should be it

2025-10-24 19:21:19 -05:00
parent a4b23fc57c
commit f09560c7b1
14047 changed files with 3161551 additions and 1 deletions
--- a/external/duckdb/test/sql/copy/copy_blob.test
+++ b/external/duckdb/test/sql/copy/copy_blob.test
@@ -0,0 +1,45 @@
+# name: test/sql/copy/copy_blob.test
+# group: [copy]
+
+statement error
+COPY (select 'foo') TO '__TEST_DIR__/test.blob' (FORMAT BLOB);
+----
+Binder Error: "COPY (FORMAT BLOB)" only supports a single BLOB column
+
+statement error
+COPY (select 'foo'::BLOB, 10) TO '__TEST_DIR__/test.blob' (FORMAT BLOB);
+----
+Binder Error: "COPY (FORMAT BLOB)" only supports a single BLOB column
+
+
+statement ok
+COPY (select 'foo'::BLOB) TO '__TEST_DIR__/test.blob' (FORMAT BLOB);
+
+query III
+select filename LIKE '%test.blob', content, size from read_blob('__TEST_DIR__/test.blob');
+----
+true	foo	3
+
+
+statement error
+COPY (select 'foo'::BLOB) TO '__TEST_DIR__/test.blob.gz' (FORMAT BLOB, ASDFGH);
+----
+Binder Error: Unrecognized option for COPY (FORMAT BLOB): "ASDFGH"
+
+# With compression
+statement ok
+COPY (select 'foo'::BLOB) TO '__TEST_DIR__/test.blob.gz' (FORMAT BLOB);
+
+query II
+select filename LIKE '%test.blob.gz', size from read_blob('__TEST_DIR__/test.blob.gz');
+----
+true	26
+
+# With explicit compression
+statement ok
+COPY (select 'foo'::BLOB) TO '__TEST_DIR__/test2.blob' (FORMAT BLOB, COMPRESSION 'GZIP');
+
+query II
+select filename LIKE '%test2.blob', size from read_blob('__TEST_DIR__/test2.blob');
+----
+true	26
--- a/external/duckdb/test/sql/copy/csv/14512.test
+++ b/external/duckdb/test/sql/copy/csv/14512.test
@@ -0,0 +1,28 @@
+# name: test/sql/copy/csv/14512.test
+# description: Test for issue #14512
+# group: [csv]
+
+statement ok
+PRAGMA enable_verification
+
+query II
+FROM read_csv('data/csv/14512.csv', strict_mode=TRUE);
+----
+onions	,
+
+query I
+select columns FROM sniff_csv('data/csv/14512.csv')
+----
+[{'name': ingredients, 'type': VARCHAR}, {'name': item_tax_data, 'type': VARCHAR}]
+
+query IIIIIIIIIIIIIIIIIIIIIIIIII
+FROM read_csv('data/csv/14512_og.csv', strict_mode = false, delim = ',', quote = '"', escape = '"');
+----
+00000579000098	13.99	EA	PINE RIDGE CHENIN VOIGNIER	750.0	ML	1	13	NULL	1	NULL	NULL	NULL	NULL	NULL	NULL	DEFAULT BRAND	NULL	NULL	NULL	NULL	BEER & WINE	NULL	NULL	7.25	{"sales_tax":{ "tax_type": "rate_percent", "value" :0.0725}}
+00000609082001	3.99	EA	MADELAINE MINI MILK CHOCOLATE TURKEY	1.0	OZ	1	13	NULL	NULL	NULL	NULL	NULL	NULL	NULL	NULL	MADELEINE	NULL	NULL	NULL	NULL	CANDY	NULL	NULL	7.25	{"sales_tax":{ "tax_type": "rate_percent", "value" :0.0725}}
+00817566020096	9.99	EA	COTSWOLD EW	5.3	OZ	1	13	NULL	NULL	NULL	NULL	NULL	NULL	NULL	NULL	LONG CLAWSON	NULL	NULL	NULL	NULL	DELI	INGREDIENTS: DOUBLE GLOUCESTER CHEESE (PASTEURIZED MILK  SALT  ENZYMES  DAIRY CULTURES  ANNATTO  EXTRACT AS A COLOR)  RECONSTITUTED MINCED ONIONS (2%)  DRIED CHIVES. CONTAINS: MILK     THIS PRODUCT WAS PRODUCED IN AN ENVIRONMENT THAT ALSO USES PEANUTS  TREE NUTS  EGGS  MILK  WHEAT  SOY  FISH  SHELLFISH  AND SESAME.	NULL	2.0	{"sales_tax":{ "tax_type": "rate_percent", "value" :0.02}}
+
+query I
+select columns FROM sniff_csv('data/csv/14512_og.csv', strict_mode = false, delim = ',', quote = '"', escape = '"')
+----
+[{'name': lookup_code, 'type': VARCHAR}, {'name': price, 'type': DOUBLE}, {'name': cost_unit, 'type': VARCHAR}, {'name': item_name, 'type': VARCHAR}, {'name': size, 'type': DOUBLE}, {'name': size_uom, 'type': VARCHAR}, {'name': available, 'type': BIGINT}, {'name': store_code, 'type': BIGINT}, {'name': private_label_item, 'type': VARCHAR}, {'name': alcoholic, 'type': BIGINT}, {'name': alcohol_by_volume, 'type': VARCHAR}, {'name': alcohol_type, 'type': VARCHAR}, {'name': nutri_info, 'type': VARCHAR}, {'name': allergens, 'type': VARCHAR}, {'name': balance_on_hand, 'type': VARCHAR}, {'name': blackout_times, 'type': VARCHAR}, {'name': brand_name, 'type': VARCHAR}, {'name': ca_prop65_text, 'type': VARCHAR}, {'name': ca_prop65_codes, 'type': VARCHAR}, {'name': configurable_products, 'type': VARCHAR}, {'name': country_of_origin, 'type': VARCHAR}, {'name': department, 'type': VARCHAR}, {'name': ingredients, 'type': VARCHAR}, {'name': item_details, 'type': VARCHAR}, {'name': tax_rate, 'type': DOUBLE}, {'name': item_tax_data, 'type': VARCHAR}]
--- a/external/duckdb/test/sql/copy/csv/14874.test
+++ b/external/duckdb/test/sql/copy/csv/14874.test
@@ -0,0 +1,22 @@
+# name: test/sql/copy/csv/14874.test
+# description: Test for issue #14784
+# group: [csv]
+
+mode skip
+
+statement ok
+PRAGMA enable_verification
+
+query I
+SELECT count(*) FROM read_csv('data/csv/drug_exposure.csv');
+----
+4113
+
+query IIIIIIIIIIIIIIIIIIIIIII
+SELECT * FROM read_csv('data/csv/drug_exposure.csv') ORDER BY ALL limit 5;
+----
+-9223335764168194396	1532249960797525190	43613338	2166-08-24	2166-08-24 08:00:00	2166-08-24	2166-08-24 23:00:00	NULL	32838	NULL	NULL	200.0	NULL	NULL	4171047	NULL	NULL	-8938795529793370194	NULL	SW 100ml Bag	2000011398	IV	mL
+-9212518512714808847	1484542834460282651	19008723	2161-11-16	2161-11-16 08:00:00	2161-11-19	2161-11-19 10:00:00	NULL	32838	NULL	NULL	0.1	NULL	NULL	4262914	NULL	NULL	2567137523204385703	NULL	45802011222	45085123	NU	TUBE
+-9206751087952985587	-9066461348710750663	35603224	2185-01-20	2185-01-20 19:00:00	2185-01-21	2185-01-21 18:00:00	NULL	32838	NULL	NULL	0.6	NULL	NULL	4171047	NULL	NULL	-7972824337100083284	NULL	00409610210	45044941	IV	VIAL
+-9204709101307434434	-6225647829918357531	35603227	2153-04-04	2153-04-04 11:00:00	2153-04-05	2153-04-05 10:00:00	NULL	32838	NULL	NULL	1.0	NULL	NULL	4171047	NULL	NULL	2405647860386309016	NULL	00409610204	45283861	IV	VIAL
+-9201491012041940131	-3780452582396805474	36249734	2115-12-29	2115-12-29 05:00:00	2115-12-31	2115-12-31 07:00:00	NULL	32838	NULL	NULL	500.0	NULL	NULL	4171047	NULL	NULL	1384337365755163052	NULL	00338001703	45214979	IV	mL
--- a/external/duckdb/test/sql/copy/csv/17738.test
+++ b/external/duckdb/test/sql/copy/csv/17738.test
@@ -0,0 +1,58 @@
+# name: test/sql/copy/csv/17738.test
+# description: Test for issue #17738
+# group: [csv]
+
+statement ok
+PRAGMA enable_verification
+
+query I
+FROM read_csv('data/csv/17738_rn.csv',header=False,skip=3, delim = ';');
+----
+xyz
+lorem ipsum
+NULL
+NULL
+John,Doe,120 jefferson st.,Riverside, NJ, 08075
+Jack,McGinnis,220 hobo Av.,Phila, PA,09119
+"John ""Da Man""",Repici,120 Jefferson St.,Riverside, NJ,08075
+Stephen,Tyler,"7452 Terrace ""At the Plaza"" road",SomeTown,SD, 91234
+,Blankman,,SomeTown, SD, 00298
+"Joan ""the bone"", Anne",Jet,"9th, at Terrace plc",Desert City,CO,00123
+
+
+query I
+FROM read_csv('data/csv/17738.csv',header=False,skip=3);
+----
+xyz
+lorem ipsum
+NULL
+NULL
+John,Doe,120 jefferson st.,Riverside, NJ, 08075
+Jack,McGinnis,220 hobo Av.,Phila, PA,09119
+"John ""Da Man""",Repici,120 Jefferson St.,Riverside, NJ,08075
+Stephen,Tyler,"7452 Terrace ""At the Plaza"" road",SomeTown,SD, 91234
+,Blankman,,SomeTown, SD, 00298
+"Joan ""the bone"", Anne",Jet,"9th, at Terrace plc",Desert City,CO,00123
+
+query I
+FROM read_csv('data/csv/17738.csv',header=False,skip=4);
+----
+lorem ipsum
+NULL
+NULL
+John,Doe,120 jefferson st.,Riverside, NJ, 08075
+Jack,McGinnis,220 hobo Av.,Phila, PA,09119
+"John ""Da Man""",Repici,120 Jefferson St.,Riverside, NJ,08075
+Stephen,Tyler,"7452 Terrace ""At the Plaza"" road",SomeTown,SD, 91234
+,Blankman,,SomeTown, SD, 00298
+"Joan ""the bone"", Anne",Jet,"9th, at Terrace plc",Desert City,CO,00123
+
+query IIIIII
+FROM read_csv('data/csv/17738.csv',header=False,skip=7);
+----
+John	Doe	120 jefferson st.	Riverside	 NJ	 08075
+Jack	McGinnis	220 hobo Av.	Phila	 PA	09119
+John "Da Man"	Repici	120 Jefferson St.	Riverside	 NJ	08075
+Stephen	Tyler	7452 Terrace "At the Plaza" road	SomeTown	SD	 91234
+NULL	Blankman	NULL	SomeTown	 SD	 00298
+Joan "the bone", Anne	Jet	9th, at Terrace plc	Desert City	CO	00123
--- a/external/duckdb/test/sql/copy/csv/17744.test
+++ b/external/duckdb/test/sql/copy/csv/17744.test
@@ -0,0 +1,70 @@
+# name: test/sql/copy/csv/17744.test
+# description: Test for issue #17744
+# group: [csv]
+
+statement ok
+PRAGMA enable_verification
+
+statement ok
+COPY (
+    SELECT
+        -- The string must start with a hash to reproduce the issue
+        '#hash start' AS first_column,
+        1 AS second_column
+    UNION ALL
+    SELECT
+        -- Quoted value can go anywhere between rows 1 and 2048 just not 1 or 2048. It must be between the hashes
+        '"my, quoted value"' AS first_column,
+        1 AS second_column
+    UNION ALL
+    -- These rows make the csv 2048 rows long which is required to reproduce
+    SELECT
+        'any value' AS first_column,
+        1 AS second_column
+    FROM range(0, 2045)
+    UNION ALL
+    SELECT
+        -- This hash value must be somewhere in the string just not at the beginning
+        'hash not at start #' AS column_value,
+     1 AS second_column
+) TO '__TEST_DIR__/test.csv' (format csv, header 1);
+
+query II
+SELECT columns, comment FROM sniff_csv('__TEST_DIR__/test.csv', null_padding = true)
+----
+[{'name': first_column, 'type': VARCHAR}, {'name': second_column, 'type': BIGINT}]	(empty)
+
+query II
+SELECT columns, comment FROM sniff_csv('__TEST_DIR__/test.csv', null_padding = true, comment = '#')
+----
+[{'name': first_column, 'type': VARCHAR}, {'name': second_column, 'type': BIGINT}]	#
+
+
+statement ok
+COPY (
+    SELECT
+        -- The string must start with a hash to reproduce the issue
+        '#hash start' AS first_column,
+        1 AS second_column
+    UNION ALL
+    SELECT
+        -- Quoted value can go anywhere between rows 1 and 2048 just not 1 or 2048. It must be between the hashes
+        '"my, quoted value"' AS first_column,
+        1 AS second_column
+    UNION ALL
+    -- These rows make the csv 2048 rows long which is required to reproduce
+    SELECT
+        'any value' AS first_column,
+        1 AS second_column
+    FROM range(0, 2045)
+    UNION ALL
+    SELECT
+        -- This hash value must be somewhere in the string just not at the beginning
+        'hash not at start #' AS column_value,
+     1 AS second_column
+) TO '__TEST_DIR__/test_2.csv' (format csv, header 1, QUOTE '');
+
+query II
+SELECT columns, comment FROM sniff_csv('__TEST_DIR__/test_2.csv')
+----
+[{'name': first_column, 'type': VARCHAR}, {'name': second_column, 'type': BIGINT}]	(empty)
--- a/external/duckdb/test/sql/copy/csv/18579.test
+++ b/external/duckdb/test/sql/copy/csv/18579.test
@@ -0,0 +1,12 @@
+# name: test/sql/copy/csv/18579.test
+# description: Test for issue #18579
+# group: [csv]
+
+statement ok
+PRAGMA enable_verification
+
+query IIIIII
+DESCRIBE FROM read_csv('data/csv/18579/*.csv', union_by_name = true);
+----
+billingAccountName	VARCHAR	YES	NULL	NULL	NULL
+partnerName	VARCHAR	YES	NULL	NULL	NULL
--- a/external/duckdb/test/sql/copy/csv/7702.test
+++ b/external/duckdb/test/sql/copy/csv/7702.test
@@ -0,0 +1,16 @@
+# name: test/sql/copy/csv/7702.test
+# description: Test for issue #7702
+# group: [csv]
+
+statement ok
+PRAGMA enable_verification
+
+query I
+SELECT count(*) FROM read_csv_auto( ['data/csv/error/mismatch/half1.csv', 'data/csv/error/mismatch/half2.csv'], ignore_errors=true, sample_size=1);
+----
+9102
+
+query I
+SELECT count(*) FROM read_csv_auto( ['data/csv/error/mismatch/half2.csv', 'data/csv/error/mismatch/half1.csv'], ignore_errors=true, sample_size=1);
+----
+9102
--- a/external/duckdb/test/sql/copy/csv/afl/fuzz_20250211_crash.test
+++ b/external/duckdb/test/sql/copy/csv/afl/fuzz_20250211_crash.test
@@ -0,0 +1,10 @@
+# name: test/sql/copy/csv/afl/fuzz_20250211_crash.test
+# description: fuzzer generated csv files - should not raise internal exception (by failed assertion).
+# group: [afl]
+
+statement ok
+PRAGMA enable_verification
+
+statement maybe
+FROM read_csv('data/csv/afl/20250211_csv_fuzz_crash/case_53.csv', buffer_size=42);
+----
--- a/external/duckdb/test/sql/copy/csv/afl/fuzz_20250226.test
+++ b/external/duckdb/test/sql/copy/csv/afl/fuzz_20250226.test
@@ -0,0 +1,17 @@
+# name: test/sql/copy/csv/afl/fuzz_20250226.test
+# description: fuzzer generated csv files - should not raise internal exception (by failed assertion).
+# group: [afl]
+
+require json
+
+statement ok
+PRAGMA enable_verification
+
+query I
+select count(file) from glob('./data/csv/afl/20250226_csv_fuzz_error/*');
+----
+1
+
+statement maybe
+FROM read_csv('data/csv/afl/20250226_csv_fuzz_error/case_1.csv', force_not_null=012%0, columns={'a':'JSON'});
+----
--- a/external/duckdb/test/sql/copy/csv/afl/test_afl_ignore_errors.test
+++ b/external/duckdb/test/sql/copy/csv/afl/test_afl_ignore_errors.test
@@ -0,0 +1,14 @@
+# name: test/sql/copy/csv/afl/test_afl_ignore_errors.test
+# description: Test AFL CSV Files work with ingore errors set to true
+# group: [afl]
+
+statement ok
+PRAGMA enable_verification
+
+loop i 1 56
+
+statement maybe
+FROM read_csv('data/csv/afl/ignore_errors/${i}.csv', ignore_errors = true)
+----
+
+endloop
--- a/external/duckdb/test/sql/copy/csv/afl/test_afl_no_parameter.test
+++ b/external/duckdb/test/sql/copy/csv/afl/test_afl_no_parameter.test
@@ -0,0 +1,14 @@
+# name: test/sql/copy/csv/afl/test_afl_no_parameter.test
+# description: Test AFL CSV Files work with null padding set
+# group: [afl]
+
+statement ok
+PRAGMA enable_verification
+
+loop i 1 25
+
+statement maybe
+FROM 'data/csv/afl/no_parameter/${i}.csv'
+----
+
+endloop
--- a/external/duckdb/test/sql/copy/csv/afl/test_afl_null_padding.test
+++ b/external/duckdb/test/sql/copy/csv/afl/test_afl_null_padding.test
@@ -0,0 +1,14 @@
+# name: test/sql/copy/csv/afl/test_afl_null_padding.test
+# description: Test AFL CSV Files work with null padding set
+# group: [afl]
+
+statement ok
+PRAGMA enable_verification
+
+loop i 1 46
+
+statement maybe
+FROM read_csv('data/csv/afl/null_padding/${i}.csv', null_padding=true)
+----
+
+endloop
--- a/external/duckdb/test/sql/copy/csv/afl/test_afl_skip.test
+++ b/external/duckdb/test/sql/copy/csv/afl/test_afl_skip.test
@@ -0,0 +1,14 @@
+# name: test/sql/copy/csv/afl/test_afl_skip.test
+# description: Test AFL CSV Files work with skip set
+# group: [afl]
+
+statement ok
+PRAGMA enable_verification
+
+loop i 1 3
+
+statement maybe
+FROM read_csv('data/csv/afl/skip/${i}.csv', skip=1)
+----
+
+endloop
--- a/external/duckdb/test/sql/copy/csv/afl/test_fuzz_3977.test
+++ b/external/duckdb/test/sql/copy/csv/afl/test_fuzz_3977.test
@@ -0,0 +1,367 @@
+# name: test/sql/copy/csv/afl/test_fuzz_3977.test
+# description: fuzzer generated csv files - should not raise internal exception (by failed assertion).
+# group: [afl]
+
+loop i 0 2
+
+query I
+select count(file) from glob('./data/csv/afl/3977/*');
+----
+88
+
+statement maybe
+FROM read_csv('data/csv/afl/3977/case_1.csv', rejects_scan=0, buffer_size=655371, all_varchar=false, rejects_scan=0, buffer_size=42);
+----
+
+statement maybe
+FROM read_csv('data/csv/afl/3977/case_2.csv', names=['a','b','c','d'], store_rejects=true);
+----
+
+statement maybe
+FROM read_csv('data/csv/afl/3977/case_3.csv', names=['a','b','c','d'], store_rejects=true);
+----
+
+statement maybe
+FROM read_csv('data/csv/afl/3977/case_4.csv', names=['a','b','c','d'], store_rejects=true);
+----
+
+statement maybe
+FROM read_csv('data/csv/afl/3977/case_5.csv', auto_detect=false, columns={'a': 'VARCHAR'}, escape='"', header=false, quote='"', strict_mode=true, store_rejects=true);
+----
+
+statement maybe
+FROM read_csv('data/csv/afl/3977/case_6.csv', auto_detect=false, buffer_size=42, columns={'a':'INTEGER','b':'INTEGER', 'c':'VARCHAR'}, delim=';', rejects_table='"', strict_mode=true);
+----
+
+statement maybe
+FROM read_csv('data/csv/afl/3977/case_7.csv', auto_detect=false, buffer_size=42, columns={'a':'INTEGER','b':'INTEGER', 'c':'VARCHAR'}, delim=';', rejects_table='"', strict_mode=true);
+----
+
+statement maybe
+FROM read_csv('data/csv/afl/3977/case_8.csv', auto_detect=false, buffer_size=42, columns={'a':'INTEGER','b':'INTEGER', 'c':'VARCHAR'}, delim=';', rejects_table='"', strict_mode=true);
+----
+
+statement maybe
+FROM read_csv('data/csv/afl/3977/case_9.csv', auto_detect=false, buffer_size=42, columns={'a':'INTEGER','b':'INTEGER', 'c':'VARCHAR'}, delim=';', rejects_table='"', strict_mode=false);
+----
+
+statement maybe
+FROM read_csv('data/csv/afl/3977/case_10.csv', auto_detect=false, buffer_size=42, columns={'a':'INTEGER','b':'INTEGER', 'c':'VARCHAR'}, delim=';', rejects_table='"', strict_mode=true);
+----
+
+statement maybe
+FROM read_csv('data/csv/afl/3977/case_11.csv', auto_detect=false, buffer_size=42, columns={'a':'INTEGER','b':'INTEGER', 'c':'VARCHAR'}, delim=';', rejects_table='"', strict_mode=true);
+----
+
+statement maybe
+FROM read_csv('data/csv/afl/3977/case_12.csv', auto_detect=false, buffer_size=42, columns={'a':'INTEGER','b':'INTEGER', 'c':'VARCHAR'}, delim=';', rejects_table='"', strict_mode=true);
+----
+
+statement maybe
+FROM read_csv('data/csv/afl/3977/case_13.csv', auto_detect=false, buffer_size=42, columns={'a':'INTEGER','b':'INTEGER', 'c':'VARCHAR'}, delim=';', rejects_table='"', strict_mode=true);
+----
+
+statement maybe
+FROM read_csv('data/csv/afl/3977/case_14.csv', auto_detect=false, buffer_size=42, columns={'a':'INTEGER','b':'INTEGER', 'c':'VARCHAR'}, delim=';', rejects_table='"', strict_mode=true);
+----
+
+statement maybe
+FROM read_csv('data/csv/afl/3977/case_15.csv', auto_detect=false, buffer_size=42, columns={'a':'INTEGER','b':'INTEGER', 'c':'VARCHAR'}, delim=';', rejects_table='"', strict_mode=true);
+----
+
+statement maybe
+FROM read_csv('data/csv/afl/3977/case_16.csv', auto_detect=false, buffer_size=42, columns={'a':'INTEGER','b':'INTEGER', 'c':'VARCHAR'}, delim=';', rejects_table='"', strict_mode=true);
+----
+
+statement maybe
+FROM read_csv('data/csv/afl/3977/case_17.csv', auto_detect=false, buffer_size=42, columns={'a':'INTEGER','b':'INTEGER', 'c':'VARCHAR'}, delim=';', rejects_table='"', strict_mode=true);
+----
+
+statement maybe
+FROM read_csv('data/csv/afl/3977/case_18.csv', auto_detect=false, buffer_size=42, columns={'a':'INTEGER','b':'INTEGER', 'c':'VARCHAR'}, delim=';', rejects_table='"', strict_mode=true);
+----
+
+statement maybe
+FROM read_csv('data/csv/afl/3977/case_19.csv', auto_detect=false, buffer_size=42, columns={'a':'INTEGER','b':'INTEGER', 'c':'VARCHAR'}, delim=';', rejects_table='"', strict_mode=true);
+----
+
+statement maybe
+FROM read_csv('data/csv/afl/3977/case_20.csv', auto_detect=false, buffer_size=42, columns={'a':'INTEGER','b':'INTEGER', 'c':'VARCHAR'}, delim=';', rejects_table='"', strict_mode=true);
+----
+
+statement maybe
+FROM read_csv('data/csv/afl/3977/case_21.csv', auto_detect=false, buffer_size=42, columns={'a':'INTEGER','b':'INTEGER', 'c':'VARCHAR'}, delim=';', rejects_table='"', strict_mode=true);
+----
+
+statement maybe
+FROM read_csv('data/csv/afl/3977/case_22.csv', auto_detect=false, buffer_size=42, columns={'a':'INTEGER','b':'INTEGER', 'c':'VARCHAR'}, delim=';', rejects_table='"', strict_mode=true);
+----
+
+statement maybe
+FROM read_csv('data/csv/afl/3977/case_23.csv', auto_detect=false, buffer_size=42, columns={'a':'INTEGER','b':'INTEGER', 'c':'VARCHAR'}, delim=';', rejects_table='"', strict_mode=true);
+----
+
+statement maybe
+FROM read_csv('data/csv/afl/3977/case_24.csv', auto_detect=false, buffer_size=42, columns={'a':'INTEGER','b':'INTEGER', 'c':'VARCHAR'}, delim=';', rejects_table='"', strict_mode=true);
+----
+
+statement maybe
+FROM read_csv('data/csv/afl/3977/case_25.csv', auto_detect=false, buffer_size=42, columns={'a':'INTEGER','b':'INTEGER', 'c':'VARCHAR'}, delim=';', rejects_table='"', strict_mode=true);
+----
+
+statement maybe
+FROM read_csv('data/csv/afl/3977/case_26.csv', auto_detect=false, buffer_size=42, columns={'a':'INTEGER','b':'INTEGER', 'c':'VARCHAR'}, delim=';', rejects_table='"', strict_mode=true);
+----
+
+statement maybe
+FROM read_csv('data/csv/afl/3977/case_27.csv', auto_detect=false, buffer_size=42, columns={'a':'INTEGER','b':'INTEGER', 'c':'VARCHAR'}, delim=';', rejects_table='"', strict_mode=true);
+----
+
+statement maybe
+FROM read_csv('data/csv/afl/3977/case_28.csv', auto_detect=false, buffer_size=42, columns={'a':'INTEGER','b':'INTEGER', 'c':'VARCHAR'}, delim=';', rejects_table='"', strict_mode=true);
+----
+
+statement maybe
+FROM read_csv('data/csv/afl/3977/case_29.csv', auto_detect=false, buffer_size=65536, columns={'a':'INTEGER','b':'INTEGER', 'c':'VARCHAR'}, delim=';', rejects_table='"', strict_mode=true);
+----
+
+statement maybe
+FROM read_csv('data/csv/afl/3977/case_30.csv', auto_detect=false, buffer_size=42, columns={'a':'INTEGER','b':'INTEGER', 'c':'VARCHAR'}, delim=';', rejects_table='"', strict_mode=true);
+----
+
+statement maybe
+FROM read_csv('data/csv/afl/3977/case_31.csv', auto_detect=false, buffer_size=42, columns={'a':'INTEGER','b':'INTEGER', 'c':'VARCHAR'}, delim=';', rejects_table='"', strict_mode=true);
+----
+
+statement maybe
+FROM read_csv('data/csv/afl/3977/case_32.csv', auto_detect=false, buffer_size=42, columns={'a':'INTEGER','b':'INTEGER', 'c':'VARCHAR'}, delim=';', rejects_table='"', strict_mode=true);
+----
+
+statement maybe
