From 8fa8dd24d58fce36f5cf61b5506a02ff914d95a5 Mon Sep 17 00:00:00 2001
From: Michael Schmidt <mitchi5000.ms@googlemail.com>
Date: Wed, 25 Nov 2020 22:59:40 +0100
Subject: [PATCH] Core: Fixed bug with greedy matching (#2632)

---
 components/prism-core.js     |  2 +-
 components/prism-core.min.js |  2 +-
 docs/prism-core.js.html      |  2 +-
 prism.js                     |  2 +-
 tests/core/greedy.js         | 21 +++++++++++++++++++++
 5 files changed, 25 insertions(+), 4 deletions(-)

diff --git a/components/prism-core.js b/components/prism-core.js
index 9f82910a8f..8b8343b485 100644
--- a/components/prism-core.js
+++ b/components/prism-core.js
@@ -890,7 +890,7 @@ function matchGrammar(text, tokenList, grammar, startNode, startPos, rematch) {
 
 				var removeCount = 1; // this is the to parameter of removeBetween
 
-				if (greedy && currentNode != tokenList.tail.prev) {
+				if (greedy) {
 					pattern.lastIndex = pos;
 					var match = pattern.exec(text);
 					if (!match) {
diff --git a/components/prism-core.min.js b/components/prism-core.min.js
index 267167ed8b..1589f00289 100644
--- a/components/prism-core.min.js
+++ b/components/prism-core.min.js
@@ -1 +1 @@
-var _self="undefined"!=typeof window?window:"undefined"!=typeof WorkerGlobalScope&&self instanceof WorkerGlobalScope?self:{},Prism=function(u){var c=/\blang(?:uage)?-([\w-]+)\b/i,n=0,M={manual:u.Prism&&u.Prism.manual,disableWorkerMessageHandler:u.Prism&&u.Prism.disableWorkerMessageHandler,util:{encode:function e(n){return n instanceof W?new W(n.type,e(n.content),n.alias):Array.isArray(n)?n.map(e):n.replace(/&/g,"&amp;").replace(/</g,"&lt;").replace(/\u00a0/g," ")},type:function(e){return Object.prototype.toString.call(e).slice(8,-1)},objId:function(e){return e.__id||Object.defineProperty(e,"__id",{value:++n}),e.__id},clone:function t(e,r){var a,n;switch(r=r||{},M.util.type(e)){case"Object":if(n=M.util.objId(e),r[n])return r[n];for(var i in a={},r[n]=a,e)e.hasOwnProperty(i)&&(a[i]=t(e[i],r));return a;case"Array":return n=M.util.objId(e),r[n]?r[n]:(a=[],r[n]=a,e.forEach(function(e,n){a[n]=t(e,r)}),a);default:return e}},getLanguage:function(e){for(;e&&!c.test(e.className);)e=e.parentElement;return e?(e.className.match(c)||[,"none"])[1].toLowerCase():"none"},currentScript:function(){if("undefined"==typeof document)return null;if("currentScript"in document)return document.currentScript;try{throw new Error}catch(e){var n=(/at [^(\r\n]*\((.*):.+:.+\)$/i.exec(e.stack)||[])[1];if(n){var t=document.getElementsByTagName("script");for(var r in t)if(t[r].src==n)return t[r]}return null}},isActive:function(e,n,t){for(var r="no-"+n;e;){var a=e.classList;if(a.contains(n))return!0;if(a.contains(r))return!1;e=e.parentElement}return!!t}},languages:{extend:function(e,n){var t=M.util.clone(M.languages[e]);for(var r in n)t[r]=n[r];return t},insertBefore:function(t,e,n,r){var a=(r=r||M.languages)[t],i={};for(var l in a)if(a.hasOwnProperty(l)){if(l==e)for(var o in n)n.hasOwnProperty(o)&&(i[o]=n[o]);n.hasOwnProperty(l)||(i[l]=a[l])}var s=r[t];return r[t]=i,M.languages.DFS(M.languages,function(e,n){n===s&&e!=t&&(this[e]=i)}),i},DFS:function e(n,t,r,a){a=a||{};var i=M.util.objId;for(var l in n)if(n.hasOwnProperty(l)){t.call(n,l,n[l],r||l);var o=n[l],s=M.util.type(o);"Object"!==s||a[i(o)]?"Array"!