Do not fork and exec cmp(1); instead, simply fstat(2), mmap(2), and

[mandoc.git] / mandocdb.c

diff --git a/mandocdb.c b/mandocdb.c
index dcfa43bd33e55a821026d6a33b236b80c92c556b..1a4ff107b5a27ce228c25fa6fa5792ab421766e8 100644 (file)
--- a/mandocdb.c
+++ b/mandocdb.c
@@ -1,4 +1,4 @@
-/*     $Id: mandocdb.c,v 1.242 2017/01/27 11:33:26 schwarze Exp $ */
+/*     $Id: mandocdb.c,v 1.255 2017/08/26 15:55:46 schwarze Exp $ */

 /*
  * Copyright (c) 2011, 2012 Kristaps Dzonsons <kristaps@bsd.lv>
  * Copyright (c) 2011-2017 Ingo Schwarze <schwarze@openbsd.org>
 /*
  * Copyright (c) 2011, 2012 Kristaps Dzonsons <kristaps@bsd.lv>
  * Copyright (c) 2011-2017 Ingo Schwarze <schwarze@openbsd.org>


@@ -19,8 +19,8 @@
 #include "config.h"
 
 #include <sys/types.h>
 #include "config.h"
 
 #include <sys/types.h>

+#include <sys/mman.h>

 #include <sys/stat.h>
 #include <sys/stat.h>

-#include <sys/wait.h>

 
 #include <assert.h>
 #include <ctype.h>
 
 #include <assert.h>
 #include <ctype.h>


@@ -162,7 +162,7 @@ static      void     putmdockey(const struct mpage *,
                        const struct roff_node *, uint64_t, int);
 static int      render_string(char **, size_t *);
 static void     say(const char *, const char *, ...)
                        const struct roff_node *, uint64_t, int);
 static int      render_string(char **, size_t *);
 static void     say(const char *, const char *, ...)

-                       __attribute__((__format__ (printf, 2, 3)));
+                       __attribute__((__format__ (__printf__, 2, 3)));

 static int      set_basedir(const char *, int);
 static int      treescan(void);
 static size_t   utf8(unsigned int, char [7]);
 static int      set_basedir(const char *, int);
 static int      treescan(void);
 static size_t   utf8(unsigned int, char [7]);


@@ -183,8 +183,7 @@ static      struct ohash     names; /* table of all names */
 static struct ohash     strings; /* table of all strings */
 static uint64_t         name_mask;
 
 static struct ohash     strings; /* table of all strings */
 static uint64_t         name_mask;
 

-static const struct mdoc_handler mdocs[MDOC_MAX] = {
-       { NULL, 0, 0 },  /* Ap */
+static const struct mdoc_handler __mdocs[MDOC_MAX - MDOC_Dd] = {

        { NULL, 0, NODE_NOPRT },  /* Dd */
        { NULL, 0, NODE_NOPRT },  /* Dt */
        { NULL, 0, NODE_NOPRT },  /* Os */
        { NULL, 0, NODE_NOPRT },  /* Dd */
        { NULL, 0, NODE_NOPRT },  /* Dt */
        { NULL, 0, NODE_NOPRT },  /* Os */


@@ -200,6 +199,7 @@ static      const struct mdoc_handler mdocs[MDOC_MAX] = {
        { NULL, 0, 0 },  /* It */
        { NULL, 0, 0 },  /* Ad */
        { NULL, TYPE_An, 0 },  /* An */
        { NULL, 0, 0 },  /* It */
        { NULL, 0, 0 },  /* Ad */
        { NULL, TYPE_An, 0 },  /* An */

+       { NULL, 0, 0 },  /* Ap */

        { NULL, TYPE_Ar, 0 },  /* Ar */
        { NULL, TYPE_Cd, 0 },  /* Cd */
        { NULL, TYPE_Cm, 0 },  /* Cm */
        { NULL, TYPE_Ar, 0 },  /* Ar */
        { NULL, TYPE_Cd, 0 },  /* Cd */
        { NULL, TYPE_Cm, 0 },  /* Cm */


