From 90ab61bbfd67522529235583bec09ce0f4eec4f7 Mon Sep 17 00:00:00 2001
From: dazzag24 <dazzag@gmail.com>
Date: Tue, 8 Jan 2019 19:25:13 +0000
Subject: [PATCH 1/3] Add na_filter=False to read_csv()

---
 csvs_to_sqlite/utils.py | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/csvs_to_sqlite/utils.py b/csvs_to_sqlite/utils.py
index 720268d..f3b4fc7 100644
--- a/csvs_to_sqlite/utils.py
+++ b/csvs_to_sqlite/utils.py
@@ -24,7 +24,7 @@ def load_csv(filepath, separator, skip_errors, quoting, shape, encodings_to_try=
                 return pd.read_csv(
                     filepath, sep=separator, quoting=quoting,
                     error_bad_lines=not skip_errors, low_memory=True,
-                    encoding=encoding, usecols=usecols
+                    encoding=encoding, usecols=usecols, na_filter=False
                 )
             except UnicodeDecodeError:
                 continue

From a2535ee371dfb93018cd290b92b6b0eef81f59e8 Mon Sep 17 00:00:00 2001
From: DazzaG <dazzag@gmail.com>
Date: Fri, 18 Jan 2019 10:25:47 +0000
Subject: [PATCH 2/3] Add cli option to control na_filter in pandas.read_csv()

---
 csvs_to_sqlite/cli.py   | 10 +++++++++-
 csvs_to_sqlite/utils.py |  3 ++-
 2 files changed, 11 insertions(+), 2 deletions(-)

diff --git a/csvs_to_sqlite/cli.py b/csvs_to_sqlite/cli.py
index 5cca320..a777e77 100644
--- a/csvs_to_sqlite/cli.py
+++ b/csvs_to_sqlite/cli.py
@@ -116,6 +116,13 @@
     is_flag=True,
     help="Skip adding full-text index on values extracted using --extract-column (default is to add them)",
 )
+@click.option(
+    "--na-filter",
+    "na_filter",
+    is_flag=True,
+    default=True,
+    help="Detect missing value markers (empty strings and the value of na_values). See pandas.read_csv() documentation",
+)
 @click.version_option()
 def cli(
     paths,
@@ -136,6 +143,7 @@ def cli(
     filename_column,
     no_index_fks,
     no_fulltext_fks,
+    na_filter
 ):
     """
     PATHS: paths to individual .csv files or to directories containing .csvs
@@ -162,7 +170,7 @@ 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, na_filter)
             df.table_name = table or name
             if filename_column:
                 df[filename_column] = name
diff --git a/csvs_to_sqlite/utils.py b/csvs_to_sqlite/utils.py
index dd03383..3d99659 100644
--- a/csvs_to_sqlite/utils.py
+++ b/csvs_to_sqlite/utils.py
@@ -25,6 +25,7 @@ def load_csv(
     skip_errors,
     quoting,
     shape,
+    na_filter,
     encodings_to_try=("utf8", "latin-1"),
 ):
     usecols = None
@@ -41,7 +42,7 @@ def load_csv(
                     low_memory=True,
                     encoding=encoding,
                     usecols=usecols,
-                    na_filter=False
+                    na_filter=na_filter
                 )
             except UnicodeDecodeError:
                 continue

From c40c2c45d7aa31a8e00b220384bc46995199f14a Mon Sep 17 00:00:00 2001
From: DazzaG <dazzag@gmail.com>
Date: Fri, 18 Jan 2019 11:05:21 +0000
Subject: [PATCH 3/3] Corrected implemntation of command line flags

---
 csvs_to_sqlite/cli.py   | 11 +++++------
 csvs_to_sqlite/utils.py |  4 ++--
 2 files changed, 7 insertions(+), 8 deletions(-)

diff --git a/csvs_to_sqlite/cli.py b/csvs_to_sqlite/cli.py
index a777e77..259b288 100644
--- a/csvs_to_sqlite/cli.py
+++ b/csvs_to_sqlite/cli.py
@@ -117,11 +117,10 @@
     help="Skip adding full-text index on values extracted using --extract-column (default is to add them)",
 )
 @click.option(
-    "--na-filter",
-    "na_filter",
+    "--no-na-filter",
+    "no_na_filter",
     is_flag=True,
-    default=True,
-    help="Detect missing value markers (empty strings and the value of na_values). See pandas.read_csv() documentation",
+    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(
@@ -143,7 +142,7 @@ def cli(
     filename_column,
     no_index_fks,
     no_fulltext_fks,
-    na_filter
+    no_na_filter
 ):
     """
     PATHS: paths to individual .csv files or to directories containing .csvs
@@ -170,7 +169,7 @@ def cli(
     sql_type_overrides = None
     for name, path in csvs.items():
         try:
-            df = load_csv(path, separator, skip_errors, quoting, shape, na_filter)
+            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
diff --git a/csvs_to_sqlite/utils.py b/csvs_to_sqlite/utils.py
index 3d99659..bfa13e8 100644
--- a/csvs_to_sqlite/utils.py
+++ b/csvs_to_sqlite/utils.py
@@ -25,7 +25,7 @@ def load_csv(
     skip_errors,
     quoting,
     shape,
-    na_filter,
+    no_na_filter,
     encodings_to_try=("utf8", "latin-1"),
 ):
     usecols = None
@@ -42,7 +42,7 @@ def load_csv(
                     low_memory=True,
                     encoding=encoding,
                     usecols=usecols,
-                    na_filter=na_filter
+                    na_filter=not no_na_filter
                 )
             except UnicodeDecodeError:
                 continue