Merge d19de20c7d into 87292cd86a

This test file verifies the functionality of the CustomModuleManager's parseSource method for Azure DevOps Git URLs, including both dev.azure.com and legacy visualstudio.com formats. It includes various assertions to check the validity and expected outputs for different URL formats.

package-lock.json

@@ -15,7 +15,6 @@
         "chalk": "^4.1.2",
         "commander": "^14.0.0",
         "csv-parse": "^6.1.0",
-        "fs-extra": "^11.3.0",
         "glob": "^11.0.3",
         "ignore": "^7.0.5",
         "js-yaml": "^4.1.0",
@@ -25,8 +24,8 @@
         "yaml": "^2.7.0"
       },
       "bin": {
-        "bmad": "tools/bmad-npx-wrapper.js",
-        "bmad-method": "tools/bmad-npx-wrapper.js"
+        "bmad": "tools/installer/bmad-cli.js",
+        "bmad-method": "tools/installer/bmad-cli.js"
       },
       "devDependencies": {
         "@astrojs/sitemap": "^3.6.0",
@@ -46,6 +45,7 @@
         "prettier": "^3.7.4",
         "prettier-plugin-packagejson": "^2.5.19",
         "sharp": "^0.33.5",
+        "unist-util-visit": "^5.1.0",
         "yaml-eslint-parser": "^1.2.3",
         "yaml-lint": "^1.7.0"
       },
@@ -6975,20 +6975,6 @@
         "url": "https://github.com/sponsors/isaacs"
       }
     },
-    "node_modules/fs-extra": {
-      "version": "11.3.3",
-      "resolved": "https://registry.npmjs.org/fs-extra/-/fs-extra-11.3.3.tgz",
-      "integrity": "sha512-VWSRii4t0AFm6ixFFmLLx1t7wS1gh+ckoa84aOeapGum0h+EZd1EhEumSB+ZdDLnEPuucsVB9oB7cxJHap6Afg==",
-      "license": "MIT",
-      "dependencies": {
-        "graceful-fs": "^4.2.0",
-        "jsonfile": "^6.0.1",
-        "universalify": "^2.0.0"
-      },
-      "engines": {
-        "node": ">=14.14"
-      }
-    },
     "node_modules/fs.realpath": {
       "version": "1.0.0",
       "resolved": "https://registry.npmjs.org/fs.realpath/-/fs.realpath-1.0.0.tgz",
@@ -7227,6 +7213,7 @@
       "version": "4.2.11",
       "resolved": "https://registry.npmjs.org/graceful-fs/-/graceful-fs-4.2.11.tgz",
       "integrity": "sha512-RbJ5/jmFcNNCcDV5o9eTnBLJ/HszWV0P73bc+Ff4nS/rJj+YaS6IGyiOL0VoBYX+l1Wrl3k63h/KrH+nhJ0XvQ==",
+      "dev": true,
       "license": "ISC"
     },
     "node_modules/h3": {
@@ -9066,18 +9053,6 @@
       "dev": true,
       "license": "MIT"
     },
-    "node_modules/jsonfile": {
-      "version": "6.2.0",
-      "resolved": "https://registry.npmjs.org/jsonfile/-/jsonfile-6.2.0.tgz",
-      "integrity": "sha512-FGuPw30AdOIUTRMC2OMRtQV+jkVj2cfPqSeWXv1NEAJ1qZ5zb1X6z1mFhbfOB/iy3ssJCD+3KuZ8r8C3uVFlAg==",
-      "license": "MIT",
-      "dependencies": {
-        "universalify": "^2.0.0"
-      },
-      "optionalDependencies": {
-        "graceful-fs": "^4.1.6"
-      }
-    },
     "node_modules/katex": {
       "version": "0.16.28",
       "resolved": "https://registry.npmjs.org/katex/-/katex-0.16.28.tgz",
@@ -13607,15 +13582,6 @@
         "url": "https://opencollective.com/unified"
       }
     },
-    "node_modules/universalify": {
-      "version": "2.0.1",
-      "resolved": "https://registry.npmjs.org/universalify/-/universalify-2.0.1.tgz",
-      "integrity": "sha512-gptHNQghINnc/vTGIk0SOFGFNXw7JVrlRUtConJRlvaw6DuX0wO5Jeko9sWrMBhh+PsYAZ7oXAiOnf/UKogyiw==",
-      "license": "MIT",
-      "engines": {
-        "node": ">= 10.0.0"
-      }
-    },
     "node_modules/unrs-resolver": {
       "version": "1.11.1",
       "resolved": "https://registry.npmjs.org/unrs-resolver/-/unrs-resolver-1.11.1.tgz",

