/* Reading/parsing the initialization file.
Copyright (C) 1996, 1997, 1998, 1999, 2000, 2001, 2002, 2003, 2004,
- 2005, 2006, 2007, 2008, 2009, 2010 Free Software Foundation, Inc.
+ 2005, 2006, 2007, 2008, 2009, 2010, 2011, 2012 Free Software Foundation,
+ Inc.
This file is part of GNU Wget.
#include <stdio.h>
#include <stdlib.h>
-#ifdef HAVE_UNISTD_H
-# include <unistd.h>
-#endif
+#include <stdbool.h>
+#include <unistd.h>
#include <string.h>
#include <errno.h>
#include <limits.h>
# endif
#endif
+#include <regex.h>
+#ifdef HAVE_LIBPCRE
+# include <pcre.h>
+#endif
#ifdef HAVE_PWD_H
# include <pwd.h>
CMD_DECLARE (cmd_spec_dirstruct);
CMD_DECLARE (cmd_spec_header);
+CMD_DECLARE (cmd_spec_warc_header);
CMD_DECLARE (cmd_spec_htmlify);
CMD_DECLARE (cmd_spec_mirror);
CMD_DECLARE (cmd_spec_prefer_family);
CMD_DECLARE (cmd_spec_progress);
CMD_DECLARE (cmd_spec_recursive);
+CMD_DECLARE (cmd_spec_regex_type);
CMD_DECLARE (cmd_spec_restrict_file_names);
#ifdef HAVE_SSL
CMD_DECLARE (cmd_spec_secure_protocol);
} commands[] = {
/* KEEP THIS LIST ALPHABETICALLY SORTED */
{ "accept", &opt.accepts, cmd_vector },
+ { "acceptregex", &opt.acceptregex_s, cmd_string },
{ "addhostdir", &opt.add_hostdir, cmd_boolean },
{ "adjustextension", &opt.adjust_extension, cmd_boolean },
{ "alwaysrest", &opt.always_rest, cmd_boolean }, /* deprecated */
{ "certificatetype", &opt.cert_type, cmd_cert_type },
{ "checkcertificate", &opt.check_cert, cmd_boolean },
#endif
+ { "chooseconfig", &opt.choose_config, cmd_file },
{ "connecttimeout", &opt.connect_timeout, cmd_time },
{ "contentdisposition", &opt.content_disposition, cmd_boolean },
+ { "contentonerror", &opt.content_on_error, cmd_boolean },
{ "continue", &opt.always_rest, cmd_boolean },
{ "convertlinks", &opt.convert_links, cmd_boolean },
{ "cookies", &opt.cookies, cmd_boolean },
{ "postdata", &opt.post_data, cmd_string },
{ "postfile", &opt.post_file_name, cmd_file },
{ "preferfamily", NULL, cmd_spec_prefer_family },
- { "preservepermissions", &opt.preserve_perm, cmd_boolean },/* deprecated */
+ { "preservepermissions", &opt.preserve_perm, cmd_boolean },
#ifdef HAVE_SSL
{ "privatekey", &opt.private_key, cmd_file },
{ "privatekeytype", &opt.private_key_type, cmd_cert_type },
{ "reclevel", &opt.reclevel, cmd_number_inf },
{ "recursive", NULL, cmd_spec_recursive },
{ "referer", &opt.referer, cmd_string },
+ { "regextype", &opt.regex_type, cmd_spec_regex_type },
{ "reject", &opt.rejects, cmd_vector },
+ { "rejectregex", &opt.rejectregex_s, cmd_string },
{ "relativeonly", &opt.relative_only, cmd_boolean },
{ "remoteencoding", &opt.encoding_remote, cmd_string },
{ "removelisting", &opt.remove_listing, cmd_boolean },
+ { "reportbps", &opt.report_bps, cmd_boolean},
{ "restrictfilenames", NULL, cmd_spec_restrict_file_names },
{ "retrsymlinks", &opt.retr_symlinks, cmd_boolean },
{ "retryconnrefused", &opt.retry_connrefused, cmd_boolean },
{ "secureprotocol", &opt.secure_protocol, cmd_spec_secure_protocol },
#endif
{ "serverresponse", &opt.server_response, cmd_boolean },
+ { "showalldnsentries", &opt.show_all_dns_entries, cmd_boolean },
