linguist-js 2.7.1 → 2.8.1

package/dist/cli.js

@@ -24,11 +24,13 @@ commander_1.program
     .option('-F|--listFiles [bool]', 'Whether to list every matching file under the language results', false)
     .option('-q|--quick [bool]', 'Skip complex language analysis (alias for -{A|I|H|S}=false)', false)
     .option('-o|--offline [bool]', 'Use packaged data files instead of fetching latest from GitHub', false)
+    .option('-L|--calculateLines [bool]', 'Calculate lines of code totals', true)
     .option('-V|--keepVendored [bool]', 'Prevent skipping over vendored/generated files', false)
     .option('-B|--keepBinary [bool]', 'Prevent skipping over binary files', false)
     .option('-r|--relativePaths [bool]', 'Convert absolute file paths to relative', false)
     .option('-A|--checkAttributes [bool]', 'Force the checking of gitattributes files', true)
     .option('-I|--checkIgnored [bool]', 'Force the checking of gitignore files', true)
+    .option('-D|--checkDetected [bool]', 'Force files marked with linguist-detectable to always appear in output', true)
     .option('-H|--checkHeuristics [bool]', 'Apply heuristics to ambiguous languages', true)
     .option('-S|--checkShebang [bool]', 'Check shebang lines for explicit classification', true)
     .option('-M|--checkModeline [bool]', 'Check modelines for explicit classification', true)
@@ -79,16 +81,17 @@ if (args.analyze)
                 }
             }
             // List parsed results
-            for (const [lang, { bytes, color }] of sortedEntries) {
+            for (const [lang, { bytes, lines, color }] of sortedEntries) {
                 const percent = (bytes) => bytes / (totalBytes || 1) * 100;
                 const fmtd = {
                     index: (++count).toString().padStart(2, ' '),
                     lang: lang.padEnd(24, ' '),
                     percent: percent(bytes).toFixed(2).padStart(5, ' '),
                     bytes: bytes.toLocaleString().padStart(10, ' '),
+                    loc: lines.code.toLocaleString().padStart(10, ' '),
                     icon: colouredMsg(hexToRgb(color !== null && color !== void 0 ? color : '#ededed'), '\u2588'),
                 };
-                console.log(`  ${fmtd.index}. ${fmtd.icon} ${fmtd.lang} ${fmtd.percent}% ${fmtd.bytes} B`);
+                console.log(`  ${fmtd.index}. ${fmtd.icon} ${fmtd.lang} ${fmtd.percent}% ${fmtd.bytes} B ${fmtd.loc} LOC`);
                 // If using `listFiles` option, list all files tagged as this language
                 if (args.listFiles) {
                     console.log(); // padding

package/dist/helpers/convert-pcre.js

@@ -1,5 +1,6 @@
 "use strict";
 Object.defineProperty(exports, "__esModule", { value: true });
+exports.default = pcre;
 /** Convert a PCRE regex into JS. */
 function pcre(regex) {
     let finalRegex = regex;
@@ -35,4 +36,3 @@ function pcre(regex) {
     // Return final regex
     return RegExp(finalRegex, [...finalFlags].join(''));
 }
-exports.default = pcre;

package/dist/helpers/load-data.d.ts

@@ -1,4 +1,4 @@
 /** Nukes unused `generated.rb` file content. */
-export declare function parseGeneratedDataFile(fileContent: string): Promise<string[]>;
+export declare function parseGeneratedDataFile(fileContent: string): string[];
 /** Load a data file from github-linguist. */
 export default function loadFile(file: string, offline?: boolean): Promise<string>;

package/dist/helpers/load-data.js

@@ -3,7 +3,8 @@ var __importDefault = (this && this.__importDefault) || function (mod) {
     return (mod && mod.__esModule) ? mod : { "default": mod };
 };
 Object.defineProperty(exports, "__esModule", { value: true });
-exports.parseGeneratedDataFile = void 0;
+exports.parseGeneratedDataFile = parseGeneratedDataFile;
+exports.default = loadFile;
 const fs_1 = __importDefault(require("fs"));
 const path_1 = __importDefault(require("path"));
 const cross_fetch_1 = __importDefault(require("cross-fetch"));
@@ -26,13 +27,11 @@ async function loadLocalFile(file) {
     return fs_1.default.promises.readFile(filePath).then(buffer => buffer.toString());
 }
 /** Nukes unused `generated.rb` file content. */
-async function parseGeneratedDataFile(fileContent) {
+function parseGeneratedDataFile(fileContent) {
     var _a;
     return [...(_a = fileContent.match(/(?<=name\.match\(\/).+?(?=(?<!\\)\/)/gm)) !== null && _a !== void 0 ? _a : []];
 }
-exports.parseGeneratedDataFile = parseGeneratedDataFile;
 /** Load a data file from github-linguist. */
-async function loadFile(file, offline = false) {
+function loadFile(file, offline = false) {
     return offline ? loadLocalFile(file) : loadWebFile(file);
 }
-exports.default = loadFile;

