Archives/gnosygnu_xowa
1
0
Fork 0
mirror of https://github.com/gnosygnu/xowa.git synced 2026-03-02 03:49:30 +00:00
Code Issues Projects Releases Wiki Activity

v2.7.3.3

Browse Source
This commit is contained in:
gnosygnu
2015-07-21 19:52:26 -04:00
parent 99f9c3ccea
commit 9d63f03b3d
31 changed files with 381 additions and 446 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
400_xowa/src/gplx/xowa/Xoa_app_.java
View File

@@ -26,7 +26,7 @@ public class Xoa_app_ {
boot_mgr.Run(args);
}
public static final String Name = "xowa";
public static final String Version = "2.7.3.2";
public static final String Version = "2.7.3.3";
public static String Build_date = "2012-12-30 00:00:00";
public static String Op_sys;
public static String User_agent = "";

6
400_xowa/src/gplx/xowa/html/Xoh_page_wtr_wkr.java
View File

@@ -117,13 +117,15 @@ public class Xoh_page_wtr_wkr implements Bry_fmtr_arg {
bfr.Add(gplx.xowa.apps.Xoa_gfs_php_mgr.Xto_php(tmp_bfr, Bool_.N, data_raw));
return;
}
Xol_vnt_mgr vnt_mgr = wiki.Lang().Vnt_mgr();
if (ns_id == Xow_ns_.Id_file) // if [[File]], add boilerplate header
app.Ns_file_page_mgr().Bld_html(wiki, ctx, page, bfr, page.Ttl(), wiki.Cfg_file_page(), page.File_queue());
gplx.xowa.html.tidy.Xoh_tidy_mgr tidy_mgr = app.Html_mgr().Tidy_mgr();
boolean tidy_enabled = tidy_mgr.Enabled();
Bry_bfr hdom_bfr = tidy_enabled ? app.Utl__bfr_mkr().Get_m001() : bfr; // if tidy, then write to tidy_bfr; note that bfr already has <html> and <head> written to it, so this can't be passed to tidy; DATE:2014-06-11
wiki.Html_mgr().Html_wtr().Write_all(hdom_bfr, page.Wikie().Ctx(), hctx, page.Root().Data_mid(), page.Root());
// Xol_vnt_mgr vnt_mgr = wiki.Lang().Vnt_mgr();
// if (vnt_mgr.Enabled()) // VNT
// hdom_bfr.Add(vnt_mgr.Convert_text(wiki, hdom_bfr.Xto_bry_and_clear()));
if (tidy_enabled) {
tidy_mgr.Run_tidy_html(page, hdom_bfr);
bfr.Add_bfr_and_clear(hdom_bfr);
@@ -143,8 +145,6 @@ public class Xoh_page_wtr_wkr implements Bry_fmtr_arg {
else
wiki.Html_mgr().Ctg_mgr().Bld(bfr, page, ctgs_len);
}
if (vnt_mgr.Enabled()) // VNT
bfr.Add(vnt_mgr.Convert_text(wiki, bfr.Xto_bry_and_clear()));
}
private void Write_body_pre(Bry_bfr bfr, Xoae_app app, Xowe_wiki wiki, byte[] data_raw, Bry_bfr tmp_bfr) {
Xoh_html_wtr_escaper.Escape(app.Parser_amp_mgr(), tmp_bfr, data_raw, 0, data_raw.length, false, false);

2
400_xowa/src/gplx/xowa/wikis/Xoa_wiki_regy.java
View File

@@ -39,7 +39,7 @@ public class Xoa_wiki_regy {
}
init_needed = true;
}
public static void Make_wiki_dir(Xoae_app app, String domain_str) { // TEST: fake wiki_dir for Parse_from_url_bar; DATE:2014-02-16
public static void Make_wiki_dir(Xoa_app app, String domain_str) { // TEST: fake wiki_dir for Parse_from_url_bar; DATE:2014-02-16
Io_url wiki_dir = app.Fsys_mgr().Wiki_dir();
Io_mgr.I.CreateDir(wiki_dir.GenSubDir(domain_str));
}

