mittens 0.2.0 → 0.3.0

data/vendor/snowball/algorithms/indonesian.sbl

@@ -62,9 +62,9 @@ backwardmode (
     // prefix not in {ke, peng, per}
     define SUFFIX_KAN_OK as (
         // On page 29, the example "kompas Q.31" says "Both Nazief and Porter
-        // stemmer converted the word peledakan (blast, explotion) to ledak (to
-        // blast, to explode)".  However, the algorithm as described doesn't
-        // behave in this way - grammatically the prefix pe- occurs as a
+        // stemmer converted the word peledakan (blast, explotion [sic]) to
+        // ledak (to blast, to explode)".  However, the algorithm as described
+        // doesn't behave in this way - grammatically the prefix pe- occurs as a
         // variation of both the first-order derivational prefix peng- and the
         // second-order derivational prefix per-, but table 2.5 doesn't include
         // "pe", only table 2.6 does, so "peledakan" is handled (incorrectly)
@@ -104,13 +104,19 @@ backwardmode (
         //
         // Elsewhere the paper defines V... as meaning "the stem starts with
         // a vowel" and K... as meaning "the stem starts with a consonant".
+        // The meaning of | isn't actually defined, but clearly means
+        // alternation.
         //
-        // In other places where it says X|Y... it seems the | binds more
+        // However nowhere is the precedence of | vs ... defined, and there
+        // isn't a standard precedence we could reasonably assume.  In other
+        // places where the paper says X|Y... it seems the | binds more
         // tightly, so it's (V|K)...cᵢcⱼ not V|(K...cᵢcⱼ).  That seems a bit
         // odd as the first letter must be either a vowel or a consonant, so
-        // that really just means "ends cᵢcⱼ".  However, nowhere in the paper
-        // uses or defines a notation such as ...X, which may explain this
-        // seemingly redundant way of specifying this.
+        // that really just means "ends cᵢcⱼ" (and has at least one letter
+        // before cᵢ but we only call SUFFIX_I_OK if $measure > 2 which
+        // ensures that part).  However, nowhere in the paper uses or defines
+        // a notation such as ...X, which may explain this seemingly redundant
+        // way of specifying this.
         //
         // The conditions elsewhere on prefix removal (e.g. V...) are clearly
         // on the stem left after the prefix is removed.  None of the other
@@ -118,7 +124,7 @@ backwardmode (
         // consistency with the prefix rules we might expect that the cᵢcⱼ
         // test is on what's left *after* removing the "i" suffix.
         //
-        // However, studying Indonesian wordlists and discussion with a native
+        // Studying Indonesian wordlists and discussion with a native
         // speaker leads us to conclude that the purpose of this check is to
         // protect words of foreign origin (e.g. "televisi", "organisasi",
         // "komunikasi") from stemming, and the common feature of these is

data/vendor/snowball/algorithms/italian.sbl

@@ -1,6 +1,5 @@
 
 routines (
-           exceptions
            prelude postlude mark_regions
            RV R1 R2
            attached_pronoun
@@ -59,6 +58,8 @@ define mark_regions as (
     do (
         ( v (non-v gopast v) or (v gopast non-v) )
         or
+        'divan' // Otherwise "divano" stems to "div" and collides with "diva".
+        or
         ( non-v (non-v gopast v) or (v next) )
         setmark pV
     )
@@ -108,7 +109,7 @@ backwardmode (
             'ismi' 'abile' 'abili' 'ibile' 'ibili' 'ista' 'iste' 'isti'
             'ist{a`}' 'ist{e`}' 'ist{i`}' 'oso' 'osi' 'osa' 'ose' 'mente'
             'atrice' 'atrici'
-            'ante' 'anti' // Note 1
+            'ante' 'anti'
                ( R2 delete )
             'azione' 'azioni' 'atore' 'atori'
                ( R2 delete
@@ -179,24 +180,13 @@ backwardmode (
     )
 )
 
