Last active
September 30, 2019 23:16
-
-
Save alexey-milovidov/4139ec557f482b8a625c2670819b3277 to your computer and use it in GitHub Desktop.
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| :) WITH 'It is the latest occurrence of the Southeast Asian haze, the issue that occurs in constant intensity during every wet season. It has mainly been caused by forest fires resulting from illegal slash-and-burn clearing performed on behalf of the palm oil industry in Kazakhstan, principally on the islands, which then spread quickly in the dry season.' AS str, alphaTokens(str) AS tokens, arrayMap(i -> [tokens[i], tokens[i + 1], tokens[i + 2]], arrayEnumerate(tokens)) AS shingles, arrayMap(x -> sipHash64(x, 1), shingles) AS hashes1, arrayMap(x -> sipHash64(x, 2), shingles) AS hashes2, sipHash64(arraySlice(arraySort(hashes1), 1, 5)) AS h1, sipHash64(arraySlice(arraySort(hashes2), 1, 5)) AS h2 SELECT h1, h2\G | |
| WITH | |
| 'It is the latest occurrence of the Southeast Asian haze, the issue that occurs in constant intensity during every wet season. It has mainly been caused by forest fires resulting from illegal slash-and-burn clearing performed on behalf of the palm oil industry in Kazakhstan, principally on the islands, which then spread quickly in the dry season.' AS str, | |
| alphaTokens(str) AS tokens, | |
| arrayMap(i -> [tokens[i], tokens[i + 1], tokens[i + 2]], arrayEnumerate(tokens)) AS shingles, | |
| arrayMap(x -> sipHash64(x, 1), shingles) AS hashes1, | |
| arrayMap(x -> sipHash64(x, 2), shingles) AS hashes2, | |
| sipHash64(arraySlice(arraySort(hashes1), 1, 5)) AS h1, | |
| sipHash64(arraySlice(arraySort(hashes2), 1, 5)) AS h2 | |
| SELECT | |
| h1, | |
| h2 | |
| Row 1: | |
| ────── | |
| h1: 4037745474664829908 | |
| h2: 18008138019670968409 | |
| WITH 'It is the latest occurrence of the Southeast European haze, the issue that occurs in constant intensity during every wet season. It has mainly been caused by forest fires resulting from illegal slash-and-burn clearing performed on behalf of the palm oil industry in Kazakhstan, principally on the islands, which then spread quickly in the dry season.' AS str, alphaTokens(str) AS tokens, arrayMap(i -> [tokens[i], tokens[i + 1], tokens[i + 2]], arrayEnumerate(tokens)) AS shingles, arrayMap(x -> sipHash64(x, 1), shingles) AS hashes1, arrayMap(x -> sipHash64(x, 2), shingles) AS hashes2, sipHash64(arraySlice(arraySort(hashes1), 1, 5)) AS h1, sipHash64(arraySlice(arraySort(hashes2), 1, 5)) AS h2 SELECT h1, h2\G | |
| WITH | |
| 'It is the latest occurrence of the Southeast European haze, the issue that occurs in constant intensity during every wet season. It has mainly been caused by forest fires resulting from illegal slash-and-burn clearing performed on behalf of the palm oil industry in Kazakhstan, principally on the islands, which then spread quickly in the dry season.' AS str, | |
| alphaTokens(str) AS tokens, | |
| arrayMap(i -> [tokens[i], tokens[i + 1], tokens[i + 2]], arrayEnumerate(tokens)) AS shingles, | |
| arrayMap(x -> sipHash64(x, 1), shingles) AS hashes1, | |
| arrayMap(x -> sipHash64(x, 2), shingles) AS hashes2, | |
| sipHash64(arraySlice(arraySort(hashes1), 1, 5)) AS h1, | |
| sipHash64(arraySlice(arraySort(hashes2), 1, 5)) AS h2 | |
| SELECT | |
| h1, | |
| h2 | |
| Row 1: | |
| ────── | |
| h1: 4037745474664829908 | |
| h2: 3268385572922067154 | |
| :) WITH 'It is the latest occurrence of the Southeast Asian haze, the issue that occurs in constant intensity during every wet season. It has mainly been caused by forest fires resulting from illegal slash-and-burn clearing performed on behalf of the palm oil industry in Kazakhstan, principally on the islands, which then spread quickly in the dry season.' AS str, alphaTokens(str) AS tokens, arrayMap(i -> [tokens[i], tokens[i + 1], tokens[i + 2]], arrayEnumerate(tokens)) AS shingles, arrayMap(x -> sipHash64(x, 1), shingles) AS hashes1, arrayMap(x -> sipHash64(x, 2), shingles) AS hashes2, sipHash64(arraySlice(arraySort(hashes1), 1, 5)) AS h1, sipHash64(arraySlice(arraySort(hashes2), 1, 5)) AS h2 SELECT h1, h2, arraySlice(arraySort(x -> sipHash64(x, 1), shingles), 1, 5) AS min_shingles1, arraySlice(arraySort(x -> sipHash64(x, 2), shingles), 1, 5) AS min_shingles2\G | |