package/dist/helpers/parse-gitattributes.d.ts

@@ -3,6 +3,7 @@ export type FlagAttributes = {
     'vendored': boolean | null;
     'generated': boolean | null;
     'documentation': boolean | null;
+    'detectable': boolean | null;
     'binary': boolean | null;
     'language': T.LanguageResult;
 };

package/dist/helpers/parse-gitattributes.js

@@ -1,5 +1,6 @@
 "use strict";
 Object.defineProperty(exports, "__esModule", { value: true });
+exports.default = parseAttributes;
 const norm_path_1 = require("./norm-path");
 /**
  * Parses a gitattributes file.
@@ -21,10 +22,12 @@ function parseAttributes(content, folderRoot = '.') {
         const falseParts = (str) => attrParts.filter(part => part.includes(str) && isFalse(part));
         const hasTrueParts = (str) => trueParts(str).length > 0;
         const hasFalseParts = (str) => falseParts(str).length > 0;
+        const boolOrNullVal = (str) => hasTrueParts(str) ? true : hasFalseParts(str) ? false : null;
         const attrs = {
-            'generated': hasTrueParts('linguist-generated') ? true : hasFalseParts('linguist-generated') ? false : null,
-            'vendored': hasTrueParts('linguist-vendored') ? true : hasFalseParts('linguist-vendored') ? false : null,
-            'documentation': hasTrueParts('linguist-documentation') ? true : hasFalseParts('linguist-documentation') ? false : null,
+            'generated': boolOrNullVal('linguist-generated'),
+            'vendored': boolOrNullVal('linguist-vendored'),
+            'documentation': boolOrNullVal('linguist-documentation'),
+            'detectable': boolOrNullVal('linguist-detectable'),
             'binary': hasTrueParts('binary') || hasFalseParts('text') ? true : hasFalseParts('binary') || hasTrueParts('text') ? false : null,
             'language': (_b = (_a = trueParts('linguist-language').at(-1)) === null || _a === void 0 ? void 0 : _a.split('=')[1]) !== null && _b !== void 0 ? _b : null,
         };
@@ -32,4 +35,3 @@ function parseAttributes(content, folderRoot = '.') {
     }
     return output;
 }
-exports.default = parseAttributes;

package/dist/helpers/parse-gitignore.js

@@ -1,5 +1,6 @@
 "use strict";
 Object.defineProperty(exports, "__esModule", { value: true });
+exports.default = parseGitignore;
 function parseGitignore(content) {
     const readableData = content
         // Remove comments unless escaped
@@ -9,4 +10,3 @@ function parseGitignore(content) {
     const arrayData = readableData.split(/\r?\n/).filter(data => data);
     return arrayData;
 }
-exports.default = parseGitignore;

package/dist/helpers/read-file.d.ts

@@ -2,4 +2,4 @@
  * Read part of a file on disc.
  * @throws 'EPERM' if the file is not readable.
  */
-export default function readFile(filename: string, onlyFirstLine?: boolean): Promise<string>;
+export default function readFileChunk(filename: string, onlyFirstLine?: boolean): Promise<string>;

package/dist/helpers/read-file.js

@@ -3,12 +3,13 @@ var __importDefault = (this && this.__importDefault) || function (mod) {
     return (mod && mod.__esModule) ? mod : { "default": mod };
 };
 Object.defineProperty(exports, "__esModule", { value: true });
+exports.default = readFileChunk;
 const fs_1 = __importDefault(require("fs"));
 /**
  * Read part of a file on disc.
  * @throws 'EPERM' if the file is not readable.
  */
-async function readFile(filename, onlyFirstLine = false) {
+async function readFileChunk(filename, onlyFirstLine = false) {
     const chunkSize = 100;
     const stream = fs_1.default.createReadStream(filename, { highWaterMark: chunkSize });
     let content = '';
@@ -20,4 +21,3 @@ async function readFile(filename, onlyFirstLine = false) {
     }
     return content;
 }
-exports.default = readFile;