-define exceptions as (
-    ['divano' atlimit ] <- 'divan' // Otherwise "divano" stems to "div" and collides with "diva"
-)
-
 define stem as (
-    exceptions or (
-        do prelude
-        do mark_regions
-        backwards (
-            do attached_pronoun
-            do (standard_suffix or verb_suffix)
-            do vowel_suffix
-        )
-        do postlude
-    )
+      do prelude
+      do mark_regions
+      backwards (
+          do attached_pronoun
+          do (standard_suffix or verb_suffix)
+          do vowel_suffix
+      )
+      do postlude
 )
-
-/*
-    Note 1: additions of 15 Jun 2005
-*/
-

data/vendor/snowball/algorithms/lithuanian.sbl

@@ -5,10 +5,10 @@ stringescapes { }
 
 /* Special characters in Unicode Latin Extended-A */
 // ' nosine
-stringdef a'   '{U+0105}'  // ą a + ogonek
-stringdef e'   '{U+0119}'  // ę e + ogonek
-stringdef i'   '{U+012F}'  // į i + ogonek
-stringdef u'   '{U+0173}'  // ų u + ogonek
+stringdef ak   '{U+0105}'  // ą a + ogonek
+stringdef ek   '{U+0119}'  // ę e + ogonek
+stringdef ik   '{U+012F}'  // į i + ogonek
+stringdef uk   '{U+0173}'  // ų u + ogonek
 
 // . taskas
 stringdef e.   '{U+0117}'  // ė e + dot
@@ -16,10 +16,10 @@ stringdef e.   '{U+0117}'  // ė e + dot
 // - ilgoji
 stringdef u-   '{U+016B}'  // ū u + macron
 
-// * varnele
-stringdef c*   '{U+010D}'  // č c + caron (haček)
-stringdef s*   '{U+0161}'  // š s + caron (haček)
-stringdef z*   '{U+017E}'  // ž z + caron (haček)
+// v varnele
+stringdef cv   '{U+010D}'  // č c + caron (haček)
+stringdef sv   '{U+0161}'  // š s + caron (haček)
+stringdef zv   '{U+017E}'  // ž z + caron (haček)
 
 // [C](VC)^m[V|C]
 // definitions of variables for
@@ -31,31 +31,30 @@ integers ( p1 )
 groupings ( v )
 
 // v - all lithuanian vowels
-define v 'aeiyou{a'}{e'}{i'}{u'}{e.}{u-}'
+define v 'aeiyou{ak}{ek}{ik}{uk}{e.}{u-}'
 
 // all lithuanian stemmer routines: 4 steps
 routines (
-  step2 R1 step1 fix_chdz fix_gd fix_conflicts
+  step2 step1 fix_chdz fix_gd fix_conflicts
 )
 
 backwardmode (
 
-  define R1 as $p1 <= cursor
   define step1 as (
-    setlimit tomark p1 for ([substring]) R1 among (
+    setlimit tomark p1 for ([substring]) among (
       // Daiktavardžiai (Nouns)
       // I linksniuotė (declension I)
       'as' 'ias' 'is' 'ys'        // vyras, kelias, brolis, gaidys
       'o'    'io'                 // vyro, kelio
       'ui'   'iui'                // vyrui, keliui
-      '{a'}' 'i{a'}' '{i'}'       // vyrą, kelią, brolį
+      '{ak}' 'i{ak}' '{ik}'       // vyrą, kelią, brolį
       'u'    'iu'                 // vyru, keliu
       'e'    'yje'                // vyre, kelyje
       'y'    'au'    'i'          // kely, brolau, broli,
       'an'                        // nusižengiman
 
       'ai'   'iai'                // vyrai, keliai
-      '{u'}' 'i{u'}'              // vyrų, kelių
+      '{uk}' 'i{uk}'              // vyrų, kelių
       'ams'  'am'                 // vyrams, vyram
       'iams' 'iam'                // broliams, broliam
       'us'   'ius'                // vyrus, brolius
@@ -65,9 +64,9 @@ backwardmode (
       'ysna'                      // žutysna
 
       'asis' 'aisi'               // sukimasis, sukimaisi
-      'osi'  '{u'}si'             // sukimosi, sukimųsi
+      'osi'  '{uk}si'             // sukimosi, sukimųsi
       'uisi'                      // sukimuisi
-      '{a'}si'                    // sukimąsi
+      '{ak}si'                    // sukimąsi
       'usi'                       // sukimusi
       'esi'                       // sukimesi
 
