From 874ea39ec0f278a48b26a172d877a094d17248eb Mon Sep 17 00:00:00 2001
From: Carter McBride <18412686+carterworks@users.noreply.github.com>
Date: Tue, 1 Sep 2026 13:33:38 -0600
Subject: [PATCH] feat: add XML grammar

---
 README.md                             |   4 +-
 docs/index.html                       |  17 +-
 src/grammars/xml.js                   | 381 ++++++++++++++++++++++++++
 test/fixtures/grammar-exhaustive.html |  12 +
 test/grammar-dependencies.spec.js     |   2 +
 5 files changed, 413 insertions(+), 3 deletions(-)
 create mode 100644 src/grammars/xml.js

diff --git a/README.md b/README.md
index cca0f63..0dc0e54 100644
--- a/README.md
+++ b/README.md
@@ -13,7 +13,7 @@ your markup stays clean and editable.
 
 - About 2 KiB compressed
 - No runtime dependencies
-- 37 languages, loaded on demand
+- 41 languages, loaded on demand
 - 10 bundled themes
 - Clean DOM with no token markup
 - Programmatic, automatic, and web component APIs
@@ -191,7 +191,7 @@ MicroLighter includes these grammars:
 `git-diff`, `go`, `graphql`, `heex`, `html`, `ini`, `java`, `javascript`, `json`,
 `kotlin`, `lua`, `markdown`, `nginx`, `objective-c`, `perl`, `php`, `powershell`,
 `python`, `r`, `ruby`, `rust`, `scss`, `sql`, `svelte`, `swift`, `toml`, `tsx`,
-`typescript`, `vue`, and `yaml`.
+`typescript`, `vue`, `xml`, and `yaml`.
 
 Grammars are ES modules and load on demand.
 
diff --git a/docs/index.html b/docs/index.html
index 2aeab99..b8194cf 100644
--- a/docs/index.html
+++ b/docs/index.html
@@ -121,7 +121,7 @@ <h2>No more spans!</h2>
       <article class="feature">
         <span class="feature-index" aria-hidden="true">02</span>
         <div class="feature-specimen size-specimen" aria-hidden="true">
-          <span class="size-value">2.09</span><span class="size-unit">kb<br>gzip</span>
+          <span class="size-value">2.10</span><span class="size-unit">kb<br>gzip</span>
         </div>
         <h2>Blazingly fast!!</h2>
       </article>
@@ -347,6 +347,7 @@ <h2 id="language-index-heading">Supported languages</h2>
           <h3>Web</h3>
           <ul>
             <li data-lang="html">HTML</li>
+            <li data-lang="xml">XML</li>
             <li data-lang="css">CSS</li>
             <li data-lang="scss">SCSS</li>
             <li data-lang="javascript">JavaScript</li>
@@ -690,6 +691,20 @@ <h2 id="playground-label">Playground</h2>
 &lt;/script&gt;
 
