feat: add .NET project file support (.sln, .csproj, .fsproj, .vbproj, .razor, .cshtml)

README.md

@@ -209,7 +209,7 @@ To remove graphify from all platforms at once: `graphify uninstall` (add `--purg
 
 | Type | Extensions |
 |------|-----------|
-| Code (31 languages) | `.py .ts .js .jsx .tsx .mjs .go .rs .java .c .cpp .h .hpp .rb .cs .kt .scala .php .swift .lua .luau .zig .ps1 .ex .exs .m .mm .jl .vue .svelte .astro .groovy .gradle .dart .v .sv .sql .f .f90 .f95 .f03 .f08 .pas .pp .dpr .dpk .lpr .inc .dfm .lfm .lpk .sh .bash .json` |
+| Code (31 languages) | `.py .ts .js .jsx .tsx .mjs .go .rs .java .c .cpp .h .hpp .rb .cs .kt .scala .php .swift .lua .luau .zig .ps1 .ex .exs .m .mm .jl .vue .svelte .astro .groovy .gradle .dart .v .sv .sql .f .f90 .f95 .f03 .f08 .pas .pp .dpr .dpk .lpr .inc .dfm .lfm .lpk .sh .bash .json .sln .csproj .fsproj .vbproj .razor .cshtml` |
 | Docs | `.md .mdx .qmd .html .txt .rst .yaml .yml` |
 | Office | `.docx .xlsx` (requires `pip install graphifyy[office]`) |
 | Google Workspace | `.gdoc .gsheet .gslides` (opt-in; requires `gws` auth and `--google-workspace`; Sheets need `pip install graphifyy[google]`) |

graphify/detect.py

@@ -25,7 +25,7 @@ class FileType(str, Enum):
 
 _MANIFEST_PATH = "graphify-out/manifest.json"
 
-CODE_EXTENSIONS = {'.py', '.ts', '.tsx', '.js', '.jsx', '.mjs', '.ejs', '.ets', '.go', '.rs', '.java', '.groovy', '.gradle', '.cpp', '.cc', '.cxx', '.c', '.h', '.hpp', '.rb', '.swift', '.kt', '.kts', '.cs', '.scala', '.php', '.lua', '.luau', '.toc', '.zig', '.ps1', '.ex', '.exs', '.m', '.mm', '.jl', '.vue', '.svelte', '.astro', '.dart', '.v', '.sv', '.sql', '.r', '.f', '.F', '.f90', '.F90', '.f95', '.F95', '.f03', '.F03', '.f08', '.F08', '.pas', '.pp', '.dpr', '.dpk', '.lpr', '.inc', '.dfm', '.lfm', '.lpk', '.sh', '.bash', '.json'}
+CODE_EXTENSIONS = {'.py', '.ts', '.tsx', '.js', '.jsx', '.mjs', '.ejs', '.ets', '.go', '.rs', '.java', '.groovy', '.gradle', '.cpp', '.cc', '.cxx', '.c', '.h', '.hpp', '.rb', '.swift', '.kt', '.kts', '.cs', '.scala', '.php', '.lua', '.luau', '.toc', '.zig', '.ps1', '.ex', '.exs', '.m', '.mm', '.jl', '.vue', '.svelte', '.astro', '.dart', '.v', '.sv', '.sql', '.r', '.f', '.F', '.f90', '.F90', '.f95', '.F95', '.f03', '.F03', '.f08', '.F08', '.pas', '.pp', '.dpr', '.dpk', '.lpr', '.inc', '.dfm', '.lfm', '.lpk', '.sh', '.bash', '.json', '.sln', '.csproj', '.fsproj', '.vbproj', '.razor', '.cshtml'}
 DOC_EXTENSIONS = {'.md', '.mdx', '.qmd', '.txt', '.rst', '.html', '.yaml', '.yml'}
 PAPER_EXTENSIONS = {'.pdf'}
 IMAGE_EXTENSIONS = {'.png', '.jpg', '.jpeg', '.gif', '.webp', '.svg'}

graphify/extract.py

@@ -7695,6 +7695,297 @@ def _prescan_functions(node) -> None:
     return {"nodes": nodes, "edges": edges}
 
