Merge pull request #981 from spencermountain/dev

Dev
spencermountain · Nov 11, 2022 · 4b0a75a · 4b0a75a
2 parents dfaec76 + f15e8ad
commit 4b0a75a
Show file tree

Hide file tree

Showing 76 changed files with 949 additions and 192 deletions.
diff --git a/README.md b/README.md
@@ -853,6 +853,11 @@ nlp.extend({
 - **[Tasking Slack-bot](https://github.com/kevinsuh/toki)** - by Kevin Suh
   [[see more]](https://observablehq.com/@spencermountain/compromise-projects)
 
+##### Comparisons
+- [Compromise and Spacy](https://observablehq.com/@spencermountain/compromise-and-spacy)
+- [Compromise and NLTK](https://observablehq.com/@spencermountain/compromise-and-NLTK)
+
+
 <!-- spacer -->
 <div align="center">
   <img height="25px" src="https://user-images.githubusercontent.com/399657/68221862-17ceb980-ffb8-11e9-87d4-7b30b6488f16.png"/>

diff --git a/builds/compromise.js b/builds/compromise.js
diff --git a/builds/one/compromise-one.cjs b/builds/one/compromise-one.cjs
diff --git a/builds/one/compromise-one.mjs b/builds/one/compromise-one.mjs
diff --git a/builds/three/compromise-three.cjs b/builds/three/compromise-three.cjs
diff --git a/builds/three/compromise-three.mjs b/builds/three/compromise-three.mjs
diff --git a/builds/two/compromise-two.cjs b/builds/two/compromise-two.cjs
diff --git a/builds/two/compromise-two.mjs b/builds/two/compromise-two.mjs
diff --git a/changelog.md b/changelog.md
@@ -9,17 +9,26 @@ While all _Major_ releases should be reviewed, our only _large_ releases are **v
 <!-- #### [planned breaking]
 - fix doc.json(0) inconsistency
 - fix text() options
+- deprecate #Participle for #PastParticiple
+- run chunker only when necessary
+- cleanup verb+noun metadata in json()
 -->
 
-<!-- #### 14.7.1 [Unreleased]
+<!-- #### 14.7.2 [Unreleased]
 -->
 
+#### 14.7.1 
+- **[fix]** - concat fix
+- **[change]** - tagging fixes
+- **[change]** - `{word/tag/sense}` sense-match syntax
+
 #### 14.7.0 
 - **[new]** - match term id
 - **[change]** - tag text by default on .concat('')
 - **[change]** - allow modifying term prePunctuation
 - **[new]** - .wrap() method
 - **[new]** - .isFull() method
+- **[new]** - support full `notIf` matches on sweep
 - **[fix]** - text params for #953
 - **[fix]** - nouns().isSingular() missing
 - **[change]** - one-character w/ dash tokenization #977

diff --git a/data/lexicon/adjectives/adjectives.js b/data/lexicon/adjectives/adjectives.js
@@ -79,7 +79,6 @@ export default [
   'blind',
   'beyond',
   'good',
-  'understood',
   'substandard',
   'on board',
   'aboard',
@@ -576,6 +575,11 @@ export default [
   'unruly',
   'many',
   'sparkly',
+  'approximately',
+  'fortunately',
+  'unfortunately',
+  'lately',
+  'ultimately',
 
   // -ry
   'legendary',
@@ -596,6 +600,7 @@ export default [
   'auditory',
   'statutory',
   'sorry',
+  'hairy',
   'uppity',
   'guilty',
   'woozy',
@@ -629,6 +634,7 @@ export default [
 
   // -ide
   'bona fide',
+  'bonafide',
   // -ate
   'affectionate',
   'alternate',
@@ -643,6 +649,21 @@ export default [
   'beside',
   'alright',
   'top notch',
-  'self sufficient'
+  'self sufficient',
+  'middle aged',
+  'no more',
+  'ashen',
+  'scarlet',
+  'alone',
+  'homesick',
+  'longtime',
+  'bigtime',
+  'inside',
+  'outside',
+  'artsy',
+  'antsy',
+  'golden',
+  'bare',
+  'subpar',
 ]
 
diff --git a/data/lexicon/adjectives/comparables.js b/data/lexicon/adjectives/comparables.js
@@ -310,4 +310,5 @@ export default [
   'weak',
   'white',
   'wide',
+  'stately',
 ]
diff --git a/data/lexicon/misc.js b/data/lexicon/misc.js
@@ -65,4 +65,5 @@ export default {
   'hurry up': 'Imperative',
   'make sure': 'Imperative',
   // 'stand back': 'Imperative'
+  // 'subpar': 'Adjective'
 }
diff --git a/data/lexicon/misc/adverbs.js b/data/lexicon/misc/adverbs.js
@@ -8,7 +8,6 @@ export default [
   'all but',
   'all that',
   'almost',
-  'alone',
   'already',
   'also',
   'always',
@@ -79,7 +78,7 @@ export default [
   'thus',
   'too',
   'totally',
-  'toward',
+  // 'toward',
   'twice',
   'up to',
   'upwards of',

diff --git a/data/lexicon/misc/prepositions.js b/data/lexicon/misc/prepositions.js
@@ -48,6 +48,7 @@ export default [
   'throughout',
   'thru',
   'till',
+  'toward',
   'towards',
   'unlike',
   'until',

diff --git a/data/lexicon/nouns/properNouns.js b/data/lexicon/nouns/properNouns.js
@@ -11,9 +11,11 @@ export default [
   'mickey',
   'finn',
   'missy',
+  'florence',
 