 &lt;button @click="count++"&gt;Count: {{ count }}&lt;/button&gt;</code></pre>
+      </template>
+      <template data-lang="xml" data-label="XML">
+        <pre><code class="language-xml">&lt;?xml version="1.0" encoding="UTF-8"?&gt;
+&lt;!DOCTYPE catalog [
+  &lt;!ENTITY publisher "MicroLighter Press"&gt;
+]&gt;
+&lt;!-- Namespaced inventory feed --&gt;
+&lt;catalog xmlns:book="urn:example:books"&gt;
+  &lt;book:item id="bk-42" available="true"&gt;
+    &lt;title&gt;Syntax &amp;amp; Semantics by &amp;publisher;&lt;/title&gt;
+    &lt;summary&gt;&lt;![CDATA[Use &lt;tokens&gt; safely.]]&gt;&lt;/summary&gt;
+    &lt;book:cover href="cover.jpg" /&gt;
+  &lt;/book:item&gt;
+&lt;/catalog&gt;</code></pre>
       </template>
       <template data-lang="yaml" data-label="YAML">
         <pre><code class="language-yaml">name: CI
diff --git a/src/grammars/xml.js b/src/grammars/xml.js
new file mode 100644
index 0000000..795a314
--- /dev/null
+++ b/src/grammars/xml.js
@@ -0,0 +1,381 @@
+// Reference: Microsoft VS Code (MIT) - https://github.com/microsoft/vscode/blob/main/extensions/xml/syntaxes/xml.tmLanguage.json
+export default {
+  "scopeName": "text.xml",
+  "patterns": [
+    {
+      "begin": "(<\\?)\\s*([-_a-zA-Z0-9]+)",
+      "captures": {
+        "1": {
+          "name": "punctuation.definition.tag.xml"
+        },
+        "2": {
+          "name": "entity.name.tag.xml"
+        }
+      },
+      "end": "(\\?>)",
+      "name": "meta.tag.preprocessor.xml",
+      "patterns": [
+        {
+          "match": " ([a-zA-Z-]+)",
+          "name": "entity.other.attribute-name.xml"
+        },
+        {
+          "include": "#doublequotedString"
+        },
+        {
+          "include": "#singlequotedString"
+        }
+      ]
+    },
+    {
+      "begin": "(<!)(DOCTYPE)\\s+([:a-zA-Z_][:a-zA-Z0-9_.-]*)",
+      "captures": {
+        "1": {
+          "name": "punctuation.definition.tag.xml"
+        },
+        "2": {
+          "name": "keyword.other.doctype.xml"
+        },
+        "3": {
+          "name": "variable.language.documentroot.xml"
+        }
+      },
+      "end": "\\s*(>)",
+      "name": "meta.tag.sgml.doctype.xml",
+      "patterns": [
+        {
+          "include": "#internalSubset"
+        }
+      ]
+    },
+    {
+      "include": "#comments"
+    },
+    {
+      "begin": "(<)((?:([-_a-zA-Z0-9]+)(:))?([-_a-zA-Z0-9:]+))(?=(\\s[^>]*)?></\\2>)",
+      "beginCaptures": {
+        "1": {
+          "name": "punctuation.definition.tag.xml"
+        },
+        "2": {
+          "name": "entity.name.tag.xml"
+        },
+        "3": {
+          "name": "entity.name.tag.namespace.xml"
+        },
+        "4": {
+          "name": "punctuation.separator.namespace.xml"
+        },
+        "5": {
+          "name": "entity.name.tag.localname.xml"
+        }
+      },
+      "end": "(>)(</)((?:([-_a-zA-Z0-9]+)(:))?([-_a-zA-Z0-9:]+))(>)",
+      "endCaptures": {
+        "1": {
+          "name": "punctuation.definition.tag.xml"
+        },
+        "2": {
+          "name": "punctuation.definition.tag.xml"
+        },
+        "3": {
+          "name": "entity.name.tag.xml"
+        },
+        "4": {
+          "name": "entity.name.tag.namespace.xml"
+        },
+        "5": {
+          "name": "punctuation.separator.namespace.xml"
+        },
+        "6": {
+          "name": "entity.name.tag.localname.xml"
+        },
+        "7": {
+          "name": "punctuation.definition.tag.xml"
+        }
+      },
+      "name": "meta.tag.no-content.xml",
+      "patterns": [
+        {
+          "include": "#tagStuff"
+        }
+      ]
+    },
+    {
+      "begin": "(</?)(?:([-\\w\\.]+)((:)))?([-\\w\\.:]+)",
+      "captures": {
+        "1": {
+          "name": "punctuation.definition.tag.xml"
+        },
+        "2": {
+          "name": "entity.name.tag.namespace.xml"
+        },
+        "3": {
+          "name": "entity.name.tag.xml"
+        },
+        "4": {
+          "name": "punctuation.separator.namespace.xml"
+        },
+        "5": {
+          "name": "entity.name.tag.localname.xml"
+        }