+FROM read_csv('data/csv/afl/3977/case_33.csv', auto_detect=false, buffer_size=42, columns={'a':'INTEGER','b':'INTEGER', 'c':'VARCHAR'}, delim=';', rejects_table='"', strict_mode=true);
+----
+
+statement maybe
+FROM read_csv('data/csv/afl/3977/case_34.csv', auto_detect=false, buffer_size=42, columns={'a':'INTEGER','b':'INTEGER', 'c':'VARCHAR'}, delim=';', rejects_table='"', strict_mode=true);
+----
+
+statement maybe
+FROM read_csv('data/csv/afl/3977/case_35.csv', auto_detect=false, buffer_size=42, columns={'a':'INTEGER','b':'INTEGER', 'c':'VARCHAR'}, delim=';', rejects_table='"', strict_mode=true);
+----
+
+statement maybe
+FROM read_csv('data/csv/afl/3977/case_36.csv', auto_detect=false, buffer_size=42, columns={'a':'INTEGER','b':'INTEGER', 'c':'VARCHAR'}, delim=';', rejects_table='"', strict_mode=true);
+----
+
+statement maybe
+FROM read_csv('data/csv/afl/3977/case_37.csv', auto_detect=false, buffer_size=42, columns={'a':'INTEGER','b':'INTEGER', 'c':'VARCHAR'}, delim=';', rejects_table='"', strict_mode=true);
+----
+
+statement maybe
+FROM read_csv('data/csv/afl/3977/case_38.csv', auto_detect=false, buffer_size=42, columns={'a':'INTEGER','b':'INTEGER', 'c':'VARCHAR'}, delim=';', rejects_table='"', strict_mode=true);
+----
+
+statement maybe
+FROM read_csv('data/csv/afl/3977/case_39.csv', auto_detect=false, buffer_size=42, columns={'a':'INTEGER','b':'INTEGER', 'c':'VARCHAR'}, delim=';', rejects_table='"', strict_mode=true);
+----
+
+statement maybe
+FROM read_csv('data/csv/afl/3977/case_40.csv', auto_detect=false, buffer_size=42, columns={'a':'INTEGER','b':'INTEGER', 'c':'VARCHAR'}, comment=';', rejects_table='"', strict_mode=false);
+----
+
+statement maybe
+FROM read_csv('data/csv/afl/3977/case_41.csv', auto_detect=false, buffer_size=42, columns={'a':'INTEGER','b':'INTEGER', 'c':'VARCHAR'}, delim=';', rejects_table='"', strict_mode=true);
+----
+
+statement maybe
+FROM read_csv('data/csv/afl/3977/case_42.csv', auto_detect=false, buffer_size=42, columns={'a':'INTEGER','b':'INTEGER', 'c':'VARCHAR'}, delim=';', rejects_table='"', strict_mode=true);
+----
+
+statement maybe
+FROM read_csv('data/csv/afl/3977/case_43.csv', auto_detect=false, buffer_size=42, columns={'a':'INTEGER','b':'INTEGER', 'c':'VARCHAR'}, delim=';', rejects_table='"', strict_mode=true);
+----
+
+statement maybe
+FROM read_csv('data/csv/afl/3977/case_44.csv', auto_detect=false, buffer_size=42, columns={'a':'INTEGER','b':'INTEGER', 'c':'VARCHAR'}, delim=';', rejects_table='"', strict_mode=true);
+----
+
+statement maybe
+FROM read_csv('data/csv/afl/3977/case_45.csv', auto_detect=false, buffer_size=810, columns={'a':'INTEGER','b':'INTEGER', 'c':'VARCHAR'}, delim=';', rejects_table='"', strict_mode=true);
+----
+
+statement maybe
+FROM read_csv('data/csv/afl/3977/case_46.csv', auto_detect=false, buffer_size=42, columns={'a':'INTEGER','b':'INTEGER', 'c':'VARCHAR'}, delim=';', rejects_table='"', strict_mode=true);
+----
+
+statement maybe
+FROM read_csv('data/csv/afl/3977/case_47.csv', auto_detect=false, buffer_size=42, columns={'a':'INTEGER','b':'INTEGER', 'c':'VARCHAR'}, delim=';', rejects_table='"', strict_mode=true);
+----
+
+statement maybe
+FROM read_csv('data/csv/afl/3977/case_48.csv', auto_detect=false, buffer_size=42, columns={'a':'INTEGER','b':'INTEGER', 'c':'VARCHAR'}, delim=';', rejects_table='"', strict_mode=true);
+----
+
+statement maybe
+FROM read_csv('data/csv/afl/3977/case_49.csv', auto_detect=false, buffer_size=42, columns={'a':'INTEGER','b':'INTEGER', 'c':'VARCHAR'}, delim=';', rejects_table='"', strict_mode=true);
+----
+
+statement maybe
+FROM read_csv('data/csv/afl/3977/case_50.csv', auto_detect=false, buffer_size=42, columns={'a':'INTEGER','':'INTEGER', 'c':'VARCHAR'}, delim=';', rejects_table='"', strict_mode=true);
+----
+
+statement maybe
+FROM read_csv('data/csv/afl/3977/case_51.csv', auto_detect=false, buffer_size=42, columns={'a':'INTEGER','b':'INTEGER', '|':'VARCHAR'}, delim=';', rejects_table='"', strict_mode=true);
+----
+
+statement maybe
+FROM read_csv('data/csv/afl/3977/case_52.csv', auto_detect=false, buffer_size=42, columns={'a':'INTEGER','b':'INTEGER', 'c':'VARCHAR'}, delim=';', rejects_table='"', strict_mode=true);
+----
+
+statement maybe
+FROM read_csv('data/csv/afl/3977/case_53.csv', auto_detect=false, buffer_size=42, columns={'a':'INTEGER','b':'INTEGER', 'c':'VARCHAR'}, delim=';', rejects_table='"', strict_mode=true);
+----
+
+statement maybe
+FROM read_csv('data/csv/afl/3977/case_54.csv', auto_detect=false, buffer_size=42, columns={'a':'INTEGER','b':'INTEGER', 'c':'VARCHAr'}, delim=';', rejects_table='"', strict_mode=true);
+----
+
+statement maybe
+FROM read_csv('data/csv/afl/3977/case_55.csv', auto_detect=false, buffer_size=42, columns={'a':'INTEGER','b':'INTEGER', 'c':'VARCHAR'}, delim=';', rejects_table='"', strict_mode=true);
+----
+
+statement maybe
+FROM read_csv('data/csv/afl/3977/case_56.csv', auto_detect=false, buffer_size=42, columns={'a':'INTEGER','b':'INTEGER', 'c':'VARCHAR'}, delim=';', rejects_table='"', strict_mode=true);
+----
+
+statement maybe
+FROM read_csv('data/csv/afl/3977/case_57.csv', auto_detect=false, buffer_size=42, columns={'a':'INTEGER','b':'INTEGER', 'c':'VARCHAR'}, delim=';', rejects_table='"', strict_mode=true);
+----
+
+statement maybe
+FROM read_csv('data/csv/afl/3977/case_58.csv', auto_detect=false, buffer_size=42, columns={'a':'INTEGER','b':'INTEGER', 'c':'VARCHAR'}, delim=';', rejects_table='"', strict_mode=true);
+----
+
+statement maybe
+FROM read_csv('data/csv/afl/3977/case_59.csv', auto_detect=false, buffer_size=42, columns={'a':'INTEGER','"':'INTEGER', 'c':'VARCHAR'}, delim=';', rejects_table='"', strict_mode=true);
+----
+
+statement maybe
+FROM read_csv('data/csv/afl/3977/case_60.csv', auto_detect=false, buffer_size=42, columns={'a':'INTEGER','b':'INTEGER', 'c':'VARCHAR'}, delim=';', rejects_table='"', strict_mode=true);
+----
+
+statement maybe
+FROM read_csv('data/csv/afl/3977/case_61.csv', auto_detect=false, buffer_size=42, columns={'a':'INTEGER','b':'INTEGER', 'c':'VARCHAR'}, delim=';', rejects_table='"', strict_mode=true);
+----
+
+statement maybe
+FROM read_csv('data/csv/afl/3977/case_62.csv', auto_detect=false, buffer_size=42, columns={'a':'INTEGER','b':'INTEGER', 'c':'VARCHAR'}, delim=';', rejects_table='"', strict_mode=true);
+----
+
+statement maybe
+FROM read_csv('data/csv/afl/3977/case_63.csv', auto_detect=false, buffer_size=42, columns={'a':'INTEGER','b':'INTEGER', 'c':'VARCHAR'}, delim=';', rejects_table='"', strict_mode=true);
+----
+
+statement maybe
+FROM read_csv('data/csv/afl/3977/case_64.csv', auto_detect=false, buffer_size=42, columns={'a':'INTEGER','b':'INTEGER', 'c':'VARCHAR'}, delim=';', rejects_table='"', strict_mode=true);
+----
+
+statement maybe
+FROM read_csv('data/csv/afl/3977/case_65.csv', auto_detect=false, buffer_size=42, columns={'a':'INTEGER','b':'INTEGER', 'c':'VARCHAR'}, delim=';', rejects_table='"', strict_mode=true);
+----
+
+statement maybe
+FROM read_csv('data/csv/afl/3977/case_66.csv', auto_detect=false, buffer_size=42, columns={'a':'INTEGER','b':'INTEGER', 'c':'VARCHAR'}, delim=';', rejects_table='"', strict_mode=true);
+----
+
+statement maybe
+FROM read_csv('data/csv/afl/3977/case_67.csv', auto_detect=false, buffer_size=42, columns={'a':'INTEGER','b':'INTEGER', 'c':'VARCHAR'}, delim=';', rejects_table='"', strict_mode=true);
+----
+
+statement maybe
+FROM read_csv('data/csv/afl/3977/case_68.csv', auto_detect=false, buffer_size=42, columns={'a':'INTEGER','b':'INTEGER', 'c':'VARCHAR'}, delim=';', rejects_table='"', strict_mode=true);
+----
+
+statement maybe
+FROM read_csv('data/csv/afl/3977/case_69.csv', auto_detect=false, buffer_size=42, columns={'a':'INTEGER','b':'INTEGER', 'c':'VARCHAR'}, delim=';', rejects_table='"', strict_mode=true);
+----
+
+statement maybe
+FROM read_csv('data/csv/afl/3977/case_70.csv', auto_detect=false, buffer_size=42, columns={'a':'INTEGER','b':'INTEGER', 'c':'VARCHAR'}, delim=';', rejects_table='"', strict_mode=true);
+----
+
+statement maybe
+FROM read_csv('data/csv/afl/3977/case_71.csv', auto_detect=false, buffer_size=16711722, columns={'a':'INTEGER','b':'INTEGER', 'c':'VARCHAR'}, delim=';', rejects_table='"', strict_mode=true);
+----
+
+statement maybe
+FROM read_csv('data/csv/afl/3977/case_72.csv', auto_detect=false, buffer_size=42, columns={'a':'INTEGER','F':'INTEGER', 'c':'VARCHAR'}, delim=';', rejects_table='"', strict_mode=true);
+----
+
+statement maybe
+FROM read_csv('data/csv/afl/3977/case_73.csv', auto_detect=false, buffer_size=42, columns={'a':'INTEGER','b':'INTEGER', 'c':'VARCHAR'}, delim=';', rejects_table='"', strict_mode=true);
+----
+
+statement maybe
+FROM read_csv('data/csv/afl/3977/case_74.csv', auto_detect=false, buffer_size=42, columns={'a':'INTEGER','b':'INTEGER', 'c':'VARCHAR'}, delim=';', rejects_table='"', strict_mode=true);
+----
+
+statement maybe
+FROM read_csv('data/csv/afl/3977/case_75.csv', auto_detect=false, buffer_size=42, columns={'a':'INTEGER','b':'INTEGER', 'c':'VARCHAR'}, delim=';', rejects_table='"', strict_mode=true);
+----
+
+statement maybe
+FROM read_csv('data/csv/afl/3977/case_76.csv', auto_detect=false, buffer_size=42, columns={'a':'INTEGER','b':'INTEGER', 'c':'VARCHAR'}, delim=';', rejects_table='"', strict_mode=true);
+----
+
+statement maybe
+FROM read_csv('data/csv/afl/3977/case_77.csv', auto_detect=false, buffer_size=42, columns={'a':'INTEGER','b':'INTEGER', 'c':'VARCHAR'}, delim=';', rejects_table='"', strict_mode=true);
+----
+
+statement maybe
+FROM read_csv('data/csv/afl/3977/case_78.csv', auto_detect=false, buffer_size=42, columns={'a':'INTEGER','b':'INTEGER', 'c':'VARCHAR'}, delim=';', rejects_table='"', strict_mode=true);
+----
+
+statement maybe
+FROM read_csv('data/csv/afl/3977/case_79.csv', auto_detect=false, buffer_size=42, columns={'a':'INTEGER','b':'INTEGER', 'c':'VARCHAR'}, delim=';', rejects_table='"', strict_mode=true);
+----
+
+statement maybe
+FROM read_csv('data/csv/afl/3977/case_80.csv', auto_detect=false, buffer_size=42, columns={'a':'INTEGER','b':'INTEGER', 'c':'VARCHAR'}, delim=';', rejects_table='"', strict_mode=true);
+----
+
+statement maybe
+FROM read_csv('data/csv/afl/3977/case_81.csv', auto_detect=false, buffer_size=42, columns={'a':'INTEGER','b':'INTEGER', 'c':'VARCHAR'}, delim=';', rejects_table='"', strict_mode=true);
+----
+
+statement maybe
+FROM read_csv('data/csv/afl/3977/case_82.csv', auto_detect=false, buffer_size=42, columns={'a':'INTEGER','b':'INTEGER', 'c':'VARCHAR'}, delim=';', rejects_table='"', strict_mode=true);
+----
+
+statement maybe
+FROM read_csv('data/csv/afl/3977/case_83.csv', auto_detect=false, parallel=false, columns={'a':'INTEGER','b':'INTEGER', 'c':'VARCHAR'}, delim=';', rejects_table='"', strict_mode=true);
+----
+
+statement maybe
+FROM read_csv('data/csv/afl/3977/case_84.csv', auto_detect=false, buffer_size=42, columns={'a':'INTEGER','b':'INTEGER', 'c':'VARCHAR'}, delim=';', rejects_table='"', strict_mode=true);
+----
+
+statement maybe
+FROM read_csv('data/csv/afl/3977/case_85.csv', auto_detect=false, buffer_size=42, columns={'a':'INTEGER','b':'INTEGER', 'c':'VARCHAR'}, delim=';', rejects_table='"', strict_mode=true);
+----
+
+statement maybe
+FROM read_csv('data/csv/afl/3977/case_86.csv', auto_detect=false, buffer_size=720938, columns={'a':'INTEGER','b':'INTEGER', 'c':'VARCHAR'}, delim=';', rejects_table='"', strict_mode=true);
+----
+
+statement maybe
+FROM read_csv('data/csv/afl/3977/case_87.csv', auto_detect=false, buffer_size=42, columns={'a2.0-22222222222222222.0222->>':'VARCHAR'}, delim=';', rejects_table='"', strict_mode=true);
+----
+
+statement maybe
+FROM read_csv('data/csv/afl/3977/case_88.csv', auto_detect=false, buffer_size=42, columns={'a':'INTEGER','b':'INTEGER', 'c':'VARCHAR'}, delim=';', rejects_table='"', strict_mode=true);
+----
+
+statement ok
+PRAGMA enable_verification
+
+endloop
--- a/external/duckdb/test/sql/copy/csv/afl/test_fuzz_4086.test
+++ b/external/duckdb/test/sql/copy/csv/afl/test_fuzz_4086.test
@@ -0,0 +1,24 @@
+# name: test/sql/copy/csv/afl/test_fuzz_4086.test
+# description: fuzzer generated csv files - should not raise internal exception (by failed assertion).
+# group: [afl]
+
+require json
+
+loop i 0 2
+
+statement maybe
+FROM read_csv('data/csv/afl/4086/case_1.csv', auto_detect=false, columns={'json': 'JSON'}, delim=NULL, buffer_size=42, store_rejects=true, rejects_limit=658694493994253607);
+----
+
+statement maybe
+FROM read_csv('data/csv/afl/4086/case_2.csv', auto_detect=false, columns={'json': 'JSON'}, delim=NULL, buffer_size=42, store_rejects=true, rejects_limit=658694493994253607);
+----
+
+statement maybe
+FROM read_csv('data/csv/afl/4086/case_3.csv', auto_detect=false, columns={'json': 'JSON'}, delim='\0', buffer_size=42, store_rejects=true, rejects_limit=658694493994253607);
+----
+
+statement ok
+PRAGMA enable_verification
+
+endloop
--- a/external/duckdb/test/sql/copy/csv/afl/test_fuzz_4172.test
+++ b/external/duckdb/test/sql/copy/csv/afl/test_fuzz_4172.test
@@ -0,0 +1,10 @@
+# name: test/sql/copy/csv/afl/test_fuzz_4172.test
+# description: fuzzer generated csv files - should not raise internal exception (by failed assertion).
+# group: [afl]
+
+statement ok
+PRAGMA enable_verification
+
+statement maybe
+FROM read_csv('data/csv/afl/4172/case_4.csv', ignore_errors=true, buffer_size=1, store_rejects=false);
+----
--- a/external/duckdb/test/sql/copy/csv/afl/test_fuzz_4496.test
+++ b/external/duckdb/test/sql/copy/csv/afl/test_fuzz_4496.test
@@ -0,0 +1,21 @@
+# name: test/sql/copy/csv/afl/test_fuzz_4496.test
+# description: fuzzer generated csv files - should not raise internal exception (by failed assertion).
+# group: [afl]
+
+require json
+
+
+loop i 0 2
+
+statement maybe
+FROM read_csv('data/csv/afl/4496/crashes/case_0.csv', auto_detect=false, buffer_size=42, columns={'json': 'JSON'}, delim=NULL, rejects_limit=658694493994253607, store_rejects=true);
+----
+
+statement maybe
+FROM read_csv('data/csv/afl/4496/crashes/case_1.csv', auto_detect=false, buffer_size=42, columns={'json': 'JSON'}, delim=NULL, rejects_limit=658694493994253607, store_rejects=true);
+----
+
+statement ok
+PRAGMA enable_verification
+
+endloop
--- a/external/duckdb/test/sql/copy/csv/afl/test_fuzz_4793.test
+++ b/external/duckdb/test/sql/copy/csv/afl/test_fuzz_4793.test
@@ -0,0 +1,18 @@
+# name: test/sql/copy/csv/afl/test_fuzz_4793.test
+# description: fuzzer generated csv files - should not raise internal exception (by failed assertion).
+# group: [afl]
+
+require json
+
+statement ok
+PRAGMA enable_verification
+
+
+statement maybe
+FROM read_csv('data/csv/afl/4793/crashes/case_0.csv', auto_detect=false, columns={'a':'varchar'}, delim='', encoding='latin-1', header=false, quote='');
+----
+
+statement maybe
+FROM read_csv('data/csv/afl/4793/crashes/case_1.csv', auto_detect=false, buffer_size=42, columns={'a':'INTEGER','b':'INTEGER', 'c':'VARCHAR'}, delim=';', escape='"', quote='"');
+----
+
--- a/external/duckdb/test/sql/copy/csv/afl/test_fuzz_5194.test
+++ b/external/duckdb/test/sql/copy/csv/afl/test_fuzz_5194.test
@@ -0,0 +1,17 @@
+# name: test/sql/copy/csv/afl/test_fuzz_5194.test
+# description: fuzzer generated csv files - should not raise internal exception (by failed assertion).
+# group: [afl]
+
+require json
+
+statement ok
+PRAGMA enable_verification
+
+statement maybe
+FROM read_csv('data/csv/afl/5194/crashes/case_0.csv', auto_detect=false, buffer_size=8, columns={'a': 'integer','b': 'integer','c': 'integer'}, header=true, maximum_line_size=0);
+----
+
+statement maybe
+FROM read_csv('data/csv/afl/5194/crashes/case_4.csv', buffer_size=30, delim=';', union_by_name=false, header=false, null_padding=true);
+----
+
--- a/external/duckdb/test/sql/copy/csv/auto/test_14177.test
+++ b/external/duckdb/test/sql/copy/csv/auto/test_14177.test
@@ -0,0 +1,11 @@
+# name: test/sql/copy/csv/auto/test_14177.test
+# description: Test CSV Sample works for #14177
+# group: [auto]
+
+statement ok
+PRAGMA enable_verification
+
+query I
+select count(*) FROM (FROM read_csv('data/csv/auto/14177.csv', buffer_size=80, ignore_errors = true)) as t
+----
+5
--- a/external/duckdb/test/sql/copy/csv/auto/test_auto_5250.test
+++ b/external/duckdb/test/sql/copy/csv/auto/test_auto_5250.test
@@ -0,0 +1,14 @@
+# name: test/sql/copy/csv/auto/test_auto_5250.test
+# description: Test CSV Sample works for #5250
+# group: [auto]
+
+statement ok
+PRAGMA enable_verification
+
+statement ok
+PRAGMA verify_parallelism
+
+query I
+select count(*) from read_csv_auto('data/csv/page_namespacepage_title_sample.csv', SAMPLE_SIZE = -1)
+----
+3993
--- a/external/duckdb/test/sql/copy/csv/auto/test_auto_5378.test
+++ b/external/duckdb/test/sql/copy/csv/auto/test_auto_5378.test
@@ -0,0 +1,14 @@
+# name: test/sql/copy/csv/auto/test_auto_5378.test
+# description: Test read_csv_auto on issue 5378
+# group: [auto]
+
+statement ok
+PRAGMA enable_verification
+
+statement ok
+PRAGMA verify_parallelism
+
+query I
+SELECT count(*) FROM read_csv_auto ('data/csv/auto/titlebasicsdebug.tsv', nullstr='\N', sample_size = -1);
+----
+3002
--- a/external/duckdb/test/sql/copy/csv/auto/test_auto_8231.test
+++ b/external/duckdb/test/sql/copy/csv/auto/test_auto_8231.test
@@ -0,0 +1,23 @@
+# name: test/sql/copy/csv/auto/test_auto_8231.test
+# description: Test issue 8231 related to missing headers and null padding
+# group: [auto]
+
+statement ok
+PRAGMA enable_verification
+
+statement ok
+create view locations_header_trailing_comma as SELECT * from read_csv_auto('data/csv/locations_row_trailing_comma.csv', null_padding=True)
+
+query IIIII
+SELECT * from locations_header_trailing_comma
+----
+1	name	0	0	value
+
+query IIIIII
+describe locations_header_trailing_comma;
+----
+id	BIGINT	YES	NULL	NULL	NULL
+name	VARCHAR	YES	NULL	NULL	NULL
+lat	BIGINT	YES	NULL	NULL	NULL
+lon	BIGINT	YES	NULL	NULL	NULL
+column4	VARCHAR	YES	NULL	NULL	NULL
--- a/external/duckdb/test/sql/copy/csv/auto/test_auto_8573.test
+++ b/external/duckdb/test/sql/copy/csv/auto/test_auto_8573.test
@@ -0,0 +1,20 @@
+# name: test/sql/copy/csv/auto/test_auto_8573.test
+# description: Test read_csv_auto on issue 8573
+# group: [auto]
+
+statement ok
+PRAGMA enable_verification
+
+
+statement ok
+PRAGMA verify_parallelism
+
+query II
+SELECT typeof(bignumber), typeof(bignumber::DECIMAL(25,3)) FROM read_csv('data/csv/big_number.csv', COLUMNS={'bignumber': 'DECIMAL(25,3)'}, QUOTE='"', DELIM=',');
+----
+DECIMAL(25,3)	DECIMAL(25,3)
+
+query II
+SELECT typeof(bignumber), typeof(bignumber::DECIMAL(25,3)) FROM read_csv_auto('data/csv/big_number.csv', COLUMNS={'bignumber': 'DECIMAL(25,3)'}, QUOTE='"', DELIM=',');
+----
+DECIMAL(25,3)	DECIMAL(25,3)
--- a/external/duckdb/test/sql/copy/csv/auto/test_auto_8649.test
+++ b/external/duckdb/test/sql/copy/csv/auto/test_auto_8649.test
@@ -0,0 +1,17 @@
+# name: test/sql/copy/csv/auto/test_auto_8649.test
+# description: Test CSV Sample works for #8649
+# group: [auto]
+
+statement ok
+PRAGMA enable_verification
+
+
+statement ok
+PRAGMA verify_parallelism
+
+# Sample
+query I
+SELECT * FROM read_csv_auto("data/csv/dim0.csv") ;
+----
+T
+0
--- a/external/duckdb/test/sql/copy/csv/auto/test_auto_8860.test
+++ b/external/duckdb/test/sql/copy/csv/auto/test_auto_8860.test
@@ -0,0 +1,14 @@
+# name: test/sql/copy/csv/auto/test_auto_8860.test
+# description: Test read_csv_auto on issue 8860
+# group: [auto]
+
+statement ok
+PRAGMA enable_verification
+
+statement ok
+PRAGMA verify_parallelism
+
+query I
+SELECT count(*) FROM read_csv_auto("data/csv/auto/product_codes_HS17_V202301.csv.gz", quote = '"', comment='', delim = ',') ;
+----
+5384
--- a/external/duckdb/test/sql/copy/csv/auto/test_auto_column_type_opt.test
+++ b/external/duckdb/test/sql/copy/csv/auto/test_auto_column_type_opt.test
@@ -0,0 +1,81 @@
+# name: test/sql/copy/csv/auto/test_auto_column_type_opt.test
+# description: Test read_csv_auto with column_types option
+# group: [auto]
+
+statement ok
+PRAGMA enable_verification
+
+
+# Test read_csv wout auto_detect throws
+statement error
+select * from read_csv('data/csv/test/multi_column_string.csv',  COLUMN_TYPES=STRUCT_PACK(a := 'INTEGER'))
+----
+Columns with names: "a" do not exist in the CSV File
+
+# Test non-struct throws
+statement error
+select * from read_csv_auto('data/csv/test/multi_column_string.csv',  COLUMN_TYPES=1)
+----
+COLUMN_TYPES requires a struct or list as input
+
+# Test empty throws
+statement error
+select * from read_csv_auto('data/csv/test/multi_column_string.csv',  COLUMN_TYPES=STRUCT_PACK())
+----
+Can't pack nothing into a struct
+
+# Test funky type throws
+statement error
+select * from read_csv_auto('data/csv/test/multi_column_string.csv',  COLUMN_TYPES=STRUCT_PACK(a := 'BLA'))
+----
+Type with name BLA does not exist!
+
+# Test funky name throws
+statement error
+select * from read_csv_auto('data/csv/test/multi_column_string.csv',  COLUMN_TYPES=STRUCT_PACK(bla := 'INTEGER'))
+----
+Columns with names: "bla" do not exist in the CSV File
+
+# Test wrong type throws
+statement error
+select * from read_csv_auto('data/csv/test/multi_column_string.csv',  COLUMN_TYPES=STRUCT_PACK(column3 := 'INTEGER'))
+----
+This type was either manually set or derived from an existing table. Select a different type to correctly parse this column.
