@arabold/docs-mcp-server 1.7.0 → 1.8.0

package/dist/{chunk-FAZDXJQN.js → chunk-ADZQJG2M.js}

@@ -144,55 +144,8 @@ var logger = {
   }
 };
 
-// node_modules/uuid/dist/esm-node/stringify.js
-var byteToHex = [];
-for (let i = 0; i < 256; ++i) {
-  byteToHex.push((i + 256).toString(16).slice(1));
-}
-function unsafeStringify(arr, offset = 0) {
-  return (byteToHex[arr[offset + 0]] + byteToHex[arr[offset + 1]] + byteToHex[arr[offset + 2]] + byteToHex[arr[offset + 3]] + "-" + byteToHex[arr[offset + 4]] + byteToHex[arr[offset + 5]] + "-" + byteToHex[arr[offset + 6]] + byteToHex[arr[offset + 7]] + "-" + byteToHex[arr[offset + 8]] + byteToHex[arr[offset + 9]] + "-" + byteToHex[arr[offset + 10]] + byteToHex[arr[offset + 11]] + byteToHex[arr[offset + 12]] + byteToHex[arr[offset + 13]] + byteToHex[arr[offset + 14]] + byteToHex[arr[offset + 15]]).toLowerCase();
-}
-
-// node_modules/uuid/dist/esm-node/rng.js
-import crypto from "node:crypto";
-var rnds8Pool = new Uint8Array(256);
-var poolPtr = rnds8Pool.length;
-function rng() {
-  if (poolPtr > rnds8Pool.length - 16) {
-    crypto.randomFillSync(rnds8Pool);
-    poolPtr = 0;
-  }
-  return rnds8Pool.slice(poolPtr, poolPtr += 16);
-}
-
-// node_modules/uuid/dist/esm-node/native.js
-import crypto2 from "node:crypto";
-var native_default = {
-  randomUUID: crypto2.randomUUID
-};
-
-// node_modules/uuid/dist/esm-node/v4.js
-function v4(options, buf, offset) {
-  if (native_default.randomUUID && !buf && !options) {
-    return native_default.randomUUID();
-  }
-  options = options || {};
-  const rnds = options.random || (options.rng || rng)();
-  rnds[6] = rnds[6] & 15 | 64;
-  rnds[8] = rnds[8] & 63 | 128;
-  if (buf) {
-    offset = offset || 0;
-    for (let i = 0; i < 16; ++i) {
-      buf[offset + i] = rnds[i];
-    }
-    return buf;
-  }
-  return unsafeStringify(rnds);
-}
-var v4_default = v4;
-
-// src/utils/url.ts
-import psl from "psl";
+// src/scraper/fetcher/HttpFetcher.ts
+import axios from "axios";
 
 // src/utils/errors.ts
 var ScraperError = class extends Error {
@@ -224,67 +177,7 @@ var RedirectError = class extends ScraperError {
   }
 };
 
