summaryrefslogtreecommitdiffstats
diff options
context:
space:
mode:
Diffstat
-rw-r--r--apropos_db.c88
-rw-r--r--cgi.c1
-rw-r--r--mandocdb.c26
-rw-r--r--mandocdb.h55
4 files changed, 114 insertions, 56 deletions
diff --git a/apropos_db.c b/apropos_db.c
index e0e48f33..6e611514 100644
--- a/apropos_db.c
+++ b/apropos_db.c
@@ -19,6 +19,7 @@
#include <fcntl.h>
#include <regex.h>
#include <stdarg.h>
+#include <stdint.h>
#include <stdlib.h>
#include <string.h>
@@ -49,7 +50,7 @@ struct rec {
struct expr {
int regex; /* is regex? */
int index; /* index in match array */
- int mask; /* type-mask */
+ uint64_t mask; /* type-mask */
int cs; /* is case-sensitive? */
int and; /* is rhs of logical AND? */
char *v; /* search value */
@@ -59,25 +60,50 @@ struct expr {
};
struct type {
- int mask;
+ uint64_t mask;
const char *name;
};
static const struct type types[] = {
- { TYPE_An, "An" },
- { TYPE_Cd, "Cd" },
- { TYPE_Er, "Er" },
- { TYPE_Ev, "Ev" },
- { TYPE_Fn, "Fn" },
- { TYPE_Fn, "Fo" },
- { TYPE_In, "In" },
- { TYPE_Nd, "Nd" },
- { TYPE_Nm, "Nm" },
- { TYPE_Pa, "Pa" },
- { TYPE_St, "St" },
- { TYPE_Va, "Va" },
- { TYPE_Va, "Vt" },
- { TYPE_Xr, "Xr" },
+ { TYPE_An, "An" },
+ { TYPE_Ar, "Ar" },
+ { TYPE_At, "At" },
+ { TYPE_Bsx, "Bsx" },
+ { TYPE_Bx, "Bx" },
+ { TYPE_Cd, "Cd" },
+ { TYPE_Cm, "Cm" },
+ { TYPE_Dv, "Dv" },
+ { TYPE_Dx, "Dx" },
+ { TYPE_Em, "Em" },
+ { TYPE_Er, "Er" },
+ { TYPE_Ev, "Ev" },
+ { TYPE_Fa, "Fa" },
+ { TYPE_Fl, "Fl" },
+ { TYPE_Fn, "Fn" },
+ { TYPE_Fn, "Fo" },
+ { TYPE_Ft, "Ft" },
+ { TYPE_Fx, "Fx" },
+ { TYPE_Ic, "Ic" },
+ { TYPE_In, "In" },
+ { TYPE_Lb, "Lb" },
+ { TYPE_Li, "Li" },
+ { TYPE_Lk, "Lk" },
+ { TYPE_Ms, "Ms" },
+ { TYPE_Mt, "Mt" },
+ { TYPE_Nd, "Nd" },
+ { TYPE_Nm, "Nm" },
+ { TYPE_Nx, "Nx" },
+ { TYPE_Ox, "Ox" },
+ { TYPE_Pa, "Pa" },
+ { TYPE_Rs, "Rs" },
+ { TYPE_Sh, "Sh" },
+ { TYPE_Ss, "Ss" },
+ { TYPE_St, "St" },
+ { TYPE_Sy, "Sy" },
+ { TYPE_Tn, "Tn" },
+ { TYPE_Va, "Va" },
+ { TYPE_Va, "Vt" },
+ { TYPE_Xr, "Xr" },
{ INT_MAX, "any" },
{ 0, NULL }
};
@@ -87,9 +113,9 @@ static int btree_read(const DBT *,
const struct mchars *, char **);
static int expreval(const struct expr *, int *);
static void exprexec(const struct expr *,
- const char *, int, struct rec *);
+ const char *, uint64_t, struct rec *);
static int exprmark(const struct expr *,
- const char *, int, int *);
+ const char *, uint64_t, int *);
static struct expr *exprexpr(int, char *[], int *, int *, size_t *);
static struct expr *exprterm(char *, int);
static DB *index_open(void);
@@ -130,6 +156,7 @@ btree_read(const DBT *v, const struct mchars *mc, char **buf)
/* Sanity: are we nil-terminated? */
assert(v->size > 0);
+
if ('\0' != ((char *)v->data)[(int)v->size - 1])
return(0);
@@ -348,7 +375,8 @@ apropos_search(const struct opts *opts, const struct expr *expr,
size_t terms, void *arg,
void (*res)(struct res *, size_t, void *))
{
- int i, rsz, root, leaf, mask, mlen, rc, ch;
+ int i, rsz, root, leaf, mlen, rc, ch;
+ uint64_t mask;
DBT key, val;
DB *btree, *idx;
struct mchars *mc;
@@ -357,6 +385,7 @@ apropos_search(const struct opts *opts, const struct expr *expr,
struct rec *rs;
struct res *ress;
struct rec r;
+ struct db_val *vbuf;
rc = 0;
root = -1;
@@ -378,17 +407,14 @@ apropos_search(const struct opts *opts, const struct expr *expr,
goto out;
while (0 == (ch = (*btree->seq)(btree, &key, &val, R_NEXT))) {
- /*
- * Low-water mark for key and value.