48
400_xowa/src/gplx/xowa/xtns/scribunto/libs/Scrib_lib_ustring.java
View File

@@ -16,7 +16,7 @@ You should have received a copy of the GNU Affero General Public License
along with this program. If not, see <http://www.gnu.org/licenses/>.
*/
package gplx.xowa.xtns.scribunto.libs; import gplx.*; import gplx.xowa.*; import gplx.xowa.xtns.*; import gplx.xowa.xtns.scribunto.*;
import gplx.texts.*; import gplx.intl.*;
import gplx.core.regxs.*; import gplx.intl.*;
public class Scrib_lib_ustring implements Scrib_lib {
private final String_surrogate_utl surrogate_utl = new String_surrogate_utl();
public Scrib_lib_ustring(Scrib_core core) {this.core = core; gsub_mgr = new Scrib_lib_ustring_gsub_mgr(core, regx_converter);} private Scrib_core core; Scrib_lib_ustring_gsub_mgr gsub_mgr;
@@ -69,12 +69,12 @@ public class Scrib_lib_ustring implements Scrib_lib {
;
}
regx = regx_converter.Parse(Bry_.new_u8(regx), Scrib_regx_converter.Anchor_G);
RegxAdp regx_adp = Scrib_lib_ustring.RegxAdp_new_(core.Ctx(), regx);
RegxMatch[] regx_rslts = regx_adp.Match_all(text_str, bgn_codepoint_idx); // NOTE: MW calculates an offset to handle mb strings. however, java's regex always takes offset in chars (not bytes like PHP preg_match); DATE:2014-03-04
Regx_adp regx_adp = Scrib_lib_ustring.RegxAdp_new_(core.Ctx(), regx);
Regx_match[] regx_rslts = regx_adp.Match_all(text_str, bgn_codepoint_idx); // NOTE: MW calculates an offset to handle mb strings. however, java's regex always takes offset in chars (not bytes like PHP preg_match); DATE:2014-03-04
int len = regx_rslts.length;
if (len == 0) return rslt.Init_ary_empty();
List_adp tmp_list = List_adp_.new_();
RegxMatch match = regx_rslts[0]; // NOTE: take only 1st result; DATE:2014-08-27
Regx_match match = regx_rslts[0]; // NOTE: take only 1st result; DATE:2014-08-27
int match_find_bgn_codepoint = match.Find_bgn(); // NOTE: java regex returns results in codepoint; PAGE:zh.w:南北鐵路 (越南) DATE:2014-08-27
int match_find_bgn_adj = -surrogate_utl.Count_surrogates__codepoint_idx1(text_bry, text_bry_len, bgn_byte_pos, match_find_bgn_codepoint - bgn_codepoint_idx); // NOTE: convert from java regex codepoint to lua / php char_idx; PAGE:zh.w:南北鐵路 (越南) DATE:2014-08-27
tmp_list.Add(match_find_bgn_codepoint + match_find_bgn_adj + -bgn_adj + Scrib_lib_ustring.Base1);
@@ -100,13 +100,13 @@ public class Scrib_lib_ustring implements Scrib_lib {
String regx = regx_converter.Parse(args.Cast_bry_or_null(1), Scrib_regx_converter.Anchor_G);
int bgn = args.Cast_int_or(2, 1);
bgn = Bgn_adjust(text, bgn);
RegxAdp regx_adp = Scrib_lib_ustring.RegxAdp_new_(core.Ctx(), regx);
RegxMatch[] regx_rslts = regx_adp.Match_all(text, bgn);
Regx_adp regx_adp = Scrib_lib_ustring.RegxAdp_new_(core.Ctx(), regx);
Regx_match[] regx_rslts = regx_adp.Match_all(text, bgn);
int len = regx_rslts.length;
if (len == 0) return rslt.Init_null(); // return null if no matches found; EX:w:Mount_Gambier_(volcano); DATE:2014-04-02; confirmed with en.d:民; DATE:2015-01-30
List_adp tmp_list = List_adp_.new_();
