fix: DuckDB compat issues in Playtomic pipeline + export_serving

- Add maximum_object_size=128MB to read_json for 14K-venue tenants file - Rewrite opening_hours to use UNION ALL unpivot (DuckDB struct dynamic access) - Add seed file guard for availability model (empty result on first run) - Fix snapshot_date VARCHAR→DATE comparison in venue_pricing_benchmarks - Fix export_serving to resolve SQLMesh physical tables from view definitions (SQLMesh views reference "local" catalog unavailable outside its context) - Add pyarrow dependency for Arrow-based cross-connection data transfer Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
2026-02-23 01:27:51 +01:00
parent a055660cd2
commit 7737b79230
8 changed files with 144 additions and 36 deletions
--- a/src/padelnomics/export_serving.py
+++ b/src/padelnomics/export_serving.py
@@ -46,24 +46,42 @@ def export_serving() -> None:

    src = duckdb.connect(pipeline_path, read_only=True)
    try:
-        tables = src.sql(
-            "SELECT table_name FROM information_schema.tables"
-            " WHERE table_schema = 'serving' ORDER BY table_name"
+        # SQLMesh creates serving views that reference "local".sqlmesh__serving.*
+        # which fails when connecting directly.  Resolve the physical table each
+        # view points to by parsing the view definition.
+        view_rows = src.execute(
+            "SELECT view_name, sql FROM duckdb_views()"
+            " WHERE schema_name = 'serving' ORDER BY view_name"
        ).fetchall()
-        assert tables, f"No tables found in serving schema of {pipeline_path}"
-        logger.info(f"Exporting {len(tables)} serving tables: {[t[0] for t in tables]}")
+        assert view_rows, f"No views found in serving schema of {pipeline_path}"
+
+        # Extract physical table reference from: CREATE VIEW ... AS SELECT * FROM "local".schema.table;
+        physical_tables: list[tuple[str, str]] = []  # (logical_name, physical_ref)
+        for view_name, view_sql in view_rows:
+            # Pattern: ... FROM "local".sqlmesh__serving.serving__name__hash;
+            # Strip the "local". prefix to get schema.table
+            import re
+            match = re.search(r'FROM\s+"local"\.(sqlmesh__serving\.\S+)', view_sql)
+            assert match, f"Cannot parse view definition for {view_name}: {view_sql[:200]}"
+            physical_tables.append((view_name, match.group(1)))
+
+        logger.info(
+            "Exporting %d serving tables: %s",
+            len(physical_tables),
+            [name for name, _ in physical_tables],
+        )

        dst = duckdb.connect(tmp_path)
        try:
            dst.execute("CREATE SCHEMA IF NOT EXISTS serving")
-            for (table,) in tables:
+            for logical_name, physical_ref in physical_tables:
                # Read via Arrow to avoid cross-connection catalog ambiguity.
-                arrow_data = src.sql(f"SELECT * FROM serving.{table}").arrow()
+                arrow_data = src.sql(f"SELECT * FROM {physical_ref}").arrow()
                dst.register("_src", arrow_data)
-                dst.execute(f"CREATE OR REPLACE TABLE serving.{table} AS SELECT * FROM _src")
+                dst.execute(f"CREATE OR REPLACE TABLE serving.{logical_name} AS SELECT * FROM _src")
                dst.unregister("_src")
-                row_count = dst.sql(f"SELECT count(*) FROM serving.{table}").fetchone()[0]
-                logger.info(f"  serving.{table}: {row_count:,} rows")
+                row_count = dst.sql(f"SELECT count(*) FROM serving.{logical_name}").fetchone()[0]
+                logger.info(f"  serving.{logical_name}: {row_count:,} rows")
        finally:
            dst.close()
    finally:
--- a/transform/sqlmesh_padelnomics/models/serving/venue_pricing_benchmarks.sql
+++ b/transform/sqlmesh_padelnomics/models/serving/venue_pricing_benchmarks.sql
@@ -26,7 +26,7 @@ WITH venue_stats AS (
    MAX(da.active_court_count)                          AS court_count,
    COUNT(DISTINCT da.snapshot_date)                    AS days_observed
  FROM foundation.fct_daily_availability da
-  WHERE da.snapshot_date >= CURRENT_DATE - INTERVAL '30 days'
+  WHERE TRY_CAST(da.snapshot_date AS DATE) >= CURRENT_DATE - INTERVAL '30 days'
    AND da.occupancy_rate IS NOT NULL
    AND da.occupancy_rate BETWEEN 0 AND 1.5
  GROUP BY da.tenant_id, da.country_code, da.city, da.price_currency
--- a/transform/sqlmesh_padelnomics/models/staging/stg_playtomic_availability.sql
+++ b/transform/sqlmesh_padelnomics/models/staging/stg_playtomic_availability.sql
@@ -8,6 +8,10 @@
 --
 -- Price parsed from strings like "14.56 EUR" or "48 GBP".
