Add comments to ClickBench queries about setting binary_as_string (#16605)

alamb · comphead · web-flow · commit 92d8632b01b9 · 2025-07-08T07:30:24.000-07:00
* Add comments to ClickBench queries about setting binary_as_string

* Add to the rest of the files

* Add to extended too

* Apply suggestions from code review

Co-authored-by: Oleks V &lt;comphead@users.noreply.github.com&gt;

---------

Co-authored-by: Oleks V &lt;comphead@users.noreply.github.com&gt;
diff --git a/benchmarks/queries/clickbench/extended/q0.sql b/benchmarks/queries/clickbench/extended/q0.sql
@@ -1 +1,4 @@
+-- Must set for ClickBench hits_partitioned dataset. See https://github.com/apache/datafusion/issues/16591
+-- set datafusion.execution.parquet.binary_as_string = true
+
 SELECT COUNT(DISTINCT "SearchPhrase"), COUNT(DISTINCT "MobilePhone"), COUNT(DISTINCT "MobilePhoneModel") FROM hits;
diff --git a/benchmarks/queries/clickbench/extended/q1.sql b/benchmarks/queries/clickbench/extended/q1.sql
@@ -1 +1,4 @@
+-- Must set for ClickBench hits_partitioned dataset. See https://github.com/apache/datafusion/issues/16591
+-- set datafusion.execution.parquet.binary_as_string = true
+
 SELECT COUNT(DISTINCT "HitColor"), COUNT(DISTINCT "BrowserCountry"), COUNT(DISTINCT "BrowserLanguage")  FROM hits;
diff --git a/benchmarks/queries/clickbench/extended/q2.sql b/benchmarks/queries/clickbench/extended/q2.sql
@@ -1 +1,4 @@
+-- Must set for ClickBench hits_partitioned dataset. See https://github.com/apache/datafusion/issues/16591
+-- set datafusion.execution.parquet.binary_as_string = true
+
 SELECT "BrowserCountry",  COUNT(DISTINCT "SocialNetwork"), COUNT(DISTINCT "HitColor"), COUNT(DISTINCT "BrowserLanguage"), COUNT(DISTINCT "SocialAction") FROM hits GROUP BY 1 ORDER BY 2 DESC LIMIT 10;
diff --git a/benchmarks/queries/clickbench/extended/q3.sql b/benchmarks/queries/clickbench/extended/q3.sql
@@ -1 +1,4 @@
+-- Must set for ClickBench hits_partitioned dataset. See https://github.com/apache/datafusion/issues/16591
+-- set datafusion.execution.parquet.binary_as_string = true
+
 SELECT "SocialSourceNetworkID", "RegionID", COUNT(*), AVG("Age"), AVG("ParamPrice"), STDDEV("ParamPrice") as s, VAR("ParamPrice")  FROM hits GROUP BY "SocialSourceNetworkID", "RegionID" HAVING s IS NOT NULL ORDER BY s DESC LIMIT 10;
diff --git a/benchmarks/queries/clickbench/extended/q4.sql b/benchmarks/queries/clickbench/extended/q4.sql
@@ -1 +1,4 @@
+-- Must set for ClickBench hits_partitioned dataset. See https://github.com/apache/datafusion/issues/16591
+-- set datafusion.execution.parquet.binary_as_string = true
+
 SELECT "ClientIP", "WatchID",  COUNT(*) c, MIN("ResponseStartTiming") tmin, MEDIAN("ResponseStartTiming") tmed, MAX("ResponseStartTiming") tmax FROM hits WHERE "JavaEnable" = 0  GROUP BY  "ClientIP", "WatchID" HAVING c > 1 ORDER BY tmed DESC LIMIT 10;
diff --git a/benchmarks/queries/clickbench/extended/q5.sql b/benchmarks/queries/clickbench/extended/q5.sql
@@ -1 +1,4 @@
+-- Must set for ClickBench hits_partitioned dataset. See https://github.com/apache/datafusion/issues/16591
+-- set datafusion.execution.parquet.binary_as_string = true
+
