notoecd 0.1.1__tar.gz → 0.1.2__tar.gz

{notoecd-0.1.1 → notoecd-0.1.2}/PKG-INFO

@@ -1,7 +1,7 @@
 Metadata-Version: 2.4
 Name: notoecd
-Version: 0.1.1
-Summary: Library for interacting with the OECD Data Explorer through Python
+Version: 0.1.2
+Summary: Unofficial library for interacting with the OECD Data Explorer through Python.
 Author-email: Daniel Vegara Balsa <daniel.vegarabalsa@oecd.org>
 License-Expression: MIT
 Project-URL: Homepage, https://github.com/dani-37/notoecd
@@ -15,6 +15,7 @@ Requires-Dist: requests>=2.31
 ⚠️ **Unofficial package, not endorsed by the OECD.**
 
 A lightweight Python interface for exploring OECD SDMX structures and downloading OECD datasets.  
+
 The package provides utilities for:
 
 - Discovering dataset metadata  
@@ -110,4 +111,3 @@ The returned object is a pandas DataFrame containing the requested subset of OEC
 ## Examples
 
 You can see this full example as a notebook called example.ipynb.
-

{notoecd-0.1.1 → notoecd-0.1.2}/README.md

@@ -3,6 +3,7 @@
 ⚠️ **Unofficial package, not endorsed by the OECD.**
 
 A lightweight Python interface for exploring OECD SDMX structures and downloading OECD datasets.  
+
 The package provides utilities for:
 
 - Discovering dataset metadata  
@@ -97,5 +98,4 @@ The returned object is a pandas DataFrame containing the requested subset of OEC
 
 ## Examples
 
-You can see this full example as a notebook called example.ipynb.
-
+You can see this full example as a notebook called example.ipynb.

{notoecd-0.1.1 → notoecd-0.1.2}/notoecd/__init__.py

@@ -1,4 +1,4 @@
-__version__ = "0.1.1"
+__version__ = "0.1.2"
 
 from .calls import get_df
 from .structure import get_structure

{notoecd-0.1.1 → notoecd-0.1.2}/notoecd/datasets.py

@@ -18,43 +18,51 @@ NS = {
 _ws_re = re.compile(r"\s+")
 _tag_re = re.compile(r"<[^>]+>")
 
-def _clean_text(s: str | None) -> str | None:
+def _clean(s: str | None) -> str | None:
     if s is None: return None
     s = html.unescape(s)
     s = _tag_re.sub("", s)
     s = _ws_re.sub(" ", s).strip()
     return s or None
 
-headers = {
-    "Accept": "application/vnd.sdmx.structure+xml;version=2.1"
-}
+# Cache
+_datasets: pd.DataFrame | None = None
+
+def _load_datasets() -> pd.DataFrame:
+    """
+    Loads OECD datasets and keeps them in memory.
+    """
+    global _datasets
+    if _datasets is not None: return _datasets
+
+    headers = {"Accept": "application/vnd.sdmx.structure+xml;version=2.1"}
+    r = requests.get(url, headers=headers, timeout=30)
+    r.raise_for_status()
+    root = ET.fromstring(r.content)
+
+    rows = []
+    for df in root.findall(".//structure:Dataflow", NS):
+        dataflow_id = df.attrib.get("id")
+        agency_id = df.attrib.get("agencyID")
+
+        name_elem = df.find("common:Name[@xml:lang='en']", NS)
+        desc_elem = df.find("common:Description[@xml:lang='en']", NS)
+
+        name = _clean("".join(name_elem.itertext())) if name_elem is not None else None
+        desc_raw = "".join(desc_elem.itertext()) if desc_elem is not None else None
+        desc = _clean(desc_raw)
+
+        rows.append(
+            {
+                "dataflowID": dataflow_id,
+                "agencyID": agency_id,
+                "name": name,
+                "description": desc,
+            }
+        )
 
-r = requests.get(url, headers=headers, timeout=30)
-r.raise_for_status()
-root = ET.fromstring(r.content)
-
-rows = []
-for df in root.findall(".//structure:Dataflow", NS):
-    dataflow_id = df.attrib.get("id")
-    agency_id = df.attrib.get("agencyID")
-
-    name_elem = df.find("common:Name[@xml:lang='en']", NS)
-    desc_elem = df.find("common:Description[@xml:lang='en']", NS)
-
-    name = _clean_text("".join(name_elem.itertext())) if name_elem is not None else None
-    desc_raw = "".join(desc_elem.itertext()) if desc_elem is not None else None
-    desc = _clean_text(desc_raw)
-
-    rows.append(
-        {
-            "dataflowID": dataflow_id,
-            "agencyID": agency_id,
-            "name": name,
-            "description": desc,
-        }
-    )
-    
-datasets = pd.DataFrame(rows)
+    _datasets = pd.DataFrame(rows)
+    return _datasets
 
 def search_keywords(keywords: Union[str, List[str]]) -> pd.DataFrame:
     """
@@ -66,6 +74,7 @@ def search_keywords(keywords: Union[str, List[str]]) -> pd.DataFrame:
     Returns:
         pd.DataFrame: Matching rows.
     """
+    datasets = _load_datasets()
 
