1
0
mirror of https://github.com/gnosygnu/xowa.git synced 2024-10-27 20:34:16 +00:00

Parser: Add more support for UNIQ substitutions with extension tags

This commit is contained in:
gnosygnu 2017-03-31 19:17:47 -04:00
parent 145635b6c7
commit 83c40c8771
7 changed files with 30 additions and 64 deletions

View File

@ -30,8 +30,8 @@ public class Xoa_app_ {
} }
} }
public static final String Name = "xowa"; public static final String Name = "xowa";
public static final int Version_id = 521; public static final int Version_id = 522;
public static final String Version = "4.5.0.1703"; public static final String Version = "4.5.1.1703";
public static String Build_date = "2012-12-30 00:00:00"; 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 Build_date_fmt = "yyyy-MM-dd HH:mm:ss";
public static String Op_sys_str; public static String Op_sys_str;

View File

@ -20,9 +20,8 @@ public class Xot_tmpl_wtr {
public static byte[] Write_all(Xop_ctx ctx, Xop_root_tkn root, byte[] src) { public static byte[] Write_all(Xop_ctx ctx, Xop_root_tkn root, byte[] src) {
Bry_bfr bfr = ctx.Wiki().Utl__bfr_mkr().Get_m001().Reset_if_gt(Io_mgr.Len_mb); Bry_bfr bfr = ctx.Wiki().Utl__bfr_mkr().Get_m001().Reset_if_gt(Io_mgr.Len_mb);
Write_tkn(bfr, ctx, src, src.length, root); Write_tkn(bfr, ctx, src, src.length, root);
return bfr.To_bry_and_rls(); byte[] rv = bfr.To_bry_and_rls();
// byte[] rv = bfr.To_bry_and_rls(); return ctx.Wiki().Parser_mgr().Uniq_mgr().Parse(rv); // NOTE: noops if no UNIQs; // UNIQ; DATE:2017-03-31
// return ctx.Wiki().Parser_mgr().Uniq_mgr().Parse(rv); // NOTE: noops if no UNIQs
} }
private static void Write_tkn(Bry_bfr rslt_bfr, Xop_ctx ctx, byte[] src, int src_len, Xop_tkn_itm tkn) { private static void Write_tkn(Bry_bfr rslt_bfr, Xop_ctx ctx, byte[] src, int src_len, Xop_tkn_itm tkn) {
switch (tkn.Tkn_tid()) { switch (tkn.Tkn_tid()) {

View File

@ -19,8 +19,8 @@ public class Xop_uniq_mgr__parse__tst {
private final Xop_fxt fxt = Xop_fxt.New_app_html(); private final Xop_fxt fxt = Xop_fxt.New_app_html();
@Before public void init() {fxt.Reset();} @Before public void init() {fxt.Reset();}
@Test public void Ref_becomes_UNIQ() { @Test public void Ref_becomes_UNIQ() {
// String wikitext = "<ref>b</ref>"; String wikitext = "<ref>b</ref>";
// fxt.Init_defn_add("test", "{{#ifeq:{{{1}}}|a" + wikitext + "c|fail|pass}}"); // fail if {{{1}}} is still wikitext; should be UNIQ fxt.Init_defn_add("test", "{{#ifeq:{{{1}}}|a" + wikitext + "c|fail|pass}}"); // fail if {{{1}}} is still wikitext; should be UNIQ
// fxt.Test__parse__tmpl_to_html("{{test|a" + wikitext + "c}}", "pass"); fxt.Test__parse__tmpl_to_html("{{test|a" + wikitext + "c}}", "pass");
} }
} }

View File

@ -106,10 +106,11 @@ public class Xop_xnde_tkn extends Xop_tkn_itm_base implements Xop_tblw_tkn {
default: // ignore tags except for xtn; NOTE: Xtn tags are part of tagRegy_wiki_tmpl stage default: // ignore tags except for xtn; NOTE: Xtn tags are part of tagRegy_wiki_tmpl stage
if (tag.Xtn()) { if (tag.Xtn()) {
Bry_bfr cur_bfr = bfr; Bry_bfr cur_bfr = bfr;
// boolean is_tmpl_mode = ctx.Wiki().Parser_mgr().Ctx().Parse_tid() == Xop_parser_tid_.Tid__tmpl; // UNIQ; DATE:2017-03-31
// if (is_tmpl_mode) { boolean is_tmpl_mode = ctx.Wiki().Parser_mgr().Ctx().Parse_tid() == Xop_parser_tid_.Tid__tmpl;
// cur_bfr = ctx.Wiki().Utl__bfr_mkr().Get_m001().Reset_if_gt(Io_mgr.Len_mb); if (is_tmpl_mode) {
// } cur_bfr = ctx.Wiki().Utl__bfr_mkr().Get_m001().Reset_if_gt(Io_mgr.Len_mb);
}
// write tag_bgn; EX: <poem> // write tag_bgn; EX: <poem>
cur_bfr.Add_mid(src, tag_open_bgn, tag_open_end); cur_bfr.Add_mid(src, tag_open_bgn, tag_open_end);
@ -127,11 +128,12 @@ public class Xop_xnde_tkn extends Xop_tkn_itm_base implements Xop_tblw_tkn {
cur_bfr.Add(Byte_ascii.Gt_bry); cur_bfr.Add(Byte_ascii.Gt_bry);
} }
// if (is_tmpl_mode) { // UNIQ; DATE:2017-03-31
// byte[] val = cur_bfr.To_bry_and_clear(); if (is_tmpl_mode) {
// byte[] key = ctx.Wiki().Parser_mgr().Uniq_mgr().Add(tag.Name_bry(), val); byte[] val = cur_bfr.To_bry_and_clear();
// bfr.Add(key); byte[] key = ctx.Wiki().Parser_mgr().Uniq_mgr().Add(tag.Name_bry(), val);
// } bfr.Add(key);
}
} }
break; break;
} }

View File

@ -545,12 +545,7 @@ public class Xop_xnde_wkr implements Xop_ctx_wkr {
return found ? rv : Bry_find_.Not_found; return found ? rv : Bry_find_.Not_found;
} }
private int Find_xtn_end_lhs(Xop_ctx ctx, Xop_xnde_tag tag, byte[] src, int src_len, int open_bgn, int open_end, byte[] open_bry, byte[] close_bry) { private int Find_xtn_end_lhs(Xop_ctx ctx, Xop_xnde_tag tag, byte[] src, int src_len, int open_bgn, int open_end, byte[] open_bry, byte[] close_bry) {
int tag_bgn = open_bgn - Pfunc_tag.Xtag_len; return Xop_xnde_wkr_.Find_xtn_end(ctx, src, open_end, src_len, open_bry, close_bry); // UNIQ; DATE:2017-03-31
if (tag_bgn > -1
&& Bry_.Eq(src, tag_bgn, tag_bgn, Pfunc_tag.Xtag_bgn_lhs)) // xtn created by tag
return Xop_xnde_wkr_.Find_xtag_end(ctx, src, open_end, src_len);
else // search rest of String for case-insensitive name; NOTE: used to do CS first, then fall-back on CI; DATE:2013-12-02
return Xop_xnde_wkr_.Find_xtn_end(ctx, src, open_end, src_len, open_bry, close_bry);
} }
private int Make_xnde_xtn(Xop_ctx ctx, Xop_tkn_mkr tkn_mkr, Xop_root_tkn root, byte[] src, int src_len, Xop_xnde_tag tag, int open_bgn, int open_end, int name_bgn, int name_end, int atrs_bgn, int atrs_end, Mwh_atr_itm[] atrs, boolean inline, boolean pre2_hack) { private int Make_xnde_xtn(Xop_ctx ctx, Xop_tkn_mkr tkn_mkr, Xop_root_tkn root, byte[] src, int src_len, Xop_xnde_tag tag, int open_bgn, int open_end, int name_bgn, int name_end, int atrs_bgn, int atrs_end, Mwh_atr_itm[] atrs, boolean inline, boolean pre2_hack) {
// NOTE: find end_tag that exactly matches bgnTag; must be case sensitive; // NOTE: find end_tag that exactly matches bgnTag; must be case sensitive;

