openredaction 1.0.0 → 1.0.8

package/dist/cli/test-pattern.js

@@ -1,430 +0,0 @@
-#!/usr/bin/env node
-#!/usr/bin/env node
-"use strict";
-
-// src/utils/safe-regex.ts
-function isUnsafePattern(pattern) {
-  if (/\*\+|\+\*|\+\+|\*\*/.test(pattern)) {
-    return true;
-  }
-  if (/\(a\+\)\+|\(b\*\)\*|\(c\+\)\+/.test(pattern)) {
-    return true;
-  }
-  return false;
-}
-function validatePattern(pattern) {
-  const patternStr = typeof pattern === "string" ? pattern : pattern.source;
-  if (patternStr.length > 5e3) {
-    throw new Error(`Regex pattern too long: ${patternStr.length} chars (max 5000)`);
-  }
-  if (isUnsafePattern(patternStr)) {
-    throw new Error(`Potentially unsafe regex pattern detected: ${patternStr.substring(0, 100)}...`);
-  }
-  try {
-    new RegExp(patternStr);
-  } catch (error) {
-    throw new Error(`Invalid regex pattern: ${error.message}`);
-  }
-}
-
-// src/cli/test-pattern.ts
-var args = process.argv.slice(2);
-function printHelp() {
-  console.log(`
-OpenRedaction Pattern Testing Tool
-
-Test custom patterns before deployment to prevent ReDoS vulnerabilities and validate functionality.
-
-Usage:
-  openredaction-test-pattern validate <pattern>           Validate pattern safety
-  openredaction-test-pattern test <pattern> <text>        Test pattern against sample text
-  openredaction-test-pattern check <pattern> [flags]      Check pattern with optional flags
-  openredaction-test-pattern benchmark <pattern> <text>   Benchmark pattern performance
-  openredaction-test-pattern --help                       Show this help message
-
-Commands:
-  validate <pattern>
-    Checks if a regex pattern is safe (no ReDoS vulnerabilities)
-    Returns: SAFE or UNSAFE with explanation
-
-  test <pattern> <text>
-    Tests a pattern against sample text and shows all matches
-    Returns: List of matches with positions
-
-  check <pattern> [flags]
-    Validates pattern syntax and compiles with optional flags
-    Returns: Pattern info and any warnings
-
-  benchmark <pattern> <text>
-    Measures pattern execution time and match count
-    Returns: Performance metrics
-
-Options:
-  --flags <flags>         Regex flags (g, i, m, etc.)
-  --timeout <ms>          Regex timeout in milliseconds (default: 100)
-  --json                  Output results as JSON
-  --verbose               Show detailed output
-
-Examples:
-  # Validate a pattern for ReDoS
-  openredaction-test-pattern validate "^[a-zA-Z0-9._%+-]+@[a-zA-Z0-9.-]+\\.[a-zA-Z]{2,}$"
-
-  # Test pattern against sample text
-  openredaction-test-pattern test "\\b\\d{3}-\\d{2}-\\d{4}\\b" "SSN: 123-45-6789"
-
-  # Check pattern with flags
-  openredaction-test-pattern check "[a-z]+" --flags gi
-
-  # Benchmark pattern performance
-  openredaction-test-pattern benchmark "\\b[A-Z][a-z]+ [A-Z][a-z]+\\b" "John Smith and Jane Doe"
-
-  # Test a custom pattern as JSON
-  openredaction-test-pattern test "\\b\\d{16}\\b" "Card: 4111111111111111" --json
-
-Safety Checks:
-  \u2713 Nested quantifiers (e.g., (a+)+)
-  \u2713 Overlapping alternation (e.g., (a|ab)+)
-  \u2713 Consecutive quantifiers (e.g., a*+)
-  \u2713 Dangerous backreferences (e.g., \\1+)
-  \u2713 Excessive pattern length (>5000 chars)
-  \u2713 Pattern compilation errors
-`);
-}
-function parseOptions(args2) {
-  const options = {};
-  for (let i = 0; i < args2.length; i++) {
-    if (args2[i] === "--flags" && args2[i + 1]) {
-      options.flags = args2[i + 1];
-      i++;
-    } else if (args2[i] === "--timeout" && args2[i + 1]) {
-      options.timeout = parseInt(args2[i + 1], 10);
-      i++;
-    } else if (args2[i] === "--json") {
-      options.json = true;
-    } else if (args2[i] === "--verbose") {
-      options.verbose = true;
-    }
-  }
-  return options;
-}