for (int i = 0; i < len; i++) {
RegxMatch match = regx_rslts[i];
Regx_match match = regx_rslts[i];
AddCapturesFromMatch(tmp_list, match, text, regx_converter.Capt_ary(), true);
}
return rslt.Init_many_list(tmp_list);
@@ -123,22 +123,22 @@ public class Scrib_lib_ustring implements Scrib_lib {
String regx = args.Pull_str(1);
KeyVal[] capt = args.Cast_kv_ary_or_null(2);
int pos = args.Pull_int(3);
RegxAdp regx_adp = Scrib_lib_ustring.RegxAdp_new_(core.Ctx(), regx);
RegxMatch[] regx_rslts = regx_adp.Match_all(text, pos);
Regx_adp regx_adp = Scrib_lib_ustring.RegxAdp_new_(core.Ctx(), regx);
Regx_match[] regx_rslts = regx_adp.Match_all(text, pos);
int len = regx_rslts.length;
if (len == 0) return rslt.Init_many_objs(pos, KeyVal_.Ary_empty);
RegxMatch match = regx_rslts[0]; // NOTE: take only 1st result
Regx_match match = regx_rslts[0]; // NOTE: take only 1st result
List_adp tmp_list = List_adp_.new_();
AddCapturesFromMatch(tmp_list, match, text, capt, true); // NOTE: was incorrectly set as false; DATE:2014-04-23
return rslt.Init_many_objs(match.Find_end(), Scrib_kv_utl_.base1_list_(tmp_list));
}
private void AddCapturesFromMatch(List_adp tmp_list, RegxMatch rslt, String text, KeyVal[] capts, boolean op_is_match) {// NOTE: this matches behavior in UstringLibrary.php!addCapturesFromMatch
RegxGroup[] grps = rslt.Groups();
private void AddCapturesFromMatch(List_adp tmp_list, Regx_match rslt, String text, KeyVal[] capts, boolean op_is_match) {// NOTE: this matches behavior in UstringLibrary.php!addCapturesFromMatch
Regx_group[] grps = rslt.Groups();
int grps_len = grps.length;
int capts_len = capts == null ? 0 : capts.length;
if (grps_len > 0) {
for (int j = 0; j < grps_len; j++) {
RegxGroup grp = grps[j];
Regx_group grp = grps[j];
if ( j < capts_len // bounds check b/c null can be passed
&& Bool_.cast_(capts[j].Val()) // check if true; indicates that group is "()" or "anypos" see regex converter; DATE:2014-04-23
)
@@ -151,8 +151,8 @@ public class Scrib_lib_ustring implements Scrib_lib {
&& tmp_list.Count() == 0) // only add match once; EX: "aaaa", "a" will have four matches; get 1st; DATE:2014-04-02
tmp_list.Add(String_.Mid(text, rslt.Find_bgn(), rslt.Find_end()));
}
public static RegxAdp RegxAdp_new_(Xop_ctx ctx, String regx) {
RegxAdp rv = RegxAdp_.new_(regx);
public static Regx_adp RegxAdp_new_(Xop_ctx ctx, String regx) {
Regx_adp rv = Regx_adp_.new_(regx);
if (rv.Pattern_is_invalid()) {
ctx.App().Usr_dlg().Warn_many("", "", "regx is invalid: regx=~{0} page=~{1}", regx, String_.new_u8(ctx.Cur_page().Ttl().Page_db()));
}
@@ -212,8 +212,8 @@ class Scrib_lib_ustring_gsub_mgr {
else throw Err_.new_unhandled(ClassAdp_.NameOf_type(repl_type));
}
private String Exec_repl(byte repl_tid, byte[] repl_bry, String text, String regx, int limit) {
RegxAdp regx_mgr = Scrib_lib_ustring.RegxAdp_new_(core.Ctx(), regx);
RegxMatch[] rslts = regx_mgr.Match_all(text, 0);
Regx_adp regx_mgr = Scrib_lib_ustring.RegxAdp_new_(core.Ctx(), regx);
Regx_match[] rslts = regx_mgr.Match_all(text, 0);
