Update feature added for headers command. (#181)

* Extend header functionality to update years.

* Updated readme, year logic in license command and added tests for headers update

* Preserve add Headers behaviour for header updates

* Minor Linting fix

* Fix git path resolution, LICENSE update logic, and pattern matching consistency

* Readme Updates

* Unexport internal copyright extraction and git helper functions

* Readme updates.

* Readme Formatting

* Year-2 update enhancements(File commit comparision to ignore header changes)

* Added test cases for calculateYearUpdates method

* Update builtin help commands.

* Decoupling update and walk logic for faster processing.

* accept unprefixed LICENSE copyright lines; error message on year updates in plan mode

* Update Readme file

Author: mohanmanikanta2299

README.md

@@ -3,8 +3,11 @@
 This repo provides utilities for managing copyright headers and license files
 across many repos at scale.
 
-You can use it to add or validate copyright headers on source code files, add a
-LICENSE file to a repo, report on what licenses repos are using, and more.
+Features:
+- Add or validate copyright headers on source code files
+- Add and/or manage LICENSE files with git-aware copyright year detection
+- Report on licenses used across multiple repositories
+- Automate compliance checks in CI/CD pipelines
 
 ## Getting Started
 
@@ -33,7 +36,7 @@ Usage:
   copywrite [command]
 
 Common Commands:
-  headers     Adds missing copyright headers to all source code files
+  headers     Adds missing copyright headers and updates existing headers' year information.
   init        Generates a .copywrite.hcl config for a new project
   license     Validates that a LICENSE file is present and remediates any issues if found
 