@@ -89,7 +88,7 @@ backwardmode (
       '{e.}'                      // gervė
       '{e.}s'                     // gervės
       'ei'                        // gervei
-      '{e'}'                      // gervę
+      '{ek}'                      // gervę
       '{e.}j' '{e.}je'            // gervėj, gervėje
       '{e.}ms'                    // gervėms
       'es'                        // gerves
@@ -114,14 +113,14 @@ backwardmode (
       // V linksniuote (declension V)
       'ies' 'ens' 'enio' 'ers'    // avies, vandens, sesers
       'eniui' 'eriai'             // vandeniui, eriai
-      'en{i'}' 'er{i'}'           // vandenį, seserį
+      'en{ik}' 'er{ik}'           // vandenį, seserį
       'imi' 'eniu' 'erimi' 'eria' // avimi, vandeniu, seserimi, seseria
       'enyje' 'eryje'             // vandenyje, seseryje
       'ie' 'enie' 'erie'          // avie, vandenie, seserie
 
       'enys' 'erys'               // vandenys, seserys
-      // 'en{u'}' konfliktas su 'žandenų' 'antenų'
-      'er{u'}'                    // seserų
+      // 'en{uk}' konfliktas su 'žandenų' 'antenų'
+      'er{uk}'                    // seserų
       'ims' 'enims' 'erims'       // avims, vandemins, seserims
       'enis'                      // vandenis
       'imis'                      // žebenkštimis
@@ -184,11 +183,11 @@ backwardmode (
       'sit' 'site'                // gersit, gersite
 
       // tariamoji nuosaka (subjunctive mood)
-      '{c*}iau' '{c*}iausi'       // dirbčiau
+      '{cv}iau' '{cv}iausi'       // dirbčiau
       'tum' 'tumei'               // dirbtum, dirbtumei
       'tumeis' 'tumeisi'          // mokytumeis, mokytumeisi
-      // 't{u'}' nes blogai batutų -> batų
-      't{u'}si'                   // mokytųsi
+      // 't{uk}' nes blogai batutų -> batų
+      't{uk}si'                   // mokytųsi
       // 'tume' konfliktas su 'šventume'
       'tum{e.}m'                  // dirbtumėm
       'tum{e.}me'                 // dirbtumėme
@@ -219,8 +218,8 @@ backwardmode (
       // 'tis' konfliktas, nes rytme-tis -> rytme
 
       // dalyviai (participles)
-      '{a'}s' 'i{a'}s' '{i'}s'    // dirbąs, žaidžiąs, gulįs
-      't{u'}s'                    // suktųs -> suk
+      '{ak}s' 'i{ak}s' '{ik}s'    // dirbąs, žaidžiąs, gulįs
+      't{uk}s'                    // suktųs -> suk
       'sim{e.}s'                  // suksimės
       'sit{e.}s'                  // suksitės
       'kite'                      // supkite
@@ -236,7 +235,7 @@ backwardmode (
       // budvardziu priesagos (Adjective suffixes)
       // 'in' // konfliktas su 'augintinis' ir 'akiniais' // lauk-in-is
       'ing'                       // tvark-ing-as
-      'i{s*}k'                    // lenk-išk-as
+      'i{sv}k'                    // lenk-išk-as
       '{e.}t'                     // dem-ėt-as
       'ot'                        // garban-ot-as
       'uot' 'iuot'                // lang-uot-as, akin-iuot-as
@@ -247,15 +246,15 @@ backwardmode (
       'iul'                       // maž-ul-is
       '{e.}l'                     // maž-ėl-is
       'yl'                        // maž-yl-is
-      'u{c*}iuk'                  // maž-učiuk-as
+      'u{cv}iuk'                  // maž-učiuk-as
       'uliuk'                     // maž-uliuk-as
       'ut{e.}ait'                 // maž-utėlait-is
       'ok'                        // did-ok-as
       'iok'                       // višč-iok-as
-      'sv' '{s*}v' 'zgan'         // sal-sv-as, pilk-šv-as, bal-zgan-as
+      'sv' '{sv}v' 'zgan'         // sal-sv-as, pilk-šv-as, bal-zgan-as
       'op' 'iop'                  // dvej-op-as, viener-iop-as
       'ain'                       // apval-ain-as
-      'yk{s*}t' 'yk{s*}{c*}'      // ten-ykšt-is, vakar-ykšč-ias
+      'yk{sv}t' 'yk{sv}{cv}'      // ten-ykšt-is, vakar-ykšč-ias
 
