Add PHP language support

Adds PHP as a supported language via a new LanguageSpec backed by
tree-sitter-php (already bundled in tree-sitter-language-pack).

Supports functions, classes, methods, interfaces, traits, enums,
constants, return types, and PHPDoc comments. PHP 8 #[Attribute]
decorator syntax is also handled.

Updates LANGUAGE_SUPPORT.md, README.md, and SPEC.md to document
the new language. Adds test fixture and test_parse_php() to the
language test suite.

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

Author: jgravelle

LANGUAGE_SUPPORT.md

@@ -10,6 +10,7 @@
 | Go         | `.go`         | tree-sitter-go         | function, method, type, constant                   | —             | `//` comments              | No class hierarchy (language limitation)                         |
 | Rust       | `.rs`         | tree-sitter-rust       | function, type (struct/enum/trait), impl, constant | `#[attr]`     | `///` and `//!` comments   | Macro-generated symbols are not visible to the parser            |
 | Java       | `.java`       | tree-sitter-java       | method, class, type (interface/enum), constant     | `@Annotation` | `/** */` Javadoc           | Deep inner-class nesting may be flattened                        |
+| PHP        | `.php`        | tree-sitter-php        | function, class, method, type (interface/trait/enum), constant | `#[Attribute]` | `/** */` PHPDoc | PHP 8+ attributes supported; language-file `<?php` tag required  |
 
 ---
 

README.md

@@ -190,6 +190,7 @@ All tool responses include a `_meta` envelope with timing and metadata.
 | Go         | `.go`         | function, method, type, constant        |
 | Rust       | `.rs`         | function, type, impl, constant          |
 | Java       | `.java`       | method, class, type, constant           |
+| PHP        | `.php`        | function, class, method, type, constant |
 
 See **LANGUAGE_SUPPORT.md** for full semantics.
 

SPEC.md

@@ -166,7 +166,7 @@ class Symbol:
     name: str                # Symbol name
     qualified_name: str      # Dot-separated with parent context
     kind: str                # function | class | method | constant | type
-    language: str            # python | javascript | typescript | go | rust | java
+    language: str            # python | javascript | typescript | go | rust | java | php
     signature: str           # Full signature line(s)
     content_hash: str = ""   # SHA-256 of source bytes (drift detection)
     docstring: str = ""
@@ -212,7 +212,7 @@ Recursive directory walk with the full security pipeline.
 
 ### Filtering Pipeline (Both Paths)
 
-1. **Extension filter** — must be in `LANGUAGE_EXTENSIONS` (.py, .js, .jsx, .ts, .tsx, .go, .rs, .java)
+1. **Extension filter** — must be in `LANGUAGE_EXTENSIONS` (.py, .js, .jsx, .ts, .tsx, .go, .rs, .java, .php)
 2. **Skip patterns** — `node_modules/`, `vendor/`, `.git/`, `build/`, `dist/`, lock files, minified files, etc.
 3. **`.gitignore`** — respected via the `pathspec` library
 4. **Secret detection** — `.env`, `*.pem`, `*.key`, `*.p12`, credentials files excluded

src/jcodemunch_mcp/parser/languages.py

@@ -53,6 +53,7 @@ class LanguageSpec:
     ".go": "go",
     ".rs": "rust",
     ".java": "java",
+    ".php": "php",
 }
 
 
@@ -241,6 +242,41 @@ class LanguageSpec:
 )
 
