Merge pull request #952 from spencermountain/dev

Dev

README.md

@@ -629,7 +629,7 @@ _(these methods are on the main `nlp` object)_
   - **[.verbs().toFutureTense()](https://observablehq.com/@spencermountain/verbs)** - `'walked' → 'will walk'`
   - **[.verbs().toInfinitive()](https://observablehq.com/@spencermountain/verbs)** - `'walks' → 'walk'`
   - **[.verbs().toGerund()](https://observablehq.com/@spencermountain/verbs)** - `'walks' → 'walking'`
-  - **[.verbs().conjugate()](https://observablehq.com/@spencermountain/verbs)** - return all forms of these verbs
+  - **[.verbs().conjugate()](https://observablehq.com/@spencermountain/verbs)** - return all conjugations of these verbs
   - **[.verbs().isNegative()](https://observablehq.com/@spencermountain/verbs)** - return verbs with 'not', 'never' or 'no'
   - **[.verbs().isPositive()](https://observablehq.com/@spencermountain/verbs)** - only verbs without 'not', 'never' or 'no'
   - **[.verbs().toNegative()](https://observablehq.com/@spencermountain/verbs)** - `'went' → 'did not go'`
@@ -689,6 +689,7 @@ _(these methods are on the main `nlp` object)_
 ##### Adjectives
 - **[.adjectives()](https://observablehq.com/@spencermountain/compromise-selections)** - things like `'quick'`
 - **[.adjectives().json()](https://observablehq.com/@spencermountain/compromise-selections)** - get adjective metadata
+- **[.adjectives().conjugate()](https://observablehq.com/@spencermountain/compromise-selections)** - return all inflections of these adjectives
 - **[.adjectives().adverbs()](https://observablehq.com/@spencermountain/compromise-selections)** - get adverbs describing this adjective
 - **[.adjectives().toComparative()](https://observablehq.com/@spencermountain/compromise-selections)** - 'quick' -> 'quicker'
 - **[.adjectives().toSuperlative()](https://observablehq.com/@spencermountain/compromise-selections)** - 'quick' -> 'quickest'

changelog.md

@@ -8,6 +8,14 @@ While all _Major_ releases should be reviewed, our only _large_ releases are **v
 
 <!-- #### 14.5.0 [Unreleased]
 -->
+
+#### 14.5.0 [August 2022]
+- **[fix]** - possible runtime error in setTag method
+- **[change]** - make #Honorific always a #Person #951
+- **[new]** - manually change conjugations/inflections from plugin #949
+- **[new]** - `.adjectives().conjugate()` method
+- **[update]** - dependencies
+
 #### 14.4.5 [August 2022]
 - **[fix]** - fix logic for greedy-negative matches - #936 
 - **[fix]** - fix tagging for 3-digit year iso dates - #868

data/README.md

@@ -0,0 +1,20 @@
+hello!
+
+here is the data compressed and compiled into the word models that compromise uses to understand text.
+
+there are some things to note:
+
+1. run `npm run pack` after making a change, to see changes appear.
+
+2. lexicon words are lowercased and compressed with [efrt](https://github.com/spencermountain/efrt), some characters are reserved -`[0-9,;!:|¦]`
+
+3. be careful adding ambiguous words - 'ray' should not be a #Person - it's a better fit for `./switches/person-date.js`
+
+4. many word-lists have conjugations automatically applied to them - #Singular words are pluralized, etc.
+
+
+the lexicon output data can be found in `./src/2-two/preTagger/model/lexicon/_data.js`
+
+and the word-conjugation data can be found in `./src/2-two/preTagger/model/models/_data.js`
+
+for more information, see the [compromise-lexicon docs](https://observablehq.com/@spencermountain/compromise-lexicon).

data/lexicon/adjectives/adjectives.js

@@ -620,7 +620,6 @@ export default [
   'contradictory',
   'satisfactory',
 
-  'premier',
   'skilled',
   'antique',
   'dependent',

data/lexicon/index.js

@@ -16,7 +16,6 @@ import cities from './places/cities.js'
 import countries from './places/countries.js'
 import femaleNames from './people/femaleNames.js'
 import firstnames from './people/firstnames.js'
-import honorifics from './people/honorifics.js'
 import lastnames from './people/lastnames.js'
 import maleNames from './people/maleNames.js'
 import people from './people/people.js'
@@ -61,6 +60,8 @@ import personDate from './switches/person-date.js'
 import personVerb from './switches/person-verb.js'
 import personPlace from './switches/person-place.js'
 import unitNoun from './switches/unit-noun.js'
+import honorificNoun from './switches/honorific-noun.js'
+
 
