-/* $Id: apropos_db.c,v 1.6 2011/11/20 12:39:08 kristaps Exp $ */
+/* $Id: apropos_db.c,v 1.21 2011/12/03 18:47:09 kristaps Exp $ */
/*
* Copyright (c) 2011 Kristaps Dzonsons <kristaps@bsd.lv>
* Copyright (c) 2011 Ingo Schwarze <schwarze@openbsd.org>
* ACTION OF CONTRACT, NEGLIGENCE OR OTHER TORTIOUS ACTION, ARISING OUT OF
* OR IN CONNECTION WITH THE USE OR PERFORMANCE OF THIS SOFTWARE.
*/
+#ifdef HAVE_CONFIG_H
+#include "config.h"
+#endif
+
#include <assert.h>
#include <fcntl.h>
#include <regex.h>
#include <stdint.h>
#include <stdlib.h>
#include <string.h>
+#include <unistd.h>
-#ifdef __linux__
+#if defined(__linux__)
+# include <endian.h>
# include <db_185.h>
+#elif defined(__APPLE__)
+# include <libkern/OSByteOrder.h>
+# include <db.h>
#else
# include <db.h>
#endif
int regex; /* is regex? */
int index; /* index in match array */
uint64_t mask; /* type-mask */
- int cs; /* is case-sensitive? */
int and; /* is rhs of logical AND? */
char *v; /* search value */
regex_t re; /* compiled re, if regex */
const char *name;
};
+struct rectree {
+ struct rec *node; /* record array for dir tree */
+ int len; /* length of record array */
+};
+
static const struct type types[] = {
- { 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" },
+ { 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 }
};
static DB *btree_open(void);
-static int btree_read(const DBT *,
- const struct mchars *, char **);
+static int btree_read(const DBT *, const DBT *,
+ const struct mchars *,
+ struct db_val *, char **);
static int expreval(const struct expr *, int *);
-static void exprexec(const struct expr *,
+static void exprexec(const struct expr *,
const char *, uint64_t, struct rec *);
-static int exprmark(const struct expr *,
+static int exprmark(const struct expr *,
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);
-static int index_read(const DBT *, const DBT *,
+static int index_read(const DBT *, const DBT *, int,
const struct mchars *, struct rec *);
static void norm_string(const char *,
const struct mchars *, char **);
static size_t norm_utf8(unsigned int, char[7]);
static void recfree(struct rec *);
+static int single_search(struct rectree *, const struct opts *,
+ const struct expr *, size_t terms,
+ struct mchars *, int);
/*
* Open the keyword mandoc-db database.
info.flags = R_DUP;
db = dbopen(MANDOC_DB, O_RDONLY, 0, DB_BTREE, &info);
- if (NULL != db)
+ if (NULL != db)
return(db);
return(NULL);
* Return 0 if the database is insane, else 1.
*/
static int
-btree_read(const DBT *v, const struct mchars *mc, char **buf)
+btree_read(const DBT *k, const DBT *v,
+ const struct mchars *mc,
+ struct db_val *dbv, char **buf)
{
+ const struct db_val *vp;
- /* Sanity: are we nil-terminated? */
-
- assert(v->size > 0);
+ /* Are our sizes sane? */
+ if (k->size < 2 || sizeof(struct db_val) != v->size)
+ return(0);
- if ('\0' != ((char *)v->data)[(int)v->size - 1])
+ /* Is our string nil-terminated? */
+ if ('\0' != ((const char *)k->data)[(int)k->size - 1])
return(0);
- norm_string((char *)v->data, mc, buf);
+ vp = v->data;
+ norm_string((const char *)k->data, mc, buf);
+ dbv->rec = betoh32(vp->rec);
+ dbv->mask = betoh64(vp->mask);
return(1);
}
/*
* Take a Unicode codepoint and produce its UTF-8 encoding.
* This isn't the best way to do this, but it works.
- * The magic numbers are from the UTF-8 packaging.
+ * The magic numbers are from the UTF-8 packaging.
* They're not as scary as they seem: read the UTF-8 spec for details.