-// src/utils/url.ts
-var defaultNormalizerOptions = {
-  ignoreCase: true,
-  removeHash: true,
-  removeTrailingSlash: true,
-  removeQuery: false,
-  removeIndex: true
-};
-function normalizeUrl(url, options = defaultNormalizerOptions) {
-  try {
-    const parsedUrl = new URL(url);
-    const finalOptions = { ...defaultNormalizerOptions, ...options };
-    const normalized = new URL(parsedUrl.origin + parsedUrl.pathname);
-    if (finalOptions.removeIndex) {
-      normalized.pathname = normalized.pathname.replace(
-        /\/index\.(html|htm|asp|php|jsp)$/i,
-        "/"
-      );
-    }
-    if (finalOptions.removeTrailingSlash && normalized.pathname.length > 1) {
-      normalized.pathname = normalized.pathname.replace(/\/+$/, "");
-    }
-    const preservedHash = !finalOptions.removeHash ? parsedUrl.hash : "";
-    const preservedSearch = !finalOptions.removeQuery ? parsedUrl.search : "";
-    let result = normalized.origin + normalized.pathname;
-    if (preservedSearch) {
-      result += preservedSearch;
-    }
-    if (preservedHash) {
-      result += preservedHash;
-    }
-    if (finalOptions.ignoreCase) {
-      result = result.toLowerCase();
-    }
-    return result;
-  } catch {
-    return url;
-  }
-}
-function validateUrl(url) {
-  try {
-    new URL(url);
-  } catch (error) {
-    throw new InvalidUrlError(url, error instanceof Error ? error : void 0);
-  }
-}
-function hasSameHostname(urlA, urlB) {
-  return urlA.hostname.toLowerCase() === urlB.hostname.toLowerCase();
-}
-function hasSameDomain(urlA, urlB) {
-  const domainA = psl.get(urlA.hostname.toLowerCase());
-  const domainB = psl.get(urlB.hostname.toLowerCase());
-  return domainA !== null && domainA === domainB;
-}
-function isSubpath(baseUrl, targetUrl) {
-  const basePath = baseUrl.pathname.endsWith("/") ? baseUrl.pathname : `${baseUrl.pathname}/`;
-  return targetUrl.pathname.startsWith(basePath);
-}
-
 // src/scraper/fetcher/HttpFetcher.ts
-import axios from "axios";
 var HttpFetcher = class {
   MAX_RETRIES = 6;
   BASE_DELAY = 1e3;
@@ -394,29 +287,6 @@ var FileFetcher = class {
   }
 };
 
-// src/scraper/strategies/BaseScraperStrategy.ts
-import { URL as URL2 } from "node:url";
-
-// src/pipeline/errors.ts
-var PipelineError = class extends Error {
-  constructor(message, cause) {
-    super(message);
-    this.cause = cause;
-    this.name = this.constructor.name;
-    if (cause?.stack) {
-      this.stack = `${this.stack}
-Caused by: ${cause.stack}`;
-    }
-  }
-};
-var PipelineStateError = class extends PipelineError {
-};
-var CancellationError = class extends PipelineError {
-  constructor(message = "Operation cancelled") {
-    super(message);
-  }
-};
-
 // src/scraper/processor/HtmlProcessor.ts
 import createDOMPurify from "dompurify";
 import { JSDOM } from "jsdom";
@@ -439,7 +309,7 @@ var HtmlProcessor = class {
     "input",
     "textarea",
     "select",
-    "form",
+    // "form", // Known issue: Some pages use alerts for important content
     ".ads",
     ".advertisement",
     ".banner",
@@ -472,18 +342,16 @@ var HtmlProcessor = class {
     ".signup-form",
     ".tooltip",
     ".dropdown-menu",
-    ".alert",
+    // ".alert", // Known issue: Some pages use alerts for important content
     ".breadcrumb",
     ".pagination",
-    '[role="alert"]',
+    // '[role="alert"]', // Known issue: Some pages use alerts for important content
     '[role="banner"]',
     '[role="dialog"]',
     '[role="alertdialog"]',
     '[role="region"][aria-label*="skip" i]',
     '[aria-modal="true"]',
-    ".noprint",
-    "figure",
-    "sup"
+    ".noprint"
   ];
   constructor(options) {
     this.turndownService = new TurndownService({
@@ -514,9 +382,17 @@ var HtmlProcessor = class {
             }
           }
         }
+        const text3 = (() => {
+          const clone = element.cloneNode(true);
+          const brElements = Array.from(clone.querySelectorAll("br"));
+          for (const br of brElements) {
+            br.replaceWith("\n");
+          }
+          return clone.textContent;
+        })();
         return `
 \`\`\`${language}
-${node2.textContent}
+${text3}
 \`\`\`
 `;
       }
@@ -622,6 +498,136 @@ var MarkdownProcessor = class {
   }
 };
 