==s||a[i(o)]||(a[i(o)]=!0,e(o,t,l,a)):(a[i(o)]=!0,e(o,t,null,a))}}},plugins:{},highlightAll:function(e,n){M.highlightAllUnder(document,e,n)},highlightAllUnder:function(e,n,t){var r={callback:t,container:e,selector:'code[class*="language-"], [class*="language-"] code, code[class*="lang-"], [class*="lang-"] code'};M.hooks.run("before-highlightall",r),r.elements=Array.prototype.slice.apply(r.container.querySelectorAll(r.selector)),M.hooks.run("before-all-elements-highlight",r);for(var a,i=0;a=r.elements[i++];)M.highlightElement(a,!0===n,r.callback)},highlightElement:function(e,n,t){var r=M.util.getLanguage(e),a=M.languages[r];e.className=e.className.replace(c,"").replace(/\s+/g," ")+" language-"+r;var i=e.parentElement;i&&"pre"===i.nodeName.toLowerCase()&&(i.className=i.className.replace(c,"").replace(/\s+/g," ")+" language-"+r);var l={element:e,language:r,grammar:a,code:e.textContent};function o(e){l.highlightedCode=e,M.hooks.run("before-insert",l),l.element.innerHTML=l.highlightedCode,M.hooks.run("after-highlight",l),M.hooks.run("complete",l),t&&t.call(l.element)}if(M.hooks.run("before-sanity-check",l),!l.code)return M.hooks.run("complete",l),void(t&&t.call(l.element));if(M.hooks.run("before-highlight",l),l.grammar)if(n&&u.Worker){var s=new Worker(M.filename);s.onmessage=function(e){o(e.data)},s.postMessage(JSON.stringify({language:l.language,code:l.code,immediateClose:!0}))}else o(M.highlight(l.code,l.grammar,l.language));else o(M.util.encode(l.code))},highlight:function(e,n,t){var r={code:e,grammar:n,language:t};return M.hooks.run("before-tokenize",r),r.tokens=M.tokenize(r.code,r.grammar),M.hooks.run("after-tokenize",r),W.stringify(M.util.encode(r.tokens),r.language)},tokenize:function(e,n){var t=n.rest;if(t){for(var r in t)n[r]=t[r];delete n.rest}var a=new i;return I(a,a.head,e),function e(n,t,r,a,i,l){for(var o in r)if(r.hasOwnProperty(o)&&r[o]){var s=r[o];s=Array.isArray(s)?s:[s];for(var u=0;u<s.length;++u){if(l&&l.cause==o+","+u)return;var c=s[u],g=c.inside,f=!!c.lookbehind,h=!!c.greedy,d=0,v=c.alias;if(h&&!c.pattern.global){var p=c.pattern.toString().match(/[imsuy]*$/)[0];c.pattern=RegExp(c.pattern.source,p+"g")}for(var m=c.pattern||c,y=a.next,k=i;y!==t.tail&&!(l&&k>=l.reach);k+=y.value.length,y=y.next){var b=y.value;if(t.length>n.length)return;if(!(b instanceof W)){var x=1;if(h&&y!=t.tail.prev){m.lastIndex=k;var w=m.exec(n);if(!w)break;var A=w.index+(f&&w[1]?w[1].length:0),P=w.index+w[0].length,S=k;for(S+=y.value.length;S<=A;)y=y.next,S+=y.value.length;if(S-=y.value.length,k=S,y.value instanceof W)continue;for(var E=y;E!==t.tail&&(S<P||"string"==typeof E.value);E=E.next)x++,S+=E.value.length;x--,b=n.slice(k,S),w.index-=k}else{m.lastIndex=0;var w=m.exec(b)}if(w){f&&(d=w[1]?w[1].length:0);var A=w.index+d,O=w[0].slice(d),P=A+O.length,L=b.slice(0,A),N=b.slice(P),j=k+b.length;l&&j>l.reach&&(l.reach=j);var C=y.prev;L&&(C=I(t,C,L),k+=L.length),z(t,C,x);var _=new W(o,g?M.tokenize(O,g):O,v,O);y=I(t,C,_),N&&I(t,y,N),1<x&&e(n,t,r,y.prev,k,{cause:o+","+u,reach:j})}}}}}}(e,a,n,a.head,0),function(e){var n=[],t=e.head.next;for(;t!==e.tail;)n.push(t.value),t=t.next;return n}(a)},hooks:{all:{},add:function(e,n){var t=M.hooks.all;t[e]=t[e]||[],t[e].push(n)},run:function(e,n){var t=M.hooks.all[e];if(t&&t.length)for(var r,a=0;r=t[a++];)r(n)}},Token:W};function W(e,n,t,r){this.type=e,this.content=n,this.alias=t,this.length=0|(r||"").length}function i(){var e={value:null,prev:null,next:null},n={value:null,prev:e,next:null};e.next=n,this.head=e,this.tail=n,this.length=0}function I(e,n,t){var r=n.next,a={value:t,prev:n,next:r};return n.next=a,r.prev=a,e.length++,a}function z(e,n,t){for(var r=n.next,a=0;a<t&&r!