 
+# PHP specification
+PHP_SPEC = LanguageSpec(
+    ts_language="php",
+    symbol_node_types={
+        "function_definition": "function",
+        "class_declaration": "class",
+        "method_declaration": "method",
+        "interface_declaration": "type",
+        "trait_declaration": "type",
+        "enum_declaration": "type",
+    },
+    name_fields={
+        "function_definition": "name",
+        "class_declaration": "name",
+        "method_declaration": "name",
+        "interface_declaration": "name",
+        "trait_declaration": "name",
+        "enum_declaration": "name",
+    },
+    param_fields={
+        "function_definition": "parameters",
+        "method_declaration": "parameters",
+    },
+    return_type_fields={
+        "function_definition": "return_type",
+        "method_declaration": "return_type",
+    },
+    docstring_strategy="preceding_comment",
+    decorator_node_type="attribute",  # PHP 8 #[Attribute] syntax
+    container_node_types=["class_declaration", "trait_declaration", "interface_declaration"],
+    constant_patterns=["const_declaration"],
+    type_patterns=["interface_declaration", "trait_declaration", "enum_declaration"],
+)
+
+
 # Language registry
 LANGUAGE_REGISTRY = {
     "python": PYTHON_SPEC,
@@ -249,4 +285,5 @@ class LanguageSpec:
     "go": GO_SPEC,
     "rust": RUST_SPEC,
     "java": JAVA_SPEC,
+    "php": PHP_SPEC,
 }

tests/fixtures/php/sample.php

@@ -0,0 +1,53 @@
+<?php
+
+const MAX_RETRIES = 3;
+
+/**
+ * Authenticate a user token.
+ */
+function authenticate(string $token): bool
+{
+    return strlen($token) > 0;
+}
+
+/**
+ * Manages user operations.
+ */
+class UserService
+{
+    /**
+     * Get a user by ID.
+     */
+    public function getUser(int $userId): array
+    {
+        return ['id' => $userId];
+    }
+
+    /**
+     * Create a new user.
+     */
+    public static function create(string $name): self
+    {
+        return new self();
+    }
+}
+
+interface Authenticatable
+{
+    public function authenticate(string $token): bool;
+}
+
+trait Timestampable
+{
+    public function getCreatedAt(): string
+    {
+        return date('Y-m-d');
+    }
+}
+
+enum Status
+{
+    case Active;
+    case Inactive;
+    case Pending;
+}

tests/test_languages.py

@@ -171,13 +171,91 @@ def test_parse_rust():
 def test_parse_java():
     """Test Java parsing."""
     symbols = parse_file(JAVA_SOURCE, "Calculator.java", "java")
-    
+
     # Should have class, method, interface
     calc = next((s for s in symbols if s.name == "Calculator"), None)
     assert calc is not None
     assert calc.kind == "class"
-    
+
     add = next((s for s in symbols if s.name == "add"), None)
     assert add is not None
     assert add.kind == "method"
 
+
+PHP_SOURCE = '''<?php
+
+const MAX_RETRIES = 3;
+
+/**
+ * Authenticate a user token.
+ */
+function authenticate(string $token): bool
+{
+    return strlen($token) > 0;
+}
+
+/**
+ * Manages user operations.
+ */
+class UserService
+{
+    /**
+     * Get a user by ID.
+     */
+    public function getUser(int $userId): array
+    {
+        return ['id' => $userId];
+    }
+}
+
+interface Authenticatable
+{
+    public function authenticate(string $token): bool;
+}
+
+trait Timestampable
+{
+    public function getCreatedAt(): string
+    {
+        return date(\'Y-m-d\');
+    }
+}
+
+enum Status
+{
+    case Active;
+    case Inactive;
+}
+'''
+
+
+def test_parse_php():
+    """Test PHP parsing."""
+    symbols = parse_file(PHP_SOURCE, "service.php", "php")
+
+    func = next((s for s in symbols if s.name == "authenticate"), None)
+    assert func is not None
+    assert func.kind == "function"
+    assert "Authenticate a user token" in func.docstring
+
+    cls = next((s for s in symbols if s.name == "UserService"), None)
+    assert cls is not None
+    assert cls.kind == "class"
+
+    method = next((s for s in symbols if s.name == "getUser"), None)
+    assert method is not None
+    assert method.kind == "method"
+    assert "Get a user by ID" in method.docstring
+
+    interface = next((s for s in symbols if s.name == "Authenticatable"), None)
+    assert interface is not None
+    assert interface.kind == "type"
+
+    trait = next((s for s in symbols if s.name == "Timestampable"), None)
+    assert trait is not None
+    assert trait.kind == "type"
+
+    enum = next((s for s in symbols if s.name == "Status"), None)
+    assert enum is not None
+    assert enum.kind == "type"
+