http://git-wip-us.apache.org/repos/asf/orc/blob/3283d238/java/core/src/test/resources/orc-file-dump-dictionary-threshold.out ---------------------------------------------------------------------- diff --git a/java/core/src/test/resources/orc-file-dump-dictionary-threshold.out b/java/core/src/test/resources/orc-file-dump-dictionary-threshold.out new file mode 100644 index 0000000..17a964b --- /dev/null +++ b/java/core/src/test/resources/orc-file-dump-dictionary-threshold.out @@ -0,0 +1,190 @@ +Structure for TestFileDump.testDump.orc +File Version: 0.12 with HIVE_13083 +Rows: 21000 +Compression: ZLIB +Compression size: 4096 +Type: struct<i:int,l:bigint,s:string> + +Stripe Statistics: + Stripe 1: + Column 0: count: 5000 hasNull: false + Column 1: count: 5000 hasNull: false min: -2147115959 max: 2145911404 sum: 159677169195 + Column 2: count: 5000 hasNull: false min: -9216505819108477308 max: 9217851628057711416 + Column 3: count: 5000 hasNull: false min: Darkness,-230 max: worst-54-290-346-648-908-996-1038-1080-1560-1584-1620-1744-1770-1798-1852-1966-2162-2244-2286-2296-2534-2660-3114-3676-3788-4068-4150-4706-4744 sum: 381254 + Stripe 2: + Column 0: count: 5000 hasNull: false + Column 1: count: 5000 hasNull: false min: -2147390285 max: 2147224606 sum: -14961457759 + Column 2: count: 5000 hasNull: false min: -9222178666167296739 max: 9221301751385928177 + Column 3: count: 5000 hasNull: false min: Darkness,-230-368-488-586-862-930-1686-2044-2636-2652-2872-3108-3162-3192-3404-3442-3508-3542-3550-3712-3980-4146-4204-4336-4390-4418-4424-4490-4512-4650-4768-4924-4950-5210 max: worst-54-290-346-648-908-996-1038-1080-1560-1584-1620-1744-1770-1798-1852-1966-2162-2244-2286-2296-2534-2660-3114-3676-3788-4068-4150-4706-4744-5350-5420-5582-5696-5726-6006-6020-6024-6098-6184-6568-6636-6802-6994-7004-7318-7498-7758-7780-7798-7920-7952-7960-7988-8232-8256-8390-8416-8478-8620-8840-8984-9038-9128-9236-9248-9344-9594-9650-9714-9928-9938 sum: 1117994 + Stripe 3: + Column 0: count: 5000 hasNull: false + Column 1: count: 5000 hasNull: false min: -2145842720 max: 2146718321 sum: 141092475520 + Column 2: count: 5000 hasNull: false min: -9221963099397084326 max: 9222722740629726770 + Column 3: count: 5000 hasNull: false min: Darkness,-230-368-488-586-862-930-1686-2044-2636-2652-2872-3108-3162-3192-3404-3442-3508-3542-3550-3712-3980-4146-4204-4336-4390-4418-4424-4490-4512-4650-4768-4924-4950-5210-5524-5630-5678-5710-5758-5952-6238-6252-6300-6366-6668-6712-6926-6942-7100-7194-7802-8030-8452-8608-8640-8862-8868-9134-9234-9412-9602-9608-9642-9678-9740-9780-10426 max: worst-54-290-346-648-908-996-1038-1080-1560-1584-1620-1744-1770-1798-1852-1966-2162-2244-2286-2296-2534-2660-3114-3676-3788-4068-4150-4706-4744-5350-5420-5582-5696-5726-6006-6020-6024-6098-6184-6568-6636-6802-6994-7004-7318-7498-7758-7780-7798-7920-7952-7960-7988-8232-8256-8390-8416-8478-8620-8840-8984-9038-9128-9236-9248-9344-9594-9650-9714-9928-9938-10178-10368-10414-10502-10732-10876-11008-11158-11410-11722-11836-11964-12054-12096-12126-12136-12202-12246-12298-12616-12774-12782-12790-12802-12976-13216-13246-13502-13766-14454-14974 sum: 1925226 + Stripe 4: + Column 0: count: 5000 hasNull: false + Column 1: count: 5000 hasNull: false min: -2145378214 max: 2147453086 sum: -153680004530 + Column 2: count: 5000 hasNull: false min: -9222731174895935707 max: 9222919052987871506 + Column 3: count: 5000 hasNull: false min: Darkness,-230-368-488-586-862-930-1686-2044-2636-2652-2872-3108-3162-3192-3404-3442-3508-3542-3550-3712-3980-4146-4204-4336-4390-4418-4424-4490-4512-4650-4768-4924-4950-5210-5524-5630-5678-5710-5758-5952-6238-6252-6300-6366-6668-6712-6926-6942-7100-7194-7802-8030-8452-8608-8640-8862-8868-9134-9234-9412-9602-9608-9642-9678-9740-9780-10426-10510-10514-10706-10814-10870-10942-11028-11244-11326-11462-11496-11656-11830-12022-12178-12418-12832-13304-13448-13590-13618-13908-14188-14246-14340-14364-14394-14762-14850-14964-15048 max: worst-54-290-346-648-908-996-1038-1080-1560-1584-1620-1744-1770-1798-1852-1966-2162-2244-2286-2296-2534-2660-3114-3676-3788-4068-4150-4706-4744-5350-5420-5582-5696-5726-6006-6020-6024-6098-6184-6568-6636-6802-6994-7004-7318-7498-7758-7780-7798-7920-7952-7960-7988-8232-8256-8390-8416-8478-8620-8840-8984-9038-9128-9236-9248-9344-9594-9650-9714-9928-9938-10178-10368-10414-10502-10732-10876-11008-11158-11410-11722-11836- 11964-12054-12096-12126-12136-12202-12246-12298-12616-12774-12782-12790-12802-12976-13216-13246-13502-13766-14454-14974-15004-15124-15252-15294-15356-15530-15610-16316-16936-17024-17122-17214-17310-17528-17682-17742-17870-17878-18010-18410-18524-18788-19204-19254-19518-19596-19786-19874-19904 sum: 2815002 + Stripe 5: + Column 0: count: 1000 hasNull: false + Column 1: count: 1000 hasNull: false min: -2143595397 max: 2136858458 sum: -22999664100 + Column 2: count: 1000 hasNull: false min: -9212379634781416464 max: 9197412874152820822 + Column 3: count: 1000 hasNull: false min: Darkness,-230-368-488-586-862-930-1686-2044-2636-2652-2872-3108-3162-3192-3404-3442-3508-3542-3550-3712-3980-4146-4204-4336-4390-4418-4424-4490-4512-4650-4768-4924-4950-5210-5524-5630-5678-5710-5758-5952-6238-6252-6300-6366-6668-6712-6926-6942-7100-7194-7802-8030-8452-8608-8640-8862-8868-9134-9234-9412-9602-9608-9642-9678-9740-9780-10426-10510-10514-10706-10814-10870-10942-11028-11244-11326-11462-11496-11656-11830-12022-12178-12418-12832-13304-13448-13590-13618-13908-14188-14246-14340-14364-14394-14762-14850-14964-15048-15494-15674-15726-16006-16056-16180-16304-16332-16452-16598-16730-16810-16994-17210-17268-17786-17962-18214-18444-18446-18724-18912-18952-19164-19348-19400-19546-19776-19896-20084 max: worst-54-290-346-648-908-996-1038-1080-1560-1584-1620-1744-1770-1798-1852-1966-2162-2244-2286-2296-2534-2660-3114-3676-3788-4068-4150-4706-4744-5350-5420-5582-5696-5726-6006-6020-6024-6098-6184-6568-6636-6802-6994-7004-7318-7498-7758-7780-7 798-7920-7952-7960-7988-8232-8256-8390-8416-8478-8620-8840-8984-9038-9128-9236-9248-9344-9594-9650-9714-9928-9938-10178-10368-10414-10502-10732-10876-11008-11158-11410-11722-11836-11964-12054-12096-12126-12136-12202-12246-12298-12616-12774-12782-12790-12802-12976-13216-13246-13502-13766-14454-14974-15004-15124-15252-15294-15356-15530-15610-16316-16936-17024-17122-17214-17310-17528-17682-17742-17870-17878-18010-18410-18524-18788-19204-19254-19518-19596-19786-19874-19904-20390-20752-20936 sum: 670762 + +File Statistics: + Column 0: count: 21000 hasNull: false + Column 1: count: 21000 hasNull: false min: -2147390285 max: 2147453086 sum: 109128518326 + Column 2: count: 21000 hasNull: false min: -9222731174895935707 max: 9222919052987871506 + Column 3: count: 21000 hasNull: false min: Darkness,-230 max: worst-54-290-346-648-908-996-1038-1080-1560-1584-1620-1744-1770-1798-1852-1966-2162-2244-2286-2296-2534-2660-3114-3676-3788-4068-4150-4706-4744-5350-5420-5582-5696-5726-6006-6020-6024-6098-6184-6568-6636-6802-6994-7004-7318-7498-7758-7780-7798-7920-7952-7960-7988-8232-8256-8390-8416-8478-8620-8840-8984-9038-9128-9236-9248-9344-9594-9650-9714-9928-9938-10178-10368-10414-10502-10732-10876-11008-11158-11410-11722-11836-11964-12054-12096-12126-12136-12202-12246-12298-12616-12774-12782-12790-12802-12976-13216-13246-13502-13766-14454-14974-15004-15124-15252-15294-15356-15530-15610-16316-16936-17024-17122-17214-17310-17528-17682-17742-17870-17878-18010-18410-18524-18788-19204-19254-19518-19596-19786-19874-19904-20390-20752-20936 sum: 6910238 + +Stripes: + Stripe: offset: 3 data: 163602 rows: 5000 tail: 68 index: 720 + Stream: column 0 section ROW_INDEX start: 3 length 17 + Stream: column 1 section ROW_INDEX start: 20 length 166 + Stream: column 2 section ROW_INDEX start: 186 length 171 + Stream: column 3 section ROW_INDEX start: 357 length 366 + Stream: column 1 section DATA start: 723 length 20035 + Stream: column 2 section DATA start: 20758 length 40050 + Stream: column 3 section DATA start: 60808 length 99226 + Stream: column 3 section LENGTH start: 160034 length 4291 + Encoding column 0: DIRECT + Encoding column 1: DIRECT_V2 + Encoding column 2: DIRECT_V2 + Encoding column 3: DIRECT_V2 + Row group indices for column 1: + Entry 0: count: 1000 hasNull: false min: -2132329551 max: 2145911404 sum: 61941331718 positions: 0,0,0 + Entry 1: count: 1000 hasNull: false min: -2138433136 max: 2145210552 sum: 14574030042 positions: 0,2050,488 + Entry 2: count: 1000 hasNull: false min: -2147115959 max: 2137805337 sum: -2032493169 positions: 4099,2054,464 + Entry 3: count: 1000 hasNull: false min: -2137828953 max: 2145877119 sum: -3167202608 positions: 8198,2058,440 + Entry 4: count: 1000 hasNull: false min: -2146452517 max: 2142394906 sum: 88361503212 positions: 12297,2062,416 + Row group indices for column 2: + Entry 0: count: 1000 hasNull: false min: -9206837518492372266 max: 9169230975203934579 positions: 0,0,0 + Entry 1: count: 1000 hasNull: false min: -9188878639954124284 max: 9213664245516510068 positions: 4099,2,488 + Entry 2: count: 1000 hasNull: false min: -9211329013123260308 max: 9217851628057711416 positions: 12297,6,464 + Entry 3: count: 1000 hasNull: false min: -9185745718227889962 max: 9181722705210917931 positions: 20495,10,440 + Entry 4: count: 1000 hasNull: false min: -9216505819108477308 max: 9196474183833079923 positions: 28693,14,416 + Row group indices for column 3: + Entry 0: count: 1000 hasNull: false min: Darkness,-230 max: worst-54-290-346-648-908-996 sum: 18442 positions: 0,0,0,0,0 + Entry 1: count: 1000 hasNull: false min: Darkness,-230-368-488-586-862-930-1686 max: worst-54-290-346-648-908-996-1038-1080-1560-1584-1620-1744-1770-1798-1852-1966 sum: 46338 positions: 4767,2058,0,695,18 + Entry 2: count: 1000 hasNull: false min: Darkness,-230-368-488-586-862-930-1686-2044 max: worst-54-290-346-648-908-996-1038-1080-1560-1584-1620-1744-1770-1798-1852-1966-2162-2244-2286-2296-2534-2660 sum: 75448 positions: 16464,3340,0,1554,14 + Entry 3: count: 1000 hasNull: false min: Darkness,-230-368-488-586-862-930-1686-2044-2636-2652-2872-3108 max: worst-54-290-346-648-908-996-1038-1080-1560-1584-1620-1744-1770-1798-1852-1966-2162-2244-2286-2296-2534-2660-3114-3676-3788 sum: 104868 positions: 36532,964,0,2372,90 + Entry 4: count: 1000 hasNull: false min: Darkness,-230-368-488-586-862-930-1686-2044-2636-2652-2872-3108-3162-3192-3404-3442-3508-3542-3550-3712-3980-4146 max: worst-54-290-346-648-908-996-1038-1080-1560-1584-1620-1744-1770-1798-1852-1966-2162-2244-2286-2296-2534-2660-3114-3676-3788-4068-4150-4706-4744 sum: 136158 positions: 63067,3432,0,3354,108 + Stripe: offset: 164393 data: 368335 rows: 5000 tail: 69 index: 956 + Stream: column 0 section ROW_INDEX start: 164393 length 17 + Stream: column 1 section ROW_INDEX start: 164410 length 157 + Stream: column 2 section ROW_INDEX start: 164567 length 166 + Stream: column 3 section ROW_INDEX start: 164733 length 616 + Stream: column 1 section DATA start: 165349 length 20035 + Stream: column 2 section DATA start: 185384 length 40050 + Stream: column 3 section DATA start: 225434 length 302715 + Stream: column 3 section LENGTH start: 528149 length 5535 + Encoding column 0: DIRECT + Encoding column 1: DIRECT_V2 + Encoding column 2: DIRECT_V2 + Encoding column 3: DIRECT_V2 + Row group indices for column 1: + Entry 0: count: 1000 hasNull: false min: -2146021688 max: 2146838901 sum: -50979197646 positions: 0,0,0 + Entry 1: count: 1000 hasNull: false min: -2143569489 max: 2141223179 sum: 22810066834 positions: 0,2050,488 + Entry 2: count: 1000 hasNull: false min: -2140649392 max: 2146301701 sum: -31694882346 positions: 4099,2054,464 + Entry 3: count: 1000 hasNull: false min: -2147390285 max: 2146299933 sum: 79371934221 positions: 8198,2058,440 + Entry 4: count: 1000 hasNull: false min: -2145928262 max: 2147224606 sum: -34469378822 positions: 12297,2062,416 + Row group indices for column 2: + Entry 0: count: 1000 hasNull: false min: -9222178666167296739 max: 9191250610515369723 positions: 0,0,0 + Entry 1: count: 1000 hasNull: false min: -9220148577547102875 max: 9213945522531717278 positions: 4099,2,488 + Entry 2: count: 1000 hasNull: false min: -9220818777591257749 max: 9221301751385928177 positions: 12297,6,464 + Entry 3: count: 1000 hasNull: false min: -9220031433030423388 max: 9207856144487414148 positions: 20495,10,440 + Entry 4: count: 1000 hasNull: false min: -9201438531577205959 max: 9212462124593119846 positions: 28693,14,416 + Row group indices for column 3: + Entry 0: count: 1000 hasNull: false min: Darkness,-230-368-488-586-862-930-1686-2044-2636-2652-2872-3108-3162-3192-3404-3442-3508-3542-3550-3712-3980-4146-4204-4336-4390-4418-4424-4490-4512-4650-4768-4924-4950-5210 max: worst-54-290-346-648-908-996-1038-1080-1560-1584-1620-1744-1770-1798-1852-1966-2162-2244-2286-2296-2534-2660-3114-3676-3788-4068-4150-4706-4744-5350-5420-5582-5696-5726 sum: 166320 positions: 0,0,0,0,0 + Entry 1: count: 1000 hasNull: false min: Darkness,-230-368-488-586-862-930-1686-2044-2636-2652-2872-3108-3162-3192-3404-3442-3508-3542-3550-3712-3980-4146-4204-4336-4390-4418-4424-4490-4512-4650-4768-4924-4950-5210-5524-5630-5678-5710-5758-5952-6238 max: worst-54-290-346-648-908-996-1038-1080-1560-1584-1620-1744-1770-1798-1852-1966-2162-2244-2286-2296-2534-2660-3114-3676-3788-4068-4150-4706-4744-5350-5420-5582-5696-5726-6006-6020-6024-6098-6184-6568-6636-6802-6994 sum: 193436 positions: 43833,2480,0,967,90 + Entry 2: count: 1000 hasNull: false min: Darkness,-230-368-488-586-862-930-1686-2044-2636-2652-2872-3108-3162-3192-3404-3442-3508-3542-3550-3712-3980-4146-4204-4336-4390-4418-4424-4490-4512-4650-4768-4924-4950-5210-5524-5630-5678-5710-5758-5952-6238-6252-6300-6366-6668-6712-6926-6942-7100 max: worst-54-290-346-648-908-996-1038-1080-1560-1584-1620-1744-1770-1798-1852-1966-2162-2244-2286-2296-2534-2660-3114-3676-3788-4068-4150-4706-4744-5350-5420-5582-5696-5726-6006-6020-6024-6098-6184-6568-6636-6802-6994-7004-7318-7498-7758-7780-7798-7920-7952-7960-7988 sum: 224740 positions: 94117,3404,0,1945,222 + Entry 3: count: 1000 hasNull: false min: Darkness,-230-368-488-586-862-930-1686-2044-2636-2652-2872-3108-3162-3192-3404-3442-3508-3542-3550-3712-3980-4146-4204-4336-4390-4418-4424-4490-4512-4650-4768-4924-4950-5210-5524-5630-5678-5710-5758-5952-6238-6252-6300-6366-6668-6712-6926-6942-7100-7194-7802-8030 max: worst-54-290-346-648-908-996-1038-1080-1560-1584-1620-1744-1770-1798-1852-1966-2162-2244-2286-2296-2534-2660-3114-3676-3788-4068-4150-4706-4744-5350-5420-5582-5696-5726-6006-6020-6024-6098-6184-6568-6636-6802-6994-7004-7318-7498-7758-7780-7798-7920-7952-7960-7988-8232-8256-8390-8416-8478-8620-8840-8984 sum: 252094 positions: 155111,2864,0,3268,48 + Entry 4: count: 1000 hasNull: false min: Darkness,-230-368-488-586-862-930-1686-2044-2636-2652-2872-3108-3162-3192-3404-3442-3508-3542-3550-3712-3980-4146-4204-4336-4390-4418-4424-4490-4512-4650-4768-4924-4950-5210-5524-5630-5678-5710-5758-5952-6238-6252-6300-6366-6668-6712-6926-6942-7100-7194-7802-8030-8452-8608-8640-8862-8868-9134 max: worst-54-290-346-648-908-996-1038-1080-1560-1584-1620-1744-1770-1798-1852-1966-2162-2244-2286-2296-2534-2660-3114-3676-3788-4068-4150-4706-4744-5350-5420-5582-5696-5726-6006-6020-6024-6098-6184-6568-6636-6802-6994-7004-7318-7498-7758-7780-7798-7920-7952-7960-7988-8232-8256-8390-8416-8478-8620-8840-8984-9038-9128-9236-9248-9344-9594-9650-9714-9928-9938 sum: 281404 positions: 224570,1006,0,4064,342 + Stripe: offset: 533753 data: 606074 rows: 5000 tail: 69 index: 1427 + Stream: column 0 section ROW_INDEX start: 533753 length 17 + Stream: column 1 section ROW_INDEX start: 533770 length 167 + Stream: column 2 section ROW_INDEX start: 533937 length 168 + Stream: column 3 section ROW_INDEX start: 534105 length 1075 + Stream: column 1 section DATA start: 535180 length 20035 + Stream: column 2 section DATA start: 555215 length 40050 + Stream: column 3 section DATA start: 595265 length 540210 + Stream: column 3 section LENGTH start: 1135475 length 5779 + Encoding column 0: DIRECT + Encoding column 1: DIRECT_V2 + Encoding column 2: DIRECT_V2 + Encoding column 3: DIRECT_V2 + Row group indices for column 1: + Entry 0: count: 1000 hasNull: false min: -2138229212 max: 2144818981 sum: -22823642812 positions: 0,0,0 + Entry 1: count: 1000 hasNull: false min: -2145842720 max: 2144179881 sum: -12562754334 positions: 0,2050,488 + Entry 2: count: 1000 hasNull: false min: -2143045885 max: 2146718321 sum: 82993638644 positions: 4099,2054,464 + Entry 3: count: 1000 hasNull: false min: -2144745617 max: 2146570474 sum: 25138722367 positions: 8198,2058,440 + Entry 4: count: 1000 hasNull: false min: -2140127150 max: 2135081620 sum: 68346511655 positions: 12297,2062,416 + Row group indices for column 2: + Entry 0: count: 1000 hasNull: false min: -9204340807292138409 max: 9208698732685326961 positions: 0,0,0 + Entry 1: count: 1000 hasNull: false min: -9221963099397084326 max: 9222722740629726770 positions: 4099,2,488 + Entry 2: count: 1000 hasNull: false min: -9210480084701091299 max: 9207767402467343058 positions: 12297,6,464 + Entry 3: count: 1000 hasNull: false min: -9195038026813631215 max: 9199201928563274421 positions: 20495,10,440 + Entry 4: count: 1000 hasNull: false min: -9215483580266514322 max: 9220102792864959501 positions: 28693,14,416 + Row group indices for column 3: + Entry 0: count: 1000 hasNull: false min: Darkness,-230-368-488-586-862-930-1686-2044-2636-2652-2872-3108-3162-3192-3404-3442-3508-3542-3550-3712-3980-4146-4204-4336-4390-4418-4424-4490-4512-4650-4768-4924-4950-5210-5524-5630-5678-5710-5758-5952-6238-6252-6300-6366-6668-6712-6926-6942-7100-7194-7802-8030-8452-8608-8640-8862-8868-9134-9234-9412-9602-9608-9642-9678-9740-9780-10426 max: worst-54-290-346-648-908-996-1038-1080-1560-1584-1620-1744-1770-1798-1852-1966-2162-2244-2286-2296-2534-2660-3114-3676-3788-4068-4150-4706-4744-5350-5420-5582-5696-5726-6006-6020-6024-6098-6184-6568-6636-6802-6994-7004-7318-7498-7758-7780-7798-7920-7952-7960-7988-8232-8256-8390-8416-8478-8620-8840-8984-9038-9128-9236-9248-9344-9594-9650-9714-9928-9938-10178-10368-10414-10502-10732-10876 sum: 313880 positions: 0,0,0,0,0 + Entry 1: count: 1000 hasNull: false min: Darkness,-230-368-488-586-862-930-1686-2044-2636-2652-2872-3108-3162-3192-3404-3442-3508-3542-3550-3712-3980-4146-4204-4336-4390-4418-4424-4490-4512-4650-4768-4924-4950-5210-5524-5630-5678-5710-5758-5952-6238-6252-6300-6366-6668-6712-6926-6942-7100-7194-7802-8030-8452-8608-8640-8862-8868-9134-9234-9412-9602-9608-9642-9678-9740-9780-10426-10510-10514-10706-10814-10870-10942-11028 