Skip to content

fix: return an error for an invalid CSV null_regex instead of panicking #25261

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

Merged
Jefffrey merged 1 commit into from
Sep 15, 2026
+27 −6
Merged

fix: return an error for an invalid CSV null_regex instead of panicking #25261

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
25 changes: 19 additions & 6 deletions datafusion/datasource-csv/src/file_format.rs
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -30,8 +30,8 @@ use arrow::error::ArrowError;
use datafusion_common::config::{ConfigField, ConfigFileType, CsvOptions};
use datafusion_common::file_options::csv_writer::CsvWriterOptions;
use datafusion_common::{
DEFAULT_CSV_EXTENSION, DataFusionError, GetExt, Result, Statistics, exec_err,
not_impl_err,
DEFAULT_CSV_EXTENSION, DataFusionError, GetExt, Result, Statistics,
exec_datafusion_err, exec_err, not_impl_err,
};
use datafusion_common_runtime::SpawnedTask;
use datafusion_datasource::TableSchema;
Expand Down Expand Up @@ -540,6 +540,21 @@ impl CsvFormat {
let mut record_number = -1;
let initial_records_to_read = records_to_read;

// Compile once rather than per chunk, and report a malformed pattern
// instead of panicking on it.
let null_regex = self
.options
.null_regex
.as_ref()
.map(|null_regex| {
Regex::new(null_regex).map_err(|e| {
exec_datafusion_err!(
"Unable to parse CSV null regex '{null_regex}': {e}"
)
})
})
.transpose()?;

pin_mut!(stream);

while let Some(chunk) = stream.next().await.transpose()? {
Expand All @@ -557,10 +572,8 @@ impl CsvFormat {
.with_quote(self.options.quote)
.with_truncated_rows(self.options.truncated_rows.unwrap_or(false));

if let Some(null_regex) = &self.options.null_regex {
let regex = Regex::new(null_regex.as_str())
.expect("Unable to parse CSV null regex.");
format = format.with_null_regex(regex);
if let Some(regex) = &null_regex {
format = format.with_null_regex(regex.clone());
}

if let Some(escape) = self.options.escape {
Expand Down
8 changes: 8 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 @@ -22,6 +22,14 @@ STORED AS CSV
LOCATION '../core/tests/data/duplicate_header.csv'
OPTIONS ('format.has_header' 'true');

# A malformed null_regex is reported as an error rather than panicking the
# query. Schema inference compiles the pattern, so CREATE is where it surfaces.
statement error Unable to parse CSV null regex
CREATE EXTERNAL TABLE csv_with_invalid_null_regex
STORED AS CSV
LOCATION '../core/tests/data/quote.csv'
OPTIONS ('format.has_header' 'true', 'format.null_regex' '(');

# create_external_table_with_quote_escape
statement ok
CREATE EXTERNAL TABLE csv_with_quote (
Expand Down