Merge branch 'dev'

.gitignore

@@ -1 +1,2 @@
-node_modules/
+node_modules/
+dist/

LICENSE

@@ -0,0 +1,7 @@
+Copyright 2018 Hsu Karinsu
+
+Permission is hereby granted, free of charge, to any person obtaining a copy of this software and associated documentation files (the "Software"), to deal in the Software without restriction, including without limitation the rights to use, copy, modify, merge, publish, distribute, sublicense, and/or sell copies of the Software, and to permit persons to whom the Software is furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in all copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE.

README.md

@@ -0,0 +1,38 @@
+hakka-dict-toolkit
+===
+
+[![NPM version](https://badge.fury.io/js/badge-list.svg)][npm]
+[![Open Source Love](https://badges.frapsoft.com/os/mit/mit.svg?v=102)][repo]
+
+A toolkit for [Taiwan Hakka Dictionary][site].
+
+Installation
+---
+
+```
+yarn add hakka-dict-toolkit
+```
+
+or
+
+```
+npm install hakka-dict-toolkit --save
+```
+
+Usage
+---
+
+``` js
+var hakka = require('hakka-dict-toolkit')
+
+hakka.entry(10377)
+```
+
+License
+---
+
+MIT
+
+[site]: https://hakka.dict.edu.tw/hakkadict/
+[repo]: https://github.com/m80126colin/hakka-dict-toolkit/
+[npm]: https://www.npmjs.com/package/hakka-dict-toolkit

lib/api/entry.ts

@@ -5,13 +5,14 @@ import * as extracter from '../extracter';
 import * as filter    from '../filter';
 import * as formatter from '../formatter';
 import { host } from '../util';
+import { WordEntry, CharacterEntry } from '../formatter/_type';
 /**
  * Provide access to the entry of MOE Hakka Dictionary by index and returns a promise.
  *
  * @param {number} idx index of entry
  * @returns a promise with either a word or a character
  */
-const entry = (idx : number) => {
+const entry = (idx : number) : Promise<WordEntry | CharacterEntry> => {
   const options = {
     method: 'GET',
     uri: `${host}/result_detail.jsp?n_no=${idx}&soundtype=0&sample=[`

lib/extracter/entry.ts

@@ -13,9 +13,9 @@ const extract = (context : string) : ExtractData[][] => {
   const $    = cheerio.load(context)
   const rows = $('font > table.t14 > tbody > tr', context)
   const data = _.map(rows, (row, idx) => {
-    if (idx !== 12)
+    if (idx !== 11 && idx !== 12)
       return _.flatMap($('tr > td', row), data => partial.extract(data))
-    // Extract special from of field 'multiple accents (多音字)'
+    // Extract special from for field 'another accents (又音)' and 'multiple accents (多音字)'
     return _.concat(
       partial.extract($('tr > td', row)[0]),
       _.flatMap($('tr', $(row)), data => partial.extract(data)))

lib/filter/character.ts

@@ -10,7 +10,7 @@ import { replace_list } from '../util';
  */
 const filter : Filter = (context : string) : string => _.reduce(
   replace_list,
-  (str, pair) => _.replace(str, new RegExp(pair[0], 'ug'), pair[1]),
+  (str, pair) => _.replace(str, new RegExp(`&#x${pair[0]};`, 'ug'), pair[1]),
   context)
 
 export default filter

lib/filter/image.ts

@@ -11,7 +11,7 @@ import { image_table } from '../util';
  */
 const filter : Filter = (context : string) : string => {
   const $ = cheerio.load(context)
-  $('img').each(node => {
+  _.map($('img'), node => {
     const link = $(node).attr('src')
     $(node).replaceWith(image_table[link])
   })

