/* Reading/parsing the initialization file.
Copyright (C) 1996, 1997, 1998, 1999, 2000, 2001, 2002, 2003, 2004,
- 2005, 2006, 2007, 2008, 2009, 2010, 2011 Free Software Foundation,
+ 2005, 2006, 2007, 2008, 2009, 2010, 2011, 2012 Free Software Foundation,
Inc.
This file is part of GNU Wget.
as that of the covered work. */
#include "wget.h"
+#include "exits.h"
#include <stdio.h>
#include <stdlib.h>
# endif
#endif
+#include <regex.h>
+#ifdef HAVE_LIBPCRE
+# include <pcre.h>
+#endif
#ifdef HAVE_PWD_H
# include <pwd.h>
#include "res.h" /* for res_cleanup */
#include "http.h" /* for http_cleanup */
#include "retr.h" /* for output_stream */
+#include "warc.h" /* for warc_close */
#ifdef TESTING
#include "test.h"
CMD_DECLARE (cmd_number);
CMD_DECLARE (cmd_number_inf);
CMD_DECLARE (cmd_string);
+CMD_DECLARE (cmd_string_uppercase);
CMD_DECLARE (cmd_file);
CMD_DECLARE (cmd_directory);
CMD_DECLARE (cmd_time);
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);
+CMD_DECLARE (cmd_spec_report_speed);
#ifdef HAVE_SSL
CMD_DECLARE (cmd_spec_secure_protocol);
#endif
} 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 */
{ "backups", &opt.backups, cmd_number },
{ "base", &opt.base_href, cmd_string },
{ "bindaddress", &opt.bind_address, cmd_string },
+ { "bodydata", &opt.body_data, cmd_string },
+ { "bodyfile", &opt.body_file, cmd_string },
#ifdef HAVE_SSL
{ "cacertificate", &opt.ca_cert, cmd_file },
#endif
#ifdef ENABLE_DEBUG
{ "debug", &opt.debug, cmd_boolean },
#endif
- { "defaultpage", &opt.default_page, cmd_string},
+ { "defaultpage", &opt.default_page, cmd_string },
{ "deleteafter", &opt.delete_after, cmd_boolean },
{ "dirprefix", &opt.dir_prefix, cmd_directory },
{ "dirstruct", NULL, cmd_spec_dirstruct },
{ "httppasswd", &opt.http_passwd, cmd_string }, /* deprecated */
{ "httppassword", &opt.http_passwd, cmd_string },
{ "httpproxy", &opt.http_proxy, cmd_string },
+#ifdef HAVE_SSL
+ { "httpsonly", &opt.https_only, cmd_boolean },
+#endif
{ "httpsproxy", &opt.https_proxy, cmd_string },
{ "httpuser", &opt.http_user, cmd_string },
{ "ignorecase", &opt.ignore_case, cmd_boolean },
{ "logfile", &opt.lfilename, cmd_file },
{ "login", &opt.ftp_user, cmd_string },/* deprecated*/
{ "maxredirect", &opt.max_redirect, cmd_number },
+ { "method", &opt.method, cmd_string_uppercase },
{ "mirror", NULL, cmd_spec_mirror },
{ "netrc", &opt.netrc, cmd_boolean },
{ "noclobber", &opt.noclobber, cmd_boolean },
{ "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 },
+ { "reportspeed", &opt.report_bps, cmd_spec_report_speed},
{ "restrictfilenames", NULL, cmd_spec_restrict_file_names },
{ "retrsymlinks", &opt.retr_symlinks, cmd_boolean },
{ "retryconnrefused", &opt.retry_connrefused, cmd_boolean },
{ "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 },
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.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;
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)
run_wgetrc (const char *file)
{
FILE *fp;
- char *line;
+ char *line = NULL;
+ size_t bufsize = 0;
int ln;
int errcnt = 0;
return true; /* not a fatal error */
}
ln = 1;
- while ((line = read_whole_line (fp)) != NULL)
+ while (getline (&line, &bufsize, fp) > 0)
{
char *com = NULL, *val = NULL;
int comind;
}
xfree_null (com);
xfree_null (val);
- xfree (line);
++ln;
}
+ xfree (line);
fclose (fp);
return errcnt == 0;
return true;
}
+/* Like cmd_string but ensure the string is upper case. */
+static bool
+cmd_string_uppercase (const char *com, const char *val, void *place)
+{
+ char *q, **pstring;
+ pstring = (char **)place;
+ xfree_null (*pstring);
+
+ *pstring = xmalloc (strlen (val) + 1);
+
+ for (q = *pstring; *val; val++, q++)
+ *q = c_toupper (*val);
+
+ *q = '\0';
+ return true;
+}
+
-/* Like the above, but handles tilde-expansion when reading a user's
+/* Like cmd_string, but handles tilde-expansion when reading a user's
`.wgetrc'. In that case, and if VAL begins with `~', the tilde
gets expanded to the user's home directory. */
static bool
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)
{
return true;
}
+static bool
+cmd_spec_report_speed (const char *com, const char *val, void *place_ignored)
+{
+ opt.report_bps = strcasecmp (val, "bits") == 0;
+ if (!opt.report_bps)
+ fprintf (stderr, _("%s: %s: Invalid value %s.\n"), exec_name, com, quote (val));
+ return opt.report_bps;
+}
+
#ifdef HAVE_SSL
static bool
cmd_spec_secure_protocol (const char *com, const char *val, void *place)
\f
void cleanup_html_url (void);
+void spider_cleanup (void);
/* Free the memory allocated by global variables. */
{
/* Free external resources, close files, etc. */
+ /* Close WARC file. */
+ if (opt.warc_filename != 0)
+ warc_close ();
+
+ log_close ();
+
if (output_stream)
- fclose (output_stream);
+ if (fclose (output_stream) == EOF)
+ inform_exit_status (CLOSEFAILED);
+
/* No need to check for error because Wget flushes its output (and
checks for errors) after any data arrives. */
res_cleanup ();
http_cleanup ();
cleanup_html_url ();
+ spider_cleanup ();
host_cleanup ();
log_cleanup ();
+ for (i = 0; i < nurl; i++)
+ xfree (url[i]);
+
{
extern acc_t *netrc_list;
free_netrc (netrc_list);
xfree_null (opt.user);
xfree_null (opt.passwd);
xfree_null (opt.base_href);
+ xfree_null (opt.method);
#endif /* DEBUG_MALLOC */
}
projects / wget / blobdiff