==e.tail;a++)r=r.next;(n.next=r).prev=n,e.length-=a}if(u.Prism=M,W.stringify=function n(e,t){if("string"==typeof e)return e;if(Array.isArray(e)){var r="";return e.forEach(function(e){r+=n(e,t)}),r}var a={type:e.type,content:n(e.content,t),tag:"span",classes:["token",e.type],attributes:{},language:t},i=e.alias;i&&(Array.isArray(i)?Array.prototype.push.apply(a.classes,i):a.classes.push(i)),M.hooks.run("wrap",a);var l="";for(var o in a.attributes)l+=" "+o+'="'+(a.attributes[o]||"").replace(/"/g,"&quot;")+'"';return"<"+a.tag+' class="'+a.classes.join(" ")+'"'+l+">"+a.content+"</"+a.tag+">"},!u.document)return u.addEventListener&&(M.disableWorkerMessageHandler||u.addEventListener("message",function(e){var n=JSON.parse(e.data),t=n.language,r=n.code,a=n.immediateClose;u.postMessage(M.highlight(r,M.languages[t],t)),a&&u.close()},!1)),M;var e=M.util.currentScript();function t(){M.manual||M.highlightAll()}if(e&&(M.filename=e.src,e.hasAttribute("data-manual")&&(M.manual=!0)),!M.manual){var r=document.readyState;"loading"===r||"interactive"===r&&e&&e.defer?document.addEventListener("DOMContentLoaded",t):window.requestAnimationFrame?window.requestAnimationFrame(t):window.setTimeout(t,16)}return M}(_self);"undefined"!=typeof module&&module.exports&&(module.exports=Prism),"undefined"!=typeof global&&(global.Prism=Prism);
\ No newline at end of file
+var _self="undefined"!=typeof window?window:"undefined"!=typeof WorkerGlobalScope&&self instanceof WorkerGlobalScope?self:{},Prism=function(u){var c=/\blang(?:uage)?-([\w-]+)\b/i,n=0,M={manual:u.Prism&&u.Prism.manual,disableWorkerMessageHandler:u.Prism&&u.Prism.disableWorkerMessageHandler,util:{encode:function e(n){return n instanceof W?new W(n.type,e(n.content),n.alias):Array.isArray(n)?n.map(e):n.replace(/&/g,"&amp;").replace(/</g,"&lt;").replace(/\u00a0/g," ")},type:function(e){return Object.prototype.toString.call(e).slice(8,-1)},objId:function(e){return e.__id||Object.defineProperty(e,"__id",{value:++n}),e.__id},clone:function t(e,r){var a,n;switch(r=r||{},M.util.type(e)){case"Object":if(n=M.util.objId(e),r[n])return r[n];for(var i in a={},r[n]=a,e)e.hasOwnProperty(i)&&(a[i]=t(e[i],r));return a;case"Array":return n=M.util.objId(e),r[n]?r[n]:(a=[],r[n]=a,e.forEach(function(e,n){a[n]=t(e,r)}),a);default:return e}},getLanguage:function(e){for(;e&&!c.test(e.className);)e=e.parentElement;return e?(e.className.match(c)||[,"none"])[1].toLowerCase():"none"},currentScript:function(){if("undefined"==typeof document)return null;if("currentScript"in document)return document.currentScript;try{throw new Error}catch(e){var n=(/at [^(\r\n]*\((.*):.+:.+\)$/i.exec(e.stack)||[])[1];if(n){var t=document.getElementsByTagName("script");for(var r in t)if(t[r].src==n)return t[r]}return null}},isActive:function(e,n,t){for(var r="no-"+n;e;){var a=e.classList;if(a.contains(n))return!0;if(a.contains(r))return!1;e=e.parentElement}return!!t}},languages:{extend:function(e,n){var t=M.util.clone(M.languages[e]);for(var r in n)t[r]=n[r];return t},insertBefore:function(t,e,n,r){var a=(r=r||M.languages)[t],i={};for(var l in a)if(a.hasOwnProperty(l)){if(l==e)for(var o in n)n.hasOwnProperty(o)&&(i[o]=n[o]);n.hasOwnProperty(l)||(i[l]=a[l])}var s=r[t];return r[t]=i,M.languages.DFS(M.languages,function(e,n){n===s&&e!