- * The key must have something in it, and the value must
- * have the correct tags/recno mix.
- */
- if (key.size < 2 || 8 != val.size)
- break;
+ if (key.size < 2 || sizeof(struct db_val) != val.size)
+ break;
if ( ! btree_read(&key, mc, &buf))
break;
- mask = *(int *)val.data;
+ vbuf = val.data;
+ rec = vbuf->rec;
+ mask = vbuf->mask;
/*
* See if this keyword record matches any of the
@@ -397,8 +423,6 @@ apropos_search(const struct opts *opts, const struct expr *expr,
if ( ! exprmark(expr, buf, mask, NULL))
continue;
- memcpy(&rec, val.data + 4, sizeof(recno_t));
-
/*
* O(log n) scan for prior records. Since a record
* number is unbounded, this has decent performance over
@@ -701,7 +725,8 @@ exprfree(struct expr *p)
}
static int
-exprmark(const struct expr *p, const char *cp, int mask, int *ms)
+exprmark(const struct expr *p, const char *cp,
+ uint64_t mask, int *ms)
{
for ( ; p; p = p->next) {
@@ -772,7 +797,8 @@ expreval(const struct expr *p, int *ms)
* If this evaluates to true, mark the expression as satisfied.
*/
static void
-exprexec(const struct expr *p, const char *cp, int mask, struct rec *r)
+exprexec(const struct expr *p, const char *cp,
+ uint64_t mask, struct rec *r)
{
assert(0 == r->matched);
diff --git a/cgi.c b/cgi.c
index be2eed1f..12c008cc 100644
--- a/cgi.c
+++ b/cgi.c
@@ -4,6 +4,7 @@
#include <regex.h>
#include <stdio.h>
#include <stdarg.h>
+#include <stdint.h>
#include <stdlib.h>
#include <string.h>
diff --git a/mandocdb.c b/mandocdb.c
index d1eb31c9..883bffbf 100644
--- a/mandocdb.c
+++ b/mandocdb.c
@@ -83,7 +83,7 @@ static void buf_append(struct buf *, const char *);
static void buf_appendb(struct buf *,
const void *, size_t);
static void dbt_put(DB *, const char *, DBT *, DBT *);
-static void hash_put(DB *, const struct buf *, int);
+static void hash_put(DB *, const struct buf *, uint64_t);
static void hash_reset(DB **);
static void index_merge(const struct of *, struct mparse *,
struct buf *, struct buf *,
@@ -450,7 +450,7 @@ index_merge(const struct of *of, struct mparse *mp,
const char *fn, *msec, *mtitle, *arch;
size_t sv;
unsigned seq;
- char vbuf[8];
+ struct db_val vbuf;
for (rec = 0; of; of = of->next) {
fn = of->fname;
@@ -513,17 +513,15 @@ index_merge(const struct of *of, struct mparse *mp,
* Copy from the in-memory hashtable of pending keywords
* into the database.