max: worst-54-290-346-648-908-996-1038-1080-1560-1584-1620-1744-1770-1798-1852-1966-2162-2244-2286-2296-2534-2660-3114-3676-3788-4068-4150-4706-4744-5350-5420-5582-5696-5726-6006-6020-6024-6098-6184-6568-6636-6802-6994-7004-7318-7498-7758-7780-7798-7920-7952-7960-7988-8232-8256-8390-8416-8478-8620-8840-8984-9038-9128-9236-9248-9344-9594-9650-9714-9928-9938-10178-10368-10414-10502-10732-10876-11008-11158-11410-11722-11836-11964 sum: 349542 positions: 87800,2584,0,1097,28 + Entry 2: count: 1000 hasNull: false min: Darkness,-230-368-488-586-862-930-1686-2044-2636-2652-2872-3108-3162-3192-3404-3442-3508-3542-3550-3712-3980-4146-4204-4336-4390-4418-4424-4490-4512-4650-4768-4924-4950-5210-5524-5630-5678-5710-5758-5952-6238-6252-6300-6366-6668-6712-6926-6942-7100-7194-7802-8030-8452-8608-8640-8862-8868-9134-9234-9412-9602-9608-9642-9678-9740-9780-10426-10510-10514-10706-10814-10870-10942-11028-11244-11326-11462-11496-11656-11830-12022 max: worst-54-290-346-648-908-996-1038-1080-1560-1584-1620-1744-1770-1798-1852-1966-2162-2244-2286-2296-2534-2660-3114-3676-3788-4068-4150-4706-4744-5350-5420-5582-5696-5726-6006-6020-6024-6098-6184-6568-6636-6802-6994-7004-7318-7498-7758-7780-7798-7920-7952-7960-7988-8232-8256-8390-8416-8478-8620-8840-8984-9038-9128-9236-9248-9344-9594-9650-9714-9928-9938-10178-10368-10414-10502-10732-10876-11008-11158-11410-11722-11836-11964-12054-12096-12126-12136-12202-12246-12298-12616-12774-12782-12790-12802-12976 sum: 386538 posit ions: 185635,3966,0,2077,162 + Entry 3: count: 1000 hasNull: false min: Darkness,-230-368-488-586-862-930-1686-2044-2636-2652-2872-3108-3162-3192-3404-3442-3508-3542-3550-3712-3980-4146-4204-4336-4390-4418-4424-4490-4512-4650-4768-4924-4950-5210-5524-5630-5678-5710-5758-5952-6238-6252-6300-6366-6668-6712-6926-6942-7100-7194-7802-8030-8452-8608-8640-8862-8868-9134-9234-9412-9602-9608-9642-9678-9740-9780-10426-10510-10514-10706-10814-10870-10942-11028-11244-11326-11462-11496-11656-11830-12022-12178-12418-12832-13304 max: worst-54-290-346-648-908-996-1038-1080-1560-1584-1620-1744-1770-1798-1852-1966-2162-2244-2286-2296-2534-2660-3114-3676-3788-4068-4150-4706-4744-5350-5420-5582-5696-5726-6006-6020-6024-6098-6184-6568-6636-6802-6994-7004-7318-7498-7758-7780-7798-7920-7952-7960-7988-8232-8256-8390-8416-8478-8620-8840-8984-9038-9128-9236-9248-9344-9594-9650-9714-9928-9938-10178-10368-10414-10502-10732-10876-11008-11158-11410-11722-11836-11964-12054-12096-12126-12136-12202-12246-12298-12616-12774-12782-12790-12802 -12976-13216-13246-13502-13766 sum: 421660 positions: 295550,1384,0,3369,16 + Entry 4: count: 1000 hasNull: false min: Darkness,-230-368-488-586-862-930-1686-2044-2636-2652-2872-3108-3162-3192-3404-3442-3508-3542-3550-3712-3980-4146-4204-4336-4390-4418-4424-4490-4512-4650-4768-4924-4950-5210-5524-5630-5678-5710-5758-5952-6238-6252-6300-6366-6668-6712-6926-6942-7100-7194-7802-8030-8452-8608-8640-8862-8868-9134-9234-9412-9602-9608-9642-9678-9740-9780-10426-10510-10514-10706-10814-10870-10942-11028-11244-11326-11462-11496-11656-11830-12022-12178-12418-12832-13304-13448-13590-13618-13908-14188 max: worst-54-290-346-648-908-996-1038-1080-1560-1584-1620-1744-1770-1798-1852-1966-2162-2244-2286-2296-2534-2660-3114-3676-3788-4068-4150-4706-4744-5350-5420-5582-5696-5726-6006-6020-6024-6098-6184-6568-6636-6802-6994-7004-7318-7498-7758-7780-7798-7920-7952-7960-7988-8232-8256-8390-8416-8478-8620-8840-8984-9038-9128-9236-9248-9344-9594-9650-9714-9928-9938-10178-10368-10414-10502-10732-10876-11008-11158-11410-11722-11836-11964-12054-12096-12126-12136-12202-12246-12298 -12616-12774-12782-12790-12802-12976-13216-13246-13502-13766-14454-14974 sum: 453606 positions: 412768,1156,0,4041,470 + Stripe: offset: 1141323 data: 864001 rows: 5000 tail: 69 index: 1975 + Stream: column 0 section ROW_INDEX start: 1141323 length 17 + Stream: column 1 section ROW_INDEX start: 1141340 length 156 + Stream: column 2 section ROW_INDEX start: 1141496 length 168 + Stream: column 3 section ROW_INDEX start: 1141664 length 1634 + Stream: column 1 section DATA start: 1143298 length 20035 + Stream: column 2 section DATA start: 1163333 length 40050 + Stream: column 3 section DATA start: 1203383 length 798014 + Stream: column 3 section LENGTH start: 2001397 length 5902 + Encoding column 0: DIRECT + Encoding column 1: DIRECT_V2 + Encoding column 2: DIRECT_V2 + Encoding column 3: DIRECT_V2 + Row group indices for column 1: + Entry 0: count: 1000 hasNull: false min: -2145319330 max: 2146998132 sum: -50856753363 positions: 0,0,0 + Entry 1: count: 1000 hasNull: false min: -2134288866 max: 2147453086 sum: -17911019023 positions: 0,2050,488 + Entry 2: count: 1000 hasNull: false min: -2139010804 max: 2144727593 sum: -24993151857 positions: 4099,2054,464 + Entry 3: count: 1000 hasNull: false min: -2145378214 max: 2144098933 sum: -18055164052 positions: 8198,2058,440 + Entry 4: count: 1000 hasNull: false min: -2140494429 max: 2144595861 sum: -41863916235 positions: 12297,2062,416 + Row group indices for column 2: + Entry 0: count: 1000 hasNull: false min: -9172774601303513941 max: 9212917101275642143 positions: 0,0,0 + Entry 1: count: 1000 hasNull: false min: -9218164880949195469 max: 9222919052987871506 positions: 4099,2,488 + Entry 2: count: 1000 hasNull: false min: -9222731174895935707 max: 9214167447015056056 positions: 12297,6,464 + Entry 3: count: 1000 hasNull: false min: -9196276654247395117 max: 9210639275226058005 positions: 20495,10,440 + Entry 4: count: 1000 hasNull: false min: -9197393848859294562 max: 9208134757538374043 positions: 28693,14,416 + Row group indices for column 3: + Entry 0: count: 1000 hasNull: false min: Darkness,-230-368-488-586-862-930-1686-2044-2636-2652-2872-3108-3162-3192-3404-3442-3508-3542-3550-3712-3980-4146-4204-4336-4390-4418-4424-4490-4512-4650-4768-4924-4950-5210-5524-5630-5678-5710-5758-5952-6238-6252-6300-6366-6668-6712-6926-6942-7100-7194-7802-8030-8452-8608-8640-8862-8868-9134-9234-9412-9602-9608-9642-9678-9740-9780-10426-10510-10514-10706-10814-10870-10942-11028-11244-11326-11462-11496-11656-11830-12022-12178-12418-12832-13304-13448-13590-13618-13908-14188-14246-14340-14364-14394-14762-14850-14964-15048 max: worst-54-290-346-648-908-996-1038-1080-1560-1584-1620-1744-1770-1798-1852-1966-2162-2244-2286-2296-2534-2660-3114-3676-3788-4068-4150-4706-4744-5350-5420-5582-5696-5726-6006-6020-6024-6098-6184-6568-6636-6802-6994-7004-7318-7498-7758-7780-7798-7920-7952-7960-7988-8232-8256-8390-8416-8478-8620-8840-8984-9038-9128-9236-9248-9344-9594-9650-9714-9928-9938-10178-10368-10414-10502-10732-10876-11008-11158-11410-11722-11836 -11964-12054-12096-12126-12136-12202-12246-12298-12616-12774-12782-12790-12802-12976-13216-13246-13502-13766-14454-14974-15004-15124-15252-15294-15356-15530-15610 sum: 492916 positions: 0,0,0,0,0 + Entry 1: count: 1000 hasNull: false min: Darkness,-230-368-488-586-862-930-1686-2044-2636-2652-2872-3108-3162-3192-3404-3442-3508-3542-3550-3712-3980-4146-4204-4336-4390-4418-4424-4490-4512-4650-4768-4924-4950-5210-5524-5630-5678-5710-5758-5952-6238-6252-6300-6366-6668-6712-6926-6942-7100-7194-7802-8030-8452-8608-8640-8862-8868-9134-9234-9412-9602-9608-9642-9678-9740-9780-10426-10510-10514-10706-10814-10870-10942-11028-11244-11326-11462-11496-11656-11830-12022-12178-12418-12832-13304-13448-13590-13618-13908-14188-14246-14340-14364-14394-14762-14850-14964-15048-15494-15674-15726-16006 max: worst-54-290-346-648-908-996-1038-1080-1560-1584-1620-1744-1770-1798-1852-1966-2162-2244-2286-2296-2534-2660-3114-3676-3788-4068-4150-4706-4744-5350-5420-5582-5696-5726-6006-6020-6024-6098-6184-6568-6636-6802-6994-7004-7318-7498-7758-7780-7798-7920-7952-7960-7988-8232-8256-8390-8416-8478-8620-8840-8984-9038-9128-9236-9248-9344-9594-9650-9714-9928-9938-10178-10368-10414-10502-10732-10876-11008 -11158-11410-11722-11836-11964-12054-12096-12126-12136-12202-12246-12298-12616-12774-12782-12790-12802-12976-13216-13246-13502-13766-14454-14974-15004-15124-15252-15294-15356-15530-15610-16316-16936 sum: 527290 positions: 139298,1396,0,1077,140 + Entry 2: count: 1000 hasNull: false min: Darkness,-230-368-488-586-862-930-1686-2044-2636-2652-2872-3108-3162-3192-3404-3442-3508-3542-3550-3712-3980-4146-4204-4336-4390-4418-4424-4490-4512-4650-4768-4924-4950-5210-5524-5630-5678-5710-5758-5952-6238-6252-6300-6366-6668-6712-6926-6942-7100-7194-7802-8030-8452-8608-8640-8862-8868-9134-9234-9412-9602-9608-9642-9678-9740-9780-10426-10510-10514-10706-10814-10870-10942-11028-11244-11326-11462-11496-11656-11830-12022-12178-12418-12832-13304-13448-13590-13618-13908-14188-14246-14340-14364-14394-14762-14850-14964-15048-15494-15674-15726-16006-16056-16180-16304-16332-16452-16598-16730-16810-16994-17210 max: worst-54-290-346-648-908-996-1038-1080-1560-1584-1620-1744-1770-1798-1852-1966-2162-2244-2286-2296-2534-2660-3114-3676-3788-4068-4150-4706-4744-5350-5420-5582-5696-5726-6006-6020-6024-6098-6184-6568-6636-6802-6994-7004-7318-7498-7758-7780-7798-7920-7952-7960-7988-8232-8256-8390-8416-8478-8620-8840-8984-9038-9128-9236-9248-9344-9594-9 