mittens 0.1.0

data/vendor/snowball/algorithms/armenian.sbl

@@ -0,0 +1,301 @@
+stringescapes {}
+
+stringdef a    '{U+0561}' // 531
+stringdef b    '{U+0562}' // 532
+stringdef g    '{U+0563}' // 533
+stringdef d    '{U+0564}' // 534
+stringdef ye   '{U+0565}' // 535
+stringdef z    '{U+0566}' // 536
+stringdef e    '{U+0567}' // 537
+stringdef y    '{U+0568}' // 538
+stringdef dt   '{U+0569}' // 539
+stringdef zh   '{U+056A}' // 53A
+stringdef i    '{U+056B}' // 53B
+stringdef l    '{U+056C}' // 53C
+stringdef kh   '{U+056D}' // 53D
+stringdef ts   '{U+056E}' // 53E
+stringdef k    '{U+056F}' // 53F
+stringdef h    '{U+0570}' // 540
+stringdef dz   '{U+0571}' // 541
+stringdef gh   '{U+0572}' // 542
+stringdef djch '{U+0573}' // 543
+stringdef m    '{U+0574}' // 544
+stringdef j    '{U+0575}' // 545
+stringdef n    '{U+0576}' // 546
+stringdef sh   '{U+0577}' // 547
+stringdef vo   '{U+0578}' // 548
+stringdef ch   '{U+0579}' // 549
+stringdef p    '{U+057A}' // 54A
+stringdef dj   '{U+057B}' // 54B
+stringdef r    '{U+057C}' // 54C
+stringdef s    '{U+057D}' // 54D
+stringdef v    '{U+057E}' // 54E
+stringdef t    '{U+057F}' // 54F
+stringdef r'   '{U+0580}' // 550
+stringdef c    '{U+0581}' // 551
+stringdef u    '{U+0582}' // 552                  //vjun
+stringdef bp   '{U+0583}' // 553
+stringdef q    '{U+0584}' // 554
+stringdef ev   '{U+0587}'
+stringdef o    '{U+0585}' // 555
+stringdef f    '{U+0586}' // 556
+
+routines ( mark_regions R2
+           adjective
+           verb
+           noun
+           ending
+)
+
+externals ( stem )
+
+integers ( pV p2 )
+
+groupings ( v )
+
+define v '{a}{e}{i}{o}{u}{ye}{vo}{y}'
+
+define mark_regions as (
+
+    $pV = limit
+    $p2 = limit
+    do (
+        gopast v  setmark pV  gopast non-v
+        gopast v  gopast non-v  setmark p2
+       )
+)
+
+backwardmode (
+
+    define R2 as $p2 <= cursor
+
+    define adjective as (
+        [substring] among (
+            '{b}{a}{r'}'
+            '{p}{ye}{s}'
+            '{vo}{r'}{e}{n}'
+            '{vo}{v}{i}{n}'
+            '{a}{k}{i}'
+            '{l}{a}{j}{n}'
+            '{r'}{vo}{r'}{d}'
+            '{ye}{r'}{vo}{r'}{d}'
+            '{a}{k}{a}{n}'
+            '{a}{l}{i}'
+            '{k}{vo}{t}'
+            '{ye}{k}{ye}{n}'
+            '{vo}{r'}{a}{k}'
+            '{ye}{gh}'
+            '{v}{vo}{u}{n}'
+            '{ye}{r'}{ye}{n}'
+            '{a}{r'}{a}{n}'
+            '{ye}{n}'
+            '{a}{v}{ye}{t}'
+            '{g}{i}{n}'
+            '{i}{v}'
+            '{a}{t}'
+            '{i}{n}'
+
+              (delete)
+        )
+    )
+
+    define verb as (
+        [substring] among (
