mirror/postgresql
2
0
Fork 0
mirror of https://git.postgresql.org/git/postgresql.git synced 2024-12-03 08:00:21 +08:00
Code Issues Packages Projects Releases Wiki Activity

Update Snowball. I have to update it because of

Browse Source 
old version doesn't available on Snowball's site and new version
of stemmers can't be compiled with old interface.
This commit is contained in:
Teodor Sigaev 2005-09-15 11:56:58 +00:00
parent 8080e8e8ce
commit b4d107a777
11 changed files with 2223 additions and 2305 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

8
contrib/tsearch2/dict_snowball.c
View File

@ -49,7 +49,7 @@ snb_en_init(PG_FUNCTION_ARGS)
PG_FREE_IF_COPY(in, 0);
}
d->z = english_create_env();
d->z = english_ISO_8859_1_create_env();
if (!d->z)
{
freestoplist(&(d->stoplist));
@ -57,7 +57,7 @@ snb_en_init(PG_FUNCTION_ARGS)
(errcode(ERRCODE_OUT_OF_MEMORY),
errmsg("out of memory")));
}
d->stem = english_stem;
d->stem = english_ISO_8859_1_stem;
PG_RETURN_POINTER(d);
}
@ -83,7 +83,7 @@ snb_ru_init(PG_FUNCTION_ARGS)
PG_FREE_IF_COPY(in, 0);
}
d->z = russian_create_env();
d->z = russian_KOI8_R_create_env();
if (!d->z)
{
freestoplist(&(d->stoplist));
@ -91,7 +91,7 @@ snb_ru_init(PG_FUNCTION_ARGS)
(errcode(ERRCODE_OUT_OF_MEMORY),
errmsg("out of memory")));
}
d->stem = russian_stem;
d->stem = russian_KOI8_R_stem;
PG_RETURN_POINTER(d);
}

11
contrib/tsearch2/gendict/README.gendict
View File

@ -50,7 +50,7 @@ Example 1:
2. Create template files for Portuguese
./config.sh -n pt -s -p portuguese -v -C'Snowball stemmer for Portuguese'
./config.sh -n pt -s -p portuguese_ISO_8859_1 -v -C'Snowball stemmer for Portuguese'
Note, that argument for -p option should be *the same* as name of stemming
function in stem.c (without _stem)
@ -81,9 +81,10 @@ Example 1:
Here is what I have in pg_ts_dict table
psql -d testdict -c "select * from pg_ts_dict where dict_name='pt';"
dict_name | dict_init | dict_initoption | dict_lexize | dict_comment
-----------+-----------+-----------------+-------------+---------------------------------
pt | 7177806 | | 7159330 | Snowball stemmer for Portuguese
dict_name | dict_init | dict_initoption | dict_lexize | dict_comment
-----------+--------------------+-----------------+---------------------------------------+---------------------------------
pt | dinit_pt(internal) | | snb_lexize(internal,internal,integer) | Snowball stemmer for Portuguese
(1 row)
@ -127,4 +128,4 @@ Example 2:
you may edit them to create actual dictionary.
Please, check Tsearch2 home page (http://www.sai.msu.su/~megera/postgres/gist/tsearch/V2/)
for additional information about "Gendict tutorial" and dictionaries.
for additional information about "Gendict tutorial" and dictionaries.

13
contrib/tsearch2/gendict/config.sh
View File

@ -131,9 +131,16 @@ fi
if [ ${#cfile} -ne 0 ] || [ ${#hfile} -ne 0 ] ; then
[ $verbose = "yes" ] && echo -n 'Copy source and header files... '
if [ ${#cfile} -ne 0 ] ; then
if ! cp $cfile ../../$dir ; then
echo "Cant cp all or one of files: $cfile"
exit 1
if [ $stemmode = "yes" ] ; then
for cfn in $cfile
do
sed s#../runtime/## < $cfn > ../../$dir/$cfn
done
else
if ! cp $cfile ../../$dir ; then
echo "Can't cp all or one of files: $cfile"
exit 1
fi
fi
fi
if [ ${#hfile} -ne 0 ] ; then