       // laisniai
       'esn'                       // did-esn-is
@@ -266,17 +265,17 @@ backwardmode (
       'ias'                       // žaliasis
       'oj' 'ioj'                  // gerojo, žaliojo
       'aj' 'iaj'                  // gerajam, žaliajam
-      '{a'}j' 'i{a'}j'            // garąjį, žaliąjį
+      '{ak}j' 'i{ak}j'            // garąjį, žaliąjį
       'uoj' 'iuoj'                // geruoju, žaliuoju
       'iej'                       // gerieji
-      '{u'}j' 'i{u'}j'            // gerųjų, žaliųjų
+      '{uk}j' 'i{uk}j'            // gerųjų, žaliųjų
       'ies'                       // geriesiems
       'uos' 'iuos'                // geruosius, žaliuosius
       'ais' 'iais'                // geraisiais, žaliaisiais
 
       // moteriska gimine (Female gender)
       'os' 'ios'                  // gerosios, žaliosios
-      '{a'}s' 'i{a'}s'            // gerąsios, žaliąsias
+      '{ak}s' 'i{ak}s'            // gerąsios, žaliąsias
 
       // būtasis dažninis laikas (frequentative past tense)
       'dav'                       // ei-dav-o
@@ -285,9 +284,9 @@ backwardmode (
       'ant' 'iant'
       'int'                       // tur-int-is
       '{e.}j'                     // tur-ėj-o
-      '{e'}'                      //
-      '{e.}j{e'}'
-      '{e'}s'                     // dirb-ęs-is
+      '{ek}'                      //
+      '{e.}j{ek}'
+      '{ek}s'                     // dirb-ęs-is
 
       'siant'                     // dirb-siant
 
@@ -336,8 +335,8 @@ backwardmode (
 
   define fix_chdz as (
     [substring] among (
-      '{c*}' (<-'t')
-      'd{z*}' (<-'d')
+      '{cv}' (<-'t')
+      'd{zv}' (<-'d')
     )
   )
 

data/vendor/snowball/algorithms/lovins.sbl

@@ -205,4 +205,3 @@ define stem as (
     do respell
   )
 )
-

data/vendor/snowball/algorithms/nepali.sbl

@@ -6,10 +6,9 @@
  */
 
 routines (
-	remove_category_1
-	check_category_2
-	remove_category_2
-	remove_category_3
+  remove_category_1
+  remove_category_2
+  remove_category_3
 )
 
 stringescapes {}
@@ -49,44 +48,146 @@ stringdef dvsau   '{U+094C}'  // DEVANAGARI_VOWEL_SIGN_AU
 stringdef dsv     '{U+094D}'  // DEVANAGARI_SIGN_VIRAMA
 
 externals ( stem )
-backwardmode (
-	define remove_category_1 as(
-		[substring] among (
-			'{dlm}{dvsaa}{dlr}{dsv}{dlpha}{dlta}' '{dld}{dsv}{dlv}{dvsaa}{dlr}{dvsaa}' '{dls}{dsc}{dlg}{dvsai}' '{dls}{dsa}{dlg}'
-			'{dls}{dsc}{dlg}' '{dll}{dvsaa}{dli}' '{dll}{dvsaa}{dlii}' '{dlpa}{dlc}{dvsi}'
-			'{dll}{dvse}' '{dlr}{dlta}' '{dlm}{dvsai}' '{dlm}{dvsaa}'
-			(delete)
-			'{dlka}{dvso}' '{dlka}{dvsaa}' '{dlka}{dvsi}' '{dlka}{dvsii}' '{dlka}{dvsai}'(('{dle}' or '{dvse}' ()) or delete)
-		)
-	)
 