+            '{vo}{u}{m}'
+            '{v}{vo}{u}{m}'
+            '{a}{l}{vo}{u}'
+            '{ye}{l}{vo}{u}'
+            '{v}{ye}{l}'
+            '{a}{n}{a}{l}'
+            '{ye}{l}{vo}{u}{c}'
+            '{a}{l}{vo}{u}{c}'
+            '{y}{a}{l}'
+            '{y}{ye}{l}'
+            '{a}{l}{vo}{v}'
+            '{ye}{l}{vo}{v}'
+            '{a}{l}{i}{s}'
+            '{ye}{l}{i}{s}'
+            '{ye}{n}{a}{l}'
+            '{a}{c}{n}{a}{l}'
+            '{ye}{c}{n}{ye}{l}'
+            '{c}{n}{ye}{l}'
+            '{n}{ye}{l}'
+            '{a}{t}{ye}{l}'
+            '{vo}{t}{ye}{l}'
+            '{k}{vo}{t}{ye}{l}'
+            '{t}{ye}{l}'
+            '{v}{a}{ts}'
+            '{ye}{c}{v}{ye}{l}'
+            '{a}{c}{v}{ye}{l}'
+            '{ye}{c}{i}{r'}'
+            '{a}{c}{i}{r'}'
+            '{ye}{c}{i}{n}{q}'
+            '{a}{c}{i}{n}{q}'
+            '{v}{ye}{c}{i}{r'}'
+            '{v}{ye}{c}{i}{n}{q}'
+            '{v}{ye}{c}{i}{q}'
+            '{v}{ye}{c}{i}{n}'
+            '{a}{c}{r'}{i}{r'}'
+            '{a}{c}{r'}{ye}{c}'
+            '{a}{c}{r'}{i}{n}{q}'
+            '{a}{c}{r'}{i}{q}'
+            '{a}{c}{r'}{i}{n}'
+            '{ye}{c}{i}{q}'
+            '{a}{c}{i}{q}'
+            '{ye}{c}{i}{n}'
+            '{a}{c}{i}{n}'
+            '{a}{c}{a}{r'}'
+            '{a}{c}{a}{v}'
+            '{a}{c}{a}{n}{q}'
+            '{a}{c}{a}{q}'
+            '{a}{c}{a}{n}'
+            '{v}{ye}{c}{i}'
+            '{a}{c}{r'}{i}'
+            '{ye}{c}{a}{r'}'
+            '{ye}{c}{a}{v}'
+            '{c}{a}{n}{q}'
+            '{c}{a}{q}'
+            '{c}{a}{n}'
+            '{a}{c}{a}'
+            '{a}{c}{i}'
+            '{ye}{c}{a}'
+            '{ch}{ye}{l}'
+            '{ye}{c}{i}'
+            '{a}{r'}'
+            '{a}{v}'
+            '{a}{n}{q}'
+            '{a}{q}'
+            '{a}{n}'
+            '{a}{l}'
+            '{ye}{l}'
+            '{ye}{c}'
+            '{a}{c}'
+            '{v}{ye}'
+            '{a}'
+
+                (delete)
+        )
+    )
+
+    define noun as (
+        [substring] among (
+            '{a}{ts}{vo}'
+            '{a}{n}{a}{k}'
+            '{a}{n}{o}{c}'
+            '{a}{r'}{a}{n}'
+            '{a}{r'}{q}'
+            '{p}{a}{n}'
+            '{s}{t}{a}{n}'
+            '{ye}{gh}{e}{n}'
+            '{ye}{n}{q}'
+            '{i}{k}'
+            '{i}{ch}'
+            '{i}{q}'
+            '{m}{vo}{u}{n}{q}'
+            '{j}{a}{k}'
+            '{j}{vo}{u}{n}'
+            '{vo}{n}{q}'
+            '{vo}{r'}{d}'
+            '{vo}{c}'
+            '{ch}{ye}{q}'
+            '{v}{a}{ts}{q}'