 SELECT "ClientIP", "WatchID",  COUNT(*) c, MIN("ResponseStartTiming") tmin, APPROX_PERCENTILE_CONT(0.95) WITHIN GROUP (ORDER BY "ResponseStartTiming") tp95, MAX("ResponseStartTiming") tmax FROM 'hits' WHERE "JavaEnable" = 0 GROUP BY  "ClientIP", "WatchID" HAVING c > 1 ORDER BY tp95 DESC LIMIT 10;
diff --git a/benchmarks/queries/clickbench/extended/q6.sql b/benchmarks/queries/clickbench/extended/q6.sql
@@ -1 +1,4 @@
+-- Must set for ClickBench hits_partitioned dataset. See https://github.com/apache/datafusion/issues/16591
+-- set datafusion.execution.parquet.binary_as_string = true
+
 SELECT COUNT(*) AS ShareCount FROM hits WHERE "IsMobile" = 1 AND "MobilePhoneModel" LIKE 'iPhone%' AND "SocialAction" = 'share' AND "SocialSourceNetworkID" IN (5, 12) AND "ClientTimeZone" BETWEEN -5 AND 5 AND regexp_match("Referer", '\/campaign\/(spring|summer)_promo') IS NOT NULL AND CASE WHEN split_part(split_part("URL", 'resolution=', 2), '&', 1) ~ '^\d+$' THEN split_part(split_part("URL", 'resolution=', 2), '&', 1)::INT ELSE 0 END > 1920 AND levenshtein(CAST("UTMSource" AS STRING), CAST("UTMCampaign" AS STRING)) < 3;
diff --git a/benchmarks/queries/clickbench/queries/q0.sql b/benchmarks/queries/clickbench/queries/q0.sql
@@ -1 +1,4 @@
+-- Must set for ClickBench hits_partitioned dataset. See https://github.com/apache/datafusion/issues/16591
+
+-- set datafusion.execution.parquet.binary_as_string = true
 SELECT COUNT(*) FROM hits;
diff --git a/benchmarks/queries/clickbench/queries/q1.sql b/benchmarks/queries/clickbench/queries/q1.sql
@@ -1 +1,4 @@
+-- Must set for ClickBench hits_partitioned dataset. See https://github.com/apache/datafusion/issues/16591
+-- set datafusion.execution.parquet.binary_as_string = true
+
 SELECT COUNT(*) FROM hits WHERE "AdvEngineID" <> 0;
diff --git a/benchmarks/queries/clickbench/queries/q10.sql b/benchmarks/queries/clickbench/queries/q10.sql
@@ -1 +1,4 @@
+-- Must set for ClickBench hits_partitioned dataset. See https://github.com/apache/datafusion/issues/16591
+-- set datafusion.execution.parquet.binary_as_string = true
+
 SELECT "MobilePhoneModel", COUNT(DISTINCT "UserID") AS u FROM hits WHERE "MobilePhoneModel" <> '' GROUP BY "MobilePhoneModel" ORDER BY u DESC LIMIT 10;
diff --git a/benchmarks/queries/clickbench/queries/q11.sql b/benchmarks/queries/clickbench/queries/q11.sql
@@ -1 +1,4 @@
+-- Must set for ClickBench hits_partitioned dataset. See https://github.com/apache/datafusion/issues/16591
+-- set datafusion.execution.parquet.binary_as_string = true
+
 SELECT "MobilePhone", "MobilePhoneModel", COUNT(DISTINCT "UserID") AS u FROM hits WHERE "MobilePhoneModel" <> '' GROUP BY "MobilePhone", "MobilePhoneModel" ORDER BY u DESC LIMIT 10;
diff --git a/benchmarks/queries/clickbench/queries/q12.sql b/benchmarks/queries/clickbench/queries/q12.sql
@@ -1 +1,4 @@
+-- Must set for ClickBench hits_partitioned dataset. See https://github.com/apache/datafusion/issues/16591
+-- set datafusion.execution.parquet.binary_as_string = true
+
 SELECT "SearchPhrase", COUNT(*) AS c FROM hits WHERE "SearchPhrase" <> '' GROUP BY "SearchPhrase" ORDER BY c DESC LIMIT 10;
diff --git a/benchmarks/queries/clickbench/queries/q13.sql b/benchmarks/queries/clickbench/queries/q13.sql
@@ -1 +1,4 @@
+-- Must set for ClickBench hits_partitioned dataset. See https://github.com/apache/datafusion/issues/16591
