pkg/fileutils: escape additional regex meta characters

milas · milas · commit 195558de5aba · 2021-10-22T11:31:11.000-04:00
There were a couple characters being explicitly escaped, but it
wasn't comprehensive.

This is now the set difference between the Golang regex meta
characters and the `filepath` match meta characters with the
exception of `\`, which already has special logic due to being
the path separator on Windows.

Signed-off-by: Milas Bowman &lt;milasb@gmail.com&gt;
diff --git a/pkg/fileutils/fileutils.go b/pkg/fileutils/fileutils.go
@@ -9,8 +9,30 @@ import (
 	"regexp"
 	"strings"
 	"text/scanner"
+	"unicode/utf8"
 )
 
+// escapeBytes is a bitmap used to check whether a character should be escaped when creating the regex.
+var escapeBytes [8]byte
+
+// shouldEscape reports whether a rune should be escaped as part of the regex.
+//
+// This only includes characters that require escaping in regex but are also NOT valid filepath pattern characters.
+// Additionally, '\' is not excluded because there is specific logic to properly handle this, as it's a path separator
+// on Windows.
+//
+// Adapted from regexp::QuoteMeta in go stdlib.
+// See https://cs.opensource.google/go/go/+/refs/tags/go1.17.2:src/regexp/regexp.go;l=703-715;drc=refs%2Ftags%2Fgo1.17.2
+func shouldEscape(b rune) bool {
+	return b < utf8.RuneSelf && escapeBytes[b%8]&(1<<(b/8)) != 0
+}
+
+func init() {
+	for _, b := range []byte(`.+()|{}$`) {
+		escapeBytes[b%8] |= 1 << (b / 8)
+	}
+}
+
 // PatternMatcher allows checking paths against a list of patterns
 type PatternMatcher struct {
 	patterns   []*Pattern
@@ -256,7 +278,7 @@ func (p *Pattern) compile() error {
 		} else if ch == '?' {
 			// "?" is any char except "/"
 			regStr += "[^" + escSL + "]"
-		} else if ch == '.' || ch == '$' {
+		} else if shouldEscape(ch) {
 			// Escape some regexp special chars that have no meaning
 			// in golang's filepath.Match
 			regStr += `\` + string(ch)
diff --git a/pkg/fileutils/fileutils_test.go b/pkg/fileutils/fileutils_test.go
@@ -373,6 +373,9 @@ func TestMatches(t *testing.T) {
 		{"abc/**", "abc/def/ghi", true},
 		{"**/.foo", ".foo", true},
 		{"**/.foo", "bar.foo", false},
+		{"a(b)c/def", "a(b)c/def", true},
+		{"a(b)c/def", "a(b)c/xyz", false},
+		{"a.|)$(}+{bc", "a.|)$(}+{bc", true},
 	}
 
 	if runtime.GOOS != "windows" {

Original file line number	Diff line number	Diff line change
`@@ -373,6 +373,9 @@ func TestMatches(t *testing.T) {`
`373`	`373`	`{"abc/**", "abc/def/ghi", true},`
`374`	`374`	`{"**/.foo", ".foo", true},`
`375`	`375`	`{"**/.foo", "bar.foo", false},`
	`376`	`+ {"a(b)c/def", "a(b)c/def", true},`
	`377`	`+ {"a(b)c/def", "a(b)c/xyz", false},`
	`378`	`+ {"a.\|)$(}+{bc", "a.\|)$(}+{bc", true},`
`376`	`379`	`}`
`377`	`380`
`378`	`381`	`if runtime.GOOS != "windows" {`