linguist-js 2.2.0 → 2.2.1

package/dist/cli.js

@@ -64,6 +64,7 @@ if (args.analyze)
             let count = 0;
             if (sortedEntries.length === 0)
                 console.log(`  None`);
+            // List parsed results
             for (const [lang, { bytes, color }] of sortedEntries) {
                 const fmtd = {
                     index: (++count).toString().padStart(2, ' '),
@@ -75,6 +76,7 @@ if (args.analyze)
                 console.log(`  ${fmtd.index}. ${fmtd.icon} ${fmtd.lang} ${fmtd.percent}% ${fmtd.bytes} B`);
             }
             console.log(` Total: ${totalBytes.toLocaleString()} B`);
+            // List unknown files/extensions
             if (unknown.bytes > 0) {
                 console.log(`\n Unknown files and extensions:`);
                 for (const [name, bytes] of Object.entries(unknown.filenames)) {
@@ -101,6 +103,6 @@ if (args.analyze)
         }
     })();
 else {
-    console.log(`Welcome to linguist-js, the JavaScript port of GitHub's language analyzer.`);
+    console.log(`Welcome to linguist-js, a JavaScript port of GitHub's language analyzer.`);
     console.log(`Type 'linguist --help' for a list of commands.`);
 }

package/dist/helpers/read-file.js

@@ -4,12 +4,15 @@ var __importDefault = (this && this.__importDefault) || function (mod) {
 };
 Object.defineProperty(exports, "__esModule", { value: true });
 const fs_1 = __importDefault(require("fs"));
-/** Read part of a file on disc. */
+/**
+ * Read part of a file on disc.
+ * @throws 'EPERM' if the file is not readable.
+ */
 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) {
+    for await (const data of stream) { // may throw
         content += data.toString();
         if (onlyFirstLine && content.includes('\n')) {
             return content.split(/\r?\n/)[0];

package/dist/index.js

@@ -69,7 +69,7 @@ async function analyse(input, opts = {}) {
                 const attributesData = await (0, read_file_1.default)(attributesFile);
                 const relPathToRegex = (path) => (0, convert_glob_1.default)(path).source.substr(1).replace(folder, '');
                 // Explicit text/binary associations
-                const contentTypeMatches = attributesData.matchAll(/^(\S+).*?(-?binary|-?text)/gm);
+                const contentTypeMatches = attributesData.matchAll(/^(\S+).*?(-?binary|-?text)(?!=auto)/gm);
                 for (const [_line, path, type] of contentTypeMatches) {
                     if (['text', '-binary'].includes(type))
                         customText.push(relPathToRegex(path));
@@ -117,16 +117,18 @@ async function analyse(input, opts = {}) {
     for (const file of files) {
         if (!fs_1.default.existsSync(file) || fs_1.default.lstatSync(file).isDirectory())
             continue;
+        const firstLine = await (0, read_file_1.default)(file, true).catch(() => null);
+        // Skip if file is unreadable
+        if (firstLine === null)
+            continue;
         // Check shebang line for explicit classification
-        if (!opts.quick && opts.checkShebang) {
-            const firstLine = await (0, read_file_1.default)(file, true);
-            if (firstLine.startsWith('#!')) {
-                const matches = Object.entries(langData).filter(([, data]) => { var _a; return (_a = data.interpreters) === null || _a === void 0 ? void 0 : _a.some(interpreter => firstLine.match('\\b' + interpreter + '\\b')); });
-                if (matches.length) {
-                    const forcedLang = matches[0][0];
-                    addResult(file, forcedLang);
-                    continue;
-                }
+        if (!opts.quick && opts.checkShebang && firstLine.startsWith('#!')) {
+            // Find matching interpreters
+            const matches = Object.entries(langData).filter(([, data]) => { var _a; return (_a = data.interpreters) === null || _a === void 0 ? void 0 : _a.some(interpreter => firstLine.match('\\b' + interpreter + '\\b')); });
+            if (matches.length) {
+                // Add explicitly-identified language
+                const forcedLang = matches[0][0];
+                addResult(file, forcedLang);
             }
         }
         // Check override for manual language classification
@@ -196,7 +198,9 @@ async function analyse(input, opts = {}) {
                     if (heuristic.named_pattern)
                         normalise(heuristicsData.named_patterns[heuristic.named_pattern]);
                     // Check file contents and apply heuristic patterns
-                    const fileContent = await (0, read_file_1.default)(file);
+                    const fileContent = await (0, read_file_1.default)(file).catch(() => null);
+                    if (fileContent === null)
+                        continue;
                     if (!patterns.length || patterns.some(pattern => (0, convert_pcre_1.default)(pattern).test(fileContent))) {
                         results.files.results[file] = heuristic.language;
                         break;

package/package.json

@@ -1,6 +1,6 @@
 {
 	"name": "linguist-js",
-	"version": "2.2.0",
+	"version": "2.2.1",
 	"description": "Analyse languages used in a folder. Powered by GitHub Linguist, although it doesn't need to be installed.",
 	"main": "dist/index.js",
 	"bin": {
@@ -37,8 +37,8 @@
 	"homepage": "https://github.com/Nixinova/Linguist#readme",
 	"dependencies": {
 		"binary-extensions": "^2.2.0",
-		"commander": "^8.3.0",
-		"cross-fetch": "^3.1.4",
+		"commander": "^9.0.0",
+		"cross-fetch": "^3.1.5",
 		"glob-to-regexp": "~0.4.1",
 		"isbinaryfile": "^4.0.8",
 		"js-yaml": "^4.1.0",
@@ -48,7 +48,7 @@
 		"@types/glob-to-regexp": "ts4.4",
 		"@types/js-yaml": "ts4.4",
 		"@types/node": "ts4.4",
-		"deep-object-diff": "^1.1.0",
-		"typescript": "~4.5.4"
+		"deep-object-diff": "^1.1.7",
+		"typescript": "~4.5.5"
 	}
 }