-function validatePatternCommand(pattern, options) {
-  const result = {
-    pattern,
-    safe: true,
-    warnings: [],
-    errors: []
-  };
-  try {
-    if (isUnsafePattern(pattern)) {
-      result.safe = false;
-      result.errors.push("Pattern contains potentially unsafe constructs (ReDoS risk)");
-      if (/(\([^)]*[*+{][^)]*\)[*+{])/.test(pattern)) {
-        result.warnings.push("Nested quantifiers detected: (a+)+ or (a*)*");
-      }
-      if (/\([^)]*\|[^)]*\)[*+{]/.test(pattern)) {
-        result.warnings.push("Overlapping alternation with quantifier: (a|ab)+");
-      }
-      if (/[*+?{][*+?{]/.test(pattern)) {
-        result.warnings.push("Consecutive quantifiers: a*+ or a+*");
-      }
-      if (/\\\d[*+{]/.test(pattern)) {
-        result.warnings.push("Backreference with quantifier: \\1+");
-      }
-    }
-    if (pattern.length > 5e3) {
-      result.safe = false;
-      result.errors.push(`Pattern too long: ${pattern.length} chars (max 5000)`);
-    }
-    validatePattern(pattern);
-    if (result.safe) {
-      result.message = "\u2713 Pattern is SAFE";
-    }
-  } catch (error) {
-    result.safe = false;
-    result.errors.push(error.message);
-  }
-  if (options.json) {
-    console.log(JSON.stringify(result, null, 2));
-  } else {
-    console.log("\nPattern Validation Result:");
-    console.log("\u2500".repeat(50));
-    console.log(`Pattern: ${pattern}`);
-    console.log(`Status: ${result.safe ? "\u2713 SAFE" : "\u2717 UNSAFE"}`);
-    if (result.warnings.length > 0) {
-      console.log("\nWarnings:");
-      result.warnings.forEach((w) => console.log(`  \u26A0 ${w}`));
-    }
-    if (result.errors.length > 0) {
-      console.log("\nErrors:");
-      result.errors.forEach((e) => console.log(`  \u2717 ${e}`));
-    }
-    if (result.safe) {
-      console.log("\n\u2713 Pattern is safe to use");
-    } else {
-      console.log("\n\u2717 Pattern is NOT safe - please revise before use");
-    }
-  }
-  process.exit(result.safe ? 0 : 1);
-}
-function testPatternCommand(pattern, text, options) {
-  const result = {
-    pattern,
-    text,
-    matches: [],
-    matchCount: 0
-  };
-  try {
-    validatePattern(pattern);
-    const flags = options.flags || "g";
-    const regex = new RegExp(pattern, flags);
-    let match;
-    while ((match = regex.exec(text)) !== null) {
-      result.matches.push({
-        value: match[0],
-        captureGroups: match.slice(1),
-        index: match.index,
-        length: match[0].length
-      });
-      result.matchCount++;
-      if (result.matchCount >= 1e3) {
-        result.warning = "Stopped after 1000 matches";
-        break;
-      }
-      if (match.index === regex.lastIndex) {
-        regex.lastIndex++;
-      }
-    }
-    result.success = true;
-  } catch (error) {
-    result.success = false;
-    result.error = error.message;
-  }
-  if (options.json) {
-    console.log(JSON.stringify(result, null, 2));
-  } else {
-    console.log("\nPattern Test Result:");
-    console.log("\u2500".repeat(50));
-    console.log(`Pattern: ${pattern}`);
-    console.log(`Flags: ${options.flags || "g"}`);
-    console.log(`Text: ${text}`);
-    console.log(`Matches: ${result.matchCount}`);
-    if (result.matchCount > 0) {
-      console.log("\nMatches Found:");
-      result.matches.forEach((m, i) => {
-        console.log(`  ${i + 1}. "${m.value}" at position ${m.index}`);
-        if (m.captureGroups.length > 0 && m.captureGroups.some((g) => g)) {
-          console.log(`     Capture groups: [${m.captureGroups.join(", ")}]`);
-        }
-      });
-    } else {
-      console.log("\n\u26A0 No matches found");
-    }
-    if (result.warning) {
-      console.log(`
-\u26A0 ${result.warning}`);
-    }
-    if (result.error) {
-      console.log(`
