opener-language-identifier 3.0.2 → 3.0.3

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA1:
-  metadata.gz: 7abeb7ee7ac0542e5948cb88b868501825efd4aa
-  data.tar.gz: e1fe36a7e665f42a1ea711f34996224c188c4e58
+  metadata.gz: dcf50a5847ebd111af672d41d6f2a40dfc6e5c2b
+  data.tar.gz: de82ac2bcc8485d334cfd9a8b84c373781abda89
 SHA512:
-  metadata.gz: 415285de95bd3ac2fd78d39c1e9d189badd4a384b086ae33767f96f1ec8df86bd24340f478f09ffedb04f4dac9d4aa23ad743e7caa0a2b06c6d6f90bf8f572f9
-  data.tar.gz: 3043ab05c774d586dd6f5aa3683313941af375017e6d02e1f6275ffda0f7adaecca0ba9f48a801d4635345488353f3a7750c356e8c83b39176ff9d1418dc065d
+  metadata.gz: 45a785402359135646b38000ad9502ebbe44389d38f91c92eed73b315d2397524a3522b9d8fa9f2a6a42626bad9ae30971ed90f6301af38d0f843b197beaca58
+  data.tar.gz: 571cbb5c6a46acabedbb572832a46c3cfe565fdc0d2ceeb78168d7e58843b88659f764fcfa810bb6f418d3b054b21b3d9f5aa9556b50d3a9430e2fac704e3e2e

data/README.md

@@ -2,20 +2,13 @@
 
 # Language Identifier
 
-The language identifier takes raw text and tries to figure out what language it
-was written in. The output can either be a plain-text i18n language code or a basic
-KAF document containing the language and raw input text.
+The language identifier takes raw text and tries to figure out what language it was written in. The output can either be a plain-text i18n language code or a basic KAF document containing the language and raw input text.
 
-The output of the language identifier can then be used to drive further text
-analysis of for example sentiments and or entities.
+The output of the language identifier can then be used to drive further text analysis of for example sentiments and or entities.
 
 ### Confused by some terminology?
 
-This software is part of a larger collection of natural language processing
-tools known as "the OpeNER project". You can find more information about the
-project at [the OpeNER portal](http://opener-project.github.io). There you can
-also find references to terms like KAF (an XML standard to represent linguistic
-annotations in texts), component, cores, scenario's and pipelines.
+This software is part of a larger collection of natural language processing tools known as "the OpeNER project". You can find more information about the project at [the OpeNER portal](http://opener-project.github.io). There you can also find references to terms like KAF (an XML standard to represent linguistic annotations in texts), component, cores, scenario's and pipelines.
 
 Quick Use Example
 -----------------
@@ -28,8 +21,7 @@ Make sure you run ```jruby``` since the language-identifier uses Java.
 
 ### Command line interface
 
-You should now be able to call the language indentifier as a regular shell
-command: by its name. Once installed the gem normally sits in your path so you can call it directly from anywhere.
+You should now be able to call the language indentifier as a regular shell command: by its name. Once installed the gem normally sits in your path so you can call it directly from anywhere.
 
 This aplication reads a text from standard input in order to identify the language.
 
@@ -44,8 +36,7 @@ This will output:
 </KAF>
 ~~~~
 
-If you just want the language code returned add the ```--no-kaf``` option like
-this
+If you just want the language code returned add the ```--no-kaf``` option like this
 
     echo "This is an English text." | language-identifier --no-kaf
 
@@ -59,8 +50,7 @@ You can launch a language identification webservice by executing:
 
     $ language-identifier-server
 
-This will launch a mini webserver with the webservice. It defaults to port 9292,
-so you can access it at <http://localhost:9292/>.
+This will launch a mini webserver with the webservice. It defaults to port 9292, so you can access it at <http://localhost:9292/>.
 