+
+# Test 1st column defined
+query I
+SELECT typeof(#1) from read_csv_auto('data/csv/test/multi_column_string.csv',  COLUMN_TYPES=STRUCT_PACK(column0 := 'DOUBLE')) LIMIT 1
+----
+DOUBLE
+
+query I
+SELECT typeof(#1) from read_csv_auto('data/csv/test/multi_column_string.csv',  COLUMN_TYPES=STRUCT_PACK(column0 := 'INTEGER')) LIMIT 1
+----
+INTEGER
+
+# Test 3rd column defined
+
+query I
+SELECT typeof(#3) from read_csv_auto('data/csv/test/multi_column_string.csv',  COLUMN_TYPES=STRUCT_PACK( column2 := 'HUGEINT')) LIMIT 1
+----
+HUGEINT
+
+# Test 1st and 3rd column defined
+
+query II
+SELECT typeof(#1),typeof(#3) from read_csv_auto('data/csv/test/multi_column_string.csv',  COLUMN_TYPES=STRUCT_PACK(column0 := 'BIGINT', column2 := 'HUGEINT')) LIMIT 1
+----
+BIGINT	HUGEINT
+
+query IIII
+SELECT * from read_csv_auto('data/csv/test/multi_column_string.csv',  COLUMN_TYPES=STRUCT_PACK(column0 := 'BIGINT', column2 := 'HUGEINT'))
+----
+1	6370	371	p1
+10	214	465	p2
+100	2403	160	p3
+1000	1564	67	p4
+10000	10617	138	p5
+100000	430	181	p6
+1000000	1904	658	p7
+10000000	12845	370	p8
+100000000	15519	785	p9
--- a/external/duckdb/test/sql/copy/csv/auto/test_auto_cranlogs.test
+++ b/external/duckdb/test/sql/copy/csv/auto/test_auto_cranlogs.test
@@ -0,0 +1,37 @@
+# name: test/sql/copy/csv/auto/test_auto_cranlogs.test
+# description: Test read_csv_auto from cranlogs gzip
+# group: [auto]
+
+statement ok
+PRAGMA enable_verification
+
+
+statement ok
+CREATE TABLE cranlogs AS SELECT * FROM read_csv_auto ('data/csv/real/tmp2013-06-15.csv.gz');
+
+query I
+SELECT COUNT(*) FROM cranlogs;
+----
+37459
+
+query TTITTTTTTI
+SELECT * FROM cranlogs LIMIT 5;
+----
+2013-06-15	00:18:11	46338	NA	NA	NA	date	1.2-33	JP	1
+2013-06-15	00:18:18	740765	NA	NA	NA	plyr	1.8	JP	2
+2013-06-15	00:54:25	1229408	NA	NA	NA	RJSONIO	1.0-3	JP	3
+2013-06-15	00:58:50	501915	2.15.3	x86_64	linux-gnu	animation	2.2	IN	4
+2013-06-15	00:14:52	254933	3.0.1	x86_64	linux-gnu	foreign	0.8-54	HK	5
+
+
+statement ok
+PRAGMA verify_parallelism
+
+statement ok
+CREATE TABLE cranlogs2 AS SELECT * FROM read_csv_auto ('data/csv/real/tmp2013-06-15.csv.gz');
+
+query IIIIIIIIII
+(SELECT * FROM cranlogs EXCEPT SELECT * FROM cranlogs2)
+UNION ALL
+(SELECT * FROM cranlogs2 EXCEPT SELECT * FROM cranlogs)
+----
--- a/external/duckdb/test/sql/copy/csv/auto/test_auto_greek_ncvoter.test
+++ b/external/duckdb/test/sql/copy/csv/auto/test_auto_greek_ncvoter.test
@@ -0,0 +1,45 @@
+# name: test/sql/copy/csv/auto/test_auto_greek_ncvoter.test
+# description: Test read_csv_auto from ncvoter csv
+# group: [auto]
+
+statement ok
+PRAGMA enable_verification
+
+
+statement ok
+CREATE TABLE IF NOT EXISTS ncvoters(county_id INTEGER, county_desc STRING, voter_reg_num STRING,status_cd STRING, voter_status_desc STRING, reason_cd STRING, voter_status_reason_desc STRING, absent_ind STRING, name_prefx_cd STRING,last_name STRING, first_name STRING, midl_name STRING, name_sufx_cd STRING, full_name_rep STRING,full_name_mail STRING, house_num STRING, half_code STRING, street_dir STRING, street_name STRING, street_type_cd STRING, street_sufx_cd STRING, unit_designator STRING, unit_num STRING, res_city_desc STRING,state_cd STRING, zip_code STRING, res_street_address STRING, res_city_state_zip STRING, mail_addr1 STRING, mail_addr2 STRING, mail_addr3 STRING, mail_addr4 STRING, mail_city STRING, mail_state STRING, mail_zipcode STRING, mail_city_state_zip STRING, area_cd STRING, phone_num STRING, full_phone_number STRING, drivers_lic STRING, race_code STRING, race_desc STRING, ethnic_code STRING, ethnic_desc STRING, party_cd STRING, party_desc STRING, sex_code STRING, sex STRING, birth_age STRING, birth_place STRING, registr_dt STRING, precinct_abbrv STRING, precinct_desc STRING,municipality_abbrv STRING, municipality_desc STRING, ward_abbrv STRING, ward_desc STRING, cong_dist_abbrv STRING, cong_dist_desc STRING, super_court_abbrv STRING, super_court_desc STRING, judic_dist_abbrv STRING, judic_dist_desc STRING, nc_senate_abbrv STRING, nc_senate_desc STRING, nc_house_abbrv STRING, nc_house_desc STRING,county_commiss_abbrv STRING, county_commiss_desc STRING, township_abbrv STRING, township_desc STRING,school_dist_abbrv STRING, school_dist_desc STRING, fire_dist_abbrv STRING, fire_dist_desc STRING, water_dist_abbrv STRING, water_dist_desc STRING, sewer_dist_abbrv STRING, sewer_dist_desc STRING, sanit_dist_abbrv STRING, sanit_dist_desc STRING, rescue_dist_abbrv STRING, rescue_dist_desc STRING, munic_dist_abbrv STRING, munic_dist_desc STRING, dist_1_abbrv STRING, dist_1_desc STRING, dist_2_abbrv STRING, dist_2_desc STRING, confidential_ind STRING, age STRING, ncid STRING, vtd_abbrv STRING, vtd_desc STRING);
+
+query I
+COPY ncvoters FROM 'data/csv/real/ncvoter.csv' (FORMAT CSV, AUTO_DETECT TRUE);
+----
+10
+
+query ITTT
+SELECT county_id, county_desc, vtd_desc, name_prefx_cd FROM ncvoters;
+----
+1	ALAMANCE	09S	NULL
+1	ALAMANCE	09S	NULL
+1	ALAMANCE	03W	NULL
+1	ALAMANCE	09S	NULL
+1	ALAMANCE	1210	NULL
+1	ALAMANCE	035	NULL
+1	ALAMANCE	124	NULL
+1	ALAMANCE	06E	NULL
+1	ALAMANCE	035	NULL
+1	ALAMANCE	064	NULL
+
+statement ok
+PRAGMA verify_parallelism
+
+statement ok
+CREATE TABLE ncvoters2 AS SELECT * FROM ncvoters LIMIT 0
+
+statement ok
+COPY ncvoters2 FROM 'data/csv/real/ncvoter.csv' (FORMAT CSV, AUTO_DETECT TRUE);
+
+query IIIIIIIIIIIIIIIIIIIIIIIIIIIIIIIIIIIIIIIIIIIIIIIIIIIIIIIIIIIIIIIIIIIIIIIIIIIIIIIIIIIIIIIIIIIIII
+(SELECT * FROM ncvoters EXCEPT SELECT * FROM ncvoters2)
+UNION ALL
+(SELECT * FROM ncvoters2 EXCEPT SELECT * FROM ncvoters)
+----
+
--- a/external/duckdb/test/sql/copy/csv/auto/test_auto_greek_utf8.test
+++ b/external/duckdb/test/sql/copy/csv/auto/test_auto_greek_utf8.test
@@ -0,0 +1,45 @@
+# name: test/sql/copy/csv/auto/test_auto_greek_utf8.test
+# description: Test read_csv_auto from greek-utf8 csv
+# group: [auto]
+
+statement ok
+PRAGMA enable_verification
+
+
+statement ok
+PRAGMA verify_parallelism
+
+
+statement ok
+CREATE TABLE greek_utf8 AS SELECT i, nfc_normalize(j) j, k FROM read_csv_auto ('data/csv/real/greek_utf8.csv') t(i, j, k)
+
+query I
+SELECT COUNT(*) FROM greek_utf8;
+----
+8
+
+query ITI
+SELECT * FROM greek_utf8 ORDER BY 1;
+----
+1689	00i\047m	2
+1690	00i\047v	2
+41561	2015‎	1
+45804	21π	1
+51981	24hours‬	1
+171067	ardèch	2
+182773	aﬁ	1
+607808	poverty‪	1
+
+# can also do this
+query ITI
+SELECT i, nfc_normalize(j) j, k FROM 'data/csv/real/greek_utf8.csv' t(i, j, k)
+----
+1689	00i\047m	2
+1690	00i\047v	2
+41561	2015‎	1
+45804	21π	1
+51981	24hours‬	1
+171067	ardèch	2
+182773	aﬁ	1
+607808	poverty‪	1
+
--- a/external/duckdb/test/sql/copy/csv/auto/test_auto_imdb.test
+++ b/external/duckdb/test/sql/copy/csv/auto/test_auto_imdb.test
@@ -0,0 +1,25 @@
+# name: test/sql/copy/csv/auto/test_auto_imdb.test
+# description: Test read_csv_auto from imdb csv
+# group: [auto]
+
+statement ok
+PRAGMA enable_verification
+
+
+statement ok
+CREATE TABLE movie_info AS SELECT * FROM read_csv_auto ('data/csv/real/imdb_movie_info_escaped.csv');
+
+query I
+SELECT COUNT(*) FROM movie_info;
+----
+201
+
+
+statement ok
+CREATE TABLE movie_info2 AS SELECT * FROM read_csv_auto ('data/csv/real/imdb_movie_info_escaped.csv');
+
+query IIIII
+(FROM movie_info EXCEPT FROM movie_info2)
+UNION ALL
+(FROM movie_info2 EXCEPT FROM movie_info)
+----
--- a/external/duckdb/test/sql/copy/csv/auto/test_auto_lineitem.test
+++ b/external/duckdb/test/sql/copy/csv/auto/test_auto_lineitem.test
@@ -0,0 +1,46 @@
+# name: test/sql/copy/csv/auto/test_auto_lineitem.test
+# description: Test copy into auto from lineitem csv
+# group: [auto]
+
+statement ok
+PRAGMA enable_verification
+
+
+statement ok
+CREATE TABLE lineitem(l_orderkey INT NOT NULL, l_partkey INT NOT NULL, l_suppkey INT NOT NULL, l_linenumber INT NOT NULL, l_quantity INTEGER NOT NULL, l_extendedprice DECIMAL(15,2) NOT NULL, l_discount DECIMAL(15,2) NOT NULL, l_tax DECIMAL(15,2) NOT NULL, l_returnflag VARCHAR(1) NOT NULL, l_linestatus VARCHAR(1) NOT NULL, l_shipdate DATE NOT NULL, l_commitdate DATE NOT NULL, l_receiptdate DATE NOT NULL, l_shipinstruct VARCHAR(25) NOT NULL, l_shipmode VARCHAR(10) NOT NULL, l_comment VARCHAR(44) NOT NULL);
+
+query I
+COPY lineitem FROM 'data/csv/real/lineitem_sample.csv' (FORMAT CSV, AUTO_DETECT TRUE);
+----
+10
+
+query I
+SELECT COUNT(*) FROM lineitem;
+----
+10
+
+query IT
+SELECT l_partkey, l_comment FROM lineitem WHERE l_orderkey=1 ORDER BY l_linenumber;
+----
+15519	egular courts above the
+6731	ly final dependencies: slyly bold 
+6370	riously. regular, express dep
+214	lites. fluffily even de
+2403	 pending foxes. slyly re
+1564	arefully slyly ex
+
+statement ok
+PRAGMA verify_parallelism
+
+statement ok
+CREATE TABLE lineitem2 AS SELECT * FROM lineitem LIMIT 0
+
+statement ok
+COPY lineitem2 FROM 'data/csv/real/lineitem_sample.csv' (FORMAT CSV, AUTO_DETECT TRUE);
+
+query IIIIIIIIIIIIIIII
+(SELECT * FROM lineitem EXCEPT SELECT * FROM lineitem2)
+UNION ALL
+(SELECT * FROM lineitem2 EXCEPT SELECT * FROM lineitem)
+----
+
--- a/external/duckdb/test/sql/copy/csv/auto/test_auto_ontime.test
+++ b/external/duckdb/test/sql/copy/csv/auto/test_auto_ontime.test
@@ -0,0 +1,45 @@
+# name: test/sql/copy/csv/auto/test_auto_ontime.test
+# description: Test read_csv_auto from on-time dataset
+# group: [auto]
+
+statement ok
+PRAGMA enable_verification
+
+
+statement ok
+CREATE TABLE ontime(year SMALLINT, quarter SMALLINT, month SMALLINT, dayofmonth SMALLINT, dayofweek SMALLINT, flightdate DATE, uniquecarrier CHAR(7), airlineid DECIMAL(8,2), carrier CHAR(2), tailnum VARCHAR(50), flightnum VARCHAR(10), originairportid INTEGER, originairportseqid INTEGER, origincitymarketid INTEGER, origin CHAR(5), origincityname VARCHAR(100), originstate CHAR(2), originstatefips VARCHAR(10), originstatename VARCHAR(100), originwac DECIMAL(8,2), destairportid INTEGER, destairportseqid INTEGER, destcitymarketid INTEGER, dest CHAR(5), destcityname VARCHAR(100), deststate CHAR(2), deststatefips VARCHAR(10), deststatename VARCHAR(100), destwac DECIMAL(8,2), crsdeptime DECIMAL(8,2), deptime DECIMAL(8,2), depdelay DECIMAL(8,2), depdelayminutes DECIMAL(8,2), depdel15 DECIMAL(8,2), departuredelaygroups DECIMAL(8,2), deptimeblk VARCHAR(20), taxiout DECIMAL(8,2), wheelsoff DECIMAL(8,2), wheelson DECIMAL(8,2), taxiin DECIMAL(8,2), crsarrtime DECIMAL(8,2), arrtime DECIMAL(8,2), arrdelay DECIMAL(8,2), arrdelayminutes DECIMAL(8,2), arrdel15 DECIMAL(8,2), arrivaldelaygroups DECIMAL(8,2), arrtimeblk VARCHAR(20), cancelled DECIMAL(8,2), cancellationcode CHAR(1), diverted DECIMAL(8,2), crselapsedtime DECIMAL(8,2), actualelapsedtime DECIMAL(8,2), airtime DECIMAL(8,2), flights DECIMAL(8,2), distance DECIMAL(8,2), distancegroup DECIMAL(8,2), carrierdelay DECIMAL(8,2), weatherdelay DECIMAL(8,2), nasdelay DECIMAL(8,2), securitydelay DECIMAL(8,2), lateaircraftdelay DECIMAL(8,2), firstdeptime VARCHAR(10), totaladdgtime VARCHAR(10), longestaddgtime VARCHAR(10), divairportlandings VARCHAR(10), divreacheddest VARCHAR(10), divactualelapsedtime VARCHAR(10), divarrdelay VARCHAR(10), divdistance VARCHAR(10), div1airport VARCHAR(10), div1aiportid INTEGER, div1airportseqid INTEGER, div1wheelson VARCHAR(10), div1totalgtime VARCHAR(10), div1longestgtime VARCHAR(10), div1wheelsoff VARCHAR(10), div1tailnum VARCHAR(10), div2airport VARCHAR(10), div2airportid INTEGER, div2airportseqid INTEGER, div2wheelson VARCHAR(10), div2totalgtime VARCHAR(10), div2longestgtime VARCHAR(10), div2wheelsoff VARCHAR(10), div2tailnum VARCHAR(10), div3airport VARCHAR(10), div3airportid INTEGER, div3airportseqid INTEGER, div3wheelson VARCHAR(10), div3totalgtime VARCHAR(10), div3longestgtime VARCHAR(10), div3wheelsoff VARCHAR(10), div3tailnum VARCHAR(10), div4airport VARCHAR(10), div4airportid INTEGER, div4airportseqid INTEGER, div4wheelson VARCHAR(10), div4totalgtime VARCHAR(10), div4longestgtime VARCHAR(10), div4wheelsoff VARCHAR(10), div4tailnum VARCHAR(10), div5airport VARCHAR(10), div5airportid INTEGER, div5airportseqid INTEGER, div5wheelson VARCHAR(10), div5totalgtime VARCHAR(10), div5longestgtime VARCHAR(10), div5wheelsoff VARCHAR(10), div5tailnum VARCHAR(10));
+
+query I
+COPY ontime FROM 'data/csv/real/ontime_sample.csv';
+----
+9
+
+query ITTTT
+SELECT year, uniquecarrier, origin, origincityname, div5longestgtime FROM ontime;
+----
+1988	AA	JFK	New York, NY	NULL
+1988	AA	JFK	New York, NY	NULL
+1988	AA	JFK	New York, NY	NULL
+1988	AA	JFK	New York, NY	NULL
+1988	AA	JFK	New York, NY	NULL
+1988	AA	JFK	New York, NY	NULL
+1988	AA	JFK	New York, NY	NULL
+1988	AA	JFK	New York, NY	NULL
+1988	AA	JFK	New York, NY	NULL
+
+
+statement ok
+PRAGMA verify_parallelism
+
+statement ok
+CREATE TABLE ontime2 AS SELECT * FROM ontime LIMIT 0
+
+statement ok
+COPY ontime2 FROM 'data/csv/real/ontime_sample.csv';
+
+query IIIIIIIIIIIIIIIIIIIIIIIIIIIIIIIIIIIIIIIIIIIIIIIIIIIIIIIIIIIIIIIIIIIIIIIIIIIIIIIIIIIIIIIIIIIIIIIIIIIIIIIIIIIII
+(SELECT * FROM ontime EXCEPT SELECT * FROM ontime2)
+UNION ALL
+(SELECT * FROM ontime2 EXCEPT SELECT * FROM ontime)
+----
+
--- a/external/duckdb/test/sql/copy/csv/auto/test_auto_voter.test_slow
+++ b/external/duckdb/test/sql/copy/csv/auto/test_auto_voter.test_slow
@@ -0,0 +1,39 @@
+# name: test/sql/copy/csv/auto/test_auto_voter.test_slow
+# description: Test read_csv_auto from voter tsv
+# group: [auto]
+
+statement ok
+PRAGMA enable_verification
+
+
+statement ok
+CREATE TABLE voters AS SELECT * FROM read_csv_auto ('data/csv/real/voter.tsv');
+
+query I
+SELECT COUNT(*) FROM voters;
+----
+5300
+
+query I
+SELECT COUNT(*) FROM "data/csv/real/voter.tsv";
+----
+5300
+
+# read with parallel reader and verify that we get the same result
+
+# FIXME: This should run on windows
+
+require notwindows
+
+
+statement ok
+PRAGMA verify_parallelism
+
+statement ok
+CREATE TABLE voters2 AS SELECT * FROM read_csv_auto ('data/csv/real/voter.tsv');
+
+query IIIIIIIIIIIIIIIIIIIIIIIIIIIIIIIIIIIIIIIIIIIIIIIIIIIIIIIIIIIIIIIIIIIIIIIIIIIIIIIIIIIIIIIIIIIIII
+(SELECT * FROM voters EXCEPT SELECT * FROM voters2)
+UNION ALL
+(SELECT * FROM voters2 EXCEPT SELECT * FROM voters)
+----
--- a/external/duckdb/test/sql/copy/csv/auto/test_auto_web_page.test
+++ b/external/duckdb/test/sql/copy/csv/auto/test_auto_web_page.test
@@ -0,0 +1,31 @@
+# name: test/sql/copy/csv/auto/test_auto_web_page.test
+# description: Test read_csv_auto from web_page csv
+# group: [auto]
+
+statement ok
+CREATE TABLE web_page AS SELECT * FROM read_csv_auto ('data/csv/real/web_page.csv');
+
+query I
+SELECT COUNT(*) FROM web_page;
+----
+60
+
+query ITTTIITITTIIII
+SELECT * FROM web_page ORDER BY column00 LIMIT 3;
+----
+1	AAAAAAAABAAAAAAA	1997-09-03	NULL	2450810	2452620	Y	98539	http://www.foo.com	welcome	2531	8	3	4
+2	AAAAAAAACAAAAAAA	1997-09-03	2000-09-02	2450814	2452580	N	NULL	http://www.foo.com	protected	1564	4	3	1
+3	AAAAAAAACAAAAAAA	2000-09-03	NULL	2450814	2452611	N	NULL	http://www.foo.com	feedback	1564	4	3	4
+
+
+statement ok
+PRAGMA verify_parallelism
+
+statement ok
+CREATE TABLE web_page2 AS SELECT * FROM read_csv_auto ('data/csv/real/web_page.csv');
+
+query IIIIIIIIIIIIII
+(SELECT * FROM web_page EXCEPT SELECT * FROM web_page2)
+UNION ALL
+(SELECT * FROM web_page2 EXCEPT SELECT * FROM web_page)
+----
--- a/external/duckdb/test/sql/copy/csv/auto/test_csv_auto.test
+++ b/external/duckdb/test/sql/copy/csv/auto/test_csv_auto.test
@@ -0,0 +1,309 @@
+# name: test/sql/copy/csv/auto/test_csv_auto.test
+# description: Test csv dialect detection
+# group: [auto]
+
+statement ok
+PRAGMA enable_verification
+
+statement ok 
+PRAGMA verify_parallelism
+
+query II
+FROM read_csv('data/csv/repromarket.csv',
+   columns={
+      'email': 'varchar',
+      'password': 'varchar'
+   },
+   all_varchar=true,
+   delim=':',
+   header=false,
+   skip=0,
+   null_padding=true,
+   ignore_errors=true,
+   strict_mode=false
+);
+----
+nemanja.krpovic@gmail.com	krlleta
+vega@example.combogus	NULL
+Vega-Inject	bogus
+mirkofoto@gmail.com	mirko
+
+query I
+FROM read_csv('data/csv/pipe_delim.csv', columns={'a': 'VARCHAR'}, auto_detect=False)
+----
+one|two|three|four
+1|2|3|4
+
+query I
+FROM read_csv('data/csv/nullterm.csv')
+----
+\0world\0
+
+query I
+FROM read_csv('data/csv/nullterm.csv', quote = '"', escape = '"')
+----
+\0world\0
+
+query I
+FROM read_csv('data/csv/single_quote.csv', quote = '"')
+----
+'Doc'
+
+query I
+select columns FROM sniff_csv('data/csv/auto/mock_duckdb_test_data.csv', ignore_errors = true);
+----
+[{'name': id, 'type': BIGINT}, {'name': name, 'type': VARCHAR}, {'name': age, 'type': BIGINT}, {'name': sex, 'type': VARCHAR}, {'name': state, 'type': VARCHAR}]
+
+query IIIII
+FROM read_csv('data/csv/auto/mock_duckdb_test_data.csv', ignore_errors = true,
+   strict_mode=true)
+----
+1	James	30	M	AL
+2	Jill	32	F	CO
+4	John	34	M	AS
+5	Matthew	31	M	NULL
+7	Olivia	36	F	OR
+8	James	37	M	AZ
+9	Titus	38	M	WY
+
+statement error
+select * from read_csv_auto('data/csv/dates.csv', auto_detect=false, delim=',', quote='"', columns={'a': 'VARCHAR'},
+   strict_mode=true)
+----
+Expected Number of Columns: 1 Found: 2
+
+query II
+select * from read_csv_auto('data/csv/dates.csv')
+----
+919 304 6161	2008-08-10
+
+query II
+select * from read_csv_auto('data/csv/from_df.csv', quote='''')
+----
+'a,b,c'	45
+NULL	234
+hello	234
+bye	2
+
+# CSV file with RFC-conform dialect
+statement ok
+CREATE TABLE test AS SELECT * FROM read_csv_auto ('data/csv/auto/rfc_conform.csv');
+
+query ITT
+SELECT * FROM test ORDER BY column0;
+----
+123	TEST1	one space
+345	TEST1	trailing_space 
+567	TEST1	no_space
+
+statement ok
+DROP TABLE test;
+
+# CSV file with RFC-conform dialect quote
+# read_csv is an alias to read_csv_auto when no extra parameters are supplied
+statement ok
+CREATE TABLE test AS SELECT * FROM read_csv_auto ('data/csv/auto/rfc_conform_quote.csv');
+
+query ITT
+SELECT * FROM test ORDER BY column0;
+----
+123	TEST2	one space
+345	TEST2	trailing_space, 
+567	TEST2	no"space
+
+statement ok
+DROP TABLE test;
+
+# CSV file with RFC-conform dialect quote/leading space of numerics
+statement ok
+CREATE TABLE test AS SELECT * FROM read_csv_auto ('data/csv/auto/leading_space_numerics.csv');
+
+query ITT
+SELECT * FROM test ORDER BY column0;
+----
+123	TEST3	text1
+345	TEST3	text2
+567	TEST3	text3
+
+statement ok
+DROP TABLE test;
+
+# CSV file with bar delimiter
+statement ok
+CREATE TABLE test AS SELECT * FROM read_csv_auto ('data/csv/auto/pipe_delim.csv');
+
+query ITT
+SELECT * FROM test ORDER BY column0;
+----
+123	TEST4	text1
+345	TEST4	text2
+567	TEST4	text3
+
+statement ok
+DROP TABLE test;
+
+# CSV file with bar delimiter and double quotes
+statement ok
+CREATE TABLE test AS SELECT * FROM read_csv_auto ('data/csv/auto/pipe_delim_quote.csv');
+
+query ITT
+SELECT * FROM test ORDER BY column0;
+----
+123	TEST5	text1
+345	TEST5	text2|
+567	TEST5	text3
+
+statement ok
+DROP TABLE test;
+
+# CSV file with bar delimiter and double quotes and double escape
+statement ok
+CREATE TABLE test AS SELECT * FROM read_csv_auto ('data/csv/auto/quote_escape.csv');
+
+query ITT
+SELECT * FROM test ORDER BY column0;
+----
+123	TEST6	text1
+345	TEST6	text"2"text
+567	TEST6	text3
+
+statement ok
+DROP TABLE test;
+
+# CSV file with bar delimiter and double quotes and backslash escape
+statement ok
+CREATE TABLE test AS SELECT * FROM read_csv_auto ('data/csv/auto/backslash_escape.csv');
+
+query ITT
+SELECT * FROM test ORDER BY column0;
+----
+123	TEST7	text1
+345	TEST7	text"2"
+567	TEST7	text3
+
+statement ok
+DROP TABLE test;
+
+# CSV file with bar delimiter and single quotes and backslash escape
+statement ok
+CREATE TABLE test AS SELECT * FROM read_csv_auto ('data/csv/auto/single_quote_backslash.csv');
+
+query ITT
+SELECT * FROM test ORDER BY column0;
+----
+123	TEST8	text1
+345	TEST8	text'2'text
+567	TEST8	text3
+
+statement ok
+DROP TABLE test;
+
+# CSV file with semicolon delimiter
+statement ok
+CREATE TABLE test AS SELECT * FROM read_csv_auto ('data/csv/auto/semicolon_delim.csv');
+
+query ITT
+SELECT * FROM test ORDER BY column0;
+----
+123	TEST9	text1
+345	TEST9	text2
+567	TEST9	text3
+
+statement ok
+DROP TABLE test;
+
+# CSV file with semicolon delimiter and double quotes
+statement ok
+CREATE TABLE test AS SELECT * FROM read_csv_auto ('data/csv/auto/semicolon_quote.csv');
+
+query ITT
+SELECT * FROM test ORDER BY column0;
+----
+123	TEST10	text1
+345	TEST10	text2
+567	TEST10	te;xt3
+
+statement ok
+DROP TABLE test;
+
+# CSV file with semicolon delimiter, double quotes and RFC escape
+statement ok
+CREATE TABLE test AS SELECT * FROM read_csv_auto ('data/csv/auto/semicolon_escape.csv');
+
+query ITT
+SELECT * FROM test ORDER BY column0;
+----
+123	TEST11	text1
+345	TEST11	text2
+567	TEST11	te"xt3
+
+statement ok
+DROP TABLE test;
+
+# CSV file with tab delimiter
+statement ok
+CREATE TABLE test AS SELECT * FROM read_csv_auto ('data/csv/auto/tab.csv');
+
+query ITT
+SELECT * FROM test ORDER BY column0;
+----
+123	TEST12	text1
+345	TEST12	text2
+567	TEST12	text3
+
+statement ok
+DROP TABLE test;
+
+# CSV file with tab delimiter and single quotes
+statement ok
+CREATE TABLE test AS SELECT * FROM read_csv_auto ('data/csv/auto/tab_single_quote.csv');
+
+query ITT
+SELECT * FROM test ORDER BY column0;
+----
+123
+TEST13
+text1
+345
+TEST13
+te	xt2
+567
+TEST13
+text3
+
+statement ok
+DROP TABLE test;
+
+# CSV file with tab delimiter and single quotes without type-hint
+statement ok
+CREATE TABLE test AS SELECT * FROM read_csv_auto ('data/csv/auto/tab_single_quote_varchar.csv');
+
+query ITT
+SELECT * FROM test ORDER BY column0;
+----
+123
+TEST14
+text1
+345
+TEST14
+te	xt2
+567
+TEST14
+text3
+
+statement ok
+DROP TABLE test;
+
+
+# CSV file with trailing empty lines 
+statement ok
+CREATE TABLE test AS SELECT * FROM read_csv_auto ('data/csv/auto/issue_1254.csv');
+
+query II
+SELECT a, b FROM test;
+----
+1	2
+1	2
+
+statement ok
+DROP TABLE test;
--- a/external/duckdb/test/sql/copy/csv/auto/test_date_format_bug_linux.test
+++ b/external/duckdb/test/sql/copy/csv/auto/test_date_format_bug_linux.test
@@ -0,0 +1,13 @@
+# name: test/sql/copy/csv/auto/test_date_format_bug_linux.test
+# group: [auto]
+
+statement ok
+PRAGMA enable_verification
+
+
+query I
+SELECT *  FROM read_csv_auto('data/csv/auto/date_format_bug_linux.csv')
+----
+8cb123cb8
+34fd321
+fg5391jn4
--- a/external/duckdb/test/sql/copy/csv/auto/test_describe_order.test
+++ b/external/duckdb/test/sql/copy/csv/auto/test_describe_order.test
@@ -0,0 +1,137 @@
+# name: test/sql/copy/csv/auto/test_describe_order.test
+# group: [auto]
+
+statement ok
+PRAGMA enable_verification
+
+statement ok
+create view v as select * from read_csv_auto('data/csv/who.csv.gz');
+
+query IIIIII
+describe v;
+----
+country	VARCHAR	YES	NULL	NULL	NULL
+iso2	VARCHAR	YES	NULL	NULL	NULL
+iso3	VARCHAR	YES	NULL	NULL	NULL
+year	BIGINT	YES	NULL	NULL	NULL
+new_sp_m014	BIGINT	YES	NULL	NULL	NULL
+new_sp_m1524	BIGINT	YES	NULL	NULL	NULL
+new_sp_m2534	BIGINT	YES	NULL	NULL	NULL
+new_sp_m3544	BIGINT	YES	NULL	NULL	NULL
+new_sp_m4554	BIGINT	YES	NULL	NULL	NULL
+new_sp_m5564	BIGINT	YES	NULL	NULL	NULL
+new_sp_m65	BIGINT	YES	NULL	NULL	NULL
+new_sp_f014	BIGINT	YES	NULL	NULL	NULL
+new_sp_f1524	BIGINT	YES	NULL	NULL	NULL
+new_sp_f2534	BIGINT	YES	NULL	NULL	NULL
+new_sp_f3544	BIGINT	YES	NULL	NULL	NULL
+new_sp_f4554	BIGINT	YES	NULL	NULL	NULL
+new_sp_f5564	BIGINT	YES	NULL	NULL	NULL
+new_sp_f65	BIGINT	YES	NULL	NULL	NULL
+new_sn_m014	BIGINT	YES	NULL	NULL	NULL
+new_sn_m1524	BIGINT	YES	NULL	NULL	NULL
+new_sn_m2534	BIGINT	YES	NULL	NULL	NULL
+new_sn_m3544	BIGINT	YES	NULL	NULL	NULL
+new_sn_m4554	BIGINT	YES	NULL	NULL	NULL
+new_sn_m5564	BIGINT	YES	NULL	NULL	NULL
+new_sn_m65	BIGINT	YES	NULL	NULL	NULL
+new_sn_f014	BIGINT	YES	NULL	NULL	NULL
+new_sn_f1524	BIGINT	YES	NULL	NULL	NULL
+new_sn_f2534	BIGINT	YES	NULL	NULL	NULL
+new_sn_f3544	BIGINT	YES	NULL	NULL	NULL
+new_sn_f4554	BIGINT	YES	NULL	NULL	NULL
+new_sn_f5564	BIGINT	YES	NULL	NULL	NULL
+new_sn_f65	BIGINT	YES	NULL	NULL	NULL
+new_ep_m014	BIGINT	YES	NULL	NULL	NULL
+new_ep_m1524	BIGINT	YES	NULL	NULL	NULL
+new_ep_m2534	BIGINT	YES	NULL	NULL	NULL
+new_ep_m3544	BIGINT	YES	NULL	NULL	NULL
+new_ep_m4554	BIGINT	YES	NULL	NULL	NULL
+new_ep_m5564	BIGINT	YES	NULL	NULL	NULL
+new_ep_m65	BIGINT	YES	NULL	NULL	NULL
+new_ep_f014	BIGINT	YES	NULL	NULL	NULL
+new_ep_f1524	BIGINT	YES	NULL	NULL	NULL
+new_ep_f2534	BIGINT	YES	NULL	NULL	NULL
+new_ep_f3544	BIGINT	YES	NULL	NULL	NULL
+new_ep_f4554	BIGINT	YES	NULL	NULL	NULL
+new_ep_f5564	BIGINT	YES	NULL	NULL	NULL
+new_ep_f65	BIGINT	YES	NULL	NULL	NULL
+newrel_m014	BIGINT	YES	NULL	NULL	NULL
+newrel_m1524	BIGINT	YES	NULL	NULL	NULL
+newrel_m2534	BIGINT	YES	NULL	NULL	NULL
+newrel_m3544	BIGINT	YES	NULL	NULL	NULL
+newrel_m4554	BIGINT	YES	NULL	NULL	NULL
+newrel_m5564	BIGINT	YES	NULL	NULL	NULL
