thisisnic

library(ellmer)

kendrick_wiki_text <- "Kendrick Lamar Duckworth (born June 17, 1987) is an American rapper, singer, songwriter, and record producer. Regarded as one of the greatest rappers of all time, he was awarded the 2018 Pulitzer Prize for Music, becoming the first musician outside of the classical and jazz genres to receive the award. Lamar's music, rooted in West Coast hip-hop, features conscious, introspective lyrics, with political criticism and social commentary concerning African-American culture."

hip_hop_theme <- type_enum(c("conscious_rap",  "party_anthems", "storytelling", "braggadocio", "love_relationships"))

artist_type <- type_object(
  name = type_string("Artist's full name"),
  birth_date = type_string("Birth date in YYYY-MM-DD format"),
  genre = type_string("Primary music genre"),

thisisnic

library(ellmer)

kendrick_wiki_text <- "Kendrick Lamar Duckworth (born June 17, 1987) is an American rapper, singer, songwriter, and record producer. Regarded as one of the greatest rappers of all time, he was awarded the 2018 Pulitzer Prize for Music, becoming the first musician outside of the classical and jazz genres to receive the award. Lamar's music, rooted in West Coast hip-hop, features conscious, introspective lyrics, with political criticism and social commentary concerning African-American culture."

artist_type <- type_object(
  name = type_string("Artist's full name"),
  birth_date = type_string("Birth date in YYYY-MM-DD format"),
  genre = type_string("Primary music genre"),
  themes = type_array(type_string("Musical themes"))
)

thisisnic

foo <- function() {
  
  time_limit <- 3
  
  setTimeLimit(cpu = time_limit, elapsed = time_limit, transient = TRUE)
  on.exit({
    setTimeLimit(cpu = Inf, elapsed = Inf, transient = FALSE)
  })
  
  tryCatch({

thisisnic

# Detect invalid timezones

all_names <- tzdb::tzdb_names()

bad_names <- c(
  all_names[startsWith(all_names, "US/")],
  all_names[!stringr::str_detect(all_names, "/")]
)

all_names[map_lgl(all_names, ~!.x %in% bad_names)]

thisisnic

library(arrow)
#> Some features are not enabled in this build of Arrow. Run `arrow_info()` for more information.
#> 
#> Attaching package: 'arrow'
#> The following object is masked from 'package:utils':
#> 
#>     timestamp
library(dplyr)
#> 

thisisnic

library(arrow)
#> Some features are not enabled in this build of Arrow. Run `arrow_info()` for more information.
#> 
#> Attaching package: 'arrow'
#> The following object is masked from 'package:utils':
#> 
#>     timestamp
library(dplyr)
#> 

thisisnic

``` r
library(arrow)
library(dplyr)
library(stringr)

tf <- tempfile()

# values to save - note the space after the final new line
dodgy_vals <- "x,y\n0,1\n ,4"
cat(dodgy_vals)

thisisnic

# query details copied from https://github.com/voltrondata-labs/arrowbench/blob/main/R/tpch-queries.R
query_results <- lineitem_db %>%
      select(l_shipdate, l_returnflag, l_linestatus, l_quantity,
           l_extendedprice, l_discount, l_tax) %>%
    # kludge, should be: filter(l_shipdate <= "1998-12-01" - interval x day) %>%
    # where x is between 60 and 120, 90 is the only one that will validate.
    filter(l_shipdate <= as.Date("1998-09-02")) %>%
    select(l_returnflag, l_linestatus, l_quantity, l_extendedprice, l_discount, l_tax) %>%
    group_by(l_returnflag, l_linestatus) %>%
    summarise(

thisisnic

---
title: "Apache Arrow R Questions on Stack Overflow"
format: html
---

```{r}
#| label: load-packages-and-code
#| include: false
library(httr)
library(dplyr)

thisisnic

#!/bin/bash
set -e

SOURCE_DIR='<path_to_project_root_goes_here>'

# Find all .R files which have been staged via git add
FILES_TO_STYLE=$(git diff --name-only --staged | grep "\.R")

for FILE in ${FILES_TO_STYLE[@]}
do