if ( rslts.length == 0 // PHP: If matches are found, the new subject will be returned, otherwise subject will be returned unchanged.; http://php.net/manual/en/function.preg-replace-callback.php
|| regx_mgr.Pattern_is_invalid() // NOTE: invalid patterns should return self; EX:[^]; DATE:2014-09-02
) return text;
@@ -222,7 +222,7 @@ class Scrib_lib_ustring_gsub_mgr {
int pos = 0;
for (int i = 0; i < len; i++) {
if (limit > -1 && repl_count == limit) break;
RegxMatch rslt = rslts[i];
Regx_match rslt = rslts[i];
tmp_bfr.Add_str(String_.Mid(text, pos, rslt.Find_bgn())); // NOTE: regx returns char pos (not bry); must add as String, not bry; DATE:2013-07-17
Exec_repl_itm(tmp_bfr, repl_tid, repl_bry, text, rslt);
pos = rslt.Find_end();
@@ -233,7 +233,7 @@ class Scrib_lib_ustring_gsub_mgr {
tmp_bfr.Add_str(String_.Mid(text, pos, text_len)); // NOTE: regx returns char pos (not bry); must add as String, not bry; DATE:2013-07-17
return tmp_bfr.Xto_str_and_clear();
}
private void Exec_repl_itm(Bry_bfr tmp_bfr, byte repl_tid, byte[] repl_bry, String text, RegxMatch match) {
private void Exec_repl_itm(Bry_bfr tmp_bfr, byte repl_tid, byte[] repl_bry, String text, Regx_match match) {
switch (repl_tid) {
case Repl_tid_string:
int len = repl_bry.length;
@@ -251,7 +251,7 @@ class Scrib_lib_ustring_gsub_mgr {
case Byte_ascii.Num_5: case Byte_ascii.Num_6: case Byte_ascii.Num_7: case Byte_ascii.Num_8: case Byte_ascii.Num_9:
int idx = b - Byte_ascii.Num_0 - List_adp_.Base1;
if (idx < match.Groups().length) { // retrieve numbered capture; TODO: support more than 9 captures
RegxGroup grp = match.Groups()[idx];
Regx_group grp = match.Groups()[idx];
tmp_bfr.Add_str(String_.Mid(text, grp.Bgn(), grp.End())); // NOTE: grp.Bgn() / .End() is for String pos (bry pos will fail for utf8 strings)
}
else {
@@ -278,13 +278,13 @@ class Scrib_lib_ustring_gsub_mgr {
break;
case Repl_tid_table: {
int match_bgn = -1, match_end = -1;
RegxGroup[] grps = match.Groups();
Regx_group[] grps = match.Groups();
if (grps.length == 0) {
match_bgn = match.Find_bgn();
match_end = match.Find_end();
}
else { // group exists, take first one (logic matches Scribunto); PAGE:en.w:Bannered_routes_of_U.S._Route_60; DATE:2014-08-15
RegxGroup grp = grps[0];
Regx_group grp = grps[0];
match_bgn = grp.Bgn();
match_end = grp.End();
}
@@ -298,7 +298,7 @@ class Scrib_lib_ustring_gsub_mgr {
}
case Repl_tid_luacbk: {
KeyVal[] luacbk_args = null;
RegxGroup[] grps = match.Groups();
Regx_group[] grps = match.Groups();
int grps_len = grps.length;
if (grps_len == 0) { // no match; use original String
String find_str = String_.Mid(text, match.Find_bgn(), match.Find_end());
@@ -307,7 +307,7 @@ class Scrib_lib_ustring_gsub_mgr {
else { // match; build ary of matches; (see UStringLibrary.php)
luacbk_args = new KeyVal[grps_len];
for (int i = 0; i < grps_len; i++) {
RegxGroup grp = grps[i];
Regx_group grp = grps[i];
String find_str = String_.Mid(text, grp.Bgn(), grp.End());
luacbk_args[i] = KeyVal_.int_(i + Scrib_core.Base_1, find_str);
}

