[src/trunk]: src/usr.sbin/makemandb Better handle MLINKS in apropos(1).

[abhinav <abhinav%NetBSD.org@localhost>]

details:   https://anonhg.NetBSD.org/src/rev/3e58fed03771
branches:  trunk
changeset: 823457:3e58fed03771
user:      abhinav <abhinav%NetBSD.org@localhost>
date:      Sun Apr 23 13:52:57 2017 +0000

description:
Better handle MLINKS in apropos(1).

apropos(1) only indexes the first .Nm entry from the NAME section in the full
text index. Rest of the .Nm entries are stored in a separate table: mandb_links.

Till now apropos(1) did not use the mandb_links table. So whenever a query
was being made for one of the man page links, such as realloc(3), it was showing
malloc(3) in the results but not as the first result. And, also the result would
show up as malloc(3), rather than realloc(3) (which can be confusing).

With this change, for single keyword queries, apropos(1) would now utilise the
mandb_links table as well. If the query is for one of the links of a man page,
it would show as the first result. Also, the result would show up as the name
of the link rather than the original man page name. For example, if the query
was for realloc, the output would be realloc(3), rather than malloc(3).

Following are some example queries showing difference in the output before this
change and after this change:

#Before changes
$ apropos -n 5 -M realloc
reallocarr (3)    reallocate array
reallocarray (3)  reallocate memory for an array of elements checking
for overflow
fgetwln (3)       get a line of wide characters from a stream
fgetln (3)        get a line from a stream
posix_memalign (3)        aligned memory allocation

#After changes
$ ./apropos -n 5 -M realloc
realloc (3)       general memory allocation operations
realloc (3)       general purpose memory allocation functions
realloc (9)       general-purpose kernel memory allocator
reallocarr (3)    reallocate array
reallocarray (3)  reallocate memory for an array of elements checking
for overflow

#Before changes
$ apropos -n 5 -M TAILQ_REMOVE
SLIST_HEAD (3) implementations of singly-linked lists, lists, simple
queues, tail queues, and singly-linked tail queues

#After changes
$ ./apropos -n 5 -M TAILQ_REMOVE
TAILQ_REMOVE (3)  implementations of singly-linked lists, lists,
simple queues, tail queues, and singly-linked tail queues

#Before changes
$ apropos -n 5 -M falloc
filedesc (9)      file descriptor tables and operations
file (9)  operations on file entries

#After changes
$ ./apropos -n 5 -M falloc
falloc (9)        file descriptor tables and operations
file (9)  operations on file entries

ok christos@

diffstat:

 usr.sbin/makemandb/apropos-utils.c |  39 +++++++++++++++++++++++++++++++++----
 1 files changed, 34 insertions(+), 5 deletions(-)

diffs (81 lines):

diff -r 4b2b97e110b1 -r 3e58fed03771 usr.sbin/makemandb/apropos-utils.c
--- a/usr.sbin/makemandb/apropos-utils.c        Sun Apr 23 13:23:02 2017 +0000
+++ b/usr.sbin/makemandb/apropos-utils.c        Sun Apr 23 13:52:57 2017 +0000
@@ -1,4 +1,4 @@
-/*     $NetBSD: apropos-utils.c,v 1.30 2017/01/10 04:34:07 kamil Exp $ */
+/*     $NetBSD: apropos-utils.c,v 1.31 2017/04/23 13:52:57 abhinav Exp $       */
 /*-
  * Copyright (c) 2011 Abhinav Upadhyay <er.abhinav.upadhyay%gmail.com@localhost>
  * All rights reserved.
@@ -31,7 +31,7 @@
  */
 
 #include <sys/cdefs.h>
-__RCSID("$NetBSD: apropos-utils.c,v 1.30 2017/01/10 04:34:07 kamil Exp $");
+__RCSID("$NetBSD: apropos-utils.c,v 1.31 2017/04/23 13:52:57 abhinav Exp $");
 
 #include <sys/queue.h>
 #include <sys/stat.h>
@@ -182,7 +182,7 @@
            "CREATE TABLE IF NOT EXISTS mandb_meta(device, inode, mtime, "
                "file UNIQUE, md5_hash UNIQUE, id  INTEGER PRIMARY KEY); "
            //mandb_links
-           "CREATE TABLE IF NOT EXISTS mandb_links(link, target, section, "
+           "CREATE TABLE IF NOT EXISTS mandb_links(link COLLATE NOCASE, target, section, "
                "machine, md5_hash); ";
 
        sqlite3_exec(db, sqlstr, NULL, NULL, &errmsg);
@@ -504,7 +504,7 @@
        char *query;
 
        if (args->machine)
-               easprintf(&machine_clause, "AND machine = \'%s\' ",
+               easprintf(&machine_clause, "AND mandb.machine = \'%s\' ",
                    args->machine);
 
 
@@ -547,7 +547,7 @@
                        if (section_clause[section_clause_len - 1] == ',')
                                section_clause[section_clause_len - 1] = 0;
                        temp = section_clause;
-                       easprintf(&section_clause, " AND section IN (%s)", temp);
+                       easprintf(&section_clause, " AND mandb.section IN (%s)", temp);
                        free(temp);
                }
        }
@@ -577,6 +577,35 @@
                section_clause ? section_clause : "",
                limit_clause ? limit_clause : "");
                free(wild);
+       } else if (strchr(args->search_str, ' ') == NULL) {
+               /*
+                * If it's a single word query, we want to search in the
+                * links table as well. If the link table contains an entry
+                * for the queried keyword, we want to use that as the name of
+                * the man page.
+                * For example, for `apropos realloc` the output should be
+                * realloc(3) and not malloc(3).
+                */
+               query = sqlite3_mprintf(
+                   "SELECT section, name, name_desc, machine,"
+                   " snippet(mandb, %Q, %Q, %Q, -1, 40 ),"
+                   " rank_func(matchinfo(mandb, \"pclxn\")) AS rank"
+                   " FROM mandb WHERE name NOT IN ("
+                   " SELECT target FROM mandb_links WHERE link=%Q AND"
+                   " mandb_links.section=mandb.section) AND mandb MATCH %Q %s %s"
+                   " UNION"
+                   " SELECT mandb.section, mandb_links.link AS name, mandb.name_desc,"
+                   " mandb.machine, '' AS snippet, 100.00 AS rank"
+                   " FROM mandb JOIN mandb_links ON mandb.name=mandb_links.target and"
+                   " mandb.section=mandb_links.section WHERE mandb_links.link=%Q"
+                   " %s %s"
+                   " ORDER BY rank DESC %s",
+                   snippet_args[0], snippet_args[1], snippet_args[2],
+                   args->search_str, args->search_str, section_clause ? section_clause : "",
+                   machine_clause ? machine_clause : "", args->search_str,
+                   machine_clause ? machine_clause : "",
+                   section_clause ? section_clause : "",
+                   limit_clause ? limit_clause : "");
        } else {
            query = sqlite3_mprintf("SELECT section, name, name_desc, machine,"
                " snippet(mandb, %Q, %Q, %Q, -1, 40 ),"