+            '{v}{vo}{r'}'
+            '{a}{v}{vo}{r'}'
+            '{vo}{u}{dt}{j}{vo}{u}{n}'
+            '{vo}{u}{k}'
+            '{vo}{u}{h}{i}'
+            '{vo}{u}{j}{dt}'
+            '{vo}{u}{j}{q}'
+            '{vo}{u}{s}{t}'
+            '{vo}{u}{s}'
+            '{c}{i}'
+            '{a}{l}{i}{q}'
+            '{a}{n}{i}{q}'
+            '{i}{l}'
+            '{i}{ch}{q}'
+            '{vo}{u}{n}{q}'
+            '{g}{a}{r'}'
+            '{vo}{u}'
+            '{a}{k}'
+            '{a}{n}'
+            '{q}'
+
+                (delete)
+        )
+    )
+
+    define ending as (
+        [substring] R2 among (
+            '{n}{ye}{r'}{y}'
+            '{n}{ye}{r'}{n}'
+            '{n}{ye}{r'}{i}'
+            '{n}{ye}{r'}{d}'
+            '{ye}{r'}{i}{c}'
+            '{n}{ye}{r'}{i}{c}'
+            '{ye}{r'}{i}'
+            '{ye}{r'}{d}'
+            '{ye}{r'}{n}'
+            '{ye}{r'}{y}'
+            '{n}{ye}{r'}{i}{n}'
+            '{vo}{u}{dt}{j}{a}{n}{n}'
+            '{vo}{u}{dt}{j}{a}{n}{y}'
+            '{vo}{u}{dt}{j}{a}{n}{s}'
+            '{vo}{u}{dt}{j}{a}{n}{d}'
+            '{vo}{u}{dt}{j}{a}{n}'
+            '{ye}{r'}{i}{n}'
+            '{i}{n}'
+            '{s}{a}'
+            '{vo}{dj}'
+            '{i}{c}'
+            '{ye}{r'}{vo}{v}'
+            '{n}{ye}{r'}{vo}{v}'
+            '{ye}{r'}{vo}{u}{m}'
+            '{n}{ye}{r'}{vo}{u}{m}'
+            '{vo}{u}{n}'
+            '{vo}{u}{d}'
+            '{v}{a}{n}{s}'
+            '{v}{a}{n}{y}'
+            '{v}{a}{n}{d}'
+            '{a}{n}{y}'
+            '{a}{n}{d}'
+            '{v}{a}{n}'
+            '{vo}{dj}{y}'
+            '{vo}{dj}{s}'
+            '{vo}{dj}{d}'
+            '{vo}{c}'
+            '{vo}{u}{c}'
+            '{vo}{dj}{i}{c}'
+            '{c}{i}{c}'
+            '{v}{i}{c}'
+            '{v}{i}'
+            '{v}{vo}{v}'
+            '{vo}{v}'
+            '{a}{n}{vo}{v}'
+            '{a}{n}{vo}{u}{m}'
+            '{v}{a}{n}{i}{c}'
+            '{a}{m}{b}'
+            '{a}{n}'
+            '{n}{ye}{r'}'
+            '{ye}{r'}'
+            '{v}{a}'
+            '{y}'
+            '{n}'
+            '{d}'
+            '{c}'
+            '{i}'
+
+                (delete)
+        )
+    )
+)
+
+define stem as (
+
+    do mark_regions
+    backwards setlimit tomark pV for (
+        do ending
+        do verb
+        do adjective
+        do noun
+    )
+)

data/vendor/snowball/algorithms/basque.sbl

@@ -0,0 +1,149 @@
+routines (
+           aditzak
+           izenak
+           adjetiboak
+           mark_regions
+           RV R2 R1
+)
+
+externals ( stem )
+
+integers ( pV p1 p2 )