+// node_modules/uuid/dist/esm-node/stringify.js
+var byteToHex = [];
+for (let i = 0; i < 256; ++i) {
+  byteToHex.push((i + 256).toString(16).slice(1));
+}
+function unsafeStringify(arr, offset = 0) {
+  return (byteToHex[arr[offset + 0]] + byteToHex[arr[offset + 1]] + byteToHex[arr[offset + 2]] + byteToHex[arr[offset + 3]] + "-" + byteToHex[arr[offset + 4]] + byteToHex[arr[offset + 5]] + "-" + byteToHex[arr[offset + 6]] + byteToHex[arr[offset + 7]] + "-" + byteToHex[arr[offset + 8]] + byteToHex[arr[offset + 9]] + "-" + byteToHex[arr[offset + 10]] + byteToHex[arr[offset + 11]] + byteToHex[arr[offset + 12]] + byteToHex[arr[offset + 13]] + byteToHex[arr[offset + 14]] + byteToHex[arr[offset + 15]]).toLowerCase();
+}
+
+// node_modules/uuid/dist/esm-node/rng.js
+import crypto from "node:crypto";
+var rnds8Pool = new Uint8Array(256);
+var poolPtr = rnds8Pool.length;
+function rng() {
+  if (poolPtr > rnds8Pool.length - 16) {
+    crypto.randomFillSync(rnds8Pool);
+    poolPtr = 0;
+  }
+  return rnds8Pool.slice(poolPtr, poolPtr += 16);
+}
+
+// node_modules/uuid/dist/esm-node/native.js
+import crypto2 from "node:crypto";
+var native_default = {
+  randomUUID: crypto2.randomUUID
+};
+
+// node_modules/uuid/dist/esm-node/v4.js
+function v4(options, buf, offset) {
+  if (native_default.randomUUID && !buf && !options) {
+    return native_default.randomUUID();
+  }
+  options = options || {};
+  const rnds = options.random || (options.rng || rng)();
+  rnds[6] = rnds[6] & 15 | 64;
+  rnds[8] = rnds[8] & 63 | 128;
+  if (buf) {
+    offset = offset || 0;
+    for (let i = 0; i < 16; ++i) {
+      buf[offset + i] = rnds[i];
+    }
+    return buf;
+  }
+  return unsafeStringify(rnds);
+}
+var v4_default = v4;
+
+// src/utils/url.ts
+import psl from "psl";
+var defaultNormalizerOptions = {
+  ignoreCase: true,
+  removeHash: true,
+  removeTrailingSlash: true,
+  removeQuery: false,
+  removeIndex: true
+};
+function normalizeUrl(url, options = defaultNormalizerOptions) {
+  try {
+    const parsedUrl = new URL(url);
+    const finalOptions = { ...defaultNormalizerOptions, ...options };
+    const normalized = new URL(parsedUrl.origin + parsedUrl.pathname);
+    if (finalOptions.removeIndex) {
+      normalized.pathname = normalized.pathname.replace(
+        /\/index\.(html|htm|asp|php|jsp)$/i,
+        "/"
+      );
+    }
+    if (finalOptions.removeTrailingSlash && normalized.pathname.length > 1) {
+      normalized.pathname = normalized.pathname.replace(/\/+$/, "");
+    }
+    const preservedHash = !finalOptions.removeHash ? parsedUrl.hash : "";
+    const preservedSearch = !finalOptions.removeQuery ? parsedUrl.search : "";
+    let result = normalized.origin + normalized.pathname;
+    if (preservedSearch) {
+      result += preservedSearch;
+    }
+    if (preservedHash) {
+      result += preservedHash;
+    }
+    if (finalOptions.ignoreCase) {
+      result = result.toLowerCase();
+    }
+    return result;
+  } catch {
+    return url;
+  }
+}
+function validateUrl(url) {
+  try {
+    new URL(url);
+  } catch (error) {
+    throw new InvalidUrlError(url, error instanceof Error ? error : void 0);
+  }
+}
+function hasSameHostname(urlA, urlB) {
+  return urlA.hostname.toLowerCase() === urlB.hostname.toLowerCase();
+}
+function hasSameDomain(urlA, urlB) {
+  const domainA = psl.get(urlA.hostname.toLowerCase());
+  const domainB = psl.get(urlB.hostname.toLowerCase());
+  return domainA !== null && domainA === domainB;
+}
+function isSubpath(baseUrl, targetUrl) {
+  const basePath = baseUrl.pathname.endsWith("/") ? baseUrl.pathname : `${baseUrl.pathname}/`;
+  return targetUrl.pathname.startsWith(basePath);
+}
+
+// src/scraper/strategies/BaseScraperStrategy.ts
+import { URL as URL2 } from "node:url";
+
+// src/pipeline/errors.ts
+var PipelineError = class extends Error {
+  constructor(message, cause) {
+    super(message);
+    this.cause = cause;
+    this.name = this.constructor.name;
+    if (cause?.stack) {
+      this.stack = `${this.stack}
+Caused by: ${cause.stack}`;
+    }
+  }
+};
+var PipelineStateError = class extends PipelineError {
+};
+var CancellationError = class extends PipelineError {
+  constructor(message = "Operation cancelled") {
+    super(message);
+  }
+};
+
 // src/scraper/strategies/BaseScraperStrategy.ts
 var DEFAULT_MAX_PAGES = 100;
 var DEFAULT_MAX_DEPTH = 3;
@@ -1315,57 +1321,54 @@ var LibraryNotFoundError = class extends ToolError {
   }
 };
 
