ConfigKit/internal/engine/glob.go

package engine

import (
	"errors"
	"io"
	"io/fs"
	"os"
	"path"
	"path/filepath"
	"slices"
	"strings"
)

const globReadBatch = 128

type globCandidate struct {
	absolute string
	relative string
}

func (s *importTraversal) expandImportGlob(basePath string, declaration importDeclaration) ([]string, []Diagnostic) {
	location := declaration.location
	segments, valid := validGlobPattern(declaration.glob)
	if !valid {
		return nil, []Diagnostic{importDiagnostic(CodeImportInvalid, "import glob pattern is invalid or uses recursive ** syntax", &location)}
	}

	candidates := []globCandidate{{absolute: basePath}}
	for index, segment := range segments {
		last := index == len(segments)-1
		literal, patterned := globLiteralSegment(segment)
		var next []globCandidate
		for _, candidate := range candidates {
			var names []string
			if patterned {
				matched, diagnostics := s.readGlobMatches(candidate.absolute, segment, location)
				if len(diagnostics) != 0 {
					return nil, diagnostics
				}
				names = matched
			} else {
				names = []string{literal}
			}
			for _, name := range names {
				absolute := filepath.Join(candidate.absolute, filepath.FromSlash(name))
				relative := path.Join(candidate.relative, name)
				if !containedPath(s.rootPath, filepath.Clean(absolute)) {
					return nil, []Diagnostic{importDiagnostic(CodeImportOutsideRoot, "glob traversal is outside the configuration root", &location)}
				}
				canonical, err := canonicalExistingPath(absolute)
				if err != nil {
					if errors.Is(err, fs.ErrNotExist) && !patterned {
						continue
					}
					return nil, []Diagnostic{globFilesystemDiagnostic(err, "glob match could not be canonicalized", location)}
				}
				if !containedPath(s.rootPath, canonical) {
					return nil, []Diagnostic{importDiagnostic(CodeImportOutsideRoot, "glob traversal resolves outside the configuration root", &location)}
				}
				if last {
					next = append(next, globCandidate{absolute: canonical, relative: relative})
					if len(s.sources)+len(next) > s.limits.sources {
						return nil, []Diagnostic{importDiagnostic(CodeImportLimitExceeded, "glob matches exceed the remaining source-count limit", &location)}
					}
					continue
				}
				info, err := os.Stat(canonical)
				if err != nil {
					return nil, []Diagnostic{globFilesystemDiagnostic(err, "glob traversal target could not be inspected", location)}
				}
				if info.IsDir() {
					next = append(next, globCandidate{absolute: canonical, relative: relative})
				}
			}
		}
		candidates = next
		if len(candidates) == 0 {
			return nil, nil
		}
	}

	matches := make([]string, len(candidates))
	for index, candidate := range candidates {
		matches[index] = candidate.relative
	}
	slices.Sort(matches)
	return matches, nil
}

func (s *importTraversal) readGlobMatches(directory, pattern string, location Location) ([]string, []Diagnostic) {
	canonical, err := canonicalExistingPath(directory)
	if err != nil {
		if errors.Is(err, fs.ErrNotExist) {
			return nil, nil
		}
		return nil, []Diagnostic{globFilesystemDiagnostic(err, "glob directory could not be canonicalized", location)}
	}
	if !containedPath(s.rootPath, canonical) {
		return nil, []Diagnostic{importDiagnostic(CodeImportOutsideRoot, "glob directory resolves outside the configuration root", &location)}
	}
	relative, err := filepath.Rel(s.rootPath, canonical)
	if err != nil || filepath.IsAbs(relative) || relative == ".." || strings.HasPrefix(relative, ".."+string(filepath.Separator)) {
		return nil, []Diagnostic{importDiagnostic(CodeImportOutsideRoot, "glob directory could not be addressed inside the configuration root", &location)}
	}
	directoryFile, err := s.root.Open(relative)
	if err != nil {
		if errors.Is(err, fs.ErrNotExist) {
			return nil, nil
		}
		return nil, []Diagnostic{globFilesystemDiagnostic(err, "glob directory could not be opened", location)}
	}

	var matches []string
	for {
		entries, readErr := directoryFile.ReadDir(globReadBatch)
		for _, entry := range entries {
			s.usedEntries++
			if s.usedEntries > s.limits.entries {
				_ = directoryFile.Close()
				return nil, []Diagnostic{importDiagnostic(CodeImportLimitExceeded, "glob traversal exceeds the directory-entry visit limit", &location)}
			}
			matched, matchErr := path.Match(pattern, entry.Name())
			if matchErr != nil {
				_ = directoryFile.Close()
				return nil, []Diagnostic{importDiagnostic(CodeImportInvalid, "import glob pattern is invalid", &location)}
			}
			if matched {
				matches = append(matches, entry.Name())
			}
		}
		if errors.Is(readErr, io.EOF) {
			break
		}
		if readErr != nil {
			_ = directoryFile.Close()
			return nil, []Diagnostic{globFilesystemDiagnostic(readErr, "glob directory could not be read", location)}
		}
	}
	if err := directoryFile.Close(); err != nil {
		return nil, []Diagnostic{globFilesystemDiagnostic(err, "glob directory could not be closed", location)}
	}
	slices.Sort(matches)
	return matches, nil
}

func validGlobPattern(pattern string) ([]string, bool) {
	if !validImportPath(pattern) {
		return nil, false
	}
	segments := strings.Split(pattern, "/")
	for _, segment := range segments {
		if segment == "" || hasRecursiveStars(segment) {
			return nil, false
		}
		if _, err := path.Match(segment, ""); err != nil {
			return nil, false
		}
	}
	return segments, true
}

func hasRecursiveStars(segment string) bool {
	inClass := false
	for index := 0; index < len(segment); index++ {
		switch segment[index] {
		case '\\':
			index++
		case '[':
			inClass = true
		case ']':
			inClass = false
		case '*':
			if !inClass && index+1 < len(segment) && segment[index+1] == '*' {
				return true
			}
		}
	}
	return false
}

func globLiteralSegment(segment string) (string, bool) {
	var literal strings.Builder
	for index := 0; index < len(segment); index++ {
		switch segment[index] {
		case '*', '?', '[':
			return "", true
		case '\\':
			index++
			if index < len(segment) {
				literal.WriteByte(segment[index])
			}
		default:
			literal.WriteByte(segment[index])
		}
	}
	return literal.String(), false
}

func globFilesystemDiagnostic(err error, message string, location Location) Diagnostic {
	code := CodeImportRead
	if errors.Is(err, fs.ErrPermission) {
		code = CodeImportPermission
	}
	return importDiagnostic(code, message, &location)
}