 To launch it on a different port provide the `-p [port-number]` option like
 this:

data/core/target/classes/profiles/af

@@ -0,0 +1 @@
+{"freq":{"D":9246,"E":2445,"F":2510,"G":3299,"A":6930,"B":3706,"C":2451,"L":2519,"M":3951,"N":3334,"O":2514,"H":3034,"I":2837,"J":2196,"K":3663,"U":687,"T":2336,"W":2258,"V":2714,"Q":182,"P":3097,"S":8234,"R":3039,"Y":252,"X":214,"Z":422,"f":13583,"g":42805,"d":77385,"Feb":207,"e":240974,"b":21626,"c":4896,"a":128566,"n":127153,"o":86673,"l":57433,"m":31352,"j":4048,"k":45378,"h":17527,"i":140621,"w":24930,"v":32618,"u":35166,"t":82606,"s":102389,"r":98861,"q":199,"p":23331,"z":1187,"y":11757,"x":1123,"ï":264,"ë":2903,"ê":1053,"é":765,"á":212,"ü":233,"ö":184,"ó":216,"Eur":318,"Eng":637," l":3565," m":7731," n":16000," o":12065," h":7358," i":23795," j":1325," k":6363," d":33601," e":13358," f":1200," g":11018,"р":242,"с":306," a":8747,"т":161," b":8379," c":434," u":1931," t":8537," w":13128," v":24617," p":4859," s":15482," r":3617," J":2155," K":3559," H":2961," I":2185," N":3120," O":2318," L":2396," M":3803," B":3554," C":2109," A":6365," F":2371," G":3138," D":8986," E":2271,"л":219,"к":266," Z":368," Y":241,"и":371,"о":333,"н":199," S":7708,"Ger":200," R":2881,"в":199," Q":162," P":2912,"а":481," W":2205," V":2322," U":571,"е":266," T":2130,"Fra":1006,"A ":345,"Da":804,"Co":478,"Ch":621,"Du":1025,"Do":201,"De":763,"Di":5828,"Fe":367,"Eu":354,"En":721,"El":212,"Ge":659,"Ga":319,"I ":452,"Fr":1217,"Fo":165,"Fi":216,"II ":246,"C ":278,"Au":486,"Ar":425,"At":187,"As":201,"D ":158,"Ba":648,"Af":2087,"Am":566,"An":491,"Ap":353,"Al":628,"Bu":243,"Br":778,"Ca":399,"Bi":180,"Be":880,"Bo":481,"Bl":161,"Kr":224,"Ko":657,"Le":490,"Li":504,"La":658,"Lu":245,"Lo":347,"Me":800,"Mi":548,"Ma":1360,"Mu":186,"Mo":627,"Ni":257,"Ne":763,"Na":666,"No":1092,"Ok":339,"Ol":206,"Her":157,"Gr":1326,"Go":356,"Ha":534,"He":680,"II":369,"Hi":301,"Ho":503,"Hu":294,"Hy":550,"In":919,"Is":158,"It":218,"Ja":713,"Je":157,"Jo":565,"Ju":623,"Ka":1489,"Ki":194,"Ke":447,"Un":253,"Tu":248,"Tr":236,"To":272,"Th":313,"Te":262,"Ta":276,"V ":280,"Sw":402,"Sy":292,"St":964,"Su":1701,"Wo":181,"Wi":534,"Wa":412,"We":720,"Vo":315,"Vr":251,"Vi":374,"Va":314,"Ve":689,"Pr":551,"S ":157,"Pe":310,"Pa":727,"Po":681,"Pi":230,"Os":236,"Oo":423,"Or":191,"Se":814,"Sc":197,"Si":387,"Sl":222,"Sk":201,"Sp":443,"So":680,"Ru":645,"Ry":194,"Sa":728,"Re":621,"Ri":222,"Ro":746,"SA":233,"Ra":223,"Gre":501,"Gri":383,"Gra":158,"b ":1179,"Gro":254,"a ":7054,"i ":2513,"gd":570,"ge":16432,"ga":1621,"gb":319,"fk":224,"fl":183,"fg":323,"ff":351,"fi":1111,"fh":169,"fs":1224,"fr":2334,"fu":174,"ft":300,"fo":725,"Int":180,"he":6229,"ha":2610,"gn":360,"gl":334,"gi":2135,"gh":921,"gg":418,"gu":592,"gt":1512,"gs":1974,"gr":3459,"go":1385,"dt":211,"du":998,"dw":506,"g ":10256,"ea":936,"eb":3497,"ec":406,"ed":5721,"de":18394,"dd":606,"dg":161,"di":29432,"dh":249,"dj":173,"dm":299,"do":2521,"ds":2062,"dr":1453,"ew":3034,"eu":3603,"ev":2016,"ey":309,"fa":570,"h ":864,"Ind":251,"fd":469,"fe":948,"eh":993,"eg":3187,"ef":995,"ee":12296,"el":15653,"ek":7920,"ei":5726,"ep":2393,"eo":692,"en":27638,"em":4686,"et":10282,"es":15156,"er":33393,"ca":479,"e ":78745,"by":1025,"br":1953,"bu":1057,"bo":2123,"bl":1117,"bi":1966,"bb":156,"be":8513,"db":222,"In ":319,"da":3617,"f ":4067,"ct":207,"co":446,"ck":502,"ci":340,"ch":1526,"ce":547,"c ":311,"az":190,"ay":279,"ba":2057,"d ":15502,"at":11369,"as":9342,"ar":11432,"aw":597,"av":407,"au":883,"ak":2797,"al":9554,"ai":1291,"aj":155,"ap":2087,"am":3989,"an":36357,"ac":615,"ad":4564,"aa":18307,"ab":1064,"ag":2729,"ah":292,"ae":907,"af":1901,"nu":917,"nt":6760,"ns":9243,"nr":212,"no":2885,"nn":1621,"ny":191,"nw":666,"nv":455,"oe":6026,"of":3797,"oc":387,"od":1636,"oa":178,"ob":729,"om":5480,"on":10533,"ok":2525,"ol":5346,"oi":587,"og":2271,"oh":382,"ot":3827,"os":3306,"ov":1152,"ou":2993,"op":4558,"oo":12667,"or":14221,"r ":19504,"ow":1144,"pe":3683,"pg":229,"pa":2371,"pl":1195,"lê":351,"po":1932,"ph":223,"pi":1008,"lo":3369,"lm":315,"ll":2990,"ls":2634,"lp":392,"lw":311,"lv":239,"lu":1548,"lt":993,"ly":716,"o ":2083,"md":261,"ma":3853,"mb":2182,"mg":224,"me":9151,"mi":2940,"mm":802,"mp":1223,"mo":1485,"ië":1437,"mt":249,"ms":966,"mu":1085,"p ":4720,"na":6444,"nb":510,"nc":507,"nd":12581,"ne":5737,"nf":203,"ng":9804,"nh":460,"ni":6127,"nj":300,"nk":2057,"nl":616,"nm":203,"jo":532,"ki":2683,"kh":210,"kg":239,"ke":8584,"ka":6722,"m ":5913,"kw":457,"ky":282,"ks":2318,"kt":2084,"ku":1443,"ko":3908,"kr":2375,"kk":1579,"kl":2200,"km":469,"li":9515,"lh":279,"lk":1158,"lj":705,"le":10290,"ld":1944,"lg":1526,"lf":717,"la":8341,"lb":446,"n ":58065,"hr":313,"ht":702,"hu":1684,"hi":1067,"ho":3048,"dé":160,"id":5034,"ic":1058,"ib":451,"ia":2568,"ig":5540,"if":581,"ie":47836,"hy":348,"k ":9212,"ir":2359,"is":17403,"it":9361,"iu":405,"iv":1008,"iw":219,"ik":8953,"il":3774,"im":1386,"in":25004,"io":1984,"eë":1032,"ip":899,"je":609,"ji":572,"iz":156,"l ":8172,"ja":1960,"wy":994,"z ":242,"wi":1800,"wo":4179,"vy":166,"y ":4684,"wa":9856,"we":6959,"vl":1196,"vi":4040,"vu":178,"vr":662,"vo":4078,"uw":282,"uu":992,"ve":5906,"va":16173,"x ":845,"ui":7822,"uk":678,"ul":2052,"ue":905,"ug":1045,"ur":5410,"us":5098,"ut":907,"um":1711,"un":2596,"up":170,"ty":1434,"tu":2643,"tt":1277,"tw":1177,"tv":217,"ub":1182,"ua":728,"ud":950,"uc":160,"w ":232,"to":5433,"tm":201,"tl":667,"ts":3814,"tr":4026,"tg":532,"te":20430,"tk":279,"tj":177,"ti":5658,"th":1701,"tb":213,"ta":9118,"su":1177,"sv":424,"ss":2799,"st":17122,"sy":1309,"sw":531,"sl":1811,"sk":5006,"sn":242,"sm":693,"sp":2566,"oë":412,"so":3731,"sr":312,"sd":385,"sc":448,"sf":208,"se":15556,"sh":473,"sg":396,"sj":338,"si":8436,"u ":1834,"sa":2367,"sb":577,"rr":652,"rs":6262,"rt":4139,"ru":2543,"rv":1198,"rw":1199,"ry":2450,"rp":1265,"ro":8165,"rn":1586,"rm":2087,"rl":1734,"rk":2996,"ri":11752,"rh":614,"rg":2653,"rf":378,"re":10923,"rd":7372,"rc":234,"rb":955,"ra":7710,"t ":22731,"qu":168,"s ":35284,"px":614,"Hy ":529,"py":231,"pt":765,"pu":844,"pp":1058,"pr":3258,"ps":659,"wê":320,"zi":170,"ze":169,"za":209,"yg":162,"ye":406,"yf":643,"yd":927,"yw":439,"ys":1141,"yn":1041,"yl":288,"yk":1145,"Apr":247,"Aug":272,"Afr":2048,"Ame":464,"Ber":218,"Bel":171,"Bre":163,"Bra":191,"Bri":282,"Des":273,"Daa":460,"Chr":224,"Cha":171,"ër":307,"ël":325,"êr":697,"ë ":1979,"ê ":310,"é ":228,"Dit":1028,"Die":4537,"Dui":918,"Ned":417,"Nas":187,"Nov":238,"Noo":595,"Okt":256,"Oli":158,"Oos":361,"Par":313,"Pro":177,"Pre":186,"SA ":161,"Ita":207,"Jan":348,"Joh":290,"Jul":297,"Jun":245,"Kaa":543,"Kan":220,"Kat":191,"Kar":171,"Ker":270,"Kon":276,"Lat":181,"Lit":162,"Mei":281,"Mar":370,"Maa":286,"Mon":210,"Mid":157,"Wil":165,"Wes":439,"Vry":192,"Vol":161,"êre":674,"Swe":193,"Sy ":252,"Sui":1515,"Sta":443,"Ste":208,"Sep":228,"Spa":253,"Rus":560,"Sch":162,"Rep":214,"Rom":176,"Ver":555,"Uni":236,"The":196,"Tur":159,"bin":400,"blo":205,"bli":525,"bla":215,"boe":246,"boo":276,"bor":587,"bou":330,"ban":283,"bal":289,"bai":191,"baa":372,"bas":270,"bar":272,"beh":366,"beg":372,"bee":325,"bed":285,"ber":1916,"bel":540,"bek":1148,"bew":349,"bev":630,"bes":1308,"bet":510,"bie":1052,"ce ":276,"bri":159,"bro":237,"bra":211,"bre":258,"bru":1062,"bur":584,"by ":693,"am ":1182,"ake":292,"al ":2759,"ain":204,"ak ":856,"aie":241,"agt":446,"anu":467,"ann":632,"ant":1705,"ans":3841,"ane":404,"ang":1856,"ani":742,"anj":191,"ank":961,"ap ":635,"ana":788,"anc":195,"and":5528,"amm":186,"amp":480,"ami":512,"ame":657,"amb":236,"ama":204,"alt":231,"als":160,"all":667,"alk":171,"alg":320,"ali":1276,"ald":217,"ale":2352,"alf":209,"ala":367,"an ":18298,"aks":261,"akt":740,"akl":166,"abe":229,"abi":201,"aby":216,"ae ":624,"aag":175,"aad":172,"aak":679,"aai":350,"aan":6190,"aal":1515,"aam":1083,"aas":579,"aar":5293,"aap":567,"aat":1563,"ad ":2565,"afg":266,"ai ":311,"age":184,"afd":268,"adm":206,"adi":436,"ade":539,"ag ":1304,"ads":176,"ach":166,"ada":249,"af ":494,"at ":6755,"arg":256,"are":965,"ard":1124,"ara":390,"aro":332,"arn":185,"arm":157,"arl":301,"ark":397,"ari":1177,"arv":249,"ars":463,"art":1494,"ary":171,"asi":1669,"ase":210,"aso":169,"ar ":3216,"apa":189,"app":418,"aps":269,"as ":5230,"awe":308,"awi":169,"ata":346,"ast":673,"ass":518,"ato":426,"ate":1382,"ati":871,"ats":404,"atu":409,"aty":167,"aus":156,"jaa":1087,"jar":470,"je ":175,"joe":306,"jin":161,"jie":306,"ito":170,"itt":191,"its":1623,"isk":182,"ism":266,"iss":374,"ist":1582,"ita":608,"ite":1331,"itg":386,"iti":469,"ius":176,"ium":203,"ivi":590,"ive":294,"is ":12546,"ion":1252,"eër":158,"ipa":265,"ir ":1648,"isi":1018,"ise":601,"isa":220,"ire":181,"it ":3772,"kil":644,"kie":536,"kin":914,"km ":266,"kgr":173,"kee":210,"kei":339,"kel":962,"ken":2090,"kep":166,"ker":1342,"ke ":3014,"kra":345,"kse":472,"kry":1085,"kri":662,"kou":249,"kor":369,"kop":214,"koo":391,"kon":866,"kom":903,"kol":246,"koe":157,"ks ":710,"kke":1272,"kki":178,"klu":430,"kle":511,"kla":387,"kli":749,"kat":157,"kar":183,"kas":204,"kap":818,"kan":1256,"kal":611,"kaa":1596,"ka ":1388," Ga":319," Ge":658," Fo":161," Fr":1217," Fi":213," Ha":534," He":680," Go":354," Gr":1318," Hy":549," Hu":294," Ho":502," II":202," Hi":301," Ja":710," Is":157," It":218," In":916,"han":779," Ka":1486,"hal":311," Ke":447,"haw":164," Ki":192,"har":356," Jo":563," Ju":622,"haa":238,"had":164," La":657," Le":488," Li":502," Ko":657," Kr":224," Ma":1348," Mi":547," Me":799,"he ":399," Lo":346," Lu":244," Ne":762," Na":662," Ni":257," Mo":624," Mu":186,"hel":273,"hei":994,"hee":465,"hed":169,"het":2911,"her":350,"hem":255," Ap":349," Am":563," An":491," Al":626," Af":2082," Ba":645," Au":486," At":187," As":200," Ar":422," Be":877,"hie":290," Bi":179," Bl":161," Bo":479," Br":777," Bu":243,"his":173," Ca":384," Ch":612," Co":473," Da":803," Di":5802," De":761," Do":196," Du":1024," El":212," En":720," Eu":354," Fe":367," Wo":179," Wi":530," We":720," Wa":412,"god":193,"gs ":887,"gor":522,"gro":2150,"gra":537,"gri":320,"gre":401," Os":236," Or":191," Oo":422," Po":674," Pi":229," Pe":309," Pa":725,"gst":406," No":1092," Ol":205," Ok":339,"gte":962,"gti":391," Ra":221," Ro":743," Re":620," Ri":222," Pr":547,"gus":284," Sy":292," Sw":400," Su":1700," St":953," Ta":273," Th":307," Te":261," Tr":236," To":270," Ry":194," Ru":645," Sa":724," Si":385," Sc":196," Se":811," So":678," Sp":441," Sk":201," Sl":222," Va":313," Ve":669," Vi":371," Vo":314," Vr":251," Tu":243," Un":253," ja":1102,"ial":357,"ian":256," in":12303,"iaa":736," is":11238," ka":1533," ki":531," ke":481,"id ":2425," ha":612," he":3438," gr":2075," go":365,"ia ":794," hy":292," hi":477," ho":1750," hu":727,"iet":320,"ieu":180,"iew":413," ni":722,"iel":277," ne":437,"ien":998," na":2339,"ier":2228,"ies":4471,"ied":1248,"ief":177,"iek":2103," mu":691,"ig ":1346," mo":667," om":1497," on":2106," of":1952,"ifi":218," no":1205," le":910," li":598," n ":10980," la":1290," ku":387,"ich":258,"ie ":34696," km":407," kl":879,"ica":209," kr":319," ko":1672," me":4100," mi":830,"ids":257," ma":1329," lu":186,"idi":291,"ide":993,"idd":457,"ida":156," lo":197," af":820," aa":2320," ad":269," am":322," an":759," ak":286," al":829," ar":263," at":229," as":2284," ba":599,"il ":459," bi":320," be":5430," bo":565," bl":263," by":612," bu":213," br":340,"ika":2950,"igd":381,"ige":1604,"igh":698,"igi":270,"igg":185,"igt":498,"igs":156,"ik ":2305," en":9738,"imp":231," ei":517," el":502,"ime":187," ek":223," ee":1730,"ind":1030,"ina":506," fa":191,"inn":302," fo":227,"int":638,"ins":1349,"ine":545,"ing":6095," fi":368,"ini":615,"ink":417," ge":8191," ga":169,"inw":455,"ikk":629," ch":185,"ike":1814,"ila":498," da":1923,"in ":12178,"iku":209,"iks":287," do":1111,"ilo":514,"ill":662," dr":523," de":3947,"ilj":228,"ili":684,"ild":294," di":25510,"imb":245,"eë ":693,"io ":196," du":309," wê":298,"hom":166,"hou":360,"hoo":1325,"hoe":410," wy":201,"hul":552,"hui":260,"hri":224,"ht ":578," ru":233," sa":888," se":2315," si":590," sl":329," sk":1250," sp":887," so":2211," ra":237," re":1576," ri":825," ro":614," pr":1589," s ":207," px":614,"hy ":302," ou":447,"hum":674," oo":2639," op":2809," or":325," pe":402," pa":556," pl":641," po":737," lê":242," wa":7840," we":1395," wo":2888," wi":454," va":14670," ve":4043," vo":2359," vr":575," vi":2068," vl":594," ty":439," tw":582," tu":692," ui":1746," ta":895," sw":227," sy":1183," st":4293," su":859," tr":387," to":1857," th":729," ti":190," te":2715,"ffe":165,"fer":157,"fel":155,"fha":158,"fge":290,"fam":176,"fde":429,"eta":359,"ete":1299,"eti":372,"esp":358,"eso":210,"est":2951,"ess":405,"eun":234,"eto":320,"etr":438,"ets":217,"ett":493,"eve":456,"eva":262,"evo":907,"evi":274,"eur":2292,"eus":242,"ewi":337,"ewe":1704,"ewo":449,"ey ":181,"ewa":222,"epe":254,"er ":10617,"epa":228,"eor":221,"es ":4626,"ept":277,"epu":400,"epr":184,"erk":2067,"erl":875,"eri":1765,"erg":1022,"erh":416,"ere":1861,"erf":286,"erd":1514,"era":1470,"erb":529,"et ":6083,"esk":1018,"esl":228,"esi":976,"ese":3607,"eu ":338,"erv":860,"erw":949,"err":349,"ert":1101,"ers":4583,"ern":1142,"erm":861,"erp":342,"ero":382,"ekg":155,"ekk":206,"eko":474,"eks":950,"ekt":701,"en ":13492,"ela":904,"eld":1199,"elf":322,"ele":2593,"eli":1906,"elj":427,"elg":226,"elk":209,"ell":778,"elo":234,"els":1983,"elt":333,"ely":255,"emb":839,"ema":484,"eme":1266,"emo":181,"emi":456,"ep ":699,"ene":1142,"enh":254,"eng":314,"enb":269,"ena":610,"end":3112,"eno":500,"enn":400,"enk":275,"eni":1151,"ens":2864,"ent":2318,"ego":497,"ege":690,"egi":516,"eha":370,"egr":238,"egs":217,"egt":193,"eho":266,"ehe":259,"ek ":1799,"eis":330,"eil":544,"ein":1010,"eie":633,"eid":1307,"el ":3516,"eit":680,"eke":2739,"eka":220,"em ":967,"gin":784,"gie":714,"ght":548,"gep":249,"gen":1564,"get":297,"ger":1248,"ges":2014,"gev":788,"gew":944,"gee":448,"ged":475,"geb":2499,"geh":356,"geg":181,"gem":756,"gel":1995,"gek":350,"gde":427,"ge ":1916,"gaa":266,"gan":539,"ga ":157,"fst":852,"fri":2089,"for":371,"fie":369,"fil":208,"fin":174,"fis":177,"da ":327,"de ":6409,"daa":645,"dag":700,"dae":480,"dat":659,"dan":233,"dam":165,"dde":490,"ch ":316,"cha":160,"ck ":233,"che":490,"ed ":1090,"eba":159,"ebe":354,"ebi":752,"ebo":768,"ebr":1168,"ei ":821,"ega":168,"eek":631,"een":2520,"eel":2072,"eem":410,"eed":587,"ees":884,"eer":3295,"eeu":449,"eet":195,"edi":638,"ede":2561,"eda":161,"eg ":316,"eds":321,"edr":340,"ee ":892,"ef ":280,"dwe":310,"dus":171,"dor":875,"doo":416,"don":160,"dom":227,"ds ":353,"dmi":211,"doe":283,"dst":428,"dui":309,"dri":421,"dra":423,"dry":204,"dsk":181,"dse":527,"dia":294,"der":4829,"des":476,"deu":1676,"dee":1279,"del":1695,"dek":186,"den":1206,"do ":172,"din":875,"dio":177,"dis":425,"dit":656,"die":24964,"dig":1168,"dik":198,"rhe":301,"rga":496,"rgi":335,"rge":595,"ret":312,"res":944,"rg ":777,"rea":245,"ree":1091,"ref":257,"red":294,"rei":545,"reg":1039,"ren":1300,"rek":765,"rel":674,"rep":191,"rf ":180,"rdo":215,"rdi":841,"rde":1873,"re ":2607,"rd ":3667,"ras":532,"rat":587,"rbi":190,"rba":160,"rbe":287,"rag":291,"ran":2011,"ram":317,"ral":832,"rak":247,"raa":1046,"raf":284,"rad":331,"rs ":1922,"ros":273,"rot":330,"rom":305,"ron":1072,"roo":1778,"rop":575,"rou":212,"rov":708,"rod":199,"rol":315,"roe":1277,"rog":195,"rno":196,"rp ":728,"rna":508,"rne":469,"rmo":164,"rma":539,"rme":324,"rmi":175,"rlo":320,"rli":409,"rle":270,"rla":508,"rks":184,"rko":248,"rki":199,"rkl":203,"rke":440,"rka":271,"rm ":692,"rio":174,"rit":493,"ris":571,"riv":501,"rig":863,"ril":278,"rik":3384,"rin":1384,"ria":924,"ric":236,"rie":2029,"rk ":1040,"rwe":410,"rwy":498,"ryf":393,"rui":1143,"rug":256,"rum":244,"ruk":231,"rus":225,"rva":502,"rvl":353,"rvo":192,"rwa":171,"ry ":383,"rsk":872,"rsi":432,"rso":249,"rsp":591,"rsa":225,"rse":478,"rta":186,"rst":1083,"rtk":160,"rto":274,"rte":620,"rti":334,"rua":209,"rty":351,"rt ":1413,"rre":272,"saa":540,"sal":170,"sam":303,"san":408,"sas":204,"sa ":155,"ryw":338,"rys":282,"ryk":576,"sge":305,"sie":4039,"sid":185,"sia":299,"sit":436,"sis":296,"sip":279,"sin":541,"sio":799,"sil":194,"sim":173,"sik":231,"sif":160,"sig":289,"sbu":231,"se ":9840,"sch":268,"ser":501,"ses":400,"set":250,"seu":239,"sea":162,"see":618,"sed":264,"sen":1323,"sem":298,"sel":1093,"sek":186,"spo":405,"spr":756,"spe":934,"spa":260,"sow":508,"som":247,"son":545,"soo":954,"soe":195,"sok":377,"st ":267,"sli":202,"slu":297,"sky":183,"sla":1006,"sle":205,"ski":804,"sko":594,"skr":1152,"sku":244,"ska":1212,"ske":665,"sië":283,"sma":173,"sme":382,"sse":1275,"ssa":198,"ssi":922,"ste":6829,"sta":5065,"sto":805,"sti":1396,"stu":693,"str":1673,"sty":226,"sui":596,"sve":167,"sy ":1199,"swa":313,"tal":1301,"taa":2499,"tad":2323,"tau":165,"tat":456,"tas":164,"tan":1021,"te ":8469,"ta ":339,"pa ":202,"pe ":459,"par":608,"pas":176,"paa":333,"pal":324,"pan":428,"pge":207,"pen":295,"per":1379,"pes":438,"pee":201,"pel":568,"pla":660,"lê ":268,"pli":169,"ple":241,"pie":480,"por":394,"poo":160,"pos":197,"pol":518,"ppy":184,"ppe":636,"pst":229,"pub":435,"pte":575,"pra":251,"pri":484,"pre":726,"pro":1677,"pun":246,"px ":614,"py ":166,"ra ":424,"ngo":161,"ngr":289,"ngs":1292,"nge":2327,"nhe":276,"nel":314,"nen":189,"nem":225,"ner":1014,"net":468,"nes":533,"ng ":4906,"nee":762,"nce":206,"ne ":1530,"ndr":216,"nds":657,"ndo":326,"ndi":878,"nde":5081,"nda":453,"nal":790,"nam":291,"nad":316,"naf":372,"nab":229,"naa":1198,"nd ":4245,"nat":282,"nas":677,"na ":1572,"nwo":542,"nus":209,"nua":266,"ntw":393,"nto":201,"nts":300,"ntr":543,"nti":571,"ntl":164,"nta":457,"nte":1815,"nst":787,"nse":3345,"nsi":1079,"nsl":207,"nsk":498,"nt ":1757,"ns ":2476,"nog":456,"noe":477,"noo":659,"nom":368,"nne":904,"nni":442,"nië":246,"nli":373,"nke":345,"nkl":391,"nks":179,"nkr":453,"nje":156,"nig":640,"nie":1831,"nk ":274,"niv":210,"nis":1512,"nin":804,"ogr":272,"ogi":423,"oi ":216,"oha":228,"oeë":178,"ok ":1432,"ol ":554,"ock":164,"oe ":303,"ode":551,"odi":176,"ods":177,"of ":2323,"oek":499,"oel":276,"oem":563,"oeg":231,"oei":336,"oer":752,"oes":295,"oet":302,"oen":602,"oep":714,"odu":188,"oed":477,"og ":895,"ofs":803,"oew":261,"od ":254,"obe":382,"oud":510,"oue":197,"ote":350,"ott":175,"ots":913,"oto":266,"ost":637,"osi":266,"ose":346,"oss":176,"oso":190,"owa":484,"owe":208,"ovi":678,"ove":370,"ous":302,"our":167,"out":306,"opo":205,"opp":449,"ope":438,"opg":213,"opa":195,"os ":1171,"oon":731,"ool":561,"oom":393,"ook":1376,"ooi":288,"oof":1146,"oog":389,"ood":288,"or ":1152,"oot":1351,"oos":958,"oor":4776,"oop":341,"ork":260,"orl":386,"orm":964,"orp":858,"ord":4583,"ore":773,"org":587,"ori":1212,"ou ":999,"ort":1219,"ors":871,"orw":195,"ot ":1528,"orb":186,"ora":235,"ola":171,"on ":1522,"oli":772,"oll":288,"olk":702,"ole":263,"olg":904,"ols":270,"olo":636,"om ":1870,"okk":553,"ona":980,"ond":1915,"one":1178,"ong":620,"oni":1012,"onl":220,"onk":232,"onn":184,"ono":391,"ons":511,"ont":1339,"oma":425,"ome":845,"omi":324,"omm":454,"omp":297,"oms":595,"op ":2264,"la ":334,"le ":3834,"lf ":175,"lde":601,"laa":982,"lad":180,"lag":434,"lak":490,"lan":4154,"lar":155,"lat":361,"las":433,"ld ":695,"kus":410,"kun":548,"kul":242,"kwe":204,"kwa":191,"kte":822,"kst":257,"ksi":463,"ktr":342,"ktu":210,"kti":247,"kto":369,"ls ":1008,"lon":293,"lom":430,"loo":382,"loe":423,"log":655,"los":274,"lië":349,"lti":157,"lub":411,"lug":221,"lst":643,"lte":252,"lse":623,"lge":754,"lew":250,"leu":193,"les":329,"let":347,"ler":415,"lem":358,"len":1056,"lek":605,"lei":1010,"leg":257,"lee":477,"led":218,"lg ":483,"lo ":169,"lla":325,"lle":1578,"lli":615,"lke":200,"lki":447,"ljo":223,"ll ":176,"lja":430,"lit":831,"lis":504,"leë":449,"lin":1208,"lim":201,"lid":165,"lia":364,"lik":2917,"lig":818,"lie":1618,"ma ":226,"mb ":655,"maa":1244,"mag":221,"mar":331,"mas":207,"mal":270,"man":726,"mat":394,"mba":172,"mbi":179,"mbe":814,"mbo":161,"me ":936,"mde":163,"med":223,"mee":1533,"met":2981,"mes":247,"mer":991,"mel":330,"men":1550,"lui":390,"lus":194,"lwe":213,"lyk":221,"lyn":187,"mpi":220,"mpe":208,"mpo":176,"mpt":267,"ms ":488,"moe":196,"mod":233,"mon":329,"mst":248,"mus":488,"mun":417,"ër ":180,"mge":191,"min":806,"mil":465,"mit":231,"mig":184,"mie":523,"mid":310,"ië ":1136,"mme":353,"wêr":319,"yst":183,"ys ":680,"ywe":370,"ye ":306,"yf ":380,"yde":281,"yds":165,"yd ":230,"yn ":461,"yns":175,"yk ":810,"wys":531,"wor":2620,"woo":760,"won":526,"we ":1260,"wes":799,"wer":1583,"wet":305,"wen":427,"wel":545,"weg":270,"wee":1257,"wis":166,"wit":342,"wie":194,"win":417,"wil":177,"wik":231,"wan":300,"wat":5174,"war":532,"was":2236,"waa":1031,"vry":194,"vro":313,"vir":1570,"vin":921,"vie":880,"vis":289,"vla":709,"vlo":280,"voe":444,"vol":1592,"voo":1083,"vor":625,"ver":4566,"ven":170,"vem":236,"vel":250,"vee":302,"val":319,"van":14723,"vat":155,"vaa":414,"uwe":229,"uur":863,"usl":180,"usi":606,"use":380,"ust":585,"uss":1129,"ute":176,"uto":171,"us ":1998,"ure":395,"urg":669,"uri":191,"urk":167,"uro":352,"urs":211,"urt":189,"ur ":2547,"umb":689,"ume":172,"unt":325,"uns":289,"uni":820,"und":530,"um ":614,"ult":270,"ull":459,"uli":358,"un ":219,"uid":2285,"uik":850,"uim":162,"uis":508,"uk ":200,"uit":3378,"ul ":272,"ugb":161,"ugu":278,"ude":184,"udi":240,"ue ":322,"ug ":159,"ub ":406,"uar":522,"ubl":464,"ud ":181,"tyn":228,"ty ":384,"tur":232,"tus":988,"tuu":617,"tui":232,"tud":171,"tyd":628,"twi":269,"twe":751,"ts ":533,"tre":1022,"tra":1128,"tri":607,"tru":366,"tro":780,"tse":746,"tsk":298,"tsl":425,"tst":993,"tte":641,"tti":226,"to ":272,"tof":244,"toe":713,"tob":268,"tot":1108,"tom":182,"ton":586,"tol":317,"tor":808,"too":280,"til":187,"tik":334,"tie":1846,"tig":1053,"tis":241,"tin":826,"tio":267,"thu":695,"tkl":165,"tli":191,"tla":301,"tem":732,"ten":1059,"tei":844,"tek":528,"tel":2135,"tee":779,"teg":166,"ted":237,"th ":270,"teu":212,"tes":357,"ter":4231,"tge":442,"the":380},"n_words":[1541130,1808182,1328687],"name":"af"}

data/lib/opener/language_identifier/server.rb

@@ -22,6 +22,7 @@ module Opener
       # @raise RunetimeError Raised when the tagging process failed.
       #
       def analyze(options)
+        options[:kaf] = true if options[:kaf].nil?
         processor = text_processor.new(options)
         output    = processor.run(options[:input])
 

data/lib/opener/language_identifier/version.rb

@@ -1,5 +1,5 @@
 module Opener
   class LanguageIdentifier
-    VERSION = "3.0.2"
+    VERSION = "3.0.3"
   end
 end

data/lib/opener/language_identifier/views/index.erb

@@ -32,7 +32,8 @@
       </div>
       <div>
         <label for="kaf">
-          <input type="checkbox" name="kaf" id="kaf"/>
+          <input type='hidden' value='false' name='kaf'>
+          <input type="checkbox" name="kaf" id="kaf" checked/>
           Output KAF instead of just the language code
         </label>
 	<br>

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: opener-language-identifier
 version: !ruby/object:Gem::Version
-  version: 3.0.2
+  version: 3.0.3
 platform: ruby
 authors:
 - development@olery.com
 autorequire:
 bindir: bin
 cert_chain: []
-date: 2014-05-23 00:00:00.000000000 Z
+date: 2014-05-24 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: builder
@@ -168,97 +168,98 @@ description: Language identifier for human readable text.
