cry-search 1.0.0

package/dist/utils/sanitiseString.d.ts

@@ -0,0 +1,26 @@
+/**
+ * Sanitises a string for search by normalizing case, removing diacritics, and filtering characters.
+ *
+ * Processing steps:
+ * 1. Converts to lowercase (case-insensitive search)
+ * 2. Removes diacritics using Unicode normalization (č,ć → c, š → s, etc.)
+ * 3. Keeps only letters (a-z), digits (0-9), periods (.), minuses (-), and spaces
+ * 4. Replaces all other characters with space
+ *
+ * @param input - The preprocessed string to sanitise
+ * @returns Sanitised string ready for tokenization
+ *
+ * @example
+ * ```typescript
+ * sanitiseString('Čokolada Milka!')
+ * // Returns: 'cokolada milka '
+ *
+ * sanitiseString('Žaba ČAČA')
+ * // Returns: 'zaba caca'
+ *
+ * sanitiseString('price: $12.50')
+ * // Returns: 'price  12.50'
+ * ```
+ */
+export declare function sanitiseString(input: string): string;
+//# sourceMappingURL=sanitiseString.d.ts.map

package/dist/utils/sanitiseString.d.ts.map

@@ -0,0 +1 @@
+{"version":3,"file":"sanitiseString.d.ts","sourceRoot":"","sources":["../../src/utils/sanitiseString.ts"],"names":[],"mappings":"AAIA;;;;;;;;;;;;;;;;;;;;;;;GAuBG;AACH,wBAAgB,cAAc,CAAC,KAAK,EAAE,MAAM,GAAG,MAAM,CAepD"}

package/dist/utils/tokenRegistry.d.ts

@@ -0,0 +1,70 @@
+/**
+ * Global token registry for numeric token optimization.
+ *
+ * This module provides a global array of tokens that allows numeric token IDs
+ * to be used instead of string tokens. The array is accessed by index for
+ * string lookups during search, avoiding the overhead of Map.get().
+ *
+ * During metadata creation, a temporary Map<string, number> (tokensMap) is used
+ * for fast string->number lookups, then cleared after use.
+ */
+/** Global array of all registered tokens. Index = token ID. */
+export declare const tokens: string[];
+/**
+ * Gets the current number of registered tokens.
+ * @returns The count of registered tokens
+ */
+export declare function getTokenCount(): number;
+/**
+ * Gets a token string by its numeric ID.
+ * Fast O(1) array access.
+ *
+ * @param id - The numeric token ID
+ * @returns The token string, or undefined if ID is out of range
+ */
+export declare function getTokenById(id: number): string | undefined;
+/**
+ * Finds a token ID by its string value.
+ * Slow O(n) linear search - use tokensMap during bulk operations.
+ *
+ * @param token - The token string to find
+ * @returns The numeric token ID, or -1 if not found
+ */
+export declare function findTokenId(token: string): number;
+/**
+ * Registers a new token and returns its ID.
+ * Should only be called when the token doesn't exist (checked via tokensMap).
+ *
+ * @param token - The token string to register
+ * @returns The newly assigned numeric token ID
+ */
+export declare function registerToken(token: string): number;
+/**
+ * Gets or creates a token ID using a tokensMap for fast lookups.
+ * This is the primary method for bulk operations during metadata creation.
+ *
+ * @param token - The token string
+ * @param tokensMap - Map from string to numeric ID (for fast lookup)
+ * @returns The numeric token ID (existing or newly created)
+ */
+export declare function getOrCreateTokenId(token: string, tokensMap: Map<string, number>): number;
+/**
+ * Creates a new temporary tokensMap populated with all currently registered tokens.
+ * Use this at the start of bulk metadata creation operations.
+ *
+ * @returns A new Map<string, number> with all existing token mappings
+ */
+export declare function createTokensMap(): Map<string, number>;
+/**
+ * Clears a tokensMap after use to free memory.
+ * The map is cleared and should be set to null by the caller.
+ *
+ * @param tokensMap - The map to clear
+ */
+export declare function clearTokensMap(tokensMap: Map<string, number>): void;
+/**
+ * Resets the token registry to empty state.
+ * WARNING: Only use for testing or complete reinitialization.
+ */
+export declare function resetTokenRegistry(): void;
+//# sourceMappingURL=tokenRegistry.d.ts.map

