xml-to-html-converter 0.4.0 → 0.4.2

package/README.md

@@ -8,7 +8,7 @@
 
 A zero-dependency Node.js package for converting XML to HTML.
 
-- **`minify(xml)`** strips inter-tag whitespace from prettified XML before parsing. Text content is left untouched
+- **`minify(xml)`** removes prettification whitespace between markup tokens before parsing. Non-whitespace text content and CDATA are left untouched
 - **`scaffold(xml)`** reads any XML string and returns a nested node tree
 - **`walk(nodes, visitor)`** traverses the full node tree depth-first, visiting every node
 - **`render(nodes)`** converts a node tree to an HTML string. Every XML element becomes a `<div>` with `data-tag` and `data-attrs-*` attributes
@@ -27,7 +27,7 @@ npm install xml-to-html-converter
 
 ### minify
 
-When your XML comes from a file or an API it is usually indented and line-broken. `minify` strips the whitespace between tags before parsing. Text content is left completely untouched.
+When your XML comes from a file or an API it is usually indented and line-broken. `minify` removes whitespace-only text nodes that include line breaks when they appear between markup tokens. Text content and CDATA are left completely untouched.
 
 ```js
 import { minify } from "xml-to-html-converter";
@@ -42,7 +42,7 @@ const clean = minify(`
 // <bookstore><book category="cooking"><title lang="en">Everyday Italian</title></book></bookstore>
 ```
 
-`minify` is opt-in. Skip it if whitespace inside your content is meaningful.
+`minify` is opt-in. Skip it if whitespace-only nodes between markup tokens are meaningful to your use case.
 
 ---
 
@@ -172,7 +172,7 @@ const html = render(
 </div>
 ```
 
-Processing instructions and doctypes are dropped. Comments are passed through unchanged.
+Processing instructions and doctypes are dropped. Comments are passed through unchanged. The output is a raw HTML string — if you are inserting it into a web page, treat it accordingly.
 
 ---
 
@@ -228,11 +228,15 @@ Every node in the tree has the following fields:
 
 `scaffold` never throws. No matter what the input looks like, it always returns a complete tree. Malformed structures are flagged with `malformed: true` in place and the walk continues.
 
-Four cases are handled:
+Eight cases are handled:
 
 - **Unclosed tags** - opens but never closes, gets `malformed: true`, children are still collected
 - **Stray closing tags** - a `</tag>` with no matching open surfaces as a `closeTag` token with `malformed: true`
 - **Unclosed brackets** - a `<` with no matching `>` captures the remainder as a malformed token
+- **Malformed attributes** - unquoted values (`<tag attr=unquoted>`), invalid separators (`<tag a="1"b="2">`), trailing junk after valid attributes (`<tag a="1" junk>`), and unclosed quoted values all flag the node `malformed: true`; any valid attributes parsed before the error are preserved
+- **Unclosed processing instructions** - `<?xml ...` with no `?>` captures the remainder as a malformed token
+- **Unclosed comments** - `<!-- ...` with no `-->` captures the remainder as a malformed token
+- **Unclosed CDATA** - `<![CDATA[ ...` with no `]]>` captures the remainder as a malformed token
 - **Excessive nesting** - documents nested beyond 500 levels have the deepest open tag flagged `malformed: true` to prevent a stack overflow
 
 ```js

package/dist/index.cjs

@@ -30,7 +30,71 @@ module.exports = __toCommonJS(src_exports);
 
 // src/modules/minify/minify.ts
 function minify(xml) {
-  return xml.replace(/>(\s+)</g, (_, gap) => gap.trim() === "" ? "><" : `>${gap}<`).trim();
+  const input = xml.trim();
+  if (input === "") return "";
+  const tokens = tokenize(input);
+  return tokens.filter((token, index) => !isRemovableWhitespace(token, tokens, index)).map((token) => token.value).join("");
+}
+function isRemovableWhitespace(token, tokens, index) {
+  if (token.type !== "text") return false;
+  if (!/^\s+$/.test(token.value)) return false;
+  if (!token.value.includes("\n") && !token.value.includes("\r")) return false;
+  const previous = tokens[index - 1];
+  const next = tokens[index + 1];
+  return previous?.type === "markup" && next?.type === "markup";
+}
+function tokenize(xml) {
+  const tokens = [];
+  let position = 0;
+  while (position < xml.length) {
+    if (xml[position] !== "<") {
+      const nextMarkup = xml.indexOf("<", position);
+      const end2 = nextMarkup === -1 ? xml.length : nextMarkup;
+      tokens.push({ type: "text", value: xml.slice(position, end2) });
+      position = end2;
+      continue;
+    }
+    const end = findMarkupEnd(xml, position);
+    tokens.push({ type: "markup", value: xml.slice(position, end) });
+    position = end;
+  }
+  return tokens;
+}
+function findMarkupEnd(xml, start) {
+  if (xml.startsWith("<!--", start)) {
+    const end = xml.indexOf("-->", start + 4);
+    return end === -1 ? xml.length : end + 3;
+  }
+  if (xml.startsWith("<![CDATA[", start)) {
+    const end = xml.indexOf("]]>", start + 9);
+    return end === -1 ? xml.length : end + 3;
+  }
+  if (xml.startsWith("<?", start)) {
+    const end = xml.indexOf("?>", start + 2);
+    return end === -1 ? xml.length : end + 2;
+  }
+  if (xml.startsWith("<!DOCTYPE", start)) {
+    const bracketOpen = xml.indexOf("[", start);
+    const firstClose = xml.indexOf(">", start);
+    if (bracketOpen !== -1 && bracketOpen < firstClose) {
+      const bracketClose = xml.indexOf("]>", bracketOpen + 1);
+      return bracketClose === -1 ? xml.length : bracketClose + 2;
+    }
+    return firstClose === -1 ? xml.length : firstClose + 1;
+  }
+  let i = start + 1;
+  while (i < xml.length) {
+    const ch = xml[i];
+    if (ch === '"' || ch === "'") {
+      const closeQuote = xml.indexOf(ch, i + 1);
+      if (closeQuote === -1) return xml.length;
+      i = closeQuote + 1;
+      continue;
+    }
+    if (ch === ">") return i + 1;
+    i++;
+  }
+  return xml.length;
 }
 
 // src/modules/render/render.ts
@@ -61,28 +125,55 @@ function buildDataAttrs(node) {
 function parseXmlAttributes(xmlInner) {
   const attributes = [];
   let i = 0;
+  let malformed = false;
   const s = xmlInner.trim();
   while (i < s.length) {
+    const whitespaceStart = i;
     while (i < s.length && /\s/.test(s[i])) i++;
+    const hasSeparatorWhitespace = i > whitespaceStart;
     if (i >= s.length) break;
+    if (attributes.length > 0 && !hasSeparatorWhitespace) {
+      malformed = true;
+      break;
+    }
     const nameStart = i;
     while (i < s.length && s[i] !== "=" && !/\s/.test(s[i])) i++;
     const name = s.slice(nameStart, i).trim();
-    if (!name) break;
+    if (!name) {
+      malformed = true;
+      break;
+    }
     while (i < s.length && /\s/.test(s[i])) i++;
-    if (s[i] !== "=") break;
+    if (s[i] !== "=") {
+      malformed = true;
+      break;
+    }
     i++;
     while (i < s.length && /\s/.test(s[i])) i++;
     const quote = s[i];
-    if (quote !== '"' && quote !== "'") break;
+    if (quote !== '"' && quote !== "'") {
+      return {
+        attributes: attributes.length > 0 ? attributes : void 0,
+        malformed: true
+      };
+    }
     i++;
     const valueStart = i;
     while (i < s.length && s[i] !== quote) i++;
+    if (i >= s.length) {
+      return {
+        attributes: attributes.length > 0 ? attributes : void 0,
+        malformed: true
+      };
+    }
     const value = s.slice(valueStart, i);
     i++;
     attributes.push({ name, value });
   }
-  return attributes.length > 0 ? attributes : void 0;
+  return {
+    attributes: attributes.length > 0 ? attributes : void 0,
+    malformed
+  };
 }
 var MAX_DEPTH = 500;
 function scaffold(xml) {
@@ -185,7 +276,8 @@ function extractXmlNodes(xml, position) {
       raw: xml.slice(position),
       role: "processingInstruction",
       tag: "",
-      end: xml.length
+      end: xml.length,
+      malformed: true
     } : {
       raw: xml.slice(position, end2 + 2),
       role: "processingInstruction",
@@ -195,7 +287,13 @@ function extractXmlNodes(xml, position) {
   }
   if (xml[position + 1] === "!" && xml[position + 2] === "[") {
     const end2 = xml.indexOf("]]>", position + 3);
-    return end2 === -1 ? { raw: xml.slice(position), role: "textLeaf", tag: "", end: xml.length } : {
+    return end2 === -1 ? {
+      raw: xml.slice(position),
+      role: "textLeaf",
+      tag: "",
+      end: xml.length,
+      malformed: true
+    } : {
       raw: xml.slice(position, end2 + 3),
       role: "textLeaf",
       tag: "",
@@ -204,7 +302,13 @@ function extractXmlNodes(xml, position) {
   }
   if (xml[position + 1] === "!" && xml[position + 2] === "-" && xml[position + 3] === "-") {
     const end2 = xml.indexOf("-->", position + 4);
-    return end2 === -1 ? { raw: xml.slice(position), role: "comment", tag: "", end: xml.length } : {
+    return end2 === -1 ? {
+      raw: xml.slice(position),
+      role: "comment",
+      tag: "",
+      end: xml.length,
+      malformed: true
+    } : {
       raw: xml.slice(position, end2 + 3),
       role: "comment",
       tag: "",
@@ -244,13 +348,29 @@ function extractXmlNodes(xml, position) {
     const trimmed = inner.slice(0, -1).trim();
     const tag2 = trimmed.split(/\s/)[0] ?? "";
     const xmlInner2 = trimmed.slice(tag2.length).trim() || void 0;
-    const xmlAttributes2 = xmlInner2 ? parseXmlAttributes(xmlInner2) : void 0;
-    return { raw, role: "selfTag", tag: tag2, xmlInner: xmlInner2, xmlAttributes: xmlAttributes2, end };
+    const parsed2 = xmlInner2 ? parseXmlAttributes(xmlInner2) : void 0;
+    return {
+      raw,
+      role: "selfTag",
+      tag: tag2,
+      xmlInner: xmlInner2,
+      xmlAttributes: parsed2?.attributes,
+      end,
+      malformed: parsed2?.malformed ? true : void 0
+    };
   }
   const tag = inner.split(/\s/)[0] ?? "";
   const xmlInner = inner.slice(tag.length).trim() || void 0;
-  const xmlAttributes = xmlInner ? parseXmlAttributes(xmlInner) : void 0;
-  return { raw, role: "openTag", tag, xmlInner, xmlAttributes, end };
+  const parsed = xmlInner ? parseXmlAttributes(xmlInner) : void 0;
+  return {
+    raw,
+    role: "openTag",
+    tag,
+    xmlInner,
+    xmlAttributes: parsed?.attributes,
+    end,
+    malformed: parsed?.malformed ? true : void 0
+  };
 }
 
 // src/modules/scaffold/types.ts

package/dist/index.js

@@ -1,6 +1,70 @@
 // src/modules/minify/minify.ts
 function minify(xml) {
-  return xml.replace(/>(\s+)</g, (_, gap) => gap.trim() === "" ? "><" : `>${gap}<`).trim();
+  const input = xml.trim();
+  if (input === "") return "";
+  const tokens = tokenize(input);
+  return tokens.filter((token, index) => !isRemovableWhitespace(token, tokens, index)).map((token) => token.value).join("");
+}
+function isRemovableWhitespace(token, tokens, index) {
+  if (token.type !== "text") return false;
+  if (!/^\s+$/.test(token.value)) return false;
+  if (!token.value.includes("\n") && !token.value.includes("\r")) return false;
+  const previous = tokens[index - 1];
+  const next = tokens[index + 1];
+  return previous?.type === "markup" && next?.type === "markup";
+}
+function tokenize(xml) {
+  const tokens = [];
+  let position = 0;
+  while (position < xml.length) {
+    if (xml[position] !== "<") {
+      const nextMarkup = xml.indexOf("<", position);
+      const end2 = nextMarkup === -1 ? xml.length : nextMarkup;
+      tokens.push({ type: "text", value: xml.slice(position, end2) });
+      position = end2;
+      continue;
+    }
+    const end = findMarkupEnd(xml, position);
+    tokens.push({ type: "markup", value: xml.slice(position, end) });
+    position = end;
+  }
+  return tokens;
+}
+function findMarkupEnd(xml, start) {
+  if (xml.startsWith("<!--", start)) {
+    const end = xml.indexOf("-->", start + 4);
+    return end === -1 ? xml.length : end + 3;
+  }
+  if (xml.startsWith("<![CDATA[", start)) {
+    const end = xml.indexOf("]]>", start + 9);
+    return end === -1 ? xml.length : end + 3;
+  }
+  if (xml.startsWith("<?", start)) {
+    const end = xml.indexOf("?>", start + 2);
+    return end === -1 ? xml.length : end + 2;
+  }
+  if (xml.startsWith("<!DOCTYPE", start)) {
+    const bracketOpen = xml.indexOf("[", start);
+    const firstClose = xml.indexOf(">", start);
+    if (bracketOpen !== -1 && bracketOpen < firstClose) {
+      const bracketClose = xml.indexOf("]>", bracketOpen + 1);
+      return bracketClose === -1 ? xml.length : bracketClose + 2;
+    }
+    return firstClose === -1 ? xml.length : firstClose + 1;
+  }
+  let i = start + 1;
+  while (i < xml.length) {
+    const ch = xml[i];
+    if (ch === '"' || ch === "'") {
+      const closeQuote = xml.indexOf(ch, i + 1);
+      if (closeQuote === -1) return xml.length;
+      i = closeQuote + 1;
+      continue;
+    }
+    if (ch === ">") return i + 1;
+    i++;
+  }
+  return xml.length;
 }
 
 // src/modules/render/render.ts
@@ -31,28 +95,55 @@ function buildDataAttrs(node) {
 function parseXmlAttributes(xmlInner) {
   const attributes = [];
   let i = 0;
+  let malformed = false;
   const s = xmlInner.trim();
   while (i < s.length) {
+    const whitespaceStart = i;
     while (i < s.length && /\s/.test(s[i])) i++;
+    const hasSeparatorWhitespace = i > whitespaceStart;
     if (i >= s.length) break;
+    if (attributes.length > 0 && !hasSeparatorWhitespace) {
+      malformed = true;
+      break;
+    }
     const nameStart = i;
     while (i < s.length && s[i] !== "=" && !/\s/.test(s[i])) i++;
     const name = s.slice(nameStart, i).trim();
-    if (!name) break;
+    if (!name) {
+      malformed = true;
+      break;
+    }
     while (i < s.length && /\s/.test(s[i])) i++;
-    if (s[i] !== "=") break;
+    if (s[i] !== "=") {
+      malformed = true;
+      break;
+    }
     i++;
     while (i < s.length && /\s/.test(s[i])) i++;
     const quote = s[i];
-    if (quote !== '"' && quote !== "'") break;
+    if (quote !== '"' && quote !== "'") {
+      return {
+        attributes: attributes.length > 0 ? attributes : void 0,
+        malformed: true
+      };
+    }
     i++;
     const valueStart = i;
     while (i < s.length && s[i] !== quote) i++;
+    if (i >= s.length) {
+      return {
+        attributes: attributes.length > 0 ? attributes : void 0,
+        malformed: true
+      };
+    }
     const value = s.slice(valueStart, i);
     i++;
     attributes.push({ name, value });
   }
-  return attributes.length > 0 ? attributes : void 0;
+  return {
+    attributes: attributes.length > 0 ? attributes : void 0,
+    malformed
+  };
 }
 var MAX_DEPTH = 500;
 function scaffold(xml) {
@@ -155,7 +246,8 @@ function extractXmlNodes(xml, position) {
       raw: xml.slice(position),
       role: "processingInstruction",
       tag: "",
-      end: xml.length
+      end: xml.length,
+      malformed: true
     } : {
       raw: xml.slice(position, end2 + 2),
       role: "processingInstruction",
@@ -165,7 +257,13 @@ function extractXmlNodes(xml, position) {
   }
   if (xml[position + 1] === "!" && xml[position + 2] === "[") {
     const end2 = xml.indexOf("]]>", position + 3);
-    return end2 === -1 ? { raw: xml.slice(position), role: "textLeaf", tag: "", end: xml.length } : {
+    return end2 === -1 ? {
+      raw: xml.slice(position),
+      role: "textLeaf",
+      tag: "",
+      end: xml.length,
+      malformed: true
+    } : {
       raw: xml.slice(position, end2 + 3),
       role: "textLeaf",
       tag: "",
@@ -174,7 +272,13 @@ function extractXmlNodes(xml, position) {
   }
   if (xml[position + 1] === "!" && xml[position + 2] === "-" && xml[position + 3] === "-") {
     const end2 = xml.indexOf("-->", position + 4);
-    return end2 === -1 ? { raw: xml.slice(position), role: "comment", tag: "", end: xml.length } : {
+    return end2 === -1 ? {
+      raw: xml.slice(position),
+      role: "comment",
+      tag: "",
+      end: xml.length,
+      malformed: true
+    } : {
       raw: xml.slice(position, end2 + 3),
       role: "comment",
       tag: "",
@@ -214,13 +318,29 @@ function extractXmlNodes(xml, position) {
     const trimmed = inner.slice(0, -1).trim();
     const tag2 = trimmed.split(/\s/)[0] ?? "";
     const xmlInner2 = trimmed.slice(tag2.length).trim() || void 0;
-    const xmlAttributes2 = xmlInner2 ? parseXmlAttributes(xmlInner2) : void 0;
-    return { raw, role: "selfTag", tag: tag2, xmlInner: xmlInner2, xmlAttributes: xmlAttributes2, end };
+    const parsed2 = xmlInner2 ? parseXmlAttributes(xmlInner2) : void 0;
+    return {
+      raw,
+      role: "selfTag",
+      tag: tag2,
+      xmlInner: xmlInner2,
+      xmlAttributes: parsed2?.attributes,
+      end,
+      malformed: parsed2?.malformed ? true : void 0
+    };
   }
   const tag = inner.split(/\s/)[0] ?? "";
   const xmlInner = inner.slice(tag.length).trim() || void 0;
-  const xmlAttributes = xmlInner ? parseXmlAttributes(xmlInner) : void 0;
-  return { raw, role: "openTag", tag, xmlInner, xmlAttributes, end };
+  const parsed = xmlInner ? parseXmlAttributes(xmlInner) : void 0;
+  return {
+    raw,
+    role: "openTag",
+    tag,
+    xmlInner,
+    xmlAttributes: parsed?.attributes,
+    end,
+    malformed: parsed?.malformed ? true : void 0
+  };
 }
 
 // src/modules/scaffold/types.ts

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "xml-to-html-converter",
-  "version": "0.4.0",
+  "version": "0.4.2",
   "description": "Zero dependency XML to HTML converter for Node environments",
   "type": "module",
   "main": "./dist/index.cjs",