 
+# ── .NET project files (.sln, .csproj, .razor) ──────────────────────────────
+
+def extract_sln(path: Path) -> dict:
+    """Extract projects and inter-project dependencies from a .sln file."""
+    try:
+        src = path.read_text(encoding="utf-8", errors="replace")
+    except OSError:
+        return {"nodes": [], "edges": [], "error": f"cannot read {path}"}
+
+    file_nid = _make_id(str(path))
+    str_path = str(path)
+    nodes: list[dict] = [{"id": file_nid, "label": path.name, "file_type": "code",
+                          "source_file": str_path, "source_location": None}]
+    edges: list[dict] = []
+    seen_ids: set[str] = set()
+    seen_ids.add(file_nid)
+
+    _PROJECT_RE = re.compile(
+        r'Project\("[^"]*"\)\s*=\s*"([^"]+)"\s*,\s*"([^"]+)"\s*,\s*"([^"]*)"'
+    )
+    _DEP_RE = re.compile(r'\{([0-9a-fA-F-]+)\}\s*=\s*\{([0-9a-fA-F-]+)\}')
+
+    guid_to_nid: dict[str, str] = {}
+
+    for m in _PROJECT_RE.finditer(src):
+        proj_name = m.group(1)
+        proj_path = m.group(2).replace("\\", "/")
+        proj_guid = m.group(3).strip("{}")
+
+        proj_nid = _make_id(proj_path)
+        if proj_nid and proj_nid not in seen_ids:
+            seen_ids.add(proj_nid)
+            nodes.append({"id": proj_nid, "label": proj_name,
+                          "file_type": "code", "source_file": proj_path,
+                          "source_location": None})
+            edges.append({"source": file_nid, "target": proj_nid,
+                          "relation": "contains", "confidence": "EXTRACTED",
+                          "source_file": str_path, "weight": 1.0})
+        if proj_guid:
+            guid_to_nid[proj_guid.lower()] = proj_nid
+
+    in_dep_section = False
+    current_proj_guid: str | None = None
+    _PROJECT_LINE_RE = re.compile(r'Project\("[^"]*"\)\s*=\s*"[^"]+"\s*,\s*"[^"]+"\s*,\s*"\{([^}]+)\}"')
+    for line in src.splitlines():
+        proj_line_m = _PROJECT_LINE_RE.search(line)
+        if proj_line_m:
+            current_proj_guid = proj_line_m.group(1).lower()
+            continue
+        if line.strip() == "EndProject":
+            current_proj_guid = None
+            continue
+        if "ProjectSection(ProjectDependencies)" in line:
+            in_dep_section = True
+            continue
+        if in_dep_section and "EndProjectSection" in line:
+            in_dep_section = False
+            continue
+        if in_dep_section and current_proj_guid:
+            dep_m = _DEP_RE.search(line)
+            if dep_m:
+                to_guid = dep_m.group(1).lower()
+                from_nid = guid_to_nid.get(current_proj_guid)
+                to_nid = guid_to_nid.get(to_guid)
+                if from_nid and to_nid and from_nid != to_nid:
+                    edges.append({"source": from_nid, "target": to_nid,
+                                  "relation": "imports", "confidence": "EXTRACTED",
+                                  "source_file": str_path, "weight": 1.0})
+
+    return {"nodes": nodes, "edges": edges}
+
+
+def extract_csproj(path: Path) -> dict:
+    """Extract packages, project refs, and target framework from a .csproj/.fsproj/.vbproj."""
+    import xml.etree.ElementTree as ET
+
+    try:
+        src = path.read_bytes()
+    except OSError:
+        return {"nodes": [], "edges": [], "error": f"cannot read {path}"}
+
+    if len(src) > 2_097_152:
+        return {"nodes": [], "edges": [], "error": "project file too large"}
+
+    try:
+        tree = ET.fromstring(src)
+    except ET.ParseError as e:
+        return {"nodes": [], "edges": [], "error": f"XML parse error: {e}"}
+
+    file_nid = _make_id(str(path))
+    str_path = str(path)
+    nodes: list[dict] = [{"id": file_nid, "label": path.name, "file_type": "code",
+                          "source_file": str_path, "source_location": None}]
+    edges: list[dict] = []
+    seen_ids: set[str] = set()
+    seen_ids.add(file_nid)
+
+    ns = ""
+    root_tag = tree.tag
+    if root_tag.startswith("{"):
+        ns = root_tag.split("}")[0] + "}"
+
+    def find_all(tag: str):
+        return tree.iter(f"{ns}{tag}")
+
+    for tf in find_all("TargetFramework"):
+        if tf.text:
+            fw_nid = _make_id("framework", tf.text.strip())
+            if fw_nid and fw_nid not in seen_ids:
+                seen_ids.add(fw_nid)
