=================================================================== RCS file: /cvs/mandoc/Attic/apropos_db.c,v retrieving revision 1.5 retrieving revision 1.9 diff -u -p -r1.5 -r1.9 --- mandoc/Attic/apropos_db.c 2011/11/18 07:02:19 1.5 +++ mandoc/Attic/apropos_db.c 2011/11/20 15:45:37 1.9 @@ -1,4 +1,4 @@ -/* $Id: apropos_db.c,v 1.5 2011/11/18 07:02:19 kristaps Exp $ */ +/* $Id: apropos_db.c,v 1.9 2011/11/20 15:45:37 kristaps Exp $ */ /* * Copyright (c) 2011 Kristaps Dzonsons * Copyright (c) 2011 Ingo Schwarze @@ -19,8 +19,10 @@ #include #include #include +#include #include #include +#include #ifdef __linux__ # include @@ -49,7 +51,7 @@ 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 */ @@ -59,22 +61,52 @@ struct expr { }; struct type { - int mask; + uint64_t mask; 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" }, @@ -87,9 +119,9 @@ 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); @@ -99,6 +131,9 @@ 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 *); /* * Open the keyword mandoc-db database. @@ -130,6 +165,7 @@ btree_read(const DBT *v, const struct mchars *mc, char /* Sanity: are we nil-terminated? */ assert(v->size > 0); + if ('\0' != ((char *)v->data)[(int)v->size - 1]) return(0); @@ -338,57 +374,102 @@ index_read(const DBT *key, const DBT *val, } /* - * Search the mandocdb database for the expression "expr". + * Search mandocdb databases in argv (size argc) for the 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 argc, char *argv[], 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; + struct rectree tree; + struct mchars *mc; + struct res *ress; + int i, mlen, rc; + + memset(&tree, 0, sizeof(struct rectree)); + + mc = mchars_alloc(); + + for (rc = 1, i = 0; rc && i < argc; i++) { + /* FIXME: ugly warning: we shouldn't get here! */ + if (chdir(argv[i])) + continue; + rc = single_search(&tree, opts, expr, terms, mc); + /* FIXME: warn and continue... ? */ + } + + /* + * Count the matching files + * and 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); + + 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 root, leaf, ch; + uint64_t mask; 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; - 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())) - goto out; - if (NULL == (idx = index_open())) - goto out; + return(0); + if (NULL == (idx = index_open())) { + (*btree->close)(btree); + return(0); + } + 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 +478,6 @@ apropos_search(const struct opts *opts, const struct e 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 @@ -450,62 +529,33 @@ apropos_search(const struct opts *opts, const struct e 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[rsz], &r, sizeof(struct rec)); - rs[rsz].matches = mandoc_calloc(terms, sizeof(int)); + memcpy(&rs[tree->len], &r, sizeof(struct rec)); + rs[tree->len].matches = + mandoc_calloc(terms, sizeof(int)); - exprexec(expr, buf, mask, &rs[rsz]); + exprexec(expr, buf, mask, &rs[tree->len]); /* Append to our tree. */ if (leaf >= 0) { if (rec > rs[leaf].res.rec) - rs[leaf].rhs = rsz; + 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. - */ + (*btree->close)(btree); + (*idx->close)(idx); - 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); - free(buf); - free(rs); - return(rc); + return(1 == ch); } static void @@ -701,7 +751,8 @@ 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 +823,8 @@ 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);