Class: Mittens::Stemmer

Inherits:
Object
  • Object
show all
Defined in:
ext/mittens/ext.c

Class Method Summary collapse

Instance Method Summary collapse

Constructor Details

#initialize(*args) ⇒ Object



49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
# File 'ext/mittens/ext.c', line 49

static VALUE stemmer_initialize(int argc, VALUE* argv, VALUE self)
{
    stemmer_t* stemmer;
    GetStemmer(self, stemmer);

    if (stemmer->stemmer != NULL)
        rb_raise(rb_eRuntimeError, "stemmer already initialized");

    VALUE opts;
    rb_scan_args(argc, argv, ":", &opts);

    VALUE language = Qnil;
    if (!NIL_P(opts))
        language = rb_hash_aref(opts, ID2SYM(rb_intern("language")));

    // if adding support for encoding, may want to change encoding returned from stem
    stemmer->stemmer = sb_stemmer_new(GetAlgorithm(language), NULL);
    if (stemmer->stemmer == NULL)
    {
        if (!NIL_P(language))
            rb_raise(rb_eArgError, "unknown language: %" PRIsVALUE, language);

        rb_raise(rb_eNoMemError, "failed to allocate memory");
    }

    // copy (after GetAlgorithm) in case string is modified in future
    stemmer->language = rb_obj_dup(language);

    return self;
}

Class Method Details

.languagesObject



122
123
124
125
126
127
128
129
130
131
# File 'ext/mittens/ext.c', line 122

static VALUE stemmer_languages(VALUE klass)
{
    VALUE out = rb_ary_new();

    const char** language = sb_stemmer_list();
    while (*language != NULL)
        rb_ary_push(out, rb_utf8_str_new_cstr(*language++));

    return out;
}

Instance Method Details

#initialize_copy(orig) ⇒ Object



102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
# File 'ext/mittens/ext.c', line 102

static VALUE stemmer_initialize_copy(VALUE self, VALUE orig)
{
    stemmer_t* stemmer;
    GetStemmer(self, stemmer);

    stemmer_t* orig_stemmer;
    GetStemmer(orig, orig_stemmer);

    if (stemmer->stemmer != NULL)
        rb_raise(rb_eRuntimeError, "stemmer already initialized");

    stemmer->stemmer = sb_stemmer_new(GetAlgorithm(orig_stemmer->language), NULL);
    if (stemmer->stemmer == NULL)
        rb_raise(rb_eNoMemError, "failed to allocate memory");

    stemmer->language = orig_stemmer->language;

    return self;
}

#stem(value) ⇒ Object



80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
# File 'ext/mittens/ext.c', line 80

static VALUE stemmer_stem(VALUE self, VALUE value)
{
    stemmer_t* stemmer;
    GetStemmer(self, stemmer);

    if (stemmer->stemmer == NULL)
        rb_raise(rb_eRuntimeError, "stemmer not initialized");

    const char* word = StringValuePtr(value);
    long size = RSTRING_LEN(value);
    if (size > INT_MAX)
        rb_raise(rb_eArgError, "string exceeds max length");

    const sb_symbol* pointer_out = sb_stemmer_stem(stemmer->stemmer, (const sb_symbol*) word, (int) size);
    int length_out = sb_stemmer_length(stemmer->stemmer);

    // place after last use of word
    RB_GC_GUARD(value);

    return rb_utf8_str_new((char*) pointer_out, (long) length_out);
}