diff options
| author | Teodor Sigaev <teodor@sigaev.ru> | 2003-07-21 10:27:44 +0000 |
|---|---|---|
| committer | Teodor Sigaev <teodor@sigaev.ru> | 2003-07-21 10:27:44 +0000 |
| commit | b88605337ea37ce1080a696937540cf8b48338d1 (patch) | |
| tree | ed26ee96ed8ca176fca8a956e938b3cc7adcb1f3 /contrib/tsearch2/snowball | |
| parent | a6053826703e288ccc7bd2a9a86a278cef6bc7ed (diff) | |
| download | postgresql-b88605337ea37ce1080a696937540cf8b48338d1.tar.gz | |
tsearch2 module
Diffstat (limited to 'contrib/tsearch2/snowball')
| -rw-r--r-- | contrib/tsearch2/snowball/api.c | 48 | ||||
| -rw-r--r-- | contrib/tsearch2/snowball/api.h | 27 | ||||
| -rw-r--r-- | contrib/tsearch2/snowball/english_stem.c | 894 | ||||
| -rw-r--r-- | contrib/tsearch2/snowball/english_stem.h | 8 | ||||
| -rw-r--r-- | contrib/tsearch2/snowball/header.h | 57 | ||||
| -rw-r--r-- | contrib/tsearch2/snowball/russian_stem.c | 626 | ||||
| -rw-r--r-- | contrib/tsearch2/snowball/russian_stem.h | 8 | ||||
| -rw-r--r-- | contrib/tsearch2/snowball/utilities.c | 328 |
8 files changed, 1996 insertions, 0 deletions
diff --git a/contrib/tsearch2/snowball/api.c b/contrib/tsearch2/snowball/api.c new file mode 100644 index 0000000000..c9019ce973 --- /dev/null +++ b/contrib/tsearch2/snowball/api.c @@ -0,0 +1,48 @@ + +#include "header.h" + +extern struct SN_env * SN_create_env(int S_size, int I_size, int B_size) +{ struct SN_env * z = (struct SN_env *) calloc(1, sizeof(struct SN_env)); + z->p = create_s(); + if (S_size) + { z->S = (symbol * *) calloc(S_size, sizeof(symbol *)); + { int i; + for (i = 0; i < S_size; i++) z->S[i] = create_s(); + } + z->S_size = S_size; + } + + if (I_size) + { z->I = (int *) calloc(I_size, sizeof(int)); + z->I_size = I_size; + } + + if (B_size) + { z->B = (symbol *) calloc(B_size, sizeof(symbol)); + z->B_size = B_size; + } + + return z; +} + +extern void SN_close_env(struct SN_env * z) +{ + if (z->S_size) + { + { int i; + for (i = 0; i < z->S_size; i++) lose_s(z->S[i]); + } + free(z->S); + } + if (z->I_size) free(z->I); + if (z->B_size) free(z->B); + if (z->p) lose_s(z->p); + free(z); +} + +extern void SN_set_current(struct SN_env * z, int size, const symbol * s) +{ + replace_s(z, 0, z->l, size, s); + z->c = 0; +} + diff --git a/contrib/tsearch2/snowball/api.h b/contrib/tsearch2/snowball/api.h new file mode 100644 index 0000000000..3e8b6e1851 --- /dev/null +++ b/contrib/tsearch2/snowball/api.h @@ -0,0 +1,27 @@ + +typedef unsigned char symbol; + +/* Or replace 'char' above with 'short' for 16 bit characters. + + More precisely, replace 'char' with whatever type guarantees the + character width you need. Note however that sizeof(symbol) should divide + HEAD, defined in header.h as 2*sizeof(int), without remainder, otherwise + there is an alignment problem. In the unlikely event of a problem here, + consult Martin Porter. + +*/ + +struct SN_env { + symbol * p; + int c; int a; int l; int lb; int bra; int ket; + int S_size; int I_size; int B_size; + symbol * * S; + int * I; + symbol * B; +}; + +extern struct SN_env * SN_create_env(int S_size, int I_size, int B_size); +extern void SN_close_env(struct SN_env * z); + +extern void SN_set_current(struct SN_env * z, int size, const symbol * s); + diff --git a/contrib/tsearch2/snowball/english_stem.c b/contrib/tsearch2/snowball/english_stem.c new file mode 100644 index 0000000000..6715c7cea4 --- /dev/null +++ b/contrib/tsearch2/snowball/english_stem.c @@ -0,0 +1,894 @@ + +/* This file was generated automatically by the Snowball to ANSI C compiler */ + +#include "header.h" + +extern int english_stem(struct SN_env * z); +static int r_exception2(struct SN_env * z); +static int r_exception1(struct SN_env * z); +static int r_Step_5(struct SN_env * z); +static int r_Step_4(struct SN_env * z); +static int r_Step_3(struct SN_env * z); +static int r_Step_2(struct SN_env * z); +static int r_Step_1c(struct SN_env * z); +static int r_Step_1b(struct SN_env * z); +static int r_Step_1a(struct SN_env * z); +static int r_R2(struct SN_env * z); +static int r_R1(struct SN_env * z); +static int r_shortv(struct SN_env * z); +static int r_mark_regions(struct SN_env * z); +static int r_postlude(struct SN_env * z); +static int r_prelude(struct SN_env * z); + +extern struct SN_env * english_create_env(void); +extern void english_close_env(struct SN_env * z); + +static symbol s_0_0[5] = { 'g', 'e', 'n', 'e', 'r' }; + +static struct among a_0[1] = +{ +/* 0 */ { 5, s_0_0, -1, -1, 0} +}; + +static symbol s_1_0[3] = { 'i', 'e', 'd' }; +static symbol s_1_1[1] = { 's' }; +static symbol s_1_2[3] = { 'i', 'e', 's' }; +static symbol s_1_3[4] = { 's', 's', 'e', 's' }; +static symbol s_1_4[2] = { 's', 's' }; +static symbol s_1_5[2] = { 'u', 's' }; + +static struct among a_1[6] = +{ +/* 0 */ { 3, s_1_0, -1, 2, 0}, +/* 1 */ { 1, s_1_1, -1, 3, 0}, +/* 2 */ { 3, s_1_2, 1, 2, 0}, +/* 3 */ { 4, s_1_3, 1, 1, 0}, +/* 4 */ { 2, s_1_4, 1, -1, 0}, +/* 5 */ { 2, s_1_5, 1, -1, 0} +}; + +static symbol s_2_1[2] = { 'b', 'b' }; +static symbol s_2_2[2] = { 'd', 'd' }; +static symbol s_2_3[2] = { 'f', 'f' }; +static symbol s_2_4[2] = { 'g', 'g' }; +static symbol s_2_5[2] = { 'b', 'l' }; +static symbol s_2_6[2] = { 'm', 'm' }; +static symbol s_2_7[2] = { 'n', 'n' }; +static symbol s_2_8[2] = { 'p', 'p' }; +static symbol s_2_9[2] = { 'r', 'r' }; +static symbol s_2_10[2] = { 'a', 't' }; +static symbol s_2_11[2] = { 't', 't' }; +static symbol s_2_12[2] = { 'i', 'z' }; + +static struct among a_2[13] = +{ +/* 0 */ { 0, 0, -1, 3, 0}, +/* 1 */ { 2, s_2_1, 0, 2, 0}, +/* 2 */ { 2, s_2_2, 0, 2, 0}, +/* 3 */ { 2, s_2_3, 0, 2, 0}, +/* 4 */ { 2, s_2_4, 0, 2, 0}, +/* 5 */ { 2, s_2_5, 0, 1, 0}, +/* 6 */ { 2, s_2_6, 0, 2, 0}, +/* 7 */ { 2, s_2_7, 0, 2, 0}, +/* 8 */ { 2, s_2_8, 0, 2, 0}, +/* 9 */ { 2, s_2_9, 0, 2, 0}, +/* 10 */ { 2, s_2_10, 0, 1, 0}, +/* 11 */ { 2, s_2_11, 0, 2, 0}, +/* 12 */ { 2, s_2_12, 0, 1, 0} +}; + +static symbol s_3_0[2] = { 'e', 'd' }; +static symbol s_3_1[3] = { 'e', 'e', 'd' }; +static symbol s_3_2[3] = { 'i', 'n', 'g' }; +static symbol s_3_3[4] = { 'e', 'd', 'l', 'y' }; +static symbol s_3_4[5] = { 'e', 'e', 'd', 'l', 'y' }; +static symbol s_3_5[5] = { 'i', 'n', 'g', 'l', 'y' }; + +static struct among a_3[6] = +{ +/* 0 */ { 2, s_3_0, -1, 2, 0}, +/* 1 */ { 3, s_3_1, 0, 1, 0}, +/* 2 */ { 3, s_3_2, -1, 2, 0}, +/* 3 */ { 4, s_3_3, -1, 2, 0}, +/* 4 */ { 5, s_3_4, 3, 1, 0}, +/* 5 */ { 5, s_3_5, -1, 2, 0} +}; + +static symbol s_4_0[4] = { 'a', 'n', 'c', 'i' }; +static symbol s_4_1[4] = { 'e', 'n', 'c', 'i' }; +static symbol s_4_2[3] = { 'o', 'g', 'i' }; +static symbol s_4_3[2] = { 'l', 'i' }; +static symbol s_4_4[3] = { 'b', 'l', 'i' }; +static symbol s_4_5[4] = { 'a', 'b', 'l', 'i' }; +static symbol s_4_6[4] = { 'a', 'l', 'l', 'i' }; +static symbol s_4_7[5] = { 'f', 'u', 'l', 'l', 'i' }; +static symbol s_4_8[6] = { 'l', 'e', 's', 's', 'l', 'i' }; +static symbol s_4_9[5] = { 'o', 'u', 's', 'l', 'i' }; +static symbol s_4_10[5] = { 'e', 'n', 't', 'l', 'i' }; +static symbol s_4_11[5] = { 'a', 'l', 'i', 't', 'i' }; +static symbol s_4_12[6] = { 'b', 'i', 'l', 'i', 't', 'i' }; +static symbol s_4_13[5] = { 'i', 'v', 'i', 't', 'i' }; +static symbol s_4_14[6] = { 't', 'i', 'o', 'n', 'a', 'l' }; +static symbol s_4_15[7] = { 'a', 't', 'i', 'o', 'n', 'a', 'l' }; +static symbol s_4_16[5] = { 'a', 'l', 'i', 's', 'm' }; +static symbol s_4_17[5] = { 'a', 't', 'i', 'o', 'n' }; +static