 --
+-- Requires: at least one availability file in the landing zone.
+-- A seed file (data/landing/playtomic/1970/01/availability_1970-01-01.json.gz)
+-- with empty venues[] ensures this model runs before real data arrives.
+--
 -- Source: data/landing/playtomic/{year}/{month}/availability_{date}.json.gz
 -- Format: {date, captured_at_utc, venues: [{tenant_id, slots: [{resource_id, start_date, slots: [...]}]}]}

@@ -29,6 +33,8 @@ WITH raw_files AS (
      venues: 'JSON[]'
    }
  )
+  WHERE venues IS NOT NULL
+    AND json_array_length(venues) > 0
 ),
 raw_venues AS (
  SELECT
--- a/transform/sqlmesh_padelnomics/models/staging/stg_playtomic_opening_hours.sql
+++ b/transform/sqlmesh_padelnomics/models/staging/stg_playtomic_opening_hours.sql
@@ -1,7 +1,10 @@
 -- Venue opening hours by day of week from Playtomic.
-- Unpivots the opening_hours JSON object into one row per (tenant_id, day_of_week).
+-- Unpivots the opening_hours struct into one row per (tenant_id, day_of_week).
 -- Used downstream to calculate total weekly/daily capacity hours.
 --
+-- DuckDB auto-infers opening_hours as STRUCT, so we access each day by literal
+-- key (no dynamic access) and UNION ALL to unpivot.
+--
 -- Source: data/landing/playtomic/{year}/{month}/tenants.json.gz
 -- Each tenant has opening_hours: {MONDAY: {opening_time, closing_time}, ...}

@@ -13,30 +16,56 @@ MODEL (
 );

 WITH venues AS (
+  SELECT
+    tenant ->> 'tenant_id'    AS tenant_id,
+    tenant -> 'opening_hours' AS oh
+  FROM (
    SELECT UNNEST(tenants) AS tenant
    FROM read_json(
      @LANDING_DIR || '/playtomic/*/*/tenants.json.gz',
-    format = 'auto'
+      format = 'auto',
+      maximum_object_size = 134217728
+    )
  )
-),
-days AS (
-  SELECT day_name, day_number FROM (VALUES
-    ('MONDAY', 1), ('TUESDAY', 2), ('WEDNESDAY', 3), ('THURSDAY', 4),
-    ('FRIDAY', 5), ('SATURDAY', 6), ('SUNDAY', 7)
-  ) AS t(day_name, day_number)
-),
-parsed AS (
-  SELECT
-    tenant ->> 'tenant_id'                                          AS tenant_id,
-    d.day_name                                                      AS day_of_week,
-    d.day_number,
-    tenant -> 'opening_hours' -> d.day_name ->> 'opening_time'      AS opening_time,
-    tenant -> 'opening_hours' -> d.day_name ->> 'closing_time'      AS closing_time
-  FROM venues
-  CROSS JOIN days d
  WHERE (tenant ->> 'tenant_id') IS NOT NULL
    AND (tenant -> 'opening_hours') IS NOT NULL
-    AND (tenant -> 'opening_hours' -> d.day_name) IS NOT NULL
+),
+-- Unpivot by UNION ALL — 7 literal key accesses
+unpivoted AS (
+  SELECT tenant_id, 'MONDAY'    AS day_of_week, 1 AS day_number,
+    oh -> 'MONDAY'    ->> 'opening_time' AS opening_time,
+    oh -> 'MONDAY'    ->> 'closing_time' AS closing_time
+  FROM venues
+  UNION ALL
+  SELECT tenant_id, 'TUESDAY'   AS day_of_week, 2,