+
+groupings ( v )
+
+stringescapes {}
+
+/* special characters */
+
+stringdef n~ '{U+00F1}'
+
+define v 'aeiou'
+
+define mark_regions as (
+
+    $pV = limit
+    $p1 = limit
+    $p2 = limit  // defaults
+
+    do (
+        ( v (non-v gopast v) or (v gopast non-v) )
+        or
+        ( non-v (non-v gopast v) or (v next) )
+        setmark pV
+    )
+    do (
+        gopast v gopast non-v setmark p1
+        gopast v gopast non-v setmark p2
+    )
+)
+
+backwardmode (
+
+    define RV as $pV <= cursor
+    define R2 as $p2 <= cursor
+    define R1 as $p1 <= cursor
+
+    define aditzak as (
+        [substring] among(
+            'le' 'la' 'tzaile' 'aldatu' 'atu' 'tzailea' 'taile' 'tailea' 'pera' 'gale' 'galea'
+            'gura' 'kura' 'kor' 'korra' 'or' 'orra' 'tun' 'tuna' 'gaitz' 'gaitza'
+            'kaitz' 'kaitza' 'ezin' 'ezina' 'tezin' 'tezina' 'errez' 'erreza'
+            'karri' 'karria' 'tzaga' 'tzaka' 'tzake' 'tzeke' 'ez' 'eza' 'tzez'
+            'keta' 'eta' 'etan' 'pen' 'pena' 'tze' 'atze' 'kuntza' 'kunde' 'kundea'
+            'kune' 'kunea' 'kuna' 'kera' 'era' 'kizun' 'kizuna' 'dura' 'tura' 'men' 'mena'
+            'go' 'ago' 'tio' 'taldi' 'taldia' 'aldi' 'aldia' 'gune' 'gunea' 'bide' 'bidea'
+            'pide' 'pidea' 'gai' 'gaia' 'ki' 'kin' 'rekin' 'kina' 'kari' 'karia' 'ari' 'tari' 'etari'
+            'gailu' 'gailua' 'kide' 'kidea' 'ide' 'idea' 'du' 'ka' 'kan' 'an' 'ean' 'tu' 'lari' 'tatu'
+            'rean' 'tarazi' 'arazi' 'tzat' 'bera' 'dako'
+            ( RV delete )
+            'garri' 'garria' 'tza'
+            (R2 delete)
+            'atseden'
+            (<- 'atseden')
+            'arabera'
+            (<- 'arabera')
+            'baditu'
+            (<- 'baditu')
+
+        )
+    )
+
+    define izenak as (
+        [substring] among(
+            'ari' 'aria' 'bizia' 'kari' 'karia' 'lari' 'laria' 'tari' 'taria' 'zain' 'zaina'
+            'tzain' 'tzaina' 'zale' 'zalea' 'tzale' 'tzalea' 'aizun' 'orde' 'ordea'
+            'burua' 'ohi' 'ohia' 'kintza' 'gintzo' 'gintzu' 'tzu' 'tzua'
+            'tzo' 'tzoa' 'kuntza' 'talde' 'taldea' 'eria' 'keria' 'teria' 'di'
+            'za' 'ada' 'tara' 'etara' 'tra' 'ta' 'tegi' 'tegia' 'keta' 'z' 'zko' 'zkoa'
+            'ti' 'tia' 'tsu' 'tsua' 'zu' 'zua' 'bera' 'pera' 'zto' 'ztoa' 'asi' 'asia'
+            'gile' 'gilea' 'estu' 'estua' 'larri' 'larria' 'nahi' 'nahia'
+            'koi' 'koia' 'oi' 'oia' 'goi' 'min' 'mina' 'dun' 'duna' 'duru' 'durua'
+            'duri' 'duria' 'os' 'osa' 'oso' 'osoa' 'ar' 'ara' 'tar' 'dar' 'dara'
+            'tiar' 'tiara' 'liar' 'liara' 'gabe' 'gabea' 'kabe' 'kabea' 'ga' 'ge'