+      },
+      "end": "(/?>)",
+      "name": "meta.tag.xml",
+      "patterns": [
+        {
+          "include": "#tagStuff"
+        }
+      ]
+    },
+    {
+      "include": "#entity"
+    },
+    {
+      "include": "#bare-ampersand"
+    },
+    {
+      "begin": "<%@",
+      "beginCaptures": {
+        "0": {
+          "name": "punctuation.section.embedded.begin.xml"
+        }
+      },
+      "end": "%>",
+      "endCaptures": {
+        "0": {
+          "name": "punctuation.section.embedded.end.xml"
+        }
+      },
+      "name": "source.java-props.embedded.xml",
+      "patterns": [
+        {
+          "match": "page|include|taglib",
+          "name": "keyword.other.page-props.xml"
+        }
+      ]
+    },
+    {
+      "begin": "<%[!=]?(?!--)",
+      "beginCaptures": {
+        "0": {
+          "name": "punctuation.section.embedded.begin.xml"
+        }
+      },
+      "end": "(?!--)%>",
+      "endCaptures": {
+        "0": {
+          "name": "punctuation.section.embedded.end.xml"
+        }
+      },
+      "name": "source.java.embedded.xml",
+      "patterns": [
+        {
+          "include": "source.java"
+        }
+      ]
+    },
+    {
+      "begin": "<!\\[CDATA\\[",
+      "beginCaptures": {
+        "0": {
+          "name": "punctuation.definition.string.begin.xml"
+        }
+      },
+      "end": "]]>",
+      "endCaptures": {
+        "0": {
+          "name": "punctuation.definition.string.end.xml"
+        }
+      },
+      "name": "string.unquoted.cdata.xml"
+    }
+  ],
+  "repository": {
+    "EntityDecl": {
+      "begin": "(<!)(ENTITY)\\s+(%\\s+)?([:a-zA-Z_][:a-zA-Z0-9_.-]*)(\\s+(?:SYSTEM|PUBLIC)\\s+)?",
+      "captures": {
+        "1": {
+          "name": "punctuation.definition.tag.xml"
+        },
+        "2": {
+          "name": "keyword.other.entity.xml"
+        },
+        "3": {
+          "name": "punctuation.definition.entity.xml"
+        },
+        "4": {
+          "name": "variable.language.entity.xml"
+        },
+        "5": {
+          "name": "keyword.other.entitytype.xml"
+        }
+      },
+      "end": "(>)",
+      "patterns": [
+        {
+          "include": "#doublequotedString"
+        },
+        {
+          "include": "#singlequotedString"
+        }
+      ]
+    },
+    "bare-ampersand": {
+      "match": "&",
+      "name": "invalid.illegal.bad-ampersand.xml"
+    },
+    "doublequotedString": {
+      "begin": "\"",
+      "beginCaptures": {
+        "0": {
+          "name": "punctuation.definition.string.begin.xml"
+        }
+      },
+      "end": "\"",
+      "endCaptures": {
+        "0": {
+          "name": "punctuation.definition.string.end.xml"
+        }
+      },
+      "name": "string.quoted.double.xml",
+      "patterns": [
+        {
+          "include": "#entity"
+        },
+        {
+          "include": "#bare-ampersand"
+        }
+      ]
+    },
+    "entity": {
+      "captures": {
+        "1": {
+          "name": "punctuation.definition.constant.xml"
+        },
+        "3": {
+          "name": "punctuation.definition.constant.xml"
+        }
+      },
+      "match": "(&)([:a-zA-Z_][:a-zA-Z0-9_.-]*|#[0-9]+|#x[0-9a-fA-F]+)(;)",
+      "name": "constant.character.entity.xml"
+    },
+    "internalSubset": {
+      "begin": "(\\[)",
+      "captures": {
+        "1": {
+          "name": "punctuation.definition.constant.xml"
+        }
+      },
+      "end": "(\\])",
+      "name": "meta.internalsubset.xml",
+      "patterns": [
+        {
+          "include": "#EntityDecl"
+        },
+        {
+          "include": "#parameterEntity"
+        },
+        {
+          "include": "#comments"
+        }
+      ]
+    },
+    "parameterEntity": {
+      "captures": {
+        "1": {
+          "name": "punctuation.definition.constant.xml"
+        },
+        "3": {
+          "name": "punctuation.definition.constant.xml"
+        }
+      },
+      "match": "(%)([:a-zA-Z_][:a-zA-Z0-9_.-]*)(;)",
+      "name": "constant.character.parameter-entity.xml"
+    },
+    "singlequotedString": {
