00001
00002
00003 #include <limits.h>
00004 #include "danish.h"
00005
00006 static const symbol s_pool[] = {
00007 #define s_0_0 0
00008 'h', 'e', 'd',
00009 #define s_0_1 3
00010 'e', 't', 'h', 'e', 'd',
00011 #define s_0_2 8
00012 'e', 'r', 'e', 'd',
00013 #define s_0_3 12
00014 'e',
00015 #define s_0_4 13
00016 'e', 'r', 'e', 'd', 'e',
00017 #define s_0_5 18
00018 'e', 'n', 'd', 'e',
00019 #define s_0_6 22
00020 'e', 'r', 'e', 'n', 'd', 'e',
00021 #define s_0_7 28
00022 'e', 'n', 'e',
00023 #define s_0_8 31
00024 'e', 'r', 'n', 'e',
00025 #define s_0_9 35
00026 'e', 'r', 'e',
00027 #define s_0_10 38
00028 'e', 'n',
00029 #define s_0_11 40
00030 'h', 'e', 'd', 'e', 'n',
00031 #define s_0_12 45
00032 'e', 'r', 'e', 'n',
00033 #define s_0_13 49
00034 'e', 'r',
00035 #define s_0_14 51
00036 'h', 'e', 'd', 'e', 'r',
00037 #define s_0_15 56
00038 'e', 'r', 'e', 'r',
00039 #define s_0_16 60
00040 's',
00041 #define s_0_17 61
00042 'h', 'e', 'd', 's',
00043 #define s_0_18 65
00044 'e', 's',
00045 #define s_0_19 67
00046 'e', 'n', 'd', 'e', 's',
00047 #define s_0_20 72
00048 'e', 'r', 'e', 'n', 'd', 'e', 's',
00049 #define s_0_21 79
00050 'e', 'n', 'e', 's',
00051 #define s_0_22 83
00052 'e', 'r', 'n', 'e', 's',
00053 #define s_0_23 88
00054 'e', 'r', 'e', 's',
00055 #define s_0_24 92
00056 'e', 'n', 's',
00057 #define s_0_25 95
00058 'h', 'e', 'd', 'e', 'n', 's',
00059 #define s_0_26 101
00060 'e', 'r', 'e', 'n', 's',
00061 #define s_0_27 106
00062 'e', 'r', 's',
00063 #define s_0_28 109
00064 'e', 't', 's',
00065 #define s_0_29 112
00066 'e', 'r', 'e', 't', 's',
00067 #define s_0_30 117
00068 'e', 't',
00069 #define s_0_31 119
00070 'e', 'r', 'e', 't',
00071 #define s_1_0 123
00072 'g', 'd',
00073 #define s_1_1 125
00074 'd', 't',
00075 #define s_1_2 127
00076 'g', 't',
00077 #define s_1_3 129
00078 'k', 't',
00079 #define s_2_0 131
00080 'i', 'g',
00081 #define s_2_1 133
00082 'l', 'i', 'g',
00083 #define s_2_2 136
00084 'e', 'l', 'i', 'g',
00085 #define s_2_3 140
00086 'e', 'l', 's',
00087 #define s_2_4 143
00088 'l', 0xC3, 0xB8, 's', 't',
00089 };
00090
00091
00092 static const struct among a_0[32] =
00093 {
00094 { 3, s_0_0, -1, 1},
00095 { 5, s_0_1, 0, 1},
00096 { 4, s_0_2, -1, 1},
00097 { 1, s_0_3, -1, 1},
00098 { 5, s_0_4, 3, 1},
00099 { 4, s_0_5, 3, 1},
00100 { 6, s_0_6, 5, 1},
00101 { 3, s_0_7, 3, 1},
00102 { 4, s_0_8, 3, 1},
00103 { 3, s_0_9, 3, 1},
00104 { 2, s_0_10, -1, 1},
00105 { 5, s_0_11, 10, 1},
00106 { 4, s_0_12, 10, 1},
00107 { 2, s_0_13, -1, 1},
00108 { 5, s_0_14, 13, 1},
00109 { 4, s_0_15, 13, 1},
00110 { 1, s_0_16, -1, 2},
00111 { 4, s_0_17, 16, 1},
00112 { 2, s_0_18, 16, 1},
00113 { 5, s_0_19, 18, 1},
00114 { 7, s_0_20, 19, 1},
00115 { 4, s_0_21, 18, 1},
00116 { 5, s_0_22, 18, 1},
00117 { 4, s_0_23, 18, 1},
00118 { 3, s_0_24, 16, 1},
00119 { 6, s_0_25, 24, 1},
00120 { 5, s_0_26, 24, 1},
00121 { 3, s_0_27, 16, 1},
00122 { 3, s_0_28, 16, 1},
00123 { 5, s_0_29, 28, 1},
