feat(python): add native distribution and release infrastructure

- add the Rust-backed Python API with PyStemmer compatibility
- distribute standard compiled models as a separate Python package
- generate model artifacts during builds instead of storing them in Git
- add GitHub release and Pages-backed package index workflows
- add Python tests, benchmarks, documentation, and Gradle integration
- refresh the documentation site, branding, and language benchmarks
This commit is contained in:
2026-08-10 22:34:32 +02:00
parent b45e143c84
commit 5e3d3c7c7d
139 changed files with 11420 additions and 747 deletions

View File

@@ -35,8 +35,8 @@ Stemmer,Language,Dictionary model ID,Dictionary model version,Dictionary model S
"ENGLISH_RADIXOR","US_UK","us-uk-default","1.0.0","8c79122993499e437ea8b54b620832dca29019298f281c1f3132f4d1be885460","LOWERCASE_GROUPS_ONLY","ALL_CANDIDATES","374384","568441","228735","555084","13357","1355","584042","374506","311382","15","0","161561989623","15","161561989638","0.000000","0","311382","0.000000","0.999951829979","1.000000000000","0.999999999907","0.999999999907","0.999999999954","0.999961463612","0.999975914409","0.999990365625","0.999951829979","0.999975914699","0.999975914653","0.000000000093","","","","",""
"ENGLISH_SNOWBALL_ORIGINAL_PORTER","US_UK","us-uk-default","1.0.0","8c79122993499e437ea8b54b620832dca29019298f281c1f3132f4d1be885460","ALL_WORDS","PRIMARY_OUTPUT","396939","591946","250964","591946","0","1","591946","321092","284940","360538","28415","175199063592","360538","175199424130","0.000206","28415","313355","9.067990","0.441440296958","0.909320100206","0.999997942128","0.999997779945","0.954659021167","0.492078968883","0.594347503684","0.750277266077","0.422826769235","0.633569676567","0.633568843266","0.000002220055","","","","",""
"ENGLISH_SNOWBALL_ORIGINAL_PORTER","US_UK","us-uk-default","1.0.0","8c79122993499e437ea8b54b620832dca29019298f281c1f3132f4d1be885460","LOWERCASE_GROUPS_ONLY","PRIMARY_OUTPUT","374384","568441","228735","568441","0","1","568441","299877","283312","357325","28070","161561632313","357325","161561989638","0.000221","28070","311382","9.014651","0.442234838138","0.909853491852","0.999997788310","0.999997614573","0.954925640081","0.492899966248","0.595181398691","0.751026553880","0.423671353822","0.634325556555","0.634324660984","0.000002385427","","","","",""
"ENGLISH_SNOWBALL_PORTER2","US_UK","us-uk-default","1.0.0","8c79122993499e437ea8b54b620832dca29019298f281c1f3132f4d1be885460","ALL_WORDS","PRIMARY_OUTPUT","396939","591946","250964","591946","0","1","591946","318385","284971","371381","28384","175199052749","371381","175199424130","0.000212","28384","313355","9.058097","0.434174040759","0.909419029535","0.999997880238","0.999997718233","0.954708454887","0.484848557029","0.587746607996","0.746086443827","0.416176453407","0.628367833992","0.628366984426","0.000002281767","","","","",""
"ENGLISH_SNOWBALL_PORTER2","US_UK","us-uk-default","1.0.0","8c79122993499e437ea8b54b620832dca29019298f281c1f3132f4d1be885460","LOWERCASE_GROUPS_ONLY","PRIMARY_OUTPUT","374384","568441","228735","568441","0","1","568441","297220","283368","368027","28014","161561621611","368027","161561989638","0.000228","28014","311382","8.996666","0.435017155489","0.910033335260","0.999997722069","0.999997548679","0.955015528665","0.485724531207","0.588647215295","0.746914872138","0.417080138768","0.629190045142","0.629189132274","0.000002451321","","","","",""
"ENGLISH_SNOWBALL_PORTER2","US_UK","us-uk-default","1.0.0","8c79122993499e437ea8b54b620832dca29019298f281c1f3132f4d1be885460","ALL_WORDS","PRIMARY_OUTPUT","396939","591946","250964","591946","0","1","591946","318389","284986","371197","28369","175199052933","371197","175199424130","0.000212","28369","313355","9.053310","0.434308721805","0.909466898566","0.999997881289","0.999997719369","0.954732389927","0.484985638615","0.587880000578","0.746191747709","0.416310229172","0.628481826499","0.628480977278","0.000002280631","","","","",""
"ENGLISH_SNOWBALL_PORTER2","US_UK","us-uk-default","1.0.0","8c79122993499e437ea8b54b620832dca29019298f281c1f3132f4d1be885460","LOWERCASE_GROUPS_ONLY","PRIMARY_OUTPUT","374384","568441","228735","568441","0","1","568441","297224","283383","367843","27999","161561621795","367843","161561989638","0.000228","27999","311382","8.991849","0.435153080497","0.910081507602","0.999997723208","0.999997549911","0.955039615405","0.485862840613","0.588781726310","0.747020963182","0.417215208510","0.629304990872","0.629304078379","0.000002450089","","","","",""
"FINNISH_LUCENE_FINNISH_LIGHT_STEM_FILTER","FI_FI","fi-fi-default","1.0.0","ca2628b3db31fee92f1b612ebbbd5e956a6dbbfb10e721325e55ef528f26072f","ALL_WORDS","PRIMARY_OUTPUT","57027","1788784","292","1788784","0","1","1788784","439975","12317229","1508153","19148370","1599840231184","1508153","1599841739337","0.000094","19148370","31465599","60.854936","0.890914189568","0.391450644242","0.999999057311","0.999987088650","0.695724850776","0.709786610775","0.543915310644","0.440884276934","0.373546480243","0.590549687554","0.590545009664","0.000012911350","","","","",""
"FINNISH_LUCENE_FINNISH_LIGHT_STEM_FILTER","FI_FI","fi-fi-default","1.0.0","ca2628b3db31fee92f1b612ebbbd5e956a6dbbfb10e721325e55ef528f26072f","LOWERCASE_GROUPS_ONLY","PRIMARY_OUTPUT","54762","1734784","274","1734784","0","1","1734784","431848","11954192","1155011","18806691","1504704980042","1155011","1504706135053","0.000077","18806691","30760883","61.138333","0.911893118140","0.388616672675","0.999999232401","0.999986734091","0.694307952538","0.718420864905","0.544981470973","0.438999334093","0.374552942180","0.595295615141","0.595290947645","0.000013265909","","","","",""
"FINNISH_RADIXOR","FI_FI","fi-fi-default","1.0.0","ca2628b3db31fee92f1b612ebbbd5e956a6dbbfb10e721325e55ef528f26072f","ALL_WORDS","PRIMARY_OUTPUT","57027","1788784","292","1788784","0","1","1788784","69091","30511413","804","954186","1599841738533","804","1599841739337","0.000000","954186","31465599","3.032474","0.999973649899","0.969675263452","0.999999999497","0.999999403084","0.984837631475","0.993763441201","0.984591422195","0.975587162604","0.969650487220","0.984707932542","0.984707638627","0.000000596916","","","","",""
@@ -205,24 +205,26 @@ Stemmer,Language,Dictionary model ID,Dictionary model version,Dictionary model S
