linguist-js - npm Package Compare versions

Comparing version 1.4.5 to 1.5.0

dist/cli.js

@@ -17,3 +17,3 @@ "use strict";
     .option('-s|--summary', 'Show output in a human-readable format', false)
-    .option('-q|--quick', 'Skip checking of gitattributes/gitignore files (alias for -AIH=false)', false)
+    .option('-q|--quick', 'Skip checking of gitattributes/gitignore files (alias for -AIHS=false)', false)
     .option('-V|--keepVendored', 'Prevent skipping over vendored/generated files', false)
@@ -23,2 +23,3 @@ .option('-A|--checkAttributes', 'Force the checking of gitattributes files (default: true unless --quick is set)')
     .option('-H|--checkHeuristics', 'Apply heuristics to ambiguous languages (default: true unless --quick is set)')
+    .option('-S|--checkShebang|--checkHashbang', 'Check shebang lines for explicit classification (default: true unless --quick is set)')
     .helpOption(`-h|--help`, 'Display this help message')
@@ -25,0 +26,0 @@ .version(VERSION, '-v|--version', 'Display the installed version of linguist-js');

dist/index.js

@@ -8,3 +8,3 @@ "use strict";
 const js_yaml_1 = __importDefault(require("js-yaml"));
-const fast_glob_1 = __importDefault(require("fast-glob"));
+const tiny_glob_1 = __importDefault(require("tiny-glob"));
 const glob_to_regexp_1 = __importDefault(require("glob-to-regexp"));
@@ -16,2 +16,13 @@ const convertToRegex = (path) => glob_to_regexp_1.default('**/' + path, { globstar: true, extended: true });
 const loadFile = async (file) => await cross_fetch_1.default(dataUrl(file)).then(data => data.text());
+async function readFile(filename, onlyFirstLine = false) {
+    const chunkSize = 100;
+    const stream = fs_1.default.createReadStream(filename, { highWaterMark: chunkSize });
+    let content = '';
+    for await (const data of stream) {
+        content += data.toString();
+        if (onlyFirstLine && /\n/.test(content))
+            return content;
+    }
+    return content;
+}
 module.exports = async function analyse(root = '.', opts = {}) {
@@ -35,7 +46,7 @@ var _a, _b, _c, _d, _e, _f, _g;
     };
-    let files = await fast_glob_1.default(root + '/**/*', { absolute: true, onlyFiles: true, dot: true });
-    files = files.filter(file => !file.includes('/.git/'));
+    let files = await tiny_glob_1.default(root + '/**/*', { absolute: true, filesOnly: true, dot: true });
+    files = files.map(path => path.replace(/\\/g, '/')).filter(file => !file.includes('/.git/'));
     const folders = new Set(files.map(file => file.replace(/[^/]+$/, '')));
     // Apply aliases
-    opts = { checkIgnored: !opts.quick, checkAttributes: !opts.quick, checkHeuristics: !opts.quick, ...opts };
+    opts = { checkIgnored: !opts.quick, checkAttributes: !opts.quick, checkHeuristics: !opts.quick, checkShebang: !opts.quick, ...opts };
     // Apply explicit ignores
@@ -56,3 +67,3 @@ if (opts.ignore) {
             if (opts.checkIgnored && fs_1.default.existsSync(ignoresFile)) {
-                const ignoresData = fs_1.default.readFileSync(ignoresFile, { encoding: 'utf8' });
+                const ignoresData = await readFile(ignoresFile);
                 const ignoresList = ignoresData.split(/\r?\n/).filter(line => line.trim() && !line.startsWith('#'));
@@ -64,3 +75,3 @@ const ignoredPaths = ignoresList.map(path => glob_to_regexp_1.default('*' + path + '*', { extended: true }).source);
             if (opts.checkAttributes && fs_1.default.existsSync(attributesFile)) {
-                const attributesData = fs_1.default.readFileSync(attributesFile, { encoding: 'utf8' });
+                const attributesData = await readFile(attributesFile);
                 // Custom vendor options
@@ -105,4 +116,17 @@ const vendorMatches = attributesData.matchAll(/^(\S+).*[^-]linguist-(vendored|generated|documentation)(?!=false)/gm);
             continue;
+        // Check shebang line for explicit classification
+        if (!opts.quick && opts.checkShebang) {
+            const firstLine = await readFile(file, true);
+            if (firstLine.startsWith('#!')) {
+                const interpreter = firstLine.split(/\s/)[1];
+                const match = Object.entries(langData).filter(([_lang, data]) => { var _a; return (_a = data.interpreters) === null || _a === void 0 ? void 0 : _a.includes(interpreter); });
+                if (match.length) {
+                    const forcedLang = match[0][0];
+                    addResult(file, forcedLang);
+                    continue;
+                }
+            }
+        }
         // Check override for manual language classification
-        if (!opts.quick) {
+        if (!opts.quick && opts.checkAttributes) {
             const match = overridesArray.find(item => RegExp(item[0]).test(file));
@@ -153,3 +177,3 @@ if (match) {
                     // Check file contents and apply heuristic patterns
-                    const fileContent = fs_1.default.readFileSync(file, { encoding: 'utf8' });
+                    const fileContent = await readFile(file);
                     if (patterns.some(pattern => RegExp(pattern).test(fileContent))) {
@@ -156,0 +180,0 @@ finalResults[file] = heuristic.language;

