text-sanctifier 1.0.17 → 1.0.19

package/package.json

@@ -1,55 +1,65 @@
-{
-    "name": "text-sanctifier",
-    "version": "1.0.17",
-    "type": "module",
-    "description": "A brutal text normalizer and invisible trash scrubber for modern web projects.",
-    "main": "./src/index.js",
-    "module":  "./src/index.js",
-    "browser": "./dist/text-sanctifier.min.js",
-    "files": [
-        "src",
-        "dist/text-sanctifier.min.js",
-        "LICENSE.md",
-        "README.md"
-    ],
-    "exports": {
-        ".": "./src/index.js",              
-        "./browser": "./dist/text-sanctifier.min.js" 
-      },
-    "types": "./src/index.d.ts",
-    "sideEffects": false,
-    "scripts": {
-        "build": "node scripts/buildc.js",
-        "test": "node tests/sanctifyText.test.js",
-        "test-min": "node tests/sanctifyText.test.min.js"
-    },
-    "keywords": [
-        "text",
-        "sanitize",
-        "normalize",
-        "invisible",
-        "scrubber",
-        "unicode",
-        "clean",
-        "sanctify"
-    ],
-    "author": "👾Dr.Watt👾 <WATT3D@protonmail.com>",
-    "license":  "👾Dr.Watt👾 License v3.0",
-    "repository": {
-        "type": "git",
-        "url": "git+https://github.com/iWhatty/text-sanctifier.git"
-    },
-    "bugs": {
-        "url": "https://github.com/iWhatty/text-sanctifier/issues"
-    },
-    "homepage": "https://github.com/iWhatty/text-sanctifier#readme",
-    "directories": {
-        "test": "tests"
-    },
-    "devDependencies": {
-        "terser": "^5.39.0",
-        "esbuild": "^0.25.3",
-        "google-closure-compiler": "^20240317.0.0"
-
-    }
-}
+{
+  "name": "text-sanctifier",
+  "version": "1.0.19",
+  "type": "module",
+  "description": "A brutal text normalizer and invisible trash scrubber for modern web projects.",
+  "main": "./src/index.js",
+  "module": "./src/index.js",
+  "browser": "./dist/text-sanctifier.min.js",
+  "files": [
+    "src",
+    "dist/text-sanctifier.min.js",
+    "dist/types",
+    "LICENSE",
+    "README.md",
+    "ADDITIONAL_TERMS.md",
+    "robots.txt"
+  ],
+  "exports": {
+    ".": {
+      "types": "./dist/types/index.d.ts",
+      "default": "./src/index.js"
+    },
+    "./browser": {
+      "default": "./dist/text-sanctifier.min.js"
+    }
+  },
+  "types": "./dist/types/index.d.ts",
+  "sideEffects": false,
+  "scripts": {
+    "build": "node scripts/buildc.js",
+    "build:types": "tsc -p tsconfig.types.json",
+    "test": "node tests/sanctifyText.test.js",
+    "test-min": "node tests/sanctifyText.test.min.js",
+    "ci": "npm run test && npm run build && npm run build:types && npm run test-min"
+  },
+  "keywords": [
+    "text",
+    "sanitize",
+    "normalize",
+    "invisible",
+    "scrubber",
+    "unicode",
+    "clean",
+    "sanctify"
+  ],
+  "author": "WATT3D <WATT3D@protonmail.com>",
+  "license": "SEE LICENSE IN LICENSE",
+  "repository": {
+    "type": "git",
+    "url": "git+https://github.com/iWhatty/text-sanctifier.git"
+  },
+  "bugs": {
+    "url": "https://github.com/iWhatty/text-sanctifier/issues"
+  },
+  "homepage": "https://github.com/iWhatty/text-sanctifier#readme",
+  "directories": {
+    "test": "tests"
+  },
+  "devDependencies": {
+    "esbuild": "^0.25.3",
+    "google-closure-compiler": "^20240317.0.0",
+    "terser": "^5.39.0",
+    "typescript": "^5.9.3"
+  }
+}

package/robots.txt

@@ -0,0 +1,79 @@
+# WATT3D — AI scraping policy
+#
+# This file enumerates known AI / LLM training and inference crawlers
+# that the WATT3D AI Training Rider does not consent to. See
+# ./ADDITIONAL_TERMS.md for the legal scope and definitions.
+#
+# Honoring robots.txt is voluntary. The rider applies whether or not
+# a bot respects this file. The enumeration is non-exhaustive — bots
+# not listed here are still bound by the rider if they perform
+# Training Use as defined in ADDITIONAL_TERMS.md §1.
+
+User-agent: GPTBot
+Disallow: /
+
+User-agent: ChatGPT-User
+Disallow: /
+
+User-agent: OAI-SearchBot
+Disallow: /
+
+User-agent: anthropic-ai
+Disallow: /
+
+User-agent: ClaudeBot
+Disallow: /
+
+User-agent: Claude-Web
+Disallow: /
+
+User-agent: Claude-SearchBot
+Disallow: /
+
+User-agent: Google-Extended
+Disallow: /
+
+User-agent: Applebot-Extended
+Disallow: /
+
+User-agent: Meta-ExternalAgent
+Disallow: /
+
+User-agent: Meta-ExternalFetcher
+Disallow: /
+
+User-agent: FacebookBot
+Disallow: /
+
+User-agent: CCBot
+Disallow: /
+
+User-agent: PerplexityBot
+Disallow: /
+
+User-agent: Perplexity-User
+Disallow: /
+
+User-agent: cohere-ai
+Disallow: /
+
+User-agent: Bytespider
+Disallow: /
+
+User-agent: Amazonbot
+Disallow: /
+
+User-agent: Omgilibot
+Disallow: /
+
+User-agent: AI2Bot
+Disallow: /
+
+User-agent: Diffbot
+Disallow: /
+
+# Everyone else: full access. Search engines and human-driven crawlers
+# remain welcome.
+
+User-agent: *
+Allow: /