*/
-
- memset(vbuf, 0, sizeof(uint32_t));
- memcpy(vbuf + 4, &rec, sizeof(uint32_t));
+ vbuf.rec = rec;
seq = R_FIRST;
while (0 == (ch = (*hash->seq)(hash, &key, &val, seq))) {
seq = R_NEXT;
- memcpy(vbuf, val.data, sizeof(uint32_t));
- val.size = sizeof(vbuf);
- val.data = vbuf;
+ vbuf.mask = *(uint64_t *)val.data;
+ val.size = sizeof(struct db_val);
+ val.data = &vbuf;
if (verb > 1)
printf("%s: Added keyword: %s\n",
@@ -568,6 +566,7 @@ index_prune(const struct of *ofile, DB *db, const char *dbf,
{
const struct of *of;
const char *fn;
+ struct db_val *vbuf;
unsigned seq, sseq;
DBT key, val;
size_t reccur;
@@ -600,8 +599,9 @@ index_prune(const struct of *ofile, DB *db, const char *dbf,
sseq = R_FIRST;
while (0 == (ch = (*db->seq)(db, &key, &val, sseq))) {
sseq = R_NEXT;
- assert(8 == val.size);
- if (*maxrec != *(recno_t *)(val.data + 4))
+ assert(sizeof(struct db_val) == val.size);
+ vbuf = val.data;
+ if (*maxrec != vbuf->rec)
continue;
if (verb)
printf("%s: Deleted keyword: %s\n",
@@ -982,7 +982,7 @@ pmdoc_Nm(MDOC_ARGS)
}
static void
-hash_put(DB *db, const struct buf *buf, int mask)
+hash_put(DB *db, const struct buf *buf, uint64_t mask)
{
DBT key, val;
int rc;
@@ -997,10 +997,10 @@ hash_put(DB *db, const struct buf *buf, int mask)
perror("hash");
exit((int)MANDOCLEVEL_SYSERR);
} else if (0 == rc)
- mask |= *(int *)val.data;
+ mask |= *(uint64_t *)val.data;
val.data = &mask;
- val.size = sizeof(int);
+ val.size = sizeof(uint64_t);
if ((rc = (*db->put)(db, &key, &val, 0)) < 0) {
perror("hash");
diff --git a/mandocdb.h b/mandocdb.h
index 240f53ba..8f8791d3 100644
--- a/mandocdb.h
+++ b/mandocdb.h
@@ -17,20 +17,51 @@
#ifndef MANDOCDB_H
#define MANDOCDB_H
+struct db_val {
+ uint64_t mask;
+ uint32_t rec;
+};
+
#define MANDOC_DB "mandoc.db"
#define MANDOC_IDX "mandoc.index"
-#define TYPE_An 0x01
-#define TYPE_Cd 0x02
-#define TYPE_Er 0x04
-#define TYPE_Ev 0x08
-#define TYPE_Fn 0x10
-#define TYPE_In 0x20
-#define TYPE_Nd 0x40
-#define TYPE_Nm 0x100
-#define TYPE_Pa 0x200
-#define TYPE_St 0x400
-#define TYPE_Va 0x1000
-#define TYPE_Xr 0x2000
+#define TYPE_An 0x0000000000000001ULL
+#define TYPE_Ar 0x0000000000000002ULL
+#define TYPE_At 0x0000000000000004ULL
+#define TYPE_Bsx 0x0000000000000008ULL
+#define TYPE_Bx 0x0000000000000010ULL
+#define TYPE_Cd 0x0000000000000020ULL
+#define TYPE_Cm 0x0000000000000040ULL
+#define TYPE_Dv 0x0000000000000080ULL
+#define TYPE_Dx 0x0000000000000100ULL
+#define TYPE_Em 0x0000000000000200ULL
+#define TYPE_Er 0x0000000000000400ULL
+#define TYPE_Ev 0x0000000000000800ULL
+#define TYPE_Fa 0x0000000000001000ULL
+#define TYPE_Fl 0x0000000000002000ULL
+#define TYPE_Fn 0x0000000000004000ULL
+#define TYPE_Ft 0x0000000000008000ULL
+#define TYPE_Fx 0x0000000000010000ULL
+#define TYPE_Ic 0x0000000000020000ULL
+#define TYPE_In 0x0000000000040000ULL
+#define TYPE_Lb 0x0000000000080000ULL
+#define TYPE_Li 0x0000000000100000ULL
+#define TYPE_Lk 0x0000000000200000ULL
+#define TYPE_Ms 0x0000000000400000ULL
+#define TYPE_Mt 0x0000000000800000ULL
+#define TYPE_Nd 0x0000000001000000ULL
+#define TYPE_Nm 0x0000000002000000ULL
+#define TYPE_Nx 0x0000000004000000ULL
+#define TYPE_Ox 0x0000000008000000ULL
+#define TYPE_Pa 0x0000000010000000ULL
+#define TYPE_Rs 0x0000000020000000ULL
+#define TYPE_Sh 0x0000000040000000ULL
+#define TYPE_Ss 0x0000000080000000ULL
+#define TYPE_St 0x0000000100000000ULL
+#define TYPE_Sy 0x0000000200000000ULL
+#define TYPE_Tn 0x0000000400000000ULL
+#define TYPE_Va 0x0000000800000000ULL
+#define TYPE_Vt 0x0000001000000000ULL
+#define TYPE_Xr 0x0000002000000000ULL
#endif /*!MANDOCDB_H */
generated by cgit (git 2.34.1) at 2024-11-10 15:57:56 +0000