Dansguardian: Skip specified namespaces

400_xowa/src/gplx/xowa/Xoa_app_.java

@@ -31,7 +31,7 @@ public class Xoa_app_ {
 	}
 	public static final String		Name			= "xowa";
 	public static final int		Version_id		= 517;
-	public static final String		Version			= "4.3.1.1702";
+	public static final String		Version			= "4.3.2.1703";
 	public static String	Build_date		= "2012-12-30 00:00:00";
 	public static String	Build_date_fmt	= "yyyy-MM-dd HH:mm:ss";
 	public static String	Op_sys_str;

400_xowa/src/gplx/xowa/bldrs/filters/core/Xob_ttl_filter_mgr.java

@@ -17,7 +17,7 @@ package gplx.xowa.bldrs.filters.core; import gplx.*; import gplx.xowa.*; import
 import gplx.xowa.wikis.ttls.*;
 public class Xob_ttl_filter_mgr {
 	private boolean exclude_is_empty = true, include_is_empty = true;
-	private final Xob_ttl_filter_mgr_srl srl = new Xob_ttl_filter_mgr_srl();
+	private final    Xob_ttl_filter_mgr_srl srl = new Xob_ttl_filter_mgr_srl();
 	private Hash_adp_bry exclude_hash = Hash_adp_bry.cs(), include_hash = Hash_adp_bry.cs();
 	public void Clear() {
 		exclude_hash.Clear();

400_xowa/src/gplx/xowa/bldrs/filters/dansguardians/Dg_match_mgr.java

@@ -25,12 +25,14 @@ public class Dg_match_mgr {
 	private final    Ordered_hash rule_group_hash = Ordered_hash_.New_bry(), rule_tally_hash = Ordered_hash_.New_bry();
 	private final    Dg_parser parser = new Dg_parser();
 	private final    Xob_ttl_filter_mgr ttl_filter_mgr = new Xob_ttl_filter_mgr();
+	private final    Dg_ns_skip_mgr ns_skip_mgr = new Dg_ns_skip_mgr();
 	private final    Dg_log_mgr log_mgr = new Dg_log_mgr();
 	public Dg_match_mgr(Io_url root_dir, int score_init, int score_fail, boolean case_match, boolean log_enabled, Io_url log_url) {
 		this.score_init = score_init; this.score_fail = score_fail; this.case_match = case_match; this.log_enabled = log_enabled;
 		if (log_enabled) log_mgr.Init(log_url);
 		ttl_filter_mgr.Load(Bool_.N, root_dir.GenSubFil("xowa.title.include.txt"));
 		ttl_filter_mgr.Load(Bool_.Y, root_dir.GenSubFil("xowa.title.exclude.txt"));
+		ns_skip_mgr.Load(root_dir.GenSubFil("xowa.ns.skip.txt"));
 		Io_url dg_root_url = root_dir.GenSubDir("dansguardian");
 		Dg_file[] files = parser.Parse_dir(dg_root_url); Gfo_usr_dlg_.Instance.Plog_many("", "", "import.dg.rules: url=~{0} files=~{1}", dg_root_url, files.length);
 		Init_by_files(files);
@@ -77,6 +79,10 @@ public class Dg_match_mgr {
 		return rv;
 	}
 	public boolean Match(int log_tid, int page_id, int page_ns, byte[] page_ttl, byte[] page_ttl_db, Xol_lang_itm lang, byte[] src) {
+		// if ns is in skip_mgr, ignore; needed to skip Template and Module
+		if (ns_skip_mgr.Has(page_ns))
+			return false;
+
 		int src_len = src.length;
 		int clude_type = 0;
 		if		(ttl_filter_mgr.Match_include(page_ttl_db)) clude_type = -1;

400_xowa/src/gplx/xowa/bldrs/filters/dansguardians/Dg_ns_skip_mgr.java

@@ -0,0 +1,40 @@
+/*
+XOWA: the XOWA Offline Wiki Application
+Copyright (C) 2012-2017 gnosygnu@gmail.com
+
+XOWA is licensed under the terms of the General Public License (GPL) Version 3,
+or alternatively under the terms of the Apache License Version 2.0.
+
+You may use XOWA according to either of these licenses as is most appropriate
+for your project on a case-by-case basis.
+
+The terms of each license can be found in the source code repository:
+
+GPLv3 License: https://github.com/gnosygnu/xowa/blob/master/LICENSE-GPLv3.txt
+Apache License: https://github.com/gnosygnu/xowa/blob/master/LICENSE-APACHE2.txt
+*/
+package gplx.xowa.bldrs.filters.dansguardians; import gplx.*; import gplx.xowa.*; import gplx.xowa.bldrs.*; import gplx.xowa.bldrs.filters.*;
+import gplx.core.lists.hashs.*;
+class Dg_ns_skip_mgr {
+	private final    Hash_adp__int ns_hash = new Hash_adp__int();
+	private boolean is_empty = true;
+	public boolean Has(int ns) {return is_empty ? false : ns_hash.Get_by_or_null(ns) != null;}
+	public void Load(Io_url url) {
+		// load from file
+		Gfo_usr_dlg_.Instance.Log_many("", "", "loading ns.skip file; url=~{0}", url.Raw());
+		byte[] src = Io_mgr.Instance.LoadFilBry_loose(url);
+
+		// parse to lines
+		byte[][] lines = Bry_split_.Split_lines(src);
+
+		// add to hash
+		for (byte[] line : lines) {
+			int ns_id = Bry_.To_int_or(line, Int_.Max_value);
+			if (ns_id != Int_.Max_value) {
+				Gfo_usr_dlg_.Instance.Log_many("", "", "adding ns; ns_id=~{0}", ns_id);
+				ns_hash.Add_if_dupe_use_1st(ns_id, line);
+				is_empty = false;
+			}
+		}
+	}
+}