sentence-splitter - npm Package Compare versions

Comparing version 1.1.0 to 1.1.1

lib/sentence-splitter.js

@@ -19,5 +19,5 @@ // LICENSE : MIT
 var defaultOptions = {
-    charRegExp: /[\.。\?\!？！]/
+    charRegExp: /[\.。\?\!？！]/,
+    whiteSpaceRegExp: /\n/
 };
-var whiteSpace = /\n/;
 var Syntax = exports.Syntax = {
@@ -28,4 +28,6 @@ "WhiteSpace": "WhiteSpace",
 function splitSentences(text) {
-    var options = arguments.length <= 1 || arguments[1] === undefined ? defaultOptions : arguments[1];
+    var options = arguments.length <= 1 || arguments[1] === undefined ? {} : arguments[1];
 
+    var matchChar = options.charRegExp || defaultOptions.charRegExp;
+    var whiteSpace = options.whiteSpaceRegExp || defaultOptions.whiteSpaceRegExp;
     var src = new _structuredSource2.default(text);
@@ -48,3 +50,2 @@ var createNode = function createNode(type, start, end) {
     var isSplitPoint = false;
-    var matchChar = options.charRegExp || defaultOptions.charRegExp;
     for (; currentIndex < text.length; currentIndex++) {
@@ -51,0 +52,0 @@ var char = text[currentIndex];

package.json

@@ -14,3 +14,3 @@ {
   },
-  "version": "1.1.0",
+  "version": "1.1.1",
   "description": "split {japanese, english} text into sentences.",
@@ -17,0 +17,0 @@ "main": "lib/sentence-splitter.js",

README.md

@@ -22,2 +22,3 @@ # sentence-splitter
         "raw": "text.",
+        "value": "text.",
         "loc": {
@@ -41,2 +42,3 @@ "start": {
         "raw": "\n",
+        "value": "\n",
         "loc": {
@@ -60,2 +62,3 @@ "start": {
         "raw": "\n",
+        "value": "\n",
         "loc": {
@@ -79,2 +82,3 @@ "start": {
         "raw": "text",
+        "value": "text",
         "loc": {
@@ -115,2 +119,141 @@ "start": {
 
+## FAQ
+
+### How to know real sentence?
+
+`sentence-splitter` split text into `Sentence` and `WhiteSpace`
+
+`sentence-splitter` following text to **3** Sentence and **3** WhiteSpace.
+
+Some markdown parser take cognizance 1 Sentence + 1 WhiteSpace + 1Sentence as 1 Sentence.
+if you want to replicate this algorithm, then you should write this algorithm.
+
+```markdown
+TextA
+TextB
+
+TextC
+```
+
+Output: 
+
+```json
+[
+    {
+        "type": "Sentence",
+        "raw": "TextA",
+        "value": "TextA",
+        "loc": {
+            "start": {
+                "line": 1,
+                "column": 0
+            },
+            "end": {
+                "line": 1,
+                "column": 5
+            }
+        },
+        "range": [
+            0,
+            5
+        ]
+    },
+    {
+        "type": "WhiteSpace",
+        "raw": "\n",
+        "value": "\n",
+        "loc": {
+            "start": {
+                "line": 1,
+                "column": 5
+            },
+            "end": {
+                "line": 2,
+                "column": 0
+            }
+        },
+        "range": [
+            5,
+            6
+        ]
+    },
+    {
+        "type": "Sentence",
+        "raw": "TextB",
+        "value": "TextB",
+        "loc": {
+            "start": {
+                "line": 2,
+                "column": 0
+            },
+            "end": {
+                "line": 2,
+                "column": 5
+            }
+        },
+        "range": [
+            6,
+            11
+        ]
+    },
+    {
+        "type": "WhiteSpace",
+        "raw": "\n",
+        "value": "\n",
+        "loc": {
+            "start": {
+                "line": 2,
+                "column": 5
+            },
+            "end": {
+                "line": 3,
+                "column": 0
+            }
+        },
+        "range": [
+            11,
+            12
+        ]
+    },
+    {
+        "type": "WhiteSpace",
+        "raw": "\n",
+        "value": "\n",
+        "loc": {
+            "start": {
+                "line": 3,
+                "column": 0
+            },
+            "end": {
+                "line": 4,
+                "column": 0
+            }
+        },
+        "range": [
+            12,
+            13
+        ]
+    },
+    {
+        "type": "Sentence",
+        "raw": "TextC",
+        "value": "TextC",
+        "loc": {
+            "start": {
+                "line": 4,
+                "column": 0
+            },
+            "end": {
+                "line": 4,
+                "column": 5
+            }
+        },
+        "range": [
+            13,
+            18
+        ]
+    }
+]
+```
+
 ## Tests
@@ -117,0 +260,0 @@

src/sentence-splitter.js

@@ -5,5 +5,5 @@ // LICENSE : MIT
 const defaultOptions = {
-    charRegExp: /[\.。\?\!？！]/
+    charRegExp: /[\.。\?\!？！]/,
+    whiteSpaceRegExp: /\n/
 };
-const whiteSpace = /\n/;
 export const Syntax = {
@@ -13,3 +13,5 @@ "WhiteSpace": "WhiteSpace",
 };
-export default function splitSentences(text, options = defaultOptions) {
+export default function splitSentences(text, options = {}) {
+    const matchChar = options.charRegExp || defaultOptions.charRegExp;
+    const whiteSpace = options.whiteSpaceRegExp || defaultOptions.whiteSpaceRegExp;
     const src = new StructureSource(text);
@@ -32,3 +34,2 @@ let createNode = (type, start, end)=> {
     let isSplitPoint = false;
-    let matchChar = options.charRegExp || defaultOptions.charRegExp;
     for (; currentIndex < text.length; currentIndex++) {
@@ -35,0 +36,0 @@ let char = text[currentIndex];

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

18026

increased by19.58%

Lines of code

167

increased by1.21%

Number of lines in readme file

268

increased by114.4%

No dependency changes