linguist-js 2.7.1 → 2.8.0

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/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

@@ -21,10 +21,12 @@ 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,
         };

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

@@ -8,7 +8,7 @@ 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 +20,4 @@ async function readFile(filename, onlyFirstLine = false) {
     }
     return content;
 }
-exports.default = readFile;
+exports.default = readFileChunk;

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,
         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/types.d.ts

@@ -19,7 +19,9 @@ export interface Options {
     childLanguages?: boolean;
     quick?: boolean;
     offline?: boolean;
+    calculateLines?: boolean;
     checkIgnored?: boolean;
+    checkDetected?: boolean;
     checkAttributes?: boolean;
     checkHeuristics?: boolean;
     checkShebang?: boolean;
@@ -29,6 +31,11 @@ export interface Results {
     files: {
         count: Integer;
         bytes: Bytes;
+        lines: {
+            total: Integer;
+            content: Integer;
+            code: Integer;
+        };
         /** Note: Results use slashes as delimiters even on Windows. */
         results: Record<FilePath, LanguageResult>;
         alternatives: Record<FilePath, LanguageResult[]>;
@@ -36,8 +43,18 @@ export interface Results {
     languages: {
         count: Integer;
         bytes: Bytes;
+        lines: {
+            total: Integer;
+            content: Integer;
+            code: Integer;
+        };
         results: Record<Language, {
             bytes: Bytes;
+            lines: {
+                total: Integer;
+                content: Integer;
+                code: Integer;
+            };
             type: Category;
             parent?: Language;
             color?: `#${string}`;
@@ -46,6 +63,11 @@ export interface Results {
     unknown: {
         count: Integer;
         bytes: Bytes;
+        lines: {
+            total: Integer;
+            content: Integer;
+            code: Integer;
+        };
         extensions: Record<string, Bytes>;
         filenames: Record<string, Bytes>;
     };

package/ext/generated.rb

@@ -8,7 +8,9 @@
 - (Gopkg|glide)\.lock
 - poetry\.lock
 - pdm\.lock
+- uv\.lock
 - (^|\/)(\w+\.)?esy.lock$
+- deno\.lock
 - npm-shrinkwrap\.json
 - package-lock\.json
 - pnpm-lock\.yaml
@@ -17,7 +19,9 @@
 - composer\.lock
 - .\.zep\.(?:c|h|php)$
 - Cargo\.lock
+- Cargo\.toml\.orig
 - (^|\/)flake\.lock$
+- (^|\/)MODULE\.bazel\.lock$
 - Pipfile\.lock
 - (?:^|\/)\.terraform\.lock\.hcl$
 - ppport\.h$

