feat: add Clojure structural extraction

ARCHITECTURE.md

@@ -57,11 +57,18 @@ Every extractor returns:
 
 ## Adding a new language extractor
 
-1. Add a `extract_<lang>(path: Path) -> dict` function in `extract.py` following the existing pattern (tree-sitter parse → walk nodes → collect `nodes` and `edges` → call-graph second pass for INFERRED `calls` edges).
-2. Register the file suffix in `extract()` dispatch and `collect_files()`.
-3. Add the suffix to `CODE_EXTENSIONS` in `detect.py` and `_WATCHED_EXTENSIONS` in `watch.py`.
-4. Add the tree-sitter package to `pyproject.toml` dependencies.
-5. Add a fixture file to `tests/fixtures/` and tests to `tests/test_languages.py`.
+1. Add `extract_<lang>(path: Path) -> dict` in
+   `graphify/extractors/<lang>.py`, following the existing pattern (tree-sitter
+   parse → walk nodes → collect `nodes` and `edges` → call-graph second pass).
+2. Re-export it from `graphify.extract`, register it in
+   `graphify.extractors.LANGUAGE_EXTRACTORS`, and register each suffix in the
+   `graphify.extract` dispatch table.
+3. Add each suffix to `CODE_EXTENSIONS` in `detect.py`; watch support derives
+   from that set.
+4. Add the tree-sitter package to `pyproject.toml` dependencies or an optional
+   language extra when the package does not provide portable wheels.
+5. Add a fixture file to `tests/fixtures/` and tests to
+   `tests/test_languages.py`.
 
 ## Security
 

README.md

@@ -258,6 +258,7 @@ Codex users also need `multi_agent = true` under `[features]` in `~/.codex/confi
 | `bedrock` | AWS Bedrock (uses IAM, no API key) | `uv tool install "graphifyy[bedrock]"` |
 | `azure` | Azure OpenAI Service (`--backend azure`, uses `AZURE_OPENAI_API_KEY` + `AZURE_OPENAI_ENDPOINT`) | `uv tool install "graphifyy[openai]"` |
 | `sql` | SQL schema extraction | `uv tool install "graphifyy[sql]"` |
+| `clojure` | Clojure/ClojureScript `.clj`/`.cljs`/`.cljc` and Babashka `.bb` AST extraction (requires a C compiler) | `uv tool install "graphifyy[clojure]"` |
 | `postgres` | Live PostgreSQL introspection (`--postgres DSN`) | `uv tool install "graphifyy[postgres]"` |
 | `dm` | BYOND DreamMaker `.dm`/`.dme` AST extraction (may need a C compiler + `python3-dev` if no wheel matches your platform) | `uv tool install "graphifyy[dm]"` |
 | `terraform` | Terraform / HCL `.tf`/`.tfvars`/`.hcl` AST extraction | `uv tool install "graphifyy[terraform]"` |
@@ -331,7 +332,7 @@ To remove graphify from all platforms at once: `graphify uninstall` (add `--purg
 
 | Type | Extensions |
 |------|-----------|
-| Code (36 tree-sitter grammars) | `.py .ts .mts .cts .js .jsx .tsx .mjs .go .rs .java .c .cpp .cc .cxx .h .hpp .cu .cuh .metal .rb .cs .kt .kts .scala .php .swift .lua .luau .toc .zig .ps1 .psm1 .psd1 .ex .exs .m .mm .jl .vue .svelte .astro .groovy .gradle .dart .v .sv .svh .sql .f .f90 .f95 .f03 .f08 .pas .pp .dpr .dpk .lpr .inc .dfm .lfm .lpk .sh .bash .json .dm .dme .dmi .dmm .dmf .sln .slnx .csproj .fsproj .vbproj .xaml .razor .cshtml` (`.dm`/`.dme` requires `uv tool install graphifyy[dm]`; `.mts`/`.cts` reuse the TypeScript grammar, `.cc`/`.cxx` and CUDA `.cu`/`.cuh` and Metal `.metal` reuse the C++ grammar) |
+| Code (37 tree-sitter grammars) | `.py .ts .mts .cts .js .jsx .tsx .mjs .go .rs .java .c .cpp .cc .cxx .h .hpp .cu .cuh .metal .rb .cs .kt .kts .scala .php .clj .cljs .cljc .bb .swift .lua .luau .toc .zig .ps1 .psm1 .psd1 .ex .exs .m .mm .jl .vue .svelte .astro .groovy .gradle .dart .v .sv .svh .sql .f .f90 .f95 .f03 .f08 .pas .pp .dpr .dpk .lpr .inc .dfm .lfm .lpk .sh .bash .json .dm .dme .dmi .dmm .dmf .sln .slnx .csproj .fsproj .vbproj .xaml .razor .cshtml` (`.clj`/`.cljs`/`.cljc`/`.bb` requires `uv tool install graphifyy[clojure]`; `.dm`/`.dme` requires `uv tool install graphifyy[dm]`; `.mts`/`.cts` reuse the TypeScript grammar, `.cc`/`.cxx` and CUDA `.cu`/`.cuh` and Metal `.metal` reuse the C++ grammar) |
 | Salesforce Apex | `.cls .trigger` (regex-based; classes, interfaces, enums, methods, triggers, SOQL/DML edges) |
 | Terraform / HCL | `.tf .tfvars .hcl` (requires `uv tool install graphifyy[terraform]`) |
 | MCP configs | `.mcp.json` `mcp.json` `mcp_servers.json` `claude_desktop_config.json` — extracts server nodes, package refs, env var requirements |

