Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

fix: pass quote parameter to CSV writer #10671

Merged
merged 1 commit into from
May 26, 2024
Merged

fix: pass quote parameter to CSV writer #10671

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
1 change: 1 addition & 0 deletions datafusion/common/src/file_options/csv_writer.rs
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -51,6 +51,7 @@ impl TryFrom<&CsvOptions> for CsvWriterOptions {
fn try_from(value: &CsvOptions) -> Result<Self> {
let mut builder = WriterBuilder::default()
.with_header(value.has_header.unwrap_or(false))
.with_quote(value.quote)
.with_delimiter(value.delimiter);

if let Some(v) = &value.date_format {
Expand Down
41 changes: 41 additions & 0 deletions datafusion/sqllogictest/test_files/csv_files.slt
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -161,3 +161,44 @@ physical_plan
01)SortPreservingMergeExec: [int_col@0 ASC NULLS LAST]
02)--SortExec: expr=[int_col@0 ASC NULLS LAST], preserve_partitioning=[true]
03)----CsvExec: file_groups={2 groups: [[WORKSPACE_ROOT/datafusion/sqllogictest/test_files/scratch/csv_files/csv_partitions/1.csv], [WORKSPACE_ROOT/datafusion/sqllogictest/test_files/scratch/csv_files/csv_partitions/2.csv]]}, projection=[int_col, string_col, bigint_col, partition_col], has_header=false


# ensure that correct quote character is used when writing to csv
statement ok
CREATE TABLE table_with_necessary_quoting (
int_col INT,
string_col TEXT,
) AS VALUES
(1, 'e|e|e'),
(2, 'f|f|f'),
(3, 'g|g|g'),
(4, 'h|h|h');

# quote is required because `|` is delimiter and part of the data
Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

I double checked the contents of the file look good

andrewlamb@Andrews-MacBook-Pro-2:~/Software/datafusion$ cat ./datafusion/sqllogictest/test_files/scratch/csv_files/table_with_necessary_quoting.csv
int_col|string_col
1|~e|e|e~
2|~f|f|f~
3|~g|g|g~
4|~h|h|h~

query IT
COPY table_with_necessary_quoting TO 'test_files/scratch/csv_files/table_with_necessary_quoting.csv'
STORED AS csv
OPTIONS ('format.quote' '~',
'format.delimiter' '|',
'format.has_header' 'true');
----
4

# read the stored csv file with quote character
statement ok
CREATE EXTERNAL TABLE stored_table_with_necessary_quoting (
c1 VARCHAR,
c2 VARCHAR
) STORED AS CSV
LOCATION 'test_files/scratch/csv_files/table_with_necessary_quoting.csv'
OPTIONS ('format.quote' '~',
'format.delimiter' '|',
'format.has_header' 'true');

query TT
select * from stored_table_with_necessary_quoting;
----
1 e|e|e
2 f|f|f
3 g|g|g
4 h|h|h