notion-to-md 2.3.4 → 2.5.0

package/build/notion-to-md.js

@@ -1,329 +1,367 @@
-"use strict";
-var __createBinding = (this && this.__createBinding) || (Object.create ? (function(o, m, k, k2) {
-    if (k2 === undefined) k2 = k;
-    var desc = Object.getOwnPropertyDescriptor(m, k);
-    if (!desc || ("get" in desc ? !m.__esModule : desc.writable || desc.configurable)) {
-      desc = { enumerable: true, get: function() { return m[k]; } };
-    }
-    Object.defineProperty(o, k2, desc);
-}) : (function(o, m, k, k2) {
-    if (k2 === undefined) k2 = k;
-    o[k2] = m[k];
-}));
-var __setModuleDefault = (this && this.__setModuleDefault) || (Object.create ? (function(o, v) {
-    Object.defineProperty(o, "default", { enumerable: true, value: v });
-}) : function(o, v) {
-    o["default"] = v;
-});
-var __importStar = (this && this.__importStar) || function (mod) {
-    if (mod && mod.__esModule) return mod;
-    var result = {};
-    if (mod != null) for (var k in mod) if (k !== "default" && Object.prototype.hasOwnProperty.call(mod, k)) __createBinding(result, mod, k);
-    __setModuleDefault(result, mod);
-    return result;
-};
-Object.defineProperty(exports, "__esModule", { value: true });
-exports.NotionToMarkdown = void 0;
-const md = __importStar(require("./utils/md"));
-const notion_1 = require("./utils/notion");
-/**
- * Converts a Notion page to Markdown.
- */
-class NotionToMarkdown {
-    constructor(options) {
-        this.notionClient = options.notionClient;
-    }
-    /**
-     * Converts Markdown Blocks to string
-     * @param {MdBlock[]} mdBlocks - Array of markdown blocks
-     * @param {number} nestingLevel - Defines max depth of nesting
-     * @returns {string} - Returns markdown string
-     */
-    toMarkdownString(mdBlocks = [], nestingLevel = 0) {
-        let mdString = "";
-        mdBlocks.forEach((mdBlocks) => {
-            if (mdBlocks.parent) {
-                mdString += `
-${md.addTabSpace(mdBlocks.parent, nestingLevel)}
-`;
-            }
-            if (mdBlocks.children && mdBlocks.children.length > 0) {
-                mdString += this.toMarkdownString(mdBlocks.children, nestingLevel + 1);
-            }
-        });
-        return mdString;
-    }
-    /**
-     * Retrieves Notion Blocks based on ID and converts them to Markdown Blocks
-     * @param {string} id - notion page id (not database id)
-     * @param {number} totalPage - Retrieve block children request number, page_size Maximum = totalPage * 100 (Default=null)
-     * @returns {Promise<MdBlock[]>} - List of markdown blocks
-     */
-    async pageToMarkdown(id, totalPage = null) {
-        if (!this.notionClient) {
-            throw new Error("notion client is not provided, for more details check out https://github.com/souvikinator/notion-to-md");
-        }
-        const blocks = await (0, notion_1.getBlockChildren)(this.notionClient, id, totalPage);
-        const parsedData = await this.blocksToMarkdown(blocks);
-        return parsedData;
-    }
-    /**
-     * Converts list of Notion Blocks to Markdown Blocks
-     * @param {ListBlockChildrenResponseResults | undefined} blocks - List of notion blocks
-     * @param {number} totalPage - Retrieve block children request number, page_size Maximum = totalPage * 100
-     * @param {MdBlock[]} mdBlocks - Defines max depth of nesting
-     * @returns {Promise<MdBlock[]>} - Array of markdown blocks with their children
-     */
-    async blocksToMarkdown(blocks, totalPage = null, mdBlocks = []) {
-        if (!this.notionClient) {
-            throw new Error("notion client is not provided, for more details check out https://github.com/souvikinator/notion-to-md");
-        }
-        if (!blocks)
-            return mdBlocks;
-        for (let i = 0; i < blocks.length; i++) {
-            let block = blocks[i];
-            if ("has_children" in block && block.has_children && block.type !== "column_list") {
-                let child_blocks = await (0, notion_1.getBlockChildren)(this.notionClient, block.id, totalPage);
-                mdBlocks.push({
-                    parent: await this.blockToMarkdown(block),
-                    children: [],
-                });
-                let l = mdBlocks.length;
-                await this.blocksToMarkdown(child_blocks, totalPage, mdBlocks[l - 1].children);
-                continue;
-            }
-            let tmp = await this.blockToMarkdown(block);
-            mdBlocks.push({ parent: tmp, children: [] });
-        }
-        return mdBlocks;
-    }
-    /**
-     * Converts a Notion Block to a Markdown Block
-     * @param {ListBlockChildrenResponseResult} block - single notion block
-     * @returns {string} corresponding markdown string of the passed block
-     */
-    async blockToMarkdown(block) {
-        if (!("type" in block))
-            return "";
-        let parsedData = "";
-        const { type } = block;
-        // console.log({ block });
-        switch (type) {
-            case "image":
-                {
-                    let blockContent = block.image;
-                    const image_caption_plain = blockContent.caption
