rspamd/contrib/snowball/algorithms/italian.sbl

routines (
           prelude postlude mark_regions
           RV R1 R2
           attached_pronoun
           standard_suffix
           verb_suffix
           vowel_suffix
)

externals ( stem )

integers ( pV p1 p2 )

groupings ( v AEIO CG )

stringescapes {}

/* special characters */

stringdef a'   '{U+00E1}'
stringdef a`   '{U+00E0}'
stringdef e'   '{U+00E9}'
stringdef e`   '{U+00E8}'
stringdef i'   '{U+00ED}'
stringdef i`   '{U+00EC}'
stringdef o'   '{U+00F3}'
stringdef o`   '{U+00F2}'
stringdef u'   '{U+00FA}'
stringdef u`   '{U+00F9}'

define v 'aeiou{a`}{e`}{i`}{o`}{u`}'

define prelude as (
    test repeat (
        [substring] among(
            '{a'}' (<- '{a`}')
            '{e'}' (<- '{e`}')
            '{i'}' (<- '{i`}')
            '{o'}' (<- '{o`}')
            '{u'}' (<- '{u`}')
            'qu'   (<- 'qU')
            ''     (next)
        )
    )
    repeat goto (
        v [ ('u' ] v <- 'U') or
            ('i' ] v <- 'I')
    )
)

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
    )
)

define postlude as repeat (

    [substring] among(
        'I'  (<- 'i')
        'U'  (<- 'u')
        ''   (next)
    )

)

backwardmode (

    define RV as $pV <= cursor
    define R1 as $p1 <= cursor
    define R2 as $p2 <= cursor

    define attached_pronoun as (
        [substring] among(
            'ci' 'gli' 'la' 'le' 'li' 'lo'
            'mi' 'ne' 'si'  'ti' 'vi'
            // the compound forms are:
            'sene' 'gliela' 'gliele' 'glieli' 'glielo' 'gliene'
            'mela' 'mele' 'meli' 'melo' 'mene'
            'tela' 'tele' 'teli' 'telo' 'tene'
            'cela' 'cele' 'celi' 'celo' 'cene'
            'vela' 'vele' 'veli' 'velo' 'vene'
        )
        among( (RV)
            'ando' 'endo'   (delete)
            'ar' 'er' 'ir'  (<- 'e')
        )
    )

    define standard_suffix as (
        [substring] among(

            'anza' 'anze' 'ico' 'ici' 'ica' 'ice' 'iche' 'ichi' 'ismo'
            '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
               ( R2 delete )
            'azione' 'azioni' 'atore' 'atori'
               ( R2 delete
                 try ( ['ic'] R2 delete )
               )
            'logia' 'logie'
               ( R2 <- 'log' )
            'uzione' 'uzioni' 'usione' 'usioni'
               ( R2 <- 'u' )
            'enza' 'enze'
               ( R2 <- 'ente' )
            'amento' 'amenti' 'imento' 'imenti'
               ( RV delete )
            'amente' (
                R1 delete
                try (
                    [substring] R2 delete among(
                        'iv' ( ['at'] R2 delete )
                        'os' 'ic' 'abil'
                    )
                )
            )
            'it{a`}' (
                R2 delete
                try (
                    [substring] among(
                        'abil' 'ic' 'iv' (R2 delete)
                    )
                )
            )
            'ivo' 'ivi' 'iva' 'ive' (
                R2 delete
                try ( ['at'] R2 delete ['ic'] R2 delete )
            )
        )
    )

    define verb_suffix as setlimit tomark pV for (
        [substring] among(
            'ammo' 'ando' 'ano' 'are' 'arono' 'asse' 'assero' 'assi'
            'assimo' 'ata' 'ate' 'ati' 'ato' 'ava' 'avamo' 'avano' 'avate'
            'avi' 'avo' 'emmo' 'enda' 'ende' 'endi' 'endo' 'er{a`}' 'erai'
            'eranno' 'ere' 'erebbe' 'erebbero' 'erei' 'eremmo' 'eremo'
            'ereste' 'eresti' 'erete' 'er{o`}' 'erono' 'essero' 'ete'
            'eva' 'evamo' 'evano' 'evate' 'evi' 'evo' 'Yamo' 'iamo' 'immo'
            'ir{a`}' 'irai' 'iranno' 'ire' 'irebbe' 'irebbero' 'irei'
            'iremmo' 'iremo' 'ireste' 'iresti' 'irete' 'ir{o`}' 'irono'
            'isca' 'iscano' 'isce' 'isci' 'isco' 'iscono' 'issero' 'ita'
            'ite' 'iti' 'ito' 'iva' 'ivamo' 'ivano' 'ivate' 'ivi' 'ivo'
            'ono' 'uta' 'ute' 'uti' 'uto'

            'ar' 'ir' // but 'er' is problematical
                (delete)
        )
    )

    define AEIO 'aeio{a`}{e`}{i`}{o`}'
    define CG 'cg'

    define vowel_suffix as (
        try (
            [AEIO] RV delete
            ['i'] RV delete
        )
        try (
            ['h'] CG RV delete
        )
    )
)

define stem as (
    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
*/