-	define check_category_2 as(
-		[substring] among(
-			'{dsc}' '{dsa}' '{dvsai}'
-		)
-	)
+backwardmode (
+  define remove_category_1 as(
+    [substring] among (
+      '{dlm}{dvsaa}{dlr}{dsv}{dlpha}{dlta}'
+      '{dld}{dsv}{dlv}{dvsaa}{dlr}{dvsaa}'
+      '{dls}{dsc}{dlg}{dvsai}'
+      '{dls}{dsa}{dlg}'
+      '{dls}{dsc}{dlg}'
+      '{dll}{dvsaa}{dli}'
+      '{dll}{dvsaa}{dlii}'
+      '{dlpa}{dlc}{dvsi}'
+      '{dll}{dvse}'
+      '{dlr}{dlta}'
+      '{dlm}{dvsai}'
+      '{dlm}{dvsaa}'
+        (delete)
+      '{dlka}{dvso}'
+      '{dlka}{dvsaa}'
+      '{dlka}{dvsi}'
+      '{dlka}{dvsii}'
+      '{dlka}{dvsai}'
+        ('{dle}' or '{dvse}' or delete)
+    )
+  )
 
-	define remove_category_2 as (
-		[substring] among(
-		'{dsc}' '{dsa}' ('{dly}{dvsau}' or '{dlc}{dvsau}' or '{dln}{dvsau}' or '{dltha}{dvse}' delete)
-		'{dvsai}' ('{dlta}{dsv}{dlr}' delete)
-		)
-	)
+  define remove_category_2 as (
+    [substring] among(
+      '{dsc}' '{dsa}'
+        ('{dly}{dvsau}' or '{dlc}{dvsau}' or '{dln}{dvsau}' or '{dltha}{dvse}' delete)
+      '{dvsai}'
+        ('{dlta}{dsv}{dlr}' delete)
+    )
+  )
 
