path, path/filepath: clarify and cross-reference packages

[gostls13.git] / src / path / filepath / path.go

// Copyright 2009 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 implements utility routines for manipulating filename paths
// in a way compatible with the target operating system-defined file paths.
//
// The filepath package uses either forward slashes or backslashes,
// depending on the operating system. To process paths such as URLs
// that always use forward slashes regardless of the operating
// system, see the path package.
package filepath

import (
        "errors"
        "os"
        "sort"
        "strings"
)

// A lazybuf is a lazily constructed path buffer.
// It supports append, reading previously appended bytes,
// and retrieving the final string. It does not allocate a buffer
// to hold the output until that output diverges from s.
type lazybuf struct {
        path       string
        buf        []byte
        w          int
        volAndPath string
        volLen     int
}

func (b *lazybuf) index(i int) byte {
        if b.buf != nil {
                return b.buf[i]
        }
        return b.path[i]
}

func (b *lazybuf) append(c byte) {
        if b.buf == nil {
                if b.w < len(b.path) && b.path[b.w] == c {
                        b.w++
                        return
                }
                b.buf = make([]byte, len(b.path))
                copy(b.buf, b.path[:b.w])
        }
        b.buf[b.w] = c
        b.w++
}

func (b *lazybuf) string() string {
        if b.buf == nil {
                return b.volAndPath[:b.volLen+b.w]
        }
        return b.volAndPath[:b.volLen] + string(b.buf[:b.w])
}

const (
        Separator     = os.PathSeparator
        ListSeparator = os.PathListSeparator
)

// Clean returns the shortest path name equivalent to path
// by purely lexical processing. It applies the following rules
// iteratively until no further processing can be done:
//
//      1. Replace multiple Separator elements with a single one.
//      2. Eliminate each . path name element (the current directory).
//      3. Eliminate each inner .. path name element (the parent directory)
//         along with the non-.. element that precedes it.
//      4. Eliminate .. elements that begin a rooted path:
//         that is, replace "/.." by "/" at the beginning of a path,
//         assuming Separator is '/'.
//
// The returned path ends in a slash only if it represents a root directory,
// such as "/" on Unix or `C:\` on Windows.
//
// Finally, any occurrences of slash are replaced by Separator.
//
// If the result of this process is an empty string, Clean
// returns the string ".".
//
// See also Rob Pike, ``Lexical File Names in Plan 9 or
// Getting Dot-Dot Right,''
// https://9p.io/sys/doc/lexnames.html
func Clean(path string) string {
        originalPath := path
        volLen := volumeNameLen(path)
        path = path[volLen:]
        if path == "" {
                if volLen > 1 && originalPath[1] != ':' {
                        // should be UNC
                        return FromSlash(originalPath)
                }
                return originalPath + "."
        }
        rooted := os.IsPathSeparator(path[0])

        // Invariants:
        //      reading from path; r is index of next byte to process.
        //      writing to buf; w is index of next byte to write.
        //      dotdot is index in buf where .. must stop, either because
        //              it is the leading slash or it is a leading ../../.. prefix.
        n := len(path)
        out := lazybuf{path: path, volAndPath: originalPath, volLen: volLen}
        r, dotdot := 0, 0
        if rooted {
                out.append(Separator)
                r, dotdot = 1, 1
        }

        for r < n {
                switch {
                case os.IsPathSeparator(path[r]):
                        // empty path element
                        r++
                case path[r] == '.' && (r+1 == n || os.IsPathSeparator(path[r+1])):
                        // . element
                        r++
                case path[r] == '.' && path[r+1] == '.' && (r+2 == n || os.IsPathSeparator(path[r+2])):
                        // .. element: remove to last separator
                        r += 2
                        switch {
                        case out.w > dotdot:
                                // can backtrack
                                out.w--
                                for out.w > dotdot && !os.IsPathSeparator(out.index(out.w)) {
                                        out.w--
                                }
                        case !rooted:
                                // cannot backtrack, but not rooted, so append .. element.
                                if out.w > 0 {
                                        out.append(Separator)
                                }
                                out.append('.')
                                out.append('.')
                                dotdot = out.w
                        }
                default:
                        // real path element.
                        // add slash if needed
                        if rooted && out.w != 1 || !rooted && out.w != 0 {
                                out.append(Separator)
                        }
                        // copy element
                        for ; r < n && !os.IsPathSeparator(path[r]); r++ {
                                out.append(path[r])
                        }
                }
        }

        // Turn empty string into "."
        if out.w == 0 {
                out.append('.')
        }

        return FromSlash(out.string())
}

// ToSlash returns the result of replacing each separator character
// in path with a slash ('/') character. Multiple separators are
// replaced by multiple slashes.
func ToSlash(path string) string {
        if Separator == '/' {
                return path
        }
        return strings.Replace(path, string(Separator), "/", -1)
}

