add words

samhess · Nov 5, 2024 · 22ae38d · 22ae38d
1 parent 5dfeb53
commit 22ae38d
Show file tree

Hide file tree

Showing 5 changed files with 126 additions and 39 deletions.
diff --git a/scripts/checkVocabulary.js b/scripts/checkVocabulary.js
@@ -0,0 +1,43 @@
+import db from '../src/lib/server/database.js'
+import {readFile, writeFile} from 'fs/promises'
+
+const contents = await readFile('./data/vocabulary.json.json')
+const words = JSON.parse(contents)
+
+for (const word of words) {
+  if (word.term.includes('(') || word.term.includes('/')) {
+    //console.log(word)
+  }
+  else {
+    const {term,type,language='eng'} = word
+    const partOfSpeech = type.split(', ')[0]
+      .replace(/([am])v/,'v')
+      .replace(/n pl/,'n')
+      .replace(/exclam/,'interj')
+      .replace(/^phr$/,'prep phr')
+      .replace(/phr v/,'phr-v')
+      .replace(/prep phr/,'prep-phr')
+    const w = await db.word.findUnique({where:{term_partOfSpeech_language:{term,partOfSpeech,language}}})
+    if (w) {
+      await db.word.update({
+        where: {term_partOfSpeech_language:{term,partOfSpeech,language}},
+        data: {
+          term,
+          language,
+          partOfSpeech
+        }
+      })
+      if (language!=='eng') {
+        console.log(`${partOfSpeech} ${word.term} ${language}`)
+      }
+    } else {
+      await db.word.create({
+        data: {
+          term,
+          language,
+          partOfSpeech
+        }
+      })
+    }
+  }
+}
diff --git a/scripts/data/vocabulary.json b/scripts/data/vocabulary.json
@@ -1073,7 +1073,8 @@
   "forever (adv)",
   "forget (v)",
   "forgive (v)",
-  "fork (n) form (n)",
+  "fork (n)",
+  "form (n)",
   "former (adj)",
   "fortnight (n)",
   "fortunately (adv)",
@@ -1146,7 +1147,8 @@
   "giant (adj)",
   "gift (n)",
   "giraffe (n)",
-  "girl (n) girlfriend (n)",
+  "girl (n)",
+  "girlfriend (n)",
   "give (v)",
   "give back (phr v) • Give me back this book on Tuesday, please.",
   "give in (phr v) • Have you given in your homework yet? • Do you give in? Shall I tell you the answer now?",
@@ -2254,7 +2256,8 @@
   "river (n)",
   "road (n)",
   "roast (adj & v)",
-  "rob (v) robot (n)",
+  "rob (v)",
+  "robot (n)",
   "rock (n) • rock (music) (n) • a hard piece of rock (n)",
   "rocket (n) • They sent a rocket into space.",
   "role (n)",

diff --git a/scripts/data/vocabulary.json.json b/scripts/data/vocabulary.json.json
@@ -4205,15 +4205,13 @@
     "type": "adv"
   },
   {
-    "term": "fall (n & v) • in the fall",
+    "term": "fall",
     "examples": [
       "in the fall (n) (Am Eng) (Br Eng: autumn )",
       "a fall in the price (n)",
       "He fell and hurt his leg. (v)"
     ],
-    "language": "ena",
-    "dialect": " (Am Eng) (Br Eng: autumn ) • a fall in the price (n) • He fell and hurt his leg. (v)",
-    "type": "n"
+    "type": "n, v"
   },
   {
     "term": "false",
@@ -4411,7 +4409,8 @@
     "type": "n"
   },
   {
-    "term": "film star"
+    "term": "film star",
+    "type": "n"
   },
   {
     "term": "final",
@@ -4654,7 +4653,11 @@
     "type": "v"
   },
   {
-    "term": "fork (n) form",
+    "term": "fork",
+    "type": "n"
+  },
+  {
+    "term": "form",
     "type": "n"
   },
   {
@@ -4996,7 +4999,11 @@
     "type": "n"
   },
   {
-    "term": "girl (n) girlfriend",
+    "term": "girl",
+    "type": "n"
+  },
+  {
+    "term": "girlfriend",
     "type": "n"
   },
   {
@@ -5912,10 +5919,6 @@
     "term": "hut",
     "type": "n"
   },
-  {
-    "term": "",
-    "type": "pron"
-  },
   {
     "term": "ice",
     "type": "n"
@@ -7014,7 +7017,11 @@
     "type": "v"
   },
   {
-    "term": "look out (phr v) Look out!"
+    "term": "look out",
+    "type": "phr v",
+    "examples": [
+      "Look out!"
+    ]
   },
   {
     "term": "look up",
@@ -10091,7 +10098,11 @@
     "type": "adj, v"
   },
   {
-    "term": "rob (v) robot",
+    "term": "rob",
+    "type": "v"
+  },
+  {
+    "term": "robot",
     "type": "n"
   },
   {
@@ -11060,12 +11071,12 @@
     "type": "adj"
   },
   {
-    "term": "smart (adj) • a smart idea",
+    "term": "smart",
     "examples": [
       "a smart idea (Am Eng)",
       "smart clothes"
     ],
-    "language": "ena"
+    "type": "adj"
   },
   {
     "term": "smartphone",
@@ -12331,11 +12342,8 @@
     "type": "n"
   },
   {
-    "term": "through"
-  },
-  {
-    "term": "",
-    "type": "prep"
+    "term": "through",
+    "type": "adj, adv, prep"
   },
   {
     "term": "throw",
@@ -12722,15 +12730,16 @@
   {
     "term": "truck",
     "language": "ena",
-    "dialect": " (Am Eng) (Br Eng: lorry )"
+    "dialect": " (Am Eng) (Br Eng: lorry )",
+    "type": "n"
   },
   {
     "term": "trunk",
     "examples": [
       "the trunk of a car"
     ],
     "language": "ena",
-    "dialect": " (Am Eng) (Br Eng: boot ) • the trunk of a car",
+    "dialect": " (Am Eng) (Br Eng: boot )",
     "type": "n"
   },
   {
@@ -13925,7 +13934,8 @@
     "type": "n"
   },
   {
-    "term": "zebra"
+    "term": "zebra",
+    "type": "n"
   },
   {
     "term": "zero",

