1
0
mirror of https://github.com/gnosygnu/xowa.git synced 2026-03-02 03:49:30 +00:00

JsonConfig: Add Localize function for tabular data

This commit is contained in:
gnosygnu
2018-02-18 08:16:43 -05:00
parent 8967ca810a
commit 54d74b0acd
67 changed files with 5592 additions and 200 deletions

View File

@@ -175,7 +175,7 @@ public class Gallery_mgr_wtr {
int len = xatr_list.Count();
for (int i = 0; i < len; i++) {
Mwh_atr_itm xatr = (Mwh_atr_itm)xatr_list.Get_at(i);
if (!whitelist_mgr.Chk(Xop_xnde_tag_.Tid__ul, src, xatr)) continue;
if (!whitelist_mgr.Chk(Xop_xnde_tag_.Tid__ul, xatr)) continue;
byte[] key = xatr.Key_bry();
byte[] val = xatr.Val_as_bry();
Gfh_wtr.Write_atr_bry(bfr, key, val);

View File

@@ -0,0 +1,151 @@
/*
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.xtns.jsonConfigs.scribunto; import gplx.*; import gplx.xowa.*; import gplx.xowa.xtns.*; import gplx.xowa.xtns.jsonConfigs.*;
import gplx.xowa.langs.*;
class Jscfg_localizer {
public Keyval[] Localize(Xol_lang_itm lang, byte[] page, Keyval[] root) {
if (lang == null) return root; // if no lang, return original
int len = root.length;
for (int i = 0; i < len; i++) {
Keyval nde = root[i];
String nde_key = nde.Key();
if (String_.Eq(nde_key, Id__root__license)) {
}
else if (String_.Eq(nde_key, Id__root__description)) {
root[i] = pickLocalizedString(lang, page, nde);
}
else if (String_.Eq(nde_key, Id__root__schema)) {
nde = Localize_schema(lang, page, nde);
}
else if (String_.Eq(nde_key, Id__root__data)) {
nde = Localize_data(lang, page, nde);
}
}
return root;
}
private Keyval Localize_schema(Xol_lang_itm lang, byte[] page, Keyval schema) {
Keyval[] schemas = Cast_to_kvary_or_null(page, schema) ; if (schemas == null) return schema;
Keyval[] fields = Cast_to_kvary_or_null(page, schemas[0]); if (fields == null) return schema;
for (Keyval field : fields) {
Keyval[] atrs = (Keyval[])field.Val();
int atrs_len = atrs.length;
for (int i = 0; i < atrs_len; i++) {
Keyval atr = atrs[i];
if (String_.Eq(atr.Key(), Id__fld__title)) {
atrs[i] = pickLocalizedString(lang, page, atr);
}
}
}
return schema;
}
private Keyval Localize_data(Xol_lang_itm lang, byte[] page, Keyval data) {
Keyval[] rows = Cast_to_kvary_or_null(page, data); if (rows == null) return data;
for (Keyval row : rows) {
Object[] vals = (Object[])row.Val();
int len = vals.length;
for (int i = 0; i < len; i++) {
Object val = vals[i];
if (Type_.Eq_by_obj(val, Keyval[].class)) {
Keyval val_as_kv = pickLocalizedString(lang, Int_.To_str(i), (Keyval[])val);
vals[i] = val_as_kv.Val();
}
}
}
return data;
}
private static Keyval pickLocalizedString(Xol_lang_itm lang, byte[] page, Keyval kv) {
Keyval[] kvs = Cast_to_kvary_or_null(page, kv.Key(), kv.Val());
Keyval rv = pickLocalizedString(lang, kv.Key(), kvs);
return rv == null ? kv : rv;
}
public static Keyval pickLocalizedString(Xol_lang_itm lang, String key, Keyval[] ary) {
// local vars for conditional logic
Object val_lang = null, val_en = null, val_1st = null;
Object[] val_fallbacks = null;
// local vars for lang
String langCode = lang.Key_str();
Ordered_hash fallback_hash = lang.Fallback_hash();
// loop ary to populate local vars
for (Keyval itm : ary) {
String itm_key = itm.Key();
Object itm_val = itm.Val();
if (val_1st == null) {
val_1st = itm_val;
}
if (String_.Eq(itm_key, langCode)) {
val_lang = itm_val;
}
else if (fallback_hash.Has(itm_key)) {
if (val_fallbacks == null) {
val_fallbacks = new Object[fallback_hash.Len()];
}
int idx = fallback_hash.Idx_of(itm_key);
val_fallbacks[idx] = itm_val;
}
else if (String_.Eq(itm_key, "en")) {
val_en = itm_val;
}
}
if (val_lang != null) {
return Keyval_.new_(key, val_lang);
}
if (val_fallbacks != null) {
for (Object v : val_fallbacks) {
if (v != null)
return Keyval_.new_(key, v);
}
}
// If fallbacks fail, check if english is defined
if (val_en != null) {
return Keyval_.new_(key, val_en);
}
// We have a custom default, return that
// if (defaultValue != null) {
// return null;
// }
// Return first available value, or an empty String
// There might be a better way to get the first value from an Object
Object val = val_1st == null ? "" : val_1st;
return Keyval_.new_(key, val);
}
private static Keyval[] Cast_to_kvary_or_null(byte[] page, Keyval kv) {return Cast_to_kvary_or_null(page, kv.Key(), kv.Val());}
private static Keyval[] Cast_to_kvary_or_null(byte[] page, String key, Object val) {
if (Type_.Eq_by_obj(val, Keyval[].class)) {
return (Keyval[])val;
}
else {
Gfo_usr_dlg_.Instance.Warn_many("", "", "could not cast to kvary; page=~{0} key=~{1}", key);
return null;
}
}
private static final String
Id__root__schema = "schema"
, Id__root__data = "data"
, Id__root__description = "description"
, Id__root__license = "license"
, Id__fld__title = "title"
;
}