+    oh -> 'TUESDAY'   ->> 'opening_time',
+    oh -> 'TUESDAY'   ->> 'closing_time'
+  FROM venues
+  UNION ALL
+  SELECT tenant_id, 'WEDNESDAY' AS day_of_week, 3,
+    oh -> 'WEDNESDAY' ->> 'opening_time',
+    oh -> 'WEDNESDAY' ->> 'closing_time'
+  FROM venues
+  UNION ALL
+  SELECT tenant_id, 'THURSDAY'  AS day_of_week, 4,
+    oh -> 'THURSDAY'  ->> 'opening_time',
+    oh -> 'THURSDAY'  ->> 'closing_time'
+  FROM venues
+  UNION ALL
+  SELECT tenant_id, 'FRIDAY'    AS day_of_week, 5,
+    oh -> 'FRIDAY'    ->> 'opening_time',
+    oh -> 'FRIDAY'    ->> 'closing_time'
+  FROM venues
+  UNION ALL
+  SELECT tenant_id, 'SATURDAY'  AS day_of_week, 6,
+    oh -> 'SATURDAY'  ->> 'opening_time',
+    oh -> 'SATURDAY'  ->> 'closing_time'
+  FROM venues
+  UNION ALL
+  SELECT tenant_id, 'SUNDAY'    AS day_of_week, 7,
+    oh -> 'SUNDAY'    ->> 'opening_time',
+    oh -> 'SUNDAY'    ->> 'closing_time'
+  FROM venues
 )
 SELECT
  tenant_id,
@@ -49,6 +78,6 @@ SELECT
    (EXTRACT(HOUR FROM closing_time::TIME) + EXTRACT(MINUTE FROM closing_time::TIME) / 60.0)
    - (EXTRACT(HOUR FROM opening_time::TIME) + EXTRACT(MINUTE FROM opening_time::TIME) / 60.0)
  , 2) AS hours_open
-FROM parsed
+FROM unpivoted
 WHERE opening_time IS NOT NULL
  AND closing_time IS NOT NULL
--- a/transform/sqlmesh_padelnomics/models/staging/stg_playtomic_resources.sql
+++ b/transform/sqlmesh_padelnomics/models/staging/stg_playtomic_resources.sql
@@ -16,7 +16,8 @@ WITH raw AS (
  SELECT UNNEST(tenants) AS tenant
  FROM read_json(
    @LANDING_DIR || '/playtomic/*/*/tenants.json.gz',
-    format = 'auto'
+    format = 'auto',
+    maximum_object_size = 134217728
  )
 ),
 unnested AS (
--- a/transform/sqlmesh_padelnomics/models/staging/stg_playtomic_venues.sql
+++ b/transform/sqlmesh_padelnomics/models/staging/stg_playtomic_venues.sql
@@ -56,7 +56,8 @@ WITH parsed AS (
    FROM read_json(
      @LANDING_DIR || '/playtomic/*/*/tenants.json.gz',
      format = 'auto',
-      filename = true
+      filename = true,
+      maximum_object_size = 134217728
    )
  )
  WHERE (tenant ->> 'tenant_id') IS NOT NULL
--- a/uv.lock
+++ b/uv.lock
@@ -1157,6 +1157,7 @@ dependencies = [
    { name = "jinja2" },
    { name = "mistune" },
    { name = "paddle-python-sdk" },
+    { name = "pyarrow" },
    { name = "python-dotenv" },
    { name = "quart" },
    { name = "resend" },
@@ -1172,6 +1173,7 @@ requires-dist = [
    { name = "jinja2", specifier = ">=3.1.0" },
    { name = "mistune", specifier = ">=3.0.0" },
    { name = "paddle-python-sdk", specifier = ">=1.13.0" },
+    { name = "pyarrow", specifier = ">=23.0.1" },
    { name = "python-dotenv", specifier = ">=1.0.0" },
    { name = "quart", specifier = ">=0.19.0" },
    { name = "resend", specifier = ">=2.22.0" },
@@ -1422,6 +1424,56 @@ wheels = [
