=================================================================== RCS file: /cvs/mandoc/mandocdb.c,v retrieving revision 1.4 retrieving revision 1.9 diff -u -p -r1.4 -r1.9 --- mandoc/mandocdb.c 2011/07/15 10:15:24 1.4 +++ mandoc/mandocdb.c 2011/11/20 12:39:08 1.9 @@ -1,4 +1,4 @@ -/* $Id: mandocdb.c,v 1.4 2011/07/15 10:15:24 kristaps Exp $ */ +/* $Id: mandocdb.c,v 1.9 2011/11/20 12:39:08 kristaps Exp $ */ /* * Copyright (c) 2011 Kristaps Dzonsons * @@ -38,48 +38,32 @@ #include "man.h" #include "mdoc.h" #include "mandoc.h" +#include "mandocdb.h" -#define MANDOC_DB "mandoc.db" -#define MANDOC_IDX "mandoc.index" #define MANDOC_BUFSZ BUFSIZ -#define MANDOC_FLAGS O_CREAT|O_TRUNC|O_RDWR #define MANDOC_SLOP 1024 -/* Bit-fields. See mandocdb.8. */ +/* Tiny list for files. No need to bring in QUEUE. */ -#define TYPE_NAME 0x01 -#define TYPE_FUNCTION 0x02 -#define TYPE_UTILITY 0x04 -#define TYPE_INCLUDES 0x08 -#define TYPE_VARIABLE 0x10 -#define TYPE_STANDARD 0x20 -#define TYPE_AUTHOR 0x40 -#define TYPE_CONFIG 0x80 -#define TYPE_DESC 0x100 -#define TYPE_XREF 0x200 -#define TYPE_PATH 0x400 -#define TYPE_ENV 0x800 -#define TYPE_ERR 0x1000 - struct of { - char *fname; - struct of *next; - struct of *first; + char *fname; /* heap-allocated */ + struct of *next; /* NULL for last one */ + struct of *first; /* first in list */ }; /* Buffer for storing growable data. */ struct buf { char *cp; - size_t len; - size_t size; + size_t len; /* current length */ + size_t size; /* total buffer size */ }; /* Operation we're going to perform. */ enum op { OP_NEW = 0, /* new database */ - OP_UPDATE, /* update entries in existing database */ + OP_UPDATE, /* delete/add entries in existing database */ OP_DELETE /* delete entries from existing database */ }; @@ -99,17 +83,18 @@ 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 *, DB *, DB *, const char *, - DB *, const char *, + DB *, const char *, int, recno_t, const recno_t *, size_t); static void index_prune(const struct of *, DB *, const char *, DB *, const char *, - recno_t *, recno_t **, size_t *); -static int ofile_build(const char *, struct of **); + int, recno_t *, recno_t **, size_t *); +static void ofile_argbuild(char *[], int, int, struct of **); +static int ofile_dirbuild(const char *, int, struct of **); static void ofile_free(struct of *); static int pman_node(MAN_ARGS); static void pmdoc_node(MDOC_ARGS); @@ -263,20 +248,23 @@ main(int argc, char *argv[]) { struct mparse *mp; /* parse sequence */ enum op op; /* current operation */ + const char *dir; char ibuf[MAXPATHLEN], /* index fname */ fbuf[MAXPATHLEN]; /* btree fname */ - int ch, i, flags; + int verb, /* output verbosity */ + ch, i, flags; DB *idx, /* index database */ *db, /* keyword database */ *hash; /* temporary keyword hashtable */ BTREEINFO info; /* btree configuration */ recno_t maxrec; /* supremum of all records */ recno_t *recs; /* buffer of empty records */ - size_t recsz, /* buffer size of recs */ + size_t