finish adding slashes method

README.md

@@ -68,7 +68,7 @@ and how hard it is to actually <b>parse</b> and <i>use</i>?
 
 <img height="45px" src="https://user-images.githubusercontent.com/399657/68221862-17ceb980-ffb8-11e9-87d4-7b30b6488f16.png"/>
 
- <!-- 
+ <!--
   it is
   <a href="https://docs.compromise.cool/compromise-filesize">small,
   <a href="https://docs.compromise.cool/compromise-performance">quick</a>,
@@ -136,7 +136,7 @@ doc.places().json()
 /*
 [{
   "text": "Milwaukee",
-  "terms": [{ 
+  "terms": [{
     "normal": "milwaukee",
     "syllables": ["mil", "wau", "kee"]
   }]
@@ -148,7 +148,7 @@ doc.places().json()
   <a href="https://docs.compromise.cool/compromise-json">json docs</a>
 </div>
 <div align="center">
-  <img height="50px" src="https://user-images.githubusercontent.com/399657/68221814-05ed1680-ffb8-11e9-8b6b-c7528d163871.png"/>  
+  <img height="50px" src="https://user-images.githubusercontent.com/399657/68221814-05ed1680-ffb8-11e9-8b6b-c7528d163871.png"/>
 </div>
 
 <!-- spacer -->
@@ -292,11 +292,11 @@ import nlp from 'compromise/one'
 
 let doc = nlp("Wayne's World, party time")
 let data = doc.json()
-/* [{ 
+/* [{
   normal:"wayne's world party time",
-    terms:[{ text: "Wayne's", normal: "wayne" }, 
+    terms:[{ text: "Wayne's", normal: "wayne" },
       ...
-      ] 
+      ]
   }]
 */
 ```
@@ -717,6 +717,8 @@ _(these methods are on the main `nlp` object)_
   - **[.possessives().strip()](https://observablehq.com/@spencermountain/compromise-selections)** - "Spencer's" -> "Spencer"
 - **[.quotations()](https://observablehq.com/@spencermountain/compromise-selections)** - return any terms inside paired quotation marks
   - **[.quotations().strip()](https://observablehq.com/@spencermountain/compromise-selections)** - remove quotation marks
+- **[.slashes()](https://observablehq.com/@spencermountain/compromise-selections)** - return any terms grouped by slashes
+  - **[.slashes().split()](https://observablehq.com/@spencermountain/compromise-selections)** - turn 'love/hate' into 'love hate'
 
 <p>
 <img height="85px" src="https://user-images.githubusercontent.com/399657/68221862-17ceb980-ffb8-11e9-87d4-7b30b6488f16.png"/>
@@ -990,7 +992,7 @@ nlpEx('This is type safe!').ngrams({ min: 1 })
       </ul>
       <p></p>
     </details>
-  </p>  
+  </p>
   <p>
     <details>
       <summary>💃 Can it run on my arduino-watch?</summary>
@@ -1021,13 +1023,13 @@ nlpEx('This is type safe!').ngrams({ min: 1 })
       <p></p>
       <ul>
         we do offer a <a href="https://observablehq.com/@spencermountain/compromise-filesize">tokenize-only</a> build, which has the POS-tagger pulled-out.
-        <br/> 
+        <br/>
         but otherwise, compromise isn't easily tree-shaken.
-        <br/> 
+        <br/>
         the tagging methods are competitive, and greedy, so it's not recommended to pull things out.
-        <br/> 
+        <br/>
         Note that without a full POS-tagging, the contraction-parser won't work perfectly. (<i>(spencer's cool)</i> vs. <i>(spencer's house)</i>)
-        <br/> 
+        <br/>
         It's recommended to run the library fully.
       </ul>
       <p></p>

changelog.md

@@ -21,6 +21,7 @@ While all _Major_ releases should be reviewed, our only _large_ releases are **v
 -->
 
 #### 14.14.0 [July 2024]
+- **[new]** - .slashes() and .slashes().split() methods #1100
 - **[fix]** - #1113 toNumbers() return values
 - **[fix]** - (plugins/wikipedia) - fix hard-coded path for #1116
 - **[fix]** - (plugins/dates) - limit values in `mm/dd` format

scratch.js

@@ -4,15 +4,12 @@ import nlp from './src/three.js'
 // nlp.plugin(plg)
 // nlp.verbose('tagger')
 //
-let str = 'they left   his/her/their  backpack '
-// const doc = nlp('IEEE/WIC/ACM')
-const doc = nlp(str)
-doc.slashes().split().debug()
-doc.debug()
-// console.log(doc.has('#SlashedTerm'))
-// doc.debug()
-// let doc = nlp(`   `).debug()
+const text = 'Worst-case Ontario, you get caught.'
 
+const doc = nlp(text)
+
+doc.match('Ontario').replaceWith('scenario', { keepTags: true })
+doc.debug()
 // -bury
 // -ford
 // -ton

tests/three/slashes.test.js

@@ -0,0 +1,31 @@
+import test from 'tape'
+import nlp from './_lib.js'
+const here = '[three/slashes] '
+
+test('slashes.split', function (t) {
+  let doc = nlp(`i saw him/her yesterday at 2pm.`)
+  t.equal(doc.has('#SlashedTerm'), true, here + 'has slash-tag')
+  let m = doc.slashes()
+  t.equal(m.length, 1, here + '1 slash')
+  t.equal(m.text(), 'him/her', here + 'slash-text')
+  m = m.split()
+  t.equal(m.text(), 'him her', here + 'slash-text-after')
+  t.equal(m.terms().length, 2, here + 'slash-terms-after')
+  t.equal(doc.text(), 'i saw him her yesterday at 2pm.', here + 'doc-text-after')
+  t.equal(doc.has('#SlashedTerm'), false, here + 'has no slash-tag')
+  t.end()
+})
+
+test('three-slashes.split', function (t) {
+  let doc = nlp(`before. one two/three/four five. after`)
+  t.equal(doc.has('#SlashedTerm'), true, here + 'has slash-tag')
+  let m = doc.slashes()
+  t.equal(m.length, 1, here + '1 slash')
+  t.equal(m.text(), 'two/three/four', here + 'slash-text')
+  m = m.split()
+  t.equal(m.text(), 'two three four', here + 'slash-text-after')
+  t.equal(m.terms().length, 3, here + 'slash-terms-after')
+  t.equal(doc.text(), 'before. one two three four five. after', here + 'doc-text-after')
+  t.equal(doc.has('#SlashedTerm'), false, here + 'has no slash-tag')
+  t.end()
+})

types/view/three.d.ts

@@ -49,6 +49,8 @@ interface Three extends View {
   possessives: (n?: number) => Possessives
   /** return any terms inside 'quotation marks' */
   quotations: (n?: number) => Quotations
+  /** return any slashed terms like 'love/hate' */
+  slashes: (n?: number) => Slashes
   /** return words like "clean" */
   adjectives: (n?: number) => Adjectives
   /** return words like "quickly" */
@@ -243,6 +245,10 @@ export interface Quotations extends View {
   /** remove leading and trailing quotation marks */
   strip: () => View
 }
+export interface Slashes extends View {
+  /** turn 'love/hate' into 'love hate' */
+  split: () => View
+}
 
 export interface Adjectives extends View {
   /** get the words describing this adjective */