symbol s_4_18[7] = { 'i', 'z', 'a', 't', 'i', 'o', 'n' }; +static symbol s_4_19[4] = { 'i', 'z', 'e', 'r' }; +static symbol s_4_20[4] = { 'a', 't', 'o', 'r' }; +static symbol s_4_21[7] = { 'i', 'v', 'e', 'n', 'e', 's', 's' }; +static symbol s_4_22[7] = { 'f', 'u', 'l', 'n', 'e', 's', 's' }; +static symbol s_4_23[7] = { 'o', 'u', 's', 'n', 'e', 's', 's' }; + +static struct among a_4[24] = +{ +/* 0 */ { 4, s_4_0, -1, 3, 0}, +/* 1 */ { 4, s_4_1, -1, 2, 0}, +/* 2 */ { 3, s_4_2, -1, 13, 0}, +/* 3 */ { 2, s_4_3, -1, 16, 0}, +/* 4 */ { 3, s_4_4, 3, 12, 0}, +/* 5 */ { 4, s_4_5, 4, 4, 0}, +/* 6 */ { 4, s_4_6, 3, 8, 0}, +/* 7 */ { 5, s_4_7, 3, 14, 0}, +/* 8 */ { 6, s_4_8, 3, 15, 0}, +/* 9 */ { 5, s_4_9, 3, 10, 0}, +/* 10 */ { 5, s_4_10, 3, 5, 0}, +/* 11 */ { 5, s_4_11, -1, 8, 0}, +/* 12 */ { 6, s_4_12, -1, 12, 0}, +/* 13 */ { 5, s_4_13, -1, 11, 0}, +/* 14 */ { 6, s_4_14, -1, 1, 0}, +/* 15 */ { 7, s_4_15, 14, 7, 0}, +/* 16 */ { 5, s_4_16, -1, 8, 0}, +/* 17 */ { 5, s_4_17, -1, 7, 0}, +/* 18 */ { 7, s_4_18, 17, 6, 0}, +/* 19 */ { 4, s_4_19, -1, 6, 0}, +/* 20 */ { 4, s_4_20, -1, 7, 0}, +/* 21 */ { 7, s_4_21, -1, 11, 0}, +/* 22 */ { 7, s_4_22, -1, 9, 0}, +/* 23 */ { 7, s_4_23, -1, 10, 0} +}; + +static symbol s_5_0[5] = { 'i', 'c', 'a', 't', 'e' }; +static symbol s_5_1[5] = { 'a', 't', 'i', 'v', 'e' }; +static symbol s_5_2[5] = { 'a', 'l', 'i', 'z', 'e' }; +static symbol s_5_3[5] = { 'i', 'c', 'i', 't', 'i' }; +static symbol s_5_4[4] = { 'i', 'c', 'a', 'l' }; +static symbol s_5_5[6] = { 't', 'i', 'o', 'n', 'a', 'l' }; +static symbol s_5_6[7] = { 'a', 't', 'i', 'o', 'n', 'a', 'l' }; +static symbol s_5_7[3] = { 'f', 'u', 'l' }; +static symbol s_5_8[4] = { 'n', 'e', 's', 's' }; + +static struct among a_5[9] = +{ +/* 0 */ { 5, s_5_0, -1, 4, 0}, +/* 1 */ { 5, s_5_1, -1, 6, 0}, +/* 2 */ { 5, s_5_2, -1, 3, 0}, +/* 3 */ { 5, s_5_3, -1, 4, 0}, +/* 4 */ { 4, s_5_4, -1, 4, 0}, +/* 5 */ { 6, s_5_5, -1, 1, 0}, +/* 6 */ { 7, s_5_6, 5, 2, 0}, +/* 7 */ { 3, s_5_7, -1, 5, 0}, +/* 8 */ { 4, s_5_8, -1, 5, 0} +}; + +static symbol s_6_0[2] = { 'i', 'c' }; +static symbol s_6_1[4] = { 'a', 'n', 'c', 'e' }; +static symbol s_6_2[4] = { 'e', 'n', 'c', 'e' }; +static symbol s_6_3[4] = { 'a', 'b', 'l', 'e' }; +static symbol s_6_4[4] = { 'i', 'b', 'l', 'e' }; +static symbol s_6_5[3] = { 'a', 't', 'e' }; +static symbol s_6_6[3] = { 'i', 'v', 'e' }; +static symbol s_6_7[3] = { 'i', 'z', 'e' }; +static symbol s_6_8[3] = { 'i', 't', 'i' }; +static symbol s_6_9[2] = { 'a', 'l' }; +static symbol s_6_10[3] = { 'i', 's', 'm' }; +static symbol s_6_11[3] = { 'i', 'o', 'n' }; +static symbol s_6_12[2] = { 'e', 'r' }; +static symbol s_6_13[3] = { 'o', 'u', 's' }; +static symbol s_6_14[3] = { 'a', 'n', 't' }; +static symbol s_6_15[3] = { 'e', 'n', 't' }; +static symbol s_6_16[4] = { 'm', 'e', 'n', 't' }; +static symbol s_6_17[5] = { 'e', 'm', 'e', 'n', 't' }; + +static struct among a_6[18] = +{ +/* 0 */ { 2, s_6_0, -1, 1, 0}, +/* 1 */ { 4, s_6_1, -1, 1, 0}, +/* 2 */ { 4, s_6_2, -1, 1, 0}, +/* 3 */ { 4, s_6_3, -1, 1, 0}, +/* 4 */ { 4, s_6_4, -1, 1, 0}, +/* 5 */ { 3, s_6_5, -1, 1, 0}, +/* 6 */ { 3, s_6_6, -1, 1, 0}, +/* 7 */ { 3, s_6_7, -1, 1, 0}, +/* 8 */ { 3, s_6_8, -1, 1, 0}, +/* 9 */ { 2, s_6_9, -1, 1, 0}, +/* 10 */ { 3, s_6_10, -1, 1, 0}, +/* 11 */ { 3, s_6_11, -1, 2, 0}, +/* 12 */ { 2, s_6_12, -1, 1, 0}, +/* 13 */ { 3, s_6_13, -1, 1, 0}, +/* 14 */ { 3, s_6_14, -1, 1, 0}, +/* 15 */ { 3, s_6_15, -1, 1, 0}, +/* 16 */ { 4, s_6_16, 15, 1, 0}, +/* 17 */ { 5, s_6_17, 16, 1, 0} +}; + +static symbol s_7_0[1] = { 'e' }; +static symbol s_7_1[1] = { 'l' }; + +static struct among a_7[2] = +{ +/* 0 */ { 1, s_7_0, -1, 1, 0}, +/* 1 */ { 1, s_7_1, -1, 2, 0} +}; + +static symbol s_8_0[7] = { 's', 'u', 'c', 'c', 'e', 'e', 'd' }; +static symbol s_8_1[7] = { 'p', 'r', 'o', 'c', 'e', 'e', 'd' }; +static symbol s_8_2[6] = { 'e', 'x', 'c', 'e', 'e', 'd' }; +static symbol s_8_3[7] = { 'c', 'a', 'n', 'n', 'i', 'n', 'g' }; +static symbol s_8_4[6] = { 'i', 'n', 'n', 'i', 'n', 'g' }; +static symbol s_8_5[7] = { 'e', 'a', 'r', 'r', 'i', 'n', 'g' }; +static symbol s_8_6[7] = { 'h', 'e', 'r', 'r', 'i', 'n', 'g' }; +static symbol s_8_7[6] = { 'o', 'u', 't', 'i', 'n', 'g' }; + +static struct among a_8[8] = +{ +/* 0 */ { 7, s_8_0, -1, -1, 0}, +/* 1 */ { 7, s_8_1, -1, -1, 0}, +/* 2 */ { 6, s_8_2, -1, -1, 0}, +/* 3 */ { 7, s_8_3, -1, -1, 0}, +/* 4 */ { 6, s_8_4, -1, -1, 0}, +/* 5 */ { 7, s_8_5, -1, -1, 0}, +/* 6 */ { 7, s_8_6, -1, -1, 0}, +/* 7 */ { 6, s_8_7, -1, -1, 0} +}; + +static symbol s_9_0[5] = { 'a', 'n', 'd', 'e', 's' }; +static symbol s_9_1[5] = { 'a', 't', 'l', 'a', 's' }; +static symbol s_9_2[4] = { 'b', 'i', 'a', 's' }; +static symbol s_9_3[6] = { 'c', 'o', 's', 'm', 'o', 's' }; +static symbol s_9_4[5] = { 'd', 'y', 'i', 'n', 'g' }; +static symbol s_9_5[5] = { 'e', 'a', 'r', 'l', 'y' }; +static symbol s_9_6[6] = { 'g', 'e', 'n', 't', 'l', 'y' }; +static symbol s_9_7[4] = { 'h', 'o', 'w', 'e' }; +static symbol s_9_8[4] = { 'i', 'd', 'l', 'y' }; +static symbol s_9_9[5] = { 'l', 'y', 'i', 'n', 'g' }; +static symbol s_9_10[4] = { 'n', 'e', 'w', 's' }; +static symbol s_9_11[4] = { 'o', 'n', 'l', 'y' }; +static symbol s_9_12[6] = { 's', 'i', 'n', 'g', 'l', 'y' }; +static symbol s_9_13[5] = { 's', 'k', 'i', 'e', 's' }; +static symbol s_9_14[4] = { 's', 'k', 'i', 's' }; +static symbol s_9_15[3] = { 's', 'k', 'y' }; +static symbol s_9_16[5] = { 't', 'y', 'i', 'n', 'g' }; +static symbol s_9_17[4] = { 'u', 'g', 'l', 'y' }; + +static struct among a_9[18] = +{ +/* 0 */ { 5, s_9_0, -1, -1, 0}, +/* 1 */ { 5, s_9_1, -1, -1, 0}, +/* 2 */ { 4, s_9_2, -1, -1, 0}, +/* 3 */ { 6, s_9_3, -1, -1, 0}, +/* 4 */ { 5, s_9_4, -1, 3, 0}, +/* 5 */ { 5, s_9_5, -1, 9, 0}, +/* 6 */ { 6, s_9_6, -1, 7, 0}, +/* 7 */ { 4, s_9_7, -1, -1, 0}, +/* 8 */ { 4, s_9_8, -1, 6, 0}, +/* 9 */ { 5, s_9_9, -1, 4, 0}, +/* 10 */ { 4, s_9_10, -1, -1, 0}, +/* 11 */ { 4, s_9_11, -1, 10, 0}, +/* 12 */ { 6, s_9_12, -1, 11, 0}, +/* 13 */ { 5, s_9_13, -1, 2, 0}, +/* 14 */ { 4, s_9_14, -1, 1, 0}, +/* 15 */ { 3, s_9_15, -1, -1, 0}, +/* 16 */ { 5, s_9_16, -1, 5, 0}, +/* 17 */ { 4, s_9_17, -1, 8, 0} +}; + +static unsigned char g_v[] = { 17, 65, 16, 1 }; + +static unsigned char g_v_WXY[] = { 1, 17, 65, 208, 1 }; + +static unsigned char g_valid_LI[] = { 55, 141, 2 }; + +static symbol s_0[] = { 'y' }; +static symbol s_1[] = { 'Y' }; +static symbol s_2[] = { 'y' }; +static symbol s_3[] = { 'Y' }; +static symbol s_4[] = { 's', 's' }; +static symbol s_5[] = { 'i', 'e' }; +static symbol s_6[] = { 'i' }; +static symbol s_7[] = { 'e', 'e' }; +static symbol s_8[] = { 'e' }; +static symbol s_9[] = { 'e' }; +static symbol s_10[] = { 'y' }; +static symbol s_11[] = { 'Y' }; +static symbol s_12[] = { 'i' }; +static symbol s_13[] = { 't', 'i', 'o', 'n' }; +static symbol s_14[] = { 'e', 'n', 'c', 'e' }; +static symbol s_15[] = { 'a', 'n', 'c', 'e' }; +static symbol s_16[] = { 'a', 'b', 'l', 'e' }; +static symbol s_17[] = { 'e', 'n', 't' }; +static symbol s_18[] = { 'i', 'z', 'e' }; +static symbol s_19[] = { 'a', 't', 'e' }; +static symbol s_20[] = { 'a', 'l' }; +static symbol s_21[] = { 'f', 'u', 'l' }; +static symbol s_22[] = { 'o', 'u', 's' }; +static symbol s_23[] = { 'i', 'v', 'e' }; +static symbol s_24[] = { 'b', 'l', 'e' }; +static symbol s_25[] = { 'l' }; +static symbol s_26[] = { 'o', 'g' }; +static symbol s_27[] = { 'f', 'u', 'l' }; +static symbol s_28[] = { 'l', 'e', 's', 's' }; +static symbol s_29[] = { 't', 'i', 'o', 'n' }; +static symbol s_30[] = { 'a', 't', 'e' }; +static symbol s_31[] = { 'a', 'l' }; +static symbol s_32[] = { 'i', 'c' }; +static symbol s_33[] = { 's' }; +static symbol s_34[] = { 't' }; +static symbol s_35[] = { 'l' }; +static symbol s_36[] = { 's', 'k', 'i' }; +static symbol s_37[] = { 's', 'k', 'y' }; +static symbol s_38[] = { 'd', 'i', 'e' }; +static symbol s_39[] = { 'l', 'i', 'e' }; +static symbol s_40[] = { 't', 'i', 'e' }; +static symbol s_41[] = { 'i', 'd', 'l' }; +static symbol s_42[] = { 'g', 'e', 'n', 't', 'l' }; +static symbol s_43[] = { 'u', 'g', 'l', 'i' }; +static symbol s_44[] = { 'e', 'a', 'r', 'l', 'i' }; +static symbol s_45[] = { 'o', 'n', 'l', 'i' }; +static symbol s_46[] = { 's', 'i', 'n', 'g', 'l' }; +static symbol s_47[] = { 'Y' }; +static symbol s_48[] = { 'y' }; + +static int r_prelude(struct SN_env * z) { + z->B[0] = 0; /* unset Y_found, line 24 */ + { int c = z->c; /* do, line 25 */ + z->bra = z->c; /* [, line 25 */ + if (!