{ "spanhosts", &opt.spanhost, cmd_boolean },
{ "spider", &opt.spider, cmd_boolean },
{ "strictcomments", &opt.strict_comments, cmd_boolean },
{ "verbose", NULL, cmd_spec_verbose },
{ "wait", &opt.wait, cmd_time },
{ "waitretry", &opt.waitretry, cmd_time },
+ { "warccdx", &opt.warc_cdx_enabled, cmd_boolean },
+ { "warccdxdedup", &opt.warc_cdx_dedup_filename, cmd_file },
+#ifdef HAVE_LIBZ
+ { "warccompression", &opt.warc_compression_enabled, cmd_boolean },
+#endif
+ { "warcdigests", &opt.warc_digests_enabled, cmd_boolean },
+ { "warcfile", &opt.warc_filename, cmd_file },
+ { "warcheader", NULL, cmd_spec_warc_header },
+ { "warckeeplog", &opt.warc_keep_log, cmd_boolean },
+ { "warcmaxsize", &opt.warc_maxsize, cmd_bytes },
+ { "warctempdir", &opt.warc_tempdir, cmd_directory },
#ifdef USE_WATT32
{ "wdebug", &opt.wdebug, cmd_boolean },
#endif
}
\f
/* Reset the variables to default values. */
-static void
+void
defaults (void)
{
char *tmp;
opt.restrict_files_nonascii = false;
opt.restrict_files_case = restrict_no_case_restriction;
+ opt.regex_type = regex_type_posix;
+
opt.max_redirect = 20;
opt.waitretry = 10;
opt.encoding_remote = NULL;
opt.useservertimestamps = true;
+ opt.show_all_dns_entries = false;
+
+ opt.warc_maxsize = 0; /* 1024 * 1024 * 1024; */
+#ifdef HAVE_LIBZ
+ opt.warc_compression_enabled = true;
+#else
+ opt.warc_compression_enabled = false;
+#endif
+ opt.warc_digests_enabled = true;
+ opt.warc_cdx_enabled = false;
+ opt.warc_cdx_dedup_filename = NULL;
+ opt.warc_tempdir = NULL;
+ opt.warc_keep_log = true;
}
\f
/* Return the user's home directory (strdup-ed), or NULL if none is
char *
home_dir (void)
{
- static char buf[PATH_MAX];
- static char *home;
+ static char *buf = NULL;
+ static char *home, *ret;
if (!home)
{
if (!home)
{
#if defined(MSDOS)
+ int len;
+
/* Under MSDOS, if $HOME isn't defined, use the directory where
`wget.exe' resides. */
const char *_w32_get_argv0 (void); /* in libwatt.a/pcconfig.c */
char *p;
- strcpy (buf, _w32_get_argv0 ());
+ buff = _w32_get_argv0 ();
+
p = strrchr (buf, '/'); /* djgpp */
if (!p)
p = strrchr (buf, '\\'); /* others */
assert (p);
- *p = '\0';
+
+ len = p - buff + 1;
+ buff = malloc (len + 1);
+ if (buff == NULL)
+ return NULL;
+
+ strncpy (buff, _w32_get_argv0 (), len);
+ buff[len] = '\0';
+
home = buf;
#elif !defined(WINDOWS)
/* If HOME is not defined, try getting it from the password
struct passwd *pwd = getpwuid (getuid ());
if (!pwd || !pwd->pw_dir)
return NULL;
- strcpy (buf, pwd->pw_dir);
- home = buf;
+ home = pwd->pw_dir;
#else /* !WINDOWS */
/* Under Windows, if $HOME isn't defined, use the directory where
`wget.exe' resides. */
}
}
- return home ? xstrdup (home) : NULL;
+ ret = home ? xstrdup (home) : NULL;
+ if (buf)
+ free (buf);
+
+ return ret;
}
/* Check the 'WGETRC' environment variable and return the file name
return NULL;
}
-/* Check for the existance of '$HOME/.wgetrc' and return it's path
+/* Check for the existance of '$HOME/.wgetrc' and return its path
if it exists and is set. */
char *
wgetrc_user_file_name (void)
{
- char *home = home_dir ();
+ char *home;
char *file = NULL;