+newrel_m65	BIGINT	YES	NULL	NULL	NULL
+newrel_f014	BIGINT	YES	NULL	NULL	NULL
+newrel_f1524	BIGINT	YES	NULL	NULL	NULL
+newrel_f2534	BIGINT	YES	NULL	NULL	NULL
+newrel_f3544	BIGINT	YES	NULL	NULL	NULL
+newrel_f4554	BIGINT	YES	NULL	NULL	NULL
+newrel_f5564	BIGINT	YES	NULL	NULL	NULL
+newrel_f65	BIGINT	YES	NULL	NULL	NULL
+
+query IIIIII
+describe select * from v;
+----
+country	VARCHAR	YES	NULL	NULL	NULL
+iso2	VARCHAR	YES	NULL	NULL	NULL
+iso3	VARCHAR	YES	NULL	NULL	NULL
+year	BIGINT	YES	NULL	NULL	NULL
+new_sp_m014	BIGINT	YES	NULL	NULL	NULL
+new_sp_m1524	BIGINT	YES	NULL	NULL	NULL
+new_sp_m2534	BIGINT	YES	NULL	NULL	NULL
+new_sp_m3544	BIGINT	YES	NULL	NULL	NULL
+new_sp_m4554	BIGINT	YES	NULL	NULL	NULL
+new_sp_m5564	BIGINT	YES	NULL	NULL	NULL
+new_sp_m65	BIGINT	YES	NULL	NULL	NULL
+new_sp_f014	BIGINT	YES	NULL	NULL	NULL
+new_sp_f1524	BIGINT	YES	NULL	NULL	NULL
+new_sp_f2534	BIGINT	YES	NULL	NULL	NULL
+new_sp_f3544	BIGINT	YES	NULL	NULL	NULL
+new_sp_f4554	BIGINT	YES	NULL	NULL	NULL
+new_sp_f5564	BIGINT	YES	NULL	NULL	NULL
+new_sp_f65	BIGINT	YES	NULL	NULL	NULL
+new_sn_m014	BIGINT	YES	NULL	NULL	NULL
+new_sn_m1524	BIGINT	YES	NULL	NULL	NULL
+new_sn_m2534	BIGINT	YES	NULL	NULL	NULL
+new_sn_m3544	BIGINT	YES	NULL	NULL	NULL
+new_sn_m4554	BIGINT	YES	NULL	NULL	NULL
+new_sn_m5564	BIGINT	YES	NULL	NULL	NULL
+new_sn_m65	BIGINT	YES	NULL	NULL	NULL
+new_sn_f014	BIGINT	YES	NULL	NULL	NULL
+new_sn_f1524	BIGINT	YES	NULL	NULL	NULL
+new_sn_f2534	BIGINT	YES	NULL	NULL	NULL
+new_sn_f3544	BIGINT	YES	NULL	NULL	NULL
+new_sn_f4554	BIGINT	YES	NULL	NULL	NULL
+new_sn_f5564	BIGINT	YES	NULL	NULL	NULL
+new_sn_f65	BIGINT	YES	NULL	NULL	NULL
+new_ep_m014	BIGINT	YES	NULL	NULL	NULL
+new_ep_m1524	BIGINT	YES	NULL	NULL	NULL
+new_ep_m2534	BIGINT	YES	NULL	NULL	NULL
+new_ep_m3544	BIGINT	YES	NULL	NULL	NULL
+new_ep_m4554	BIGINT	YES	NULL	NULL	NULL
+new_ep_m5564	BIGINT	YES	NULL	NULL	NULL
+new_ep_m65	BIGINT	YES	NULL	NULL	NULL
+new_ep_f014	BIGINT	YES	NULL	NULL	NULL
+new_ep_f1524	BIGINT	YES	NULL	NULL	NULL
+new_ep_f2534	BIGINT	YES	NULL	NULL	NULL
+new_ep_f3544	BIGINT	YES	NULL	NULL	NULL
+new_ep_f4554	BIGINT	YES	NULL	NULL	NULL
+new_ep_f5564	BIGINT	YES	NULL	NULL	NULL
+new_ep_f65	BIGINT	YES	NULL	NULL	NULL
+newrel_m014	BIGINT	YES	NULL	NULL	NULL
+newrel_m1524	BIGINT	YES	NULL	NULL	NULL
+newrel_m2534	BIGINT	YES	NULL	NULL	NULL
+newrel_m3544	BIGINT	YES	NULL	NULL	NULL
+newrel_m4554	BIGINT	YES	NULL	NULL	NULL
+newrel_m5564	BIGINT	YES	NULL	NULL	NULL
+newrel_m65	BIGINT	YES	NULL	NULL	NULL
+newrel_f014	BIGINT	YES	NULL	NULL	NULL
+newrel_f1524	BIGINT	YES	NULL	NULL	NULL
+newrel_f2534	BIGINT	YES	NULL	NULL	NULL
+newrel_f3544	BIGINT	YES	NULL	NULL	NULL
+newrel_f4554	BIGINT	YES	NULL	NULL	NULL
+newrel_f5564	BIGINT	YES	NULL	NULL	NULL
+newrel_f65	BIGINT	YES	NULL	NULL	NULL
+
--- a/external/duckdb/test/sql/copy/csv/auto/test_double_quoted_header.test
+++ b/external/duckdb/test/sql/copy/csv/auto/test_double_quoted_header.test
@@ -0,0 +1,17 @@
+# name: test/sql/copy/csv/auto/test_double_quoted_header.test
+# group: [auto]
+
+statement ok
+PRAGMA enable_verification
+
+query IIIIII
+describe from 'data/csv/double_quoted_header.csv';
+----
+foo "bar	BIGINT	YES	NULL	NULL	NULL
+name	VARCHAR	YES	NULL	NULL	NULL
+
+query II
+from 'data/csv/double_quoted_header.csv';
+----
+1	rob
+2	sally
--- a/external/duckdb/test/sql/copy/csv/auto/test_early_out.test
+++ b/external/duckdb/test/sql/copy/csv/auto/test_early_out.test
@@ -0,0 +1,11 @@
+# name: test/sql/copy/csv/auto/test_early_out.test
+# group: [auto]
+
+statement ok
+PRAGMA enable_verification
+
+statement error
+SELECT *
+FROM read_csv('data/csv/auto/early_out_error.csv', buffer_size = 8, maximum_line_size = 8, auto_detect = false, columns = {'a': 'integer','b': 'integer','c': 'integer'}, header = true)
+----
+Error when converting column "b". Could not convert string "\n" to 'INTEGER'
--- a/external/duckdb/test/sql/copy/csv/auto/test_fallback_all_varchar.test_slow
+++ b/external/duckdb/test/sql/copy/csv/auto/test_fallback_all_varchar.test_slow
@@ -0,0 +1,43 @@
+# name: test/sql/copy/csv/auto/test_fallback_all_varchar.test_slow
+# description: Test optional parameters for read csv
+# group: [auto]
+
+statement ok
+PRAGMA enable_verification
+
+
+statement ok
+PRAGMA verify_parallelism
+
+# CSV file with irregularity in first column and default sample size
+statement ok
+CREATE TABLE test AS SELECT * FROM read_csv_auto ('data/csv/auto/test_fallback.csv');
+
+query TTTT
+SELECT typeof(TestDoubleError), typeof(TestDouble), typeof(TestText), typeof(TestInteger) FROM test LIMIT 1
+----
+VARCHAR	DOUBLE	VARCHAR	BIGINT
+
+statement ok
+DROP TABLE test
+
+loop i 1 100
+
+# CSV file with irregularity in first column and small sample size
+statement error
+CREATE TABLE test AS SELECT * FROM read_csv_auto ('data/csv/auto/test_fallback.csv', SAMPLE_SIZE=1);
+----
+Column TestDoubleError is being converted as type DOUBLE
+
+endloop
+# CSV file with irregularity in first column, small sample size and fallback activated
+statement ok
+CREATE TABLE test AS SELECT * FROM read_csv_auto ('data/csv/auto/test_fallback.csv', SAMPLE_SIZE=1, ALL_VARCHAR=1);
+
+query TTTT
+SELECT typeof(TestDoubleError), typeof(TestDouble), typeof(TestText), typeof(TestInteger) FROM test LIMIT 1
+----
+VARCHAR	VARCHAR	VARCHAR	VARCHAR
+
+statement ok
+DROP TABLE test
--- a/external/duckdb/test/sql/copy/csv/auto/test_header_completion.test
+++ b/external/duckdb/test/sql/copy/csv/auto/test_header_completion.test
@@ -0,0 +1,112 @@
+# name: test/sql/copy/csv/auto/test_header_completion.test
+# description: Test csv header completion
+# group: [auto]
+
+statement ok
+PRAGMA enable_verification
+
+
+# CSV file with one missing header
+statement ok
+CREATE TABLE test AS SELECT * FROM read_csv_auto ('data/csv/auto/missing_header_col.csv');
+
+query ITT
+SELECT a, column1, c FROM test ORDER BY a;
+----
+123	TEST1	text1
+345	TEST1	text2
+
+statement ok
+DROP TABLE test;
+
+# CSV file with one duplicate header
+statement ok
+CREATE TABLE test AS SELECT * FROM read_csv_auto ('data/csv/auto/duplicate_header_col.csv');
+
+query ITT
+SELECT a, b, a_1 FROM test ORDER BY a;
+----
+123	TEST2	text1
+345	TEST2	text2
+
+statement ok
+DROP TABLE test;
+
+# CSV file with one duplicate header and collision
+statement ok
+CREATE TABLE test AS SELECT * FROM read_csv_auto ('data/csv/auto/duplicate_header_collision.csv');
+
+query ITTT
+SELECT a, b, a_1, a_1_1 FROM test ORDER BY a;
+----
+123	TEST2	text1	text1
+345	TEST2	text2	text2
+
+statement ok
+DROP TABLE test;
+
+# CSV file with all column names missing
+statement ok
+CREATE TABLE test AS SELECT * FROM read_csv_auto ('data/csv/auto/empty_header.csv');
+
+query ITT
+SELECT column0, column1, column2 FROM test ORDER BY column0;
+----
+123	TEST3	text1
+345	TEST3	text2
+
+statement ok
+DROP TABLE test;
+
+# CSV file with 12 columns and all but one column name missing
+statement ok
+CREATE TABLE test AS SELECT * FROM read_csv_auto ('data/csv/auto/missing_many_col.csv');
+
+query ITT
+SELECT a, column01, column12 FROM test;
+----
+123	TEST2	value1
+345	TEST2	value2
+
+statement ok
+DROP TABLE test;
+
+# CSV file with 12 equally called columns
+statement ok
+CREATE TABLE test AS SELECT * FROM read_csv_auto ('data/csv/auto/duplicate_header_columns.csv');
+
+query IIIT
+SELECT a, a_8, a_9, column12 FROM test;
+----
+123	NULL	NULL	value1
+345	NULL	NULL	value2
+
+statement ok
+DROP TABLE test;
+
+# CSV file with 10 equally called columns, one named column12 and column 11 and 12 missing
+statement ok
+CREATE TABLE test AS SELECT * FROM read_csv_auto ('data/csv/auto/test_header_mix.csv');
+
+query IIIIIT
+SELECT a, a_8, a_9, column12, column11, column12_1 FROM test;
+----
+123	NULL	NULL	NULL	NULL	value1
+345	NULL	NULL	NULL	NULL	value2
+
+statement ok
+DROP TABLE test;
+
+# CSV file with 12 unnamed columns and check for correct naming
+statement ok
+CREATE TABLE test AS SELECT * FROM read_csv_auto ('data/csv/auto/unnamed_columns.csv');
+
+query ITTIIIIIIIIIT
+SELECT column00, column01, column02, column03, column04, column05, column06, column07, column08, column09, column10, column11, column12 FROM test;
+----
+123	TEST2	text1	NULL	NULL	NULL	NULL	NULL	NULL	NULL	NULL	NULL	value1
+345	TEST2	text2	NULL	NULL	NULL	NULL	NULL	NULL	NULL	NULL	NULL	value2
+
+statement ok
+DROP TABLE test;
+
--- a/external/duckdb/test/sql/copy/csv/auto/test_header_detection.test
+++ b/external/duckdb/test/sql/copy/csv/auto/test_header_detection.test
@@ -0,0 +1,176 @@
+# name: test/sql/copy/csv/auto/test_header_detection.test
+# description: Test csv header detection
+# group: [auto]
+
+statement ok
+PRAGMA enable_verification
+
+
+# CSV file with two lines, none header
+statement ok
+CREATE TABLE test AS SELECT * FROM read_csv_auto ('data/csv/auto/no_header.csv');
+
+query RTT
+SELECT column0, column1, column2 FROM test ORDER BY column0;
+----
+123.000000	TEST1	2000-12-12
+345.000000	TEST1	2000-12-13
+
+statement ok
+DROP TABLE test;
+
+# CSV file with two lines, one header
+statement ok
+CREATE TABLE test AS SELECT * FROM read_csv_auto ('data/csv/auto/single_header.csv');
+
+query RTT
+SELECT number, text, date FROM test ORDER BY number;
+----
+345.000000	TEST2	2000-12-13
+
+statement ok
+DROP TABLE test;
+
+# CSV file with three lines, one header, one skip row
+statement ok
+CREATE TABLE test AS SELECT * FROM read_csv_auto ('data/csv/auto/skip_row.csv');
+
+query RTT
+SELECT number, text, date FROM test ORDER BY number;
+----
+345.000000	TEST3	2000-12-13
+
+statement ok
+DROP TABLE test;
+
+# CSV file with three lines, one header, two skip rows
+statement ok
+CREATE TABLE test AS SELECT * FROM read_csv_auto ('data/csv/auto/multiple_skip_row.csv');
+
+query RTT
+SELECT number, text, date FROM test ORDER BY number;
+----
+345.000000	TEST4	2000-12-13
+
+statement ok
+DROP TABLE test;
+
+# CSV file with two lines both only strings
+statement ok
+CREATE TABLE test AS SELECT * FROM read_csv_auto ('data/csv/auto/varchar_multi_line.csv', header = 0);
+
+query TTT
+SELECT * FROM test ORDER BY column0;
+----
+Alice	StreetA	TEST5
+Bob	StreetB	TEST5
+
+statement ok
+DROP TABLE test;
+
+# CSV file with one line, two columns, only strings
+statement ok
+CREATE TABLE test AS SELECT * FROM read_csv_auto ('data/csv/auto/varchar_single_line.csv', header = 0);
+
+query TT
+SELECT column0, column1 FROM test ORDER BY column0;
+----
+Alice	StreetA
+
+statement ok
+DROP TABLE test;
+
+# CSV file with one line, two columns - one numeric, one string
+statement ok
+CREATE TABLE test AS SELECT * FROM read_csv_auto ('data/csv/auto/mixed_single_line.csv');
+
+query IT
+SELECT column0, column1 FROM test ORDER BY column0;
+----
+1	StreetA
+
+statement ok
+DROP TABLE test;
+
+# CSV file with one line, one string column
+statement ok
+CREATE TABLE test AS SELECT * FROM read_csv_auto ('data/csv/auto/single_value.csv');
+
+query T
+SELECT * FROM test;
+----
+
+statement ok
+DROP TABLE test;
+
+# CSV file with one line, one numeric column
+statement ok
+CREATE TABLE test AS SELECT * FROM read_csv_auto ('data/csv/auto/single_numeric.csv');
+
+query I
+SELECT * FROM test;
+----
+1
+
+statement ok
+DROP TABLE test;
+
+# CSV with UTF-8 BOM marker that could mess up the header line parsing
+statement ok
+CREATE TABLE test AS SELECT * FROM read_csv_auto('data/csv/auto/utf8bom.csv');
+
+query II
+SELECT * FROM test;
+----
+1	Mark
+2	Hannes
+
+query I
+SELECT id FROM test;
+----
+1
+2
+
+statement ok
+DROP TABLE test;
+
+statement ok
+CREATE TABLE my_varchars(a VARCHAR, b VARCHAR, c VARCHAR);
+
+statement ok
+INSERT INTO my_varchars VALUES ('Hello', 'Beautiful', 'World');
+
+statement ok
+COPY my_varchars TO '__TEST_DIR__/varchar_header.csv' (HEADER 1);
+
+statement ok
+COPY my_varchars TO '__TEST_DIR__/varchar_no_header.csv' (HEADER 0);
+
+statement ok
+COPY my_varchars FROM '__TEST_DIR__/varchar_header.csv' ;
+
+statement ok
+COPY my_varchars FROM '__TEST_DIR__/varchar_no_header.csv' (HEADER 0);
+
+query III
+FROM my_varchars ;
+----
+Hello	Beautiful	World
+Hello	Beautiful	World
+Hello	Beautiful	World
+
+statement ok
+COPY my_varchars TO '__TEST_DIR__/big_varchar.csv';
+
+statement ok
+COPY my_varchars FROM '__TEST_DIR__/big_varchar.csv';
+
+query III
+FROM my_varchars;
+----
+Hello	Beautiful	World
+Hello	Beautiful	World
+Hello	Beautiful	World
+Hello	Beautiful	World
+Hello	Beautiful	World
+Hello	Beautiful	World
--- a/external/duckdb/test/sql/copy/csv/auto/test_normalize_names.test
+++ b/external/duckdb/test/sql/copy/csv/auto/test_normalize_names.test
@@ -0,0 +1,114 @@
+# name: test/sql/copy/csv/auto/test_normalize_names.test
+# description: Test csv header normalization
+# group: [auto]
+
+statement ok
+PRAGMA enable_verification
+
+query I
+select columns from sniff_csv('data/csv/test_commit_rollback.csv',  normalize_names = true)
+----
+[{'name': _commit, 'type': BIGINT}, {'name': _rollback, 'type': BIGINT}, {'name': _abort, 'type': BIGINT}]
+
+# CSV file with uppercase header
+statement ok
+CREATE TABLE test AS SELECT * FROM read_csv_auto ('data/csv/auto/normalize_names_1.csv', normalize_names=TRUE);
+
+query ITT
+SELECT a, b, c FROM test ORDER BY a;
+----
+123	TEST1	text1
+345	TEST1	text2
+
+statement ok
+DROP TABLE test;
+
+# CSV file with uppercase header and normalize names off
+statement ok
+CREATE TABLE test AS SELECT * FROM read_csv_auto ('data/csv/auto/normalize_names_1.csv');
+
+query ITT
+SELECT A, B, C FROM test ORDER BY a;
+----
+123	TEST1	text1
+345	TEST1	text2
+
+statement ok
+DROP TABLE test;
+
+
+query I
+select columns from sniff_csv('data/csv/auto/normalize_names_2.csv', normalize_names = true)
+----
+[{'name': _select, 'type': BIGINT}, {'name': _insert, 'type': VARCHAR}, {'name': _join, 'type': VARCHAR}]
+
+
+# CSV file with keywords in header
+statement ok
+CREATE TABLE test AS SELECT * FROM read_csv_auto ('data/csv/auto/normalize_names_2.csv', normalize_names=TRUE);
+
+query ITT
+SELECT _select, _insert, _join FROM test ORDER BY _select;
+----
+123	TEST1	text1
+345	TEST1	text2
+
+statement ok
+DROP TABLE test;
+
+# CSV file with names starting with numerics
+statement ok
+CREATE TABLE test AS SELECT * FROM read_csv_auto ('data/csv/auto/normalize_names_3.csv', normalize_names=TRUE);
+
+query ITT
+SELECT _0_a, _1_b, _9_c FROM test ORDER BY _0_a;
+----
+123	TEST1	text1
+345	TEST1	text2
+
+statement ok
+DROP TABLE test;
+
+# CSV file with accents and UTF8 characters
+statement ok
+CREATE TABLE test AS SELECT * FROM read_csv_auto ('data/csv/auto/normalize_names_4.csv', normalize_names=TRUE);
+
+query ITT
+SELECT allo, teost, _ FROM test ORDER BY allo;
+----
+123	TEST1	text1
+345	TEST1	text2
+
+statement ok
+DROP TABLE test;
+
+# CSV file with accents and UTF8 characters
+statement ok
+CREATE TABLE test AS SELECT * FROM read_csv_auto ('data/csv/auto/normalize_names_5.csv', normalize_names=TRUE);
+
+query ITT
+SELECT a, b, c FROM test ORDER BY a;
+----
+123	TEST1	text1
+345	TEST1	text2
+
+statement ok
+DROP TABLE test;
+
+# CSV file with superscripts and UTF8 characters
+statement ok
+CREATE TABLE test AS SELECT * FROM read_csv_auto ('data/csv/auto/normalize_names_6.csv', normalize_names=TRUE);
+
+query ITT
+SELECT aax, hello_world, qty_m2 FROM test ORDER BY aax;
+----
+123	TEST1	text1
+345	TEST1	text2
+
+statement ok
+DROP TABLE test;
+
+query I
+select columns from sniff_csv('data/csv/normalize.csv', normalize_names = true)
+----
+[{'name': _name, 'type': VARCHAR}, {'name': _text, 'type': VARCHAR}]
--- a/external/duckdb/test/sql/copy/csv/auto/test_sample_size.test
+++ b/external/duckdb/test/sql/copy/csv/auto/test_sample_size.test
@@ -0,0 +1,105 @@
+# name: test/sql/copy/csv/auto/test_sample_size.test
+# description: Test optional parameters for read csv
+# group: [auto]
+
+statement ok
+PRAGMA enable_verification
+
+
+# CSV file with very sparse column
+statement ok
+CREATE TABLE test AS SELECT * FROM read_csv_auto ('data/csv/auto/issue_811.csv', SAMPLE_SIZE=1);
+
+query IIII
+SELECT typeof(TestInteger), typeof(TestDouble), typeof(TestDate), typeof(TestText) FROM test LIMIT 1
+----
+BIGINT	VARCHAR	DATE	VARCHAR
+
+statement ok
+DROP TABLE test
+
+# CSV file with very sparse column
+statement ok
+CREATE TABLE test AS SELECT * FROM read_csv_auto ('data/csv/auto/issue_811.csv', SAMPLE_SIZE=-1);
+
+
+query IIII
+SELECT typeof(TestInteger), typeof(TestDouble), typeof(TestDate), typeof(TestText) FROM test LIMIT 1
+----
+BIGINT	DOUBLE	DATE	VARCHAR
+
+statement ok
+DROP TABLE test
+
+# CSV file with very sparse column and sample size 500
+statement ok
+CREATE TABLE test AS SELECT * FROM read_csv_auto ('data/csv/auto/issue_811.csv', SAMPLE_SIZE = -1);
+
+query IRTT
+SELECT TestInteger, TestDouble, TestDate, TestText FROM test WHERE TestDouble is not NULL ;
+----
+5	1.1	2015-05-01	fdf
+
+query TTTT
+SELECT typeof(TestInteger), typeof(TestDouble), typeof(TestDate), typeof(TestText) FROM test LIMIT 1;
+----
+BIGINT	DOUBLE	DATE	VARCHAR
+
+statement ok
+drop table test;
+
+# CSV file with very sparse column and number of samples 50
+statement ok
+CREATE TABLE test AS SELECT * FROM read_csv_auto ('data/csv/auto/issue_811.csv');
+
+query IRTT
+SELECT TestInteger, TestDouble, TestDate, TestText FROM test WHERE TestDouble is not NULL ;
+----
+5	1.1	2015-05-01	fdf
+
+query TTTT
+SELECT typeof(TestInteger), typeof(TestDouble), typeof(TestDate), typeof(TestText) FROM test LIMIT 1;
+----
+BIGINT	DOUBLE	DATE	VARCHAR
+
+statement ok
+drop table test;
+
+# CSV file with very sparse column with sample size 200 and number of samples 20
+statement ok
+CREATE TABLE test AS SELECT * FROM read_csv_auto ('data/csv/auto/issue_811.csv', SAMPLE_SIZE = -1);
+
+query IRTT
+SELECT TestInteger, TestDouble, TestDate, TestText FROM test WHERE TestDouble is not NULL ;
+----
+5	1.1	2015-05-01	fdf
+
+query TTTT
+SELECT typeof(TestInteger), typeof(TestDouble), typeof(TestDate), typeof(TestText) FROM test LIMIT 1;
+----
+BIGINT	DOUBLE	DATE	VARCHAR
+
+statement ok
+drop table test;
+
+# CSV file with very sparse column using copy into
+statement ok
+CREATE TABLE test (TestInteger integer, TestDouble double, TestDate varchar, TestText varchar);
+
+# CSV file with very sparse column, automatically aligns column types, small sample size
+statement ok
+COPY test FROM 'data/csv/auto/issue_811.csv' (AUTO_DETECT TRUE);
+
+statement ok
+drop table test;
+
+# CSV file with very sparse column using copy into
+statement ok
+CREATE TABLE test (TestInteger integer, TestDouble double, TestDate varchar, TestText varchar);
+
+# CSV file with very sparse column, automatically aligns column types, small sample size
+statement ok
+COPY test FROM 'data/csv/auto/issue_811.csv' (SAMPLE_SIZE -1, AUTO_DETECT TRUE);
+
+statement ok
+drop table test;
--- a/external/duckdb/test/sql/copy/csv/auto/test_sniffer_blob.test
+++ b/external/duckdb/test/sql/copy/csv/auto/test_sniffer_blob.test
@@ -0,0 +1,36 @@
+# name: test/sql/copy/csv/auto/test_sniffer_blob.test
+# description: Test reading a blob with the sniffer
+# group: [auto]
+
+statement ok
+PRAGMA enable_verification
+
+
+# This is the only way to try to trick the sniffer into checking blobs and it is not valid
+statement error
+select count(*) from read_csv('data/csv/test/blob.csv',auto_type_candidates=['blob'])
+----
+Auto Type Candidate of type BLOB is not accepted as a valid input
+
+# All this is cool and should work.
+
+query I
+select count(*) from read_csv('data/csv/test/blob.csv',types=['blob'], header = 0)
+----
+1
+
+query I
+select count(*) from read_csv('data/csv/test/blob.csv',columns={'col1': 'BLOB'})
+----
+1
+
+statement ok
+create table t ( a blob)
+
+statement ok
+COPY t FROM 'data/csv/test/blob.csv';
+
+query I
+select count(*) from read_csv('data/csv/test/blob.csv',columns={'col1': 'BLOB'})
+----
+1
--- a/external/duckdb/test/sql/copy/csv/auto/test_sniffer_empty_start_value.test
+++ b/external/duckdb/test/sql/copy/csv/auto/test_sniffer_empty_start_value.test
@@ -0,0 +1,14 @@
+# name: test/sql/copy/csv/auto/test_sniffer_empty_start_value.test
+# description: Test reading a value with empty spaces at the beginning
+# group: [auto]
+
+statement ok
+PRAGMA enable_verification
+
+query III
+from read_csv('data/csv/empty_space_start_value.csv')
+----
+1968	86	Greetings
+1970	17	Bloody Mama
+1970	73	Hi, Mom!
+1971	40	Born to Win
--- a/external/duckdb/test/sql/copy/csv/auto/test_timings_csv.test
+++ b/external/duckdb/test/sql/copy/csv/auto/test_timings_csv.test
@@ -0,0 +1,18 @@
+# name: test/sql/copy/csv/auto/test_timings_csv.test
+# description: Test CSV Sample works for Gabor's timings csv file
+# group: [auto]
+
+statement ok
+PRAGMA enable_verification
+
+
+statement ok
+PRAGMA verify_parallelism
+
+statement ok
+CREATE OR REPLACE TABLE timings(tool string, sf float, day string, batch_type string, q string, parameters string, time float);
+
+query I
+COPY timings FROM 'data/csv/timings.csv' (HEADER, DELIMITER '|')
+----
+1095
--- a/external/duckdb/test/sql/copy/csv/auto/test_type_candidates.test
+++ b/external/duckdb/test/sql/copy/csv/auto/test_type_candidates.test
@@ -0,0 +1,117 @@
+# name: test/sql/copy/csv/auto/test_type_candidates.test
+# description: Test Type Candidates for auto_csv
+# group: [auto]
+
+statement ok
+PRAGMA enable_verification
+
+statement ok
+create table t (a integer, b double, c varchar)
+
+statement ok
+insert into t values (1,1.1,'bla');
+
+statement ok
+COPY (SELECT * from t) TO '__TEST_DIR__/csv_file.csv'  (FORMAT CSV, DELIMITER '|', HEADER 0);
+
+query III
+SELECT * FROM read_csv_auto ('__TEST_DIR__/csv_file.csv');
+----
+1	1.1	bla
+
+query TTT
+SELECT typeof(column0), typeof(column1), typeof(column2) FROM read_csv_auto ('__TEST_DIR__/csv_file.csv');
+----
+BIGINT	DOUBLE	VARCHAR
+
+query III
+SELECT * FROM read_csv_auto ('__TEST_DIR__/csv_file.csv', auto_type_candidates=['BIGINT', 'DOUBLE', 'VARCHAR']);
+----
+1	1.1	bla
+
+statement error
+SELECT * FROM read_csv_auto ('__TEST_DIR__/csv_file.csv', auto_type_candidates=['MAP']);
+----
+Value "MAP" can not be converted to a DuckDB Type.
+
+query TTT
+SELECT typeof(column0), typeof(column1), typeof(column2) FROM read_csv_auto ('__TEST_DIR__/csv_file.csv', auto_type_candidates=['BIGINT', 'DOUBLE', 'VARCHAR']);
+----
+BIGINT	DOUBLE	VARCHAR
+
+
+query III
+SELECT * FROM read_csv_auto ('__TEST_DIR__/csv_file.csv', auto_type_candidates=['VARCHAR'], header = 0);
+----
+1	1.1	bla
+
+query TTT
+SELECT typeof(column0), typeof(column1), typeof(column2) FROM read_csv_auto ('__TEST_DIR__/csv_file.csv', auto_type_candidates=['VARCHAR'], header = 0);
+----
+VARCHAR	VARCHAR	VARCHAR
+
+query III
+SELECT * FROM read_csv_auto ('__TEST_DIR__/csv_file.csv', auto_type_candidates=['BIGINT']);
+----
+1	1.1	bla
+
+query TTT
+SELECT typeof(column0), typeof(column1), typeof(column2) FROM read_csv_auto ('__TEST_DIR__/csv_file.csv', auto_type_candidates=['BIGINT']);
+----
+BIGINT	VARCHAR	VARCHAR
+
+
+query III
+SELECT * FROM read_csv_auto ('__TEST_DIR__/csv_file.csv', auto_type_candidates=['BIGINT','VARCHAR']);
+----
+1	1.1	bla
+
+query TTT
+SELECT typeof(column0), typeof(column1), typeof(column2) FROM read_csv_auto ('__TEST_DIR__/csv_file.csv', auto_type_candidates=['BIGINT','VARCHAR']);
+----
+BIGINT	VARCHAR	VARCHAR
+
+query III
+SELECT * FROM read_csv_auto ('__TEST_DIR__/csv_file.csv', auto_type_candidates=['FLOAT','VARCHAR']);
+----
+1.0	1.1	bla
+
+query TTT
+SELECT typeof(column0), typeof(column1), typeof(column2) FROM read_csv_auto ('__TEST_DIR__/csv_file.csv', auto_type_candidates=['FLOAT','VARCHAR']);
+----
+FLOAT	FLOAT	VARCHAR
+
+query III
+SELECT * FROM read_csv_auto ('__TEST_DIR__/csv_file.csv', auto_type_candidates=['SMALLINT','BIGINT', 'DOUBLE', 'FLOAT','VARCHAR']);
+----
+1	1.1	bla
+
+query TTT
+SELECT typeof(column0), typeof(column1), typeof(column2) FROM read_csv_auto ('__TEST_DIR__/csv_file.csv', auto_type_candidates=['SMALLINT','BIGINT', 'DOUBLE', 'FLOAT','VARCHAR']);
+----
+SMALLINT	FLOAT	VARCHAR
+
+query III
+SELECT * FROM read_csv_auto ('__TEST_DIR__/csv_file.csv', auto_type_candidates=['SMALLINT','BIGINT', 'DOUBLE', 'FLOAT','VARCHAR','SMALLINT','BIGINT', 'DOUBLE', 'FLOAT','VARCHAR']);
+----
+1	1.1	bla
+
+query TTT
+SELECT typeof(column0), typeof(column1), typeof(column2) FROM read_csv_auto ('__TEST_DIR__/csv_file.csv', auto_type_candidates=['SMALLINT','BIGINT', 'DOUBLE', 'FLOAT','VARCHAR','SMALLINT','BIGINT', 'DOUBLE', 'FLOAT','VARCHAR']);
+----
+SMALLINT	FLOAT	VARCHAR
+
+statement error
+SELECT * FROM read_csv_auto ('__TEST_DIR__/csv_file.csv', auto_type_candidates=['USMALLINT', 'VARCHAR']);
+----
+Auto Type Candidate of type USMALLINT is not accepted as a valid input
+
+statement error
+SELECT * FROM read_csv_auto ('__TEST_DIR__/csv_file.csv', auto_type_candidates=['bla', 'VARCHAR'])
+----
+Type with name bla does not exist!