package/dist/helpers/walk-tree.js

@@ -3,6 +3,7 @@ var __importDefault = (this && this.__importDefault) || function (mod) {
     return (mod && mod.__esModule) ? mod : { "default": mod };
 };
 Object.defineProperty(exports, "__esModule", { value: true });
+exports.default = walk;
 const fs_1 = __importDefault(require("fs"));
 const path_1 = __importDefault(require("path"));
 const parse_gitignore_1 = __importDefault(require("./parse-gitignore"));
@@ -36,7 +37,12 @@ function walk(data) {
         if (fs_1.default.existsSync(gitignoreFilename)) {
             const gitignoreContents = fs_1.default.readFileSync(gitignoreFilename, 'utf-8');
             const ignoredPaths = (0, parse_gitignore_1.default)(gitignoreContents);
-            ignored.add(ignoredPaths);
+            const rootRelIgnoredPaths = ignoredPaths.map(ignorePath => 
+            // get absolute path of the ignore glob
+            (0, norm_path_1.normPath)(folder, ignorePath)
+                // convert abs ignore glob to be relative to the root folder
+                .replace(commonRoot + '/', ''));
+            ignored.add(rootRelIgnoredPaths);
         }
         // Add gitattributes if present
         const gitattributesPath = (0, norm_path_1.normPath)(folder, '.gitattributes');
@@ -82,4 +88,3 @@ function walk(data) {
         folders: [...allFolders],
     };
 }
-exports.default = walk;

