aboutsummaryrefslogtreecommitdiff
path: root/contrib/ltree/ltxtquery_io.c
diff options
context:
space:
mode:
Diffstat (limited to 'contrib/ltree/ltxtquery_io.c')
-rw-r--r--contrib/ltree/ltxtquery_io.c484
1 files changed, 484 insertions, 0 deletions
diff --git a/contrib/ltree/ltxtquery_io.c b/contrib/ltree/ltxtquery_io.c
new file mode 100644
index 00000000000..e70d643b855
--- /dev/null
+++ b/contrib/ltree/ltxtquery_io.c
@@ -0,0 +1,484 @@
+/*
+ * txtquery io
+ * Teodor Sigaev <teodor@stack.net>
+ */
+
+#include "ltree.h"
+#include <ctype.h>
+#include "crc32.h"
+
+PG_FUNCTION_INFO_V1(ltxtq_in);
+Datum ltxtq_in(PG_FUNCTION_ARGS);
+PG_FUNCTION_INFO_V1(ltxtq_out);
+Datum ltxtq_out(PG_FUNCTION_ARGS);
+
+
+/* parser's states */
+#define WAITOPERAND 1
+#define INOPERAND 2
+#define WAITOPERATOR 3
+
+/*
+ * node of query tree, also used
+ * for storing polish notation in parser
+ */
+typedef struct NODE {
+ int4 type;
+ int4 val;
+ int2 distance;
+ int2 length;
+ uint16 flag;
+ struct NODE *next;
+} NODE;
+
+typedef struct {
+ char *buf;
+ int4 state;
+ int4 count;
+ /* reverse polish notation in list (for temprorary usage) */
+ NODE *str;
+ /* number in str */
+ int4 num;
+
+ /* user-friendly operand */
+ int4 lenop;
+ int4 sumlen;
+ char *op;
+ char *curop;
+} QPRS_STATE;
+
+/*
+ * get token from query string
+ */
+static int4
+gettoken_query(QPRS_STATE * state, int4 *val, int4 *lenval, char **strval, uint16 *flag)
+{
+ while (1)
+ {
+ switch (state->state)
+ {
+ case WAITOPERAND:
+ if (*(state->buf) == '!')
+ {
+ (state->buf)++;
+ *val = (int4) '!';
+ return OPR;
+ }
+ else if (*(state->buf) == '(')
+ {
+ state->count++;
+ (state->buf)++;
+ return OPEN;
+ }
+ else if ( ISALNUM(*(state->buf)) )
+ {
+ state->state = INOPERAND;
+ *strval = state->buf;
+ *lenval = 1;
+ *flag = 0;
+ } else if ( !isspace(*(state->buf)) )
+ elog(ERROR,"Operand syntax error");
+ break;
+ case INOPERAND:
+ if ( ISALNUM(*(state->buf)) ) {
+ if ( *flag )
+ elog(ERROR,"Modificators syntax error");
+ (*lenval)++;
+ } else if ( *(state->buf) == '%' ) {
+ *flag |= LVAR_SUBLEXEM;
+ } else if ( *(state->buf) == '@' ) {
+ *flag |= LVAR_INCASE;
+ } else if ( *(state->buf) == '*' ) {
+ *flag |= LVAR_ANYEND;
+ } else {
+ state->state = WAITOPERATOR;
+ return VAL;
+ }
+ break;
+ case WAITOPERATOR:
+ if (*(state->buf) == '&' || *(state->buf) == '|')
+ {
+ state->state = WAITOPERAND;
+ *val = (int4) *(state->buf);
+ (state->buf)++;
+ return OPR;
+ }
+ else if (*(state->buf) == ')')
+ {
+ (state->buf)++;
+ state->count--;
+ return (state->count < 0) ? ERR : CLOSE;
+ }
+ else if (*(state->buf) == '\0')
+ return (state->count) ? ERR : END;
+ else if (*(state->buf) != ' ')
+ return ERR;
+ break;
+ default:
+ return ERR;
+ break;
+ }
+ (state->buf)++;
+ }
+ return END;
+}
+
+/*
+ * push new one in polish notation reverse view
+ */
+static void
+pushquery(QPRS_STATE * state, int4 type, int4 val, int4 distance, int4 lenval, uint16 flag)
+{
+ NODE *tmp = (NODE *) palloc(sizeof(NODE));
+
+ tmp->type = type;
+ tmp->val = val;
+ tmp->flag = flag;
+ if (distance > 0xffff)
+ elog(ERROR, "Value is too big");
+ if (lenval > 0xff)
+ elog(ERROR, "Operand is too long");
+ tmp->distance = distance;
+ tmp->length = lenval;
+ tmp->next = state->str;
+ state->str = tmp;
+ state->num++;
+}
+
+/*
+ * This function is used for query_txt parsing
+ */
+static void
+pushval_asis(QPRS_STATE * state, int type, char *strval, int lenval, uint16 flag)
+{
+ if (lenval > 0xffff)
+ elog(ERROR, "Word is too long");
+
+ pushquery(state, type, crc32_sz((uint8 *) strval, lenval),
+ state->curop - state->op, lenval, flag);
+
+ while (state->curop - state->op + lenval + 1 >= state->lenop)
+ {
+ int4 tmp = state->curop - state->op;
+
+ state->lenop *= 2;
+ state->op = (char *) repalloc((void *) state->op, state->lenop);
+ state->curop = state->op + tmp;
+ }
+ memcpy((void *) state->curop, (void *) strval, lenval);
+ state->curop += lenval;
+ *(state->curop) = '\0';
+ state->curop++;
+ state->sumlen += lenval + 1;
+ return;
+}
+
+#define STACKDEPTH 32
+/*
+ * make polish notaion of query
+ */
+static int4
+makepol(QPRS_STATE * state)
+{
+ int4 val,
+ type;
+ int4 lenval;
+ char *strval;
+ int4 stack[STACKDEPTH];
+ int4 lenstack = 0;
+ uint16 flag;
+
+ while ((type = gettoken_query(state, &val, &lenval, &strval,&flag)) != END) {
+ switch (type)
+ {
+ case VAL:
+ pushval_asis(state, VAL, strval, lenval,flag);
+ while (lenstack && (stack[lenstack - 1] == (int4) '&' ||
+ stack[lenstack - 1] == (int4) '!'))