test/test-parse-source-urls.js

@@ -0,0 +1,210 @@
+/**
+ * parseSource() URL parsing tests
+ *
+ * Verifies that CustomModuleManager.parseSource() correctly handles Git URLs
+ * across arbitrary hosts and path shapes (deep paths, nested groups, browse
+ * links, repo names containing dots, etc.) using host-agnostic rules.
+ *
+ * Usage: node test/test-parse-source-urls.js
+ */
+
+const { CustomModuleManager } = require('../tools/installer/modules/custom-module-manager');
+
+// ANSI colors
+const colors = {
+  reset: '\u001B[0m',
+  green: '\u001B[32m',
+  red: '\u001B[31m',
+  cyan: '\u001B[36m',
+  dim: '\u001B[2m',
+};
+
+let passed = 0;
+let failed = 0;
+
+function assert(condition, testName, errorMessage = '') {
+  if (condition) {
+    console.log(`${colors.green}✓${colors.reset} ${testName}`);
+    passed++;
+  } else {
+    console.log(`${colors.red}✗${colors.reset} ${testName}`);
+    if (errorMessage) {
+      console.log(`  ${colors.dim}${errorMessage}${colors.reset}`);
+    }
+    failed++;
+  }
+}
+
+const manager = new CustomModuleManager();
+
+// ─── Deep path shapes (4+ segments) ─────────────────────────────────────────
+
+console.log(`\n${colors.cyan}Deep path shapes${colors.reset}\n`);
+
+{
+  // Hosts that expose the repo at a nested path like /<org>/<project>/<marker>/<repo>.
+  // The parser must preserve the full path (no stripping of intermediate segments).
+  const result = manager.parseSource('https://git.example.com/myorg/MyProject/_git/my-module');
+  assert(result.isValid === true, 'nested-path URL is valid');
+  assert(result.type === 'url', 'nested-path type is url');
+  assert(
+    result.cloneUrl === 'https://git.example.com/myorg/MyProject/_git/my-module',
+    'nested-path cloneUrl preserves full path',
+    `Got: ${result.cloneUrl}`,
+  );
+  assert(result.subdir === null, 'nested-path URL has no subdir');
+  assert(
+    result.cacheKey === 'git.example.com/myorg/MyProject/_git/my-module',
+    'nested-path cacheKey includes full repo path',
+    `Got: ${result.cacheKey}`,
+  );
+  assert(result.displayName === '_git/my-module', 'nested-path displayName uses last two segments', `Got: ${result.displayName}`);
+}
+
+{
+  const result = manager.parseSource('https://git.example.com/myorg/MyProject/_git/my-module.git');
+  assert(result.isValid === true, 'nested-path URL with .git suffix is valid');
+  assert(
+    result.cloneUrl === 'https://git.example.com/myorg/MyProject/_git/my-module',
+    'nested-path .git suffix stripped from cloneUrl',
+    `Got: ${result.cloneUrl}`,
+  );
+}
+
+{
+  // Browse links that use ?path=/... to point at a subdirectory.
+  const result = manager.parseSource('https://git.example.com/myorg/MyProject/_git/my-module?path=/path/to/subdir');
+  assert(result.isValid === true, 'URL with ?path= is valid');
+  assert(
+    result.cloneUrl === 'https://git.example.com/myorg/MyProject/_git/my-module',
