feat(projectgraph): link Python dependency code, read its type hints, and add the distribution graph

README.md

@@ -16,3 +16,6 @@ summary steps.
 
 See [docs/modgraph.md](./docs/modgraph.md) for the module graph of a Go module: which module
 imports which, from the code on the disk, with no Go toolchain.
+
+See [docs/distgraph.md](./docs/distgraph.md) for the distribution graph of a Python project: which
+installed distribution imports which, from the code on the disk, with no Python.

distgraph/files.go

@@ -0,0 +1,87 @@
+package distgraph
+
+import (
+	"errors"
+	"io/fs"
+	"path"
+	"slices"
+	"strings"
+
+	"github.com/safedep/code/projectgraph/modules"
+)
+
+// compiledExts are the extensions of a Python extension module.
+var compiledExts = map[string]bool{".so": true, ".pyd": true, ".dylib": true}
+
+// pythonFiles returns the Python files of a node, in path order, and its
+// extension modules. The project gives each .py file under its root, except
+// under a hidden directory, a __pycache__, a node_modules, a site-packages
+// or a virtual environment, which holds a pyvenv.cfg. A distribution gives
+// the files under each of its top-level names, except its test files,
+// which no program imports.
+func (b *builder) pythonFiles(d *dist) ([]string, []string, error) {
+	var files, compiled []string
+	visit := func(p string, entry fs.DirEntry, err error) error {
+		if err != nil {
+			if errors.Is(err, fs.ErrNotExist) {
+				return nil
+			}
+			return err
+		}
+		if entry.IsDir() {
+			if b.skipDir(d, p) {
+				return fs.SkipDir
+			}
+			return nil
+		}
+		switch ext := path.Ext(p); {
+		case ext == ".py" && (d.meta.Name == "" || !modules.PythonTestPath(p)):
+			files = append(files, p)
+		case compiledExts[ext]:
+			compiled = append(compiled, p)
+		}
+		return nil
+	}
+	roots := []string{"."}
+	if d.meta.Name != "" {
+		roots = nil
+		for _, top := range d.meta.TopLevel {
+			if _, err := fs.Stat(d.fsys, top+".py"); err == nil {
+				files = append(files, top+".py")
+			}
+			roots = append(roots, top)
+		}
+		compiled = append(compiled, d.meta.Compiled...)
+	}
+	for _, root := range roots {
+		if root != "." {
+			if info, err := fs.Stat(d.fsys, root); err != nil || !info.IsDir() {
+				continue
+			}
+		}
+		if err := fs.WalkDir(d.fsys, root, visit); err != nil {
+			return nil, nil, err
+		}
+	}
+	slices.Sort(files)
+	slices.Sort(compiled)
+	return slices.Compact(files), slices.Compact(compiled), nil
+}
+
+// skipDir reports whether no file of a directory is code of the node.
+func (b *builder) skipDir(d *dist, p string) bool {
+	if p == "." {
+		return false
+	}
+	base := path.Base(p)
+	switch {
+	case strings.HasPrefix(base, ".") || base == "__pycache__" || base == "node_modules":
+		return true
+	case d.meta.Name != "":
+		return false
+	case base == "site-packages":
+		return true
+	}
+	_, err := fs.Stat(d.fsys, path.Join(p, "pyvenv.cfg"))
+	return err == nil
+}