(eq_s(z, 1, s_0))) goto lab0; + z->ket = z->c; /* ], line 25 */ + if (!(in_grouping(z, g_v, 97, 121))) goto lab0; + slice_from_s(z, 1, s_1); /* <-, line 25 */ + z->B[0] = 1; /* set Y_found, line 25 */ + lab0: + z->c = c; + } + { int c = z->c; /* do, line 26 */ + while(1) { /* repeat, line 26 */ + int c = z->c; + while(1) { /* goto, line 26 */ + int c = z->c; + if (!(in_grouping(z, g_v, 97, 121))) goto lab3; + z->bra = z->c; /* [, line 26 */ + if (!(eq_s(z, 1, s_2))) goto lab3; + z->ket = z->c; /* ], line 26 */ + z->c = c; + break; + lab3: + z->c = c; + if (z->c >= z->l) goto lab2; + z->c++; + } + slice_from_s(z, 1, s_3); /* <-, line 26 */ + z->B[0] = 1; /* set Y_found, line 26 */ + continue; + lab2: + z->c = c; + break; + } + lab1: + z->c = c; + } + return 1; +} + +static int r_mark_regions(struct SN_env * z) { + z->I[0] = z->l; + z->I[1] = z->l; + { int c = z->c; /* do, line 32 */ + { int c = z->c; /* or, line 36 */ + if (!(find_among(z, a_0, 1))) goto lab2; /* among, line 33 */ + goto lab1; + lab2: + z->c = c; + while(1) { /* gopast, line 36 */ + if (!(in_grouping(z, g_v, 97, 121))) goto lab3; + break; + lab3: + if (z->c >= z->l) goto lab0; + z->c++; + } + while(1) { /* gopast, line 36 */ + if (!(out_grouping(z, g_v, 97, 121))) goto lab4; + break; + lab4: + if (z->c >= z->l) goto lab0; + z->c++; + } + } + lab1: + z->I[0] = z->c; /* setmark p1, line 37 */ + while(1) { /* gopast, line 38 */ + if (!(in_grouping(z, g_v, 97, 121))) goto lab5; + break; + lab5: + if (z->c >= z->l) goto lab0; + z->c++; + } + while(1) { /* gopast, line 38 */ + if (!(out_grouping(z, g_v, 97, 121))) goto lab6; + break; + lab6: + if (z->c >= z->l) goto lab0; + z->c++; + } + z->I[1] = z->c; /* setmark p2, line 38 */ + lab0: + z->c = c; + } + return 1; +} + +static int r_shortv(struct SN_env * z) { + { int m = z->l - z->c; /* or, line 46 */ + if (!(out_grouping_b(z, g_v_WXY, 89, 121))) goto lab1; + if (!(in_grouping_b(z, g_v, 97, 121))) goto lab1; + if (!(out_grouping_b(z, g_v, 97, 121))) goto lab1; + goto lab0; + lab1: + z->c = z->l - m; + if (!(out_grouping_b(z, g_v, 97, 121))) return 0; + if (!(in_grouping_b(z, g_v, 97, 121))) return 0; + if (z->c > z->lb) return 0; /* atlimit, line 47 */ + } +lab0: + return 1; +} + +static int r_R1(struct SN_env * z) { + if (!(z->I[0] <= z->c)) return 0; + return 1; +} + +static int r_R2(struct SN_env * z) { + if (!(z->I[1] <= z->c)) return 0; + return 1; +} + +static int r_Step_1a(struct SN_env * z) { + int among_var; + z->ket = z->c; /* [, line 54 */ + among_var = find_among_b(z, a_1, 6); /* substring, line 54 */ + if (!(among_var)) return 0; + z->bra = z->c; /* ], line 54 */ + switch(among_var) { + case 0: return 0; + case 1: + slice_from_s(z, 2, s_4); /* <-, line 55 */ + break; + case 2: + { int m = z->l - z->c; /* or, line 57 */ + if (z->c <= z->lb) goto lab1; + z->c--; /* next, line 57 */ + if (z->c > z->lb) goto lab1; /* atlimit, line 57 */ + slice_from_s(z, 2, s_5); /* <-, line 57 */ + goto lab0; + lab1: + z->c = z->l - m; + slice_from_s(z, 1, s_6); /* <-, line 57 */ + } + lab0: + break; + case 3: + if (z->c <= z->lb) return 0; + z->c--; /* next, line 58 */ + while(1) { /* gopast, line 58 */ + if (!(in_grouping_b(z, g_v, 97, 121))) goto lab2; + break; + lab2: + if (z->c <= z->lb) return 0; + z->c--; + } + slice_del(z); /* delete, line 58 */ + break; + } + return 1; +} + +static int r_Step_1b(struct SN_env * z) { + int among_var; + z->ket = z->c; /* [, line 64 */ + among_var = find_among_b(z, a_3, 6); /* substring, line 64 */ + if (!(among_var)) return 0; + z->bra = z->c; /* ], line 64 */ + switch(among_var) { + case 0: return 0; + case 1: + if (!r_R1(z)) return 0; /* call R1, line 66 */ + slice_from_s(z, 2, s_7); /* <-, line 66 */ + break; + case 2: + { int m_test = z->l - z->c; /* test, line 69 */ + while(1) { /* gopast, line 69 */ + if (!(in_grouping_b(z, g_v, 97, 121))) goto lab0; + break; + lab0: + if (z->c <= z->lb) return 0; + z->c--; + } + z->c = z->l - m_test; + } + slice_del(z); /* delete, line 69 */ + { int m_test = z->l - z->c; /* test, line 70 */ + among_var = find_among_b(z, a_2, 13); /* substring, line 70 */ + if (!(among_var)) return 0; + z->c = z->l - m_test; + } + switch(among_var) { + case 0: return 0; + case 1: + { int c = z->c; + insert_s(z, z->c, z->c, 1, s_8); /* <+, line 72 */ + z->c = c; + } + break; + case 2: + z->ket = z->c; /* [, line 75 */ + if (z->c <= z->lb) return 0; + z->c--; /* next, line 75 */ + z->bra = z->c; /* ], line 75 */ + slice_del(z); /* delete, line 75 */ + break; + case 3: + if (z->c != z->I[0]) return 0; /* atmark, line 76 */ + { int m_test = z->l - z->c; /* test, line 76 */ + if (!r_shortv(z)) return 0; /* call shortv, line 76 */ + z->c = z->l - m_test; + } + { int c = z->c; + insert_s(z, z->c, z->c, 1, s_9); /* <+, line 76 */ + z->c = c; + } + break; + } + break; + } + return 1; +} + +static int r_Step_1c(struct SN_env * z) { + z->ket = z->c; /* [, line 83 */ + { int m = z->l - z->c; /* or, line 83 */ + if (!(eq_s_b(z, 1, s_10))) goto lab1; + goto lab0; + lab1: + z->c = z->l - m; + if (!(eq_s_b(z, 1, s_11))) return 0; + } +lab0: + z->bra = z->c; /* ], line 83 */ + if (!(out_grouping_b(z, g_v, 97, 121))) return 0; + { int m = z->l - z->c; /* not, line 84 */ + if (z->c > z->lb) goto lab2; /* atlimit, line 84 */ + return 0; + lab2: + z->c = z->l - m; + } + slice_from_s(z, 1, s_12); /* <-, line 85 */ + return 1; +} + +static int r_Step_2(struct SN_env * z) { + int among_var; + z->ket = z->c; /* [, line 89 */ + among_var = find_among_b(z, a_4, 24); /* substring, line 89 */ + if (!(among_var)) return 0; + z->bra = z->c; /* ], line 89 */ + if (!r_R1(z)) return 0; /* call R1, line 89 */ + switch(among_var) { + case 0: return 0; + case 1: + slice_from_s(z, 4, s_13); /* <-, line 90 */ + break; + case 2: + slice_from_s(z, 4, s_14); /* <-, line 91 */ + break; + case 3: + slice_from_s(z, 4, s_15); /* <-, line 92 */ + break; + case 4: + slice_from_s(z, 4, s_16); /* <-, line 93 */ + break; + case 5: + slice_from_s(z, 3, s_17); /* <-, line 94 */ + break; + case 6: + slice_from_s(z, 3, s_18); /* <-, line 96 */ + break; + case 7: + slice_from_s(z, 3, s_19); /* <-, line 98 */ + break; + case 8: + slice_from_s(z, 2, s_20); /* <-, line 100 */ + break; + case 9: + slice_from_s(z, 3, s_21); /* <-, line 101 */ + break; + case 10: + slice_from_s(z, 3, s_22); /* <-, line 103 */ + break; + case 11: + slice_from_s(z, 3, s_23); /* <-, line 105 */ + break; + case 12: + slice_from_s(z, 3, s_24); /* <-, line 107 */ + break; + case 13: + if (!