View File

@ -30,9 +30,9 @@ class Xop_xnde_wkr_ {
root.Subs_move(owner, subs_bgn, subs_len); // move everything after "|" back to root root.Subs_move(owner, subs_bgn, subs_len); // move everything after "|" back to root
} }
public static int Find_xtn_end(Xop_ctx ctx, byte[] src, int open_end, int src_end, byte[] open_bry, byte[] close_bry) { public static int Find_xtn_end(Xop_ctx ctx, byte[] src, int open_end, int src_end, byte[] open_bry, byte[] close_bry) {
// UNIQ; DATE:2017-03-31
Btrie_slim_mgr xtn_end_tag_trie = ctx.Tmp_mgr().Xnde__xtn_end(); Btrie_slim_mgr xtn_end_tag_trie = ctx.Tmp_mgr().Xnde__xtn_end();
xtn_end_tag_trie.Clear(); xtn_end_tag_trie.Clear();
xtn_end_tag_trie.Add_obj(Pfunc_tag.Xtag_bgn_lhs, Find_xtn_end__key__xtag);
xtn_end_tag_trie.Add_obj(open_bry, Find_xtn_end__key__bgn); xtn_end_tag_trie.Add_obj(open_bry, Find_xtn_end__key__bgn);
xtn_end_tag_trie.Add_obj(close_bry, Find_xtn_end__key__end); xtn_end_tag_trie.Add_obj(close_bry, Find_xtn_end__key__end);
int depth = 0; int depth = 0;
@ -53,30 +53,14 @@ class Xop_xnde_wkr_ {
else else
--depth; --depth;
break; break;
case Find_xtn_end__tid__xtag: // xtag found; skip over it; PAGE:it.s:La_Secchia_rapita/Canto_primo DATE:2015-12-03
int xtag_end = Find_xtag_end(ctx, src, i, src_end);
int angle_end = Bry_find_.Find_fwd(src, Byte_ascii.Angle_end, xtag_end, src_end);
i = angle_end;
break;
} }
} }
} }
return Bry_find_.Not_found; return Bry_find_.Not_found;
} }
public static int Find_xtag_end(Xop_ctx ctx, byte[] src, int pos, int src_end) { private static final int Find_xtn_end__tid__bgn = 0, Find_xtn_end__tid__end = 1;//, Find_xtn_end__tid__xtag = 2;
int xtag_bgn = pos + Pfunc_tag.Xtag_bgn_lhs.length;
int tag_id = Bry_.To_int_or(src, xtag_bgn, xtag_bgn + Pfunc_tag.Id_len, -1); if (tag_id == -1) {Xoa_app_.Usr_dlg().Warn_many("", "", "parser.xtn: could not extract id from xtag_bgn: page=~{0}", ctx.Page().Url().To_str()); return Bry_find_.Not_found;}
Bry_bfr tmp_bfr = ctx.Wiki().Utl__bfr_mkr().Get_b128();
tmp_bfr.Add(Pfunc_tag.Xtag_end_lhs).Add_int_pad_bgn(Byte_ascii.Num_0, Pfunc_tag.Id_len, tag_id).Add(Pfunc_tag.Xtag_rhs);
byte[] tag_end = tmp_bfr.To_bry_and_clear();
tmp_bfr.Mkr_rls();
int rv = Bry_find_.Find_fwd(src, tag_end, pos + Pfunc_tag.Xtag_rhs.length); if (rv == Bry_find_.Not_found) {ctx.App().Usr_dlg().Warn_many("", "", "parser.xtn: could not find xtag end: page=~{0}", ctx.Page().Url().To_str()); return Bry_find_.Not_found;}
rv = Bry_find_.Find_bwd(src, Byte_ascii.Lt, rv - 1); if (rv == Bry_find_.Not_found) {ctx.App().Usr_dlg().Warn_many("", "", "parser.xtn: could not find <: page=~{0}", ctx.Page().Url().To_str()); return Bry_find_.Not_found;}
return rv;
}
private static final int Find_xtn_end__tid__bgn = 0, Find_xtn_end__tid__end = 1, Find_xtn_end__tid__xtag = 2;
private static final Int_obj_val private static final Int_obj_val
Find_xtn_end__key__bgn = new Int_obj_val(Find_xtn_end__tid__bgn) Find_xtn_end__key__bgn = new Int_obj_val(Find_xtn_end__tid__bgn)
, Find_xtn_end__key__end = new Int_obj_val(Find_xtn_end__tid__end) , Find_xtn_end__key__end = new Int_obj_val(Find_xtn_end__tid__end)
, Find_xtn_end__key__xtag = new Int_obj_val(Find_xtn_end__tid__xtag); ;
} }