-	define remove_category_3 as(
-		[substring] among(
-			'{dltha}{dvsi}{dli}{dls}{dsv}' '{dlh}{dvsu}{dln}{dvse}{dlc}' '{dlh}{dvsu}{dln}{dsv}{dlc}' '{dln}{dvse}{dlc}{dls}{dsv}' '{dln}{dvse}{dlc}{dln}{dsv}' '{dli}{dle}{dlka}{dvsii}' '{dli}{dle}{dlka}{dvsaa}' '{dli}{dle}{dlka}{dvso}' '{dvsi}{dle}{dlka}{dvsii}' '{dvsi}{dle}{dlka}{dvsaa}' '{dvsi}{dle}{dlka}{dvso}' '{dli}{dlc}{dln}{dsv}' '{dvsi}{dlc}{dln}{dsv}' '{dli}{dlc}{dls}{dsv}' '{dvsi}{dlc}{dls}{dsv}' '{dle}{dlc}{dln}{dsv}' '{dvse}{dlc}{dln}{dsv}' '{dle}{dlc}{dls}{dsv}' '{dvse}{dlc}{dls}{dsv}' '{dlc}{dvsi}{dln}{dsv}' '{dlc}{dvse}{dls}{dsv}' '{dlc}{dsv}{dly}{dvsau}' '{dltha}{dvsi}{dln}{dsv}' '{dltha}{dvsi}{dly}{dvso}' '{dltha}{dvsi}{dly}{dvsau}' '{dltha}{dvsi}{dls}{dsv}' '{dltha}{dsv}{dly}{dvso}' '{dltha}{dsv}{dly}{dvsau}' '{dld}{dvsi}{dly}{dvso}' '{dld}{dvse}{dlkha}{dvsi}' '{dld}{dvse}{dlkha}{dvsii}' '{dll}{dvsaa}{dln}{dsv}' '{dlm}{dvsaa}{dltha}{dvsi}' '{dln}{dvse}{dlka}{dvsai}' '{dln}{dvse}{dlka}{dvsaa}' '{dln}{dvse}{dlka}{dvso}' '{dln}{dvse}{dlc}{dvsau}' '{dlh}{dvso}{dls}{dsv}' '{dli}{dln}{dsv}{dlc}' '{dvsi}{dln}{dsv}{dlc}' '{dln}{dvse}{dlc}{dvsu}' '{dli}{dlc}{dvsau}' '{dvsi}{dlc}{dvsau}' '{dli}{dls}{dsv}' '{dvsi}{dls}{dsv}' '{dvsi}{dly}{dvso}' '{dli}{dly}{dvso}' '{dle}{dlka}{dvsaa}' '{dvse}{dlka}{dvsaa}' '{dle}{dlka}{dvsii}' '{dvse}{dlka}{dvsii}' '{dle}{dlka}{dvsai}' '{dvse}{dlka}{dvsai}' '{dle}{dlka}{dvso}' '{dvse}{dlka}{dvso}' '{dle}{dlc}{dvsu}' '{dvse}{dlc}{dvsu}' '{dle}{dlc}{dvsau}' '{dvse}{dlc}{dvsau}' '{dlc}{dln}{dsv}' '{dlc}{dls}{dsv}' '{dltha}{dvsi}{dle}' '{dlpa}{dlr}{dsv}' '{dlb}{dly}{dvso}' '{dlh}{dlr}{dvsu}' '{dlh}{dlr}{dvsuu}' '{dvsi}{dld}{dvsaa}' '{dli}{dld}{dvsaa}' '{dvsi}{dld}{dvso}' '{dli}{dld}{dvso}' '{dvsi}{dld}{dvsai}' '{dli}{dld}{dvsai}' '{dln}{dvse}{dlc}' '{dli}{dlc}' '{dvsi}{dlc}' '{dle}{dlc}' '{dvse}{dlc}' '{dlc}{dvsu}' '{dlc}{dvse}' '{dlc}{dvsau}' '{dltha}{dvsii}' '{dltha}{dvse}' '{dld}{dvsaa}' '{dld}{dvsii}' '{dld}{dvsai}' '{dld}{dvso}' '{dln}{dvsu}' '{dln}{dvse}' '{dly}{dvso}' '{dly}{dvsau}' '{dlc}'
-			(delete)
-		)
-	)
+  define remove_category_3 as(
+    [substring] among(
+      '{dltha}{dvsi}{dli}{dls}{dsv}'
+      '{dlh}{dvsu}{dln}{dvse}{dlc}'
+      '{dlh}{dvsu}{dln}{dsv}{dlc}'
+      '{dln}{dvse}{dlc}{dls}{dsv}'
+      '{dln}{dvse}{dlc}{dln}{dsv}'
+      '{dli}{dle}{dlka}{dvsii}'
+      '{dli}{dle}{dlka}{dvsaa}'
+      '{dli}{dle}{dlka}{dvso}'
+      '{dvsi}{dle}{dlka}{dvsii}'
+      '{dvsi}{dle}{dlka}{dvsaa}'
+      '{dvsi}{dle}{dlka}{dvso}'
+      '{dli}{dlc}{dln}{dsv}'
+      '{dvsi}{dlc}{dln}{dsv}'
+      '{dli}{dlc}{dls}{dsv}'
+      '{dvsi}{dlc}{dls}{dsv}'
+      '{dle}{dlc}{dln}{dsv}'
+      '{dvse}{dlc}{dln}{dsv}'
+      '{dle}{dlc}{dls}{dsv}'
+      '{dvse}{dlc}{dls}{dsv}'
+      '{dlc}{dvsi}{dln}{dsv}'
+      '{dlc}{dvse}{dls}{dsv}'
+      '{dlc}{dsv}{dly}{dvsau}'
+      '{dltha}{dvsi}{dln}{dsv}'
+      '{dltha}{dvsi}{dly}{dvso}'
+      '{dltha}{dvsi}{dly}{dvsau}'
+      '{dltha}{dvsi}{dls}{dsv}'
+      '{dltha}{dsv}{dly}{dvso}'
+      '{dltha}{dsv}{dly}{dvsau}'
+      '{dld}{dvsi}{dly}{dvso}'
+      '{dld}{dvse}{dlkha}{dvsi}'
+      '{dld}{dvse}{dlkha}{dvsii}'
+      '{dll}{dvsaa}{dln}{dsv}'
+      '{dlm}{dvsaa}{dltha}{dvsi}'
+      '{dln}{dvse}{dlka}{dvsai}'
+      '{dln}{dvse}{dlka}{dvsaa}'
+      '{dln}{dvse}{dlka}{dvso}'
+      '{dln}{dvse}{dlc}{dvsau}'
+      '{dlh}{dvso}{dls}{dsv}'
+      '{dli}{dln}{dsv}{dlc}'
+      '{dvsi}{dln}{dsv}{dlc}'
+      '{dln}{dvse}{dlc}{dvsu}'
+      '{dli}{dlc}{dvsau}'
+      '{dvsi}{dlc}{dvsau}'
+      '{dli}{dls}{dsv}'
+      '{dvsi}{dls}{dsv}'
+      '{dvsi}{dly}{dvso}'
+      '{dli}{dly}{dvso}'
+      '{dle}{dlka}{dvsaa}'
+      '{dvse}{dlka}{dvsaa}'
+      '{dle}{dlka}{dvsii}'
+      '{dvse}{dlka}{dvsii}'
+      '{dle}{dlka}{dvsai}'
+      '{dvse}{dlka}{dvsai}'
+      '{dle}{dlka}{dvso}'
+      '{dvse}{dlka}{dvso}'
+      '{dle}{dlc}{dvsu}'
+      '{dvse}{dlc}{dvsu}'
+      '{dle}{dlc}{dvsau}'
+      '{dvse}{dlc}{dvsau}'
+      '{dlc}{dln}{dsv}'
+      '{dlc}{dls}{dsv}'
+      '{dltha}{dvsi}{dle}'
+      '{dlpa}{dlr}{dsv}'
+      '{dlb}{dly}{dvso}'
+      '{dlh}{dlr}{dvsu}'
+      '{dlh}{dlr}{dvsuu}'
+      '{dvsi}{dld}{dvsaa}'
+      '{dli}{dld}{dvsaa}'
+      '{dvsi}{dld}{dvso}'
+      '{dli}{dld}{dvso}'
+      '{dvsi}{dld}{dvsai}'
+      '{dli}{dld}{dvsai}'
+      '{dln}{dvse}{dlc}'
+      '{dli}{dlc}'
+      '{dvsi}{dlc}'
+      '{dle}{dlc}'
+      '{dvse}{dlc}'
+      '{dlc}{dvsu}'
+      '{dlc}{dvse}'
+      '{dlc}{dvsau}'
+      '{dltha}{dvsii}'
+      '{dltha}{dvse}'
+      '{dld}{dvsaa}'
+      '{dld}{dvsii}'
+      '{dld}{dvsai}'
+      '{dld}{dvso}'
+      '{dln}{dvsu}'
+      '{dln}{dvse}'
+      '{dly}{dvso}'
+      '{dly}{dvsau}'
+      '{dlc}'
+        (delete)
+    )
+  )
 