/* If that failed, try $HOME/.wgetrc (or equivalent). */
/* Initialize variables from a wgetrc file. Returns zero (failure) if
there were errors in the file. */
-static bool
+bool
run_wgetrc (const char *file)
{
FILE *fp;
initialize (void)
{
char *file, *env_sysrc;
- int ok = true;
-
- /* Load the hard-coded defaults. */
- defaults ();
+ bool ok = true;
/* Run a non-standard system rc file when the according environment
variable has been set. For internal testing purposes only! */
env_sysrc = getenv ("SYSTEM_WGETRC");
if (env_sysrc && file_exists_p (env_sysrc))
- ok &= run_wgetrc (env_sysrc);
+ {
+ ok &= run_wgetrc (env_sysrc);
+ /* If there are any problems parsing the system wgetrc file, tell
+ the user and exit */
+ if (! ok)
+ {
+ fprintf (stderr, _("\
+Parsing system wgetrc file (env SYSTEM_WGETRC) failed. Please check\n\
+'%s',\n\
+or specify a different file using --config.\n"), env_sysrc);
+ exit (2);
+ }
+ }
/* Otherwise, if SYSTEM_WGETRC is defined, use it. */
#ifdef SYSTEM_WGETRC
else if (file_exists_p (SYSTEM_WGETRC))
ok &= run_wgetrc (SYSTEM_WGETRC);
+ /* If there are any problems parsing the system wgetrc file, tell
+ the user and exit */
+ if (! ok)
+ {
+ fprintf (stderr, _("\
+Parsing system wgetrc file failed. Please check\n\
+'%s',\n\
+or specify a different file using --config.\n"), SYSTEM_WGETRC);
+ exit (2);
+ }
#endif
/* Override it with your own, if one exists. */
file = wgetrc_file_name ();
return true;
}
+static bool
+cmd_spec_warc_header (const char *com, const char *val, void *place_ignored)
+{
+ /* Empty value means reset the list of headers. */
+ if (*val == '\0')
+ {
+ free_vec (opt.warc_user_headers);
+ opt.warc_user_headers = NULL;
+ return true;
+ }
+
+ if (!check_user_specified_header (val))
+ {
+ fprintf (stderr, _("%s: %s: Invalid WARC header %s.\n"),
+ exec_name, com, quote (val));
+ return false;
+ }
+ opt.warc_user_headers = vec_append (opt.warc_user_headers, val);
+ return true;
+}
+
static bool
cmd_spec_htmlify (const char *com, const char *val, void *place_ignored)
{
return true;
}
+/* Validate --regex-type and set the choice. */
+
+static bool
+cmd_spec_regex_type (const char *com, const char *val, void *place_ignored)
+{
+ static const struct decode_item choices[] = {
+ { "posix", regex_type_posix },
+#ifdef HAVE_LIBPCRE
+ { "pcre", regex_type_pcre },
+#endif
+ };
+ int regex_type = regex_type_posix;
+ int ok = decode_string (val, choices, countof (choices), ®ex_type);
+ if (!ok)
+ fprintf (stderr, _("%s: %s: Invalid value %s.\n"), exec_name, com, quote (val));
+ opt.regex_type = regex_type;
+ return ok;
+}
+
static bool
cmd_spec_restrict_file_names (const char *com, const char *val, void *place_ignored)
{
extern acc_t *netrc_list;
free_netrc (netrc_list);
}
+ xfree_null (opt.choose_config);
xfree_null (opt.lfilename);
xfree_null (opt.dir_prefix);
xfree_null (opt.input_filename);
xfree_null (opt.http_user);
xfree_null (opt.http_passwd);
free_vec (opt.user_headers);
+ free_vec (opt.warc_user_headers);
# ifdef HAVE_SSL
xfree_null (opt.cert_file);
xfree_null (opt.private_key);
projects / wget / blobdiff