+                nodes.append({"id": fw_nid, "label": tf.text.strip(),
+                              "file_type": "concept", "source_file": str_path,
+                              "source_location": None})
+                edges.append({"source": file_nid, "target": fw_nid,
+                              "relation": "references", "confidence": "EXTRACTED",
+                              "source_file": str_path, "weight": 1.0})
+
+    for tf in find_all("TargetFrameworks"):
+        if tf.text:
+            for fw in tf.text.strip().split(";"):
+                fw = fw.strip()
+                if fw:
+                    fw_nid = _make_id("framework", fw)
+                    if fw_nid and fw_nid not in seen_ids:
+                        seen_ids.add(fw_nid)
+                        nodes.append({"id": fw_nid, "label": fw,
+                                      "file_type": "concept", "source_file": str_path,
+                                      "source_location": None})
+                        edges.append({"source": file_nid, "target": fw_nid,
+                                      "relation": "references", "confidence": "EXTRACTED",
+                                      "source_file": str_path, "weight": 1.0})
+
+    for pkg in find_all("PackageReference"):
+        name = pkg.get("Include") or pkg.get("include") or ""
+        version = pkg.get("Version") or pkg.get("version") or ""
+        if not name:
+            continue
+        pkg_nid = _make_id("nuget", name)
+        label = f"{name} ({version})" if version else name
+        if pkg_nid and pkg_nid not in seen_ids:
+            seen_ids.add(pkg_nid)
+            nodes.append({"id": pkg_nid, "label": label,
+                          "file_type": "code", "source_file": str_path,
+                          "source_location": None})
+        edges.append({"source": file_nid, "target": pkg_nid,
+                      "relation": "imports", "confidence": "EXTRACTED",
+                      "source_file": str_path, "weight": 1.0})
+
+    for proj in find_all("ProjectReference"):
+        ref_path = proj.get("Include") or proj.get("include") or ""
+        if not ref_path:
+            continue
+        ref_path_norm = ref_path.replace("\\", "/")
+        proj_nid = _make_id(ref_path_norm)
+        if proj_nid and proj_nid not in seen_ids:
+            seen_ids.add(proj_nid)
+            proj_label = Path(ref_path_norm).name
+            nodes.append({"id": proj_nid, "label": proj_label,
+                          "file_type": "code", "source_file": ref_path_norm,
+                          "source_location": None})
+        edges.append({"source": file_nid, "target": proj_nid,
+                      "relation": "imports", "confidence": "EXTRACTED",
+                      "source_file": str_path, "weight": 1.0})
+
+    sdk = tree.get("Sdk") or ""
+    if sdk:
+        sdk_nid = _make_id("sdk", sdk)
+        if sdk_nid and sdk_nid not in seen_ids:
+            seen_ids.add(sdk_nid)
+            nodes.append({"id": sdk_nid, "label": sdk,
+                          "file_type": "concept", "source_file": str_path,
+                          "source_location": None})
+            edges.append({"source": file_nid, "target": sdk_nid,
+                          "relation": "references", "confidence": "EXTRACTED",
+                          "source_file": str_path, "weight": 1.0})
+
+    return {"nodes": nodes, "edges": edges}
+
+
+def extract_razor(path: Path) -> dict:
+    """Extract directives, component refs, and @code methods from .razor/.cshtml."""
+    try:
+        src = path.read_text(encoding="utf-8", errors="replace")
+    except OSError:
+        return {"nodes": [], "edges": [], "error": f"cannot read {path}"}
+
+    file_nid = _make_id(str(path))
+    str_path = str(path)
+    nodes: list[dict] = [{"id": file_nid, "label": path.name, "file_type": "code",
+                          "source_file": str_path, "source_location": None}]
+    edges: list[dict] = []
+    seen_ids: set[str] = set()
+    seen_ids.add(file_nid)
+
+    def _add_ref(target_name: str, relation: str, line: int) -> None:
+        tgt_nid = _make_id(target_name)
+        if not tgt_nid:
+            return
+        if tgt_nid not in seen_ids:
+            seen_ids.add(tgt_nid)
+            nodes.append({"id": tgt_nid, "label": target_name,
+                          "file_type": "code", "source_file": str_path,
