backend redesign

iceberg/ohlc_schema.sql

@@ -0,0 +1,53 @@
+-- Iceberg OHLC Table Schema (Iceberg 1.10.1)
+-- Single table for all periods with hidden partitioning
+-- Natural key: (ticker, period_seconds, timestamp) - enforced by application logic
+-- Partition by: (ticker, days(timestamp)) - hidden partitioning for efficiency
+
+CREATE TABLE IF NOT EXISTS trading.ohlc (
+  -- Natural key fields (uniqueness enforced by Flink upsert logic)
+  ticker STRING NOT NULL COMMENT 'Market identifier (e.g., BINANCE:BTC/USDT)',
+  period_seconds INT NOT NULL COMMENT 'OHLC period in seconds (60, 300, 900, 3600, 14400, 86400, 604800, etc.)',
+  timestamp BIGINT NOT NULL COMMENT 'Candle timestamp in microseconds since epoch',
+
+  -- OHLC price data (stored as integers, divide by rational denominator from market metadata)
+  open BIGINT NOT NULL COMMENT 'Opening price',
+  high BIGINT NOT NULL COMMENT 'Highest price',
+  low BIGINT NOT NULL COMMENT 'Lowest price',
+  close BIGINT NOT NULL COMMENT 'Closing price',
+
+  -- Volume data
+  volume BIGINT COMMENT 'Total volume',
+  buy_vol BIGINT COMMENT 'Buy volume',
+  sell_vol BIGINT COMMENT 'Sell volume',
+
+  -- Timing data
+  open_time BIGINT COMMENT 'Timestamp when open price occurred',
+  high_time BIGINT COMMENT 'Timestamp when high price occurred',
+  low_time BIGINT COMMENT 'Timestamp when low price occurred',
+  close_time BIGINT COMMENT 'Timestamp when close time occurred',
+
+  -- Additional fields
+  open_interest BIGINT COMMENT 'Open interest for futures',
+
+  -- Metadata fields for tracking
+  request_id STRING COMMENT 'Request ID that generated this data (for historical requests)',
+  ingested_at BIGINT NOT NULL COMMENT 'Timestamp when data was ingested by Flink'
+)
+USING iceberg
+PARTITIONED BY (ticker)
+TBLPROPERTIES (
+  'write.format.default' = 'parquet',
+  'write.parquet.compression-codec' = 'snappy',
+  'write.metadata.compression-codec' = 'gzip',
+  'format-version' = '1',
+  'write.merge.mode' = 'copy-on-write'
+);
+
+-- Note: Iceberg 1.x does not support primary key constraints
+-- Uniqueness of (ticker, period_seconds, timestamp) is enforced at application layer:
+-- - Flink Iceberg sink uses equality delete files for upsert behavior
+-- - Last-write-wins semantics for duplicate rows
+-- - Copy-on-write mode rewrites data files on updates
+-- - Queries automatically filter deleted rows
+
+COMMENT ON TABLE trading.ohlc IS 'Historical OHLC candle data from exchanges. Single table for all periods. Uniqueness enforced by Flink upsert mode with equality deletes.';