View File

@@ -18,6 +18,7 @@ import gplx.xowa.xtns.scribunto.*; import gplx.xowa.xtns.scribunto.libs.*; impor
import gplx.xowa.wikis.domains.*;
public class Jscfg_scrib_lib implements Scrib_lib {
private final Scrib_lib_text__json_util json_util = new Scrib_lib_text__json_util();
private final Jscfg_localizer localizer = new Jscfg_localizer();
private Scrib_core core;
public Scrib_lua_mod Mod() {return mod;} private Scrib_lua_mod mod;
public Scrib_lib Init() {procs.Init_by_lib(this, Proc_names); return this;}
@@ -57,6 +58,8 @@ public class Jscfg_scrib_lib implements Scrib_lib {
throw Err_.new_wo_type("bad argument #1 to 'get' (not a valid title) " + String_.new_u8(ttl_bry));
}
return Scrib_lib_text.JsonDecodeStatic(args, rslt, core, json_util, page, Scrib_lib_text__json_util.Opt__force_assoc, Scrib_lib_text__json_util.Flag__none);
Keyval[] rv = Scrib_lib_text.JsonDecodeStatic(args, core, json_util, page, Scrib_lib_text__json_util.Opt__force_assoc, Scrib_lib_text__json_util.Flag__none);
rv = localizer.Localize(core.Wiki().Lang(), page, rv);
return rslt.Init_obj(rv);
}
}