*/
static size_t
const char *seq, *cpp;
int len, u, pos;
enum mandoc_esc esc;
- static const char res[] = { '\\', '\t',
+ static const char res[] = { '\\', '\t',
ASCII_NBRSP, ASCII_HYPH, '\0' };
/* Pre-allocate by the length of the input */
if (ESCAPE_ERROR == esc)
break;
- /*
+ /*
* XXX - this just does UTF-8, but we need to know
* beforehand whether we should do text substitution.
*/
* Returns 1 if an entry was unpacked, 0 if the database is insane.
*/
static int
-index_read(const DBT *key, const DBT *val,
+index_read(const DBT *key, const DBT *val, int index,
const struct mchars *mc, struct rec *rec)
{
size_t left;
cp = (char *)val->data;
rec->res.rec = *(recno_t *)key->data;
+ rec->res.volume = index;
+ INDEX_BREAD(rec->res.type);
INDEX_BREAD(rec->res.file);
INDEX_BREAD(rec->res.cat);
INDEX_BREAD(rec->res.title);
}
/*
- * Search the mandocdb database for the expression "expr".
+ * Search mandocdb databases in paths for expression "expr".
* Filter out by "opts".
* Call "res" with the results, which may be zero.
* Return 0 if there was a database error, else return 1.
*/
int
-apropos_search(const struct opts *opts, const struct expr *expr,
- size_t terms, void *arg,
+apropos_search(int pathsz, char **paths, 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, mlen, rc, ch;
- uint64_t mask;
+ struct rectree tree;
+ struct mchars *mc;
+ struct res *ress;
+ int i, mlen, rc;
+
+ memset(&tree, 0, sizeof(struct rectree));
+
+ rc = 0;
+ mc = mchars_alloc();
+
+ /*
+ * Main loop. Change into the directory containing manpage
+ * databases. Run our expession over each database in the set.
+ */
+
+ for (i = 0; i < pathsz; i++) {
+ if (chdir(paths[i]))
+ continue;
+ if ( ! single_search(&tree, opts, expr, terms, mc, i))
+ goto out;
+ }
+
+ /*
+ * Count matching files, transfer to a "clean" array, then feed
+ * them to the output handler.
+ */
+
+ for (mlen = i = 0; i < tree.len; i++)
+ if (tree.node[i].matched)
+ mlen++;
+
+ ress = mandoc_malloc(mlen * sizeof(struct res));
+
+ for (mlen = i = 0; i < tree.len; i++)
+ if (tree.node[i].matched)
+ memcpy(&ress[mlen++], &tree.node[i].res,
+ sizeof(struct res));
+
+ (*res)(ress, mlen, arg);
+ free(ress);
+
+ rc = 1;
+out:
+ for (i = 0; i < tree.len; i++)
+ recfree(&tree.node[i]);
+
+ free(tree.node);
+ mchars_free(mc);
+ return(rc);
+}
+
+static int
+single_search(struct rectree *tree, const struct opts *opts,
+ const struct expr *expr, size_t terms,
+ struct mchars *mc, int vol)
+{
+ int root, leaf, ch;
DBT key, val;
DB *btree, *idx;
- struct mchars *mc;
char *buf;
- recno_t rec;
struct rec *rs;
- struct res *ress;
struct rec r;
- struct db_val *vbuf;
+ struct db_val vb;
- rc = 0;
root = -1;
leaf = -1;
btree = NULL;
idx = NULL;
- mc = NULL;
buf = NULL;
- rs = NULL;
- rsz = 0;
+ rs = tree->node;
memset(&r, 0, sizeof(struct rec));
- mc = mchars_alloc();
+ if (NULL == (btree = btree_open()))
+ return(1);
- if (NULL == (btree = btree_open()))
- goto out;
- if (NULL == (idx = index_open()))
- goto out;
+ if (NULL == (idx = index_open())) {
+ (*btree->close)(btree);
+ return(1);
+ }
while (0 == (ch = (*btree->seq)(btree, &key, &val, R_NEXT))) {
- if (key.size < 2 || sizeof(struct db_val) != val.size)
- break;
- if ( ! btree_read(&key, mc, &buf))
+ if ( ! btree_read(&key, &val, mc, &vb, &buf))
break;
- vbuf = val.data;
- rec = vbuf->rec;
- mask = vbuf->mask;
-
/*
* See if this keyword record matches any of the
* expressions we have stored.