+ {
+ lenstack--;
+ pushquery(state, OPR, stack[lenstack], 0, 0, 0);
+ }
+ break;
+ case OPR:
+ if (lenstack && val == (int4) '|')
+ pushquery(state, OPR, val, 0, 0, 0);
+ else
+ {
+ if (lenstack == STACKDEPTH)
+ elog(ERROR, "Stack too short");
+ stack[lenstack] = val;
+ lenstack++;
+ }
+ break;
+ case OPEN:
+ if (makepol(state) == ERR)
+ return ERR;
+ if (lenstack && (stack[lenstack - 1] == (int4) '&' ||
+ stack[lenstack - 1] == (int4) '!'))
+ {
+ lenstack--;
+ pushquery(state, OPR, stack[lenstack], 0, 0, 0);
+ }
+ break;
+ case CLOSE:
+ while (lenstack)
+ {
+ lenstack--;
+ pushquery(state, OPR, stack[lenstack], 0, 0, 0);
+ };
+ return END;
+ break;
+ case ERR:
+ default:
+ elog(ERROR, "Syntax error");
+ return ERR;
+
+ }
+ }
+ while (lenstack) {
+ lenstack--;
+ pushquery(state, OPR, stack[lenstack], 0, 0, 0);
+ };
+ return END;
+}
+
+static void
+findoprnd(ITEM * ptr, int4 *pos)
+{
+ if (ptr[*pos].type == VAL || ptr[*pos].type == VALTRUE)
+ {
+ ptr[*pos].left = 0;
+ (*pos)++;
+ }
+ else if (ptr[*pos].val == (int4) '!')
+ {
+ ptr[*pos].left = 1;
+ (*pos)++;
+ findoprnd(ptr, pos);
+ }
+ else
+ {
+ ITEM *curitem = &ptr[*pos];
+ int4 tmp = *pos;
+
+ (*pos)++;
+ findoprnd(ptr, pos);
+ curitem->left = *pos - tmp;
+ findoprnd(ptr, pos);
+ }
+}
+
+
+/*
+ * input
+ */
+static ltxtquery *
+queryin(char *buf)
+{
+ QPRS_STATE state;
+ int4 i;
+ ltxtquery *query;
+ int4 commonlen;
+ ITEM *ptr;
+ NODE *tmp;
+ int4 pos = 0;
+
+#ifdef BS_DEBUG
+ char pbuf[16384],
+ *cur;
+#endif
+
+ /* init state */
+ state.buf = buf;
+ state.state = WAITOPERAND;
+ state.count = 0;
+ state.num = 0;
+ state.str = NULL;
+
+ /* init list of operand */
+ state.sumlen = 0;
+ state.lenop = 64;
+ state.curop = state.op = (char *) palloc(state.lenop);
+ *(state.curop) = '\0';
+
+ /* parse query & make polish notation (postfix, but in reverse order) */
+ makepol(&state);
+ if (!state.num)
+ elog(ERROR, "Empty query");
+ /* make finish struct */
+ commonlen = COMPUTESIZE(state.num, state.sumlen);
+ query = (ltxtquery *) palloc(commonlen);
+ query->len = commonlen;
+ query->size = state.num;
+ ptr = GETQUERY(query);
+
+ /* set item in polish notation */
+ for (i = 0; i < state.num; i++)
+ {
+ ptr[i].type = state.str->type;
+ ptr[i].val = state.str->val;
+ ptr[i].distance = state.str->distance;
+ ptr[i].length = state.str->length;
+ ptr[i].flag = state.str->flag;
+ tmp = state.str->next;
+ pfree(state.str);
+ state.str = tmp;
+ }
+
+ /* set user friendly-operand view */
+ memcpy((void *) GETOPERAND(query), (void *) state.op, state.sumlen);
+ pfree(state.op);
+
+ /* set left operand's position for every operator */
+ pos = 0;
+ findoprnd(ptr, &pos);
+
+ return query;
+}
+
+/*
+ * in without morphology
+ */
+Datum