package/src/index.d.ts

@@ -1,116 +1,4 @@
-// src/index.d.ts
-
-export interface SanctifyOptions {
-  /** Remove ZWSP, NBSP, bidi, and other invisible Unicode trash */
-  purgeInvisibleChars?: boolean;
-
-  /** Remove emoji characters */
-  purgeEmojis?: boolean;
-
-  /** Nuke hidden control characters (excluding whitespace like \n and \t) */
-  nukeControls?: boolean;
-
-  /** Restrict to printable ASCII (+ emoji if `purgeEmojis` is false) */
-  keyboardOnlyFilter?: boolean;
-
-  /** Normalize all newline sequences to LF (`\n`) */
-  normalizeNewlines?: boolean;
-
-  /** Remove tabs and spaces before/after newline characters */
-  trimSpacesAroundNewlines?: boolean;
-
-  /** Collapse multiple consecutive newlines */
-  collapseNewLines?: boolean;
-
-  /** When collapsing newlines, preserve paragraph breaks as double `\n\n` */
-  preserveParagraphs?: boolean;
-
-  /** Collapse multiple spaces into a single space */
-  collapseSpaces?: boolean;
-
-  /** Trim leading and trailing whitespace from final result */
-  finalTrim?: boolean;
-}
-
-/** Preconfigured sanitizer function */
-export type Sanctifier = (text: string) => string;
-
-/**
- * Summon a reusable text sanitizer.
- */
-export function summonSanctifier(
-  defaultOptions?: SanctifyOptions,
-): Sanctifier;
-
-/**
- * Strict sanitizer preset:
- * - Collapse spaces
- * - Collapse all newlines
- * - Nuke control characters
- * - Purge emojis
- */
-export namespace summonSanctifier {
-  const strict: Sanctifier;
-  const loose: Sanctifier;
-
-  /**
-   * Keeps printable ASCII and emoji.
-   * Leaves spacing soft and preserves emoji.
-   */
-  const keyboardOnlyEmoji: Sanctifier;
-
-  /**
-   * Keeps printable ASCII only.
-   * Collapses whitespace and purges emoji.
-   */
-  const keyboardOnly: Sanctifier;
-}
-
-/**
- * Brutally normalizes and cleans a string of text.
- */
-export function sanctifyText(
-  text: string,
-  purgeInvisibleChars?: boolean,
-  purgeEmojis?: boolean,
-  nukeControls?: boolean,
-  keyboardOnlyFilter?: boolean,
-  normalizeNewlines?: boolean,
-  trimSpacesAroundNewlines?: boolean,
-  collapseNewLines?: boolean,
-  preserveParagraphs?: boolean,
-  collapseSpaces?: boolean,
-  finalTrim?: boolean,
-): string;
-
-/** Style of newline characters detected in a string */
-export type NewlineStyle = 'LF' | 'CRLF' | 'CR' | 'Mixed' | null;
-
-/**
- * A structural report of anomalies found in text.
- */
-export interface UnicodeTrashReport {
-  hasControlChars: boolean;
-  hasInvisibleChars: boolean;
-  hasMixedNewlines: boolean;
-  newlineStyle: NewlineStyle;
-  hasEmojis: boolean;
-  hasNonKeyboardChars: boolean;
-  summary: string[];
-}
-
-/**
- * Analyze a string and return a report of Unicode/control character issues,
- * invisible characters, newline styles, emojis, and more.
- */
-export function inspectText(text: string): UnicodeTrashReport;
-
-
-/**
- * Creates a recommended set of `summonSanctifier` options based on the findings
- * of `inspectText()`. This maps only what can be inferred automatically —
- * user-preference settings like whitespace collapsing are left unset.
- */
-export function getRecommendedSanctifierOptions(
-  report: UnicodeTrashReport
-): SanctifyOptions;
+import { inspectText } from './inspectText.js';
+import { getRecommendedSanctifierOptions } from './inspectText.js';
+import { summonSanctifier } from './sanctifyText.js';
+export { inspectText, getRecommendedSanctifierOptions, summonSanctifier };

package/src/index.js

@@ -1,12 +1,12 @@
-// src/index.js
-
-
-import { inspectText, getRecommendedSanctifierOptions } from './inspectText.js';
-export { inspectText, getRecommendedSanctifierOptions };
-
-import { summonSanctifier } from './sanctifyText.js';
-export { summonSanctifier };
-
-
-// In Future: export helpers for power users
-// export { purgeInvisibleTrash, purgeEmojisCharacters, normalizeNewlines, trimSpacesAroundNewlines, collapseParagraphs, collapseExtraSpaces, purgeControlCharacters } from './sanctifyText.js';
+// src/index.js
+
+
+import { inspectText, getRecommendedSanctifierOptions } from './inspectText.js';
+export { inspectText, getRecommendedSanctifierOptions };
+
+import { summonSanctifier } from './sanctifyText.js';
+export { summonSanctifier };
+
+
+// In Future: export helpers for power users
+// export { purgeInvisibleTrash, purgeEmojisCharacters, normalizeNewlines, trimSpacesAroundNewlines, collapseParagraphs, collapseExtraSpaces, purgeControlCharacters } from './sanctifyText.js';