-\u2717 Error: ${result.error}`);
-    }
-  }
-  process.exit(result.success ? 0 : 1);
-}
-function checkPatternCommand(pattern, options) {
-  const result = {
-    pattern,
-    valid: false,
-    info: {},
-    warnings: []
-  };
-  try {
-    validatePattern(pattern);
-    const flags = options.flags || "";
-    const regex = new RegExp(pattern, flags);
-    result.valid = true;
-    result.info = {
-      source: regex.source,
-      flags: regex.flags,
-      length: pattern.length,
-      hasGroups: /\([^)]*\)/.test(pattern),
-      hasQuantifiers: /[*+?{]/.test(pattern),
-      hasAnchors: /[\^$]/.test(pattern),
-      hasLookahead: /\(\?[=!]/.test(pattern),
-      hasLookbehind: /\(\?<[=!]/.test(pattern)
-    };
-    if (isUnsafePattern(pattern)) {
-      result.warnings.push("Pattern may be vulnerable to ReDoS attacks");
-    }
-    if (pattern.length > 1e3) {
-      result.warnings.push("Pattern is very long, may impact performance");
-    }
-    if (!flags.includes("g") && /[*+{]/.test(pattern)) {
-      result.warnings.push("Pattern has quantifiers but no global flag - will only match once");
-    }
-  } catch (error) {
-    result.valid = false;
-    result.error = error.message;
-  }
-  if (options.json) {
-    console.log(JSON.stringify(result, null, 2));
-  } else {
-    console.log("\nPattern Check Result:");
-    console.log("\u2500".repeat(50));
-    console.log(`Pattern: ${pattern}`);
-    console.log(`Flags: ${options.flags || "(none)"}`);
-    console.log(`Valid: ${result.valid ? "\u2713 Yes" : "\u2717 No"}`);
-    if (result.valid) {
-      console.log("\nPattern Info:");
-      console.log(`  Length: ${result.info.length} characters`);
-      console.log(`  Has capture groups: ${result.info.hasGroups ? "Yes" : "No"}`);
-      console.log(`  Has quantifiers: ${result.info.hasQuantifiers ? "Yes" : "No"}`);
-      console.log(`  Has anchors (^/$): ${result.info.hasAnchors ? "Yes" : "No"}`);
-      console.log(`  Has lookahead: ${result.info.hasLookahead ? "Yes" : "No"}`);
-      console.log(`  Has lookbehind: ${result.info.hasLookbehind ? "Yes" : "No"}`);
-    }
-    if (result.warnings.length > 0) {
-      console.log("\nWarnings:");
-      result.warnings.forEach((w) => console.log(`  \u26A0 ${w}`));
-    }
-    if (result.error) {
-      console.log(`
-\u2717 Error: ${result.error}`);
-    }
-  }
-  process.exit(result.valid ? 0 : 1);
-}
-function benchmarkPatternCommand(pattern, text, options) {
-  const result = {
-    pattern,
-    text,
-    textLength: text.length,
-    metrics: {}
-  };
-  try {
-    validatePattern(pattern);
-    const flags = options.flags || "g";
-    const regex = new RegExp(pattern, flags);
-    const startTime = performance.now();
-    let matchCount = 0;
-    let match;
-    while ((match = regex.exec(text)) !== null) {
-      matchCount++;
-      if (matchCount >= 1e4) {
-        result.warning = "Stopped after 10000 matches";
-        break;
-      }
-      if (match.index === regex.lastIndex) {
-        regex.lastIndex++;
-      }
-    }
-    const endTime = performance.now();
-    const executionTime = endTime - startTime;
-    result.metrics = {
-      executionTime: `${executionTime.toFixed(3)}ms`,
-      matchCount,
-      matchesPerMs: matchCount > 0 ? (matchCount / executionTime).toFixed(2) : "0",
-      charsPerMs: (text.length / executionTime).toFixed(0)
-    };
-    result.success = true;
-  } catch (error) {
-    result.success = false;
-    result.error = error.message;
-  }
-  if (options.json) {
-    console.log(JSON.stringify(result, null, 2));
-  } else {
-    console.log("\nPattern Benchmark Result:");
-    console.log("\u2500".repeat(50));
-    console.log(`Pattern: ${pattern}`);
-    console.log(`Text length: ${result.textLength} characters`);
