feat(extract): extract systemd units so a repo's scheduled-job topology reaches the graph (#2848)

README.md

@@ -343,6 +343,7 @@ To remove graphify from all platforms at once: `graphify uninstall` (add `--purg
 | Terraform / HCL | `.tf .tfvars .hcl` (requires `uv tool install graphifyy[terraform]`) |
 | OCaml | `.ml .mli` (requires `uv tool install graphifyy[ocaml]`) |
 | Common Lisp | `.lisp .cl .lsp .asd` (requires `uv tool install graphifyy[commonlisp]`) |
+| systemd units | `.service .timer .socket .target .path .mount .slice` (INI, no grammar) — a timer/socket/path `activates` its unit, a service `runs` the script named by `ExecStart=`, `Documentation=file://` becomes `documented_by`, and `After=`/`Wants=`/`Requires=`/`WantedBy=`… become unit→unit edges (only to units in the same directory, so the host's `network.target` is never fabricated) |
 | MCP configs | `.mcp.json` `mcp.json` `mcp_servers.json` `claude_desktop_config.json` — extracts server nodes, package refs, env var requirements |
 | Package manifests | `apm.yml` `pyproject.toml` `go.mod` `pom.xml` — one canonical package node per package (by name) plus `depends_on` edges, so a package referenced from many manifests is a single hub |
 | Docs | `.md .mdx .qmd .html .txt .rst .yaml .yml` (markdown `[text](./other.md)` links and `[[wikilinks]]` become `references` edges between docs) |

graphify/detect.py

@@ -41,7 +41,7 @@ class FileType(str, Enum):
 _MTIME_COARSE_S = 2.0
 _MTIME_SUBSECOND_S = 0.05
 
-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', '.ml', '.mli', '.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', '.lisp', '.cl', '.lsp', '.asd'}
+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', '.ml', '.mli', '.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', '.lisp', '.cl', '.lsp', '.asd', '.service', '.timer', '.socket', '.target', '.path', '.mount', '.slice'}
 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

@@ -54,6 +54,7 @@
 from graphify.extractors.razor import extract_razor  # noqa: F401
 from graphify.extractors.rust import extract_rust  # noqa: F401
 from graphify.extractors.sln import extract_sln  # noqa: F401
+from graphify.extractors.systemd import SYSTEMD_UNIT_EXTENSIONS, extract_systemd  # noqa: F401
 from graphify.extractors.sql import extract_sql  # noqa: F401
 from graphify.extractors.terraform import extract_terraform  # noqa: F401
 from graphify.extractors.verilog import extract_verilog  # noqa: F401
@@ -5252,6 +5253,8 @@ def add_existing_edge(edge: dict) -> None:
     ".dmf": extract_dmf,
     ".sln": extract_sln,
     ".slnx": extract_slnx,
+    # systemd units (#2848): .service .timer .socket .target .path .mount .slice
+    **{ext: extract_systemd for ext in sorted(SYSTEMD_UNIT_EXTENSIONS)},
     ".csproj": extract_csproj,
     ".fsproj": extract_csproj,
     ".vbproj": extract_csproj,

graphify/extractors/resolution.py

@@ -640,6 +640,19 @@ def _blank(s: str) -> str:
     out.append(_blank(src[pos:]))
     return "".join(out), lang
 
+# Relations whose edges may carry a transient ``target_file`` stamp naming the
+# file the target id was minted from. Import-style edges (#1814/#1983), plus
+# the systemd unit edges (#2848): a `.timer` and its `.service` share the
+# extension-less file-node id, so without the stamp the timer's `activates`
+# edge would be disambiguated against the timer's own path — a self-loop.
+_TARGET_FILE_RELATIONS: frozenset[str] = frozenset({
+    "imports", "imports_from", "re_exports",
+    "activates", "runs", "documented_by",
+    "after", "before", "wants", "requires", "binds_to", "part_of", "conflicts",
+    "wanted_by", "required_by",
+})
+
+
 def _source_key(source_file: str, root: Path) -> str:
     if not source_file:
         return ""
@@ -766,7 +779,7 @@ def _disambiguate_colliding_node_ids(
         # every language and to re_exports. `pop` it as we consume it: this is the
         # hint's only reader, and its absolute path must not persist into graph.json.
         target_file = edge.pop("target_file", None)
-        if target_file and edge.get("relation") in ("imports", "imports_from", "re_exports"):
+        if target_file and edge.get("relation") in _TARGET_FILE_RELATIONS:
             target_edge_key = _source_key(str(target_file), root)
         else:
             target_edge_key = edge_source_key