+    '?path= cloneUrl excludes subdir',
+    `Got: ${result.cloneUrl}`,
+  );
+  assert(result.subdir === 'path/to/subdir', '?path= subdir correctly extracted', `Got: ${result.subdir}`);
+}
+
+// ─── Subdomain hosts ────────────────────────────────────────────────────────
+
+console.log(`\n${colors.cyan}Subdomain hosts${colors.reset}\n`);
+
+{
+  const result = manager.parseSource('https://myorg.example.com/MyProject/_git/my-module');
+  assert(result.isValid === true, 'subdomain URL is valid');
+  assert(result.type === 'url', 'subdomain type is url');
+  assert(
+    result.cloneUrl === 'https://myorg.example.com/MyProject/_git/my-module',
+    'subdomain cloneUrl preserves full path',
+    `Got: ${result.cloneUrl}`,
+  );
+  assert(result.subdir === null, 'subdomain URL has no subdir');
+  assert(
+    result.cacheKey === 'myorg.example.com/MyProject/_git/my-module',
+    'subdomain cacheKey includes full repo path',
+    `Got: ${result.cacheKey}`,
+  );
+}
+
+// ─── Simple owner/repo URLs (regression) ────────────────────────────────────
+
+console.log(`\n${colors.cyan}Simple owner/repo URLs (regression check)${colors.reset}\n`);
+
+{
+  const result = manager.parseSource('https://github.com/owner/repo');
+  assert(result.isValid === true, 'GitHub basic URL still valid');
+  assert(result.cloneUrl === 'https://github.com/owner/repo', 'GitHub cloneUrl unchanged', `Got: ${result.cloneUrl}`);
+  assert(result.cacheKey === 'github.com/owner/repo', 'GitHub cacheKey unchanged', `Got: ${result.cacheKey}`);
+}
+
+{
+  const result = manager.parseSource('https://github.com/owner/repo/tree/main/subdir');
+  assert(result.isValid === true, 'GitHub URL with tree path still valid');
+  assert(result.cloneUrl === 'https://github.com/owner/repo', 'GitHub tree URL cloneUrl correct', `Got: ${result.cloneUrl}`);
+  assert(result.subdir === 'subdir', 'GitHub tree subdir still extracted', `Got: ${result.subdir}`);
+}
+
+{
+  const result = manager.parseSource('git@github.com:owner/repo.git');
+  assert(result.isValid === true, 'SSH URL still valid');
+  assert(result.cloneUrl === 'git@github.com:owner/repo.git', 'SSH cloneUrl unchanged', `Got: ${result.cloneUrl}`);
+}
+
+// ─── Generic URL handling (any host, any path depth) ────────────────────────
+
+console.log(`\n${colors.cyan}Generic URL handling${colors.reset}\n`);
+
+{
+  // GitLab nested groups — the old 2-segment regex would have failed this.
+  const result = manager.parseSource('https://gitlab.com/group/subgroup/repo');
+  assert(result.isValid === true, 'GitLab nested-group URL is valid');
+  assert(
+    result.cloneUrl === 'https://gitlab.com/group/subgroup/repo',
+    'GitLab nested-group cloneUrl preserves full path',
+    `Got: ${result.cloneUrl}`,
+  );
+  assert(
+    result.cacheKey === 'gitlab.com/group/subgroup/repo',
