From c459afbba406d895626c3feb23dfe4b815d5b56e Mon Sep 17 00:00:00 2001 From: Mihailo Milosevic Date: Wed, 26 Jun 2024 10:11:58 +0800 Subject: [PATCH] [SPARK-48573][SQL] Upgrade ICU version ### What changes were proposed in this pull request? Upgrade of ICU version from 72.1 -> 75.1 ### Why are the changes needed? We need to keep the version up-to-date. ### Does this PR introduce _any_ user-facing change? No. ### How was this patch tested? Existing tests were not broken. ### Was this patch authored or co-authored using generative AI tooling? No. Closes #47011 from mihailom-db/upgrade-icu. Authored-by: Mihailo Milosevic Signed-off-by: Kent Yao --- dev/deps/spark-deps-hadoop-3-hive-2.3 | 2 +- pom.xml | 2 +- .../CollationBenchmark-jdk21-results.txt | 48 +++--- .../benchmarks/CollationBenchmark-results.txt | 48 +++--- ...llationNonASCIIBenchmark-jdk21-results.txt | 48 +++--- .../CollationNonASCIIBenchmark-results.txt | 48 +++--- .../collations/ICU-collations-map.md | 141 +++++++++--------- 7 files changed, 169 insertions(+), 168 deletions(-) diff --git a/dev/deps/spark-deps-hadoop-3-hive-2.3 b/dev/deps/spark-deps-hadoop-3-hive-2.3 index b99ec346e6ab8..be8b21206c76c 100644 --- a/dev/deps/spark-deps-hadoop-3-hive-2.3 +++ b/dev/deps/spark-deps-hadoop-3-hive-2.3 @@ -98,7 +98,7 @@ hk2-locator/3.0.3//hk2-locator-3.0.3.jar hk2-utils/3.0.3//hk2-utils-3.0.3.jar httpclient/4.5.14//httpclient-4.5.14.jar httpcore/4.4.16//httpcore-4.4.16.jar -icu4j/72.1//icu4j-72.1.jar +icu4j/75.1//icu4j-75.1.jar ini4j/0.5.4//ini4j-0.5.4.jar istack-commons-runtime/3.0.8//istack-commons-runtime-3.0.8.jar ivy/2.5.2//ivy-2.5.2.jar diff --git a/pom.xml b/pom.xml index a6dc3a60d89c8..b2e7bba3ec752 100644 --- a/pom.xml +++ b/pom.xml @@ -216,7 +216,7 @@ 6.0.0 4.1.110.Final 2.0.65.Final - 72.1 + 75.1 5.9.3 1.9.3 0.11.1 diff --git a/sql/core/benchmarks/CollationBenchmark-jdk21-results.txt b/sql/core/benchmarks/CollationBenchmark-jdk21-results.txt index ba9be4ceaeea4..56b1523344a72 100644 --- a/sql/core/benchmarks/CollationBenchmark-jdk21-results.txt +++ b/sql/core/benchmarks/CollationBenchmark-jdk21-results.txt @@ -2,53 +2,53 @@ OpenJDK 64-Bit Server VM 21.0.3+9-LTS on Linux 6.5.0-1022-azure AMD EPYC 7763 64-Core Processor collation unit benchmarks - equalsFunction: Best Time(ms) Avg Time(ms) Stdev(ms) Rate(M/s) Per Row(ns) Relative -------------------------------------------------------------------------------------------------------------------------- -UTF8_BINARY 1355 1358 4 0.1 13551.1 1.0X -UTF8_LCASE 4983 4984 3 0.0 49826.4 0.3X -UNICODE 18212 18220 12 0.0 182120.9 0.1X -UNICODE_CI 17568 17577 14 0.0 175677.2 0.1X +UTF8_BINARY 1352 1352 1 0.1 13516.4 1.0X +UTF8_LCASE 4678 4693 21 0.0 46778.6 0.3X +UNICODE 17213 17223 