*/
- if ( ! exprmark(expr, buf, mask, NULL))
+ if ( ! exprmark(expr, buf, vb.mask, NULL))
continue;
/*
*/
for (leaf = root; leaf >= 0; )
- if (rec > rs[leaf].res.rec &&
+ if (vb.rec > rs[leaf].res.rec &&
rs[leaf].rhs >= 0)
leaf = rs[leaf].rhs;
- else if (rec < rs[leaf].res.rec &&
+ else if (vb.rec < rs[leaf].res.rec &&
rs[leaf].lhs >= 0)
leaf = rs[leaf].lhs;
- else
+ else
break;
/*
* try to evaluate it now and continue anyway.
*/
- if (leaf >= 0 && rs[leaf].res.rec == rec) {
+ if (leaf >= 0 && rs[leaf].res.rec == vb.rec) {
if (0 == rs[leaf].matched)
- exprexec(expr, buf, mask, &rs[leaf]);
+ exprexec(expr, buf, vb.mask, &rs[leaf]);
continue;
}
* database, then begin partial evaluation.
*/
- key.data = &rec;
+ key.data = &vb.rec;
key.size = sizeof(recno_t);
if (0 != (*idx->get)(idx, &key, &val, 0))
break;
r.lhs = r.rhs = -1;
- if ( ! index_read(&key, &val, mc, &r))
+ if ( ! index_read(&key, &val, vol, mc, &r))
break;
/* XXX: this should be elsewhere, I guess? */
if (opts->arch && strcasecmp(opts->arch, r.res.arch))
continue;
- rs = mandoc_realloc
- (rs, (rsz + 1) * sizeof(struct rec));
+ tree->node = rs = mandoc_realloc
+ (rs, (tree->len + 1) * sizeof(struct rec));
+
+ memcpy(&rs[tree->len], &r, sizeof(struct rec));
+ rs[tree->len].matches =
+ mandoc_calloc(terms, sizeof(int));
- memcpy(&rs[rsz], &r, sizeof(struct rec));
- rs[rsz].matches = mandoc_calloc(terms, sizeof(int));
+ exprexec(expr, buf, vb.mask, &rs[tree->len]);
- exprexec(expr, buf, mask, &rs[rsz]);
/* Append to our tree. */
if (leaf >= 0) {
- if (rec > rs[leaf].res.rec)
- rs[leaf].rhs = rsz;
+ if (vb.rec > rs[leaf].res.rec)
+ rs[leaf].rhs = tree->len;
else
- rs[leaf].lhs = rsz;
+ rs[leaf].lhs = tree->len;
} else
- root = rsz;
-
+ root = tree->len;
+
memset(&r, 0, sizeof(struct rec));
- rsz++;
+ tree->len++;
}
-
- /*
- * If we haven't encountered any database errors, then construct
- * an array of results and push them to the caller.
- */
- if (1 == ch) {
- for (mlen = i = 0; i < rsz; i++)
- if (rs[i].matched)
- mlen++;
- ress = mandoc_malloc(mlen * sizeof(struct res));
- for (mlen = i = 0; i < rsz; i++)
- if (rs[i].matched)
- memcpy(&ress[mlen++], &rs[i].res,
- sizeof(struct res));
- (*res)(ress, mlen, arg);
- free(ress);
- rc = 1;
- }
-
-out:
- for (i = 0; i < rsz; i++)
- recfree(&rs[i]);
-
- recfree(&r);
-
- if (mc)
- mchars_free(mc);
- if (btree)
- (*btree->close)(btree);
- if (idx)
- (*idx->close)(idx);
+ (*btree->close)(btree);
+ (*idx->close)(idx);
free(buf);
- free(rs);
- return(rc);
+ return(1 == ch);
}
static void
recfree(struct rec *rec)
{
+ free(rec->res.type);
free(rec->res.file);
free(rec->res.cat);
free(rec->res.title);
free(rec->matches);
}
+/*
+ * Compile a list of straight-up terms.