View File

@@ -14,18 +14,14 @@ 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.xtns.jsonConfigs.scribunto; import gplx.*; import gplx.xowa.*; import gplx.xowa.xtns.*; import gplx.xowa.xtns.jsonConfigs.*;
import org.junit.*;
import org.junit.*; import gplx.core.tests.*;
import gplx.xowa.xtns.scribunto.*; import gplx.xowa.xtns.scribunto.libs.*;
import gplx.xowa.langs.*;
import gplx.langs.jsons.*;
public class Jscfg_scrib_lib_tst {
@Before public void init() {
fxt.Clear_for_lib();
lib = new Jscfg_scrib_lib();
lib.Init();
lib.Core_(fxt.Core());
} private Scrib_invoke_func_fxt fxt = new Scrib_invoke_func_fxt(); private Jscfg_scrib_lib lib;
private final Jscfg_scrib_lib_fxt fxt = new Jscfg_scrib_lib_fxt();
@Test public void Get() {
Xowe_wiki commons_wiki = fxt.Parser_fxt().Wiki().Appe().Wiki_mgr().Get_by_or_make(gplx.xowa.wikis.domains.Xow_domain_itm_.Bry__commons).Init_assert();
fxt.Parser_fxt().Init_page_create(commons_wiki, "Data:Test.tab", gplx.langs.jsons.Json_doc.Make_str_by_apos
fxt.Init__page("Data:Test.tab", Json_doc.Make_str_by_apos
( "{"
, " 'data':"
, " ["
@@ -41,7 +37,7 @@ public class Jscfg_scrib_lib_tst {
, " ]"
, "}"
));
fxt.Test_scrib_proc_str_ary(lib, Jscfg_scrib_lib.Invk_get, Keyval_.Ary(Keyval_.int_(1, "Test.tab")), String_.Concat_lines_nl_skip_last
fxt.Test__get("Test.tab", String_.Concat_lines_nl_skip_last
( "1="
, " data="
, " 1="
@@ -52,4 +48,126 @@ public class Jscfg_scrib_lib_tst {
, " 2=Data:Q2"
));
}
@Test public void Get_localize() {
fxt.Init__page("Data:Test_localize.tab", Json_doc.Make_str_by_apos
( "{"
, " 'license': 'CC0-1.0',"
, " 'description': {"
, " 'de': 'Objekttabelle',"
, " 'en': 'Object table'"
, " },"
, " 'sources': 'Objects in Data:Data.tab completed by [https://www.wikidata.org Wikidata]',"
, " 'schema': {"
, " 'fields': ["
, " {"
, " 'name': 'wikidataID',"
, " 'type': 'String',"
, " 'title': {"
, " 'de': 'Wikidata-Item',"
, " 'en': 'Wikidata item'"
, " }"
, " },"
, " {"
, " 'name': 'wikidataLabel',"
, " 'type': 'localized',"
, " 'title': {"
, " 'de': 'Wikidata-Label',"
, " 'en': 'Wikidata label'"
, " }"
, " }"
, " ]"
, " },"
, " 'data': ["
, " ["
, " 'Q183',"
, " {"
, " 'de': 'Deutschland',"
, " 'en': 'Germany'"
, " }"
, " ],"
, " ["
, " 'Q61912',"
, " {"
, " 'de': 'Wertheim',"
, " 'en': 'Wertheim am Main'"
, " }"
, " ]"
, " ]"
, "}"
));
fxt.Test__get( "Test_localize.tab", String_.Concat_lines_nl_skip_last
( "1="
, " license=CC0-1.0"
, " description=Object table"
, " sources=Objects in Data:Data.tab completed by [https://www.wikidata.org Wikidata]"
, " schema="
, " fields="
, " 1="
, " name=wikidataID"
, " type=String"
, " title=Wikidata item"
, " 2="
, " name=wikidataLabel"
, " type=localized"
, " title=Wikidata label"
, " data="
, " 1="
, " 1=Q183"
, " 2=Germany"
, " 2="
, " 1=Q61912"
, " 2=Wertheim am Main"
));
}
@Test public void pickLocalizedString() {
Xol_lang_itm lang = fxt.Init__lang("zh-cn", "zh1,zh0");
// match key
fxt.Test__pickLocalizedString(lang, fxt.Init__picklocalizedStringKvs("fr", "zh-cn"), "zh-cn");
// match fallback; note that zh1 is higher in fallback list, but lower in kvs
fxt.Test__pickLocalizedString(lang, fxt.Init__picklocalizedStringKvs("zh0", "zh1"), "zh1");
// match en if no key or fallbacks
fxt.Test__pickLocalizedString(lang, fxt.Init__picklocalizedStringKvs("fr", "en"), "en");
// pick 1st if no match
fxt.Test__pickLocalizedString(lang, fxt.Init__picklocalizedStringKvs("fr", "de"), "fr");
}
}
class Jscfg_scrib_lib_fxt {
private final Scrib_invoke_func_fxt fxt = new Scrib_invoke_func_fxt();
private final Jscfg_scrib_lib lib;
private final Xowe_wiki commons_wiki;
public Jscfg_scrib_lib_fxt() {
fxt.Clear_for_lib();
lib = new Jscfg_scrib_lib();
lib.Init();
lib.Core_(fxt.Core());
this.commons_wiki = fxt.Parser_fxt().Wiki().Appe().Wiki_mgr().Get_by_or_make(gplx.xowa.wikis.domains.Xow_domain_itm_.Bry__commons).Init_assert();
}
public void Init__page(String page, String text) {
fxt.Parser_fxt().Init_page_create(commons_wiki, page, text);
}
public Xol_lang_itm Init__lang(String key, String fallbacks) {
Xol_lang_itm lang = new Xol_lang_itm(fxt.Core().App().Lang_mgr(), Bry_.new_u8(key));
lang.Fallback_bry_(Bry_.new_a7(fallbacks));
return lang;
}
public Keyval[] Init__picklocalizedStringKvs(String... vals) {
int len = vals.length;
Keyval[] rv = new Keyval[len];
for (int i = 0; i < len; i++) {
String val = vals[i];
rv[i] = Keyval_.new_(val, val);
}
return rv;
}
public void Test__get(String page, String expd) {
fxt.Test_scrib_proc_str_ary(lib, Jscfg_scrib_lib.Invk_get, Keyval_.Ary(Keyval_.int_(1, page)), expd);
}
public void Test__pickLocalizedString(Xol_lang_itm lang, Keyval[] kv_ary, String expd) {
Keyval actl_kv = Jscfg_localizer.pickLocalizedString(lang, "key", kv_ary);
Gftest.Eq__obj_or_null(expd, actl_kv.Val());
}
}

