=================================================================== RCS file: /cvs/mandoc/cgi.c,v retrieving revision 1.9 retrieving revision 1.21 diff -u -p -r1.9 -r1.21 --- mandoc/cgi.c 2011/12/04 22:52:50 1.9 +++ mandoc/cgi.c 2011/12/09 23:18:51 1.21 @@ -1,4 +1,4 @@ -/* $Id: cgi.c,v 1.9 2011/12/04 22:52:50 kristaps Exp $ */ +/* $Id: cgi.c,v 1.21 2011/12/09 23:18:51 kristaps Exp $ */ /* * Copyright (c) 2011 Kristaps Dzonsons * @@ -54,6 +54,18 @@ enum page { PAGE__MAX }; +/* + * A query as passed to the search function. + * See kval_query() on how this is parsed. + */ +struct query { + const char *arch; /* architecture */ + const char *sec; /* manual section */ + const char *expr; /* unparsed expression string */ + int whatis; /* whether whatis mode */ + int legacy; /* whether legacy mode */ +}; + struct kval { char *key; char *val; @@ -67,11 +79,15 @@ struct req { static int atou(const char *, unsigned *); static void catman(const char *); +static int cmp(const void *, const void *); static void format(const char *); static void html_print(const char *); +static void html_putchar(char); static int kval_decode(char *); -static void kval_parse(struct kval **, size_t *, char *); static void kval_free(struct kval *, size_t); +static void kval_parse(struct kval **, size_t *, char *); +static void kval_query(struct query *, + const struct kval *, size_t); static void pg_index(const struct manpaths *, const struct req *, char *); static void pg_search(const struct manpaths *, @@ -80,9 +96,8 @@ static void pg_show(const struct manpaths *, const struct req *, char *); static void resp_bad(void); static void resp_baddb(void); -static void resp_badexpr(const struct req *); -static void resp_badmanual(void); -static void resp_badpage(void); +static void resp_error400(void); +static void resp_error404(const char *); static void resp_begin_html(int, const char *); static void resp_begin_http(int, const char *); static void resp_end_html(void); @@ -101,6 +116,56 @@ static const char * const pages[PAGE__MAX] = { }; /* + * Initialise and parse a query structure from input. + * This accomodates for mdocml's man.cgi and also for legacy man.cgi + * input keys ("sektion" and "apropos"). + * Note that legacy mode has some quirks: if apropos legacy mode is + * detected, we unset the section and architecture string. + */ +static void +kval_query(struct query *q, const struct kval *fields, size_t sz) +{ + int i, legacy; + + memset(q, 0, sizeof(struct query)); + q->whatis = 1; + legacy = -1; + + for (i = 0; i < (int)sz; i++) + if (0 == strcmp(fields[i].key, "expr")) + q->expr = fields[i].val; + else if (0 == strcmp(fields[i].key, "query")) + q->expr = fields[i].val; + else if (0 == strcmp(fields[i].key, "sec")) + q->sec = fields[i].val; + else if (0 == strcmp(fields[i].key, "sektion")) + q->sec = fields[i].val; + else if (0 == strcmp(fields[i].key, "arch")) + q->arch = fields[i].val; + else if (0 == strcmp(fields[i].key, "apropos")) + legacy = 0 == strcmp + (fields[i].val, "0"); + else if (0 == strcmp(fields[i].key, "op")) + q->whatis = 0 == strcasecmp + (fields[i].val, "whatis"); + + /* Test for old man.cgi compatibility mode. */ + + if (legacy == 0) { + q->whatis = 0; + q->legacy = 1; + } else if (legacy > 0) { + q->legacy = 1; + q->whatis = 1; + } + + /* Section "0" means no section when in legacy mode. */ + + if (q->legacy && NULL != q->sec && 0 == strcmp(q->sec, "0")) + q->sec = NULL; +} + +/* * This is just OpenBSD's strtol(3) suggestion. * I use it instead of strtonum(3) for portability's sake. */ @@ -124,35 +189,44 @@ atou(const char *buf, unsigned *v) } /* - * Print a word, escaping HTML along the way. + * Print a character, escaping HTML along the way. * This will pass non-ASCII straight to output: be warned! */ static void +html_putchar(char c) +{ + + switch (c) { + case ('"'): + printf(""e;"); + break; + case ('&'): + printf("&"); + break; + case ('>'): + printf(">"); + break; + case ('<'): + printf("<"); + break; + default: + putchar((unsigned char)c); + break; + } +} + +/* + * Call through to html_putchar(). + * Accepts NULL strings. + */ +static void html_print(const char *p) { - char c; if (NULL == p) return; - while ('\0' != *p) - switch ((c = *p++)) { - case ('"'): - printf(""e;"); - break; - case ('&'): - printf("&"); - break; - case ('>'): - printf(">"); - break; - case ('<'): - printf("<"); - break; - default: - putchar((unsigned char)c); - break; - } + html_putchar(*p++); } static void @@ -271,9 +345,9 @@ resp_begin_http(int code, const char *msg) if (200 != code) printf("Status: %d %s\n", code, msg); - puts("Content-Type: text/html; charset=utf-8" "\n" - "Cache-Control: no-cache" "\n" - "Pragma: no-cache" "\n" + puts("Content-Type: text/html; charset=utf-8\n" + "Cache-Control: no-cache\n" + "Pragma: no-cache\n" ""); fflush(stdout); @@ -285,14 +359,18 @@ resp_begin_html(int code, const char *msg) resp_begin_http(code, msg); - puts("" "\n" - "" "\n" - " " "\n" - " System Manpage Reference" "\n" - " " "\n" - " " "\n" + puts("\n" + "\n" + "\n" + "\n" + "\n" + "System Manpage Reference\n" + "\n" + "\n" ""); } @@ -300,44 +378,42 @@ static void resp_end_html(void) { - puts(" \n"); + puts("\n" + ""); } static void resp_searchform(const struct req *req) { - int i; - const char *expr, *sec, *arch; + struct query q; - expr = sec = arch = ""; + kval_query(&q, req->fields, req->fieldsz); - for (i = 0; i < (int)req->fieldsz; i++) - if (0 == strcmp(req->fields[i].key, "expr")) - expr = req->fields[i].val; - else if (0 == strcmp(req->fields[i].key, "sec")) - sec = req->fields[i].val; - else if (0 == strcmp(req->fields[i].key, "arch")) - arch = req->fields[i].val; - puts(""); printf("
\n"); - puts("
" "\n" - " "); - printf(" Terms: "); - printf(" Section: "); - printf(" Arch: "); - puts("
\n
\n"); + printf("
\n" + "Search Parameters\n" + " or \n" + " for manuals satisfying \n" + ", section " + ", arch " + ".\n" + "\n" + "
\n" + ""); + puts(""); } static void @@ -350,34 +426,38 @@ resp_index(const struct req *req) } static void -resp_badpage(void) +resp_error400(void) { - resp_begin_html(404, "Not Found"); - puts("