 //add-in the generic, flat word-lists
 const data = [
@@ -93,7 +94,6 @@ const data = [
 
   [femaleNames, 'FemaleName'],
   [firstnames, 'FirstName'],
-  [honorifics, 'Honorific'],
   [lastnames, 'LastName'],
   [maleNames, 'MaleName'],
   [people, 'Person'],
@@ -125,6 +125,7 @@ const data = [
   [personDate, 'Person|Date'],
   [personVerb, 'Person|Verb'],
   [unitNoun, 'Unit|Noun'],
+  [honorificNoun, 'Honorific|Noun'],
 ]
 for (let i = 0; i < data.length; i++) {
   const list = data[i][0]

data/lexicon/nouns/singulars.js

@@ -402,6 +402,7 @@ export default [
   'stone',
   'man',
   'tributary',
+  'flower',
 ]
 
 

data/lexicon/switches/adj-noun.js

@@ -69,7 +69,7 @@ export default [
   'periodical',
   'pet',
   'potential',
-  // 'premier',
+  'premier',
   'present',
   'principal',
   'rear',

data/lexicon/people/honorifics.js → data/lexicon/switches/honorific-noun.js

@@ -2,28 +2,34 @@
 export default [
   'admiral',
   'ayatullah',
+  'baron',
+  'baroness',
   'brigadier',
-  'captain',
   'chancellor',
   'colonel',
   'commander',
   'congressman',
   'congresswoman',
   'constable',
+  'corporal',
   'councillor',
-  'count',
   'doctor',
   'dutchess',
   'excellency',
   'field marshal',
-  'first lady',
-  'first lieutenant',
-  // 'judge',
-  'king',
   'lieutenant',
+  // 'count',
+  'captain',
+  'judge',
+  'king',
+  'lady',
+  'lord',
   'magistrate',
   'marshal',
   'mayor',
+  // 'miss',
+  'missus',
+  'mister',
   'officer',
   'pastor',
   'president',
@@ -35,9 +41,9 @@ export default [
   'rabbi',
   'rear admiral',
   'reverend',
-  'second lieutenant',
   'sergeant',
+  'secretary',
   'sultan',
   'taoiseach',
-  'vice admiral',
-]
+  'vice admiral'
+]

data/lexicon/switches/noun-verb.js

@@ -228,7 +228,6 @@ export default [
   'float',
   'flood',
   'flow',
-  'flower',
   'fly',
   'focus',
   'fog',
@@ -353,6 +352,7 @@ export default [
   'milk',
   'mind',
   'mine',
+  'miss',
   'mirror',
   'mix',
   'model',

data/lexicon/verbs/infinitives.js

@@ -403,7 +403,6 @@ export default [
   'mingle',
   'minus',
   'misplace',
-  'miss',
   'molest',
   'mourn',
   'multiply',

data/pairs/PastTense.js

@@ -1928,7 +1928,7 @@ export default [
   ['bit', 'bite'],
   ['bled', 'bleed'],
   ['blitzed', 'blitz'],
-  ['blown', 'blow'],
+  // ['blown', 'blow'],
   ['boned', 'bone'],
   ['burst', 'burst'],
   ['caned', 'cane'],
@@ -2038,10 +2038,11 @@ export default [
   ['levelled', 'level'],
   ['dared', 'dare'],
   ['swam', 'swim'],
-  ['collide', 'collided'],
-  ['slam', 'slammed'],
-  ['shun', 'shunned'],
-  ['prod', 'prodded'],
-  ['outgrow', 'outgrew'],
-  ['fulfil', 'fulfilled'],
+  ['collided', 'collide'],
+  ['slammed', 'slam'],
+  ['shunned', 'shun'],
+  ['prodded', 'prod'],
+  ['outgrew', 'outgrow'],
+  ['fulfilled', 'fulfil'],
+  ['blew', 'blow'],
 ]