retext-japanese - npm Package Compare versions

Comparing version 0.1.0 to 0.2.0

index.js

@@ -13,3 +13,2 @@ /**
  */
-
 var Parser = require('parse-japanese-basic')
@@ -40,3 +39,22 @@ var visit = require('unist-util-visit')
     /**
-     * Create TextNode for SymbolNode, PunctuationNode, WhiteSpaceNode, SourceNode, and TextNode with POS.
+     * Create WordNode with POS.
+     * @param item
+     * @returns {{type: string, value: *}}
+     */
+    function createWordNode (item) {
+      var wordNode = parser.createParentNode('Word')
+
+      if (options && options.pos) {
+        wordNode.data = item
+      }
+
+      var textNode = parser.createTextNode('Text', item.surface_form)
+
+      parser.add(textNode, wordNode)
+
+      return wordNode
+    }
+
+    /**
+     * Create TextNode for SymbolNode, PunctuationNode, WhiteSpaceNode and SourceNode with POS.
      * @param type
@@ -77,3 +95,4 @@ * @param item
             /**
-             * 以降の解析はParagraphNodeの子ノードはTextNodeとWhiteSpaceNodeとなることを前提としている。
+             * 以降の解析はparse-japanece-basicによるNLCSTを前提としている。
+             * ParagraphNodeの子ノードはTextNodeとWhiteSpaceNodeとなる
              *  ParagraphNode[2]
@@ -99,3 +118,2 @@ *  ├─ TextNode: 'あいうえお'
             var sentenceNode = parser.createParentNode('Sentence')
-            var wordNode = parser.createParentNode('Word')
 
@@ -115,48 +133,30 @@ // kuromoji.jsにより形態素解析を行う
 
-              // 文字が空白の場合
               if (item.pos_detail_1 === WS) {
-                // インラインの場合
-                if (linedepth) {
-                  parser.add(createTextNode('WhiteSpace', item), wordNode)
-                } else {
-                  // アウトラインの場合
-                  // WordNodeに子ノードが存在する場合、WordNodeを終了する
-                  if (wordNode.children.length) {
-                    parser.add(wordNode, sentenceNode)
-                    wordNode = parser.createParentNode('Word')
-                  }
-                  parser.add(createTextNode('WhiteSpace', item), sentenceNode)
-                }
+                // 文字が空白の場合
+                parser.add(createTextNode('WhiteSpace', item), sentenceNode)
               } else if (item.pos_detail_1 === M_OP) {
                 // 文字が開括弧の場合
                 linedepth++
-                parser.add(createTextNode('Punctuation', item), wordNode)
+                parser.add(createTextNode('Punctuation', item), sentenceNode)
               } else if (item.pos_detail_1 === M_CP) {
                 // 文字が閉括弧の場合
                 linedepth--
-                parser.add(createTextNode('Punctuation', item), wordNode)
+                parser.add(createTextNode('Punctuation', item), sentenceNode)
               } else if (item.pos_detail_1 === M_P) {
                 // 文字が句点の場合
-                parser.add(createTextNode('Punctuation', item), wordNode)
-                // アウトラインの場合、WordNodeを終了し、次のWordNodeを作る
-                if (!linedepth) {
-                  parser.add(wordNode, sentenceNode)
-                  wordNode = parser.createParentNode('Word')
-
+                parser.add(createTextNode('Punctuation', item), sentenceNode)
+                // インラインではない場合
+                if (!linedepth && index !== data.length - 1) {
                   // 行末でなければ次のSentenceNodeを作る
-                  if (index !== data.length - 1) {
-                    sentenceNode = parser.createParentNode('Sentence')
-                    parser.add(sentenceNode, paragraphNode)
-                  }
+                  sentenceNode = parser.createParentNode('Sentence')
+                  parser.add(sentenceNode, paragraphNode)
                 }
               } else {
                 // 改行以外のその他の文字の場合
-                parser.add(createTextNode('Text', item), wordNode)
-              }
 
