✨ Add go grep package to replace OS-specific grep commands for builtin provider

go.mod

@@ -7,6 +7,7 @@ require (
 	github.com/antchfx/jsonquery v1.3.0
 	github.com/antchfx/xmlquery v1.3.12
 	github.com/bombsimon/logrusr/v3 v3.0.0
+	github.com/dlclark/regexp2 v1.11.4
 	github.com/go-logr/logr v1.2.3
 	github.com/golang-jwt/jwt/v5 v5.2.1
 	github.com/jhump/protoreflect v1.16.0
@@ -18,6 +19,7 @@ require (
 	go.lsp.dev/uri v0.3.0
 	go.opentelemetry.io/otel/trace v1.11.2
 	golang.org/x/oauth2 v0.16.0
+	golang.org/x/sync v0.6.0
 	google.golang.org/grpc v1.62.1
 	google.golang.org/protobuf v1.33.1-0.20240408130810-98873a205002
 	gopkg.in/yaml.v2 v2.4.0

go.sum

@@ -27,6 +27,8 @@ github.com/cpuguy83/go-md2man/v2 v2.0.2/go.mod h1:tgQtvFlXSQOSOSIRvRPT7W67SCa46t
 github.com/davecgh/go-spew v1.1.0/go.mod h1:J7Y8YcW2NihsgmVo/mv3lAwl/skON4iLHjSsI+c5H38=
 github.com/davecgh/go-spew v1.1.1 h1:vj9j/u1bqnvCEfJOwUhtlOARqs3+rkHYY13jYWTU97c=
 github.com/davecgh/go-spew v1.1.1/go.mod h1:J7Y8YcW2NihsgmVo/mv3lAwl/skON4iLHjSsI+c5H38=
+github.com/dlclark/regexp2 v1.11.4 h1:rPYF9/LECdNymJufQKmri9gV604RvvABwgOA8un7yAo=
+github.com/dlclark/regexp2 v1.11.4/go.mod h1:DHkYz0B9wPfa6wondMfaivmHpzrQ3v9q8cnmRbL6yW8=
 github.com/go-logr/logr v1.2.2/go.mod h1:jdQByPbusPIv2/zmleS9BjJVeZ6kBagPoEUsqbVz/1A=
 github.com/go-logr/logr v1.2.3 h1:2DntVwHkVopvECVRSlL5PSo9eG+cAkDCuckLubN+rq0=
 github.com/go-logr/logr v1.2.3/go.mod h1:jdQByPbusPIv2/zmleS9BjJVeZ6kBagPoEUsqbVz/1A=

provider/internal/builtin/service_client.go

@@ -1,24 +1,26 @@
 package builtin
 
 import (
+	"bufio"
 	"context"
 	"fmt"
 	"io/fs"
 	"os"
-	"os/exec"
 	"path/filepath"
 	"regexp"
-	"strconv"
 	"strings"
 	"sync"
 
 	"github.com/antchfx/jsonquery"
 	"github.com/antchfx/xmlquery"
 	"github.com/antchfx/xpath"
+	"github.com/dlclark/regexp2"
 	"github.com/go-logr/logr"
+	"github.com/konveyor/analyzer-lsp/lsp/protocol"
 	"github.com/konveyor/analyzer-lsp/provider"
 	"github.com/konveyor/analyzer-lsp/tracing"
 	"go.lsp.dev/uri"
+	"golang.org/x/sync/errgroup"
 	"gopkg.in/yaml.v2"
 )
 
@@ -83,58 +85,32 @@ func (p *builtinServiceClient) Evaluate(ctx context.Context, cap string, conditi
 		if c.Pattern == "" {
 			return response, fmt.Errorf("could not parse provided regex pattern as string: %v", conditionInfo)
 		}
-		var outputBytes []byte
-		grep := exec.Command("grep", "-o", "-n", "-R", "-P", c.Pattern, p.config.Location)
-		outputBytes, err := grep.Output()
+
+		patternRegex, err := regexp2.Compile(c.Pattern, regexp2.None)
 		if err != nil {
-			if exitError, ok := err.(*exec.ExitError); ok && exitError.ExitCode() == 1 {
-				return response, nil
-			}
-			return response, fmt.Errorf("could not run grep with provided pattern %+v", err)
+			return response, fmt.Errorf("could not compile provided regex pattern '%s': %v", c.Pattern, err)
 		}
 