   // currencies
   'nis',
   'riel',
   'euro',
+  'iron maiden',
 ]
diff --git a/data/lexicon/nouns/singulars.js b/data/lexicon/nouns/singulars.js
@@ -275,6 +275,7 @@ export default [
   'aspect',
   'prospect',
   'insect',
+  'intellect',
   'verdict',
   'district',
   'free market',
@@ -404,6 +405,13 @@ export default [
   'flower',
   'sandwich',
   'x ray',
+  'pig',
+  'loser',
+  'time out',
+  'time off',
+  'darling',
+  'dump truck',
+  'sweetheart',
 ]
 
 
diff --git a/data/lexicon/nouns/uncountables.js b/data/lexicon/nouns/uncountables.js
@@ -243,4 +243,8 @@ export default [
   'hunger',
   'sushi',
   'seating',
+  'existence',
+  'make up',
+  'you guys',
+  'improv'
 ]
diff --git a/data/lexicon/people/femaleNames.js b/data/lexicon/people/femaleNames.js
@@ -589,7 +589,6 @@ export default [
   'fien',
   'fiona',
   'flora',
-  'florence',
   'florencia',
   'fozia',
   'fran',
@@ -1500,7 +1499,7 @@ export default [
   'sasha',
   'savanna',
   'savannah',
-  'scarlet',
+  // 'scarlet',
   'scarlett',
   'selena',
   'selene',

diff --git a/data/lexicon/switches/adj-gerund.js b/data/lexicon/switches/adj-gerund.js
@@ -224,6 +224,7 @@ export default [
   // prefixes
   'resting',
   'redefining',
+  'overpowering'
 
 ]
 
diff --git a/data/lexicon/switches/adj-past.js b/data/lexicon/switches/adj-past.js
@@ -223,7 +223,15 @@ export default [
   'wet',
   'worried',
   // prefixes
-  'overlooked'
+  'overlooked',
+  'muted',
+  'burnt',
+  'understood',
+  'inflated',
+  'exaggerated',
+  'delighted',
+  'elated',
+  'confused',
 ]
 
 

diff --git a/data/lexicon/switches/noun-verb.js b/data/lexicon/switches/noun-verb.js
@@ -444,6 +444,7 @@ export default [
   'range',
   'rank',
   'rat',
+  'read',
   'reason',
   'recall',
   'record',
@@ -791,4 +792,21 @@ export default [
   'ask',
   'drone',
   'tangle',
+  'ditch',
+  'guess',
+  'temper',
+  'commit',
+  'lick',
+  'capture',
+  'ground',
+  'hug',
+  'rape',
+  'panic',
+  'rage',
+  'parent',
+  'shot',
+  'dock',
+  'manner',
+  'bitch',
+  'war',
 ]
diff --git a/data/lexicon/verbs/infinitives.js b/data/lexicon/verbs/infinitives.js
@@ -703,11 +703,19 @@ export default [
 
   // present participles
   'awaken',
+  'freshen',
   'frighten',
   'hasten',
   'heighten',
   'lengthen',
   'lessen',
-  'worsen',
+  'strengthen',
   'sweeten',
+  'worsen',
+
+  'explain',
+  'occur',
+  'concur',
+  'maintain',
+  'undercut',
 ]
diff --git a/data/lexicon/verbs/participles.js b/data/lexicon/verbs/participles.js
@@ -4,11 +4,7 @@ export default [
   'seen',
   'flown',
   'shown',
-  'frighten',
   'given',
-  'hasten',
-  'heighten',
-  'lessen',
-  'worsen',
   'written',
+
 ]
diff --git a/data/lexicon/verbs/phrasals.js b/data/lexicon/verbs/phrasals.js
@@ -86,6 +86,7 @@ export default [
   'bring in',
   'bring out',
   'bring up',
+  'bring under',
   'brush off',
   'brush up',
   'bubble over',
@@ -117,6 +118,7 @@ export default [
   'call off',
   'call on',
   'call up',
+  'call out',
   'calm down',
   'cancel out',
   'carry away',
@@ -142,6 +144,10 @@ export default [
   'chip in',
   'clean down',
   'clean up',
+  'close up',
+  'close off',
+  'close out',
+  'close in',
   'come apart',
   'come around',
   'come away',
@@ -207,6 +213,7 @@ export default [
   'fall out',
   'fall over',
   'fall through',
+  'fall victim',
   'farm out',
   'fatten up',
   'feed off',
@@ -286,6 +293,7 @@ export default [
   'get up',
   'give away',
   'give back',
+  'give birth',
   'give down',
   'give in',
   'give off',
@@ -419,6 +427,7 @@ export default [
   'listen up',
   'live off',
   'live up',
+  'live out',
   'load down',
   'load up',
   'lock down',
@@ -444,6 +453,7 @@ export default [
   'make off',
   'make out',
   'make up',
+  'make sure',
   'man down',
   'man up',
   'mark down',
@@ -513,6 +523,7 @@ export default [
   'pipe down',
   'pipe up',
   'play around',
+  'place under',
   'plug in',
   'plump down',
   'plump up',
@@ -693,6 +704,7 @@ export default [
   'stand up',
   'start out',
   'start up',
+  'start off',
   'stave off',
   'stay up',
   'step up',