    { url = "https://files.pythonhosted.org/packages/8e/37/efad0257dc6e593a18957422533ff0f87ede7c9c6ea010a2177d738fb82f/pure_eval-0.2.3-py3-none-any.whl", hash = "sha256:1db8e35b67b3d218d818ae653e27f06c3aa420901fa7b081ca98cbedc874e0d0", size = 11842, upload-time = "2024-07-21T12:58:20.04Z" },
 ]

+[[package]]
+name = "pyarrow"
+version = "23.0.1"
+source = { registry = "https://pypi.org/simple" }
+sdist = { url = "https://files.pythonhosted.org/packages/88/22/134986a4cc224d593c1afde5494d18ff629393d74cc2eddb176669f234a4/pyarrow-23.0.1.tar.gz", hash = "sha256:b8c5873e33440b2bc2f4a79d2b47017a89c5a24116c055625e6f2ee50523f019", size = 1167336, upload-time = "2026-02-16T10:14:12.39Z" }
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/b0/41/8e6b6ef7e225d4ceead8459427a52afdc23379768f54dd3566014d7618c1/pyarrow-23.0.1-cp311-cp311-macosx_12_0_arm64.whl", hash = "sha256:6f0147ee9e0386f519c952cc670eb4a8b05caa594eeffe01af0e25f699e4e9bb", size = 34302230, upload-time = "2026-02-16T10:09:03.859Z" },
+    { url = "https://files.pythonhosted.org/packages/bf/4a/1472c00392f521fea03ae93408bf445cc7bfa1ab81683faf9bc188e36629/pyarrow-23.0.1-cp311-cp311-macosx_12_0_x86_64.whl", hash = "sha256:0ae6e17c828455b6265d590100c295193f93cc5675eb0af59e49dbd00d2de350", size = 35850050, upload-time = "2026-02-16T10:09:11.877Z" },
+    { url = "https://files.pythonhosted.org/packages/0c/b2/bd1f2f05ded56af7f54d702c8364c9c43cd6abb91b0e9933f3d77b4f4132/pyarrow-23.0.1-cp311-cp311-manylinux_2_28_aarch64.whl", hash = "sha256:fed7020203e9ef273360b9e45be52a2a47d3103caf156a30ace5247ffb51bdbd", size = 44491918, upload-time = "2026-02-16T10:09:18.144Z" },
+    { url = "https://files.pythonhosted.org/packages/0b/62/96459ef5b67957eac38a90f541d1c28833d1b367f014a482cb63f3b7cd2d/pyarrow-23.0.1-cp311-cp311-manylinux_2_28_x86_64.whl", hash = "sha256:26d50dee49d741ac0e82185033488d28d35be4d763ae6f321f97d1140eb7a0e9", size = 47562811, upload-time = "2026-02-16T10:09:25.792Z" },
+    { url = "https://files.pythonhosted.org/packages/7d/94/1170e235add1f5f45a954e26cd0e906e7e74e23392dcb560de471f7366ec/pyarrow-23.0.1-cp311-cp311-musllinux_1_2_aarch64.whl", hash = "sha256:3c30143b17161310f151f4a2bcfe41b5ff744238c1039338779424e38579d701", size = 48183766, upload-time = "2026-02-16T10:09:34.645Z" },
+    { url = "https://files.pythonhosted.org/packages/0e/2d/39a42af4570377b99774cdb47f63ee6c7da7616bd55b3d5001aa18edfe4f/pyarrow-23.0.1-cp311-cp311-musllinux_1_2_x86_64.whl", hash = "sha256:db2190fa79c80a23fdd29fef4b8992893f024ae7c17d2f5f4db7171fa30c2c78", size = 50607669, upload-time = "2026-02-16T10:09:44.153Z" },
+    { url = "https://files.pythonhosted.org/packages/00/ca/db94101c187f3df742133ac837e93b1f269ebdac49427f8310ee40b6a58f/pyarrow-23.0.1-cp311-cp311-win_amd64.whl", hash = "sha256:f00f993a8179e0e1c9713bcc0baf6d6c01326a406a9c23495ec1ba9c9ebf2919", size = 27527698, upload-time = "2026-02-16T10:09:50.263Z" },