"RUSSIAN_RADIXOR","RU_RU","ru-ru-default","1.0.0","df7ea25e63a875eeec7a4185be685bd5372a3c568db85c34c44fdf5d8d980a40","LOWERCASE_GROUPS_ONLY","PRIMARY_OUTPUT","37297","758584","10","758584","0","1","758584","37282","12780071","0","255156","287711428009","0","287711428009","0.000000","255156","13035227","1.957434","1.000000000000","0.980425657336","1.000000000000","0.999999113193","0.990212828668","0.996022851412","0.990116093179","0.984278980143","0.980425657336","0.990164459742","0.990164020680","0.000000886807","","","","",""
"RUSSIAN_RADIXOR","RU_RU","ru-ru-default","1.0.0","df7ea25e63a875eeec7a4185be685bd5372a3c568db85c34c44fdf5d8d980a40","LOWERCASE_GROUPS_ONLY","ANY_CANDIDATE","37297","758584","10","749142","9442","4","768163","37306","","","","","0","287711428009","0.000000","0","13035227","0.000000","","","","","","","","","","","","","","","","",""
"RUSSIAN_RADIXOR","RU_RU","ru-ru-default","1.0.0","df7ea25e63a875eeec7a4185be685bd5372a3c568db85c34c44fdf5d8d980a40","LOWERCASE_GROUPS_ONLY","ALL_CANDIDATES","37297","758584","10","749142","9442","4","768163","37306","13035227","0","0","287711428009","0","287711428009","0.000000","0","13035227","0.000000","1.000000000000","1.000000000000","1.000000000000","1.000000000000","1.000000000000","1.000000000000","1.000000000000","1.000000000000","1.000000000000","1.000000000000","1.000000000000","0.000000000000","","","","",""
"SNOWBALL_DANISH_DIRECT","DA_DK","da-dk-default","1.0.0","3f7b670a0e7b872bda0381f5154ce058a4656297b39b7157b4ccf6560257cb90","ALL_WORDS","PRIMARY_OUTPUT","4179","27921","32","27921","0","1","27921","5553","78545","4795","11150","389682670","4795","389687465","0.001230","11150","89695","12.431016","0.942464602832","0.875689837784","0.999987695268","0.999959092010","0.937838766526","0.928307194100","0.907851012801","0.888276938388","0.831251984337","0.908463909669","0.908443737019","0.000040907990","","","","",""
"SNOWBALL_DANISH_DIRECT","DA_DK","da-dk-default","1.0.0","3f7b670a0e7b872bda0381f5154ce058a4656297b39b7157b4ccf6560257cb90","LOWERCASE_GROUPS_ONLY","PRIMARY_OUTPUT","4173","27875","32","27875","0","1","27875","5539","78440","4795","11100","388399540","4795","388404335","0.001235","11100","89540","12.396694","0.942392022587","0.876033057851","0.999987654618","0.999959085584","0.938010356234","0.928327968188","0.908001736362","0.888546539947","0.831504743732","0.908606936602","0.908586757624","0.000040914416","","","","",""
"SNOWBALL_CZECH_DIRECT","CS_CZ","cs-cz-default","1.0.0","62afdaa6dc7a721b54a0dc278a0c648a63ad52a34a412d27b5b52fbcde9c1ce4","ALL_WORDS","PRIMARY_OUTPUT","5113","51401","2","51401","0","1","51401","10932","172114","11935","128395","1320693256","11935","1320705191","0.000904","128395","300509","42.725842","0.935153138566","0.572741581783","0.999990963161","0.999893770330","0.786366272472","0.830101137739","0.710395865923","0.620863799839","0.550863514742","0.731847721723","0.731803909891","0.000106229670","","","","",""
"SNOWBALL_CZECH_DIRECT","CS_CZ","cs-cz-default","1.0.0","62afdaa6dc7a721b54a0dc278a0c648a63ad52a34a412d27b5b52fbcde9c1ce4","LOWERCASE_GROUPS_ONLY","PRIMARY_OUTPUT","5038","50697","2","50697","0","1","50697","10817","169464","11863","128023","1284758206","11863","1284770069","0.000923","128023","297487","43.034822","0.934576759115","0.569651783103","0.999990766441","0.999891145022","0.784821274772","0.828435805807","0.707848976847","0.617906692677","0.547806691450","0.729646021901","0.729601212980","0.000108854978","","","","",""
"SNOWBALL_DANISH_DIRECT","DA_DK","da-dk-default","1.0.0","3f7b670a0e7b872bda0381f5154ce058a4656297b39b7157b4ccf6560257cb90","ALL_WORDS","PRIMARY_OUTPUT","4179","27921","32","27921","0","1","27921","5409","79378","4816","10317","389682649","4816","389687465","0.001236","10317","89695","11.502313","0.942798774259","0.884976866046","0.999987641378","0.999961175252","0.942482253712","0.930637722143","0.912973218547","0.895966806178","0.839881072045","0.913430404878","0.913411201871","0.000038824748","","","","",""
"SNOWBALL_DANISH_DIRECT","DA_DK","da-dk-default","1.0.0","3f7b670a0e7b872bda0381f5154ce058a4656297b39b7157b4ccf6560257cb90","LOWERCASE_GROUPS_ONLY","PRIMARY_OUTPUT","4173","27875","32","27875","0","1","27875","5403","79223","4816","10317","388399519","4816","388404335","0.001240","10317","89540","11.522225","0.942693273361","0.884777752960","0.999987600550","0.999961047005","0.942382676755","0.930511444787","0.912817794779","0.895784477125","0.839618042308","0.913276538697","0.913257272617","0.000038952995","","","","",""
"SNOWBALL_DANISH_LUCENE_FILTER","DA_DK","da-dk-default","1.0.0","3f7b670a0e7b872bda0381f5154ce058a4656297b39b7157b4ccf6560257cb90","ALL_WORDS","PRIMARY_OUTPUT","4179","27921","32","27921","0","1","27921","5546","78557","4961","11138","389682504","4961","389687465","0.001273","11138","89695","12.417638","0.940599631217","0.875823624505","0.999987269285","0.999958696913","0.937905446895","0.926889068757","0.907056629699","0.888055112164","0.829920977011","0.907633945058","0.907613558620","0.000041303087","","","","",""
"SNOWBALL_DANISH_LUCENE_FILTER","DA_DK","da-dk-default","1.0.0","3f7b670a0e7b872bda0381f5154ce058a4656297b39b7157b4ccf6560257cb90","LOWERCASE_GROUPS_ONLY","PRIMARY_OUTPUT","4173","27875","32","27875","0","1","27875","5539","78440","4795","11100","388399540","4795","388404335","0.001235","11100","89540","12.396694","0.942392022587","0.876033057851","0.999987654618","0.999959085584","0.938010356234","0.928327968188","0.908001736362","0.888546539947","0.831504743732","0.908606936602","0.908586757624","0.000040914416","","","","",""
"SNOWBALL_DUTCH_DIRECT","NL_NL","nl-nl-default","1.0.0","c098034adc42da2ca3e419160e6dd2c2b3868f8af334303b3a191e09caadaf5e","ALL_WORDS","PRIMARY_OUTPUT","4992","26201","85","26201","0","1","26201","12051","29267","2987","35170","343165676","2987","343168663","0.000870","35170","64437","54.580443","0.907391331308","0.454195570868","0.999991295825","0.999888830652","0.727093433346","0.756436964017","0.605371751249","0.504599968276","0.434073920266","0.641975952605","0.641933549660","0.000111169348","","","","",""
"SNOWBALL_DUTCH_DIRECT","NL_NL","nl-nl-default","1.0.0","c098034adc42da2ca3e419160e6dd2c2b3868f8af334303b3a191e09caadaf5e","LOWERCASE_GROUPS_ONLY","PRIMARY_OUTPUT","4796","25402","84","25402","0","1","25402","11466","29053","2987","33965","322552096","2987","322555083","0.000926","33965","63018","53.897299","0.906772784020","0.461027008156","0.999990739566","0.999885462099","0.730508873861","0.759841613575","0.611268909508","0.511294841471","0.440163623968","0.646565343716","0.646521311443","0.000114537901","","","","",""