13 0.0 172131.7 0.1X +UNICODE_CI 17101 17133 46 0.0 171009.6 0.1X OpenJDK 64-Bit Server VM 21.0.3+9-LTS on Linux 6.5.0-1022-azure AMD EPYC 7763 64-Core Processor collation unit benchmarks - compareFunction: Best Time(ms) Avg Time(ms) Stdev(ms) Rate(M/s) Per Row(ns) Relative --------------------------------------------------------------------------------------------------------------------------- -UTF8_BINARY 1772 1774 3 0.1 17722.3 1.0X -UTF8_LCASE 4365 4365 0 0.0 43649.6 0.4X -UNICODE 16538 16544 9 0.0 165375.5 0.1X -UNICODE_CI 16296 16305 12 0.0 162961.9 0.1X +UTF8_BINARY 1775 1775 0 0.1 17749.8 1.0X +UTF8_LCASE 5342 5367 35 0.0 53423.0 0.3X +UNICODE 17011 17020 12 0.0 170110.1 0.1X +UNICODE_CI 16734 16760 37 0.0 167338.2 0.1X OpenJDK 64-Bit Server VM 21.0.3+9-LTS on Linux 6.5.0-1022-azure AMD EPYC 7763 64-Core Processor collation unit benchmarks - hashFunction: Best Time(ms) Avg Time(ms) Stdev(ms) Rate(M/s) Per Row(ns) Relative ------------------------------------------------------------------------------------------------------------------------ -UTF8_BINARY 7279 7280 1 0.0 72791.2 1.0X -UTF8_LCASE 18538 18543 6 0.0 185381.0 0.4X -UNICODE 71514 71520 8 0.0 715144.6 0.1X -UNICODE_CI 60488 60488 0 0.0 604880.9 0.1X +UTF8_BINARY 7253 7256 4 0.0 72529.6 1.0X +UTF8_LCASE 16634 16676 59 0.0 166342.5 0.4X +UNICODE 66146 66163 23 0.0 661461.1 0.1X +UNICODE_CI 54563 54606 62 0.0 545625.5 0.1X OpenJDK 64-Bit Server VM 21.0.3+9-LTS on Linux 6.5.0-1022-azure AMD EPYC 7763 64-Core Processor collation unit benchmarks - contains: Best Time(ms) Avg Time(ms) Stdev(ms) Rate(M/s) Per Row(ns) Relative ------------------------------------------------------------------------------------------------------------------------ -UTF8_BINARY 7516 7519 4 0.0 75162.9 1.0X -UTF8_LCASE 120330 120338 12 0.0 1203299.2 0.1X -UNICODE 371784 371946 228 0.0 3717840.7 0.0X -UNICODE_CI 427401 427547 207 0.0 4274009.0 0.0X +UTF8_BINARY 6570 6577 10 0.0 65696.6 1.0X +UTF8_LCASE 120073 120137 91 0.0 1200726.4 0.1X +UNICODE 364027 364291 374 0.0 3640267.9 0.0X +UNICODE_CI 421444 422138 981 0.0 4214438.7 0.0X OpenJDK 64-Bit Server VM 21.0.3+9-LTS on Linux 6.5.0-1022-azure AMD EPYC 7763 64-Core Processor collation unit benchmarks - startsWith: Best Time(ms) Avg Time(ms) Stdev(ms) Rate(M/s) Per Row(ns) Relative ------------------------------------------------------------------------------------------------------------------------ -UTF8_BINARY 6504 6507 3 0.0 65044.6 1.0X -UTF8_LCASE 60331 60359 40 0.0 603313.9 0.1X -UNICODE 369394 369404 13 0.0 3693943.0 0.0X -UNICODE_CI 427382 427421 55 0.0 4273819.7 0.0X +UTF8_BINARY 6573 6596 32 0.0 65733.4 1.0X +UTF8_LCASE 60284 60293 12 0.0 602844.4 0.1X +UNICODE 363685 364220 757 0.0 