-    console.log("\nPerformance Metrics:");
-    console.log(`  Execution time: ${result.metrics.executionTime}`);
-    console.log(`  Matches found: ${result.metrics.matchCount}`);
-    console.log(`  Throughput: ${result.metrics.charsPerMs} chars/ms`);
-    if (result.warning) {
-      console.log(`
-\u26A0 ${result.warning}`);
-    }
-    if (result.error) {
-      console.log(`
-\u2717 Error: ${result.error}`);
-    }
-    const execTime = parseFloat(result.metrics.executionTime);
-    console.log("\nPerformance Assessment:");
-    if (execTime < 1) {
-      console.log("  \u2713 Excellent - Very fast execution");
-    } else if (execTime < 10) {
-      console.log("  \u2713 Good - Acceptable performance");
-    } else if (execTime < 50) {
-      console.log("  \u26A0 Fair - May be slow on large texts");
-    } else {
-      console.log("  \u2717 Poor - Pattern needs optimization");
-    }
-  }
-  process.exit(result.success ? 0 : 1);
-}
-async function main() {
-  if (args.length === 0 || args.includes("--help") || args.includes("-h")) {
-    printHelp();
-    process.exit(0);
-  }
-  const command = args[0];
-  const options = parseOptions(args);
-  try {
-    switch (command) {
-      case "validate": {
-        const pattern = args[1];
-        if (!pattern) {
-          console.error("Error: Pattern is required");
-          console.log("Usage: openredaction-test-pattern validate <pattern>");
-          process.exit(1);
-        }
-        validatePatternCommand(pattern, options);
-        break;
-      }
-      case "test": {
-        const pattern = args[1];
-        const text = args[2];
-        if (!pattern || !text) {
-          console.error("Error: Pattern and text are required");
-          console.log("Usage: openredaction-test-pattern test <pattern> <text>");
-          process.exit(1);
-        }
-        testPatternCommand(pattern, text, options);
-        break;
-      }
-      case "check": {
-        const pattern = args[1];
-        if (!pattern) {
-          console.error("Error: Pattern is required");
-          console.log("Usage: openredaction-test-pattern check <pattern> [--flags <flags>]");
-          process.exit(1);
-        }
-        checkPatternCommand(pattern, options);
-        break;
-      }
-      case "benchmark": {
-        const pattern = args[1];
-        const text = args[2];
-        if (!pattern || !text) {
-          console.error("Error: Pattern and text are required");
-          console.log("Usage: openredaction-test-pattern benchmark <pattern> <text>");
-          process.exit(1);
-        }
-        benchmarkPatternCommand(pattern, text, options);
-        break;
-      }
-      default:
-        console.error(`Unknown command: ${command}`);
-        console.log("Run with --help for usage information");
-        process.exit(1);
-    }
-  } catch (error) {
-    console.error("Error:", error.message);
-    process.exit(1);
-  }
-}
-main().catch((error) => {
-  console.error("Fatal error:", error);
-  process.exit(1);
-});

package/dist/document-AOMZP7UR.mjs

@@ -1,26 +0,0 @@
-import {
-  CsvProcessor,
-  DocumentProcessor,
-  JsonProcessor,
-  OCRProcessor,
-  XlsxProcessor,
-  createCsvProcessor,
-  createDocumentProcessor,
-  createJsonProcessor,
-  createOCRProcessor,
-  createXlsxProcessor
-} from "./chunk-7OGNW2MU.mjs";
-import "./chunk-WMJKH4XE.mjs";
-export {
-  CsvProcessor,
-  DocumentProcessor,
-  JsonProcessor,
-  OCRProcessor,
-  XlsxProcessor,
-  createCsvProcessor,
-  createDocumentProcessor,
-  createJsonProcessor,
-  createOCRProcessor,
-  createXlsxProcessor
-};
-//# sourceMappingURL=document-AOMZP7UR.mjs.map

package/dist/document-AOMZP7UR.mjs.map

@@ -1 +0,0 @@
-{"version":3,"sources":[],"sourcesContent":[],"mappings":"","names":[]}