650-9714-9928-9938-10178-10368-10414-10502-10732-10876-11008-11158-11410-11722-11836-11964-12054-12096-12126-12136-12202-12246-12298-12616-12774-12782-12790-12802-12976-13216-13246-13502-13766-14454-14974-15004-15124-15252-15294-15356-15530-15610-16316-16936-17024-17122-17214-17310-17528-17682-17742-17870-17878 sum: 568274 positions: 286457,302,0,1926,462 + Entry 3: count: 1000 hasNull: false min: Darkness,-230-368-488-586-862-930-1686-2044-2636-2652-2872-3108-3162-3192-3404-3442-3508-3542-3550-3712-3980-4146-4204-4336-4390-4418-4424-4490-4512-4650-4768-4924-4950-5210-5524-5630-5678-5710-5758-5952-6238-6252-6300-6366-6668-6712-6926-6942-7100-7194-7802-8030-8452-8608-8640-8862-8868-9134-9234-9412-9602-9608-9642-9678-9740-9780-10426-10510-10514-10706-10814-10870-10942-11028-11244-11326-11462-11496-11656-11830-12022-12178-12418-12832-13304-13448-13590-13618-13908-14188-14246-14340-14364-14394-14762-14850-14964-15048-15494-15674-15726-16006-16056-16180-16304-16332-16452-16598-16730-16810-16994-17210-17268-17786-17962-18214 max: worst-54-290-346-648-908-996-1038-1080-1560-1584-1620-1744-1770-1798-1852-1966-2162-2244-2286-2296-2534-2660-3114-3676-3788-4068-4150-4706-4744-5350-5420-5582-5696-5726-6006-6020-6024-6098-6184-6568-6636-6802-6994-7004-7318-7498-7758-7780-7798-7920-7952-7960-7988-8232-8256-8390-8416-8478-8620-8840-8984-9038-91 28-9236-9248-9344-9594-9650-9714-9928-9938-10178-10368-10414-10502-10732-10876-11008-11158-11410-11722-11836-11964-12054-12096-12126-12136-12202-12246-12298-12616-12774-12782-12790-12802-12976-13216-13246-13502-13766-14454-14974-15004-15124-15252-15294-15356-15530-15610-16316-16936-17024-17122-17214-17310-17528-17682-17742-17870-17878-18010-18410-18524-18788 sum: 594578 positions: 447943,3328,0,3444,250 + Entry 4: count: 1000 hasNull: false min: Darkness,-230-368-488-586-862-930-1686-2044-2636-2652-2872-3108-3162-3192-3404-3442-3508-3542-3550-3712-3980-4146-4204-4336-4390-4418-4424-4490-4512-4650-4768-4924-4950-5210-5524-5630-5678-5710-5758-5952-6238-6252-6300-6366-6668-6712-6926-6942-7100-7194-7802-8030-8452-8608-8640-8862-8868-9134-9234-9412-9602-9608-9642-9678-9740-9780-10426-10510-10514-10706-10814-10870-10942-11028-11244-11326-11462-11496-11656-11830-12022-12178-12418-12832-13304-13448-13590-13618-13908-14188-14246-14340-14364-14394-14762-14850-14964-15048-15494-15674-15726-16006-16056-16180-16304-16332-16452-16598-16730-16810-16994-17210-17268-17786-17962-18214-18444-18446-18724-18912-18952-19164 max: worst-54-290-346-648-908-996-1038-1080-1560-1584-1620-1744-1770-1798-1852-1966-2162-2244-2286-2296-2534-2660-3114-3676-3788-4068-4150-4706-4744-5350-5420-5582-5696-5726-6006-6020-6024-6098-6184-6568-6636-6802-6994-7004-7318-7498-7758-7780-7798-7920-7952-7960-7988-8232-8256-8 390-8416-8478-8620-8840-8984-9038-9128-9236-9248-9344-9594-9650-9714-9928-9938-10178-10368-10414-10502-10732-10876-11008-11158-11410-11722-11836-11964-12054-12096-12126-12136-12202-12246-12298-12616-12774-12782-12790-12802-12976-13216-13246-13502-13766-14454-14974-15004-15124-15252-15294-15356-15530-15610-16316-16936-17024-17122-17214-17310-17528-17682-17742-17870-17878-18010-18410-18524-18788-19204-19254-19518-19596-19786-19874-19904 sum: 631944 positions: 616471,3986,3778,547,292 + Stripe: offset: 2007368 data: 207295 rows: 1000 tail: 67 index: 841 + Stream: column 0 section ROW_INDEX start: 2007368 length 12 + Stream: column 1 section ROW_INDEX start: 2007380 length 38 + Stream: column 2 section ROW_INDEX start: 2007418 length 41 + Stream: column 3 section ROW_INDEX start: 2007459 length 750 + Stream: column 1 section DATA start: 2008209 length 4007 + Stream: column 2 section DATA start: 2012216 length 8010 + Stream: column 3 section DATA start: 2020226 length 194018 + Stream: column 3 section LENGTH start: 2214244 length 1260 + Encoding column 0: DIRECT + Encoding column 1: DIRECT_V2 + Encoding column 2: DIRECT_V2 + Encoding column 3: DIRECT_V2 + Row group indices for column 1: + Entry 0: count: 1000 hasNull: false min: -2143595397 max: 2136858458 sum: -22999664100 positions: 0,0,0 + Row group indices for column 2: + Entry 0: count: 1000 hasNull: false min: -9212379634781416464 max: 9197412874152820822 positions: 0,0,0 + Row group indices for column 3: + Entry 0: count: 1000 hasNull: false min: Darkness,-230-368-488-586-862-930-1686-2044-2636-2652-2872-3108-3162-3192-3404-3442-3508-3542-3550-3712-3980-4146-4204-4336-4390-4418-4424-4490-4512-4650-4768-4924-4950-5210-5524-5630-5678-5710-5758-5952-6238-6252-6300-6366-6668-6712-6926-6942-7100-7194-7802-8030-8452-8608-8640-8862-8868-9134-9234-9412-9602-9608-9642-9678-9740-9780-10426-10510-10514-10706-10814-10870-10942-11028-11244-11326-11462-11496-11656-11830-12022-12178-12418-12832-13304-13448-13590-13618-13908-14188-14246-14340-14364-14394-14762-14850-14964-15048-15494-15674-15726-16006-16056-16180-16304-16332-16452-16598-16730-16810-16994-17210-17268-17786-17962-18214-18444-18446-18724-18912-18952-19164-19348-19400-19546-19776-19896-20084 max: worst-54-290-346-648-908-996-1038-1080-1560-1584-1620-1744-1770-1798-1852-1966-2162-2244-2286-2296-2534-2660-3114-3676-3788-4068-4150-4706-4744-5350-5420-5582-5696-5726-6006-6020-6024-6098-6184-6568-6636-6802-6994-7004-7318-7498-7758-7780- 7798-7920-7952-7960-7988-8232-8256-8390-8416-8478-8620-8840-8984-9038-9128-9236-9248-9344-9594-9650-9714-9928-9938-10178-10368-10414-10502-10732-10876-11008-11158-11410-11722-11836-11964-12054-12096-12126-12136-12202-12246-12298-12616-12774-12782-12790-12802-12976-13216-13246-13502-13766-14454-14974-15004-15124-15252-15294-15356-15530-15610-16316-16936-17024-17122-17214-17310-17528-17682-17742-17870-17878-18010-18410-18524-18788-19204-19254-19518-19596-19786-19874-19904-20390-20752-20936 sum: 670762 positions: 0,0,0,0,0 + +File length: 2217685 bytes +Padding length: 0 bytes +Padding ratio: 0% +________________________________________________________________________________________________________________________ +
http://git-wip-us.apache.org/repos/asf/orc/blob/3283d238/java/core/src/test/resources/orc-file-dump.json ---------------------------------------------------------------------- diff --git a/java/core/src/test/resources/orc-file-dump.json b/java/core/src/test/resources/orc-file-dump.json new file mode 100644 index 0000000..bf654a1 --- /dev/null +++ b/java/core/src/test/resources/orc-file-dump.json @@ -0,0 +1,1355 @@ +{ + "fileName": "TestFileDump.testDump.orc", + "fileVersion": "0.12", + "writerVersion": "HIVE_13083", + "numberOfRows": 21000, + "compression": "ZLIB", + "compressionBufferSize": 4096, + "schemaString": "struct<i:int,l:bigint,s:string>", + "schema": [ + { + "columnId": 0, + "columnType": "STRUCT", + "childColumnNames": [ + "i", + "l", + "s" + ], + "childColumnIds": [ + 1, + 2, + 3 + ] + }, + { + "columnId": 1, + "columnType": "INT" + }, + { + "columnId": 2, + "columnType": "LONG" + }, + { + "columnId": 3, + "columnType": "STRING" + } + ], + "stripeStatistics": [ + { + "stripeNumber": 1, + "columnStatistics": [ + { + "columnId": 0, + "count": 5000, + "hasNull": false + }, + { + "columnId": 1, + "count": 5000, + "hasNull": false, + "min": -2147115959, + "max": 2145210552, + "sum": 50111854553, + "type": "LONG" + }, + { + "columnId": 2, + "count": 5000, + "hasNull": false, + "min": -9223180583305557329, + "max": 9221614132680747961, + "type": "LONG" + }, + { + "columnId": 3, + "count": 4950, + "hasNull": true, + "min": "Darkness,", + "max": "worst", + "totalLength": 19283, + "type": "STRING" + } + ] + }, + { + "stripeNumber": 2, + "columnStatistics": [ + { + "columnId": 0, + "count": 5000, + "hasNull": false + }, + { + "columnId": 1, + "count": 5000, + "hasNull": false, + "min": -2147390285, + "max": 2147224606, + "sum": -22290798217, + "type": "LONG" + }, + { + "columnId": 2, + "count": 5000, + "hasNull": false, + "min": -9219295160509160427, + "max": 9217571024994660020, + "type": "LONG" + }, + { + "columnId": 3, + "count": 4950, + "hasNull": true, + "min": "Darkness,", + "max": "worst", + "totalLength": 19397, + "type": "STRING" + } + ] + }, + { + "stripeNumber": 3, + "columnStatistics": [ + { + "columnId": 0, + "count": 5000, + "hasNull": false + }, + { + "columnId": 1, + "count": 5000, + "hasNull": false, + "min": -2146954065, + "max": 2146722468, + "sum": 20639652136, + "type": "LONG" + }, + { + "columnId": 2, + "count": 5000, + "hasNull": false, + "min": -9214076359988107846, + "max": 9222919052987871506, + "type": "LONG" + }, + { + "columnId": 3, + "count": 4950, + "hasNull": true, + "min": "Darkness,", + "max": "worst", + "totalLength": 19031, + "type": "STRING" + } + ] + }, + { + "stripeNumber": 4, + "columnStatistics": [ + { + "columnId": 0, + "count": 5000, + "hasNull": false + }, + { + "columnId": 1, + "count": 5000, + "hasNull": false, + "min": -2146969085, + "max": 2146025044, + "sum": -5156814387, + "type": "LONG" + }, + { + "columnId": 2, + "count": 5000, + "hasNull": false, + "min": -9222731174895935707, + "max": 9220625004936875965, + "type": "LONG" + }, + { + "columnId": 3, + "count": 4950, + "hasNull": true, + "min": "Darkness,", + "max": "worst", + "totalLength": 19459, + "type": "STRING" + } + ] + }, + { + "stripeNumber": 5, + "columnStatistics": [ + { + "columnId": 0, + "count": 1000, + "hasNull": false + }, + { + "columnId": 1, + "count": 1000, + "hasNull": false, + "min": -2144303438, + "max": 2127599049, + "sum": 62841564778, + "type": "LONG" + }, + { + "columnId": 2, + "count": 1000, + "hasNull": false, + "min": -9195133638801798919, + "max": 9218626063131504414, + "type": "LONG" + }, + { + "columnId": 3, + "count": 990, + "hasNull": true, + "min": "Darkness,", + "max": "worst", + "totalLength": 3963, + "type": "STRING" + } + ] + } + ], + "fileStatistics": [ + { + "columnId": 0, + "count": 21000, + "hasNull": false + }, + { + "columnId": 1, + "count": 21000, + "hasNull": false, + "min": -2147390285, + "max": 2147224606, + "sum": 106145458863, + "type": "LONG" + }, + { + "columnId": 2, + "count": 21000, + "hasNull": false, + "min": -9223180583305557329, + "max": 9222919052987871506, + "type": "LONG" + }, + { + "columnId": 3, + "count": 20790, + "hasNull": true, + "min": "Darkness,", + "max": "worst", + "totalLength": 81133, + "type": "STRING" + } + ], + "stripes": [ + { + "stripeNumber": 1, + "stripeInformation": { + "offset": 3, + "indexLength": 970, + "dataLength": 63770, + "footerLength": 90, + "rowCount": 5000 + }, + "streams": [ + { + "columnId": 0, + "section": "ROW_INDEX", + "startOffset": 3, + "length": 17 + }, + { + "columnId": 1, + "section": "ROW_INDEX", + "startOffset": 20, + "length": 167 + }, + { + "columnId": 2, + "section": "ROW_INDEX", + "startOffset": 187, + "length": 171 + }, + { + "columnId": 3, + "section": "ROW_INDEX", + "startOffset": 358, + "length": 103 + }, + { + "columnId": 3, + "section": "BLOOM_FILTER", + "startOffset": 461, + "length": 512 + }, + { + "columnId": 1, + "section": "DATA", + "startOffset": 973, + "length": 20035 + }, + { + "columnId": 2, + "section": "DATA", + "startOffset": 21008, + "length": 40050 + }, + { + "columnId": 3, + "section": "PRESENT", + "startOffset": 61058, + "length": 17 + }, + { + "columnId": 3, + "section": "DATA", + "startOffset": 61075, + "length": 3510 + }, + { + "columnId": 3, + "section": "LENGTH", + "startOffset": 64585, + "length": 25 + }, + { + "columnId": 3, + "section": "DICTIONARY_DATA", + "startOffset": 64610, + "length": 133 + } + ], + "encodings": [ + { + "columnId": 0, + "kind": "DIRECT" + }, + { + "columnId": 1, + "kind": "DIRECT_V2" + }, + { + "columnId": 2, + "kind": "DIRECT_V2" + }, + { + "columnId": 3, + "kind": "DICTIONARY_V2", + "dictionarySize": 35 + } + ], + "indexes": [{ + "columnId": 3, + "rowGroupIndexes": [ + { + "entryId": 0, + "count": 990, + "hasNull": true, + "min": "Darkness,", + "max": "worst", + "totalLength": 3873, + "type": "STRING", + "positions": [ + 0, + 0, + 0, + 0, + 0, + 0, + 0 + ] + }, + { + "entryId": 1, + "count": 990, + "hasNull": true, + "min": "Darkness,", + "max": "worst", + "totalLength": 3861, + "type": "STRING", + "positions": [ + 0, + 38, + 12, + 0, + 0, + 736, + 23 + ] + }, + { + "entryId": 2, + "count": 990, + "hasNull": true, + "min": "Darkness,", + "max": "worst", + "totalLength": 3946, + "type": "STRING", + "positions": [ + 0, + 78, + 12, + 0, + 0, + 1473, + 43 + ] + }, + { + "entryId": 3, + "count": 990, + "hasNull": true, + "min": "Darkness,", + "max": "worst", + "totalLength": 3774, + "type": "STRING", + "positions": [ + 0, + 118, + 12, + 0, + 0, + 2067, + 261 + ] + }, + { + "entryId": 4, + "count": 990, + "hasNull": true, + "min": "Darkness,", + "max": "worst", + "totalLength": 3829, + "type": "STRING", + "positions": [ + 0, + 158, + 12, + 0, + 0, + 2992, + 35 + ] + } + ], + "bloomFilterIndexes": [ + { + "entryId": 0, + "numHashFunctions": 4, + "bitCount": 6272, + "popCount": 138, + "loadFactor": 0.022002551704645157, + "expectedFpp": 2.3436470542037569E-7 + }, + { + "entryId": 1, + "numHashFunctions": 4, + "bitCount": 6272, + "popCount": 138, + "loadFactor": 0.022002551704645157, + "expectedFpp": 2.3436470542037569E-7 + }, + { + "entryId": 2, + "numHashFunctions": 4, + "bitCount": 6272, + "popCount": 138, + "loadFactor": 0.022002551704645157, + "expectedFpp": 2.3436470542037569E-7 + }, + { + "entryId": 3, + "numHashFunctions": 4, + "bitCount": 6272, + "popCount": 138, + "loadFactor": 0.022002551704645157, + "expectedFpp": 2.3436470542037569E-7 + }, + { + "entryId": 4, + "numHashFunctions": 4, + "bitCount": 6272, + "popCount": 138, + "loadFactor": 0.022002551704645157, + "expectedFpp": 2.3436470542037569E-7 + } + ], + "stripeLevelBloomFilter": { + "numHashFunctions": 4, + "bitCount": 6272, + "popCount": 138, + "loadFactor": 0.022002551704645157, + "expectedFpp": 2.3436470542037569E-7 + } + }] + }, + { + "stripeNumber": 2, + "stripeInformation": { + "offset": 64833, + "indexLength": 961, + "dataLength": 63763, + "footerLength": 88, + "rowCount": 5000 + }, + "streams": [ + { + "columnId": 0, + "section": "ROW_INDEX", + "startOffset": 64833, + "length": 17 + }, + { + "columnId": 1, + "section": "ROW_INDEX", + "startOffset": 64850, + "length": 166 + }, + { + "columnId": 2, + "section": "ROW_INDEX", + "startOffset": 65016, + "length": 166 + }, + { + "columnId": 3, + "section": "ROW_INDEX", + "startOffset": 65182, + "length": 100 + }, + { + "columnId": 3, + "section": "BLOOM_FILTER", + "startOffset": 65282, + "length": 512 + }, + { + "columnId": 1, + "section": "DATA", + "startOffset": 65794, + "length": 20035 + }, + { + "columnId": 2, + "section": "DATA", + "startOffset": 85829, + "length": 40050 + }, + { + "columnId": 3, + "section": "PRESENT", + "startOffset": 125879, + "length": 17 + }, + { + "columnId": 3, + "section": "DATA", + "startOffset": 125896, + "length": 3503 + }, + { + "columnId": 3, + "section": "LENGTH", + "startOffset": 129399, + "length": 25 + }, + { + "columnId": 3, + "section": "DICTIONARY_DATA", + "startOffset": 129424, + "length": 133 + } + ], + "encodings": [ + { + "columnId": 0, + "kind": "DIRECT" + }, + { + "columnId": 1, + "kind": "DIRECT_V2" + }, + { + "columnId": 2, + "kind": "DIRECT_V2" + }, + { + "columnId": 3, + "kind": "DICTIONARY_V2", + "dictionarySize": 35 + } + ], + "indexes": [{ + "columnId": 3, + "rowGroupIndexes": [ + { + "entryId": 0, + "count": 990, + "hasNull": true, + "min": "Darkness,", + "max": "worst", + "totalLength": 3946, + "type": "STRING", + "positions": [ + 0, + 0, + 0, + 0, + 0, + 0, + 0 + ] + }, + { + "entryId": 1, + "count": 990, + "hasNull": true, + "min": "Darkness,", + "max": "worst", + "totalLength": 3836, + "type": "STRING", + "positions": [ + 0, + 38, + 12, + 0, + 0, + 746, + 11 + ] + }, + { + "entryId": 2, + "count": 990, + "hasNull": true, + "min": "Darkness,", + "max": "worst", + "totalLength": 3791, + "type": "STRING", + "positions": [ + 0, + 78, + 12, + 0, + 0, + 1430, + 95 + ] + }, + { + "entryId": 3, + "count": 990, + "hasNull": true, + "min": "Darkness,", + "max": "worst", + "totalLength": 3904, + "type": "STRING", + "positions": [ + 0, + 118, + 12, + 0, + 0, + 2239, + 23 + ] + }, + { + "entryId": 4, + "count": 990, + "hasNull": true, + "min": "Darkness,", + "max": "worst", + "totalLength": 3920, + "type": "STRING", + "positions": [ + 0, + 158, + 12, + 0, + 0, + 2994, + 17 + ] + } + ], + "bloomFilterIndexes": [ + { + "entryId": 0, + "numHashFunctions": 4, + "bitCount": 6272, + "popCount": 138, + "loadFactor": 0.022002551704645157, + "expectedFpp": 2.3436470542037569E-7 + }, + { + "entryId": 1, + "numHashFunctions": 4, + "bitCount": 6272, + "popCount": 138, + "loadFactor": 0.022002551704645157, + "expectedFpp": 2.3436470542037569E-7 + }, + { + "entryId": 2, + "numHashFunctions": 4, + "bitCount": 6272, + "popCount": 138, + "loadFactor": 0.022002551704645157, + "expectedFpp": 2.3436470542037569E-7 + }, + { + "entryId": 3, + "numHashFunctions": 4, + "bitCount": 6272, + "popCount": 138, + "loadFactor": 0.022002551704645157, + "expectedFpp": 2.3436470542037569E-7 + }, + { + "entryId": 4, + "numHashFunctions": 4, + "bitCount": 6272, + "popCount": 138, + "loadFactor": 0.022002551704645157, + "expectedFpp": 2.3436470542037569E-7 + } + ], + "stripeLevelBloomFilter": { + "numHashFunctions": 4, + "bitCount": 6272, + "popCount": 138, + "loadFactor": 0.022002551704645157, + "expectedFpp": 2.3436470542037569E-7 + } + }] + }, + { + "stripeNumber": 3, + "stripeInformation": { + "offset": 129645, + "indexLength": 962, + "dataLength": 63770, + "footerLength": 91, + "rowCount": 5000 + }, + "streams": [ + { + "columnId": 0, + "section": "ROW_INDEX", + "startOffset": 129645, + "length": 17 + }, + { + "columnId": 1, + "section": "ROW_INDEX", + "startOffset": 129662, + "length": 164 + }, + { + "columnId": 2, + "section": "ROW_INDEX", + "startOffset": 129826, + "length": 167 + }, + { + "columnId": 3, + "section": "ROW_INDEX", + "startOffset": 129993, + "length": 102 + }, + { + "columnId": 3, + "section": "BLOOM_FILTER", + "startOffset": 130095, + "length": 512 + }, + { + "columnId": 1, + "section": "DATA", + "startOffset": 130607, + "length": 20035 + }, + { + "columnId": 2, + "section": "DATA", + "startOffset": 150642, + "length": 40050 + }, + { + "columnId": 3, + "section": "PRESENT", + "startOffset": 190692, + "length": 17 + }, + { + "columnId": 3, + "section": "DATA", + "startOffset": 190709, + "length": 3510 + }, + { + "columnId": 3, + "section": "LENGTH", + "startOffset": 