package/dist/index.js

@@ -39,14 +39,16 @@ const parse_gitattributes_1 = __importDefault(require("./helpers/parse-gitattrib
 const convert_pcre_1 = __importDefault(require("./helpers/convert-pcre"));
 const norm_path_1 = require("./helpers/norm-path");
 async function analyse(rawPaths, opts = {}) {
-    var _a, _b, _c, _d, _e, _f, _g, _h, _j, _k, _l, _m, _o, _p, _q;
-    var _r, _s;
+    var _a, _b, _c, _d, _e, _f, _g, _h, _j, _k, _l, _m, _o, _p, _q, _r, _s, _t;
+    var _u, _v;
     const useRawContent = opts.fileContent !== undefined;
     const input = [rawPaths !== null && rawPaths !== void 0 ? rawPaths : []].flat();
     const manualFileContent = [(_a = opts.fileContent) !== null && _a !== void 0 ? _a : []].flat();
     // Normalise input option arguments
     opts = {
+        calculateLines: (_b = opts.calculateLines) !== null && _b !== void 0 ? _b : true, // default to true if unset
         checkIgnored: !opts.quick,
+        checkDetected: !opts.quick,
         checkAttributes: !opts.quick,
         checkHeuristics: !opts.quick,
         checkShebang: !opts.quick,
@@ -65,9 +67,9 @@ async function analyse(rawPaths, opts = {}) {
     const extensions = {};
     const globOverrides = {};
     const results = {
-        files: { count: 0, bytes: 0, results: {}, alternatives: {} },
-        languages: { count: 0, bytes: 0, results: {} },
-        unknown: { count: 0, bytes: 0, extensions: {}, filenames: {} },
+        files: { count: 0, bytes: 0, lines: { total: 0, content: 0, code: 0 }, results: {}, alternatives: {} },
+        languages: { count: 0, bytes: 0, lines: { total: 0, content: 0, code: 0 }, results: {} },
+        unknown: { count: 0, bytes: 0, lines: { total: 0, content: 0, code: 0 }, extensions: {}, filenames: {} },
     };
     // Set a common root path so that vendor paths do not incorrectly match parent folders
     const resolvedInput = input.map(path => (0, norm_path_1.normPath)(path_1.default.resolve(path)));
@@ -81,7 +83,7 @@ async function analyse(rawPaths, opts = {}) {
     // Prepare list of ignored files
     const ignored = (0, ignore_1.default)();
     ignored.add('.git/');
-    ignored.add((_b = opts.ignoredFiles) !== null && _b !== void 0 ? _b : []);
+    ignored.add((_c = opts.ignoredFiles) !== null && _c !== void 0 ? _c : []);
     const regexIgnores = opts.keepVendored ? [] : vendorPaths.map(path => RegExp(path, 'i'));
     // Load file paths and folders
     let files;
@@ -176,7 +178,7 @@ async function analyse(rawPaths, opts = {}) {
         files.push(...unignoredList);
     }
     // Ignore specific languages
-    for (const lang of (_c = opts.ignoredLanguages) !== null && _c !== void 0 ? _c : []) {
+    for (const lang of (_d = opts.ignoredLanguages) !== null && _d !== void 0 ? _d : []) {
         for (const key in langData) {
             if (lang.toLowerCase() === key.toLowerCase()) {
                 delete langData[key];
@@ -229,7 +231,7 @@ async function analyse(rawPaths, opts = {}) {
         // Check first line for readability
         let firstLine;
         if (useRawContent) {
-            firstLine = (_e = (_d = manualFileContent[files.indexOf(file)]) === null || _d === void 0 ? void 0 : _d.split('\n')[0]) !== null && _e !== void 0 ? _e : null;
+            firstLine = (_f = (_e = manualFileContent[files.indexOf(file)]) === null || _e === void 0 ? void 0 : _e.split('\n')[0]) !== null && _f !== void 0 ? _f : null;
         }
         else if (fs_1.default.existsSync(file) && !fs_1.default.lstatSync(file).isDirectory()) {
             firstLine = await (0, read_file_1.default)(file, true).catch(() => null);
@@ -248,7 +250,7 @@ async function analyse(rawPaths, opts = {}) {
                 const langMatcher = (lang) => `\\b${lang.toLowerCase().replace(/\W/g, '\\$&')}(?![\\w#+*]|-\*-)`;
                 // Check for interpreter match
                 if (opts.checkShebang && hasShebang) {
-                    const matchesInterpretor = (_f = data.interpreters) === null || _f === void 0 ? void 0 : _f.some(interpreter => firstLine.match(`\\b${interpreter}\\b`));
+                    const matchesInterpretor = (_g = data.interpreters) === null || _g === void 0 ? void 0 : _g.some(interpreter => firstLine.match(`\\b${interpreter}\\b`));
                     if (matchesInterpretor)
                         matches.push(lang);
                 }
@@ -256,7 +258,7 @@ async function analyse(rawPaths, opts = {}) {
                 if (opts.checkModeline && hasModeline) {
                     const modelineText = firstLine.toLowerCase().replace(/^.*-\*-(.+)-\*-.*$/, '$1');
                     const matchesLang = modelineText.match(langMatcher(lang));
-                    const matchesAlias = (_g = data.aliases) === null || _g === void 0 ? void 0 : _g.some(lang => modelineText.match(langMatcher(lang)));
+                    const matchesAlias = (_h = data.aliases) === null || _h === void 0 ? void 0 : _h.some(lang => modelineText.match(langMatcher(lang)));
                     if (matchesLang || matchesAlias)
                         matches.push(lang);
                 }
@@ -275,7 +277,7 @@ async function analyse(rawPaths, opts = {}) {
         let skipExts = false;
         // Check if filename is a match
         for (const lang in langData) {
-            const matchesName = (_h = langData[lang].filenames) === null || _h === void 0 ? void 0 : _h.some(name => path_1.default.basename(file.toLowerCase()) === name.toLowerCase());
+            const matchesName = (_j = langData[lang].filenames) === null || _j === void 0 ? void 0 : _j.some(name => path_1.default.basename(file.toLowerCase()) === name.toLowerCase());
             if (matchesName) {
                 addResult(file, lang);
                 skipExts = true;
@@ -285,7 +287,7 @@ async function analyse(rawPaths, opts = {}) {
         const possibleExts = [];
         if (!skipExts)
             for (const lang in langData) {
-                const extMatches = (_j = langData[lang].extensions) === null || _j === void 0 ? void 0 : _j.filter(ext => file.toLowerCase().endsWith(ext.toLowerCase()));
+                const extMatches = (_k = langData[lang].extensions) === null || _k === void 0 ? void 0 : _k.filter(ext => file.toLowerCase().endsWith(ext.toLowerCase()));
                 if (extMatches === null || extMatches === void 0 ? void 0 : extMatches.length) {
                     for (const ext of extMatches)
                         possibleExts.push({ ext, lang });
@@ -331,7 +333,7 @@ async function analyse(rawPaths, opts = {}) {
                         heuristic.language = heuristic.language[0];
                     }