(eq_s_b(z, 1, s_25))) return 0; + slice_from_s(z, 2, s_26); /* <-, line 108 */ + break; + case 14: + slice_from_s(z, 3, s_27); /* <-, line 109 */ + break; + case 15: + slice_from_s(z, 4, s_28); /* <-, line 110 */ + break; + case 16: + if (!(in_grouping_b(z, g_valid_LI, 99, 116))) return 0; + slice_del(z); /* delete, line 111 */ + break; + } + return 1; +} + +static int r_Step_3(struct SN_env * z) { + int among_var; + z->ket = z->c; /* [, line 116 */ + among_var = find_among_b(z, a_5, 9); /* substring, line 116 */ + if (!(among_var)) return 0; + z->bra = z->c; /* ], line 116 */ + if (!r_R1(z)) return 0; /* call R1, line 116 */ + switch(among_var) { + case 0: return 0; + case 1: + slice_from_s(z, 4, s_29); /* <-, line 117 */ + break; + case 2: + slice_from_s(z, 3, s_30); /* <-, line 118 */ + break; + case 3: + slice_from_s(z, 2, s_31); /* <-, line 119 */ + break; + case 4: + slice_from_s(z, 2, s_32); /* <-, line 121 */ + break; + case 5: + slice_del(z); /* delete, line 123 */ + break; + case 6: + if (!r_R2(z)) return 0; /* call R2, line 125 */ + slice_del(z); /* delete, line 125 */ + break; + } + return 1; +} + +static int r_Step_4(struct SN_env * z) { + int among_var; + z->ket = z->c; /* [, line 130 */ + among_var = find_among_b(z, a_6, 18); /* substring, line 130 */ + if (!(among_var)) return 0; + z->bra = z->c; /* ], line 130 */ + if (!r_R2(z)) return 0; /* call R2, line 130 */ + switch(among_var) { + case 0: return 0; + case 1: + slice_del(z); /* delete, line 133 */ + break; + case 2: + { int m = z->l - z->c; /* or, line 134 */ + if (!(eq_s_b(z, 1, s_33))) goto lab1; + goto lab0; + lab1: + z->c = z->l - m; + if (!(eq_s_b(z, 1, s_34))) return 0; + } + lab0: + slice_del(z); /* delete, line 134 */ + break; + } + return 1; +} + +static int r_Step_5(struct SN_env * z) { + int among_var; + z->ket = z->c; /* [, line 139 */ + among_var = find_among_b(z, a_7, 2); /* substring, line 139 */ + if (!(among_var)) return 0; + z->bra = z->c; /* ], line 139 */ + switch(among_var) { + case 0: return 0; + case 1: + { int m = z->l - z->c; /* or, line 140 */ + if (!r_R2(z)) goto lab1; /* call R2, line 140 */ + goto lab0; + lab1: + z->c = z->l - m; + if (!r_R1(z)) return 0; /* call R1, line 140 */ + { int m = z->l - z->c; /* not, line 140 */ + if (!r_shortv(z)) goto lab2; /* call shortv, line 140 */ + return 0; + lab2: + z->c = z->l - m; + } + } + lab0: + slice_del(z); /* delete, line 140 */ + break; + case 2: + if (!r_R2(z)) return 0; /* call R2, line 141 */ + if (!(eq_s_b(z, 1, s_35))) return 0; + slice_del(z); /* delete, line 141 */ + break; + } + return 1; +} + +static int r_exception2(struct SN_env * z) { + z->ket = z->c; /* [, line 147 */ + if (!(find_among_b(z, a_8, 8))) return 0; /* substring, line 147 */ + z->bra = z->c; /* ], line 147 */ + if (z->c > z->lb) return 0; /* atlimit, line 147 */ + return 1; +} + +static int r_exception1(struct SN_env * z) { + int among_var; + z->bra = z->c; /* [, line 159 */ + among_var = find_among(z, a_9, 18); /* substring, line 159 */ + if (!(among_var)) return 0; + z->ket = z->c; /* ], line 159 */ + if (z->c < z->l) return 0; /* atlimit, line 159 */ + switch(among_var) { + case 0: return 0; + case 1: + slice_from_s(z, 3, s_36); /* <-, line 163 */ + break; + case 2: + slice_from_s(z, 3, s_37); /* <-, line 164 */ + break; + case 3: + slice_from_s(z, 3, s_38); /* <-, line 165 */ + break; + case 4: + slice_from_s(z, 3, s_39); /* <-, line 166 */ + break; + case 5: + slice_from_s(z, 3, s_40); /* <-, line 167 */ + break; + case 6: + slice_from_s(z, 3, s_41); /* <-, line 171 */ + break; + case 7: + slice_from_s(z, 5, s_42); /* <-, line 172 */ + break; + case 8: + slice_from_s(z, 4, s_43); /* <-, line 173 */ + break; + case 9: + slice_from_s(z, 5, s_44); /* <-, line 174 */ + break; + case 10: + slice_from_s(z, 4, s_45); /* <-, line 175 */ + break; + case 11: + slice_from_s(z, 5, s_46); /* <-, line 176 */ + break; + } + return 1; +} + +static int r_postlude(struct SN_env * z) { + if (!(z->B[0])) return 0; /* Boolean test Y_found, line 192 */ + while(1) { /* repeat, line 192 */ + int c = z->c; + while(1) { /* goto, line 192 */ + int c = z->c; + z->bra = z->c; /* [, line 192 */ + if (!(eq_s(z, 1, s_47))) goto lab1; + z->ket = z->c; /* ], line 192 */ + z->c = c; + break; + lab1: + z->c = c; + if (z->c >= z->l) goto lab0; + z->c++; + } + slice_from_s(z, 1, s_48); /* <-, line 192 */ + continue; + lab0: + z->c = c; + break; + } + return 1; +} + +extern int english_stem(struct SN_env * z) { + { int c = z->c; /* or, line 196 */ + if (!r_exception1(z)) goto lab1; /* call exception1, line 196 */ + goto lab0; + lab1: + z->c = c; + { int c_test = z->c; /* test, line 198 */ + { int c = z->c + 3; + if (0 > c || c > z->l) return 0; + z->c = c; /* hop, line 198 */ + } + z->c = c_test; + } + { int c = z->c; /* do, line 199 */ + if (!r_prelude(z)) goto lab2; /* call prelude, line 199 */ + lab2: + z->c = c; + } + { int c = z->c; /* do, line 200 */ + if (!r_mark_regions(z)) goto lab3; /* call mark_regions, line 200 */ + lab3: + z->c = c; + } + z->lb = z->c; z->c = z->l; /* backwards, line 201 */ + + { int m = z->l - z->c; /* do, line 203 */ + if (!r_Step_1a(z)) goto lab4; /* call Step_1a, line 203 */ + lab4: + z->c = z->l - m; + } + { int m = z->l - z->c; /* or, line 205 */ + if (!r_exception2(z)) goto lab6; /* call exception2, line 205 */ + goto lab5; + lab6: + z->c = z->l - m; + { int m = z->l - z->c; /* do, line 207 */ + if (!r_Step_1b(z)) goto lab7; /* call Step_1b, line 207 */ + lab7: + z->c = z->l - m; + } + { int m = z->l - z->c; /* do, line 208 */ + if (!r_Step_1c(z)) goto lab8; /* call Step_1c, line 208 */ + lab8: + z->c = z->l - m; + } + { int m = z->l - z->c; /* do, line 210 */ + if (!r_Step_2(z)) goto lab9; /* call Step_2, line 210 */ + lab9: + z->c = z->l - m; + } + { int m = z->l - z->c; /* do, line 211 */ + if (!r_Step_3(z)) goto lab10; /* call Step_3, line 211 */ + lab10: + z->c = z->l - m; + } + { int m = z->l - z->c; /* do, line 212 */ + if (!r_Step_4(z)) goto lab11; /* call Step_4, line 212 */ + lab11: + z->c = z->l - m; + } + { int m = z->l - z->c; /* do, line 214 */ + if (!r_Step_5(z)) goto lab12; /* call Step_5, line 214 */ + lab12: + z->c = z->l - m; + } + } + lab5: + z->c = z->lb; + { int c = z->c; /* do, line 217 */ + if (!r_postlude(z)) goto lab13; /* call postlude, line 217 */ + lab13: + z->c = c; + } + } +lab0: + return 1; +} + +extern struct SN_env * english_create_env(void) { return SN_create_env(0, 2, 1); } + +extern void english_close_env(struct SN_env * z) { SN_close_env(z); } + diff --git a/contrib/tsearch2/snowball/english_stem.h b/contrib/tsearch2/snowball/english_stem.h new file mode 100644 index 0000000000..bfefcd5656 --- /dev/null +++ b/contrib/tsearch2/snowball/english_stem.h @@ -0,0 +1,8 @@ + +/* This file was generated automatically by the Snowball to ANSI C compiler */ + +extern struct SN_env * english_create_env(void); +extern void english_close_env(struct SN_env * z); + +extern int english_stem(struct SN_env * z); + diff --git a/contrib/tsearch2/snowball/header.h b/contrib/tsearch2/snowball/header.h new file mode 100644 index 0000000000..aaec3ae5d1 --- /dev/null +++ b/contrib/tsearch2/snowball/header.h @@ -0,0 +1,57 @@ + +#include <limits.h> + +#include "api.h" + +#define MAXINT INT_MAX +#define MININT INT_MIN + +#define HEAD 2*sizeof(int) + +#define SIZE(p) ((int *)(p))[-1] +#define SET_SIZE(p, n) ((int *)(p))[-1] = n +#define CAPACITY(p) ((int *)(p))[-2] + +struct among +{ int s_size; /* number of chars in string */ + symbol * s; /* search string */ + int substring_i;/* index to longest matching substring */ + int result; /* result of the lookup */ + int (* function)(struct SN_env *); +}; + +extern symbol * create_s(void); +extern void lose_s(symbol * p); + +extern int in_grouping(struct SN_env * z, unsigned char * s, int min, int max); +extern int in_grouping_b(struct SN_env * z, unsigned char * s, int min, int max); +extern int out_grouping(struct SN_env * z, unsigned char * s, int min, int max); +extern int out_grouping_b(struct SN_env * z, unsigned char * s, int min, int max); + +extern int in_range(struct SN_env * z, int min, int max); +extern int in_range_b(struct SN_env * z, int min, int max); +extern int out_range(struct SN_env * z, int min, int max); +extern int out_range_b(struct SN_env * z, int min, int max); + +extern int eq_s(struct SN_env * z, int s_size, symbol * s); +extern int eq_s_b(struct SN_env * z, int s_size, symbol * s); +extern int eq_v(struct SN_env * z, symbol * p); +extern int eq_v_b(struct SN_env * z, symbol * p); + +extern int find_among(struct SN_env * z, struct among * v, int v_size); +extern int find_among_b(struct SN_env * z, struct among * v, int v_size); + +extern symbol * increase_size(symbol * p, int n); +extern int replace_s(struct SN_env * z, int c_bra, int c_ket, int s_size, const symbol * s); +extern void slice_from_s(struct SN_env * z, int s_size, symbol * s); +extern void slice_from_v(struct SN_env * z, symbol * p); +extern void slice_del(struct SN_env * z); + +extern void insert_s(struct SN_env * z, int bra, int ket, int s_size, symbol * s); +extern void insert_v(struct SN_env * z, int bra, int ket, symbol * p); + +extern symbol * slice_to(struct SN_env * z, symbol * p); +extern symbol * assign_to(struct SN_env * z, symbol * p); + +extern void debug(struct SN_env * z, int number, int line_count); + diff --git a/contrib/tsearch2/snowball/russian_stem.c b/contrib/tsearch2/snowball/russian_stem.c new file mode 100644 index 0000000000..14fd49156b --- /dev/null +++ b/contrib/tsearch2/snowball/russian_stem.c @@ -0,0 +1,626 @@ + +/* This file was generated automatically by the Snowball to ANSI C compiler */ + +#include "header.h" + +extern int russian_stem(struct SN_env * z); +static int r_tidy_up(struct SN_env * z); +static int r_derivational(struct SN_env * z); +static int r_noun(struct SN_env * z); +static int r_verb(struct SN_env * z); +static int r_reflexive(struct SN_env * z); +static int r_adjectival(struct SN_env * z); +static int r_adjective(struct SN_env * z); +static int r_perfective_gerund(struct SN_env * z); +static int r_R2(struct SN_env * z); +static int r_mark_regions(struct SN_env * z); + +extern struct SN_env * russian_create_env(void); +extern void russian_close_env(struct SN_env * z); + +static symbol s_0_0[3] = { 215, 219, 201 }; +static symbol s_0_1[4] = { 201, 215, 219, 201 }; +static symbol s_0_2[4] = { 217, 215, 219, 201 }; +static symbol s_0_3[1] = { 215 }; +static symbol s_0_4[2] = { 201, 215 }; +static symbol s_0_5[2] = { 217, 215 }; +static symbol s_0_6[5] = { 215, 219, 201, 211, 216 }; +static symbol s_0_7[6] = { 201, 215, 219, 201, 211, 216 }; +static symbol s_0_8[6] = { 217, 215, 219, 201, 211, 216 }; + +static struct among a_0[9] = +{ +/* 0 */ { 3, s_0_0, -1, 1, 0}, +/* 1 */ { 4, s_0_1, 0, 2, 0}, +/* 2 */ { 4, s_0_2, 0, 2, 0}, +/* 3 */ { 1, s_0_3, -1, 1, 0}, +/* 4 */ { 2, s_0_4, 3, 2, 0}, +/* 5 */ { 2, s_0_5, 3, 2, 0}, +/* 6 */ { 5, s_0_6, -1, 1, 0}, +/* 7 */ { 6, s_0_7, 6, 2, 0}, +/* 8 */ { 6, s_0_8, 6, 2, 0} +}; + +static symbol s_1_0[2] = { 192, 192 }; +static symbol s_1_1[2] = { 197, 192 }; +static symbol s_1_2[2] = { 207, 192 }; +static symbol s_1_3[2] = { 213, 192 }; +static symbol s_1_4[2] = { 197, 197 }; +static symbol s_1_5[2] = { 201, 197 }; +static symbol s_1_6[2] = { 207, 197 }; +static symbol s_1_7[2] = { 217, 197 }; +static symbol s_1_8[2] = { 201, 200 }; +static symbol s_1_9[2] = { 217, 200 }; +static symbol s_1_10[3] = { 201, 205, 201 }; +static symbol s_1_11[3] = { 217, 205, 201 }; +static symbol s_1_12[2] = { 197, 202 }; +static symbol s_1_13[2] = { 201, 202 }; +static symbol s_1_14[2] = { 207, 202 }; +static symbol s_1_15[2] = { 217, 202 }; +static symbol s_1_16[2] = { 197, 205 }; +static symbol s_1_17[2] = { 201, 205 }; +static symbol s_1_18[2] = { 207, 205 }; +static symbol s_1_19[2] = { 217, 205 }; +static symbol s_1_20[3] = { 197, 199, 207 }; +static symbol s_1_21[3] = { 207, 199, 207 }; +static symbol s_1_22[2] = { 193, 209 }; +static symbol s_1_23[2] = { 209, 209 }; +static symbol s_1_24[3] = { 197, 205, 213 }; +static symbol s_1_25[3] = { 207, 205, 213 }; + +static struct among a_1[26] = +{ +/* 0 */ { 2, s_1_0, -1, 1, 0}, +/* 1 */ { 2, s_1_1, -1, 1, 0}, +/* 2 */ { 2, s_1_2, -1, 1, 0}, +/* 3 */ { 2, s_1_3, -1, 1, 0}, +/* 4 */ { 2, s_1_4, -1, 1, 0}, +/* 5 */ { 2, s_1_5, -1, 1, 0}, +/* 6 */ { 2, s_1_6, -1, 1, 0}, +/* 7 */ { 2, s_1_7, -1, 1, 0}, +/* 8 */ { 2, s_1_8, -1, 1, 0}, +/* 9 */ { 2, s_1_9, -1, 1, 0}, +/* 10 */ { 3, s_1_10, -1, 1, 0}, +/* 11 */ { 3, s_1_11, -1, 1, 0}, +/* 12 */ { 2, s_1_12, -1, 1, 0}, +/* 13 */ { 2, s_1_13, -1, 1, 0}, +/* 14 */ { 2, s_1_14, -1, 1, 0}, +/* 15 */ { 2, s_1_15, -1, 1, 0}, +/* 16 */ { 2, s_1_16, -1, 1, 0}, +/* 17 */ { 2, s_1_17, -1, 1, 0}, +/* 18 */ { 2, s_1_18, -1, 1, 0}, +/* 19 */ { 2, s_1_19, -1, 1, 0}, +/* 20 */ { 3, s_1_20, -1, 1, 0}, +/* 21 */ { 3, s_1_21, -1, 1, 0}, +/* 22 */ { 2, s_1_22, -1, 1, 0}, +/* 23 */ { 2, s_1_23, -1, 1, 0}, +/* 24 */ { 3, s_1_24, -1, 1, 0}, +/* 25 */ { 3, s_1_25, -1, 1, 0} +}; + +static symbol s_2_0[2] = { 197, 205 }; +static symbol s_2_1[2] = { 206, 206 }; +static symbol s_2_2[2] = { 215, 219 }; +static symbol s_2_3[3] = { 201, 215, 219 }; +static symbol s_2_4[3] = { 217, 215, 219 }; +static symbol s_2_5[1] = { 221 }; +static symbol s_2_6[2] = { 192, 221 }; +static symbol s_2_7[3] = { 213, 192, 221 }; + +static struct among a_2[8] = +{ +/* 0 */ { 2, s_2_0, -1, 1, 0}, +/* 1 */ { 2, s_2_1, -1, 1, 0}, +/* 2 */ { 2, s_2_2, -1, 1, 0}, +/* 3 */ { 3, s_2_3, 2, 2, 0}, +/* 4 */ { 3, s_2_4, 2, 2, 0}, +/* 5 */ { 1, s_2_5, -1, 1, 0}, +/* 6 */ { 2, s_2_6, 5, 1, 0}, +/* 7 */ { 3, s_2_7, 6, 2, 0} +}; + +static symbol s_3_0[2] = { 211, 209 }; +static symbol s_3_1[2] = { 211, 216 }; + +static struct among a_3[2] = +{ +/* 0 */ { 2, s_3_0, -1, 1, 0}, +/* 1 */ { 2, s_3_1, -1, 1, 0} +}; + +static symbol s_4_0[1] = { 192 }; +static symbol s_4_1[2] = { 213, 192 }; +static symbol s_4_2[2] = { 204, 193 }; +static symbol s_4_3[3] = { 201, 204, 193 }; +static symbol s_4_4[3] = { 217, 204, 193 }; +static symbol s_4_5[2] = { 206, 193 }; +static symbol s_4_6[3] = { 197, 206, 193 }; +static symbol s_4_7[3] = { 197, 212, 197 }; +static symbol s_4_8[3] = { 201, 212, 197 }; +static symbol s_4_9[3] = { 202, 212, 197 }; +static symbol s_4_10[4] = { 197, 202, 212, 197 }; +static symbol s_4_11[4] = { 213, 202, 212, 197 }; +static symbol s_4_12[2] = { 204, 201 }; +static symbol s_4_13[3] = { 201, 204, 201 }; +static symbol s_4_14[3] = { 217, 204, 201 }; +static symbol s_4_15[1] = { 202 }; +static symbol s_4_16[2] = { 197, 202 }; +static symbol s_4_17[2] = { 213, 202 }; +static symbol s_4_18[1] = { 204 }; +static symbol s_4_19[2] = { 201, 204 }; +static symbol s_4_20[2] = { 217, 204 }; +static symbol s_4_21[2] = { 197, 205 }; +static symbol s_4_22[2] = { 201, 205 }; +static symbol s_4_23[2] = { 217, 205 }; +static symbol s_4_24[1] = { 206 }; +static symbol s_4_25[2] = { 197, 206 }; +static symbol s_4_26[2] = { 204, 207 }; +static symbol s_4_27[3] = { 201, 204, 207 }; +static symbol s_4_28[3] = { 217, 204, 207 }; +static symbol s_4_29[2] = { 206, 207 }; +static symbol s_4_30[3] = { 197, 206, 207 }; +static symbol s_4_31[3] = { 206, 206, 207 }; +static symbol s_4_32[2] = { 192, 212 }; +static symbol s_4_33[3] = { 213, 192, 212 }; +static symbol s_4_34[2] = { 197, 212 }; +static symbol s_4_35[3] = { 213, 197, 212 }; +static symbol s_4_36[2] = { 201, 212 }; +static symbol s_4_37[2] = { 209, 212 }; +static symbol s_4_38[2] = { 217, 212 }; +static symbol s_4_39[2] = { 212, 216 }; +static symbol s_4_40[3] = { 201, 212, 216 }; +static symbol s_4_41[3] = { 217, 212, 216 }; +static symbol s_4_42[3] = { 197, 219, 216 }; +static symbol s_4_43[3] = { 201, 219, 216 }; +static symbol s_4_44[2] = { 206, 217 }; +static symbol s_4_45[3] = { 197, 206, 217 }; + +static struct among a_4[46] = +{ +/* 0 */ { 1, s_4_0, -1, 2, 0}, +/* 1 */ { 2, s_4_1, 0, 2, 0}, +/* 2 */ { 2, s_4_2, -1, 1, 0}, +/* 3 */ { 3, s_4_3, 2, 2, 0}, +/* 4 */ { 3, s_4_4, 2, 2, 0}, +/* 5 */ { 2, s_4_5, -1, 1, 0}, +/* 6 */ { 3, s_4_6, 5, 2, 0}, +/* 7 */ { 3, s_4_7, -1, 1, 0}, +/* 8 */ { 3, s_4_8, -1, 2, 0}, +/* 9 */ { 3, s_4_9, -1, 1, 0}, +/* 10 */ { 4, s_4_10, 9, 2, 0}, +/* 11 */ { 4, s_4_11, 9, 2, 0}, +/* 12 */ { 2, s_4_12, -1, 1, 0}, +/* 13 */ { 3, s_4_13, 12, 2, 0}, +/* 14 */ { 3, s_4_14, 12, 2, 0}, +/* 15 */ { 1, s_4_15, -1, 1, 0}, +/* 16 */ { 2, s_4_16, 15, 2, 0}, +/* 17 */ { 2, s_4_17, 15, 2, 0}, +/* 18 */ { 1, s_4_18, -1, 1, 0}, +/* 19 */ { 2, s_4_19, 18, 2, 0}, +/* 20 */ { 2, s_4_20, 18, 2, 0}, +/* 21 */ { 2, s_4_21, -1, 1, 0}, +/* 22 */ { 2, s_4_22, -1, 2, 0}, +/* 23 */ { 2, s_4_23, -1, 2, 0}, +/* 24 */ { 1, s_4_24, -1, 1, 0}, +/* 25 */ { 2, s_4_25, 24, 2, 0}, +/* 26 */ { 2, s_4_26, -1, 1, 0}, +/* 27 */ { 3, s_4_27, 26, 2, 0}, +/* 28 */ { 3, s_4_28, 26, 2, 0}, +/* 29 */ { 2, s_4_29, -1, 1, 0}, +/* 30 */ { 3, s_4_30, 29, 2, 0}, +/* 31 */ { 3, s_4_31, 29, 1, 0}, +/* 32 */ { 2, s_4_32, -1, 1, 0}, +/* 33 */ { 3, s_4_33, 32, 2, 0}, +/* 34 */ { 2, s_4_34, -1, 1, 0}, +/* 35 */ { 3, s_4_35, 34, 2, 0}, +/* 36 */ { 2, s_4_36, -1, 2, 0}, +/* 37 */ { 2, s_4_37, -1, 2, 0}, +/* 38 */ { 2, s_4_38, -1, 2, 0}, +/* 39 */ { 2, s_4_39, -1, 1, 0}, +/* 40 */ { 3, s_4_40, 39, 2, 0}, +/* 41 */ { 3, s_4_41, 39, 2, 0}, +/* 42 */ { 3, s_4_42, -1, 1, 0}, +/* 43 */ { 3, s_4_43, -1, 2, 0}, +/* 44 */ { 2, s_4_44, -1, 1, 0}, +/* 45 */ { 3, s_4_45, 44, 2, 0} +}; + +static symbol s_5_0[1] = { 192 }; +static symbol s_5_1[2] = { 201, 192 }; +static symbol s_5_2[2] = { 216, 192 }; +static symbol s_5_3[1] = { 193 }; +static symbol s_5_4[1] = { 197 }; +static symbol s_5_5[2] = { 201, 197 }; +static symbol s_5_6[2] = { 216, 197 }; +static symbol s_5_7[2] = { 193, 200 }; +static symbol s_5_8[2] = { 209, 200 }; +static symbol s_5_9[3] = { 201, 209, 200 }; +static symbol s_5_10[1] = { 201 }; +static symbol s_5_11[2] = { 197, 201 }; +static symbol s_5_12[2] = { 201, 201 }; +static symbol s_5_13[3] = { 193, 205, 201 }; +static symbol s_5_14[3] = { 209, 205, 201 }; +static symbol s_5_15[4] = { 201, 209, 205, 201 }; +static symbol s_5_16[1] = { 202 }; +static symbol s_5_17[2] = { 197, 202 }; +static symbol s_5_18[3] = { 201, 197, 202 }; +static symbol s_5_19[2] = { 201, 202 }; +static symbol s_5_20[2] = { 207, 202 }; +static symbol s_5_21[2] = { 193, 205 }; +static symbol s_5_22[2] = { 197, 205 }; +static symbol s_5_23[3] = { 201, 197, 205 }; +static symbol s_5_24[2] = { 207, 205 }; +static symbol s_5_25[2] = { 209, 205 }; +static symbol s_5_26[3] = { 201, 209, 205 }; +static symbol s_5_27[1] = { 207 }; +static symbol s_5_28[1] = { 209 }; +static symbol s_5_29[2] = { 201, 209 }; +static symbol s_5_30[2] = { 216, 209 }; +static symbol s_5_31[1] = { 213 }; +static symbol s_5_32[2] = { 197, 215 }; +static symbol s_5_33[2] = { 207, 215 }; +static symbol s_5_34[1] = { 216 }; +static symbol s_5_35[1] = { 217 }; + +static struct among a_5[36] = +{ +/* 0 */ { 1, s_5_0, -1, 1, 0}, +/* 1 */ { 2, s_5_1, 0, 1, 0}, +/* 2 */ { 2, s_5_2, 0, 1, 0}, +/* 3 */ { 1, s_5_3, -1, 1, 0}, +/* 4 */ { 1, s_5_4, -1, 1, 0}, +/* 5 */ { 2, s_5_5, 4, 1, 0}, +/* 6 */ { 2, s_5_6, 4, 1, 0}, +/* 7 */ { 2, s_5_7, -1, 1, 0}, +/* 8 */ { 2, s_5_8, -1, 1, 0}, +/* 9 */ { 3, s_5_9, 8, 1, 0}, +/* 10 */ { 1, s_5_10, -1, 1, 0}, +/* 11 */ { 2, s_5_11, 10, 1, 0}, +/* 12 */ { 2, s_5_12, 10, 1, 0}, +/* 13 */ { 3, s_5_13, 10, 1, 0}, +/* 14 */ { 3, s_5_14, 10, 1, 0}, +/* 15 */ { 4, s_5_15, 14, 1, 0}, +/* 16 */ { 1, s_5_16, -1, 1, 0}, +/* 17 */ { 2, s_5_17, 16, 1, 0}, +/* 18 */ { 3, s_5_18, 17, 1, 0}, +/* 19 */ { 2, s_5_19, 16, 1, 0}, +/* 20 */ { 2, s_5_20, 16, 1, 0}, +/* 21 */ { 2, s_5_21, -1, 1, 0}, +/* 22 */ { 2, s_5_22, -1, 1, 0}, +/* 23 */ { 3, s_5_23, 22, 1, 0}, +/* 24 */ { 2, s_5_24, -1, 1, 0}, +/* 25 */ { 2, s_5_25, -1, 1, 0}, +/* 26 */ { 3, s_5_26, 25, 1, 0}, +/* 27 */ { 1, s_5_27, -1, 1, 0}, +/* 28 */ { 1, s_5_28, -1, 1, 0}, +/* 29 */ { 2, s_5_29, 28, 1, 0}, +/* 30 */ { 2, s_5_30, 28, 1, 0}, +/* 31 */ { 1, s_5_31, -1, 1, 0}, +/* 32 */ { 2, s_5_32, -1, 1, 0}, +/* 33 */ { 2, s_5_33, -1, 1, 0}, +/* 34 */ { 1, s_5_34, -1, 1, 0}, +/* 35 */ { 1, s_5_35, -1, 1, 0} +}; + +static symbol s_6_0[3] = { 207, 211, 212 }; +static symbol s_6_1[4] = { 207, 211, 212, 216 }; + +static struct among a_6[2] = +{ +/* 0 */ { 3, s_6_0, -1, 1, 0}, +/* 1 */ { 4, s_6_1, -1, 1, 0} +}; + +static symbol s_7_0[4] = { 197, 202, 219, 197 }; +static symbol s_7_1[1] = { 206 }; +static symbol s_7_2[1] = { 216 }; +static symbol s_7_3[3] = { 197, 202, 219 }; + +static struct among a_7[4] = +{ +/* 0 */ { 4, s_7_0, -1, 1, 0}, +/* 1 */ { 1, s_7_1, -1, 2, 0}, +/* 2 */ { 1, s_7_2, -1, 3, 0}, +/* 3 */ { 3, s_7_3, -1, 1, 0} +}; + +static unsigned char g_v[] = { 35, 130, 34, 18 }; + +static symbol s_0[] = { 193 }; +static symbol s_1[] = { 209 }; +static symbol s_2[] = { 193 }; +static symbol s_3[] = { 209 }; +static symbol s_4[] = { 193 }; +static symbol s_5[] = { 209 }; +static symbol s_6[] = { 206 }; +static symbol s_7[] = { 206 }; +static symbol s_8[] = { 206 }; +static symbol s_9[] = { 201 }; + +static int r_mark_regions(struct SN_env * z) { + z->I[0] = z->l; + z->I[1] = z->l; + { int c = z->c; /* do, line 100 */ + while(1) { /* gopast, line 101 */ + if (!(in_grouping(z, g_v, 192, 220))) goto lab1; + break; + lab1: + if (z->c >= z->l) goto lab0; + z->c++; + } + z->I[0] = z->c; /* setmark pV, line 101 */ + while(1) { /* gopast, line 101 */ + if (!(out_grouping(z, g_v, 192, 220))) goto lab2; + break; + lab2: + if (z->c >= z->l) goto lab0; + z->c++; + } + while(1) { /* gopast, line 102 */ + if (!(in_grouping(z, g_v, 192, 220))) goto lab3; + break; + lab3: + if (z->c >= z->l) goto lab0; + z->c++; + } + while(1) { /* gopast, line 102 */ + if (!(out_grouping(z, g_v, 192, 220))) goto lab4; + break; + lab4: + if (z->c >= z->l) goto lab0; + z->c++; + } + z->I[1] = z->c; /* setmark p2, line 102 */ + lab0: + z->c = c; + } + return 1; +} + +static int r_R2(struct SN_env * z) { + if (!