package/ext/heuristics.yml

@@ -59,6 +59,8 @@ disambiguations:
   - language: Asymptote
 - extensions: ['.bas']
   rules:
+  - language: B4X
+    pattern: '\A\W{0,3}(?:.*(?:\r?\n|\r)){0,9}B4(?:J|A|R|i)=true'
   - language: FreeBasic
     pattern: '^[ \t]*#(?i)(?:define|endif|endmacro|ifn?def|include|lang|macro)(?:$|\s)'
   - language: BASIC
@@ -107,6 +109,11 @@ disambiguations:
   rules:
   - language: XML
     pattern: '^(\s*)(?i:<Project|<Import|<Property|<?xml|xmlns)'
+- extensions: ['.cairo']
+  rules:
+    - language: Cairo Zero
+      pattern: '(^(\s*)%lang(\s+)([A-Za-z0-9_]+))|(^(\s*)%builtins(\s+)([A-Za-z0-9_]+\s*)*$)|(^(\s*)from(\s+)starkware\.(cairo|starknet)\.([A-Za-z0-9_.\s]+?)import)|(,\s*ap\+\+;$)|(;\s*ap\+\+$)'
+    - language: Cairo
 - extensions: ['.ch']
   rules:
   - language: xBase
@@ -190,7 +197,7 @@ disambiguations:
   - language: Erlang
     pattern: '^\s*(?:%%|main\s*\(.*?\)\s*->)'
   - language: JavaScript
-    pattern: '\/\/|("|'')use strict\1|export\s+default\s|\/\*(?:.|[\r\n])*?\*\/'
+    pattern: '\/\/|["'']use strict["'']|export\s+default\s|\/\*(?:.|[\r\n])*?\*\/'
 - extensions: ['.ex']
   rules:
   - language: Elixir
@@ -315,7 +322,7 @@ disambiguations:
 - extensions: ['.ice']
   rules:
   - language: JSON
-    pattern: '\A\s*[{\[]'
+    named_pattern: json
   - language: Slice
 - extensions: ['.inc']
   rules:
@@ -433,6 +440,8 @@ disambiguations:
   rules:
   - language: XML
     pattern: '<!ENTITY '
+  - language: NMODL
+    pattern: '\b(NEURON|INITIAL|UNITS)\b'
   - language: Modula-2
     pattern: '^\s*(?i:MODULE|END) [\w\.]+;'
   - language: [Linux Kernel Module, AMPL]
@@ -470,6 +479,11 @@ disambiguations:
   - language: NL
     pattern: '^(b|g)[0-9]+ '
   - language: NewLisp
+- extensions: ['.nr']
+  rules:
+  - language: Roff
+    pattern: '^\.'
+  - language: Noir
 - extensions: ['.nu']
   rules:
   - language: Nushell
@@ -494,6 +508,13 @@ disambiguations:
     pattern: '<\?hh'
   - language: PHP
     pattern: '<\?[^h]'
+- extensions: ['.pkl']
+  rules:
+    - language: Pkl
+      pattern:
+      - '^\s*(module|import|amends|extends|local|const|fixed|abstract|open|class|typealias|@\w+)\b'
+      - '^\s*[a-zA-Z0-9_$]+\s*(=|{|:)|^\s*`[^`]+`\s*(=|{|:)|for\s*\(|when\s*\('
+    - language: Pickle
 - extensions: ['.pl']
   rules:
   - language: Prolog
@@ -507,7 +528,7 @@ disambiguations:
 - extensions: ['.plist']
