ai-nevermore 0.0.7 → 0.0.9

package/README.md

@@ -7,11 +7,11 @@ Text
 ---
 while a user will see
 
-![original text](./images/original.png)
+![original text](https://raw.githubusercontent.com/khrome/nevermore/master/images/original.png)
 
 A scraper coming to your site will see something like
 
-![encoded text](./images/encoded.png)
+![encoded text](https://raw.githubusercontent.com/khrome/nevermore/master/images/encoded.png)
 
 Which will both prevent the scraper from acquiring your content as well as [poisoning the model trained](https://en.wikipedia.org/wiki/Adversarial_machine_learning#Data_poisoning) from it.
 
@@ -53,6 +53,14 @@ Then you include the encoded image along with it's key(This uses the source dire
 </html>
 ```
 
+Markup
+------
+Nevermore can traverse and inline transform all text and image elements in an HTML body.
+
+`nevermore pseudomarkup <target> --unified-output <output location>`
+
+this puts imports, styles and image decodes all inline.
+
 Programmatic Usage
 ------------------
 This library can be used to generate the html and css:
@@ -84,8 +92,9 @@ Install with `npm install -g ai-nevermore`
 nevermore [command]
 
 Commands:
-  nevermore pseudotext [input-file]   transform text to poison
-  nevermore pseudoimage [input-file]  transform XOR image encoding
+  nevermore pseudotext [input-file]    transform text to poison
+  nevermore pseudoimage [input-file]   transform XOR image encoding
+  nevermore pseudomarkup [input-file]  transform html content
 
 Options:
       --version            Show version number                         [boolean]

package/bin/nevermore

@@ -3,7 +3,9 @@ import yargs from 'yargs';
 import { hideBin } from 'yargs/helpers';
 import { computeIndexKeys, generateHTMLAndCSS } from '../src/index.mjs';
 import { NevermoreImage } from '../src/image.mjs';
+import { transformHTML } from '../src/html.mjs'
 import { Canvas } from '@environment-safe/canvas';
+import { parse } from 'parse5';
 import { readFile, writeFile } from 'node:fs/promises';
 import { join } from 'node:path';
 const { cwd } = process;
@@ -100,6 +102,7 @@ yargs(hideBin(process.argv))
             let canvas = null; 
             if(argv['encode']){
                 canvas = await image.encode();
+                console.log('KEY:', image.key);
             }
             if(argv['decode']){
                 canvas = await image.decode();
@@ -108,6 +111,32 @@ yargs(hideBin(process.argv))
         }else{
             throw new Error('piped output not yet supported');
         }
+    }).command('pseudomarkup [input-file]', 'transform html content', (yargs) => {
+        return yargs
+        .positional('input-file', {
+            describe: 'file input'
+        })
+    }, async (argv) => {
+        let result = null;
+        if(!argv['input-file']){
+            //TODO: pipe support
+            throw new Error('pipe not yet supported');
+        }else{
+            const target = await readFile(argv['input-file']);
+            const parsed = parse(target.toString());
+            let idx = null;
+            if(argv['custom-dictionary']){
+                const result = await readFile(argv['custom-dictionary']);
+                idx = result.toString();
+            }
+            result = await transformHTML(parsed, idx);
+        }
+        if(result && argv['unified-output']){
+            await writeFile(argv['unified-output'], result);
+        }else{
+            console.log(result);
+            //throw new Error('piped output not yet supported');
+        }
     }).option('key', {
         alias: 'K',
         type: 'string',