(z->I[1] <= z->c)) return 0; + return 1; +} + +static int r_perfective_gerund(struct SN_env * z) { + int among_var; + z->ket = z->c; /* [, line 111 */ + among_var = find_among_b(z, a_0, 9); /* substring, line 111 */ + if (!(among_var)) return 0; + z->bra = z->c; /* ], line 111 */ + switch(among_var) { + case 0: return 0; + case 1: + { int m = z->l - z->c; /* or, line 115 */ + if (!(eq_s_b(z, 1, s_0))) goto lab1; + goto lab0; + lab1: + z->c = z->l - m; + if (!(eq_s_b(z, 1, s_1))) return 0; + } + lab0: + slice_del(z); /* delete, line 115 */ + break; + case 2: + slice_del(z); /* delete, line 122 */ + break; + } + return 1; +} + +static int r_adjective(struct SN_env * z) { + int among_var; + z->ket = z->c; /* [, line 127 */ + among_var = find_among_b(z, a_1, 26); /* substring, line 127 */ + if (!(among_var)) return 0; + z->bra = z->c; /* ], line 127 */ + switch(among_var) { + case 0: return 0; + case 1: + slice_del(z); /* delete, line 136 */ + break; + } + return 1; +} + +static int r_adjectival(struct SN_env * z) { + int among_var; + if (!r_adjective(z)) return 0; /* call adjective, line 141 */ + { int m = z->l - z->c; /* try, line 148 */ + z->ket = z->c; /* [, line 149 */ + among_var = find_among_b(z, a_2, 8); /* substring, line 149 */ + if (!(among_var)) { z->c = z->l - m; goto lab0; } + z->bra = z->c; /* ], line 149 */ + switch(among_var) { + case 0: { z->c = z->l - m; goto lab0; } + case 1: + { int m = z->l - z->c; /* or, line 154 */ + if (!(eq_s_b(z, 1, s_2))) goto lab2; + goto lab1; + lab2: + z->c = z->l - m; + if (!(eq_s_b(z, 1, s_3))) { z->c = z->l - m; goto lab0; } + } + lab1: + slice_del(z); /* delete, line 154 */ + break; + case 2: + slice_del(z); /* delete, line 161 */ + break; + } + lab0: + ; + } + return 1; +} + +static int r_reflexive(struct SN_env * z) { + int among_var; + z->ket = z->c; /* [, line 168 */ + among_var = find_among_b(z, a_3, 2); /* substring, line 168 */ + if (!(among_var)) return 0; + z->bra = z->c; /* ], line 168 */ + switch(among_var) { + case 0: return 0; + case 1: + slice_del(z); /* delete, line 171 */ + break; + } + return 1; +} + +static int r_verb(struct SN_env * z) { + int among_var; + z->ket = z->c; /* [, line 176 */ + among_var = find_among_b(z, a_4, 46); /* substring, line 176 */ + if (!(among_var)) return 0; + z->bra = z->c; /* ], line 176 */ + switch(among_var) { + case 0: return 0; + case 1: + { int m = z->l - z->c; /* or, line 182 */ + if (!(eq_s_b(z, 1, s_4))) goto lab1; + goto lab0; + lab1: + z->c = z->l - m; + if (!(eq_s_b(z, 1, s_5))) return 0; + } + lab0: + slice_del(z); /* delete, line 182 */ + break; + case 2: + slice_del(z); /* delete, line 190 */ + break; + } + return 1; +} + +static int r_noun(struct SN_env * z) { + int among_var; + z->ket = z->c; /* [, line 199 */ + among_var = find_among_b(z, a_5, 36); /* substring, line 199 */ + if (!(among_var)) return 0; + z->bra = z->c; /* ], line 199 */ + switch(among_var) { + case 0: return 0; + case 1: + slice_del(z); /* delete, line 206 */ + break; + } + return 1; +} + +static int r_derivational(struct SN_env * z) { + int among_var; + z->ket = z->c; /* [, line 215 */ + among_var = find_among_b(z, a_6, 2); /* substring, line 215 */ + if (!(among_var)) return 0; + z->bra = z->c; /* ], line 215 */ + if (!r_R2(z)) return 0; /* call R2, line 215 */ + switch(among_var) { + case 0: return 0; + case 1: + slice_del(z); /* delete, line 218 */ + break; + } + return 1; +} + +static int r_tidy_up(struct SN_env * z) { + int among_var; + z->ket = z->c; /* [, line 223 */ + among_var = find_among_b(z, a_7, 4); /* substring, line 223 */ + if (!(among_var)) return 0; + z->bra = z->c; /* ], line 223 */ + switch(among_var) { + case 0: return 0; + case 1: + slice_del(z); /* delete, line 227 */ + z->ket = z->c; /* [, line 228 */ + if (!(eq_s_b(z, 1, s_6))) return 0; + z->bra = z->c; /* ], line 228 */ + if (!(eq_s_b(z, 1, s_7))) return 0; + slice_del(z); /* delete, line 228 */ + break; + case 2: + if (!(eq_s_b(z, 1, s_8))) return 0; + slice_del(z); /* delete, line 231 */ + break; + case 3: + slice_del(z); /* delete, line 233 */ + break; + } + return 1; +} + +extern int russian_stem(struct SN_env * z) { + { int c = z->c; /* do, line 240 */ + if (!r_mark_regions(z)) goto lab0; /* call mark_regions, line 240 */ + lab0: + z->c = c; + } + z->lb = z->c; z->c = z->l; /* backwards, line 241 */ + + { int m = z->l - z->c; /* setlimit, line 241 */ + int m3; + if (z->c < z->I[0]) return 0; + z->c = z->I[0]; /* tomark, line 241 */ + m3 = z->lb; z->lb = z->c; + z->c = z->l - m; + { int m = z->l - z->c; /* do, line 242 */ + { int m = z->l - z->c; /* or, line 243 */ + if (!r_perfective_gerund(z)) goto lab3; /* call perfective_gerund, line 243 */ + goto lab2; + lab3: + z->c = z->l - m; + { int m = z->l - z->c; /* try, line 244 */ + if (!r_reflexive(z)) { z->c = z->l - m; goto lab4; } /* call reflexive, line 244 */ + lab4: + ; + } + { int m = z->l - z->c; /* or, line 245 */ + if (!r_adjectival(z)) goto lab6; /* call adjectival, line 245 */ + goto lab5; + lab6: + z->c = z->l - m; + if (!r_verb(z)) goto lab7; /* call verb, line 245 */ + goto lab5; + lab7: + z->c = z->l - m; + if (!r_noun(z)) goto lab1; /* call noun, line 245 */ + } + lab5: + ; + } + lab2: + lab1: + z->c = z->l - m; + } + { int m = z->l - z->c; /* try, line 248 */ + z->ket = z->c; /* [, line 248 */ + if (!(eq_s_b(z, 1, s_9))) { z->c = z->l - m; goto lab8; } + z->bra = z->c; /* ], line 248 */ + slice_del(z); /* delete, line 248 */ + lab8: + ; + } + { int m = z->l - z->c; /* do, line 251 */ + if (!r_derivational(z)) goto lab9; /* call derivational, line 251 */ + lab9: + z->c = z->l - m; + } + { int m = z->l - z->c; /* do, line 252 */ + if (!r_tidy_up(z)) goto lab10; /* call tidy_up, line 252 */ + lab10: + z->c = z->l - m; + } + z->lb = m3; + } + z->c = z->lb; + return 1; +} + +extern struct SN_env * russian_create_env(void) { return SN_create_env(0, 2, 0); } + +extern void russian_close_env(struct SN_env * z) { SN_close_env(z); } + diff --git a/contrib/tsearch2/snowball/russian_stem.h b/contrib/tsearch2/snowball/russian_stem.h new file mode 100644 index 0000000000..7dc26d45c8 --- /dev/null +++ b/contrib/tsearch2/snowball/russian_stem.h @@ -0,0 +1,8 @@ + +/* This file was generated automatically by the Snowball to ANSI C compiler */ + +extern struct SN_env * russian_create_env(void); +extern void russian_close_env(struct SN_env * z); + +extern int russian_stem(struct SN_env * z); + diff --git a/contrib/tsearch2/snowball/utilities.c b/contrib/tsearch2/snowball/utilities.c new file mode 100644 index 0000000000..5dc752445b --- /dev/null +++ b/contrib/tsearch2/snowball/utilities.c @@ -0,0 +1,328 @@ + +#include <stdio.h> +#include <stdlib.h> +#include <string.h> + +#include "header.h" + +#define unless(C) if(!(C)) + +#define CREATE_SIZE 1 + +extern symbol * create_s(void) +{ symbol * p = (symbol *) (HEAD + (char *) malloc(HEAD + (CREATE_SIZE + 1) * sizeof(symbol))); + CAPACITY(p) = CREATE_SIZE; + SET_SIZE(p, CREATE_SIZE); + return p; +} + +extern void lose_s(symbol * p) { free((char *) p - HEAD); } + +extern int in_grouping(struct SN_env * z, unsigned char * s, int min, int max) +{ if (z->c >= z->l) return 0; + { int ch = z->p[z->c]; + if + (ch > max || (ch -= min) < 0 || + (s[ch >> 3] & (0X1 << (ch & 0X7))) == 0) return 0; + } + z->c++; return 1; +} + +extern int in_grouping_b(struct SN_env * z, unsigned char * s, int min, int max) +{ if (z->c <= z->lb) return 0; + { int ch = z->p[z->c - 1]; + if + (ch > max || (ch -= min) < 0 || + (s[ch >> 3] & (0X1 << (ch & 0X7))) == 0) return 0; + } + z->c--; return 1; +} + +extern int out_grouping(struct SN_env * z, unsigned char * s, int min, int max) +{ if (z->c >= z->l) return 0; + { int ch = z->p[z->c]; + unless + (ch > max || (ch -= min) < 0 || + (s[ch >> 3] & (0X1 << (ch & 0X7))) == 0) return 0; + } + z->c++; return 1; +} + +extern int out_grouping_b(struct SN_env * z, unsigned char * s, int min, int max) +{ if (z->c <= z->lb) return 0; + { int ch = z->p[z->c - 1]; + unless + (ch > max || (ch -= min) < 0 || + (s[ch >> 3] & (0X1 << (ch & 0X7))) == 0) return 0; + } + z->c--; return 1; +} + + +extern int in_range(struct SN_env * z, int min, int max) +{ if (z->c >= z->l) return 0; + { int ch = z->p[z->c]; + if + (ch > max || ch < min) return 0; + } + z->c++; return 1; +} + +extern int in_range_b(struct SN_env * z, int min, int max) +{ if (z->c <= z->lb) return 0; + { int ch = z->p[z->c - 1]; + if + (ch > max || ch < min) return 0; + } + z->c--; return 1; +} + +extern int out_range(struct SN_env * z, int min, int max) +{ if (z->c >= z->l) return 0; + { int ch = z->p[z->c]; + unless + (ch > max || ch < min) return 0; + } + z->c++; return 1; +} + +extern int out_range_b(struct SN_env * z, int min, int max) +{ if (z->c <= z->lb) return 0; + { int ch = z->p[z->c - 1]; + unless + (ch > max || ch < min) return 0; + } + z->c--; return 1; +} + +extern int eq_s(struct SN_env * z, int s_size, symbol * s) +{ if (z->l - z->c < s_size || + memcmp(z->p + z->c, s, s_size * sizeof(symbol)) != 0) return 0; + z->c += s_size; return 1; +} + +extern int eq_s_b(struct SN_env * z, int s_size, symbol * s) +{ if (z->c - z->lb < s_size || + memcmp(z->p + z->c - s_size, s, s_size * sizeof(symbol)) != 0) return 0; + z->c -= s_size; return 1; +} + +extern int eq_v(struct SN_env * z, symbol * p) +{ return eq_s(z, SIZE(p), p); +} + +extern int eq_v_b(struct SN_env * z, symbol * p) +{ return eq_s_b(z, SIZE(p), p); +} + +extern int find_among(struct SN_env * z, struct among * v, int v_size) +{ + int i = 0; + int j = v_size; + + int c = z->c; int l = z->l; + symbol * q = z->p + c; + + struct among * w; + + int common_i = 0; + int common_j = 0; + + int first_key_inspected = 0; + + while(1) + { int k = i + ((j - i) >> 1); + int diff = 0; + int common = common_i < common_j ? common_i : common_j; /* smaller */ + w = v + k; + { int i; for (i = common; i < w->s_size; i++) + { if (c + common == l) { diff = -1; break; } + diff = q[common] - w->s[i]; + if (diff != 0) break; + common++; + } + } + if (diff < 0) { j = k; common_j = common; } + else { i = k; common_i = common; } + if (j - i <= 1) + { if (i > 0) break; /* v->s has been inspected */ + if (j == i) break; /* only one item in v */ + + /* - but now we need to go round once more to get + v->s inspected. This looks messy, but is actually + the optimal approach. */ + + if (first_key_inspected) break; + first_key_inspected = 1; + } + } + while(1) + { w = v + i; + if (common_i >= w->s_size) + { z->c = c + w->s_size; + if (w->function == 0) return w->result; + { int res = w->function(z); + z->c = c + w->s_size; + if (res) return w->result; + } + } + i = w->substring_i; + if (i < 0) return 0; + } +} + +/* find_among_b is for backwards processing. Same comments apply */ + +extern int find_among_b(struct SN_env * z, struct among * v, int v_size) +{ + int i = 0; + int j = v_size; + + int c = z->c; int lb = z->lb; + symbol * q = z->p + c - 1; + + struct among * w; + + int common_i = 0; + int common_j = 0; + + int first_key_inspected = 0; + + while(1) + { int k = i + ((j - i) >> 1); + int diff = 0; + int common = common_i < common_j ? common_i : common_j; + w = v + k; + { int i; for (i = w->s_size - 1 - common; i >= 0; i--) + { if (c - common == lb) { diff = -1; break; } + diff = q[- common] - w->s[i]; + if (diff != 0) break; + common++; + } + } + if (diff < 0) { j = k; common_j = common; } + else { i = k; common_i = common; } + if (j - i <= 1) + { if (i > 0) break; + if (j == i) break; + if (first_key_inspected) break; + first_key_inspected = 1; + } + } + while(1) + { w = v + i; + if (common_i >= w->s_size) + { z->c = c - w->s_size; + if (w->function == 0) return w->result; + { int res = w->function(z); + z->c = c - w->s_size; + if (res) return w->result; + } + } + i = w->substring_i; + if (i < 0) return 0; + } +} + + +extern symbol * increase_size(symbol * p, int n) +{ int new_size = n + 20; + symbol * q = (symbol *) (HEAD + (char *) malloc(HEAD + (new_size + 1) * sizeof(symbol))); + CAPACITY(q) = new_size; + memmove(q, p, CAPACITY(p) * sizeof(symbol)); lose_s(p); return q; +} + +/* to replace symbols between c_bra and c_ket in z->p by the + s_size symbols at s +*/ + +extern int replace_s(struct SN_env * z, int c_bra, int c_ket, int s_size, const symbol * s) +{ int adjustment = s_size - (c_ket - c_bra); + int len = SIZE(z->p); + if (adjustment != 0) + { if (adjustment + len > CAPACITY(z->p)) z->p = increase_size(z->p, adjustment + len); + memmove(z->p + c_ket + adjustment, z->p + c_ket, (len - c_ket) * sizeof(symbol)); + SET_SIZE(z->p, adjustment + len); + z->l += adjustment; + if (z->c >= c_ket) z->c += adjustment; else + if (z->c > c_bra) z->c = c_bra; + } + unless (s_size == 0) memmove(z->p + c_bra, s, s_size * sizeof(symbol)); + return adjustment; +} + +static void slice_check(struct SN_env * z) +{ + if (!(0 <= z->bra && + z->bra <= z->ket && + z->ket <= z->l && + z->l <= SIZE(z->p))) /* this line could be removed */ + { + fprintf(stderr, "faulty slice operation:\n"); + debug(z, -1, 0); + exit(1); + } +} + +extern void slice_from_s(struct SN_env * z, int s_size, symbol * s) +{ slice_check(z); + replace_s(z, z->bra, z->ket, s_size, s); +} + +extern void slice_from_v(struct SN_env * z, symbol * p) +{ slice_from_s(z, SIZE(p), p); +} + +extern void slice_del(struct SN_env * z) +{ slice_from_s(z, 0, 0); +} + +extern void insert_s(struct SN_env * z, int bra, int ket, int s_size, symbol * s) +{ int adjustment = replace_s(z, bra, ket, s_size, s); + if (bra <= z->bra) z->bra += adjustment; + if (bra <= z->ket) z->ket += adjustment; +} + +extern void insert_v(struct SN_env * z, int bra, int ket, symbol * p) +{ int adjustment = replace_s(z, bra, ket, SIZE(p), p); + if (bra <= z->bra) z->bra += adjustment; + if (bra <= z->ket) z->ket += adjustment; +} + +extern symbol * slice_to(struct SN_env * z, symbol * p) +{ slice_check(z); + { int len = z->ket - z->bra; + if (CAPACITY(p) < len) p = increase_size(p, len); + memmove(p, z->p + z->bra, len * sizeof(symbol)); + SET_SIZE(p, len); + } + return p; +} + +extern symbol * assign_to(struct SN_env * z, symbol * p) +{ int len = z->l; + if (CAPACITY(p) < len) p = increase_size(p, len); + memmove(p, z->p, len * sizeof(symbol)); + SET_SIZE(p, len); + return p; +} + +extern void debug(struct SN_env * z, int number, int line_count) +{ int i; + int limit = SIZE(z->p); + /*if (number >= 0) printf("%3d (line %4d): '", number, line_count);*/ + if (number >= 0) printf("%3d (line %4d): [%d]'", number, line_count,limit); + for (i = 0; i <= limit; i++) + { if (z->lb == i) printf("{"); + if (z->bra == i) printf("["); + if (z->c == i) printf("|"); + if (z->ket == i) printf("]"); + if (z->l == i) printf("}"); + if (i < limit) + { int ch = z->p[i]; + if (ch == 0) ch = '#'; + printf("%c", ch); + } + } + printf("'\n"); +} |