-// src/tools/SearchTool.ts
-var SearchTool = class {
-  docService;
-  constructor(docService) {
-    this.docService = docService;
+// src/tools/FetchUrlTool.ts
+var FetchUrlTool = class {
+  constructor(httpFetcher, fileFetcher, processor) {
+    this.processor = processor;
+    this.fetchers = [httpFetcher, fileFetcher];
   }
+  /**
+   * Collection of fetchers that will be tried in order for a given URL.
+   */
+  fetchers;
+  /**
+   * Fetches content from a URL and converts it to Markdown.
+   * Supports both HTTP/HTTPS URLs and local file URLs (file://).
+   * @returns The processed Markdown content
+   * @throws {ToolError} If fetching or processing fails
+   */
   async execute(options) {
-    const { library, version = "latest", query, limit = 5, exactMatch = false } = options;
-    logger.info(
-      `\u{1F50D} Searching ${library}@${version} for: ${query}${exactMatch ? " (exact match)" : ""}`
-    );
-    try {
-      await this.docService.validateLibraryExists(library);
-      let versionToSearch = version;
-      if (!exactMatch) {
-        const versionResult = await this.docService.findBestVersion(library, version);
-        versionToSearch = versionResult.bestMatch;
-      }
-      const results = await this.docService.searchStore(
-        library,
-        versionToSearch,
-        query,
-        limit
+    const { url } = options;
+    const canFetchResults = this.fetchers.map((f) => f.canFetch(url));
+    const fetcherIndex = canFetchResults.findIndex((result) => result === true);
+    if (fetcherIndex === -1) {
+      throw new ToolError(
+        `Invalid URL: ${url}. Must be an HTTP/HTTPS URL or a file:// URL.`,
+        this.constructor.name
       );
-      logger.info(`\u2705 Found ${results.length} matching results`);
-      return { results };
+    }
+    const fetcher = this.fetchers[fetcherIndex];
+    try {
+      logger.info(`\u{1F4E1} Fetching ${url}...`);
+      const rawContent = await fetcher.fetch(url, {
+        followRedirects: options.followRedirects ?? true,
+        maxRetries: 3
+      });
+      logger.info("\u{1F504} Converting to Markdown...");
+      const processed = await this.processor.process(rawContent);
+      logger.info(`\u2705 Successfully converted ${url} to Markdown`);
+      return processed.content;
     } catch (error) {
-      if (error instanceof LibraryNotFoundError) {
-        logger.info(`\u2139\uFE0F Library not found: ${error.message}`);
-        return {
-          results: [],
-          error: {
-            message: error.message,
-            suggestions: error.suggestions
-          }
-        };
-      }
-      if (error instanceof VersionNotFoundError) {
-        logger.info(`\u2139\uFE0F Version not found: ${error.message}`);
-        return {
-          results: [],
-          error: {
-            message: error.message,
-            availableVersions: error.availableVersions
-          }
-        };
+      if (error instanceof ScraperError) {
+        throw new ToolError(
+          `Failed to fetch or process URL: ${error.message}`,
+          this.constructor.name
+        );
       }
-      logger.error(
-        `\u274C Search failed: ${error instanceof Error ? error.message : "Unknown error"}`
+      throw new ToolError(
+        `Failed to fetch or process URL: ${error instanceof Error ? error.message : String(error)}`,
+        this.constructor.name
       );
-      throw error;
     }
   }
 };
@@ -1531,72 +1534,69 @@ var ScrapeTool = class {
   }
 };
 