+-- set datafusion.execution.parquet.binary_as_string = true
+
 SELECT "SearchPhrase", COUNT(DISTINCT "UserID") AS u FROM hits WHERE "SearchPhrase" <> '' GROUP BY "SearchPhrase" ORDER BY u DESC LIMIT 10;
diff --git a/benchmarks/queries/clickbench/queries/q14.sql b/benchmarks/queries/clickbench/queries/q14.sql
@@ -1 +1,4 @@
+-- Must set for ClickBench hits_partitioned dataset. See https://github.com/apache/datafusion/issues/16591
+-- set datafusion.execution.parquet.binary_as_string = true
+
 SELECT "SearchEngineID", "SearchPhrase", COUNT(*) AS c FROM hits WHERE "SearchPhrase" <> '' GROUP BY "SearchEngineID", "SearchPhrase" ORDER BY c DESC LIMIT 10;
diff --git a/benchmarks/queries/clickbench/queries/q15.sql b/benchmarks/queries/clickbench/queries/q15.sql
@@ -1 +1,4 @@
+-- Must set for ClickBench hits_partitioned dataset. See https://github.com/apache/datafusion/issues/16591
+-- set datafusion.execution.parquet.binary_as_string = true
+
 SELECT "UserID", COUNT(*) FROM hits GROUP BY "UserID" ORDER BY COUNT(*) DESC LIMIT 10;
diff --git a/benchmarks/queries/clickbench/queries/q16.sql b/benchmarks/queries/clickbench/queries/q16.sql
@@ -1 +1,4 @@
+-- Must set for ClickBench hits_partitioned dataset. See https://github.com/apache/datafusion/issues/16591
+-- set datafusion.execution.parquet.binary_as_string = true
+
 SELECT "UserID", "SearchPhrase", COUNT(*) FROM hits GROUP BY "UserID", "SearchPhrase" ORDER BY COUNT(*) DESC LIMIT 10;
diff --git a/benchmarks/queries/clickbench/queries/q17.sql b/benchmarks/queries/clickbench/queries/q17.sql
@@ -1 +1,4 @@
+-- Must set for ClickBench hits_partitioned dataset. See https://github.com/apache/datafusion/issues/16591
+-- set datafusion.execution.parquet.binary_as_string = true
+
 SELECT "UserID", "SearchPhrase", COUNT(*) FROM hits GROUP BY "UserID", "SearchPhrase" LIMIT 10;
diff --git a/benchmarks/queries/clickbench/queries/q18.sql b/benchmarks/queries/clickbench/queries/q18.sql
@@ -1 +1,4 @@
+-- Must set for ClickBench hits_partitioned dataset. See https://github.com/apache/datafusion/issues/16591
+-- set datafusion.execution.parquet.binary_as_string = true
+
 SELECT "UserID", extract(minute FROM to_timestamp_seconds("EventTime")) AS m, "SearchPhrase", COUNT(*) FROM hits GROUP BY "UserID", m, "SearchPhrase" ORDER BY COUNT(*) DESC LIMIT 10;
diff --git a/benchmarks/queries/clickbench/queries/q19.sql b/benchmarks/queries/clickbench/queries/q19.sql
@@ -1 +1,4 @@
+-- Must set for ClickBench hits_partitioned dataset. See https://github.com/apache/datafusion/issues/16591
+-- set datafusion.execution.parquet.binary_as_string = true
+
 SELECT "UserID" FROM hits WHERE "UserID" = 435090932899640449;
diff --git a/benchmarks/queries/clickbench/queries/q2.sql b/benchmarks/queries/clickbench/queries/q2.sql
@@ -1 +1,4 @@
+-- Must set for ClickBench hits_partitioned dataset. See https://github.com/apache/datafusion/issues/16591
+-- set datafusion.execution.parquet.binary_as_string = true
+
 SELECT SUM("AdvEngineID"), COUNT(*), AVG("ResolutionWidth") FROM hits;
diff --git a/benchmarks/queries/clickbench/queries/q20.sql b/benchmarks/queries/clickbench/queries/q20.sql
@@ -1 +1,4 @@