// FromSlash returns the result of replacing each slash ('/') character
// in path with a separator character. Multiple slashes are replaced
// by multiple separators.
func FromSlash(path string) string {
        if Separator == '/' {
                return path
        }
        return strings.Replace(path, "/", string(Separator), -1)
}

// SplitList splits a list of paths joined by the OS-specific ListSeparator,
// usually found in PATH or GOPATH environment variables.
// Unlike strings.Split, SplitList returns an empty slice when passed an empty
// string.
func SplitList(path string) []string {
        return splitList(path)
}

// 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) {
        vol := VolumeName(path)
        i := len(path) - 1
        for i >= len(vol) && !os.IsPathSeparator(path[i]) {
                i--
        }
        return path[:i+1], path[i+1:]
}

// Join joins any number of path elements into a single path, adding
// a Separator if necessary. Join calls Clean on the result; in particular,
// all empty strings are ignored.
// On Windows, the result is a UNC path if and only if the first path
// element is a UNC path.
func Join(elem ...string) string {
        return join(elem)
}

// Ext returns the file name extension used by path.
// The extension is the suffix beginning at the final dot
// in the final element of path; it is empty if there is
// no dot.
func Ext(path string) string {
        for i := len(path) - 1; i >= 0 && !os.IsPathSeparator(path[i]); i-- {
                if path[i] == '.' {
                        return path[i:]
                }
        }
        return ""
}

// EvalSymlinks returns the path name after the evaluation of any symbolic
// links.
// If path is relative the result will be relative to the current directory,
// unless one of the components is an absolute symbolic link.
// EvalSymlinks calls Clean on the result.
func EvalSymlinks(path string) (string, error) {
        return evalSymlinks(path)
}

// Abs returns an absolute representation of path.
// If the path is not absolute it will be joined with the current
// working directory to turn it into an absolute path. The absolute
// path name for a given file is not guaranteed to be unique.
// Abs calls Clean on the result.
func Abs(path string) (string, error) {
        return abs(path)
}

func unixAbs(path string) (string, error) {
        if IsAbs(path) {
                return Clean(path), nil
        }
        wd, err := os.Getwd()
        if err != nil {
                return "", err
        }
        return Join(wd, path), nil
}

// Rel returns a relative path that is lexically equivalent to targpath when
// joined to basepath with an intervening separator. That is,
// Join(basepath, Rel(basepath, targpath)) is equivalent to targpath itself.
// On success, the returned path will always be relative to basepath,
// even if basepath and targpath share no elements.
// An error is returned if targpath can't be made relative to basepath or if
// knowing the current working directory would be necessary to compute it.
// Rel calls Clean on the result.
func Rel(basepath, targpath string) (string, error) {
        baseVol := VolumeName(basepath)
        targVol := VolumeName(targpath)
        base := Clean(basepath)
        targ := Clean(targpath)
        if sameWord(targ, base) {
                return ".", nil
        }
        base = base[len(baseVol):]
        targ = targ[len(targVol):]
        if base == "." {
                base = ""
        }
        // Can't use IsAbs - `\a` and `a` are both relative in Windows.
        baseSlashed := len(base) > 0 && base[0] == Separator
        targSlashed := len(targ) > 0 && targ[0] == Separator
        if baseSlashed != targSlashed || !sameWord(baseVol, targVol) {
                return "", errors.New("Rel: can't make " + targpath + " relative to " + basepath)
        }
        // Position base[b0:bi] and targ[t0:ti] at the first differing elements.
        bl := len(base)
        tl := len(targ)
        var b0, bi, t0, ti int
        for {
                for bi < bl && base[bi] != Separator {
                        bi++
                }
                for ti < tl && targ[ti] != Separator {
                        ti++
                }
                if !sameWord(targ[t0:ti], base[b0:bi]) {
                        break
                }
                if bi < bl {
                        bi++
                }
                if ti < tl {
                        ti++
                }
                b0 = bi
                t0 = ti
        }
        if base[b0:bi] == ".." {
                return "", errors.New("Rel: can't make " + targpath + " relative to " + basepath)
        }
        if b0 != bl {
                // Base elements left. Must go up before going down.
                seps := strings.Count(base[b0:bl], string(Separator))
                size := 2 + seps*3
                if tl != t0 {
                        size += 1 + tl - t0
                }
                buf := make([]byte, size)
                n := copy(buf, "..")
                for i := 0; i < seps; i++ {
                        buf[n] = Separator
                        copy(buf[n+1:], "..")
                        n += 3
                }
                if t0 != tl {
                        buf[n] = Separator
                        copy(buf[n+1:], targ[t0:])
                }
                return string(buf), nil
        }
        return targ[t0:], nil
}