View File

@@ -15,11 +15,23 @@ Apache License: https://github.com/gnosygnu/xowa/blob/master/LICENSE-APACHE2.txt
*/
package gplx.xowa.xtns.jsonConfigs.scribunto; import gplx.*; import gplx.xowa.*; import gplx.xowa.xtns.*; import gplx.xowa.xtns.jsonConfigs.*;
import gplx.xowa.xtns.scribunto.*;
import gplx.xowa.mediawiki.*;
public class Jscfg_xtn_mgr extends Xox_mgr_base {
@Override public byte[] Xtn_key() {return XTN_KEY;} public static final byte[] XTN_KEY = Bry_.new_a7("JsonConfig");
@Override public void Xtn_init_by_wiki(Xowe_wiki wiki) {
Scrib_xtn_mgr scrib_xtn = (Scrib_xtn_mgr)wiki.Xtn_mgr().Get_or_fail(Scrib_xtn_mgr.XTN_KEY);
scrib_xtn.Lib_mgr().Add(new Jscfg_scrib_lib());
}
/*
@Override public void Xtn_ctor_by_app(Xoae_app app) {
Init_xtn();
}
public void Init_xtn() {
JCSingleton singleton = new JCSingleton();
singleton.ConfigModels().Add(JCTabularContent.Model_id, JCTabularContent.Model_id);
XophpEnv.Instance.Singletons().Add(JCSingleton.Singleton_Id, singleton);
XophpEnv.Instance.ClassBldrs().Add(JCTabularContent.Model_id, new JCTabularContentFactory());
}
*/
@Override public Xox_mgr Xtn_clone_new() {return new Jscfg_xtn_mgr();}
}

