Fix #73817: Incorrect entries in get_html_translation_table

Due to incorrect string termination and length handling, several HTML
entities missed the trailing semicolon.

We also fix the obviously wrong expectations in two already existing
tests.

NEWS

@@ -9,6 +9,9 @@ PHP                                                                        NEWS
 - PDO_Firebird:
   . Fixed bug #76488 (Memory leak when fetching a BLOB field). (Simonov Denis)
 
+- Standard:
+  . Fixed bug #73817 (Incorrect entries in get_html_translation_table). (cmb)
+
 - Zip:
   . Fixed bug #76524 (ZipArchive memory leak (OVERWRITE flag and empty archive)).
     (Timur Ibragimov)

ext/standard/html.c

@@ -1598,8 +1598,7 @@ static inline void write_s3row_data(
 			written_k2 = write_octet_sequence((unsigned char*)&key[written_k1], charset, spe_cp);
 			memcpy(&entity[1], mcpr[i].normal_entry.entity, l);
 			entity[l + 1] = ';';
-			entity[l + 1] = '\0';
+			add_assoc_stringl_ex(arr, key, written_k1 + written_k2, entity, l + 2);
-			add_assoc_stringl_ex(arr, key, written_k1 + written_k2, entity, l + 1);
 		}
 	}
 }

ext/standard/tests/strings/bug73817.phpt

@@ -0,0 +1,14 @@
+--TEST--
+Bug #73817 (Incorrect entries in get_html_translation_table)
+--FILE--
+<?php
+$entities = get_html_translation_table( HTML_ENTITIES, ENT_QUOTES | ENT_HTML5);
+foreach ($entities as $entity) {
+    if (substr($entity, -1) !== ';') {
+        var_dump($entity);
+    }
+}
+?>
+===DONE===
+--EXPECT--
+===DONE===