@@ -62,8 +65,18 @@ scan all files in your repo and copyright headers to any that are missing:
 copywrite headers --spdx "MPL-2.0"
 ```
 
-You may omit the `--spdx` flag if you add a `.copywrite.hcl` config, as outlined
-[here](#config-structure).
+The `copywrite license` command validates and manages LICENSE files with git-aware copyright years:
+
+```sh
+copywrite license --spdx "MPL-2.0"
+```
+
+**Copyright Year Behavior:**
+- **Start Year**: Auto-detected from config file and if not found defaults to repository's first commit
+- **End Year**: Set to current year when an update is triggered (git history only determines if update is needed)
+- **Update Trigger**: Git detects if source code file was modified since the copyright end year
+
+You may omit the `--spdx` flag if you add a `.copywrite.hcl` config, as outlined [here](#config-structure).
 
 ### `--plan` Flag
 
@@ -72,6 +85,24 @@ performs a dry-run and will outline what changes would be made. This flag also
 returns a non-zero exit code if any changes are needed. As such, it can be used
 to validate if a repo is in compliance or not.
 
+## Technical Details
+
+### Copyright Year Logic
+
+**Source File Headers:**
+- End year: Set to current year when file's source code is modified
+- Git history determines if update is needed (compares file's last commit year to copyright end year)
+- When triggered, end year updates to current year
+- Ignores copyright header updates made to a file as it is not source code change.
+
+**LICENSE Files:**
+- End year: Set to current year when any project file is modified
+- Git history determines if update is needed (compares repo's last commit year to copyright end year)
+- When triggered, end year updates to current year
+- Preserves historical accuracy for archived projects (no forced updates)
+
+**Key Distinction:** Git history is used as a trigger to determine *whether* an update is needed, but the actual end year value is always set to the current year when an update occurs.
+
 ## Config Structure
 
 > :bulb: You can automatically generate a new `.copywrite.hcl` config with the
@@ -99,8 +130,8 @@ project {
 
   # (OPTIONAL) Represents the year that the project initially began
   # This is used as the starting year in copyright statements
-  # If set and different from current year, headers will show: "copyright_year, current_year"
-  # If set and same as current year, headers will show: "current_year"
+  # If set and different from current year, headers will show: "copyright_year, year-2"
+  # If set and same as year-2, headers will show: "copyright_year"
   # If not set (0), the tool will auto-detect from git history (first commit year)
   # If auto-detection fails, it will fallback to current year only
   # Default: 0 (auto-detect)

addlicense/main.go

@@ -280,7 +280,7 @@ func walk(ch chan<- *file, start string, logger *log.Logger) error {
 		if fi.IsDir() {
 			return nil
 		}
-		if fileMatches(path, ignorePatterns) {
+		if FileMatches(path, ignorePatterns) {
 			// The [DEBUG] level is inferred by go-hclog as a debug statement
 			logger.Printf("[DEBUG] skipping: %s", path)
 			return nil
@@ -290,9 +290,9 @@ func walk(ch chan<- *file, start string, logger *log.Logger) error {
 	})
 }
 
-// fileMatches determines if path matches one of the provided file patterns.
+// FileMatches determines if path matches one of the provided file patterns.
 // Patterns are assumed to be valid.
-func fileMatches(path string, patterns []string) bool {
+func FileMatches(path string, patterns []string) bool {
 	for _, p := range patterns {
 
 		if runtime.GOOS == "windows" {

addlicense/main_test.go

@@ -471,7 +471,7 @@ func TestFileMatches(t *testing.T) {
 
 	for _, tt := range tests {
 		patterns := []string{tt.pattern}
-		if got := fileMatches(tt.path, patterns); got != tt.wantMatch {
+		if got := FileMatches(tt.path, patterns); got != tt.wantMatch {
 			t.Errorf("fileMatches(%q, %q) returned %v, want %v", tt.path, patterns, got, tt.wantMatch)
 		}
 	}

cmd/headers.go

@@ -6,8 +6,14 @@ package cmd
 import (
 	"fmt"
 	"os"
+	"path/filepath"
+	"runtime"
+	"strings"
+	"sync"
+	"sync/atomic"
 
 	"github.com/hashicorp/copywrite/addlicense"
+	"github.com/hashicorp/copywrite/licensecheck"
 	"github.com/hashicorp/go-hclog"
 	"github.com/jedib0t/go-pretty/v6/text"
 	"github.com/samber/lo"
@@ -21,9 +27,13 @@ var (
 
 var headersCmd = &cobra.Command{
 	Use:   "headers",
-	Short: "Adds missing copyright headers to all source code files",
+	Short: "Adds missing copyright headers and updates existing headers' year information in all source code files",
 	Long: `Recursively checks for all files in the given directory and subdirectories,
-adding copyright statements and license headers to any that are missing them.