"SNOWBALL_DUTCH_LUCENE_FILTER","NL_NL","nl-nl-default","1.0.0","c098034adc42da2ca3e419160e6dd2c2b3868f8af334303b3a191e09caadaf5e","ALL_WORDS","PRIMARY_OUTPUT","4992","26201","85","26201","0","1","26201","14573","15204","759","49233","343167904","759","343168663","0.000221","49233","64437","76.404861","0.952452546514","0.235951394385","0.999997788260","0.999854349712","0.617974591322","0.592568341791","0.378208955224","0.277738198319","0.233204491073","0.474059602198","0.474021680915","0.000145650288","","","","",""
"SNOWBALL_DUTCH_LUCENE_FILTER","NL_NL","nl-nl-default","1.0.0","c098034adc42da2ca3e419160e6dd2c2b3868f8af334303b3a191e09caadaf5e","LOWERCASE_GROUPS_ONLY","PRIMARY_OUTPUT","4796","25402","84","25402","0","1","25402","14116","14874","715","48144","322554368","715","322555083","0.000222","48144","63018","76.397220","0.954134325486","0.236027801581","0.999997783324","0.999848554685","0.618012792452","0.593185189912","0.378439579172","0.277851461363","0.233379881694","0.474554767395","0.474515425112","0.000151445315","","","","",""
"SNOWBALL_FINNISH_DIRECT","FI_FI","fi-fi-default","1.0.0","ca2628b3db31fee92f1b612ebbbd5e956a6dbbfb10e721325e55ef528f26072f","ALL_WORDS","PRIMARY_OUTPUT","57027","1788784","292","1788784","0","1","1788784","381483","15082807","952306","16382792","1599840787031","952306","1599841739337","0.000060","16382792","31465599","52.065724","0.940611207417","0.479342757784","0.999999404750","0.999989164705","0.739671081267","0.788799811426","0.635056038739","0.531468350160","0.465261620083","0.671472389727","0.671468317739","0.000010835295","","","","",""
"SNOWBALL_FINNISH_DIRECT","FI_FI","fi-fi-default","1.0.0","ca2628b3db31fee92f1b612ebbbd5e956a6dbbfb10e721325e55ef528f26072f","LOWERCASE_GROUPS_ONLY","PRIMARY_OUTPUT","54762","1734784","274","1734784","0","1","1734784","372232","14663371","936765","16097512","1504705198288","936765","1504706135053","0.000062","16097512","30760883","52.331112","0.939951485038","0.476688884386","0.999999377443","0.999988679564","0.738344130915","0.786987247415","0.632573283171","0.528815026735","0.462601231486","0.669376145960","0.669371899615","0.000011320436","","","","",""
"SNOWBALL_FINNISH_DIRECT","FI_FI","fi-fi-default","1.0.0","ca2628b3db31fee92f1b612ebbbd5e956a6dbbfb10e721325e55ef528f26072f","ALL_WORDS","PRIMARY_OUTPUT","57027","1788784","292","1788784","0","1","1788784","381016","15095314","952479","16370285","1599840786858","952479","1599841739337","0.000060","16370285","31465599","52.025976","0.940647352567","0.479740239491","0.999999404642","0.999989172414","0.739869822067","0.789035310423","0.635413022080","0.531861528280","0.465644940456","0.671763638639","0.671759568086","0.000010827586","","","","",""
"SNOWBALL_FINNISH_DIRECT","FI_FI","fi-fi-default","1.0.0","ca2628b3db31fee92f1b612ebbbd5e956a6dbbfb10e721325e55ef528f26072f","LOWERCASE_GROUPS_ONLY","PRIMARY_OUTPUT","54762","1734784","274","1734784","0","1","1734784","371779","14675605","936938","16085278","1504705198115","936938","1504706135053","0.000062","16085278","30760883","52.291340","0.939988123652","0.477086597287","0.999999377328","0.999988687580","0.738542987307","0.787224487482","0.632931670824","0.529208871663","0.462984663835","0.669668377186","0.669664132316","0.000011312420","","","","",""
"SNOWBALL_FINNISH_LUCENE_FILTER","FI_FI","fi-fi-default","1.0.0","ca2628b3db31fee92f1b612ebbbd5e956a6dbbfb10e721325e55ef528f26072f","ALL_WORDS","PRIMARY_OUTPUT","57027","1788784","292","1788784","0","1","1788784","377778","15121052","1288634","16344547","1599840450703","1288634","1599841739337","0.000081","16344547","31465599","51.944179","0.921471136011","0.480558212161","0.999999194524","0.999988978388","0.740278703342","0.778598131291","0.631685095974","0.531413183368","0.461651842069","0.665447610018","0.665443363449","0.000011021612","","","","",""
"SNOWBALL_FINNISH_LUCENE_FILTER","FI_FI","fi-fi-default","1.0.0","ca2628b3db31fee92f1b612ebbbd5e956a6dbbfb10e721325e55ef528f26072f","LOWERCASE_GROUPS_ONLY","PRIMARY_OUTPUT","54762","1734784","274","1734784","0","1","1734784","372232","14663371","936765","16097512","1504705198288","936765","1504706135053","0.000062","16097512","30760883","52.331112","0.939951485038","0.476688884386","0.999999377443","0.999988679564","0.738344130915","0.786987247415","0.632573283171","0.528815026735","0.462601231486","0.669376145960","0.669371899615","0.000011320436","","","","",""
"SNOWBALL_FRENCH_DIRECT","FR_FR","fr-fr-default","1.0.0","a988658758952fd599dc7360e0234178a6d65ac46e5cedc7dcd325a7cb7e71d9","ALL_WORDS","PRIMARY_OUTPUT","59240","404011","2301","404011","0","1","404011","85627","3744838","1092238","1625361","81605779618","1092238","81606871856","0.001338","1625361","5370199","30.266309","0.774194575401","0.697336914330","0.999986615858","0.999966701086","0.848661765094","0.757496924470","0.733758618240","0.711462917671","0.579477680015","0.734761496202","0.734744993787","0.000033298914","","","","",""
"SNOWBALL_FRENCH_DIRECT","FR_FR","fr-fr-default","1.0.0","a988658758952fd599dc7360e0234178a6d65ac46e5cedc7dcd325a7cb7e71d9","LOWERCASE_GROUPS_ONLY","PRIMARY_OUTPUT","57698","400712","2133","400712","0","1","400712","84526","3736871","1088903","1619380","80278407962","1088903","80279496865","0.001356","1619380","5356251","30.233460","0.774356818202","0.697665400669","0.999986436101","0.999966266576","0.848825918385","0.757698693319","0.734013322497","0.711763857056","0.579795455624","0.735011537210","0.734994818860","0.000033733424","","","","",""
"SNOWBALL_FRENCH_LUCENE_FILTER","FR_FR","fr-fr-default","1.0.0","a988658758952fd599dc7360e0234178a6d65ac46e5cedc7dcd325a7cb7e71d9","ALL_WORDS","PRIMARY_OUTPUT","59240","404011","2301","404011","0","1","404011","85202","3742072","1097843","1628127","81605774013","1097843","81606871856","0.001345","1628127","5370199","30.317815","0.773168950281","0.696821849619","0.999986547175","0.999966598516","0.848404198397","0.756589837411","0.733012775372","0.710860736247","0.578547882033","0.734003418250","0.733986862867","0.000033401484","","","","",""
"SNOWBALL_FRENCH_LUCENE_FILTER","FR_FR","fr-fr-default","1.0.0","a988658758952fd599dc7360e0234178a6d65ac46e5cedc7dcd325a7cb7e71d9","LOWERCASE_GROUPS_ONLY","PRIMARY_OUTPUT","57698","400712","2133","400712","0","1","400712","84810","3734232","1086494","1622019","80278410371","1086494","80279496865","0.001353","1622019","5356251","30.282729","0.774620254294","0.697172705312","0.999986466109","0.999966263711","0.848579585710","0.757784104203","0.733858787339","0.711398006457","0.579602638316","0.734876927298","0.734860210439","0.000033736289","","","","",""