                     // Make sure the results includes this language
-                    const languageGroup = (_k = langData[heuristic.language]) === null || _k === void 0 ? void 0 : _k.group;
+                    const languageGroup = (_l = langData[heuristic.language]) === null || _l === void 0 ? void 0 : _l.group;
                     const matchesLang = fileAssociations[file].includes(heuristic.language);
                     const matchesParent = languageGroup && fileAssociations[file].includes(languageGroup);
                     if (!matchesLang && !matchesParent)
@@ -376,17 +378,23 @@ async function analyse(rawPaths, opts = {}) {
         }
     }
     // Skip specified categories
-    if ((_l = opts.categories) === null || _l === void 0 ? void 0 : _l.length) {
+    if ((_m = opts.categories) === null || _m === void 0 ? void 0 : _m.length) {
         const categories = ['data', 'markup', 'programming', 'prose'];
         const hiddenCategories = categories.filter(cat => !opts.categories.includes(cat));
         for (const [file, lang] of Object.entries(results.files.results)) {
-            if (!hiddenCategories.some(cat => { var _a; return lang && ((_a = langData[lang]) === null || _a === void 0 ? void 0 : _a.type) === cat; })) {
+            // Skip if language is not hidden
+            if (!hiddenCategories.some(cat => { var _a; return lang && ((_a = langData[lang]) === null || _a === void 0 ? void 0 : _a.type) === cat; }))
                 continue;
+            // Skip if language is forced as detectable
+            if (opts.checkDetected) {
+                const detectable = (0, ignore_1.default)().add(getFlaggedGlobs('detectable', true));
+                if (detectable.ignores(relPath(file)))
+                    continue;
             }
+            // Delete result otherwise
             delete results.files.results[file];
-            if (lang) {
+            if (lang)
                 delete results.languages.results[lang];
-            }
         }
         for (const category of hiddenCategories) {
             for (const [lang, { type }] of Object.entries(results.languages.results)) {
@@ -412,26 +420,59 @@ async function analyse(rawPaths, opts = {}) {
     for (const [file, lang] of Object.entries(results.files.results)) {
         if (lang && !langData[lang])
             continue;
-        const fileSize = (_o = (_m = manualFileContent[files.indexOf(file)]) === null || _m === void 0 ? void 0 : _m.length) !== null && _o !== void 0 ? _o : fs_1.default.statSync(file).size;
+        // Calculate file size
+        const fileSize = (_p = (_o = manualFileContent[files.indexOf(file)]) === null || _o === void 0 ? void 0 : _o.length) !== null && _p !== void 0 ? _p : fs_1.default.statSync(file).size;
+        // Calculate lines of code
+        const loc = { total: 0, content: 0, code: 0 };
+        if (opts.calculateLines) {
+            const fileContent = (_r = ((_q = manualFileContent[files.indexOf(file)]) !== null && _q !== void 0 ? _q : fs_1.default.readFileSync(file).toString())) !== null && _r !== void 0 ? _r : '';
+            const allLines = fileContent.split(/\r?\n/gm);
+            loc.total = allLines.length;
+            loc.content = allLines.filter(line => line.trim().length > 0).length;
+            const codeLines = fileContent
+                .replace(/^\s*(\/\/|# |;|--).+/gm, '')
+                .replace(/\/\*.+\*\/|<!--.+-->/sg, '');
+            loc.code = codeLines.split(/\r?\n/gm).filter(line => line.trim().length > 0).length;
+        }
+        // Apply to files totals
         results.files.bytes += fileSize;
-        // If no language found, add extension in other section
-        if (!lang) {
+        results.files.lines.total += loc.total;
+        results.files.lines.content += loc.content;
+        results.files.lines.code += loc.code;
+        // Add results to 'languages' section if language match found, or 'unknown' section otherwise
+        if (lang) {
+            const { type } = langData[lang];
+            // set default if unset
+            (_s = (_u = results.languages.results)[lang]) !== null && _s !== void 0 ? _s : (_u[lang] = { type, bytes: 0, lines: { total: 0, content: 0, code: 0 }, color: langData[lang].color });
+            // apply results to 'languages' section
+            if (opts.childLanguages) {
+                results.languages.results[lang].parent = langData[lang].group;
+            }
+            results.languages.results[lang].bytes += fileSize;
+            results.languages.bytes += fileSize;
+            results.languages.results[lang].lines.total += loc.total;
+            results.languages.results[lang].lines.content += loc.content;
+            results.languages.results[lang].lines.code += loc.code;
+            results.languages.lines.total += loc.total;
+            results.languages.lines.content += loc.content;
+            results.languages.lines.code += loc.code;
+        }
+        else {
             const ext = path_1.default.extname(file);
-            const unknownType = ext === '' ? 'filenames' : 'extensions';
-            const name = ext === '' ? path_1.default.basename(file) : ext;
-            (_p = (_r = results.unknown[unknownType])[name]) !== null && _p !== void 0 ? _p : (_r[name] = 0);
+            const unknownType = ext ? 'extensions' : 'filenames';
+            const name = ext || path_1.default.basename(file);
+            // apply results to 'unknown' section
+            (_t = (_v = results.unknown[unknownType])[name]) !== null && _t !== void 0 ? _t : (_v[name] = 0);
             results.unknown[unknownType][name] += fileSize;
             results.unknown.bytes += fileSize;
-            continue;
+            results.unknown.lines.total += loc.total;
+            results.unknown.lines.content += loc.content;
+            results.unknown.lines.code += loc.code;
         }
-        // Add language and bytes data to corresponding section
-        const { type } = langData[lang];
-        (_q = (_s = results.languages.results)[lang]) !== null && _q !== void 0 ? _q : (_s[lang] = { type, bytes: 0, color: langData[lang].color });
-        if (opts.childLanguages) {
-            results.languages.results[lang].parent = langData[lang].group;
-        }
-        results.languages.results[lang].bytes += fileSize;
-        results.languages.bytes += fileSize;
+    }
+    // Set lines output to NaN when line calculation is disabled
+    if (opts.calculateLines === false) {
+        results.files.lines = { total: NaN, content: NaN, code: NaN };
     }
     // Set counts
     results.files.count = Object.keys(results.files.results).length;

