librime-lua-script/lua/tools/english_dict.lua at main · shewer/librime-lua-script · GitHub

Repository navigation

History

100

101

102

103

104

105

106

107

108

109

110

111

112

113

114

115

116

117

118

119

120

121

122

123

124

125

126

127

128

129

130

131

132

133

134

135

136

137

138

139

140

141

142

143

144

145

146

147

148

149

150

151

152

153

154

155

156

157

158

159

160

161

162

163

164

165

166

167

168

169

170

171

172

173

174

175

176

177

178

179

180

181

182

183

184

185

186

187

188

189

190

191

192

193

194

195

196

197

198

199

200

201

202

203

204

205

206

207

208

209

210

211

212

213

214

215

216

217

218

219

220

221

222

223

224

225

226

227

228

229

230

231

232

233

234

235

236

237

238

239

240

241

242

243

244

245

246

247

248

249

250

251

252

253

254

255

256

257

258

259

260

261

262

263

264

265

266

267

268

269

270

271

272

273

274

275

276

277

278

279

280

281

282

283

284

285

286

287

288

289

290

291

292

293

294

295

296

297

298

299

300

301

302

303

304

305

306

307

308

309

310

311

312

313

314

315

316

317

318

319

320

321

322

323

324

325

326

327

328

329

330

331

332

333

334

335

336

337

338

339

340

341

342

343

344

345

346

347

348

349

350

351

352

353

354

355

356

357

358

359

360

361

362

363

364

365

366

367

368

369

370

371

372

373

374

375

376

377

378

379

380

381

382

383

384

385

386

387

388

389

390

391

392

393

394

395

396

397

398

399

400

401

402

403

404

405

406

407

408

409

410

411

412

413

414

415

416

417

418

419

420

421

422

423

424

425

426

427

428

429

430

431

432

433

434

435

436

437

438

439

440

441

442

443

444

445

446

447

448

449

450

451

452

453

454

455

456

#! /usr/bin/env lua

-- english_dict.lua

-- Distributed under terms of the MIT license.

--[[

ex :

Eng=require('tools/english_dict' )

e = Eng( 'english')

for w in e:iter('th/i:ad') do -- * ? / :

print(w.word,w:get_info(1) )

end

list = e:match('th/i:ad') --List table

for i,v in ipairs(list)

print(w.word,w:get_info(1)

end

pw=function(w) print(w.word,w:get_info()) end

list:each(pw)

--]]

require 'tools/string'

require 'tools/_file'

local List = List or require 'tools/list'

--USERDIR= ( USERDIR or os.getenv("APPDATA") or "" ) .. [[\Rime]]

-- 字典字根查碼 table

--local eng_suffixe1={ ["Control+f"] ="*ful" , ["Control+y"]= "*ly" , ["Control+n"]= "*tion" , ["Control+a"] = "*able" ,

--["Control+i"] = "*ing" , ["Control+m"]= "*ment" , ["Control+r"]= "*er", }

--env.keyname2={ f ="*ful" , y= "*ly" , n= "*tion" , a = "*able" ,

--i = "ing" , m= "*ment" , r= "*er",

--}

-- f="ful" --> /f or Control+f

--require 'tools/object'

-- 設定存入bin格式

--local chunk_bin= true

local NR = package.config:sub(1,1):match("/") and "\n" or "\r"

local eng_suffix={ f ="ful" , y= "ly" , t= "tion" ,s="sion", a = "able" ,

i = "ing" , m= "ment" , r= "er", g="ght" , n="ness", l="less" , }

local eng_suffix_list={ }

-- 詞類

local eng_parts={ "a", "abbr", "ad", "art", "aux", "phr", "pl", "pp", "prep", "pron", "conj", "int", "v", "vi", "vt" }

setmetatable(eng_parts,{__index=table } )

-- 可接收輸入字串 %a[%a%-%.%:_[]%?%*]* 萬用字 ? 0-1 *0-N 萬用字符合字元[%a%-%.:_] [] 限制字元範圍

-- / 快捷字串 : 詞類

-- 字頭[/快捷1[/快捷2][:詞類]