+    'GitLab nested-group cacheKey includes full path',
+    `Got: ${result.cacheKey}`,
+  );
+  assert(result.displayName === 'subgroup/repo', 'GitLab nested-group displayName uses last two segments', `Got: ${result.displayName}`);
+}
+
+{
+  const result = manager.parseSource('https://gitlab.com/group/subgroup/repo/-/tree/main/src/module');
+  assert(result.isValid === true, 'GitLab nested-group tree URL is valid');
+  assert(
+    result.cloneUrl === 'https://gitlab.com/group/subgroup/repo',
+    'GitLab nested-group tree cloneUrl excludes subdir',
+    `Got: ${result.cloneUrl}`,
+  );
+  assert(result.subdir === 'src/module', 'GitLab nested-group tree subdir extracted', `Got: ${result.subdir}`);
+}
+
+{
+  // Self-hosted host with a repo name containing dots — the old regex
+  // explicitly excluded dots from the repo segment.
+  const result = manager.parseSource('https://git.example.com/owner/my.repo.name');
+  assert(result.isValid === true, 'repo name with dots is valid');
+  assert(
+    result.cloneUrl === 'https://git.example.com/owner/my.repo.name',
+    'repo name with dots preserved in cloneUrl',
+    `Got: ${result.cloneUrl}`,
+  );
+  assert(result.displayName === 'owner/my.repo.name', 'repo name with dots preserved in displayName', `Got: ${result.displayName}`);
+}
+
+{
+  // Browser URL pointing at a ref with NO trailing subdir must still strip
+  // the /tree/<ref> segment from the clone URL.
+  const result = manager.parseSource('https://github.com/owner/repo/tree/main');
+  assert(result.isValid === true, 'tree URL without subdir is valid');
+  assert(
+    result.cloneUrl === 'https://github.com/owner/repo',
+    'tree URL without subdir strips ref from cloneUrl',
+    `Got: ${result.cloneUrl}`,
+  );
+  assert(result.subdir === null, 'tree URL without subdir yields null subdir', `Got: ${result.subdir}`);
+  assert(result.displayName === 'owner/repo', 'tree URL without subdir displayName is owner/repo', `Got: ${result.displayName}`);
+}
+
+{
+  // Same shape for GitLab's /-/tree form and Gitea's /src/branch form.
+  const gitlab = manager.parseSource('https://gitlab.com/group/repo/-/tree/main');
+  assert(
+    gitlab.cloneUrl === 'https://gitlab.com/group/repo' && gitlab.subdir === null,
+    'GitLab /-/tree/<ref> without subdir strips ref',
+    `Got: ${gitlab.cloneUrl} subdir=${gitlab.subdir}`,
+  );
+
+  const gitea = manager.parseSource('https://gitea.example.com/owner/repo/src/branch/main');
+  assert(
+    gitea.cloneUrl === 'https://gitea.example.com/owner/repo' && gitea.subdir === null,
+    'Gitea /src/branch/<ref> without subdir strips ref',
+    `Got: ${gitea.cloneUrl} subdir=${gitea.subdir}`,
+  );
+}
+
+// ─── Summary ────────────────────────────────────────────────────────────────
+
+console.log(`\n${colors.cyan}Results: ${passed} passed, ${failed} failed${colors.reset}\n`);
+process.exit(failed > 0 ? 1 : 0);

