diff --git a/dist/commonjs/atomic.d.ts b/dist/commonjs/atomic.d.ts
index 6807242..deb10e9 100644
--- a/dist/commonjs/atomic.d.ts
+++ b/dist/commonjs/atomic.d.ts
@@ -1,6 +1,6 @@
 export interface StringComparisonOptions {
-    transforms?: ((str: string) => string)[];
-    strategies?: ComparisonStrategy[];
+    transforms?: StringTransformFunc[];
+    strategies?: ComparisonStrategy<ComparisonStrategyResultValue>[];
 }
 export interface StringSamenessResult {
     strategies: {
@@ -26,8 +26,8 @@ export interface NamedComparisonStrategyObjectResult extends ComparisonStrategyR
     name: string;
 }
 export type ComparisonStrategyResultValue = number | ComparisonStrategyResultObject;
-export type StrategyFunc = (strA: string, strB: string) => ComparisonStrategyResultValue;
-export interface ComparisonStrategy {
+export type StrategyFunc<T extends ComparisonStrategyResultValue> = (strA: string, strB: string) => T;
+export interface ComparisonStrategy<T extends ComparisonStrategyResultValue> {
     /**
      * The name of this strategy
      * */
@@ -35,9 +35,10 @@ export interface ComparisonStrategy {
     /**
      * A function that accepts two string arguments and returns a number
      * */
-    strategy: StrategyFunc;
+    strategy: StrategyFunc<T>;
     /**
      * An optional function that accepts two string arguments and returns whether this strategy should be used
      * */
     isValid?: (strA: string, strB: string) => boolean;
 }
+export type StringTransformFunc = (str: string) => string;
diff --git a/dist/commonjs/atomic.js b/dist/commonjs/atomic.js
index c8ad2e5..25299c0 100644
--- a/dist/commonjs/atomic.js
+++ b/dist/commonjs/atomic.js
@@ -1,2 +1,3 @@
 "use strict";
 Object.defineProperty(exports, "__esModule", { value: true });
+//# sourceMappingURL=atomic.js.map
\ No newline at end of file
diff --git a/dist/commonjs/atomic.js.map b/dist/commonjs/atomic.js.map
new file mode 100644
index 0000000..d76053d
--- /dev/null
+++ b/dist/commonjs/atomic.js.map
@@ -0,0 +1 @@
+{"version":3,"file":"atomic.js","sourceRoot":"","sources":["../../src/atomic.ts"],"names":[],"mappings":""}
\ No newline at end of file
diff --git a/dist/commonjs/index.d.ts b/dist/commonjs/index.d.ts
index 8c1309f..a9ac7c2 100644
--- a/dist/commonjs/index.d.ts
+++ b/dist/commonjs/index.d.ts
@@ -1,11 +1,13 @@
-import { StringComparisonOptions, StringSamenessResult } from "./atomic.js";
-declare const defaultStrCompareTransformFuncs: ((str: string) => string)[];
-declare const defaultStrategies: import("./atomic.js").ComparisonStrategy[];
+import { ComparisonStrategyResult, StringComparisonOptions, StringSamenessResult, StringTransformFunc } from "./atomic.js";
+import { strDefaultTransforms, transforms } from "./normalization/index.js";
+declare const defaultStrategies: import("./atomic.js").ComparisonStrategy<import("./atomic.js").ComparisonStrategyResultObject>[];
 declare const stringSameness: (valA: string, valB: string, options?: StringComparisonOptions) => StringSamenessResult;
 declare const createStringSameness: (defaults: StringComparisonOptions) => (valA: string, valB: string, options?: StringComparisonOptions) => StringSamenessResult;
 declare const strategies: {
-    diceStrategy: import("./atomic.js").ComparisonStrategy;
-    levenStrategy: import("./atomic.js").ComparisonStrategy;
-    cosineStrategy: import("./atomic.js").ComparisonStrategy;
+    diceStrategy: import("./atomic.js").ComparisonStrategy<import("./atomic.js").ComparisonStrategyResultObject>;
+    levenStrategy: import("./atomic.js").ComparisonStrategy<import("./atomic.js").ComparisonStrategyResultObject>;
+    cosineStrategy: import("./atomic.js").ComparisonStrategy<import("./atomic.js").ComparisonStrategyResultObject>;
+    cosineStrategyAggressive: import("./atomic.js").ComparisonStrategy<import("./atomic.js").ComparisonStrategyResultObject>;
 };
-export { StringSamenessResult, StringComparisonOptions, stringSameness, createStringSameness, defaultStrategies, strategies, defaultStrCompareTransformFuncs };
+declare const defaultStrCompareTransformFuncs: StringTransformFunc[];
+export { StringSamenessResult, StringComparisonOptions, stringSameness, createStringSameness, defaultStrategies, strategies, transforms, defaultStrCompareTransformFuncs, strDefaultTransforms, ComparisonStrategyResult, StringTransformFunc };
diff --git a/dist/commonjs/index.js b/dist/commonjs/index.js
index 60c7b17..bcaffef 100644
--- a/dist/commonjs/index.js
+++ b/dist/commonjs/index.js
@@ -1,23 +1,15 @@
 "use strict";
 Object.defineProperty(exports, "__esModule", { value: true });
-exports.defaultStrCompareTransformFuncs = exports.strategies = exports.defaultStrategies = exports.createStringSameness = exports.stringSameness = void 0;
+exports.strDefaultTransforms = exports.defaultStrCompareTransformFuncs = exports.transforms = exports.strategies = exports.defaultStrategies = exports.createStringSameness = exports.stringSameness = void 0;
 const index_js_1 = require("./matchingStrategies/index.js");
+const index_js_2 = require("./normalization/index.js");
+Object.defineProperty(exports, "strDefaultTransforms", { enumerable: true, get: function () { return index_js_2.strDefaultTransforms; } });
+Object.defineProperty(exports, "transforms", { enumerable: true, get: function () { return index_js_2.transforms; } });
 const sentenceLengthWeight = (length) => {
     // thanks jordan :')
     // constants are black magic
     return (Math.log(length) / 0.20) - 5;
 };
-const defaultStrCompareTransformFuncs = [
-    // lower case to remove case sensitivity
-    (str) => str.toLocaleLowerCase(),
-    // remove excess whitespace
-    (str) => str.trim(),
-    // remove non-alphanumeric characters so that differences in punctuation don't subtract from comparison score
-    (str) => str.replace(/[^A-Za-z0-9 ]/g, ""),
-    // replace all instances of 2 or more whitespace with one whitespace
-    (str) => str.replace(/\s{2,}|\n/g, " ")
-];
-exports.defaultStrCompareTransformFuncs = defaultStrCompareTransformFuncs;
 const defaultStrategies = [
     index_js_1.diceStrategy,
     index_js_1.levenStrategy,
@@ -25,7 +17,7 @@ const defaultStrategies = [
 ];
 exports.defaultStrategies = defaultStrategies;
 const stringSameness = (valA, valB, options) => {
-    const { transforms = defaultStrCompareTransformFuncs, strategies = defaultStrategies, } = options || {};
+    const { transforms = index_js_2.strDefaultTransforms, strategies = defaultStrategies, } = options || {};
     const cleanA = transforms.reduce((acc, curr) => curr(acc), valA);
     const cleanB = transforms.reduce((acc, curr) => curr(acc), valB);
     const shortest = cleanA.length > cleanB.length ? cleanB : cleanA;
@@ -69,6 +61,11 @@ exports.createStringSameness = createStringSameness;
 const strategies = {
     diceStrategy: index_js_1.diceStrategy,
     levenStrategy: index_js_1.levenStrategy,
-    cosineStrategy: index_js_1.cosineStrategy
+    cosineStrategy: index_js_1.cosineStrategy,
+    cosineStrategyAggressive: index_js_1.cosineStrategyAggressive
 };
 exports.strategies = strategies;
+// maintaining compatibility
+const defaultStrCompareTransformFuncs = index_js_2.strDefaultTransforms;
+exports.defaultStrCompareTransformFuncs = defaultStrCompareTransformFuncs;
+//# sourceMappingURL=index.js.map
\ No newline at end of file
diff --git a/dist/commonjs/index.js.map b/dist/commonjs/index.js.map
new file mode 100644
index 0000000..c217079
--- /dev/null
+++ b/dist/commonjs/index.js.map
@@ -0,0 +1 @@
+{"version":3,"file":"index.js","sourceRoot":"","sources":["../../src/index.ts"],"names":[],"mappings":";;;AAAA,4DAAoH;AAQpH,uDAA0E;AAqFtE,qGArFI,+BAAoB,OAqFJ;AAFpB,2FAnF0B,qBAAU,OAmF1B;AAjFd,MAAM,oBAAoB,GAAG,CAAC,MAAc,EAAE,EAAE;IAC5C,oBAAoB;IACpB,4BAA4B;IAC5B,OAAO,CAAC,IAAI,CAAC,GAAG,CAAC,MAAM,CAAC,GAAG,IAAI,CAAC,GAAG,CAAC,CAAC;AACzC,CAAC,CAAA;AAED,MAAM,iBAAiB,GAAG;IACtB,uBAAY;IACZ,wBAAa;IACb,yBAAc;CACjB,CAAA;AAqEG,8CAAiB;AAnErB,MAAM,cAAc,GAAG,CAAC,IAAY,EAAE,IAAY,EAAE,OAAiC,EAAwB,EAAE;IAE3G,MAAM,EACF,UAAU,GAAG,+BAAoB,EACjC,UAAU,GAAG,iBAAiB,GACjC,GAAG,OAAO,IAAI,EAAE,CAAC;IAElB,MAAM,MAAM,GAAG,UAAU,CAAC,MAAM,CAAC,CAAC,GAAG,EAAE,IAAI,EAAE,EAAE,CAAC,IAAI,CAAC,GAAG,CAAC,EAAE,IAAI,CAAC,CAAC;IACjE,MAAM,MAAM,GAAG,UAAU,CAAC,MAAM,CAAC,CAAC,GAAG,EAAE,IAAI,EAAE,EAAE,CAAC,IAAI,CAAC,GAAG,CAAC,EAAE,IAAI,CAAC,CAAC;IAEjE,MAAM,QAAQ,GAAG,MAAM,CAAC,MAAM,GAAG,MAAM,CAAC,MAAM,CAAC,CAAC,CAAC,MAAM,CAAC,CAAC,CAAC,MAAM,CAAC;IAEjE,MAAM,YAAY,GAA0C,EAAE,CAAC;IAE/D,KAAK,MAAM,KAAK,IAAI,UAAU,EAAE;QAC5B,IAAI,KAAK,CAAC,OAAO,KAAK,SAAS,IAAI,CAAC,KAAK,CAAC,OAAO,CAAC,MAAM,EAAE,MAAM,CAAC,EAAE;YAC/D,SAAS;SACZ;QACD,MAAM,GAAG,GAAG,KAAK,CAAC,QAAQ,CAAC,MAAM,EAAE,MAAM,CAAC,CAAC;QAC3C,MAAM,MAAM,GAAG,OAAO,GAAG,KAAK,QAAQ,CAAC,CAAC,CAAC,EAAC,KAAK,EAAE,GAAG,EAAC,CAAC,CAAC,CAAC,GAAG,CAAC;QAC5D,YAAY,CAAC,IAAI,CAAC;YACd,GAAG,MAAM;YACT,IAAI,EAAE,KAAK,CAAC,IAAI;SACnB,CAAC,CAAC;KACN;IAED,mCAAmC;IACnC,MAAM,WAAW,GAAG,oBAAoB,CAAC,QAAQ,CAAC,MAAM,CAAC,CAAC;IAE1D,qBAAqB;IACrB,MAAM,SAAS,GAAG,YAAY,CAAC,MAAM,CAAC,CAAC,GAAG,EAAE,IAAI,EAAE,EAAE,CAAC,GAAG,GAAG,IAAI,CAAC,KAAK,EAAE,CAAC,CAAC,GAAG,YAAY,CAAC,MAAM,CAAC;IAChG,kCAAkC;IAClC,MAAM,iBAAiB,GAAG,SAAS,GAAG,IAAI,CAAC,GAAG,CAAC,WAAW,EAAE,EAAE,CAAC,CAAC;IAChE,MAAM,QAAQ,GAAG,YAAY,CAAC,MAAM,CAAC,CAAC,GAAgD,EAAE,IAAI,EAAE,EAAE;QAC5F,MAAM,EAAC,IAAI,EAAE,KAAK,EAAE,GAAG,IAAI,EAAC,GAAG,IAAI,CAAC;QACpC,GAAG,CAAC,IAAI,CAAC,IAAI,CAAC,GAAG;YACb,GAAG,IAAI;YACP,KAAK;SACR,CAAC;QACF,OAAO,GAAG,CAAC;IACf,CAAC,EAAE,EAAE,CAAC,CAAC;IACP,OAAO;QACH,UAAU,EAAE,QAAQ;QACpB,SAAS;QACT,iBAAiB;KACpB,CAAA;AACL,CAAC,CAAA;AAmBG,wCAAc;AAjBlB,MAAM,oBAAoB,GAAG,CAAC,QAAiC,EAAE,EAAE;IAC/D,OAAO,CAAC,IAAY,EAAE,IAAY,EAAE,UAAmC,EAAE,EAAE,EAAE,CAAC,cAAc,CAAC,IAAI,EAAE,IAAI,EAAE,EAAC,GAAG,QAAQ,EAAE,GAAG,OAAO,EAAC,CAAC,CAAC;AACxI,CAAC,CAAA;AAgBG,oDAAoB;AAdxB,MAAM,UAAU,GAAG;IACf,YAAY,EAAZ,uBAAY;IACZ,aAAa,EAAb,wBAAa;IACb,cAAc,EAAd,yBAAc;IACd,wBAAwB,EAAxB,mCAAwB;CAC3B,CAAC;AAWE,gCAAU;AATd,4BAA4B;AAC5B,MAAM,+BAA+B,GAAG,+BAAoB,CAAC;AAUzD,0EAA+B"}
\ No newline at end of file
diff --git a/dist/commonjs/matchingStrategies/cosineSimilarity.d.ts b/dist/commonjs/matchingStrategies/cosineSimilarity.d.ts
index faeb8d6..1a6679e 100644
--- a/dist/commonjs/matchingStrategies/cosineSimilarity.d.ts
+++ b/dist/commonjs/matchingStrategies/cosineSimilarity.d.ts
@@ -1,3 +1,14 @@
-import { ComparisonStrategy } from "../atomic.js";
+import { ComparisonStrategy, ComparisonStrategyResultObject } from "../atomic.js";
 export declare const calculateCosineSimilarity: (strA: string, strB: string) => number;
-export declare const cosineStrategy: ComparisonStrategy;
+/**
+ * Compares whole tokens (words) within a string independent of order
+ *
+ * This strategy is automatically disabled for strings with less than 4 words because it can lead to inaccurate scores due to not comparing characters IE it is not very useful for short sentences and comparing single words with typos
+ *
+ * If you'd like to use it even in these scenarios build your own strategy array using cosineStrategyAggressive instead of this one
+ * */
+export declare const cosineStrategy: ComparisonStrategy<ComparisonStrategyResultObject>;
+/**
+ * Always runs (strings are always valid) which may lead to inaccurate scores in low token-count strings