diff --git a/scripts/parseCambridge.js b/scripts/parseCambridge.js
@@ -121,7 +121,20 @@ async function getVocabulary() {
       terms[index-1] += ' ' + term
       terms.splice(index,1)
     }
+    if (term==='fork (n) form (n)') {
+      terms[index] = 'fork (n)'
+      terms.splice(index+1,0,'form (n)')
+    }
+    if (term==='girl (n) girlfriend (n)') {
+      terms[index] = 'girl (n)'
+      terms.splice(index+1,0,'girlfriend (n)')
+    }
+    if (term==='rob (v) robot (n)') {
+      terms[index] = 'rob (v)'
+      terms.splice(index+1,0,'robot (n)')
+    }
   }
+
   return terms
 }
 

diff --git a/scripts/parseVocabulary.js b/scripts/parseVocabulary.js
@@ -4,6 +4,8 @@ import {readFile, writeFile} from 'fs/promises'
 const contents = await readFile('./data/vocabulary.json')
 const terms = JSON.parse(contents)
 
+const outFile = './data/vocabulary.json.json'
+
 const endings = [
   '(av & v)',
   '(adj)',
@@ -75,29 +77,29 @@ const endings = [
 ]
 
 const words = []
-for (const term of terms) {
+for (const [index,term] of terms.entries()) {
   const word = {term}
   const bulletPos = term.indexOf(' •')
   if (bulletPos !== -1) {
-    word.examples = term.slice(bulletPos).replace(' • ','').split(' • ')
     word.term = term.slice(0,bulletPos)
+    word.examples = term.slice(bulletPos).replace(' • ','').split(' • ')
   }
-  const enbPos = term.indexOf(' (Br Eng) (Am Eng:')
+  const enbPos = word.term.indexOf(' (Br Eng) (Am Eng:')
   if (enbPos !== -1) {
     word.language = 'enb'
-    word.dialect = term.slice(enbPos)
-    word.term = term.slice(0,enbPos)
+    word.dialect = word.term.slice(enbPos)
+    word.term = word.term.slice(0,enbPos)
   }
-  const enaPos = term.indexOf(' (Am Eng) (Br Eng:')
+  const enaPos = word.term.indexOf(' (Am Eng) (Br Eng:')
   if (enaPos !== -1) {
     word.language = 'ena'
-    word.dialect = term.slice(enaPos)
-    word.term = term.slice(0,enaPos)
+    word.dialect = word.term.slice(enaPos)
+    word.term = word.term.slice(0,enaPos)
   }
-  const enaPos2 = term.indexOf(' (Am Eng)')
+  const enaPos2 = word.term.indexOf(' (Am Eng)')
   if (enaPos2 !== -1) {
     word.language = 'ena'
-    word.term = term.slice(0,enaPos2)
+    word.term = word.term.slice(0,enaPos2)
   }
   for (const ending of endings) {
     const term = word.term
@@ -113,8 +115,24 @@ for (const term of terms) {
       word.type = ending.slice(1,-1).replace(' &', ',')
     }
   }
-  if (word.term.endsWith(')')) console.log(word.term)
-  words.push(word)
+  if (['film star', 'truck', 'zebra'].includes(word.term)) {
+    word.type = 'n'
+  }
+  if (word.term === 'through') {
+    word.type = 'adj, adv, prep'
+  }
+  if (word.term.startsWith('look out')) {
+    word.term = 'look out'
+    word.type = 'phr v'
+    word.examples = ['Look out!']
+  }
+  if (word.term.endsWith(')')) {
+    //console.log(word.term)
+  }
+  if (word.term) {
+    words.push(word)
+  }
 }
 
-await writeFile('./data/vocabulary.json.json', JSON.stringify(words,null,2))
+await writeFile(outFile, JSON.stringify(words,null,2))
+console.log(`${words.length} words written to ${outFile}`)