   rules:
   - language: XML Property List
-    pattern: '^\s*(?:<\?xml\s|<!DOCTYPE\s+plist|<plist(?:\s+version\s*=\s*(["''])\d+(?:\.\d+)?\1)?\s*>\s*$)'
+    pattern: '^\s*(?:<\?xml\s|<!DOCTYPE\s+plist|<plist(?:\s+version\s*=\s*["'']\d+(?:\.\d+)?["''])?\s*>\s*$)'
   - language: OpenStep Property List
 - extensions: ['.plt']
   rules:
@@ -599,6 +620,11 @@ disambiguations:
     pattern:
     - '^\s*(let|module|type)\s+\w*\s+=\s+'
     - '^\s*(?:include|open)\s+\w+\s*$'
+- extensions: ['.resource']
+  rules:
+  - language: RobotFramework
+    pattern:
+    - '^\*{3} (Settings|Variables|Keywords) \*{3}$'
 - extensions: ['.rno']
   rules:
   - language: RUNOFF
@@ -720,6 +746,10 @@ disambiguations:
   rules:
   - language: Vim Help File
     pattern: '(?:(?:^|[ \t])(?:vi|Vi(?=m))(?:m[<=>]?[0-9]+|m)?|[ \t]ex)(?=:(?=[ \t]*set?[ \t][^\r\n:]+:)|:(?![ \t]*set?[ \t]))(?:(?:[ \t]*:[ \t]*|[ \t])\w*(?:[ \t]*=(?:[^\\\s]|\\.)*)?)*[ \t:](?:filetype|ft|syntax)[ \t]*=(help)(?=$|\s|:)'
+  - language: Hosts File
+    pattern: '(?xi) ^(?<ipv4>(?!\.)(?:\.?(?: 25[0-5]|   2[0-4]\d|   1\d\d|   [1-9]?\d)\b){4})(?<cidr>/(3[0-2]|[12]?\d)\b)?(?<domains>[ \t]+\w[-\w]* (?:\.\w[-\w]*)*(?<!-)\b)*+'
+
+      (?=$|\s)
   - language: Adblock Filter List
     pattern: '\A\[(?<version>(?:[Aa]d[Bb]lock(?:[ \t][Pp]lus)?|u[Bb]lock(?:[ \t][Oo]rigin)?|[Aa]d[Gg]uard)(?:[ \t] \d+(?:\.\d+)*+)?)(?:[ \t]?;[ \t]?\g<version>)*+\]'
   - language: Text
@@ -745,6 +775,12 @@ disambiguations:
   - language: Vim Script
     pattern: '^UseVimball'
   - language: VBA
+- extensions: ['.vcf']
+  rules:
+  - language: TSV
+    pattern: '\A##fileformat=VCF'
+  - language: vCard
+    pattern: '\ABEGIN:VCARD'
 - extensions: ['.w']
   rules:
   - language: OpenEdge ABL
@@ -774,7 +810,7 @@ disambiguations:
 - extensions: ['.yy']
   rules:
   - language: JSON
-    pattern: '\"modelName\"\:\s*\"GM'
+    named_pattern: json
   - language: Yacc
 named_patterns:
   cpp:
@@ -796,6 +832,7 @@ named_patterns:
   - '^\s*(?>(?:autoexec|private)\s+){0,2}function\s+(?>(?:autoexec|private)\s+){0,2}\w+\s*\('
   - '\b(?:level|self)[ \t]+thread[ \t]+(?:\[\[[ \t]*(?>\w+\.)*\w+[ \t]*\]\]|\w+)[ \t]*\([^\r\n\)]*\)[ \t]*;'
   - '^[ \t]*#[ \t]*(?:precache|using_animtree)[ \t]*\('
+  json: '\A\s*[{\[]'
   key_equals_value: '^[^#!;][^=]*='
   m68k:
   - '(?im)\bmoveq(?:\.l)?\s+#(?:\$-?[0-9a-f]{1,3}|%[0-1]{1,8}|-?[0-9]{1,3}),\s*d[0-7]\b'