+ * */
+export declare const cosineStrategyAggressive: ComparisonStrategy<ComparisonStrategyResultObject>;
diff --git a/dist/commonjs/matchingStrategies/cosineSimilarity.js b/dist/commonjs/matchingStrategies/cosineSimilarity.js
index f7b84f0..2895abe 100644
--- a/dist/commonjs/matchingStrategies/cosineSimilarity.js
+++ b/dist/commonjs/matchingStrategies/cosineSimilarity.js
@@ -2,7 +2,7 @@
 // reproduced from https://github.com/sumn2u/string-comparison/blob/master/jscosine.js
 // https://sumn2u.medium.com/string-similarity-comparision-in-js-with-examples-4bae35f13968
 Object.defineProperty(exports, "__esModule", { value: true });
-exports.cosineStrategy = exports.calculateCosineSimilarity = void 0;
+exports.cosineStrategyAggressive = exports.cosineStrategy = exports.calculateCosineSimilarity = void 0;
 function termFreqMap(str) {
     var words = str.split(' ');
     var termFreq = {};
@@ -51,13 +51,41 @@ const calculateCosineSimilarity = (strA, strB) => {
     return cosineSimilarity(termFreqVecA, termFreqVecB);
 };
 exports.calculateCosineSimilarity = calculateCosineSimilarity;
-exports.cosineStrategy = {
+const cosineBaseStrategy = {
     name: 'cosine',
     strategy: (valA, valB) => {
-        const res = (0, exports.calculateCosineSimilarity)(valA, valB);
+        let res = (0, exports.calculateCosineSimilarity)(valA, valB);
+        if (res > 0.99999) {
+            res = 1;
+        }
         return {
             score: res * 100,
             rawScore: res
         };
     }
 };
+/**
+ * Compares whole tokens (words) within a string independent of order
+ *
+ * This strategy is automatically disabled for strings with less than 4 words because it can lead to inaccurate scores due to not comparing characters IE it is not very useful for short sentences and comparing single words with typos
+ *
+ * If you'd like to use it even in these scenarios build your own strategy array using cosineStrategyAggressive instead of this one
+ * */
+exports.cosineStrategy = {
+    ...cosineBaseStrategy,
+    isValid: (valA, valB) => {
+        // cosine only compares full tokens (words), rather than characters, in a string
+        // which makes its score very inaccurate when comparing low token-count strings (short sentences and/or words with typos)
+        // so disable its usage if there are less than 4 tokens
+        const valATokenLength = valA.split(' ').length;
+        const valBTokenLength = valB.split(' ').length;
+        return valATokenLength < 4 || valBTokenLength < 4;
+    }
+};
+/**
+ * Always runs (strings are always valid) which may lead to inaccurate scores in low token-count strings
+ * */
+exports.cosineStrategyAggressive = {
+    ...cosineBaseStrategy
+};
+//# sourceMappingURL=cosineSimilarity.js.map
\ No newline at end of file
diff --git a/dist/commonjs/matchingStrategies/cosineSimilarity.js.map b/dist/commonjs/matchingStrategies/cosineSimilarity.js.map
new file mode 100644
index 0000000..3158aaa
--- /dev/null
+++ b/dist/commonjs/matchingStrategies/cosineSimilarity.js.map
@@ -0,0 +1 @@
+{"version":3,"file":"cosineSimilarity.js","sourceRoot":"","sources":["../../../src/matchingStrategies/cosineSimilarity.ts"],"names":[],"mappings":";AAAA,sFAAsF;AACtF,2FAA2F;;;AAa3F,SAAS,WAAW,CAAC,GAAW;IAC5B,IAAI,KAAK,GAAG,GAAG,CAAC,KAAK,CAAC,GAAG,CAAC,CAAC;IAC3B,IAAI,QAAQ,GAAW,EAAE,CAAC;IAC1B,KAAK,CAAC,OAAO,CAAC,UAAU,CAAC;QACrB,QAAQ,CAAC,CAAC,CAAC,GAAG,CAAC,QAAQ,CAAC,CAAC,CAAC,IAAI,CAAC,CAAC,GAAG,CAAC,CAAC;IACzC,CAAC,CAAC,CAAC;IACH,OAAO,QAAQ,CAAC;AACpB,CAAC;AAED,SAAS,aAAa,CAAC,GAAW,EAAE,IAAa;IAC7C,KAAK,IAAI,GAAG,IAAI,GAAG,EAAE;QACjB,IAAI,CAAC,GAAG,CAAC,GAAG,IAAI,CAAC;KACpB;AACL,CAAC;AAED,SAAS,mBAAmB,CAAC,GAAW,EAAE,IAAY;IAClD,IAAI,cAAc,GAAG,EAAE,CAAC;IACxB,KAAK,IAAI,IAAI,IAAI,IAAI,EAAE;QACnB,cAAc,CAAC,IAAI,CAAC,GAAG,CAAC,IAAI,CAAC,IAAI,CAAC,CAAC,CAAC;KACvC;IACD,OAAO,cAAc,CAAC;AAC1B,CAAC;AAED,SAAS,aAAa,CAAC,IAAc,EAAE,IAAc;IACjD,IAAI,OAAO,GAAG,CAAC,CAAC;IAChB,KAAK,IAAI,CAAC,GAAG,CAAC,EAAE,CAAC,GAAG,IAAI,CAAC,MAAM,EAAE,CAAC,EAAE,EAAE;QAClC,OAAO,IAAI,IAAI,CAAC,CAAC,CAAC,GAAG,IAAI,CAAC,CAAC,CAAC,CAAC;KAChC;IACD,OAAO,OAAO,CAAC;AACnB,CAAC;AAED,SAAS,YAAY,CAAC,GAAa;IAC/B,IAAI,GAAG,GAAG,CAAC,CAAC;IACZ,KAAK,IAAI,CAAC,GAAG,CAAC,EAAE,CAAC,GAAG,GAAG,CAAC,MAAM,EAAE,CAAC,EAAE,EAAE;QACjC,GAAG,IAAI,GAAG,CAAC,CAAC,CAAC,GAAG,GAAG,CAAC,CAAC,CAAC,CAAC;KAC1B;IACD,OAAO,IAAI,CAAC,IAAI,CAAC,GAAG,CAAC,CAAC;AAC1B,CAAC;AAED,SAAS,gBAAgB,CAAC,IAAc,EAAE,IAAc;IACpD,OAAO,aAAa,CAAC,IAAI,EAAE,IAAI,CAAC,GAAG,CAAC,YAAY,CAAC,IAAI,CAAC,GAAG,YAAY,CAAC,IAAI,CAAC,CAAC,CAAC;AACjF,CAAC;AAEM,MAAM,yBAAyB,GAAG,CAAC,IAAY,EAAE,IAAY,EAAE,EAAE;IACpE,IAAI,SAAS,GAAG,WAAW,CAAC,IAAI,CAAC,CAAC;IAClC,IAAI,SAAS,GAAG,WAAW,CAAC,IAAI,CAAC,CAAC;IAElC,IAAI,IAAI,GAAG,EAAE,CAAC;IACd,aAAa,CAAC,SAAS,EAAE,IAAI,CAAC,CAAC;IAC/B,aAAa,CAAC,SAAS,EAAE,IAAI,CAAC,CAAC;IAE/B,IAAI,YAAY,GAAG,mBAAmB,CAAC,SAAS,EAAE,IAAI,CAAC,CAAC;IACxD,IAAI,YAAY,GAAG,mBAAmB,CAAC,SAAS,EAAE,IAAI,CAAC,CAAC;IAExD,OAAO,gBAAgB,CAAC,YAAY,EAAE,YAAY,CAAC,CAAC;AACxD,CAAC,CAAA;AAZY,QAAA,yBAAyB,6BAYrC;AAED,MAAM,kBAAkB,GAAuD;IAC3E,IAAI,EAAE,QAAQ;IACd,QAAQ,EAAE,CAAC,IAAY,EAAE,IAAY,EAAE,EAAE;QACrC,IAAI,GAAG,GAAG,IAAA,iCAAyB,EAAC,IAAI,EAAE,IAAI,CAAC,CAAC;QAChD,IAAG,GAAG,GAAG,OAAO,EAAE;YACd,GAAG,GAAG,CAAC,CAAC;SACX;QACD,OAAO;YACH,KAAK,EAAE,GAAG,GAAG,GAAG;YAChB,QAAQ,EAAE,GAAG;SAChB,CAAA;IACL,CAAC;CACJ,CAAA;AAED;;;;;;KAMK;AACQ,QAAA,cAAc,GAAuD;IAC9E,GAAG,kBAAkB;IACrB,OAAO,EAAE,CAAC,IAAY,EAAE,IAAY,EAAE,EAAE;QACpC,gFAAgF;QAChF,yHAAyH;QACzH,uDAAuD;QACvD,MAAM,eAAe,GAAG,IAAI,CAAC,KAAK,CAAC,GAAG,CAAC,CAAC,MAAM,CAAC;QAC/C,MAAM,eAAe,GAAG,IAAI,CAAC,KAAK,CAAC,GAAG,CAAC,CAAC,MAAM,CAAC;QAC/C,OAAO,eAAe,GAAG,CAAC,IAAI,eAAe,GAAG,CAAC,CAAC;IACtD,CAAC;CACJ,CAAA;AAED;;KAEK;AACQ,QAAA,wBAAwB,GAAuD;IACxF,GAAG,kBAAkB;CACxB,CAAA"}
\ No newline at end of file
diff --git a/dist/commonjs/matchingStrategies/diceSimilarity.d.ts b/dist/commonjs/matchingStrategies/diceSimilarity.d.ts
index 6cb2a48..65d0389 100644
--- a/dist/commonjs/matchingStrategies/diceSimilarity.d.ts
+++ b/dist/commonjs/matchingStrategies/diceSimilarity.d.ts
@@ -1,3 +1,3 @@
-import { ComparisonStrategy } from "../atomic.js";
+import { ComparisonStrategy, ComparisonStrategyResultObject } from "../atomic.js";
 export declare const calculateDiceSimilarity: (valA: string, valB: string) => number;
-export declare const diceStrategy: ComparisonStrategy;
+export declare const diceStrategy: ComparisonStrategy<ComparisonStrategyResultObject>;
diff --git a/dist/commonjs/matchingStrategies/diceSimilarity.js b/dist/commonjs/matchingStrategies/diceSimilarity.js
index de9caf5..a83d16f 100644
--- a/dist/commonjs/matchingStrategies/diceSimilarity.js
+++ b/dist/commonjs/matchingStrategies/diceSimilarity.js
@@ -17,3 +17,4 @@ exports.diceStrategy = {
         };
     }
 };
+//# sourceMappingURL=diceSimilarity.js.map
\ No newline at end of file
diff --git a/dist/commonjs/matchingStrategies/diceSimilarity.js.map b/dist/commonjs/matchingStrategies/diceSimilarity.js.map
new file mode 100644
index 0000000..c06824b
--- /dev/null
+++ b/dist/commonjs/matchingStrategies/diceSimilarity.js.map
@@ -0,0 +1 @@
+{"version":3,"file":"diceSimilarity.js","sourceRoot":"","sources":["../../../src/matchingStrategies/diceSimilarity.ts"],"names":[],"mappings":";;;;;;AAAA,0EAAiD;AAG1C,MAAM,uBAAuB,GAAG,CAAC,IAAY,EAAE,IAAY,EAAE,EAAE,CAAC,2BAAgB,CAAC,iBAAiB,CAAC,IAAI,EAAE,IAAI,CAAC,CAAC;AAAzG,QAAA,uBAAuB,2BAAkF;AACzG,QAAA,YAAY,GAAuD;IAC5E,IAAI,EAAE,MAAM;IACZ,QAAQ,EAAE,CAAC,IAAY,EAAE,IAAY,EAAE,EAAE;QACrC,MAAM,GAAG,GAAG,IAAA,+BAAuB,EAAC,IAAI,EAAE,IAAI,CAAC,CAAC;QAChD,OAAO;YACH,KAAK,EAAE,GAAG,GAAG,GAAG;YAChB,QAAQ,EAAE,GAAG;SAChB,CAAA;IACL,CAAC;CACJ,CAAA"}
\ No newline at end of file
diff --git a/dist/commonjs/matchingStrategies/index.d.ts b/dist/commonjs/matchingStrategies/index.d.ts
index a3d62ec..8c9b96f 100644
--- a/dist/commonjs/matchingStrategies/index.d.ts
+++ b/dist/commonjs/matchingStrategies/index.d.ts
@@ -1,5 +1,5 @@
 import { levenStrategy } from "./levenSimilarity.js";
-import { cosineStrategy } from "./cosineSimilarity.js";
+import { cosineStrategy, cosineStrategyAggressive } from "./cosineSimilarity.js";
 import { diceStrategy } from "./diceSimilarity.js";
 import { ComparisonStrategy, ComparisonStrategyResultValue, ComparisonStrategyResultObject, StrategyFunc } from '../atomic.js';
-export { levenStrategy, cosineStrategy, diceStrategy, ComparisonStrategy, ComparisonStrategyResultObject, ComparisonStrategyResultValue, StrategyFunc };
+export { levenStrategy, cosineStrategy, cosineStrategyAggressive, diceStrategy, ComparisonStrategy, ComparisonStrategyResultObject, ComparisonStrategyResultValue, StrategyFunc };
diff --git a/dist/commonjs/matchingStrategies/index.js b/dist/commonjs/matchingStrategies/index.js
index 7fdf920..d1ce17c 100644
--- a/dist/commonjs/matchingStrategies/index.js
+++ b/dist/commonjs/matchingStrategies/index.js
@@ -1,9 +1,11 @@
 "use strict";
 Object.defineProperty(exports, "__esModule", { value: true });
-exports.diceStrategy = exports.cosineStrategy = exports.levenStrategy = void 0;
+exports.diceStrategy = exports.cosineStrategyAggressive = exports.cosineStrategy = exports.levenStrategy = void 0;
 const levenSimilarity_js_1 = require("./levenSimilarity.js");
 Object.defineProperty(exports, "levenStrategy", { enumerable: true, get: function () { return levenSimilarity_js_1.levenStrategy; } });
 const cosineSimilarity_js_1 = require("./cosineSimilarity.js");
 Object.defineProperty(exports, "cosineStrategy", { enumerable: true, get: function () { return cosineSimilarity_js_1.cosineStrategy; } });
+Object.defineProperty(exports, "cosineStrategyAggressive", { enumerable: true, get: function () { return cosineSimilarity_js_1.cosineStrategyAggressive; } });
 const diceSimilarity_js_1 = require("./diceSimilarity.js");
 Object.defineProperty(exports, "diceStrategy", { enumerable: true, get: function () { return diceSimilarity_js_1.diceStrategy; } });
+//# sourceMappingURL=index.js.map
\ No newline at end of file
diff --git a/dist/commonjs/matchingStrategies/index.js.map b/dist/commonjs/matchingStrategies/index.js.map
new file mode 100644
index 0000000..a655b05
--- /dev/null
+++ b/dist/commonjs/matchingStrategies/index.js.map
@@ -0,0 +1 @@
+{"version":3,"file":"index.js","sourceRoot":"","sources":["../../../src/matchingStrategies/index.ts"],"names":[],"mappings":";;;AAAA,6DAAmD;AAM/C,8FANI,kCAAa,OAMJ;AALjB,+DAA+E;AAM3E,+FANI,oCAAc,OAMJ;AACd,yGAPoB,8CAAwB,OAOpB;AAN5B,2DAAiD;AAO7C,6FAPI,gCAAY,OAOJ"}
\ No newline at end of file
diff --git a/dist/commonjs/matchingStrategies/levenSimilarity.d.ts b/dist/commonjs/matchingStrategies/levenSimilarity.d.ts
index 113d82d..4dee4fe 100644
--- a/dist/commonjs/matchingStrategies/levenSimilarity.d.ts
+++ b/dist/commonjs/matchingStrategies/levenSimilarity.d.ts
@@ -1,3 +1,3 @@
-import { ComparisonStrategy } from "../atomic.js";
+import { ComparisonStrategy, ComparisonStrategyResultObject } from "../atomic.js";
 export declare const calculateLevenSimilarity: (valA: string, valB: string) => number[];
-export declare const levenStrategy: ComparisonStrategy;
+export declare const levenStrategy: ComparisonStrategy<ComparisonStrategyResultObject>;