Page not found.

"); + resp_begin_html(400, "Query Malformed"); + printf("

Malformed Query

\n" + "

\n" + "The query your entered was malformed.\n" + "Try again from the\n" + "main page\n" + "

", progname); resp_end_html(); } static void -resp_badmanual(void) +resp_error404(const char *page) { resp_begin_html(404, "Not Found"); - puts("

Requested manual not found.

"); + puts("

Page Not Found

\n" + "

\n" + "The page you're looking for, "); + printf(""); + html_print(page); + printf(",\n" + "could not be found.\n" + "Try searching from the\n" + "main page\n" + "

", progname); resp_end_html(); } static void -resp_badexpr(const struct req *req) -{ - - resp_begin_html(200, NULL); - resp_searchform(req); - puts("

Your search didn't work.

"); - resp_end_html(); -} - -static void resp_bad(void) { resp_begin_html(500, "Internal Server Error"); @@ -397,7 +477,9 @@ resp_baddb(void) static void resp_search(struct res *r, size_t sz, void *arg) { - int i; + int i; + struct query q; + const struct req *req; if (1 == sz) { /* @@ -412,14 +494,41 @@ resp_search(struct res *r, size_t sz, void *arg) return; } + qsort(r, sz, sizeof(struct res), cmp); + resp_begin_html(200, NULL); - resp_searchform((const struct req *)arg); - if (0 == sz) - puts("

No results found.