-- 分割詞類字頭[/快捷1[/快捷2] [:詞類] --> 字頭[/快捷1[/快捷2] 詞類

-- 分割快捷碼字頭 [/快捷1 [/快捷2] --> 字頭快捷快捷

-- 截取字頭字串 %a[%a%-%.%:_]*

-- 如果字字串 1 字元查全表

-- 如果字頭字串大於2 查表至不符合時中斷查詢因爲字典是按照字元排序

-- 如果input 長度 1 送出全表不用查

-- 詞類快捷字串查表轉換 *ing *tion ... 查不到的字串加上 * v* a* adv ad* ...

-- input: string [%a][%a/: %*%.%?_%-]

-- ?* -> "([%?%*])","([%a%.%-_]%%%1" --? * [$a%.%-_]? [%a%.%-]*

-- 1 gen per_suffix input input:match("^%a[%a%-%.-]+") %a[%a-._]+

-- 2 pre_suffix input conver rex with escap gsub("([%.%-_])","%%%1")

-- 3 pattern , wild_word

-- 1 split(":") 英文單字：詞類

-- 2 split("/") 字根萬用字快捷碼分割

-- "ab*/i/n" ab* i n

-- "i" -> *ing n -> tion not match: g -> *g

-- 取得字頭英文字串 a-z A-Z . - _

local function pre_suffix_word(wild_word)

return wild_word:match("^[-.%a][%a%.%-_]*"),wild_word

end

-- 轉換 reg pattern 隔離字元 - . %- %. 萬用字元 ? * .? .*

local function conver_rex(str)

return str:gsub("([%-%.])","%%%1"):gsub("([?*])",".%1")

end

-- 切割字串轉換字串再組合 return 字頭全字詞類

local function split_str(str)

str= type(str)== "string" and str or ""

local w,p=table.unpack(str:split(":"))

local pw= w:match("^[-.%a][%a%.%-_ ]*")

local ws= List( w:split("/") )

local ww= ws:shift()

ww= ww .. ws:map(function(elm)

return "*" .. (eng_suffix[elm] or elm)

end):concat()

return pw , ww , p or ""

end

-- 轉換 reg 字串字頭全字詞類

local function conv_pattern(org_text)

local pw,ww,p = split_str(org_text)

pw= "^" .. conver_rex(pw:lower() or "")

ww="^" .. conver_rex(ww:lower())

p= p:len() >0

--and "%s" .. conver_rex(p:lower() ) .. "[%l%-%.]*%."

and conver_rex(p:lower() ) .. "[%l%-%.]*%."

or "" -- [ ] p [%a]*%."

return pw, ww, p

end

local function conv_pattern1(org_text,level)

level = level or 3

local pw,ww,p = split_str(org_text)

pw=pw:lower():sub(1,level)

ww=ww:lower()

p=p:lower()

pw= "^" .. conver_rex(pw)

ww="^" .. conver_rex(ww)

p= p:len() >0 and "%s" .. conver_rex(p) .. "[%a-%.]*%." or "" -- [ ] p [%a]*%."

return pw, ww, p

end

--local Word= require 'tools/english_word'

local function New(self,...)

local obj= setmetatable({} , self)

return not obj._initialize and obj or obj:_initialize(...)

end

--- Word

local class= require 'tools/class'

-- Word

-- class method Phrase_chunk(row_chunk) Parse_text(row_tab)

-- instance method get_info(mode_num) to_s() prefix_match(prefix_str) match:(text)

--local Word=Class("Word")

--Word.__name= "Word"