"SNOWBALL_GERMAN_DIRECT","DE_DE","de-de-default","1.0.0","cbfa038122823f02e4bdb54b0035492c356b6ecd80f11eb11290d7a7248a59f5","ALL_WORDS","PRIMARY_OUTPUT","54092","277266","1474","277266","0","1","277266","81649","742376","65811","602476","38436668082","65811","38436733893","0.000171","602476","1344852","44.798684","0.918569588474","0.552013158325","0.999998287810","0.999982613933","0.776005723068","0.810879063265","0.689607573295","0.599890587538","0.526260347085","0.712083211201","0.712076031428","0.000017386067","","","","",""
"SNOWBALL_GERMAN_DIRECT","DE_DE","de-de-default","1.0.0","cbfa038122823f02e4bdb54b0035492c356b6ecd80f11eb11290d7a7248a59f5","LOWERCASE_GROUPS_ONLY","PRIMARY_OUTPUT","16007","145574","228","145574","0","1","145574","37843","506459","41477","351958","10594922057","41477","10594963534","0.000391","351958","858417","41.000819","0.924303203294","0.589991810507","0.999996085215","0.999962868855","0.794993947861","0.830216831177","0.720244490537","0.635998708058","0.562798507380","0.738465517386","0.738449797528","0.000037131145","","","","",""
"SNOWBALL_GERMAN_DIRECT","DE_DE","de-de-default","1.0.0","cbfa038122823f02e4bdb54b0035492c356b6ecd80f11eb11290d7a7248a59f5","ALL_WORDS","PRIMARY_OUTPUT","54092","277266","1474","277266","0","1","277266","81641","742393","65811","602459","38436668082","65811","38436733893","0.000171","602459","1344852","44.797420","0.918571301305","0.552025799121","0.999998287810","0.999982614376","0.776012043466","0.810885586285","0.689617919831","0.599902676509","0.526272398156","0.712092028219","0.712084848565","0.000017385624","","","","",""
"SNOWBALL_GERMAN_DIRECT","DE_DE","de-de-default","1.0.0","cbfa038122823f02e4bdb54b0035492c356b6ecd80f11eb11290d7a7248a59f5","LOWERCASE_GROUPS_ONLY","PRIMARY_OUTPUT","16007","145574","228","145574","0","1","145574","37842","506464","41477","351953","10594922057","41477","10594963534","0.000391","351953","858417","41.000236","0.924303894032","0.589997635182","0.999996085215","0.999962869327","0.794996860199","0.830219583690","0.720249040429","0.636004188257","0.562804063590","0.738469438547","0.738453718829","0.000037130673","","","","",""
"SNOWBALL_GERMAN_LUCENE_FILTER","DE_DE","de-de-default","1.0.0","cbfa038122823f02e4bdb54b0035492c356b6ecd80f11eb11290d7a7248a59f5","ALL_WORDS","PRIMARY_OUTPUT","54092","277266","1474","277266","0","1","277266","86669","723725","142783","621127","38436591110","142783","38436733893","0.000371","621127","1344852","46.185528","0.835220217240","0.538144717783","0.999996285246","0.999980126218","0.769070501515","0.752174652309","0.654551949931","0.579358576068","0.486493662760","0.670424751999","0.670415952491","0.000019873782","","","","",""
"SNOWBALL_GERMAN_LUCENE_FILTER","DE_DE","de-de-default","1.0.0","cbfa038122823f02e4bdb54b0035492c356b6ecd80f11eb11290d7a7248a59f5","LOWERCASE_GROUPS_ONLY","PRIMARY_OUTPUT","16007","145574","228","145574","0","1","145574","46077","471644","34482","386773","10594929052","34482","10594963534","0.000325","386773","858417","45.056540","0.931870719939","0.549434598802","0.999996745435","0.999960243292","0.774715672118","0.817996747049","0.691284921032","0.598564290417","0.528216517210","0.715543160924","0.715527026594","0.000039756708","","","","",""
"SNOWBALL_HUNGARIAN_DIRECT","HU_HU","hu-hu-default","1.0.0","359d46a01d751ec823705ad7f3dd1cc8f6663feb1a9d13cb04d0c6fb51ab646e","ALL_WORDS","PRIMARY_OUTPUT","19406","910688","1","910688","0","1","910688","116105","14275129","1281527","7842726","414652461946","1281527","414653743473","0.000309","7842726","22117855","35.458800","0.917621949087","0.645411998587","0.999996909404","0.999977996662","0.822704453996","0.846239680964","0.757813631609","0.686119053091","0.610064359819","0.769574048489","0.769564274829","0.000022003338","","","","",""
@@ -241,6 +243,10 @@ Stemmer,Language,Dictionary model ID,Dictionary model version,Dictionary model S
"SNOWBALL_NORWEGIAN_NYNORSK_DIRECT","NN_NO","nn-no-default","1.0.0","900cf2005605aea2a3d8d731ec0b0c1f47fb4469b4ba6b9134145d4d026a0398","LOWERCASE_GROUPS_ONLY","PRIMARY_OUTPUT","4681","16906","23","16906","0","1","16906","6120","20847","1201","7458","142868459","1201","142869660","0.000841","7458","28305","26.348702","0.945527939042","0.736512983572","0.999991593737","0.999939404316","0.868252288654","0.894744070663","0.828034079399","0.770581364403","0.706534264217","0.834502009245","0.834474211808","0.000060595684","","","","",""
"SNOWBALL_NORWEGIAN_NYNORSK_LUCENE_FILTER","NN_NO","nn-no-default","1.0.0","900cf2005605aea2a3d8d731ec0b0c1f47fb4469b4ba6b9134145d4d026a0398","ALL_WORDS","PRIMARY_OUTPUT","4688","16937","23","16937","0","1","16937","6144","20854","1222","7508","143392932","1222","143394154","0.000852","7508","28362","26.472040","0.944645769161","0.735279599464","0.999991478035","0.999939130896","0.867635538749","0.893747964274","0.826916213966","0.769384020542","0.704908058410","0.833413920441","0.833385994629","0.000060869104","","","","",""
"SNOWBALL_NORWEGIAN_NYNORSK_LUCENE_FILTER","NN_NO","nn-no-default","1.0.0","900cf2005605aea2a3d8d731ec0b0c1f47fb4469b4ba6b9134145d4d026a0398","LOWERCASE_GROUPS_ONLY","PRIMARY_OUTPUT","4681","16906","23","16906","0","1","16906","6130","20824","1201","7481","142868459","1201","142869660","0.000841","7481","28305","26.429959","0.945471055619","0.735700406289","0.999991593737","0.999939243362","0.867846000013","0.894463296250","0.827498509835","0.769862102111","0.705754761743","0.834016450529","0.833988591624","0.000060756638","","","","",""
"SNOWBALL_PERSIAN_DIRECT","FA_IR","fa-ir-default","1.0.0","b29a0d168a6a97f980666aa40b74a0edd8b6be4ab3320a7abfbb76b3529f4ea1","ALL_WORDS","PRIMARY_OUTPUT","69","3544","0","3544","0","1","3544","2029","6748","79","89296","6182073","79","6182152","0.001278","89296","96044","92.974054","0.988428299399","0.070259464412","0.999987221278","0.985764222716","0.535123342845","0.273526169012","0.131193436440","0.086290898024","0.070201720712","0.263526930171","0.261598150185","0.014235777284","","","","",""