"); + req = (const struct req *)arg; + resp_searchform(req); + kval_query(&q, req->fields, req->fieldsz); + if (0 == sz) { + printf("

\n" + "No %s results found.", + q.whatis ? "whatis" : "apropos"); + if (q.whatis) { + printf("(Try apropos?)"); + } + puts("

"); + resp_end_html(); + return; + } + + puts("

\n" + ""); + for (i = 0; i < (int)sz; i++) { - printf("

\n" + "

\n" + "\n" + ""); } + puts("
\n" + "", r[i].volume, r[i].rec); html_print(r[i].title); @@ -429,11 +538,15 @@ resp_search(struct res *r, size_t sz, void *arg) putchar('/'); html_print(r[i].arch); } - printf(") "); + printf(")\n" + ""); html_print(r[i].desc); - puts("

"); + puts("
"); resp_end_html(); } @@ -448,24 +561,147 @@ pg_index(const struct manpaths *ps, const struct req * static void catman(const char *file) { - int fd; - char buf[BUFSIZ]; - ssize_t ssz; + FILE *f; + size_t len; + int i; + char *p; + int italic, bold; - if (-1 == (fd = open(file, O_RDONLY, 0))) { + if (NULL == (f = fopen(file, "r"))) { resp_baddb(); return; } resp_begin_http(200, NULL); + puts("\n" + "\n" + "\n" + "\n" + "\n" + "System Manpage Reference\n" + "\n" + "\n" + "\n" + "
");
 
-	while ((ssz = read(fd, buf, BUFSIZ)) > 0)
-		write(STDOUT_FILENO, buf, (size_t)ssz);
+	while (NULL != (p = fgetln(f, &len))) {
+		bold = italic = 0;
+		for (i = 0; i < (int)len - 1; i++) {
+			/* 
+			 * This means that the catpage is out of state.
+			 * Ignore it and keep going (although the
+			 * catpage is bogus).
+			 */
 
-	if (ssz < 0)
-		perror(file);
+			if ('\b' == p[i] || '\n' == p[i])
+				continue;
 
