Adds gitignore support

Author: Oleg Sklyar

Diff for: plumbing/format/gitignore/dir.go

@@ -0,0 +1,50 @@
+package gitignore
+
+import (
+	"io/ioutil"
+	"strings"
+
+	"gopkg.in/src-d/go-billy.v2"
+)
+
+const (
+	commentPrefix = "#"
+	eol           = "\n"
+	gitDir        = ".git"
+	gitignoreFile = ".gitignore"
+)
+
+// ReadPatterns reads gitignore patterns recursively traversing through the directory
+// structure. The result is in the ascending order of priority (last higher).
+func ReadPatterns(fs billy.Filesystem, path []string) (ps []Pattern, err error) {
+	if f, err := fs.Open(fs.Join(append(path, gitignoreFile)...)); err == nil {
+		defer f.Close()
+		if data, err := ioutil.ReadAll(f); err == nil {
+			for _, s := range strings.Split(string(data), eol) {
+				if !strings.HasPrefix(s, commentPrefix) && len(strings.TrimSpace(s)) > 0 {
+					ps = append(ps, ParsePattern(s, path))
+				}
+			}
+		}
+	}
+
+	var fis []billy.FileInfo
+	fis, err = fs.ReadDir(fs.Join(path...))
+	if err != nil {
+		return
+	}
+	for _, fi := range fis {
+		if fi.IsDir() && fi.Name() != gitDir {
+			var subps []Pattern
+			subps, err = ReadPatterns(fs, append(path, fi.Name()))
+			if err != nil {
+				return
+			}
+			if len(subps) > 0 {
+				ps = append(ps, subps...)
+			}
+		}
+	}
+
+	return
+}

Diff for: plumbing/format/gitignore/dir_test.go

@@ -0,0 +1,41 @@
+package gitignore
+
+import (
+	"os"
+	"testing"
+
+	"gopkg.in/src-d/go-billy.v2"
+	"gopkg.in/src-d/go-billy.v2/memfs"
+)
+
+func setupTestFS(subdirError bool) billy.Filesystem {
+	fs := memfs.New()
+	f, _ := fs.Create(".gitignore")
+	f.Write([]byte("vendor/g*/\n"))
+	f.Close()
+	fs.MkdirAll("vendor", os.ModePerm)
+	f, _ = fs.Create("vendor/.gitignore")
+	f.Write([]byte("!github.com/\n"))
+	f.Close()
+	fs.MkdirAll("another", os.ModePerm)
+	fs.MkdirAll("vendor/github.com", os.ModePerm)
+	fs.MkdirAll("vendor/gopkg.in", os.ModePerm)
+	return fs
+}
+
+func TestDir_ReadPatterns(t *testing.T) {
+	ps, err := ReadPatterns(setupTestFS(false), nil)
+	if err != nil {
+		t.Errorf("no error expected, found %v", err)
+	}
+	if len(ps) != 2 {
+		t.Errorf("expected 2 patterns, found %v", len(ps))
+	}
+	m := NewMatcher(ps)
+	if !m.Match([]string{"vendor", "gopkg.in"}, true) {
+		t.Error("expected a match")
+	}
+	if m.Match([]string{"vendor", "github.com"}, true) {
+		t.Error("expected no match")
+	}
+}