ext/standard/tests/strings/get_html_translation_table_basic5.phpt

@@ -273,27 +273,27 @@ Array
     [≢] => ≢
     [≭] => ≭
     [≠] => ≠
-    [≧̸] => &NotGreaterFullEqual
+    [≧̸] => ≧̸
-    [≫̸] => &NotGreaterGreater
+    [≫̸] => ≫̸
     [≹] => ≹
-    [⧏̸] => &NotLeftTriangleBar
+    [⧏̸] => ⧏̸
     [≮] => ≮
     [≰] => ≰
-    [⪢̸] => &NotNestedGreaterGreater
+    [⪢̸] => ⪢̸
-    [⪡̸] => &NotNestedLessLess
+    [⪡̸] => ⪡̸
-    [⪯̸] => &NotPrecedesEqual
+    [⪯̸] => ⪯̸
     [⋠] => ⋠
-    [⧐̸] => &NotRightTriangleBar
+    [⧐̸] => ⧐̸
     [⋭] => ⋭
-    [⊏̸] => &NotSquareSubset
+    [⊏̸] => ⊏̸
     [⋢] => ⋢
-    [⊐̸] => &NotSquareSuperset
+    [⊐̸] => ⊐̸
     [⋣] => ⋣
     [⊈] => ⊈
     [⊁] => ⊁
-    [⪰̸] => &NotSucceedsEqual
+    [⪰̸] => ⪰̸
     [⋡] => ⋡
-    [≿̸] => &NotSucceedsTilde
+    [≿̸] => ≿̸
     [⊉] => ⊉
     [≁] => ≁
     [𝒩] => 𝒩
@@ -394,7 +394,7 @@ Array
     [Т] => Т
     [𝔗] => 𝔗
     [Θ] => Θ
-    [  ] => &ThickSpace
+    [  ] =>   
     [ ] =>  
     [≅] => ≅
     [𝕋] => 𝕋
@@ -469,7 +469,7 @@ Array
     [á] => á
     [ă] => ă
     [∾] => ∾
-    [∾̳] => &acE
+    [∾̳] => ∾̳
     [∿] => ∿
     [â] => â
     [а] => а
@@ -552,8 +552,8 @@ Array
     [░] => ░
     [▓] => ▓
     [█] => █
-    [=⃥] => &bne
+    [=⃥] => =⃥
-    [≡⃥] => &bnequiv
+    [≡⃥] => ≡⃥
     [⌐] => ⌐
     [𝕓] => 𝕓
     [⋈] => ⋈
@@ -616,7 +616,7 @@ Array
     [⩋] => ⩋
     [⩇] => ⩇
     [⩀] => ⩀
-    [∩︀] => &caps
+    [∩︀] => ∩︀
     [⁁] => ⁁
     [⩍] => ⩍
     [č] => č
@@ -668,7 +668,7 @@ Array
     [⩊] => ⩊
     [⊍] => ⊍
     [⩅] => ⩅
-    [∪︀] => &cups
+    [∪︀] => ∪︀
     [↷] => ↷
     [⤼] => ⤼
     [⋞] => ⋞
@@ -772,7 +772,7 @@ Array
     [ffl] => ffl
     [𝔣] => 𝔣
     [fi] => fi
-    [fj] => &fjlig
+    [fj] => fj
     [♭] => ♭
     [fl] => fl
     [▱] => ▱
@@ -814,7 +814,7 @@ Array
     [⪀] => ⪀
     [⪂] => ⪂
     [⪄] => ⪄
-    [⋛︀] => &gesl
+    [⋛︀] => ⋛︀
     [⪔] => ⪔
     [𝔤] => 𝔤
     [≫] => ≫
@@ -841,7 +841,7 @@ Array
     [⥸] => ⥸
     [⋗] => ⋗
     [⋛] => ⋛
-    [≩︀] => &gvertneqq
+    [≩︀] => ≩︀
     [⇔] => ⇔
     [ ] =>  
     [½] => ½
@@ -940,7 +940,7 @@ Array
     [⪫] => ⪫
     [⤙] => ⤙
     [⪭] => ⪭
-    [⪭︀] => &lates
+    [⪭︀] => ⪭︀
     [⤌] => ⤌
     [❲] => ❲
     [{] => {
@@ -965,7 +965,7 @@ Array
     [⩿] => ⩿
     [⪁] => ⪁
     [⪃] => ⪃
-    [⋚︀] => &lesg
+    [⋚︀] => ⋚︀
     [⪓] => ⪓
     [⋖] => ⋖
     [⋚] => ⋚
@@ -1022,7 +1022,7 @@ Array
     [◃] => ◃
     [⥊] => ⥊
     [⥦] => ⥦
-    [≨︀] => &lvertneqq
+    [≨︀] => ≨︀
     [∺] => ∺
     [¯] => ¯
     [♂] => ♂
@@ -1046,42 +1046,42 @@ Array
     [𝓂] => 𝓂
     [μ] => μ
     [⊸] => ⊸
-    [⋙̸] => &nGg
+    [⋙̸] => ⋙̸
-    [≫⃒] => &nGt
+    [≫⃒] => ≫⃒
     [⇍] => ⇍
-    [⋘̸] => &nLl
+    [⋘̸] => ⋘̸
-    [≪⃒] => &nLt
+    [≪⃒] => ≪⃒
-    [≪̸] => &nLtv
+    [≪̸] => ≪̸
     [⊯] => ⊯
     [⊮] => ⊮
     [∇] => ∇
     [ń] => ń
-    [∠⃒] => &nang
+    [∠⃒] => ∠⃒
-    [⩰̸] => &napE
+    [⩰̸] => ⩰̸
-    [≋̸] => &napid
+    [≋̸] => ≋̸
     [ʼn] => ʼn
     [≉] => ≉
     [♮] => ♮
     [ℕ] => ℕ
     [ ] =>  
-    [≎̸] => &nbump
+    [≎̸] => ≎̸
-    [≏̸] => &nbumpe
+    [≏̸] => ≏̸
     [⩃] => ⩃
     [ň] => ň
     [ņ] => ņ
