, but the output is
+    indented so GitHub renders multi-line diffs. Checksums are computed over the
+    canonical form of the parsed value, so this layout does not affect integrity.
+    """
+    normalized = _normalize_nfc(value)
+    text = json.dumps(normalized, ensure_ascii=False, indent=2, sort_keys=True)
+    return (text + "\n").encode("utf-8")

{refdatakit-0.1.2 → refdatakit-0.2.0}/src/refdatakit/country_codes.py

@@ -4,8 +4,3 @@ from enum import StrEnum
 
 class CountryCode(StrEnum):
     BD = "BD"
-    BT = "BT"
-    LK = "LK"
-    MV = "MV"
-    NP = "NP"
-    SG = "SG"