+
+statement error
+SELECT * FROM read_csv_auto ('__TEST_DIR__/csv_file.csv', auto_type_candidates=[]);
+----
+auto_type_candidates requires at least one type
--- a/external/duckdb/test/sql/copy/csv/auto/test_type_detection.test
+++ b/external/duckdb/test/sql/copy/csv/auto/test_type_detection.test
@@ -0,0 +1,213 @@
+# name: test/sql/copy/csv/auto/test_type_detection.test
+# description: Test csv type detection
+# group: [auto]
+
+statement ok
+PRAGMA enable_verification
+
+
+# a CSV file with many strings
+statement ok
+CREATE TABLE test AS SELECT * FROM read_csv_auto ('data/csv/auto/large_mixed_data.csv', SAMPLE_SIZE=-1);
+
+query ITR
+SELECT linenr, mixed_string, mixed_double FROM test LIMIT 3;
+----
+1	1	1.000000
+2	2	2.000000
+3	3	3.000000
+
+query TTT
+SELECT typeof(linenr), typeof(mixed_string), typeof(mixed_double) FROM test LIMIT 1;
+----
+BIGINT	VARCHAR	DOUBLE
+
+query ITR
+SELECT linenr, mixed_string, mixed_double FROM test WHERE linenr > 27000 LIMIT 3;
+----
+27001	1	1.000000
+27002	2	2.000000
+27003	3	3.500000
+
+query I
+SELECT count(*) FROM test;
+----
+27003
+
+statement ok
+DROP TABLE test;
+
+# a CSV file containing time, date and timestamp columns
+statement ok
+CREATE TABLE test AS SELECT * FROM read_csv_auto ('data/csv/auto/time_date_timestamp.csv');
+
+query ITTTT
+SELECT a, b, t, d, ts FROM test ORDER BY a;
+----
+123	TEST2	12:12:12	2000-01-01	2000-01-01 12:12:00
+345	TEST2	14:15:30	2002-02-02	2002-02-02 14:15:00
+346	TEST2	15:16:17	2004-12-13	2004-12-13 15:16:00
+
+
+query TTTTT
+SELECT typeof(a), typeof(b), typeof(t), typeof(d), typeof(ts) FROM test LIMIT 1;
+----
+BIGINT	VARCHAR	TIME	DATE	TIMESTAMP
+
+statement ok
+DROP TABLE test;
+
+# a CSV file containing time and date columns with leading/trailing chars
+statement ok
+CREATE TABLE test AS SELECT * FROM read_csv_auto ('data/csv/auto/time_date_timestamp_trailing.csv');
+
+query ITTTTT
+SELECT a, b, t, tf, d, df FROM test ORDER BY a;
+----
+123	TEST2	12:12:12	12:12:12	2000-01-01	2000-01-01
+345	TEST2	14:15:30	14:15:30	2002-02-02	2000-01-01 a
+346	TEST2	15:16:17	15:16:17 01	2004-12-13	2000-01-01
+
+query TTTTTT
+SELECT typeof(a), typeof(b), typeof(t), typeof(tf), typeof(d), typeof(df) FROM test LIMIT 1;
+----
+BIGINT	VARCHAR	TIME	VARCHAR	DATE	VARCHAR
+
+statement ok
+DROP TABLE test;
+
+# a CSV file containing time, date and timestamp columns in mm-dd-yyyy (12 hour)
+statement ok
+CREATE TABLE test AS SELECT * FROM read_csv_auto ('data/csv/auto/time_date_timestamp_mm-dd-yyyy.csv');
+
+query ITTTT
+SELECT a, b, t, d, ts FROM test ORDER BY a;
+----
+123	TEST2	12:12:12	2000-01-01	2000-01-01 00:12:00
+345	TEST2	14:15:30	2002-02-02	2002-02-02 14:15:00
+346	TEST2	15:16:17	2004-12-13	2004-12-13 15:16:00
+
+query TTTTT
+SELECT typeof(a), typeof(b), typeof(t), typeof(d), typeof(ts) FROM test LIMIT 1;
+----
+BIGINT	VARCHAR	TIME	DATE	TIMESTAMP
+
+statement ok
+DROP TABLE test;
+
+# a CSV file containing time, date and timestamp columns in mm-dd-yy format (12 hour)
+statement ok
+CREATE TABLE test AS SELECT * FROM read_csv_auto ('data/csv/auto/time_date_timestamp_mm-dd-yy.csv');
+
+query ITTTT
+SELECT a, b, t, d, ts FROM test ORDER BY a;
+----
+123	TEST2	12:12:12	1990-01-01	1990-01-01 00:12:00
+345	TEST2	14:15:30	2002-02-02	2002-02-02 14:15:00
+346	TEST2	15:16:17	2004-12-13	2004-12-13 15:16:00
+
+query TTTTT
+SELECT typeof(a), typeof(b), typeof(t), typeof(d), typeof(ts) FROM test LIMIT 1;
+----
+BIGINT	VARCHAR	TIME	DATE	TIMESTAMP
+
+statement ok
+DROP TABLE test;
+
+# a CSV file containing time, date and timestamp columns in dd-mm-yyyy format
+statement ok
+CREATE TABLE test AS SELECT * FROM read_csv_auto ('data/csv/auto/time_date_timestamp_dd-mm-yyyy.csv');
+
+query ITTTT
+SELECT a, b, t, d, ts FROM test ORDER BY a;
+----
+123	TEST2	12:12:12	2000-01-01	2000-01-01 12:12:00
+345	TEST2	14:15:30	2002-02-02	2002-02-02 14:15:00
+346	TEST2	15:16:17	2004-12-13	2004-12-13 15:16:00
+
+query TTTTT
+SELECT typeof(a), typeof(b), typeof(t), typeof(d), typeof(ts) FROM test LIMIT 1;
+----
+BIGINT	VARCHAR	TIME	DATE	TIMESTAMP
+
+statement ok
+DROP TABLE test;
+
+# a CSV file containing time, date and timestamp columns in dd-mm-yy format
+statement ok
+CREATE TABLE test AS SELECT * FROM read_csv_auto ('data/csv/auto/time_date_timestamp_dd-mm-yy.csv');
+
+query ITTTT
+SELECT a, b, t, d, ts FROM test ORDER BY a;
+----
+123	TEST2	12:12:12	2000-01-01	1990-01-01 12:12:00
+345	TEST2	14:15:30	2002-02-02	2002-02-02 14:15:00
+346	TEST2	15:16:17	2004-12-13	2004-12-13 15:16:00
+
+query TTTTT
+SELECT typeof(a), typeof(b), typeof(t), typeof(d), typeof(ts) FROM test LIMIT 1;
+----
+BIGINT	VARCHAR	TIME	DATE	TIMESTAMP
+
+statement ok
+DROP TABLE test;
+
+# a CSV file containing time, date and timestamp columns in yyyy.mm.dd format
+statement ok
+CREATE TABLE test AS SELECT * FROM read_csv_auto ('data/csv/auto/time_date_timestamp_yyyy.mm.dd.csv');
+
+query ITTTT
+SELECT a, b, t, d, ts FROM test ORDER BY a;
+----
+123	TEST2	12:12:12	2000-01-01	2000-01-01 12:12:00
+345	TEST2	14:15:30	2002-02-02	2002-02-02 14:15:00
+346	TEST2	15:16:17	2004-12-13	2004-12-13 15:16:00
+
+
+query TTTTT
+SELECT typeof(a), typeof(b), typeof(t), typeof(d), typeof(ts) FROM test LIMIT 1;
+----
+BIGINT	VARCHAR	TIME	DATE	TIMESTAMP
+
+statement ok
+DROP TABLE test;
+
+# a CSV file containing time, date and timestamp columns in yy.mm.dd format
+statement ok
+CREATE TABLE test AS SELECT * FROM read_csv_auto ('data/csv/auto/time_date_timestamp_yy.mm.dd.csv');
+
+query ITTTT
+SELECT a, b, t, d, ts FROM test ORDER BY a;
+----
+123	TEST2	12:12:12	1990-01-01	1990-01-01 00:12:00
+345	TEST2	14:15:30	2002-02-02	2002-02-02 14:15:00
+346	TEST2	15:16:17	2004-12-13	2004-12-13 15:16:00
+
+query TTTTT
+SELECT typeof(a), typeof(b), typeof(t), typeof(d), typeof(ts) FROM test LIMIT 1;
+----
+BIGINT	VARCHAR	TIME	DATE	TIMESTAMP
+
+statement ok
+DROP TABLE test;
+
+# a CSV file containing integer bool value
+statement ok
+CREATE TABLE test AS SELECT * FROM read_csv_auto ('data/csv/auto/int_bol.csv');
+
+query I
+SELECT i FROM test ORDER BY i;
+----
+1
+2
+3
+4
+
+query TT
+SELECT typeof(i), typeof(b) FROM test LIMIT 1;
+----
+BIGINT	BOOLEAN
+
+statement ok
+DROP TABLE test;
+
--- a/external/duckdb/test/sql/copy/csv/auto_glob_directory.test
+++ b/external/duckdb/test/sql/copy/csv/auto_glob_directory.test
@@ -0,0 +1,12 @@
+# name: test/sql/copy/csv/auto_glob_directory.test
+# description: Test auto globbing a directory
+# group: [csv]
+
+statement ok
+COPY (SELECT i%2 AS grp, i FROM range(1000) t(i)) TO '__TEST_DIR__/partitioned_glob_csv' (FORMAT csv, PARTITION_BY (grp));
+
+query II
+SELECT grp, COUNT(*) FROM read_csv('__TEST_DIR__/partitioned_glob_csv') GROUP BY ALL ORDER BY ALL
+----
+0	500
+1	500
--- a/external/duckdb/test/sql/copy/csv/batched_write/batch_csv_mixed_batches.test_slow
+++ b/external/duckdb/test/sql/copy/csv/batched_write/batch_csv_mixed_batches.test_slow
@@ -0,0 +1,182 @@
+# name: test/sql/copy/csv/batched_write/batch_csv_mixed_batches.test_slow
+# description: Test batch CSV write with mixed batches
+# group: [batched_write]
+
+require parquet
+
+statement ok
+PRAGMA enable_verification
+
+statement ok
+COPY (FROM range(100000) tbl(i)) TO '__TEST_DIR__/mix_batches_small.parquet' (ROW_GROUP_SIZE 5000)
+
+statement ok
+COPY (FROM range(100000, 400000) tbl(i)) TO '__TEST_DIR__/mix_batches_large.parquet' (ROW_GROUP_SIZE 200000)
+
+statement ok
+COPY (FROM range(400000, 700000) tbl(i)) TO '__TEST_DIR__/mix_batches_odd.parquet' (ROW_GROUP_SIZE 999)
+
+statement ok
+COPY (FROM range(700000, 1000000) tbl(i)) TO '__TEST_DIR__/mix_batches_odd_again.parquet' (ROW_GROUP_SIZE 99979)
+
+# create views that read the batches
+statement ok
+CREATE VIEW v1 AS SELECT * FROM parquet_scan(['__TEST_DIR__/mix_batches_small.parquet', '__TEST_DIR__/mix_batches_large.parquet', '__TEST_DIR__/mix_batches_odd.parquet',  '__TEST_DIR__/mix_batches_odd_again.parquet'])
+
+statement ok
+CREATE VIEW v2 AS FROM v1 WHERE (i//10000)%2=0;
+
+statement ok
+CREATE VIEW v3 AS FROM v1 WHERE (i//10000)%2=0 OR (i>200000 AND i < 400000) OR (i>600000 AND i < 800000);
+
+# empty table
+statement ok
+CREATE VIEW v4 AS FROM v1 WHERE i>998 AND i<1000 AND i%2=0
+
+loop i 0 2
+
+query I
+COPY v1 TO '__TEST_DIR__/mixed_batches_v1.csv' (HEADER)
+----
+1000000
+
+query I
+CREATE TABLE mixed_batches_v1 AS FROM '__TEST_DIR__/mixed_batches_v1.csv'
+----
+1000000
+
+foreach table v1 mixed_batches_v1
+
+query IIIII
+SELECT SUM(i), MIN(i), MAX(i), COUNT(i), COUNT(*) FROM ${table}
+----
+499999500000	0	999999	1000000	1000000
+
+query I
+SELECT * FROM ${table} LIMIT 5 OFFSET 99998
+----
+99998
+99999
+100000
+100001
+100002
+
+endloop
+
+# now do the same, but filter out half of the values
+query I
+COPY v2 TO '__TEST_DIR__/mixed_batches_v2.csv' (HEADER)
+----
+500000
+
+query I
+CREATE TABLE mixed_batches_v2 AS FROM '__TEST_DIR__/mixed_batches_v2.csv'
+----
+500000
+
+foreach table v2 mixed_batches_v2
+
+query IIIII
+SELECT SUM(i), MIN(i), MAX(i), COUNT(i), COUNT(*) FROM ${table}
+----
+247499750000	0	989999	500000	500000
+
+query I
+SELECT * FROM ${table} LIMIT 5 OFFSET 99998
+----
+189998
+189999
+200000
+200001
+200002
+
+endloop
+
+# do it again, but this time only filter out SOME small batches
+query I
+COPY v3 TO '__TEST_DIR__/mixed_batches_v3.csv' (HEADER)
+----
+700000
+
+query I
+CREATE TABLE mixed_batches_v3 AS FROM '__TEST_DIR__/mixed_batches_v3.csv'
+----
+700000
+
+foreach table v3 mixed_batches_v3
+
+query IIIII
+SELECT SUM(i), MIN(i), MAX(i), COUNT(i), COUNT(*) FROM ${table}
+----
+348499650000	0	989999	700000	700000
+
+query I
+SELECT * FROM ${table} LIMIT 5 OFFSET 9999
+----
+9999
+20000
+20001
+20002
+20003
+
+endloop
+
+# now with an empty table
+query I
+COPY v4 TO '__TEST_DIR__/mixed_batches_v4.csv' (HEADER)
+----
+0
+
+query I
+CREATE TABLE mixed_batches_v4 AS SELECT i::BIGINT as i FROM read_csv_auto('__TEST_DIR__/mixed_batches_v4.csv')
+----
+0
+
+foreach table v4 mixed_batches_v4
+
+query IIIII
+SELECT SUM(i), MIN(i), MAX(i), COUNT(i), COUNT(*) FROM ${table}
+----
+NULL	NULL	NULL	0	0
+
+query I
+SELECT * FROM ${table} LIMIT 5
+----
+
+endloop
+
+statement ok
+DROP TABLE mixed_batches_v1
+
+statement ok
+DROP TABLE mixed_batches_v2
+
+statement ok
+DROP TABLE mixed_batches_v3
+
+statement ok
+DROP TABLE mixed_batches_v4
+
+statement ok
+drop view if exists v2;
+
+statement ok
+drop view if exists v3;
+
+statement ok
+drop view if exists v4;
+
+# create views that read the batches using unions
+statement ok
+CREATE OR REPLACE VIEW v1 AS FROM '__TEST_DIR__/mix_batches_small.parquet' UNION ALL FROM '__TEST_DIR__/mix_batches_large.parquet' UNION ALL FROM '__TEST_DIR__/mix_batches_odd.parquet' UNION ALL FROM '__TEST_DIR__/mix_batches_odd_again.parquet'
+
+statement ok
+CREATE OR REPLACE VIEW v2 AS FROM v1 WHERE (i//10000)%2=0;
+
+statement ok
+CREATE OR REPLACE VIEW v3 AS FROM v1 WHERE (i//10000)%2=0 OR (i>200000 AND i < 400000) OR (i>600000 AND i < 800000);
+
+statement ok
+CREATE OR REPLACE VIEW v4 AS FROM v1 WHERE i>998 AND i<1000 AND i%2=0
+
+endloop
--- a/external/duckdb/test/sql/copy/csv/batched_write/batch_csv_write.test_slow
+++ b/external/duckdb/test/sql/copy/csv/batched_write/batch_csv_write.test_slow
@@ -0,0 +1,89 @@
+# name: test/sql/copy/csv/batched_write/batch_csv_write.test_slow
+# description: Batched copy to file
+# group: [batched_write]
+
+statement ok
+PRAGMA enable_verification
+
+statement ok
+CREATE TABLE integers AS SELECT i, i // 5 AS j FROM range(1000000) t(i) ;
+
+statement ok
+COPY integers TO '__TEST_DIR__/batched_integers.csv' (HEADER);
+
+statement ok
+CREATE TABLE integers_copied AS FROM '__TEST_DIR__/batched_integers.csv'
+
+query IIIII
+SELECT SUM(i), SUM(j), COUNT(*), COUNT(i), COUNT(j) FROM integers_copied
+----
+499999500000	99999500000	1000000	1000000	1000000
+
+query II
+SELECT * FROM integers_copied LIMIT 5
+----
+0	0
+1	0
+2	0
+3	0
+4	0
+
+query II
+SELECT * FROM integers_copied LIMIT 5 OFFSET 99997
+----
+99997	19999
+99998	19999
+99999	19999
+100000	20000
+100001	20000
+
+query II
+SELECT * FROM integers_copied QUALIFY i<=lag(i) over ()
+----
+
+# now with filters
+statement ok
+CREATE VIEW v1 AS SELECT * FROM integers WHERE (i%2=0 AND i<300000) OR (i BETWEEN 500000 AND 700000)
+
+statement ok
+COPY v1 TO '__TEST_DIR__/batched_integers_filters.csv' (HEADER);
+
+statement ok
+CREATE TABLE integers_filtered AS FROM '__TEST_DIR__/batched_integers_filters.csv'
+
+
+foreach table v1 integers_filtered
+
+query IIIII
+SELECT SUM(i), SUM(j), COUNT(*), COUNT(i), COUNT(j) FROM ${table}
+----
+142500450000	28499950000	350001	350001	350001
+
+query II
+SELECT * FROM ${table} LIMIT 5
+----
+0	0
+2	0
+4	0
+6	1
+8	1
+
+query II
+SELECT * FROM ${table} LIMIT 5 OFFSET 99997
+----
+199994	39998
+199996	39999
+199998	39999
+200000	40000
+200002	40000
+
+query II
+SELECT * FROM ${table} LIMIT 5 OFFSET 300000
+----
+650000	130000
+650001	130000
+650002	130000
+650003	130000
+650004	130000
+
+endloop
--- a/external/duckdb/test/sql/copy/csv/batched_write/batch_json_mixed_batches.test_slow
+++ b/external/duckdb/test/sql/copy/csv/batched_write/batch_json_mixed_batches.test_slow
@@ -0,0 +1,161 @@
+# name: test/sql/copy/csv/batched_write/batch_json_mixed_batches.test_slow
+# description: Test batch CSV write with mixed batches
+# group: [batched_write]
+
+require parquet
+
+require json
+
+statement ok
+PRAGMA enable_verification
+
+statement ok
+COPY (FROM range(100000) tbl(i)) TO '__TEST_DIR__/mix_batches_small.parquet' (ROW_GROUP_SIZE 5000)
+
+statement ok
+COPY (FROM range(100000, 400000) tbl(i)) TO '__TEST_DIR__/mix_batches_large.parquet' (ROW_GROUP_SIZE 200000)
+
+statement ok
+COPY (FROM range(400000, 700000) tbl(i)) TO '__TEST_DIR__/mix_batches_odd.parquet' (ROW_GROUP_SIZE 999)
+
+statement ok
+COPY (FROM range(700000, 1000000) tbl(i)) TO '__TEST_DIR__/mix_batches_odd_again.parquet' (ROW_GROUP_SIZE 99979)
+
+# create views that read the batches
+statement ok
+CREATE VIEW v1 AS SELECT * FROM parquet_scan(['__TEST_DIR__/mix_batches_small.parquet', '__TEST_DIR__/mix_batches_large.parquet', '__TEST_DIR__/mix_batches_odd.parquet',  '__TEST_DIR__/mix_batches_odd_again.parquet'])
+
+statement ok
+CREATE VIEW v2 AS FROM v1 WHERE (i//10000)%2=0;
+
+statement ok
+CREATE VIEW v3 AS FROM v1 WHERE (i//10000)%2=0 OR (i>200000 AND i < 400000) OR (i>600000 AND i < 800000);
+
+# empty table
+statement ok
+CREATE VIEW v4 AS FROM v1 WHERE i>998 AND i<1000 AND i%2=0
+
+foreach ARRAY_SETTING TRUE FALSE
+
+query I
+COPY v1 TO '__TEST_DIR__/mixed_batches_v1.json' (ARRAY ${ARRAY_SETTING})
+----
+1000000
+
+query I
+CREATE TABLE mixed_batches_v1 AS FROM '__TEST_DIR__/mixed_batches_v1.json'
+----
+1000000
+
+foreach table v1 mixed_batches_v1
+
+query IIIII
+SELECT SUM(i), MIN(i), MAX(i), COUNT(i), COUNT(*) FROM ${table}
+----
+499999500000	0	999999	1000000	1000000
+
+query I
+SELECT * FROM ${table} LIMIT 5 OFFSET 99998
+----
+99998
+99999
+100000
+100001
+100002
+
+endloop
+
+# now do the same, but filter out half of the values
+query I
+COPY v2 TO '__TEST_DIR__/mixed_batches_v2.json' (ARRAY ${ARRAY_SETTING})
+----
+500000
+
+query I
+CREATE TABLE mixed_batches_v2 AS FROM '__TEST_DIR__/mixed_batches_v2.json'
+----
+500000
+
+foreach table v2 mixed_batches_v2
+
+query IIIII
+SELECT SUM(i), MIN(i), MAX(i), COUNT(i), COUNT(*) FROM ${table}
+----
+247499750000	0	989999	500000	500000
+
+query I
+SELECT * FROM ${table} LIMIT 5 OFFSET 99998
+----
+189998
+189999
+200000
+200001
+200002
+
+endloop
+
+# do it again, but this time only filter out SOME small batches
+query I
+COPY v3 TO '__TEST_DIR__/mixed_batches_v3.json' (ARRAY ${ARRAY_SETTING})
+----
+700000
+
+query I
+CREATE TABLE mixed_batches_v3 AS FROM '__TEST_DIR__/mixed_batches_v3.json'
+----
+700000
+
+foreach table v3 mixed_batches_v3
+
+query IIIII
+SELECT SUM(i), MIN(i), MAX(i), COUNT(i), COUNT(*) FROM ${table}
+----
+348499650000	0	989999	700000	700000
+
+query I
+SELECT * FROM ${table} LIMIT 5 OFFSET 9999
+----
+9999
+20000
+20001
+20002
+20003
+
+endloop
+
+query I
+COPY v4 TO '__TEST_DIR__/mixed_batches_v4.json' (ARRAY ${ARRAY_SETTING})
+----
+0
+
+query I
+CREATE TABLE mixed_batches_v4 AS SELECT i::BIGINT as i FROM '__TEST_DIR__/mixed_batches_v4.json' t(i)
+----
+0
+
+foreach table v4 mixed_batches_v4
+
+query IIIII
+SELECT SUM(i), MIN(i), MAX(i), COUNT(i), COUNT(*) FROM ${table}
+----
+NULL	NULL	NULL	0	0
+
+query I
+SELECT * FROM ${table} LIMIT 5
+----
+
+endloop
+
+statement ok
+DROP TABLE mixed_batches_v1
+
+statement ok
+DROP TABLE mixed_batches_v2
+
+statement ok
+DROP TABLE mixed_batches_v3
+
+statement ok
+DROP TABLE mixed_batches_v4
+
+endloop
--- a/external/duckdb/test/sql/copy/csv/batched_write/csv_write_memory_limit.test_slow
+++ b/external/duckdb/test/sql/copy/csv/batched_write/csv_write_memory_limit.test_slow
@@ -0,0 +1,32 @@
+# name: test/sql/copy/csv/batched_write/csv_write_memory_limit.test_slow
+# description: Verify data is streamed and memory limit is not exceeded in CSV write
+# group: [batched_write]
+
+require parquet
+
+require 64bit
+
+statement ok
+PRAGMA enable_verification
+
+# 100M rows, 2 BIGINT columns = 1.6GB uncompressed
+statement ok
+COPY (SELECT i, i // 5 AS j FROM range(100000000) t(i)) TO '__TEST_DIR__/large_integers.parquet'
+
+# set a memory limit of 300MB
+statement ok
+SET memory_limit='300MB'
+
+# stream from one parquet file to another
+query I
+COPY '__TEST_DIR__/large_integers.parquet' TO '__TEST_DIR__/large_integers.csv'
+----
+100000000
+
+# verify that the file is correctly written
+statement ok
+SET memory_limit='-1'
+
+query II
+SELECT * FROM '__TEST_DIR__/large_integers.parquet' EXCEPT FROM '__TEST_DIR__/large_integers.csv'
+----
--- a/external/duckdb/test/sql/copy/csv/bug_10283.test_slow
+++ b/external/duckdb/test/sql/copy/csv/bug_10283.test_slow
--- a/external/duckdb/test/sql/copy/csv/code_cov/buffer_manager_finalize.test
+++ b/external/duckdb/test/sql/copy/csv/code_cov/buffer_manager_finalize.test
@@ -0,0 +1,22 @@
+# name: test/sql/copy/csv/code_cov/buffer_manager_finalize.test
+# description: Test to reach Finalize call in the csv buffer manager for codecov
+# group: [code_cov]
+
+statement ok
+PRAGMA enable_verification
+
+statement ok
+CREATE TABLE t1 AS select i, (i+1) as j from range(0,3000) tbl(i)
+
+statement ok
+COPY t1 TO '__TEST_DIR__/t1.csv' (FORMAT CSV, DELIMITER '|', HEADER);
+
+query I
+select count(*) from '__TEST_DIR__/t1.csv'
+----
+3000
+
+query I
+select count(*) from read_csv('data/csv/empty.csv', columns=STRUCT_PACK(d := 'BIGINT'), header=0, auto_detect = false)
+----
+0
--- a/external/duckdb/test/sql/copy/csv/code_cov/csv_dialect_detection.test
+++ b/external/duckdb/test/sql/copy/csv/code_cov/csv_dialect_detection.test
@@ -0,0 +1,21 @@
+# name: test/sql/copy/csv/code_cov/csv_dialect_detection.test
+# description: Test to reach missing Dialect Detection code.
+# group: [code_cov]
+
+statement ok
+PRAGMA enable_verification
+
+query I
+SELECT * from read_csv_auto('data/csv/escape.csv', escape=']', header = 0)
+----
+"bla"
+
+query I
+SELECT * from read_csv_auto('data/csv/escape.csv', header = 0)
+----
+"]"bla]""
+
+statement error
+SELECT * from read_csv_auto('data/csv/no_opt.csv', delim = ';')
+----
+It was not possible to automatically detect the CSV parsing dialect
--- a/external/duckdb/test/sql/copy/csv/code_cov/csv_disk_reload.test
+++ b/external/duckdb/test/sql/copy/csv/code_cov/csv_disk_reload.test
@@ -0,0 +1,24 @@
+# name: test/sql/copy/csv/code_cov/csv_disk_reload.test
+# description: Test to reach Disk Reaload call in the csv buffer manager for codecov
+# group: [code_cov]
+
+statement ok
+PRAGMA enable_verification
+
+statement ok
+CREATE TABLE t1 AS select i, (i+1) as j from range(0,300000) tbl(i)
+
+statement ok
+COPY t1 TO '__TEST_DIR__/t1.csv' (FORMAT CSV, DELIMITER '|', HEADER);
+
+# Let's set a memory limit
+statement ok
+PRAGMA memory_limit='2M'
+
+statement ok
+PRAGMA threads=2
+
+query I
+select count(*) from read_csv_auto('__TEST_DIR__/t1.csv',buffer_size = 262144, sample_size=-1)
+----
+300000
--- a/external/duckdb/test/sql/copy/csv/code_cov/csv_exact_buffer_size.test
+++ b/external/duckdb/test/sql/copy/csv/code_cov/csv_exact_buffer_size.test
@@ -0,0 +1,23 @@
+# name: test/sql/copy/csv/code_cov/csv_exact_buffer_size.test
+# description: Test with exact buffer size being the file size
+# group: [code_cov]
+
+statement ok
+PRAGMA enable_verification
+
+query II
+FROM read_csv('data/csv/auto/issue_1254_rn.csv', buffer_size=10)
+----
+1	2
+1	2
+
+query II
+FROM read_csv('data/csv/auto/issue_1254_rn.csv', buffer_size=8)
+----
+1	2
+1	2
+
+query I
+select count(*) from read_csv_auto('data/csv/small_file.csv', buffer_size = 7)
+----
+2
--- a/external/duckdb/test/sql/copy/csv/code_cov/csv_sniffer_header.test
+++ b/external/duckdb/test/sql/copy/csv/code_cov/csv_sniffer_header.test
@@ -0,0 +1,37 @@
+# name: test/sql/copy/csv/code_cov/csv_sniffer_header.test
+# description: Tests to enforce codecov in csv header sniffing
+# group: [code_cov]
+
+statement ok
+PRAGMA enable_verification
+
+query I
+SELECT count(*) from read_csv_auto('data/csv/header_left_space.csv')
+----
+3
+
+statement ok
+create table t as select * from read_csv_auto('data/csv/header_normalize.csv', normalize_names=1)
+
+query IIIIII
+describe t
+----
+bla	BIGINT	YES	NULL	NULL	NULL
+bla_1	BIGINT	YES	NULL	NULL	NULL
+b_la	BIGINT	YES	NULL	NULL	NULL
+_	BIGINT	YES	NULL	NULL	NULL
+_3b	BIGINT	YES	NULL	NULL	NULL
+
+
+query III
+FROM read_csv(['data/csv/auto/sample.csv','data/csv/auto/sample.csv','data/csv/auto/sample.csv'])
+----
+c1	pedro	1992
+c2	mark	1992
+c3	oogie	2021
+c1	pedro	1992
+c2	mark	1992
+c3	oogie	2021
+c1	pedro	1992
+c2	mark	1992
+c3	oogie	2021
--- a/external/duckdb/test/sql/copy/csv/code_cov/csv_state_machine_invalid_utf.test
+++ b/external/duckdb/test/sql/copy/csv/code_cov/csv_state_machine_invalid_utf.test
@@ -0,0 +1,209 @@
+# name: test/sql/copy/csv/code_cov/csv_state_machine_invalid_utf.test
+# description: Tests related to invalid UTF-8 detection
+# group: [code_cov]
+
+# Error during sniffing
+statement error
+from read_csv_auto('data/csv/test/invalid_utf.csv')
+----
+Invalid unicode (byte sequence mismatch) detected
+
+statement error
+from read_csv_auto('data/csv/test/invalid_utf.csv')
+----
+CSV Error on Line: 1
+
+# Error during parsing
+statement error
+from read_csv('data/csv/test/invalid_utf.csv',columns = {'col1': 'VARCHAR','col2': 'VARCHAR','col3': 'VARCHAR'}, auto_detect=false, header = 0, delim = ',')
+----
+Invalid unicode (byte sequence mismatch) detected.