+    { url = "https://files.pythonhosted.org/packages/9a/4b/4166bb5abbfe6f750fc60ad337c43ecf61340fa52ab386da6e8dbf9e63c4/pyarrow-23.0.1-cp312-cp312-macosx_12_0_arm64.whl", hash = "sha256:f4b0dbfa124c0bb161f8b5ebb40f1a680b70279aa0c9901d44a2b5a20806039f", size = 34214575, upload-time = "2026-02-16T10:09:56.225Z" },
+    { url = "https://files.pythonhosted.org/packages/e1/da/3f941e3734ac8088ea588b53e860baeddac8323ea40ce22e3d0baa865cc9/pyarrow-23.0.1-cp312-cp312-macosx_12_0_x86_64.whl", hash = "sha256:7707d2b6673f7de054e2e83d59f9e805939038eebe1763fe811ee8fa5c0cd1a7", size = 35832540, upload-time = "2026-02-16T10:10:03.428Z" },
+    { url = "https://files.pythonhosted.org/packages/88/7c/3d841c366620e906d54430817531b877ba646310296df42ef697308c2705/pyarrow-23.0.1-cp312-cp312-manylinux_2_28_aarch64.whl", hash = "sha256:86ff03fb9f1a320266e0de855dee4b17da6794c595d207f89bba40d16b5c78b9", size = 44470940, upload-time = "2026-02-16T10:10:10.704Z" },
+    { url = "https://files.pythonhosted.org/packages/2c/a5/da83046273d990f256cb79796a190bbf7ec999269705ddc609403f8c6b06/pyarrow-23.0.1-cp312-cp312-manylinux_2_28_x86_64.whl", hash = "sha256:813d99f31275919c383aab17f0f455a04f5a429c261cc411b1e9a8f5e4aaaa05", size = 47586063, upload-time = "2026-02-16T10:10:17.95Z" },
+    { url = "https://files.pythonhosted.org/packages/5b/3c/b7d2ebcff47a514f47f9da1e74b7949138c58cfeb108cdd4ee62f43f0cf3/pyarrow-23.0.1-cp312-cp312-musllinux_1_2_aarch64.whl", hash = "sha256:bf5842f960cddd2ef757d486041d57c96483efc295a8c4a0e20e704cbbf39c67", size = 48173045, upload-time = "2026-02-16T10:10:25.363Z" },
+    { url = "https://files.pythonhosted.org/packages/43/b2/b40961262213beaba6acfc88698eb773dfce32ecdf34d19291db94c2bd73/pyarrow-23.0.1-cp312-cp312-musllinux_1_2_x86_64.whl", hash = "sha256:564baf97c858ecc03ec01a41062e8f4698abc3e6e2acd79c01c2e97880a19730", size = 50621741, upload-time = "2026-02-16T10:10:33.477Z" },
+    { url = "https://files.pythonhosted.org/packages/f6/70/1fdda42d65b28b078e93d75d371b2185a61da89dda4def8ba6ba41ebdeb4/pyarrow-23.0.1-cp312-cp312-win_amd64.whl", hash = "sha256:07deae7783782ac7250989a7b2ecde9b3c343a643f82e8a4df03d93b633006f0", size = 27620678, upload-time = "2026-02-16T10:10:39.31Z" },
+    { url = "https://files.pythonhosted.org/packages/47/10/2cbe4c6f0fb83d2de37249567373d64327a5e4d8db72f486db42875b08f6/pyarrow-23.0.1-cp313-cp313-macosx_12_0_arm64.whl", hash = "sha256:6b8fda694640b00e8af3c824f99f789e836720aa8c9379fb435d4c4953a756b8", size = 34210066, upload-time = "2026-02-16T10:10:45.487Z" },
+    { url = "https://files.pythonhosted.org/packages/cb/4f/679fa7e84dadbaca7a65f7cdba8d6c83febbd93ca12fa4adf40ba3b6362b/pyarrow-23.0.1-cp313-cp313-macosx_12_0_x86_64.whl", hash = "sha256:8ff51b1addc469b9444b7c6f3548e19dc931b172ab234e995a60aea9f6e6025f", size = 35825526, upload-time = "2026-02-16T10:10:52.266Z" },