-              // 行末の場合
-              if (index === data.length - 1) {
-                // WordNodeに子ノードが存在する場合、WordNodeを終了する（句点で終わらない文章の場合）
-                if (wordNode.children.length) {
-                  parser.add(wordNode, sentenceNode)
+                // 記号であれば PunctuationNode を作る
+                if (item.pos === '記号' && item.pos_detail_1 === '一般') {
+                  parser.add(createTextNode('Punctuation', item), sentenceNode)
+                } else {
+                  parser.add(createWordNode(item), sentenceNode)
                 }
@@ -163,0 +163,0 @@ }

package.json

 {
   "name": "retext-japanese",
   "description": "Japanese language support for retext",
-  "version": "0.1.0",
+  "version": "0.2.0",
   "author": "Kenichiro Murata <[e-mail]>",
@@ -11,3 +11,3 @@ "bugs": {
     "kuromoji": "0.0.4",
-    "parse-japanese-basic": "^0.2.0",
+    "parse-japanese-basic": "^0.3.0",
     "unist-util-visit": "^1.0.0"
@@ -20,3 +20,3 @@ },
     "mocha": "^2.3.3",
-    "power-assert": "^1.0.1",
+    "power-assert": "^1.1.0",
     "retext": "^1.0.0",
@@ -29,4 +29,3 @@ "retext-emoji": "^1.0.0",
   "files": [
-    "index.js",
-    "lib"
+    "index.js"
   ],
@@ -53,3 +52,3 @@ "homepage": "https://github.com/muraken720/retext-japanese#readme",
     "standard": "standard",
-    "test": "mocha --compilers js:espower-babel/guess test/**/*.js"
+    "test": "npm run standard && mocha --compilers js:espower-babel/guess test/**/*.js"
   },
@@ -56,0 +55,0 @@ "standard": {

