Support for hive partitioning about duckdb-r HOT 2 CLOSED

library("duckdb")
library("dplyr")
con <- dbConnect(duckdb())
duckdb_register(con, "flights", nycflights13::flights)

# Establish a set of Parquet files
dbExecute(con, "COPY flights TO 'dataset' (FORMAT PARQUET, PARTITION_BY (year, month))")

# Summarize the dataset in DuckDB to avoid reading 12 Parquet files into R's memory
tbl(con, "read_parquet('dataset/**/*.parquet', hive_partitioning = 1)") |>
  filter(month == "3") |>
  summarise(delay = mean(dep_time, na.rm = TRUE)) |>
  collect()