+-- Must set for ClickBench hits_partitioned dataset. See https://github.com/apache/datafusion/issues/16591
+-- set datafusion.execution.parquet.binary_as_string = true
+
 SELECT COUNT(*) FROM hits WHERE "URL" LIKE '%google%';
diff --git a/benchmarks/queries/clickbench/queries/q21.sql b/benchmarks/queries/clickbench/queries/q21.sql
@@ -1 +1,4 @@
+-- Must set for ClickBench hits_partitioned dataset. See https://github.com/apache/datafusion/issues/16591
+-- set datafusion.execution.parquet.binary_as_string = true
+
 SELECT "SearchPhrase", MIN("URL"), COUNT(*) AS c FROM hits WHERE "URL" LIKE '%google%' AND "SearchPhrase" <> '' GROUP BY "SearchPhrase" ORDER BY c DESC LIMIT 10;
diff --git a/benchmarks/queries/clickbench/queries/q22.sql b/benchmarks/queries/clickbench/queries/q22.sql
@@ -1 +1,4 @@
+-- Must set for ClickBench hits_partitioned dataset. See https://github.com/apache/datafusion/issues/16591
+-- set datafusion.execution.parquet.binary_as_string = true
+
 SELECT "SearchPhrase", MIN("URL"), MIN("Title"), COUNT(*) AS c, COUNT(DISTINCT "UserID") FROM hits WHERE "Title" LIKE '%Google%' AND "URL" NOT LIKE '%.google.%' AND "SearchPhrase" <> '' GROUP BY "SearchPhrase" ORDER BY c DESC LIMIT 10;
diff --git a/benchmarks/queries/clickbench/queries/q23.sql b/benchmarks/queries/clickbench/queries/q23.sql
@@ -1 +1,4 @@
+-- Must set for ClickBench hits_partitioned dataset. See https://github.com/apache/datafusion/issues/16591
+-- set datafusion.execution.parquet.binary_as_string = true
+
 SELECT * FROM hits WHERE "URL" LIKE '%google%' ORDER BY "EventTime" LIMIT 10;
diff --git a/benchmarks/queries/clickbench/queries/q24.sql b/benchmarks/queries/clickbench/queries/q24.sql
@@ -1 +1,4 @@
+-- Must set for ClickBench hits_partitioned dataset. See https://github.com/apache/datafusion/issues/16591
+-- set datafusion.execution.parquet.binary_as_string = true
+
 SELECT "SearchPhrase" FROM hits WHERE "SearchPhrase" <> '' ORDER BY "EventTime" LIMIT 10;
diff --git a/benchmarks/queries/clickbench/queries/q25.sql b/benchmarks/queries/clickbench/queries/q25.sql
@@ -1 +1,4 @@
+-- Must set for ClickBench hits_partitioned dataset. See https://github.com/apache/datafusion/issues/16591
+-- set datafusion.execution.parquet.binary_as_string = true
+
 SELECT "SearchPhrase" FROM hits WHERE "SearchPhrase" <> '' ORDER BY "SearchPhrase" LIMIT 10;
diff --git a/benchmarks/queries/clickbench/queries/q26.sql b/benchmarks/queries/clickbench/queries/q26.sql
@@ -1 +1,4 @@
+-- Must set for ClickBench hits_partitioned dataset. See https://github.com/apache/datafusion/issues/16591
+-- set datafusion.execution.parquet.binary_as_string = true
+
 SELECT "SearchPhrase" FROM hits WHERE "SearchPhrase" <> '' ORDER BY "EventTime", "SearchPhrase" LIMIT 10;
diff --git a/benchmarks/queries/clickbench/queries/q27.sql b/benchmarks/queries/clickbench/queries/q27.sql
@@ -1 +1,4 @@
+-- Must set for ClickBench hits_partitioned dataset. See https://github.com/apache/datafusion/issues/16591
+-- set datafusion.execution.parquet.binary_as_string = true
+
 SELECT "CounterID", AVG(length("URL")) AS l, COUNT(*) AS c FROM hits WHERE "URL" <> '' GROUP BY "CounterID" HAVING COUNT(*) > 100000 ORDER BY l DESC LIMIT 25;