tools/installer/modules/custom-module-manager.js

@@ -73,40 +73,95 @@ class CustomModuleManager {
       };
     }
 
-    // HTTPS URL: https://host/owner/repo[/tree/branch/subdir][.git]
-    const httpsMatch = trimmed.match(/^https?:\/\/([^/]+)\/([^/]+)\/([^/.]+?)(?:\.git)?(\/.*)?$/);
-    if (httpsMatch) {
-      const [, host, owner, repo, remainder] = httpsMatch;
-      const cloneUrl = `https://${host}/${owner}/${repo}`;
-      let subdir = null;
+    // HTTPS URL: generic handling for any Git host.
+    // We avoid host-specific parsing — `git clone` will accept whatever URL the
+    // user provides. We only need to (a) separate an optional browser-style
+    // subdir suffix from the clone URL, and (b) derive a cache key / display
+    // name from the path.
+    if (/^https?:\/\//i.test(trimmed)) {
+      let url;
+      try {
+        url = new URL(trimmed);
+      } catch {
+        url = null;
+      }
 
-      if (remainder) {
-        // Extract subdir from deep path patterns used by various Git hosts
+      if (url && url.host) {
+        const host = url.host;
+        let repoPath = url.pathname.replace(/^\/+/, '').replace(/\/+$/, '');
+        let subdir = null;
+
+        // Detect browser-style deep-path patterns that embed a subdirectory
+        // after a ref (branch/tag/commit). These appear across many hosts:
+        //   GitHub  /<repo>/tree|blob/<ref>/<subdir>
+        //   GitLab  /<repo>/-/tree|blob/<ref>/<subdir>
+        //   Gitea   /<repo>/src/<ref>/<subdir>
+        //   Gitea   /<repo>/src/(branch|commit|tag)/<ref>/<subdir>
+        // Group 1 = repo path prefix, Group 2 = subdir.
+        // Trailing subdir is optional: a URL like /<repo>/tree/<ref> with no
+        // further path still identifies a repo at a ref (no subdir).
         const deepPathPatterns = [
-          /^\/(?:-\/)?tree\/[^/]+\/(.+)$/, // GitHub /tree/branch/path, GitLab /-/tree/branch/path
-          /^\/(?:-\/)?blob\/[^/]+\/(.+)$/, // /blob/branch/path (treat same as tree)
-          /^\/src\/[^/]+\/(.+)$/, // Gitea/Forgejo /src/branch/path
+          /^(.+?)\/(?:-\/)?(?:tree|blob)\/[^/]+(?:\/(.+))?$/,
+          /^(.+?)\/src\/(?:branch\/|commit\/|tag\/)?[^/]+(?:\/(.+))?$/,
         ];
-
         for (const pattern of deepPathPatterns) {
-          const match = remainder.match(pattern);
+          const match = repoPath.match(pattern);
           if (match) {
-            subdir = match[1].replace(/\/$/, ''); // strip trailing slash
+            repoPath = match[1];
+            if (match[2]) {
+              const cleaned = match[2].replace(/\/+$/, '');
+              if (cleaned) subdir = cleaned;
+            }
             break;
           }
         }
-      }
 
-      return {
-        type: 'url',
-        cloneUrl,
-        subdir,
-        localPath: null,
-        cacheKey: `${host}/${owner}/${repo}`,
-        displayName: `${owner}/${repo}`,
-        isValid: true,
-        error: null,
-      };
+        // Some hosts use ?path=/subdir on browse links to point at a file or
+        // directory. Honor it when no deep-path marker matched above.
+        if (!subdir) {
+          const pathParam = url.searchParams.get('path');
+          if (pathParam) {
+            const cleaned = pathParam.replace(/^\/+/, '').replace(/\/+$/, '');
+            if (cleaned) subdir = cleaned;
+          }
+        }
+
+        // Strip a single trailing .git for a stable cacheKey/displayName.
+        const repoPathClean = repoPath.replace(/\.git$/i, '');
+        if (!repoPathClean) {
+          return {
+            type: null,
+            cloneUrl: null,
+            subdir: null,
+            localPath: null,
+            cacheKey: null,
+            displayName: null,
+            isValid: false,
+            error: 'Not a valid Git URL or local path',
+          };
+        }
+
+        const cloneUrl = `${url.protocol}//${host}/${repoPathClean}`;
+        const cacheKey = `${host}/${repoPathClean}`;
+
+        // Display name: prefer "<owner>/<repo>" using the last two meaningful
+        // path segments.
+        const segments = repoPathClean.split('/').filter(Boolean);
+        const repoSeg = segments.at(-1);
+        const ownerSeg = segments.at(-2);
+        const displayName = ownerSeg ? `${ownerSeg}/${repoSeg}` : repoSeg;
+
+        return {
+          type: 'url',
+          cloneUrl,
+          subdir,
+          localPath: null,
+          cacheKey,
+          displayName,
+          isValid: true,
+          error: null,
+        };
+      }
     }
 
     return {