+            'kada' 'tasun' 'tasuna' 'asun' 'asuna' 'go' 'mendu' 'mendua' 'mentu' 'mentua'
+            'mendi' 'mendia' 'zio' 'zioa' 'zino' 'zinoa' 'zione' 'zionea' 'ezia'
+            'degi' 'degia' 'egi' 'egia' 'toki' 'tokia' 'leku' 'lekua' 'gintza' 'alde'
+            'aldea' 'kalde' 'kaldea' 'gune' 'gunea' 'une' 'unea' 'una' 'pe' 'pea'
+            'gibel' 'gibela' 'ondo' 'ondoa' 'arte' 'artea' 'aurre' 'aurrea'
+            'etxe' 'etxea' 'ola' 'ontzi' 'ontzia' 'gela' 'denda' 'taldi' 'taldia'
+            'aldi' 'aldia' 'te' 'tea' 'zaro' 'zaroa' 'taro' 'taroa' 'oro' 'oroa'
+            'aro' 'aroa' 'ero' 'eroa' 'eroz' 'eroza' 'ka' 'kan' 'kana' 'tako' 'etako' 'takoa'
+            'kote' 'kotea' 'tzar' 'tzarra' 'handi' 'handia' 'kondo' 'kondoa' 'skila'
+            'no' 'noa' '{n~}o' '{n~}oa' 'ska' 'xka' 'zka' 'tila' 'to' 'toa' 'tto' 'ttoa'
+            'txo' 'txoa' 'txu' 'txua' 'anda' 'anga' 'urren' 'urrena' 'gai' 'gaia'
+            'gei' 'geia' 'eme' 'emea' 'kume' 'kumea' 'sa' 'ko' 'eko' 'koa' 'ena'
+            'enea' 'ne' 'nea' 'kor' 'korra' 'ez' 'eza' 'eta' 'etan'
+            'ki' 'kia' 'kin' 'kina' 'tu' 'tua' 'du' 'dua' 'ek'
+            'tarik' 'tariko' 'tan' 'ordu' 'ordua' 'oste' 'ostea' 'tzara'
+            'ra' 'antza' 'behar' 'ro' 'giro' 'ak' 'zp' 'ket'
+            'kail' 'kaila' 'ail' 'kirri' 'kirria' 'ngo' 'ngoa' '{n~}i' 'sko'
+            'sta' 'koitz' 'koitza' 'na' 'garren' 'garrena' 'kera'
+            'gerren' 'gerrena' 'garna' 'kide' 'tz' 'tuko'
+            ( RV delete )
+            'ora' 'garri' 'garria' 'or' 'buru' 'ren' 'tza'
+            ( R2 delete )
+            'joka'
+            (<- 'jok')
+            'tzen' 'ten' 'en' 'tatu'
+            (R1 delete)
+            'trako'
+            (<- 'tra')
+            'minutuko'
+            (<- 'minutu')
+            'zehar'
+            (<- 'zehar')
+            'geldi'
+            (<- 'geldi')
+            'igaro'
+            (<- 'igaro')
+            'aurka'
+            (<- 'aurka')
+        )
+    )
+
+    define adjetiboak as (
+        [substring] among(
+            'era' 'ero' 'go' 'tate' 'tade' 'date' 'dade' 'keria'
+            'ki' 'to' 'ro' 'la' 'gi' 'larik' 'lanik' 'ik' 'ztik' 'rik'
+            ( RV delete )
+            'zlea'
+            (<- 'z')
+        )
+    )
+
+)
+
+define stem as (
+    do mark_regions
+    backwards (
+        repeat aditzak
+        repeat izenak
+        do adjetiboak
+    )
+
+)
+
+/*
+    Note 1: additions of 21 Jul 2010
+*/

data/vendor/snowball/algorithms/catalan.sbl

@@ -0,0 +1,202 @@
+routines (
+           cleaning mark_regions
+           R1  R2