=t&&(this[e]=i)}),i},DFS:function e(n,t,r,a){a=a||{};var i=M.util.objId;for(var l in n)if(n.hasOwnProperty(l)){t.call(n,l,n[l],r||l);var o=n[l],s=M.util.type(o);"Object"!==s||a[i(o)]?"Array"!==s||a[i(o)]||(a[i(o)]=!0,e(o,t,l,a)):(a[i(o)]=!0,e(o,t,null,a))}}},plugins:{},highlightAll:function(e,n){M.highlightAllUnder(document,e,n)},highlightAllUnder:function(e,n,t){var r={callback:t,container:e,selector:'code[class*="language-"], [class*="language-"] code, code[class*="lang-"], [class*="lang-"] code'};M.hooks.run("before-highlightall",r),r.elements=Array.prototype.slice.apply(r.container.querySelectorAll(r.selector)),M.hooks.run("before-all-elements-highlight",r);for(var a,i=0;a=r.elements[i++];)M.highlightElement(a,!0===n,r.callback)},highlightElement:function(e,n,t){var r=M.util.getLanguage(e),a=M.languages[r];e.className=e.className.replace(c,"").replace(/\s+/g," ")+" language-"+r;var i=e.parentElement;i&&"pre"===i.nodeName.toLowerCase()&&(i.className=i.className.replace(c,"").replace(/\s+/g," ")+" language-"+r);var l={element:e,language:r,grammar:a,code:e.textContent};function o(e){l.highlightedCode=e,M.hooks.run("before-insert",l),l.element.innerHTML=l.highlightedCode,M.hooks.run("after-highlight",l),M.hooks.run("complete",l),t&&t.call(l.element)}if(M.hooks.run("before-sanity-check",l),!l.code)return M.hooks.run("complete",l),void(t&&t.call(l.element));if(M.hooks.run("before-highlight",l),l.grammar)if(n&&u.Worker){var s=new Worker(M.filename);s.onmessage=function(e){o(e.data)},s.postMessage(JSON.stringify({language:l.language,code:l.code,immediateClose:!0}))}else o(M.highlight(l.code,l.grammar,l.language));else o(M.util.encode(l.code))},highlight:function(e,n,t){var r={code:e,grammar:n,language:t};return M.hooks.run("before-tokenize",r),r.tokens=M.tokenize(r.code,r.grammar),M.hooks.run("after-tokenize",r),W.stringify(M.util.encode(r.tokens),r.language)},tokenize:function(e,n){var t=n.rest;if(t){for(var r in t)n[r]=t[r];delete n.rest}var a=new i;return I(a,a.head,e),function e(n,t,r,a,i,l){for(var o in r)if(r.hasOwnProperty(o)&&r[o]){var s=r[o];s=Array.isArray(s)?s:[s];for(var u=0;u<s.length;++u){if(l&&l.cause==o+","+u)return;var c=s[u],g=c.inside,f=!!c.lookbehind,h=!!c.greedy,d=0,v=c.alias;if(h&&!c.pattern.global){var p=c.pattern.toString().match(/[imsuy]*$/)[0];c.pattern=RegExp(c.pattern.source,p+"g")}for(var m=c.pattern||c,y=a.next,k=i;y!==t.tail&&!(l&&k>=l.reach);k+=y.value.length,y=y.next){var b=y.value;if(t.length>n.length)return;if(!(b instanceof W)){var x=1;if(h){m.lastIndex=k;var w=m.exec(n);if(!w)break;var A=w.index+(f&&w[1]?w[1].length:0),P=w.index+w[0].length,S=k;for(S+=y.value.length;S<=A;)y=y.next,S+=y.value.length;if(S-=y.value.length,k=S,y.value instanceof W)continue;for(var E=y;E!==t.tail&&(S<P||"string"==typeof E.value);E=E.next)x++,S+=E.value.length;x--,b=n.slice(k,S),w.index-=k}else{m.lastIndex=0;var w=m.exec(b)}if(w){f&&(d=w[1]?w[1].length:0);var A=w.index+d,O=w[0].slice(d),P=A+O.length,L=b.slice(0,A),N=b.slice(P),j=k+b.length;l&&j>l.reach&&(l.reach=j);var C=y.prev;L&&(C=I(t,C,L),k+=L.length),z(t,C,x);var _=new W(o,g?M.tokenize(O,g):O,v,O);y=I(t,C,_),N&&I(t,y,N),1<x&&e(n,t,r,y.prev,k,{cause:o+","+u,reach:j})}}}}}}(e,a,n,a.head,0),function(e){var n=[],t=e.head.next;for(;t!