project-librarian 0.4.0 → 0.4.2

package/dist/code-index/evidence.js

@@ -0,0 +1,79 @@
+"use strict";
+Object.defineProperty(exports, "__esModule", { value: true });
+exports.collectCodeEvidence = collectCodeEvidence;
+const ownership_1 = require("./ownership");
+const search_1 = require("./search");
+function sortedUnique(values) {
+    return Array.from(new Set(values.filter(Boolean))).sort();
+}
+function ownerRowsForFilePaths(filePaths, options) {
+    const ownership = (0, ownership_1.ownershipContext)();
+    const ownersByName = new Map();
+    for (const filePath of filePaths) {
+        const info = (0, ownership_1.ownershipInfo)(filePath, ownership);
+        const current = ownersByName.get(info.owner) ?? {
+            codeowners: new Set(),
+            files: 0,
+            owner: info.owner,
+            owner_source: info.owner_source,
+            sample_files: [],
+        };
+        current.files += 1;
+        if (current.sample_files.length < options.ownerSampleLimit)
+            current.sample_files.push(filePath);
+        if (options.includeOwnerCodeowners && info.codeowners) {
+            for (const owner of info.codeowners.split(", ").filter(Boolean))
+                current.codeowners.add(owner);
+        }
+        ownersByName.set(info.owner, current);
+    }
+    return Array.from(ownersByName.values()).map((owner) => {
+        const row = {
+            files: owner.files,
+            owner: owner.owner,
+            owner_source: owner.owner_source,
+            sample_files: owner.sample_files,
+        };
+        if (options.includeOwnerCodeowners)
+            row.codeowners = Array.from(owner.codeowners).sort().join(", ");
+        return row;
+    }).sort((left, right) => right.files - left.files || left.owner.localeCompare(right.owner));
+}
+function collectCodeEvidence(database, query, options) {
+    const normalized = query.trim();
+    const like = (0, search_1.containsLikePattern)(normalized);
+    const files = (0, search_1.searchFiles)(database, normalized, options.fileLimit);
+    const symbols = (0, search_1.searchSymbols)(database, normalized, options.symbolLimit);
+    const routes = database.prepare("SELECT method, route, file_path, line, handler FROM routes WHERE route LIKE ? ESCAPE '\\' OR handler LIKE ? ESCAPE '\\' OR file_path LIKE ? ESCAPE '\\' ORDER BY file_path, line LIMIT ?").all(like, like, like, options.routeLimit);
+    const imports = database.prepare("SELECT from_file, to_ref, imported, line, raw FROM imports WHERE from_file LIKE ? ESCAPE '\\' OR to_ref LIKE ? ESCAPE '\\' OR imported LIKE ? ESCAPE '\\' ORDER BY from_file, line LIMIT ?").all(like, like, like, options.importLimit);
+    const outgoingEdges = options.includeEdgeEvidenceMatches
+        ? database.prepare("SELECT kind, source_kind, source, target_kind, target, file_path, line, evidence FROM edges WHERE file_path LIKE ? ESCAPE '\\' OR source LIKE ? ESCAPE '\\' OR evidence LIKE ? ESCAPE '\\' ORDER BY file_path, line LIMIT ?").all(like, like, like, options.edgeLimit)
+        : database.prepare("SELECT kind, source_kind, source, target_kind, target, file_path, line, evidence FROM edges WHERE file_path LIKE ? ESCAPE '\\' OR source LIKE ? ESCAPE '\\' ORDER BY file_path, line LIMIT ?").all(like, like, options.edgeLimit);
+    const incomingEdges = options.includeEdgeEvidenceMatches
+        ? database.prepare("SELECT kind, source_kind, source, target_kind, target, file_path, line, evidence FROM edges WHERE target LIKE ? ESCAPE '\\' OR evidence LIKE ? ESCAPE '\\' ORDER BY file_path, line LIMIT ?").all(like, like, options.edgeLimit)
+        : database.prepare("SELECT kind, source_kind, source, target_kind, target, file_path, line, evidence FROM edges WHERE target LIKE ? ESCAPE '\\' ORDER BY file_path, line LIMIT ?").all(like, options.edgeLimit);
+    const routeTargets = routes.map((row) => `${String(row.method)} ${String(row.route)}`);
+    const routeEdges = options.includeRouteEdges && routeTargets.length > 0
+        ? database.prepare(`SELECT kind, source_kind, source, target_kind, target, file_path, line, evidence FROM edges WHERE source IN (${routeTargets.map(() => "?").join(", ")}) ORDER BY file_path, line LIMIT ?`).all(...routeTargets, options.routeEdgeLimit)
+        : [];
+    const relatedFilePaths = sortedUnique([
+        ...files.map((row) => String(row.path ?? "")),
+        ...symbols.map((row) => String(row.file_path ?? "")),
+        ...routes.map((row) => String(row.file_path ?? "")),
+        ...imports.map((row) => String(row.from_file ?? "")),
+        ...outgoingEdges.map((row) => String(row.file_path ?? "")),
+        ...incomingEdges.map((row) => String(row.file_path ?? "")),
+        ...routeEdges.map((row) => String(row.file_path ?? "")),
+    ]);
+    return {
+        files,
+        imports,
+        incomingEdges,
+        owners: ownerRowsForFilePaths(relatedFilePaths, options),
+        relatedFilePaths,
+        outgoingEdges,
+        routeEdges,
+        routes,
+        symbols,
+    };
+}