+           attached_pronoun
+           standard_suffix
+           verb_suffix
+           residual_suffix
+)
+
+externals ( stem )
+
+integers ( p1 p2 )
+
+groupings ( v )
+
+stringescapes {}
+
+/* special characters */
+
+stringdef a'   '{U+00E1}'  // a-acute
+stringdef a`   '{U+00E0}'  // a-grave
+stringdef c,   '{U+00E7}'  // c-cedilla
+stringdef e'   '{U+00E9}'  // e-acute
+stringdef e`   '{U+00E8}'  // e-grave
+stringdef i'   '{U+00ED}'  // i-acute
+stringdef i`   '{U+00EC}'  // i-grave
+stringdef i"   '{U+00EF}'  // i-diaeresis
+stringdef o'   '{U+00F3}'  // o-acute
+stringdef o`   '{U+00F2}'  // o-grave
+stringdef u'   '{U+00FA}'  // u-acute
+stringdef u"   '{U+00FC}'  // u-diaeresis
+stringdef .    '{U+00B7}'   // - per l aggeminades
+
+define v 'aeiou{a'}{a`}{e'}{e`}{i'}{i"}{o'}{o`}{u'}{u"}'
+
+define mark_regions as (
+
+    $p1 = limit
+    $p2 = limit  // defaults
+
+    do (
+        gopast v gopast non-v setmark p1
+        gopast v gopast non-v setmark p2
+    )
+)
+
+define cleaning as repeat (
+    [substring] among(
+        '{a'}' (<- 'a')
+        '{a`}' (<- 'a')
+        '{e'}' (<- 'e')
+        '{e`}' (<- 'e')
+        '{i'}' (<- 'i')
+        '{i`}' (<- 'i')
+        '{o'}' (<- 'o')
+        '{o`}' (<- 'o')
+        '{u'}' (<- 'u')
+        '{u"}' (<- 'u')
+        '{i"}' (<- 'i')
+        '{.}' (<- '.')
+        ''     (next)
+    )
+)
+
+backwardmode (
+
+    define R1 as $p1 <= cursor
+    define R2 as $p2 <= cursor
+
+    define attached_pronoun as (
+    [substring] among (
+        '{'}s'  '{'}hi' '{'}ho' '{'}l' '{'}ls'
+        '-ls' '-la' '-les' '-li'
+        'vos' 'se'  'nos' '-nos' '-us' 'us'
+        '{'}n' '{'}ns' '-n' '-ns'
+        '{'}m' '-me' '-m'
+        '-te' '{'}t'
+        'li' 'lo' 'los'
+        'me'  'sela' 'selo' 'selas' 'selos' 'le'
+        'la' 'las' 'les' 'ens' 'ho' 'hi'
+        (R1 delete)
+    )
+    )
+
+    define standard_suffix as (
+        [substring] among(
+            'ar' 'atge' 'formes' 'icte' 'ictes'
+            'ell' 'ells' 'ella'  '{e'}s' '{e`}s' 'esc' 'essa' 'et' 'ets' 'eta'
+            'eres' 'eries' 'ers' 'ina' 'ines' 'able' 'ls'
+            'i{o'}' 'itat' 'itats' 'itzar' 'iva' 'ives' 'ivisme' 'ius'
+            'fer' 'ment' 'amen' 'ament' 'aments' 'ments' 'ot' 'sfera' 'al' 'als' 'era' 'ana' 'iste'
+            'aire' 'eria' 'esa' 'eses' 'esos' 'or' '{i'}cia' '{i'}cies' 'icis' 'ici' '{i'}ci' '{i'}cis'
+            '{a`}ria' '{a`}ries' 'alla' 'ci{o'}' 'cions' 'n{c,}a' 'nces' '{o'}' 'dor' 'all'
+            'il' '{i'}stic' 'enc' 'enca' '{i'}s' 'issa' 'issos' '{i'}ssem' '{i'}ssiu' 'issem' 'isseu' '{i'}sseu'