diff --git a/benchmarks/queries/clickbench/queries/q28.sql b/benchmarks/queries/clickbench/queries/q28.sql
@@ -1 +1,4 @@
+-- Must set for ClickBench hits_partitioned dataset. See https://github.com/apache/datafusion/issues/16591
+-- set datafusion.execution.parquet.binary_as_string = true
+
 SELECT REGEXP_REPLACE("Referer", '^https?://(?:www\.)?([^/]+)/.*$', '\1') AS k, AVG(length("Referer")) AS l, COUNT(*) AS c, MIN("Referer") FROM hits WHERE "Referer" <> '' GROUP BY k HAVING COUNT(*) > 100000 ORDER BY l DESC LIMIT 25;
diff --git a/benchmarks/queries/clickbench/queries/q29.sql b/benchmarks/queries/clickbench/queries/q29.sql
@@ -1 +1,4 @@
+-- Must set for ClickBench hits_partitioned dataset. See https://github.com/apache/datafusion/issues/16591
+-- set datafusion.execution.parquet.binary_as_string = true
+
 SELECT SUM("ResolutionWidth"), SUM("ResolutionWidth" + 1), SUM("ResolutionWidth" + 2), SUM("ResolutionWidth" + 3), SUM("ResolutionWidth" + 4), SUM("ResolutionWidth" + 5), SUM("ResolutionWidth" + 6), SUM("ResolutionWidth" + 7), SUM("ResolutionWidth" + 8), SUM("ResolutionWidth" + 9), SUM("ResolutionWidth" + 10), SUM("ResolutionWidth" + 11), SUM("ResolutionWidth" + 12), SUM("ResolutionWidth" + 13), SUM("ResolutionWidth" + 14), SUM("ResolutionWidth" + 15), SUM("ResolutionWidth" + 16), SUM("ResolutionWidth" + 17), SUM("ResolutionWidth" + 18), SUM("ResolutionWidth" + 19), SUM("ResolutionWidth" + 20), SUM("ResolutionWidth" + 21), SUM("ResolutionWidth" + 22), SUM("ResolutionWidth" + 23), SUM("ResolutionWidth" + 24), SUM("ResolutionWidth" + 25), SUM("ResolutionWidth" + 26), SUM("ResolutionWidth" + 27), SUM("ResolutionWidth" + 28), SUM("ResolutionWidth" + 29), SUM("ResolutionWidth" + 30), SUM("ResolutionWidth" + 31), SUM("ResolutionWidth" + 32), SUM("ResolutionWidth" + 33), SUM("ResolutionWidth" + 34), SUM("ResolutionWidth" + 35), SUM("ResolutionWidth" + 36), SUM("ResolutionWidth" + 37), SUM("ResolutionWidth" + 38), SUM("ResolutionWidth" + 39), SUM("ResolutionWidth" + 40), SUM("ResolutionWidth" + 41), SUM("ResolutionWidth" + 42), SUM("ResolutionWidth" + 43), SUM("ResolutionWidth" + 44), SUM("ResolutionWidth" + 45), SUM("ResolutionWidth" + 46), SUM("ResolutionWidth" + 47), SUM("ResolutionWidth" + 48), SUM("ResolutionWidth" + 49), SUM("ResolutionWidth" + 50), SUM("ResolutionWidth" + 51), SUM("ResolutionWidth" + 52), SUM("ResolutionWidth" + 53), SUM("ResolutionWidth" + 54), SUM("ResolutionWidth" + 55), SUM("ResolutionWidth" + 56), SUM("ResolutionWidth" + 57), SUM("ResolutionWidth" + 58), SUM("ResolutionWidth" + 59), SUM("ResolutionWidth" + 60), SUM("ResolutionWidth" + 61), SUM("ResolutionWidth" + 62), SUM("ResolutionWidth" + 63), SUM("ResolutionWidth" + 64), SUM("ResolutionWidth" + 65), SUM("ResolutionWidth" + 66), SUM("ResolutionWidth" + 67), SUM("ResolutionWidth" + 68), SUM("ResolutionWidth" + 69), SUM("ResolutionWidth" + 70), SUM("ResolutionWidth" + 71), SUM("ResolutionWidth" + 72), SUM("ResolutionWidth" + 73), SUM("ResolutionWidth" + 74), SUM("ResolutionWidth" + 75), SUM("ResolutionWidth" + 76), SUM("ResolutionWidth" + 77), SUM("ResolutionWidth" + 78), SUM("ResolutionWidth" + 79), SUM("ResolutionWidth" + 80), SUM("ResolutionWidth" + 81), SUM("ResolutionWidth" + 82), SUM("ResolutionWidth" + 83), SUM("ResolutionWidth" + 84), SUM("ResolutionWidth" + 85), SUM("ResolutionWidth" + 86), SUM("ResolutionWidth" + 87), SUM("ResolutionWidth" + 88), SUM("ResolutionWidth" + 89) FROM hits;