@@ -302,12 +302,10 @@ static    const struct mdoc_handler mdocs[MDOC_MAX] = {
        { NULL, 0, 0 },  /* En */
        { NULL, TYPE_Dx, NODE_NOSRC },  /* Dx */
        { NULL, 0, 0 },  /* %Q */
        { NULL, 0, 0 },  /* En */
        { NULL, TYPE_Dx, NODE_NOSRC },  /* Dx */
        { NULL, 0, 0 },  /* %Q */

-       { NULL, 0, 0 },  /* br */
-       { NULL, 0, 0 },  /* sp */

        { NULL, 0, 0 },  /* %U */
        { NULL, 0, 0 },  /* Ta */
        { NULL, 0, 0 },  /* %U */
        { NULL, 0, 0 },  /* Ta */

-       { NULL, 0, 0 },  /* ll */

 };
 };

+static const struct mdoc_handler *const mdocs = __mdocs - MDOC_Dd;

 
 
 int
 
 
 int


@@ -321,7 +319,7 @@ mandocdb(int argc, char *argv[])
        int               ch, i;
 
 #if HAVE_PLEDGE
        int               ch, i;
 
 #if HAVE_PLEDGE

-       if (pledge("stdio rpath wpath cpath fattr flock proc exec", NULL) == -1) {
+       if (pledge("stdio rpath wpath cpath", NULL) == -1) {

                warn("pledge");
                return (int)MANDOCLEVEL_SYSERR;
        }
                warn("pledge");
                return (int)MANDOCLEVEL_SYSERR;
        }


@@ -422,7 +420,8 @@ mandocdb(int argc, char *argv[])
 
        exitcode = (int)MANDOCLEVEL_OK;
        mchars_alloc();
 
        exitcode = (int)MANDOCLEVEL_OK;
        mchars_alloc();

-       mp = mparse_alloc(mparse_options, MANDOCLEVEL_BADARG, NULL, NULL);
+       mp = mparse_alloc(mparse_options, MANDOCERR_MAX, NULL,
+           MANDOC_OS_OTHER, NULL);

        mandoc_ohash_init(&mpages, 6, offsetof(struct mpage, inodev));
        mandoc_ohash_init(&mlinks, 6, offsetof(struct mlink, file));
 
        mandoc_ohash_init(&mpages, 6, offsetof(struct mpage, inodev));
        mandoc_ohash_init(&mlinks, 6, offsetof(struct mlink, file));
 


@@ -441,15 +440,6 @@ mandocdb(int argc, char *argv[])
                         * The existing database is usable.  Process
                         * all files specified on the command-line.
                         */
                         * The existing database is usable.  Process
                         * all files specified on the command-line.
                         */

-#if HAVE_PLEDGE
-                       if (!nodb) {
-                               if (pledge("stdio rpath wpath cpath fattr flock", NULL) == -1) {
-                                       warn("pledge");
-                                       exitcode = (int)MANDOCLEVEL_SYSERR;
-                                       goto out;
-                               }
-                       }
-#endif

                        use_all = 1;
                        for (i = 0; i < argc; i++)
                                filescan(argv[i]);
                        use_all = 1;
                        for (i = 0; i < argc; i++)
                                filescan(argv[i]);


@@ -589,7 +579,7 @@ treescan(void)
        const char      *argv[2];
 
        argv[0] = ".";
        const char      *argv[2];
 
        argv[0] = ".";

-       argv[1] = (char *)NULL;
+       argv[1] = NULL;

 
        f = fts_open((char * const *)argv, FTS_PHYSICAL | FTS_NOCHDIR,
            fts_compare);
 
        f = fts_open((char * const *)argv, FTS_PHYSICAL | FTS_NOCHDIR,
            fts_compare);


@@ -1211,7 +1201,7 @@ mpages_merge(struct dba *dba, struct mparse *mp)
                } else if (man != NULL && man->macroset == MACROSET_MAN) {
                        man_validate(man);
                        if (*man->meta.msec != '\0' ||
                } else if (man != NULL && man->macroset == MACROSET_MAN) {
                        man_validate(man);
                        if (*man->meta.msec != '\0' ||

-                           *man->meta.msec != '\0') {
+                           *man->meta.title != '\0') {