+            '{o'}s' 'osa'  'dora' 'dores' 'dors' 'adura' 'ble' 'bles' '{i'}vol' '{i'}vola' 'd{i'}s' 'egar' 'ejar' 'ificar'
+            'itar' 'ables' 'adors' 'idores' 'idors'
+            'adora' 'aci{o'}' 'doras' 'dur' 'dures' 'alleng{u"}es'
+            'ant' 'ants' 'ancia' 'ancies' 'at{o`}ria' 'at{o`}ries' 'tori' 'toris'
+            'ats' 'ions'  'ota' 'isam' 'ors' 'ora' 'ores' 'isament'
+            'bilitat' 'bilitats' 'ivitat' 'ivitats' 'ari' 'aris' 'ionisme' 'ionista' 'ionistes'
+            'ialista' 'ialistes' 'ialisme' 'ialismes' 'ud' 'uts' 'uds' 'encia' 'encies' '{e`}ncia' '{e`}ncies'
+            '{i"}tat' '{i"}tats' 'atiu' 'atius' 'atives' 'ativa' 'ativitat' 'ativitats' 'ible' 'ibles'
+            'assa' 'asses' 'assos'
+             'ent' 'ents'
+             '{i'}ssim' '{i'}ssima' '{i'}ssims' '{i'}ssimes' '{i`}ssem' '{i`}sseu' '{i`}ssin'
+             'ims' 'ima' 'imes'
+             'isme' 'ista' 'ismes' 'istes'
+             'inia' 'inies' '{i'}inia' '{i'}nies' 'ita' 'ites' 'triu' 'trius'
+             'oses' 'osos' 'ient' 'otes' 'ots'
+            (R1 delete)
+            'acions' 'ada' 'ades'
+            (R2 delete)
+            'log{i'}a' 'log{i'}es''logia' 'logies' 'logi' 'logis' 'l{o'}gica' 'l{o'}gics' 'l{o'}giques'
+            (R2 <- 'log')
+            'ic' 'ica' 'ics' 'iques'
+            (R2 <- 'ic')
+            'qu{i'}ssim' 'qu{i'}ssims' 'qu{i'}ssimes' 'qu{i'}ssima'
+            (R1 <- 'c')
+        )
+    )
+
+    define verb_suffix as (
+        [substring] among(
+            'ador' 'adora'  'adors' 'adores' 're' 'ie'
+             'ent' 'ents' 'udes' 'ar{a`}' 'eren'
+            'ar{a'}' 'ar{i'}an' 'ar{i'}as' 'ar{a'}n' 'ar{a'}s' 'ar{i'}ais'
+            'aria' 'arian' 'arien' 'aries' 'ar{a`}s'
+            'ar{i'}a' 'ar{e'}is' 'ar{i'}amos' 'aremos' 'ara'
+            'ar{e'}' 'ar{e'}s'
+            'er{i'}an' 'er{i'}as' 'er{a'}n' 'er{a'}s' 'er{i'}ais'
+            'er{i'}a' 'er{e'}is' 'er{i'}amos' 'eremos' 'er{a'}'
+            'er{e'}' 'er' 'erau' 'erass'
+            'ir{i'}an' 'ir{i'}as' 'ir{a'}n' 'ir{a'}s' 'ir{i'}ais'
+            'ir{i'}a' 'ir{e'}is' 'ir{i'}amos' 'iremos' 'ir{a'}'
+            'ir{e'}' '{i'}rem' '{i'}reu' '{i'}eu'
+            'ia' 'ies' '{i'}em' '{i`}eu' 'ien'
+            'at' 'ut' 'uda' 'ava' 'aves' 'avem' '{a'}vem' '{a`}vem' '{a`}veu' '{a'}veu' 'aven' 'au' 'ats'
+            'asseu' 'esseu' 'eresseu' '{a`}sseu' '{a`}ssem' '{a`}ssim' '{a`}ssiu'
+            'essen' 'esses' 'assen' 'asses' 'assim' 'assiu'
+            '{e'}ssen' '{e'}sseu'  '{e'}ssim' '{e'}ssiu' '{e'}ssem'
+            '{i'}' 'ares' '{a`}rem' '{a`}reu' '{a`}ren'
+            'ar{i'}em' 'ar{i'}eu'
