decant-core 1.10.0 → 1.10.1

package/README.md

@@ -41,7 +41,7 @@ AI platforms don't expose stable public APIs for reading conversation history. N
 
 Maintaining that per-platform logic in every exporter is wasteful and fragile. `decant-core` centralizes it:
 
-- ✅ **10+ AI chat platform parsers** with normalized output — you get structured messages, models, metadata and Markdown, not DOM soup.
+- ✅ **18 AI chat platform parsers** with normalized output — you get structured messages, models, metadata and Markdown, not DOM soup.
 - ✅ **Web article extraction** — Mozilla Readability, Defuddle, and Article-Extractor run in parallel and arbitrate by content-quality scoring.
 - ✅ **Detection utilities** — tell an "AI chat page" apart from a "regular web page" before you decide which parser to run.
 - ✅ **Math & Markdown handling** — LaTeX normalization plus GFM tables/code fencing that survive round-trips into Obsidian, Logseq and Notion.
@@ -117,13 +117,34 @@ import { normalizeLatexMath } from "decant-core";
 
 ## Supported Platforms
 
-10+ AI chat platform parsers plus generic web article extraction:
-
-**ChatGPT · Claude · Google Gemini · Microsoft Copilot · Perplexity · DeepSeek · Qwen · Meta AI · Mistral (Le Chat) · Proton Lumo · Z.ai · Google AI Studio · NotebookLM · Google Search AI · Gemini Cloud Assist · Joyland · Chub**
+18 AI chat platform parsers plus generic web article extraction:
+
+| Platform                            | Parser                    | Extraction strategy                        |
+| :---------------------------------- | :------------------------ | :----------------------------------------- |
+| **ChatGPT**                         | `ChatGPTParser`           | DOM + internal API                         |
+| **Claude**                          | `ClaudeParser`            | DOM + internal API + React fiber           |
+| **Google Gemini**                   | `GeminiParser`            | DOM + batchexecute RPC                     |
+| **Microsoft Copilot**               | `CopilotParser`           | DOM (multi-domain)                         |
+| **Perplexity**                      | `PerplexityParser`        | Internal API + DOM fallback                |
+| **DeepSeek**                        | `DeepSeekParser`          | DOM + internal API (`fragments[]`)         |
+| **Qwen**                            | `QwenParser`              | DOM                                        |
+| **Meta AI**                         | `MetaParser`              | Internal API (GraphQL) + DOM fallback      |
+| **Mistral / Le Chat**               | `MistralParser`           | DOM                                        |
+| **Proton Lumo**                     | `LumoParser`              | DOM (API is E2E-encrypted, not readable)   |
+| **Z.ai**                            | `ZAiParser`               | Internal API (chat + batch) + DOM fallback |
+| **Grok**                            | `GrokParser`              | Internal API (response-node + load) + DOM  |
+| **Google AI Studio**                | `GoogleAIStudioParser`    | DOM                                        |
+| **NotebookLM**                      | `NotebookLMParser`        | DOM                                        |
+| **Google Search AI (AI Overviews)** | `GoogleSearchAIParser`    | DOM                                        |
+| **Gemini Cloud Assist**             | `GeminiCloudAssistParser` | DOM                                        |
+| **Joyland**                         | `JoylandParser`           | DOM                                        |
+| **Chub**                            | `ChubParser`              | DOM                                        |
+| **Generic Web Article**             | `ArticleParser`           | Readability + Defuddle + Article-Extractor |
 
 All parsers extend the base [`ChatParser`](ai/base.js) interface — a consistent `isAvailable(url)` +
-normalized `parse()` contract. For the extraction-strategy breakdown and maintenance model, see
-[SUPPORTED_PLATFORMS.md](SUPPORTED_PLATFORMS.md).
+normalized `parse()` contract. For the full extraction-strategy breakdown and maintenance model, see
+[SUPPORTED_PLATFORMS.md](SUPPORTED_PLATFORMS.md), also published as the
+[platform matrix](https://covai-labs.github.io/decant-core/platforms/) on the developer docs site.
 