diff --git a/benchmarks/queries/clickbench/queries/q3.sql b/benchmarks/queries/clickbench/queries/q3.sql
@@ -1 +1,4 @@
+-- Must set for ClickBench hits_partitioned dataset. See https://github.com/apache/datafusion/issues/16591
+-- set datafusion.execution.parquet.binary_as_string = true
+
 SELECT AVG("UserID") FROM hits;
diff --git a/benchmarks/queries/clickbench/queries/q30.sql b/benchmarks/queries/clickbench/queries/q30.sql
@@ -1 +1,4 @@
+-- Must set for ClickBench hits_partitioned dataset. See https://github.com/apache/datafusion/issues/16591
+-- set datafusion.execution.parquet.binary_as_string = true
+
 SELECT "SearchEngineID", "ClientIP", COUNT(*) AS c, SUM("IsRefresh"), AVG("ResolutionWidth") FROM hits WHERE "SearchPhrase" <> '' GROUP BY "SearchEngineID", "ClientIP" ORDER BY c DESC LIMIT 10;
diff --git a/benchmarks/queries/clickbench/queries/q31.sql b/benchmarks/queries/clickbench/queries/q31.sql
@@ -1 +1,4 @@
+-- Must set for ClickBench hits_partitioned dataset. See https://github.com/apache/datafusion/issues/16591
+-- set datafusion.execution.parquet.binary_as_string = true
+
 SELECT "WatchID", "ClientIP", COUNT(*) AS c, SUM("IsRefresh"), AVG("ResolutionWidth") FROM hits WHERE "SearchPhrase" <> '' GROUP BY "WatchID", "ClientIP" ORDER BY c DESC LIMIT 10;
diff --git a/benchmarks/queries/clickbench/queries/q32.sql b/benchmarks/queries/clickbench/queries/q32.sql
@@ -1 +1,4 @@
+-- Must set for ClickBench hits_partitioned dataset. See https://github.com/apache/datafusion/issues/16591
+-- set datafusion.execution.parquet.binary_as_string = true
+
 SELECT "WatchID", "ClientIP", COUNT(*) AS c, SUM("IsRefresh"), AVG("ResolutionWidth") FROM hits GROUP BY "WatchID", "ClientIP" ORDER BY c DESC LIMIT 10;
diff --git a/benchmarks/queries/clickbench/queries/q33.sql b/benchmarks/queries/clickbench/queries/q33.sql
@@ -1 +1,4 @@
+-- Must set for ClickBench hits_partitioned dataset. See https://github.com/apache/datafusion/issues/16591
+-- set datafusion.execution.parquet.binary_as_string = true
+
 SELECT "URL", COUNT(*) AS c FROM hits GROUP BY "URL" ORDER BY c DESC LIMIT 10;
diff --git a/benchmarks/queries/clickbench/queries/q34.sql b/benchmarks/queries/clickbench/queries/q34.sql
@@ -1 +1,4 @@
+-- Must set for ClickBench hits_partitioned dataset. See https://github.com/apache/datafusion/issues/16591
+-- set datafusion.execution.parquet.binary_as_string = true
+
 SELECT 1, "URL", COUNT(*) AS c FROM hits GROUP BY 1, "URL" ORDER BY c DESC LIMIT 10;
diff --git a/benchmarks/queries/clickbench/queries/q35.sql b/benchmarks/queries/clickbench/queries/q35.sql
@@ -1 +1,4 @@
+-- Must set for ClickBench hits_partitioned dataset. See https://github.com/apache/datafusion/issues/16591
+-- set datafusion.execution.parquet.binary_as_string = true
+
 SELECT "ClientIP", "ClientIP" - 1, "ClientIP" - 2, "ClientIP" - 3, COUNT(*) AS c FROM hits GROUP BY "ClientIP", "ClientIP" - 1, "ClientIP" - 2, "ClientIP" - 3 ORDER BY c DESC LIMIT 10;
diff --git a/benchmarks/queries/clickbench/queries/q36.sql b/benchmarks/queries/clickbench/queries/q36.sql