3636848.4 0.0X +UNICODE_CI 422761 423000 337 0.0 4227611.0 0.0X OpenJDK 64-Bit Server VM 21.0.3+9-LTS on Linux 6.5.0-1022-azure AMD EPYC 7763 64-Core Processor collation unit benchmarks - endsWith: Best Time(ms) Avg Time(ms) Stdev(ms) Rate(M/s) Per Row(ns) Relative ------------------------------------------------------------------------------------------------------------------------ -UTF8_BINARY 6600 6601 1 0.0 66002.7 1.0X -UTF8_LCASE 58723 58751 39 0.0 587230.1 0.1X -UNICODE 379668 379789 172 0.0 3796677.7 0.0X -UNICODE_CI 437119 437194 106 0.0 4371189.5 0.0X +UTF8_BINARY 6507 6508 1 0.0 65068.3 1.0X +UTF8_LCASE 59098 59118 28 0.0 590983.6 0.1X +UNICODE 378437 378790 499 0.0 3784367.4 0.0X +UNICODE_CI 433987 434294 435 0.0 4339869.2 0.0X diff --git a/sql/core/benchmarks/CollationBenchmark-results.txt b/sql/core/benchmarks/CollationBenchmark-results.txt index bffa884468d45..09847bbcaa260 100644 --- a/sql/core/benchmarks/CollationBenchmark-results.txt +++ b/sql/core/benchmarks/CollationBenchmark-results.txt @@ -2,53 +2,53 @@ OpenJDK 64-Bit Server VM 17.0.11+9-LTS on Linux 6.5.0-1022-azure AMD EPYC 7763 64-Core Processor collation unit benchmarks - equalsFunction: Best Time(ms) Avg Time(ms) Stdev(ms) Rate(M/s) Per Row(ns) Relative -------------------------------------------------------------------------------------------------------------------------- -UTF8_BINARY 1370 1370 1 0.1 13698.4 1.0X -UTF8_LCASE 4836 4836 0 0.0 48359.5 0.3X -UNICODE 19239 19271 45 0.0 192391.8 0.1X -UNICODE_CI 18936 18954 25 0.0 189362.4 0.1X +UTF8_BINARY 1372 1374 3 0.1 13718.1 1.0X +UTF8_LCASE 6311 6311 0 0.0 63106.7 0.2X +UNICODE 19273 19300 37 0.0 192731.3 0.1X +UNICODE_CI 18991 18998 10 0.0 189906.3 0.1X OpenJDK 64-Bit Server VM 17.0.11+9-LTS on Linux 6.5.0-1022-azure AMD EPYC 7763 64-Core Processor collation unit benchmarks - compareFunction: Best Time(ms) Avg Time(ms) Stdev(ms) Rate(M/s) Per Row(ns) Relative --------------------------------------------------------------------------------------------------------------------------- -UTF8_BINARY 1726 1727 1 0.1 17260.4 1.0X -UTF8_LCASE 6293 6304 16 0.0 62927.1 0.3X -UNICODE 18677 18679 4 0.0 186768.3 0.1X -UNICODE_CI 18488 18504 23 0.0 184879.6 0.1X +UTF8_BINARY 1725 1726 2 0.1 17249.0 1.0X +UTF8_LCASE 5806 5828 31 0.0 58061.5 0.3X +UNICODE 19105 19111 8 0.0 191051.5 0.1X +UNICODE_CI 18991 18996 7 0.0 189913.3 0.1X OpenJDK 64-Bit Server VM 17.0.11+9-LTS on Linux 6.5.0-1022-azure AMD EPYC 7763 64-Core Processor collation unit benchmarks - hashFunction: Best Time(ms) Avg Time(ms) Stdev(ms) Rate(M/s) Per Row(ns) Relative ------------------------------------------------------------------------------------------------------------------------ -UTF8_BINARY 3028 