graphify/analyze.py

@@ -32,6 +32,7 @@
     **{e: "swift" for e in (".swift",)},
     **{e: "dotnet" for e in (".cs",)},
     **{e: "php" for e in (".php",)},
+    **{e: "clojure" for e in (".clj", ".cljs", ".cljc", ".bb")},
     **{e: "r" for e in (".r",)},
 }
 

graphify/build.py

@@ -51,6 +51,7 @@
     ".cxx": "c", ".hh": "c", ".hxx": "c",
     ".cu": "c", ".cuh": "c", ".metal": "c", ".m": "c", ".mm": "c",
     ".rb": "rb", ".rake": "rb", ".php": "php", ".cs": "cs", ".swift": "swift", ".lua": "lua",
+    ".clj": "clojure", ".cljs": "clojure", ".cljc": "clojure", ".bb": "clojure",
 }
 
 

graphify/cli.py

@@ -71,7 +71,8 @@
 _HOOK_SOURCE_EXTS = (
     '.py', '.js', '.cjs', '.ts', '.tsx', '.jsx', '.astro', '.vue', '.svelte', '.go',
     '.rs', '.java', '.rb', '.c', '.h', '.cpp', '.hpp', '.cc', '.cs', '.kt',
-    '.swift', '.php', '.scala', '.lua', '.sh', '.md', '.rst', '.txt', '.mdx',
+    '.swift', '.php', '.scala', '.clj', '.cljs', '.cljc', '.bb', '.lua', '.sh',
+    '.md', '.rst', '.txt', '.mdx',
 )
 _GEMINI_NUDGE_TEXT = (
     'graphify: knowledge graph at graphify-out/. For focused questions, run '

graphify/detect.py

@@ -28,7 +28,7 @@ class FileType(str, Enum):
 
 _MANIFEST_PATH = str(out_path("manifest.json"))
 
