github-repos/wget
1
0
Fork 0
mirror of https://github.com/mirror/wget.git synced 2025-01-27 12:50:13 +08:00
Code Issues Packages Projects Releases Wiki Activity

Improved exit status handling.

Browse Source
This commit is contained in:
Micah Cowan 2009-08-27 23:08:58 -07:00
parent 88253c0d00
commit b014f8fae9
23 changed files with 232 additions and 33 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
ChangeLog
View File

@ -1,3 +1,7 @@
2009-08-27 Micah Cowan <micah@cowan.name>
* NEWS: Mention the changes to exit codes.
2009-08-27 Micah Cowan <micah@cowan.name>
* NEWS: Add mention of the NUL characters SSL security fix.

3
NEWS
View File

@ -32,6 +32,9 @@ are translated from their source encoding to UTF-8 before percent-encoding.
IRI support was added by Saint Xavier <wget@sxav.eu>, as his
project for the Google Summer of Code.
** Wget now provides more sensible exit status codes when downloads
don't proceed as expected (see the manual).
** --default-page option (and associated wgetrc command) added to
support alternative default names for index.html.

25
src/ChangeLog
View File

@ -1,3 +1,28 @@
2009-08-27 Micah Cowan <micah@cowan.name>
* wget.h (uerr_t): added new VERIFCERTERR code for SSL certificate
problems. Marked exit codes that are defined but never used (at
least, the ones I could find).
* retr.c, retr.h (retrieve_url): Added a new boolean argument to
determine whether an exit status should be recorded.
(retrieve_from_file): Adjust to new retrieve_url signature.
* res.c (res_retrieve_file): Don't have retrieve_url record an
exit status for robots.txt.
* recur.c (retrieve_tree): Adjust to new retrieve_url signature.
* main.c (main): Use the exit status stored by retrieve_url.
* http.c (gethttp): Distinguish certificate verification problems
from SSL connection issues.
(http_loop): Handle newly-created VERIFCERTERR error code.
* exits.c, exits.h: Newly added.
* Makefile.am (wget_SOURCES): Add exits.c and exits.h.
2009-08-27 Micah Cowan <micah@cowan.name>
* http.c (gethttp): Make sure Wget heeds cookies when they

3
src/Makefile.am
View File

@ -49,7 +49,8 @@ wget_SOURCES = cmpt.c connect.c convert.c cookies.c ftp.c \
ftp.h gen-md5.h hash.h host.h html-parse.h html-url.h \
http.h http-ntlm.h init.h log.h mswindows.h netrc.h \
options.h progress.h ptimer.h recur.h res.h retr.h \
spider.h ssl.h sysdep.h url.h utils.h wget.h iri.h
spider.h ssl.h sysdep.h url.h utils.h wget.h iri.h \
exits.c exits.h
nodist_wget_SOURCES = build_info.c version.c
EXTRA_wget_SOURCES = mswindows.c iri.c
LDADD = $(LIBOBJS) ../lib/libgnu.a @MD5_LDADD@