View File

@@ -67,7 +67,7 @@ class Xomath_html_wtr {
}
// write html: <span>math_expr</math>
byte[] unique_bry = wiki.Parser_mgr().Uniq_mgr().Add(Bry__math, math_bry);
byte[] unique_bry = wiki.Parser_mgr().Uniq_mgr().Add(Bool_.Y, Bry__math, math_bry);
Bry_fmt fmt = is_latex ? fmt__latex : fmt__mathjax;
fmt.Bld_many(tmp_bfr, uid, unique_bry);
bfr.Add_bfr_and_clear(tmp_bfr);

View File

@@ -52,7 +52,7 @@ public class Pfunc_tag extends Pf_func_base {// REF:CoreParserFunctions.php
// add to UNIQ hash; DATE:2017-03-31
byte[] val = tmp_bfr.To_bry_and_clear();
byte[] key = ctx.Wiki().Parser_mgr().Uniq_mgr().Add(tag_name, val);
byte[] key = ctx.Wiki().Parser_mgr().Uniq_mgr().Add(Bool_.Y, tag_name, val);
bfr.Add(key);
}
finally {tmp_bfr.Mkr_rls();}

View File

@@ -14,12 +14,18 @@ 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.xtns.scribunto.libs; import gplx.*; import gplx.xowa.*; import gplx.xowa.xtns.*; import gplx.xowa.xtns.scribunto.*;
import gplx.core.bits.*;
import gplx.core.bits.*; import gplx.core.btries.*;
import gplx.xowa.langs.msgs.*;
import gplx.xowa.xtns.scribunto.procs.*;
public class Scrib_lib_text implements Scrib_lib {
private final Scrib_lib_text__json_util json_util = new Scrib_lib_text__json_util();
public Scrib_lib_text(Scrib_core core) {this.core = core;} private Scrib_core core;
private final Scrib_lib_text__nowiki_util nowiki_util = new Scrib_lib_text__nowiki_util();
private final Scrib_core core;
private final Btrie_slim_mgr trie;
public Scrib_lib_text(Scrib_core core) {
this.core = core;
this.trie = nowiki_util.Make_trie(gplx.xowa.parsers.xndes.Xop_xnde_tag_.Tag__nowiki.Name_bry());
}
public Scrib_lua_mod Mod() {return mod;} private Scrib_lua_mod mod;
public Scrib_lib Init() {procs.Init_by_lib(this, Proc_names); return this;}
public Scrib_lib Clone_lib(Scrib_core core) {return new Scrib_lib_text(core);}
@@ -47,7 +53,11 @@ public class Scrib_lib_text implements Scrib_lib {
, Invk_init_text_for_wiki = "init_text_for_wiki", Invk_jsonEncode = "jsonEncode", Invk_jsonDecode = "jsonDecode";
private static final String[] Proc_names = String_.Ary(Invk_unstrip, Invk_unstripNoWiki, Invk_killMarkers, Invk_getEntityTable, Invk_init_text_for_wiki, Invk_jsonEncode, Invk_jsonDecode);
public boolean Unstrip(Scrib_proc_args args, Scrib_proc_rslt rslt) {return rslt.Init_obj(args.Pull_str(0));} // NOTE: XOWA does not use MediaWiki strip markers; just return original; DATE:2015-01-20
public boolean UnstripNoWiki(Scrib_proc_args args, Scrib_proc_rslt rslt) {return rslt.Init_obj(args.Pull_str(0));} // NOTE: XOWA does not use MediaWiki strip markers; just return original; DATE:2015-01-20
public boolean UnstripNoWiki(Scrib_proc_args args, Scrib_proc_rslt rslt) {
// NOTE: XOWA does not use MediaWiki strip markers; just return original; DATE:2015-01-20
byte[] src = args.Pull_bry(0);
return rslt.Init_obj(nowiki_util.Strip_tag(core.Page().Url_bry_safe(), src, trie));
}
public boolean KillMarkers(Scrib_proc_args args, Scrib_proc_rslt rslt) {return rslt.Init_obj(args.Pull_str(0));} // NOTE: XOWA does not use MediaWiki strip markers; just return original; DATE:2015-01-20
public boolean GetEntityTable(Scrib_proc_args args, Scrib_proc_rslt rslt) {
if (html_entities == null) html_entities = Scrib_lib_text_html_entities.new_();
@@ -108,10 +118,11 @@ public class Scrib_lib_text implements Scrib_lib {
if (Bitmask_.Has_int(flags, Scrib_lib_text__json_util.Flag__try_fixing))
opts = Bitmask_.Add_int(opts, Scrib_lib_text__json_util.Flag__try_fixing);
return JsonDecodeStatic(args, rslt, core, json_util, json, opts, flags);
Keyval[] rv = JsonDecodeStatic(args, core, json_util, json, opts, flags);
return rslt.Init_obj(rv);
}
public static boolean JsonDecodeStatic
( Scrib_proc_args args, Scrib_proc_rslt rslt, Scrib_core core, Scrib_lib_text__json_util json_util
public static Keyval[] JsonDecodeStatic
( Scrib_proc_args args, Scrib_core core, Scrib_lib_text__json_util json_util
, byte[] json, int opts, int flags) {
// decode json to Object; note that Bool_.Y means ary and Bool_.N means ary
byte rv_tid = json_util.Decode(core.App().Utl__json_parser(), json, opts);
@@ -125,10 +136,10 @@ public class Scrib_lib_text implements Scrib_lib {
json_util.Reindex_arrays(reindex_data, rv_as_kvy, false);
rv_as_kvy = reindex_data.Rv_is_kvy() ? (Keyval[])reindex_data.Rv_as_kvy() : (Keyval[])reindex_data.Rv_as_ary();
}
return rslt.Init_obj(rv_as_kvy);
return rv_as_kvy;
}
else
return rslt.Init_obj(json_util.Decode_rslt_as_ary());
return json_util.Decode_rslt_as_ary();
}
public void Notify_wiki_changed() {if (notify_wiki_changed_fnc != null) core.Interpreter().CallFunction(notify_wiki_changed_fnc.Id(), Keyval_.Ary_empty);}

