From f3804fcd2d6360ce5759615410c82e0eeae6e6cd Mon Sep 17 00:00:00 2001
From: Luke Hagar <lukeslakemail@gmail.com>
Date: Thu, 11 Sep 2025 21:02:14 +0000
Subject: [PATCH] Add respect_gitignore input to action.yml and update related
 logic in entrypoint.sh, check.go, and fsurls.go to support .gitignore
 handling during URL collection.

---
 action.yml                |  5 +++++
 cmd/check.go              | 12 +++++++-----
 entrypoint.sh             |  6 ++++++
 internal/fsurls/fsurls.go |  6 +++---
 4 files changed, 21 insertions(+), 8 deletions(-)

diff --git a/action.yml b/action.yml
index b4a9315..344ebe2 100644
--- a/action.yml
+++ b/action.yml
@@ -22,6 +22,10 @@ inputs:
     description: "HTTP timeout seconds"
     required: false
     default: "10"
+  respect_gitignore:
+    description: "Respect .gitignore while scanning"
+    required: false
+    default: "true"
   json_out:
     description: "Optional path to write JSON results"
     required: false
@@ -56,6 +60,7 @@ runs:
     INPUT_PATTERNS: ${{ inputs.patterns }}
     INPUT_CONCURRENCY: ${{ inputs.concurrency }}
     INPUT_TIMEOUT: ${{ inputs.timeout }}
+    INPUT_RESPECT_GITIGNORE: ${{ inputs.respect_gitignore }}
     INPUT_JSON_OUT: ${{ inputs.json_out }}
     INPUT_MD_OUT: ${{ inputs.md_out }}
     INPUT_REPO_BLOB_BASE: ${{ inputs.repo_blob_base }}
diff --git a/cmd/check.go b/cmd/check.go
index 93292ac..35a3989 100644
--- a/cmd/check.go
+++ b/cmd/check.go
@@ -51,7 +51,7 @@ func init() {
 			cfg := web.Config{MaxConcurrency: maxConcurrency, RequestTimeout: timeout}
 
 			// Collect URLs
-			urlToFiles, err := fsurls.CollectURLs(path, gl)
+			urlToFiles, err := fsurls.CollectURLs(path, gl, respectGitignore)
 			if err != nil {
 				return err
 			}
@@ -157,13 +157,15 @@ func init() {
 	checkCmd.Flags().StringVar(&repoBlobBase, "repo-blob-base", "", "override GitHub blob base URL (e.g. https://github.com/owner/repo/blob/<sha>)")
 	checkCmd.Flags().IntVar(&timeoutSeconds, "timeout", 10, "HTTP request timeout in seconds")
 	checkCmd.Flags().BoolVar(&failOnFailures, "fail-on-failures", true, "exit non-zero if any links fail")
+	checkCmd.Flags().BoolVar(&respectGitignore, "respect-gitignore", true, "respect .gitignore while scanning (default true)")
 
 	rootCmd.AddCommand(checkCmd)
 }
 
 var (
-	timeoutSeconds int
-	failOnFailures bool
-	patterns       []string
-	repoBlobBase   string
+	timeoutSeconds   int
+	failOnFailures   bool
+	patterns         []string
+	repoBlobBase     string
+	respectGitignore bool
 )
diff --git a/entrypoint.sh b/entrypoint.sh
index 4c0cbba..224ff16 100644
--- a/entrypoint.sh
+++ b/entrypoint.sh
@@ -5,6 +5,7 @@ PATH_ARG="${INPUT_PATH:-.}"
 PATTERNS_ARG="${INPUT_PATTERNS:-**/*}"
 CONCURRENCY_ARG="${INPUT_CONCURRENCY:-16}"
 TIMEOUT_ARG="${INPUT_TIMEOUT:-10}"
+RESPECT_GITIGNORE_ARG="${INPUT_RESPECT_GITIGNORE:-true}"
 JSON_OUT_ARG="${INPUT_JSON_OUT:-results.json}"
 MD_OUT_ARG="${INPUT_MD_OUT:-results.md}"
 REPO_BLOB_BASE_ARG="${INPUT_REPO_BLOB_BASE:-}"
@@ -35,6 +36,11 @@ fi
 if [ -n "${MD_OUT_ARG}" ]; then
   set -- "$@" --md-out "$MD_OUT_ARG"
 fi
+if [ "${RESPECT_GITIGNORE_ARG}" = "true" ]; then
+  set -- "$@" --respect-gitignore=true
+else
+  set -- "$@" --respect-gitignore=false
+fi
 
 # Compute GitHub blob base URL for file links used in the Markdown report
 if [ -n "${REPO_BLOB_BASE_ARG}" ]; then
diff --git a/internal/fsurls/fsurls.go b/internal/fsurls/fsurls.go
index 2343970..132869f 100644
--- a/internal/fsurls/fsurls.go
+++ b/internal/fsurls/fsurls.go
@@ -28,9 +28,9 @@ var hostnameRegex = regexp.MustCompile(`^(?i)([a-z0-9](?:[a-z0-9-]{0,61}[a-z0-9]
 
 // CollectURLs walks the directory tree rooted at rootPath and collects URLs found in
 // text-based files matching any of the provided glob patterns (doublestar ** supported).
-// If globs is empty, all files are considered. Respects .gitignore if present.
+// If globs is empty, all files are considered. Respects .gitignore if present and respectGitignore=true.
 // Returns a map from URL -> sorted unique list of file paths that contained it.
-func CollectURLs(rootPath string, globs []string) (map[string][]string, error) {
+func CollectURLs(rootPath string, globs []string, respectGitignore bool) (map[string][]string, error) {
 	if strings.TrimSpace(rootPath) == "" {
 		rootPath = "."
 	}
@@ -39,7 +39,7 @@ func CollectURLs(rootPath string, globs []string) (map[string][]string, error) {
 	st, _ := os.Stat(cleanRoot)
 	isFileRoot := st != nil && !st.IsDir()
 	var ign *ignore.GitIgnore
-	if !isFileRoot {
+	if !isFileRoot && respectGitignore {
 		ign = loadGitIgnore(cleanRoot)
 	}