diff --git a/dist/commonjs/matchingStrategies/levenSimilarity.js b/dist/commonjs/matchingStrategies/levenSimilarity.js
index d8ba8eb..ffb2786 100644
--- a/dist/commonjs/matchingStrategies/levenSimilarity.js
+++ b/dist/commonjs/matchingStrategies/levenSimilarity.js
@@ -17,7 +17,11 @@ const calculateLevenSimilarity = (valA, valB) => {
         shorter = valA;
     }
     const distance = (0, leven_1.default)(longer, shorter);
-    const diff = (distance / longer.length) * 100;
+    // use the shorter length
+    // because if we have more move/change operations than the length of the shortest string than we have two unique strings
+    // and if we use the longer length the score actually gets *better* as the length gap gets larger (not what we want)
+    // -- cap at 100% diff
+    const diff = Math.min((distance / shorter.length) * 100, 100);
     return [distance, 100 - diff];
 };
 exports.calculateLevenSimilarity = calculateLevenSimilarity;
@@ -33,3 +37,4 @@ exports.levenStrategy = {
     name: 'leven',
     strategy: stratFunc
 };
+//# sourceMappingURL=levenSimilarity.js.map
\ No newline at end of file
diff --git a/dist/commonjs/matchingStrategies/levenSimilarity.js.map b/dist/commonjs/matchingStrategies/levenSimilarity.js.map
new file mode 100644
index 0000000..c1ee3c1
--- /dev/null
+++ b/dist/commonjs/matchingStrategies/levenSimilarity.js.map
@@ -0,0 +1 @@
+{"version":3,"file":"levenSimilarity.js","sourceRoot":"","sources":["../../../src/matchingStrategies/levenSimilarity.ts"],"names":[],"mappings":";;;;;;AAAA,kDAA0B;AAGnB,MAAM,wBAAwB,GAAG,CAAC,IAAY,EAAE,IAAY,EAAE,EAAE;IACnE,IAAI,MAAc,CAAC;IACnB,IAAI,OAAe,CAAC;IACpB,IAAI,IAAI,CAAC,MAAM,GAAG,IAAI,CAAC,MAAM,EAAE;QAC3B,MAAM,GAAG,IAAI,CAAC;QACd,OAAO,GAAG,IAAI,CAAC;KAClB;SAAM;QACH,MAAM,GAAG,IAAI,CAAC;QACd,OAAO,GAAG,IAAI,CAAC;KAClB;IAED,MAAM,QAAQ,GAAG,IAAA,eAAK,EAAC,MAAM,EAAE,OAAO,CAAC,CAAC;IACxC,yBAAyB;IACzB,wHAAwH;IACxH,oHAAoH;IACpH,sBAAsB;IACtB,MAAM,IAAI,GAAG,IAAI,CAAC,GAAG,CAAC,CAAC,QAAQ,GAAG,OAAO,CAAC,MAAM,CAAC,GAAG,GAAG,EAAE,GAAG,CAAC,CAAC;IAC9D,OAAO,CAAC,QAAQ,EAAE,GAAG,GAAG,IAAI,CAAC,CAAC;AAClC,CAAC,CAAA;AAlBY,QAAA,wBAAwB,4BAkBpC;AAED,MAAM,SAAS,GAAG,CAAC,IAAY,EAAE,IAAY,EAAE,EAAE;IAC7C,MAAM,GAAG,GAAG,IAAA,gCAAwB,EAAC,IAAI,EAAE,IAAI,CAAC,CAAC;IACjD,OAAO;QACH,QAAQ,EAAE,GAAG,CAAC,CAAC,CAAC;QAChB,QAAQ,EAAE,GAAG,CAAC,CAAC,CAAC;QAChB,KAAK,EAAE,GAAG,CAAC,CAAC,CAAC;KAChB,CAAC;AACN,CAAC,CAAA;AAEY,QAAA,aAAa,GAAuD;IAC7E,IAAI,EAAE,OAAO;IACb,QAAQ,EAAE,SAAS;CACtB,CAAA"}
\ No newline at end of file
diff --git a/dist/commonjs/normalization/index.d.ts b/dist/commonjs/normalization/index.d.ts
new file mode 100644
index 0000000..ae891c2
--- /dev/null
+++ b/dist/commonjs/normalization/index.d.ts
@@ -0,0 +1,17 @@
+import { StringTransformFunc } from "../atomic.js";
+declare const lowercase: StringTransformFunc;
+declare const trim: StringTransformFunc;
+declare const replaceUnicode: StringTransformFunc;
+declare const removePunctuation: StringTransformFunc;
+declare const removeWhitespace: StringTransformFunc;
+declare const replaceMultiWhitespace: StringTransformFunc;
+declare const transforms: {
+    lowercase: StringTransformFunc;
+    trim: StringTransformFunc;
+    replaceMultiWhitespace: StringTransformFunc;
+    replaceUnicode: StringTransformFunc;
+    removeWhitespace: StringTransformFunc;
+    removePunctuation: StringTransformFunc;
+};
+declare const strDefaultTransforms: StringTransformFunc[];
+export { lowercase, trim, replaceUnicode, removePunctuation, removeWhitespace, replaceMultiWhitespace, transforms, strDefaultTransforms };
diff --git a/dist/commonjs/normalization/index.js b/dist/commonjs/normalization/index.js
new file mode 100644
index 0000000..73080ed
--- /dev/null
+++ b/dist/commonjs/normalization/index.js
@@ -0,0 +1,36 @@
+"use strict";
+Object.defineProperty(exports, "__esModule", { value: true });
+exports.strDefaultTransforms = exports.transforms = exports.replaceMultiWhitespace = exports.removeWhitespace = exports.removePunctuation = exports.replaceUnicode = exports.trim = exports.lowercase = void 0;
+const PUNCTUATION_REGEX = new RegExp(/[^\w\s]|_/g);
+const WHITESPACE_REGEX = new RegExp(/\s/g);
+const MULTI_WHITESPACE_REGEX = new RegExp(/\s{2,}|\n/g);
+const lowercase = (str) => str.toLocaleLowerCase();
+exports.lowercase = lowercase;
+const trim = (str) => str.trim();
+exports.trim = trim;
+const replaceUnicode = (str) => str.normalize('NFD').replace(/[\u0300-\u036f]/g, "");
+exports.replaceUnicode = replaceUnicode;
+const removePunctuation = (str) => str.replace(PUNCTUATION_REGEX, '');
+exports.removePunctuation = removePunctuation;
+const removeWhitespace = (str) => str.replace(WHITESPACE_REGEX, '');
+exports.removeWhitespace = removeWhitespace;
+const replaceMultiWhitespace = (str) => str.replace(MULTI_WHITESPACE_REGEX, '');
+exports.replaceMultiWhitespace = replaceMultiWhitespace;
+const transforms = {
+    lowercase,
+    trim,
+    replaceMultiWhitespace,
+    replaceUnicode,
+    removeWhitespace,
+    removePunctuation
+};
+exports.transforms = transforms;
+const strDefaultTransforms = [
+    replaceUnicode,
+    removePunctuation,
+    trim,
+    replaceMultiWhitespace,
+    lowercase
+];
+exports.strDefaultTransforms = strDefaultTransforms;
+//# sourceMappingURL=index.js.map
\ No newline at end of file
diff --git a/dist/commonjs/normalization/index.js.map b/dist/commonjs/normalization/index.js.map
new file mode 100644
index 0000000..84f643e
--- /dev/null
+++ b/dist/commonjs/normalization/index.js.map
@@ -0,0 +1 @@
+{"version":3,"file":"index.js","sourceRoot":"","sources":["../../../src/normalization/index.ts"],"names":[],"mappings":";;;AAEA,MAAM,iBAAiB,GAAG,IAAI,MAAM,CAAC,YAAY,CAAC,CAAC;AACnD,MAAM,gBAAgB,GAAG,IAAI,MAAM,CAAC,KAAK,CAAC,CAAC;AAC3C,MAAM,sBAAsB,GAAG,IAAI,MAAM,CAAC,YAAY,CAAC,CAAC;AAExD,MAAM,SAAS,GAAwB,CAAC,GAAW,EAAE,EAAE,CAAC,GAAG,CAAC,iBAAiB,EAAE,CAAC;AAyB5E,8BAAS;AAxBb,MAAM,IAAI,GAAwB,CAAC,GAAW,EAAE,EAAE,CAAC,GAAG,CAAC,IAAI,EAAE,CAAC;AAyB1D,oBAAI;AAxBR,MAAM,cAAc,GAAwB,CAAC,GAAW,EAAE,EAAE,CAAC,GAAG,CAAC,SAAS,CAAC,KAAK,CAAC,CAAC,OAAO,CAAC,kBAAkB,EAAE,EAAE,CAAC,CAAC;AAyB9G,wCAAc;AAxBlB,MAAM,iBAAiB,GAAwB,CAAC,GAAW,EAAE,EAAE,CAAC,GAAG,CAAC,OAAO,CAAC,iBAAiB,EAAE,EAAE,CAAC,CAAC;AAyB/F,8CAAiB;AAxBrB,MAAM,gBAAgB,GAAwB,CAAC,GAAW,EAAE,EAAE,CAAC,GAAG,CAAC,OAAO,CAAC,gBAAgB,EAAE,EAAE,CAAC,CAAC;AAyB7F,4CAAgB;AAxBpB,MAAM,sBAAsB,GAAwB,CAAC,GAAW,EAAE,EAAE,CAAC,GAAG,CAAC,OAAO,CAAC,sBAAsB,EAAE,EAAE,CAAC,CAAC;AAyBzG,wDAAsB;AAvB1B,MAAM,UAAU,GAAG;IACf,SAAS;IACT,IAAI;IACJ,sBAAsB;IACtB,cAAc;IACd,gBAAgB;IAChB,iBAAiB;CACpB,CAAA;AAiBG,gCAAU;AAfd,MAAM,oBAAoB,GAA0B;IAChD,cAAc;IACd,iBAAiB;IACjB,IAAI;IACJ,sBAAsB;IACtB,SAAS;CACZ,CAAC;AAUE,oDAAoB"}
\ No newline at end of file
diff --git a/dist/esm/atomic.d.ts b/dist/esm/atomic.d.ts
index 6807242..deb10e9 100644
--- a/dist/esm/atomic.d.ts
+++ b/dist/esm/atomic.d.ts
@@ -1,6 +1,6 @@
 export interface StringComparisonOptions {
-    transforms?: ((str: string) => string)[];
-    strategies?: ComparisonStrategy[];
+    transforms?: StringTransformFunc[];
+    strategies?: ComparisonStrategy<ComparisonStrategyResultValue>[];
 }
 export interface StringSamenessResult {
     strategies: {
@@ -26,8 +26,8 @@ export interface NamedComparisonStrategyObjectResult extends ComparisonStrategyR
     name: string;
 }
 export type ComparisonStrategyResultValue = number | ComparisonStrategyResultObject;
-export type StrategyFunc = (strA: string, strB: string) => ComparisonStrategyResultValue;
-export interface ComparisonStrategy {
+export type StrategyFunc<T extends ComparisonStrategyResultValue> = (strA: string, strB: string) => T;
+export interface ComparisonStrategy<T extends ComparisonStrategyResultValue> {
     /**
      * The name of this strategy
      * */
@@ -35,9 +35,10 @@ export interface ComparisonStrategy {
     /**
      * A function that accepts two string arguments and returns a number
      * */
-    strategy: StrategyFunc;
+    strategy: StrategyFunc<T>;
     /**
      * An optional function that accepts two string arguments and returns whether this strategy should be used
      * */
     isValid?: (strA: string, strB: string) => boolean;
 }
+export type StringTransformFunc = (str: string) => string;
diff --git a/dist/esm/atomic.js b/dist/esm/atomic.js
index cb0ff5c..7730b0a 100644
--- a/dist/esm/atomic.js
+++ b/dist/esm/atomic.js
@@ -1 +1,2 @@
 export {};
+//# sourceMappingURL=atomic.js.map
\ No newline at end of file
diff --git a/dist/esm/atomic.js.map b/dist/esm/atomic.js.map
new file mode 100644
index 0000000..d76053d
--- /dev/null
+++ b/dist/esm/atomic.js.map
@@ -0,0 +1 @@
+{"version":3,"file":"atomic.js","sourceRoot":"","sources":["../../src/atomic.ts"],"names":[],"mappings":""}
\ No newline at end of file
diff --git a/dist/esm/index.d.ts b/dist/esm/index.d.ts
index 8c1309f..a9ac7c2 100644
--- a/dist/esm/index.d.ts
+++ b/dist/esm/index.d.ts
@@ -1,11 +1,13 @@
-import { StringComparisonOptions, StringSamenessResult } from "./atomic.js";
-declare const defaultStrCompareTransformFuncs: ((str: string) => string)[];
-declare const defaultStrategies: import("./atomic.js").ComparisonStrategy[];
+import { ComparisonStrategyResult, StringComparisonOptions, StringSamenessResult, StringTransformFunc } from "./atomic.js";
+import { strDefaultTransforms, transforms } from "./normalization/index.js";
+declare const defaultStrategies: import("./atomic.js").ComparisonStrategy<import("./atomic.js").ComparisonStrategyResultObject>[];
 declare const stringSameness: (valA: string, valB: string, options?: StringComparisonOptions) => StringSamenessResult;
 declare const createStringSameness: (defaults: StringComparisonOptions) => (valA: string, valB: string, options?: StringComparisonOptions) => StringSamenessResult;
 declare const strategies: {
-    diceStrategy: import("./atomic.js").ComparisonStrategy;
-    levenStrategy: import("./atomic.js").ComparisonStrategy;
-    cosineStrategy: import("./atomic.js").ComparisonStrategy;
+    diceStrategy: import("./atomic.js").ComparisonStrategy<import("./atomic.js").ComparisonStrategyResultObject>;
+    levenStrategy: import("./atomic.js").ComparisonStrategy<import("./atomic.js").ComparisonStrategyResultObject>;
+    cosineStrategy: import("./atomic.js").ComparisonStrategy<import("./atomic.js").ComparisonStrategyResultObject>;
+    cosineStrategyAggressive: import("./atomic.js").ComparisonStrategy<import("./atomic.js").ComparisonStrategyResultObject>;
 };
-export { StringSamenessResult, StringComparisonOptions, stringSameness, createStringSameness, defaultStrategies, strategies, defaultStrCompareTransformFuncs };
+declare const defaultStrCompareTransformFuncs: StringTransformFunc[];
+export { StringSamenessResult, StringComparisonOptions, stringSameness, createStringSameness, defaultStrategies, strategies, transforms, defaultStrCompareTransformFuncs, strDefaultTransforms, ComparisonStrategyResult, StringTransformFunc };
diff --git a/dist/esm/index.js b/dist/esm/index.js
index 9cb183b..9740d73 100644
--- a/dist/esm/index.js
+++ b/dist/esm/index.js
@@ -1,26 +1,17 @@
-import { cosineStrategy, levenStrategy, diceStrategy } from "./matchingStrategies/index.js";
+import { cosineStrategy, levenStrategy, diceStrategy, cosineStrategyAggressive } from "./matchingStrategies/index.js";