-CODE_EXTENSIONS = {'.py', '.ts', '.tsx', '.mts', '.cts', '.js', '.jsx', '.mjs', '.cjs', '.ejs', '.ets', '.go', '.rs', '.java', '.groovy', '.gradle', '.cpp', '.cc', '.cxx', '.c', '.h', '.hpp', '.cu', '.cuh', '.metal', '.rb', '.rake', '.swift', '.kt', '.kts', '.cs', '.scala', '.php', '.lua', '.luau', '.toc', '.zig', '.ps1', '.psm1', '.psd1', '.ex', '.exs', '.m', '.mm', '.jl', '.vue', '.svelte', '.astro', '.dart', '.v', '.sv', '.svh', '.sql', '.r', '.f', '.F', '.f90', '.F90', '.f95', '.F95', '.f03', '.F03', '.f08', '.F08', '.pas', '.pp', '.dpr', '.dpk', '.lpr', '.inc', '.dfm', '.lfm', '.lpk', '.sh', '.bash', '.json', '.tf', '.tfvars', '.hcl', '.dm', '.dme', '.dmi', '.dmm', '.dmf', '.sln', '.slnx', '.csproj', '.fsproj', '.vbproj', '.xaml', '.razor', '.cshtml', '.cls', '.trigger'}
+CODE_EXTENSIONS = {'.py', '.ts', '.tsx', '.mts', '.cts', '.js', '.jsx', '.mjs', '.cjs', '.ejs', '.ets', '.go', '.rs', '.java', '.groovy', '.gradle', '.cpp', '.cc', '.cxx', '.c', '.h', '.hpp', '.cu', '.cuh', '.metal', '.rb', '.rake', '.swift', '.kt', '.kts', '.cs', '.scala', '.php', '.clj', '.cljs', '.cljc', '.bb', '.lua', '.luau', '.toc', '.zig', '.ps1', '.psm1', '.psd1', '.ex', '.exs', '.m', '.mm', '.jl', '.vue', '.svelte', '.astro', '.dart', '.v', '.sv', '.svh', '.sql', '.r', '.f', '.F', '.f90', '.F90', '.f95', '.F95', '.f03', '.F03', '.f08', '.F08', '.pas', '.pp', '.dpr', '.dpk', '.lpr', '.inc', '.dfm', '.lfm', '.lpk', '.sh', '.bash', '.json', '.tf', '.tfvars', '.hcl', '.dm', '.dme', '.dmi', '.dmm', '.dmf', '.sln', '.slnx', '.csproj', '.fsproj', '.vbproj', '.xaml', '.razor', '.cshtml', '.cls', '.trigger'}
 DOC_EXTENSIONS = {'.md', '.mdx', '.qmd', '.skill', '.txt', '.rst', '.html', '.yaml', '.yml'}
 PAPER_EXTENSIONS = {'.pdf'}
 IMAGE_EXTENSIONS = {'.png', '.jpg', '.jpeg', '.gif', '.webp', '.svg'}

graphify/extract.py

@@ -33,6 +33,7 @@
 from graphify.extractors.apex import extract_apex  # noqa: F401
 from graphify.extractors.bash import extract_bash  # noqa: F401
 from graphify.extractors.blade import extract_blade  # noqa: F401
+from graphify.extractors.clojure import extract_clojure  # noqa: F401
 from graphify.extractors.csharp import (
     _resolve_cross_file_csharp_imports,
     _resolve_csharp_type_references,
@@ -1887,6 +1888,7 @@ def _lang_is_case_insensitive(source_file: object) -> bool:
     ".zig": "zig",
     ".ex": "elixir", ".exs": "elixir",
     ".jl": "julia",
+    ".clj": "clojure", ".cljs": "clojure", ".cljc": "clojure", ".bb": "clojure",
     ".dart": "dart",
     ".sh": "shell", ".bash": "shell",
     ".ps1": "powershell", ".psm1": "powershell", ".psd1": "powershell",
@@ -3995,6 +3997,10 @@ def add_existing_edge(edge: dict) -> None:
     ".kts": extract_kotlin,
     ".scala": extract_scala,
     ".php": extract_php,
+    ".clj": extract_clojure,
+    ".cljs": extract_clojure,
+    ".cljc": extract_clojure,
+    ".bb": extract_clojure,
     ".swift": extract_swift,
     ".lua": extract_lua,
     ".luau": extract_lua,
@@ -4068,6 +4074,10 @@ def add_existing_edge(edge: dict) -> None:
 # rather than falling back like Pascal does. Used by the #1745 warning in
 # extract() to tell the user which extra restores the language.
 _EXTRA_FOR_EXTENSION = {
+    ".clj": "clojure",
+    ".cljs": "clojure",
+    ".cljc": "clojure",
+    ".bb": "clojure",
     ".sql": "sql",
     ".tf": "terraform",
     ".tfvars": "terraform",

graphify/extractors/__init__.py

@@ -13,6 +13,7 @@
 from graphify.extractors.apex import extract_apex
 from graphify.extractors.bash import extract_bash
 from graphify.extractors.blade import extract_blade
+from graphify.extractors.clojure import extract_clojure
 from graphify.extractors.dart import extract_dart
 from graphify.extractors.dm import extract_dm, extract_dmf, extract_dmi, extract_dmm
 from graphify.extractors.elixir import extract_elixir
@@ -37,6 +38,7 @@
     "apex": extract_apex,
     "bash": extract_bash,
     "blade": extract_blade,
+    "clojure": extract_clojure,
     "dart": extract_dart,
     "delphi_form": extract_delphi_form,
     "dm": extract_dm,