src/path/filepath/match.go

// Copyright 2010 The Go Authors. All rights reserved.
// Use of this source code is governed by a BSD-style
// license that can be found in the LICENSE file.

package filepath

import (
	"errors"
	"internal/filepathlite"
	"os"
	"runtime"
	"slices"
	"strings"
	"unicode/utf8"
)

// ErrBadPattern indicates a pattern was malformed.
var ErrBadPattern = errors.New("syntax error in pattern")

// Match reports whether name matches the shell file name pattern.
// The pattern syntax is:
//
//	pattern:
//		{ term }
//	term:
//		'*'         matches any sequence of non-Separator characters
//		'?'         matches any single non-Separator character
//		'[' [ '^' ] { character-range } ']'
//		            character class (must be non-empty)
//		c           matches character c (c != '*', '?', '\\', '[')
//		'\\' c      matches character c (except on Windows)
//
//	character-range:
//		c           matches character c (c != '\\', '-', ']')
//		'\\' c      matches character c (except on Windows)
//		lo '-' hi   matches character c for lo <= c <= hi
//
// Path segments in the pattern must be separated by [Separator].
//
// Match requires pattern to match all of name, not just a substring.
// The only possible returned error is [ErrBadPattern], when pattern
// is malformed.
//
// On Windows, escaping is disabled. Instead, '\\' is treated as
// path separator.
func Match(pattern, name string) (matched bool, err error) {
Pattern:
	for len(pattern) > 0 {
		var star bool
		var chunk string
		star, chunk, pattern = scanChunk(pattern)
		if star && chunk == "" {
			// Trailing * matches rest of string unless it has a /.
			return !strings.Contains(name, string(Separator)), nil
		}
		// Look for match at current position.
		t, ok, err := matchChunk(chunk, name)
		// if we're the last chunk, make sure we've exhausted the name
		// otherwise we'll give a false result even if we could still match
		// using the star
		if ok && (len(t) == 0 || len(pattern) > 0) {
			name = t
			continue
		}
		if err != nil {
			return false, err
		}
		if star {
			// Look for match skipping i+1 bytes.
			// Cannot skip /.
			for i := 0; i < len(name) && name[i] != Separator; i++ {
				t, ok, err := matchChunk(chunk, name[i+1:])
				if ok {
					// if we're the last chunk, make sure we exhausted the name
					if len(pattern) == 0 && len(t) > 0 {
						continue
					}
					name = t
					continue Pattern
				}
				if err != nil {
					return false, err
				}
			}
		}
		return false, nil
	}
	return len(name) == 0, nil
}

// scanChunk gets the next segment of pattern, which is a non-star string
// possibly preceded by a star.
func scanChunk(pattern string) (star bool, chunk, rest string) {
	for len(pattern) > 0 && pattern[0] == '*' {
		pattern = pattern[1:]
		star = true
	}
	inrange := false
	for i := 0; i < len(pattern); i++ {
		switch pattern[i] {
		case '\\':
			// error check handled in matchChunk: bad pattern.
			if runtime.GOOS != "windows" && i+1 < len(pattern) {
				i++
			}
		case '[':
			inrange = true
		case ']':
			inrange = false
		case '*':
			if !inrange {
				return star, pattern[:i], pattern[i:]
			}
		}
	}
	return star, pattern, ""
}

// matchChunk checks whether chunk matches the beginning of s.
// If so, it returns the remainder of s (after the match).
// Chunk is all single-character operators: literals, char classes, and ?.
func matchChunk(chunk, s string) (rest string, ok bool, err error) {
	// failed records whether the match has failed.
	// After the match fails, the loop continues on processing chunk,
	// checking that the pattern is well-formed but no longer reading s.
	failed := false
	for len(chunk) > 0 {
		failed = failed || len(s) == 0
		switch chunk[0] {
		case '[':
			// character class
			var r rune
			if !failed {
				var n int
				r, n = utf8.DecodeRuneInString(s)
				s = s[n:]
			}
			chunk = chunk[1:]
			// possibly negated
			negated := false
			if len(chunk) > 0 && chunk[0] == '^' {
				negated = true
				chunk = chunk[1:]
			}
			// parse all ranges
			match := false
			nrange := 0
			for {
				if len(chunk) > 0 && chunk[0] == ']' && nrange > 0 {
					chunk = chunk[1:]
					break
				}
				var lo, hi rune
				if lo, chunk, err = getEsc(chunk); err != nil {
					return "", false, err
				}
				hi = lo
				if chunk[0] == '-' {
					if hi, chunk, err = getEsc(chunk[1:]); err != nil {
						return "", false, err
					}
				}
				match = match || lo <= r && r <= hi
				nrange++
			}
			failed = failed || match == negated

		case '?':
			if !failed {
				failed = s[0] == Separator
				_, n := utf8.DecodeRuneInString(s)
				s = s[n:]
			}
			chunk = chunk[1:]

		case '\\':
			if runtime.GOOS != "windows" {
				chunk = chunk[1:]
				if len(chunk) == 0 {
					return "", false, ErrBadPattern
				}
			}
			fallthrough

		default:
			if !failed {
				failed = chunk[0] != s[0]
				s = s[1:]
			}
			chunk = chunk[1:]
		}
	}
	if failed {
		return "", false, nil
	}
	return s, true, nil
}