package/dist/package.json

@@ -0,0 +1,56 @@
+{
+    "name": "linguist-js",
+    "version": "2.8.0",
+    "description": "Analyse languages used in a folder. Powered by GitHub Linguist, although it doesn't need to be installed.",
+    "main": "dist/index.js",
+    "bin": {
+        "linguist-js": "bin/index.js",
+        "linguist": "bin/index.js"
+    },
+    "engines": {
+        "node": ">=12"
+    },
+    "scripts": {
+        "download-files": "npx tsx@3 build/download-files",
+        "pre-publish": "npm run download-files && npm test && npm run perf",
+        "perf": "tsc && node test/perf",
+        "test": "tsc && node test/folder && node test/unit"
+    },
+    "files": [
+        "bin/",
+        "dist/",
+        "ext/"
+    ],
+    "repository": {
+        "type": "git",
+        "url": "git+https://github.com/Nixinova/Linguist.git"
+    },
+    "keywords": [
+        "linguist",
+        "languages",
+        "language-analysis",
+        "language-analyzer"
+    ],
+    "author": "Nixinova (https://nixinova.com)",
+    "license": "ISC",
+    "bugs": {
+        "url": "https://github.com/Nixinova/Linguist/issues"
+    },
+    "homepage": "https://github.com/Nixinova/Linguist#readme",
+    "dependencies": {
+        "binary-extensions": "^2.3.0 <3",
+        "commander": "^9.5.0 <10",
+        "common-path-prefix": "^3.0.0",
+        "cross-fetch": "^3.1.8 <4",
+        "ignore": "^5.3.2",
+        "isbinaryfile": "^4.0.10 <5",
+        "js-yaml": "^4.1.0",
+        "node-cache": "^5.1.2"
+    },
+    "devDependencies": {
+        "@types/js-yaml": "^4.0.9",
+        "@types/node": "ts5.0",
+        "deep-object-diff": "^1.1.9",
+        "typescript": "~5.0.4 <5.1"
+    }
+}

package/dist/src/cli.d.ts

@@ -0,0 +1 @@
+export {};