+ * The arguments are re-written into ~[[:<:]]term[[:>:]], or "term"
+ * surrounded by word boundaries, then pumped through exprterm().
+ * Terms are case-insensitive.
+ * This emulates whatis(1) behaviour.
+ */
+struct expr *
+termcomp(int argc, char *argv[], size_t *tt)
+{
+ char *buf;
+ int pos;
+ struct expr *e, *next;
+ size_t sz;
+
+ buf = NULL;
+ e = NULL;
+ *tt = 0;
+
+ for (pos = argc - 1; pos >= 0; pos--) {
+ sz = strlen(argv[pos]) + 18;
+ buf = mandoc_realloc(buf, sz);
+ strlcpy(buf, "Nm~[[:<:]]", sz);
+ strlcat(buf, argv[pos], sz);
+ strlcat(buf, "[[:>:]]", sz);
+ if (NULL == (next = exprterm(buf, 0))) {
+ free(buf);
+ exprfree(e);
+ return(NULL);
+ }
+ next->next = e;
+ e = next;
+ (*tt)++;
+ }
+
+ free(buf);
+ return(e);
+}
+
+/*
+ * Compile a sequence of logical expressions.
+ * See apropos.1 for a grammar of this sequence.
+ */
struct expr *
exprcomp(int argc, char *argv[], size_t *tt)
{
log = 0;
if (NULL != e && 0 == strcmp("-a", argv[*pos]))
- log = 1;
+ log = 1;
else if (NULL != e && 0 == strcmp("-o", argv[*pos]))
log = 2;
++(*pos);
++(*lvl);
next = mandoc_calloc(1, sizeof(struct expr));
- next->cs = 1;
next->subexpr = exprexpr(argc, argv, pos, lvl, tt);
if (NULL == next->subexpr) {
free(next);
memset(&e, 0, sizeof(struct expr));
- e.cs = cs;
-
/* Choose regex or substring match. */
if (NULL == (e.v = strpbrk(buf, "=~"))) {
e.mask = TYPE_Nm | TYPE_Nd;
if (e.regex) {
- i = REG_EXTENDED | REG_NOSUB | cs ? 0 : REG_ICASE;
+ i = REG_EXTENDED | REG_NOSUB | (cs ? 0 : REG_ICASE);
if (regcomp(&e.re, e.v, i))
return(NULL);
}
exprfree(struct expr *p)
{
struct expr *pp;
-
+
while (NULL != p) {
if (p->subexpr)
exprfree(p->subexpr);
}
static int
-exprmark(const struct expr *p, const char *cp,
+exprmark(const struct expr *p, const char *cp,
uint64_t mask, int *ms)
{
if (p->regex) {
if (regexec(&p->re, cp, 0, NULL, 0))
continue;
- } else if (p->cs) {
- if (NULL == strstr(cp, p->v))
- continue;
- } else {
- if (NULL == strcasestr(cp, p->v))
- continue;
- }
+ } else if (NULL == strcasestr(cp, p->v))
+ continue;
if (NULL == ms)
return(1);
for ( ; p->next && p->next->and; p = p->next) {
/* Evaluate a subexpression, if applicable. */
if (p->next->subexpr && ! ms[p->next->index])
- ms[p->next->index] =
+ ms[p->next->index] =
expreval(p->next->subexpr, ms);
match = match && ms[p->next->index];
}
* If this evaluates to true, mark the expression as satisfied.
*/
static void
-exprexec(const struct expr *p, const char *cp,
+exprexec(const struct expr *e, const char *cp,
uint64_t mask, struct rec *r)
{
assert(0 == r->matched);
- exprmark(p, cp, mask, r->matches);
- r->matched = expreval(p, r->matches);
+ exprmark(e, cp, mask, r->matches);
+ r->matched = expreval(e, r->matches);
}
git.ckatri.com / mandoc.git / blobdiff