filepath.go

// Original: src/path/filepath/match.go
//
// Copyright 2010 The Go Authors. All rights reserved.
// Portions Copyright 2021 Hiroshi Ioka. All rights reserved.
//
// Redistribution and use in source and binary forms, with or without
// modification, are permitted provided that the following conditions are
// met:
//
//    * Redistributions of source code must retain the above copyright
// notice, this list of conditions and the following disclaimer.
//    * Redistributions in binary form must reproduce the above
// copyright notice, this list of conditions and the following disclaimer
// in the documentation and/or other materials provided with the
// distribution.
//    * Neither the name of Google Inc. nor the names of its
// contributors may be used to endorse or promote products derived from
// this software without specific prior written permission.
//
// THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
// "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
// LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
// A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
// OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
// SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
// LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
// DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
// THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
// (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
// OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.

package smb2

import (
	"errors"
	"os"
	"regexp"
	"sort"
	"strings"
	"unicode/utf8"

	. "github.com/elimity-com/go-smb2/internal/erref"
)

// 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 != '*', '?', '[')
//
//	character-range:
//		c           matches character c (c != '-', ']')
//		lo '-' hi   matches character c for lo <= c <= hi
//
// Match requires pattern to match all of name, not just a substring.
// The only possible returned error is ErrBadPattern, when pattern
// is malformed.
func Match(pattern, name string) (matched bool, err error) {
	pattern = normPattern(pattern)

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(PathSeparator)), 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] != PathSeparator; 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
	var i int
Scan:
	for i = 0; i < len(pattern); i++ {
		switch pattern[i] {
		case '[':
			inrange = true
		case ']':
			inrange = false
		case '*':
			if !inrange {
				break Scan
			}
		}
	}
	return star, pattern[0:i], pattern[i:]
}

// 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 {
		if !failed && len(s) == 0 {
			failed = true
		}
		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
					}
				}
				if lo <= r && r <= hi {
					match = true
				}
				nrange++
			}
			if match == negated {
				failed = true
			}

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

		default:
			if !failed {
				if chunk[0] != s[0] {
					failed = true
				}
				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
	}
	r, n := utf8.DecodeRuneInString(chunk)
	if r == utf8.RuneError && n == 1 {
		err = ErrBadPattern
	}
	nchunk = chunk[n:]
	if len(nchunk) == 0 {
		err = ErrBadPattern
	}
	return
}

// Glob should work like filepath.Glob.
func (fs *Share) Glob(pattern string) (matches []string, err error) {
	pattern = normPattern(pattern)

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

	if !hasMeta(pattern) {
		if _, err = fs.Lstat(pattern); err != nil {
			return nil, nil
		}
		return []string{pattern}, nil
	}

	dir, file := split(pattern)

	dir = cleanGlobPath(dir)

	if !hasMeta(dir) {
		return fs.glob(dir, file, nil)
	}

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

	var m []string
	m, err = fs.Glob(dir)
	if err != nil {
		return
	}
	for _, d := range m {
		matches, err = fs.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(PathSeparator):
		// do nothing to the path
		return path
	default:
		return path[0 : len(path)-1] // chop off trailing separator
	}
}

var characterRangePattern = regexp.MustCompile(`\[^?[^\[\]]+\]`)

func simplifyPattern(pattern string) string {
	return characterRangePattern.ReplaceAllLiteralString(pattern, "?")
}

// 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 (fs *Share) glob(dir, pattern string, matches []string) (m []string, e error) {
	m = matches
	fi, err := fs.Stat(dir)
	if err != nil {
		return // ignore I/O error
	}
	if !fi.IsDir() {
		return // ignore I/O error
	}
	d, err := fs.Open(dir)
	if err != nil {
		return // ignore I/O error
	}
	defer d.Close()

	var names []string

L:
	for {
		dirents, err := d.readdir(simplifyPattern(pattern))
		for _, st := range dirents {
			names = append(names, st.Name())
		}
		if err != nil {
			if err, ok := err.(*ResponseError); ok {
				switch NtStatus(err.Code) {
				case STATUS_NO_SUCH_FILE:
					return []string{}, nil
				case STATUS_NO_MORE_FILES:
					break L
				}
			}
			return nil, &os.PathError{Op: "readdir", Path: d.name, Err: err}
		}
	}

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

	sort.Strings(m)

	return
}

// hasMeta reports whether path contains any of the magic characters
// recognized by Match.
func hasMeta(path string) bool {
	return strings.ContainsAny(path, `*?[`)
}