128
contrib/tsearch2/snowball/api.c
View File

@ -1,89 +1,69 @@
#include <stdlib.h>
#include <stdlib.h> /* for calloc, free */
#include "header.h"
struct SN_env *
SN_create_env(int S_size, int I_size, int B_size)
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));
struct SN_env *z2 = z;
struct SN_env * z = (struct SN_env *) calloc(1, sizeof(struct SN_env));
if (z == NULL) return NULL;
z->p = create_s();
if (z->p == NULL) goto error;
if (S_size)
{
int i;
z->S = (symbol * *) calloc(S_size, sizeof(symbol *));
if (z->S == NULL) goto error;
if (!z)
return z;
for (i = 0; i < S_size; i++)
{
z->S[i] = create_s();
if (z->S[i] == NULL) goto error;
}
z->S_size = S_size;
}
z->p = create_s();
if (!z->p)
z = NULL;
if (I_size)
{
z->I = (int *) calloc(I_size, sizeof(int));
if (z->I == NULL) goto error;
z->I_size = I_size;
}
if (z && S_size)
{
if ((z->S = (symbol * *) calloc(S_size, sizeof(symbol *))))
{
int i;
if (B_size)
{
z->B = (symbol *) calloc(B_size, sizeof(symbol));
if (z->B == NULL) goto error;
z->B_size = B_size;
}
for (i = 0; i < S_size; i++)
{
if (!(z->S[i] = create_s()))
{
z = NULL;
break;
}
}
z2->S_size = i;
}
else
z = NULL;
}
if (z && I_size)
{
z->I = (int *) calloc(I_size, sizeof(int));
if (z->I)
z->I_size = I_size;
else
z = NULL;
}
if (z && B_size)
{
z->B = (symbol *) calloc(B_size, sizeof(symbol));
if (z->B)
z->B_size = B_size;
else
z = NULL;
}
if (!z)
SN_close_env(z2);
return z;
return z;
error:
SN_close_env(z);
return NULL;
}
void
SN_close_env(struct SN_env * z)
extern void SN_close_env(struct SN_env * z)
{
if (z->S && 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);
if (z == NULL) return;
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);
}
void
SN_set_current(struct SN_env * z, int size, const symbol * s)
extern int SN_set_current(struct SN_env * z, int size, const symbol * s)
{
replace_s(z, 0, z->l, size, s);
z->c = 0;
int err = replace_s(z, 0, z->l, size, s, NULL);
z->c = 0;
return err;
}

27
contrib/tsearch2/snowball/api.h
View File

@ -11,24 +11,17 @@ typedef unsigned char symbol;
*/
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;
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 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);
extern int SN_set_current(struct SN_env * z, int size, const symbol * s);

2135
contrib/tsearch2/snowball/english_stem.c
View File

File diff suppressed because it is too large Load Diff

15
contrib/tsearch2/snowball/english_stem.h
View File

@ -1,7 +1,16 @@
/* 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);
#ifdef __cplusplus
extern "C" {
#endif
extern struct SN_env * english_ISO_8859_1_create_env(void);
extern void english_ISO_8859_1_close_env(struct SN_env * z);
extern int english_ISO_8859_1_stem(struct SN_env * z);
#ifdef __cplusplus
}
#endif
extern int english_stem(struct SN_env * z);

69
contrib/tsearch2/snowball/header.h
View File

@ -1,51 +1,58 @@
#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 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 *);
{ 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 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 skip_utf8(const symbol * p, int c, int lb, int l, int n);
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 in_grouping_U(struct SN_env * z, unsigned char * s, int min, int max);
extern int in_grouping_b_U(struct SN_env * z, unsigned char * s, int min, int max);
extern int out_grouping_U(struct SN_env * z, unsigned char * s, int min, int max);
extern int out_grouping_b_U(struct SN_env * z, unsigned char * s, 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 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 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 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 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 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 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 int replace_s(struct SN_env * z, int c_bra, int c_ket, int s_size, const symbol * s, int * adjustment);
extern int slice_from_s(struct SN_env * z, int s_size, symbol * s);
extern int slice_from_v(struct SN_env * z, symbol * p);
extern int slice_del(struct SN_env * z);
extern symbol *slice_to(struct SN_env * z, symbol * p);
extern symbol *assign_to(struct SN_env * z, symbol * p);
extern int insert_s(struct SN_env * z, int bra, int ket, int s_size, symbol * s);
extern int 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);

1321
contrib/tsearch2/snowball/russian_stem.c
View File

File diff suppressed because it is too large Load Diff

15
contrib/tsearch2/snowball/russian_stem.h
View File

@ -1,7 +1,16 @@
/* 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);
#ifdef __cplusplus
extern "C" {
#endif
extern struct SN_env * russian_KOI8_R_create_env(void);
extern void russian_KOI8_R_close_env(struct SN_env * z);
extern int russian_KOI8_R_stem(struct SN_env * z);
#ifdef __cplusplus
}
#endif
extern int russian_stem(struct SN_env * z);

786
contrib/tsearch2/snowball/utilities.c
View File

@ -9,510 +9,438 @@
#define CREATE_SIZE 1
symbol *
create_s(void)
{
symbol *p = (symbol *) (HEAD + (char *) malloc(HEAD + (CREATE_SIZE + 1) * sizeof(symbol)));
if (p == (symbol *) (HEAD))
return NULL;
CAPACITY(p) = CREATE_SIZE;
SET_SIZE(p, CREATE_SIZE);
return p;
extern symbol * create_s(void) {
symbol * p;
void * mem = malloc(HEAD + (CREATE_SIZE + 1) * sizeof(symbol));
if (mem == NULL) return NULL;
p = (symbol *) (HEAD + (char *) mem);
CAPACITY(p) = CREATE_SIZE;
SET_SIZE(p, CREATE_SIZE);
return p;
}
void
lose_s(symbol * p)
{
free((char *) p - HEAD);
extern void lose_s(symbol * p) {
if (p == NULL) return;
free((char *) p - HEAD);
}
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];
/*
new_p = X_skip_utf8(p, c, lb, l, n); skips n characters forwards from p + c
if n +ve, or n characters backwards from p +c - 1 if n -ve. new_p is the new
position, or 0 on failure.
if
(ch > max || (ch -= min) < 0 ||
(s[ch >> 3] & (0X1 << (ch & 0X7))) == 0)
return 0;
}
z->c++;
return 1;
-- used to implement hop and next in the utf8 case.
*/
extern int skip_utf8(const symbol * p, int c, int lb, int l, int n) {
int b;
if (n >= 0) {
for (; n > 0; n--) {
if (c >= l) return -1;
b = p[c++];
if (b >= 0xC0) { /* 1100 0000 */
while (c < l) {
b = p[c];
if (b >= 0xC0 || b < 0x80) break;
/* break unless b is 10------ */
c++;
}
}
}
} else {
for (; n < 0; n++) {
if (c <= lb) return -1;
b = p[--c];
if (b >= 0x80) { /* 1000 0000 */
while (c > lb) {
b = p[c];
if (b >= 0xC0) break; /* 1100 0000 */
c--;
}
}
}
}
return c;
}
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];
/* Code for character groupings: utf8 cases */
if
(ch > max || (ch -= min) < 0 ||
(s[ch >> 3] & (0X1 << (ch & 0X7))) == 0)
return 0;
}
z->c--;
return 1;
static int get_utf8(const symbol * p, int c, int l, int * slot) {
int b0, b1;
if (c >= l) return 0;
b0 = p[c++];
if (b0 < 0xC0 || c == l) { /* 1100 0000 */
* slot = b0; return 1;
}
b1 = p[c++];
if (b0 < 0xE0 || c == l) { /* 1110 0000 */
* slot = (b0 & 0x1F) << 6 | (b1 & 0x3F); return 2;
}
* slot = (b0 & 0xF) << 12 | (b1 & 0x3F) << 6 | (*p & 0x3F); return 3;
}
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;
static int get_b_utf8(const symbol * p, int c, int lb, int * slot) {
int b0, b1;
if (c <= lb) return 0;
b0 = p[--c];
if (b0 < 0x80 || c == lb) { /* 1000 0000 */
* slot = b0; return 1;
}
b1 = p[--c];
if (b1 >= 0xC0 || c == lb) { /* 1100 0000 */
* slot = (b1 & 0x1F) << 6 | (b0 & 0x3F); return 2;
}
* slot = (*p & 0xF) << 12 | (b1 & 0x3F) << 6 | (b0 & 0x3F); return 3;
}
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_grouping_U(struct SN_env * z, unsigned char * s, int min, int max) {
int ch;
int w = get_utf8(z->p, z->c, z->l, & ch);
unless (w) return 0;
if (ch > max || (ch -= min) < 0 || (s[ch >> 3] & (0X1 << (ch & 0X7))) == 0) return 0;
z->c += w; return 1;
}
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_grouping_b_U(struct SN_env * z, unsigned char * s, int min, int max) {
int ch;
int w = get_b_utf8(z->p, z->c, z->lb, & ch);
unless (w) return 0;
if (ch > max || (ch -= min) < 0 || (s[ch >> 3] & (0X1 << (ch & 0X7))) == 0) return 0;
z->c -= w; return 1;
}
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_grouping_U(struct SN_env * z, unsigned char * s, int min, int max) {
int ch;
int w = get_utf8(z->p, z->c, z->l, & ch);
unless (w) return 0;
unless (ch > max || (ch -= min) < 0 || (s[ch >> 3] & (0X1 << (ch & 0X7))) == 0) return 0;
z->c += w; return 1;
}
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_grouping_b_U(struct SN_env * z, unsigned char * s, int min, int max) {
int ch;
int w = get_b_utf8(z->p, z->c, z->lb, & ch);
unless (w) return 0;
unless (ch > max || (ch -= min) < 0 || (s[ch >> 3] & (0X1 << (ch & 0X7))) == 0) return 0;
z->c -= w; return 1;
}
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];
/* Code for character groupings: non-utf8 cases */
unless
(ch > max || ch < min) return 0;
}
z->c--;
return 1;
extern int in_grouping(struct SN_env * z, unsigned char * s, int min, int max) {
int ch;
if (z->c >= z->l) return 0;
ch = z->p[z->c];
if (ch > max || (ch -= min) < 0 || (s[ch >> 3] & (0X1 << (ch & 0X7))) == 0) return 0;
z->c++; return 1;
}
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 in_grouping_b(struct SN_env * z, unsigned char * s, int min, int max) {
int ch;
if (z->c <= z->lb) return 0;
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;
}
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 out_grouping(struct SN_env * z, unsigned char * s, int min, int max) {
int ch;
if (z->c >= z->l) return 0;
ch = z->p[z->c];
unless (ch > max || (ch -= min) < 0 || (s[ch >> 3] & (0X1 << (ch & 0X7))) == 0) return 0;
z->c++; return 1;
}
int
eq_v(struct SN_env * z, symbol * p)
{
return eq_s(z, SIZE(p), p);
extern int out_grouping_b(struct SN_env * z, unsigned char * s, int min, int max) {
int ch;
if (z->c <= z->lb) return 0;
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;
}
int
eq_v_b(struct SN_env * z, symbol * p)
{
return eq_s_b(z, SIZE(p), p);
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;
}
int
find_among(struct SN_env * z, struct among * v, int v_size)
{
int i = 0;
int j = v_size;
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;
}
int c = z->c;
int l = z->l;
symbol *q = z->p + c;
extern int eq_v(struct SN_env * z, symbol * p) {
return eq_s(z, SIZE(p), p);
}
struct among *w;
extern int eq_v_b(struct SN_env * z, symbol * p) {
return eq_s_b(z, SIZE(p), p);
}
int common_i = 0;
int common_j = 0;
extern int find_among(struct SN_env * z, struct among * v, int v_size) {
int first_key_inspected = 0;
int i = 0;
int j = v_size;
while (1)
{
int k = i + ((j - i) >> 1);
int diff = 0;
int common = common_i < common_j ? common_i : common_j; /* smaller */
int c = z->c; int l = z->l;
symbol * q = z->p + c;
w = v + k;
{
int i;
struct among * w;
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 */
int common_i = 0;
int common_j = 0;
/*
* - but now we need to go round once more to get v->s
* inspected. This looks messy, but is actually the optimal
* approach.
*/
int first_key_inspected = 0;
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);
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 */
z->c = c + w->s_size;
if (res)
return w->result;
}
}
i = w->substring_i;
if (i < 0)
return 0;
}
/* - 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 */
int
find_among_b(struct SN_env * z, struct among * v, int v_size)
{
int i = 0;
int j = v_size;
extern int find_among_b(struct SN_env * z, struct among * v, int v_size) {
int c = z->c;
int lb = z->lb;
symbol *q = z->p + c - 1;
int i = 0;
int j = v_size;
struct among *w;
int c = z->c; int lb = z->lb;
symbol * q = z->p + c - 1;
int common_i = 0;
int common_j = 0;
struct among * w;
int first_key_inspected = 0;
int common_i = 0;
int common_j = 0;
while (1)
{
int k = i + ((j - i) >> 1);
int diff = 0;
int common = common_i < common_j ? common_i : common_j;
int first_key_inspected = 0;
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;
}
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;
}
}
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;
/* Increase the size of the buffer pointed to by p to at least n symbols.
* If insufficient memory, returns NULL and frees the old buffer.
*/
static symbol * increase_size(symbol * p, int n) {
symbol * q;
int new_size = n + 20;
void * mem = realloc((char *) p - HEAD,
HEAD + (new_size + 1) * sizeof(symbol));
if (mem == NULL) {
lose_s(p);
return NULL;
}
q = (symbol *) (HEAD + (char *)mem);
CAPACITY(q) = new_size;
return q;
}
/* to replace symbols between c_bra and c_ket in z->p by the
s_size symbols at s
s_size symbols at s.
Returns 0 on success, -1 on error.
Also, frees z->p (and sets it to NULL) on error.
*/
int
replace_s(struct SN_env * z, int c_bra, int c_ket, int s_size, const symbol * s)
extern int replace_s(struct SN_env * z, int c_bra, int c_ket, int s_size, const symbol * s, int * adjptr)
{
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;
int adjustment;
int len;
if (z->p == NULL) {
z->p = create_s();
if (z->p == NULL) return -1;
}
adjustment = s_size - (c_ket - c_bra);
len = SIZE(z->p);
if (adjustment != 0) {
if (adjustment + len > CAPACITY(z->p)) {
z->p = increase_size(z->p, adjustment + len);
if (z->p == NULL) return -1;
}
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));
if (adjptr != NULL)
*adjptr = adjustment;
return 0;
}
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);
}
static int slice_check(struct SN_env * z) {
if (z->bra < 0 ||
z->bra > z->ket ||
z->ket > z->l ||
z->p == NULL ||
z->l > SIZE(z->p)) /* this line could be removed */
{
#if 0
fprintf(stderr, "faulty slice operation:\n");
debug(z, -1, 0);
#endif
return -1;
}
return 0;
}
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 int slice_from_s(struct SN_env * z, int s_size, symbol * s) {
if (slice_check(z)) return -1;
return replace_s(z, z->bra, z->ket, s_size, s, NULL);
}
void
slice_from_v(struct SN_env * z, symbol * p)
{
slice_from_s(z, SIZE(p), p);
extern int slice_from_v(struct SN_env * z, symbol * p) {
return slice_from_s(z, SIZE(p), p);
}
void
slice_del(struct SN_env * z)
{
slice_from_s(z, 0, NULL);
extern int slice_del(struct SN_env * z) {
return slice_from_s(z, 0, 0);
}
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 int insert_s(struct SN_env * z, int bra, int ket, int s_size, symbol * s) {
int adjustment;
if (replace_s(z, bra, ket, s_size, s, &adjustment))
return -1;
if (bra <= z->bra) z->bra += adjustment;
if (bra <= z->ket) z->ket += adjustment;
return 0;
}
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 int insert_v(struct SN_env * z, int bra, int ket, symbol * p) {
int adjustment;
if (replace_s(z, bra, ket, SIZE(p), p, &adjustment))
return -1;
if (bra <= z->bra) z->bra += adjustment;
if (bra <= z->ket) z->ket += adjustment;
return 0;
}
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 * slice_to(struct SN_env * z, symbol * p) {
if (slice_check(z)) {
lose_s(p);
return NULL;
}
{
int len = z->ket - z->bra;
if (CAPACITY(p) < len) {
p = increase_size(p, len);
if (p == NULL)
return NULL;
}
memmove(p, z->p + z->bra, len * sizeof(symbol));
SET_SIZE(p, len);
}
return p;
}
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 symbol * assign_to(struct SN_env * z, symbol * p) {
int len = z->l;
if (CAPACITY(p) < len) {
p = increase_size(p, len);
if (p == NULL)
return NULL;
}
memmove(p, z->p, len * sizeof(symbol));
SET_SIZE(p, len);
return p;
}
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");
#if 0
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");
}
#endif