-// src/tools/ListJobsTool.ts
-var ListJobsTool = class {
-  manager;
-  // Change property name and type
-  /**
-   * Creates an instance of ListJobsTool.
-   * @param manager The PipelineManager instance.
-   */
-  constructor(manager) {
-    this.manager = manager;
+// src/tools/SearchTool.ts
+var SearchTool = class {
+  docService;
+  constructor(docService) {
+    this.docService = docService;
   }
-  /**
-   * Executes the tool to retrieve a list of pipeline jobs.
-   * @param input - The input parameters, optionally including a status filter.
-   * @returns A promise that resolves with the list of simplified job objects.
-   * @throws {PipelineStateError} If the pipeline manager is somehow unavailable.
-   */
-  async execute(input) {
-    const jobs = await this.manager.getJobs(input.status);
-    const simplifiedJobs = jobs.map(
-      (job) => ({
-        id: job.id,
-        library: job.library,
-        version: job.version,
-        status: job.status,
-        createdAt: job.createdAt.toISOString(),
-        startedAt: job.startedAt?.toISOString() ?? null,
-        finishedAt: job.finishedAt?.toISOString() ?? null,
-        error: job.error?.message ?? null
-      })
+  async execute(options) {
+    const { library, version, query, limit = 5, exactMatch = false } = options;
+    if (exactMatch && (!version || version === "latest")) {
+      await this.docService.validateLibraryExists(library);
+      const versions = await this.docService.listVersions(library);
+      throw new VersionNotFoundError(
+        library,
+        "latest",
+        versions
+        // versions already has the correct { version: string, indexed: boolean } format
+      );
+    }
+    const resolvedVersion = version || "latest";
+    logger.info(
+      `\u{1F50D} Searching ${library}@${resolvedVersion} for: ${query}${exactMatch ? " (exact match)" : ""}`
     );
-    return { jobs: simplifiedJobs };
-  }
-};
-
-// src/tools/GetJobInfoTool.ts
-var GetJobInfoTool = class {
-  manager;
-  /**
-   * Creates an instance of GetJobInfoTool.
-   * @param manager The PipelineManager instance.
-   */
-  constructor(manager) {
-    this.manager = manager;
-  }
-  /**
-   * Executes the tool to retrieve simplified info for a specific job.
-   * @param input - The input parameters, containing the jobId.
-   * @returns A promise that resolves with the simplified job info or null if not found.
-   */
-  async execute(input) {
-    const job = await this.manager.getJob(input.jobId);
-    if (!job) {
-      return { job: null };
+    try {
+      await this.docService.validateLibraryExists(library);
+      let versionToSearch = resolvedVersion;
+      if (!exactMatch) {
+        const versionResult = await this.docService.findBestVersion(library, version);
+        versionToSearch = versionResult.bestMatch;
+      }
+      const results = await this.docService.searchStore(
+        library,
+        versionToSearch,
+        query,
+        limit
+      );
+      logger.info(`\u2705 Found ${results.length} matching results`);
+      return { results };
+    } catch (error) {
+      if (error instanceof LibraryNotFoundError) {
+        logger.info(`\u2139\uFE0F Library not found: ${error.message}`);
+        return {
+          results: [],
+          error: {
+            message: error.message,
+            suggestions: error.suggestions
+          }
+        };
+      }
+      if (error instanceof VersionNotFoundError) {
+        logger.info(`\u2139\uFE0F Version not found: ${error.message}`);
+        return {
+          results: [],
+          error: {
+            message: error.message,
+            availableVersions: error.availableVersions
+          }
+        };
+      }
+      logger.error(
+        `\u274C Search failed: ${error instanceof Error ? error.message : "Unknown error"}`
+      );
+      throw error;
     }
-    const jobInfo = {
-      id: job.id,
-      library: job.library,
-      version: job.version,
-      status: job.status,
-      createdAt: job.createdAt.toISOString(),
-      startedAt: job.startedAt?.toISOString() ?? null,
-      finishedAt: job.finishedAt?.toISOString() ?? null,
-      error: job.error?.message ?? null
-    };
-    return { job: jobInfo };
   }
 };
 