@@ -1 +1,4 @@
+-- Must set for ClickBench hits_partitioned dataset. See https://github.com/apache/datafusion/issues/16591
+-- set datafusion.execution.parquet.binary_as_string = true
+
 SELECT "URL", COUNT(*) AS PageViews FROM hits WHERE "CounterID" = 62 AND "EventDate" >= '2013-07-01' AND "EventDate" <= '2013-07-31' AND "DontCountHits" = 0 AND "IsRefresh" = 0 AND "URL" <> '' GROUP BY "URL" ORDER BY PageViews DESC LIMIT 10;
diff --git a/benchmarks/queries/clickbench/queries/q37.sql b/benchmarks/queries/clickbench/queries/q37.sql
@@ -1 +1,4 @@
+-- Must set for ClickBench hits_partitioned dataset. See https://github.com/apache/datafusion/issues/16591
+-- set datafusion.execution.parquet.binary_as_string = true
+
 SELECT "Title", COUNT(*) AS PageViews FROM hits WHERE "CounterID" = 62 AND "EventDate" >= '2013-07-01' AND "EventDate" <= '2013-07-31' AND "DontCountHits" = 0 AND "IsRefresh" = 0 AND "Title" <> '' GROUP BY "Title" ORDER BY PageViews DESC LIMIT 10;
diff --git a/benchmarks/queries/clickbench/queries/q38.sql b/benchmarks/queries/clickbench/queries/q38.sql
@@ -1 +1,4 @@
+-- Must set for ClickBench hits_partitioned dataset. See https://github.com/apache/datafusion/issues/16591
+-- set datafusion.execution.parquet.binary_as_string = true
+
 SELECT "URL", COUNT(*) AS PageViews FROM hits WHERE "CounterID" = 62 AND "EventDate" >= '2013-07-01' AND "EventDate" <= '2013-07-31' AND "IsRefresh" = 0 AND "IsLink" <> 0 AND "IsDownload" = 0 GROUP BY "URL" ORDER BY PageViews DESC LIMIT 10 OFFSET 1000;
diff --git a/benchmarks/queries/clickbench/queries/q39.sql b/benchmarks/queries/clickbench/queries/q39.sql
@@ -1 +1,4 @@
+-- Must set for ClickBench hits_partitioned dataset. See https://github.com/apache/datafusion/issues/16591
+-- set datafusion.execution.parquet.binary_as_string = true
+
 SELECT "TraficSourceID", "SearchEngineID", "AdvEngineID", CASE WHEN ("SearchEngineID" = 0 AND "AdvEngineID" = 0) THEN "Referer" ELSE '' END AS Src, "URL" AS Dst, COUNT(*) AS PageViews FROM hits WHERE "CounterID" = 62 AND "EventDate" >= '2013-07-01' AND "EventDate" <= '2013-07-31' AND "IsRefresh" = 0 GROUP BY "TraficSourceID", "SearchEngineID", "AdvEngineID", Src, Dst ORDER BY PageViews DESC LIMIT 10 OFFSET 1000;
diff --git a/benchmarks/queries/clickbench/queries/q4.sql b/benchmarks/queries/clickbench/queries/q4.sql
@@ -1 +1,4 @@
+-- Must set for ClickBench hits_partitioned dataset. See https://github.com/apache/datafusion/issues/16591
+-- set datafusion.execution.parquet.binary_as_string = true
+
 SELECT COUNT(DISTINCT "UserID") FROM hits;
diff --git a/benchmarks/queries/clickbench/queries/q40.sql b/benchmarks/queries/clickbench/queries/q40.sql
@@ -1 +1,4 @@
+-- Must set for ClickBench hits_partitioned dataset. See https://github.com/apache/datafusion/issues/16591
+-- set datafusion.execution.parquet.binary_as_string = true
+
 SELECT "URLHash", "EventDate", COUNT(*) AS PageViews FROM hits WHERE "CounterID" = 62 AND "EventDate" >= '2013-07-01' AND "EventDate" <= '2013-07-31' AND "IsRefresh" = 0 AND "TraficSourceID" IN (-1, 6) AND "RefererHash" = 3594120000172545465 GROUP BY "URLHash", "EventDate" ORDER BY PageViews DESC LIMIT 10 OFFSET 100;