+                          "source_location": f"L{line}"})
+        edges.append({"source": file_nid, "target": tgt_nid,
+                      "relation": relation, "confidence": "EXTRACTED",
+                      "source_file": str_path, "source_location": f"L{line}",
+                      "weight": 1.0})
+
+    for i, line in enumerate(src.splitlines(), 1):
+        m = re.match(r'@using\s+([\w.]+)', line)
+        if m:
+            _add_ref(m.group(1), "imports", i)
+            continue
+
+        m = re.match(r'@inject\s+([\w.<>\[\]]+)\s+(\w+)', line)
+        if m:
+            _add_ref(m.group(1), "imports", i)
+            continue
+
+        m = re.match(r'@inherits\s+([\w.<>\[\]]+)', line)
+        if m:
+            _add_ref(m.group(1), "inherits", i)
+            continue
+
+        m = re.match(r'@model\s+([\w.<>\[\]]+)', line)
+        if m:
+            _add_ref(m.group(1), "references", i)
+            continue
+
+        m = re.match(r'@page\s+"([^"]+)"', line)
+        if m:
+            route = m.group(1)
+            route_nid = _make_id("route", route)
+            if route_nid and route_nid not in seen_ids:
+                seen_ids.add(route_nid)
+                nodes.append({"id": route_nid, "label": f"route:{route}",
+                              "file_type": "concept", "source_file": str_path,
+                              "source_location": f"L{i}"})
+                edges.append({"source": file_nid, "target": route_nid,
+                              "relation": "references", "confidence": "EXTRACTED",
+                              "source_file": str_path, "weight": 1.0})
+            continue
+
+    _COMPONENT_RE = re.compile(r'<([A-Z][A-Za-z0-9]+)[\s/>]')
+    _HTML_TAGS = frozenset({
+        "DOCTYPE", "Html", "Head", "Body", "Div", "Span", "Table", "Form",
+        "Input", "Button", "Select", "Option", "Label", "Textarea",
+        "Script", "Style", "Link", "Meta", "Title", "Header", "Footer",
+        "Nav", "Main", "Section", "Article", "Aside",
+    })
+    for m in _COMPONENT_RE.finditer(src):
+        comp_name = m.group(1)
+        if comp_name in _HTML_TAGS:
+            continue
+        line_num = src[:m.start()].count("\n") + 1
+        _add_ref(comp_name, "calls", line_num)
+
+    _CODE_BLOCK_RE = re.compile(r'@code\s*\{', re.MULTILINE)
+    for m in _CODE_BLOCK_RE.finditer(src):
+        block_start = m.end()
+        depth = 1
+        pos = block_start
+        while pos < len(src) and depth > 0:
+            if src[pos] == '{':
+                depth += 1
+            elif src[pos] == '}':
+                depth -= 1
+            pos += 1
+        code_block = src[block_start:pos - 1] if depth == 0 else ""
+
+        _METHOD_RE = re.compile(
+            r'(?:public|private|protected|internal|static|async|override|virtual|abstract)\s+'
+            r'[\w<>\[\],\s]+\s+(\w+)\s*\('
+        )
+        for mm in _METHOD_RE.finditer(code_block):
+            method_name = mm.group(1)
+            abs_pos = block_start + mm.start()
+            method_line = src[:abs_pos].count("\n") + 1
+            method_nid = _make_id(_file_stem(path), method_name)
+            if method_nid and method_nid not in seen_ids:
+                seen_ids.add(method_nid)
+                nodes.append({"id": method_nid, "label": method_name,
+                              "file_type": "code", "source_file": str_path,
+                              "source_location": f"L{method_line}"})
+                edges.append({"source": file_nid, "target": method_nid,
+                              "relation": "contains", "confidence": "EXTRACTED",
+                              "source_file": str_path, "weight": 1.0})
+
+    return {"nodes": nodes, "edges": edges}
+
+
 def extract_json(path: Path) -> dict:
     """Extract top-level keys, nested structure, and dependency edges from a .json file."""
     _JSON_MAX_BYTES = 1_048_576  # 1 MiB — skip large fixture dumps / GeoJSON blobs
@@ -7907,6 +8198,12 @@ def walk_object(obj_node, parent_nid: str, parent_key: str | None,
     ".sh": extract_bash,
     ".bash": extract_bash,
     ".json": extract_json,
+    ".sln": extract_sln,
+    ".csproj": extract_csproj,
+    ".fsproj": extract_csproj,
+    ".vbproj": extract_csproj,
+    ".razor": extract_razor,
+    ".cshtml": extract_razor,
 }
 
