Nicola Crane created ARROW-17700:
------------------------------------
Summary: [R] Can't open CSV dataset with partitioning and a schema
Key: ARROW-17700
URL: https://issues.apache.org/jira/browse/ARROW-17700
Project: Apache Arrow
Issue Type: Bug
Components: R
Reporter: Nicola Crane
I feel like this might be a duplicate of a previous ticket, but can't find it.
{code:r}
``` r
library(dplyr)
#>
#> Attaching package: 'dplyr'
#> The following objects are masked from 'package:stats':
#>
#> filter, lag
#> The following objects are masked from 'package:base':
#>
#> intersect, setdiff, setequal, union
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
# all good!
tf <- tempfile()
dir.create(tf)
write_dataset(mtcars, tf, format = "csv")
open_dataset(tf, format = "csv") %>% collect()
#> # A tibble: 32 × 11
#> mpg cyl disp hp drat wt qsec vs am gear carb
#> <dbl> <int> <dbl> <int> <dbl> <dbl> <dbl> <int> <int> <int> <int>
#> 1 21 6 160 110 3.9 2.62 16.5 0 1 4 4
#> 2 21 6 160 110 3.9 2.88 17.0 0 1 4 4
#> 3 22.8 4 108 93 3.85 2.32 18.6 1 1 4 1
#> 4 21.4 6 258 110 3.08 3.22 19.4 1 0 3 1
#> 5 18.7 8 360 175 3.15 3.44 17.0 0 0 3 2
#> 6 18.1 6 225 105 2.76 3.46 20.2 1 0 3 1
#> 7 14.3 8 360 245 3.21 3.57 15.8 0 0 3 4
#> 8 24.4 4 147. 62 3.69 3.19 20 1 0 4 2
#> 9 22.8 4 141. 95 3.92 3.15 22.9 1 0 4 2
#> 10 19.2 6 168. 123 3.92 3.44 18.3 1 0 4 4
#> # … with 22 more rows
# all good
tf <- tempfile()
dir.create(tf)
write_dataset(group_by(mtcars, cyl), tf, format = "csv")
open_dataset(tf, format = "csv") %>% collect()
#> # A tibble: 32 × 11
#> mpg disp hp drat wt qsec vs am gear carb cyl
#> <dbl> <dbl> <int> <dbl> <dbl> <dbl> <int> <int> <int> <int> <int>
#> 1 22.8 108 93 3.85 2.32 18.6 1 1 4 1 4
#> 2 24.4 147. 62 3.69 3.19 20 1 0 4 2 4
#> 3 22.8 141. 95 3.92 3.15 22.9 1 0 4 2 4
#> 4 32.4 78.7 66 4.08 2.2 19.5 1 1 4 1 4
#> 5 30.4 75.7 52 4.93 1.62 18.5 1 1 4 2 4
#> 6 33.9 71.1 65 4.22 1.84 19.9 1 1 4 1 4
#> 7 21.5 120. 97 3.7 2.46 20.0 1 0 3 1 4
#> 8 27.3 79 66 4.08 1.94 18.9 1 1 4 1 4
#> 9 26 120. 91 4.43 2.14 16.7 0 1 5 2 4
#> 10 30.4 95.1 113 3.77 1.51 16.9 1 1 5 2 4
#> # … with 22 more rows
list.files(tf)
#> [1] "cyl=4" "cyl=6" "cyl=8"
# hive-style=FALSE leads to no `cyl` column, which, sure, makes sense
tf <- tempfile()
dir.create(tf)
write_dataset(group_by(mtcars, cyl), tf, format = "csv", hive_style = FALSE)
open_dataset(tf, format = "csv") %>% collect()
#> # A tibble: 32 × 10
#> mpg disp hp drat wt qsec vs am gear carb
#> <dbl> <dbl> <int> <dbl> <dbl> <dbl> <int> <int> <int> <int>
#> 1 22.8 108 93 3.85 2.32 18.6 1 1 4 1
#> 2 24.4 147. 62 3.69 3.19 20 1 0 4 2
#> 3 22.8 141. 95 3.92 3.15 22.9 1 0 4 2
#> 4 32.4 78.7 66 4.08 2.2 19.5 1 1 4 1
#> 5 30.4 75.7 52 4.93 1.62 18.5 1 1 4 2
#> 6 33.9 71.1 65 4.22 1.84 19.9 1 1 4 1
#> 7 21.5 120. 97 3.7 2.46 20.0 1 0 3 1
#> 8 27.3 79 66 4.08 1.94 18.9 1 1 4 1
#> 9 26 120. 91 4.43 2.14 16.7 0 1 5 2
#> 10 30.4 95.1 113 3.77 1.51 16.9 1 1 5 2
#> # … with 22 more rows
list.files(tf)
#> [1] "4" "6" "8"
# *but* if we try to add it in via a schema, it doesn't work
desired_schema <- schema(mpg = float64(), disp = float64(), hp = int64(), drat
= float64(),
wt = float64(), qsec = float64(), vs = int64(), am = int64(),
gear = int64(), carb = int64(), cyl = int64())
tf <- tempfile()
dir.create(tf)
write_dataset(group_by(mtcars, cyl), tf, format = "csv", hive_style = FALSE)
open_dataset(tf, format = "csv", schema = desired_schema) %>% collect()
#> Error in `dplyr::collect()`:
#> ! Invalid: Could not open CSV input source
'/tmp/RtmpnInOwc/file13f0d38c5b994/4/part-0.csv': Invalid: CSV parse error: Row
#1: Expected 11 columns, got 10:
"mpg","disp","hp","drat","wt","qsec","vs","am","gear","carb"
#> /home/nic2/arrow/cpp/src/arrow/csv/parser.cc:477
(ParseLine<SpecializedOptions, false>(values_writer, parsed_writer, data,
data_end, is_final, &line_end, bulk_filter))
#> /home/nic2/arrow/cpp/src/arrow/csv/parser.cc:566
ParseChunk<SpecializedOptions>( &values_writer, &parsed_writer, data, data_end,
is_final, rows_in_chunk, &data, &finished_parsing, bulk_filter)
#> /home/nic2/arrow/cpp/src/arrow/csv/reader.cc:426 parser->ParseFinal(views,
&parsed_size)
#> /home/nic2/arrow/cpp/src/arrow/compute/exec/exec_plan.cc:573
iterator_.Next()
#> /home/nic2/arrow/cpp/src/arrow/record_batch.cc:337 ReadNext(&batch)
#> /home/nic2/arrow/cpp/src/arrow/record_batch.cc:351 ToRecordBatches()
list.files(tf)
#> [1] "4" "6" "8"
```
<sup>Created on 2022-09-13 by the [reprex
package](https://reprex.tidyverse.org) (v2.0.1)</sup>
{code}
--
This message was sent by Atlassian Jira
(v8.20.10#820010)