--[[

function Word:__eq(obj)

return self.word == obj

end

--]]

local Word = class()--{}

Word.__name="Word"

function Word:_initialize(tab)

if type(tab)=="table" and tab.word and tab.word:len() >0 then

--and tab.translation and tab.phonetic then

for k,v in next, tab do

self[k] = v

end

self.phonetic = self.phonetic or ""

return self

end

-- <word>\t<translation>

function Word.Parse_text(line)

local tab={}

local word, translation= table.unpack(line:split("\t"))

if word:len() < 1 then return end

tab.word=word

translation= translation or ""

local head,tail=translation:find('^%[.*%];')

if head and tail then

tab.phonetic=translation:sub(head,tail-1)

tab.translation=translation:sub(tail+1)

else

tab.phonetic=""

tab.translation=translation

end

return Word(tab)

end

function Word.Parse_chunk(str,replace)

if type(str) == "string" then

str = replace and str:gsub("\\n","\\n"):gsub("\\r","\r") or str

local tab=load("return " .. str )()

return Word(tab)

end

function Word:to_s()

local l = List()

for k,v in next,self do

l:push( string.format(" %s=%q",k,v) )

end

return "{ " .. l:concat(',') .. "}"

end

-- 利用此func 設定comment 輸出格式

function Word:get_info(mode)

mode= tonumber(mode)

local info= self

if not info then return "" end

mode= mode and mode % 7 or 0

if mode == 1 then

return (info.phonetic .. " " .. info.translation):gsub("\\n",NR)

elseif mode == 2 then

return info.translation:gsub("\\n", " ")

elseif mode == 3 then

return info.translation:gsub("\\n", NR)

elseif mode == 4 then

return info.phonetic

elseif mode == 5 then

return info.word

elseif mode== 6 then

return ""

else

return (info.phonetic .. " " .. info.translation):gsub("\\n"," ")

end

function Word:prefix_match(prefix, case_match )

if case_match then

return self.word:find( prefix) == 1

else

return self.word:lower():find( prefix:lower()) == 1

end

return false

end

function Word:chk_parts(parts)

return (self.translation:match(parts) and true) or false

end

function Word:match(text,case_match)

local pw,ww,pn = conv_pattern(text)

--Log(DEBUG,'word match :', pw,ww,pn,self.word, self.word:match(ww) and true or false ,self:prefix_match(pw))

local w_match = case_match and self.word:match(ww) or self.word:lower():match(ww)

local p_match = #pn<1 and true or self.translation:match(pn)

return w_match and p_match and true or false

end

Word.is_match= Word.match

--local class = require 'tools/class'

--return class(Word)

--local MT={}

--MT.__index=MT

--MT.__call=New

-- Dict instance method

-- iter(text) return iter function for match text pattern

-- get(word) return

-- LuaDict

local function init_tree(tree_tab, index, word,level)

local prefix=word:sub(1,level):lower()

for i= #prefix, 1,-1 do

local w = prefix:sub(1,i)

if tree_tab[w] then break end

tree_tab[w] = index

init_tree(tree_tab, index, word, level -1)

end

local LuaDict=class() --setmetatable({},MT)

--LuaDict.__index = LuaDict

LuaDict.__name = 'LuaDict'

LuaDict._db={}

function LuaDict:_initialize(full_path,level)

level = level and level>1 and level or 3

if T03 and GD then GD() end

if not isFile(full_path) then return end

--self._db = loadfile(full_path)()

self._db = dofile(full_path)

self._tree = {}

self._words = {}

for i,v in next,self._db do

local w = Word(v)

self._db[i] = w

self._words[v.word] = i

init_tree(self._tree,i,w.word,level)

end

return self

end

function LuaDict:_prefix_index(pw)

--local pw,ww,pn = conv_pattern(text)

local index = 1

if #pw <1 then return index end

-- 找最近的index

for i= #pw,1,-1 do

local tree_index= self._tree[ pw:sub(1,i) ]

if tree_index then

index = tree_index

break

end

-- 找 prefix word index

local count = 0

repeat

local ww = self._db[index]

if self._db[index]:prefix_match(pw) then

-- 找到索引如果count > 200 增加 pw 索引

if count > 200 then

self._tree[pw] = index

end

break

end

count = count +1

index = index+1

until index > #self._db

return index

end

function LuaDict:iter(text)

local pw,ww,pn = split_str(text)