+            'areu' 'aren' 'ant' '{i"}m' '{i"}u'
+            '{e'}s' '{i"}en' 'en' 'es' 'em' 'am' 'ams' '{i"}a' '{i"}es'
+            'dre' 'eix' 'eixer' 'tzar' 'eixes' 'ides' '{i"}des' 'it' '{i"}t' '{i"}da'
+            'aba' 'ada' 'ades' 'ida' '{i'}a' 'iera' 'ad' 'ed' 'its'
+            'id' 'ids'  'ase' 'iese' 'aste' 'iste' 'an' 'aban' '{i'}an'
+            'aran' 'ieran' 'asen' 'iesen' 'aron' 'ieron' 'ado'
+            'ido' 'iendo' 'i{o'}' 'ar' 'ir' 'as'
+            'ieu' 'ii' 'io' 'i{a`}'
+            'ess' 'essin' 'essis'  'ass' 'assin' 'assis' 'essim' '{e`}ssim' '{e`}ssiu'
+            'abas' 'adas' 'idas' '{i'}as' 'aras' 'ieras' 'ases'
+            'ieses' '{i'}s' '{a'}is' 'abais' '{i'}ais' 'arais'
+            'ierais'  'aseis' 'ieseis' 'asteis' 'isteis' 'ados'
+            'idos' 'amos' '{a'}bamos' '{i'}amos' 'imos' 'ques'
+            '{a'}ramos' 'i{e'}ramos' 'i{e'}semos' '{a'}semos'
+            'ira' 'iran' 'irem' 'iren' 'ires' 'ireu' 'iria' 'irien'
+            'iries' 'ir{a`}' 'ir{a`}s' 'ir{e`}' 'ir{i`}em' 'ir{i`}eu'
+            'isquen' 'iguem' 'igueu' 'esqui' 'esquin' 'esquis' 'eixi' 'eixin' 'eixis'
+            'eixen' 'eixo' 'isin' 'isis'  'esques' 'sis' 'sin'
+            'int' 'ir{i'}em' 'ir{i'}eu' 'isc' 'atges' 'esca' 'esquen'
+            'issen' 'isses' 'issin' 'issis' 'isca' 'issiu' 'issim'
+            '{i"}sc' '{i"}sca' '{i"}ssin' '{i'}ssiu' '{i'}ssim' '{i"}ssis' '{i"}guem' '{i"}gueu'
+            '{i"}ra' '{i"}ren' '{i"}res'
+            '{i"}squen' '{i"}sques' '{i"}ssen' '{i"}sses' '{i"}xo' '{i"}xen' '{i"}xes' '{i"}x'
+            'ixo' 'ixen' 'ixes' 'ix' 'ixa' 'inin' 'inis' 'ini' 'ineu' 'itza' 'itzi' 'itzeu' 'itzis'
+            'itzo' 'itz' 'itz{a`}' 'arem' 'in' '{a`}s' 'i{i"}' 'i{i"}n' 'i{i"}s'
+                (R1 delete)
+            'ando'
+                (R2 delete)
+        )
+    )
+
+    define residual_suffix as (
+        [substring] among(
+            'os' 'a' 'o' '{a'}' '{a`}' '{i'}' '{o'}' 'e' '{e'}' 'eu' 'iu'
+            'is' 'i' 'ir'  's' '{i`}' 'itz' '{i"}' '{i"}n' '{i"}s' 'it'
+            (R1 delete)
+            'iqu'
+            (R1 <- 'ic')
+        )
+    )
+)
+
+define stem as (
+    do mark_regions
+    backwards (
+    do attached_pronoun
+    do ( standard_suffix or
+             verb_suffix
+           )
+        do residual_suffix
+    )
+    do cleaning
+)
+
+/*
+     First works 2010/07/19
+     First Grammatical Reviews: https://ca.wikipedia.org/wiki/Gram%C3%A0tica_del_catal%C3%A0
+     Suffix list: https://ca.wikipedia.org/wiki/Llista_de_sufixos
+     Irregular Verbs: https://ca.wikipedia.org/wiki/Flexi%C3%B3_verbal_del_catal%C3%A0
+*/