3029 1 0.0 30283.4 1.0X -UTF8_LCASE 19773 19830 81 0.0 197726.4 0.2X -UNICODE 68565 68594 41 0.0 685646.9 0.0X -UNICODE_CI 53100 53101 2 0.0 530996.0 0.1X +UTF8_BINARY 3019 3021 3 0.0 30194.7 1.0X +UTF8_LCASE 19437 19439 3 0.0 194372.6 0.2X +UNICODE 63550 63568 25 0.0 635504.3 0.0X +UNICODE_CI 57839 57866 39 0.0 578385.0 0.1X OpenJDK 64-Bit Server VM 17.0.11+9-LTS on Linux 6.5.0-1022-azure AMD EPYC 7763 64-Core Processor collation unit benchmarks - contains: Best Time(ms) Avg Time(ms) Stdev(ms) Rate(M/s) Per Row(ns) Relative ------------------------------------------------------------------------------------------------------------------------ -UTF8_BINARY 7024 7026 3 0.0 70244.6 1.0X -UTF8_LCASE 118693 118703 15 0.0 1186926.5 0.1X -UNICODE 385409 386299 1257 0.0 3854093.7 0.0X -UNICODE_CI 434618 435527 1285 0.0 4346181.0 0.0X +UTF8_BINARY 7022 7023 2 0.0 70216.8 1.0X +UTF8_LCASE 118836 118887 72 0.0 1188364.9 0.1X +UNICODE 376381 376546 234 0.0 3763807.3 0.0X +UNICODE_CI 427858 427981 174 0.0 4278584.6 0.0X OpenJDK 64-Bit Server VM 17.0.11+9-LTS on Linux 6.5.0-1022-azure AMD EPYC 7763 64-Core Processor collation unit benchmarks - startsWith: Best Time(ms) Avg Time(ms) Stdev(ms) Rate(M/s) Per Row(ns) Relative ------------------------------------------------------------------------------------------------------------------------ -UTF8_BINARY 6069 6090 29 0.0 60691.9 1.0X -UTF8_LCASE 61809 61828 27 0.0 618094.5 0.1X -UNICODE 370523 371729 1705 0.0 3705229.7 0.0X -UNICODE_CI 435805 436945 1612 0.0 4358051.5 0.0X +UTF8_BINARY 6720 6723 5 0.0 67197.9 1.0X +UTF8_LCASE 67132 67177 63 0.0 671324.6 0.1X +UNICODE 368690 369292 852 0.0 3686899.6 0.0X +UNICODE_CI 431481 431583 144 0.0 4314814.9 0.0X OpenJDK 64-Bit Server VM 17.0.11+9-LTS on Linux 6.5.0-1022-azure AMD EPYC 7763 64-Core Processor collation unit benchmarks - endsWith: Best Time(ms) Avg Time(ms) Stdev(ms) Rate(M/s) Per Row(ns) Relative ------------------------------------------------------------------------------------------------------------------------ -UTF8_BINARY 6725 6732 10 0.0 67247.9 1.0X -UTF8_LCASE 54990 55010 28 0.0 549896.0 0.1X -UNICODE 380872 383258 3375 0.0 3808722.0 0.0X -UNICODE_CI 443911 444111 283 0.0 4439112.3 0.0X +UTF8_BINARY 7097 7099 3 0.0 70970.8 1.0X +UTF8_LCASE 57327 57351 35 0.0 573265.4 0.1X +UNICODE 375819 376473 924 0.0 3758191.8 0.0X +UNICODE_CI 445167 445212 64 0.0 4451666.7 0.0X diff --git a/sql/core/benchmarks/CollationNonASCIIBenchmark-jdk21-results.txt b/sql/core/benchmarks/CollationNonASCIIBenchmark-jdk21-results.txt index 7c83ae015a359..a7d2afb3fffc9 100644 --- a/sql/core/benchmarks/CollationNonASCIIBenchmark-jdk21-results.txt +++ b/sql/core/benchmarks/CollationNonASCIIBenchmark-jdk21-results.txt @@ -2,53 +2,53 @@ OpenJDK 64-Bit Server VM 21.0.3+9-LTS on Linux 6.5.0-1022-azure AMD EPYC 7763 64-Core Processor collation unit benchmarks - equalsFunction: Best Time(ms) Avg Time(ms) Stdev(ms) Rate(M/s) Per Row(ns) Relative -------------------------------------------------------------------------------------------------------------------------- -UTF8_BINARY 177 178 2 0.2 4421.6 1.0X -UTF8_LCASE 7165 7178 19 0.0 179129.7 0.0X -UNICODE 5601 5607 8 0.0 140030.5 0.0X -UNICODE_CI 5389 5402 19 0.0 134734.8 0.0X +UTF8_BINARY 171 171 1 0.2 4268.9 1.0X +UTF8_LCASE 6540 6549 12 0.0 163512.0 0.0X +UNICODE 5195 5196 2 0.0 129870.7 0.0X +UNICODE_CI 5129 5134 7 0.0 128222.9 0.0X OpenJDK 64-Bit Server VM 21.0.3+9-LTS on Linux 6.5.0-1022-azure AMD EPYC 7763 64-Core Processor collation unit benchmarks - compareFunction: Best Time(ms) Avg Time(ms) Stdev(ms) Rate(M/s) Per Row(ns) Relative --------------------------------------------------------------------------------------------------------------------------- -UTF8_BINARY 307 310 4 0.1 7684.9 1.0X -UTF8_LCASE 6668 6673 6 0.0 166712.0 0.0X -UNICODE 5135 5138 4 0.0 128375.9 0.1X -UNICODE_CI 5074 5079 7 0.0 126857.9 0.1X +UTF8_BINARY 316 316 1 0.1 7899.6 1.0X +UTF8_LCASE 6525 6528 3 0.0 163136.8 0.0X +UNICODE 5186 5201 21 0.0 129654.8 0.1X +UNICODE_CI 5119 5120 0 0.0 127985.4 0.1X OpenJDK 64-Bit Server VM 21.0.3+9-LTS on Linux 6.5.0-1022-azure AMD EPYC 7763 64-Core Processor collation unit benchmarks - hashFunction: Best Time(ms) Avg Time(ms) Stdev(ms) Rate(M/s) Per Row(ns) Relative ------------------------------------------------------------------------------------------------------------------------ -UTF8_BINARY 382 383 1 0.1 9546.3 1.0X -UTF8_LCASE 3302 3304 3 0.0 82540.3 0.1X -UNICODE 15198 15221 33 0.0 379949.7 0.0X -UNICODE_CI 11761 11763 3 0.0 294018.9 0.0X +UTF8_BINARY 384 386 2 0.1 9604.9 1.0X +UTF8_LCASE 3250 3255 7 0.0 81245.9 0.1X +UNICODE 14666 14668 3 0.0 366645.0 0.0X +UNICODE_CI 11055 11073 25 0.0 276376.4 0.0X OpenJDK 64-Bit Server VM 21.0.3+9-LTS on Linux 6.5.0-1022-azure AMD EPYC 7763 64-Core Processor collation unit benchmarks - contains: Best Time(ms) Avg Time(ms) Stdev(ms) Rate(M/s) Per Row(ns) Relative ------------------------------------------------------------------------------------------------------------------------ -UTF8_BINARY 1343 1344 1 0.0 33576.2 1.0X -UTF8_LCASE 34362 34362 1 0.0 859049.8 0.0X -UNICODE 70951 70968 24 0.0 1773767.5 0.0X -UNICODE_CI 80623 80806 258 0.0 2015572.4 0.0X +UTF8_BINARY 1439 1440 1 0.0 35973.9 1.0X +UTF8_LCASE 33643 33664 30 0.0 841072.8 0.0X +UNICODE 69901 69945 62 0.0 1747527.1 0.0X +UNICODE_CI 78298 78390 129 0.0 1957458.9 0.0X OpenJDK 64-Bit Server VM 21.0.3+9-LTS on Linux 