rspamd/contrib/snowball/algorithms/russian/stem_Unicode.sbl

stringescapes {}

/* the 32 Cyrillic letters in Unicode */

stringdef a    hex '430'
stringdef b    hex '431'
stringdef v    hex '432'
stringdef g    hex '433'
stringdef d    hex '434'
stringdef e    hex '435'
stringdef zh   hex '436'
stringdef z    hex '437'
stringdef i    hex '438'
stringdef i`   hex '439'
stringdef k    hex '43A'
stringdef l    hex '43B'
stringdef m    hex '43C'
stringdef n    hex '43D'
stringdef o    hex '43E'
stringdef p    hex '43F'
stringdef r    hex '440'
stringdef s    hex '441'
stringdef t    hex '442'
stringdef u    hex '443'
stringdef f    hex '444'
stringdef kh   hex '445'
stringdef ts   hex '446'
stringdef ch   hex '447'
stringdef sh   hex '448'
stringdef shch hex '449'
stringdef "    hex '44A'
stringdef y    hex '44B'
stringdef '    hex '44C'
stringdef e`   hex '44D'
stringdef iu   hex '44E'
stringdef ia   hex '44F'

routines ( mark_regions R2
           perfective_gerund
           adjective
           adjectival
           reflexive
           verb
           noun
           derivational
           tidy_up
)

externals ( stem )

integers ( pV p2 )

groupings ( v )

define v '{a}{e}{i}{o}{u}{y}{e`}{iu}{ia}'

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 perfective_gerund as (
        [substring] among (
            '{v}'
            '{v}{sh}{i}'
            '{v}{sh}{i}{s}{'}'
                ('{a}' or '{ia}' delete)
            '{i}{v}'
            '{i}{v}{sh}{i}'
            '{i}{v}{sh}{i}{s}{'}'
            '{y}{v}'
            '{y}{v}{sh}{i}'
            '{y}{v}{sh}{i}{s}{'}'
                (delete)
        )
    )

    define adjective as (
        [substring] among (
            '{e}{e}' '{i}{e}' '{y}{e}' '{o}{e}' '{i}{m}{i}' '{y}{m}{i}'
            '{e}{i`}' '{i}{i`}' '{y}{i`}' '{o}{i`}' '{e}{m}' '{i}{m}'
            '{y}{m}' '{o}{m}' '{e}{g}{o}' '{o}{g}{o}' '{e}{m}{u}'
            '{o}{m}{u}' '{i}{kh}' '{y}{kh}' '{u}{iu}' '{iu}{iu}' '{a}{ia}'
            '{ia}{ia}'
                        // and -
            '{o}{iu}'   // - which is somewhat archaic
            '{e}{iu}'   // - soft form of {o}{iu}
                (delete)
        )
    )

    define adjectival as (
        adjective

        /* of the participle forms, em, vsh, ivsh, yvsh are readily removable.
           nn, {iu}shch, shch, u{iu}shch can be removed, with a small proportion of
           errors. Removing im, uem, enn creates too many errors.
        */

        try (
            [substring] among (
                '{e}{m}'                  // present passive participle
                '{n}{n}'                  // adjective from past passive participle
                '{v}{sh}'                 // past active participle
                '{iu}{shch}' '{shch}'     // present active participle
                    ('{a}' or '{ia}' delete)

     //but not  '{i}{m}' '{u}{e}{m}'      // present passive participle
     //or       '{e}{n}{n}'               // adjective from past passive participle

                '{i}{v}{sh}' '{y}{v}{sh}'// past active participle
                '{u}{iu}{shch}'          // present active participle
                    (delete)
            )
        )

    )

    define reflexive as (
        [substring] among (
            '{s}{ia}'
            '{s}{'}'
                (delete)
        )
    )

    define verb as (
        [substring] among (
            '{l}{a}' '{n}{a}' '{e}{t}{e}' '{i`}{t}{e}' '{l}{i}' '{i`}'
            '{l}' '{e}{m}' '{n}' '{l}{o}' '{n}{o}' '{e}{t}' '{iu}{t}'
            '{n}{y}' '{t}{'}' '{e}{sh}{'}'

            '{n}{n}{o}'
                ('{a}' or '{ia}' delete)

            '{i}{l}{a}' '{y}{l}{a}' '{e}{n}{a}' '{e}{i`}{t}{e}'
            '{u}{i`}{t}{e}' '{i}{t}{e}' '{i}{l}{i}' '{y}{l}{i}' '{e}{i`}'
            '{u}{i`}' '{i}{l}' '{y}{l}' '{i}{m}' '{y}{m}' '{e}{n}'
            '{i}{l}{o}' '{y}{l}{o}' '{e}{n}{o}' '{ia}{t}' '{u}{e}{t}'
            '{u}{iu}{t}' '{i}{t}' '{y}{t}' '{e}{n}{y}' '{i}{t}{'}'
            '{y}{t}{'}' '{i}{sh}{'}' '{u}{iu}' '{iu}'
                (delete)
            /* note the short passive participle tests:
               '{n}{a}' '{n}' '{n}{o}' '{n}{y}'
               '{e}{n}{a}' '{e}{n}' '{e}{n}{o}' '{e}{n}{y}'
            */
        )
    )

    define noun as (
        [substring] among (
            '{a}' '{e}{v}' '{o}{v}' '{i}{e}' '{'}{e}' '{e}'
            '{i}{ia}{m}{i}' '{ia}{m}{i}' '{a}{m}{i}' '{e}{i}' '{i}{i}'
            '{i}' '{i}{e}{i`}' '{e}{i`}' '{o}{i`}' '{i}{i`}' '{i`}'
            '{i}{ia}{m}' '{ia}{m}' '{i}{e}{m}' '{e}{m}' '{a}{m}' '{o}{m}'
            '{o}' '{u}' '{a}{kh}' '{i}{ia}{kh}' '{ia}{kh}' '{y}' '{'}'
            '{i}{iu}' '{'}{iu}' '{iu}' '{i}{ia}' '{'}{ia}' '{ia}'
                (delete)
            /* the small class of neuter forms '{e}{n}{i}' '{e}{n}{e}{m}'
               '{e}{n}{a}' '{e}{n}' '{e}{n}{a}{m}' '{e}{n}{a}{m}{i}' '{e}{n}{a}{x}'
               omitted - they only occur on 12 words.
            */
        )
    )

    define derivational as (
        [substring] R2 among (
            '{o}{s}{t}'
            '{o}{s}{t}{'}'
                (delete)
        )
    )

    define tidy_up as (
        [substring] among (

            '{e}{i`}{sh}'
            '{e}{i`}{sh}{e}'  // superlative forms
               (delete
                ['{n}'] '{n}' delete
               )
            '{n}'
               ('{n}' delete) // e.g. -nno endings
            '{'}'
               (delete)  // with some slight false conflations
        )
    )
)

define stem as (

    do mark_regions
    backwards setlimit tomark pV for (
        do (
             perfective_gerund or
             ( try reflexive
               adjectival or verb or noun
             )
        )
        try([ '{i}' ] delete)
        // because noun ending -i{iu} is being treated as verb ending -{iu}

        do derivational
        do tidy_up
    )
)