+
+
+statement error
+from read_csv('data/csv/test/invalid_utf.csv',columns = {'col1': 'VARCHAR','col2': 'VARCHAR','col3': 'VARCHAR'}, auto_detect=false, header = 0, delim = ',')
+----
+CSV Error on Line: 1
+
+# Test ignore errors over more complex file
+statement error
+from read_csv('data/csv/test/invalid_utf_complex.csv',columns = {'col1': 'VARCHAR','col2': 'VARCHAR','col3': 'VARCHAR'}, auto_detect=false, header = 0, delim = ',')
+----
+CSV Error on Line: 11
+
+query III
+from read_csv('data/csv/test/invalid_utf_complex.csv',columns = {'col1': 'VARCHAR','col2': 'VARCHAR','col3': 'VARCHAR'}, auto_detect=false, header = 0, delim = ',', ignore_errors=true)
+----
+valid	valid	valid
+valid	valid	valid
+valid	valid	valid
+valid	valid	valid
+valid	valid	valid
+valid	valid	valid
+valid	valid	valid
+valid	valid	valid
+valid	valid	valid
+valid	valid	valid
+valid	valid	valid
+valid	valid	valid
+valid	valid	valid
+valid	valid	valid
+valid	valid	valid
+valid	valid	valid
+valid	valid	valid
+valid	valid	valid
+valid	valid	valid
+valid	valid	valid
+
+# Test error in the second vector
+statement ok
+create table t as from read_csv('data/csv/test/invalid_utf_big.csv',columns = {'col1': 'VARCHAR','col2': 'VARCHAR','col3': 'VARCHAR'}, auto_detect=false, header = 0, delim = ',', ignore_errors=true)
+
+query I
+select count(*) from t
+----
+3030
+
+statement error
+from read_csv('data/csv/test/invalid_utf_big.csv',columns = {'col1': 'VARCHAR','col2': 'VARCHAR','col3': 'VARCHAR'}, auto_detect=false, header = 0, delim = ',')
+----
+CSV Error on Line: 3001
+
+# Test borked utf-8 within quotes
+statement error
+from read_csv('data/csv/test/invalid_utf_quoted.csv',columns = {'col1': 'VARCHAR','col2': 'VARCHAR','col3': 'VARCHAR'}, auto_detect=false, header = 0, delim = ',', quote = '"')
+----
+CSV Error on Line: 11
+
+query III
+from read_csv('data/csv/test/invalid_utf_complex.csv',columns = {'col1': 'VARCHAR','col2': 'VARCHAR','col3': 'VARCHAR'}, auto_detect=false, header = 0, delim = ',', quote = '"', ignore_errors=true)
+----
+valid	valid	valid
+valid	valid	valid
+valid	valid	valid
+valid	valid	valid
+valid	valid	valid
+valid	valid	valid
+valid	valid	valid
+valid	valid	valid
+valid	valid	valid
+valid	valid	valid
+valid	valid	valid
+valid	valid	valid
+valid	valid	valid
+valid	valid	valid
+valid	valid	valid
+valid	valid	valid
+valid	valid	valid
+valid	valid	valid
+valid	valid	valid
+valid	valid	valid
+
+# Test Invalid Header
+statement error
+from read_csv('data/csv/test/invalid_utf_header.csv', delim = ',', quote = '"')
+----
+Invalid unicode (byte sequence mismatch) detected.
+
+statement error
+from read_csv('data/csv/test/invalid_utf_header.csv', header=1,  delim = ',', quote = '"')
+----
+Invalid unicode (byte sequence mismatch) detected.
+
+query III
+from read_csv('data/csv/test/invalid_utf_header.csv', header=1,  delim = ',', quote = '"', ignore_errors = true)
+----
+valid	valid	valid
+valid	valid	valid
+valid	valid	valid
+valid	valid	valid
+valid	valid	valid
+valid	valid	valid
+valid	valid	valid
+valid	valid	valid
+valid	valid	valid
+valid	valid	valid
+
+# Test invalid unicode in between a quoted newline
+statement error
+from read_csv('data/csv/test/invalid_utf_quoted_nl.csv',columns = {'col1': 'VARCHAR','col2': 'VARCHAR','col3': 'VARCHAR'}, auto_detect=false, header = 0, delim = ',', quote = '"')
+----
+CSV Error on Line: 11
+
+query III
+from read_csv('data/csv/test/invalid_utf_quoted_nl.csv',columns = {'col1': 'VARCHAR','col2': 'VARCHAR','col3': 'VARCHAR'}, auto_detect=false, header = 0, delim = ',', quote = '"', ignore_errors=true)
+----
+valid	valid	valid
+valid	valid	valid
+valid	valid	valid
+valid	valid	valid
+valid	valid	valid
+valid	valid	valid
+valid	valid	valid
+valid	valid	valid
+valid	valid	valid
+valid	valid	valid
+valid	valid	valid
+valid	valid	valid
+valid	valid	valid
+valid	valid	valid
+valid	valid	valid
+valid	valid	valid
+valid	valid	valid
+valid	valid	valid
+valid	valid	valid
+valid	valid	valid
+
+# Test error between buffers
+statement error
+from read_csv('data/csv/test/invalid_utf_complex.csv',columns = {'col1': 'VARCHAR','col2': 'VARCHAR','col3': 'VARCHAR'}, auto_detect=false, header = 0, delim = ',', quote = '"', buffer_size = 198)
+----
+CSV Error on Line: 11
+
+# Test error between buffers (with ignore_errors set)
+query III
+from read_csv('data/csv/test/invalid_utf_complex.csv',columns = {'col1': 'VARCHAR','col2': 'VARCHAR','col3': 'VARCHAR'}, auto_detect=false, header = 0, delim = ',', ignore_errors=true, buffer_size = 198)
+----
+valid	valid	valid
+valid	valid	valid
+valid	valid	valid
+valid	valid	valid
+valid	valid	valid
+valid	valid	valid
+valid	valid	valid
+valid	valid	valid
+valid	valid	valid
+valid	valid	valid
+valid	valid	valid
+valid	valid	valid
+valid	valid	valid
+valid	valid	valid
+valid	valid	valid
+valid	valid	valid
+valid	valid	valid
+valid	valid	valid
+valid	valid	valid
+valid	valid	valid
+
+
+# We get a casting error
+statement error
+SELECT * FROM read_csv('data/csv/test/invalid_utf_list.csv', header=0, auto_detect=false, quote = '"',columns = {'col1': 'INTEGER[]'} )
+----
+Invalid unicode (byte sequence mismatch) detected.
+
+statement error
+SELECT * FROM read_csv('data/csv/test/invalid_utf_list.csv', header=0, auto_detect=false, quote = '"',columns = {'col1': 'INTEGER[]'} )
+----
+CSV Error on Line: 11
+
+# We get a invalid unicode error
+statement error
+SELECT * FROM read_csv('data/csv/test/invalid_utf_list.csv', header=0, auto_detect=false, quote = '"',columns = {'col1': 'VARCHAR'} )
+----
+Invalid unicode (byte sequence mismatch) detected.
+
+statement error
+SELECT * FROM read_csv('data/csv/test/invalid_utf_list.csv', header=0, auto_detect=false, quote = '"',columns = {'col1': 'VARCHAR'} )
+----
+CSV Error on Line: 11
--- a/external/duckdb/test/sql/copy/csv/code_cov/csv_type_detection.test
+++ b/external/duckdb/test/sql/copy/csv/code_cov/csv_type_detection.test
@@ -0,0 +1,26 @@
+# name: test/sql/copy/csv/code_cov/csv_type_detection.test
+# description: Tests to enforce codecov in csv type detection sniffing
+# group: [code_cov]
+
+statement ok
+PRAGMA enable_verification
+
+statement error
+from read_csv_auto('data/csv/invalid_utf8.csv', auto_detect = false, columns={'c01': 'VARCHAR'} )
+----
+Invalid unicode (byte sequence mismatch) detected
+
+query I
+select * from read_csv_auto('data/csv/empty.csv')
+----
+
+query II
+select * from read_csv_auto('data/csv/small_file.csv', sample_size=1)
+----
+1	2
+5	3
+
+query I
+select * from read_csv_auto('data/csv/date_format_percentage.csv')
+----
+336%584%3205
--- a/external/duckdb/test/sql/copy/csv/code_cov/csv_type_refinement.test
+++ b/external/duckdb/test/sql/copy/csv/code_cov/csv_type_refinement.test
@@ -0,0 +1,16 @@
+# name: test/sql/copy/csv/code_cov/csv_type_refinement.test
+# description: Tests to enforce codecov in csv type refinement sniffing
+# group: [code_cov]
+
+statement ok
+PRAGMA enable_verification
+
+query I
+select count(*) from read_csv_auto('data/csv/borked_date.csv', header = 0)
+----
+2070
+
+query I
+select count(*) from read_csv_auto('data/csv/big_not_bool.csv', header = 0)
+----
+2450
--- a/external/duckdb/test/sql/copy/csv/column_names.test
+++ b/external/duckdb/test/sql/copy/csv/column_names.test
@@ -0,0 +1,58 @@
+# name: test/sql/copy/csv/column_names.test
+# description: Test correct column name output in read_csv functions
+# group: [csv]
+
+statement ok
+PRAGMA enable_verification
+
+statement ok
+CREATE TABLE t1 AS SELECT * FROM read_csv_auto('data/csv/test/issue2518.csv', header=False, columns={'rsID':'INT', 'CHR': 'VARCHAR', 'POS': 'INT','REFB': 'VARCHAR','ALTB':'VARCHAR'}, auto_detect = false)
+
+query IIIII
+SELECT rsID, chr, pos, refb, altb FROM t1
+----
+4690	1	14673	G	A,C,T
+5	7	91839110	C	T
+6	7	91747131	A	G
+7	7	91779557	T	A
+8	7	92408329	C	T
+9	7	92373453	TG	T
+10	7	92383888	A	C,G,T
+1090	8	402108	C	G,T
+11	7	11364201	C	T
+1184	6	187649	T	A,C,G
+
+statement ok
+CREATE TABLE t2 AS SELECT * FROM read_csv_auto('data/csv/test/issue2518.csv', header=False, columns={'rsID':'INT', 'CHR': 'VARCHAR', 'POS': 'INT','REFB': 'VARCHAR','ALTB':'VARCHAR'}, AUTO_DETECT=0)
+
+query IIIII
+SELECT rsID, chr, pos, refb, altb FROM t2
+----
+4690	1	14673	G	A,C,T
+5	7	91839110	C	T
+6	7	91747131	A	G
+7	7	91779557	T	A
+8	7	92408329	C	T
+9	7	92373453	TG	T
+10	7	92383888	A	C,G,T
+1090	8	402108	C	G,T
+11	7	11364201	C	T
+1184	6	187649	T	A,C,G
+
+
+statement ok
+CREATE TABLE t3 AS SELECT * FROM read_csv_auto('data/csv/test/issue2518.csv', columns={'rsID':'INT', 'CHR': 'VARCHAR', 'POS': 'INT','REFB': 'VARCHAR','ALTB':'VARCHAR'}, auto_detect = false)
+
+query IIIII
+SELECT rsID, chr, pos, refb, altb FROM t3
+----
+4690	1	14673	G	A,C,T
+5	7	91839110	C	T
+6	7	91747131	A	G
+7	7	91779557	T	A
+8	7	92408329	C	T
+9	7	92373453	TG	T
+10	7	92383888	A	C,G,T
+1090	8	402108	C	G,T
+11	7	11364201	C	T
+1184	6	187649	T	A,C,G
--- a/external/duckdb/test/sql/copy/csv/copy_disable_parallelism.test
+++ b/external/duckdb/test/sql/copy/csv/copy_disable_parallelism.test
@@ -0,0 +1,15 @@
+# name: test/sql/copy/csv/copy_disable_parallelism.test
+# description: Test copy statement
+# group: [csv]
+
+statement ok
+PRAGMA enable_verification
+
+
+statement ok
+CREATE TABLE test (a INTEGER, b INTEGER, c VARCHAR(10));
+
+query I
+COPY test FROM 'data/csv/test/test.csv';
+----
+5000
--- a/external/duckdb/test/sql/copy/csv/copy_expression.test
+++ b/external/duckdb/test/sql/copy/csv/copy_expression.test
@@ -0,0 +1,40 @@
+# name: test/sql/copy/csv/copy_expression.test
+# description: Test copy with expressions
+# group: [csv]
+
+statement ok
+PRAGMA enable_verification
+
+statement ok
+SET VARIABLE copy_target = '__TEST_DIR__/copy_expression_target.csv';
+
+statement ok
+COPY (SELECT * FROM range(5) t(i)) TO (getvariable('copy_target')) WITH (HEADER)
+
+statement ok
+CREATE TABLE tbl(i INTEGER);
+
+query I
+COPY tbl FROM (getvariable('copy_target'));
+----
+5
+
+query I
+SELECT * FROM tbl
+----
+0
+1
+2
+3
+4
+
+statement ok
+PREPARE v1 AS COPY (SELECT 'hello world' str) TO $1;
+
+statement ok
+EXECUTE v1('__TEST_DIR__/prepared_copy.csv');
+
+query I
+FROM '__TEST_DIR__/prepared_copy.csv'
+----
+hello world
--- a/external/duckdb/test/sql/copy/csv/copy_to_overwrite.test
+++ b/external/duckdb/test/sql/copy/csv/copy_to_overwrite.test
@@ -0,0 +1,67 @@
+# name: test/sql/copy/csv/copy_to_overwrite.test
+# description: Test copy to overwriting behavior
+# group: [csv]
+
+statement ok
+PRAGMA enable_verification
+
+statement ok
+SET threads=1;
+
+# run with and without preservation of insertion order
+loop i 0 2
+
+statement ok
+COPY (SELECT * FROM range(5) t(i)) TO '__TEST_DIR__/copy_to_overwrite.csv' (HEADER)
+
+query I
+SELECT * FROM '__TEST_DIR__/copy_to_overwrite.csv'
+----
+0
+1
+2
+3
+4
+
+statement ok
+COPY (SELECT * FROM range(5, 10) t(i)) TO '__TEST_DIR__/copy_to_overwrite.csv' (HEADER)
+
+query I
+SELECT * FROM '__TEST_DIR__/copy_to_overwrite.csv'
+----
+5
+6
+7
+8
+9
+
+# gzip
+statement ok
+COPY (SELECT * FROM range(5) t(i)) TO '__TEST_DIR__/copy_to_overwrite.csv.gz' (HEADER)
+
+query I
+SELECT * FROM '__TEST_DIR__/copy_to_overwrite.csv.gz'
+----
+0
+1
+2
+3
+4
+
+statement ok
+COPY (SELECT * FROM range(5, 10) t(i)) TO '__TEST_DIR__/copy_to_overwrite.csv.gz' (HEADER)
+
+query I
+SELECT * FROM '__TEST_DIR__/copy_to_overwrite.csv.gz'
+----
+5
+6
+7
+8
+9
+
+statement ok
+SET preserve_insertion_order=false
+
+endloop
+
--- a/external/duckdb/test/sql/copy/csv/csv_copy_sniffer.test
+++ b/external/duckdb/test/sql/copy/csv/csv_copy_sniffer.test
@@ -0,0 +1,22 @@
+# name: test/sql/copy/csv/csv_copy_sniffer.test
+# description: Test CSV sniffer copy
+# group: [csv]
+
+statement ok
+PRAGMA enable_verification
+
+statement ok
+CREATE TABLE sales (
+    salesid INTEGER  NOT NULL PRIMARY KEY,
+    listid INTEGER NOT NULL,
+    sellerid INTEGER NOT NULL,
+    buyerid  INTEGER NOT NULL,
+    eventid INTEGER NOT NULL,
+    dateid  SMALLINT  NOT NULL,
+    qtysold   SMALLINT  NOT NULL,
+    pricepaid DECIMAL (8,2),
+    commission DECIMAL (8,2),
+    saletime TIMESTAMP);
+
+statement ok
+COPY sales FROM 'data/csv/sales_snippet.csv' (TIMESTAMPFORMAT '%m/%d/%Y %I:%M:%S', IGNORE_ERRORS true);
--- a/external/duckdb/test/sql/copy/csv/csv_decimal_separator.test
+++ b/external/duckdb/test/sql/copy/csv/csv_decimal_separator.test
@@ -0,0 +1,100 @@
+# name: test/sql/copy/csv/csv_decimal_separator.test
+# description: Support decimal separators
+# group: [csv]
+
+statement ok
+PRAGMA enable_verification
+
+# period-separated decimal doesn't parse
+statement error
+CREATE TABLE decimal_separators AS SELECT * FROM read_csv_auto('data/csv/decimal_separators/decimal_separators.csv', column_types={'commas': 'double', 'periods': 'double'}, delim=';', decimal_separator=',')
+----
+Line: 2
+
+statement ok
+CREATE TABLE decimal_separators AS SELECT * FROM read_csv_auto('data/csv/decimal_separators/decimal_separators.csv', column_types={'commas': 'double'}, delim=';', decimal_separator=',')
+
+query II
+SELECT commas, periods FROM decimal_separators;
+----
+1.1	1.1
+0.25	0.25
+15300.0	1.53e4
+15300.0	+1.53e4
+-15300.0	-1.53e4
+
+query II
+SELECT typeof(commas), typeof(periods) FROM decimal_separators limit 1;
+----
+DOUBLE	VARCHAR
+
+# reading the commas column as decimal fails when decimal separator is set to '.'
+statement error
+CREATE TABLE decimal_separators2 AS SELECT * FROM read_csv_auto('data/csv/decimal_separators/decimal_separators.csv',  column_types={'commas': 'decimal', 'periods': 'decimal'}, delim=';', decimal_separator='.')
+----
+Line: 2
+
+# reading the commas column as float fails when decimal separator is set to '.'
+statement error
+CREATE TABLE decimal_separators2 AS SELECT * FROM read_csv_auto('data/csv/decimal_separators/decimal_separators.csv',  column_types={'commas': 'float', 'periods': 'decimal'}, delim=';', decimal_separator='.')
+----
+Line: 2
+
+statement ok
+CREATE TABLE decimal_separators2 AS SELECT * FROM read_csv_auto('data/csv/decimal_separators/decimal_separators.csv', column_types={'commas': 'decimal'}, delim=';', decimal_separator=',')
+
+query II
+SELECT commas, periods FROM decimal_separators2;
+----
+1.100	1.1
+0.250	0.25
+15300.000	1.53e4
+15300.000	+1.53e4
+-15300.000	-1.53e4
+
+query II
+SELECT typeof(commas), typeof(periods) FROM decimal_separators2 limit 1;
+----
+DECIMAL(18,3)	VARCHAR
+
+
+# no separator specified => commas get read as varchar
+statement ok
+CREATE TABLE decimal_separators3 AS SELECT * FROM read_csv_auto('data/csv/decimal_separators/decimal_separators.csv',  column_types={'periods': 'decimal'}, delim=';')
+
+query II
+SELECT commas, periods FROM decimal_separators3;
+----
+1,1	1.100
+0,25	0.250
+1,53e4	15300.000
+1,53e4	+15300.000
+-1,53e4	-15300.000
+
+
+# in a comma-delimited file, comma as decimal separator is OK when quoted
+statement ok
+CREATE TABLE decimal_separators4 AS SELECT * FROM read_csv_auto('data/csv/decimal_separators/decimal_separators_csv.csv', column_types={'commas': 'double'}, quote='"',delim=',',decimal_separator=',')
+
+query II
+SELECT commas, periods FROM decimal_separators4;
+----
+1.2345	1.2345
+
+# auto-detection should read period-separated decimals as varchar
+query II
+SELECT typeof(commas), typeof(periods) FROM decimal_separators4 limit 1;
+----
+DOUBLE	VARCHAR
+
+# unsupported separator characters result in error
+statement error
+SELECT * FROM read_csv_auto('data/csv/decimal_separators/invalid_char.csv', column_types={'foo': 'double'}, decimal_separator='ö')
+----
+Binder Error: Unsupported parameter for DECIMAL_SEPARATOR: should be '.' or ','
+
+# data with mixed separators will fail reading
+statement error
+SELECT * FROM read_csv_auto('data/csv/decimal_separators/mixed_format_fail.csv', column_types={'foo': 'double'}, decimal_separator=',', skip=0)
+----
+Line: 4
--- a/external/duckdb/test/sql/copy/csv/csv_dtypes.test
+++ b/external/duckdb/test/sql/copy/csv/csv_dtypes.test
@@ -0,0 +1,57 @@
+# name: test/sql/copy/csv/csv_dtypes.test
+# description: Read a CSV with dtypes flags
+# group: [csv]
+
+statement ok
+PRAGMA enable_verification
+
+query II
+select typeof(Year), typeof(Quarter) from 'data/csv/real/ontime_sample.csv' LIMIT 1;
+----
+BIGINT	BIGINT
+
+query II
+select typeof(Year), typeof(Quarter) from read_csv_auto('data/csv/real/ontime_sample.csv', dtypes={'Quarter': 'TINYINT'}) LIMIT 1
+----
+BIGINT	TINYINT
+
+# case insensitivity for struct
+query II
+select typeof(Year), typeof(Quarter) from read_csv_auto('data/csv/real/ontime_sample.csv', dtypes={'quArTeR': 'TINYINT'}) LIMIT 1
+----
+BIGINT	TINYINT
+
+query II
+select typeof(Year), typeof(Quarter) from read_csv_auto('data/csv/real/ontime_sample.csv', dtypes=['INT', 'TINYINT']) LIMIT 1
+----
+INTEGER	TINYINT
+
+# mix of struct and list parameters
+statement error
+select * from read_csv_auto('data/csv/real/ontime_sample.csv', dtypes=['INT'], column_types={'Quarter': 'TINYINT'}) LIMIT 1
+----
+can only be supplied once
+
+# invalid list type
+statement error
+select * from read_csv_auto('data/csv/real/ontime_sample.csv', dtypes=[42]) LIMIT 1
+----
+requires a list of types
+
+# invalid type
+statement error
+select * from read_csv_auto('data/csv/real/ontime_sample.csv', dtypes=['unknown_type']) LIMIT 1
+----
+unknown_type
+
+# invalid struct type
+statement error
+select * from read_csv_auto('data/csv/real/ontime_sample.csv', dtypes={'Quarter': 42}) LIMIT 1
+----
+requires a type specification as string
+
+# too many sql types provided in list
+statement error
+select * from read_csv_auto('data/csv/auto/int_bol.csv', dtypes=['varchar', 'varchar', 'varchar']) LIMIT 1
+----
+3 types were provided, but CSV file only has 2 columns
--- a/external/duckdb/test/sql/copy/csv/csv_dtypes_union_by_name.test
+++ b/external/duckdb/test/sql/copy/csv/csv_dtypes_union_by_name.test
@@ -0,0 +1,69 @@
+# name: test/sql/copy/csv/csv_dtypes_union_by_name.test
+# description: Read a CSV with dtypes and UNION BY NAME
+# group: [csv]
+
+statement ok
+PRAGMA enable_verification
+
+statement ok
+CREATE TABLE ubn1(a BIGINT);
+
+statement ok
+CREATE TABLE ubn2(a INTEGER, b INTEGER);
+
+statement ok
+CREATE TABLE ubn3(a INTEGER, c INTEGER);
+
+statement ok
+INSERT INTO ubn1 VALUES (1), (2), (9223372036854775807);
+
+statement ok
+INSERT INTO ubn2 VALUES (3,4), (5, 6);
+
+statement ok
+INSERT INTO ubn3 VALUES (100,101), (102, 103);
+
+statement ok
+COPY ubn1 TO '__TEST_DIR__/ubn1.csv' WITH (DELIMITER ',');
+
+statement ok
+COPY ubn2 TO '__TEST_DIR__/ubn2.csv' WITH ( DELIMITER ',');
+
+statement ok
+COPY ubn3 TO '__TEST_DIR__/ubn3.csv' WITH (DELIMITER ',');
+
+query III
+SELECT typeof(a), typeof(b), typeof(c)
+FROM  read_csv_auto('__TEST_DIR__/ubn*.csv', UNION_BY_NAME=TRUE, dtypes={'c': TINYINT})
+LIMIT 1;
+----
+BIGINT	BIGINT	TINYINT
+
+query III
+SELECT typeof(a), typeof(b), typeof(c)
+FROM  read_csv_auto('__TEST_DIR__/ubn*.csv', UNION_BY_NAME=TRUE, dtypes={'c': TINYINT, 'A': DOUBLE})
+LIMIT 1;
+----
+DOUBLE	BIGINT	TINYINT
+
+# unrecognized in any file
+statement error
+SELECT typeof(a), typeof(b), typeof(c)
+FROM  read_csv_auto('__TEST_DIR__/ubn*.csv', UNION_BY_NAME=TRUE, dtypes={'xxx': TINYINT})
+LIMIT 1;
+----
+xxx
+
+statement error
+SELECT typeof(a), typeof(b), typeof(c)
+FROM  read_csv_auto('__TEST_DIR__/ubn*.csv', UNION_BY_NAME=TRUE, dtypes={'c': TINYINT, 'A': DOUBLE, 'C': FLOAT})
+LIMIT 1;
+----
+Duplicate struct entry name
+
+statement error
+SELECT typeof(a), typeof(b), typeof(c)
+FROM  read_csv_auto('__TEST_DIR__/ubn*.csv', UNION_BY_NAME=TRUE, dtypes={'c': TINYINT, 'A': DOUBLE, 'xZX': FLOAT})
+LIMIT 1;
+----
+xZX
--- a/external/duckdb/test/sql/copy/csv/csv_duck_fuzz.test
+++ b/external/duckdb/test/sql/copy/csv/csv_duck_fuzz.test
@@ -0,0 +1,31 @@
+# name: test/sql/copy/csv/csv_duck_fuzz.test
+# description: Issues found from DuckFuzz regarding the CSV Reader
+# group: [csv]
+
+statement ok
+PRAGMA enable_verification
+
+# The important thing here is that we don't crash, some parameters accept null values (i.e., delimiter),
+# and others will have different error messages, not making it possible to use a regex to test errors.
+
+foreach parameter sep delim quote new_line escape nullstr columns auto_type_candidates header auto_detect sample_size all_varchar dateformat timestampformat normalize_names compression skip max_line_size maximum_line_size ignore_errors store_rejects rejects_table rejects_scan rejects_limit force_not_null buffer_size decimal_separator parallel null_padding allow_quoted_nulls column_types dtypes types names column_names comment encoding strict_mode
+
+statement maybe
+SELECT NULL FROM sniff_csv('data/csv/14512.csv', ${parameter} := NULL)
+----
+
+statement maybe
+SELECT NULL FROM read_csv('data/csv/14512.csv', ${parameter} := NULL)
+----
+
+endloop
+
+statement error
+SELECT NULL FROM sniff_csv(NULL)
+----
+sniff_csv cannot take NULL as a file path parameter
+
+statement error
+SELECT NULL FROM read_csv(NULL)
+----
+read_csv cannot take NULL list as parameter
--- a/external/duckdb/test/sql/copy/csv/csv_enum.test
+++ b/external/duckdb/test/sql/copy/csv/csv_enum.test
@@ -0,0 +1,40 @@
+# name: test/sql/copy/csv/csv_enum.test
+# description: Read a CSV with enum types
+# group: [csv]
+
+statement ok
+PRAGMA enable_verification
+
+statement ok
+CREATE TYPE bla AS ENUM ('Y', 'N');
+
+query I
+select * from read_csv_auto('data/csv/response.csv', header = 0)
+----
+Y
+Y
+N
+Null
+
+query I
+FROM read_csv('data/csv/response.csv', columns={'response': 'bla'}, nullstr = 'Null');
+----
+Y
+Y
+N
+NULL
+
+
+query I
+FROM read_csv_auto('data/csv/response.csv', types={'column0': 'bla'}, nullstr = 'Null', header = 0);
+----
+Y
+Y
+N
+NULL
+
+statement error
+FROM read_csv_auto('data/csv/response.csv', auto_type_candidates=['bla'], nullstr = 'Null');
+----
+Auto Type Candidate of type ENUM is not accepted as a valid input
+
--- a/external/duckdb/test/sql/copy/csv/csv_enum_storage.test
+++ b/external/duckdb/test/sql/copy/csv/csv_enum_storage.test
@@ -0,0 +1,45 @@
+# name: test/sql/copy/csv/csv_enum_storage.test
+# description: Read a CSV with enum types
+# group: [csv]
+
+statement ok
+PRAGMA enable_verification
+
+
+# load the DB from disk
+load __TEST_DIR__/test_csv_enum.db
+
+statement ok
+CREATE TYPE bla AS ENUM ('Y', 'N');
+
+restart
+
+query I
+select * from read_csv_auto('data/csv/response.csv', header = 0)
+----
+Y
+Y
+N
+Null
+
+query I
+FROM read_csv('data/csv/response.csv', columns={'response': 'bla'}, nullstr = 'Null');
+----
+Y
+Y
+N
+NULL
+
+
+query I
+FROM read_csv_auto('data/csv/response.csv', types={'column0': 'bla'}, nullstr = 'Null', header = 0);
+----
+Y
+Y
+N
+NULL
+
+statement error
+FROM read_csv_auto('data/csv/response.csv', auto_type_candidates=['bla'], nullstr = 'Null');
+----
+Auto Type Candidate of type ENUM is not accepted as a valid input
--- a/external/duckdb/test/sql/copy/csv/csv_error_message.test
+++ b/external/duckdb/test/sql/copy/csv/csv_error_message.test
@@ -0,0 +1,39 @@
+# name: test/sql/copy/csv/csv_error_message.test
+# description: Various CSV reader error messages
+# group: [csv]
+
+statement ok
+PRAGMA enable_verification
+
+# Test columns error
+
+statement error
+FROM read_csv('data/csv/15473.csv', delim = ',', columns = {'A' : 'VARCHAR','B' : 'VARCHAR','C' : 'VARCHAR','D' : 'VARCHAR'})
+----
+Columns are set as: "columns = { 'A' : 'VARCHAR', 'B' : 'VARCHAR', 'C' : 'VARCHAR', 'D' : 'VARCHAR'}", and they contain: 4 columns. It does not match the number of columns found by the sniffer: 3. Verify the columns parameter is correctly set.
