fix(data)!: use integer for YAML file version (#87)

This diff changes the YAML file version to be an integer. While there,
we also publish data for 2025-07/country.

Author: bassosimone

data/generate_data.py

@@ -39,7 +39,7 @@ class PipelineMatrix:
 
 @dataclass(frozen=True, kw_only=True)
 class PipelineConfig:
-    version: str
+    version: int
     matrix: PipelineMatrix
 
 
@@ -73,7 +73,7 @@ def coerce_str(value):
     except dacite.DaciteError as exc:
         raise click.ClickException(f"Invalid pipeline config: {exc}") from exc
 
-    if config.version != "v0":
+    if config.version != 0:
         raise click.ClickException(f"Unsupported pipeline config version: {config.version}")
 
     time_periods = [(entry.start, entry.end) for entry in config.matrix.dates]

data/pipeline.yaml

@@ -1,4 +1,4 @@
-version: "v0"
+version: 0
 matrix:
   dates:
     - start: "2024-10-01"
@@ -15,6 +15,8 @@ matrix:
       end: "2025-06-01"
     - start: "2025-06-01"
       end: "2025-07-01"
+    - start: "2025-07-01"
+      end: "2025-08-01"
     - start: "2025-10-01"
       end: "2025-11-01"
   granularities:

data/state/ghremote/manifest.json

@@ -192,6 +192,22 @@
       "sha256": "f2e545292c10b7bad55e1e3599ed9748e12a119d6a70db1d95a2fa863e6e50f9",
       "url": "https://github.com/m-lab/iqb/releases/download/v0.2.0/f2e545292c10__cache__v1__20250601T000000Z__20250701T000000Z__uploads_by_country__stats.json"
     },
+    "cache/v1/20250701T000000Z/20250801T000000Z/downloads_by_country/data.parquet": {
+      "sha256": "e0e00d4a2f659354d79508428ca165f1b05ac15ba7e23ef3f4360ff6eeb6aab8",
+      "url": "https://github.com/m-lab/iqb/releases/download/v0.2.0/e0e00d4a2f65__cache__v1__20250701T000000Z__20250801T000000Z__downloads_by_country__data.parquet"
+    },
+    "cache/v1/20250701T000000Z/20250801T000000Z/downloads_by_country/stats.json": {
+      "sha256": "8aa265058f210d32b5fd0f35625c9e21a16bd2e1d281016b23791f4ea0a074b9",
+      "url": "https://github.com/m-lab/iqb/releases/download/v0.2.0/8aa265058f21__cache__v1__20250701T000000Z__20250801T000000Z__downloads_by_country__stats.json"
+    },
+    "cache/v1/20250701T000000Z/20250801T000000Z/uploads_by_country/data.parquet": {
+      "sha256": "88bb523fda2f6659923573598d71f3b83f5c83505ca8c371683a532d25a24f97",
+      "url": "https://github.com/m-lab/iqb/releases/download/v0.2.0/88bb523fda2f__cache__v1__20250701T000000Z__20250801T000000Z__uploads_by_country__data.parquet"
+    },
+    "cache/v1/20250701T000000Z/20250801T000000Z/uploads_by_country/stats.json": {
+      "sha256": "b594ecb1a50f6bce18e0b03036fb11e61b9dd577368f7d7f0bdc0ca8759f2565",
+      "url": "https://github.com/m-lab/iqb/releases/download/v0.2.0/b594ecb1a50f__cache__v1__20250701T000000Z__20250801T000000Z__uploads_by_country__stats.json"
+    },
     "cache/v1/20251001T000000Z/20251101T000000Z/downloads_by_country/data.parquet": {
       "sha256": "82226cc007001bd5545d5b1f036eefe1707c43608581cc5c06e5f055867be376",
       "url": "https://github.com/m-lab/iqb/releases/download/v0.2.0/82226cc00700__cache__v1__20251001T000000Z__20251101T000000Z__downloads_by_country__data.parquet"

data/tests/generate_data_test.py

@@ -22,7 +22,7 @@ def test_load_pipeline_config_valid(tmp_path: Path):
     config_path.write_text(
         "\n".join(
             [
-                'version: "v0"',
+                "version: 0",
                 "matrix:",
                 "  dates:",
                 "    - start: 2024-01-01",
@@ -47,7 +47,7 @@ def test_load_pipeline_config_rejects_wrong_version(tmp_path: Path):
     config_path.write_text(
         "\n".join(
             [
-                'version: "v1"',
+                "version: 1",
                 "matrix:",
                 "  dates:",
                 "    - start: 2024-01-01",
@@ -69,7 +69,7 @@ def test_load_pipeline_config_rejects_empty_dates(tmp_path: Path):
     config_path.write_text(
         "\n".join(
             [
-                'version: "v0"',
+                "version: 0",
                 "matrix:",
                 "  dates: []",
                 "  granularities:",
@@ -89,7 +89,7 @@ def test_load_pipeline_config_rejects_blank_granularity(tmp_path: Path):
     config_path.write_text(
         "\n".join(
             [
-                'version: "v0"',
+                "version: 0",
                 "matrix:",
                 "  dates:",
                 "    - start: 2024-01-01",