feat: add GDC query via REST

tcga_downloader/query.py

@@ -0,0 +1,42 @@
+from __future__ import annotations
+
+import requests
+
+GDC_FILES_URL = "https://api.gdc.cancer.gov/files"
+
+
+def build_filters(project: str, data_type: str) -> dict:
+    return {
+        "op": "and",
+        "content": [
+            {
+                "op": "in",
+                "content": {
+                    "field": "cases.project.project_id",
+                    "value": [project],
+                },
+            },
+            {
+                "op": "in",
+                "content": {
+                    "field": "data_type",
+                    "value": [data_type],
+                },
+            },
+        ],
+    }
+
+
+def query_files(project: str, data_type: str, fields: list[str] | None = None, size: int = 1000) -> list[dict]:
+    if fields is None:
+        fields = ["file_id", "file_name", "data_type", "data_format", "file_size", "md5sum"]
+    payload = {
+        "filters": build_filters(project, data_type),
+        "fields": ",".join(fields),
+        "format": "JSON",
+        "size": size,
+    }
+    resp = requests.post(GDC_FILES_URL, json=payload, timeout=30)
+    resp.raise_for_status()
+    data = resp.json()
+    return data.get("data", {}).get("hits", [])

tests/test_query.py

@@ -0,0 +1,7 @@
+from tcga_downloader.query import build_filters
+
+
+def test_build_filters_project_and_type():
+    filters = build_filters(project="TCGA-BRCA", data_type="Gene Expression")
+    assert filters["op"] == "and"
+    assert filters["content"][0]["content"]["field"] == "cases.project.project_id"