                                mpage->form = FORM_SRC;
                                mpage->sec = mandoc_strdup(man->meta.msec);
                                mpage->arch = mandoc_strdup(mlink->arch);
                                mpage->form = FORM_SRC;
                                mpage->sec = mandoc_strdup(man->meta.msec);
                                mpage->arch = mandoc_strdup(mlink->arch);


@@ -1545,25 +1535,26 @@ parse_mdoc(struct mpage *mpage, const struct roff_meta *meta,
        const struct roff_node *n)
 {
 
        const struct roff_node *n)
 {
 

-       assert(NULL != n);
-       for (n = n->child; NULL != n; n = n->next) {
-               if (n->flags & mdocs[n->tok].taboo)
+       for (n = n->child; n != NULL; n = n->next) {
+               if (n->tok == TOKEN_NONE ||
+                   n->tok < ROFF_MAX ||
+                   n->flags & mdocs[n->tok].taboo)

                        continue;
                        continue;

+               assert(n->tok >= MDOC_Dd && n->tok < MDOC_MAX);

                switch (n->type) {
                case ROFFT_ELEM:
                case ROFFT_BLOCK:
                case ROFFT_HEAD:
                case ROFFT_BODY:
                case ROFFT_TAIL:
                switch (n->type) {
                case ROFFT_ELEM:
                case ROFFT_BLOCK:
                case ROFFT_HEAD:
                case ROFFT_BODY:
                case ROFFT_TAIL:

-                       if (NULL != mdocs[n->tok].fp)
-                              if (0 == (*mdocs[n->tok].fp)(mpage, meta, n))
-                                      break;
+                       if (mdocs[n->tok].fp != NULL &&
+                           (*mdocs[n->tok].fp)(mpage, meta, n) == 0)
+                               break;

                        if (mdocs[n->tok].mask)
                                putmdockey(mpage, n->child,
                                    mdocs[n->tok].mask, mdocs[n->tok].taboo);
                        break;
                default:
                        if (mdocs[n->tok].mask)
                                putmdockey(mpage, n->child,
                                    mdocs[n->tok].mask, mdocs[n->tok].taboo);
                        break;
                default:

-                       assert(n->type != ROFFT_ROOT);

                        continue;
                }
                if (NULL != n->child)
                        continue;
                }
                if (NULL != n->child)


@@ -2119,9 +2110,27 @@ dbprune(struct dba *dba)
 static void
 dbwrite(struct dba *dba)
 {
 static void
 dbwrite(struct dba *dba)
 {

-       char             tfn[32];
-       int              status;
-       pid_t            child;
+       struct stat      sb1, sb2;
+       char             tfn[33], *cp1, *cp2;
+       off_t            i;
+       int              fd1, fd2;
+
+       /*
+        * Do not write empty databases, and delete existing ones
+        * when makewhatis -u causes them to become empty.
+        */
+
+       dba_array_start(dba->pages);
+       if (dba_array_next(dba->pages) == NULL) {
+               if (unlink(MANDOC_DB) == -1 && errno != ENOENT)
+                       say(MANDOC_DB, "&unlink");
+               return;
+       }
+
+       /*
+        * Build the database in a temporary file,
+        * then atomically move it into place.
+        */

 
        if (dba_write(MANDOC_DB "~", dba) != -1) {
                if (rename(MANDOC_DB "~", MANDOC_DB) == -1) {
 
        if (dba_write(MANDOC_DB "~", dba) != -1) {
                if (rename(MANDOC_DB "~", MANDOC_DB) == -1) {


@@ -2132,65 +2141,73 @@ dbwrite(struct dba *dba)
                return;
        }
 
                return;
        }
 

+       /*
+        * We lack write permission and cannot replace the database
+        * file, but let's at least check whether the data changed.
+        */
+

        (void)strlcpy(tfn, "/tmp/mandocdb.XXXXXXXX", sizeof(tfn));
        if (mkdtemp(tfn) == NULL) {
                exitcode = (int)MANDOCLEVEL_SYSERR;
                say("", "&%s", tfn);
                return;
        }
        (void)strlcpy(tfn, "/tmp/mandocdb.XXXXXXXX", sizeof(tfn));
        if (mkdtemp(tfn) == NULL) {
                exitcode = (int)MANDOCLEVEL_SYSERR;
                say("", "&%s", tfn);
                return;
        }

