@canaryai/cli 0.2.5 → 0.2.7

package/dist/{chunk-ILEPYWZX.js → chunk-A44B2PEA.js}

@@ -1,7 +1,7 @@
 import { createRequire as __cr } from "module"; const require = __cr(import.meta.url);
 import {
   __require
-} from "./chunk-VLFUCAPZ.js";
+} from "./chunk-VKVL7WBN.js";
 
 // src/runner/config.ts
 import path2 from "path";
@@ -1288,4 +1288,4 @@ export {
   wrapExpect,
   wrapPage
 };
-//# sourceMappingURL=chunk-ILEPYWZX.js.map
+//# sourceMappingURL=chunk-A44B2PEA.js.map

package/dist/chunk-P5Z2Y5VV.js

@@ -0,0 +1,94 @@
+import { createRequire as __cr } from "module"; const require = __cr(import.meta.url);
+
+// ../browser-core/src/pdf-extract.ts
+import * as fs from "fs/promises";
+
+// ../browser-core/src/logger.ts
+var consoleLogger = {
+  debug: (msg, data) => {
+    if (data) console.debug(msg, data);
+    else console.debug(msg);
+  },
+  info: (msg, data) => {
+    if (data) console.info(msg, data);
+    else console.info(msg);
+  },
+  warn: (msg, data) => {
+    if (data) console.warn(msg, data);
+    else console.warn(msg);
+  },
+  error: (msg, data) => {
+    if (data) console.error(msg, data);
+    else console.error(msg);
+  }
+};
+
+// ../browser-core/src/pdf-extract.ts
+var _logger = consoleLogger;
+function setPdfExtractLogger(l) {
+  _logger = l;
+}
+var MAX_FILE_SIZE_BYTES = 50 * 1024 * 1024;
+var MAX_OUTPUT_CHARS = 1e5;
+async function extractPdfTextFromBuffer(buffer) {
+  if (buffer.length > MAX_FILE_SIZE_BYTES) {
+    _logger.warn("[PdfExtract] PDF too large for text extraction", {
+      sizeBytes: buffer.length,
+      maxBytes: MAX_FILE_SIZE_BYTES
+    });
+    return {
+      text: `[PDF too large for text extraction: ${formatBytes(buffer.length)} exceeds ${formatBytes(MAX_FILE_SIZE_BYTES)} limit]`,
+      totalPages: 0
+    };
+  }
+  const { extractText } = await import("./dist-5CSYV6PJ.js");
+  const uint8 = new Uint8Array(buffer);
+  const result = await extractText(uint8, { mergePages: true });
+  let text = result.text ?? "";
+  const totalPages = result.totalPages ?? 0;
+  if (text.length > MAX_OUTPUT_CHARS) {
+    _logger.info("[PdfExtract] Truncating extracted text", {
+      originalLength: text.length,
+      truncatedTo: MAX_OUTPUT_CHARS,
+      totalPages
+    });
+    text = text.slice(0, MAX_OUTPUT_CHARS) + `
+
+[Text truncated at ${MAX_OUTPUT_CHARS} characters]`;
+  }
+  _logger.info("[PdfExtract] Text extracted successfully", {
+    textLength: text.length,
+    totalPages,
+    sizeBytes: buffer.length
+  });
+  return { text, totalPages };
+}
+async function extractPdfText(filePath) {
+  const stat2 = await fs.stat(filePath);
+  if (stat2.size > MAX_FILE_SIZE_BYTES) {
+    _logger.warn("[PdfExtract] PDF file too large for text extraction", {
+      filePath,
+      sizeBytes: stat2.size,
+      maxBytes: MAX_FILE_SIZE_BYTES
+    });
+    return {
+      text: `[PDF too large for text extraction: ${formatBytes(stat2.size)} exceeds ${formatBytes(MAX_FILE_SIZE_BYTES)} limit]`,
+      totalPages: 0
+    };
+  }
+  const buffer = await fs.readFile(filePath);
+  return extractPdfTextFromBuffer(Buffer.from(buffer));
+}
+function formatBytes(bytes) {
+  if (bytes < 1024) return `${bytes}B`;
+  if (bytes < 1024 * 1024) return `${(bytes / 1024).toFixed(1)}KB`;
+  return `${(bytes / (1024 * 1024)).toFixed(1)}MB`;
+}
+
+export {
+  consoleLogger,
+  setPdfExtractLogger,
+  extractPdfTextFromBuffer,
+  extractPdfText
+};
+//# sourceMappingURL=chunk-P5Z2Y5VV.js.map