18
400_xowa/src/gplx/xowa/xtns/scribunto/libs/Scrib_lib_ustring__lib_tst.java
View File

@@ -16,7 +16,7 @@ You should have received a copy of the GNU Affero General Public License
along with this program. If not, see <http://www.gnu.org/licenses/>.
*/
package gplx.xowa.xtns.scribunto.libs; import gplx.*; import gplx.xowa.*; import gplx.xowa.xtns.*; import gplx.xowa.xtns.scribunto.*;
import org.junit.*;
import org.junit.*; import gplx.core.regxs.*;
public class Scrib_lib_ustring__lib_tst {
@Before public void init() {
fxt.Clear_for_lib();
@@ -116,11 +116,19 @@ public class Scrib_lib_ustring__lib_tst {
, " 1=2"
));
}
@Test public void Gsub_frontier_pattern() { // PURPOSE: handle frontier pattern; EX:"%f[%a]"; NOTE:test will fail if run in 1.6 environment; DATE:2015-07-20
// @Test public void Gsub_frontier_pattern() { // PURPOSE: handle frontier pattern; EX:"%f[%a]"; DATE:2015-07-21
// fxt.Init_cbk(Scrib_core.Key_mw_interface, fxt.Core().Lib_ustring(), Scrib_lib_ustring.Invk_gsub);
// //Exec_gsub_regx("THE QUICK brOWN FOx JUMPS", "%f[%a]%u+%f[%A]", 1, "", "THE;1;QUICK;2;JUMPS;3;");
// Exec_gsub_regx("thE QUICK brOWN FOx JUMPS", "%f[%a]%u+%f[%A]", 1, "", "THE;1;QUICK;2;JUMPS;3;");
}
// Exec_gsub_regx("a b c", "%f[%W]", 5, "()", "a() b() c();3");
// Exec_gsub_regx("abC DEF gHI JKm NOP", "%f[%a]%u+%f[%A]", Int_.MaxValue, "()", "abC () gHI JKm ();2"); // based on http://lua-users.org/wiki/FrontierPattern
// }
// @Test public void Gsub_frontier_pattern_utl() {// PURPOSE: standalone test for \0 logic in frontier pattern; note that verified against PHP: echo(preg_match( "/[\w]/us", "\0" )); DATE:2015-07-21
// Tfds.Eq(Bool_.N, Regx_adp_.Match("\0", "a")); // \0 not matched by a
// Tfds.Eq(Bool_.N, Regx_adp_.Match("\0", "0")); // \0 not matched by numeric 0
// Tfds.Eq(Bool_.N, Regx_adp_.Match("\0", "[\\w]")); // \0 not matched by word_char
// Tfds.Eq(Bool_.Y, Regx_adp_.Match("\0", "[\\W]")); // \0 matched by !word_char
// Tfds.Eq(Bool_.Y, Regx_adp_.Match("\0", "[\\x]")); // \0 matched by any_char
// Tfds.Eq(Bool_.Y, Regx_adp_.Match("\0", "[\\X]")); // \0 matched by !any_char
// }
// @Test public void Match_viwiktionary() {
// fxt.Init_cbk(Scrib_core.Key_mw_interface, fxt.Core().Lib_ustring(), Scrib_lib_ustring.Invk_match);
// Exec_match("tr" , "()(r)", 1, ";"); // should return all matches

20
400_xowa/src/gplx/xowa/xtns/scribunto/libs/Scrib_regx_converter.java
View File

