* USE OR PERFORMANCE OF THIS SOFTWARE.
*
*/
+/**
+ * \file ccltoken.c
+ * \brief Implements CCL lexical analyzer (scanner)
+ */
/* CCL - lexical analysis
* Europagate, 1995
*
- * $Id: ccltoken.c,v 1.1 2003-10-27 12:21:30 adam Exp $
+ * $Id: ccltoken.c,v 1.9 2005-08-22 20:34:21 adam Exp $
*
* Old Europagate Log:
*
aliases = ccl_qual_search_special(cclp->bibset, "case");
if (aliases)
- case_sensitive = atoi(aliases);
+ case_sensitive = atoi(aliases);
if (!kw)
return 0;
while ((cp2 = strchr (cp1, ' ')))
return 1;
}
}
- cp1 = cp2+1;
+ cp1 = cp2+1;
}
if (case_sensitive)
return token->len == strlen(cp1)
}
/*
- * ccl_token_simple: tokenize CCL raw tokens
- */
-struct ccl_token *ccl_token_simple (const char *command)
-{
- const char *cp = command;
- struct ccl_token *first = NULL;
- struct ccl_token *last = NULL;
-
- while (1)
- {
- while (*cp && strchr (" \t\r\n", *cp))
- {
- cp++;
- continue;
- }
- if (!first)
- {
- first = last = (struct ccl_token *)xmalloc (sizeof (*first));
- ccl_assert (first);
- last->prev = NULL;
- }
- else
- {
- last->next = (struct ccl_token *)xmalloc (sizeof(*first));
- ccl_assert (last->next);
- last->next->prev = last;
- last = last->next;
- }
- last->next = NULL;
- last->name = cp;
- last->len = 1;
- switch (*cp++)
- {
- case '\0':
- last->kind = CCL_TOK_EOL;
- return first;
- case '\"':
- last->kind = CCL_TOK_TERM;
- last->name = cp;
- last->len = 0;
- while (*cp && *cp != '\"')
- {
- cp++;
- ++ last->len;
- }
- if (*cp == '\"')
- cp++;
- break;
- default:
- while (*cp && !strchr (" \t\n\r", *cp))
- {
- cp++;
- ++ last->len;
- }
- last->kind = CCL_TOK_TERM;
- }
- }
- return first;
-}
-
-
-/*
* ccl_tokenize: tokenize CCL command string.
* return: CCL token list.
*/
struct ccl_token *ccl_parser_tokenize (CCL_parser cclp, const char *command)
{
const char *aliases;
- const char *cp = command;
+ const unsigned char *cp = (const unsigned char *) command;
struct ccl_token *first = NULL;
struct ccl_token *last = NULL;
while (1)
{
- while (*cp && strchr (" \t\r\n", *cp))
- {
- cp++;
- continue;
- }
- if (!first)
- {
- first = last = (struct ccl_token *)xmalloc (sizeof (*first));
- ccl_assert (first);
- last->prev = NULL;
- }
- else
- {
- last->next = (struct ccl_token *)xmalloc (sizeof(*first));
- ccl_assert (last->next);
- last->next->prev = last;
- last = last->next;
- }
- last->next = NULL;
- last->name = cp;
- last->len = 1;
- switch (*cp++)
- {
+ const unsigned char *cp0 = cp;
+ while (*cp && strchr (" \t\r\n", *cp))
+ cp++;
+ if (!first)
+ {
+ first = last = (struct ccl_token *)xmalloc (sizeof (*first));
+ ccl_assert (first);
+ last->prev = NULL;
+ }
+ else
+ {
+ last->next = (struct ccl_token *)xmalloc (sizeof(*first));