package/ext/languages.yml

@@ -463,6 +463,18 @@ Awk:
   tm_scope: source.awk
   ace_mode: text
   language_id: 28
+B4X:
+  type: programming
+  color: "#00e4ff"
+  extensions:
+  - ".bas"
+  tm_scope: source.vba
+  aliases:
+  - basic for android
+  ace_mode: text
+  codemirror_mode: vb
+  codemirror_mime_type: text/x-vb
+  language_id: 96642275
 BASIC:
   type: programming
   extensions:
@@ -471,6 +483,14 @@ BASIC:
   ace_mode: text
   color: "#ff0000"
   language_id: 28923963
+BQN:
+  type: programming
+  color: "#2b7067"
+  extensions:
+  - ".bqn"
+  tm_scope: source.bqn
+  ace_mode: text
+  language_id: 330386870
 Ballerina:
   type: programming
   extensions:
@@ -896,6 +916,18 @@ Cabal Config:
   codemirror_mime_type: text/x-haskell
   tm_scope: source.cabal
   language_id: 677095381
+Caddyfile:
+  type: data
+  color: "#22b638"
+  aliases:
+  - Caddy
+  extensions:
+  - ".caddyfile"
+  filenames:
+  - Caddyfile
+  ace_mode: text
+  tm_scope: source.Caddyfile
+  language_id: 615465151
 Cadence:
   type: programming
   color: "#00ef8b"
@@ -911,7 +943,17 @@ Cairo:
   tm_scope: source.cairo
   extensions:
   - ".cairo"
+  group: Cairo
   language_id: 620599567
+Cairo Zero:
+  type: programming
+  color: "#ff4a48"
+  ace_mode: text
+  tm_scope: source.cairo0
+  extensions:
+  - ".cairo"
+  group: Cairo
+  language_id: 891399890
 CameLIGO:
   type: programming
   color: "#3be133"
@@ -931,6 +973,16 @@ Cap'n Proto:
   - ".capnp"
   ace_mode: text
   language_id: 52
+Carbon:
+  type: programming
+  color: "#222222"
+  extensions:
+  - ".carbon"
+  ace_mode: golang
+  codemirror_mode: go
+  codemirror_mime_type: text/x-go
+  tm_scope: source.v
+  language_id: 55627273
 CartoCSS:
   type: programming
   aliases:
@@ -1344,6 +1396,17 @@ Cycript:
   codemirror_mode: javascript
   codemirror_mime_type: text/javascript
   language_id: 78
+Cylc:
+  type: data
+  color: "#00b3fd"
+  extensions:
+  - ".cylc"
+  filenames:
+  - suite.rc
+  tm_scope: source.cylc
+  ace_mode: ini
+  group: INI
+  language_id: 476447814
 Cypher:
   type: programming
   color: "#34c0eb"
@@ -1571,6 +1634,14 @@ Dotenv:
   tm_scope: source.dotenv
   ace_mode: text
   language_id: 111148035
+Dune:
+  type: programming
+  ace_mode: lisp
+  filenames:
+  - dune-project
+  tm_scope: source.dune
+  color: "#89421e"
+  language_id: 754574151
 Dylan:
   type: programming
   color: "#6c616e"
@@ -1916,6 +1987,14 @@ FIGlet Font:
   tm_scope: source.figfont
   ace_mode: text
   language_id: 686129783
+FIRRTL:
+  type: programming
+  color: "#2f632f"
+  extensions:
+  - ".fir"
+  tm_scope: source.firrtl
+  ace_mode: text
+  language_id: 906694254
 FLUX:
   type: programming
   color: "#88ccff"
@@ -2654,7 +2733,7 @@ HCL:
   ace_mode: ruby
   codemirror_mode: ruby
   codemirror_mime_type: text/x-ruby
-  tm_scope: source.terraform
+  tm_scope: source.hcl
   language_id: 144
 HLSL:
   type: programming
@@ -2883,6 +2962,7 @@ Hosts File:
   filenames:
   - HOSTS
   - hosts
+  - hosts.txt
   aliases:
   - hosts
   tm_scope: source.hosts
@@ -3176,6 +3256,7 @@ JSON:
   - ".tern-config"
   - ".tern-project"
   - ".watchmanconfig"
+  - MODULE.bazel.lock