@@ -16,6 +16,7 @@ You should have received a copy of the GNU Affero General Public License
along with this program. If not, see <http://www.gnu.org/licenses/>.
*/
package gplx.xowa.xtns.scribunto.libs; import gplx.*; import gplx.xowa.*; import gplx.xowa.xtns.*; import gplx.xowa.xtns.scribunto.*;
import gplx.core.regxs.*;
public class Scrib_regx_converter {
private List_adp capt_list = List_adp_.new_(), grps_parens = List_adp_.new_(); private List_adp grps_open = List_adp_.new_();
public Scrib_regx_converter() {Init();}
@@ -94,20 +95,21 @@ public class Scrib_regx_converter {
}
}
break;
// case Byte_ascii.Ltr_f: { // EX: "%f[%a]"
// case Byte_ascii.Ltr_f: { // EX: lua frontier pattern; "%f[%a]"; DATE:2015-07-21
// ++i;
// if (i + 1 >= len || src[i] != Byte_ascii.Brack_bgn) throw Err_.new_("scribunto", "missing '[' after %f in pattern at pattern character $ii");
//
// // %f always followed by bracketed term; convert lua bracketed term to regex
// Bry_bfr tmp_bfr = Xoa_app_.Utl__bfr_mkr().Get_b128();
// i = bracketedCharSetToRegex(tmp_bfr, src, i, len);
// byte[] bracketed_regx = tmp_bfr.To_bry_and_rls();
// int j = 1;
// bfr.Add_str_a7("(?<!").Add(bracketed_regx).Add_str_a7(")(?=$").Add(bracketed_regx).Add_str_a7(")");
//// if ( preg_match( "/$re2/us", "\0" ) ) {
//// $re .= "(?<!^)(?<!$re2)(?=$re2|$)";
//// } else {
//// $re .= "(?<!$re2)(?=$re2)";
//// }
//
//
// // scrib has following comment: 'Because %f considers the beginning and end of the String to be \0, determine if $re2 matches that and take it into account with "^" and "$".'
// // if the bracketed_regx is a negative class it will match \0; so, \W means anything not a word char, which will match \0; \w means word char which will not match \0
// if (Regx_adp_.Match("\0", String_.new_u8(bracketed_regx)))
// bfr.Add_str_a7("(?<!^)(?<!").Add(bracketed_regx).Add_str_a7(")(?=").Add(bracketed_regx).Add_str_a7("|$)"); // match bgn / end of String
// else
// bfr .Add_str_a7("(?<!").Add(bracketed_regx).Add_str_a7(")(?=").Add(bracketed_regx).Add_str_a7( ")");
// break;
// }
case Byte_ascii.Num_0: case Byte_ascii.Num_1: case Byte_ascii.Num_2: case Byte_ascii.Num_3: case Byte_ascii.Num_4:

5
400_xowa/src/gplx/xowa/xtns/scribunto/libs/Scrib_regx_converter_tst.java
View File

@@ -16,8 +16,7 @@ You should have received a copy of the GNU Affero General Public License
along with this program. If not, see <http://www.gnu.org/licenses/>.
*/
package gplx.xowa.xtns.scribunto.libs; import gplx.*; import gplx.xowa.*; import gplx.xowa.xtns.*; import gplx.xowa.xtns.scribunto.*;
import org.junit.*;
import gplx.texts.*;
import org.junit.*; import gplx.core.regxs.*;
public class Scrib_regx_converter_tst {
@Before public void init() {fxt.Clear();} private Scrib_regx_converter_fxt fxt = new Scrib_regx_converter_fxt();
@Test public void Basic() {fxt.Test_parse("abc012ABC" , "abc012ABC");}
@@ -61,7 +60,7 @@ class Scrib_regx_converter_fxt {
}
public void Test_replace(String text, String find, String replace, String expd) {
String regex_str = under.Parse(Bry_.new_u8(find), Scrib_regx_converter.Anchor_G);
String actl = RegxAdp_.Replace(text, regex_str, replace);
String actl = Regx_adp_.Replace(text, regex_str, replace);
Tfds.Eq(expd, actl);
}
}