+ ccl_assert (last->next);
+ last->next->prev = last;
+ last = last->next;
+ }
+ last->ws_prefix_buf = (const char *) cp0;
+ last->ws_prefix_len = cp - cp0;
+ last->next = NULL;
+ last->name = (const char *) cp;
+ last->len = 1;
+ switch (*cp++)
+ {
case '\0':
last->kind = CCL_TOK_EOL;
return first;
- case '(':
- last->kind = CCL_TOK_LP;
- break;
- case ')':
- last->kind = CCL_TOK_RP;
- break;
- case ',':
- last->kind = CCL_TOK_COMMA;
- break;
- case '%':
- case '!':
- last->kind = CCL_TOK_PROX;
+ case '(':
+ last->kind = CCL_TOK_LP;
+ break;
+ case ')':
+ last->kind = CCL_TOK_RP;
+ break;
+ case ',':
+ last->kind = CCL_TOK_COMMA;
+ break;
+ case '%':
+ case '!':
+ last->kind = CCL_TOK_PROX;
while (isdigit(*cp))
- {
- ++ last->len;
- cp++;
- }
- break;
- case '>':
- case '<':
- case '=':
- if (*cp == '=' || *cp == '<' || *cp == '>')
- {
- cp++;
- last->kind = CCL_TOK_REL;
- ++ last->len;
- }
- else if (cp[-1] == '=')
- last->kind = CCL_TOK_EQ;
- else
- last->kind = CCL_TOK_REL;
- break;
- case '\"':
- last->kind = CCL_TOK_TERM;
- last->name = cp;
- last->len = 0;
- while (*cp && *cp != '\"')
- {
- cp++;
- ++ last->len;
- }
- if (*cp == '\"')
- cp++;
- break;
- default:
- if (!strchr ("(),%!><= \t\n\r", cp[-1]))
- {
- while (*cp && !strchr ("(),%!><= \t\n\r", *cp))
- {
- cp++;
- ++ last->len;
- }
- }
- last->kind = CCL_TOK_TERM;
+ {
+ ++ last->len;
+ cp++;
+ }
+ break;
+ case '>':
+ case '<':
+ case '=':
+ if (*cp == '=' || *cp == '<' || *cp == '>')
+ {
+ cp++;
+ last->kind = CCL_TOK_REL;
+ ++ last->len;
+ }
+ else if (cp[-1] == '=')
+ last->kind = CCL_TOK_EQ;
+ else
+ last->kind = CCL_TOK_REL;
+ break;
+ case '\"':
+ last->kind = CCL_TOK_TERM;
+ last->name = (const char *) cp;
+ last->len = 0;
+ while (*cp && *cp != '\"')
+ {
+ cp++;
+ ++ last->len;
+ }
+ if (*cp == '\"')
+ cp++;
+ break;
+ default:
+ if (!strchr ("(),%!><= \t\n\r", cp[-1]))
+ {
+ while (*cp && !strchr ("(),%!><= \t\n\r", *cp))
+ {
+ cp++;
+ ++ last->len;
+ }
+ }
+ last->kind = CCL_TOK_TERM;
- aliases = ccl_qual_search_special(cclp->bibset, "and");
- if (!aliases)
- aliases = cclp->ccl_token_and;
- if (token_cmp (cclp, aliases, last))
- last->kind = CCL_TOK_AND;
+ aliases = ccl_qual_search_special(cclp->bibset, "and");
+ if (!aliases)
+ aliases = cclp->ccl_token_and;
+ if (token_cmp (cclp, aliases, last))
+ last->kind = CCL_TOK_AND;
- aliases = ccl_qual_search_special(cclp->bibset, "or");
- if (!aliases)
- aliases = cclp->ccl_token_or;
- if (token_cmp (cclp, aliases, last))
- last->kind = CCL_TOK_OR;
+ aliases = ccl_qual_search_special(cclp->bibset, "or");
+ if (!aliases)
+ aliases = cclp->ccl_token_or;
+ if (token_cmp (cclp, aliases, last))
+ last->kind = CCL_TOK_OR;