-                        .map((item) => item.plain_text)
-                        .join("");
-                    const image_type = blockContent.type;
-                    if (image_type === "external")
-                        return md.image(image_caption_plain, blockContent.external.url);
-                    if (image_type === "file")
-                        return md.image(image_caption_plain, blockContent.file.url);
-                }
-                break;
-            case "divider": {
-                return md.divider();
-            }
-            case "equation": {
-                return md.codeBlock(block.equation.expression);
-            }
-            case "video":
-            case "file":
-            case "pdf":
-                {
-                    let blockContent;
-                    if (type === "video")
-                        blockContent = block.video;
-                    if (type === "file")
-                        blockContent = block.file;
-                    if (type === "pdf")
-                        blockContent = block.pdf;
-                    if (blockContent) {
-                        const file_type = blockContent.type;
-                        if (file_type === "external")
-                            return md.link("image", blockContent.external.url);
-                        if (file_type === "file")
-                            return md.link("image", blockContent.file.url);
-                    }
-                }
-                break;
-            case "bookmark":
-            case "embed":
-            case "link_preview":
-            case "link_to_page":
-                {
-                    let blockContent;
-                    if (type === "bookmark")
-                        blockContent = block.bookmark;
-                    if (type === "embed")
-                        blockContent = block.embed;
-                    if (type === "link_preview")
-                        blockContent = block.link_preview;
-                    if (type === "link_to_page" && block.link_to_page.type === "page_id")
-                        blockContent = { url: block.link_to_page.page_id };
-                    if (blockContent)
-                        return md.link(type, blockContent.url);
-                }
-                break;
-            case "table": {
-                const { id, has_children } = block;
-                let tableArr = [];
-                if (has_children) {
-                    const tableRows = await (0, notion_1.getBlockChildren)(this.notionClient, id, 100);
-                    // console.log(">>", tableRows);
-                    let rowsPromise = tableRows === null || tableRows === void 0 ? void 0 : tableRows.map(async (row) => {
-                        const { type } = row;
-                        const cells = row[type]["cells"];
-                        /**
-                         * this is more like a hack since matching the type text was
-                         * difficult. So converting each cell to paragraph type to
-                         * reuse the blockToMarkdown function
-                         */
-                        let cellStringPromise = cells.map(async (cell) => await this.blockToMarkdown({
-                            type: "paragraph",
-                            paragraph: { rich_text: cell },
-                        }));
-                        const cellStringArr = await Promise.all(cellStringPromise);
-                        // console.log("~~", cellStringArr);
-                        tableArr.push(cellStringArr);
-                        // console.log(tableArr);
-                    });
-                    await Promise.all(rowsPromise || []);
-                }
-                parsedData = md.table(tableArr);
-                return parsedData;
-            }
-            case "column_list": {
-                const { id, has_children } = block;
-                if (!has_children)
-                    return "";
-                const column_list_children = await (0, notion_1.getBlockChildren)(this.notionClient, id, 100);
-                let column_list_promise = column_list_children.map(async (column) => await this.blockToMarkdown(column));
-                let column_list = await Promise.all(column_list_promise);
-                // console.log(column_list);
-                return column_list.join("\n\n");
-            }
-            case "column": {
-                const { id, has_children } = block;
-                if (!has_children)
-                    return "";
-                const column_children = await (0, notion_1.getBlockChildren)(this.notionClient, id, 100);
-                const column_children_promise = column_children.map(async (column_child) => await this.blockToMarkdown(column_child));
-                let column = await Promise.all(column_children_promise);
-                return column.join("\n\n");
-            }
-            // Rest of the types
-            // "paragraph"
-            // "heading_1"
-            // "heading_2"
-            // "heading_3"
-            // "bulleted_list_item"