194219, + "length": 25 + }, + { + "columnId": 3, + "section": "DICTIONARY_DATA", + "startOffset": 194244, + "length": 133 + } + ], + "encodings": [ + { + "columnId": 0, + "kind": "DIRECT" + }, + { + "columnId": 1, + "kind": "DIRECT_V2" + }, + { + "columnId": 2, + "kind": "DIRECT_V2" + }, + { + "columnId": 3, + "kind": "DICTIONARY_V2", + "dictionarySize": 35 + } + ], + "indexes": [{ + "columnId": 3, + "rowGroupIndexes": [ + { + "entryId": 0, + "count": 990, + "hasNull": true, + "min": "Darkness,", + "max": "worst", + "totalLength": 3829, + "type": "STRING", + "positions": [ + 0, + 0, + 0, + 0, + 0, + 0, + 0 + ] + }, + { + "entryId": 1, + "count": 990, + "hasNull": true, + "min": "Darkness,", + "max": "worst", + "totalLength": 3853, + "type": "STRING", + "positions": [ + 0, + 38, + 12, + 0, + 0, + 698, + 74 + ] + }, + { + "entryId": 2, + "count": 990, + "hasNull": true, + "min": "Darkness,", + "max": "worst", + "totalLength": 3796, + "type": "STRING", + "positions": [ + 0, + 78, + 12, + 0, + 0, + 1483, + 39 + ] + }, + { + "entryId": 3, + "count": 990, + "hasNull": true, + "min": "Darkness,", + "max": "worst", + "totalLength": 3736, + "type": "STRING", + "positions": [ + 0, + 118, + 12, + 0, + 0, + 2148, + 155 + ] + }, + { + "entryId": 4, + "count": 990, + "hasNull": true, + "min": "Darkness,", + "max": "worst", + "totalLength": 3817, + "type": "STRING", + "positions": [ + 0, + 158, + 12, + 0, + 0, + 3018, + 8 + ] + } + ], + "bloomFilterIndexes": [ + { + "entryId": 0, + "numHashFunctions": 4, + "bitCount": 6272, + "popCount": 138, + "loadFactor": 0.022002551704645157, + "expectedFpp": 2.3436470542037569E-7 + }, + { + "entryId": 1, + "numHashFunctions": 4, + "bitCount": 6272, + "popCount": 138, + "loadFactor": 0.022002551704645157, + "expectedFpp": 2.3436470542037569E-7 + }, + { + "entryId": 2, + "numHashFunctions": 4, + "bitCount": 6272, + "popCount": 138, + "loadFactor": 0.022002551704645157, + "expectedFpp": 2.3436470542037569E-7 + }, + { + "entryId": 3, + "numHashFunctions": 4, + "bitCount": 6272, + "popCount": 138, + "loadFactor": 0.022002551704645157, + "expectedFpp": 2.3436470542037569E-7 + }, + { + "entryId": 4, + "numHashFunctions": 4, + "bitCount": 6272, + "popCount": 138, + "loadFactor": 0.022002551704645157, + "expectedFpp": 2.3436470542037569E-7 + } + ], + "stripeLevelBloomFilter": { + "numHashFunctions": 4, + "bitCount": 6272, + "popCount": 138, + "loadFactor": 0.022002551704645157, + "expectedFpp": 2.3436470542037569E-7 + } + }] + }, + { + "stripeNumber": 4, + "stripeInformation": { + "offset": 194468, + "indexLength": 973, + "dataLength": 63756, + "footerLength": 91, + "rowCount": 5000 + }, + "streams": [ + { + "columnId": 0, + "section": "ROW_INDEX", + "startOffset": 194468, + "length": 17 + }, + { + "columnId": 1, + "section": "ROW_INDEX", + "startOffset": 194485, + "length": 166 + }, + { + "columnId": 2, + "section": "ROW_INDEX", + "startOffset": 194651, + "length": 171 + }, + { + "columnId": 3, + "section": "ROW_INDEX", + "startOffset": 194822, + "length": 107 + }, + { + "columnId": 3, + "section": "BLOOM_FILTER", + "startOffset": 194929, + "length": 512 + }, + { + "columnId": 1, + "section": "DATA", + "startOffset": 195441, + "length": 20035 + }, + { + "columnId": 2, + "section": "DATA", + "startOffset": 215476, + "length": 40050 + }, + { + "columnId": 3, + "section": "PRESENT", + "startOffset": 255526, + "length": 17 + }, + { + "columnId": 3, + "section": "DATA", + "startOffset": 255543, + "length": 3496 + }, + { + "columnId": 3, + "section": "LENGTH", + "startOffset": 259039, + "length": 25 + }, + { + "columnId": 3, + "section": "DICTIONARY_DATA", + "startOffset": 259064, + "length": 133 + } + ], + "encodings": [ + { + "columnId": 0, + "kind": "DIRECT" + }, + { + "columnId": 1, + "kind": "DIRECT_V2" + }, + { + "columnId": 2, + "kind": "DIRECT_V2" + }, + { + "columnId": 3, + "kind": "DICTIONARY_V2", + "dictionarySize": 35 + } + ], + "indexes": [{ + "columnId": 3, + "rowGroupIndexes": [ + { + "entryId": 0, + "count": 990, + "hasNull": true, + "min": "Darkness,", + "max": "worst", + "totalLength": 3959, + "type": "STRING", + "positions": [ + 0, + 0, + 0, + 0, + 0, + 0, + 0 + ] + }, + { + "entryId": 1, + "count": 990, + "hasNull": true, + "min": "Darkness,", + "max": "worst", + "totalLength": 3816, + "type": "STRING", + "positions": [ + 0, + 38, + 12, + 0, + 0, + 495, + 338 + ] + }, + { + "entryId": 2, + "count": 990, + "hasNull": true, + "min": "Darkness,", + "max": "worst", + "totalLength": 3883, + "type": "STRING", + "positions": [ + 0, + 78, + 12, + 0, + 0, + 1449, + 71 + ] + }, + { + "entryId": 3, + "count": 990, + "hasNull": true, + "min": "Darkness,", + "max": "worst", + "totalLength": 3938, + "type": "STRING", + "positions": [ + 0, + 118, + 12, + 0, + 0, + 2207, + 59 + ] + }, + { + "entryId": 4, + "count": 990, + "hasNull": true, + "min": "Darkness,", + "max": "worst", + "totalLength": 3863, + "type": "STRING", + "positions": [ + 0, + 158, + 12, + 0, + 0, + 2838, + 223 + ] + } + ], + "bloomFilterIndexes": [ + { + "entryId": 0, + "numHashFunctions": 4, + "bitCount": 6272, + "popCount": 138, + "loadFactor": 0.022002551704645157, + "expectedFpp": 2.3436470542037569E-7 + }, + { + "entryId": 1, + "numHashFunctions": 4, + "bitCount": 6272, + "popCount": 138, + "loadFactor": 0.022002551704645157, + "expectedFpp": 2.3436470542037569E-7 + }, + { + "entryId": 2, + "numHashFunctions": 4, + "bitCount": 6272, + "popCount": 138, + "loadFactor": 0.022002551704645157, + "expectedFpp": 2.3436470542037569E-7 + }, + { + "entryId": 3, + "numHashFunctions": 4, + "bitCount": 6272, + "popCount": 138, + "loadFactor": 0.022002551704645157, + "expectedFpp": 2.3436470542037569E-7 + }, + { + "entryId": 4, + "numHashFunctions": 4, + "bitCount": 6272, + "popCount": 138, + "loadFactor": 0.022002551704645157, + "expectedFpp": 2.3436470542037569E-7 + } + ], + "stripeLevelBloomFilter": { + "numHashFunctions": 4, + "bitCount": 6272, + "popCount": 138, + "loadFactor": 0.022002551704645157, + "expectedFpp": 2.3436470542037569E-7 + } + }] + }, + { + "stripeNumber": 5, + "stripeInformation": { + "offset": 259288, + "indexLength": 433, + "dataLength": 12943, + "footerLength": 83, + "rowCount": 1000 + }, + "streams": [ + { + "columnId": 0, + "section": "ROW_INDEX", + "startOffset": 259288, + "length": 12 + }, + { + "columnId": 1, + "section": "ROW_INDEX", + "startOffset": 259300, + "length": 38 + }, + { + "columnId": 2, + "section": "ROW_INDEX", + "startOffset": 259338, + "length": 41 + }, + { + "columnId": 3, + "section": "ROW_INDEX", + "startOffset": 259379, + "length": 41 + }, + { + "columnId": 3, + "section": "BLOOM_FILTER", + "startOffset": 259420, + "length": 301 + }, + { + "columnId": 1, + "section": "DATA", + "startOffset": 259721, + "length": 4007 + }, + { + "columnId": 2, + "section": "DATA", + "startOffset": 263728, + "length": 8010 + }, + { + "columnId": 3, + "section": "PRESENT", + "startOffset": 271738, + "length": 16 + }, + { + "columnId": 3, + "section": "DATA", + "startOffset": 271754, + "length": 752 + }, + { + "columnId": 3, + "section": "LENGTH", + "startOffset": 272506, + "length": 25 + }, + { + "columnId": 3, + "section": "DICTIONARY_DATA", + "startOffset": 272531, + "length": 133 + } + ], + "encodings": [ + { + "columnId": 0, + "kind": "DIRECT" + }, + { + "columnId": 1, + "kind": "DIRECT_V2" + }, + { + "columnId": 2, + "kind": "DIRECT_V2" + }, + { + "columnId": 3, + "kind": "DICTIONARY_V2", + "dictionarySize": 35 + } + ], + "indexes": [{ + "columnId": 3, + "rowGroupIndexes": [{ + "entryId": 0, + "count": 990, + "hasNull": true, + "min": "Darkness,", + "max": "worst", + "totalLength": 3963, + "type": "STRING", + "positions": [ + 0, + 0, + 0, + 0, + 0, + 0, + 0 + ] + }], + "bloomFilterIndexes": [{ + "entryId": 0, + "numHashFunctions": 4, + "bitCount": 6272, + "popCount": 138, + "loadFactor": 0.022002551704645157, + "expectedFpp": 2.3436470542037569E-7 + }], + "stripeLevelBloomFilter": { + "numHashFunctions": 4, + "bitCount": 6272, + "popCount": 138, + "loadFactor": 0.022002551704645157, + "expectedFpp": 2.3436470542037569E-7 + } + }] + } + ], + "fileLength": 273300, + "paddingLength": 0, + "paddingRatio": 0, + "status": "OK" +} http://git-wip-us.apache.org/repos/asf/orc/blob/3283d238/java/core/src/test/resources/orc-file-dump.out ---------------------------------------------------------------------- diff --git a/java/core/src/test/resources/orc-file-dump.out b/java/core/src/test/resources/orc-file-dump.out new file mode 100644 index 0000000..70f7fbd --- /dev/null +++ b/java/core/src/test/resources/orc-file-dump.out @@ -0,0 +1,195 @@ +Structure for TestFileDump.testDump.orc +File Version: 0.12 with HIVE_13083 +Rows: 21000 +Compression: ZLIB +Compression size: 4096 +Type: struct<i:int,l:bigint,s:string> + +Stripe Statistics: + Stripe 1: + Column 0: count: 5000 hasNull: false + Column 1: count: 5000 hasNull: false min: -2146021688 max: 2147223299 sum: 515792826 + Column 2: count: 5000 hasNull: false min: -9218592812243954469 max: 9221614132680747961 + Column 3: count: 5000 hasNull: false min: Darkness, max: worst sum: 19280 + Stripe 2: + Column 0: count: 5000 hasNull: false + Column 1: count: 5000 hasNull: false min: -2146733128 max: 2147001622 sum: 7673427 + Column 2: count: 5000 hasNull: false min: -9220818777591257749 max: 9222259462014003839 + Column 3: count: 5000 hasNull: false min: Darkness, max: worst sum: 19504 + Stripe 3: + Column 0: count: 5000 hasNull: false + Column 1: count: 5000 hasNull: false min: -2146993718 max: 2147378179 sum: 132660742551 + Column 2: count: 5000 hasNull: false min: -9218342074710552826 max: 9222303228623055266 + Column 3: count: 5000 hasNull: false min: Darkness, max: worst sum: 19641 + Stripe 4: + Column 0: count: 5000 hasNull: false + Column 1: count: 5000 hasNull: false min: -2146658006 max: 2145520931 sum: 8533549236 + Column 2: count: 5000 hasNull: false min: -9222758097219661129 max: 9221043130193737406 + Column 3: count: 5000 hasNull: false min: Darkness, max: worst sum: 19470 + Stripe 5: + Column 0: count: 1000 hasNull: false + Column 1: count: 1000 hasNull: false min: -2146245500 max: 2146378640 sum: 51299706363 + Column 2: count: 1000 hasNull: false min: -9208193203370316142 max: 9218567213558056476 + Column 3: count: 1000 hasNull: false min: Darkness, max: worst sum: 3866 + +File Statistics: + Column 0: count: 21000 hasNull: false + Column 1: count: 21000 hasNull: false min: -2146993718 max: 2147378179 sum: 193017464403 + Column 2: count: 21000 hasNull: false min: -9222758097219661129 max: 9222303228623055266 + Column 3: count: 21000 hasNull: false min: Darkness, max: worst sum: 81761 + +Stripes: + Stripe: offset: 3 data: 63786 rows: 5000 tail: 79 index: 439 + Stream: column 0 section ROW_INDEX start: 3 length 17 + Stream: column 1 section ROW_INDEX start: 20 length 166 + Stream: column 2 section ROW_INDEX start: 186 length 169 + Stream: column 3 section ROW_INDEX start: 355 length 87 + Stream: column 1 section DATA start: 442 length 20035 + Stream: column 2 section DATA start: 20477 length 40050 + Stream: column 3 section DATA start: 60527 length 3543 + Stream: column 3 section LENGTH start: 64070 length 25 + Stream: column 3 section DICTIONARY_DATA start: 64095 length 133 + Encoding column 0: DIRECT + Encoding column 1: DIRECT_V2 + Encoding column 2: DIRECT_V2 + Encoding column 3: DICTIONARY_V2[35] + Row group indices for column 1: + Entry 0: count: 1000 hasNull: false min: -2145365268 max: 2135491313 sum: 7521792925 positions: 0,0,0 + Entry 1: count: 1000 hasNull: false min: -2139452528 max: 2147223299 sum: -12923774313 positions: 0,2050,488 + Entry 2: count: 1000 hasNull: false min: -2142420586 max: 2143898386 sum: -25521983511 positions: 4099,2054,464 + Entry 3: count: 1000 hasNull: false min: -2137233441 max: 2144267163 sum: 40993386199 positions: 8198,2058,440 + Entry 4: count: 1000 hasNull: false min: -2146021688 max: 2146838901 sum: -9553628474 positions: 12297,2062,416 + Row group indices for column 2: + Entry 0: count: 1000 hasNull: false min: -9200577545527640566 max: 9175500305011173751 positions: 0,0,0 + Entry 1: count: 1000 hasNull: false min: -9203618157670445774 max: 9208123824411178101 positions: 4099,2,488 + Entry 2: count: 1000 hasNull: false min: -9218592812243954469 max: 9221351515892923972 positions: 12297,6,464 + Entry 3: count: 1000 hasNull: false min: -9206585617947511272 max: 9167703224425685487 positions: 20495,10,440 + Entry 4: count: 1000 hasNull: false min: -9206645795733282496 max: 9221614132680747961 positions: 28693,14,416 + Row group indices for column 3: + Entry 0: count: 1000 hasNull: false min: Darkness, max: worst sum: 3862 positions: 0,0,0 + Entry 1: count: 1000 hasNull: false min: Darkness, max: worst sum: 3884 positions: 0,659,149 + Entry 2: count: 1000 hasNull: false min: Darkness, max: worst sum: 3893 positions: 0,1531,3 + Entry 3: count: 1000 hasNull: false min: Darkness, max: worst sum: 3798 positions: 0,2281,32 + Entry 4: count: 1000 hasNull: false min: Darkness, max: worst sum: 3843 positions: 0,3033,45 + Stripe: offset: 64307 data: 63775 rows: 5000 tail: 79 index: 432 + Stream: column 0 section ROW_INDEX start: 64307 length 17 + Stream: column 1 section ROW_INDEX start: 64324 length 164 + Stream: column 2 section ROW_INDEX start: 64488 length 168 + Stream: column 3 section ROW_INDEX start: 64656 length 83 + Stream: column 1 section DATA start: 64739 length 20035 + Stream: column 2 section DATA start: 84774 length 40050 + Stream: column 3 section DATA start: 124824 length 3532 + Stream: column 3 section LENGTH start: 128356 length 25 + Stream: column 3 section DICTIONARY_DATA start: 128381 length 133 + Encoding column 0: DIRECT + Encoding column 1: DIRECT_V2 + Encoding column 2: DIRECT_V2 + Encoding column 3: DICTIONARY_V2[35] + Row group indices for column 1: + Entry 0: count: 1000 hasNull: false min: -2143799121 max: 2145249879 sum: -6966266181 positions: 0,0,0 + Entry 1: count: 1000 hasNull: false min: -2146733128 max: 2147001622 sum: -35930106333 positions: 0,2050,488 + Entry 2: count: 1000 hasNull: false min: -2144302712 max: 2146299933 sum: 6944230435 positions: 4099,2054,464 + Entry 3: count: 1000 hasNull: false min: -2145172948 max: 2144335014 sum: -29624404959 positions: 8198,2058,440 + Entry 4: count: 1000 hasNull: false min: -2146428427 max: 2144067253 sum: 65584220465 positions: 12297,2062,416 + Row group indices for column 2: + Entry 0: count: 1000 hasNull: false min: -9218450653857701562 max: 9189819526332228512 positions: 0,0,0 + Entry 1: count: 1000 hasNull: false min: -9220818777591257749 max: 9178821722829648113 positions: 4099,2,488 + Entry 2: count: 1000 hasNull: false min: -9220031433030423388 max: 9210838931786956852 positions: 12297,6,464 + Entry 3: count: 1000 hasNull: false min: -9208195729739635607 max: 9222259462014003839 positions: 20495,10,440 + Entry 4: count: 1000 hasNull: false min: -9174271499932339698 max: 9212277876771676916 positions: 28693,14,416 + Row group indices for column 3: + Entry 0: count: 1000 hasNull: false min: Darkness, max: worst sum: 3923 positions: 0,0,0 + Entry 1: count: 1000 hasNull: false min: Darkness, max: worst sum: 3869 positions: 0,761,12 + Entry 2: count: 1000 hasNull: false min: Darkness, max: worst sum: 3817 positions: 0,1472,70 + Entry 3: count: 1000 hasNull: false min: Darkness, max: worst sum: 3931 positions: 0,2250,43 + Entry 4: count: 1000 hasNull: false min: Darkness, max: worst sum: 3964 positions: 0,2978,88 + Stripe: offset: 128593 data: 63787 rows: 5000 tail: 79 index: 438 + Stream: column 0 section ROW_INDEX start: 128593 length 17 + Stream: column 1 section ROW_INDEX start: 128610 length 163 + Stream: column 2 section ROW_INDEX start: 128773 length 168 + Stream: column 3 section ROW_INDEX start: 128941 length 90 + Stream: column 1 section DATA start: 129031 length 20035 + Stream: column 2 section DATA start: 149066 length 40050 + Stream: column 3 section DATA start: 189116 length 3544 + Stream: column 3 section LENGTH start: 192660 length 25 + Stream: column 3 section DICTIONARY_DATA start: 192685 length 133 + Encoding column 0: DIRECT + Encoding column 1: DIRECT_V2 + Encoding column 2: DIRECT_V2 + Encoding column 3: DICTIONARY_V2[35] + Row group indices for column 1: + Entry 0: count: 1000 hasNull: false min: -2146993718 max: 2144179881 sum: -7829543271 positions: 0,0,0 + Entry 1: count: 1000 hasNull: false min: -2144095505 max: 2144883384 sum: 51623839692 positions: 0,2050,488 + Entry 2: count: 1000 hasNull: false min: -2144113995 max: 2143773575 sum: 56574412741 positions: 4099,2054,464 + Entry 3: count: 1000 hasNull: false min: -2146954065 max: 2146794873 sum: 4336083432 positions: 8198,2058,440 + Entry 4: count: 1000 hasNull: false min: -2135511523 max: 2147378179 sum: 27955949957 positions: 12297,2062,416 + Row group indices for column 2: + Entry 0: count: 1000 hasNull: false min: -9211978436552246208 max: 9179058898902097152 positions: 0,0,0 + Entry 1: count: 1000 hasNull: false min: -9195645160817780503 max: 9189147759444307708 positions: 4099,2,488 + Entry 2: count: 1000 hasNull: false min: -9202888157616520823 max: 9193561362676960747 positions: 12297,6,464 + Entry 3: count: 1000 hasNull: false min: -9216318198067839390 max: 9221286760675829363 positions: 20495,10,440 + Entry 4: count: 1000 hasNull: false min: -9218342074710552826 max: 9222303228623055266 positions: 28693,14,416 + Row group indices for column 3: + Entry 0: count: 1000 hasNull: false min: Darkness, max: worst sum: 3817 positions: 0,0,0 + Entry 1: count: 1000 hasNull: false min: Darkness, max: worst sum: 4008 positions: 0,634,174 + Entry 2: count: 1000 hasNull: false min: Darkness, max: worst sum: 3999 positions: 0,1469,69 + Entry 3: count: 1000 hasNull: false min: Darkness, max: worst sum: 3817 positions: 0,2133,194 + Entry 4: count: 1000 hasNull: false min: Darkness, max: worst sum: 4000 positions: 0,3005,43 + Stripe: offset: 192897 data: 63817 rows: 5000 tail: 79 index: 440 + Stream: column 0 section ROW_INDEX start: 192897 length 17 + Stream: column 1 section ROW_INDEX start: 192914 length 165 + Stream: column 2 section ROW_INDEX start: 193079 length 167 + Stream: column 3 section ROW_INDEX start: 193246 length 91 + Stream: column 1 section DATA start: 193337 length 20035 + Stream: column 2 section DATA start: 213372 length 40050 + Stream: column 3 section