+    { url = "https://files.pythonhosted.org/packages/f9/63/d2747d930882c9d661e9398eefc54f15696547b8983aaaf11d4a2e8b5426/pyarrow-23.0.1-cp313-cp313-manylinux_2_28_aarch64.whl", hash = "sha256:71c5be5cbf1e1cb6169d2a0980850bccb558ddc9b747b6206435313c47c37677", size = 44473279, upload-time = "2026-02-16T10:11:01.557Z" },
+    { url = "https://files.pythonhosted.org/packages/b3/93/10a48b5e238de6d562a411af6467e71e7aedbc9b87f8d3a35f1560ae30fb/pyarrow-23.0.1-cp313-cp313-manylinux_2_28_x86_64.whl", hash = "sha256:9b6f4f17b43bc39d56fec96e53fe89d94bac3eb134137964371b45352d40d0c2", size = 47585798, upload-time = "2026-02-16T10:11:09.401Z" },
+    { url = "https://files.pythonhosted.org/packages/5c/20/476943001c54ef078dbf9542280e22741219a184a0632862bca4feccd666/pyarrow-23.0.1-cp313-cp313-musllinux_1_2_aarch64.whl", hash = "sha256:9fc13fc6c403d1337acab46a2c4346ca6c9dec5780c3c697cf8abfd5e19b6b37", size = 48179446, upload-time = "2026-02-16T10:11:17.781Z" },
+    { url = "https://files.pythonhosted.org/packages/4b/b6/5dd0c47b335fcd8edba9bfab78ad961bd0fd55ebe53468cc393f45e0be60/pyarrow-23.0.1-cp313-cp313-musllinux_1_2_x86_64.whl", hash = "sha256:5c16ed4f53247fa3ffb12a14d236de4213a4415d127fe9cebed33d51671113e2", size = 50623972, upload-time = "2026-02-16T10:11:26.185Z" },
+    { url = "https://files.pythonhosted.org/packages/d5/09/a532297c9591a727d67760e2e756b83905dd89adb365a7f6e9c72578bcc1/pyarrow-23.0.1-cp313-cp313-win_amd64.whl", hash = "sha256:cecfb12ef629cf6be0b1887f9f86463b0dd3dc3195ae6224e74006be4736035a", size = 27540749, upload-time = "2026-02-16T10:12:23.297Z" },
+    { url = "https://files.pythonhosted.org/packages/a5/8e/38749c4b1303e6ae76b3c80618f84861ae0c55dd3c2273842ea6f8258233/pyarrow-23.0.1-cp313-cp313t-macosx_12_0_arm64.whl", hash = "sha256:29f7f7419a0e30264ea261fdc0e5fe63ce5a6095003db2945d7cd78df391a7e1", size = 34471544, upload-time = "2026-02-16T10:11:32.535Z" },
+    { url = "https://files.pythonhosted.org/packages/a3/73/f237b2bc8c669212f842bcfd842b04fc8d936bfc9d471630569132dc920d/pyarrow-23.0.1-cp313-cp313t-macosx_12_0_x86_64.whl", hash = "sha256:33d648dc25b51fd8055c19e4261e813dfc4d2427f068bcecc8b53d01b81b0500", size = 35949911, upload-time = "2026-02-16T10:11:39.813Z" },
+    { url = "https://files.pythonhosted.org/packages/0c/86/b912195eee0903b5611bf596833def7d146ab2d301afeb4b722c57ffc966/pyarrow-23.0.1-cp313-cp313t-manylinux_2_28_aarch64.whl", hash = "sha256:cd395abf8f91c673dd3589cadc8cc1ee4e8674fa61b2e923c8dd215d9c7d1f41", size = 44520337, upload-time = "2026-02-16T10:11:47.764Z" },
+    { url = "https://files.pythonhosted.org/packages/69/c2/f2a717fb824f62d0be952ea724b4f6f9372a17eed6f704b5c9526f12f2f1/pyarrow-23.0.1-cp313-cp313t-manylinux_2_28_x86_64.whl", hash = "sha256:00be9576d970c31defb5c32eb72ef585bf600ef6d0a82d5eccaae96639cf9d07", size = 47548944, upload-time = "2026-02-16T10:11:56.607Z" },