View File

@@ -0,0 +1,90 @@
/*
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.xtns.scribunto.libs; import gplx.*; import gplx.xowa.*; import gplx.xowa.xtns.*; import gplx.xowa.xtns.scribunto.*;
import gplx.core.btries.*;
import gplx.core.primitives.*;
public class Scrib_lib_text__nowiki_util {
public Btrie_slim_mgr Make_trie(byte[] tag) {
Bry_bfr tmp = Bry_bfr_.New();
Btrie_slim_mgr rv = Btrie_slim_mgr.ci_u8();
byte[] lhs_bry = tmp.Add_bry_many(Byte_ascii.Angle_bgn_bry, tag, Byte_ascii.Angle_end_bry).To_bry_and_clear();
byte[] rhs_bry = tmp.Add_bry_many(Byte_ascii.Angle_bgn_bry, Byte_ascii.Slash_bry, tag, Byte_ascii.Angle_end_bry).To_bry_and_clear();
rv.Add_obj(lhs_bry, Bool_obj_val.True);
rv.Add_obj(rhs_bry, Bool_obj_val.False);
return rv;
}
public byte[] Strip_tag(byte[] page, byte[] src, Btrie_slim_mgr trie) {
Btrie_rv trv = new Btrie_rv();
Bry_bfr tmp = null;
int bgn = 0;
int end = src.length;
// main loop
boolean lhs_found = false;
int pos = bgn;
int rhs_end = pos, lhs_bgn = pos, lhs_end = pos;
while (pos < end) {
// check byte against trie
Object o = trie.Match_at_w_b0(trv, src[pos], src, pos, end);
// no match; increment and continue;
if (o == null) {
pos++;
continue;
}
// match found
Bool_obj_val tag_marker = (Bool_obj_val)o;
// match is open tag; EX: <tag>
if (tag_marker.Val()) {
// set lhs_bgn and lhs_end; note that if there are multiple open tags, it will only keep the first
if (!lhs_found) {
lhs_found = true;
lhs_bgn = pos;
lhs_end = trv.Pos();
}
}
// match is close tag; EX: </tag>
else {
// only splice if open tag exists; avoids dangling rhs; EX: "a</tag>b"
if (lhs_found) {
lhs_found = false;
if (tmp == null) tmp = Bry_bfr_.New();
// add text from previous </tag> to current <tag>;
tmp.Add_mid(src, rhs_end, lhs_bgn);
// add text between <tag> and </tag>;
tmp.Add_mid(src, lhs_end, pos);
// update </tag> pos
rhs_end = trv.Pos();
}
}
// update pos to after match
pos = trv.Pos();
}
// add remaining text to bfr
if (tmp != null) {
tmp.Add_mid(src, rhs_end, end);
}
return tmp == null ? src : tmp.To_bry_and_clear();
}
}

