Merge pull request #18 from jhaynie/master

Proposed changes to support API

processor/processor.go

@@ -4,10 +4,10 @@ import (
 	"encoding/base64"
 	"encoding/json"
 	"fmt"
-	"runtime"
-	"strings"
 	"io/ioutil"
+	"runtime"
 	"sort"
+	"strings"
 )
 
 // Flags set via the CLI which control how the output is displayed
@@ -39,9 +39,9 @@ var DirFilePaths = []string{}
 var ExtensionToLanguage = map[string]string{}
 var LanguageFeatures = map[string]LanguageFeature{}
 
-// Responsible for setting up the language features based on the JSON file that is stored in constants
+// ProcessConstants is responsible for setting up the language features based on the JSON file that is stored in constants
 // Needs to be called at least once in order for anything to actually happen
-func processConstants() {
+func ProcessConstants() {
 	var database = loadDatabase()
 
 	startTime := makeTimestampNano()
@@ -121,7 +121,6 @@ func processFlags() {
 	}
 }
 
-
 func loadDatabase() map[string]Language {
 	var database map[string]Language
 	startTime := makeTimestampMilli()
@@ -165,7 +164,7 @@ func Process() {
 		return
 	}
 
-	processConstants()
+	ProcessConstants()
 	processFlags()
 
 	// Clean up any invalid arguments before setting everything up

processor/processor_test.go

@@ -5,7 +5,7 @@ import (
 )
 
 func TestProcessConstants(t *testing.T) {
-	processConstants()
+	ProcessConstants()
 
 	if len(ExtensionToLanguage) == 0 {
 		t.Error("Should not be 0")

processor/structs.go

@@ -21,6 +21,12 @@ type LanguageFeature struct {
 	StringChecks      []OpenClose
 }
 
+// FileJobCallback is an interface that FileJobs can implement to get a per line callback with the line type
+type FileJobCallback interface {
+	// ProcessLine should return true to continue processing or false to stop further processing and return
+	ProcessLine(job *FileJob, currentLine int64, lineType LineType) bool
+}
+
 type FileJob struct {
 	Language           string
 	Filename           string
@@ -35,6 +41,7 @@ type FileJob struct {
 	Complexity         int64
 	WeightedComplexity float64
 	Hash               []byte
+	Callback           FileJobCallback
 }
 
 type LanguageSummary struct {

processor/workers.go

@@ -18,6 +18,14 @@ const (
 	S_STRING             int64 = 8
 )
 
+type LineType int32
+
+const (
+	LINE_BLANK LineType = iota
+	LINE_CODE
+	LINE_COMMENT
+)
+
 func checkForMatch(currentByte byte, index int, endPoint int, matches [][]byte, fileJob *FileJob) bool {
 	potentialMatch := true
 	for i := 0; i < len(matches); i++ {
@@ -166,11 +174,12 @@ func isWhitespace(currentByte byte) bool {
 	return true
 }
 
+// CountStats will process the fileJob
 // If the file contains anything even just a newline its line count should be >= 1.
 // If the file has a size of 0 its line count should be 0.
 // Newlines belong to the line they started on so a file of \n means only 1 line
 // This is the 'hot' path for the application and needs to be as fast as possible
-func countStats(fileJob *FileJob) {
+func CountStats(fileJob *FileJob) {
 
 	// If the file has a length of 0 it is is empty then we say it has no lines
 	fileJob.Bytes = int64(len(fileJob.Content))
@@ -304,11 +313,32 @@ func countStats(fileJob *FileJob) {
 
 			switch {
 			case currentState == S_BLANK:
-				fileJob.Blank++
+				{
+					if fileJob.Callback != nil {
+						if !fileJob.Callback.ProcessLine(fileJob, fileJob.Lines, LINE_BLANK) {
+							return
+						}
+					}
+					fileJob.Blank++
+				}
 			case currentState == S_CODE || currentState == S_STRING || currentState == S_COMMENT_CODE || currentState == S_MULTICOMMENT_CODE:
-				fileJob.Code++
+				{
+					if fileJob.Callback != nil {
+						if !fileJob.Callback.ProcessLine(fileJob, fileJob.Lines, LINE_CODE) {
+							return
+						}
+					}
+					fileJob.Code++
+				}
 			case currentState == S_COMMENT || currentState == S_MULTICOMMENT || currentState == S_MULTICOMMENT_BLANK:
-				fileJob.Comment++
+				{
+					if fileJob.Callback != nil {
+						if !fileJob.Callback.ProcessLine(fileJob, fileJob.Lines, LINE_COMMENT) {
+							return
+						}
+					}
+					fileJob.Comment++
+				}
 			}
 
 			// If we are in a multiline comment that started after some code then we need
@@ -384,7 +414,7 @@ func fileProcessorWorker(input *chan *FileJob, output *chan *FileJob) {
 		wg.Add(1)
 		go func(res *FileJob) {
 			fileStartTime := makeTimestampNano()
-			countStats(res)
+			CountStats(res)
 
 			if Duplicates {
 				if duplicates.Check(res.Bytes, res.Hash) {