 email:
 executables:
 - language-identifier
-- language-identifier-server
 - language-identifier-daemon
+- language-identifier-server
 extensions: []
 extra_rdoc_files: []
 files:
+- README.md
+- bin/language-identifier
+- bin/language-identifier-daemon
+- bin/language-identifier-server
+- config.ru
 - core/target/LanguageDetection-0.0.1.jar
-- core/target/classes/org/vicomtech/opennlp/LanguageDetection/CybozuDetector.class
-- core/target/classes/org/vicomtech/opennlp/LanguageDetection/Main.class
+- core/target/classes/com/cybozu/labs/langdetect/Command.class
+- core/target/classes/com/cybozu/labs/langdetect/Detector.class
+- core/target/classes/com/cybozu/labs/langdetect/DetectorFactory.class
 - core/target/classes/com/cybozu/labs/langdetect/ErrorCode.class
 - core/target/classes/com/cybozu/labs/langdetect/GenProfile.class
-- core/target/classes/com/cybozu/labs/langdetect/Command.class
 - core/target/classes/com/cybozu/labs/langdetect/LangDetectException.class
 - core/target/classes/com/cybozu/labs/langdetect/Language.class
-- core/target/classes/com/cybozu/labs/langdetect/Detector.class
-- core/target/classes/com/cybozu/labs/langdetect/DetectorFactory.class
-- core/target/classes/com/cybozu/labs/langdetect/util/TagExtractor.class
-- core/target/classes/com/cybozu/labs/langdetect/util/NGram.class
+- core/target/classes/com/cybozu/labs/langdetect/af
 - core/target/classes/com/cybozu/labs/langdetect/util/LangProfile.class
 - core/target/classes/com/cybozu/labs/langdetect/util/Messages.class
+- core/target/classes/com/cybozu/labs/langdetect/util/NGram.class
+- core/target/classes/com/cybozu/labs/langdetect/util/TagExtractor.class
 - core/target/classes/com/cybozu/labs/langdetect/util/messages.properties
-- core/target/classes/profiles/fi
-- core/target/classes/profiles/ta
-- core/target/classes/profiles/mr
-- core/target/classes/profiles/ml
-- core/target/classes/profiles/hr
-- core/target/classes/profiles/id
-- core/target/classes/profiles/es
-- core/target/classes/profiles/no
+- core/target/classes/org/vicomtech/opennlp/LanguageDetection/CybozuDetector.class
+- core/target/classes/org/vicomtech/opennlp/LanguageDetection/Main.class
+- core/target/classes/profiles/af
+- core/target/classes/profiles/ar
+- core/target/classes/profiles/bg
+- core/target/classes/profiles/bn
 - core/target/classes/profiles/ca
+- core/target/classes/profiles/cs
+- core/target/classes/profiles/da
+- core/target/classes/profiles/de
+- core/target/classes/profiles/el
 - core/target/classes/profiles/en
-- core/target/classes/profiles/ru
-- core/target/classes/profiles/te
-- core/target/classes/profiles/lt
-- core/target/classes/profiles/pa
+- core/target/classes/profiles/es
+- core/target/classes/profiles/et
 - core/target/classes/profiles/eu
-- core/target/classes/profiles/ja
-- core/target/classes/profiles/he
-- core/target/classes/profiles/nl
-- core/target/classes/profiles/sl
-- core/target/classes/profiles/tr
-- core/target/classes/profiles/pl
-- core/target/classes/profiles/sk
 - core/target/classes/profiles/fa
-- core/target/classes/profiles/de
-- core/target/classes/profiles/bg
-- core/target/classes/profiles/it
+- core/target/classes/profiles/fi
 - core/target/classes/profiles/fr
-- core/target/classes/profiles/el
-- core/target/classes/profiles/pt
-- core/target/classes/profiles/uk
-- core/target/classes/profiles/da
-- core/target/classes/profiles/ar
-- core/target/classes/profiles/zh-tw
-- core/target/classes/profiles/sq
-- core/target/classes/profiles/th
+- core/target/classes/profiles/gu
+- core/target/classes/profiles/he
+- core/target/classes/profiles/hi
+- core/target/classes/profiles/hr
+- core/target/classes/profiles/hu
+- core/target/classes/profiles/id
+- core/target/classes/profiles/it
+- core/target/classes/profiles/ja
 - core/target/classes/profiles/kn
-- core/target/classes/profiles/sw
 - core/target/classes/profiles/ko
-- core/target/classes/profiles/ro
+- core/target/classes/profiles/lt
 - core/target/classes/profiles/lv
-- core/target/classes/profiles/sv
-- core/target/classes/profiles/so
-- core/target/classes/profiles/vi
-- core/target/classes/profiles/et
-- core/target/classes/profiles/hi
-- core/target/classes/profiles/gu
-- core/target/classes/profiles/zh-cn
 - core/target/classes/profiles/mk
+- core/target/classes/profiles/ml
+- core/target/classes/profiles/mr
 - core/target/classes/profiles/ne
-- core/target/classes/profiles/ur
-- core/target/classes/profiles/hu
-- core/target/classes/profiles/cs
-- core/target/classes/profiles/bn
+- core/target/classes/profiles/nl
+- core/target/classes/profiles/no
+- core/target/classes/profiles/pa
+- core/target/classes/profiles/pl
+- core/target/classes/profiles/pt
+- core/target/classes/profiles/ro
+- core/target/classes/profiles/ru
+- core/target/classes/profiles/sk
+- core/target/classes/profiles/sl
+- core/target/classes/profiles/so
+- core/target/classes/profiles/sq
+- core/target/classes/profiles/sv
+- core/target/classes/profiles/sw
+- core/target/classes/profiles/ta
+- core/target/classes/profiles/te
+- core/target/classes/profiles/th
 - core/target/classes/profiles/tl
-- core/target/classes/com/cybozu/labs/langdetect/af
+- core/target/classes/profiles/tr
+- core/target/classes/profiles/uk
+- core/target/classes/profiles/ur
+- core/target/classes/profiles/vi
+- core/target/classes/profiles/zh-cn
+- core/target/classes/profiles/zh-tw
 - exec/language-identifier.rb
 - lib/opener/language_identifier.rb
-- lib/opener/language_identifier/kaf_builder.rb
-- lib/opener/language_identifier/version.rb
-- lib/opener/language_identifier/server.rb
-- lib/opener/language_identifier/detector.rb
 - lib/opener/language_identifier/cli.rb
+- lib/opener/language_identifier/detector.rb
+- lib/opener/language_identifier/kaf_builder.rb
 - lib/opener/language_identifier/public/markdown.css
+- lib/opener/language_identifier/server.rb
+- lib/opener/language_identifier/version.rb
 - lib/opener/language_identifier/views/index.erb
 - lib/opener/language_identifier/views/result.erb
-- config.ru
 - opener-language-identifier.gemspec
-- README.md
-- bin/language-identifier
-- bin/language-identifier-server
-- bin/language-identifier-daemon
 homepage: http://opener-project.github.com/
 licenses: []
 metadata: {}
@@ -278,9 +279,8 @@ required_rubygems_version: !ruby/object:Gem::Requirement
       version: '0'
 requirements: []
 rubyforge_project:
-rubygems_version: 2.1.9
+rubygems_version: 2.2.2
 signing_key:
 specification_version: 4
 summary: Language identifier for human readable text.
 test_files: []
-has_rdoc: yard