"SNOWBALL_PERSIAN_DIRECT","FA_IR","fa-ir-default","1.0.0","b29a0d168a6a97f980666aa40b74a0edd8b6be4ab3320a7abfbb76b3529f4ea1","LOWERCASE_GROUPS_ONLY","PRIMARY_OUTPUT","69","3544","0","3544","0","1","3544","2029","6748","79","89296","6182073","79","6182152","0.001278","89296","96044","92.974054","0.988428299399","0.070259464412","0.999987221278","0.985764222716","0.535123342845","0.273526169012","0.131193436440","0.086290898024","0.070201720712","0.263526930171","0.261598150185","0.014235777284","","","","",""
"SNOWBALL_POLISH_DIRECT","PL_PL","pl-pl-unimorph","1.0.0","8191ed727097839cc808cbc5c56a1bd78b3c851e7733ad226ad9a51519a54721","ALL_WORDS","PRIMARY_OUTPUT","9990","120867","1","120867","0","1","120867","19265","723037","70656","394036","7303167682","70656","7303238338","0.000967","394036","1117073","35.273970","0.910978174181","0.647260295433","0.999990325388","0.999936381518","0.823625310410","0.842338201869","0.756803292502","0.687038256475","0.608755869394","0.767880200391","0.767851723211","0.000063618482","","","","",""
"SNOWBALL_POLISH_DIRECT","PL_PL","pl-pl-unimorph","1.0.0","8191ed727097839cc808cbc5c56a1bd78b3c851e7733ad226ad9a51519a54721","LOWERCASE_GROUPS_ONLY","PRIMARY_OUTPUT","9846","119451","1","119451","0","1","119451","18927","718592","70647","392165","7133029571","70647","7133100218","0.000990","392165","1110757","35.306102","0.910487190826","0.646938979453","0.999990095891","0.999935127795","0.823464537672","0.841893538764","0.756414224030","0.686692785364","0.608252553741","0.767482673444","0.767453627968","0.000064872205","","","","",""
"SNOWBALL_PORTUGUESE_DIRECT","PT_PT","pt-pt-default","1.0.0","7a035ff330a6f0548f446cd0d6617bc1cf4751292125a3564d3a255c5d6f516d","ALL_WORDS","PRIMARY_OUTPUT","4001","211091","0","211091","0","1","211091","11315","4816198","146201","670154","22273967042","146201","22274113243","0.000656","670154","5486352","12.214929","0.970538241685","0.877850710272","0.999993436282","0.999963358632","0.938922073277","0.950467296507","0.921870566157","0.894944355740","0.855064834721","0.923031789707","0.923014032222","0.000036641368","","","","",""
"SNOWBALL_PORTUGUESE_DIRECT","PT_PT","pt-pt-default","1.0.0","7a035ff330a6f0548f446cd0d6617bc1cf4751292125a3564d3a255c5d6f516d","LOWERCASE_GROUPS_ONLY","PRIMARY_OUTPUT","4001","211091","0","211091","0","1","211091","11315","4816198","146201","670154","22273967042","146201","22274113243","0.000656","670154","5486352","12.214929","0.970538241685","0.877850710272","0.999993436282","0.999963358632","0.938922073277","0.950467296507","0.921870566157","0.894944355740","0.855064834721","0.923031789707","0.923014032222","0.000036641368","","","","",""
"SNOWBALL_PORTUGUESE_LUCENE_FILTER","PT_PT","pt-pt-default","1.0.0","7a035ff330a6f0548f446cd0d6617bc1cf4751292125a3564d3a255c5d6f516d","ALL_WORDS","PRIMARY_OUTPUT","4001","211091","0","211091","0","1","211091","11315","4816198","146201","670154","22273967042","146201","22274113243","0.000656","670154","5486352","12.214929","0.970538241685","0.877850710272","0.999993436282","0.999963358632","0.938922073277","0.950467296507","0.921870566157","0.894944355740","0.855064834721","0.923031789707","0.923014032222","0.000036641368","","","","",""
1 Stemmer Language Dictionary model ID Dictionary model version Dictionary model SHA-256 Dictionary mode Output policy Applied dictionary rows Processed word forms Singleton dictionary rows Forms with one candidate Forms with multiple candidates Maximum candidates for one form Total candidate assignments Distinct output stems True-positive pairs False-positive pairs False-negative pairs True-negative pairs Over-stemming error pairs Over-stemming possible pairs Over-stemming percentage Under-stemming error pairs Under-stemming possible pairs Under-stemming percentage Pairwise precision Pairwise recall Pairwise specificity Pairwise accuracy Balanced accuracy Pairwise F0.5 Pairwise F1 Pairwise F2 Jaccard index Fowlkes-Mallows index Matthews correlation coefficient Pairwise error rate Adjusted Rand Index Homogeneity Completeness V-measure Normalized mutual information
35 ENGLISH_RADIXOR US_UK us-uk-default 1.0.0 8c79122993499e437ea8b54b620832dca29019298f281c1f3132f4d1be885460 LOWERCASE_GROUPS_ONLY ALL_CANDIDATES 374384 568441 228735 555084 13357 1355 584042 374506 311382 15 0 161561989623 15 161561989638 0.000000 0 311382 0.000000 0.999951829979 1.000000000000 0.999999999907 0.999999999907 0.999999999954 0.999961463612 0.999975914409 0.999990365625 0.999951829979 0.999975914699 0.999975914653 0.000000000093
36 ENGLISH_SNOWBALL_ORIGINAL_PORTER US_UK us-uk-default 1.0.0 8c79122993499e437ea8b54b620832dca29019298f281c1f3132f4d1be885460 ALL_WORDS PRIMARY_OUTPUT 396939 591946 250964 591946 0 1 591946 321092 284940 360538 28415 175199063592 360538 175199424130 0.000206 28415 313355 9.067990 0.441440296958 0.909320100206 0.999997942128 0.999997779945 0.954659021167 0.492078968883 0.594347503684 0.750277266077 0.422826769235 0.633569676567 0.633568843266 0.000002220055
37 ENGLISH_SNOWBALL_ORIGINAL_PORTER US_UK us-uk-default 1.0.0 8c79122993499e437ea8b54b620832dca29019298f281c1f3132f4d1be885460 LOWERCASE_GROUPS_ONLY PRIMARY_OUTPUT 374384 568441 228735 568441 0 1 568441 299877 283312 357325 28070 161561632313 357325 161561989638 0.000221 28070 311382 9.014651 0.442234838138 0.909853491852 0.999997788310 0.999997614573 0.954925640081 0.492899966248 0.595181398691 0.751026553880 0.423671353822 0.634325556555 0.634324660984 0.000002385427
38 ENGLISH_SNOWBALL_PORTER2 US_UK us-uk-default 1.0.0 8c79122993499e437ea8b54b620832dca29019298f281c1f3132f4d1be885460 ALL_WORDS PRIMARY_OUTPUT 396939 591946 250964 591946 0 1 591946 318385 318389 284971 284986 371381 371197 28384 28369 175199052749 175199052933 371381 371197 175199424130 0.000212 28384 28369 313355 9.058097 9.053310 0.434174040759 0.434308721805 0.909419029535 0.909466898566 0.999997880238 0.999997881289 0.999997718233 0.999997719369 0.954708454887 0.954732389927 0.484848557029 0.484985638615 0.587746607996 0.587880000578 0.746086443827 0.746191747709 0.416176453407 0.416310229172 0.628367833992 0.628481826499 0.628366984426 0.628480977278 0.000002281767 0.000002280631
39 ENGLISH_SNOWBALL_PORTER2 US_UK us-uk-default 1.0.0 8c79122993499e437ea8b54b620832dca29019298f281c1f3132f4d1be885460 LOWERCASE_GROUPS_ONLY PRIMARY_OUTPUT 374384 568441 228735 568441 0 1 568441 297220 297224 283368 283383 368027 367843 28014 27999 161561621611 161561621795 368027 367843 161561989638 0.000228 28014 27999 311382 8.996666 8.991849 0.435017155489 0.435153080497 0.910033335260 0.910081507602 0.999997722069 0.999997723208 0.999997548679 0.999997549911 0.955015528665 0.955039615405 0.485724531207 0.485862840613 0.588647215295 0.588781726310 0.746914872138 0.747020963182 0.417080138768 0.417215208510 0.629190045142 0.629304990872 0.629189132274 0.629304078379 0.000002451321 0.000002450089