111
src/exits.c Normal file
View File

@ -0,0 +1,111 @@
/* Command line parsing.
Copyright (C) 1996, 1997, 1998, 1999, 2000, 2001, 2002, 2003,
2004, 2005, 2006, 2007, 2008, 2009 Free Software Foundation, Inc.
This file is part of GNU Wget.
GNU Wget is free software; you can redistribute it and/or modify
it under the terms of the GNU General Public License as published by
the Free Software Foundation; either version 3 of the License, or
(at your option) any later version.
GNU Wget is distributed in the hope that it will be useful,
but WITHOUT ANY WARRANTY; without even the implied warranty of
MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
GNU General Public License for more details.
You should have received a copy of the GNU General Public License
along with Wget. If not, see <http://www.gnu.org/licenses/>.
*/
#include "wget.h"
#include "exits.h"
/* Final exit code possibilities. Exit codes 1 and 2 are reserved
* for situations that lead to direct exits from Wget, not using the
* value of final_exit_status. */
enum
{
WGET_EXIT_SUCCESS = 0,
WGET_EXIT_MINIMUM = 3,
WGET_EXIT_IO_FAIL = WGET_EXIT_MINIMUM,
WGET_EXIT_NETWORK_FAIL = 4,
WGET_EXIT_SSL_AUTH_FAIL = 5,
WGET_EXIT_SERVER_AUTH_FAIL = 6,
WGET_EXIT_PROTOCOL_ERROR = 7,
WGET_EXIT_SERVER_ERROR = 8,
WGET_EXIT_UNKNOWN
};
static int final_exit_status = WGET_EXIT_SUCCESS;
/* XXX: I don't like that newly-added uerr_t codes will doubtless fall
through the craccks, or the fact that we seem to have way more
codes than we know what to do with. Need to go through and sort
through the truly essential codes, and merge the rest with
those. Quite a few are never even used!
Quite a few of the codes below would have no business being
returned to retrieve_url's caller, but since it's very difficult to
determine which do and which don't, I grab virtually all of them to
be safe. */
static int
get_status_for_err (uerr_t err)
{
switch (err)
{
case RETROK:
return WGET_EXIT_SUCCESS;
case FOPENERR: case FOPEN_EXCL_ERR: case FWRITEERR: case WRITEFAILED:
return WGET_EXIT_IO_FAIL;
case NOCONERROR: case HOSTERR: case CONSOCKERR: case CONERROR:
case CONSSLERR: case CONIMPOSSIBLE: case FTPRERR: case FTPINVPASV:
case READERR: case TRYLIMEXC:
return WGET_EXIT_NETWORK_FAIL;
case VERIFCERTERR:
return WGET_EXIT_SSL_AUTH_FAIL;
case FTPLOGINC: case FTPLOGREFUSED: case AUTHFAILED:
return WGET_EXIT_SERVER_AUTH_FAIL;
case HEOF: case HERR:
return WGET_EXIT_PROTOCOL_ERROR;
case WRONGCODE: case FTPPORTERR: case FTPSYSERR:
case FTPNSFOD: case FTPUNKNOWNTYPE: case FTPSRVERR:
case FTPRETRINT: case FTPRESTFAIL: case FTPNOPASV:
case CONTNOTSUPPORTED: case RANGEERR: case RETRBADPATTERN:
case PROXERR:
return WGET_EXIT_SERVER_ERROR;
case URLERROR: case QUOTEXC: case SSLINITFAILED:
default:
return WGET_EXIT_UNKNOWN;
}
}
/* inform_exit_status
*
* Ensure that Wget's exit status will reflect the problem indicated
* by ERR, unless the exit status has already been set to reflect a more
* important problem. */
void
inform_exit_status (uerr_t err)
{
int new_status = get_status_for_err (err);
if (new_status != WGET_EXIT_SUCCESS
&& (final_exit_status == WGET_EXIT_SUCCESS
|| new_status < final_exit_status))
{
final_exit_status = new_status;
}
}
int
get_exit_status (void)
{
return
(final_exit_status == WGET_EXIT_UNKNOWN)
? 1
: final_exit_status;
}

30
src/exits.h Normal file
View File

@ -0,0 +1,30 @@
/* Internationalization related declarations.
Copyright (C) 2008 Free Software Foundation, Inc.
This file is part of GNU Wget.
GNU Wget is free software; you can redistribute it and/or modify
it under the terms of the GNU General Public License as published by
the Free Software Foundation; either version 3 of the License, or
(at your option) any later version.
GNU Wget is distributed in the hope that it will be useful,
but WITHOUT ANY WARRANTY; without even the implied warranty of
MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
GNU General Public License for more details.
You should have received a copy of the GNU General Public License
along with Wget. If not, see <http://www.gnu.org/licenses/>. */
#ifndef WGET_EXITS_H
#define WGET_EXITS_H
#include "wget.h"
void inform_exit_status (uerr_t err);
int get_exit_status (void);
#endif /* WGET_EXITS_H */