View File

@ -16,7 +16,7 @@ Apache License: https://github.com/gnosygnu/xowa/blob/master/LICENSE-APACHE2.txt
package gplx.xowa.xtns.pfuncs.strings; import gplx.*; import gplx.xowa.*; import gplx.xowa.xtns.*; import gplx.xowa.xtns.pfuncs.*; package gplx.xowa.xtns.pfuncs.strings; import gplx.*; import gplx.xowa.*; import gplx.xowa.xtns.*; import gplx.xowa.xtns.pfuncs.*;
import gplx.xowa.langs.*; import gplx.xowa.langs.kwds.*; import gplx.xowa.langs.*; import gplx.xowa.langs.kwds.*;
import gplx.xowa.parsers.*; import gplx.xowa.parsers.xndes.*; import gplx.xowa.parsers.tmpls.*; import gplx.xowa.parsers.*; import gplx.xowa.parsers.xndes.*; import gplx.xowa.parsers.tmpls.*;
public class Pfunc_tag extends Pf_func_base { public class Pfunc_tag extends Pf_func_base {// REF:CoreParserFunctions.php
@Override public int Id() {return Xol_kwd_grp_.Id_misc_tag;} @Override public int Id() {return Xol_kwd_grp_.Id_misc_tag;}
@Override public Pf_func New(int id, byte[] name) {return new Pfunc_tag().Name_(name);} @Override public Pf_func New(int id, byte[] name) {return new Pfunc_tag().Name_(name);}
@Override public boolean Func_require_colon_arg() {return true;} @Override public boolean Func_require_colon_arg() {return true;}
@ -24,15 +24,10 @@ public class Pfunc_tag extends Pf_func_base {
// make <xnde> based on {{#tag}}; EX: {{#tag:ref|a|name=1}} -> <ref name='1'>a</ref> // make <xnde> based on {{#tag}}; EX: {{#tag:ref|a|name=1}} -> <ref name='1'>a</ref>
Bry_bfr tmp_bfr = ctx.Wiki().Utl__bfr_mkr().Get_b512(); Bry_bfr tmp_bfr = ctx.Wiki().Utl__bfr_mkr().Get_b512();
try { try {
// get tag_idx, tag_data, and tag_is_ref // get vars
int tag_idx = ctx.Wiki().Parser_mgr().Tag__next_idx();
byte[] tag_name = Eval_argx(ctx, src, caller, self); if (tag_name.length == 0) return; byte[] tag_name = Eval_argx(ctx, src, caller, self); if (tag_name.length == 0) return;
Xop_xnde_tag tag = (Xop_xnde_tag)ctx.Xnde_tag_regy().Get_trie(ctx.Xnde_names_tid()).Match_exact(tag_name, 0, tag_name.length);
boolean tag_is_ref = tag != null && tag.Id() == Xop_xnde_tag_.Tid__ref;
// open tag // open tag
if (tag_is_ref) // <ref>; add <xtag_bgn> to handle nested refs; PAGE:en.w:Battle_of_Midway; DATE:2014-06-27
tmp_bfr.Add(Xtag_bgn_lhs).Add_int_pad_bgn(Byte_ascii.Num_0, 10, tag_idx).Add(Xtag_rhs);
tmp_bfr.Add_byte(Byte_ascii.Lt).Add(tag_name); // EX: "<ref" tmp_bfr.Add_byte(Byte_ascii.Lt).Add(tag_name); // EX: "<ref"
// iterate args and build attributes; EX: "|a=1|b=2" -> "a='1' b='2'" // iterate args and build attributes; EX: "|a=1|b=2" -> "a='1' b='2'"
@ -54,21 +49,12 @@ public class Pfunc_tag extends Pf_func_base {
// close tag // close tag
tmp_bfr.Add_byte(Byte_ascii.Lt).Add_byte(Byte_ascii.Slash).Add(tag_name).Add_byte(Byte_ascii.Gt); // EX: "</ref>" tmp_bfr.Add_byte(Byte_ascii.Lt).Add_byte(Byte_ascii.Slash).Add(tag_name).Add_byte(Byte_ascii.Gt); // EX: "</ref>"
if (tag_is_ref) // <ref>; add <xtag_end> to handle nested refs; PAGE:en.w:Battle_of_Midway; DATE:2014-06-27
tmp_bfr.Add(Xtag_end_lhs).Add_int_pad_bgn(Byte_ascii.Num_0, 10, tag_idx).Add(Xtag_rhs); // add to UNIQ hash; DATE:2017-03-31
bfr.Add_bfr_and_clear(tmp_bfr); byte[] val = tmp_bfr.To_bry_and_clear();
byte[] key = ctx.Wiki().Parser_mgr().Uniq_mgr().Add(tag_name, val);
bfr.Add(key);
} }
finally {tmp_bfr.Mkr_rls();} finally {tmp_bfr.Mkr_rls();}
} }
public static final byte[]
Xtag_bgn_lhs = Bry_.new_a7("<xtag_bgn id='")
, Xtag_end_lhs = Bry_.new_a7("<xtag_end id='")
, Xtag_rhs = Bry_.new_a7("'/>")
;
public static final int
Xtag_len = 27 // <xtag_bgn id='1234567890'/>
, Xtag_bgn = 14 // <xtag_bgn id='
, Id_len = 10
;
} }