-            // "numbered_list_item"
-            // "quote"
-            // "to_do"
-            // "toggle"
-            // "template"
-            // "synced_block"
-            // "child_page"
-            // "child_database"
-            // "code"
-            // "callout"
-            // "breadcrumb"
-            // "table_of_contents"
-            // "column_list"
-            // "column"
-            // "link_to_page"
-            // "audio"
-            // "unsupported"
-            default: {
-                // In this case typescript is not able to index the types properly, hence ignoring the error
-                // @ts-ignore
-                let blockContent = block[type].text || block[type].rich_text || [];
-                blockContent.map((content) => {
-                    const annotations = content.annotations;
-                    let plain_text = content.plain_text;
-                    plain_text = this.annotatePlainText(plain_text, annotations);
-                    if (content["href"])
-                        plain_text = md.link(plain_text, content["href"]);
-                    parsedData += plain_text;
-                });
-            }
-        }
-        switch (type) {
-            case "code":
-                {
-                    parsedData = md.codeBlock(parsedData, block[type].language);
-                }
-                break;
-            case "heading_1":
-                {
-                    parsedData = md.heading1(parsedData);
-                }
-                break;
-            case "heading_2":
-                {
-                    parsedData = md.heading2(parsedData);
-                }
-                break;
-            case "heading_3":
-                {
-                    parsedData = md.heading3(parsedData);
-                }
-                break;
-            case "quote":
-                {
-                    parsedData = md.quote(parsedData);
-                }
-                break;
-            case "callout":
-                {
-                    parsedData = md.callout(parsedData, block[type].icon);
-                }
-                break;
-            case "bulleted_list_item":
-            case "numbered_list_item":
-                {
-                    parsedData = md.bullet(parsedData);
-                }
-                break;
-            case "to_do":
-                {
-                    parsedData = md.todo(parsedData, block.to_do.checked);
-                }
-                break;
-        }
-        return parsedData;
-    }
-    /**
-     * Annoate text using provided annotations
-     * @param {string} text - String to be annotated
-     * @param {Annotations} annotations - Annotation object of a notion block
-     * @returns {string} - Annotated text
-     */
-    annotatePlainText(text, annotations) {
-        // if text is all spaces, don't annotate
-        if (text.match(/^\s*$/))
-            return text;
-        const leadingSpaceMatch = text.match(/^(\s*)/);
-        const trailingSpaceMatch = text.match(/(\s*)$/);
-        const leading_space = leadingSpaceMatch ? leadingSpaceMatch[0] : "";
-        const trailing_space = trailingSpaceMatch ? trailingSpaceMatch[0] : "";
-        text = text.trim();
-        if (text !== "") {
-            if (annotations.code)
-                text = md.inlineCode(text);
-            if (annotations.bold)
-                text = md.bold(text);
-            if (annotations.italic)
-                text = md.italic(text);
-            if (annotations.strikethrough)
-                text = md.strikethrough(text);
-            if (annotations.underline)
-                text = md.underline(text);
-        }
-        return leading_space + text + trailing_space;
-    }
-}
-exports.NotionToMarkdown = NotionToMarkdown;
+"use strict";
+var __createBinding = (this && this.__createBinding) || (Object.create ? (function(o, m, k, k2) {
+    if (k2 === undefined) k2 = k;
+    var desc = Object.getOwnPropertyDescriptor(m, k);
+    if (!desc || ("get" in desc ? !m.__esModule : desc.writable || desc.configurable)) {
+      desc = { enumerable: true, get: function() { return m[k]; } };
+    }
+    Object.defineProperty(o, k2, desc);
+}) : (function(o, m, k, k2) {
+    if (k2 === undefined) k2 = k;
+    o[k2] = m[k];
+}));
+var __setModuleDefault = (this && this.__setModuleDefault) || (Object.create ? (function(o, v) {
+    Object.defineProperty(o, "default", { enumerable: true, value: v });
+}) : function(o, v) {
+    o["default"] = v;
+});
+var __importStar = (this && this.__importStar) || function (mod) {
+    if (mod && mod.__esModule) return mod;
+    var result = {};
+    if (mod != null) for (var k in mod) if (k !== "default" && Object.prototype.hasOwnProperty.call(mod, k)) __createBinding(result, mod, k);
+    __setModuleDefault(result, mod);
+    return result;
+};
+Object.defineProperty(exports, "__esModule", { value: true });
+exports.NotionToMarkdown = void 0;
+const md = __importStar(require("./utils/md"));
+const notion_1 = require("./utils/notion");
+/**
+ * Converts a Notion page to Markdown.