- aliases = ccl_qual_search_special(cclp->bibset, "not");
- if (!aliases)
- aliases = cclp->ccl_token_not;
+ aliases = ccl_qual_search_special(cclp->bibset, "not");
+ if (!aliases)
+ aliases = cclp->ccl_token_not;
if (token_cmp (cclp, aliases, last))
- last->kind = CCL_TOK_NOT;
+ last->kind = CCL_TOK_NOT;
- aliases = ccl_qual_search_special(cclp->bibset, "set");
- if (!aliases)
- aliases = cclp->ccl_token_set;
+ aliases = ccl_qual_search_special(cclp->bibset, "set");
+ if (!aliases)
+ aliases = cclp->ccl_token_set;
- if (token_cmp (cclp, aliases, last))
- last->kind = CCL_TOK_SET;
- }
+ if (token_cmp (cclp, aliases, last))
+ last->kind = CCL_TOK_SET;
+ }
}
return first;
}
+struct ccl_token *ccl_token_add (struct ccl_token *at)
+{
+ struct ccl_token *n = (struct ccl_token *)xmalloc (sizeof(*n));
+ ccl_assert(n);
+ n->next = at->next;
+ n->prev = at;
+ at->next = n;
+ if (n->next)
+ n->next->prev = n;
+
+ n->kind = CCL_TOK_TERM;
+ n->name = 0;
+ n->len = 0;
+ n->ws_prefix_buf = 0;
+ n->ws_prefix_len = 0;
+ return n;
+}
+
struct ccl_token *ccl_tokenize (const char *command)
{
CCL_parser cclp = ccl_parser_create ();
{
CCL_parser p = (CCL_parser)xmalloc (sizeof(*p));
if (!p)
- return p;
+ return p;
p->look_token = NULL;
p->error_code = 0;
p->error_pos = NULL;
void ccl_parser_destroy (CCL_parser p)
{
if (!p)
- return;
+ return;
xfree (p->ccl_token_and);
xfree (p->ccl_token_or);
xfree (p->ccl_token_not);
{
if (p && op)
{
- if (p->ccl_token_and)
- xfree (p->ccl_token_and);
- p->ccl_token_and = ccl_strdup (op);
+ if (p->ccl_token_and)
+ xfree (p->ccl_token_and);
+ p->ccl_token_and = ccl_strdup (op);
}
}
{
if (p && op)
{
- if (p->ccl_token_or)
- xfree (p->ccl_token_or);
- p->ccl_token_or = ccl_strdup (op);
+ if (p->ccl_token_or)
+ xfree (p->ccl_token_or);
+ p->ccl_token_or = ccl_strdup (op);
}
}
void ccl_parser_set_op_not (CCL_parser p, const char *op)
{
if (p && op)
{
- if (p->ccl_token_not)
- xfree (p->ccl_token_not);
- p->ccl_token_not = ccl_strdup (op);
+ if (p->ccl_token_not)
+ xfree (p->ccl_token_not);
+ p->ccl_token_not = ccl_strdup (op);
}
}
void ccl_parser_set_op_set (CCL_parser p, const char *op)
{
if (p && op)
{
- if (p->ccl_token_set)
- xfree (p->ccl_token_set);
- p->ccl_token_set = ccl_strdup (op);
+ if (p->ccl_token_set)
+ xfree (p->ccl_token_set);
+ p->ccl_token_set = ccl_strdup (op);
}
}
void ccl_parser_set_case (CCL_parser p, int case_sensitivity_flag)
{
if (p)
- p->ccl_case_sensitive = case_sensitivity_flag;
+ p->ccl_case_sensitive = case_sensitivity_flag;
}
+/*
+ * Local variables:
+ * c-basic-offset: 4
+ * indent-tabs-mode: nil
+ * End:
+ * vim: shiftwidth=4 tabstop=8 expandtab
+ */
+
projects / yaz-moved-to-github.git / blobdiff