Content Sanitization & PHP Documentation Transformer

.github/workflows/generate-docs.yml

@@ -0,0 +1,50 @@
+name: 📚 Generate Documentation
+
+on:
+  push:
+    branches: [ main ]
+    paths:
+      - 'context.json'
+  workflow_dispatch:  # Allow manual trigger
+  release:
+    types: [ published ]
+
+jobs:
+  generate-docs:
+    runs-on: ubuntu-latest
+    permissions:
+      contents: write  # Needed to push updates back to the repository
+    steps:
+      - name: Checkout repository
+        uses: actions/checkout@v4
+        with:
+          fetch-depth: 0
+
+      - name: Setup PHP
+        uses: shivammathur/setup-php@v2
+        with:
+          php-version: '8.2'
+          coverage: none
+
+      - name: Download context-generator
+        run: |
+          wget https://github.com/butschster/context-generator/releases/download/1.5.0/context-generator.phar
+          chmod +x context-generator.phar
+          ./context-generator.phar version
+
+      - name: Generate documentation
+        run: |
+          ./context-generator.phar
+
+      - name: List generated documents
+        run: |
+          find .context -type f | sort
+          echo "Generated documentation files in .context directory"
+
+      - name: 📤 Upload documentation as release assets
+        uses: softprops/[email protected]
+        if: github.event_name == 'release'
+        with:
+          token: "${{ secrets.GITHUB_TOKEN }}"
+          files: |
+            .context/**/*

json-schema.json

@@ -538,6 +538,214 @@
         }
       }
     },
+    "php-docs": {
+      "type": "object",
+      "properties": {
+        "include_private_methods": {
+          "type": "boolean",
+          "description": "Whether to include private methods in documentation",
+          "default": false
+        },
+        "include_protected_methods": {
+          "type": "boolean",
+          "description": "Whether to include protected methods in documentation",
+          "default": true
+        },
+        "include_private_properties": {
+          "type": "boolean",
+          "description": "Whether to include private properties in documentation",
+          "default": false
+        },
+        "include_protected_properties": {
+          "type": "boolean",
+          "description": "Whether to include protected properties in documentation",
+          "default": true
+        },
+        "include_implementations": {
+          "type": "boolean",
+          "description": "Whether to include method implementations in code blocks",
+          "default": true
+        },
+        "include_property_defaults": {
+          "type": "boolean",
+          "description": "Whether to include property default values",
+          "default": true
+        },
+        "include_constants": {
+          "type": "boolean",
+          "description": "Whether to include class constants",
+          "default": true
+        },
+        "code_block_format": {
+          "type": "string",
+          "description": "Language identifier for code blocks (e.g., 'php')",
+          "default": "php"
+        },
+        "class_heading_level": {
+          "type": "integer",
+          "description": "Heading level for class names (1-6)",
+          "minimum": 1,
+          "maximum": 6,
+          "default": 1
+        },
+        "extract_routes": {
+          "type": "boolean",
+          "description": "Whether to extract route information from annotations/attributes",
+          "default": true
+        },
+        "keep_doc_comments": {
+          "type": "boolean",
+          "description": "Whether to keep doc comments in the output",
+          "default": true
+        }
+      }
+    },
+    "sanitizer": {
+      "type": "object",
+      "properties": {
+        "rules": {
+          "type": "array",
+          "description": "Array of sanitization rules to apply",
+          "items": {
+            "type": "object",
+            "oneOf": [
+              {
+                "type": "object",
+                "properties": {
+                  "type": {
+                    "type": "string",
+                    "enum": [
+                      "keyword"
+                    ],
+                    "description": "Keyword removal rule"
+                  },
+                  "name": {
+                    "type": "string",
+                    "description": "Optional unique rule name"
+                  },
+                  "keywords": {
+                    "type": "array",
+                    "items": {
+                      "type": "string"
+                    },
+                    "description": "Array of keywords to search for and remove"
+                  },
+                  "replacement": {
+                    "type": "string",
+                    "description": "Text to replace the found keywords with"
+                  },
+                  "caseSensitive": {
+                    "type": "boolean",
+                    "description": "Whether matching should be case-sensitive"
+                  },
+                  "removeLines": {
+                    "type": "boolean",
+                    "description": "Whether to remove entire lines containing the keyword"
+                  }
+                },
+                "required": [
+                  "type",
+                  "keywords"
+                ]
+              },
+              {
+                "type": "object",
+                "properties": {
+                  "type": {
+                    "type": "string",
+                    "enum": [
+                      "regex"
+                    ],
+                    "description": "Regular expression replacement rule"
+                  },
+                  "name": {
+                    "type": "string",
+                    "description": "Optional unique rule name"
+                  },
+                  "patterns": {
+                    "type": "object",
+                    "additionalProperties": {
+                      "type": "string"
+                    },
+                    "description": "Object mapping regex patterns to their replacements"
+                  },
+                  "usePatterns": {
+                    "type": "array",
+                    "items": {
+                      "type": "string",
+                      "enum": [
+                        "credit-card",
+                        "email",
+                        "api-key",
+                        "ip-address",
+                        "jwt",
+                        "phone-number",
+                        "password-field",
+                        "url",
+                        "social-security",
+                        "aws-key",
+                        "private-key",
+                        "database-conn"
+                      ]
+                    },
+                    "description": "Predefined pattern aliases to use"
+                  }
+                },
+                "required": [
+                  "type"
+                ]
+              },
+              {
+                "type": "object",
+                "properties": {
+                  "type": {
+                    "type": "string",
+                    "enum": [
+                      "comment"
+                    ],
+                    "description": "Comment insertion rule"
+                  },
+                  "name": {
+                    "type": "string",
+                    "description": "Optional unique rule name"
+                  },
+                  "fileHeaderComment": {
+                    "type": "string",
+                    "description": "Comment to insert at the top of file"
+                  },
+                  "classComment": {
+                    "type": "string",
+                    "description": "Comment to insert before class definitions"
+                  },
+                  "methodComment": {
+                    "type": "string",
+                    "description": "Comment to insert before method definitions"
+                  },
+                  "frequency": {
+                    "type": "integer",
+                    "minimum": 0,
+                    "description": "How often to insert random comments (0 = disabled, 1 = every line, 5 = every 5th line)"
+                  },
+                  "randomComments": {
+                    "type": "array",
+                    "items": {
+                      "type": "string"
+                    },
+                    "description": "Array of random comments to insert"
+                  }
+                },
+                "required": [
+                  "type"
+                ]
+              }
+            ],
+            "required": [
+              "type"
+            ]
+          }
+        }
+      }
+    },
     "modifiers": {
       "type": "array",
       "description": "List of content modifiers to apply",
@@ -551,7 +759,8 @@
               "type": "string",
               "description": "Modifier identifier",
               "enum": [
-                "php-content-filter"
+                "php-signature",
+                "php-docs"
               ]
             }
           },
@@ -569,7 +778,9 @@
                   "type": "string",
                   "description": "Modifier identifier",
                   "enum": [
-                    "php-content-filter"
+                    "php-content-filter",
+                    "php-docs",
+                    "sanitizer"
                   ]
                 },
                 "options": {
@@ -586,6 +797,30 @@
                       "then": {
                         "$ref": "#/definitions/php-content-filter"
                       }
+                    },
+                    {
+                      "if": {
+                        "properties": {
+                          "name": {
+                            "const": "php-docs"
+                          }
+                        }
+                      },
+                      "then": {
+                        "$ref": "#/definitions/php-docs"
+                      }
+                    },
+                    {
+                      "if": {
+                        "properties": {
+                          "name": {
+                            "const": "sanitizer"
+                          }
+                        }
+                      },
+                      "then": {
+                        "$ref": "#/definitions/sanitizer"
+                      }
                     }
                   ]
                 }