 

tests/fixtures/sample.csproj

@@ -0,0 +1,21 @@
+<Project Sdk="Microsoft.NET.Sdk.Web">
+
+  <PropertyGroup>
+    <TargetFramework>net8.0</TargetFramework>
+    <Nullable>enable</Nullable>
+    <ImplicitUsings>enable</ImplicitUsings>
+  </PropertyGroup>
+
+  <ItemGroup>
+    <PackageReference Include="Microsoft.AspNetCore.Authentication.JwtBearer" Version="8.0.0" />
+    <PackageReference Include="Swashbuckle.AspNetCore" Version="6.5.0" />
+    <PackageReference Include="MediatR" Version="12.2.0" />
+    <PackageReference Include="FluentValidation" Version="11.9.0" />
+  </ItemGroup>
+
+  <ItemGroup>
+    <ProjectReference Include="..\Domain\Domain.csproj" />
+    <ProjectReference Include="..\Infrastructure\Infrastructure.csproj" />
+  </ItemGroup>
+
+</Project>

tests/fixtures/sample.razor

@@ -0,0 +1,36 @@
+@page "/counter"
+@using Microsoft.AspNetCore.Components
+@using MyApp.Services
+@inject ICounterService CounterService
+@inject NavigationManager Navigation
+@inherits ComponentBase
+
+<h1>Counter</h1>
+
+<p>Current count: @currentCount</p>
+
+<Button OnClick="IncrementCount">Click me</Button>
+<WeatherDisplay City="@city" />
+<DataGrid TItem="CounterRecord" Items="@records" />
+
+@code {
+    private int currentCount = 0;
+    private string city = "Seattle";
+    private List<CounterRecord> records = new();
+
+    private void IncrementCount()
+    {
+        currentCount++;
+        CounterService.Increment();
+    }
+
+    public async Task LoadData()
+    {
+        records = await CounterService.GetRecords();
+    }
+
+    protected override async Task OnInitializedAsync()
+    {
+        await LoadData();
+    }
+}