   - Pipfile.lock
   - composer.lock
   - deno.lock
@@ -3197,6 +3278,7 @@ JSON with Comments:
   - ".code-snippets"
   - ".code-workspace"
   - ".sublime-build"
+  - ".sublime-color-scheme"
   - ".sublime-commands"
   - ".sublime-completions"
   - ".sublime-keymap"
@@ -3310,6 +3392,17 @@ Java Server Pages:
   codemirror_mode: htmlembedded
   codemirror_mime_type: application/x-jsp
   language_id: 182
+Java Template Engine:
+  type: programming
+  color: "#2A6277"
+  group: Java
+  aliases:
+  - jte
+  extensions:
+  - ".jte"
+  ace_mode: text
+  tm_scope: text.html.jte
+  language_id: 599494012
 JavaScript:
   type: programming
   tm_scope: source.js
@@ -3462,6 +3555,13 @@ Julia:
   codemirror_mode: julia
   codemirror_mime_type: text/x-julia
   language_id: 184
+Julia REPL:
+  type: programming
+  color: "#a270ba"
+  tm_scope: source.julia.console
+  group: Julia
+  ace_mode: text
+  language_id: 220689142
 Jupyter Notebook:
   type: markup
   ace_mode: json
@@ -3483,9 +3583,14 @@ Just:
   color: "#384d54"
   tm_scope: source.just
   filenames:
+  - ".JUSTFILE"
+  - ".Justfile"
+  - ".justfile"
   - JUSTFILE
   - Justfile
   - justfile
+  extensions:
+  - ".just"
   ace_mode: text
   language_id: 128447695
 KRL:
@@ -3823,6 +3928,14 @@ Literate Haskell:
   codemirror_mode: haskell-literate
   codemirror_mime_type: text/x-literate-haskell
   language_id: 207
+LiveCode Script:
+  type: programming
+  color: "#0c5ba5"
+  extensions:
+  - ".livecodescript"
+  tm_scope: source.livecodescript
+  ace_mode: text
+  language_id: 891017
 LiveScript:
   type: programming
   color: "#499886"
@@ -3896,6 +4009,18 @@ Lua:
   interpreters:
   - lua
   language_id: 213
+Luau:
+  type: programming
+  tm_scope: source.luau
+  ace_mode: lua
+  codemirror_mode: lua
+  codemirror_mime_type: text/x-lua
+  color: "#00A2FF"
+  extensions:
+  - ".luau"
+  interpreters:
+  - luau
+  language_id: 365050359
 M:
   type: programming
   aliases:
@@ -4431,6 +4556,14 @@ NL:
   tm_scope: none
   ace_mode: text
   language_id: 241
+NMODL:
+  type: programming
+  color: "#00356B"
+  extensions:
+  - ".mod"
+  tm_scope: none
+  ace_mode: text
+  language_id: 136456478
 NPM Config:
   type: data
   color: "#cb3837"
@@ -4596,6 +4729,18 @@ Nix:
   tm_scope: source.nix
   ace_mode: nix
   language_id: 252
+Noir:
+  type: programming
+  aliases:
+  - nargo
+  ace_mode: rust
+  codemirror_mode: rust
+  codemirror_mime_type: text/x-rustsrc
+  extensions:
+  - ".nr"
+  color: "#2f1f49"
+  tm_scope: source.nr
+  language_id: 813068465
 Nu:
   type: programming
   color: "#c9df40"
@@ -4990,7 +5135,8 @@ PEG.js:
   color: "#234d6b"
   extensions:
   - ".pegjs"
-  tm_scope: source.pegjs
+  - ".peggy"
+  tm_scope: source.peggy
   ace_mode: javascript
   codemirror_mode: javascript
   codemirror_mime_type: text/javascript
@@ -5256,6 +5402,16 @@ Pip Requirements:
   ace_mode: text
   tm_scope: source.pip-requirements
   language_id: 684385621
+Pkl:
+  type: programming
+  color: "#6b9543"
+  extensions:
+  - ".pkl"
+  interpreters:
+  - pkl
+  tm_scope: source.pkl
+  ace_mode: text
+  language_id: 288822799
 PlantUML:
   type: data
   color: "#fbbd16"
@@ -5351,7 +5507,7 @@ PowerBuilder:
   - ".sra"
   - ".sru"
   - ".srw"
-  tm_scope: none
+  tm_scope: source.powerbuilder
   ace_mode: text
   language_id: 292
 PowerShell:
@@ -5733,6 +5889,14 @@ RMarkdown:
   - ".rmd"
   tm_scope: text.md
   language_id: 313
+RON:
+  type: data
+  color: "#a62c00"
+  extensions:
+  - ".ron"
+  ace_mode: rust
+  tm_scope: source.ron
+  language_id: 587855233
 RPC:
   type: programming
   aliases:
@@ -6008,6 +6172,7 @@ RobotFramework:
   color: "#00c0b5"
   extensions:
   - ".robot"
+  - ".resource"
   tm_scope: text.robot
   ace_mode: text
   language_id: 324
@@ -6500,6 +6665,7 @@ Shell:
   - shell-script
   - bash
   - zsh
+  - envrc
   extensions:
   - ".sh"
   - ".bash"
@@ -6522,6 +6688,7 @@ Shell:
   - ".bash_profile"
   - ".bashrc"
   - ".cshrc"
+  - ".envrc"
   - ".flaskenv"
   - ".kshrc"
   - ".login"
@@ -6957,10 +7124,12 @@ TOML:
   - ".toml"
   filenames:
   - Cargo.lock
+  - Cargo.toml.orig
   - Gopkg.lock
   - Pipfile
   - pdm.lock
   - poetry.lock
+  - uv.lock
   tm_scope: source.toml
   ace_mode: toml
   codemirror_mode: toml
@@ -6981,6 +7150,9 @@ TSV:
   tm_scope: source.generic-db
   extensions:
   - ".tsv"
+  - ".vcf"
+  aliases:
+  - tab-seperated values
   language_id: 1035892117
 TSX:
   type: programming
@@ -7248,6 +7420,7 @@ TypeScript:
   interpreters:
   - deno
   - ts-node
+  - tsx
   extensions:
   - ".ts"
   - ".cts"
@@ -7464,6 +7637,7 @@ Vim Script:
   - vim
   - viml
   - nvim
+  - vimscript
   extensions:
   - ".vim"
   - ".vba"
@@ -7520,7 +7694,7 @@ Visual Basic 6.0:
   - ".ctl"
   - ".Dsr"
   - ".frm"
-  tm_scope: source.vbnet
+  tm_scope: source.vba
   aliases:
   - vb6
   - vb 6
@@ -8147,6 +8321,7 @@ Zig:
   color: "#ec915c"
   extensions:
   - ".zig"
+  - ".zig.zon"
   tm_scope: source.zig
   ace_mode: text
   language_id: 646424281
@@ -8171,6 +8346,17 @@ cURL Config:
   tm_scope: source.curlrc
   ace_mode: text
   language_id: 992375436
+crontab:
+  type: data
+  color: "#ead7ac"
+  aliases:
+  - cron
+  - cron table
+  filenames:
+  - crontab
+  tm_scope: text.crontab
+  ace_mode: tcl
+  language_id: 705203557
 desktop:
   type: data
   extensions:
@@ -8231,6 +8417,19 @@ hoon:
   extensions:
   - ".hoon"
   language_id: 560883276
+iCalendar:
+  type: data
+  color: "#ec564c"
+  extensions:
+  - ".ics"
+  - ".ical"
+  tm_scope: source.iCalendar
+  aliases:
+  - iCal
+  ace_mode: properties
+  codemirror_mode: properties
+  codemirror_mime_type: text/x-properties
+  language_id: 98384424
 jq:
   color: "#c7254e"
   ace_mode: text
@@ -8353,6 +8552,27 @@ sed:
   ace_mode: text
   tm_scope: source.sed
   language_id: 847830017
+templ:
+  type: markup
+  color: "#66D0DD"
+  extensions:
+  - ".templ"
+  ace_mode: text
+  tm_scope: source.templ
+  language_id: 795579337
+vCard:
+  type: data
+  color: "#ee2647"
+  extensions:
+  - ".vcf"
+  tm_scope: source.vcard
+  aliases:
+  - virtual contact file
+  - electronic business card
+  ace_mode: properties
+  codemirror_mode: properties
+  codemirror_mime_type: text/x-properties
+  language_id: 851476558
 wisp:
   type: programming
   ace_mode: clojure