@@ -1657,6 +1657,75 @@ var CancelJobTool = class {
   }
 };
 
+// src/tools/GetJobInfoTool.ts
+var GetJobInfoTool = class {
+  manager;
+  /**
+   * Creates an instance of GetJobInfoTool.
+   * @param manager The PipelineManager instance.
+   */
+  constructor(manager) {
+    this.manager = manager;
+  }
+  /**
+   * Executes the tool to retrieve simplified info for a specific job.
+   * @param input - The input parameters, containing the jobId.
+   * @returns A promise that resolves with the simplified job info or null if not found.
+   */
+  async execute(input) {
+    const job = await this.manager.getJob(input.jobId);
+    if (!job) {
+      return { job: null };
+    }
+    const jobInfo = {
+      id: job.id,
+      library: job.library,
+      version: job.version,
+      status: job.status,
+      createdAt: job.createdAt.toISOString(),
+      startedAt: job.startedAt?.toISOString() ?? null,
+      finishedAt: job.finishedAt?.toISOString() ?? null,
+      error: job.error?.message ?? null
+    };
+    return { job: jobInfo };
+  }
+};
+
+// src/tools/ListJobsTool.ts
+var ListJobsTool = class {
+  manager;
+  // Change property name and type
+  /**
+   * Creates an instance of ListJobsTool.
+   * @param manager The PipelineManager instance.
+   */
+  constructor(manager) {
+    this.manager = manager;
+  }
+  /**
+   * Executes the tool to retrieve a list of pipeline jobs.
+   * @param input - The input parameters, optionally including a status filter.
+   * @returns A promise that resolves with the list of simplified job objects.
+   * @throws {PipelineStateError} If the pipeline manager is somehow unavailable.
+   */
+  async execute(input) {
+    const jobs = await this.manager.getJobs(input.status);
+    const simplifiedJobs = jobs.map(
+      (job) => ({
+        id: job.id,
+        library: job.library,
+        version: job.version,
+        status: job.status,
+        createdAt: job.createdAt.toISOString(),
+        startedAt: job.startedAt?.toISOString() ?? null,
+        finishedAt: job.finishedAt?.toISOString() ?? null,
+        error: job.error?.message ?? null
+      })
+    );
+    return { jobs: simplifiedJobs };
+  }
+};
+
 // src/tools/RemoveTool.ts
 var RemoveToolInputSchema = {
   type: "object",
@@ -11269,7 +11338,8 @@ var DocumentManagementService = class {
       dbPath = path3.join(dbDir, "documents.db");
       logger.debug(`\u{1F4BE} Using database directory from DOCS_MCP_STORE_PATH: ${dbDir}`);
     } else {
-      const oldDbDir = path3.join(process.cwd(), ".store");
+      const projectRoot = path3.resolve(import.meta.dirname, "..");
+      const oldDbDir = path3.join(projectRoot, ".store");
       const oldDbPath = path3.join(oldDbDir, "documents.db");
       const oldDbExists = existsSync(oldDbPath);
       if (oldDbExists) {
@@ -11498,17 +11568,21 @@ var DocumentManagementService = class {
 export {
   setLogLevel,
   logger,
+  HttpFetcher,
+  FileFetcher,
+  HtmlProcessor,
   PipelineJobStatus,
   PipelineManager,
+  CancelJobTool,
   VersionNotFoundError,
-  SearchTool,
+  FetchUrlTool,
   FindVersionTool,
-  ListLibrariesTool,
-  ScrapeTool,
-  ListJobsTool,
   GetJobInfoTool,
-  CancelJobTool,
+  ListJobsTool,
+  ListLibrariesTool,
   RemoveTool,
+  ScrapeTool,
+  SearchTool,
   DocumentManagementService
 };
-//# sourceMappingURL=chunk-FAZDXJQN.js.map
+//# sourceMappingURL=chunk-ADZQJG2M.js.map