+import { strDefaultTransforms, transforms } from "./normalization/index.js";
 const sentenceLengthWeight = (length) => {
     // thanks jordan :')
     // constants are black magic
     return (Math.log(length) / 0.20) - 5;
 };
-const defaultStrCompareTransformFuncs = [
-    // lower case to remove case sensitivity
-    (str) => str.toLocaleLowerCase(),
-    // remove excess whitespace
-    (str) => str.trim(),
-    // remove non-alphanumeric characters so that differences in punctuation don't subtract from comparison score
-    (str) => str.replace(/[^A-Za-z0-9 ]/g, ""),
-    // replace all instances of 2 or more whitespace with one whitespace
-    (str) => str.replace(/\s{2,}|\n/g, " ")
-];
 const defaultStrategies = [
     diceStrategy,
     levenStrategy,
     cosineStrategy
 ];
 const stringSameness = (valA, valB, options) => {
-    const { transforms = defaultStrCompareTransformFuncs, strategies = defaultStrategies, } = options || {};
+    const { transforms = strDefaultTransforms, strategies = defaultStrategies, } = options || {};
     const cleanA = transforms.reduce((acc, curr) => curr(acc), valA);
     const cleanB = transforms.reduce((acc, curr) => curr(acc), valB);
     const shortest = cleanA.length > cleanB.length ? cleanB : cleanA;
@@ -62,6 +53,10 @@ const createStringSameness = (defaults) => {
 const strategies = {
     diceStrategy,
     levenStrategy,
-    cosineStrategy
+    cosineStrategy,
+    cosineStrategyAggressive
 };
-export { stringSameness, createStringSameness, defaultStrategies, strategies, defaultStrCompareTransformFuncs };
+// maintaining compatibility
+const defaultStrCompareTransformFuncs = strDefaultTransforms;
+export { stringSameness, createStringSameness, defaultStrategies, strategies, transforms, defaultStrCompareTransformFuncs, strDefaultTransforms };
+//# sourceMappingURL=index.js.map
\ No newline at end of file
diff --git a/dist/esm/index.js.map b/dist/esm/index.js.map
new file mode 100644
index 0000000..c57cb68
--- /dev/null
+++ b/dist/esm/index.js.map
@@ -0,0 +1 @@
+{"version":3,"file":"index.js","sourceRoot":"","sources":["../../src/index.ts"],"names":[],"mappings":"AAAA,OAAO,EAAC,cAAc,EAAE,aAAa,EAAE,YAAY,EAAE,wBAAwB,EAAC,MAAM,+BAA+B,CAAC;AAQpH,OAAO,EAAC,oBAAoB,EAAE,UAAU,EAAC,MAAM,0BAA0B,CAAC;AAE1E,MAAM,oBAAoB,GAAG,CAAC,MAAc,EAAE,EAAE;IAC5C,oBAAoB;IACpB,4BAA4B;IAC5B,OAAO,CAAC,IAAI,CAAC,GAAG,CAAC,MAAM,CAAC,GAAG,IAAI,CAAC,GAAG,CAAC,CAAC;AACzC,CAAC,CAAA;AAED,MAAM,iBAAiB,GAAG;IACtB,YAAY;IACZ,aAAa;IACb,cAAc;CACjB,CAAA;AAED,MAAM,cAAc,GAAG,CAAC,IAAY,EAAE,IAAY,EAAE,OAAiC,EAAwB,EAAE;IAE3G,MAAM,EACF,UAAU,GAAG,oBAAoB,EACjC,UAAU,GAAG,iBAAiB,GACjC,GAAG,OAAO,IAAI,EAAE,CAAC;IAElB,MAAM,MAAM,GAAG,UAAU,CAAC,MAAM,CAAC,CAAC,GAAG,EAAE,IAAI,EAAE,EAAE,CAAC,IAAI,CAAC,GAAG,CAAC,EAAE,IAAI,CAAC,CAAC;IACjE,MAAM,MAAM,GAAG,UAAU,CAAC,MAAM,CAAC,CAAC,GAAG,EAAE,IAAI,EAAE,EAAE,CAAC,IAAI,CAAC,GAAG,CAAC,EAAE,IAAI,CAAC,CAAC;IAEjE,MAAM,QAAQ,GAAG,MAAM,CAAC,MAAM,GAAG,MAAM,CAAC,MAAM,CAAC,CAAC,CAAC,MAAM,CAAC,CAAC,CAAC,MAAM,CAAC;IAEjE,MAAM,YAAY,GAA0C,EAAE,CAAC;IAE/D,KAAK,MAAM,KAAK,IAAI,UAAU,EAAE;QAC5B,IAAI,KAAK,CAAC,OAAO,KAAK,SAAS,IAAI,CAAC,KAAK,CAAC,OAAO,CAAC,MAAM,EAAE,MAAM,CAAC,EAAE;YAC/D,SAAS;SACZ;QACD,MAAM,GAAG,GAAG,KAAK,CAAC,QAAQ,CAAC,MAAM,EAAE,MAAM,CAAC,CAAC;QAC3C,MAAM,MAAM,GAAG,OAAO,GAAG,KAAK,QAAQ,CAAC,CAAC,CAAC,EAAC,KAAK,EAAE,GAAG,EAAC,CAAC,CAAC,CAAC,GAAG,CAAC;QAC5D,YAAY,CAAC,IAAI,CAAC;YACd,GAAG,MAAM;YACT,IAAI,EAAE,KAAK,CAAC,IAAI;SACnB,CAAC,CAAC;KACN;IAED,mCAAmC;IACnC,MAAM,WAAW,GAAG,oBAAoB,CAAC,QAAQ,CAAC,MAAM,CAAC,CAAC;IAE1D,qBAAqB;IACrB,MAAM,SAAS,GAAG,YAAY,CAAC,MAAM,CAAC,CAAC,GAAG,EAAE,IAAI,EAAE,EAAE,CAAC,GAAG,GAAG,IAAI,CAAC,KAAK,EAAE,CAAC,CAAC,GAAG,YAAY,CAAC,MAAM,CAAC;IAChG,kCAAkC;IAClC,MAAM,iBAAiB,GAAG,SAAS,GAAG,IAAI,CAAC,GAAG,CAAC,WAAW,EAAE,EAAE,CAAC,CAAC;IAChE,MAAM,QAAQ,GAAG,YAAY,CAAC,MAAM,CAAC,CAAC,GAAgD,EAAE,IAAI,EAAE,EAAE;QAC5F,MAAM,EAAC,IAAI,EAAE,KAAK,EAAE,GAAG,IAAI,EAAC,GAAG,IAAI,CAAC;QACpC,GAAG,CAAC,IAAI,CAAC,IAAI,CAAC,GAAG;YACb,GAAG,IAAI;YACP,KAAK;SACR,CAAC;QACF,OAAO,GAAG,CAAC;IACf,CAAC,EAAE,EAAE,CAAC,CAAC;IACP,OAAO;QACH,UAAU,EAAE,QAAQ;QACpB,SAAS;QACT,iBAAiB;KACpB,CAAA;AACL,CAAC,CAAA;AAED,MAAM,oBAAoB,GAAG,CAAC,QAAiC,EAAE,EAAE;IAC/D,OAAO,CAAC,IAAY,EAAE,IAAY,EAAE,UAAmC,EAAE,EAAE,EAAE,CAAC,cAAc,CAAC,IAAI,EAAE,IAAI,EAAE,EAAC,GAAG,QAAQ,EAAE,GAAG,OAAO,EAAC,CAAC,CAAC;AACxI,CAAC,CAAA;AAED,MAAM,UAAU,GAAG;IACf,YAAY;IACZ,aAAa;IACb,cAAc;IACd,wBAAwB;CAC3B,CAAC;AAEF,4BAA4B;AAC5B,MAAM,+BAA+B,GAAG,oBAAoB,CAAC;AAE7D,OAAO,EAGH,cAAc,EACd,oBAAoB,EACpB,iBAAiB,EACjB,UAAU,EACV,UAAU,EACV,+BAA+B,EAC/B,oBAAoB,EAGvB,CAAA"}
\ No newline at end of file
diff --git a/dist/esm/matchingStrategies/cosineSimilarity.d.ts b/dist/esm/matchingStrategies/cosineSimilarity.d.ts
index faeb8d6..1a6679e 100644
--- a/dist/esm/matchingStrategies/cosineSimilarity.d.ts
+++ b/dist/esm/matchingStrategies/cosineSimilarity.d.ts
@@ -1,3 +1,14 @@
-import { ComparisonStrategy } from "../atomic.js";
+import { ComparisonStrategy, ComparisonStrategyResultObject } from "../atomic.js";
 export declare const calculateCosineSimilarity: (strA: string, strB: string) => number;
-export declare const cosineStrategy: ComparisonStrategy;
+/**
+ * Compares whole tokens (words) within a string independent of order
+ *
+ * This strategy is automatically disabled for strings with less than 4 words because it can lead to inaccurate scores due to not comparing characters IE it is not very useful for short sentences and comparing single words with typos
+ *
+ * If you'd like to use it even in these scenarios build your own strategy array using cosineStrategyAggressive instead of this one
+ * */
+export declare const cosineStrategy: ComparisonStrategy<ComparisonStrategyResultObject>;
+/**
+ * Always runs (strings are always valid) which may lead to inaccurate scores in low token-count strings
+ * */
+export declare const cosineStrategyAggressive: ComparisonStrategy<ComparisonStrategyResultObject>;
diff --git a/dist/esm/matchingStrategies/cosineSimilarity.js b/dist/esm/matchingStrategies/cosineSimilarity.js
index 318a709..f0623b3 100644
--- a/dist/esm/matchingStrategies/cosineSimilarity.js
+++ b/dist/esm/matchingStrategies/cosineSimilarity.js
@@ -47,13 +47,41 @@ export const calculateCosineSimilarity = (strA, strB) => {
     var termFreqVecB = termFreqMapToVector(termFreqB, dict);
     return cosineSimilarity(termFreqVecA, termFreqVecB);
 };
-export const cosineStrategy = {
+const cosineBaseStrategy = {
     name: 'cosine',
     strategy: (valA, valB) => {
-        const res = calculateCosineSimilarity(valA, valB);
+        let res = calculateCosineSimilarity(valA, valB);
+        if (res > 0.99999) {
+            res = 1;
+        }
         return {
             score: res * 100,
             rawScore: res
         };
     }
 };
+/**
+ * Compares whole tokens (words) within a string independent of order
+ *
+ * This strategy is automatically disabled for strings with less than 4 words because it can lead to inaccurate scores due to not comparing characters IE it is not very useful for short sentences and comparing single words with typos
+ *
+ * If you'd like to use it even in these scenarios build your own strategy array using cosineStrategyAggressive instead of this one
+ * */
+export const cosineStrategy = {
+    ...cosineBaseStrategy,
+    isValid: (valA, valB) => {
+        // cosine only compares full tokens (words), rather than characters, in a string
+        // which makes its score very inaccurate when comparing low token-count strings (short sentences and/or words with typos)
+        // so disable its usage if there are less than 4 tokens
+        const valATokenLength = valA.split(' ').length;
+        const valBTokenLength = valB.split(' ').length;
+        return valATokenLength < 4 || valBTokenLength < 4;
+    }
+};
+/**
+ * Always runs (strings are always valid) which may lead to inaccurate scores in low token-count strings
+ * */
+export const cosineStrategyAggressive = {
+    ...cosineBaseStrategy
+};
+//# sourceMappingURL=cosineSimilarity.js.map
\ No newline at end of file
diff --git a/dist/esm/matchingStrategies/cosineSimilarity.js.map b/dist/esm/matchingStrategies/cosineSimilarity.js.map
new file mode 100644
index 0000000..eaef648
--- /dev/null
+++ b/dist/esm/matchingStrategies/cosineSimilarity.js.map
@@ -0,0 +1 @@
+{"version":3,"file":"cosineSimilarity.js","sourceRoot":"","sources":["../../../src/matchingStrategies/cosineSimilarity.ts"],"names":[],"mappings":"AAAA,sFAAsF;AACtF,2FAA2F;AAa3F,SAAS,WAAW,CAAC,GAAW;IAC5B,IAAI,KAAK,GAAG,GAAG,CAAC,KAAK,CAAC,GAAG,CAAC,CAAC;IAC3B,IAAI,QAAQ,GAAW,EAAE,CAAC;IAC1B,KAAK,CAAC,OAAO,CAAC,UAAU,CAAC;QACrB,QAAQ,CAAC,CAAC,CAAC,GAAG,CAAC,QAAQ,CAAC,CAAC,CAAC,IAAI,CAAC,CAAC,GAAG,CAAC,CAAC;IACzC,CAAC,CAAC,CAAC;IACH,OAAO,QAAQ,CAAC;AACpB,CAAC;AAED,SAAS,aAAa,CAAC,GAAW,EAAE,IAAa;IAC7C,KAAK,IAAI,GAAG,IAAI,GAAG,EAAE;QACjB,IAAI,CAAC,GAAG,CAAC,GAAG,IAAI,CAAC;KACpB;AACL,CAAC;AAED,SAAS,mBAAmB,CAAC,GAAW,EAAE,IAAY;IAClD,IAAI,cAAc,GAAG,EAAE,CAAC;IACxB,KAAK,IAAI,IAAI,IAAI,IAAI,EAAE;QACnB,cAAc,CAAC,IAAI,CAAC,GAAG,CAAC,IAAI,CAAC,IAAI,CAAC,CAAC,CAAC;KACvC;IACD,OAAO,cAAc,CAAC;AAC1B,CAAC;AAED,SAAS,aAAa,CAAC,IAAc,EAAE,IAAc;IACjD,IAAI,OAAO,GAAG,CAAC,CAAC;IAChB,KAAK,IAAI,CAAC,GAAG,CAAC,EAAE,CAAC,GAAG,IAAI,CAAC,MAAM,EAAE,CAAC,EAAE,EAAE;QAClC,OAAO,IAAI,IAAI,CAAC,CAAC,CAAC,GAAG,IAAI,CAAC,CAAC,CAAC,CAAC;KAChC;IACD,OAAO,OAAO,CAAC;AACnB,CAAC;AAED,SAAS,YAAY,CAAC,GAAa;IAC/B,IAAI,GAAG,GAAG,CAAC,CAAC;IACZ,KAAK,IAAI,CAAC,GAAG,CAAC,EAAE,CAAC,GAAG,GAAG,CAAC,MAAM,EAAE,CAAC,EAAE,EAAE;QACjC,GAAG,IAAI,GAAG,CAAC,CAAC,CAAC,GAAG,GAAG,CAAC,CAAC,CAAC,CAAC;KAC1B;IACD,OAAO,IAAI,CAAC,IAAI,CAAC,GAAG,CAAC,CAAC;AAC1B,CAAC;AAED,SAAS,gBAAgB,CAAC,IAAc,EAAE,IAAc;IACpD,OAAO,aAAa,CAAC,IAAI,EAAE,IAAI,CAAC,GAAG,CAAC,YAAY,CAAC,IAAI,CAAC,GAAG,YAAY,CAAC,IAAI,CAAC,CAAC,CAAC;AACjF,CAAC;AAED,MAAM,CAAC,MAAM,yBAAyB,GAAG,CAAC,IAAY,EAAE,IAAY,EAAE,EAAE;IACpE,IAAI,SAAS,GAAG,WAAW,CAAC,IAAI,CAAC,CAAC;IAClC,IAAI,SAAS,GAAG,WAAW,CAAC,IAAI,CAAC,CAAC;IAElC,IAAI,IAAI,GAAG,EAAE,CAAC;IACd,aAAa,CAAC,SAAS,EAAE,IAAI,CAAC,CAAC;IAC/B,aAAa,CAAC,SAAS,EAAE,IAAI,CAAC,CAAC;IAE/B,IAAI,YAAY,GAAG,mBAAmB,CAAC,SAAS,EAAE,IAAI,CAAC,CAAC;IACxD,IAAI,YAAY,GAAG,mBAAmB,CAAC,SAAS,EAAE,IAAI,CAAC,CAAC;IAExD,OAAO,gBAAgB,CAAC,YAAY,EAAE,YAAY,CAAC,CAAC;AACxD,CAAC,CAAA;AAED,MAAM,kBAAkB,GAAuD;IAC3E,IAAI,EAAE,QAAQ;IACd,QAAQ,EAAE,CAAC,IAAY,EAAE,IAAY,EAAE,EAAE;QACrC,IAAI,GAAG,GAAG,yBAAyB,CAAC,IAAI,EAAE,IAAI,CAAC,CAAC;QAChD,IAAG,GAAG,GAAG,OAAO,EAAE;YACd,GAAG,GAAG,CAAC,CAAC;SACX;QACD,OAAO;YACH,KAAK,EAAE,GAAG,GAAG,GAAG;YAChB,QAAQ,EAAE,GAAG;SAChB,CAAA;IACL,CAAC;CACJ,CAAA;AAED;;;;;;KAMK;AACL,MAAM,CAAC,MAAM,cAAc,GAAuD;IAC9E,GAAG,kBAAkB;IACrB,OAAO,EAAE,CAAC,IAAY,EAAE,IAAY,EAAE,EAAE;QACpC,gFAAgF;QAChF,yHAAyH;QACzH,uDAAuD;QACvD,MAAM,eAAe,GAAG,IAAI,CAAC,KAAK,CAAC,GAAG,CAAC,CAAC,MAAM,CAAC;QAC/C,MAAM,eAAe,GAAG,IAAI,CAAC,KAAK,CAAC,GAAG,CAAC,CAAC,MAAM,CAAC;QAC/C,OAAO,eAAe,GAAG,CAAC,IAAI,eAAe,GAAG,CAAC,CAAC;IACtD,CAAC;CACJ,CAAA;AAED;;KAEK;AACL,MAAM,CAAC,MAAM,wBAAwB,GAAuD;IACxF,GAAG,kBAAkB;CACxB,CAAA"}
\ No newline at end of file
diff --git a/dist/esm/matchingStrategies/diceSimilarity.d.ts b/dist/esm/matchingStrategies/diceSimilarity.d.ts
index 6cb2a48..65d0389 100644
--- a/dist/esm/matchingStrategies/diceSimilarity.d.ts
+++ b/dist/esm/matchingStrategies/diceSimilarity.d.ts
@@ -1,3 +1,3 @@
-import { ComparisonStrategy } from "../atomic.js";
+import { ComparisonStrategy, ComparisonStrategyResultObject } from "../atomic.js";
 export declare const calculateDiceSimilarity: (valA: string, valB: string) => number;
-export declare const diceStrategy: ComparisonStrategy;
+export declare const diceStrategy: ComparisonStrategy<ComparisonStrategyResultObject>;
diff --git a/dist/esm/matchingStrategies/diceSimilarity.js b/dist/esm/matchingStrategies/diceSimilarity.js
index 595377a..cd00b1a 100644
--- a/dist/esm/matchingStrategies/diceSimilarity.js
+++ b/dist/esm/matchingStrategies/diceSimilarity.js
@@ -10,3 +10,4 @@ export const diceStrategy = {
         };
     }
 };
+//# sourceMappingURL=diceSimilarity.js.map
\ No newline at end of file
diff --git a/dist/esm/matchingStrategies/diceSimilarity.js.map b/dist/esm/matchingStrategies/diceSimilarity.js.map
new file mode 100644
index 0000000..cb4e84e
--- /dev/null
+++ b/dist/esm/matchingStrategies/diceSimilarity.js.map
@@ -0,0 +1 @@
+{"version":3,"file":"diceSimilarity.js","sourceRoot":"","sources":["../../../src/matchingStrategies/diceSimilarity.ts"],"names":[],"mappings":"AAAA,OAAO,gBAAgB,MAAM,mBAAmB,CAAC;AAGjD,MAAM,CAAC,MAAM,uBAAuB,GAAG,CAAC,IAAY,EAAE,IAAY,EAAE,EAAE,CAAC,gBAAgB,CAAC,iBAAiB,CAAC,IAAI,EAAE,IAAI,CAAC,CAAC;AACtH,MAAM,CAAC,MAAM,YAAY,GAAuD;IAC5E,IAAI,EAAE,MAAM;IACZ,QAAQ,EAAE,CAAC,IAAY,EAAE,IAAY,EAAE,EAAE;QACrC,MAAM,GAAG,GAAG,uBAAuB,CAAC,IAAI,EAAE,IAAI,CAAC,CAAC;QAChD,OAAO;YACH,KAAK,EAAE,GAAG,GAAG,GAAG;YAChB,QAAQ,EAAE,GAAG;SAChB,CAAA;IACL,CAAC;CACJ,CAAA"}
\ No newline at end of file
diff --git a/dist/esm/matchingStrategies/index.d.ts b/dist/esm/matchingStrategies/index.d.ts
index a3d62ec..8c9b96f 100644
--- a/dist/esm/matchingStrategies/index.d.ts
+++ b/dist/esm/matchingStrategies/index.d.ts
@@ -1,5 +1,5 @@
 import { levenStrategy } from "./levenSimilarity.js";
-import { cosineStrategy } from "./cosineSimilarity.js";
+import { cosineStrategy, cosineStrategyAggressive } from "./cosineSimilarity.js";
 import { diceStrategy } from "./diceSimilarity.js";
 import { ComparisonStrategy, ComparisonStrategyResultValue, ComparisonStrategyResultObject, StrategyFunc } from '../atomic.js';
-export { levenStrategy, cosineStrategy, diceStrategy, ComparisonStrategy, ComparisonStrategyResultObject, ComparisonStrategyResultValue, StrategyFunc };
+export { levenStrategy, cosineStrategy, cosineStrategyAggressive, diceStrategy, ComparisonStrategy, ComparisonStrategyResultObject, ComparisonStrategyResultValue, StrategyFunc };
diff --git a/dist/esm/matchingStrategies/index.js b/dist/esm/matchingStrategies/index.js
index f55d695..2cdbf8c 100644
--- a/dist/esm/matchingStrategies/index.js
+++ b/dist/esm/matchingStrategies/index.js
@@ -1,4 +1,5 @@
 import { levenStrategy } from "./levenSimilarity.js";
-import { cosineStrategy } from "./cosineSimilarity.js";
+import { cosineStrategy, cosineStrategyAggressive } from "./cosineSimilarity.js";
 import { diceStrategy } from "./diceSimilarity.js";
-export { levenStrategy, cosineStrategy, diceStrategy };
+export { levenStrategy, cosineStrategy, cosineStrategyAggressive, diceStrategy };
+//# sourceMappingURL=index.js.map
\ No newline at end of file
diff --git a/dist/esm/matchingStrategies/index.js.map b/dist/esm/matchingStrategies/index.js.map
new file mode 100644
index 0000000..5e4098b
--- /dev/null
+++ b/dist/esm/matchingStrategies/index.js.map
@@ -0,0 +1 @@
+{"version":3,"file":"index.js","sourceRoot":"","sources":["../../../src/matchingStrategies/index.ts"],"names":[],"mappings":"AAAA,OAAO,EAAC,aAAa,EAAC,MAAM,sBAAsB,CAAC;AACnD,OAAO,EAAC,cAAc,EAAE,wBAAwB,EAAC,MAAM,uBAAuB,CAAC;AAC/E,OAAO,EAAC,YAAY,EAAC,MAAM,qBAAqB,CAAC;AAGjD,OAAO,EACH,aAAa,EACb,cAAc,EACd,wBAAwB,EACxB,YAAY,EAKf,CAAA"}
\ No newline at end of file
diff --git a/dist/esm/matchingStrategies/levenSimilarity.d.ts b/dist/esm/matchingStrategies/levenSimilarity.d.ts
index 113d82d..4dee4fe 100644
--- a/dist/esm/matchingStrategies/levenSimilarity.d.ts
+++ b/dist/esm/matchingStrategies/levenSimilarity.d.ts
@@ -1,3 +1,3 @@
-import { ComparisonStrategy } from "../atomic.js";
+import { ComparisonStrategy, ComparisonStrategyResultObject } from "../atomic.js";
 export declare const calculateLevenSimilarity: (valA: string, valB: string) => number[];
-export declare const levenStrategy: ComparisonStrategy;
+export declare const levenStrategy: ComparisonStrategy<ComparisonStrategyResultObject>;
diff --git a/dist/esm/matchingStrategies/levenSimilarity.js b/dist/esm/matchingStrategies/levenSimilarity.js
index 0e4f765..3852db8 100644
--- a/dist/esm/matchingStrategies/levenSimilarity.js
+++ b/dist/esm/matchingStrategies/levenSimilarity.js
@@ -11,7 +11,11 @@ export const calculateLevenSimilarity = (valA, valB) => {
         shorter = valA;
     }
     const distance = leven(longer, shorter);
-    const diff = (distance / longer.length) * 100;
+    // use the shorter length
+    // because if we have more move/change operations than the length of the shortest string than we have two unique strings
+    // and if we use the longer length the score actually gets *better* as the length gap gets larger (not what we want)
+    // -- cap at 100% diff
+    const diff = Math.min((distance / shorter.length) * 100, 100);
     return [distance, 100 - diff];
 };
 const stratFunc = (valA, valB) => {
@@ -26,3 +30,4 @@ export const levenStrategy = {
     name: 'leven',
     strategy: stratFunc
 };
+//# sourceMappingURL=levenSimilarity.js.map
\ No newline at end of file
diff --git a/dist/esm/matchingStrategies/levenSimilarity.js.map b/dist/esm/matchingStrategies/levenSimilarity.js.map
new file mode 100644
index 0000000..a8faf41
--- /dev/null
+++ b/dist/esm/matchingStrategies/levenSimilarity.js.map
@@ -0,0 +1 @@
+{"version":3,"file":"levenSimilarity.js","sourceRoot":"","sources":["../../../src/matchingStrategies/levenSimilarity.ts"],"names":[],"mappings":"AAAA,OAAO,KAAK,MAAM,OAAO,CAAC;AAG1B,MAAM,CAAC,MAAM,wBAAwB,GAAG,CAAC,IAAY,EAAE,IAAY,EAAE,EAAE;IACnE,IAAI,MAAc,CAAC;IACnB,IAAI,OAAe,CAAC;IACpB,IAAI,IAAI,CAAC,MAAM,GAAG,IAAI,CAAC,MAAM,EAAE;QAC3B,MAAM,GAAG,IAAI,CAAC;QACd,OAAO,GAAG,IAAI,CAAC;KAClB;SAAM;QACH,MAAM,GAAG,IAAI,CAAC;QACd,OAAO,GAAG,IAAI,CAAC;KAClB;IAED,MAAM,QAAQ,GAAG,KAAK,CAAC,MAAM,EAAE,OAAO,CAAC,CAAC;IACxC,yBAAyB;IACzB,wHAAwH;IACxH,oHAAoH;IACpH,sBAAsB;IACtB,MAAM,IAAI,GAAG,IAAI,CAAC,GAAG,CAAC,CAAC,QAAQ,GAAG,OAAO,CAAC,MAAM,CAAC,GAAG,GAAG,EAAE,GAAG,CAAC,CAAC;IAC9D,OAAO,CAAC,QAAQ,EAAE,GAAG,GAAG,IAAI,CAAC,CAAC;AAClC,CAAC,CAAA;AAED,MAAM,SAAS,GAAG,CAAC,IAAY,EAAE,IAAY,EAAE,EAAE;IAC7C,MAAM,GAAG,GAAG,wBAAwB,CAAC,IAAI,EAAE,IAAI,CAAC,CAAC;IACjD,OAAO;QACH,QAAQ,EAAE,GAAG,CAAC,CAAC,CAAC;QAChB,QAAQ,EAAE,GAAG,CAAC,CAAC,CAAC;QAChB,KAAK,EAAE,GAAG,CAAC,CAAC,CAAC;KAChB,CAAC;AACN,CAAC,CAAA;AAED,MAAM,CAAC,MAAM,aAAa,GAAuD;IAC7E,IAAI,EAAE,OAAO;IACb,QAAQ,EAAE,SAAS;CACtB,CAAA"}
\ No newline at end of file
diff --git a/dist/esm/normalization/index.d.ts b/dist/esm/normalization/index.d.ts
new file mode 100644
index 0000000..ae891c2
--- /dev/null
+++ b/dist/esm/normalization/index.d.ts
@@ -0,0 +1,17 @@
+import { StringTransformFunc } from "../atomic.js";
+declare const lowercase: StringTransformFunc;
+declare const trim: StringTransformFunc;
+declare const replaceUnicode: StringTransformFunc;
+declare const removePunctuation: StringTransformFunc;
+declare const removeWhitespace: StringTransformFunc;
+declare const replaceMultiWhitespace: StringTransformFunc;
+declare const transforms: {
+    lowercase: StringTransformFunc;
+    trim: StringTransformFunc;
+    replaceMultiWhitespace: StringTransformFunc;
+    replaceUnicode: StringTransformFunc;
+    removeWhitespace: StringTransformFunc;
+    removePunctuation: StringTransformFunc;
+};
+declare const strDefaultTransforms: StringTransformFunc[];
+export { lowercase, trim, replaceUnicode, removePunctuation, removeWhitespace, replaceMultiWhitespace, transforms, strDefaultTransforms };
diff --git a/dist/esm/normalization/index.js b/dist/esm/normalization/index.js
new file mode 100644
index 0000000..8029f5d
--- /dev/null
+++ b/dist/esm/normalization/index.js
@@ -0,0 +1,26 @@
+const PUNCTUATION_REGEX = new RegExp(/[^\w\s]|_/g);
+const WHITESPACE_REGEX = new RegExp(/\s/g);
+const MULTI_WHITESPACE_REGEX = new RegExp(/\s{2,}|\n/g);
+const lowercase = (str) => str.toLocaleLowerCase();
+const trim = (str) => str.trim();
+const replaceUnicode = (str) => str.normalize('NFD').replace(/[\u0300-\u036f]/g, "");
+const removePunctuation = (str) => str.replace(PUNCTUATION_REGEX, '');
+const removeWhitespace = (str) => str.replace(WHITESPACE_REGEX, '');
+const replaceMultiWhitespace = (str) => str.replace(MULTI_WHITESPACE_REGEX, '');
+const transforms = {
+    lowercase,
+    trim,
+    replaceMultiWhitespace,
+    replaceUnicode,
+    removeWhitespace,
+    removePunctuation
+};
+const strDefaultTransforms = [
+    replaceUnicode,
+    removePunctuation,
+    trim,
+    replaceMultiWhitespace,
+    lowercase
+];
+export { lowercase, trim, replaceUnicode, removePunctuation, removeWhitespace, replaceMultiWhitespace, transforms, strDefaultTransforms };
+//# sourceMappingURL=index.js.map
\ No newline at end of file
diff --git a/dist/esm/normalization/index.js.map b/dist/esm/normalization/index.js.map
new file mode 100644
index 0000000..68fe96f
--- /dev/null
+++ b/dist/esm/normalization/index.js.map
@@ -0,0 +1 @@
+{"version":3,"file":"index.js","sourceRoot":"","sources":["../../../src/normalization/index.ts"],"names":[],"mappings":"AAEA,MAAM,iBAAiB,GAAG,IAAI,MAAM,CAAC,YAAY,CAAC,CAAC;AACnD,MAAM,gBAAgB,GAAG,IAAI,MAAM,CAAC,KAAK,CAAC,CAAC;AAC3C,MAAM,sBAAsB,GAAG,IAAI,MAAM,CAAC,YAAY,CAAC,CAAC;AAExD,MAAM,SAAS,GAAwB,CAAC,GAAW,EAAE,EAAE,CAAC,GAAG,CAAC,iBAAiB,EAAE,CAAC;AAChF,MAAM,IAAI,GAAwB,CAAC,GAAW,EAAE,EAAE,CAAC,GAAG,CAAC,IAAI,EAAE,CAAC;AAC9D,MAAM,cAAc,GAAwB,CAAC,GAAW,EAAE,EAAE,CAAC,GAAG,CAAC,SAAS,CAAC,KAAK,CAAC,CAAC,OAAO,CAAC,kBAAkB,EAAE,EAAE,CAAC,CAAC;AAClH,MAAM,iBAAiB,GAAwB,CAAC,GAAW,EAAE,EAAE,CAAC,GAAG,CAAC,OAAO,CAAC,iBAAiB,EAAE,EAAE,CAAC,CAAC;AACnG,MAAM,gBAAgB,GAAwB,CAAC,GAAW,EAAE,EAAE,CAAC,GAAG,CAAC,OAAO,CAAC,gBAAgB,EAAE,EAAE,CAAC,CAAC;AACjG,MAAM,sBAAsB,GAAwB,CAAC,GAAW,EAAE,EAAE,CAAC,GAAG,CAAC,OAAO,CAAC,sBAAsB,EAAE,EAAE,CAAC,CAAC;AAE7G,MAAM,UAAU,GAAG;IACf,SAAS;IACT,IAAI;IACJ,sBAAsB;IACtB,cAAc;IACd,gBAAgB;IAChB,iBAAiB;CACpB,CAAA;AAED,MAAM,oBAAoB,GAA0B;IAChD,cAAc;IACd,iBAAiB;IACjB,IAAI;IACJ,sBAAsB;IACtB,SAAS;CACZ,CAAC;AAEF,OAAO,EACH,SAAS,EACT,IAAI,EACJ,cAAc,EACd,iBAAiB,EACjB,gBAAgB,EAChB,sBAAsB,EACtB,UAAU,EACV,oBAAoB,EACvB,CAAA"}
\ No newline at end of file
diff --git a/package.json b/package.json
index ef1425a..ad5ef6a 100644
--- a/package.json
+++ b/package.json
@@ -19,7 +19,7 @@
     "typedoc": "typedoc",
     "build": "tsc",
     "prepare": "tshy",
-    "test":  "mocha --recursive ./tests/*.test.ts"
+    "test": "mocha --recursive ./tests/*.test.ts"
   },
   "exports": {
     "./package.json": "./package.json",
diff --git a/src/atomic.ts b/src/atomic.ts
index 1d73f02..37aacdf 100644
--- a/src/atomic.ts
+++ b/src/atomic.ts
@@ -1,5 +1,5 @@
 export interface StringComparisonOptions {
-    transforms?: ((str: string) => string)[]
+    transforms?: StringTransformFunc[]
     strategies?: ComparisonStrategy<ComparisonStrategyResultValue>[]
 }
 
@@ -52,3 +52,5 @@ export interface ComparisonStrategy<T extends ComparisonStrategyResultValue> {
      * */
     isValid?: (strA: string, strB: string) => boolean
 }
+
+export type StringTransformFunc = (str: string) => string;
diff --git a/src/index.ts b/src/index.ts
index 5d70858..06063c2 100644
--- a/src/index.ts
+++ b/src/index.ts
@@ -3,8 +3,10 @@ import {
     ComparisonStrategyResult,
     NamedComparisonStrategyObjectResult,
     StringComparisonOptions,
-    StringSamenessResult
+    StringSamenessResult,
+    StringTransformFunc
 } from "./atomic.js";
+import {strDefaultTransforms, transforms} from "./normalization/index.js";
 
 const sentenceLengthWeight = (length: number) => {
     // thanks jordan :')
@@ -12,17 +14,6 @@ const sentenceLengthWeight = (length: number) => {
     return (Math.log(length) / 0.20) - 5;
 }
 
-const defaultStrCompareTransformFuncs = [
-    // lower case to remove case sensitivity
-    (str: string) => str.toLocaleLowerCase(),
-    // remove excess whitespace
-    (str: string) => str.trim(),
-    // remove non-alphanumeric characters so that differences in punctuation don't subtract from comparison score
-    (str: string) => str.replace(/[^A-Za-z0-9 ]/g, ""),
-    // replace all instances of 2 or more whitespace with one whitespace
-    (str: string) => str.replace(/\s{2,}|\n/g, " ")
-];
-
 const defaultStrategies = [
     diceStrategy,
     levenStrategy,
@@ -32,7 +23,7 @@ const defaultStrategies = [
 const stringSameness = (valA: string, valB: string, options?: StringComparisonOptions): StringSamenessResult => {
 
     const {
-        transforms = defaultStrCompareTransformFuncs,
+        transforms = strDefaultTransforms,
         strategies = defaultStrategies,
     } = options || {};
 
@@ -88,6 +79,9 @@ const strategies = {
     cosineStrategyAggressive
 };
 
+// maintaining compatibility
+const defaultStrCompareTransformFuncs = strDefaultTransforms;
+
 export {
     StringSamenessResult,
     StringComparisonOptions,
@@ -95,6 +89,9 @@ export {
     createStringSameness,
     defaultStrategies,
     strategies,
+    transforms,
     defaultStrCompareTransformFuncs,
-    ComparisonStrategyResult
+    strDefaultTransforms,
+    ComparisonStrategyResult,
+    StringTransformFunc
 }
diff --git a/src/normalization/index.ts b/src/normalization/index.ts
new file mode 100644
index 0000000..61c85b7
--- /dev/null
+++ b/src/normalization/index.ts
@@ -0,0 +1,40 @@
+import {StringTransformFunc} from "../atomic.js";
+
+const PUNCTUATION_REGEX = new RegExp(/[^\w\s]|_/g);
+const WHITESPACE_REGEX = new RegExp(/\s/g);
+const MULTI_WHITESPACE_REGEX = new RegExp(/\s{2,}/g);
+
+const lowercase: StringTransformFunc = (str: string) => str.toLocaleLowerCase();
+const trim: StringTransformFunc = (str: string) => str.trim();
+const replaceUnicode: StringTransformFunc = (str: string) => str.normalize('NFD').replace(/[\u0300-\u036f]/g, "");
+const removePunctuation: StringTransformFunc = (str: string) => str.replace(PUNCTUATION_REGEX, '');
+const removeWhitespace: StringTransformFunc = (str: string) => str.replace(WHITESPACE_REGEX, '');
+const replaceMultiWhitespace: StringTransformFunc = (str: string) => str.replace(MULTI_WHITESPACE_REGEX, ' ');
+
+const transforms = {
+    lowercase,
+    trim,
+    replaceMultiWhitespace,
+    replaceUnicode,
+    removeWhitespace,
+    removePunctuation
+}
+
+const strDefaultTransforms: StringTransformFunc[] = [
+    replaceUnicode,
+    removePunctuation,
+    trim,
+    replaceMultiWhitespace,
+    lowercase
+];
+
+export {
+    lowercase,
+    trim,
+    replaceUnicode,
+    removePunctuation,
+    removeWhitespace,
+    replaceMultiWhitespace,
+    transforms,
+    strDefaultTransforms
+}
diff --git a/tests/index.test.ts b/tests/index.test.ts
index 41fcc53..a82c8f1 100644
--- a/tests/index.test.ts
+++ b/tests/index.test.ts
@@ -16,33 +16,43 @@ describe('String normalization', function() {
     it('should normalize punctuation', async function () {
 
         const valA = 'this string! is the. same';
-        const valB = 'this string is the same';
 
-        assert.equal(normalizeStr(valA), normalizeStr(valB))
+        assert.equal(normalizeStr(valA), sameString)
     });
 
     it('should normalize whitespace', async function () {
 
         const valA = 'this string   is the   same   ';
-        const valB = 'this string is the same';
 
-        assert.equal(normalizeStr(valA), normalizeStr(valB))
+        assert.equal(normalizeStr(valA), sameString)
     });
 
     it('should normalize whitespace at end and beginning', async function () {
 
         const valA = ' this string is the same ';
-        const valB = 'this string is the same';
 
-        assert.equal(normalizeStr(valA), normalizeStr(valB))
+        assert.equal(normalizeStr(valA), sameString)
     });
 
     it('should normalize case', async function () {
 
         const valA = 'ThIs STRING iS THe SAMe';
-        const valB = 'this string is the same';
 
-        assert.equal(normalizeStr(valA), normalizeStr(valB))
+        assert.equal(normalizeStr(valA), sameString)
+    });
+
+    it('should normalize unicode', async function () {
+
+        const tests = [
+            ['enamorate bailando','Enamórate Bailando'],
+            ['dina ogon', 'Dina Ögon'],
+            ['nana', 'Nanã'],
+            ['nana', 'Nanä']
+        ]
+
+        for(const test of tests) {
+            assert.equal(normalizeStr(test[1]), test[0])
+        }
     });
 });
 
diff --git a/typedoc.json b/typedoc.json
index d01e4ef..e9ff722 100644
--- a/typedoc.json
+++ b/typedoc.json
@@ -1,7 +1,11 @@
 {
   "$schema": "https://typedoc.org/schema.json",
   "name": "string-sameness Docs",
-  "entryPoints": ["./src","./src/matchingStrategies/index.ts"],
+  "entryPoints": [
+    "./src",
+    "./src/matchingStrategies/index.ts",
+    "./src/normalization/index.ts"
+  ],
   "sort": ["source-order"],
   "categorizeByGroup": false,
   "searchGroupBoosts": {