+adding copyright statements and license headers to any that are missing them and
+updating the year information in existing headers based on git history.
+
+By default, the command will modify files in place. To perform a dry-run without
+modifying any files, use the --plan flag.
 
 Autogenerated files and common file types that don't support headers (e.g., prose)
 will automatically be exempted. Any other files or folders should be added to the
@@ -87,10 +97,23 @@ config, see the "copywrite init" command.`,
 			".github/workflows/**",
 			".github/dependabot.yml",
 			"**/node_modules/**",
+			".copywrite.hcl",
 		}
 		ignoredPatterns := lo.Union(conf.Project.HeaderIgnore, autoSkippedPatterns)
 
-		// Construct the configuration addLicense needs to properly format headers
+		// STEP 1: Update existing copyright headers
+		gha.StartGroup("Updating existing copyright headers:")
+		updatedCount, anyFileUpdated, licensePath := updateExistingHeaders(cmd, ignoredPatterns, plan)
+		gha.EndGroup()
+		if updatedCount > 0 {
+			if plan {
+				cmd.Printf("\n%s\n\n", text.FgYellow.Sprintf("[DRY RUN] Would update %d file(s) with new copyright years", updatedCount))
+			} else {
+				cmd.Printf("\n%s\n\n", text.FgGreen.Sprintf("Successfully updated %d file(s) with new copyright years", updatedCount))
+			}
+		}
+
+		// STEP 2: Construct the configuration addLicense needs to properly format headers
 		licenseData := addlicense.LicenseData{
 			Year:   conf.FormatCopyrightYears(), // Format year(s) for copyright statements
 			Holder: conf.Project.CopyrightHolder,
@@ -112,10 +135,33 @@ config, see the "copywrite init" command.`,
 		// cobra.CheckErr on the return, which will indeed output to stderr and
 		// return a non-zero error code.
 
-		gha.StartGroup("The following files are missing headers:")
-		err := addlicense.Run(ignoredPatterns, "only", licenseData, "", verbose, plan, []string{"."}, stdcliLogger)
+		// STEP 3: Add missing headers
+		gha.StartGroup("Adding missing copyright headers:")
+		var err error
+		// In dry-run mode, if updateExistingHeaders found files that would be
+		// updated (year bumps), treat that as an error so the command exits
+		// non-zero to indicate work would be performed.
+		if plan && updatedCount > 0 {
+			err = fmt.Errorf("[DRY RUN] %d file(s) would be updated with new copyright years", updatedCount)
+		}
+		runErr := addlicense.Run(ignoredPatterns, "only", licenseData, "", verbose, plan, []string{"."}, stdcliLogger)
+		if err != nil && runErr != nil {
+			err = fmt.Errorf("%v; %v", err, runErr)
+		} else if err == nil {
+			err = runErr
+		}
 		gha.EndGroup()
 
+		// STEP 4: Update LICENSE file if any files were modified (either updated or added headers)
+		// In plan mode: if addlicense found missing headers (returns error), assume files would be modified
+		// In normal mode: if addlicense succeeded, assume files were modified
+		if runErr != nil || (!plan && runErr == nil) {
+			anyFileUpdated = true
+		}
+
+		updateLicenseFile(cmd, licensePath, anyFileUpdated, plan)
+
+		// Check for errors after LICENSE file update so we still show what would happen
 		cobra.CheckErr(err)
 	},
 }
@@ -131,3 +177,125 @@ func init() {
 	headersCmd.Flags().StringP("spdx", "s", "", "SPDX-compliant license identifier (e.g., 'MPL-2.0')")
 	headersCmd.Flags().StringP("copyright-holder", "c", "", "Copyright holder (default \"IBM Corp.\")")
 }
+
+// updateExistingHeaders walks through files and updates copyright headers based on config and git history
+// Returns the count of updated files, a boolean indicating if any file was updated, and the LICENSE file path (if found)
+func updateExistingHeaders(cmd *cobra.Command, ignoredPatterns []string, dryRun bool) (int, bool, string) {
+	targetHolder := conf.Project.CopyrightHolder
+	if targetHolder == "" {
+		targetHolder = "IBM Corp."
+	}
+
+	configYear := conf.Project.CopyrightYear
+	updatedCount := 0
+	anyFileUpdated := false
+	var licensePath string
+
+	// Producer/consumer: walk files (producer) and process them with a bounded
+	// worker pool (consumers). This preserves existing semantics while
+	// bounding concurrency and allowing the walk to run ahead of processors.
+	ch := make(chan string, 1000)
+
+	var wg sync.WaitGroup
+	var updatedCount64 int64
+	var anyFileUpdatedFlag int32
+	var mu sync.Mutex
+
+	workers := runtime.NumCPU() * 4
+	if workers < 2 {
+		workers = 2
+	}
+
+	// Start worker pool
+	wg.Add(workers)
+	for i := 0; i < workers; i++ {
+		go func() {
+			defer wg.Done()
+			for path := range ch {
+				// capture base and skip LICENSE files here as well
+				base := filepath.Base(path)
+				if strings.EqualFold(base, "LICENSE") || strings.EqualFold(base, "LICENSE.TXT") || strings.EqualFold(base, "LICENSE.MD") {
+					mu.Lock()
+					if licensePath == "" {