package/dist/src/cli.js

@@ -0,0 +1,146 @@
+"use strict";
+var __importDefault = (this && this.__importDefault) || function (mod) {
+    return (mod && mod.__esModule) ? mod : { "default": mod };
+};
+Object.defineProperty(exports, "__esModule", { value: true });
+const package_json_1 = __importDefault(require("../package.json"));
+;
+const node_fs_1 = __importDefault(require("node:fs"));
+const node_path_1 = __importDefault(require("node:path"));
+const commander_1 = require("commander");
+const index_1 = __importDefault(require("./index"));
+const norm_path_1 = require("./helpers/norm-path");
+const colouredMsg = ([r, g, b], msg) => `\u001B[${38};2;${r};${g};${b}m${msg}${'\u001b[0m'}`;
+const hexToRgb = (hex) => [parseInt(hex.slice(1, 3), 16), parseInt(hex.slice(3, 5), 16), parseInt(hex.slice(5, 7), 16)];
+commander_1.program
+    .name('linguist')
+    .usage('--analyze [<folders...>] [<options...>]')
+    .option('-a|--analyze|--analyse [folders...]', 'Analyse the languages of all files in a folder')
+    .option('-i|--ignoredFiles <files...>', `A list of file path globs to ignore`)
+    .option('-l|--ignoredLanguages <languages...>', `A list of languages to ignore`)
+    .option('-c|--categories <categories...>', 'Language categories to include in output')
+    .option('-C|--childLanguages [bool]', 'Display child languages instead of their parents', false)
+    .option('-j|--json [bool]', 'Display the output as JSON', false)
+    .option('-t|--tree <traversal>', 'Which part of the output JSON to display (dot-delimited)')
+    .option('-F|--listFiles [bool]', 'Whether to list every matching file under the language results', false)
+    .option('-q|--quick [bool]', 'Skip complex language analysis (alias for -{A|I|H|S}=false)', false)
+    .option('-o|--offline [bool]', 'Use packaged data files instead of fetching latest from GitHub', false)
+    .option('-L|--calculateLines [bool]', 'Calculate lines of code totals', true)
+    .option('-V|--keepVendored [bool]', 'Prevent skipping over vendored/generated files', false)
+    .option('-B|--keepBinary [bool]', 'Prevent skipping over binary files', false)
+    .option('-r|--relativePaths [bool]', 'Convert absolute file paths to relative', false)
+    .option('-A|--checkAttributes [bool]', 'Force the checking of gitattributes files', true)
+    .option('-I|--checkIgnored [bool]', 'Force the checking of gitignore files', true)
+    .option('-D|--checkDetected [bool]', 'Force files marked with linguist-detectable to always appear in output', true)
+    .option('-H|--checkHeuristics [bool]', 'Apply heuristics to ambiguous languages', true)
+    .option('-S|--checkShebang [bool]', 'Check shebang lines for explicit classification', true)
+    .option('-M|--checkModeline [bool]', 'Check modelines for explicit classification', true)
+    .helpOption(`-h|--help`, 'Display this help message')
+    .version(package_json_1.default.version, '-v|--version', 'Display the installed version of linguist-js');
+commander_1.program.parse(process.argv);
+const args = commander_1.program.opts();
+// Normalise arguments
+for (const arg in args) {
+    const normalise = (val) => {
+        if (typeof val !== 'string')
+            return val;
+        val = val.replace(/^=/, '');
+        if (val.match(/true$|false$/))
+            val = val === 'true';
+        return val;
+    };
+    if (Array.isArray(args[arg]))
+        args[arg] = args[arg].map(normalise);
+    else
+        args[arg] = normalise(args[arg]);
+}
+// Run Linguist
+if (args.analyze)
+    (async () => {
+        // Fetch language data
+        const root = args.analyze === true ? '.' : args.analyze;
+        const data = await (0, index_1.default)(root, args);
+        const { files, languages, unknown } = data;
+        // Print output
+        if (!args.json) {
+            const sortedEntries = Object.entries(languages.results).sort((a, b) => a[1].bytes < b[1].bytes ? +1 : -1);
+            const totalBytes = languages.bytes;
+            console.log(`\n Analysed ${files.bytes.toLocaleString()} B from ${files.count} files with linguist-js`);
+            console.log(`\n Language analysis results: \n`);
+            let count = 0;
+            if (sortedEntries.length === 0)
+                console.log(`  None`);
+            // Collate files per language
+            const filesPerLanguage = {};
+            if (args.listFiles) {
+                for (const language of Object.keys(languages.results)) {
+                    filesPerLanguage[language] = [];
+                }
+                for (const [file, lang] of Object.entries(files.results)) {
+                    if (lang)
+                        filesPerLanguage[lang].push(file);
+                }
+            }
+            // List parsed results
+            for (const [lang, { bytes, lines, color }] of sortedEntries) {
+                const percent = (bytes) => bytes / (totalBytes || 1) * 100;
+                const fmtd = {
+                    index: (++count).toString().padStart(2, ' '),
+                    lang: lang.padEnd(24, ' '),
+                    percent: percent(bytes).toFixed(2).padStart(5, ' '),
+                    bytes: bytes.toLocaleString().padStart(10, ' '),
+                    loc: lines.code.toLocaleString().padStart(10, ' '),
+                    icon: colouredMsg(hexToRgb(color !== null && color !== void 0 ? color : '#ededed'), '\u2588'),
+                };
+                console.log(`  ${fmtd.index}. ${fmtd.icon} ${fmtd.lang} ${fmtd.percent}% ${fmtd.bytes} B ${fmtd.loc} LOC`);
+                // If using `listFiles` option, list all files tagged as this language
+                if (args.listFiles) {
+                    console.log(); // padding
+                    for (const file of filesPerLanguage[lang]) {
+                        let relFile = (0, norm_path_1.normPath)(node_path_1.default.relative(node_path_1.default.resolve('.'), file));
+                        if (!relFile.startsWith('../'))
+                            relFile = './' + relFile;
+                        const bytes = (await node_fs_1.default.promises.stat(file)).size;
+                        const fmtd2 = {
+                            file: relFile.padEnd(42, ' '),
+                            percent: percent(bytes).toFixed(2).padStart(5, ' '),
+                            bytes: bytes.toLocaleString().padStart(10, ' '),
+                        };
+                        console.log(`        ${fmtd.icon} ${fmtd2.file}  ${fmtd2.percent}% ${fmtd2.bytes} B`);
+                    }
+                    console.log(); // padding
+                }
+            }
+            if (!args.listFiles)
+                console.log(); // padding
+            console.log(` Total: ${totalBytes.toLocaleString()} B`);
+            // List unknown files/extensions
+            if (unknown.bytes > 0) {
+                console.log(`\n Unknown files and extensions:`);
+                for (const [name, bytes] of Object.entries(unknown.filenames)) {
+                    console.log(`  '${name}': ${bytes.toLocaleString()} B`);
+                }
+                for (const [ext, bytes] of Object.entries(unknown.extensions)) {
+                    console.log(`  '*${ext}': ${bytes.toLocaleString()} B`);
+                }
+                console.log(` Total: ${unknown.bytes.toLocaleString()} B`);
+            }
+        }
+        else if (args.tree) {
+            const treeParts = args.tree.split('.');
+            let nestedData = data;
+            for (const part of treeParts) {
+                if (!nestedData[part])
+                    throw Error(`TraversalError: Key '${part}' cannot be found on output object.`);
+                nestedData = nestedData[part];
+            }
+            console.log(nestedData);
+        }
+        else {
+            console.dir(data, { depth: null });
+        }
+    })();
+else {
+    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/src/helpers/convert-pcre.d.ts