+ltxtq_in(PG_FUNCTION_ARGS)
+{
+ PG_RETURN_POINTER(queryin((char *) PG_GETARG_POINTER(0)));
+}
+
+/*
+ * out function
+ */
+typedef struct
+{
+ ITEM *curpol;
+ char *buf;
+ char *cur;
+ char *op;
+ int4 buflen;
+} INFIX;
+
+#define RESIZEBUF(inf,addsize) \
+while( ( inf->cur - inf->buf ) + addsize + 1 >= inf->buflen ) \
+{ \
+ int4 len = inf->cur - inf->buf; \
+ inf->buflen *= 2; \
+ inf->buf = (char*) repalloc( (void*)inf->buf, inf->buflen ); \
+ inf->cur = inf->buf + len; \
+}
+
+/*
+ * recursive walk on tree and print it in
+ * infix (human-readable) view
+ */
+static void
+infix(INFIX * in, bool first)
+{
+ if (in->curpol->type == VAL)
+ {
+ char *op = in->op + in->curpol->distance;
+
+ RESIZEBUF(in, in->curpol->length * 2 + 5);
+ while (*op) {
+ *(in->cur) = *op;
+ op++;
+ in->cur++;
+ }
+ if ( in->curpol->flag & LVAR_SUBLEXEM ) {
+ *(in->cur) = '%';
+ in->cur++;
+ }
+ if ( in->curpol->flag & LVAR_INCASE ) {
+ *(in->cur) = '@';
+ in->cur++;
+ }
+ if ( in->curpol->flag & LVAR_ANYEND ) {
+ *(in->cur) = '*';
+ in->cur++;
+ }
+ *(in->cur) = '\0';
+ in->curpol++;
+ }
+ else if (in->curpol->val == (int4) '!')
+ {
+ bool isopr = false;
+
+ RESIZEBUF(in, 1);
+ *(in->cur) = '!';
+ in->cur++;
+ *(in->cur) = '\0';
+ in->curpol++;
+ if (in->curpol->type == OPR)
+ {
+ isopr = true;
+ RESIZEBUF(in, 2);
+ sprintf(in->cur, "( ");
+ in->cur = strchr(in->cur, '\0');
+ }
+ infix(in, isopr);
+ if (isopr)
+ {
+ RESIZEBUF(in, 2);
+ sprintf(in->cur, " )");
+ in->cur = strchr(in->cur, '\0');
+ }
+ }
+ else
+ {
+ int4 op = in->curpol->val;
+ INFIX nrm;
+
+ in->curpol++;
+ if (op == (int4) '|' && !first)
+ {
+ RESIZEBUF(in, 2);
+ sprintf(in->cur, "( ");
+ in->cur = strchr(in->cur, '\0');
+ }
+
+ nrm.curpol = in->curpol;
+ nrm.op = in->op;
+ nrm.buflen = 16;
+ nrm.cur = nrm.buf = (char *) palloc(sizeof(char) * nrm.buflen);
+
+ /* get right operand */
+ infix(&nrm, false);
+
+ /* get & print left operand */
+ in->curpol = nrm.curpol;
+ infix(in, false);
+
+ /* print operator & right operand */
+ RESIZEBUF(in, 3 + (nrm.cur - nrm.buf));
+ sprintf(in->cur, " %c %s", op, nrm.buf);
+ in->cur = strchr(in->cur, '\0');
+ pfree(nrm.buf);
+
+ if (op == (int4) '|' && !first)
+ {
+ RESIZEBUF(in, 2);
+ sprintf(in->cur, " )");
+ in->cur = strchr(in->cur, '\0');
+ }
+ }
+}
+
+Datum
+ltxtq_out(PG_FUNCTION_ARGS)
+{
+ ltxtquery *query = PG_GETARG_LTXTQUERY(0);
+ INFIX nrm;
+
+ if (query->size == 0)
+ elog(ERROR, "Empty");
+ nrm.curpol = GETQUERY(query);
+ nrm.buflen = 32;
+ nrm.cur = nrm.buf = (char *) palloc(sizeof(char) * nrm.buflen);
+ *(nrm.cur) = '\0';
+ nrm.op = GETOPERAND(query);
+ infix(&nrm, true);
+
+ PG_FREE_IF_COPY(query, 0);
+ PG_RETURN_POINTER(nrm.buf);
+}
+
generated by cgit v1.2.3 (git 2.25.1) at 2025-05-30 23:26:07 +0000