package/dist/code-index/extractors/config.js

@@ -0,0 +1,58 @@
+"use strict";
+var __createBinding = (this && this.__createBinding) || (Object.create ? (function(o, m, k, k2) {
+    if (k2 === undefined) k2 = k;
+    var desc = Object.getOwnPropertyDescriptor(m, k);
+    if (!desc || ("get" in desc ? !m.__esModule : desc.writable || desc.configurable)) {
+      desc = { enumerable: true, get: function() { return m[k]; } };
+    }
+    Object.defineProperty(o, k2, desc);
+}) : (function(o, m, k, k2) {
+    if (k2 === undefined) k2 = k;
+    o[k2] = m[k];
+}));
+var __setModuleDefault = (this && this.__setModuleDefault) || (Object.create ? (function(o, v) {
+    Object.defineProperty(o, "default", { enumerable: true, value: v });
+}) : function(o, v) {
+    o["default"] = v;
+});
+var __importStar = (this && this.__importStar) || (function () {
+    var ownKeys = function(o) {
+        ownKeys = Object.getOwnPropertyNames || function (o) {
+            var ar = [];
+            for (var k in o) if (Object.prototype.hasOwnProperty.call(o, k)) ar[ar.length] = k;
+            return ar;
+        };
+        return ownKeys(o);
+    };
+    return function (mod) {
+        if (mod && mod.__esModule) return mod;
+        var result = {};
+        if (mod != null) for (var k = ownKeys(mod), i = 0; i < k.length; i++) if (k[i] !== "default") __createBinding(result, mod, k[i]);
+        __setModuleDefault(result, mod);
+        return result;
+    };
+})();
+Object.defineProperty(exports, "__esModule", { value: true });
+exports.indexConfigs = indexConfigs;
+const path = __importStar(require("node:path"));
+const shared_1 = require("./shared");
+function indexConfigs(file, insertConfig) {
+    if (path.basename(file.path) === "package.json") {
+        try {
+            const parsed = JSON.parse(file.text);
+            for (const [name, value] of Object.entries(parsed.scripts ?? {}))
+                insertConfig.run(`script:${name}`, value, file.path, 1);
+            for (const [name, value] of Object.entries(parsed.dependencies ?? {}))
+                insertConfig.run(`dependency:${name}`, value, file.path, 1);
+            for (const [name, value] of Object.entries(parsed.devDependencies ?? {}))
+                insertConfig.run(`devDependency:${name}`, value, file.path, 1);
+        }
+        catch {
+            insertConfig.run("parse-error", "package.json is not valid JSON", file.path, 1);
+        }
+        return;
+    }
+    (0, shared_1.insertMatches)(file, /^\s*([A-Za-z0-9_.-]+)\s*[:=]\s*(.+)$/gm, (match, line) => {
+        insertConfig.run(match[1] ?? "", (match[2] ?? "").trim(), file.path, line);
+    });
+}