40 FINNISH_LUCENE_FINNISH_LIGHT_STEM_FILTER FI_FI fi-fi-default 1.0.0 ca2628b3db31fee92f1b612ebbbd5e956a6dbbfb10e721325e55ef528f26072f ALL_WORDS PRIMARY_OUTPUT 57027 1788784 292 1788784 0 1 1788784 439975 12317229 1508153 19148370 1599840231184 1508153 1599841739337 0.000094 19148370 31465599 60.854936 0.890914189568 0.391450644242 0.999999057311 0.999987088650 0.695724850776 0.709786610775 0.543915310644 0.440884276934 0.373546480243 0.590549687554 0.590545009664 0.000012911350
41 FINNISH_LUCENE_FINNISH_LIGHT_STEM_FILTER FI_FI fi-fi-default 1.0.0 ca2628b3db31fee92f1b612ebbbd5e956a6dbbfb10e721325e55ef528f26072f LOWERCASE_GROUPS_ONLY PRIMARY_OUTPUT 54762 1734784 274 1734784 0 1 1734784 431848 11954192 1155011 18806691 1504704980042 1155011 1504706135053 0.000077 18806691 30760883 61.138333 0.911893118140 0.388616672675 0.999999232401 0.999986734091 0.694307952538 0.718420864905 0.544981470973 0.438999334093 0.374552942180 0.595295615141 0.595290947645 0.000013265909
42 FINNISH_RADIXOR FI_FI fi-fi-default 1.0.0 ca2628b3db31fee92f1b612ebbbd5e956a6dbbfb10e721325e55ef528f26072f ALL_WORDS PRIMARY_OUTPUT 57027 1788784 292 1788784 0 1 1788784 69091 30511413 804 954186 1599841738533 804 1599841739337 0.000000 954186 31465599 3.032474 0.999973649899 0.969675263452 0.999999999497 0.999999403084 0.984837631475 0.993763441201 0.984591422195 0.975587162604 0.969650487220 0.984707932542 0.984707638627 0.000000596916
205 RUSSIAN_RADIXOR RU_RU ru-ru-default 1.0.0 df7ea25e63a875eeec7a4185be685bd5372a3c568db85c34c44fdf5d8d980a40 LOWERCASE_GROUPS_ONLY PRIMARY_OUTPUT 37297 758584 10 758584 0 1 758584 37282 12780071 0 255156 287711428009 0 287711428009 0.000000 255156 13035227 1.957434 1.000000000000 0.980425657336 1.000000000000 0.999999113193 0.990212828668 0.996022851412 0.990116093179 0.984278980143 0.980425657336 0.990164459742 0.990164020680 0.000000886807
206 RUSSIAN_RADIXOR RU_RU ru-ru-default 1.0.0 df7ea25e63a875eeec7a4185be685bd5372a3c568db85c34c44fdf5d8d980a40 LOWERCASE_GROUPS_ONLY ANY_CANDIDATE 37297 758584 10 749142 9442 4 768163 37306 0 287711428009 0.000000 0 13035227 0.000000
207 RUSSIAN_RADIXOR RU_RU ru-ru-default 1.0.0 df7ea25e63a875eeec7a4185be685bd5372a3c568db85c34c44fdf5d8d980a40 LOWERCASE_GROUPS_ONLY ALL_CANDIDATES 37297 758584 10 749142 9442 4 768163 37306 13035227 0 0 287711428009 0 287711428009 0.000000 0 13035227 0.000000 1.000000000000 1.000000000000 1.000000000000 1.000000000000 1.000000000000 1.000000000000 1.000000000000 1.000000000000 1.000000000000 1.000000000000 1.000000000000 0.000000000000
208 SNOWBALL_DANISH_DIRECT SNOWBALL_CZECH_DIRECT DA_DK CS_CZ da-dk-default cs-cz-default 1.0.0 3f7b670a0e7b872bda0381f5154ce058a4656297b39b7157b4ccf6560257cb90 62afdaa6dc7a721b54a0dc278a0c648a63ad52a34a412d27b5b52fbcde9c1ce4 ALL_WORDS PRIMARY_OUTPUT 4179 5113 27921 51401 32 2 27921 51401 0 1 27921 51401 5553 10932 78545 172114 4795 11935 11150 128395 389682670 1320693256 4795 11935 389687465 1320705191 0.001230 0.000904 11150 128395 89695 300509 12.431016 42.725842 0.942464602832 0.935153138566 0.875689837784 0.572741581783 0.999987695268 0.999990963161 0.999959092010 0.999893770330 0.937838766526 0.786366272472 0.928307194100 0.830101137739 0.907851012801 0.710395865923 0.888276938388 0.620863799839 0.831251984337 0.550863514742 0.908463909669 0.731847721723 0.908443737019 0.731803909891 0.000040907990 0.000106229670
209 SNOWBALL_DANISH_DIRECT SNOWBALL_CZECH_DIRECT DA_DK CS_CZ da-dk-default cs-cz-default 1.0.0 3f7b670a0e7b872bda0381f5154ce058a4656297b39b7157b4ccf6560257cb90 62afdaa6dc7a721b54a0dc278a0c648a63ad52a34a412d27b5b52fbcde9c1ce4 LOWERCASE_GROUPS_ONLY PRIMARY_OUTPUT 4173 5038 27875 50697 32 2 27875 50697 0 1 27875 50697 5539 10817 78440 169464 4795 11863 11100 128023 388399540 1284758206 4795 11863 388404335 1284770069 0.001235 0.000923 11100 128023 89540 297487 12.396694 43.034822 0.942392022587 0.934576759115 0.876033057851 0.569651783103 0.999987654618 0.999990766441 0.999959085584 0.999891145022 0.938010356234 0.784821274772 0.928327968188 0.828435805807 0.908001736362 0.707848976847 0.888546539947 0.617906692677 0.831504743732 0.547806691450 0.908606936602 0.729646021901 0.908586757624 0.729601212980 0.000040914416 0.000108854978
210 SNOWBALL_DANISH_DIRECT DA_DK da-dk-default 1.0.0 3f7b670a0e7b872bda0381f5154ce058a4656297b39b7157b4ccf6560257cb90 ALL_WORDS PRIMARY_OUTPUT 4179 27921 32 27921 0 1 27921 5409 79378 4816 10317 389682649 4816 389687465 0.001236 10317 89695 11.502313 0.942798774259 0.884976866046 0.999987641378 0.999961175252 0.942482253712 0.930637722143 0.912973218547 0.895966806178 0.839881072045 0.913430404878 0.913411201871 0.000038824748
211 SNOWBALL_DANISH_DIRECT DA_DK da-dk-default 1.0.0 3f7b670a0e7b872bda0381f5154ce058a4656297b39b7157b4ccf6560257cb90 LOWERCASE_GROUPS_ONLY PRIMARY_OUTPUT 4173 27875 32 27875 0 1 27875 5403 79223 4816 10317 388399519 4816 388404335 0.001240 10317 89540 11.522225 0.942693273361 0.884777752960 0.999987600550 0.999961047005 0.942382676755 0.930511444787 0.912817794779 0.895784477125 0.839618042308 0.913276538697 0.913257272617 0.000038952995
212 SNOWBALL_DANISH_LUCENE_FILTER DA_DK da-dk-default 1.0.0 3f7b670a0e7b872bda0381f5154ce058a4656297b39b7157b4ccf6560257cb90 ALL_WORDS PRIMARY_OUTPUT 4179 27921 32 27921 0 1 27921 5546 78557 4961 11138 389682504 4961 389687465 0.001273 11138 89695 12.417638 0.940599631217 0.875823624505 0.999987269285 0.999958696913 0.937905446895 0.926889068757 0.907056629699 0.888055112164 0.829920977011 0.907633945058 0.907613558620 0.000041303087
213 SNOWBALL_DANISH_LUCENE_FILTER DA_DK da-dk-default 1.0.0 3f7b670a0e7b872bda0381f5154ce058a4656297b39b7157b4ccf6560257cb90 LOWERCASE_GROUPS_ONLY PRIMARY_OUTPUT 4173 27875 32 27875 0 1 27875 5539 78440 4795 11100 388399540 4795 388404335 0.001235 11100 89540 12.396694 0.942392022587 0.876033057851 0.999987654618 0.999959085584 0.938010356234 0.928327968188 0.908001736362 0.888546539947 0.831504743732 0.908606936602 0.908586757624 0.000040914416
214 SNOWBALL_DUTCH_DIRECT NL_NL nl-nl-default 1.0.0 c098034adc42da2ca3e419160e6dd2c2b3868f8af334303b3a191e09caadaf5e ALL_WORDS PRIMARY_OUTPUT 4992 26201 85 26201 0 1 26201 12051 29267 2987 35170 343165676 2987 343168663 0.000870 35170 64437 54.580443 0.907391331308 0.454195570868 0.999991295825 0.999888830652 0.727093433346 0.756436964017 0.605371751249 0.504599968276 0.434073920266 0.641975952605 0.641933549660 0.000111169348