+    { url = "https://files.pythonhosted.org/packages/84/a7/90007d476b9f0dc308e3bc57b832d004f848fd6c0da601375d20d92d1519/pyarrow-23.0.1-cp313-cp313t-musllinux_1_2_aarch64.whl", hash = "sha256:c2139549494445609f35a5cda4eb94e2c9e4d704ce60a095b342f82460c73a83", size = 48236269, upload-time = "2026-02-16T10:12:04.47Z" },
+    { url = "https://files.pythonhosted.org/packages/b0/3f/b16fab3e77709856eb6ac328ce35f57a6d4a18462c7ca5186ef31b45e0e0/pyarrow-23.0.1-cp313-cp313t-musllinux_1_2_x86_64.whl", hash = "sha256:7044b442f184d84e2351e5084600f0d7343d6117aabcbc1ac78eb1ae11eb4125", size = 50604794, upload-time = "2026-02-16T10:12:11.797Z" },
+    { url = "https://files.pythonhosted.org/packages/e9/a1/22df0620a9fac31d68397a75465c344e83c3dfe521f7612aea33e27ab6c0/pyarrow-23.0.1-cp313-cp313t-win_amd64.whl", hash = "sha256:a35581e856a2fafa12f3f54fce4331862b1cfb0bef5758347a858a4aa9d6bae8", size = 27660642, upload-time = "2026-02-16T10:12:17.746Z" },
+    { url = "https://files.pythonhosted.org/packages/8d/1b/6da9a89583ce7b23ac611f183ae4843cd3a6cf54f079549b0e8c14031e73/pyarrow-23.0.1-cp314-cp314-macosx_12_0_arm64.whl", hash = "sha256:5df1161da23636a70838099d4aaa65142777185cc0cdba4037a18cee7d8db9ca", size = 34238755, upload-time = "2026-02-16T10:12:32.819Z" },
+    { url = "https://files.pythonhosted.org/packages/ae/b5/d58a241fbe324dbaeb8df07be6af8752c846192d78d2272e551098f74e88/pyarrow-23.0.1-cp314-cp314-macosx_12_0_x86_64.whl", hash = "sha256:fa8e51cb04b9f8c9c5ace6bab63af9a1f88d35c0d6cbf53e8c17c098552285e1", size = 35847826, upload-time = "2026-02-16T10:12:38.949Z" },
+    { url = "https://files.pythonhosted.org/packages/54/a5/8cbc83f04aba433ca7b331b38f39e000efd9f0c7ce47128670e737542996/pyarrow-23.0.1-cp314-cp314-manylinux_2_28_aarch64.whl", hash = "sha256:0b95a3994f015be13c63148fef8832e8a23938128c185ee951c98908a696e0eb", size = 44536859, upload-time = "2026-02-16T10:12:45.467Z" },
+    { url = "https://files.pythonhosted.org/packages/36/2e/c0f017c405fcdc252dbccafbe05e36b0d0eb1ea9a958f081e01c6972927f/pyarrow-23.0.1-cp314-cp314-manylinux_2_28_x86_64.whl", hash = "sha256:4982d71350b1a6e5cfe1af742c53dfb759b11ce14141870d05d9e540d13bc5d1", size = 47614443, upload-time = "2026-02-16T10:12:55.525Z" },
+    { url = "https://files.pythonhosted.org/packages/af/6b/2314a78057912f5627afa13ba43809d9d653e6630859618b0fd81a4e0759/pyarrow-23.0.1-cp314-cp314-musllinux_1_2_aarch64.whl", hash = "sha256:c250248f1fe266db627921c89b47b7c06fee0489ad95b04d50353537d74d6886", size = 48232991, upload-time = "2026-02-16T10:13:04.729Z" },
+    { url = "https://files.pythonhosted.org/packages/40/f2/1bcb1d3be3460832ef3370d621142216e15a2c7c62602a4ea19ec240dd64/pyarrow-23.0.1-cp314-cp314-musllinux_1_2_x86_64.whl", hash = "sha256:5f4763b83c11c16e5f4c15601ba6dfa849e20723b46aa2617cb4bffe8768479f", size = 50645077, upload-time = "2026-02-16T10:13:14.147Z" },