9
src/http.c
View File

@ -1762,11 +1762,16 @@ gethttp (struct url *u, struct http_stat *hs, int *dt, struct url *proxy,
if (conn->scheme == SCHEME_HTTPS)
{
if (!ssl_connect_wget (sock) || !ssl_check_certificate (sock, u->host))
if (!ssl_connect_wget (sock))
{
fd_close (sock);
return CONSSLERR;
}
else if (!ssl_check_certificate (sock, u->host))
{
fd_close (sock);
return VERIFCERTERR;
}
using_ssl = true;
}
#endif /* HAVE_SSL */
@ -2598,7 +2603,7 @@ Spider mode enabled. Check if remote file exists.\n"));
logprintf (LOG_NOTQUIET, _("Cannot write to %s (%s).\n"),
quote (hstat.local_file), strerror (errno));
case HOSTERR: case CONIMPOSSIBLE: case PROXERR: case AUTHFAILED:
case SSLINITFAILED: case CONTNOTSUPPORTED:
case SSLINITFAILED: case CONTNOTSUPPORTED: case VERIFCERTERR:
/* Fatal errors just return from the function. */
ret = err;
goto exit;

8
src/main.c
View File

@ -44,6 +44,7 @@ as that of the covered work. */
#include <errno.h>
#include <time.h>
#include "exits.h"
#include "utils.h"
#include "init.h"
#include "retr.h"
@ -1289,7 +1290,7 @@ WARNING: Can't reopen standard output in binary mode;\n\
else
{
status = retrieve_url (url_parsed, *t, &filename, &redirected_URL,
NULL, &dt, opt.recursive, iri);
NULL, &dt, opt.recursive, iri, true);
}
if (opt.delete_after && file_exists_p(filename))
@ -1354,10 +1355,7 @@ WARNING: Can't reopen standard output in binary mode;\n\
xfree (url[i]);
cleanup ();
if (status == RETROK)
return 0;
else
return 1;
return get_exit_status ();
}
#endif /* TESTING */

2
src/recur.c
View File

@ -283,7 +283,7 @@ retrieve_tree (struct url *start_url_parsed, struct iri *pi)
struct url *url_parsed = url_parse (url, &url_err, i, true);
status = retrieve_url (url_parsed, url, &file, &redirected, referer,
&dt, false, i);
&dt, false, i, true);
if (html_allowed && file && status == RETROK
&& (dt & RETROKF) && (dt & TEXTHTML))

2
src/res.c
View File

@ -562,7 +562,7 @@ res_retrieve_file (const char *url, char **file, struct iri *iri)
else
{
err = retrieve_url (url_parsed, robots_url, file, NULL, NULL, NULL,
false, i);
false, i, false);
url_free(url_parsed);
}

