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.

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

Add command line argument to control pandas.read_csv() na_filter option #45

Open
wants to merge 4 commits into
base: master
Choose a base branch
from
Open
Show file tree
Hide file tree
Changes from all commits
Commits
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
9 changes: 8 additions & 1 deletion csvs_to_sqlite/cli.py
Original file line number Diff line number Diff line change
Expand Up @@ -116,6 +116,12 @@
is_flag=True,
help="Skip adding full-text index on values extracted using --extract-column (default is to add them)",
)
@click.option(
"--no-na-filter",
"no_na_filter",
is_flag=True,
help="Skip detection of missing value markers (empty strings and the value of na_values). See pandas.read_csv() documentation",
)
@click.version_option()
def cli(
paths,
Expand All @@ -136,6 +142,7 @@ def cli(
filename_column,
no_index_fks,
no_fulltext_fks,
no_na_filter
):
"""
PATHS: paths to individual .csv files or to directories containing .csvs
Expand All @@ -162,7 +169,7 @@ def cli(
sql_type_overrides = None
for name, path in csvs.items():
try:
df = load_csv(path, separator, skip_errors, quoting, shape)
df = load_csv(path, separator, skip_errors, quoting, shape, no_na_filter)
df.table_name = table or name
if filename_column:
df[filename_column] = name
Expand Down
2 changes: 2 additions & 0 deletions csvs_to_sqlite/utils.py
Original file line number Diff line number Diff line change
Expand Up @@ -25,6 +25,7 @@ def load_csv(
skip_errors,
quoting,
shape,
no_na_filter,
encodings_to_try=("utf8", "latin-1"),
):
usecols = None
Expand All @@ -41,6 +42,7 @@ def load_csv(
low_memory=True,
encoding=encoding,
usecols=usecols,
na_filter=not no_na_filter
)
except UnicodeDecodeError:
continue
Expand Down