View File

@@ -0,0 +1,55 @@
/*
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.xtns.scribunto.libs; import gplx.*; import gplx.xowa.*; import gplx.xowa.xtns.*; import gplx.xowa.xtns.scribunto.*;
import org.junit.*; import gplx.core.tests.*;
import gplx.core.btries.*;
import gplx.xowa.parsers.xndes.*;
public class Scrib_lib_text__nowiki_util_tst {
private final Scrib_lib_text__nowiki_util_fxt fxt = new Scrib_lib_text__nowiki_util_fxt();
@Test public void Basic() {
// noop
fxt.Test__Strip_tag("abc", "abc");
// one
fxt.Test__Strip_tag("a<nowiki>b</nowiki>c", "abc");
// mixed case
fxt.Test__Strip_tag("a<NOwiki>b</noWIKI>c", "abc");
// multiple: consecutive
fxt.Test__Strip_tag("a<nowiki>b</nowiki>c<nowiki>d</nowiki>e", "abcde");
// dangling: left
fxt.Test__Strip_tag("a<nowiki>b<nowiki>c</nowiki>d", "ab<nowiki>cd");
// dangling: right
fxt.Test__Strip_tag( "a<nowiki>b</nowiki>c</nowiki>d", "abc</nowiki>d");
// nested
fxt.Test__Strip_tag("a<nowiki>b<nowiki>c</nowiki>d</nowiki>e", "ab<nowiki>cd</nowiki>e");
}
}
class Scrib_lib_text__nowiki_util_fxt {
private final Scrib_lib_text__nowiki_util util = new Scrib_lib_text__nowiki_util();
private final Btrie_slim_mgr trie;
public Scrib_lib_text__nowiki_util_fxt() {
this.trie = util.Make_trie(Xop_xnde_tag_.Tag__nowiki.Name_bry());
}
public void Test__Strip_tag(String src, String expd) {
byte[] actl = util.Strip_tag(Bry_.new_a7("Page"), Bry_.new_u8(src), trie);
Gftest.Eq__str(expd, actl);
}
}

View File

@@ -25,6 +25,9 @@ public class Scrib_lib_text_tst {
@Test public void Unstrip() {
fxt.Test_scrib_proc_str(lib, Scrib_lib_text.Invk_unstrip, Object_.Ary("a"), "a");
}
@Test public void UnstripNoWiki() {
fxt.Test_scrib_proc_str(lib, Scrib_lib_text.Invk_unstripNoWiki, Object_.Ary("a<nowiki>b</nowiki>c"), "abc");
}
@Test public void GetEntityTable() {
Keyval[] actl = fxt.Test_scrib_proc_rv_as_kv_ary(lib, Scrib_lib_text.Invk_getEntityTable, Object_.Ary());
Tfds.Eq(1510, actl.length); // large result; only test # of entries