22
src/retr.c
View File

@ -39,6 +39,7 @@ as that of the covered work. */
#include <string.h>
#include <assert.h>
#include "exits.h"
#include "utils.h"
#include "retr.h"
#include "progress.h"
@ -611,7 +612,7 @@ static char *getproxy (struct url *);
uerr_t
retrieve_url (struct url * orig_parsed, const char *origurl, char **file,
char **newloc, const char *refurl, int *dt, bool recursive,
struct iri *iri)
struct iri *iri, bool register_status)
{
uerr_t result;
char *url;
@ -668,7 +669,8 @@ retrieve_url (struct url * orig_parsed, const char *origurl, char **file,
xfree (url);
xfree (error);
RESTORE_POST_DATA;
return PROXERR;
result = PROXERR;
goto bail;
}
if (proxy_url->scheme != SCHEME_HTTP && proxy_url->scheme != u->scheme)
{
@ -676,7 +678,8 @@ retrieve_url (struct url * orig_parsed, const char *origurl, char **file,
url_free (proxy_url);
xfree (url);
RESTORE_POST_DATA;
return PROXERR;
result = PROXERR;
goto bail;
}
}
@ -757,7 +760,7 @@ retrieve_url (struct url * orig_parsed, const char *origurl, char **file,
xfree (mynewloc);
xfree (error);
RESTORE_POST_DATA;
return result;
goto bail;
}
/* Now mynewloc will become newloc_parsed->url, because if the
@ -779,7 +782,8 @@ retrieve_url (struct url * orig_parsed, const char *origurl, char **file,
xfree (url);
xfree (mynewloc);
RESTORE_POST_DATA;
return WRONGCODE;
result = WRONGCODE;
goto bail;
}
xfree (url);
@ -866,6 +870,9 @@ retrieve_url (struct url * orig_parsed, const char *origurl, char **file,
RESTORE_POST_DATA;
bail:
if (register_status)
inform_exit_status (result);
return result;
}
@ -910,7 +917,7 @@ retrieve_from_file (const char *file, bool html, int *count)
opt.base_href = xstrdup (url);
status = retrieve_url (url_parsed, url, &input_file, NULL, NULL, &dt,
false, iri);
false, iri, true);
if (status != RETROK)
return status;
@ -970,7 +977,8 @@ retrieve_from_file (const char *file, bool html, int *count)
else
status = retrieve_url (parsed_url ? parsed_url : cur_url->url,
cur_url->url->url, &filename,
&new_file, NULL, &dt, opt.recursive, tmpiri);
&new_file, NULL, &dt, opt.recursive, tmpiri,
true);
if (parsed_url)
url_free (parsed_url);

2
src/retr.h
View File

@ -54,7 +54,7 @@ char *fd_read_hunk (int, hunk_terminator_t, long, long);
char *fd_read_line (int);
uerr_t retrieve_url (struct url *, const char *, char **, char **,
const char *, int *, bool, struct iri *);
const char *, int *, bool, struct iri *, bool);
uerr_t retrieve_from_file (const char *, bool, int *);
const char *retr_rate (wgint, double);

16
src/wget.h
View File

@ -331,21 +331,23 @@ typedef enum
{
/* 0 */
NOCONERROR, HOSTERR, CONSOCKERR, CONERROR, CONSSLERR,
CONIMPOSSIBLE, NEWLOCATION, NOTENOUGHMEM, CONPORTERR, CONCLOSED,
CONIMPOSSIBLE, NEWLOCATION, NOTENOUGHMEM /* ! */,
CONPORTERR /* ! */, CONCLOSED /* ! */,
/* 10 */
FTPOK, FTPLOGINC, FTPLOGREFUSED, FTPPORTERR, FTPSYSERR,
FTPNSFOD, FTPRETROK, FTPUNKNOWNTYPE, FTPRERR, FTPREXC,
FTPNSFOD, FTPRETROK /* ! */, FTPUNKNOWNTYPE, FTPRERR, FTPREXC /* ! */,
/* 20 */
FTPSRVERR, FTPRETRINT, FTPRESTFAIL, URLERROR, FOPENERR,
FOPEN_EXCL_ERR, FWRITEERR, HOK, HLEXC, HEOF,
FOPEN_EXCL_ERR, FWRITEERR, HOK /* ! */, HLEXC /* ! */, HEOF,
/* 30 */
HERR, RETROK, RECLEVELEXC, FTPACCDENIED, WRONGCODE,
HERR, RETROK, RECLEVELEXC, FTPACCDENIED /* ! */, WRONGCODE,
FTPINVPASV, FTPNOPASV, CONTNOTSUPPORTED, RETRUNNEEDED, RETRFINISHED,
/* 40 */
READERR, TRYLIMEXC, URLBADPATTERN, FILEBADFILE, RANGEERR,
RETRBADPATTERN, RETNOTSUP, ROBOTSOK, NOROBOTS, PROXERR,
READERR, TRYLIMEXC, URLBADPATTERN /* ! */, FILEBADFILE /* ! */, RANGEERR,
RETRBADPATTERN, RETNOTSUP /* ! */, ROBOTSOK /* ! */, NOROBOTS /* ! */,
PROXERR,
/* 50 */
AUTHFAILED, QUOTEXC, WRITEFAILED, SSLINITFAILED
AUTHFAILED, QUOTEXC, WRITEFAILED, SSLINITFAILED, VERIFCERTERR
} uerr_t;
/* 2005-02-19 SMS.