+    { url = "https://files.pythonhosted.org/packages/eb/3f/b1da7b61cd66566a4d4c8383d376c606d1c34a906c3f1cb35c479f59d1aa/pyarrow-23.0.1-cp314-cp314-win_amd64.whl", hash = "sha256:3a4c85ef66c134161987c17b147d6bffdca4566f9a4c1d81a0a01cdf08414ea5", size = 28234271, upload-time = "2026-02-16T10:14:09.397Z" },
+    { url = "https://files.pythonhosted.org/packages/b5/78/07f67434e910a0f7323269be7bfbf58699bd0c1d080b18a1ab49ba943fe8/pyarrow-23.0.1-cp314-cp314t-macosx_12_0_arm64.whl", hash = "sha256:17cd28e906c18af486a499422740298c52d7c6795344ea5002a7720b4eadf16d", size = 34488692, upload-time = "2026-02-16T10:13:21.541Z" },
+    { url = "https://files.pythonhosted.org/packages/50/76/34cf7ae93ece1f740a04910d9f7e80ba166b9b4ab9596a953e9e62b90fe1/pyarrow-23.0.1-cp314-cp314t-macosx_12_0_x86_64.whl", hash = "sha256:76e823d0e86b4fb5e1cf4a58d293036e678b5a4b03539be933d3b31f9406859f", size = 35964383, upload-time = "2026-02-16T10:13:28.63Z" },
+    { url = "https://files.pythonhosted.org/packages/46/90/459b827238936d4244214be7c684e1b366a63f8c78c380807ae25ed92199/pyarrow-23.0.1-cp314-cp314t-manylinux_2_28_aarch64.whl", hash = "sha256:a62e1899e3078bf65943078b3ad2a6ddcacf2373bc06379aac61b1e548a75814", size = 44538119, upload-time = "2026-02-16T10:13:35.506Z" },
+    { url = "https://files.pythonhosted.org/packages/28/a1/93a71ae5881e99d1f9de1d4554a87be37da11cd6b152239fb5bd924fdc64/pyarrow-23.0.1-cp314-cp314t-manylinux_2_28_x86_64.whl", hash = "sha256:df088e8f640c9fae3b1f495b3c64755c4e719091caf250f3a74d095ddf3c836d", size = 47571199, upload-time = "2026-02-16T10:13:42.504Z" },
+    { url = "https://files.pythonhosted.org/packages/88/a3/d2c462d4ef313521eaf2eff04d204ac60775263f1fb08c374b543f79f610/pyarrow-23.0.1-cp314-cp314t-musllinux_1_2_aarch64.whl", hash = "sha256:46718a220d64677c93bc243af1d44b55998255427588e400677d7192671845c7", size = 48259435, upload-time = "2026-02-16T10:13:49.226Z" },
+    { url = "https://files.pythonhosted.org/packages/cc/f1/11a544b8c3d38a759eb3fbb022039117fd633e9a7b19e4841cc3da091915/pyarrow-23.0.1-cp314-cp314t-musllinux_1_2_x86_64.whl", hash = "sha256:a09f3876e87f48bc2f13583ab551f0379e5dfb83210391e68ace404181a20690", size = 50629149, upload-time = "2026-02-16T10:13:57.238Z" },
+    { url = "https://files.pythonhosted.org/packages/50/f2/c0e76a0b451ffdf0cf788932e182758eb7558953f4f27f1aff8e2518b653/pyarrow-23.0.1-cp314-cp314t-win_amd64.whl", hash = "sha256:527e8d899f14bd15b740cd5a54ad56b7f98044955373a17179d5956ddb93d9ce", size = 28365807, upload-time = "2026-02-16T10:14:03.892Z" },
+]
+
 [[package]]
 name = "pycparser"
 version = "3.0"
--- a/web/pyproject.toml
+++ b/web/pyproject.toml
@@ -16,6 +16,7 @@ dependencies = [
    "resend>=2.22.0",
    "weasyprint>=68.1",
    "duckdb>=1.0.0",
+    "pyarrow>=23.0.1",
 ]

 [build-system]