lib/formatter/entry.ts

@@ -19,13 +19,19 @@ const makeAnother = (data : ExtractData[][]) : Sound[] => {
     .tail()
     .flatMap(acc => partial.another([acc]))
     .value()
+  // another accents
+  const another = _.chain(data[11])
+    .tail()
+    .chunk(2)
+    .flatMap(partial.another)
+    .value()
   // multiple accents
   const multi_accents = _.chain(data[12])
     .tail()
     .chunk(2)
     .flatMap(partial.another)
     .value()
-  return _.concat([], vunpag, multi_accents)
+  return _.concat([], vunpag, another, multi_accents)
 }
 /**
  * Format synonym or antonym into an array of EntryItem.
@@ -55,7 +61,15 @@ const makeBasicEntry = (data : ExtractData[][]) : BasicEntry => {
   let basic = {
     title:   partial.item(data[0][1]).text,
     type:    (data[0][2].text.match('詞性') === null) ? 'character' : 'word',
-    sounds:  _.map(_.range(1, 1 + 6), idx => partial.sound(data[idx])),
+    sounds:  _.chain(_.range(1, 1 + 6))
+      .map(idx => {
+        const res = partial.sound(_.tail(data[idx]))
+        if (_.toPairs(res).length === 0)
+          return undefined
+        return _.merge(res, { type: data[idx][0].text })
+      })
+      .compact()
+      .value(),
     meaning: data[7][1].text
   }
   // another accents

lib/formatter/partial/_accents.ts

@@ -23,8 +23,12 @@ const pattern = _.chain(list).map(o => o.tag).join('').value()
  * @returns {Sound[]} an array of accents
  */
 const format = (text : string) : Sound[] => {
-  const temp = text.match(new RegExp(`([${pattern}]|[0-9a-zA-Z ]+)`, 'ug'))
-  let state : { vunpag? : number, accent? : number } = {}
+  const regexp = new RegExp(`([${pattern}]|[0-9a-zA-Z ]+)`, 'ug')
+  const temp   = _.flatMap(text.match(/([^、]+)/ug), str => _.chain(str.match(regexp))
+    .map(_.trim)
+    .compact()
+    .value())
+  let state : { vunpag? : number, type? : number } = {}
   return _.chain(temp)
     .map(value => _.chain(value)
       .split(/\s+/)
@@ -40,7 +44,7 @@ const format = (text : string) : Sound[] => {
       }
       const idx_accent = _.findIndex(list, o => o.tag === value)
       if (idx_accent > -1) {
-        state.accent = idx_accent
+        state.type   = idx_accent
         return undefined
       }
       const result : Sound = _.chain(state)

lib/formatter/partial/another.ts

@@ -4,6 +4,17 @@ import * as accents from './_accents';
 import { host }     from '../../util';
 import { Sound }    from '../_type';
 import { ExtractData, ExtractDataType } from '../../extracter/_type';
+
+const reducer = (current : Sound[], ext : ExtractData) => {
+  switch (ext.type) {
+    case ExtractDataType.Text:
+      return _.chain(accents.format(ext.text)).concat(current).value()
+    case ExtractDataType.Link:
+      return _.map(current, c => _.assign(c, { related: `${host}/${ext.link}` }))
+    default:
+      return current
+  }
+}
 /**
  * Format another accent fields different from the main 6 accents.
  *
@@ -12,16 +23,7 @@ import { ExtractData, ExtractDataType } from '../../extracter/_type';
  */
 const formatter = (data : ExtractData[]) : Sound[] => {
   let init : Sound[] = []
-  const s = _.reduce(data, (current, ext) => {
-    switch (ext.type) {
-      case ExtractDataType.Text:
-        return _.chain(accents.format(ext.text)).concat(current).value()
-      case ExtractDataType.Link:
-        return _.map(current, c => _.assign(c, { related: `${host}/${ext.link}` }))
-      default:
-        return current
-    }
-  }, init)
+  const s = _.reduce(data, reducer, init)
   return s
 }
 

lib/formatter/partial/sound.ts

@@ -18,8 +18,6 @@ const formatter = (data : ExtractData[]) : Sound => {
       case ExtractDataType.Media:
         return { media: `${host}/${ext.link}` }
       case ExtractDataType.Text:
-        if (idx === 0)
-          return { type: ext.text }
         return accents.format(ext.text)[0]
       default:
         break;

lib/util/index.ts

@@ -70,7 +70,7 @@ const unicode_table = [
   ['䯋', 'koupng/F448.png'],
   ['⿺皮卜', 'koupng/F545.png']]
 
-export const host  = 'http://hakka.dict.edu.tw/hakkadict'
+export const host  = 'https://hakka.dict.edu.tw/hakkadict'
 
 export const image_table = _
   .chain(unicode_table)