// SkipDir is used as a return value from WalkFuncs to indicate that
// the directory named in the call is to be skipped. It is not returned
// as an error by any function.
var SkipDir = errors.New("skip this directory")

// WalkFunc is the type of the function called for each file or directory
// visited by Walk. The path argument contains the argument to Walk as a
// prefix; that is, if Walk is called with "dir", which is a directory
// containing the file "a", the walk function will be called with argument
// "dir/a". The info argument is the os.FileInfo for the named path.
//
// If there was a problem walking to the file or directory named by path, the
// incoming error will describe the problem and the function can decide how
// to handle that error (and Walk will not descend into that directory). If
// an error is returned, processing stops. The sole exception is when the function
// returns the special value SkipDir. If the function returns SkipDir when invoked
// on a directory, Walk skips the directory's contents entirely.
// If the function returns SkipDir when invoked on a non-directory file,
// Walk skips the remaining files in the containing directory.
type WalkFunc func(path string, info os.FileInfo, err error) error

var lstat = os.Lstat // for testing

// walk recursively descends path, calling w.
func walk(path string, info os.FileInfo, walkFn WalkFunc) error {
        err := walkFn(path, info, nil)
        if err != nil {
                if info.IsDir() && err == SkipDir {
                        return nil
                }
                return err
        }

        if !info.IsDir() {
                return nil
        }

        names, err := readDirNames(path)
        if err != nil {
                return walkFn(path, info, err)
        }

        for _, name := range names {
                filename := Join(path, name)
                fileInfo, err := lstat(filename)
                if err != nil {
                        if err := walkFn(filename, fileInfo, err); err != nil && err != SkipDir {
                                return err
                        }
                } else {
                        err = walk(filename, fileInfo, walkFn)
                        if err != nil {
                                if !fileInfo.IsDir() || err != SkipDir {
                                        return err
                                }
                        }
                }
        }
        return nil
}

// Walk walks the file tree rooted at root, calling walkFn for each file or
// directory in the tree, including root. All errors that arise visiting files
// and directories are filtered by walkFn. The files are walked in lexical
// order, which makes the output deterministic but means that for very
// large directories Walk can be inefficient.
// Walk does not follow symbolic links.
func Walk(root string, walkFn WalkFunc) error {
        info, err := os.Lstat(root)
        if err != nil {
                err = walkFn(root, nil, err)
        } else {
                err = walk(root, info, walkFn)
        }
        if err == SkipDir {
                return nil
        }
        return err
}

// readDirNames reads the directory named by dirname and returns
// a sorted list of directory entries.
func readDirNames(dirname string) ([]string, error) {
        f, err := os.Open(dirname)
        if err != nil {
                return nil, err
        }
        names, err := f.Readdirnames(-1)
        f.Close()
        if err != nil {
                return nil, err
        }
        sort.Strings(names)
        return names, nil
}

// Base returns the last element of path.
// Trailing path separators are removed before extracting the last element.
// If the path is empty, Base returns ".".
// If the path consists entirely of separators, Base returns a single separator.
func Base(path string) string {
        if path == "" {
                return "."
        }
        // Strip trailing slashes.
        for len(path) > 0 && os.IsPathSeparator(path[len(path)-1]) {
                path = path[0 : len(path)-1]
        }
        // Throw away volume name
        path = path[len(VolumeName(path)):]
        // Find the last element
        i := len(path) - 1
        for i >= 0 && !os.IsPathSeparator(path[i]) {
                i--
        }
        if i >= 0 {
                path = path[i+1:]
        }
        // If empty now, it had only slashes.
        if path == "" {
                return string(Separator)
        }
        return path
}

// Dir returns all but the last element of path, typically the path's directory.
// After dropping the final element, Dir calls Clean on the path and trailing
// slashes are removed.
// If the path is empty, Dir returns ".".
// If the path consists entirely of separators, Dir returns a single separator.
// The returned path does not end in a separator unless it is the root directory.
func Dir(path string) string {
        vol := VolumeName(path)
        i := len(path) - 1
        for i >= len(vol) && !os.IsPathSeparator(path[i]) {
                i--
        }
        dir := Clean(path[len(vol) : i+1])
        if dir == "." && len(vol) > 2 {
                // must be UNC
                return vol
        }
        return vol + dir
}

// VolumeName returns leading volume name.
// Given "C:\foo\bar" it returns "C:" on Windows.
// Given "\\host\share\foo" it returns "\\host\share".
// On other platforms it returns "".
func VolumeName(path string) string {
        return path[:volumeNameLen(path)]
}