diff --git a/benchmarks/queries/clickbench/queries/q41.sql b/benchmarks/queries/clickbench/queries/q41.sql
@@ -1 +1,3 @@
+-- Must set for ClickBench hits_partitioned dataset. See https://github.com/apache/datafusion/issues/16591
+-- set datafusion.execution.parquet.binary_as_string = true
 SELECT "WindowClientWidth", "WindowClientHeight", COUNT(*) AS PageViews FROM hits WHERE "CounterID" = 62 AND "EventDate" >= '2013-07-01' AND "EventDate" <= '2013-07-31' AND "IsRefresh" = 0 AND "DontCountHits" = 0 AND "URLHash" = 2868770270353813622 GROUP BY "WindowClientWidth", "WindowClientHeight" ORDER BY PageViews DESC LIMIT 10 OFFSET 10000;
diff --git a/benchmarks/queries/clickbench/queries/q42.sql b/benchmarks/queries/clickbench/queries/q42.sql
@@ -1 +1,4 @@
+-- Must set for ClickBench hits_partitioned dataset. See https://github.com/apache/datafusion/issues/16591
+-- set datafusion.execution.parquet.binary_as_string = true
+
 SELECT DATE_TRUNC('minute', to_timestamp_seconds("EventTime")) AS M, COUNT(*) AS PageViews FROM hits WHERE "CounterID" = 62 AND "EventDate" >= '2013-07-14' AND "EventDate" <= '2013-07-15' AND "IsRefresh" = 0 AND "DontCountHits" = 0 GROUP BY DATE_TRUNC('minute', to_timestamp_seconds("EventTime")) ORDER BY DATE_TRUNC('minute', M) LIMIT 10 OFFSET 1000;
diff --git a/benchmarks/queries/clickbench/queries/q5.sql b/benchmarks/queries/clickbench/queries/q5.sql
@@ -1 +1,4 @@
+-- Must set for ClickBench hits_partitioned dataset. See https://github.com/apache/datafusion/issues/16591
+-- set datafusion.execution.parquet.binary_as_string = true
+
 SELECT COUNT(DISTINCT "SearchPhrase") FROM hits;
diff --git a/benchmarks/queries/clickbench/queries/q6.sql b/benchmarks/queries/clickbench/queries/q6.sql
@@ -1 +1,4 @@
+-- Must set for ClickBench hits_partitioned dataset. See https://github.com/apache/datafusion/issues/16591
+-- set datafusion.execution.parquet.binary_as_string = true
+
 SELECT MIN("EventDate"), MAX("EventDate") FROM hits;
diff --git a/benchmarks/queries/clickbench/queries/q7.sql b/benchmarks/queries/clickbench/queries/q7.sql
@@ -1 +1,4 @@
+-- Must set for ClickBench hits_partitioned dataset. See https://github.com/apache/datafusion/issues/16591
+-- set datafusion.execution.parquet.binary_as_string = true
+
 SELECT "AdvEngineID", COUNT(*) FROM hits WHERE "AdvEngineID" <> 0 GROUP BY "AdvEngineID" ORDER BY COUNT(*) DESC;
diff --git a/benchmarks/queries/clickbench/queries/q8.sql b/benchmarks/queries/clickbench/queries/q8.sql
@@ -1 +1,4 @@
+-- Must set for ClickBench hits_partitioned dataset. See https://github.com/apache/datafusion/issues/16591
+-- set datafusion.execution.parquet.binary_as_string = true
+
 SELECT "RegionID", COUNT(DISTINCT "UserID") AS u FROM hits GROUP BY "RegionID" ORDER BY u DESC LIMIT 10;
diff --git a/benchmarks/queries/clickbench/queries/q9.sql b/benchmarks/queries/clickbench/queries/q9.sql
@@ -1 +1,4 @@
+-- Must set for ClickBench hits_partitioned dataset. See https://github.com/apache/datafusion/issues/16591
+-- set datafusion.execution.parquet.binary_as_string = true
+
 SELECT "RegionID", SUM("AdvEngineID"), COUNT(*) AS c, AVG("ResolutionWidth"), COUNT(DISTINCT "UserID") FROM hits GROUP BY "RegionID" ORDER BY c DESC LIMIT 10;