+
+statement ok
+COPY (SELECT i::VARCHAR i FROM range(103) tbl(i) UNION ALL SELECT 'hello') TO '__TEST_DIR__/int_parse_error.csv' (HEADER, DELIMITER '|')
+
+statement error
+SELECT * FROM read_csv('__TEST_DIR__/int_parse_error.csv', columns={'i': 'INT'})
+----
+Column at position: 0 Set type: INTEGER Sniffed type: VARCHAR
+
+statement error
+SELECT * FROM read_csv('__TEST_DIR__/int_parse_error.csv', columns={'i': 'INT'}, header=True, auto_detect=false)
+----
+Line: 105
+
+statement ok
+COPY (SELECT i::VARCHAR i FROM range(103) tbl(i) UNION ALL SELECT 'hello') TO '__TEST_DIR__/int_parse_error.csv' (HEADER 0, DELIMITER '|')
+
+statement error
+SELECT * FROM read_csv('__TEST_DIR__/int_parse_error.csv', columns={'i': 'INT'}, header=False, auto_detect=false)
+----
+Line: 104
+
+statement error
+SELECT * FROM read_csv('__TEST_DIR__/int_parse_error.csv', columns={'i': 'INT'}, header=False, auto_detect=false)
+----
+Original Line: hello
--- a/external/duckdb/test/sql/copy/csv/csv_external_access.test
+++ b/external/duckdb/test/sql/copy/csv/csv_external_access.test
@@ -0,0 +1,47 @@
+# name: test/sql/copy/csv/csv_external_access.test
+# description: Test that enable_external_access blocks CSV readers
+# group: [csv]
+
+statement ok
+PRAGMA enable_verification
+
+statement ok
+CREATE TABLE date_test(d date);
+
+statement ok
+COPY date_test FROM 'data/csv/test/date.csv';
+
+statement ok
+SET enable_external_access=false;
+
+statement error
+SELECT * FROM read_csv('data/csv/test/date.csv', columns = {'d': 'DATE'});
+----
+Permission Error
+
+statement error
+SELECT * FROM read_csv_auto('data/csv/test/date.csv');
+----
+Permission Error
+
+statement error
+COPY date_test FROM 'data/csv/test/date.csv';
+----
+Permission Error
+
+statement error
+COPY date_test TO '__TEST_DIR__/date.csv'
+----
+Permission Error
+
+# we also can't just enable external access again
+statement error
+SET enable_external_access=true;
+----
+Cannot change enable_external_access setting while database is running
+
+# sniffer also respects external access flag
+statement error
+FROM sniff_csv('data/csv/test/date.csv');
+----
+Permission Error
--- a/external/duckdb/test/sql/copy/csv/csv_glob_fallback.test
+++ b/external/duckdb/test/sql/copy/csv/csv_glob_fallback.test
@@ -0,0 +1,18 @@
+# name: test/sql/copy/csv/csv_glob_fallback.test
+# description: Test glob fallback (#4699)
+# group: [csv]
+
+statement ok
+PRAGMA enable_verification
+
+query III
+SELECT * FROM 'data/csv/[avalon]_daily-avg.csv'
+----
+1	2	3
+3	4	5
+4	5	6
+
+statement error
+SELECT * FROM 'data/csv/[avxalon]_daily-avg.csv'
+----
+<REGEX>:.*IO Error: No files found.*
--- a/external/duckdb/test/sql/copy/csv/csv_hive.test
+++ b/external/duckdb/test/sql/copy/csv/csv_hive.test
@@ -0,0 +1,151 @@
+# name: test/sql/copy/csv/csv_hive.test
+# description: Test the automatic parsing of the hive partitioning scheme
+# group: [csv]
+
+statement ok
+PRAGMA enable_verification
+
+statement ok
+CREATE TABLE test AS SELECT 1 as id, 'value1' as value;
+CREATE TABLE test2 AS SELECT 2 as id, 'value2' as value;
+
+# filenames could allow you to parse hive partitions manually using SQL
+query III
+select id, value, replace(filename, '\', '/') from read_csv_auto('data/csv/hive-partitioning/simple/*/*/test.csv', FILENAME=1) order by id
+----
+1	value1	data/csv/hive-partitioning/simple/part=a/date=2012-01-01/test.csv
+2	value2	data/csv/hive-partitioning/simple/part=b/date=2013-01-01/test.csv
+
+# however this is just a lot nicer
+query IIII
+select id, value, part, date from read_csv_auto('data/csv/hive-partitioning/simple/*/*/test.csv', HIVE_PARTITIONING=1) order by id
+----
+1	value1	a	2012-01-01
+2	value2	b	2013-01-01
+
+# As long as the names match, we don't really mind since everything is a string anyway
+query IIII
+select id, value, part, date from read_csv_auto('data/csv/hive-partitioning/different_order/*/*/test.csv', HIVE_PARTITIONING=1)  order by id
+----
+1	value1	a	2012-01-01
+2	value2	b	2013-01-01
+
+# If the key names don't add up, we throw
+statement error
+select * from read_csv_auto('data/csv/hive-partitioning/mismatching_names/*/*/test.csv', HIVE_PARTITIONING=1)
+----
+Hive partition mismatch
+
+# If the key names don't add up, we throw
+statement error
+select * from read_csv_auto('data/csv/hive-partitioning/mismatching_count/*/*/test.csv', HIVE_PARTITIONING=1)
+----
+Hive partition mismatch
+
+# Now we do a bunch of filtering on the partitions, to test the file skipping mechanism
+query IIII
+select id, value, part, date from read_csv_auto('data/csv/hive-partitioning/different_order/*/*/test.csv', HIVE_PARTITIONING=1) where part='a'
+----
+1	value1	a	2012-01-01
+
+query IIII
+select id, value, part, date from read_csv_auto('data/csv/hive-partitioning/different_order/*/*/test.csv', HIVE_PARTITIONING=1) where part='b'
+----
+2	value2	b	2013-01-01
+
+query IIII
+select id, value, CAST(part AS INT) as part_cast, CAST(date AS DATE) as date_cast from read_csv_auto('data/csv/hive-partitioning/types/*/*/test.csv', HIVE_PARTITIONING=1) where part_cast > 0 and part_cast < 5000;
+----
+1	value1	1000	2012-01-01
+
+query IIII
+select id, value, CAST(part AS INT) as part_cast, CAST(date AS DATE) as date_cast from read_csv_auto('data/csv/hive-partitioning/types/*/*/test.csv', HIVE_PARTITIONING=1) where part_cast > 5000;
+----
+2	value2	9000	2013-01-01
+
+query IIII
+select id, value, CAST(part AS INT) as part_cast, CAST(date AS DATE) as date_cast from read_csv_auto('data/csv/hive-partitioning/types/*/*/test.csv', HIVE_PARTITIONING=1) where date_cast > CAST('2000-01-01' as DATE) and date_cast < CAST('2012-12-12' as DATE);
+----
+1	value1	1000	2012-01-01
+
+query IIII
+select id, value, CAST(part AS INT) as part_cast, CAST(date AS DATE) as date_cast from read_csv_auto('data/csv/hive-partitioning/types/*/*/test.csv', HIVE_PARTITIONING=1) where date_cast > CAST('2000-01-01' as DATE) order by date_cast;
+----
+1	value1	1000	2012-01-01
+2	value2	9000	2013-01-01
+
+query IIII
+select id, value, CAST(part AS INT) as part_cast, CAST(date AS DATE) as date_cast from read_csv_auto('data/csv/hive-partitioning/types/*/*/test.csv', HIVE_PARTITIONING=1) where date_cast=CAST('2012-01-01' as DATE) OR part_cast=9000 ORDER BY date_cast;
+----
+1	value1	1000	2012-01-01
+2	value2	9000	2013-01-01
+
+## Filter expressions we can calculate during pushdown using filenames/hive partitions should be pruned
+
+# Filtering out 0/2 files
+query IIII
+select id, value, CAST(part AS INT) as part_cast, CAST(date AS DATE) as date_cast from read_csv_auto('data/csv/hive-partitioning/types/*/*/test.csv', HIVE_PARTITIONING=1) where (date_cast=CAST('2012-01-01' as DATE) AND concat(date_cast::VARCHAR, part_cast::VARCHAR) == '2012-01-011000') OR (part_cast=9000) ORDER BY date_cast;
+----
+1	value1	1000	2012-01-01
+2	value2	9000	2013-01-01
+
+# There should not be any filter operation remaining since it can be handled completely during pushdown by pruning file list
+query II
+EXPLAIN select id, value, CAST(part AS INT) as part_cast, CAST(date AS DATE) as date_cast from read_csv_auto('data/csv/hive-partitioning/types/*/*/test.csv', HIVE_PARTITIONING=1) where (date_cast=CAST('2012-01-01' as DATE) AND concat(date_cast::VARCHAR, part_cast::VARCHAR) == '2012-01-011000') OR (part_cast=9000) ORDER BY date_cast;
+----
+physical_plan	<!REGEX>:.*FILTER.*
+
+# Query filtering out first file
+query IIII
+select id, value, CAST(part AS INT) as part_cast, CAST(date AS DATE) as date_cast from read_csv_auto('data/csv/hive-partitioning/types/*/*/test.csv', HIVE_PARTITIONING=1) where (date_cast=CAST('2012-01-01' as DATE) AND concat(date_cast::VARCHAR, part_cast::VARCHAR) == 'foobar') OR (part_cast=9000) ORDER BY date_cast;
+----
+2	value2	9000	2013-01-01
+
+# Again, we should not have a filter operator here
+query II
+explain select id, value, CAST(part AS INT) as part_cast, CAST(date AS DATE) as date_cast from read_csv_auto('data/csv/hive-partitioning/types/*/*/test.csv', HIVE_PARTITIONING=1) where (date_cast=CAST('2012-01-01' as DATE) AND concat(date_cast::VARCHAR, part_cast::VARCHAR) == 'foobar') OR (part_cast=9000) ORDER BY date_cast;
+----
+physical_plan	<!REGEX>:.*FILTER.*
+
+# Query filtering out second file
+query IIII
+select id, value, CAST(part AS INT) as part_cast, CAST(date AS DATE) as date_cast from read_csv_auto('data/csv/hive-partitioning/types/*/*/test.csv', HIVE_PARTITIONING=1) where (date_cast=CAST('2012-01-01' as DATE) AND concat(date_cast::VARCHAR, part_cast::VARCHAR) == '2012-01-011000') OR (part_cast=1337) ORDER BY date_cast;
+----
+1	value1	1000	2012-01-01
+
+# Again, we should not have a filter operator here
+query II
+explain select id, value, CAST(part AS INT) as part_cast, CAST(date AS DATE) as date_cast from read_csv_auto('data/csv/hive-partitioning/types/*/*/test.csv', HIVE_PARTITIONING=1) where (date_cast=CAST('2012-01-01' as DATE) AND concat(date_cast::VARCHAR, part_cast::VARCHAR) == '2012-01-011000') OR (part_cast=1337) ORDER BY date_cast;
+----
+physical_plan	<!REGEX>:.*FILTER.*
+
+# Filtering out both files
+query IIII
+select id, value, CAST(part AS INT) as part_cast, CAST(date AS DATE) as date_cast from read_csv_auto('data/csv/hive-partitioning/types/*/*/test.csv', HIVE_PARTITIONING=1) where (date_cast=CAST('2012-01-01' as DATE) AND concat(date_cast::VARCHAR, part_cast::VARCHAR) == 'foobar') OR (part_cast=1337) ORDER BY date_cast;
+----
+
+# Again, we should not have a filter operator here
+query II
+EXPLAIN select id, value, CAST(part AS INT) as part_cast, CAST(date AS DATE) as date_cast from read_csv_auto('data/csv/hive-partitioning/types/*/*/test.csv', HIVE_PARTITIONING=1) where (date_cast=CAST('2012-01-01' as DATE) AND concat(date_cast::VARCHAR, part_cast::VARCHAR) == 'foobar') OR (part_cast=1337) ORDER BY date_cast;
+----
+physical_plan	<!REGEX>:.*FILTER.*
+
+# projection pushdown
+query I
+select value from read_csv_auto('data/csv/hive-partitioning/different_order/*/*/test.csv', HIVE_PARTITIONING=1)  order by 1
+----
+value1
+value2
+
+query I
+select part from read_csv_auto('data/csv/hive-partitioning/different_order/*/*/test.csv', HIVE_PARTITIONING=1)  order by 1
+----
+a
+b
+
+# project only some columns from a hive partition
+query I
+select date from read_csv_auto('data/csv/hive-partitioning/different_order/*/*/test.csv', HIVE_PARTITIONING=1)  order by 1
+----
+2012-01-01
+2013-01-01
--- a/external/duckdb/test/sql/copy/csv/csv_hive_filename_union.test
+++ b/external/duckdb/test/sql/copy/csv/csv_hive_filename_union.test
@@ -0,0 +1,74 @@
+# name: test/sql/copy/csv/csv_hive_filename_union.test
+# description: Test the automatic parsing of the hive partitioning scheme
+# group: [csv]
+
+statement ok
+PRAGMA enable_verification
+
+# projection pushdown
+query I
+select filename.replace('\', '/').split('/')[-2] from read_csv_auto('data/csv/hive-partitioning/simple/*/*/test.csv', HIVE_PARTITIONING=1,  FILENAME=1)  order by 1
+----
+date=2012-01-01
+date=2013-01-01
+
+query III
+select part, filename.replace('\', '/').split('/')[-2], value from read_csv_auto('data/csv/hive-partitioning/simple/*/*/test.csv', HIVE_PARTITIONING=1,  FILENAME=1)  order by 1
+----
+a	date=2012-01-01	value1
+b	date=2013-01-01	value2
+
+query III
+select part, filename.replace('\', '/').split('/')[-2], value from read_csv_auto('data/csv/hive-partitioning/simple/*/*/test.csv', HIVE_PARTITIONING=1,  FILENAME=1, UNION_BY_NAME=1)  order by 1
+----
+a	date=2012-01-01	value1
+b	date=2013-01-01	value2
+
+query III
+select * exclude(filename) from read_csv_auto('data/csv/hive-partitioning/mismatching_types/*/*.csv', HIVE_PARTITIONING=1, FILENAME=1)  order by 1
+----
+99	world	2
+xxx	42	1
+
+query III
+select * from read_csv_auto('data/csv/hive-partitioning/mismatching_types/*/*.csv', HIVE_PARTITIONING=1,  UNION_BY_NAME=1)  order by 1
+----
+99	world	2
+xxx	42	1
+
+query IIII
+select * exclude(filename), filename.replace('\', '/').split('/')[-2] from read_csv_auto('data/csv/hive-partitioning/mismatching_types/*/*.csv', HIVE_PARTITIONING=1, FILENAME=1, UNION_BY_NAME=1)  order by 1
+----
+99	world	2	part=2
+xxx	42	1	part=1
+
+query IIII
+select part, filename.replace('\', '/').split('/')[-2], a, b from read_csv_auto('data/csv/hive-partitioning/mismatching_types/*/*.csv', HIVE_PARTITIONING=1, FILENAME=1, UNION_BY_NAME=1)  order by 1
+----
+1	part=1	xxx	42
+2	part=2	99	world
+
+query II
+select * exclude (filename) from read_csv_auto('data/csv/hive-partitioning/mismatching_types/*/*.csv', HIVE_PARTITIONING=0,  FILENAME=1, UNION_BY_NAME=1)  order by 1
+----
+99	world
+xxx	42
+
+# This can either throw a cast error or a schema mismatch error depending on what is executed first because of
+# parallelism
+statement error
+select * from read_csv_auto(['data/csv/hive-partitioning/mismatching_contents/part=1/test.csv', 'data/csv/hive-partitioning/mismatching_contents/part=2/test.csv'])  order by 1
+----
+If you are trying to read files with different schemas, try setting union_by_name=True
+
+query III
+select a, b, c from read_csv_auto('data/csv/hive-partitioning/mismatching_contents/*/*.csv', UNION_BY_NAME=1)  order by 2 NULLS LAST
+----
+42	world	NULL
+42	NULL	1992-01-01
+
+query IIII
+select a, b, part, c from read_csv_auto('data/csv/hive-partitioning/mismatching_contents/*/*.csv',  UNION_BY_NAME=1, HIVE_PARTITIONING=1)  order by 2 NULLS LAST
+----
+42	world	2	NULL
+42	NULL	1	1992-01-01
--- a/external/duckdb/test/sql/copy/csv/csv_home_directory.test
+++ b/external/duckdb/test/sql/copy/csv/csv_home_directory.test
@@ -0,0 +1,61 @@
+# name: test/sql/copy/csv/csv_home_directory.test
+# description: CSV writer home directory
+# group: [csv]
+
+statement ok
+PRAGMA enable_verification
+
+statement ok
+SET home_directory='__TEST_DIR__'
+
+statement ok
+CREATE TABLE integers AS SELECT * FROM range(10)
+
+statement ok
+COPY integers TO '__TEST_DIR__/integers.csv' (FORMAT CSV);
+
+query I
+SELECT * FROM '~/integers.csv'
+----
+0
+1
+2
+3
+4
+5
+6
+7
+8
+9
+
+statement ok
+CREATE TABLE integers_load(i INTEGER);
+
+statement ok
+COPY integers_load FROM '~/integers.csv'
+
+query I
+SELECT * FROM integers_load
+----
+0
+1
+2
+3
+4
+5
+6
+7
+8
+9
+
+# glob from home directory
+statement ok
+COPY integers TO '__TEST_DIR__/homedir_integers1.csv'
+
+statement ok
+COPY integers TO '__TEST_DIR__/homedir_integers2.csv'
+
+query I
+SELECT COUNT(*) FROM '~/homedir_integers*.csv'
+----
+20
--- a/external/duckdb/test/sql/copy/csv/csv_limit_copy.test
+++ b/external/duckdb/test/sql/copy/csv/csv_limit_copy.test
@@ -0,0 +1,18 @@
+# name: test/sql/copy/csv/csv_limit_copy.test
+# description: CSV limit copy
+# group: [csv]
+
+statement ok
+PRAGMA enable_verification
+
+
+statement ok
+CREATE TABLE integers AS FROM range(1000000) t(i);
+
+statement ok
+COPY (FROM integers LIMIT 30000) TO '__TEST_DIR__/limit_copy.csv'
+
+query I
+SELECT COUNT(*) FROM '__TEST_DIR__/limit_copy.csv'
+----
+30000
--- a/external/duckdb/test/sql/copy/csv/csv_line_too_long.test
+++ b/external/duckdb/test/sql/copy/csv/csv_line_too_long.test
@@ -0,0 +1,28 @@
+# name: test/sql/copy/csv/csv_line_too_long.test
+# description: Test that verifies that the CSV has long lines and properly errors that
+# group: [csv]
+
+statement ok
+PRAGMA enable_verification
+
+statement ok
+CREATE TABLE T1 (name VARCHAR);
+
+foreach header true false
+
+statement error
+COPY T1(name) from 'data/csv/line_too_long.csv.gz' (DELIMITER ',', HEADER ${header} , COMPRESSION gzip, ALLOW_QUOTED_NULLS false);
+----
+Maximum line size of 2000000 bytes exceeded
+
+statement error
+COPY T1(name) from 'data/csv/line_too_long_with_newline.csv.gz' (DELIMITER ',', HEADER ${header} , COMPRESSION gzip, ALLOW_QUOTED_NULLS false);
+----
+Possible Solution: Change the maximum length size, e.g., max_line_size=2097165
+
+statement error
+COPY T1(name) from 'data/csv/multiple_line_too_long.csv.gz' (DELIMITER ',', HEADER ${header} , COMPRESSION gzip, ALLOW_QUOTED_NULLS false);
+----
+Possible Solution: Change the maximum length size, e.g., max_line_size=2097165
+
+endloop
--- a/external/duckdb/test/sql/copy/csv/csv_memory_management.test_slow
+++ b/external/duckdb/test/sql/copy/csv/csv_memory_management.test_slow
@@ -0,0 +1,41 @@
+# name: test/sql/copy/csv/csv_memory_management.test_slow
+# description: Test the CSV Buffer Manager under strict memory limit conditions
+# group: [csv]
+
+statement ok
+PRAGMA enable_verification
+
+statement ok
+SET memory_limit='512MB';
+
+statement ok
+SET threads=16;
+
+#100KK rows, 2 BIGINT columns = 1.6GB uncompressed
+statement ok
+COPY (SELECT i, i // 5 AS j FROM range(100000000) t(i)) TO '__TEST_DIR__/integers.csv'
+
+statement ok
+CALL enable_logging('FileSystem')
+
+query I
+select count(*) from '__TEST_DIR__/integers.csv'
+----
+100000000
+
+statement ok
+COPY (SELECT i, i // 5 AS j FROM range(100000000) t(i)) TO '__TEST_DIR__/integers.csv.gz'
+
+statement ok
+SET temp_directory='';
+
+statement ok
+SET memory_limit='80MB';
+
+statement ok
+SET threads=1;
+
+query I
+select count(*) from '__TEST_DIR__/integers.csv.gz'
+----
+100000000
--- a/external/duckdb/test/sql/copy/csv/csv_names.test
+++ b/external/duckdb/test/sql/copy/csv/csv_names.test
@@ -0,0 +1,144 @@
+# name: test/sql/copy/csv/csv_names.test
+# description: Read a CSV with names flags
+# group: [csv]
+
+statement ok
+PRAGMA enable_verification
+
+# Duplicate names shuold not be accepted
+statement error
+from read_csv('data/csv/header_bug.csv', names=['col1', 'col1']) LIMIT 1;
+----
+read_csv names must have unique values
+
+# Empty Names should not be accepted
+statement error
+from read_csv('data/csv/header_bug.csv', names=['']) LIMIT 1;
+----
+read_csv names cannot have empty (or all whitespace) value
+
+statement error
+from read_csv('data/csv/header_bug.csv', names=[' ', '  '], header = 0);
+----
+read_csv names cannot have empty (or all whitespace) value
+
+# no names provided
+query IIII
+select column00, column01, column02, column03 from 'data/csv/real/lineitem_sample.csv' LIMIT 1;
+----
+1	15519	785	1
+
+# override the names partially
+query IIII
+select l_orderkey, l_partkey, column02, column03 from read_csv_auto('data/csv/real/lineitem_sample.csv', names=['l_orderkey', 'l_partkey']) LIMIT 1;
+----
+1	15519	785	1
+
+# empty list
+query IIII
+select column00, column01, column02, column03 from read_csv_auto('data/csv/real/lineitem_sample.csv', names=[]) LIMIT 1;
+----
+1	15519	785	1
+
+# specify all names
+query IIII
+select l_orderkey, l_partkey, l_commitdate, l_comment from read_csv_auto('data/csv/real/lineitem_sample.csv', column_names=['l_orderkey', 'l_partkey', 'l_suppkey', 'l_linenumber', 'l_quantity', 'l_extendedprice', 'l_discount', 'l_tax', 'l_returnflag', 'l_linestatus', 'l_shipdate', 'l_commitdate', 'l_receiptdate', 'l_shipinstruct', 'l_shipmode', 'l_comment']) LIMIT 1;
+----
+1	15519	1996-02-12	egular courts above the
+
+# specify too many names
+statement error
+select l_orderkey, l_partkey, l_commitdate, l_comment from read_csv_auto('data/csv/real/lineitem_sample.csv', names=['l_orderkey', 'l_partkey', 'l_suppkey', 'l_linenumber', 'l_quantity', 'l_extendedprice', 'l_discount', 'l_tax', 'l_returnflag', 'l_linestatus', 'l_shipdate', 'l_commitdate', 'l_receiptdate', 'l_shipinstruct', 'l_shipmode', 'l_comment', 'xx']) LIMIT 1;
+----
+Error when sniffing file "data/csv/real/lineitem_sample.csv".
+
+# specify names on a file with a header
+query II
+select yr, Quarter from read_csv_auto('data/csv/real/ontime_sample.csv', names=['yr']) LIMIT 1;
+----
+1988	1
+
+# NULL
+statement error
+select column00, column01, column02, column03 from read_csv_auto('data/csv/real/lineitem_sample.csv', names=NULL) LIMIT 1;
+----
+read_csv names cannot be NULL
+
+# specify the names twice
+statement error
+select l_orderkey, l_partkey, column02, column03 from read_csv_auto('data/csv/real/lineitem_sample.csv', names=['l_orderkey', 'l_partkey'], column_names=['l_orderkey']) LIMIT 1;
+----
+read_csv column_names/names can only be supplied once
+
+statement error
+select l_orderkey, l_partkey, column02, column03 from read_csv_auto('data/csv/real/lineitem_sample.csv', names=42) LIMIT 1;
+----
+Failed to cast value: Unimplemented type for cast (INTEGER -> VARCHAR[])
+
+# specify options delim and sep
+statement error
+select column00 from read_csv_auto('data/csv/real/lineitem_sample.csv', delim='|', sep='|') LIMIT 1;
+----
+CSV Reader function option delim and sep are aliases, only one can be supplied
+
+# duplicate names
+statement error
+select l_orderkey, l_partkey, column02, column03 from read_csv_auto('data/csv/real/lineitem_sample.csv', names=['l_orderkey', 'l_orderkey']) LIMIT 1;
+----
+read_csv names must have unique values. "l_orderkey" is repeated.
+
+query I
+select Columns FROM sniff_csv('data/csv/header.csv', names = ['a'])
+----
+[{'name': a, 'type': VARCHAR}]
+
+query I
+FROM read_csv('data/csv/header.csv', names = ['a'])
+----
+line2
+line3
+
+query I
+select Columns FROM sniff_csv('data/csv/header.csv', names = ['a'], header = false)
+----
+[{'name': a, 'type': VARCHAR}]
+
+query I
+FROM read_csv('data/csv/header.csv', names = ['a'], header = false)
+----
+line1
+line2
+line3
+
+query I
+select Columns FROM sniff_csv('data/csv/header_2.csv', names = ['a'])
+----
+[{'name': a, 'type': VARCHAR}, {'name': line1_2, 'type': VARCHAR}, {'name': line1_3, 'type': VARCHAR}]
+
+query III
+FROM read_csv('data/csv/header_2.csv', names = ['a'])
+----
+line2	line2_2	line2_3
+line3	line3_2	line3_3
+
+
+query I
+select Columns FROM sniff_csv('data/csv/header_2.csv', names = ['a'], header=False)
+----
+[{'name': a, 'type': VARCHAR}, {'name': column1, 'type': VARCHAR}, {'name': column2, 'type': VARCHAR}]
+
+statement error
+select Columns FROM sniff_csv('data/csv/header_2.csv', names = ['a','b','c','d'])
+----
+Error when sniffing file "data/csv/header_2.csv"
+
+query I
+select Columns FROM sniff_csv('data/csv/header_2.csv', names = ['a','b','c','d'], null_padding = True)
+----
+[{'name': a, 'type': VARCHAR}, {'name': b, 'type': VARCHAR}, {'name': c, 'type': VARCHAR}, {'name': d, 'type': VARCHAR}]
+
+query IIII
+FROM read_csv('data/csv/header_2.csv', names = ['a','b','c','d'], null_padding = True)
+----
+line2	line2_2	line2_3	NULL
+line3	line3_2	line3_3	NULL
--- a/external/duckdb/test/sql/copy/csv/csv_null_byte.test
+++ b/external/duckdb/test/sql/copy/csv/csv_null_byte.test
@@ -0,0 +1,32 @@
+# name: test/sql/copy/csv/csv_null_byte.test
+# description: Read a CSV with a null byte
+# group: [csv]
+
+statement ok
+PRAGMA enable_verification
+
+query III
+select * from 'data/csv/nullbyte.csv';
+----
+val1	val\02	val3
+
+query III
+select * from read_csv('data/csv/nullbyte.csv', columns={'col1': 'VARCHAR', 'col2': 'VARCHAR', 'col3': 'VARCHAR'}, delim='|');
+----
+val1	val\02	val3
+
+query II
+select * from 'data/csv/nullbyte_header.csv';
+----
+val1	val2
+
+query II
+select * from read_csv('data/csv/nullbyte_header.csv', columns={'col1': 'VARCHAR', 'col2': 'VARCHAR'}, delim='|', header=False);
+----
+col1	col\02
+val1	val2
+
+query II
+select * from read_csv('data/csv/nullbyte_header.csv', columns={'col1': 'VARCHAR', 'col2': 'VARCHAR'}, delim='|', header=True);
+----
+val1	val2
--- a/external/duckdb/test/sql/copy/csv/csv_null_padding.test
+++ b/external/duckdb/test/sql/copy/csv/csv_null_padding.test
@@ -0,0 +1,51 @@
+# name: test/sql/copy/csv/csv_null_padding.test
+# description: Test nullpadding setting
+# group: [csv]
+
+statement ok
+PRAGMA enable_verification
+
+# null padding with a header
+query IIII
+FROM read_csv_auto('data/csv/nullpadding_header.csv', null_padding=True, comment = '')
+----
+one	two	three	four
+1	a	alice	NULL
+2	b	bob	NULL
+
+# without null padding we can only read one column
+query I
+FROM read_csv_auto('data/csv/nullpadding_header.csv', null_padding=False, header = 0)
+----
+# this file has a bunch of gunk at the top
+one,two,three,four
+1,a,alice
+2,b,bob
+
+query I
+FROM read_csv_auto('data/csv/nullpadding_header.csv', null_padding=False, skip=1, header = 0, comment = '')
+----
+one,two,three,four
+1,a,alice
+2,b,bob
+
+query III
+FROM read_csv_auto('data/csv/nullpadding_header.csv', null_padding=False, skip=2)
+----
+1	a	alice
+2	b	bob
+
+query I
+FROM read_csv_auto('data/csv/blank_line.csv', null_padding=True)
+----
+1
+2
+3
+4
+5
+6
+7
+8
+9
+NULL
+11
--- a/external/duckdb/test/sql/copy/csv/csv_nullstr_list.test
+++ b/external/duckdb/test/sql/copy/csv/csv_nullstr_list.test
@@ -0,0 +1,163 @@
+# name: test/sql/copy/csv/csv_nullstr_list.test
+# description: Test CSVs with multiple nullstring values
+# group: [csv]
+
+statement ok
+PRAGMA enable_verification
+
+# Test List
+query III
+FROM read_csv('data/csv/null/multiple_nulls.csv', auto_detect=false, delim=',', quote='"', escape='"',  skip=0, header=true, columns={'name': 'VARCHAR', 'age': 'VARCHAR', 'height': 'VARCHAR'}, nullstr = ['','none','null']);
+----
+Pedro	31	1.73
+Mark	NULL	NULL
+Thijs	26	NULL
+
+# Test Quoted
+query III
+FROM read_csv('data/csv/null/multiple_quoted_nulls.csv', auto_detect=false, delim=',', quote='"', escape='"', skip=0, header=true, columns={'name': 'VARCHAR', 'age': 'VARCHAR', 'height': 'VARCHAR'}, nullstr = ['','none','null']);
+----
+Pedro	31	1.73
+Mark	NULL	NULL
+Thijs	26	NULL
+
+#allow_quoted_nulls = false
+query III
+FROM read_csv('data/csv/null/multiple_quoted_nulls.csv', auto_detect=false, delim=',', quote='"', escape='"',  skip=0, header=true, columns={'name': 'VARCHAR', 'age': 'VARCHAR', 'height': 'VARCHAR'}, nullstr = ['','none','null'], allow_quoted_nulls = false);
+----
+Pedro	31	1.73
+Mark	null	(empty)
+Thijs	26	none
+
+# Test nullstr = []
+statement error
+FROM read_csv('data/csv/null/multiple_nulls.csv', auto_detect=false, delim=',', quote='"', escape='"', skip=0, header=true, columns={'name': 'VARCHAR', 'age': 'VARCHAR', 'height': 'VARCHAR'}, nullstr = []);
+----
+CSV Reader function option nullstr requires a non-empty list of possible null strings (varchar) as input
+
+# Test nullstr = ['a', NULL]
+statement error
+FROM read_csv('data/csv/null/multiple_nulls.csv', auto_detect=false, delim=',', quote='"', escape='"',  skip=0, header=true, columns={'name': 'VARCHAR', 'age': 'VARCHAR', 'height': 'VARCHAR'}, nullstr = ['a', NULL]);
+----
+CSV Reader function option nullstr does not accept NULL values as a valid nullstr option
+
+# Test nullstr = NULL
+statement error
+FROM read_csv('data/csv/null/multiple_nulls.csv', auto_detect=false, delim=',', quote='"', escape='"',  skip=0, header=true, columns={'name': 'VARCHAR', 'age': 'VARCHAR', 'height': 'VARCHAR'}, nullstr = NULL);
+----
+CSV Reader function option nullstr requires a string or a list as input
+
+# Test nullstr = [42]
+statement error
+FROM read_csv('data/csv/null/multiple_nulls.csv', auto_detect=false, delim=',', quote='"', escape='"',  skip=0, header=true, columns={'name': 'VARCHAR', 'age': 'VARCHAR', 'height': 'VARCHAR'}, nullstr = [42]);
+----
+CSV Reader function option nullstr requires a non-empty list of possible null strings (varchar) as input
+
+# Test Null Strings equal to delim quote escape
+statement error
+FROM read_csv('data/csv/null/multiple_quoted_nulls.csv', auto_detect=false, delim=',', quote='"', escape='"', skip=0, header=true, columns={'name': 'VARCHAR', 'age': 'VARCHAR', 'height': 'VARCHAR'}, nullstr = ['',',','null'], allow_quoted_nulls = false);
+----
+DELIMITER must not appear in the NULL specification and vice versa
+
+statement error
+FROM read_csv('data/csv/null/multiple_quoted_nulls.csv', auto_detect=false, delim=',', quote='"', escape='\', skip=0, header=true, columns={'name': 'VARCHAR', 'age': 'VARCHAR', 'height': 'VARCHAR'}, nullstr = ['','"','null'], allow_quoted_nulls = false);
+----
+QUOTE must not appear in the NULL specification and vice versa
+
+statement error
+FROM read_csv('data/csv/null/multiple_quoted_nulls.csv', auto_detect=false, delim=',', quote='"', escape='\',  skip=0, header=true, columns={'name': 'VARCHAR', 'age': 'VARCHAR', 'height': 'VARCHAR'}, nullstr = ['','\','null'], allow_quoted_nulls = false);
+----
+ESCAPE must not appear in the NULL specification and vice versa
+
+# What if we have repeated values in our nullstr list?