 )
 
 define stem as (
-	backwards (
-		do remove_category_1
-			do (
-				repeat (do (check_category_2 and remove_category_2) remove_category_3)
-			)
-	)
+  backwards (
+    do remove_category_1
+    repeat (
+      do remove_category_2
+      remove_category_3
+    )
+  )
 )

data/vendor/snowball/algorithms/norwegian.sbl

@@ -17,18 +17,22 @@ stringescapes {}
 
 stringdef ae   '{U+00E6}'
 stringdef ao   '{U+00E5}'
+stringdef e^   '{U+00EA}'  // e-circumflex
+stringdef o`   '{U+00F2}'  // o-grave
+stringdef o'   '{U+00F3}'  // o-acute
+stringdef o^   '{U+00F4}'  // o-circumflex
 stringdef o/   '{U+00F8}'
 
-define v 'aeiouy{ae}{ao}{o/}'
+define v 'ae{e^}io{o`}{o'}{o^}uy{ae}{ao}{o/}'
 
-define s_ending  'bcdfghjlmnoprtvyz'
+define s_ending  'bcdfghjlmnoptvyz'
 
 define mark_regions as (
 
     $p1 = limit
 
     test ( hop 3 setmark x )
-    goto v  gopast non-v  setmark p1
+    gopast v  gopast non-v  setmark p1
     try ( $p1 < x  $p1 = x )
 )
 
