X-Git-Url: http://sjero.net/git/?p=wget;a=blobdiff_plain;f=src%2Finit.c;h=b55aa968af14623d7854f38c6edc6c9524a8abf4;hp=ffdaa6d6a93c65fc1f7af6beb05b81287ab940fd;hb=96418c68851d00fd66014d2dc7bd46b3d715e525;hpb=8c7afaf3bb737e50bf289c2a2d60128425d1426b diff --git a/src/init.c b/src/init.c index ffdaa6d6..b55aa968 100644 --- a/src/init.c +++ b/src/init.c @@ -1,6 +1,7 @@ /* 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. @@ -33,9 +34,7 @@ as that of the covered work. */ #include #include #include -#ifdef HAVE_UNISTD_H -# include -#endif +#include #include #include #include @@ -47,6 +46,10 @@ as that of the covered work. */ # endif #endif +#include +#ifdef HAVE_LIBPCRE +# include +#endif #ifdef HAVE_PWD_H # include @@ -89,11 +92,13 @@ CMD_DECLARE (cmd_vector); 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); @@ -116,6 +121,7 @@ static const struct { } 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 */ @@ -140,6 +146,7 @@ static const struct { { "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 }, @@ -214,7 +221,7 @@ static const struct { { "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 }, @@ -234,10 +241,13 @@ static const struct { { "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 }, @@ -248,6 +258,7 @@ static const struct { { "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 }, @@ -263,6 +274,17 @@ static const struct { { "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 @@ -347,6 +369,8 @@ defaults (void) 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; @@ -360,6 +384,19 @@ defaults (void) 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; } /* Return the user's home directory (strdup-ed), or NULL if none is @@ -367,8 +404,8 @@ defaults (void) char * home_dir (void) { - static char buf[PATH_MAX]; - static char *home; + static char *buf = NULL; + static char *home, *ret; if (!home) { @@ -376,17 +413,28 @@ home_dir (void) 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 @@ -394,8 +442,7 @@ home_dir (void) 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 $HOME isn't defined, use the directory where `wget.exe' resides. */ @@ -404,7 +451,11 @@ home_dir (void) } } - return home ? xstrdup (home) : NULL; + ret = home ? xstrdup (home) : NULL; + if (buf) + free (buf); + + return ret; } /* Check the 'WGETRC' environment variable and return the file name @@ -428,7 +479,7 @@ wgetrc_env_file_name (void) return NULL; } -/* Check for the existance of '$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) @@ -582,11 +633,33 @@ initialize (void) 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 (); @@ -1197,6 +1270,27 @@ cmd_spec_header (const char *com, const char *val, void *place_ignored) 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) { @@ -1284,6 +1378,25 @@ cmd_spec_recursive (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) { @@ -1601,6 +1714,7 @@ cleanup (void) 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);