README.md

@@ -19,3 +19,3 @@ # retext-japanese [![js-standard-style](https://img.shields.io/badge/code%20style-standard-brightgreen.svg?style=flat)](https://github.com/feross/standard)
 var retext = require('retext')
-var japanese = require('../')
+var japanese = require('retext-japanese')
 var inspect = require('unist-util-inspect')
@@ -52,35 +52,50 @@
 * └─ ParagraphNode[4] (3:1-3:39, 4-44)
-*    ├─ SentenceNode[3] (3:1-3:11, 4-14)
+*    ├─ SentenceNode[7] (3:1-3:11, 4-14)
 *    │  ├─ WordNode[1] (3:1-3:2, 4-5)
 *    │  │  └─ TextNode: "1" (3:1-3:2, 4-5)
 *    │  ├─ WhiteSpaceNode: " " (3:2-3:3, 5-6)
-*    │  └─ WordNode[5] (3:3-3:11, 6-14)
-*    │     ├─ TextNode: "これ" (3:3-3:5, 6-8)
-*    │     ├─ TextNode: "は" (3:5-3:6, 8-9)
-*    │     ├─ TextNode: "前段" (3:6-3:8, 9-11)
-*    │     ├─ TextNode: "です" (3:8-3:10, 11-13)
-*    │     └─ PunctuationNode: "。" (3:10-3:11, 13-14)
-*    ├─ SentenceNode[1] (3:11-3:30, 14-33)
-*    │  └─ WordNode[14] (3:11-3:30, 14-33)
-*    │     ├─ TextNode: "これ" (3:11-3:13, 14-16)
-*    │     ├─ TextNode: "は" (3:13-3:14, 16-17)
-*    │     ├─ TextNode: "中段" (3:14-3:16, 17-19)
-*    │     ├─ PunctuationNode: "（" (3:16-3:17, 19-20)
-*    │     ├─ TextNode: "２" (3:17-3:18, 20-21)
-*    │     ├─ TextNode: "文" (3:18-3:19, 21-22)
-*    │     ├─ TextNode: "の" (3:19-3:20, 22-23)
-*    │     ├─ TextNode: "場合" (3:20-3:22, 23-25)
-*    │     ├─ TextNode: "は" (3:22-3:23, 25-26)
-*    │     ├─ TextNode: "後段" (3:23-3:25, 26-28)
-*    │     ├─ PunctuationNode: "。" (3:25-3:26, 28-29)
-*    │     ├─ PunctuationNode: "）" (3:26-3:27, 29-30)
-*    │     ├─ TextNode: "です" (3:27-3:29, 30-32)
-*    │     └─ PunctuationNode: "。" (3:29-3:30, 32-33)
-*    ├─ SentenceNode[1] (3:30-3:38, 33-41)
-*    │  └─ WordNode[5] (3:30-3:38, 33-41)
-*    │     ├─ TextNode: "これ" (3:30-3:32, 33-35)
-*    │     ├─ TextNode: "は" (3:32-3:33, 35-36)
-*    │     ├─ TextNode: "後段" (3:33-3:35, 36-38)
-*    │     ├─ TextNode: "です" (3:35-3:37, 38-40)
-*    │     └─ PunctuationNode: "。" (3:37-3:38, 40-41)
+*    │  ├─ WordNode[1] (3:3-3:5, 6-8)
+*    │  │  └─ TextNode: "これ" (3:3-3:5, 6-8)
+*    │  ├─ WordNode[1] (3:5-3:6, 8-9)
+*    │  │  └─ TextNode: "は" (3:5-3:6, 8-9)
+*    │  ├─ WordNode[1] (3:6-3:8, 9-11)
+*    │  │  └─ TextNode: "前段" (3:6-3:8, 9-11)
+*    │  ├─ WordNode[1] (3:8-3:10, 11-13)
+*    │  │  └─ TextNode: "です" (3:8-3:10, 11-13)
+*    │  └─ PunctuationNode: "。" (3:10-3:11, 13-14)
+*    ├─ SentenceNode[14] (3:11-3:30, 14-33)
+*    │  ├─ WordNode[1] (3:11-3:13, 14-16)
+*    │  │  └─ TextNode: "これ" (3:11-3:13, 14-16)
+*    │  ├─ WordNode[1] (3:13-3:14, 16-17)
+*    │  │  └─ TextNode: "は" (3:13-3:14, 16-17)
+*    │  ├─ WordNode[1] (3:14-3:16, 17-19)
+*    │  │  └─ TextNode: "中段" (3:14-3:16, 17-19)
+*    │  ├─ PunctuationNode: "（" (3:16-3:17, 19-20)
+*    │  ├─ WordNode[1] (3:17-3:18, 20-21)
+*    │  │  └─ TextNode: "２" (3:17-3:18, 20-21)
+*    │  ├─ WordNode[1] (3:18-3:19, 21-22)
+*    │  │  └─ TextNode: "文" (3:18-3:19, 21-22)
+*    │  ├─ WordNode[1] (3:19-3:20, 22-23)
+*    │  │  └─ TextNode: "の" (3:19-3:20, 22-23)
+*    │  ├─ WordNode[1] (3:20-3:22, 23-25)
+*    │  │  └─ TextNode: "場合" (3:20-3:22, 23-25)
+*    │  ├─ WordNode[1] (3:22-3:23, 25-26)
+*    │  │  └─ TextNode: "は" (3:22-3:23, 25-26)
+*    │  ├─ WordNode[1] (3:23-3:25, 26-28)