 ---
 

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "decant-core",
-  "version": "1.10.0",
+  "version": "1.10.1",
   "description": "A shared web extraction layer for AI conversations and regular web pages.",
   "type": "module",
   "engines": {

package/utils/html-to-markdown.js

@@ -192,28 +192,63 @@ export function convertToMarkdown(htmlContent, options = {}) {
       registerMath(el, latex, isBlock, clone.ownerDocument);
     });
 
-    // 3. Process Google Search SGE LaTeX images with [data-xpm-latex]
-    clone.querySelectorAll("[data-xpm-latex]").forEach((el) => {
-      if (!clone.contains(el)) return;
-      const copyRoot = el.closest("[data-xpm-copy-root]");
-      if (!copyRoot) return;
-      const container = el.closest(".cPGBZb") || copyRoot;
-      if (!container.parentNode) return;
-
-      const latex = el.getAttribute("data-xpm-latex");
-
-      // Determine if it is block math
-      let isBlock = false;
-      const parent = container.parentNode;
-      if (parent) {
-        const parentText = parent.textContent
-          .replace(container.textContent, "")
-          .trim();
-        isBlock = parentText === "";
-      }
+    // 3. Process Google Search SGE LaTeX images with [data-xpm-latex] or fallback math roots
+    clone
+      .querySelectorAll(
+        "[data-xpm-latex], [data-xpm-copy-root][data-xpm-copy-text], [data-xpm-copy-root] img[alt]",
+      )
+      .forEach((el) => {
+        if (!clone.contains(el)) return;
+        const copyRoot = el.hasAttribute("data-xpm-copy-root")
+          ? el
+          : el.closest("[data-xpm-copy-root]");
+        if (!copyRoot) return;
+        const blockContainer = el.closest(".cPGBZb");
+        const inlineWrapper = el.closest(".mTEjhd") || el.closest(".dteT0b");
+        const container = blockContainer || inlineWrapper || copyRoot;
+        if (!container.parentNode) return;
+
+        const img = el.tagName === "IMG" ? el : copyRoot.querySelector("img");
+        const latex =
+          copyRoot.getAttribute("data-xpm-latex") ||
+          el.getAttribute("data-xpm-latex") ||
+          copyRoot.getAttribute("data-xpm-copy-text") ||
+          (img && img.getAttribute("data-xpm-latex")) ||
+          el.getAttribute("alt") ||
+          (img && img.getAttribute("alt")) ||
+          "";
+        if (!latex) return;
+
+        // Determine if block or inline based on DOM structure
+        let isBlock = false;
+        if (blockContainer) {
+          // Full block container (.cPGBZb)
+          isBlock = true;
+        } else if (inlineWrapper) {
+          // Inline math wrapper (.mTEjhd, .dteT0b)
+          isBlock = false;
+        } else {
+          const style = copyRoot.getAttribute("style") || "";
+          if (/display:\s*inline/i.test(style)) {
+            isBlock = false;
+          } else {
+            // Check enclosing block element (p, li, td, th, div) for surrounding text
+            const enclosingBlock = container.closest("p, li, td, th, div");
+            if (enclosingBlock) {
+              const cloneBlock = enclosingBlock.cloneNode(true);
+              const targetInClone =
+                cloneBlock
+                  .querySelector("[data-xpm-latex]")
+                  ?.closest("[data-xpm-copy-root]") ||
+                cloneBlock.querySelector("[data-xpm-latex]");
+              if (targetInClone) targetInClone.remove();
+              isBlock = cloneBlock.textContent.trim() === "";
+            }
+          }
+        }
 
-      registerMath(container, latex, isBlock, clone.ownerDocument);
-    });
+        registerMath(container, latex, isBlock, clone.ownerDocument);
+      });
 
     // 4. Process block display KaTeX (.katex-display)
     clone.querySelectorAll(".katex-display").forEach((el) => {