00124 { 2, s_0_30, -1, 1},
00125 { 4, s_0_31, 30, 1}
00126 };
00127
00128
00129 static const struct among a_1[4] =
00130 {
00131 { 2, s_1_0, -1, -1},
00132 { 2, s_1_1, -1, -1},
00133 { 2, s_1_2, -1, -1},
00134 { 2, s_1_3, -1, -1}
00135 };
00136
00137
00138 static const struct among a_2[5] =
00139 {
00140 { 2, s_2_0, -1, 1},
00141 { 3, s_2_1, 0, 1},
00142 { 4, s_2_2, 1, 1},
00143 { 3, s_2_3, -1, 1},
00144 { 5, s_2_4, -1, 2}
00145 };
00146
00147 static const unsigned char g_v[] = { 17, 65, 16, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 48, 0, 128 };
00148
00149 static const unsigned char g_s_ending[] = { 239, 254, 42, 3, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 16 };
00150
00151 static const symbol s_0[] = { 's', 't' };
00152 static const symbol s_1[] = { 'i', 'g' };
00153 static const symbol s_2[] = { 'l', 0xC3, 0xB8, 's' };
00154
00155 int Xapian::InternalStemDanish::r_mark_regions() {
00156 I_p1 = l;
00157 { int c_test1 = c;
00158 { int ret = skip_utf8(p, c, 0, l, + 3);
00159 if (ret < 0) return 0;
00160 c = ret;
00161 }
00162 I_x = c;
00163 c = c_test1;
00164 }
00165 if (out_grouping_U(g_v, 97, 248, 1) < 0) return 0;
00166 { int ret = in_grouping_U(g_v, 97, 248, 1);
00167 if (ret < 0) return 0;
00168 c += ret;
00169 }
00170 I_p1 = c;
00171
00172 if (!(I_p1 < I_x)) goto lab0;
00173 I_p1 = I_x;
00174 lab0:
00175 return 1;
00176 }
00177
00178 int Xapian::InternalStemDanish::r_main_suffix() {
00179 int among_var;
00180 { int m1 = l - c; (void)m1;
00181 int mlimit1;
00182 if (c < I_p1) return 0;
00183 c = I_p1;
00184 mlimit1 = lb; lb = c;
00185 c = l - m1;
00186 ket = c;
00187 if (c <= lb || p[c - 1] >> 5 != 3 || !((1851440 >> (p[c - 1] & 0x1f)) & 1)) { lb = mlimit1; return 0; }
00188 among_var = find_among_b(s_pool, a_0, 32, 0, 0);
00189 if (!(among_var)) { lb = mlimit1; return 0; }
00190 bra = c;
00191 lb = mlimit1;
00192 }
00193 switch(among_var) {
00194 case 0: return 0;
00195 case 1:
00196 if (slice_del() == -1) return -1;
00197 break;
00198 case 2:
00199 if (in_grouping_b_U(g_s_ending, 97, 229, 0)) return 0;
00200 if (slice_del() == -1) return -1;
00201 break;
00202 }
00203 return 1;
00204 }
00205
00206 int Xapian::InternalStemDanish::r_consonant_pair() {
00207 { int m_test1 = l - c;
00208 { int m2 = l - c; (void)m2;
00209 int mlimit2;
00210 if (c < I_p1) return 0;
00211 c = I_p1;
00212 mlimit2 = lb; lb = c;
00213 c = l - m2;
00214 ket = c;
00215 if (c - 1 <= lb || (p[c - 1] != 100 && p[c - 1] != 116)) { lb = mlimit2; return 0; }
00216 if (!(find_among_b(s_pool, a_1, 4, 0, 0))) { lb = mlimit2; return 0; }
00217 bra = c;
00218 lb = mlimit2;
00219 }
00220 c = l - m_test1;
00221 }
00222 { int ret = skip_utf8(p, c, lb, 0, -1);
00223 if (ret < 0) return 0;
00224 c = ret;
00225 }
00226 bra = c;
00227 if (slice_del() == -1) return -1;
00228 return 1;
00229 }
00230
00231 int Xapian::InternalStemDanish::r_other_suffix() {
00232 int among_var;
00233 { int m1 = l - c; (void)m1;