+*    │  │  └─ TextNode: "後段" (3:23-3:25, 26-28)
+*    │  ├─ PunctuationNode: "。" (3:25-3:26, 28-29)
+*    │  ├─ PunctuationNode: "）" (3:26-3:27, 29-30)
+*    │  ├─ WordNode[1] (3:27-3:29, 30-32)
+*    │  │  └─ TextNode: "です" (3:27-3:29, 30-32)
+*    │  └─ PunctuationNode: "。" (3:29-3:30, 32-33)
+*    ├─ SentenceNode[5] (3:30-3:38, 33-41)
+*    │  ├─ WordNode[1] (3:30-3:32, 33-35)
+*    │  │  └─ TextNode: "これ" (3:30-3:32, 33-35)
+*    │  ├─ WordNode[1] (3:32-3:33, 35-36)
+*    │  │  └─ TextNode: "は" (3:32-3:33, 35-36)
+*    │  ├─ WordNode[1] (3:33-3:35, 36-38)
+*    │  │  └─ TextNode: "後段" (3:33-3:35, 36-38)
+*    │  ├─ WordNode[1] (3:35-3:37, 38-40)
+*    │  │  └─ TextNode: "です" (3:35-3:37, 38-40)
+*    │  └─ PunctuationNode: "。" (3:37-3:38, 40-41)
 *    └─ WhiteSpaceNode: "\n" (3:38-3:39, 43-44)
@@ -114,14 +129,20 @@ *
 /**
-* RootNode[1] (1:1-1:14, 0-13)
-* └─ ParagraphNode[2] (1:1-1:14, 0-13)
-*    ├─ SentenceNode[1] (1:1-1:13, 0-12)
-*    │  └─ WordNode[7] (1:1-1:13, 0-12)
-*    │     ├─ TextNode: "すもも" (1:1-1:4, 0-3) [data={"word_id":404420,"word_type":"KNOWN","word_position":1,"surface_form":"すもも","pos":"名詞","pos_detail_1":"一般","pos_detail_2":"*","pos_detail_3":"*","conjugated_type":"*","conjugated_form":"*","basic_form":"すもも","reading":"スモモ","pronunciation":"スモモ"}]
-*    │     ├─ TextNode: "も" (1:4-1:5, 3-4) [data={"word_id":2595480,"word_type":"KNOWN","word_position":4,"surface_form":"も","pos":"助詞","pos_detail_1":"係助詞","pos_detail_2":"*","pos_detail_3":"*","conjugated_type":"*","conjugated_form":"*","basic_form":"も","reading":"モ","pronunciation":"モ"}]
-*    │     ├─ TextNode: "もも" (1:5-1:7, 4-6) [data={"word_id":604730,"word_type":"KNOWN","word_position":5,"surface_form":"もも","pos":"名詞","pos_detail_1":"一般","pos_detail_2":"*","pos_detail_3":"*","conjugated_type":"*","conjugated_form":"*","basic_form":"もも","reading":"モモ","pronunciation":"モモ"}]
-*    │     ├─ TextNode: "も" (1:7-1:8, 6-7) [data={"word_id":2595480,"word_type":"KNOWN","word_position":7,"surface_form":"も","pos":"助詞","pos_detail_1":"係助詞","pos_detail_2":"*","pos_detail_3":"*","conjugated_type":"*","conjugated_form":"*","basic_form":"も","reading":"モ","pronunciation":"モ"}]
-*    │     ├─ TextNode: "もも" (1:8-1:10, 7-9) [data={"word_id":604730,"word_type":"KNOWN","word_position":8,"surface_form":"もも","pos":"名詞","pos_detail_1":"一般","pos_detail_2":"*","pos_detail_3":"*","conjugated_type":"*","conjugated_form":"*","basic_form":"もも","reading":"モモ","pronunciation":"モモ"}]
-*    │     ├─ TextNode: "の" (1:10-1:11, 9-10) [data={"word_id":2595360,"word_type":"KNOWN","word_position":10,"surface_form":"の","pos":"助詞","pos_detail_1":"連体化","pos_detail_2":"*","pos_detail_3":"*","conjugated_type":"*","conjugated_form":"*","basic_form":"の","reading":"ノ","pronunciation":"ノ"}]
-*    │     └─ TextNode: "うち" (1:11-1:13, 10-12) [data={"word_id":1467000,"word_type":"KNOWN","word_position":11,"surface_form":"うち","pos":"名詞","pos_detail_1":"非自立","pos_detail_2":"副詞可能","pos_detail_3":"*","conjugated_type":"*","conjugated_form":"*","basic_form":"うち","reading":"ウチ","pronunciation":"ウチ"}]
-*    └─ WhiteSpaceNode: "\n" (1:13-1:14, 12-13)
+* RootNode[1]
+* └─ ParagraphNode[2]
+*    ├─ SentenceNode[7]