6.5.0-1022-azure AMD EPYC 7763 64-Core Processor collation unit benchmarks - startsWith: Best Time(ms) Avg Time(ms) Stdev(ms) Rate(M/s) Per Row(ns) Relative ------------------------------------------------------------------------------------------------------------------------ -UTF8_BINARY 1054 1065 15 0.0 26353.2 1.0X -UTF8_LCASE 19162 19185 31 0.0 479061.4 0.1X -UNICODE 70920 70969 69 0.0 1773010.7 0.0X -UNICODE_CI 80608 80637 42 0.0 2015195.3 0.0X +UTF8_BINARY 1019 1020 1 0.0 25470.5 1.0X +UTF8_LCASE 18811 18833 32 0.0 470272.7 0.1X +UNICODE 67687 67758 101 0.0 1692181.1 0.0X +UNICODE_CI 77039 77148 154 0.0 1925975.7 0.0X OpenJDK 64-Bit Server VM 21.0.3+9-LTS on Linux 6.5.0-1022-azure AMD EPYC 7763 64-Core Processor collation unit benchmarks - endsWith: Best Time(ms) Avg Time(ms) Stdev(ms) Rate(M/s) Per Row(ns) Relative ------------------------------------------------------------------------------------------------------------------------ -UTF8_BINARY 1085 1085 1 0.0 27116.4 1.0X -UTF8_LCASE 18171 18194 32 0.0 454278.5 0.1X -UNICODE 76434 76440 8 0.0 1910849.8 0.0X -UNICODE_CI 85673 85704 44 0.0 2141822.3 0.0X +UTF8_BINARY 1020 1031 16 0.0 25493.0 1.0X +UTF8_LCASE 18574 18583 12 0.0 464350.7 0.1X +UNICODE 73937 74335 563 0.0 1848436.0 0.0X +UNICODE_CI 82022 82303 397 0.0 2050548.1 0.0X diff --git a/sql/core/benchmarks/CollationNonASCIIBenchmark-results.txt b/sql/core/benchmarks/CollationNonASCIIBenchmark-results.txt index 36c61b0107fa2..06d2e883cf788 100644 --- a/sql/core/benchmarks/CollationNonASCIIBenchmark-results.txt +++ b/sql/core/benchmarks/CollationNonASCIIBenchmark-results.txt @@ -2,53 +2,53 @@ OpenJDK 64-Bit Server VM 17.0.11+9-LTS on Linux 6.5.0-1022-azure AMD EPYC 7763 64-Core Processor collation unit benchmarks - equalsFunction: Best Time(ms) Avg Time(ms) Stdev(ms) Rate(M/s) Per Row(ns) Relative -------------------------------------------------------------------------------------------------------------------------- -UTF8_BINARY 133 133 1 0.3 3320.1 1.0X -UTF8_LCASE 7715 7735 28 0.0 192878.1 0.0X -UNICODE 5509 5517 11 0.0 137725.8 0.0X -UNICODE_CI 5585 5586 1 0.0 139631.8 0.0X +UTF8_BINARY 133 133 0 0.3 3318.0 1.0X +UTF8_LCASE 9483 9494 16 0.0 237079.3 0.0X +UNICODE 5963 5965 3 0.0 149081.4 0.0X +UNICODE_CI 5661 5663 3 0.0 141518.7 0.0X OpenJDK 64-Bit Server VM 17.0.11+9-LTS on Linux 6.5.0-1022-azure AMD EPYC 7763 64-Core Processor collation unit benchmarks - compareFunction: Best Time(ms) Avg Time(ms) Stdev(ms) Rate(M/s) Per Row(ns) Relative --------------------------------------------------------------------------------------------------------------------------- -UTF8_BINARY 446 448 3 0.1 11161.3 1.0X -UTF8_LCASE 7237 7250 17 0.0 180932.4 0.1X -UNICODE 5734 5734 1 0.0 