     # Normalize keywords input
     if isinstance(keywords, str): keywords = [keywords]
@@ -78,10 +87,8 @@ def search_keywords(keywords: Union[str, List[str]]) -> pd.DataFrame:
     def _normalize_series(s: pd.Series) -> pd.Series:
         s = s.fillna("").astype(str).str.lower()
         return s.map(
-            lambda x: "".join(
-                ch for ch in unicodedata.normalize("NFKD", x)
-                if not unicodedata.combining(ch)
-            )
+            lambda x: "".join(ch for ch in unicodedata.normalize("NFKD", x)
+                if not unicodedata.combining(ch))
         )
 
     # Combined normalized text for each row

{notoecd-0.1.1 → notoecd-0.1.2}/notoecd.egg-info/PKG-INFO

@@ -1,7 +1,7 @@
 Metadata-Version: 2.4
 Name: notoecd
-Version: 0.1.1
-Summary: Library for interacting with the OECD Data Explorer through Python
+Version: 0.1.2
+Summary: Unofficial library for interacting with the OECD Data Explorer through Python.
 Author-email: Daniel Vegara Balsa <daniel.vegarabalsa@oecd.org>
 License-Expression: MIT
 Project-URL: Homepage, https://github.com/dani-37/notoecd
@@ -15,6 +15,7 @@ Requires-Dist: requests>=2.31
 ⚠️ **Unofficial package, not endorsed by the OECD.**
 
 A lightweight Python interface for exploring OECD SDMX structures and downloading OECD datasets.  
+
 The package provides utilities for:
 
 - Discovering dataset metadata  
@@ -110,4 +111,3 @@ The returned object is a pandas DataFrame containing the requested subset of OEC
 ## Examples
 
 You can see this full example as a notebook called example.ipynb.
-

{notoecd-0.1.1 → notoecd-0.1.2}/pyproject.toml

@@ -4,8 +4,8 @@ build-backend = "setuptools.build_meta"
 
 [project]
 name = "notoecd"
-version = "0.1.1"
-description = "Library for interacting with the OECD Data Explorer through Python"
+version = "0.1.2"
+description = "Unofficial library for interacting with the OECD Data Explorer through Python."
 readme = "README.md"
 license = "MIT"
 requires-python = ">=3.10"

{notoecd-0.1.1 → notoecd-0.1.2}/tests/test_datasets.py

@@ -1,6 +1,5 @@
 import importlib
 import requests
-import pandas as pd
 
 
 def _fake_dataflow_all_xml() -> bytes:
@@ -44,9 +43,12 @@ class _Resp:
             raise requests.HTTPError(f"HTTP {self.status_code}")
 
 
-def test_datasets_dataframe_built_on_import(monkeypatch):
+def test_datasets_lazy_loaded_and_cached_in_memory(monkeypatch):
+    calls = {"n": 0}
+
     def fake_get(url, *args, **kwargs):
         if url.endswith("/public/rest/dataflow/all"):
+            calls["n"] += 1
             return _Resp(_fake_dataflow_all_xml())
         raise AssertionError(f"Unexpected URL in test_datasets: {url}")
 
@@ -55,9 +57,18 @@ def test_datasets_dataframe_built_on_import(monkeypatch):
     datasets_mod = importlib.import_module("notoecd.datasets")
     importlib.reload(datasets_mod)
 
-    assert isinstance(datasets_mod.datasets, pd.DataFrame)
-    assert {"agencyID", "dataflowID", "name", "description"}.issubset(datasets_mod.datasets.columns)
-    assert len(datasets_mod.datasets) == 3
+    # Import should not fetch
+    assert calls["n"] == 0
+
+    # First search triggers load
+    hits = datasets_mod.search_keywords(["gdp"])
+    assert calls["n"] == 1
+    assert len(hits) == 1
+
+    # Second search should reuse in-memory cache (no extra fetch)
+    hits2 = datasets_mod.search_keywords(["cafe"])
+    assert calls["n"] == 1
+    assert len(hits2) == 1
 
 
 def test_search_keywords_or_and_normalization(monkeypatch):