package/dist/chunk-P5Z2Y5VV.js.map

@@ -0,0 +1 @@
+{"version":3,"sources":["../../browser-core/src/pdf-extract.ts","../../browser-core/src/logger.ts"],"sourcesContent":["/**\n * PDF text extraction utility.\n *\n * Uses `unpdf` to extract text content from PDF files and buffers.\n * Includes size guards to prevent excessive memory usage.\n *\n * @module pdf-extract\n */\n\nimport * as fs from 'fs/promises';\nimport { consoleLogger, type BrowserLogger } from './logger.js';\n\nlet _logger: BrowserLogger = consoleLogger;\n\nexport function setPdfExtractLogger(l: BrowserLogger): void {\n  _logger = l;\n}\n\nconst MAX_FILE_SIZE_BYTES = 50 * 1024 * 1024; // 50MB\nconst MAX_OUTPUT_CHARS = 100_000;\n\n/**\n * Extract text content from a PDF buffer.\n * Returns the extracted text and total page count.\n */\nexport async function extractPdfTextFromBuffer(\n  buffer: Buffer\n): Promise<{ text: string; totalPages: number }> {\n  if (buffer.length > MAX_FILE_SIZE_BYTES) {\n    _logger.warn('[PdfExtract] PDF too large for text extraction', {\n      sizeBytes: buffer.length,\n      maxBytes: MAX_FILE_SIZE_BYTES,\n    });\n    return {\n      text: `[PDF too large for text extraction: ${formatBytes(buffer.length)} exceeds ${formatBytes(MAX_FILE_SIZE_BYTES)} limit]`,\n      totalPages: 0,\n    };\n  }\n\n  const { extractText } = await import('unpdf');\n  const uint8 = new Uint8Array(buffer);\n  const result = await extractText(uint8, { mergePages: true });\n\n  let text = result.text ?? '';\n  const totalPages = result.totalPages ?? 0;\n\n  if (text.length > MAX_OUTPUT_CHARS) {\n    _logger.info('[PdfExtract] Truncating extracted text', {\n      originalLength: text.length,\n      truncatedTo: MAX_OUTPUT_CHARS,\n      totalPages,\n    });\n    text = text.slice(0, MAX_OUTPUT_CHARS) + `\\n\\n[Text truncated at ${MAX_OUTPUT_CHARS} characters]`;\n  }\n\n  _logger.info('[PdfExtract] Text extracted successfully', {\n    textLength: text.length,\n    totalPages,\n    sizeBytes: buffer.length,\n  });\n\n  return { text, totalPages };\n}\n\n/**\n * Extract text content from a PDF file on disk.\n */\nexport async function extractPdfText(\n  filePath: string\n): Promise<{ text: string; totalPages: number }> {\n  const stat = await fs.stat(filePath);\n\n  if (stat.size > MAX_FILE_SIZE_BYTES) {\n    _logger.warn('[PdfExtract] PDF file too large for text extraction', {\n      filePath,\n      sizeBytes: stat.size,\n      maxBytes: MAX_FILE_SIZE_BYTES,\n    });\n    return {\n      text: `[PDF too large for text extraction: ${formatBytes(stat.size)} exceeds ${formatBytes(MAX_FILE_SIZE_BYTES)} limit]`,\n      totalPages: 0,\n    };\n  }\n\n  const buffer = await fs.readFile(filePath);\n  return extractPdfTextFromBuffer(Buffer.from(buffer));\n}\n\nfunction formatBytes(bytes: number): string {\n  if (bytes < 1024) return `${bytes}B`;\n  if (bytes < 1024 * 1024) return `${(bytes / 1024).toFixed(1)}KB`;\n  return `${(bytes / (1024 * 1024)).toFixed(1)}MB`;\n}\n","/**\n * Browser Logger Interface\n *\n * Abstracts logging so browser-core works in any environment:\n * - Cloud (apps/api): Wraps pino logger\n * - CLI (canary-cli): Uses console logger\n *\n * @module logger\n */\n\nexport interface BrowserLogger {\n  debug(msg: string, data?: Record<string, unknown>): void;\n  info(msg: string, data?: Record<string, unknown>): void;\n  warn(msg: string, data?: Record<string, unknown>): void;\n  error(msg: string, data?: Record<string, unknown>): void;\n}\n\n/**\n * Default console-based logger. Works everywhere without dependencies.\n */\nexport const consoleLogger: BrowserLogger = {\n  debug: (msg, data) => {\n    if (data) console.debug(msg, data);\n    else console.debug(msg);\n  },\n  info: (msg, data) => {\n    if (data) console.info(msg, data);\n    else console.info(msg);\n  },\n  warn: (msg, data) => {\n    if (data) console.warn(msg, data);\n    else console.warn(msg);\n  },\n  error: (msg, data) => {\n    if (data) console.error(msg, data);\n    else console.error(msg);\n  },\n};\n"],"mappings":";;;AASA,YAAY,QAAQ;;;ACWb,IAAM,gBAA+B;AAAA,EAC1C,OAAO,CAAC,KAAK,SAAS;AACpB,QAAI,KAAM,SAAQ,MAAM,KAAK,IAAI;AAAA,QAC5B,SAAQ,MAAM,GAAG;AAAA,EACxB;AAAA,EACA,MAAM,CAAC,KAAK,SAAS;AACnB,QAAI,KAAM,SAAQ,KAAK,KAAK,IAAI;AAAA,QAC3B,SAAQ,KAAK,GAAG;AAAA,EACvB;AAAA,EACA,MAAM,CAAC,KAAK,SAAS;AACnB,QAAI,KAAM,SAAQ,KAAK,KAAK,IAAI;AAAA,QAC3B,SAAQ,KAAK,GAAG;AAAA,EACvB;AAAA,EACA,OAAO,CAAC,KAAK,SAAS;AACpB,QAAI,KAAM,SAAQ,MAAM,KAAK,IAAI;AAAA,QAC5B,SAAQ,MAAM,GAAG;AAAA,EACxB;AACF;;;ADzBA,IAAI,UAAyB;AAEtB,SAAS,oBAAoB,GAAwB;AAC1D,YAAU;AACZ;AAEA,IAAM,sBAAsB,KAAK,OAAO;AACxC,IAAM,mBAAmB;AAMzB,eAAsB,yBACpB,QAC+C;AAC/C,MAAI,OAAO,SAAS,qBAAqB;AACvC,YAAQ,KAAK,kDAAkD;AAAA,MAC7D,WAAW,OAAO;AAAA,MAClB,UAAU;AAAA,IACZ,CAAC;AACD,WAAO;AAAA,MACL,MAAM,uCAAuC,YAAY,OAAO,MAAM,CAAC,YAAY,YAAY,mBAAmB,CAAC;AAAA,MACnH,YAAY;AAAA,IACd;AAAA,EACF;AAEA,QAAM,EAAE,YAAY,IAAI,MAAM,OAAO,oBAAO;AAC5C,QAAM,QAAQ,IAAI,WAAW,MAAM;AACnC,QAAM,SAAS,MAAM,YAAY,OAAO,EAAE,YAAY,KAAK,CAAC;AAE5D,MAAI,OAAO,OAAO,QAAQ;AAC1B,QAAM,aAAa,OAAO,cAAc;AAExC,MAAI,KAAK,SAAS,kBAAkB;AAClC,YAAQ,KAAK,0CAA0C;AAAA,MACrD,gBAAgB,KAAK;AAAA,MACrB,aAAa;AAAA,MACb;AAAA,IACF,CAAC;AACD,WAAO,KAAK,MAAM,GAAG,gBAAgB,IAAI;AAAA;AAAA,qBAA0B,gBAAgB;AAAA,EACrF;AAEA,UAAQ,KAAK,4CAA4C;AAAA,IACvD,YAAY,KAAK;AAAA,IACjB;AAAA,IACA,WAAW,OAAO;AAAA,EACpB,CAAC;AAED,SAAO,EAAE,MAAM,WAAW;AAC5B;AAKA,eAAsB,eACpB,UAC+C;AAC/C,QAAMA,QAAO,MAAS,QAAK,QAAQ;AAEnC,MAAIA,MAAK,OAAO,qBAAqB;AACnC,YAAQ,KAAK,uDAAuD;AAAA,MAClE;AAAA,MACA,WAAWA,MAAK;AAAA,MAChB,UAAU;AAAA,IACZ,CAAC;AACD,WAAO;AAAA,MACL,MAAM,uCAAuC,YAAYA,MAAK,IAAI,CAAC,YAAY,YAAY,mBAAmB,CAAC;AAAA,MAC/G,YAAY;AAAA,IACd;AAAA,EACF;AAEA,QAAM,SAAS,MAAS,YAAS,QAAQ;AACzC,SAAO,yBAAyB,OAAO,KAAK,MAAM,CAAC;AACrD;AAEA,SAAS,YAAY,OAAuB;AAC1C,MAAI,QAAQ,KAAM,QAAO,GAAG,KAAK;AACjC,MAAI,QAAQ,OAAO,KAAM,QAAO,IAAI,QAAQ,MAAM,QAAQ,CAAC,CAAC;AAC5D,SAAO,IAAI,SAAS,OAAO,OAAO,QAAQ,CAAC,CAAC;AAC9C;","names":["stat"]}