143338.0 0.1X -UNICODE_CI 5699 5700 1 0.0 142483.5 0.1X +UTF8_BINARY 560 561 1 0.1 14008.3 1.0X +UTF8_LCASE 7535 7550 21 0.0 188384.6 0.1X +UNICODE 5868 5873 8 0.0 146691.2 0.1X +UNICODE_CI 5838 5839 1 0.0 145945.7 0.1X OpenJDK 64-Bit Server VM 17.0.11+9-LTS on Linux 6.5.0-1022-azure AMD EPYC 7763 64-Core Processor collation unit benchmarks - hashFunction: Best Time(ms) Avg Time(ms) Stdev(ms) Rate(M/s) Per Row(ns) Relative ------------------------------------------------------------------------------------------------------------------------ -UTF8_BINARY 413 413 0 0.1 10316.4 1.0X -UTF8_LCASE 3407 3407 0 0.0 85177.8 0.1X -UNICODE 15026 15046 28 0.0 375646.1 0.0X -UNICODE_CI 12181 12204 32 0.0 304526.9 0.0X +UTF8_BINARY 420 420 0 0.1 10489.3 1.0X +UTF8_LCASE 3524 3529 7 0.0 88101.6 0.1X +UNICODE 15630 15659 40 0.0 390755.8 0.0X +UNICODE_CI 12822 12838 22 0.0 320560.2 0.0X OpenJDK 64-Bit Server VM 17.0.11+9-LTS on Linux 6.5.0-1022-azure AMD EPYC 7763 64-Core Processor collation unit benchmarks - contains: Best Time(ms) Avg Time(ms) Stdev(ms) Rate(M/s) Per Row(ns) Relative ------------------------------------------------------------------------------------------------------------------------ -UTF8_BINARY 1217 1217 1 0.0 30413.5 1.0X -UTF8_LCASE 34426 34438 17 0.0 860656.8 0.0X -UNICODE 68095 68202 151 0.0 1702375.3 0.0X -UNICODE_CI 77954 78229 388 0.0 1948859.6 0.0X +UTF8_BINARY 1269 1270 2 0.0 31731.7 1.0X +UTF8_LCASE 34422 34448 37 0.0 860554.5 0.0X +UNICODE 66641 66780 196 0.0 1666024.0 0.0X +UNICODE_CI 76047 76084 52 0.0 1901185.9 0.0X OpenJDK 64-Bit Server VM 17.0.11+9-LTS on Linux 6.5.0-1022-azure AMD EPYC 7763 64-Core Processor collation unit benchmarks - startsWith: Best Time(ms) Avg Time(ms) Stdev(ms) Rate(M/s) Per Row(ns) Relative ------------------------------------------------------------------------------------------------------------------------ -UTF8_BINARY 960 961 2 0.0 23990.6 1.0X -UTF8_LCASE 18582 18599 24 0.0 464545.8 0.1X -UNICODE 68340 68426 121 0.0 1708511.0 0.0X -UNICODE_CI 79017 79051 48 0.0 1975424.4 0.0X +UTF8_BINARY 1114 1115 2 0.0 27839.1 1.0X +UTF8_LCASE 19656 19659 4 0.0 491401.9 0.1X +UNICODE 65990 66056 93 0.0 1649760.3 0.0X +UNICODE_CI 75764 75877 161 0.0 1894091.8 0.0X OpenJDK 64-Bit Server VM 17.0.11+9-LTS on Linux 6.5.0-1022-azure AMD EPYC 7763 64-Core Processor collation unit benchmarks - endsWith: Best Time(ms) Avg Time(ms) Stdev(ms) Rate(M/s) Per Row(ns) Relative ------------------------------------------------------------------------------------------------------------------------ -UTF8_BINARY 1083 1083 0 0.0 27073.4 1.0X -UTF8_LCASE 18868 18879 15 0.0 471690.7 0.1X -UNICODE 73435 73580 205 0.0 1835881.8 0.0X -UNICODE_CI 83324 83416 130 0.0 