| WITH | |
| 'It is the latest occurrence of the Southeast Asian haze, the issue that occurs in constant intensity during every wet season. It has mainly been caused by forest fires resulting from illegal slash-and-burn clearing performed on behalf of the palm oil industry in Kazakhstan, principally on the islands, which then spread quickly in the dry season.' AS str, | |
| alphaTokens(str) AS tokens, | |
| arrayMap(i -> [tokens[i], tokens[i + 1], tokens[i + 2]], arrayEnumerate(tokens)) AS shingles, | |
| arrayMap(x -> sipHash64(x, 1), shingles) AS hashes1, | |
| arrayMap(x -> sipHash64(x, 2), shingles) AS hashes2, | |
| sipHash64(arraySlice(arraySort(hashes1), 1, 5)) AS h1, | |
| sipHash64(arraySlice(arraySort(hashes2), 1, 5)) AS h2 | |
| SELECT | |
| h1, | |
| h2, | |
| arraySlice(arraySort(x -> sipHash64(x, 1), shingles), 1, 5) AS min_shingles1, | |
| arraySlice(arraySort(x -> sipHash64(x, 2), shingles), 1, 5) AS min_shingles2 | |
| Row 1: | |
| ────── | |
| h1: 4037745474664829908 | |
| h2: 18008138019670968409 | |
| min_shingles1: [['season','It','has'],['then','spread','quickly'],['islands','which','then'],['the','latest','occurrence'],['principally','on','the']] | |
| min_shingles2: [['palm','oil','industry'],['slash','and','burn'],['Asian','haze','the'],['the','islands','which'],['the','palm','oil']] | |
| 1 rows in set. Elapsed: 0.012 sec. | |
| :) WITH 'It is the latest occurrence of the Southeast Europeian haze, the issue that occurs in constant intensity during every wet season. It has mainly been caused by forest fires resulting from illegal slash-and-burn clearing performed on behalf of the palm oil industry in Kazakhstan, principally on the islands, which then spread quickly in the dry season.' AS str, alphaTokens(str) AS tokens, arrayMap(i -> [tokens[i], tokens[i + 1], tokens[i + 2]], arrayEnumerate(tokens)) AS shingles, arrayMap(x -> sipHash64(x, 1), shingles) AS hashes1, arrayMap(x -> sipHash64(x, 2), shingles) AS hashes2, sipHash64(arraySlice(arraySort(hashes1), 1, 5)) AS h1, sipHash64(arraySlice(arraySort(hashes2), 1, 5)) AS h2 SELECT h1, h2, arraySlice(arraySort(x -> sipHash64(x, 1), shingles), 1, 5) AS min_shingles1, arraySlice(arraySort(x -> sipHash64(x, 2), shingles), 1, 5) AS min_shingles2\G | |
| WITH | |
| 'It is the latest occurrence of the Southeast Europeian haze, the issue that occurs in constant intensity during every wet season. It has mainly been caused by forest fires resulting from illegal slash-and-burn clearing performed on behalf of the palm oil industry in Kazakhstan, principally on the islands, which then spread quickly in the dry season.' AS str, | |
| alphaTokens(str) AS tokens, | |
| arrayMap(i -> [tokens[i], tokens[i + 1], tokens[i + 2]], arrayEnumerate(tokens)) AS shingles, | |
| arrayMap(x -> sipHash64(x, 1), shingles) AS hashes1, | |
| arrayMap(x -> sipHash64(x, 2), shingles) AS hashes2, | |
| sipHash64(arraySlice(arraySort(hashes1), 1, 5)) AS h1, | |
| sipHash64(arraySlice(arraySort(hashes2), 1, 5)) AS h2 | |
| SELECT | |
| h1, | |
| h2, | |
| arraySlice(arraySort(x -> sipHash64(x, 1), shingles), 1, 5) AS min_shingles1, | |
| arraySlice(arraySort(x -> sipHash64(x, 2), shingles), 1, 5) AS min_shingles2 | |
| Row 1: | |
| ────── | |
| h1: 4037745474664829908 | |
| h2: 17895668912250717102 | |
| min_shingles1: [['season','It','has'],['then','spread','quickly'],['islands','which','then'],['the','latest','occurrence'],['principally','on','the']] | |
| min_shingles2: [['palm','oil','industry'],['slash','and','burn'],['the','islands','which'],['the','palm','oil'],['been','caused','by']] | |
| 1 rows in set. Elapsed: 0.011 sec. |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment