stream-markdown-parser 0.0.40 → 0.0.41

package/dist/index.js

@@ -6888,7 +6888,24 @@ const BASE_COMMON_HTML_TAGS = new Set([
 ]);
 const OPEN_TAG_RE = /<([A-Z][\w-]*)(?=[\s/>]|$)/gi;
 const CLOSE_TAG_RE = /<\/\s*([A-Z][\w-]*)(?=[\s/>]|$)/gi;
-const FULL_TAG_RE = /^<\s*(?:\/\s*)?([A-Z][\w-]*)(?:\s[^>]*?)?\/?>/i;
+const TAG_NAME_AT_START_RE = /^<\s*(?:\/\s*)?([A-Z][\w-]*)/i;
+function findTagCloseIndexOutsideQuotes(html) {
+	let inSingle = false;
+	let inDouble = false;
+	for (let i = 0; i < html.length; i++) {
+		const ch = html[i];
+		if (ch === "\"" && !inSingle) {
+			inDouble = !inDouble;
+			continue;
+		}
+		if (ch === "'" && !inDouble) {
+			inSingle = !inSingle;
+			continue;
+		}
+		if (ch === ">" && !inSingle && !inDouble) return i;
+	}
+	return -1;
+}
 function tokenToRaw$1(token) {
 	const shape = token;
 	return String(shape.raw ?? shape.content ?? shape.markup ?? "");
@@ -6916,7 +6933,7 @@ function findFirstIncompleteTag(content, tagSet) {
 		if (idx < 0) continue;
 		const tag = (m[1] ?? "").toLowerCase();
 		if (!tagSet.has(tag)) continue;
-		if (content.slice(idx).includes(">")) continue;
+		if (findTagCloseIndexOutsideQuotes(content.slice(idx)) !== -1) continue;
 		if (!first || idx < first.index) first = {
 			index: idx,
 			tag,
@@ -6928,7 +6945,7 @@ function findFirstIncompleteTag(content, tagSet) {
 		if (idx < 0) continue;
 		const tag = (m[1] ?? "").toLowerCase();
 		if (!isCommonHtmlTagOrPrefix(tag, tagSet)) continue;
-		if (content.slice(idx).includes(">")) continue;
+		if (findTagCloseIndexOutsideQuotes(content.slice(idx)) !== -1) continue;
 		if (!first || idx < first.index) first = {
 			index: idx,
 			tag,
@@ -6987,14 +7004,21 @@ function fixStreamingHtmlInlineChildren(children, tagSet) {
 				break;
 			}
 			pushTextPart(chunk.slice(cursor, lt), baseToken);
-			const fullMatch = chunk.slice(lt).match(FULL_TAG_RE);
-			if (!fullMatch) {
+			const sub = chunk.slice(lt);
+			const tagMatch = sub.match(TAG_NAME_AT_START_RE);
+			if (!tagMatch) {
+				pushTextPart("<", baseToken);
+				cursor = lt + 1;
+				continue;
+			}
+			const closeIdx = findTagCloseIndexOutsideQuotes(sub);
+			if (closeIdx === -1) {
 				pushTextPart("<", baseToken);
 				cursor = lt + 1;
 				continue;
 			}
-			const tagText = fullMatch[0];
-			const tagName = (fullMatch[1] ?? "").toLowerCase();
+			const tagText = sub.slice(0, closeIdx + 1);
+			const tagName = (tagMatch[1] ?? "").toLowerCase();
 			if (tagSet.has(tagName)) out.push({
 				type: "html_inline",
 				tag: "",
@@ -7025,7 +7049,7 @@ function fixStreamingHtmlInlineChildren(children, tagSet) {
 		if (pending) {
 			pending.buffer += tokenToRaw$1(child);
 			pendingAtEnd = pending.buffer;
-			const closeIdx = pending.buffer.indexOf(">");
+			const closeIdx = findTagCloseIndexOutsideQuotes(pending.buffer);
 			if (closeIdx === -1) continue;
 			const tagChunk = pending.buffer.slice(0, closeIdx + 1);
 			const afterChunk = pending.buffer.slice(closeIdx + 1);
@@ -7040,6 +7064,19 @@ function fixStreamingHtmlInlineChildren(children, tagSet) {
 			if (afterChunk) processTextChunk(afterChunk);
 			continue;
 		}
+		if (child.type === "html_inline") {
+			const content = tokenToRaw$1(child);
+			const tagName = (content.match(TAG_NAME_AT_START_RE)?.[1] ?? "").toLowerCase();
+			if (tagName && tagSet.has(tagName) && findTagCloseIndexOutsideQuotes(content) === -1) {
+				pending = {
+					tag: tagName,
+					buffer: content,
+					closing: /^<\s*\//.test(content)
+				};
+				pendingAtEnd = pending.buffer;
+				continue;
+			}
+		}
 		if (child.type === "text") {
 			const content = String(child.content ?? "");
 			if (!content.includes("<")) {
@@ -7165,16 +7202,26 @@ function applyFixHtmlInlineTokens(md, options = {}) {
 					attrs.push([attrName, attrValue]);
 				}
 				if (customTagSet.has(tag)) {
-					const contentMatch = t.content?.match(new RegExp(`<\\s*${tag}[^>]*>([\\s\\S]*?)<\\s*\\/\\s*${tag}\\s*>`, "i"));
+					const contentMatch = t.content?.match(new RegExp(`<\\s*${tag}[^>]*>([\\s\\S]*)`, "i"));
 					const raw$1 = t.content;
+					const endTagRegex = new RegExp(`</\\s*${tag}\\s*>`, "i");
+					const endTagIndex = t.content?.toLowerCase().indexOf(`</${tag}>`) ?? -1;
 					t.children = [{
 						type: tag,
-						content: contentMatch ? contentMatch[1] : "",
+						content: endTagIndex !== -1 ? contentMatch[1].split(endTagRegex)[0] ? contentMatch ? contentMatch[1] : "" : "" : contentMatch ? contentMatch[1].replace(/<.*$/, "") : "",
 						raw: raw$1,
 						attrs,
 						tag,
 						loading
 					}];
+					if (endTagIndex !== -1) {
+						const afterContent = t.content?.slice(endTagIndex + tag.length + 3) || "";
+						if (afterContent.trim()) toks.splice(i + 1, 0, {
+							type: "text",
+							content: afterContent,
+							raw: afterContent
+						});
+					}
 				} else t.children = [{
 					type: "html_block",
 					content: t.content,