2083108.7 0.0X +UTF8_BINARY 1137 1137 0 0.0 28427.5 1.0X +UTF8_LCASE 18734 18765 44 0.0 468347.9 0.1X +UNICODE 74629 74646 24 0.0 1865724.7 0.0X +UNICODE_CI 83838 83888 70 0.0 2095948.2 0.0X diff --git a/sql/core/src/test/resources/collations/ICU-collations-map.md b/sql/core/src/test/resources/collations/ICU-collations-map.md index 598c3c4b40240..a704034c694aa 100644 --- a/sql/core/src/test/resources/collations/ICU-collations-map.md +++ b/sql/core/src/test/resources/collations/ICU-collations-map.md @@ -71,73 +71,74 @@ | 66 | ku | | 67 | ky | | 68 | lb | -| 69 | lkt | -| 70 | ln | -| 71 | lo | -| 72 | lt | -| 73 | lv | -| 74 | mk | -| 75 | ml | -| 76 | mn | -| 77 | mr | -| 78 | ms | -| 79 | mt | -| 80 | my | -| 81 | nb | -| 82 | nb_NOR | -| 83 | ne | -| 84 | nl | -| 85 | nn | -| 86 | no | -| 87 | om | -| 88 | or | -| 89 | pa | -| 90 | pa_Guru | -| 91 | pa_Guru_IND | -| 92 | pl | -| 93 | ps | -| 94 | pt | -| 95 | ro | -| 96 | ru | -| 97 | sa | -| 98 | se | -| 99 | si | -| 100 | sk | -| 101 | sl | -| 102 | smn | -| 103 | sq | -| 104 | sr | -| 105 | sr_Cyrl | -| 106 | sr_Cyrl_BIH | -| 107 | sr_Cyrl_MNE | -| 108 | sr_Cyrl_SRB | -| 109 | sr_Latn | -| 110 | sr_Latn_BIH | -| 111 | sr_Latn_SRB | -| 112 | sv | -| 113 | sw | -| 114 | ta | -| 115 | te | -| 116 | th | -| 117 | tk | -| 118 | to | -| 119 | tr | -| 120 | ug | -| 121 | uk | -| 122 | ur | -| 123 | uz | -| 124 | vi | -| 125 | wae | -| 126 | wo | -| 127 | xh | -| 128 | yi | -| 129 | yo | -| 130 | zh | -| 131 | zh_Hans | -| 132 | zh_Hans_CHN | -| 133 | zh_Hans_SGP | -| 134 | zh_Hant | -| 135 | zh_Hant_HKG | -| 136 | zh_Hant_MAC | -| 137 | zh_Hant_TWN | -| 138 | zu | +| 69 | lij | +| 70 | lkt | +| 71 | ln | +| 72 | lo | +| 73 | lt | +| 74 | lv | +| 75 | mk | +| 76 | ml | +| 77 | mn | +| 78 | mr | +| 79 | ms | +| 80 | mt | +| 81 | my | +| 82 | nb | +| 83 | nb_NOR | +| 84 | ne | +| 85 | nl | +| 86 | nn | +| 87 | no | +| 88 | om | +| 89 | or | +| 90 | pa | +| 91 | pa_Guru | +| 92 | pa_Guru_IND | +| 93 | pl | +| 94 | ps | +| 95 | pt | +| 96 | ro | +| 97 | ru | +| 98 | sa | +| 99 | se | +| 100 | si | +| 101 | sk | +| 102 | sl | +| 103 | smn | +| 104 | sq | +| 105 | sr | +| 106 | sr_Cyrl | +| 107 | sr_Cyrl_BIH | +| 108 | sr_Cyrl_MNE | +| 109 | sr_Cyrl_SRB | +| 110 | sr_Latn | +| 111 | sr_Latn_BIH | +| 112 | sr_Latn_SRB | +| 113 | sv | +| 114 | sw | +| 115 | ta | +| 116 | te | +| 117 | th | +| 118 | tk | +| 119 | to | +| 120 | tr | +| 121 | ug | +| 122 | uk | +| 123 | ur | +| 124 | uz | +| 125 | vi | +| 126 | wae | +| 127 | wo | +| 128 | xh | +| 129 | yi | +| 130 | yo | +| 131 | zh | +| 132 | zh_Hans | +| 133 | zh_Hans_CHN | +| 134 | zh_Hans_SGP | +| 135 | zh_Hant | +| 136 | zh_Hant_HKG | +| 137 | zh_Hant_MAC | +| 138 | zh_Hant_TWN | +| 139 | zu |