package/dist/code-index/extractors/light-languages.js

@@ -0,0 +1,52 @@
+"use strict";
+Object.defineProperty(exports, "__esModule", { value: true });
+exports.indexPythonLight = indexPythonLight;
+exports.indexGoLight = indexGoLight;
+const shared_1 = require("./shared");
+function indexPythonLight(file, statements) {
+    const symbolPatterns = [
+        [/^\s*def\s+([A-Za-z_]\w*)\s*\(([^)]*)\)/gm, "function", (match) => `def ${match[1] ?? ""}(${match[2] ?? ""})`],
+        [/^\s*class\s+([A-Za-z_]\w*)/gm, "class", (match) => `class ${match[1] ?? ""}`],
+    ];
+    for (const [regex, kind, signature] of symbolPatterns) {
+        (0, shared_1.insertMatches)(file, regex, (match, line) => (0, shared_1.insertSymbol)(statements, match[1] ?? "", kind, file, line, signature(match)));
+    }
+    const importPatterns = [
+        [/^\s*from\s+([A-Za-z0-9_.$]+)\s+import\s+(.+)$/gm, (match) => [match[1] ?? "", match[2] ?? ""]],
+        [/^\s*import\s+([A-Za-z0-9_.$, \t]+)$/gm, (match) => [match[1] ?? "", ""]],
+    ];
+    for (const [regex, fields] of importPatterns) {
+        (0, shared_1.insertMatches)(file, regex, (match, line) => {
+            const [toRef, imported] = fields(match);
+            statements.insertImport.run(file.path, toRef, imported.trim(), line, match[0].trim());
+            (0, shared_1.insertEdge)(statements, "import", "file", file.path, "module", toRef, file, line, match[0].trim());
+        });
+    }
+}
+function indexGoLight(file, statements) {
+    const symbolPatterns = [
+        [/^\s*func\s*\(\s*[^)]*\)\s*([A-Za-z_]\w*)\s*\(([^)]*)\)/gm, "method", (match) => match[1] ?? "", (match) => `func (...) ${match[1] ?? ""}(${match[2] ?? ""})`],
+        [/^\s*func\s+([A-Za-z_]\w*)\s*\(([^)]*)\)/gm, "function", (match) => match[1] ?? "", (match) => `func ${match[1] ?? ""}(${match[2] ?? ""})`],
+        [/^\s*type\s+([A-Za-z_]\w*)\s+(struct|interface)?/gm, "type", (match) => match[1] ?? "", (match) => `type ${match[1] ?? ""} ${match[2] ?? ""}`.trim()],
+        [/^\s*const\s+([A-Za-z_]\w*)\b/gm, "constant", (match) => match[1] ?? "", (match) => `const ${match[1] ?? ""}`],
+        [/^\s*var\s+([A-Za-z_]\w*)\b/gm, "variable", (match) => match[1] ?? "", (match) => `var ${match[1] ?? ""}`],
+    ];
+    for (const [regex, kind, name, signature] of symbolPatterns) {
+        (0, shared_1.insertMatches)(file, regex, (match, line) => (0, shared_1.insertSymbol)(statements, name(match), kind, file, line, signature(match)));
+    }
+    (0, shared_1.insertMatches)(file, /^\s*import\s+(?:(?:([A-Za-z_]\w*|[_.])\s+)?\"([^\"]+)\"|`([^`]+)`)/gm, (match, line) => {
+        const imported = match[1] ?? "";
+        const toRef = match[2] ?? match[3] ?? "";
+        (0, shared_1.insertGoImport)(file, statements, toRef, imported, line, match[0].trim());
+    });
+    (0, shared_1.insertMatches)(file, /^\s*import\s*\(([\s\S]*?)^\s*\)/gm, (blockMatch) => {
+        const block = blockMatch[1] ?? "";
+        const blockStart = blockMatch.index ?? 0;
+        for (const lineMatch of block.matchAll(/^\s*(?:([A-Za-z_]\w*|[_.])\s+)?\"([^\"]+)\"/gm)) {
+            const imported = lineMatch[1] ?? "";
+            const toRef = lineMatch[2] ?? "";
+            const line = (0, shared_1.lineNumber)(file.text, blockStart + (lineMatch.index ?? 0));
+            (0, shared_1.insertGoImport)(file, statements, toRef, imported, line, lineMatch[0].trim());
+        }
+    });
+}

package/dist/code-index/extractors/registry.js

@@ -0,0 +1,137 @@
+"use strict";
+var __createBinding = (this && this.__createBinding) || (Object.create ? (function(o, m, k, k2) {
+    if (k2 === undefined) k2 = k;
+    var desc = Object.getOwnPropertyDescriptor(m, k);
+    if (!desc || ("get" in desc ? !m.__esModule : desc.writable || desc.configurable)) {
+      desc = { enumerable: true, get: function() { return m[k]; } };
+    }
+    Object.defineProperty(o, k2, desc);
+}) : (function(o, m, k, k2) {
+    if (k2 === undefined) k2 = k;
+    o[k2] = m[k];
+}));
+var __setModuleDefault = (this && this.__setModuleDefault) || (Object.create ? (function(o, v) {
+    Object.defineProperty(o, "default", { enumerable: true, value: v });
+}) : function(o, v) {
+    o["default"] = v;
+});
+var __importStar = (this && this.__importStar) || (function () {
+    var ownKeys = function(o) {
+        ownKeys = Object.getOwnPropertyNames || function (o) {
+            var ar = [];
+            for (var k in o) if (Object.prototype.hasOwnProperty.call(o, k)) ar[ar.length] = k;
+            return ar;
+        };
+        return ownKeys(o);
+    };
+    return function (mod) {
+        if (mod && mod.__esModule) return mod;
+        var result = {};
+        if (mod != null) for (var k = ownKeys(mod), i = 0; i < k.length; i++) if (k[i] !== "default") __createBinding(result, mod, k[i]);
+        __setModuleDefault(result, mod);
+        return result;
+    };
+})();
+Object.defineProperty(exports, "__esModule", { value: true });
+exports.extractionProfile = extractionProfile;
+exports.createExtractionBackendRegistry = createExtractionBackendRegistry;
+const path = __importStar(require("node:path"));
+const config_1 = require("./config");
+const light_languages_1 = require("./light-languages");
+const tree_sitter_1 = require("./tree-sitter");
+const typescript_1 = require("./typescript");
+function treeSitterProfile(relativePath) {
+    const extension = path.extname(relativePath).toLowerCase();
+    if ([".ts", ".mts", ".cts"].includes(extension))
+        return "tree-sitter-typescript";
+    if (extension === ".tsx")
+        return "tree-sitter-tsx";
+    if ([".js", ".mjs", ".cjs", ".jsx"].includes(extension))
+        return "tree-sitter-javascript";
+    if (extension === ".py")
+        return "tree-sitter-python";
+    if (extension === ".go")
+        return "tree-sitter-go";
+    if ([".c", ".h"].includes(extension))
+        return "tree-sitter-c";
+    if ([".cc", ".cpp", ".cxx", ".hpp", ".hh", ".hxx"].includes(extension))
+        return "tree-sitter-cpp";
+    if (extension === ".cs")
+        return "tree-sitter-csharp";
+    if (extension === ".java")
+        return "tree-sitter-java";
+    if ([".kt", ".kts"].includes(extension))
+        return "tree-sitter-kotlin";
+    if (extension === ".php")
+        return "tree-sitter-php";
+    if (extension === ".rs")
+        return "tree-sitter-rust";
+    if (extension === ".swift")
+        return "tree-sitter-swift";
+    return "inventory-only";
+}
+function extractionProfile(relativePath, language, parserMode) {
+    if (language === "config")
+        return "config";
+    if (parserMode === "tree-sitter")
+        return treeSitterProfile(relativePath);
+    if (isJavaScriptLikeProfileInput(language))
+        return "typescript-ast";
+    if (language === "python")
+        return "python-light";
+    if (language === "go")
+        return "go-light";
+    return "inventory-only";
+}
+function isJavaScriptLikeProfileInput(language) {
+    return language === "javascript" || language === "typescript";
+}
+function createExtractionBackendRegistry(fail) {
+    const extractionBackends = [
+        {
+            id: "typescript-compiler",
+            index: typescript_1.indexJavaScriptLike,
+            label: "TypeScript compiler API",
+            profile: "typescript-ast",
+            strength: "structural",
+        },
+        {
+            id: "regex-light",
+            index: light_languages_1.indexPythonLight,
+            label: "Python lightweight regex",
+            profile: "python-light",
+            strength: "light",
+        },
+        {
+            id: "regex-light",
+            index: light_languages_1.indexGoLight,
+            label: "Go lightweight regex",
+            profile: "go-light",
+            strength: "light",
+        },
+        ...(0, tree_sitter_1.treeSitterBackends)(fail),
+        {
+            id: "config-key-value",
+            index: (file, statements) => (0, config_1.indexConfigs)(file, statements.insertConfig),
+            label: "Configuration key/value extractor",
+            profile: "config",
+            strength: "config",
+        },
+        {
+            id: "inventory-only",
+            index: () => undefined,
+            label: "Inventory-only file listing",
+            profile: "inventory-only",
+            strength: "inventory",
+        },
+    ];
+    const extractionBackendsByProfile = new Map(extractionBackends.map((backend) => [backend.profile, backend]));
+    return {
+        backendForProfile(profile) {
+            const backend = extractionBackendsByProfile.get(profile);
+            if (!backend)
+                fail(`missing extraction backend for profile: ${profile}`);
+            return backend;
+        },
+    };
+}

package/dist/code-index/extractors/shared.js

@@ -0,0 +1,36 @@
+"use strict";
+Object.defineProperty(exports, "__esModule", { value: true });
+exports.oneLine = oneLine;
+exports.lineNumber = lineNumber;
+exports.insertSymbol = insertSymbol;
+exports.insertEdge = insertEdge;
+exports.insertMatches = insertMatches;
+exports.insertGoImport = insertGoImport;
+function oneLine(text) {
+    return text.replace(/\s+/g, " ").trim().slice(0, 240);
+}
+function lineNumber(text, index) {
+    return text.slice(0, index).split(/\r?\n/).length;
+}
+function insertSymbol(statements, name, kind, file, line, signature) {
+    if (!name)
+        return;
+    statements.insertSymbol.run(name, kind, file.path, line, signature);
+    statements.insertSymbolFts.run(name, kind, file.path, signature);
+}
+function insertEdge(statements, kind, sourceKind, source, targetKind, target, file, line, evidence) {
+    if (!target)
+        return;
+    statements.insertEdge.run(kind, sourceKind, source, targetKind, target, file.path, line, evidence);
+}
+function insertMatches(file, regex, insert) {
+    for (const match of file.text.matchAll(regex)) {
+        insert(match, lineNumber(file.text, match.index ?? 0));
+    }
+}
+function insertGoImport(file, statements, toRef, imported, line, raw) {
+    if (!toRef)
+        return;
+    statements.insertImport.run(file.path, toRef, imported, line, raw);
+    insertEdge(statements, "import", "file", file.path, "module", toRef, file, line, raw);
+}