rclone/vendor/github.com/pkg/sftp/match.go

package sftp

import (
	"path"
	"strings"
	"unicode/utf8"
)

// ErrBadPattern indicates a globbing pattern was malformed.
var ErrBadPattern = path.ErrBadPattern

// Unix separator
const separator = "/"

// 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
//
//	character-range:
//		c           matches character c (c != '\\', '-', ']')
//		'\\' c      matches character 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) {
	return path.Match(pattern, name)
}

// detect if byte(char) is path separator
func isPathSeparator(c byte) bool {
	return string(c) == "/"
}

// 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 '\\':

			// error check handled in matchChunk: bad pattern.
			if i+1 < len(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) {
	for len(chunk) > 0 {
		if len(s) == 0 {
			return
		}
		switch chunk[0] {
		case '[':
			// character class
			r, n := utf8.DecodeRuneInString(s)
			s = s[n:]
			chunk = chunk[1:]
			// We can't end right after '[', we're expecting at least
			// a closing bracket and possibly a caret.
			if len(chunk) == 0 {
				err = ErrBadPattern
				return
			}
			// possibly negated
			negated := chunk[0] == '^'
			if negated {
				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
				}
				hi = lo
				if chunk[0] == '-' {
					if hi, chunk, err = getEsc(chunk[1:]); err != nil {
						return
					}
				}
				if lo <= r && r <= hi {
					match = true
				}
				nrange++
			}
			if match == negated {
				return
			}

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

		case '\\':
			chunk = chunk[1:]
			if len(chunk) == 0 {
				err = ErrBadPattern
				return
			}
			fallthrough

		default:
			if chunk[0] != s[0] {
				return
			}
			s = s[1:]
			chunk = chunk[1:]
		}
	}
	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] == '\\' {
		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
}

// Split splits path immediately following the final Separator,
// separating it into a directory and file name component.
// If there is no Separator in path, Split returns an empty dir
// and file set to path.
// The returned values have the property that path = dir+file.
func Split(path string) (dir, file string) {
	i := len(path) - 1
	for i >= 0 && !isPathSeparator(path[i]) {
		i--
	}
	return path[:i+1], path[i+1:]
}

// 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 (c *Client) Glob(pattern string) (matches []string, err error) {
	if !hasMeta(pattern) {
		file, err := c.Lstat(pattern)
		if err != nil {
			return nil, nil
		}
		dir, _ := Split(pattern)
		dir = cleanGlobPath(dir)
		return []string{Join(dir, file.Name())}, nil
	}

	dir, file := Split(pattern)
	dir = cleanGlobPath(dir)

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

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

	var m []string
	m, err = c.Glob(dir)
	if err != nil {
		return
	}
	for _, d := range m {
		matches, err = c.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
	}
}

// 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 (c *Client) glob(dir, pattern string, matches []string) (m []string, e error) {
	m = matches
	fi, err := c.Stat(dir)
	if err != nil {
		return
	}
	if !fi.IsDir() {
		return
	}
	names, err := c.ReadDir(dir)
	if err != nil {
		return
	}
	//sort.Strings(names)

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

// Join joins any number of path elements into a single path, adding
// a Separator if necessary.
// all empty strings are ignored.
func Join(elem ...string) string {
	return path.Join(elem...)
}

// hasMeta reports whether path contains any of the magic characters
// recognized by Match.
func hasMeta(path string) bool {
	// TODO(niemeyer): Should other magic characters be added here?
	return strings.ContainsAny(path, "*?[")
}