+ */
+class NotionToMarkdown {
+    constructor(options) {
+        this.notionClient = options.notionClient;
+        this.customTransformers = {};
+    }
+    setCustomTransformer(type, transformer) {
+        this.customTransformers[type] = transformer;
+        return this;
+    }
+    /**
+     * Converts Markdown Blocks to string
+     * @param {MdBlock[]} mdBlocks - Array of markdown blocks
+     * @param {number} nestingLevel - Defines max depth of nesting
+     * @returns {string} - Returns markdown string
+     */
+    toMarkdownString(mdBlocks = [], nestingLevel = 0) {
+        let mdString = "";
+        mdBlocks.forEach((mdBlocks) => {
+            if (mdBlocks.parent) {
+                mdString += `
+${md.addTabSpace(mdBlocks.parent, nestingLevel)}
+`;
+            }
+            if (mdBlocks.children && mdBlocks.children.length > 0) {
+                mdString += this.toMarkdownString(mdBlocks.children, nestingLevel + 1);
+            }
+        });
+        return mdString;
+    }
+    /**
+     * Retrieves Notion Blocks based on ID and converts them to Markdown Blocks
+     * @param {string} id - notion page id (not database id)
+     * @param {number} totalPage - Retrieve block children request number, page_size Maximum = totalPage * 100 (Default=null)
+     * @returns {Promise<MdBlock[]>} - List of markdown blocks
+     */
+    async pageToMarkdown(id, totalPage = null) {
+        if (!this.notionClient) {
+            throw new Error("notion client is not provided, for more details check out https://github.com/souvikinator/notion-to-md");
+        }
+        const blocks = await (0, notion_1.getBlockChildren)(this.notionClient, id, totalPage);
+        const parsedData = await this.blocksToMarkdown(blocks);
+        return parsedData;
+    }
+    /**
+     * Converts list of Notion Blocks to Markdown Blocks
+     * @param {ListBlockChildrenResponseResults | undefined} blocks - List of notion blocks
+     * @param {number} totalPage - Retrieve block children request number, page_size Maximum = totalPage * 100
+     * @param {MdBlock[]} mdBlocks - Defines max depth of nesting
+     * @returns {Promise<MdBlock[]>} - Array of markdown blocks with their children
+     */
+    async blocksToMarkdown(blocks, totalPage = null, mdBlocks = []) {
+        if (!this.notionClient) {
+            throw new Error("notion client is not provided, for more details check out https://github.com/souvikinator/notion-to-md");
+        }
+        if (!blocks)
+            return mdBlocks;
+        for (let i = 0; i < blocks.length; i++) {
+            let block = blocks[i];
+            if ("has_children" in block &&
+                block.has_children &&
+                block.type !== "column_list" &&
+                block.type !== "toggle") {
+                let child_blocks = await (0, notion_1.getBlockChildren)(this.notionClient, block.id, totalPage);
+                mdBlocks.push({
+                    parent: await this.blockToMarkdown(block),
+                    children: [],
+                });
+                let l = mdBlocks.length;
+                await this.blocksToMarkdown(child_blocks, totalPage, mdBlocks[l - 1].children);
+                continue;
+            }
+            let tmp = await this.blockToMarkdown(block);
+            mdBlocks.push({ parent: tmp, children: [] });
+        }
+        return mdBlocks;
+    }
+    /**
+     * Converts a Notion Block to a Markdown Block
+     * @param {ListBlockChildrenResponseResult} block - single notion block
+     * @returns {string} corresponding markdown string of the passed block
+     */
+    async blockToMarkdown(block) {
+        var _a;
+        if (typeof block !== "object" || !("type" in block))
+            return "";
+        let parsedData = "";
+        const { type } = block;
+        if (type in this.customTransformers && !!this.customTransformers[type])
+            return await this.customTransformers[type](block);
+        switch (type) {
+            case "image":
+                {
+                    let blockContent = block.image;
+                    const image_caption_plain = blockContent.caption
+                        .map((item) => item.plain_text)
+                        .join("");
+                    const image_type = blockContent.type;
+                    if (image_type === "external")
+                        return md.image(image_caption_plain, blockContent.external.url);
+                    if (image_type === "file")
+                        return md.image(image_caption_plain, blockContent.file.url);
+                }
+                break;
+            case "divider": {
+                return md.divider();
+            }
+            case "equation": {
+                return md.codeBlock(block.equation.expression);
+            }
+            case "video":
+            case "file":