@@ -40,10 +44,20 @@ backwardmode (
 
             'a' 'e' 'ede' 'ande' 'ende' 'ane' 'ene' 'hetene' 'en' 'heten' 'ar'
             'er' 'heter' 'as' 'es' 'edes' 'endes' 'enes' 'hetenes' 'ens'
-            'hetens' 'ers' 'ets' 'et' 'het' 'ast'
+            'hetens' 'ets' 'et' 'het' 'ast'
                 (delete)
+            'ers'
+                (
+                  among (
+                    'amm' 'ast' 'ind' 'kap' 'kk' 'lt' 'nk' 'omm' 'pp' 'v'
+                    '{o/}st'
+                        ()
+                    'giv' 'hav' 'skap' ''
+                        (delete)
+                  )
+                )
             's'
-                (s_ending or ('k' non-v) delete)
+                (s_ending or ('r' not 'e') or ('k' non-v) delete)
             'erte' 'ert'
                 (<-'er')
         )

data/vendor/snowball/algorithms/porter.sbl

@@ -38,11 +38,11 @@ backwardmode (
                 test gopast v  delete
                 test substring among(
                     'at' 'bl' 'iz'
-                         (<+ 'e')
+                         (insert 'e')
                     'bb' 'dd' 'ff' 'gg' 'mm' 'nn' 'pp' 'rr' 'tt'
                     // ignoring double c, h, j, k, q, v, w, and x
                          ([next]  delete)
-                    ''   (atmark p1  test shortv  <+ 'e')
+                    ''   (atmark p1  test shortv  insert 'e')
                 )
             )
         )

data/vendor/snowball/algorithms/portuguese.sbl

@@ -25,7 +25,7 @@ stringdef i'   '{U+00ED}'  // i-acute
 stringdef o^   '{U+00F4}'  // o-circumflex
 stringdef o'   '{U+00F3}'  // o-acute
 stringdef u'   '{U+00FA}'  // u-acute
-stringdef c,   '{U+00E7}'  // c-cedilla
+stringdef cc   '{U+00E7}'  // c-cedilla
 
 stringdef a~   '{U+00E3}'  // a-tilde
 stringdef o~   '{U+00F5}'  // o-tilde
@@ -38,7 +38,7 @@ define prelude as repeat (
         '{a~}' (<- 'a~')
         '{o~}' (<- 'o~')
         ''     (next)
-    ) //or next
+    )
 )
 
 define mark_regions as (
@@ -64,7 +64,7 @@ define postlude as repeat (
         'a~' (<- '{a~}')
         'o~' (<- '{o~}')
         ''   (next)
-    ) //or next
+    )
 )
 
 backwardmode (
@@ -86,9 +86,9 @@ backwardmode (
             'amento' 'amentos'
             'imento' 'imentos'
 
-           'adora' 'ador' 'a{c,}a~o'
-           'adoras' 'adores' 'a{c,}o~es'  // no -ic test
-           'ante' 'antes' '{a^}ncia' // Note 1
+           'adora' 'ador' 'a{cc}a~o'
+           'adoras' 'adores' 'a{cc}o~es'  // no -ic test
+           'ante' 'antes' '{a^}ncia'
             (
                 R2 delete
             )
@@ -97,7 +97,7 @@ backwardmode (
             (
                 R2 <- 'log'
             )
-            'u{c,}a~o' 'u{c,}o~es'
+            'u{cc}a~o' 'u{cc}o~es'
             (
                 R2 <- 'u'
             )
@@ -122,7 +122,7 @@ backwardmode (
                 R2 delete
                 try (
                     [substring] among(
-                        'ante' // Note 1
+                        'ante'
                         'avel'
                         '{i'}vel' (R2 delete)
                     )
@@ -193,7 +193,7 @@ backwardmode (
             'e' '{e'}' '{e^}'
                 ( RV delete [('u'] test 'g') or
                              ('i'] test 'c') RV delete )
-            '{c,}' (<-'c')
+            '{cc}' (<-'c')
         )
     )
 )
@@ -212,7 +212,3 @@ define stem as (
     )
     do postlude
 )
-
-/*
-    Note 1: additions of 15 Jun 2005
-*/