Diff for: plumbing/format/gitignore/doc.go

@@ -0,0 +1,70 @@
+// Package gitignore implements matching file system paths to gitignore patterns that
+// can be automatically read from a git repository tree in the order of definition
+// priorities. It support all pattern formats as specified in the original gitignore
+// documentation, copied below:
+//
+//   Pattern format
+//   ==============
+//
+//		- A blank line matches no files, so it can serve as a separator for readability.
+//
+//		- A line starting with # serves as a comment. Put a backslash ("\") in front of
+//		  the first hash for patterns that begin with a hash.
+//
+//		- Trailing spaces are ignored unless they are quoted with backslash ("\").
+//
+//		- An optional prefix "!" which negates the pattern; any matching file excluded
+//		  by a previous pattern will become included again. It is not possible to
+//		  re-include a file if a parent directory of that file is excluded.
+//		  Git doesn’t list excluded directories for performance reasons, so
+//		  any patterns on contained files have no effect, no matter where they are
+//		  defined. Put a backslash ("\") in front of the first "!" for patterns
+//		  that begin with a literal "!", for example, "\!important!.txt".
+//
+//		- If the pattern ends with a slash, it is removed for the purpose of the
+//		  following description, but it would only find a match with a directory.
+//		  In other words, foo/ will match a directory foo and paths underneath it,
+//		  but will not match a regular file or a symbolic link foo (this is consistent
+//		  with the way how pathspec works in general in Git).
+//
+//		- If the pattern does not contain a slash /, Git treats it as a shell glob
+//		  pattern and checks for a match against the pathname relative to the location
+//		  of the .gitignore file (relative to the toplevel of the work tree if not
+//		  from a .gitignore file).
+//
+//		- Otherwise, Git treats the pattern as a shell glob suitable for consumption
+//		  by fnmatch(3) with the FNM_PATHNAME flag: wildcards in the pattern will
+//		  not match a / in the pathname. For example, "Documentation/*.html" matches
+//		  "Documentation/git.html" but not "Documentation/ppc/ppc.html" or
+//		  "tools/perf/Documentation/perf.html".
+//
+//		- A leading slash matches the beginning of the pathname. For example,
+//		  "/*.c" matches "cat-file.c" but not "mozilla-sha1/sha1.c".
+//
+//		Two consecutive asterisks ("**") in patterns matched against full pathname
+//		may have special meaning:
+//
+//		- A leading "**" followed by a slash means match in all directories.
+//		  For example, "**/foo" matches file or directory "foo" anywhere, the same as
+//		  pattern "foo". "**/foo/bar" matches file or directory "bar"
+//		  anywhere that is directly under directory "foo".
+//
+//		- A trailing "/**" matches everything inside. For example, "abc/**" matches
+//		  all files inside directory "abc", relative to the location of the
+//		  .gitignore file, with infinite depth.
+//
+//		- A slash followed by two consecutive asterisks then a slash matches
+//		  zero or more directories. For example, "a/**/b" matches "a/b", "a/x/b",
+//		  "a/x/y/b" and so on.
+//
+//		- Other consecutive asterisks are considered invalid.
+//
+//   Copyright and license
+//   =====================
+//
+//		Copyright (c) Oleg Sklyar, Silvertern and source{d}
+//
+//		The package code was donated to source{d} to include, modify and develop
+//		further as a part of the `go-git` project, release it on the license of
+//		the whole project or delete it from the project.
+package gitignore

Diff for: plumbing/format/gitignore/matcher.go

@@ -0,0 +1,30 @@
+package gitignore
+
+// Matcher defines a global multi-pattern matcher for gitignore patterns
+type Matcher interface {
+	// Match matches patterns in the order of priorities. As soon as an inclusion or
+	// exclusion is found, not further matching is performed.
+	Match(path []string, isDir bool) bool
+}
+
+// NewMatcher constructs a new global matcher. Patterns must be given in the order of
+// increasing priority. That is most generic settings files first, then the content of
+// the repo .gitignore, then content of .gitignore down the path or the repo and then
+// the content command line arguments.
+func NewMatcher(ps []Pattern) Matcher {
+	return &matcher{ps}
+}
+
+type matcher struct {
+	patterns []Pattern
+}
+
+func (m *matcher) Match(path []string, isDir bool) bool {
+	n := len(m.patterns)
+	for i := n - 1; i >= 0; i-- {
+		if match := m.patterns[i].Match(path, isDir); match > NoMatch {
+			return match == Exclude
+		}
+	}
+	return false
+}

Diff for: plumbing/format/gitignore/matcher_test.go

@@ -0,0 +1,17 @@
+package gitignore
+
+import "testing"
+
+func TestMatcher_Match(t *testing.T) {
+	ps := []Pattern{
+		ParsePattern("**/middle/v[uo]l?ano", nil),
+		ParsePattern("!volcano", nil),
+	}
+	m := NewMatcher(ps)
+	if !m.Match([]string{"head", "middle", "vulkano"}, false) {
+		t.Errorf("expected a match, found mismatch")
+	}
+	if m.Match([]string{"head", "middle", "volcano"}, false) {
+		t.Errorf("expected a mismatch, found a match")
+	}
+}