// getEsc gets a possibly-escaped character from chunk, for a character class.
func getEsc(chunk string) (r rune, nchunk string, err error) {
	if len(chunk) == 0 || chunk[0] == '-' || chunk[0] == ']' {
		err = ErrBadPattern
		return
	}
	if chunk[0] == '\\' && runtime.GOOS != "windows" {
		chunk = chunk[1:]
		if len(chunk) == 0 {
			err = ErrBadPattern
			return
		}
	}
	r, n := utf8.DecodeRuneInString(chunk)
	if r == utf8.RuneError && n == 1 {
		err = ErrBadPattern
	}
	nchunk = chunk[n:]
	if len(nchunk) == 0 {
		err = ErrBadPattern
	}
	return
}

// Glob returns the names of all files matching pattern or nil
// if there is no matching file. The syntax of patterns is the same
// as in [Match]. The pattern may describe hierarchical names such as
// /usr/*/bin/ed (assuming the [Separator] is '/').
//
// Glob ignores file system errors such as I/O errors reading directories.
// The only possible returned error is [ErrBadPattern], when pattern
// is malformed.
func Glob(pattern string) (matches []string, err error) {
	return globWithLimit(pattern, 0)
}

func globWithLimit(pattern string, depth int) (matches []string, err error) {
	// This limit is used prevent stack exhaustion issues. See CVE-2022-30632.
	const pathSeparatorsLimit = 10000
	if depth == pathSeparatorsLimit {
		return nil, ErrBadPattern
	}

	// Check pattern is well-formed.
	if _, err := Match(pattern, ""); err != nil {
		return nil, err
	}
	if !hasMeta(pattern) {
		if _, err = os.Lstat(pattern); err != nil {
			return nil, nil
		}
		return []string{pattern}, nil
	}

	dir, file := Split(pattern)
	volumeLen := 0
	if runtime.GOOS == "windows" {
		volumeLen, dir = cleanGlobPathWindows(dir)
	} else {
		dir = cleanGlobPath(dir)
	}

	if !hasMeta(dir[volumeLen:]) {
		return glob(dir, file, nil)
	}

	// Prevent infinite recursion. See issue 15879.
	if dir == pattern {
		return nil, ErrBadPattern
	}

	var m []string
	m, err = globWithLimit(dir, depth+1)
	if err != nil {
		return
	}
	for _, d := range m {
		matches, err = glob(d, file, matches)
		if err != nil {
			return
		}
	}
	return
}

// cleanGlobPath prepares path for glob matching.
func cleanGlobPath(path string) string {
	switch path {
	case "":
		return "."
	case string(Separator):
		// do nothing to the path
		return path
	default:
		return path[0 : len(path)-1] // chop off trailing separator
	}
}

// cleanGlobPathWindows is windows version of cleanGlobPath.
func cleanGlobPathWindows(path string) (prefixLen int, cleaned string) {
	vollen := filepathlite.VolumeNameLen(path)
	switch {
	case path == "":
		return 0, "."
	case vollen+1 == len(path) && os.IsPathSeparator(path[len(path)-1]): // /, \, C:\ and C:/
		// do nothing to the path
		return vollen + 1, path
	case vollen == len(path) && len(path) == 2: // C:
		return vollen, path + "." // convert C: into C:.
	default:
		if vollen >= len(path) {
			vollen = len(path) - 1
		}
		return vollen, path[0 : len(path)-1] // chop off trailing separator
	}
}

// glob searches for files matching pattern in the directory dir
// and appends them to matches. If the directory cannot be
// opened, it returns the existing matches. New matches are
// added in lexicographical order.
func glob(dir, pattern string, matches []string) (m []string, e error) {
	m = matches
	fi, err := os.Stat(dir)
	if err != nil {
		return // ignore I/O error
	}
	if !fi.IsDir() {
		return // ignore I/O error
	}
	d, err := os.Open(dir)
	if err != nil {
		return // ignore I/O error
	}
	defer d.Close()

	names, _ := d.Readdirnames(-1)
	slices.Sort(names)

	for _, n := range names {
		matched, err := Match(pattern, n)
		if err != nil {
			return m, err
		}
		if matched {
			m = append(m, Join(dir, n))
		}
	}
	return
}

// hasMeta reports whether path contains any of the magic characters
// recognized by Match.
func hasMeta(path string) bool {
	magicChars := `*?[`
	if runtime.GOOS != "windows" {
		magicChars = `*?[\`
	}
	return strings.ContainsAny(path, magicChars)
}