--if not index then GD() end

return coroutine.wrap(function()

local index = self:_prefix_index(pw)

while self._db[index] and self._db[index]:prefix_match(pw) do

if self._db[index]:match(text) then

coroutine.yield(self._db[index])

end

index = index +1

end

end)

end

function LuaDict:get(word)

local index = self._words[word]

return self._db[index]

end

-- Dict instance method

-- iter(text) return iter function for match text pattern

-- get(word) return

-- LevelDict

local LevelDict= LevelDb and class() --setmetatable({},MT)

if LevelDict then

--LevelDict.__index = LevelDict

LevelDict.__name = 'LewelDict'

function LevelDict:_initialize(full_path)

if rime_api.LevelDb.open(full_path) then

self._dbname=full_path

return self

end

function LevelDict:_getdict()

return rime_api.LevelDb.get_db(self._dbname)

end

function LevelDict:iter(text, case_match)

--local pw,ww,pn = conv_pattern(text)

local pw,ww,pn = split_str(text)

local dbacc = self:_getdict():query(pw:lower())

return coroutine.wrap(function()

for k,v in dbacc:iter() do

local w = Word.Parse_chunk(v)

if w and w:match(text,case_match) then

coroutine.yield(w)

end

end)

end

function LevelDict:get(word)

-- have upcae word ex Abort abort\tAbort

word = word:match("%u") and string.format("%s\t%s",word:lower(),word) or word

local chk_str = self:_getdict():fetch(word)

return chk_str and Word.Parse_chunk(chk_str)

end

-- English(dict_name)

-- instance method

-- iter(text) return Word for w in e:iter(text) do ... end

-- match(text) return Word of List

-- word(word) return Word

local English = class() -- setmetatable({},MT)

--English.__index=English

English.__name="English"

English._dicts={}

function English:_getdict()

return English._dicts[self._dict_name]

end

--[[

function English:_setdict()

English._dicts[self._dict_name] = self._dict

end

--]]

function English:_initialize(dict_name,reload)

dict_name= dict_name or "english_tw"

self._dict_name = dict_name

--local dictdb = self:_getdb()

if reload or not self:_getdict() then

self:reload()

end

return self:_getdict() and self or nil

end

function English:reload(force)

local dict_name = self._dict_name

local full_path = get_full_path(dict_name)

-- 1 try LevelDict

if LevelDict and full_path and isDir(full_path) then

self._dicts[self._dict_name] = LevelDict(full_path)

return self._dicts[self._dict_name] and true or false

end

-- 2 try LuaDict

full_path= get_full_path(dict_name .. ".txtl")

if LuaDict and full_path and isFile(full_path) then

self._dicts[self._dict_name] = LuaDict(full_path)

return self._dicts[self._dict_name] and true or false

end

Log(ERROR, "English_dict " .. dict_name .. ' not find ')

end

function English:iter(org_text,case_match)

return self:_getdict():iter(org_text,case_match)

end

function English:match(org_text)

local tab=List()

for w in self:iter(org_text) do

tab:push(w)

end

return tab

end

function English:word(word)

return self:_getdict():get(word)

end

-- for debug and check

--[[ debug function

English.Split=split_str --1 ('seteu/i/a:m') 字首seteu 單字 seteu*ing*able 詞類 m

English.Conver_rex=conver_rex --2 ('seteu*?ing:m') 展開/ : seteu.*.?ing:ment 2

English.Conver_pattern= conv_pattern --3 ('seteu/i/a:m') 字首 ^seteu ^seteu.*ing.*able%sm[%a%-%.]*%.

English.Word=Word

--]]

English.LevelDict = LevelDict

English.LuaDict = LuaDict

return English

librime-lua-script/lua/tools/english_dict.lua at main · shewer/librime-lua-script · GitHub

Repository navigation

Expand file tree

Breadcrumbs

english_dict.lua

Latest commit

History

Breadcrumbs

english_dict.lua

File metadata and controls