215 SNOWBALL_DUTCH_DIRECT NL_NL nl-nl-default 1.0.0 c098034adc42da2ca3e419160e6dd2c2b3868f8af334303b3a191e09caadaf5e LOWERCASE_GROUPS_ONLY PRIMARY_OUTPUT 4796 25402 84 25402 0 1 25402 11466 29053 2987 33965 322552096 2987 322555083 0.000926 33965 63018 53.897299 0.906772784020 0.461027008156 0.999990739566 0.999885462099 0.730508873861 0.759841613575 0.611268909508 0.511294841471 0.440163623968 0.646565343716 0.646521311443 0.000114537901
216 SNOWBALL_DUTCH_LUCENE_FILTER NL_NL nl-nl-default 1.0.0 c098034adc42da2ca3e419160e6dd2c2b3868f8af334303b3a191e09caadaf5e ALL_WORDS PRIMARY_OUTPUT 4992 26201 85 26201 0 1 26201 14573 15204 759 49233 343167904 759 343168663 0.000221 49233 64437 76.404861 0.952452546514 0.235951394385 0.999997788260 0.999854349712 0.617974591322 0.592568341791 0.378208955224 0.277738198319 0.233204491073 0.474059602198 0.474021680915 0.000145650288
217 SNOWBALL_DUTCH_LUCENE_FILTER NL_NL nl-nl-default 1.0.0 c098034adc42da2ca3e419160e6dd2c2b3868f8af334303b3a191e09caadaf5e LOWERCASE_GROUPS_ONLY PRIMARY_OUTPUT 4796 25402 84 25402 0 1 25402 14116 14874 715 48144 322554368 715 322555083 0.000222 48144 63018 76.397220 0.954134325486 0.236027801581 0.999997783324 0.999848554685 0.618012792452 0.593185189912 0.378439579172 0.277851461363 0.233379881694 0.474554767395 0.474515425112 0.000151445315
218 SNOWBALL_FINNISH_DIRECT FI_FI fi-fi-default 1.0.0 ca2628b3db31fee92f1b612ebbbd5e956a6dbbfb10e721325e55ef528f26072f ALL_WORDS PRIMARY_OUTPUT 57027 1788784 292 1788784 0 1 1788784 381483 381016 15082807 15095314 952306 952479 16382792 16370285 1599840787031 1599840786858 952306 952479 1599841739337 0.000060 16382792 16370285 31465599 52.065724 52.025976 0.940611207417 0.940647352567 0.479342757784 0.479740239491 0.999999404750 0.999999404642 0.999989164705 0.999989172414 0.739671081267 0.739869822067 0.788799811426 0.789035310423 0.635056038739 0.635413022080 0.531468350160 0.531861528280 0.465261620083 0.465644940456 0.671472389727 0.671763638639 0.671468317739 0.671759568086 0.000010835295 0.000010827586
219 SNOWBALL_FINNISH_DIRECT FI_FI fi-fi-default 1.0.0 ca2628b3db31fee92f1b612ebbbd5e956a6dbbfb10e721325e55ef528f26072f LOWERCASE_GROUPS_ONLY PRIMARY_OUTPUT 54762 1734784 274 1734784 0 1 1734784 372232 371779 14663371 14675605 936765 936938 16097512 16085278 1504705198288 1504705198115 936765 936938 1504706135053 0.000062 16097512 16085278 30760883 52.331112 52.291340 0.939951485038 0.939988123652 0.476688884386 0.477086597287 0.999999377443 0.999999377328 0.999988679564 0.999988687580 0.738344130915 0.738542987307 0.786987247415 0.787224487482 0.632573283171 0.632931670824 0.528815026735 0.529208871663 0.462601231486 0.462984663835 0.669376145960 0.669668377186 0.669371899615 0.669664132316 0.000011320436 0.000011312420
220 SNOWBALL_FINNISH_LUCENE_FILTER FI_FI fi-fi-default 1.0.0 ca2628b3db31fee92f1b612ebbbd5e956a6dbbfb10e721325e55ef528f26072f ALL_WORDS PRIMARY_OUTPUT 57027 1788784 292 1788784 0 1 1788784 377778 15121052 1288634 16344547 1599840450703 1288634 1599841739337 0.000081 16344547 31465599 51.944179 0.921471136011 0.480558212161 0.999999194524 0.999988978388 0.740278703342 0.778598131291 0.631685095974 0.531413183368 0.461651842069 0.665447610018 0.665443363449 0.000011021612
221 SNOWBALL_FINNISH_LUCENE_FILTER FI_FI fi-fi-default 1.0.0 ca2628b3db31fee92f1b612ebbbd5e956a6dbbfb10e721325e55ef528f26072f LOWERCASE_GROUPS_ONLY PRIMARY_OUTPUT 54762 1734784 274 1734784 0 1 1734784 372232 14663371 936765 16097512 1504705198288 936765 1504706135053 0.000062 16097512 30760883 52.331112 0.939951485038 0.476688884386 0.999999377443 0.999988679564 0.738344130915 0.786987247415 0.632573283171 0.528815026735 0.462601231486 0.669376145960 0.669371899615 0.000011320436
222 SNOWBALL_FRENCH_DIRECT FR_FR fr-fr-default 1.0.0 a988658758952fd599dc7360e0234178a6d65ac46e5cedc7dcd325a7cb7e71d9 ALL_WORDS PRIMARY_OUTPUT 59240 404011 2301 404011 0 1 404011 85627 3744838 1092238 1625361 81605779618 1092238 81606871856 0.001338 1625361 5370199 30.266309 0.774194575401 0.697336914330 0.999986615858 0.999966701086 0.848661765094 0.757496924470 0.733758618240 0.711462917671 0.579477680015 0.734761496202 0.734744993787 0.000033298914
223 SNOWBALL_FRENCH_DIRECT FR_FR fr-fr-default 1.0.0 a988658758952fd599dc7360e0234178a6d65ac46e5cedc7dcd325a7cb7e71d9 LOWERCASE_GROUPS_ONLY PRIMARY_OUTPUT 57698 400712 2133 400712 0 1 400712 84526 3736871 1088903 1619380 80278407962 1088903 80279496865 0.001356 1619380 5356251 30.233460 0.774356818202 0.697665400669 0.999986436101 0.999966266576 0.848825918385 0.757698693319 0.734013322497 0.711763857056 0.579795455624 0.735011537210 0.734994818860 0.000033733424
224 SNOWBALL_FRENCH_LUCENE_FILTER FR_FR fr-fr-default 1.0.0 a988658758952fd599dc7360e0234178a6d65ac46e5cedc7dcd325a7cb7e71d9 ALL_WORDS PRIMARY_OUTPUT 59240 404011 2301 404011 0 1 404011 85202 3742072 1097843 1628127 81605774013 1097843 81606871856 0.001345 1628127 5370199 30.317815 0.773168950281 0.696821849619 0.999986547175 0.999966598516 0.848404198397 0.756589837411 0.733012775372 0.710860736247 0.578547882033 0.734003418250 0.733986862867 0.000033401484
225 SNOWBALL_FRENCH_LUCENE_FILTER FR_FR fr-fr-default 1.0.0 a988658758952fd599dc7360e0234178a6d65ac46e5cedc7dcd325a7cb7e71d9 LOWERCASE_GROUPS_ONLY PRIMARY_OUTPUT 57698 400712 2133 400712 0 1 400712 84810 3734232 1086494 1622019 80278410371 1086494 80279496865 0.001353 1622019 5356251 30.282729 0.774620254294 0.697172705312 0.999986466109 0.999966263711 0.848579585710 0.757784104203 0.733858787339 0.711398006457 0.579602638316 0.734876927298 0.734860210439 0.000033736289
226 SNOWBALL_GERMAN_DIRECT DE_DE de-de-default 1.0.0 cbfa038122823f02e4bdb54b0035492c356b6ecd80f11eb11290d7a7248a59f5 ALL_WORDS PRIMARY_OUTPUT 54092 277266 1474 277266 0 1 277266 81649 81641 742376 742393 65811 602476 602459 38436668082 65811 38436733893 0.000171 602476 602459 1344852 44.798684 44.797420 0.918569588474 0.918571301305 0.552013158325 0.552025799121 0.999998287810 0.999982613933 0.999982614376 0.776005723068 0.776012043466 0.810879063265 0.810885586285 0.689607573295 0.689617919831 0.599890587538 0.599902676509 0.526260347085 0.526272398156 0.712083211201 0.712092028219 0.712076031428 0.712084848565 0.000017386067 0.000017385624