-
+       cp1 = cp2 = NULL;
+       fd1 = fd2 = -1;

        (void)strlcat(tfn, "/" MANDOC_DB, sizeof(tfn));
        if (dba_write(tfn, dba) == -1) {
        (void)strlcat(tfn, "/" MANDOC_DB, sizeof(tfn));
        if (dba_write(tfn, dba) == -1) {

-               exitcode = (int)MANDOCLEVEL_SYSERR;

                say(tfn, "&dba_write");
                say(tfn, "&dba_write");

-               goto out;
+               goto err;

        }
        }

-
-       switch (child = fork()) {
-       case -1:
-               exitcode = (int)MANDOCLEVEL_SYSERR;
-               say("", "&fork cmp");
-               return;
-       case 0:
-               execlp("cmp", "cmp", "-s", tfn, MANDOC_DB, (char *)NULL);
-               say("", "&exec cmp");
-               exit(0);
-       default:
-               break;
+       if ((fd1 = open(MANDOC_DB, O_RDONLY, 0)) == -1) {
+               say(MANDOC_DB, "&open");
+               goto err;

        }
        }

-       if (waitpid(child, &status, 0) == -1) {
-               exitcode = (int)MANDOCLEVEL_SYSERR;
-               say("", "&wait cmp");
-       } else if (WIFSIGNALED(status)) {
-               exitcode = (int)MANDOCLEVEL_SYSERR;
-               say("", "cmp died from signal %d", WTERMSIG(status));
-       } else if (WEXITSTATUS(status)) {
-               exitcode = (int)MANDOCLEVEL_SYSERR;
-               say(MANDOC_DB,
-                   "Data changed, but cannot replace database");
+       if ((fd2 = open(tfn, O_RDONLY, 0)) == -1) {
+               say(tfn, "&open");
+               goto err;
+       }
+       if (fstat(fd1, &sb1) == -1) {
+               say(MANDOC_DB, "&fstat");
+               goto err;
+       }
+       if (fstat(fd2, &sb2) == -1) {
+               say(tfn, "&fstat");
+               goto err;

        }
        }

+       if (sb1.st_size != sb2.st_size)
+               goto err;
+       if ((cp1 = mmap(NULL, sb1.st_size, PROT_READ, MAP_PRIVATE,
+           fd1, 0)) == NULL) {
+               say(MANDOC_DB, "&mmap");
+               goto err;
+       }
+       if ((cp2 = mmap(NULL, sb2.st_size, PROT_READ, MAP_PRIVATE,
+           fd2, 0)) == NULL) {
+               say(tfn, "&mmap");
+               goto err;
+       }
+       for (i = 0; i < sb1.st_size; i++)
+               if (cp1[i] != cp2[i])
+                       goto err;
+       goto out;
+
+err:
+       exitcode = (int)MANDOCLEVEL_SYSERR;
+       say(MANDOC_DB, "Data changed, but cannot replace database");

 
 out:
 
 out:

+       if (cp1 != NULL)
+               munmap(cp1, sb1.st_size);
+       if (cp2 != NULL)
+               munmap(cp2, sb2.st_size);
+       if (fd1 != -1)
+               close(fd1);
+       if (fd2 != -1)
+               close(fd2);
+       unlink(tfn);

        *strrchr(tfn, '/') = '\0';
        *strrchr(tfn, '/') = '\0';

-       switch (child = fork()) {
-       case -1:
-               exitcode = (int)MANDOCLEVEL_SYSERR;
-               say("", "&fork rm");
-               return;
-       case 0:
-               execlp("rm", "rm", "-rf", tfn, (char *)NULL);
-               say("", "&exec rm");
-               exit((int)MANDOCLEVEL_SYSERR);
-       default:
-               break;
-       }
-       if (waitpid(child, &status, 0) == -1) {
-               exitcode = (int)MANDOCLEVEL_SYSERR;
-               say("", "&wait rm");
-       } else if (WIFSIGNALED(status) || WEXITSTATUS(status)) {
-               exitcode = (int)MANDOCLEVEL_SYSERR;
-               say("", "%s: Cannot remove temporary directory", tfn);
-       }
+       rmdir(tfn);

 }
 
 static int
 }
 
 static int