From: schwarze@mdocml.bsd.lv
To: source@mdocml.bsd.lv
Subject: mdocml: Fix whatis(1) to correctly match words instead of any
Date: Sat, 12 Jul 2014 10:00:26 -0400 (EDT) [thread overview]
Message-ID: <201407121400.s6CE0PRl020859@krisdoz.my.domain> (raw)
Log Message:
-----------
Fix whatis(1) to correctly match words instead of any substrings.
While here, also provide an internal mode (MANSEARCH_MAN) to match
complete names, to be used by man.cgi(8).
Modified Files:
--------------
mdocml:
mansearch.c
mansearch.h
Revision Data
-------------
Index: mansearch.h
===================================================================
RCS file: /usr/vhosts/mdocml.bsd.lv/cvs/mdocml/mansearch.h,v
retrieving revision 1.13
retrieving revision 1.14
diff -Lmansearch.h -Lmansearch.h -u -p -r1.13 -r1.14
--- mansearch.h
+++ mansearch.h
@@ -82,7 +82,8 @@ struct mansearch {
const char *sec; /* mansection/NULL */
uint64_t deftype; /* type if no key */
int flags;
-#define MANSEARCH_WHATIS 0x01 /* whatis mode: equality, no key */
+#define MANSEARCH_WHATIS 0x01 /* whatis(1) mode: whole words, no keys */
+#define MANSEARCH_MAN 0x02 /* man(1) mode: string equality, no keys */
};
int mansearch_setup(int);
Index: mansearch.c
===================================================================
RCS file: /usr/vhosts/mdocml.bsd.lv/cvs/mdocml/mansearch.c,v
retrieving revision 1.37
retrieving revision 1.38
diff -Lmansearch.c -Lmansearch.c -u -p -r1.37 -r1.38
--- mansearch.c
+++ mansearch.c
@@ -64,13 +64,14 @@ extern const char *const mansearch_keyna
} while (0)
struct expr {
- uint64_t bits; /* type-mask */
- const char *substr; /* to search for, if applicable */
regex_t regexp; /* compiled regexp, if applicable */
+ const char *substr; /* to search for, if applicable */
+ struct expr *next; /* next in sequence */
+ uint64_t bits; /* type-mask */
+ int equal; /* equality, not subsring match */
int open; /* opening parentheses before */
int and; /* logical AND before */
int close; /* closing parentheses after */
- struct expr *next; /* next in sequence */
};
struct match {
@@ -561,6 +562,9 @@ sql_statement(const struct expr *e)
? (NULL == e->substr
? "pageid IN (SELECT pageid FROM names "
"WHERE name REGEXP ?)"
+ : e->equal
+ ? "pageid IN (SELECT pageid FROM names "
+ "WHERE name = ?)"
: "pageid IN (SELECT pageid FROM names "
"WHERE name MATCH ?)")
: (NULL == e->substr
@@ -702,7 +706,7 @@ exprterm(const struct mansearch *search,
{
char errbuf[BUFSIZ];
struct expr *e;
- char *key, *v;
+ char *key, *val;
uint64_t iterbit;
int i, irc;
@@ -711,40 +715,64 @@ exprterm(const struct mansearch *search,
e = mandoc_calloc(1, sizeof(struct expr));
- /*"whatis" mode uses an opaque string and default fields. */
-
- if (MANSEARCH_WHATIS & search->flags) {
- e->substr = buf;
+ if (MANSEARCH_MAN & search->flags) {
e->bits = search->deftype;
+ e->substr = buf;
+ e->equal = 1;
return(e);
}
/*
- * If no =~ is specified, search with equality over names and
- * descriptions.
- * If =~ begins the phrase, use name and description fields.
+ * Look for an '=' or '~' operator,
+ * unless forced to some fixed macro keys.
*/
- if (NULL == (v = strpbrk(buf, "=~"))) {
- e->substr = buf;
- e->bits = search->deftype;
- return(e);
- } else if (v == buf)
+ if (MANSEARCH_WHATIS & search->flags)
+ val = NULL;
+ else
+ val = strpbrk(buf, "=~");
+
+ if (NULL == val) {
e->bits = search->deftype;
+ e->substr = buf;
- if ('~' == *v++) {
+ /*
+ * Found an operator.
+ * Regexp search is requested by !e->substr.
+ */
+
+ } else {
+ if (val == buf)
+ e->bits = search->deftype;
+ if ('=' == *val)
+ e->substr = val + 1;
+ *val++ = '\0';
if (NULL != strstr(buf, "arch"))
cs = 0;
- if (0 != (irc = regcomp(&e->regexp, v,
- REG_EXTENDED | REG_NOSUB | (cs ? 0 : REG_ICASE)))) {
+ }
+
+ /* Compile regular expressions. */
+
+ if (MANSEARCH_WHATIS & search->flags) {
+ e->substr = NULL;
+ mandoc_asprintf(&val, "[[:<:]]%s[[:>:]]", buf);
+ }
+
+ if (NULL == e->substr) {
+ irc = regcomp(&e->regexp, val,
+ REG_EXTENDED | REG_NOSUB | (cs ? 0 : REG_ICASE));
+ if (MANSEARCH_WHATIS & search->flags)
+ free(val);
+ if (irc) {
regerror(irc, &e->regexp, errbuf, sizeof(errbuf));
fprintf(stderr, "regcomp: %s\n", errbuf);
free(e);
return(NULL);
}
- } else
- e->substr = v;
- v[-1] = '\0';
+ }
+
+ if (e->bits)
+ return(e);
/*
* Parse out all possible fields.
--
To unsubscribe send an email to source+unsubscribe@mdocml.bsd.lv
reply other threads:[~2014-07-12 14:00 UTC|newest]
Thread overview: [no followups] expand[flat|nested] mbox.gz Atom feed
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=201407121400.s6CE0PRl020859@krisdoz.my.domain \
--to=schwarze@mdocml.bsd.lv \
--cc=source@mdocml.bsd.lv \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).