227 SNOWBALL_GERMAN_DIRECT DE_DE de-de-default 1.0.0 cbfa038122823f02e4bdb54b0035492c356b6ecd80f11eb11290d7a7248a59f5 LOWERCASE_GROUPS_ONLY PRIMARY_OUTPUT 16007 145574 228 145574 0 1 145574 37843 37842 506459 506464 41477 351958 351953 10594922057 41477 10594963534 0.000391 351958 351953 858417 41.000819 41.000236 0.924303203294 0.924303894032 0.589991810507 0.589997635182 0.999996085215 0.999962868855 0.999962869327 0.794993947861 0.794996860199 0.830216831177 0.830219583690 0.720244490537 0.720249040429 0.635998708058 0.636004188257 0.562798507380 0.562804063590 0.738465517386 0.738469438547 0.738449797528 0.738453718829 0.000037131145 0.000037130673
228 SNOWBALL_GERMAN_LUCENE_FILTER DE_DE de-de-default 1.0.0 cbfa038122823f02e4bdb54b0035492c356b6ecd80f11eb11290d7a7248a59f5 ALL_WORDS PRIMARY_OUTPUT 54092 277266 1474 277266 0 1 277266 86669 723725 142783 621127 38436591110 142783 38436733893 0.000371 621127 1344852 46.185528 0.835220217240 0.538144717783 0.999996285246 0.999980126218 0.769070501515 0.752174652309 0.654551949931 0.579358576068 0.486493662760 0.670424751999 0.670415952491 0.000019873782
229 SNOWBALL_GERMAN_LUCENE_FILTER DE_DE de-de-default 1.0.0 cbfa038122823f02e4bdb54b0035492c356b6ecd80f11eb11290d7a7248a59f5 LOWERCASE_GROUPS_ONLY PRIMARY_OUTPUT 16007 145574 228 145574 0 1 145574 46077 471644 34482 386773 10594929052 34482 10594963534 0.000325 386773 858417 45.056540 0.931870719939 0.549434598802 0.999996745435 0.999960243292 0.774715672118 0.817996747049 0.691284921032 0.598564290417 0.528216517210 0.715543160924 0.715527026594 0.000039756708
230 SNOWBALL_HUNGARIAN_DIRECT HU_HU hu-hu-default 1.0.0 359d46a01d751ec823705ad7f3dd1cc8f6663feb1a9d13cb04d0c6fb51ab646e ALL_WORDS PRIMARY_OUTPUT 19406 910688 1 910688 0 1 910688 116105 14275129 1281527 7842726 414652461946 1281527 414653743473 0.000309 7842726 22117855 35.458800 0.917621949087 0.645411998587 0.999996909404 0.999977996662 0.822704453996 0.846239680964 0.757813631609 0.686119053091 0.610064359819 0.769574048489 0.769564274829 0.000022003338
243 SNOWBALL_NORWEGIAN_NYNORSK_DIRECT NN_NO nn-no-default 1.0.0 900cf2005605aea2a3d8d731ec0b0c1f47fb4469b4ba6b9134145d4d026a0398 LOWERCASE_GROUPS_ONLY PRIMARY_OUTPUT 4681 16906 23 16906 0 1 16906 6120 20847 1201 7458 142868459 1201 142869660 0.000841 7458 28305 26.348702 0.945527939042 0.736512983572 0.999991593737 0.999939404316 0.868252288654 0.894744070663 0.828034079399 0.770581364403 0.706534264217 0.834502009245 0.834474211808 0.000060595684
244 SNOWBALL_NORWEGIAN_NYNORSK_LUCENE_FILTER NN_NO nn-no-default 1.0.0 900cf2005605aea2a3d8d731ec0b0c1f47fb4469b4ba6b9134145d4d026a0398 ALL_WORDS PRIMARY_OUTPUT 4688 16937 23 16937 0 1 16937 6144 20854 1222 7508 143392932 1222 143394154 0.000852 7508 28362 26.472040 0.944645769161 0.735279599464 0.999991478035 0.999939130896 0.867635538749 0.893747964274 0.826916213966 0.769384020542 0.704908058410 0.833413920441 0.833385994629 0.000060869104
245 SNOWBALL_NORWEGIAN_NYNORSK_LUCENE_FILTER NN_NO nn-no-default 1.0.0 900cf2005605aea2a3d8d731ec0b0c1f47fb4469b4ba6b9134145d4d026a0398 LOWERCASE_GROUPS_ONLY PRIMARY_OUTPUT 4681 16906 23 16906 0 1 16906 6130 20824 1201 7481 142868459 1201 142869660 0.000841 7481 28305 26.429959 0.945471055619 0.735700406289 0.999991593737 0.999939243362 0.867846000013 0.894463296250 0.827498509835 0.769862102111 0.705754761743 0.834016450529 0.833988591624 0.000060756638
246 SNOWBALL_PERSIAN_DIRECT FA_IR fa-ir-default 1.0.0 b29a0d168a6a97f980666aa40b74a0edd8b6be4ab3320a7abfbb76b3529f4ea1 ALL_WORDS PRIMARY_OUTPUT 69 3544 0 3544 0 1 3544 2029 6748 79 89296 6182073 79 6182152 0.001278 89296 96044 92.974054 0.988428299399 0.070259464412 0.999987221278 0.985764222716 0.535123342845 0.273526169012 0.131193436440 0.086290898024 0.070201720712 0.263526930171 0.261598150185 0.014235777284
247 SNOWBALL_PERSIAN_DIRECT FA_IR fa-ir-default 1.0.0 b29a0d168a6a97f980666aa40b74a0edd8b6be4ab3320a7abfbb76b3529f4ea1 LOWERCASE_GROUPS_ONLY PRIMARY_OUTPUT 69 3544 0 3544 0 1 3544 2029 6748 79 89296 6182073 79 6182152 0.001278 89296 96044 92.974054 0.988428299399 0.070259464412 0.999987221278 0.985764222716 0.535123342845 0.273526169012 0.131193436440 0.086290898024 0.070201720712 0.263526930171 0.261598150185 0.014235777284
248 SNOWBALL_POLISH_DIRECT PL_PL pl-pl-unimorph 1.0.0 8191ed727097839cc808cbc5c56a1bd78b3c851e7733ad226ad9a51519a54721 ALL_WORDS PRIMARY_OUTPUT 9990 120867 1 120867 0 1 120867 19265 723037 70656 394036 7303167682 70656 7303238338 0.000967 394036 1117073 35.273970 0.910978174181 0.647260295433 0.999990325388 0.999936381518 0.823625310410 0.842338201869 0.756803292502 0.687038256475 0.608755869394 0.767880200391 0.767851723211 0.000063618482
249 SNOWBALL_POLISH_DIRECT PL_PL pl-pl-unimorph 1.0.0 8191ed727097839cc808cbc5c56a1bd78b3c851e7733ad226ad9a51519a54721 LOWERCASE_GROUPS_ONLY PRIMARY_OUTPUT 9846 119451 1 119451 0 1 119451 18927 718592 70647 392165 7133029571 70647 7133100218 0.000990 392165 1110757 35.306102 0.910487190826 0.646938979453 0.999990095891 0.999935127795 0.823464537672 0.841893538764 0.756414224030 0.686692785364 0.608252553741 0.767482673444 0.767453627968 0.000064872205
250 SNOWBALL_PORTUGUESE_DIRECT PT_PT pt-pt-default 1.0.0 7a035ff330a6f0548f446cd0d6617bc1cf4751292125a3564d3a255c5d6f516d ALL_WORDS PRIMARY_OUTPUT 4001 211091 0 211091 0 1 211091 11315 4816198 146201 670154 22273967042 146201 22274113243 0.000656 670154 5486352 12.214929 0.970538241685 0.877850710272 0.999993436282 0.999963358632 0.938922073277 0.950467296507 0.921870566157 0.894944355740 0.855064834721 0.923031789707 0.923014032222 0.000036641368
251 SNOWBALL_PORTUGUESE_DIRECT PT_PT pt-pt-default 1.0.0 7a035ff330a6f0548f446cd0d6617bc1cf4751292125a3564d3a255c5d6f516d LOWERCASE_GROUPS_ONLY PRIMARY_OUTPUT 4001 211091 0 211091 0 1 211091 11315 4816198 146201 670154 22273967042 146201 22274113243 0.000656 670154 5486352 12.214929 0.970538241685 0.877850710272 0.999993436282 0.999963358632 0.938922073277 0.950467296507 0.921870566157 0.894944355740 0.855064834721 0.923031789707 0.923014032222 0.000036641368
252 SNOWBALL_PORTUGUESE_LUCENE_FILTER PT_PT pt-pt-default 1.0.0 7a035ff330a6f0548f446cd0d6617bc1cf4751292125a3564d3a255c5d6f516d ALL_WORDS PRIMARY_OUTPUT 4001 211091 0 211091 0 1 211091 11315 4816198 146201 670154 22273967042 146201 22274113243 0.000656 670154 5486352 12.214929 0.970538241685 0.877850710272 0.999993436282 0.999963358632 0.938922073277 0.950467296507 0.921870566157 0.894944355740 0.855064834721 0.923031789707 0.923014032222 0.000036641368