src/Cli/ContextGenerator.php

@@ -17,6 +17,8 @@
 use Butschster\ContextGenerator\Loader\CompositeDocumentsLoader;
 use Butschster\ContextGenerator\Loader\ConfigDocumentsLoader;
 use Butschster\ContextGenerator\Loader\JsonConfigDocumentsLoader;
+use Butschster\ContextGenerator\Modifier\AstDocTransformer;
+use Butschster\ContextGenerator\Modifier\ContextSanitizerModifier;
 use Butschster\ContextGenerator\Modifier\PhpContentFilter;
 use Butschster\ContextGenerator\Modifier\PhpSignature;
 use Butschster\ContextGenerator\Modifier\SourceModifierRegistry;
@@ -48,8 +50,12 @@ protected function execute(InputInterface $input, OutputInterface $output): int
     {
         $files = new Files();
         $modifiers = new SourceModifierRegistry();
-        $modifiers->register(new PhpSignature());
-        $modifiers->register(new PhpContentFilter());
+        $modifiers->register(
+            new PhpSignature(),
+            new ContextSanitizerModifier(),
+            new PhpContentFilter(),
+            new AstDocTransformer(),
+        );
 
         // Create GitHub-related components
         $githubToken = \getenv('GITHUB_TOKEN') ?: null;

src/Fetcher/FileSourceFetcher.php

@@ -58,10 +58,8 @@
             $fileName = $file->getFilename();
             $filePath = empty($relativePath) ? $fileName : "$relativePath/$fileName";
 
-            $content .= "```\n";
             $content .= "// Path: {$filePath}\n";
             $content .= $this->getContent($file, $source) . "\n\n";
-            $content .= "```\n";
         }
 
         return $content;
@@ -79,7 +77,7 @@
         $content = $file->getContents();
 
         // Apply modifiers if available and the source is a FileSource
         foreach ($source->modifiers as $modifierId) {
             if ($this->modifiers->has($modifierId)) {
                 $modifier = $this->modifiers->get($modifierId);
                 if ($modifier->supports($file->getFilename())) {