dist/types.d.ts

@@ -13,2 +13,3 @@ import { LanguageType } from "./schema";
     checkHeuristics?: boolean;
+    checkShebang?: boolean;
     ignore?: string[];
@@ -15,0 +16,0 @@ }

package.json

 {
 	"name": "linguist-js",
-	"version": "1.4.5",
+	"version": "1.5.0",
 	"description": "Analyse languages used in a folder. Powered by GitHub Linguist, although it doesn't need to be installed.",
@@ -37,5 +37,5 @@ "main": "dist/index.js",
 		"cross-fetch": "^3.1.4",
-		"fast-glob": "^3.2.7",
 		"glob-to-regexp": "^0.4.1",
-		"js-yaml": "^4.1.0"
+		"js-yaml": "^4.1.0",
+		"tiny-glob": "^0.2.9"
 	},
@@ -42,0 +42,0 @@ "devDependencies": {

readme.md

@@ -88,3 +88,3 @@ [![Latest version](https://img.shields.io/github/v/release/Nixinova/Linguist?label=latest%20version&style=flat-square)](https://github.com/Nixinova/Linguist/releases)
       Whether to skip the checking of `.gitattributes` and `.gitignore` files for manual language classifications (defaults to `false`).
-      Alias for `checkAttributes: false, checkIgnored: false`.
+      Alias for `checkAttributes:false, checkIgnored:false, checkHeuristics:false, checkShebang:false`.
     - `keepVendored` (boolean):
@@ -98,2 +98,4 @@ Whether to keep vendored files (dependencies, etc) (defaults to `false`).
       Apply heuristics to ambiguous languages (defaults to `true` unless `quick` is set).
+    - `checkShebang` (boolean):
+      Check shebang (`#!`) lines for explicit language classification (defaults to `true` unless `quick` is set).
 
@@ -121,11 +123,13 @@ ### Command-line
     Whether to skip the checking of `.gitattributes` and `.gitignore` files for manual language classifications.
-    Alias for `--checkAttributes=false --checkIgnored=false --checkHeuristics=false`.
+    Alias for `--checkAttributes=false --checkIgnored=false --checkHeuristics=false --checkShebang=false`.
   - `--keepVendored` (optional):
     Whether to include vendored files (auto-generated files, dependencies folder, etc).
-  - `checkAttributes` (optional):
+  - `--checkAttributes` (optional):
     Force the checking of `.gitatributes` files (use alongside `--quick` to overwrite).
-  - `checkIgnored` (optional):
+  - `--checkIgnored` (optional):
     Force the checking of `.gitignore` files (use alongside `--quick` to overwrite).
-  - `checkHeuristics` (optional):
+  - `--checkHeuristics` (optional):
     Apply heuristics to ambiguous languages (use alongside `--quick` to overwrite).
+  - `--checkShebang` (optional):
+    Check shebang (`#!`) lines for explicit classification (use alongside `--quick` to overwrite).
 - `--help`:
@@ -132,0 +136,0 @@ Display a help message.

New alerts

License Policy Violation

License

This package is not allowed per your license policy. Review the package's license to ensure compliance.

Found 1 instance in 1 package

Fixed alerts

License Policy Violation

License

This package is not allowed per your license policy. Review the package's license to ensure compliance.

Found 1 instance in 1 package

Improved metrics

Total package byte prevSize

23961

increased by7.07%

Lines of code

354

increased by7.93%

Number of lines in readme file

136

increased by3.03%

Dependency changes

• + Addedtiny-glob@^0.2.9

• + Addedglobalyzer@0.1.0(transitive)

• + Addedglobrex@0.1.2(transitive)

• + Addedtiny-glob@0.2.9(transitive)

• - Removedfast-glob@^3.2.7

• - Removed@nodelib/fs.scandir@2.1.5(transitive)

• - Removed@nodelib/fs.stat@2.0.5(transitive)

• - Removed@nodelib/fs.walk@1.2.8(transitive)

• - Removedbraces@3.0.3(transitive)

• - Removedfast-glob@3.3.2(transitive)

• - Removedfastq@1.17.1(transitive)

• - Removedfill-range@7.1.1(transitive)

• - Removedglob-parent@5.1.2(transitive)

• - Removedis-extglob@2.1.1(transitive)

• - Removedis-glob@4.0.3(transitive)

• - Removedis-number@7.0.0(transitive)

• - Removedmerge2@1.4.1(transitive)

• - Removedmicromatch@4.0.8(transitive)

• - Removedpicomatch@2.3.1(transitive)

• - Removedqueue-microtask@1.2.3(transitive)

• - Removedreusify@1.0.4(transitive)

• - Removedrun-parallel@1.2.0(transitive)

• - Removedto-regex-range@5.0.1(transitive)