sz1, sz2, + recsz, /* buffer size of recs */ reccur; /* valid number of recs */ struct buf buf, /* keyword buffer */ dbuf; /* description buffer */ - struct of *of; + struct of *of; /* list of files for processing */ extern int optind; extern char *optarg; @@ -286,6 +274,7 @@ main(int argc, char *argv[]) else ++progname; + verb = 0; of = NULL; db = idx = NULL; mp = NULL; @@ -294,12 +283,21 @@ main(int argc, char *argv[]) recsz = reccur = 0; maxrec = 0; op = OP_NEW; + dir = NULL; - memset(&buf, 0, sizeof(struct buf)); - memset(&dbuf, 0, sizeof(struct buf)); - - while (-1 != (ch = getopt(argc, argv, ""))) + while (-1 != (ch = getopt(argc, argv, "d:u:v"))) switch (ch) { + case ('d'): + dir = optarg; + op = OP_UPDATE; + break; + case ('u'): + dir = optarg; + op = OP_DELETE; + break; + case ('v'): + verb++; + break; default: usage(); return((int)MANDOCLEVEL_BADARG); @@ -313,27 +311,79 @@ main(int argc, char *argv[]) mp = mparse_alloc(MPARSE_AUTO, MANDOCLEVEL_FATAL, NULL, NULL); - flags = OP_NEW == op ? O_CREAT|O_TRUNC|O_RDWR : O_CREAT|O_RDWR; + memset(&buf, 0, sizeof(struct buf)); + memset(&dbuf, 0, sizeof(struct buf)); buf.size = dbuf.size = MANDOC_BUFSZ; buf.cp = mandoc_malloc(buf.size); dbuf.cp = mandoc_malloc(dbuf.size); + flags = OP_NEW == op ? O_CREAT|O_TRUNC|O_RDWR : O_CREAT|O_RDWR; + + if (OP_UPDATE == op || OP_DELETE == op) { + ibuf[0] = fbuf[0] = '\0'; + + strlcat(fbuf, dir, MAXPATHLEN); + strlcat(fbuf, "/", MAXPATHLEN); + sz1 = strlcat(fbuf, MANDOC_DB, MAXPATHLEN); + + strlcat(ibuf, dir, MAXPATHLEN); + strlcat(ibuf, "/", MAXPATHLEN); + sz2 = strlcat(ibuf, MANDOC_IDX, MAXPATHLEN); + + if (sz1 >= MAXPATHLEN || sz2 >= MAXPATHLEN) { + fprintf(stderr, "%s: Path too long\n", dir); + exit((int)MANDOCLEVEL_BADARG); + } + + db = dbopen(fbuf, flags, 0644, DB_BTREE, &info); + idx = dbopen(ibuf, flags, 0644, DB_RECNO, NULL); + + if (NULL == db) { + perror(fbuf); + exit((int)MANDOCLEVEL_SYSERR); + } else if (NULL == db) { + perror(ibuf); + exit((int)MANDOCLEVEL_SYSERR); + } + + if (verb > 2) { + printf("%s: Opened\n", fbuf); + printf("%s: Opened\n", ibuf); + } + + ofile_argbuild(argv, argc, verb, &of); + if (NULL == of) + goto out; + + of = of->first; + + index_prune(of, db, fbuf, idx, ibuf, verb, + &maxrec, &recs, &recsz); + + if (OP_UPDATE == op) + index_merge(of, mp, &dbuf, &buf, hash, + db, fbuf, idx, ibuf, verb, + maxrec, recs, reccur); + + goto out; + } + for (i = 0; i < argc; i++) { - ibuf[0] = ibuf[MAXPATHLEN - 2] = - fbuf[0] = fbuf[MAXPATHLEN - 2] = '\0'; + ibuf[0] = fbuf[0] = '\0'; strlcat(fbuf, argv[i], MAXPATHLEN); - strlcat(fbuf, MANDOC_DB, MAXPATHLEN); + strlcat(fbuf, "/", MAXPATHLEN); + sz1 = strlcat(fbuf, MANDOC_DB, MAXPATHLEN); strlcat(ibuf, argv[i], MAXPATHLEN); - strlcat(ibuf, MANDOC_IDX, MAXPATHLEN); + strlcat(ibuf, "/", MAXPATHLEN); + sz2 = strlcat(ibuf, MANDOC_IDX, MAXPATHLEN); - if ('\0' != fbuf[MAXPATHLEN - 2] || - '\0' != ibuf[MAXPATHLEN - 2]) { + if (sz1 >= MAXPATHLEN || sz2 >= MAXPATHLEN) { fprintf(stderr, "%s: Path too long\n", argv[i]); - break; + exit((int)MANDOCLEVEL_BADARG); } db = dbopen(fbuf, flags, 0644, DB_BTREE, &info); @@ -341,30 +391,33 @@ main(int argc, char *argv[]) if (NULL == db) { perror(fbuf); - break; + exit((int)MANDOCLEVEL_SYSERR); } else if (NULL == db) { perror(ibuf); - break; + exit((int)MANDOCLEVEL_SYSERR); } + if (verb > 2) { + printf("%s: Truncated\n", fbuf); + printf("%s: Truncated\n", ibuf); + } + ofile_free(of); of = NULL; - if ( ! ofile_build(argv[i], &of)) - break; - of = of->first; + if ( ! ofile_dirbuild(argv[i], verb, &of)) + exit((int)MANDOCLEVEL_SYSERR); - if (OP_DELETE == op || OP_UPDATE == op) - index_prune(of, db, fbuf, idx, ibuf, - &maxrec, &recs, &recsz); - - if (OP_DELETE == op) + if (NULL == of) continue; - index_merge(of, mp, &dbuf, &buf, hash, db, - fbuf, idx, ibuf, maxrec, recs, reccur); + of = of->first; + + index_merge(of, mp, &dbuf, &buf, hash, db, fbuf, + idx, ibuf, verb, maxrec, recs, reccur); } +out: if (db) (*db->close)(db); if (idx) @@ -379,14 +432,14 @@ main(int argc, char *argv[]) free(dbuf.cp); free(recs); - return(i < argc ? MANDOCLEVEL_SYSERR : MANDOCLEVEL_OK); + return(MANDOCLEVEL_OK); } void index_merge(const struct of *of, struct mparse *mp, struct buf *dbuf, struct buf *buf, DB *hash, DB *db, const char *dbf, - DB *idx, const char *idxf, + DB *idx, const char *idxf, int verb, recno_t maxrec, const recno_t *recs, size_t reccur) { recno_t rec; @@ -397,7 +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; @@ -460,20 +513,19 @@ 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; - printf("%s: Added keyword: %s\n", - fn, (char *)key.data); + if (verb > 1) + printf("%s: Added keyword: %s\n", + fn, (char *)key.data); dbt_put(db, dbf, &key, &val); } if (ch < 0) { @@ -495,7 +547,8 @@ index_merge(const struct of *of, struct mparse *mp, val.data = dbuf->cp; val.size = dbuf->len; - printf("%s: Added index\n", fn); + if (verb) + printf("%s: Added index\n", fn); dbt_put(idx, idxf, &key, &val); } } @@ -508,11 +561,12 @@ index_merge(const struct of *of, struct mparse *mp, */ static void index_prune(const struct of *ofile, DB *db, const char *dbf, - DB *idx, const char *idxf, + DB *idx, const char *idxf, int verb, recno_t *maxrec, recno_t **recs, size_t *recsz) { const struct of *of; const char *fn; + struct db_val *vbuf; unsigned seq, sseq; DBT key, val; size_t reccur; @@ -545,11 +599,13 @@ index_prune(const struct of *ofile, DB *db, const char 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; - printf("%s: Deleted keyword: %s\n", - fn, (char *)key.data); + if (verb) + printf("%s: Deleted keyword: %s\n", + fn, (char *)key.data); ch = (*db->del)(db, &key, R_CURSOR); if (ch < 0) break; @@ -559,7 +615,8 @@ index_prune(const struct of *ofile, DB *db, const char exit((int)MANDOCLEVEL_SYSERR); } - printf("%s: Deleted index\n", fn); + if (verb) + printf("%s: Deleted index\n", fn); val.size = 0; ch = (*idx->put)(idx, &key, &val, R_CURSOR); @@ -654,7 +711,7 @@ pmdoc_An(MDOC_ARGS) return; buf_appendmdoc(buf, n->child, 0); - hash_put(hash, buf, TYPE_AUTHOR); + hash_put(hash, buf, TYPE_An); } static void @@ -665,7 +722,7 @@ hash_reset(DB **db) if (NULL != (hash = *db)) (*hash->close)(hash); - *db = dbopen(NULL, MANDOC_FLAGS, 0644, DB_HASH, NULL); + *db = dbopen(NULL, O_CREAT|O_RDWR, 0644, DB_HASH, NULL); if (NULL == *db) { perror("hash"); exit((int)MANDOCLEVEL_SYSERR); @@ -715,7 +772,7 @@ pmdoc_Fd(MDOC_ARGS) buf_appendb(buf, start, (size_t)(end - start + 1)); buf_appendb(buf, "", 1); - hash_put(hash, buf, TYPE_INCLUDES); + hash_put(hash, buf, TYPE_In); } /* ARGSUSED */ @@ -727,7 +784,7 @@ pmdoc_Cd(MDOC_ARGS) return; buf_appendmdoc(buf, n->child, 0); - hash_put(hash, buf, TYPE_CONFIG); + hash_put(hash, buf, TYPE_Cd); } /* ARGSUSED */ @@ -741,7 +798,7 @@ pmdoc_In(MDOC_ARGS) return; buf_append(buf, n->child->string); - hash_put(hash, buf, TYPE_INCLUDES); + hash_put(hash, buf, TYPE_In); } /* ARGSUSED */ @@ -767,7 +824,7 @@ pmdoc_Fn(MDOC_ARGS) cp++; buf_append(buf, cp); - hash_put(hash, buf, TYPE_FUNCTION); + hash_put(hash, buf, TYPE_Fn); } /* ARGSUSED */ @@ -781,7 +838,7 @@ pmdoc_St(MDOC_ARGS) return; buf_append(buf, n->child->string); - hash_put(hash, buf, TYPE_STANDARD); + hash_put(hash, buf, TYPE_St); } /* ARGSUSED */ @@ -800,7 +857,7 @@ pmdoc_Xr(MDOC_ARGS) } else buf_appendb(buf, ".", 2); - hash_put(hash, buf, TYPE_XREF); + hash_put(hash, buf, TYPE_Xr); } /* ARGSUSED */ @@ -837,7 +894,7 @@ pmdoc_Vt(MDOC_ARGS) buf_appendb(buf, start, sz); buf_appendb(buf, "", 1); - hash_put(hash, buf, TYPE_VARIABLE); + hash_put(hash, buf, TYPE_Va); } /* ARGSUSED */ @@ -851,7 +908,7 @@ pmdoc_Fo(MDOC_ARGS) return; buf_append(buf, n->child->string); - hash_put(hash, buf, TYPE_FUNCTION); + hash_put(hash, buf, TYPE_Fn); } @@ -866,7 +923,7 @@ pmdoc_Nd(MDOC_ARGS) buf_appendmdoc(dbuf, n->child, 1); buf_appendmdoc(buf, n->child, 0); - hash_put(hash, buf, TYPE_DESC); + hash_put(hash, buf, TYPE_Nd); } /* ARGSUSED */ @@ -878,7 +935,7 @@ pmdoc_Er(MDOC_ARGS) return; buf_appendmdoc(buf, n->child, 0); - hash_put(hash, buf, TYPE_ERR); + hash_put(hash, buf, TYPE_Er); } /* ARGSUSED */ @@ -890,7 +947,7 @@ pmdoc_Ev(MDOC_ARGS) return; buf_appendmdoc(buf, n->child, 0); - hash_put(hash, buf, TYPE_ENV); + hash_put(hash, buf, TYPE_Ev); } /* ARGSUSED */ @@ -902,7 +959,7 @@ pmdoc_Pa(MDOC_ARGS) return; buf_appendmdoc(buf, n->child, 0); - hash_put(hash, buf, TYPE_PATH); + hash_put(hash, buf, TYPE_Pa); } /* ARGSUSED */ @@ -912,7 +969,7 @@ pmdoc_Nm(MDOC_ARGS) if (SEC_NAME == n->sec) { buf_appendmdoc(buf, n->child, 0); - hash_put(hash, buf, TYPE_NAME); + hash_put(hash, buf, TYPE_Nm); return; } else if (SEC_SYNOPSIS != n->sec || MDOC_HEAD != n->type) return; @@ -921,11 +978,11 @@ pmdoc_Nm(MDOC_ARGS) buf_append(buf, m->name); buf_appendmdoc(buf, n->child, 0); - hash_put(hash, buf, TYPE_UTILITY); + hash_put(hash, buf, TYPE_Nm); } 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; @@ -940,10 +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"); @@ -1051,7 +1108,7 @@ pman_node(MAN_ARGS) buf_appendb(buf, start, sz); buf_appendb(buf, "", 1); - hash_put(hash, buf, TYPE_NAME); + hash_put(hash, buf, TYPE_Nm); if (' ' == start[(int)sz]) { start += (int)sz + 1; @@ -1090,18 +1147,39 @@ pman_node(MAN_ARGS) buf_appendb(dbuf, start, sz); buf_appendb(buf, start, sz); - hash_put(hash, buf, TYPE_DESC); + hash_put(hash, buf, TYPE_Nd); } } - if (pman_node(hash, buf, dbuf, n->child)) - return(1); - if (pman_node(hash, buf, dbuf, n->next)) - return(1); + for (n = n->child; n; n = n->next) + if (pman_node(hash, buf, dbuf, n)) + return(1); return(0); } +static void +ofile_argbuild(char *argv[], int argc, int verb, struct of **of) +{ + int i; + struct of *nof; + + for (i = 0; i < argc; i++) { + nof = mandoc_calloc(1, sizeof(struct of)); + nof->fname = strdup(argv[i]); + if (verb > 2) + printf("%s: Scheduling\n", argv[i]); + if (NULL == *of) { + *of = nof; + (*of)->first = nof; + } else { + nof->first = (*of)->first; + (*of)->next = nof; + *of = nof; + } + } +} + /* * Recursively build up a list of files to parse. * We use this instead of ftw() and so on because I don't want global @@ -1111,8 +1189,10 @@ pman_node(MAN_ARGS) * Pass in a pointer to a NULL structure for the first invocation. */ static int -ofile_build(const char *dir, struct of **of) +ofile_dirbuild(const char *dir, int verb, struct of **of) { + char buf[MAXPATHLEN]; + size_t sz; DIR *d; const char *fn; struct of *nof; @@ -1126,29 +1206,59 @@ ofile_build(const char *dir, struct of **of) while (NULL != (dp = readdir(d))) { fn = dp->d_name; if (DT_DIR == dp->d_type) { - if (strcmp(".", fn) && strcmp("..", fn)) - if ( ! ofile_build(dp->d_name, of)) + if (0 == strcmp(".", fn)) + continue; + if (0 == strcmp("..", fn)) + continue; + + buf[0] = '\0'; + strlcat(buf, dir, MAXPATHLEN); + strlcat(buf, "/", MAXPATHLEN); + sz = strlcat(buf, fn, MAXPATHLEN); + + if (sz < MAXPATHLEN) { + if ( ! ofile_dirbuild(buf, verb, of)) return(0); + continue; + } else if (sz < MAXPATHLEN) + continue; + + fprintf(stderr, "%s: Path too long\n", dir); + return(0); + } + if (DT_REG != dp->d_type) continue; - } else if (DT_REG != dp->d_type) - continue; if (0 == strcmp(MANDOC_DB, fn) || 0 == strcmp(MANDOC_IDX, fn)) continue; + buf[0] = '\0'; + strlcat(buf, dir, MAXPATHLEN); + strlcat(buf, "/", MAXPATHLEN); + sz = strlcat(buf, fn, MAXPATHLEN); + if (sz >= MAXPATHLEN) { + fprintf(stderr, "%s: Path too long\n", dir); + return(0); + } + nof = mandoc_calloc(1, sizeof(struct of)); - nof->fname = mandoc_strdup(fn); + nof->fname = mandoc_strdup(buf); + if (verb > 2) + printf("%s: Scheduling\n", buf); + if (NULL == *of) { *of = nof; (*of)->first = nof; } else { + nof->first = (*of)->first; (*of)->next = nof; *of = nof; } } + closedir(d); return(1); } @@ -1169,5 +1279,8 @@ static void usage(void) { - fprintf(stderr, "usage: %s [dir...]\n", progname); + fprintf(stderr, "usage: %s [-v] " + "[-d dir [files...] |" + " -u dir [files...] |" + " dir...]\n", progname); }