-	close(fd);
+			/*
+			 * Print a regular character.
+			 * Close out any bold/italic scopes.
+			 * If we're in back-space mode, make sure we'll
+			 * have something to enter when we backspace.
+			 */
+
+			if ('\b' != p[i + 1]) {
+				if (italic)
+					printf("");
+				if (bold)
+					printf("");
+				italic = bold = 0;
+				html_putchar(p[i]);
+				continue;
+			} else if (i + 2 >= (int)len)
+				continue;
+
+			/* Italic mode. */
+
+			if ('_' == p[i]) {
+				if (bold)
+					printf("");
+				if ( ! italic)
+					printf("");
+				bold = 0;
+				italic = 1;
+				i += 2;
+				html_putchar(p[i]);
+				continue;
+			}
+
+			/* 
+			 * Handle funny behaviour troff-isms.
+			 * These grok'd from the original man2html.c.
+			 */
+
+			if (('+' == p[i] && 'o' == p[i + 2]) ||
+					('o' == p[i] && '+' == p[i + 2]) ||
+					('|' == p[i] && '=' == p[i + 2]) ||
+					('=' == p[i] && '|' == p[i + 2]) ||
+					('*' == p[i] && '=' == p[i + 2]) ||
+					('=' == p[i] && '*' == p[i + 2]) ||
+					('*' == p[i] && '|' == p[i + 2]) ||
+					('|' == p[i] && '*' == p[i + 2]))  {
+				if (italic)
+					printf("");
+				if (bold)
+					printf("");
+				italic = bold = 0;
+				putchar('*');
+				i += 2;
+				continue;
+			} else if (('|' == p[i] && '-' == p[i + 2]) ||
+					('-' == p[i] && '|' == p[i + 1]) ||
+					('+' == p[i] && '-' == p[i + 1]) ||
+					('-' == p[i] && '+' == p[i + 1]) ||
+					('+' == p[i] && '|' == p[i + 1]) ||
+					('|' == p[i] && '+' == p[i + 1]))  {
+				if (italic)
+					printf("");
+				if (bold)
+					printf("");
+				italic = bold = 0;
+				putchar('+');
+				i += 2;
+				continue;
+			}
+
+			/* Bold mode. */
+			
+			if (italic)
+				printf("");
+			if ( ! bold)
+				printf("");
+			bold = 1;
+			italic = 0;
+			i += 2;
+			html_putchar(p[i]);
+		}
+
+		/* 
+		 * Clean up the last character.
+		 * We can get to a newline; don't print that. 
+		 */
+
+		if (italic)
+			printf("");
+		if (bold)
+			printf("");
+
+		if (i == (int)len - 1 && '\n' != p[i])
+			html_putchar(p[i]);
+
+		putchar('\n');
+	}
+
+	puts("
\n" + "\n" + ""); + + fclose(f); } static void @@ -477,6 +713,7 @@ format(const char *file) struct man *man; void *vp; enum mandoclevel rc; + char opts[MAXPATHLEN + 128]; if (-1 == (fd = open(file, O_RDONLY, 0))) { resp_baddb(); @@ -492,8 +729,13 @@ format(const char *file) return; } + snprintf(opts, sizeof(opts), "style=/man.css," + "man=%s/search.html?sec=%%S&expr=%%N," + /*"includes=/cgi-bin/man.cgi/usr/include/%%I"*/, + progname); + mparse_result(mp, &mdoc, &man); - vp = html_alloc(NULL); + vp = html_alloc(opts); if (NULL != mdoc) { resp_begin_http(200, NULL); @@ -520,19 +762,19 @@ pg_show(const struct manpaths *ps, const struct req *r DBT key, val; if (NULL == path) { - resp_badmanual(); + resp_error400(); return; } else if (NULL == (sub = strrchr(path, '/'))) { - resp_badmanual(); + resp_error400(); return; } else *sub++ = '\0'; if ( ! (atou(path, &vol) && atou(sub, &rec))) { - resp_badmanual(); + resp_error400(); return; } else if (vol >= (unsigned int)ps->sz) { - resp_badmanual(); + resp_error400(); return; } @@ -551,7 +793,7 @@ pg_show(const struct manpaths *ps, const struct req *r key.size = 4; if (0 != (rc = (*idx->get)(idx, &key, &val, 0))) { - rc < 0 ? resp_baddb() : resp_badmanual(); + rc < 0 ? resp_baddb() : resp_error400(); goto out; } @@ -564,7 +806,7 @@ pg_show(const struct manpaths *ps, const struct req *r else if (NULL == memchr(fn, '\0', val.size - (fn - cp))) resp_baddb(); else { - strlcpy(file, ps->paths[vol], MAXPATHLEN); + strlcpy(file, cache, MAXPATHLEN); strlcat(file, "/", MAXPATHLEN); strlcat(file, fn, MAXPATHLEN); if (0 == strcmp(cp, "cat")) @@ -585,21 +827,17 @@ pg_search(const struct manpaths *ps, const struct req char **cp; struct opts opt; struct expr *expr; + struct query q; - expr = NULL; - cp = NULL; - ep = NULL; - sz = 0; - + kval_query(&q, req->fields, req->fieldsz); memset(&opt, 0, sizeof(struct opts)); - for (sz = i = 0; i < (int)req->fieldsz; i++) - if (0 == strcmp(req->fields[i].key, "expr")) - ep = req->fields[i].val; - else if (0 == strcmp(req->fields[i].key, "sec")) - opt.cat = req->fields[i].val; - else if (0 == strcmp(req->fields[i].key, "arch")) - opt.arch = req->fields[i].val; + ep = q.expr; + opt.arch = q.arch; + opt.cat = q.sec; + rc = -1; + sz = 0; + cp = NULL; /* * Poor man's tokenisation. @@ -622,14 +860,15 @@ pg_search(const struct manpaths *ps, const struct req ep++; } - rc = -1; - /* * Pump down into apropos backend. * The resp_search() function is called with the results. */ - if (NULL != (expr = exprcomp(sz, cp, &tt))) + expr = q.whatis ? termcomp(sz, cp, &tt) : + exprcomp(sz, cp, &tt); + + if (NULL != expr) rc = apropos_search (ps->sz, ps->paths, &opt, expr, tt, (void *)req, resp_search); @@ -639,7 +878,7 @@ pg_search(const struct manpaths *ps, const struct req if (0 == rc) resp_baddb(); else if (-1 == rc) - resp_badexpr(req); + resp_search(NULL, 0, (void *)req); for (i = 0; i < sz; i++) free(cp[i]); @@ -729,7 +968,7 @@ main(void) pg_show(&paths, &req, subpath); break; default: - resp_badpage(); + resp_error404(path); break; } @@ -738,3 +977,12 @@ main(void) return(EXIT_SUCCESS); } + +static int +cmp(const void *p1, const void *p2) +{ + + return(strcasecmp(((const struct res *)p1)->title, + ((const struct res *)p2)->title)); +} +