@@ -0,0 +1,2 @@
+/** Convert a PCRE regex into JS. */
+export default function pcre(regex: string): RegExp;

package/dist/src/helpers/convert-pcre.js

@@ -0,0 +1,38 @@
+"use strict";
+Object.defineProperty(exports, "__esModule", { value: true });
+exports.default = pcre;
+/** Convert a PCRE regex into JS. */
+function pcre(regex) {
+    let finalRegex = regex;
+    const replace = (search, replace) => finalRegex = finalRegex.replace(search, replace);
+    const finalFlags = new Set();
+    // Convert inline flag declarations
+    const inlineMatches = regex.matchAll(/\?(-)?([a-z]):/g);
+    const startMatches = regex.matchAll(/\(\?(-)?([a-z]+)\)/g);
+    for (const [match, isNegative, flags] of [...inlineMatches, ...startMatches]) {
+        replace(match, '');
+        const func = (flag) => isNegative ? finalFlags.delete(flag) : finalFlags.add(flag);
+        [...flags].forEach(func);
+    }
+    // Remove PCRE-only syntax
+    replace(/([*+]){2}/g, '$1');
+    replace(/\(\?>/g, '(?:');
+    // Remove start/end-of-file markers
+    if (/\\[AZ]/.test(finalRegex)) {
+        replace(/\\A/g, '^');
+        replace(/\\Z/g, '$');
+        finalFlags.delete('m');
+    }
+    else {
+        finalFlags.add('m');
+    }
+    // Reformat free-spacing mode
+    if (finalFlags.has('x')) {
+        finalFlags.delete('x');
+        replace(/#.+/g, '');
+        replace(/^\s+|\s+$|\n/gm, '');
+        replace(/\s+/g, ' ');
+    }
+    // Return final regex
+    return RegExp(finalRegex, [...finalFlags].join(''));
+}