+						licensePath = path
+					}
+					mu.Unlock()
+					continue
+				}
+
+				if !dryRun {
+					updated, err := licensecheck.UpdateCopyrightHeader(path, targetHolder, configYear, false)
+					if err == nil && updated {
+						cmd.Printf("  %s\n", path)
+						atomic.AddInt64(&updatedCount64, 1)
+						atomic.StoreInt32(&anyFileUpdatedFlag, 1)
+					}
+				} else {
+					needsUpdate, err := licensecheck.NeedsUpdate(path, targetHolder, configYear, false)
+					if err == nil && needsUpdate {
+						cmd.Printf("  %s\n", path)
+						atomic.AddInt64(&updatedCount64, 1)
+						atomic.StoreInt32(&anyFileUpdatedFlag, 1)
+					}
+				}
+			}
+		}()
+	}
+
+	// Producer: walk the tree and push files onto the channel
+	go func() {
+		_ = filepath.Walk(".", func(path string, info os.FileInfo, err error) error {
+			if err != nil || info.IsDir() {
+				return nil
+			}
+
+			// Check if file should be ignored
+			if addlicense.FileMatches(path, ignoredPatterns) {
+				return nil
+			}
+
+			// Non-ignored file -> enqueue for processing. If channel is full,
+			// this will block until a worker consumes entries, which is fine.
+			ch <- path
+			return nil
+		})
+		close(ch)
+	}()
+
+	// wait for workers to finish
+	wg.Wait()
+
+	// finalize counts
+	updatedCount = int(atomic.LoadInt64(&updatedCount64))
+	anyFileUpdated = atomic.LoadInt32(&anyFileUpdatedFlag) != 0
+
+	return updatedCount, anyFileUpdated, licensePath
+}
+
+// updateLicenseFile updates the LICENSE file with current year if any files were modified
+func updateLicenseFile(cmd *cobra.Command, licensePath string, anyFileUpdated bool, dryRun bool) {
+	// If no LICENSE file was found during the walk, nothing to do
+	if licensePath == "" {
+		return
+	}
+
+	targetHolder := conf.Project.CopyrightHolder
+	if targetHolder == "" {
+		targetHolder = "IBM Corp."
+	}
+
+	configYear := conf.Project.CopyrightYear
+
+	// Update LICENSE file, forcing current year if any file was updated
+	if !dryRun {
+		updated, err := licensecheck.UpdateCopyrightHeader(licensePath, targetHolder, configYear, anyFileUpdated)
+		if err == nil && updated {
+			cmd.Printf("\nUpdated LICENSE file: %s\n", licensePath)
+		}
+	} else {
+		needsUpdate, err := licensecheck.NeedsUpdate(licensePath, targetHolder, configYear, anyFileUpdated)
+		if err == nil && needsUpdate {
+			cmd.Printf("\n[DRY RUN] Would update LICENSE file: %s\n", licensePath)
+		}
+	}
+}

cmd/license.go

@@ -7,6 +7,8 @@ import (
 	"errors"
 	"fmt"
 	"path/filepath"
+	"strconv"
+	"time"
 
 	"github.com/hashicorp/copywrite/github"
 	"github.com/hashicorp/copywrite/licensecheck"
@@ -63,10 +65,14 @@ var licenseCmd = &cobra.Command{
 	Run: func(cmd *cobra.Command, args []string) {
 
 		cmd.Printf("Licensing under the following terms: %s\n", conf.Project.License)
-		cmd.Printf("Using copyright years: %v\n", conf.FormatCopyrightYears())
+
+		// Determine appropriate copyright years for LICENSE file
+		licenseYears := determineLicenseCopyrightYears(dirPath)
+
+		cmd.Printf("Using copyright years: %v\n", licenseYears)
 		cmd.Printf("Using copyright holder: %v\n\n", conf.Project.CopyrightHolder)
 
-		copyright := "Copyright " + conf.FormatCopyrightYears() + " " + conf.Project.CopyrightHolder
+		copyright := "Copyright " + conf.Project.CopyrightHolder + " " + licenseYears
 
 		licenseFiles, err := licensecheck.FindLicenseFiles(dirPath)
 		if err != nil {
@@ -175,3 +181,34 @@ func init() {
 	licenseCmd.Flags().StringP("spdx", "s", "", "SPDX License Identifier indicating what the LICENSE file should represent")
 	licenseCmd.Flags().StringP("copyright-holder", "c", "", "Copyright holder (default \"IBM Corp.\")")
 }
+
+// determineLicenseCopyrightYears determines the appropriate copyright year range for LICENSE file
+// Uses git history to get the start year (first commit) and end year (last commit)
+func determineLicenseCopyrightYears(dirPath string) string {
+	currentYear := time.Now().Year()
+	startYear := conf.Project.CopyrightYear
+
+	// If no start year configured, try to auto-detect from git
+	if startYear == 0 {
+		if detectedYear, err := licensecheck.GetRepoFirstCommitYear(dirPath); err == nil && detectedYear > 0 {
+			startYear = detectedYear
+		} else {
+			// Fallback to current year
+			return strconv.Itoa(currentYear)
+		}
+	}
+
+	// Determine end year from repository's last commit year
+	endYear := currentYear // Default fallback
+	if lastRepoCommitYear, err := licensecheck.GetRepoLastCommitYear(dirPath); err == nil && lastRepoCommitYear > 0 && lastRepoCommitYear <= currentYear {
+		endYear = lastRepoCommitYear
+	}
+
+	// If start year equals end year, return single year
+	if startYear == endYear {
+		return strconv.Itoa(endYear)
+	}
+
+	// Return year range: "startYear, endYear"
+	return fmt.Sprintf("%d, %d", startYear, endYear)
+}