+      "begin": "'",
+      "beginCaptures": {
+        "0": {
+          "name": "punctuation.definition.string.begin.xml"
+        }
+      },
+      "end": "'",
+      "endCaptures": {
+        "0": {
+          "name": "punctuation.definition.string.end.xml"
+        }
+      },
+      "name": "string.quoted.single.xml",
+      "patterns": [
+        {
+          "include": "#entity"
+        },
+        {
+          "include": "#bare-ampersand"
+        }
+      ]
+    },
+    "tagStuff": {
+      "patterns": [
+        {
+          "captures": {
+            "1": {
+              "name": "entity.other.attribute-name.namespace.xml"
+            },
+            "2": {
+              "name": "entity.other.attribute-name.xml"
+            },
+            "3": {
+              "name": "punctuation.separator.namespace.xml"
+            },
+            "4": {
+              "name": "entity.other.attribute-name.localname.xml"
+            }
+          },
+          "match": "(?:^|\\s+)(?:([-\\w.]+)((:)))?([-\\w.:]+)\\s*="
+        },
+        {
+          "include": "#doublequotedString"
+        },
+        {
+          "include": "#singlequotedString"
+        }
+      ]
+    },
+    "comments": {
+      "patterns": [
+        {
+          "begin": "<%--",
+          "captures": {
+            "0": {
+              "name": "punctuation.definition.comment.xml"
+            },
+            "end": "--%>",
+            "name": "comment.block.xml"
+          }
+        },
+        {
+          "begin": "<!--",
+          "captures": {
+            "0": {
+              "name": "punctuation.definition.comment.xml"
+            }
+          },
+          "end": "-->",
+          "name": "comment.block.xml",
+          "patterns": [
+            {
+              "begin": "--(?!>)",
+              "captures": {
+                "0": {
+                  "name": "invalid.illegal.bad-comments-or-CDATA.xml"
+                }
+              }
+            }
+          ]
+        }
+      ]
+    }
+  }
+};
diff --git a/test/fixtures/grammar-exhaustive.html b/test/fixtures/grammar-exhaustive.html
index 06d1254..6382e1e 100644
--- a/test/fixtures/grammar-exhaustive.html
+++ b/test/fixtures/grammar-exhaustive.html
@@ -208,6 +208,18 @@
 const count = ref(0)
 &lt;/script&gt;
 &lt;button @click="count++"&gt;Count: {{ count }}&lt;/button&gt;</code></pre>
+    <pre><code class="language-xml">&lt;?xml version="1.0" encoding="UTF-8"?&gt;
+&lt;!DOCTYPE catalog [
+  &lt;!ENTITY publisher "MicroLighter Press"&gt;
+]&gt;
+&lt;!-- Namespaced inventory feed --&gt;
+&lt;catalog xmlns:book="urn:example:books"&gt;
+  &lt;book:item id="bk-42" available="true"&gt;
+    &lt;title&gt;Syntax &amp;amp; Semantics by &amp;publisher;&lt;/title&gt;
+    &lt;summary&gt;&lt;![CDATA[Use &lt;tokens&gt; safely.]]&gt;&lt;/summary&gt;
+    &lt;book:cover href="cover.jpg" /&gt;
+  &lt;/book:item&gt;
+&lt;/catalog&gt;</code></pre>
     <pre><code class="language-yaml">name: CI
 on: [push]
 jobs:
diff --git a/test/grammar-dependencies.spec.js b/test/grammar-dependencies.spec.js
index e7dcf03..7d72158 100644
--- a/test/grammar-dependencies.spec.js
+++ b/test/grammar-dependencies.spec.js
@@ -16,6 +16,7 @@ import tsx from "../src/grammars/tsx.js";
 import typescript from "../src/grammars/typescript.js";
 import svelte from "../src/grammars/svelte.js";
 import vue from "../src/grammars/vue.js";
+import xml from "../src/grammars/xml.js";
 
 test("finds external grammar languages in nested rules", () => {
   const grammar = {
@@ -64,6 +65,7 @@ test("reports dependencies used by the shipped grammars", () => {
   assert.deepEqual([...getExternalLanguages(cpp)], ["c"]);
   assert.deepEqual([...getExternalLanguages(tsx)], ["js", "ts"]);
   assert.deepEqual([...getExternalLanguages(objectiveC)], ["c"]);
+  assert.deepEqual([...getExternalLanguages(xml)], ["java"]);
   assert.deepEqual(heex.dependencies, ["html", "elixir"]);
   assert.deepEqual(svelte.dependencies, ["html", "css", "scss", "javascript", "typescript"]);
   assert.deepEqual(vue.dependencies, ["html", "css", "scss", "javascript", "typescript"]);