plumbing: format index, Index.Add and Index.Glob methods

Signed-off-by: Máximo Cuadros <mcuadros@gmail.com>

Author: mcuadros

plumbing/format/index/index.go

@@ -4,6 +4,7 @@ import (
 	"bytes"
 	"errors"
 	"fmt"
+	"path/filepath"
 	"time"
 
 	"gopkg.in/src-d/go-git.v4/plumbing"
@@ -51,8 +52,20 @@ type Index struct {
 	ResolveUndo *ResolveUndo
 }
 
+// Add creates a new Entry and returns it. The caller should first check that
+// another entry with the same path does not exist.
+func (i *Index) Add(path string) *Entry {
+	e := &Entry{
+		Name: filepath.ToSlash(path),
+	}
+
+	i.Entries = append(i.Entries, e)
+	return e
+}
+
 // Entry returns the entry that match the given path, if any.
 func (i *Index) Entry(path string) (*Entry, error) {
+	path = filepath.ToSlash(path)
 	for _, e := range i.Entries {
 		if e.Name == path {
 			return e, nil
@@ -64,6 +77,7 @@ func (i *Index) Entry(path string) (*Entry, error) {
 
 // Remove remove the entry that match the give path and returns deleted entry.
 func (i *Index) Remove(path string) (*Entry, error) {
+	path = filepath.ToSlash(path)
 	for index, e := range i.Entries {
 		if e.Name == path {
 			i.Entries = append(i.Entries[:index], i.Entries[index+1:]...)
@@ -74,6 +88,24 @@ func (i *Index) Remove(path string) (*Entry, error) {
 	return nil, ErrEntryNotFound
 }
 
+// Glob returns the all entries matching pattern or nil if there is no matching
+// entry. The syntax of patterns is the same as in filepath.Glob.
+func (i *Index) Glob(pattern string) (matches []*Entry, err error) {
+	pattern = filepath.ToSlash(pattern)
+	for _, e := range i.Entries {
+		m, err := match(pattern, e.Name)
+		if err != nil {
+			return nil, err
+		}
+
+		if m {
+			matches = append(matches, e)
+		}
+	}
+
+	return
+}
+
 // String is equivalent to `git ls-files --stage --debug`
 func (i *Index) String() string {
 	buf := bytes.NewBuffer(nil)

plumbing/format/index/index_test.go

@@ -1,9 +1,22 @@
 package index
 
 import (
+	"path/filepath"
+
 	. "gopkg.in/check.v1"
 )
 
+func (s *IndexSuite) TestIndexAdd(c *C) {
+	idx := &Index{}
+	e := idx.Add("foo")
+	e.Size = 42
+
+	e, err := idx.Entry("foo")
+	c.Assert(err, IsNil)
+	c.Assert(e.Name, Equals, "foo")
+	c.Assert(e.Size, Equals, uint32(42))
+}
+
 func (s *IndexSuite) TestIndexEntry(c *C) {
 	idx := &Index{
 		Entries: []*Entry{
@@ -37,3 +50,27 @@ func (s *IndexSuite) TestIndexRemove(c *C) {
 	c.Assert(e, IsNil)
 	c.Assert(err, Equals, ErrEntryNotFound)
 }
+
+func (s *IndexSuite) TestIndexGlob(c *C) {
+	idx := &Index{
+		Entries: []*Entry{
+			{Name: "foo/bar/bar", Size: 42},
+			{Name: "foo/baz/qux", Size: 42},
+			{Name: "fux", Size: 82},
+		},
+	}
+
+	m, err := idx.Glob(filepath.Join("foo", "b*"))
+	c.Assert(err, IsNil)
+	c.Assert(m, HasLen, 2)
+	c.Assert(m[0].Name, Equals, "foo/bar/bar")
+	c.Assert(m[1].Name, Equals, "foo/baz/qux")
+
+	m, err = idx.Glob("f*")
+	c.Assert(err, IsNil)
+	c.Assert(m, HasLen, 3)
+
+	m, err = idx.Glob("f*/baz/q*")
+	c.Assert(err, IsNil)
+	c.Assert(m, HasLen, 1)
+}

plumbing/format/index/match.go

@@ -0,0 +1,186 @@
+package index
+
+import (
+	"path/filepath"
+	"runtime"
+	"unicode/utf8"
+)
+
+// match is filepath.Match with support to match fullpath and not only filenames
+// code from:
+// https://github.com/golang/go/blob/39852bf4cce6927e01d0136c7843f65a801738cb/src/path/filepath/match.go#L44-L224
+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)
+
+		// 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); 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 '\\':
+			if runtime.GOOS != "windows" {
+				// 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 = filepath.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 '?':
+			_, n := utf8.DecodeRuneInString(s)
+			s = s[n:]
+			chunk = chunk[1:]
+
+		case '\\':
+			if runtime.GOOS != "windows" {
+				chunk = chunk[1:]
+				if len(chunk) == 0 {
+					err = filepath.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 = filepath.ErrBadPattern
+		return
+	}
+	if chunk[0] == '\\' && runtime.GOOS != "windows" {
+		chunk = chunk[1:]
+		if len(chunk) == 0 {
+			err = filepath.ErrBadPattern
+			return
+		}
+	}
+	r, n := utf8.DecodeRuneInString(chunk)
+	if r == utf8.RuneError && n == 1 {
+		err = filepath.ErrBadPattern
+	}
+	nchunk = chunk[n:]
+	if len(nchunk) == 0 {
+		err = filepath.ErrBadPattern
+	}
+	return
+}