+            case "pdf":
+                {
+                    let blockContent;
+                    if (type === "video")
+                        blockContent = block.video;
+                    if (type === "file")
+                        blockContent = block.file;
+                    if (type === "pdf")
+                        blockContent = block.pdf;
+                    if (blockContent) {
+                        const file_type = blockContent.type;
+                        if (file_type === "external")
+                            return md.link("image", blockContent.external.url);
+                        if (file_type === "file")
+                            return md.link("image", blockContent.file.url);
+                    }
+                }
+                break;
+            case "bookmark":
+            case "embed":
+            case "link_preview":
+            case "link_to_page":
+            case "child_page":
+            case "child_database":
+                {
+                    let blockContent;
+                    let title = type;
+                    if (type === "bookmark")
+                        blockContent = block.bookmark;
+                    if (type === "embed")
+                        blockContent = block.embed;
+                    if (type === "link_preview")
+                        blockContent = block.link_preview;
+                    if (type === "link_to_page" &&
+                        block.link_to_page.type === "page_id") {
+                        blockContent = { url: block.link_to_page.page_id };
+                    }
+                    if (type === "child_page") {
+                        blockContent = { url: block.id };
+                        title = block.child_page.title;
+                    }
+                    if (type === "child_database") {
+                        blockContent = { url: block.id };
+                        title = block.child_database.title || "child_database";
+                    }
+                    if (blockContent)
+                        return md.link(title, blockContent.url);
+                }
+                break;
+            case "table": {
+                const { id, has_children } = block;
+                let tableArr = [];
+                if (has_children) {
+                    const tableRows = await (0, notion_1.getBlockChildren)(this.notionClient, id, 100);
+                    // console.log(">>", tableRows);
+                    let rowsPromise = tableRows === null || tableRows === void 0 ? void 0 : tableRows.map(async (row) => {
+                        const { type } = row;
+                        const cells = row[type]["cells"];
+                        /**
+                         * this is more like a hack since matching the type text was
+                         * difficult. So converting each cell to paragraph type to
+                         * reuse the blockToMarkdown function
+                         */
+                        let cellStringPromise = cells.map(async (cell) => await this.blockToMarkdown({
+                            type: "paragraph",
+                            paragraph: { rich_text: cell },
+                        }));
+                        const cellStringArr = await Promise.all(cellStringPromise);
+                        // console.log("~~", cellStringArr);
+                        tableArr.push(cellStringArr);
+                        // console.log(tableArr);
+                    });
+                    await Promise.all(rowsPromise || []);
+                }
+                return md.table(tableArr);
+            }
+            case "column_list": {
+                const { id, has_children } = block;
+                if (!has_children)
+                    return "";
+                const column_list_children = await (0, notion_1.getBlockChildren)(this.notionClient, id, 100);
+                let column_list_promise = column_list_children.map(async (column) => await this.blockToMarkdown(column));
+                let column_list = await Promise.all(column_list_promise);
+                return column_list.join("\n\n");
+            }
+            case "column": {
+                const { id, has_children } = block;
+                if (!has_children)
+                    return "";
+                const column_children = await (0, notion_1.getBlockChildren)(this.notionClient, id, 100);
+                const column_children_promise = column_children.map(async (column_child) => await this.blockToMarkdown(column_child));
+                let column = await Promise.all(column_children_promise);
+                return column.join("\n\n");
+            }
+            case "toggle": {
+                const { id, has_children } = block;
+                const toggle_summary = (_a = block.toggle.rich_text[0]) === null || _a === void 0 ? void 0 : _a.plain_text;
