initial commit

Author: takahashim

.babelrc

@@ -0,0 +1,4 @@
+{
+    "presets": ["es2015"],
+    "plugins": ["add-module-exports"]
+}

.gitignore

@@ -0,0 +1,40 @@
+# from https://github.com/github/gitignore/blob/master/Node.gitignore
+
+# Logs
+logs
+*.log
+npm-debug.log*
+
+# Runtime data
+pids
+*.pid
+*.seed
+
+# Directory for instrumented libs generated by jscoverage/JSCover
+lib-cov
+
+# Coverage directory used by tools like istanbul
+coverage
+
+# Grunt intermediate storage (http://gruntjs.com/creating-plugins#storing-task-files)
+.grunt
+
+# node-waf configuration
+.lock-wscript
+
+# Compiled binary addons (http://nodejs.org/api/addons.html)
+build/Release
+
+# Dependency directories
+node_modules
+jspm_packages
+
+# Optional npm cache directory
+.npm
+
+# Optional REPL history
+.node_repl_history
+
+# Others
+/lib
+

.npmignore

@@ -0,0 +1,3 @@
+src
+test
+node_modules

LICENSE

@@ -0,0 +1,19 @@
+Copyright (c) 2016 takahashim
+
+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 +1,45 @@
+# textlint-rule-no-doubled-conjunction
+
+This module is a textlint plugin to check duplicated same conjunctions.
+
+同じ接続詞が連続して出現していないかどうかをチェックするための[textlint](https://github.com/textlint/textlint "textlint")ルールです。
+
+ex)
+
+> かな漢字変換により漢字が多用される傾向がある。しかし漢字の多用が読みにくさをもたらす側面は否定できない。しかし、平仮名が多い文は間延びした印象を与える恐れもある。
+
+In this example, "**しかし**" are used sequentially.
+
+## Installation
+
+    npm install textlint-rule-no-doubled-conjunction
+
+### Require
+
+- textlint 5.0 >=
+
+### Dependencies
+
+- [azu/kuromojin](https://github.com/azu/kuromojin): a wrapper of [kuromoji.js](https://github.com/takuyaa/kuromoji.js "kuromoji.js")
+- [azu/sentence-splitter](https://github.com/azu/sentence-splitter)
+
+## Usage
+
+    textlint --rule no-doubled-conjunction sample.md
+
+### Options
+
+There's no options for this plugin.
+
+## Tests
+
+    npm test
+
+## Reference
+
+- [textlint](https://github.com/textlint/textlint)
+- [textlint-rule-no-doubled-joshi](https://github.com/azu/textlint-rule-no-doubled-joshi): this plugin is based on it
+
+## License
+
+MIT

package.json

@@ -0,0 +1,47 @@
+{
+  "name": "textlint-rule-no-doubled-conjunction",
+  "version": "1.0.0",
+  "description": "textlint rule plugin to check duplicated conjunctions.",
+  "main": "lib/no-doubled-conjunction.js",
+  "directories": {
+    "example": "example",
+    "test": "test"
+  },
+  "dependencies": {
+    "kuromojin": "^1.1.0",
+    "sentence-splitter": "^1.2.0",
+    "textlint-rule-helper": "^1.1.5",
+    "textlint-util-to-string": "^1.2.0"
+  },
+  "devDependencies": {
+    "babel-cli": "^6.5.1",
+    "babel-plugin-add-module-exports": "^0.1.2",
+    "babel-preset-es2015": "^6.5.0",
+    "espower-babel": "^4.0.1",
+    "mocha": "^2.4.5",
+    "power-assert": "^1.2.0",
+    "textlint": "^5.2.1",
+    "textlint-tester": "^0.4.1"
+  },
+  "scripts": {
+    "build": "babel src --out-dir lib --source-maps",
+    "watch": "babel src --out-dir lib --watch --source-maps",
+    "prepublish": "npm run --if-present build",
+    "test": "mocha",
+    "textlint": "textlint"
+  },
+  "keywords": [
+    "textlint",
+    "rule"
+  ],
+  "author": "takahashim <takahashimm@gmail.com>",
+  "license": "MIT",
+  "repository": {
+    "type": "git",
+    "url": "https://github.com/takahashim/textlint-rule-no-doubled-conjunction.git"
+  },
+  "bugs": {
+    "url": "https://github.com/takahashim/textlint-rule-no-doubled-conjunction/issues"
+  },
+  "homepage": "https://github.com/takahashim/textlint-rule-no-doubled-conjunction"
+}

