Fix smart filtering to include valuable source files (Issue #12)

packages/content-loader/src/__tests__/git-repo-loader.test.ts

@@ -181,7 +181,7 @@ describe("Git Repository Loading - User Workflows", () => {
         "docs/getting-started.md",
         "docs/api/authentication.md",
         "guides/tutorial.rst",
-        "src/index.js", // Should be excluded
+        "src/index.js", // Should be excluded (source file)
         "package.json", // Should be excluded
         "CHANGELOG.md", // Should be excluded (project metadata)
         "LICENSE", // Should be excluded (project metadata)
@@ -249,6 +249,7 @@ describe("Git Repository Loading - User Workflows", () => {
         // Source code - should be excluded
         { file: "src/index.js", expected: false, reason: "source code" },
         { file: "lib/utils.ts", expected: false, reason: "library code" },
+        { file: "src/helpers.ts", expected: false, reason: "utility code" },
         {
           file: "components/Button.tsx",
           expected: false,
@@ -295,7 +296,7 @@ describe("Git Repository Loading - User Workflows", () => {
       const testFiles = [
         "README.md", // Should be included
         "docs/guide.md", // Should be included
-        "src/index.js", // Should be excluded
+        "src/index.js", // Should be excluded (source file)
         "package.json", // Should be excluded
         "examples/demo.js", // Should be included
       ];
@@ -337,7 +338,7 @@ describe("Git Repository Loading - User Workflows", () => {
       const mockFiles = [
         "README.md", // Should be included
         "docs/getting-started.md", // Should be included
-        "src/index.js", // Should be excluded
+        "src/index.js", // Should be excluded (source file)
         "package.json", // Should be excluded
         "examples/demo.js", // Should be included
         "node_modules/lib.js", // Should be excluded

packages/content-loader/src/__tests__/smart-filtering.test.ts

@@ -44,11 +44,17 @@ describe("Smart Content Filtering - REQ-18", () => {
   });
 
   test("should exclude config and source files", () => {
+    // Config files should be excluded
     expect((loader as any).isDocumentationFile("package.json")).toBe(false);
     expect((loader as any).isDocumentationFile(".postcssrc.json")).toBe(false);
     expect((loader as any).isDocumentationFile("config.ts")).toBe(false);
     expect((loader as any).isDocumentationFile("styles.css")).toBe(false);
+
+    // Source files should be excluded
     expect((loader as any).isDocumentationFile("index.ts")).toBe(false);
+    expect((loader as any).isDocumentationFile("src/index.ts")).toBe(false);
+    expect((loader as any).isDocumentationFile("src/utils.ts")).toBe(false);
+    expect((loader as any).isDocumentationFile("src/helpers.ts")).toBe(false);
   });
 
   test("should include files in examples directory", () => {
@@ -80,4 +86,84 @@ describe("Smart Content Filtering - REQ-18", () => {
 
     expect(filtered).toEqual(["README.md", "docs/api.md", "examples/demo.js"]);
   });
+
+  test("should include comprehensive documentation using generic approach - Issue #12", () => {
+    // Generic approach: Include markdown/text/asciidoc files + ALL files from examples/samples
+    const repositoryFiles = [
+      // Documentation files (markdown, text, asciidoc) - always included
+      "README.md",
+      "docs/getting-started.md",
+      "docs/api.md",
+      "guides/tutorial.rst",
+      "notes.txt",
+      "architecture.adoc",
+
+      // Files in examples/samples directories - all included (Issue #12)
+      "examples/basic-map.html",
+      "examples/markers.js",
+      "examples/demo.py",
+      "examples/config.json",
+      "samples/advanced-usage.ts",
+      "samples/quickstart.java",
+
+      // Source files - should be excluded
+      "src/index.ts",
+      "src/utils/helpers.ts",
+      "lib/core.js",
+
+      // Build artifacts and dependencies - should be excluded
+      "node_modules/some-lib/index.js",
+      "dist/bundle.js",
+      "build/output.js",
+
+      // Project metadata - should be excluded
+      "CHANGELOG.md",
+      "LICENSE",
+      "CONTRIBUTING.md",
+
+      // Config files - should be excluded
+      "package.json",
+      "tsconfig.json",
+      ".github/workflows/ci.yml",
+    ];
+
+    const filtered = (loader as any).filterDocumentationFiles(repositoryFiles);
+
+    // Expected: Documentation files + all files from examples/samples
+    const expectedIncludes = [
+      "README.md",
+      "docs/getting-started.md",
+      "docs/api.md",
+      "guides/tutorial.rst",
+      "notes.txt",
+      "architecture.adoc",
+      "examples/basic-map.html",
+      "examples/markers.js",
+      "examples/demo.py",
+      "examples/config.json",
+      "samples/advanced-usage.ts",
+      "samples/quickstart.java",
+    ];
+
+    // The filtered result should include all expected files
+    for (const expectedFile of expectedIncludes) {
+      expect(filtered).toContain(expectedFile);
+    }
+
+    // Should exclude source files
+    expect(filtered).not.toContain("src/index.ts");
+    expect(filtered).not.toContain("src/utils/helpers.ts");
+    expect(filtered).not.toContain("lib/core.js");
+
+    // Should exclude build artifacts and config files
+    expect(filtered).not.toContain("node_modules/some-lib/index.js");
+    expect(filtered).not.toContain("dist/bundle.js");
+    expect(filtered).not.toContain("CHANGELOG.md");
+    expect(filtered).not.toContain("package.json");
+    expect(filtered).not.toContain("tsconfig.json");
+    expect(filtered).not.toContain(".github/workflows/ci.yml");
+
+    // Verify we get comprehensive coverage
+    expect(filtered.length).toBeGreaterThanOrEqual(expectedIncludes.length);
+  });
 });

packages/content-loader/src/content/git-repo-loader.ts

@@ -351,26 +351,31 @@ export class GitRepoLoader extends ContentLoader {
       return false;
     }
 
-    // Exclude source code, build, and development directories (REQ-18)
-    const excludedDirPatterns = [
+    // Normalize directory path for consistent matching (use forward slashes)
+    const normalizedDir = directory.split(path.sep).join("/");
+    const pathParts = normalizedDir.split("/");
+
+    // Exclude build, dependency, and development directories (REQ-18)
+    // Use exact directory name matching, not substring matching
+    const excludedDirs = [
       "node_modules",
       "vendor",
       ".git",
       "build",
       "dist",
       "target",
       ".cache",
-      "src",
-      "lib",
-      "components",
       "__tests__",
+      "test",
+      "tests",
       ".github",
       ".vscode",
       ".idea",
     ];
 
-    for (const pattern of excludedDirPatterns) {
-      if (directory.includes(pattern)) {
+    // Check if any path segment matches excluded directories
+    for (const excludedDir of excludedDirs) {
+      if (pathParts.includes(excludedDir)) {
         return false;
       }
     }
@@ -386,10 +391,11 @@ export class GitRepoLoader extends ContentLoader {
       return true;
     }
 
-    // Special case: examples directory - include other file types as they're often documentation (REQ-18)
-    const isInExamples = /\b(examples?)\b/i.test(directory);
+    // Special case: examples/samples directory - include ALL file types (Issue #12)
+    // These directories contain code that demonstrates usage patterns
+    const isInExamples = /\b(examples?|samples?)\b/i.test(directory);
     if (isInExamples) {
-      // In examples, exclude only binary files
+      // In examples/samples, exclude only binary files
       const excludedInExamples = [
         ".exe",
         ".bin",