DATA start: 253422 length 3574 + Stream: column 3 section LENGTH start: 256996 length 25 + Stream: column 3 section DICTIONARY_DATA start: 257021 length 133 + Encoding column 0: DIRECT + Encoding column 1: DIRECT_V2 + Encoding column 2: DIRECT_V2 + Encoding column 3: DICTIONARY_V2[35] + Row group indices for column 1: + Entry 0: count: 1000 hasNull: false min: -2141355639 max: 2145520931 sum: 2726719912 positions: 0,0,0 + Entry 1: count: 1000 hasNull: false min: -2138324170 max: 2140167376 sum: -23606674002 positions: 0,2050,488 + Entry 2: count: 1000 hasNull: false min: -2146658006 max: 2144329742 sum: -41530109703 positions: 4099,2054,464 + Entry 3: count: 1000 hasNull: false min: -2144207593 max: 2139456355 sum: 13559842458 positions: 8198,2058,440 + Entry 4: count: 1000 hasNull: false min: -2145744719 max: 2145417153 sum: 57383770571 positions: 12297,2062,416 + Row group indices for column 2: + Entry 0: count: 1000 hasNull: false min: -9222731174895935707 max: 9214167447015056056 positions: 0,0,0 + Entry 1: count: 1000 hasNull: false min: -9222758097219661129 max: 9221043130193737406 positions: 4099,2,488 + Entry 2: count: 1000 hasNull: false min: -9174483776261243438 max: 9208134757538374043 positions: 12297,6,464 + Entry 3: count: 1000 hasNull: false min: -9174329712613510612 max: 9197412874152820822 positions: 20495,10,440 + Entry 4: count: 1000 hasNull: false min: -9221162005892422758 max: 9220625004936875965 positions: 28693,14,416 + Row group indices for column 3: + Entry 0: count: 1000 hasNull: false min: Darkness, max: worst sum: 3901 positions: 0,0,0 + Entry 1: count: 1000 hasNull: false min: Darkness, max: worst sum: 3900 positions: 0,431,431 + Entry 2: count: 1000 hasNull: false min: Darkness, max: worst sum: 3909 positions: 0,1485,52 + Entry 3: count: 1000 hasNull: false min: Darkness, max: worst sum: 3947 positions: 0,2196,104 + Entry 4: count: 1000 hasNull: false min: Darkness, max: worst sum: 3813 positions: 0,2934,131 + Stripe: offset: 257233 data: 12943 rows: 1000 tail: 71 index: 131 + Stream: column 0 section ROW_INDEX start: 257233 length 12 + Stream: column 1 section ROW_INDEX start: 257245 length 38 + Stream: column 2 section ROW_INDEX start: 257283 length 41 + Stream: column 3 section ROW_INDEX start: 257324 length 40 + Stream: column 1 section DATA start: 257364 length 4007 + Stream: column 2 section DATA start: 261371 length 8010 + Stream: column 3 section DATA start: 269381 length 768 + Stream: column 3 section LENGTH start: 270149 length 25 + Stream: column 3 section DICTIONARY_DATA start: 270174 length 133 + Encoding column 0: DIRECT + Encoding column 1: DIRECT_V2 + Encoding column 2: DIRECT_V2 + Encoding column 3: DICTIONARY_V2[35] + Row group indices for column 1: + Entry 0: count: 1000 hasNull: false min: -2146245500 max: 2146378640 sum: 51299706363 positions: 0,0,0 + Row group indices for column 2: + Entry 0: count: 1000 hasNull: false min: -9208193203370316142 max: 9218567213558056476 positions: 0,0,0 + Row group indices for column 3: + Entry 0: count: 1000 hasNull: false min: Darkness, max: worst sum: 3866 positions: 0,0,0 + +File length: 270923 bytes +Padding length: 0 bytes +Padding ratio: 0% +________________________________________________________________________________________________________________________ + http://git-wip-us.apache.org/repos/asf/orc/blob/3283d238/java/core/src/test/resources/orc-file-has-null.out ---------------------------------------------------------------------- diff --git a/java/core/src/test/resources/orc-file-has-null.out b/java/core/src/test/resources/orc-file-has-null.out new file mode 100644 index 0000000..e98a73f --- /dev/null +++ b/java/core/src/test/resources/orc-file-has-null.out @@ -0,0 +1,112 @@ +Structure for TestOrcFile.testHasNull.orc +File Version: 0.12 with HIVE_13083 +Rows: 20000 +Compression: ZLIB +Compression size: 4096 +Type: struct<bytes1:binary,string1:string> + +Stripe Statistics: + Stripe 1: + Column 0: count: 5000 hasNull: false + Column 1: count: 5000 hasNull: false sum: 15000 + Column 2: count: 2000 hasNull: true min: RG1 max: RG3 sum: 6000 + Stripe 2: + Column 0: count: 5000 hasNull: false + Column 1: count: 5000 hasNull: false sum: 15000 + Column 2: count: 0 hasNull: true + Stripe 3: + Column 0: count: 5000 hasNull: false + Column 1: count: 5000 hasNull: false sum: 15000 + Column 2: count: 5000 hasNull: false min: STRIPE-3 max: STRIPE-3 sum: 40000 + Stripe 4: + Column 0: count: 5000 hasNull: false + Column 1: count: 5000 hasNull: false sum: 15000 + Column 2: count: 0 hasNull: true + +File Statistics: + Column 0: count: 20000 hasNull: false + Column 1: count: 20000 hasNull: false sum: 60000 + Column 2: count: 7000 hasNull: true min: RG1 max: STRIPE-3 sum: 46000 + +Stripes: + Stripe: offset: 3 data: 220 rows: 5000 tail: 65 index: 154 + Stream: column 0 section ROW_INDEX start: 3 length 17 + Stream: column 1 section ROW_INDEX start: 20 length 60 + Stream: column 2 section ROW_INDEX start: 80 length 77 + Stream: column 1 section DATA start: 157 length 159 + Stream: column 1 section LENGTH start: 316 length 15 + Stream: column 2 section PRESENT start: 331 length 13 + Stream: column 2 section DATA start: 344 length 18 + Stream: column 2 section LENGTH start: 362 length 6 + Stream: column 2 section DICTIONARY_DATA start: 368 length 9 + Encoding column 0: DIRECT + Encoding column 1: DIRECT_V2 + Encoding column 2: DICTIONARY_V2[2] + Row group indices for column 2: + Entry 0: count: 1000 hasNull: false min: RG1 max: RG1 sum: 3000 positions: 0,0,0,0,0,0,0 + Entry 1: count: 0 hasNull: true positions: 0,0,125,0,0,4,488 + Entry 2: count: 1000 hasNull: false min: RG3 max: RG3 sum: 3000 positions: 0,2,125,0,0,4,488 + Entry 3: count: 0 hasNull: true positions: 0,4,125,0,0,12,488 + Entry 4: count: 0 hasNull: true positions: 0,6,125,0,0,12,488 + Stripe: offset: 442 data: 185 rows: 5000 tail: 64 index: 116 + Stream: column 0 section ROW_INDEX start: 442 length 17 + Stream: column 1 section ROW_INDEX start: 459 length 60 + Stream: column 2 section ROW_INDEX start: 519 length 39 + Stream: column 1 section DATA start: 558 length 159 + Stream: column 1 section LENGTH start: 717 length 15 + Stream: column 2 section PRESENT start: 732 length 11 + Stream: column 2 section DATA start: 743 length 0 + Stream: column 2 section LENGTH start: 743 length 0 + Stream: column 2 section DICTIONARY_DATA start: 743 length 0 + Encoding column 0: DIRECT + Encoding column 1: DIRECT_V2 + Encoding column 2: DICTIONARY_V2[0] + Row group indices for column 2: + Entry 0: count: 0 hasNull: true positions: 0,0,0,0,0,0,0 + Entry 1: count: 0 hasNull: true positions: 0,0,125,0,0,0,0 + Entry 2: count: 0 hasNull: true positions: 0,2,120,0,0,0,0 + Entry 3: count: 0 hasNull: true positions: 0,4,115,0,0,0,0 + Entry 4: count: 0 hasNull: true positions: 0,6,110,0,0,0,0 + Stripe: offset: 807 data: 206 rows: 5000 tail: 60 index: 137 + Stream: column 0 section ROW_INDEX start: 807 length 17 + Stream: column 1 section ROW_INDEX start: 824 length 60 + Stream: column 2 section ROW_INDEX start: 884 length 60 + Stream: column 1 section DATA start: 944 length 159 + Stream: column 1 section LENGTH start: 1103 length 15 + Stream: column 2 section DATA start: 1118 length 15 + Stream: column 2 section LENGTH start: 1133 length 6 + Stream: column 2 section DICTIONARY_DATA start: 1139 length 11 + Encoding column 0: DIRECT + Encoding column 1: DIRECT_V2 + Encoding column 2: DICTIONARY_V2[1] + Row group indices for column 2: + Entry 0: count: 1000 hasNull: false min: STRIPE-3 max: STRIPE-3 sum: 8000 positions: 0,0,0 + Entry 1: count: 1000 hasNull: false min: STRIPE-3 max: STRIPE-3 sum: 8000 positions: 0,4,488 + Entry 2: count: 1000 hasNull: false min: STRIPE-3 max: STRIPE-3 sum: 8000 positions: 0,12,464 + Entry 3: count: 1000 hasNull: false min: STRIPE-3 max: STRIPE-3 sum: 8000 positions: 0,20,440 + Entry 4: count: 1000 hasNull: false min: STRIPE-3 max: STRIPE-3 sum: 8000 positions: 0,28,416 + Stripe: offset: 1210 data: 185 rows: 5000 tail: 64 index: 116 + Stream: column 0 section ROW_INDEX start: 1210 length 17 + Stream: column 1 section ROW_INDEX start: 1227 length 60 + Stream: column 2 section ROW_INDEX start: 1287 length 39 + Stream: column 1 section DATA start: 1326 length 159 + Stream: column 1 section LENGTH start: 1485 length 15 + Stream: column 2 section PRESENT start: 1500 length 11 + Stream: column 2 section DATA start: 1511 length 0 + Stream: column 2 section LENGTH start: 1511 length 0 + Stream: column 2 section DICTIONARY_DATA start: 1511 length 0 + Encoding column 0: DIRECT + Encoding column 1: DIRECT_V2 + Encoding column 2: DICTIONARY_V2[0] + Row group indices for column 2: + Entry 0: count: 0 hasNull: true positions: 0,0,0,0,0,0,0 + Entry 1: count: 0 hasNull: true positions: 0,0,125,0,0,0,0 + Entry 2: count: 0 hasNull: true positions: 0,2,120,0,0,0,0 + Entry 3: count: 0 hasNull: true positions: 0,4,115,0,0,0,0 + Entry 4: count: 0 hasNull: true positions: 0,6,110,0,0,0,0 + +File length: 1823 bytes +Padding length: 0 bytes +Padding ratio: 0% +________________________________________________________________________________________________________________________ +