src/no-doubled-conjunction.js

@@ -0,0 +1,66 @@
+// LICENSE : MIT
+"use strict";
+import {RuleHelper} from "textlint-rule-helper";
+import {getTokenizer} from "kuromojin";
+import splitSentences, {Syntax as SentenceSyntax} from "sentence-splitter";
+import StringSource from "textlint-util-to-string";
+
+/*
+    1. Paragraph Node -> text
+    2. text -> sentences
+    3. tokenize sentence
+    4. report error if found word that match the rule.
+
+    TODO: need abstraction
+ */
+export default function (context, options = {}) {
+    const helper = new RuleHelper(context);
+    const {Syntax, report, getSource, RuleError} = context;
+    return {
+        [Syntax.Paragraph](node){
+            if (helper.isChildNode(node, [Syntax.Link, Syntax.Image, Syntax.BlockQuote, Syntax.Emphasis])) {
+                return;
+            }
+            const source = new StringSource(node);
+            const text = source.toString();
+            const isSentenceNode = (node) => node.type === SentenceSyntax.Sentence;
+            let sentences = splitSentences(text, {
+                charRegExp: /[。\?\!？！]/
+            }).filter(isSentenceNode);
+            return getTokenizer().then(tokenizer => {
+              const selectConjenction = (sentence) => {
+                let tokens = tokenizer.tokenizeForSentence(sentence.raw);
+                let conjunctionTokens = tokens.filter((token) => token.pos === "接続詞");
+                return [sentence, conjunctionTokens];
+              };
+              let prev_token = null;
+              sentences.map(selectConjenction).reduce((prev, current) => {
+                let token = prev_token;
+                let [sentence, current_tokens] = current;
+                let [prev_sentence, prev_tokens] = prev;
+                if (prev_tokens && prev_tokens.length > 0) {
+                  token = prev_tokens[0];
+                }
+                if (current_tokens.length > 0) {
+                  if (token && current_tokens[0].surface_form === token.surface_form) {
+                    let originalPosition = source.originalPositionFor({
+                      line: sentence.loc.start.line,
+                      column: sentence.loc.start.column + (current_tokens[0].word_position - 1)
+                    });
+                    // padding position
+                    var padding = {
+                      line: originalPosition.line - 1,
+                      // matchLastToken.word_position start with 1
+                      // this is padding column start with 0 (== -1)
+                      column: originalPosition.column
+                    };
+                    report(node, new RuleError(`同じ接続詞が連続して使われています。`, padding));
+                  }
+                }
+                prev_token = token;
+                return current;
+              });
+            });
+        }
+    }
+};

test/mocha.opts

@@ -0,0 +1 @@
+--compilers js:espower-babel/guess

test/no-doubled-conjunction.js

@@ -0,0 +1,46 @@
+import assert from "power-assert";
+import rule from "../src/no-doubled-conjunction";
+import TextLintTester from "textlint-tester";
+var tester = new TextLintTester();
+tester.run("no-doubled-conjunction", rule, {
+    valid: [
+        "朝起きた。そして、夜に寝た。",
+        "そして朝起きた。けれど昼は仕事をした。そして夜に寝た。"
+    ],
+    invalid: [
+      {
+          text: "朝起きた。そして昼は仕事をした。そして夜に寝た",
+          errors: [
+              {
+                  message: `同じ接続詞が連続して使われています。`,
+                  // last match
+                  line: 1,
+                  column: 17
+              }
+          ]
+      },
+      {
+          text: "そして朝起きた。昼は仕事をした。そして夜に寝た",
+          errors: [
+              {
+                  message: `同じ接続詞が連続して使われています。`,
+                  // last match
+                  line: 1,
+                  column: 17
+              }
+          ]
+      },
+      {
+          text: "かな漢字変換により漢字が多用される傾向がある。しかし漢字の多用が読みにくさをもたらす側面は否定できない。しかし、平仮名が多い文は間延びした印象を与える恐れもある。",
+          errors: [
+              {
+                  message: `同じ接続詞が連続して使われています。`,
+                  // last match
+                  line: 1,
+                  column: 53
+              }
+          ]
+      }
+
+    ]
+});