-		matches := []string{}
-		outputString := strings.TrimSpace(string(outputBytes))
-		if outputString != "" {
-			matches = append(matches, strings.Split(outputString, "\n")...)
+		matches, err := parallelWalk(p.config.Location, patternRegex)
+		if err != nil {
+			return response, err
 		}
 
 		for _, match := range matches {
-			//TODO(fabianvf): This will not work if there is a `:` in the filename, do we care?
-			pieces := strings.SplitN(match, ":", 3)
-			if len(pieces) != 3 {
-				//TODO(fabianvf): Just log or return?
-				//(shawn-hurley): I think the return is good personally
-				return response, fmt.Errorf(
-					"malformed response from grep, cannot parse grep output '%s' with pattern {filepath}:{lineNumber}:{matchingText}", match)
-			}
-
-			containsFile, err := provider.FilterFilePattern(c.FilePattern, pieces[0])
+			containsFile, err := provider.FilterFilePattern(c.FilePattern, match.positionParams.TextDocument.URI)
 			if err != nil {
 				return response, err
 			}
 			if !containsFile {
 				continue
 			}
+			lineNumber := int(match.positionParams.Position.Line)
 
-			absPath, err := filepath.Abs(pieces[0])
-			if err != nil {
-				absPath = pieces[0]
-			}
-
-			if !p.isFileIncluded(absPath) {
-				continue
-			}
-
-			lineNumber, err := strconv.Atoi(pieces[1])
-			if err != nil {
-				return response, fmt.Errorf("cannot convert line number string to integer")
-			}
 			response.Incidents = append(response.Incidents, provider.IncidentContext{
-				FileURI:    uri.File(absPath),
+				FileURI:    uri.URI(match.positionParams.TextDocument.URI),
 				LineNumber: &lineNumber,
 				Variables: map[string]interface{}{
-					"matchingText": pieces[2],
+					"matchingText": match.match,
 				},
 				CodeLocation: &provider.Location{
 					StartPosition: provider.Position{Line: float64(lineNumber)},
@@ -497,3 +473,91 @@ func (b *builtinServiceClient) isFileIncluded(absolutePath string) bool {
 	b.log.V(7).Info("excluding file from search", "file", absolutePath)
 	return false
 }
+
+type walkResult struct {
+	positionParams protocol.TextDocumentPositionParams
+	match          string
+}
+
+func parallelWalk(location string, regex *regexp2.Regexp) ([]walkResult, error) {
+	var positions []walkResult
+	var positionsMu sync.Mutex
+	var eg errgroup.Group
+
+	err := filepath.Walk(location, func(path string, f os.FileInfo, err error) error {
+		if err != nil {
+			return err
+		}
+
+		if f.Mode().IsRegular() {
+			eg.Go(func() error {
+				pos, err := processFile(path, regex)
+				if err != nil {
+					return err
+				}
+
+				positionsMu.Lock()
+				defer positionsMu.Unlock()
+				positions = append(positions, pos...)
+				return nil
+			})
+		}
+
+		return nil
+	})
+	if err != nil {
+		return nil, err
+	}
+
+	if err := eg.Wait(); err != nil {
+		return nil, err
+	}
+
+	return positions, nil
+}
+
+func processFile(path string, regex *regexp2.Regexp) ([]walkResult, error) {
+	f, err := os.Open(path)
+	if err != nil {
+		return nil, err
+	}
+	defer f.Close()
+
+	var r []walkResult
+
+	scanner := bufio.NewScanner(f)
+	lineNumber := 1
+	for scanner.Scan() {
+		line := scanner.Text()
+		match, err := regex.FindStringMatch(line)
+		if err != nil {
+			return nil, err
+		}
+		for match != nil {
+			absPath, err := filepath.Abs(path)
+			if err != nil {
+				return nil, err
+			}
+
+			r = append(r, walkResult{
+				positionParams: protocol.TextDocumentPositionParams{
+					TextDocument: protocol.TextDocumentIdentifier{
+						URI: fmt.Sprintf("file:///%s", filepath.ToSlash(absPath)),
+					},
+					Position: protocol.Position{
+						Line:      uint32(lineNumber),
+						Character: uint32(match.Index),
+					},
+				},
+				match: match.String(),
+			})
+			match, err = regex.FindNextMatch(match)
+			if err != nil {
+				return nil, err
+			}
+		}
+		lineNumber++
+	}
+
+	return r, nil
+}