Skip to content

fix: make csv-read-options.py example self-contained (#1728) #1729

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

Open
dedsec-terminal wants to merge 3 commits into
base: main
Choose a base branch
from
+94 −68
Open

fix: make csv-read-options.py example self-contained (#1728) #1729

Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
f1e9c37
fix: make csv-read-options.py example self-contained with temporary f…
dedsec-terminal Sep 11, 2026
20ab8fa
chore(examples): add df.show() to execute Example 3 in csv-read-optio…
dedsec-terminal Sep 11, 2026
c0452ed
fix(examples): match builder fixture delimiter
dedsec-terminal Sep 11, 2026
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
162 changes: 94 additions & 68 deletions examples/csv-read-options.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -17,80 +17,106 @@

"""Example demonstrating CsvReadOptions usage."""

import gzip
import tempfile
from pathlib import Path

from datafusion import CsvReadOptions, SessionContext

# Create a SessionContext
ctx = SessionContext()
# Create sample data files in a temporary directory to make the example self-contained
with tempfile.TemporaryDirectory() as tmp_dir:
tmp_path = Path(tmp_dir)
csv_file = tmp_path / "data.csv"
gz_file = tmp_path / "data.csv.gz"
builder_csv_file = tmp_path / "builder-data.csv"

sample_csv = "id,name,value\n1,alice,100\n2,bob,200\n3,charlie,null\n"
csv_file.write_text(sample_csv)

builder_csv = "id|name|value\n1|'alice'|100\n2|'bob'|200\n3|'charlie'|null\n"
builder_csv_file.write_text(builder_csv)

with gzip.open(gz_file, "wt") as f:
f.write(sample_csv)

# Create a SessionContext
ctx = SessionContext()

# Example 1: Using CsvReadOptions with default values
print("Example 1: Default CsvReadOptions")
options = CsvReadOptions()
df = ctx.read_csv("data.csv", options=options)
# Example 1: Using CsvReadOptions with default values
print("Example 1: Default CsvReadOptions")
options = CsvReadOptions()
df = ctx.read_csv(str(csv_file), options=options)
df.show()

# Example 2: Using CsvReadOptions with custom parameters
print("\nExample 2: Custom CsvReadOptions")
options = CsvReadOptions(
has_header=True,
delimiter=",",
quote='"',
schema_infer_max_records=1000,
file_extension=".csv",
)
df = ctx.read_csv("data.csv", options=options)
# Example 2: Using CsvReadOptions with custom parameters
print("\nExample 2: Custom CsvReadOptions")
options = CsvReadOptions(
has_header=True,
delimiter=",",
quote='"',
schema_infer_max_records=1000,
file_extension=".csv",
)
df = ctx.read_csv(str(csv_file), options=options)
df.show()

# Example 3: Using the builder pattern (recommended for readability)
print("\nExample 3: Builder pattern")
options = (
CsvReadOptions()
.with_has_header(True) # noqa: FBT003
.with_delimiter("|")
.with_quote("'")
.with_schema_infer_max_records(500)
.with_truncated_rows(False) # noqa: FBT003
.with_newlines_in_values(True) # noqa: FBT003
)
df = ctx.read_csv("data.csv", options=options)
# Example 3: Using the builder pattern (recommended for readability)
print("\nExample 3: Builder pattern")
options = (
CsvReadOptions()
.with_has_header(True) # noqa: FBT003
.with_delimiter("|")
.with_quote("'")
.with_schema_infer_max_records(500)
.with_truncated_rows(False) # noqa: FBT003
.with_newlines_in_values(True) # noqa: FBT003
)
df = ctx.read_csv(str(builder_csv_file), options=options)
df.show()

# Example 4: Advanced options
print("\nExample 4: Advanced options")
options = (
CsvReadOptions()
.with_has_header(True) # noqa: FBT003
.with_delimiter(",")
.with_comment("#") # Skip lines starting with #
.with_escape("\\") # Escape character
.with_null_regex(r"^(null|NULL|N/A)$") # Treat these as NULL
.with_truncated_rows(True) # noqa: FBT003
.with_file_compression_type("gzip") # Read gzipped CSV
.with_file_extension(".gz")
)
df = ctx.read_csv("data.csv.gz", options=options)
# Example 4: Advanced options
print("\nExample 4: Advanced options")
options = (
CsvReadOptions()
.with_has_header(True) # noqa: FBT003
.with_delimiter(",")
.with_comment("#") # Skip lines starting with #
.with_escape("\\") # Escape character
.with_null_regex(r"^(null|NULL|N/A)$") # Treat these as NULL
.with_truncated_rows(True) # noqa: FBT003
.with_file_compression_type("gzip") # Read gzipped CSV
.with_file_extension(".gz")
)
df = ctx.read_csv(str(gz_file), options=options)
df.show()

# Example 5: Register CSV table with options
print("\nExample 5: Register CSV table")
options = CsvReadOptions().with_has_header(True).with_delimiter(",") # noqa: FBT003
ctx.register_csv("my_table", "data.csv", options=options)
df = ctx.sql("SELECT * FROM my_table")
# Example 5: Register CSV table with options
print("\nExample 5: Register CSV table")
options = CsvReadOptions().with_has_header(True).with_delimiter(",") # noqa: FBT003
ctx.register_csv("my_table", str(csv_file), options=options)
df = ctx.sql("SELECT * FROM my_table")
df.show()

# Example 6: Backward compatibility (without options)
print("\nExample 6: Backward compatibility")
# Still works the old way!
df = ctx.read_csv("data.csv", has_header=True, delimiter=",")
# Example 6: Backward compatibility (without options)
print("\nExample 6: Backward compatibility")
# Still works the old way!
df = ctx.read_csv(str(csv_file), has_header=True, delimiter=",")
df.show()

print("\nAll examples completed!")
print("\nFor all available options, see the CsvReadOptions documentation:")
print(" - has_header: bool")
print(" - delimiter: str")
print(" - quote: str")
print(" - terminator: str | None")
print(" - escape: str | None")
print(" - comment: str | None")
print(" - newlines_in_values: bool")
print(" - schema: pa.Schema | None")
print(" - schema_infer_max_records: int")
print(" - file_extension: str")
print(" - table_partition_cols: list[tuple[str, pa.DataType]]")
print(" - file_compression_type: str")
print(" - file_sort_order: list[list[SortExpr]]")
print(" - null_regex: str | None")
print(" - truncated_rows: bool")
print("\nAll examples completed!")
print("\nFor all available options, see the CsvReadOptions documentation:")
print(" - has_header: bool")
print(" - delimiter: str")
print(" - quote: str")
print(" - terminator: str | None")
print(" - escape: str | None")
print(" - comment: str | None")
print(" - newlines_in_values: bool")
print(" - schema: pa.Schema | None")
print(" - schema_infer_max_records: int")
print(" - file_extension: str")
print(" - table_partition_cols: list[tuple[str, pa.DataType]]")
print(" - file_compression_type: str")
print(" - file_sort_order: list[list[SortExpr]]")
print(" - null_regex: str | None")
print(" - truncated_rows: bool")