     [≇] => ≇
-    [⩭̸] => &ncongdot
+    [⩭̸] => ⩭̸
     [⩂] => ⩂
     [н] => н
     [–] => –
     [⇗] => ⇗
     [⤤] => ⤤
-    [≐̸] => &nedot
+    [≐̸] => ≐̸
-    [≂̸] => &nesim
+    [≂̸] => ≂̸
     [∄] => ∄
     [𝔫] => 𝔫
     [≱] => ≱
-    [⩾̸] => &nges
+    [⩾̸] => ⩾̸
     [≵] => ≵
     [≯] => ≯
     [⇎] => ⇎
@@ -1089,41 +1089,41 @@ Array
     [⋼] => ⋼
     [⋺] => ⋺
     [њ] => њ
-    [≦̸] => &nlE
+    [≦̸] => ≦̸
     [‥] => ‥
     [↚] => ↚
     [↮] => ↮
-    [⩽̸] => &nles
+    [⩽̸] => ⩽̸
     [≴] => ≴
     [⋪] => ⋪
     [⋬] => ⋬
     [𝕟] => 𝕟
     [¬] => ¬
     [∉] => ∉
-    [⋹̸] => &notinE
+    [⋹̸] => ⋹̸
-    [⋵̸] => &notindot
+    [⋵̸] => ⋵̸
     [⋷] => ⋷
     [⋶] => ⋶
     [∌] => ∌
     [⋾] => ⋾
     [⋽] => ⋽
     [∦] => ∦
-    [⫽⃥] => &nparsl
+    [⫽⃥] => ⫽⃥
-    [∂̸] => &npart
+    [∂̸] => ∂̸
     [⨔] => ⨔
     [⊀] => ⊀
     [⇏] => ⇏
     [↛] => ↛
-    [⤳̸] => &nrarrc
+    [⤳̸] => ⤳̸
-    [↝̸] => &nrarrw
+    [↝̸] => ↝̸
     [𝓃] => 𝓃
     [∤] => ∤
     [≄] => ≄
     [⊄] => ⊄
-    [⫅̸] => &nsubE
+    [⫅̸] => ⫅̸
     [⊅] => ⊅
-    [⊃⃒] => &nsupset
+    [⊃⃒] => ⊃⃒
-    [⫆̸] => &nsupseteqq
+    [⫆̸] => ⫆̸
     [ñ] => ñ
     [≸] => ≸
     [⋫] => ⋫
@@ -1133,18 +1133,18 @@ Array
     [ ] =>  
     [⊭] => ⊭
     [⤄] => ⤄
-    [≍⃒] => &nvap
+    [≍⃒] => ≍⃒
     [⊬] => ⊬
-    [≥⃒] => &nvge
+    [≥⃒] => ≥⃒
-    [>⃒] => &nvgt
+    [>⃒] => >⃒
     [⧞] => ⧞
     [⤂] => ⤂
-    [≤⃒] => &nvle
+    [≤⃒] => ≤⃒
-    [<⃒] => &nvlt
+    [<⃒] => &nvlt;
-    [⊴⃒] => &nvltrie
+    [⊴⃒] => &nvltrie;
     [⤃] => &nvrArr;
-    [⊵⃒] => &nvrtrie
+    [⊵⃒] => &nvrtrie;
-    [∼⃒] => &nvsim
+    [∼⃒] => &nvsim;
     [⇖] => &nwArr;
     [⤣] => &nwarhk;
     [↖] => &nwarrow;
@@ -1254,7 +1254,7 @@ Array
     [⇛] => &rAarr;
     [⤜] => &rAtail;
     [⥤] => &rHar;
-    [∽̱] => &race
+    [∽̱] => &race;
     [ŕ] => &racute;
     [⦳] => &raemptyv;
     [⦒] => &rangd;
@@ -1364,7 +1364,7 @@ Array
     [⌣] => &smile;
     [⪪] => &smt;
     [⪬] => &smte;
-    [⪬︀] => &smtes
+    [⪬︀] => &smtes;
     [ь] => &softcy;
     [/] => &sol;
     [⧄] => &solb;
@@ -1372,9 +1372,9 @@ Array
     [𝕤] => &sopf;
     [♠] => &spadesuit;
     [⊓] => &sqcap;
-    [⊓︀] => &sqcaps
+    [⊓︀] => &sqcaps;
     [⊔] => &sqcup;
-    [⊔︀] => &sqcups
+    [⊔︀] => &sqcups;
     [⊏] => &sqsub;
     [⊐] => &sqsupset;
     [▪] => &squarf;
@@ -1501,7 +1501,7 @@ Array
     [⫩] => &vBarv;
     [⦜] => &vangrt;
     [ϰ] => &varkappa;
-    [⫌︀] => &varsupsetneqq
+    [⫌︀] => &varsupsetneqq;
     [⊲] => &vartriangleleft;
     [в] => &vcy;
     [⊢] => &vdash;
@@ -1510,13 +1510,13 @@ Array
     [⋮] => &vellip;
     [|] => &vert;
     [𝔳] => &vfr;
-    [⊂⃒] => &vnsub
+    [⊂⃒] => &vnsub;
     [𝕧] => &vopf;
     [⊳] => &vrtri;
     [𝓋] => &vscr;
-    [⫋︀] => &vsubnE
+    [⫋︀] => &vsubnE;
-    [⊊︀] => &vsubne
+    [⊊︀] => &vsubne;
-    [⊋︀] => &vsupne
+    [⊋︀] => &vsupne;
     [⦚] => &vzigzag;
     [ŵ] => &wcirc;
     [⩟] => &wedbar;

ext/standard/tests/strings/get_html_translation_table_basic6.phpt

@@ -81,7 +81,7 @@ Array
     [^] => ^
     [_] => _
     [`] => `
-    [fj] => &fjlig
+    [fj] => fj
     [{] => {
     [|] => |
     [}] => }