+query III
+FROM read_csv('data/csv/null/multiple_quoted_nulls.csv', auto_detect=false, delim=',', quote='"', escape='"',  skip=0, header=true, columns={'name': 'VARCHAR', 'age': 'VARCHAR', 'height': 'VARCHAR'}, nullstr = ['','none','null','','none','null'], allow_quoted_nulls = false);
+----
+Pedro	31	1.73
+Mark	null	(empty)
+Thijs	26	none
+
+# Test with force_not_null
+query III
+FROM read_csv('data/csv/null/multiple_nulls.csv', auto_detect=false, delim=',', quote='"', escape='"',  skip=0, header=true, columns={'name': 'VARCHAR', 'age': 'VARCHAR', 'height': 'VARCHAR'}, nullstr = ['','none','null'], force_not_null = ['height']);
+----
+Pedro	31	1.73
+Mark	NULL	(empty)
+Thijs	26	(empty)
+
+query III
+FROM read_csv('data/csv/null/multiple_nulls.csv', auto_detect=false, delim=',', quote='"', escape='"',  skip=0, header=true, columns={'name': 'VARCHAR', 'age': 'VARCHAR', 'height': 'VARCHAR'}, nullstr = ['','none','null'], force_not_null = ['age','height']);
+----
+Pedro	31	1.73
+Mark	(empty)	(empty)
+Thijs	26	(empty)
+
+# Test Quoted
+query III
+FROM read_csv('data/csv/null/multiple_quoted_nulls.csv', auto_detect=false, delim=',', quote='"', escape='"', skip=0, header=true, columns={'name': 'VARCHAR', 'age': 'VARCHAR', 'height': 'VARCHAR'}, nullstr = ['','none','null'], force_not_null = ['height']);
+----
+Pedro	31	1.73
+Mark	NULL	(empty)
+Thijs	26	(empty)
+
+query III
+FROM read_csv('data/csv/null/multiple_quoted_nulls.csv', auto_detect=true, delim=',', quote='"', escape='"',  skip=0, header=true, nullstr = ['','none','null'], force_not_null = ['age','height'], ALL_VARCHAR = 1);
+----
+Pedro	31	1.73
+Mark	(empty)	(empty)
+Thijs	26	(empty)
+
+# Test with projection push-down
+query I
+select height FROM read_csv('data/csv/null/multiple_nulls.csv', delim=',', quote='"', escape='"',  skip=0, header=true, nullstr = ['','none','null']);
+----
+1.73
+NULL
+NULL
+
+query I
+select age FROM read_csv('data/csv/null/multiple_nulls.csv',  delim=',', quote='"', escape='"',  skip=0, header=true,  nullstr = ['','none','null']);
+----
+31
+NULL
+26
+
+# Test force_not_null fails for made-up column
+statement error
+FROM read_csv('data/csv/null/multiple_nulls.csv', auto_detect=false, delim=',', quote='"', escape='"',  skip=0, header=true, columns={'name': 'VARCHAR', 'age': 'VARCHAR', 'height': 'VARCHAR'}, nullstr = ['','none','null'], force_not_null = ['dont_exist']);
+----
+"force_not_null" expected to find dont_exist, but it was not found in the table
+
+# Lests add a few tests with copy from
+statement ok
+CREATE TABLE data (a VARCHAR, b VARCHAR, c VARCHAR)
+
+statement ok
+COPY data FROM 'data/csv/null/multiple_nulls.csv' (nullstr  ['','none','null'], HEADER 1);
+
+statement error
+COPY data FROM 'data/csv/null/multiple_nulls.csv' (nullstr NULL, HEADER 1);
+----
+NULL is not supported
+
+statement error
+COPY data FROM 'data/csv/null/multiple_nulls.csv' (nullstr [NULL], HEADER 1);
+----
+Binder Error: CSV Reader function option nullstr requires a non-empty list of possible null strings (varchar) as input
+
+statement error
+COPY data FROM 'data/csv/null/multiple_nulls.csv' (nullstr [42], HEADER 1);
+----
+Binder Error: CSV Reader function option nullstr requires a non-empty list of possible null strings (varchar) as input
+
+query III
+FROM data
+----
+Pedro	31	1.73
+Mark	NULL	NULL
+Thijs	26	NULL
+
+statement error
+COPY data TO '__TEST_DIR__/multiple_nulls.csv' (nullstr ['a', 'b']);
+----
+CSV Writer function option nullstr only accepts one nullstr value.
--- a/external/duckdb/test/sql/copy/csv/csv_projection_pushdown.test
+++ b/external/duckdb/test/sql/copy/csv/csv_projection_pushdown.test
@@ -0,0 +1,49 @@
+# name: test/sql/copy/csv/csv_projection_pushdown.test
+# description: CSV reader projection pushdown
+# group: [csv]
+
+statement ok
+PRAGMA enable_verification
+
+statement ok
+CREATE TABLE tbl(i INT, j VARCHAR, k DATE);
+
+statement ok
+INSERT INTO tbl VALUES (42, 'hello world', NULL),  (NULL, NULL, DATE '1992-01-01'), (100, 'thisisalongstring', DATE '2000-01-01');
+
+statement ok
+COPY tbl TO '__TEST_DIR__/projection_pushdown.csv' (FORMAT CSV);
+
+statement ok
+CREATE VIEW v1 AS FROM read_csv_auto('__TEST_DIR__/projection_pushdown.csv', filename=True)
+
+query I
+SELECT COUNT(*) FROM v1
+----
+3
+
+query III
+SELECT i, j, k FROM v1 ORDER BY i NULLS LAST
+----
+42	hello world	NULL
+100	thisisalongstring	2000-01-01
+NULL	NULL	1992-01-01
+
+query I
+SELECT j FROM v1 ORDER BY j NULLS LAST
+----
+hello world
+thisisalongstring
+NULL
+
+query I
+SELECT j FROM v1 ORDER BY j NULLS LAST
+----
+hello world
+thisisalongstring
+NULL
+
+query I
+SELECT filename.replace('\', '/').split('/')[-1] FROM v1 LIMIT 1
+----
+projection_pushdown.csv
--- a/external/duckdb/test/sql/copy/csv/csv_quoted_newline_incorrect.test
+++ b/external/duckdb/test/sql/copy/csv/csv_quoted_newline_incorrect.test
@@ -0,0 +1,15 @@
+# name: test/sql/copy/csv/csv_quoted_newline_incorrect.test
+# description: Read a CSV with an incorrect quoted newline, is expected that the csv reader manages to skip dirty lines
+# group: [csv]
+
+statement ok
+PRAGMA enable_verification
+
+# force parallelism of the queries
+statement ok
+PRAGMA verify_parallelism
+
+# CSV reader skips malformed lines
+statement ok
+from 'data/csv/csv_quoted_newline_odd.csv';
+
--- a/external/duckdb/test/sql/copy/csv/csv_roundtrip_single_null.test
+++ b/external/duckdb/test/sql/copy/csv/csv_roundtrip_single_null.test
@@ -0,0 +1,20 @@
+# name: test/sql/copy/csv/csv_roundtrip_single_null.test
+# description: Round-trip a single NULL value
+# group: [csv]
+
+statement ok
+PRAGMA enable_verification
+
+statement ok
+COPY (SELECT NULL) TO '__TEST_DIR__/single_null.csv' (HEADER 0)
+
+statement ok
+CREATE TABLE integers(i INTEGER);
+
+statement ok
+COPY integers FROM '__TEST_DIR__/single_null.csv' (HEADER 0)
+
+query I
+FROM integers
+----
+NULL
--- a/external/duckdb/test/sql/copy/csv/csv_windows_mixed_separators.test
+++ b/external/duckdb/test/sql/copy/csv/csv_windows_mixed_separators.test
@@ -0,0 +1,45 @@
+# name: test/sql/copy/csv/csv_windows_mixed_separators.test
+# description: Test mixed separators on Windows
+# group: [csv]
+
+require windows
+
+statement ok
+PRAGMA enable_verification
+
+# \  and / are interchangeable on Windows
+query I
+SELECT * FROM 'data\csv/test/date.csv'
+----
+2019-06-05
+
+query I
+SELECT * FROM glob('data/csv\test/*.csv') t(g) WHERE g LIKE '%date.csv'
+----
+data\csv\test\date.csv
+
+# also for attach
+statement ok
+ATTACH '__TEST_DIR__/windows_test.db' AS s1
+
+statement  ok
+CREATE TABLE s1.tbl AS SELECT * FROM range(10) t(i);
+
+query I
+SELECT SUM(i) FROM s1.tbl
+----
+45
+
+statement ok
+DETACH s1
+
+statement ok
+ATTACH '__TEST_DIR__\windows_test.db' AS s1
+
+query I
+SELECT SUM(i) FROM s1.tbl
+----
+45
+
+statement ok
+DETACH s1
--- a/external/duckdb/test/sql/copy/csv/csv_write_gz.test_slow
+++ b/external/duckdb/test/sql/copy/csv/csv_write_gz.test_slow
@@ -0,0 +1,35 @@
+# name: test/sql/copy/csv/csv_write_gz.test_slow
+# description: Test round-trip writing of gzip CSV files
+# group: [csv]
+
+statement ok
+PRAGMA enable_verification
+
+foreach csv_name greek_utf8.csv imdb_movie_info_escaped.csv lineitem_sample.csv ncvoter.csv nfc_normalization.csv ontime_sample.csv voter.tsv web_page.csv
+
+statement ok
+CREATE TABLE csv_data AS SELECT * FROM 'data/csv/real/${csv_name}';
+
+statement ok
+COPY csv_data TO '__TEST_DIR__/${csv_name}.gz' (COMPRESSION GZIP, HEADER 0);
+
+statement ok
+CREATE TABLE csv_data_gz AS SELECT * FROM '__TEST_DIR__/${csv_name}.gz';
+
+query I
+SELECT COUNT(*) FROM (SELECT * FROM csv_data EXCEPT SELECT * FROM csv_data_gz)
+----
+0
+
+query I
+SELECT COUNT(*) FROM (SELECT * FROM csv_data_gz EXCEPT SELECT * FROM csv_data)
+----
+0
+
+statement ok
+DROP TABLE csv_data;
+
+statement ok
+DROP TABLE csv_data_gz;
+
+endloop
--- a/external/duckdb/test/sql/copy/csv/csv_write_zstd.test_slow
+++ b/external/duckdb/test/sql/copy/csv/csv_write_zstd.test_slow
@@ -0,0 +1,39 @@
+# name: test/sql/copy/csv/csv_write_zstd.test_slow
+# description: Test round-trip writing of zstd CSV files
+# group: [csv]
+
+require parquet
+
+require no_extension_autoloading "FIXME: Autoloading on zstd compression (parquet) not yet there"
+
+statement ok
+PRAGMA enable_verification
+
+foreach csv_name greek_utf8.csv imdb_movie_info_escaped.csv lineitem_sample.csv ncvoter.csv nfc_normalization.csv ontime_sample.csv voter.tsv web_page.csv
+
+statement ok
+CREATE TABLE csv_data AS SELECT * FROM 'data/csv/real/${csv_name}';
+
+statement ok
+COPY csv_data TO '__TEST_DIR__/${csv_name}.zst' (COMPRESSION ZSTD, HEADER 0);
+
+statement ok
+CREATE TABLE csv_data_zst AS SELECT * FROM '__TEST_DIR__/${csv_name}.zst';
+
+query I
+SELECT COUNT(*) FROM (SELECT * FROM csv_data EXCEPT SELECT * FROM csv_data_zst)
+----
+0
+
+query I
+SELECT COUNT(*) FROM (SELECT * FROM csv_data_zst EXCEPT SELECT * FROM csv_data)
+----
+0
+
+statement ok
+DROP TABLE csv_data;
+
+statement ok
+DROP TABLE csv_data_zst;
+
+endloop
--- a/external/duckdb/test/sql/copy/csv/duck_fuzz/test_internal_4048.test
+++ b/external/duckdb/test/sql/copy/csv/duck_fuzz/test_internal_4048.test
@@ -0,0 +1,20 @@
+# name: test/sql/copy/csv/duck_fuzz/test_internal_4048.test
+# description: Test Fuzz Issue 4048
+# group: [duck_fuzz]
+
+statement ok
+PRAGMA enable_verification
+
+statement error
+FROM sniff_csv('data/csv/14512.csv', names := [NULL]);
+----
+Binder Error: read_csv names parameter cannot have a NULL value
+
+statement ok
+create table all_types as select * exclude(small_enum, medium_enum, large_enum) from test_all_types() limit 0;
+
+statement error
+SELECT DISTINCT NULL, c3, (c4 <= c1), (c3 BETWEEN c4 AND c2)
+FROM sniff_csv('1a616242-1dcd-4914-99d1-16119d9b6e4c', "names" := ['1970-01-01'::DATE, 'infinity'::DATE, '-infinity'::DATE, NULL, '2022-05-12'::DATE], filename := '9be2bc9d-d49f-4564-bfa4-6336b211a874') AS t5(c1, c2, c3, c4) WHERE c1 GROUP BY c3 LIMIT ('c4000757-69ca-400e-b58a-1dac73b85595' IS NULL);
+----
+Binder Error: read_csv names parameter cannot have a NULL value
--- a/external/duckdb/test/sql/copy/csv/empty_first_line.test
+++ b/external/duckdb/test/sql/copy/csv/empty_first_line.test
@@ -0,0 +1,20 @@
+# name: test/sql/copy/csv/empty_first_line.test
+# description: Issue #4933: Reading a CSV file with an empty header is problematic
+# group: [csv]
+
+statement ok
+PRAGMA enable_verification
+
+query II
+SELECT * FROM read_csv_auto('data/csv/empty_first_line.csv', delim=' ');
+----
+a	1
+b	2
+c	3
+
+query I
+SELECT * FROM read_csv_auto('data/csv/empty_first_line.csv', delim='|', auto_detect=false, columns={'column00': 'VARCHAR'}, skip = 1);
+----
+a 1
+b 2
+c 3
--- a/external/duckdb/test/sql/copy/csv/empty_string_quote.test
+++ b/external/duckdb/test/sql/copy/csv/empty_string_quote.test
@@ -0,0 +1,37 @@
+# name: test/sql/copy/csv/empty_string_quote.test
+# description: Test empty string quote
+# group: [csv]
+
+statement ok
+PRAGMA enable_verification
+
+statement ok
+CREATE TABLE customer(c_customer_sk INTEGER, c_customer_id VARCHAR, c_current_cdemo_sk INTEGER, c_current_hdemo_sk INTEGER, c_current_addr_sk INTEGER, c_first_shipto_date_sk INTEGER, c_first_sales_date_sk INTEGER, c_salutation VARCHAR, c_first_name VARCHAR, c_last_name VARCHAR, c_preferred_cust_flag VARCHAR, c_birth_day INTEGER, c_birth_month INTEGER, c_birth_year INTEGER, c_birth_country VARCHAR, c_login VARCHAR, c_email_address VARCHAR, c_last_review_date_sk INTEGER);
+
+statement ok
+COPY customer FROM 'data/csv/customer.csv' (FORMAT 'csv', quote '"', delimiter ',', header 0);
+
+query IIIIIIIIIIIIIIIIII
+SELECT * FROM customer
+----
+1	AAAAAAAABAAAAAAA	980124	7135	32946	2452238	2452208	Mr.	Javier	Lewis	Y	9	12	1936	CHILE	NULL	Javier.Lewis@VFAxlnZEvOx.org	2452508
+2	AAAAAAAACAAAAAAA	819667	1461	31655	2452318	2452288	Dr.	Amy	Moses	Y	9	4	1966	TOGO	NULL	Amy.Moses@Ovk9KjHH.com	2452318
+3	AAAAAAAADAAAAAAA	1473522	6247	48572	2449130	2449100	Miss	Latisha	Hamilton	Y	18	9	1979	NIUE	NULL	Latisha.Hamilton@V.com	2452313
+4	AAAAAAAAEAAAAAAA	1703214	3986	39558	2450030	2450000	Dr.	Michael	White	Y	7	6	1983	MEXICO	NULL	Michael.White@i.org	2452361
+5	AAAAAAAAFAAAAAAA	953372	4470	36368	2449438	2449408	Sir	Robert	Moran	N	8	5	1956	FIJI	NULL	Robert.Moran@Hh.edu	2452469
+6	AAAAAAAAGAAAAAAA	213219	6374	27082	2451883	2451853	Ms.	Brunilda	Sharp	Y	4	12	1925	SURINAME	NULL	Brunilda.Sharp@T3pylZEUQjm.org	2452430
+7	AAAAAAAAHAAAAAAA	68377	3219	44814	2451438	2451408	Ms.	Fonda	Wiles	N	24	4	1985	GAMBIA	NULL	Fonda.Wiles@S9KnyEtz9hv.org	2452360
+8	AAAAAAAAIAAAAAAA	1215897	2471	16598	2449406	2449376	Sir	Ollie	Shipman	N	26	12	1938	KOREA, REPUBLIC OF	NULL	Ollie.Shipman@be.org	2452334
+9	AAAAAAAAJAAAAAAA	1168667	1404	49388	2452275	2452245	Sir	Karl	Gilbert	N	26	10	1966	MONTSERRAT	NULL	Karl.Gilbert@Crg5KyP2IxX9C4d6.edu	2452454
+10	AAAAAAAAKAAAAAAA	1207553	5143	19580	2451353	2451323	Ms.	Albert	Brunson	N	15	10	1973	JORDAN	NULL	Albert.Brunson@62.com	2452641
+
+statement ok
+CREATE TABLE customer_quoted_nulls(c_customer_sk INTEGER, c_customer_id VARCHAR, c_current_cdemo_sk INTEGER, c_current_hdemo_sk INTEGER, c_current_addr_sk INTEGER, c_first_shipto_date_sk INTEGER, c_first_sales_date_sk INTEGER, c_salutation VARCHAR, c_first_name VARCHAR, c_last_name VARCHAR, c_preferred_cust_flag VARCHAR, c_birth_day INTEGER, c_birth_month INTEGER, c_birth_year INTEGER, c_birth_country VARCHAR, c_login VARCHAR, c_email_address VARCHAR, c_last_review_date_sk INTEGER);
+
+statement ok
+insert into customer_quoted_nulls select * from read_csv_auto('data/csv/customer.csv', allow_quoted_nulls=False)
+
+query I
+SELECT COUNT(c_login) FROM customer_quoted_nulls
+----
+10
--- a/external/duckdb/test/sql/copy/csv/except.test
+++ b/external/duckdb/test/sql/copy/csv/except.test
@@ -0,0 +1,14 @@
+# name: test/sql/copy/csv/except.test
+# description: Test Except works when one of the children is a CSV File
+# group: [csv]
+
+statement ok
+PRAGMA enable_verification
+
+statement ok
+COPY (SELECT 1 a, 2 b) TO '__TEST_DIR__/mismatch_types_except.csv';
+
+query II
+FROM '__TEST_DIR__/mismatch_types_except.csv' EXCEPT select 'bla' as a, 1 as b;
+----
+1	2
--- a/external/duckdb/test/sql/copy/csv/glob/copy_csv_glob.test
+++ b/external/duckdb/test/sql/copy/csv/glob/copy_csv_glob.test
@@ -0,0 +1,33 @@
+# name: test/sql/copy/csv/glob/copy_csv_glob.test
+# description: Test globbing CSVs
+# group: [glob]
+
+statement ok
+PRAGMA enable_verification
+
+statement ok
+CREATE TABLE dates(d DATE);
+
+# simple globbing
+statement ok
+COPY dates FROM 'data/csv/glob/a?/*.csv' (AUTO_DETECT 1);
+
+query I
+SELECT * FROM dates ORDER BY 1
+----
+2019-06-05
+2019-06-15
+2019-06-25
+2019-07-05
+2019-07-15
+2019-07-25
+2019-08-05
+2019-08-15
+2019-08-25
+
+# nothing matches the glob
+statement error
+COPY dates FROM read_csv('data/csv/glob/*/a*a.csv', auto_detect=1)
+----
+syntax error at or near "'data/csv/glob/*/a*a.csv'"
+
--- a/external/duckdb/test/sql/copy/csv/glob/read_csv_glob.test
+++ b/external/duckdb/test/sql/copy/csv/glob/read_csv_glob.test
@@ -0,0 +1,287 @@
+# name: test/sql/copy/csv/glob/read_csv_glob.test
+# description: Test globbing CSVs
+# group: [glob]
+
+statement ok
+PRAGMA enable_verification
+
+query IIIII
+select typeof(#1),typeof(#2),typeof(#3),typeof(#4),typeof(#5) FROM read_csv('data/csv/per_thread/*.csv') limit 1
+----
+VARCHAR	BOOLEAN	DOUBLE	DOUBLE	VARCHAR
+
+query IIIII
+select typeof(#1),typeof(#2),typeof(#3),typeof(#4),typeof(#5) FROM read_csv(['data/csv/per_thread/c1.csv', 'data/csv/per_thread/c2.csv']) limit 1
+----
+VARCHAR	BOOLEAN	DOUBLE	DOUBLE	VARCHAR
+
+query IIIII
+select typeof(#1),typeof(#2),typeof(#3),typeof(#4),typeof(#5) FROM read_csv(['data/csv/per_thread/c2.csv', 'data/csv/per_thread/c1.csv', 'data/csv/per_thread/c3.csv']) limit 1
+----
+VARCHAR	BOOLEAN	DOUBLE	DOUBLE	VARCHAR
+
+# simple globbing
+query I
+SELECT * FROM read_csv('data/csv/glob/a?/*.csv') ORDER BY 1
+----
+2019-06-05
+2019-06-15
+2019-06-25
+2019-07-05
+2019-07-15
+2019-07-25
+2019-08-05
+2019-08-15
+2019-08-25
+
+query I
+SELECT * FROM read_csv('data/csv/glob/a?/a*.csv') ORDER BY 1
+----
+2019-06-05
+2019-06-15
+2019-06-25
+2019-07-05
+2019-07-15
+2019-07-25
+
+# list parameter
+query I
+SELECT * FROM read_csv(['data/csv/glob/a1/a1.csv', 'data/csv/glob/a2/a2.csv']) ORDER BY 1
+----
+2019-06-05
+2019-06-15
+2019-06-25
+2019-07-05
+2019-07-15
+2019-07-25
+
+query I
+SELECT * FROM read_csv_auto(['data/csv/glob/a1/a1.csv', 'data/csv/glob/a2/a2.csv']) ORDER BY 1
+----
+2019-06-05
+2019-06-15
+2019-06-25
+2019-07-05
+2019-07-15
+2019-07-25
+
+# multiple globs
+query I
+SELECT * FROM read_csv(['data/csv/glob/a?/a*.csv', 'data/csv/glob/a?/a*.csv']) ORDER BY 1
+----
+2019-06-05
+2019-06-05
+2019-06-15
+2019-06-15
+2019-06-25
+2019-06-25
+2019-07-05
+2019-07-05
+2019-07-15
+2019-07-15
+2019-07-25
+2019-07-25
+
+# more asterisks for directories
+query I
+SELECT * FROM read_csv('data/csv/*/a?/a*.csv') ORDER BY 1
+----
+2019-06-05
+2019-06-15
+2019-06-25
+2019-07-05
+2019-07-15
+2019-07-25
+
+query II
+SELECT a, b LIKE '%a1.csv%' FROM read_csv('data/csv/*/a?/a*.csv', filename=1) t1(a,b) ORDER BY 1
+----
+2019-06-05	1
+2019-06-15	1
+2019-06-25	1
+2019-07-05	0
+2019-07-15	0
+2019-07-25	0
+
+# read-csv auto fails here because of a type mismatch: most files contain dates, but one file contains integers
+statement error
+SELECT * FROM read_csv('data/csv/glob/*/*.csv') ORDER BY 1
+----
+Schema mismatch between globbed files.
+
+# forcing string parsing works
+query I
+SELECT * FROM read_csv('data/csv/glob/*/*.csv', columns=STRUCT_PACK(d := 'STRING')) ORDER BY 1
+----
+1
+2
+2019-06-05
+2019-06-15
+2019-06-25
+2019-07-05
+2019-07-15
+2019-07-25
+2019-08-05
+2019-08-15
+2019-08-25
+3
+
+query II
+SELECT a, b LIKE '%a_.csv' FROM read_csv('data/csv/glob/*/*.csv', columns=STRUCT_PACK(d := 'STRING'), filename=1) t(a,b) ORDER BY 1
+----
+1	0
+2	0
+2019-06-05	1
+2019-06-15	1
+2019-06-25	1
+2019-07-05	1
+2019-07-15	1
+2019-07-25	1
+2019-08-05	0
+2019-08-15	0
+2019-08-25	0
+3	0
+
+# test glob parsing
+query I
+SELECT COUNT(*) FROM glob('data/csv/glob/*/*.csv')
+----
+5
+
+query I
+SELECT COUNT(*) FROM glob(['data/csv/glob/*/*.csv'])
+----
+5
+
+
+query I
+SELECT COUNT(*) FROM glob(['data/csv/glob/*/*.csv', 'data/csv/glob/*/*.csv'])
+----
+10
+
+# we can also use windows file slashes
+query I
+SELECT COUNT(*) FROM glob('data\csv\glob\*\*.csv')
+----
+5
+
+# consecutive slashes are ignored
+query I
+SELECT COUNT(*) FROM glob('data//csv///glob///*//////*.csv')
+----
+5
+
+# nothing matches the glob
+statement error
+SELECT * FROM read_csv('data/csv/glob/*/a*a.csv') ORDER BY 1
+----
+No files found that match the pattern "data/csv/glob/*/a*a.csv"
+
+statement error
+SELECT * FROM read_csv(['data/csv/glob/*/a*a.csv']) ORDER BY 1
+----
+No files found that match the pattern "data/csv/glob/*/a*a.csv"
+
+statement error
+SELECT * FROM read_csv_auto(['data/csv/glob/*/a*a.csv']) ORDER BY 1
+----
+No files found that match the pattern "data/csv/glob/*/a*a.csv"
+
+query I
+SELECT COUNT(*) FROM glob('data/csv/glob/*/a*a.csv')
+----
+0
+
+query I
+select count(*) from glob('/rewoiarwiouw3rajkawrasdf790273489*.csv') limit 10;
+----
+0
+
+query I
+select count(*) from glob('~/rewoiarwiouw3rajkawrasdf790273489*.py') limit 10;
+----
+0
+
+require skip_reload
+
+# file_search_path with one path
+statement ok
+set file_search_path='data/csv/glob';
+
+query I
+SELECT COUNT(*) FROM glob('*/*.csv');
+----
+5
+
+# file_search_path with multiple paths
+statement ok
+set file_search_path='data/csv/glob/a1,data/csv/glob/a2';
+
+query I
+SELECT COUNT(*) FROM glob('*.csv');
+----
+2
+
+# file_search_path with a non-existent path
+statement ok
+set file_search_path='data/csv/glob,garbage';
+
+query I
+SELECT COUNT(*) FROM glob('*/*.csv');
+----
+5
+
+# Only file_search_path is searched
+query I
+SELECT COUNT(*) FROM glob('data/csv/glob/*/*.csv');
+----
+0
+
+# file_search_path can be cleared
+statement ok
+set file_search_path='';
+
+query I
+SELECT COUNT(*) FROM glob('data/csv/glob/*/*.csv');
+----
+5
+
+# empty list
+statement error
+SELECT * FROM read_csv_auto([]) ORDER BY 1
+----
+No function matches
+
+statement error
+SELECT * FROM read_csv_auto([]::VARCHAR[]) ORDER BY 1
+----
+at least one file
+
+# null list
+statement error
+SELECT * FROM read_csv_auto(NULL) ORDER BY 1
+----
+NULL
+
+statement error
+SELECT * FROM read_csv_auto([NULL]) ORDER BY 1
+----
+NULL
+
+statement error
+SELECT * FROM read_csv_auto(NULL::VARCHAR) ORDER BY 1
+----
+NULL
+
+statement error
+SELECT * FROM read_csv_auto(NULL::VARCHAR[]) ORDER BY 1
+----
+NULL
+
+statement ok
+SET threads=1;
+
+statement error
+FROM read_csv('data/csv/glob/*/*.csv');
+----
+Schema mismatch between globbed files.
--- a/Show More
+++ b/Show More