+                // empty toggle
+                if (!has_children) {
+                    return md.toggle(toggle_summary);
+                }
+                const toggle_children_object = await (0, notion_1.getBlockChildren)(this.notionClient, id, 100);
+                // parse children blocks to md object
+                const toggle_children = await this.blocksToMarkdown(toggle_children_object);
+                // convert children md object to md string
+                const toggle_children_md_string = this.toMarkdownString(toggle_children);
+                return md.toggle(toggle_summary, toggle_children_md_string);
+            }
+            // Rest of the types
+            // "paragraph"
+            // "heading_1"
+            // "heading_2"
+            // "heading_3"
+            // "bulleted_list_item"
+            // "numbered_list_item"
+            // "quote"
+            // "to_do"
+            // "template"
+            // "synced_block"
+            // "child_page"
+            // "child_database"
+            // "code"
+            // "callout"
+            // "breadcrumb"
+            // "table_of_contents"
+            // "column_list"
+            // "column"
+            // "link_to_page"
+            // "audio"
+            // "unsupported"
+            default: {
+                // In this case typescript is not able to index the types properly, hence ignoring the error
+                // @ts-ignore
+                let blockContent = block[type].text || block[type].rich_text || [];
+                blockContent.map((content) => {
+                    const annotations = content.annotations;
+                    let plain_text = content.plain_text;
+                    plain_text = this.annotatePlainText(plain_text, annotations);
+                    if (content["href"])
+                        plain_text = md.link(plain_text, content["href"]);
+                    parsedData += plain_text;
+                });
+            }
+        }
+        switch (type) {
+            case "code":
+                {
+                    parsedData = md.codeBlock(parsedData, block[type].language);
+                }
+                break;
+            case "heading_1":
+                {
+                    parsedData = md.heading1(parsedData);
+                }
+                break;
+            case "heading_2":
+                {
+                    parsedData = md.heading2(parsedData);
+                }
+                break;
+            case "heading_3":
+                {
+                    parsedData = md.heading3(parsedData);
+                }
+                break;
+            case "quote":
+                {
+                    parsedData = md.quote(parsedData);
+                }
+                break;
+            case "callout":
+                {
+                    parsedData = md.callout(parsedData, block[type].icon);
+                }
+                break;
+            case "bulleted_list_item":
+                {
+                    parsedData = md.bullet(parsedData);
+                }
+                break;
+            case "numbered_list_item":
+                {
+                    parsedData = md.bullet(parsedData, block.numbered_list_item.number);
+                }
+                break;
+            case "to_do":
+                {
+                    parsedData = md.todo(parsedData, block.to_do.checked);
+                }
+                break;
+        }
+        return parsedData;
+    }
+    /**
+     * Annoate text using provided annotations
+     * @param {string} text - String to be annotated
+     * @param {Annotations} annotations - Annotation object of a notion block
+     * @returns {string} - Annotated text
+     */
+    annotatePlainText(text, annotations) {
+        // if text is all spaces, don't annotate
+        if (text.match(/^\s*$/))
+            return text;
+        const leadingSpaceMatch = text.match(/^(\s*)/);
+        const trailingSpaceMatch = text.match(/(\s*)$/);
+        const leading_space = leadingSpaceMatch ? leadingSpaceMatch[0] : "";
+        const trailing_space = trailingSpaceMatch ? trailingSpaceMatch[0] : "";
+        text = text.trim();
+        if (text !== "") {
+            if (annotations.code)
+                text = md.inlineCode(text);
+            if (annotations.bold)
+                text = md.bold(text);
+            if (annotations.italic)
+                text = md.italic(text);
+            if (annotations.strikethrough)
+                text = md.strikethrough(text);
+            if (annotations.underline)
+                text = md.underline(text);
+        }
+        return leading_space + text + trailing_space;
+    }
+}
+exports.NotionToMarkdown = NotionToMarkdown;
 //# sourceMappingURL=notion-to-md.js.map