Diff for: plumbing/format/gitignore/pattern.go

@@ -0,0 +1,150 @@
+package gitignore
+
+import (
+	"path/filepath"
+	"strings"
+)
+
+// MatchResult defines outcomes of a match, no match, exclusion or inclusion.
+type MatchResult int
+
+const (
+	// NoMatch defines the no match outcome of a match check
+	NoMatch MatchResult = iota
+	// Exclude defines an exclusion of a file as a result of a match check
+	Exclude
+	// Exclude defines an explicit inclusion of a file as a result of a match check
+	Include
+)
+
+const (
+	inclusionPrefix = "!"
+	zeroToManyDirs  = "**"
+	patternDirSep   = "/"
+)
+
+// Pattern defines a single gitignore pattern.
+type Pattern interface {
+	// Match matches the given path to the pattern.
+	Match(path []string, isDir bool) MatchResult
+}
+
+type pattern struct {
+	domain    []string
+	pattern   []string
+	inclusion bool
+	dirOnly   bool
+	isGlob    bool
+}
+
+// ParsePattern parses a gitignore pattern string into the Pattern structure.
+func ParsePattern(p string, domain []string) Pattern {
+	res := pattern{domain: domain}
+
+	if strings.HasPrefix(p, inclusionPrefix) {
+		res.inclusion = true
+		p = p[1:]
+	}
+
+	if !strings.HasSuffix(p, "\\ ") {
+		p = strings.TrimRight(p, " ")
+	}
+
+	if strings.HasSuffix(p, patternDirSep) {
+		res.dirOnly = true
+		p = p[:len(p)-1]
+	}
+
+	if strings.Contains(p, patternDirSep) {
+		res.isGlob = true
+	}
+
+	res.pattern = strings.Split(p, patternDirSep)
+	return &res
+}
+
+func (p *pattern) Match(path []string, isDir bool) MatchResult {
+	if len(path) <= len(p.domain) {
+		return NoMatch
+	}
+	for i, e := range p.domain {
+		if path[i] != e {
+			return NoMatch
+		}
+	}
+
+	path = path[len(p.domain):]
+	if p.isGlob && !p.globMatch(path, isDir) {
+		return NoMatch
+	} else if !p.isGlob && !p.simpleNameMatch(path, isDir) {
+		return NoMatch
+	}
+
+	if p.inclusion {
+		return Include
+	} else {
+		return Exclude
+	}
+}
+
+func (p *pattern) simpleNameMatch(path []string, isDir bool) bool {
+	for i, name := range path {
+		if match, err := filepath.Match(p.pattern[0], name); err != nil {
+			return false
+		} else if !match {
+			continue
+		}
+		if p.dirOnly && !isDir && i == len(path)-1 {
+			return false
+		}
+		return true
+	}
+	return false
+}
+
+func (p *pattern) globMatch(path []string, isDir bool) bool {
+	matched := false
+	canTraverse := false
+	for i, pattern := range p.pattern {
+		if pattern == "" {
+			canTraverse = false
+			continue
+		}
+		if pattern == zeroToManyDirs {
+			if i == len(p.pattern)-1 {
+				break
+			}
+			canTraverse = true
+			continue
+		}
+		if strings.Contains(pattern, zeroToManyDirs) {
+			return false
+		}
+		if len(path) == 0 {
+			return false
+		}
+		if canTraverse {
+			canTraverse = false
+			for len(path) > 0 {
+				e := path[0]
+				path = path[1:]
+				if match, err := filepath.Match(pattern, e); err != nil {
+					return false
+				} else if match {
+					matched = true
+					break
+				}
+			}
+		} else {
+			if match, err := filepath.Match(pattern, path[0]); err != nil || !match {
+				return false
+			}
+			matched = true
+			path = path[1:]
+		}
+	}
+	if matched && p.dirOnly && !isDir && len(path) == 0 {
+		matched = false
+	}
+	return matched
+}