+*    │  ├─ WordNode[1] [data={"word_id":404420,"word_type":"KNOWN","word_position":1,"surface_form":"すもも","pos":"名詞","pos_detail_1":"一般","pos_detail_2":"*","pos_detail_3":"*","conjugated_type":"*","conjugated_form":"*","basic_form":"すもも","reading":"スモモ","pronunciation":"スモモ"}]
+*    │  │  └─ TextNode: "すもも"
+*    │  ├─ WordNode[1] [data={"word_id":2595480,"word_type":"KNOWN","word_position":4,"surface_form":"も","pos":"助詞","pos_detail_1":"係助詞","pos_detail_2":"*","pos_detail_3":"*","conjugated_type":"*","conjugated_form":"*","basic_form":"も","reading":"モ","pronunciation":"モ"}]
+*    │  │  └─ TextNode: "も"
+*    │  ├─ WordNode[1] [data={"word_id":604730,"word_type":"KNOWN","word_position":5,"surface_form":"もも","pos":"名詞","pos_detail_1":"一般","pos_detail_2":"*","pos_detail_3":"*","conjugated_type":"*","conjugated_form":"*","basic_form":"もも","reading":"モモ","pronunciation":"モモ"}]
+*    │  │  └─ TextNode: "もも"
+*    │  ├─ WordNode[1] [data={"word_id":2595480,"word_type":"KNOWN","word_position":7,"surface_form":"も","pos":"助詞","pos_detail_1":"係助詞","pos_detail_2":"*","pos_detail_3":"*","conjugated_type":"*","conjugated_form":"*","basic_form":"も","reading":"モ","pronunciation":"モ"}]
+*    │  │  └─ TextNode: "も"
+*    │  ├─ WordNode[1] [data={"word_id":604730,"word_type":"KNOWN","word_position":8,"surface_form":"もも","pos":"名詞","pos_detail_1":"一般","pos_detail_2":"*","pos_detail_3":"*","conjugated_type":"*","conjugated_form":"*","basic_form":"もも","reading":"モモ","pronunciation":"モモ"}]
+*    │  │  └─ TextNode: "もも"
+*    │  ├─ WordNode[1] [data={"word_id":2595360,"word_type":"KNOWN","word_position":10,"surface_form":"の","pos":"助詞","pos_detail_1":"連体化","pos_detail_2":"*","pos_detail_3":"*","conjugated_type":"*","conjugated_form":"*","basic_form":"の","reading":"ノ","pronunciation":"ノ"}]
+*    │  │  └─ TextNode: "の"
+*    │  └─ WordNode[1] [data={"word_id":1467000,"word_type":"KNOWN","word_position":11,"surface_form":"うち","pos":"名詞","pos_detail_1":"非自立","pos_detail_2":"副詞可能","pos_detail_3":"*","conjugated_type":"*","conjugated_form":"*","basic_form":"うち","reading":"ウチ","pronunciation":"ウチ"}]
+*    │     └─ TextNode: "うち"
+*    └─ WhiteSpaceNode: "\n"
 * 
@@ -146,3 +167,3 @@ * === doc ===
     *   `pos` (`boolean`, default: `false`) - Whether to add part-of-speech information(by using [kuromoji.js](https://github.com/takuyaa/kuromoji.js)) to nodes.
-    *   `dicDir` (`string`, default: `node_modules/parse-japanese/node_modules/kuromoji/dist/dict/`) - Whether to set Dictionaries directory for kuromoji.js. 
+    *   `dicDir` (`string`, default: `node_modules/retext-japanese/node_modules/kuromoji/dist/dict/`) - Whether to set Dictionaries directory for kuromoji.js. 
 
@@ -149,0 +170,0 @@ ## Related

New alerts

License Policy Violation

License

This package is not allowed per your license policy. Review the package's license to ensure compliance.

Found 1 instance in 1 package

Fixed alerts

License Policy Violation

License

This package is not allowed per your license policy. Review the package's license to ensure compliance.

Found 1 instance in 1 package

Improved metrics

Total package byte prevSize

15841

increased by2.07%

Number of lines in readme file

175

increased by13.64%

Worsened metrics

Lines of code

139

decreased by-2.11%

Dependency changes

• + Addedparse-japanese-basic@0.3.0(transitive)

• - Removedparse-japanese-basic@0.2.0(transitive)

• Updatedparse-japanese-basic@^0.3.0