package/package.json

@@ -1,6 +1,6 @@
 {
 	"name": "linguist-js",
-	"version": "2.7.1",
+	"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": {
@@ -11,7 +11,7 @@
 		"node": ">=12"
 	},
 	"scripts": {
-		"download-files": "npx tsx@4 build/download-files",
+		"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"
@@ -38,11 +38,11 @@
 	},
 	"homepage": "https://github.com/Nixinova/Linguist#readme",
 	"dependencies": {
-		"binary-extensions": "^2.2.0 <3",
+		"binary-extensions": "^2.3.0 <3",
 		"commander": "^9.5.0 <10",
 		"common-path-prefix": "^3.0.0",
 		"cross-fetch": "^3.1.8 <4",
-		"ignore": "^5.3.1",
+		"ignore": "^5.3.2",
 		"isbinaryfile": "^4.0.10 <5",
 		"js-yaml": "^4.1.0",
 		"node-cache": "^5.1.2"

package/readme.md

@@ -50,6 +50,11 @@ Running LinguistJS on this folder will return the following JSON:
   "files": {
     "count": 5,
     "bytes": 6020,
+	"lines": {
+		"total": 100,
+		"content": 90,
+		"code": 80,
+	},
     "results": {
       "/src/index.ts": "TypeScript",
       "/src/cli.js": "JavaScript",
@@ -64,16 +69,26 @@ Running LinguistJS on this folder will return the following JSON:
   "languages": {
     "count": 3,
     "bytes": 6010,
+	"lines": {
+		"total": 90,
+		"content": 80,
+		"code": 70,
+	},
     "results": {
-        "JavaScript": { "type": "programming", "bytes": 1000, "color": "#f1e05a" },
-        "Markdown": { "type": "prose", "bytes": 3000, "color": "#083fa1" },
-        "Ruby": { "type": "programming", "bytes": 10, "color": "#701516" },
-        "TypeScript": { "type": "programming", "bytes": 2000, "color": "#2b7489" },
+        "JavaScript": { "type": "programming", "bytes": 1000, "lines": { "total": 49, "content": 49, "code": 44 }, "color": "#f1e05a" },
+        "Markdown": { "type": "prose", "bytes": 3000, "lines": { "total": 10, "content": 5, "code": 5 }, "color": "#083fa1" },
+        "Ruby": { "type": "programming", "bytes": 10, "lines": { "total": 1, "content": 1, "code": 1 }, "color": "#701516" },
+        "TypeScript": { "type": "programming", "bytes": 2000, "lines": { "total": 30, "content": 25, "code": 20 }, "color": "#2b7489" },
     },
   },
   "unknown": {
     "count": 1,
     "bytes": 10,
+	"lines": {
+		"total": 10,
+		"content": 10,
+		"code": 10,
+	},
     "filenames": {
       "no-lang": 10,
     },
@@ -127,9 +142,11 @@ const { files, languages, unknown } = await linguist(fileNames, { fileContent, .
       Whether to display sub-languages instead of their parents when possible (defaults to `false`).
     - `quick` (boolean):
       Whether to skip complex language analysis such as the checking of heuristics and gitattributes statements (defaults to `false`).
-      Alias for `checkAttributes:false, checkIgnored:false, checkHeuristics:false, checkShebang:false, checkModeline:false`.
+      Alias for `checkAttributes:false, checkIgnored:false, checkDetected:false, checkHeuristics:false, checkShebang:false, checkModeline:false`.
     - `offline` (boolean):
       Whether to use pre-packaged metadata files instead of fetching them from GitHub at runtime (defaults to `false`).
+    - `calculateLines` (boolean):
+      Whether to calculate line of code totals (defaults to `true`).
     - `keepVendored` (boolean):
       Whether to keep vendored files (dependencies, etc) (defaults to `false`).
       Does nothing when `fileContent` is set.
@@ -143,6 +160,8 @@ const { files, languages, unknown } = await linguist(fileNames, { fileContent, .
     - `checkIgnored` (boolean):
       Force the checking of `.gitignore` files (defaults to `true` unless `quick` is set).
       Does nothing when `fileContent` is set.
+    - `checkDetected` (boolean):
+      Force files marked with `linguist-detectable` to show up in the output, even if the file is not part of the declared `categories`.
     - `checkHeuristics` (boolean):
       Apply heuristics to ambiguous languages (defaults to `true` unless `quick` is set).
     - `checkShebang` (boolean):
@@ -187,6 +206,8 @@ linguist --version
     Alias for `--checkAttributes=false --checkIgnored=false --checkHeuristics=false --checkShebang=false --checkModeline=false`.
   - `--offline`:
     Use pre-packaged metadata files instead of fetching them from GitHub at runtime.
+  - `--calculateLines`:
+    Calculate line of code totals from files.
   - `--keepVendored`:
     Include vendored files (auto-generated files, dependencies folder, etc) in the output.
   - `--keepBinary`:
@@ -199,6 +220,9 @@ linguist --version
   - `--checkIgnored`:
     Force the checking of `.gitignore` files.
     Use alongside `--quick` to override it disabling this option.
+  - `--checkDetected`:
+    Force files marked with `linguist-detectable` to show up in the output, even if the file is not part of the declared `--categories`.
+    Use alongside `--quick` to override it disabling this option.
   - `--checkHeuristics`:
     Apply heuristics to ambiguous languages.
     Use alongside `--quick` to override it disabling this option.