11
tests/ChangeLog
View File

@ -1,3 +1,14 @@
2009-08-27 Micah Cowan <micah@cowan.name>
* WgetTest.pm.in (run): Shift the errcode right by 8 binary places.
* Test--spider-fail.px, Test--spider-r--no-content-disposition.px,
Test--spider-r--no-content-disposition-trivial.px,
Test--spider-r-HTTP-Content-Disposition.px, Test--spider-r.px,
Test-O-nonexisting.px, Test-cookies-401.px,
Test-nonexisting-quiet.px: Adjusted "expected error code"; Wget's
exit codes have changed.
2009-08-27 Micah Cowan <micah@cowan.name>
* run-px: Added Test-cookies.px, Test-cookies-401.px

2
tests/Test--spider-fail.px
View File

@ -35,7 +35,7 @@ my %urls = (
my $cmdline = $WgetTest::WGETPATH . " --spider http://localhost:{{port}}/nonexistent";
my $expected_error_code = 256;
my $expected_error_code = 8;
my %expected_downloaded_files = (
);

2
tests/Test--spider-r--no-content-disposition-trivial.px
View File

@ -92,7 +92,7 @@ my %urls = (
my $cmdline = $WgetTest::WGETPATH . " --spider -r --no-content-disposition http://localhost:{{port}}/";
my $expected_error_code = 0;
my $expected_error_code = 8;
my %expected_downloaded_files = (
);

2
tests/Test--spider-r--no-content-disposition.px
View File

@ -93,7 +93,7 @@ my %urls = (
my $cmdline = $WgetTest::WGETPATH . " --spider -r --no-content-disposition http://localhost:{{port}}/";
my $expected_error_code = 0;
my $expected_error_code = 8;
my %expected_downloaded_files = (
);

2
tests/Test--spider-r-HTTP-Content-Disposition.px
View File

@ -93,7 +93,7 @@ my %urls = (
my $cmdline = $WgetTest::WGETPATH . " --spider -r http://localhost:{{port}}/";
my $expected_error_code = 0;
my $expected_error_code = 8;
my %expected_downloaded_files = (
);

2
tests/Test--spider-r.px
View File

@ -92,7 +92,7 @@ my %urls = (
my $cmdline = $WgetTest::WGETPATH . " --spider -r http://localhost:{{port}}/";
my $expected_error_code = 0;
my $expected_error_code = 8;
my %expected_downloaded_files = (
);

2
tests/Test-O-nonexisting.px
View File

@ -26,7 +26,7 @@ my %urls = (
my $cmdline = $WgetTest::WGETPATH . " --quiet -O out http://localhost:{{port}}/nonexistent";
my $expected_error_code = 256;
my $expected_error_code = 8;
my %expected_downloaded_files = (
'out' => {

2
tests/Test-cookies-401.px
View File

@ -32,7 +32,7 @@ my %urls = (
my $cmdline = $WgetTest::WGETPATH . " -d http://localhost:{{port}}/one.txt"
. " http://localhost:{{port}}/two.txt";
my $expected_error_code = 0;
my $expected_error_code = 6;
my %expected_downloaded_files = (
'two.txt' => {

2
tests/Test-nonexisting-quiet.px
View File

@ -26,7 +26,7 @@ my %urls = (
my $cmdline = $WgetTest::WGETPATH . " --quiet http://localhost:{{port}}/nonexistent";
my $expected_error_code = 256;
my $expected_error_code = 8;
my %expected_downloaded_files = (
);

1
tests/WgetTest.pm.in
View File

@ -88,6 +88,7 @@ sub run {
($cmdline =~ m{^/.*})
? system ($cmdline)
: system ("$self->{_workdir}/../src/$cmdline");
$errcode >>= 8; # XXX: should handle abnormal error codes.
# Shutdown server
# if we didn't explicitely kill the server, we would have to call