==e.tail;)n.push(t.value),t=t.next;return n}(a)},hooks:{all:{},add:function(e,n){var t=M.hooks.all;t[e]=t[e]||[],t[e].push(n)},run:function(e,n){var t=M.hooks.all[e];if(t&&t.length)for(var r,a=0;r=t[a++];)r(n)}},Token:W};function W(e,n,t,r){this.type=e,this.content=n,this.alias=t,this.length=0|(r||"").length}function i(){var e={value:null,prev:null,next:null},n={value:null,prev:e,next:null};e.next=n,this.head=e,this.tail=n,this.length=0}function I(e,n,t){var r=n.next,a={value:t,prev:n,next:r};return n.next=a,r.prev=a,e.length++,a}function z(e,n,t){for(var r=n.next,a=0;a<t&&r!==e.tail;a++)r=r.next;(n.next=r).prev=n,e.length-=a}if(u.Prism=M,W.stringify=function n(e,t){if("string"==typeof e)return e;if(Array.isArray(e)){var r="";return e.forEach(function(e){r+=n(e,t)}),r}var a={type:e.type,content:n(e.content,t),tag:"span",classes:["token",e.type],attributes:{},language:t},i=e.alias;i&&(Array.isArray(i)?Array.prototype.push.apply(a.classes,i):a.classes.push(i)),M.hooks.run("wrap",a);var l="";for(var o in a.attributes)l+=" "+o+'="'+(a.attributes[o]||"").replace(/"/g,"&quot;")+'"';return"<"+a.tag+' class="'+a.classes.join(" ")+'"'+l+">"+a.content+"</"+a.tag+">"},!u.document)return u.addEventListener&&(M.disableWorkerMessageHandler||u.addEventListener("message",function(e){var n=JSON.parse(e.data),t=n.language,r=n.code,a=n.immediateClose;u.postMessage(M.highlight(r,M.languages[t],t)),a&&u.close()},!1)),M;var e=M.util.currentScript();function t(){M.manual||M.highlightAll()}if(e&&(M.filename=e.src,e.hasAttribute("data-manual")&&(M.manual=!0)),!M.manual){var r=document.readyState;"loading"===r||"interactive"===r&&e&&e.defer?document.addEventListener("DOMContentLoaded",t):window.requestAnimationFrame?window.requestAnimationFrame(t):window.setTimeout(t,16)}return M}(_self);"undefined"!=typeof module&&module.exports&&(module.exports=Prism),"undefined"!=typeof global&&(global.Prism=Prism);
\ No newline at end of file
diff --git a/docs/prism-core.js.html b/docs/prism-core.js.html
index fed9633629..f8a5edcd1e 100644
--- a/docs/prism-core.js.html
+++ b/docs/prism-core.js.html
@@ -943,7 +943,7 @@ <h1 class="page-title">prism-core.js</h1>
 
 				var removeCount = 1; // this is the to parameter of removeBetween
 
-				if (greedy &amp;&amp; currentNode != tokenList.tail.prev) {
+				if (greedy) {
 					pattern.lastIndex = pos;
 					var match = pattern.exec(text);
 					if (!match) {
diff --git a/prism.js b/prism.js
index c25249c8e8..02af74b4c8 100644
--- a/prism.js
+++ b/prism.js
@@ -895,7 +895,7 @@ function matchGrammar(text, tokenList, grammar, startNode, startPos, rematch) {
 
 				var removeCount = 1; // this is the to parameter of removeBetween
 
-				if (greedy && currentNode != tokenList.tail.prev) {
+				if (greedy) {
 					pattern.lastIndex = pos;
 					var match = pattern.exec(text);
 					if (!match) {
diff --git a/tests/core/greedy.js b/tests/core/greedy.js
index f21f87d1e3..d7fc9fbcc7 100644
--- a/tests/core/greedy.js
+++ b/tests/core/greedy.js
@@ -84,4 +84,25 @@ describe('Greedy matching', function () {
 			]
 		});
 	});
+
+	it('should always match tokens against the whole text', function () {
+		// this is to test for a bug where greedy tokens where matched like non-greedy ones if the token stream ended on
+		// a string
+		testTokens({
+			grammar: {
+				'a': /a/,
+				'b': {
+					pattern: /^b/,
+					greedy: true
+				}
+			},
+			code: 'bab',
+			expected: [
+				["b", "b"],
+				["a", "a"],
+				"b"
+			]
+		});
+	});
+
 });