00234 ket = c;
00235 if (!(eq_s_b(2, s_0))) goto lab0;
00236 bra = c;
00237 if (!(eq_s_b(2, s_1))) goto lab0;
00238 if (slice_del() == -1) return -1;
00239 lab0:
00240 c = l - m1;
00241 }
00242 { int m2 = l - c; (void)m2;
00243 int mlimit2;
00244 if (c < I_p1) return 0;
00245 c = I_p1;
00246 mlimit2 = lb; lb = c;
00247 c = l - m2;
00248 ket = c;
00249 if (c - 1 <= lb || p[c - 1] >> 5 != 3 || !((1572992 >> (p[c - 1] & 0x1f)) & 1)) { lb = mlimit2; return 0; }
00250 among_var = find_among_b(s_pool, a_2, 5, 0, 0);
00251 if (!(among_var)) { lb = mlimit2; return 0; }
00252 bra = c;
00253 lb = mlimit2;
00254 }
00255 switch(among_var) {
00256 case 0: return 0;
00257 case 1:
00258 if (slice_del() == -1) return -1;
00259 { int m3 = l - c; (void)m3;
00260 { int ret = r_consonant_pair();
00261 if (ret == 0) goto lab1;
00262 if (ret < 0) return ret;
00263 }
00264 lab1:
00265 c = l - m3;
00266 }
00267 break;
00268 case 2:
00269 { int ret = slice_from_s(4, s_2);
00270 if (ret < 0) return ret;
00271 }
00272 break;
00273 }
00274 return 1;
00275 }
00276
00277 int Xapian::InternalStemDanish::r_undouble() {
00278 { int m1 = l - c; (void)m1;
00279 int mlimit1;
00280 if (c < I_p1) return 0;
00281 c = I_p1;
00282 mlimit1 = lb; lb = c;
00283 c = l - m1;
00284 ket = c;
00285 if (out_grouping_b_U(g_v, 97, 248, 0)) { lb = mlimit1; return 0; }
00286 bra = c;
00287 { symbol * ret = slice_to(S_ch);
00288 if (ret == 0) return -1;
00289 S_ch = ret;
00290 }
00291 lb = mlimit1;
00292 }
00293 if (!(eq_v_b(S_ch))) return 0;
00294 if (slice_del() == -1) return -1;
00295 return 1;
00296 }
00297
00298 int Xapian::InternalStemDanish::stem() {
00299 { int c1 = c;
00300 { int ret = r_mark_regions();
00301 if (ret == 0) goto lab0;
00302 if (ret < 0) return ret;
00303 }
00304 lab0:
00305 c = c1;
00306 }
00307 lb = c; c = l;
00308
00309 { int m2 = l - c; (void)m2;
00310 { int ret = r_main_suffix();
00311 if (ret == 0) goto lab1;
00312 if (ret < 0) return ret;
00313 }
00314 lab1:
00315 c = l - m2;
00316 }
00317 { int m3 = l - c; (void)m3;
00318 { int ret = r_consonant_pair();
00319 if (ret == 0) goto lab2;
00320 if (ret < 0) return ret;
00321 }
00322 lab2:
00323 c = l - m3;
00324 }
00325 { int m4 = l - c; (void)m4;
00326 { int ret = r_other_suffix();
00327 if (ret == 0) goto lab3;
00328 if (ret < 0) return ret;
00329 }
00330 lab3:
00331 c = l - m4;
00332 }
00333 { int m5 = l - c; (void)m5;
00334 { int ret = r_undouble();
00335 if (ret == 0) goto lab4;
00336 if (ret < 0) return ret;
00337 }
00338 lab4:
00339 c = l - m5;
00340 }
00341 c = lb;
00342 return 1;
00343 }
00344
00345 Xapian::InternalStemDanish::InternalStemDanish()
00346 : I_x(0), I_p1(0), S_ch(0)
00347 {
00348 S_ch = create_s();
00349 }
00350
00351 Xapian::InternalStemDanish::~InternalStemDanish()
00352 {
00353 lose_s(S_ch);
00354 }
00355
00356 const char *
00357 Xapian::InternalStemDanish::get_description() const
00358 {
00359 return "danish";
00360 }