Port Scotland

pyproject.toml

@@ -47,9 +47,12 @@ dependencies = [
   "rdflib >=7.0.0", # Required to parse BEL TTL Metadata catalogue.
   "icecream >=2.1.3", # General debugging tool
   "python-slugify >=8.0.4", # Required for generating asset names from GBR Ordnance Survey OpenData Product names
+  "openpyxl",
+  "zipfile-deflate64",
   "jcs >=0.2.1", # For generating IDs from class attributes
   "beautifulsoup4 >=4.12.3", # For extracting catalogs from web pages
   "openpyxl >=3.1.3", # For reading Excel files
+  "xlrd >=2.0.1", # For reading Excel files
   "iso639-lang >=2.2.3", # For checking ISO639-3 language codes
   "aiohttp >=3.9.5", # Async HTTP
 ]

python/popgetter/assets/__init__.py

@@ -1,7 +1,9 @@
 from __future__ import annotations
 
-from . import bel, gb_nir, uk, us
+from . import bel, gb_nir, gb_sct, uk, us
 
-countries = [(mod, mod.__name__.split(".")[-1]) for mod in [bel, gb_nir, uk, us]]
+countries = [
+    (mod, mod.__name__.split(".")[-1]) for mod in [bel, gb_nir, uk, us, gb_sct]
+]
 
 __all__ = ["countries"]

python/popgetter/assets/gb_nir/__init__.py

@@ -594,7 +594,7 @@ def pivot_df(df: pd.DataFrame, end: str) -> tuple[list[str], pd.DataFrame]:
             # Ensure columns are string
             else:
                 pivot.columns = [str(col).strip() for col in pivot.columns.to_numpy()]
-            out_cols = [col.replace(var_type, "").strip() for col in pivot_cols]
+            out_cols = [col.replace(end, "").strip() for col in pivot_cols]
             return out_cols, pivot
 
         # Pivot for codes and labels
@@ -608,6 +608,7 @@ def pivot_df(df: pd.DataFrame, end: str) -> tuple[list[str], pd.DataFrame]:
                 new_mmd = source_mmd.copy()
                 new_mmd.parent_metric_id = source_mmd.source_metric_id
                 new_mmd.metric_parquet_path = parquet_file_name
+                # TODO: check this
                 key_val = dict(zip(out_cols, metric_col.split(SEP), strict=True))
 
                 def gen_hxltag(kv: dict[str, str]) -> str: