From eead40033e760ff7bc51d3b507c849f2d6842126 Mon Sep 17 00:00:00 2001
From: Jake Boone <jakeboone02@gmail.com>
Date: Thu, 18 Jan 2024 10:12:16 -0700
Subject: [PATCH] Add `ignoreUOMs` option

---
 CHANGELOG.md                |  4 ++-
 README.md                   | 61 +++++++++++++++++++++----------------
 src/constants.ts            |  1 +
 src/parseIngredient.ts      | 11 +++++--
 src/parseIngredientTests.ts | 22 +++++++++++++
 src/types.ts                | 24 +++++++++++++++
 6 files changed, 93 insertions(+), 30 deletions(-)

diff --git a/CHANGELOG.md b/CHANGELOG.md
index 014aa0d..f72579b 100644
--- a/CHANGELOG.md
+++ b/CHANGELOG.md
@@ -7,7 +7,9 @@ and this project adheres to [Semantic Versioning](http://semver.org/spec/v2.0.0.
 
 ## [Unreleased]
 
-- N/A
+### Added
+
+- New option `ignoreUOMs`, an array of strings that will _not_ be considered units of measure.
 
 ## [v1.1.1] - 2024-01-15
 
diff --git a/README.md b/README.md
index a0221ae..590b210 100644
--- a/README.md
+++ b/README.md
@@ -64,7 +64,7 @@ In the browser, all exports including the `parseIngredient` function are availab
 ```html
 <script src="https://unpkg.com/parse-ingredient"></script>
 <script>
-  console.log(ParseIngredient.parseIngredient('1 1/2 cups sugar'));
+  ParseIngredient.parseIngredient('1 1/2 cups sugar');
   // [
   //   {
   //     quantity: 1.5,
@@ -83,7 +83,7 @@ In the browser, all exports including the `parseIngredient` function are availab
 ```js
 import { parseIngredient } from 'parse-ingredient';
 
-console.log(parseIngredient('1-2 pears'));
+parseIngredient('1-2 pears');
 // [
 //   {
 //     quantity: 1,
@@ -94,11 +94,10 @@ console.log(parseIngredient('1-2 pears'));
 //     isGroupHeader: false,
 //   }
 // ]
-console.log(
-  parseIngredient(
-    `2/3 cup flour
+
+parseIngredient(
+  `2/3 cup flour
 1 tsp baking powder`
-  )
 );
 // [
 //   {
@@ -118,7 +117,7 @@ console.log(
 //     isGroupHeader: false,
 //   },
 // ]
-console.log(parseIngredient('For cake:'));
+parseIngredient('For cake:');
 // [
 //   {
 //     quantity: null,
@@ -129,7 +128,7 @@ console.log(parseIngredient('For cake:'));
 //     isGroupHeader: true,
 //   }
 // ]
-console.log(parseIngredient('Ripe tomato x2'));
+parseIngredient('Ripe tomato x2');
 // [
 //   {
 //     quantity: 2,
@@ -148,10 +147,8 @@ console.log(parseIngredient('Ripe tomato x2'));
 
 Pass `true` to convert units of measure to their long, singular form, e.g. "ml" becomes "milliliter" and "cups" becomes "cup". This can help normalize the units of measure for processing. In most cases, this option will make `unitOfMeasure` equivalent to `unitOfMeasureID`.
 
-Example:
-
 ```js
-console.log(parseIngredient('1 c sugar', { normalizeUOM: true }));
+parseIngredient('1 c sugar', { normalizeUOM: true });
 // [
 //   {
 //     quantity: 1,
@@ -168,20 +165,16 @@ console.log(parseIngredient('1 c sugar', { normalizeUOM: true }));
 
 Pass an object that matches the format of the exported `unitsOfMeasure` object. Keys that match any in the exported object will be used instead of the default, and any others will be added to the list of known units of measure when parsing ingredients.
 
-Example:
-
 ```js
-console.log(
-  parseIngredient('2 buckets of widgets', {
-    additionalUOMs: {
-      bucket: {
-        short: 'bkt',
-        plural: 'buckets',
-        versions: ['bk'],
-      },
+parseIngredient('2 buckets of widgets', {
+  additionalUOMs: {
+    bucket: {
+      short: 'bkt',
+      plural: 'buckets',
+      versions: ['bk'],
     },
-  })
-);
+  },
+});
 // [
 //   {
 //     quantity: 2,
@@ -198,10 +191,8 @@ console.log(
 
 When `true`, ingredient descriptions that start with "of " will not be modified. (By default, a leading "of " will be removed from all descriptions.)
 
-Example:
-
 ```js
-console.log(parseIngredient('1 cup of sugar', { allowLeadingOf: true }));
+parseIngredient('1 cup of sugar', { allowLeadingOf: true });
 // [
 //   {
 //     quantity: 1,
@@ -214,6 +205,24 @@ console.log(parseIngredient('1 cup of sugar', { allowLeadingOf: true }));
 // ]
 ```
 
+### `ignoreUOMs`
+
+An array of strings to ignore as units of measure when parsing ingredients.
+
+```js
+parseIngredient('2 large eggs', { ignoreUOMs: ['large'] });
+// [
+//   {
+//     quantity: 2,
+//     quantity2: null,
+//     unitOfMeasure: null,
+//     unitOfMeasureID: null,
+//     description: 'large eggs',
+//     isGroupHeader: false,
+//   }
+// ]
+```
+
 ## Contributors ✨
 
 Thanks goes to these wonderful people ([emoji key](https://allcontributors.org/docs/en/emoji-key)):
diff --git a/src/constants.ts b/src/constants.ts
index 966b7a2..7be2b1e 100644
--- a/src/constants.ts
+++ b/src/constants.ts
@@ -8,6 +8,7 @@ export const defaultOptions = {
   additionalUOMs: {},
   allowLeadingOf: false,
   normalizeUOM: false,
+  ignoreUOMs: [],
 } as const satisfies Required<ParseIngredientOptions>;
 
 /**
diff --git a/src/parseIngredient.ts b/src/parseIngredient.ts
index c2d4d11..66a855c 100644
--- a/src/parseIngredient.ts
+++ b/src/parseIngredient.ts
@@ -52,8 +52,11 @@ export const parseIngredient = (
       // The first character is not numeric. First check for trailing quantity/uom.
       const trailingQtyResult = trailingQuantityRegEx.exec(line);
 
-      if (trailingQtyResult) {
-        // Trailing quantity detected.
+      if (trailingQtyResult && opts.ignoreUOMs.includes(trailingQtyResult.at(-1) ?? '')) {
+        // Trailing quantity detected, but bailing out since the UOM should be ignored.
+        oIng.description = line;
+      } else if (trailingQtyResult) {
+        // Trailing quantity detected with missing or non-ignored UOM.
         // Remove the quantity and unit of measure from the description.
         oIng.description = line.replace(trailingQuantityRegEx, '').trim();
 
@@ -153,7 +156,9 @@ export const parseIngredient = (
 
         while (++i < uomArrayLength && !uom) {
           const { alternates, id, short, plural } = uomArray[i];
-          const versions = [...alternates, id, short, plural];
+          const versions = [...alternates, id, short, plural].filter(
+            unit => !opts.ignoreUOMs.includes(unit)
+          );
           if (versions.includes(firstWord)) {
             uom = firstWord;
             uomID = id;
diff --git a/src/parseIngredientTests.ts b/src/parseIngredientTests.ts
index b0c393b..34d6caf 100644
--- a/src/parseIngredientTests.ts
+++ b/src/parseIngredientTests.ts
@@ -526,4 +526,26 @@ export const parseIngredientTests: Record<
       },
     ],
   ],
+  'ignores units of measure': [
+    '1 cup stuff\nstuff x 2 cups',
+    [
+      {
+        quantity: 1,
+        quantity2: null,
+        unitOfMeasureID: null,
+        unitOfMeasure: null,
+        description: 'cup stuff',
+        isGroupHeader: false,
+      },
+      {
+        quantity: null,
+        quantity2: null,
+        unitOfMeasureID: null,
+        unitOfMeasure: null,
+        description: 'stuff x 2 cups',
+        isGroupHeader: false,
+      },
+    ],
+    { ignoreUOMs: ['cup', 'cups'] },
+  ],
 };
diff --git a/src/types.ts b/src/types.ts
index 993e4fe..9276db2 100644
--- a/src/types.ts
+++ b/src/types.ts
@@ -69,6 +69,30 @@ export interface ParseIngredientOptions {
    * @default {}
    */
   additionalUOMs?: UnitOfMeasureDefinitions;
+  /**
+   * An array of strings to ignore as units of measure when parsing ingredients.
+   *
+   * @example
+   *
+   * ```ts
+   * parseIngredient('2 small eggs', {
+   *   ignoreUOMs: ['small', 'medium', 'large']
+   * })
+   * // [
+   * //   {
+   * //     quantity: 2,
+   * //     quantity2: null,
+   * //     unitOfMeasure: null,
+   * //     unitOfMeasureID: null,
+   * //     description: 'small eggs',
+   * //     isGroupHeader: false,
+   * //   }
+   * // ]
+   * ```
+   *
+   * @default []
+   */
+  ignoreUOMs?: string[];
   /**
    * If `true`, ingredient descriptions that start with "of " will not be
    * modified. (By default, a leading "of " will be removed from all descriptions.)