package/dist/utils/tokenRegistry.d.ts.map

@@ -0,0 +1 @@
+{"version":3,"file":"tokenRegistry.d.ts","sourceRoot":"","sources":["../../src/utils/tokenRegistry.ts"],"names":[],"mappings":"AAAA;;;;;;;;;GASG;AAKH,+DAA+D;AAC/D,eAAO,MAAM,MAAM,EAAE,MAAM,EAAgC,CAAC;AAK5D;;;GAGG;AACH,wBAAgB,aAAa,IAAI,MAAM,CAEtC;AAED;;;;;;GAMG;AACH,wBAAgB,YAAY,CAAC,EAAE,EAAE,MAAM,GAAG,MAAM,GAAG,SAAS,CAE3D;AAED;;;;;;GAMG;AACH,wBAAgB,WAAW,CAAC,KAAK,EAAE,MAAM,GAAG,MAAM,CAOjD;AAED;;;;;;GAMG;AACH,wBAAgB,aAAa,CAAC,KAAK,EAAE,MAAM,GAAG,MAAM,CAKnD;AAED;;;;;;;GAOG;AACH,wBAAgB,kBAAkB,CAAC,KAAK,EAAE,MAAM,EAAE,SAAS,EAAE,GAAG,CAAC,MAAM,EAAE,MAAM,CAAC,GAAG,MAAM,CAQxF;AAED;;;;;GAKG;AACH,wBAAgB,eAAe,IAAI,GAAG,CAAC,MAAM,EAAE,MAAM,CAAC,CAMrD;AAED;;;;;GAKG;AACH,wBAAgB,cAAc,CAAC,SAAS,EAAE,GAAG,CAAC,MAAM,EAAE,MAAM,CAAC,GAAG,IAAI,CAEnE;AAED;;;GAGG;AACH,wBAAgB,kBAAkB,IAAI,IAAI,CAKzC"}

package/dist/utils/tokenize.d.ts

@@ -0,0 +1,46 @@
+export interface TokenizeConfig {
+    /** Map of tokens to replace (key -> value) */
+    replaceTokens?: Map<string, string>;
+    /** Set of tokens to remove */
+    removeTokens?: Set<string>;
+    /**
+     * Optional map for string->number token ID conversion.
+     * If provided, tokenize will use this for fast lookups during bulk operations.
+     * If not provided, tokenize returns string tokens as before.
+     */
+    tokensMap?: Map<string, number>;
+}
+/** Default token replacements for common terms */
+export declare const DEFAULT_REPLACE_TOKENS: Map<string, string>;
+/** Default tokens to remove (common short words with low search value) */
+export declare const DEFAULT_REMOVE_TOKENS: Set<string>;
+/** Default tokenize config using the default replacements and removals */
+export declare const DEFAULT_TOKENIZE_CONFIG: TokenizeConfig;
+/**
+ * Tokenizes a string for search by splitting on spaces.
+ *
+ * Processing steps:
+ * 1. Splits on spaces
+ * 2. Trims all substrings
+ * 3. Filters out empty strings
+ * 4. Replaces tokens according to replaceTokens map (if provided)
+ * 5. Removes tokens in removeTokens set (if provided)
+ *
+ * @param input - The sanitized string to tokenize
+ * @param config - Optional configuration for token replacement and removal
+ * @returns Array of non-empty tokens
+ *
+ * @example
+ * ```typescript
+ * tokenize('hello world')
+ * // Returns: ['hello', 'world']
+ *
+ * tokenize('  foo   bar  ')
+ * // Returns: ['foo', 'bar']
+ *
+ * tokenize('zdravilo za psi', DEFAULT_TOKENIZE_CONFIG)
+ * // Returns: ['zdr', 'ps'] (za is removed, zdravilo->zdr, psi->ps)
+ * ```
+ */
+export declare function tokenize(input: string, config?: TokenizeConfig): string[];
+//# sourceMappingURL=tokenize.d.ts.map

package/dist/utils/tokenize.d.ts.map

@@ -0,0 +1 @@
+{"version":3,"file":"tokenize.d.ts","sourceRoot":"","sources":["../../src/utils/tokenize.ts"],"names":[],"mappings":"AAAA,MAAM,WAAW,cAAc;IAC7B,8CAA8C;IAC9C,aAAa,CAAC,EAAE,GAAG,CAAC,MAAM,EAAE,MAAM,CAAC,CAAC;IACpC,8BAA8B;IAC9B,YAAY,CAAC,EAAE,GAAG,CAAC,MAAM,CAAC,CAAC;IAC3B;;;;OAIG;IACH,SAAS,CAAC,EAAE,GAAG,CAAC,MAAM,EAAE,MAAM,CAAC,CAAC;CACjC;AAED,kDAAkD;AAClD,eAAO,MAAM,sBAAsB,qBAcjC,CAAC;AAEH,0EAA0E;AAC1E,eAAO,MAAM,qBAAqB,aAUhC,CAAC;AAEH,0EAA0E;AAC1E,eAAO,MAAM,uBAAuB,EAAE,cAGrC,CAAC;AAEF;;;;;;;;;;;;;;;;;;;;;;;;;GAyBG;AACH,wBAAgB,QAAQ,CAAC,KAAK,EAAE,MAAM,EAAE,MAAM,CAAC,EAAE,cAAc,GAAG,MAAM,EAAE,CAuBzE"}

package/package.json

@@ -0,0 +1,67 @@
+{
+  "name": "cry-search",
+  "version": "1.0.0",
+  "description": "A fast, memory-efficient search library for large datasets with support for tokenized matching, linked collections, and per-field match modes.",
+  "type": "module",
+  "main": "./dist/index.js",
+  "module": "./dist/index.js",
+  "types": "./dist/index.d.ts",
+  "exports": {
+    ".": {
+      "import": {
+        "types": "./dist/index.d.ts",
+        "default": "./dist/index.js"
+      },
+      "require": {
+        "types": "./dist/index.d.cts",
+        "default": "./dist/index.cjs"
+      }
+    }
+  },
+  "files": [
+    "dist",
+    "README.md",
+    "CLAUDE.md",
+    "UNIVERSE.md",
+    "LICENSE.md"
+  ],
+  "scripts": {
+    "build": "bun run build:js && bun run build:types",
+    "build:esm": "bun build ./src/index.ts --outdir ./dist --target browser --format esm",
+    "build:cjs": "bun build ./src/index.ts --target browser --format cjs --outfile ./dist/index.cjs",
+    "build:js": "bun run build:esm && bun run build:cjs",
+    "build:types": "tsc -p tsconfig.build.json && cp ./dist/index.d.ts ./dist/index.d.cts",
+    "clean": "rm -rf dist",
+    "test": "bun test",
+    "prepublishOnly": "bun run clean && bun run build"
+  },
+  "keywords": [
+    "search",
+    "fuzzy-search",
+    "tokenize",
+    "metadata",
+    "fast-search",
+    "linked-collections",
+    "typescript"
+  ],
+  "author": "Primož Krajnik",
+  "license": "SEE LICENSE IN LICENSE.md",
+  "repository": {
+    "type": "git",
+    "url": ""
+  },
+  "devDependencies": {
+    "@types/bun": "latest"
+  },
+  "peerDependencies": {
+    "typescript": "^5"
+  },
+  "directories": {
+    "test": "test"
+  },
+  "dependencies": {
+    "bun-types": "^1.3.6",
+    "typescript": "^5.9.3",
+    "undici-types": "^7.16.0"
+  }
+}