split-string - npm Package Compare versions

Comparing version 4.0.0 to 5.0.0

index.js

 /*!
  * split-string <https://github.com/jonschlinkert/split-string>
  *
- * Copyright (c) 2015-2017, Jon Schlinkert.
+ * Copyright (c) 2015-2018, Jon Schlinkert.
  * Released under the MIT License.
@@ -10,3 +10,8 @@ */
 
-var extend = require('extend-shallow');
+const Lexer = require('snapdragon-lexer');
+const union = require('arr-union');
+const defaults = {
+  brackets: { '<': '>', '(': ')', '[': ']', '{': '}' },
+  quotes: { '"': '"', "'": "'", '`': '`', '“': '”' }
+};
 
@@ -23,163 +28,197 @@ module.exports = function(str, options, fn) {
 
-  // allow separator to be defined as a string
-  if (typeof options === 'string') {
-    options = { sep: options };
-  }
-
-  var opts = extend({sep: '.'}, options);
-  var quotes = opts.quotes || {
-    '"': '"',
-    "'": "'",
-    '`': '`',
-    '“': '”'
+  const opts = Object.assign({ separator: '.' }, options);
+  const sep = opts.sep || opts.separator;
+  const lexer = new Lexer(str, opts);
+  lexer.split = (token) => {
+    if (typeof lexer.options.split === 'function') {
+      return lexer.options.split.call(lexer, token);
+    }
+    return true;
   };
 
-  if (Array.isArray(quotes)) {
-    quotes = quotes.reduce(function(acc, ele) {
-      acc[ele] = ele;
-      return acc;
-    }, {});
-  }
+  // brackets support
+  const brackets = opts.brackets === true ? defaults.brackets : opts.brackets;
 
-  var brackets;
-  if (opts.brackets === true) {
-    brackets = {
-      '<': '>',
-      '(': ')',
-      '[': ']',
-      '{': '}'
-    };
-  } else if (opts.brackets) {
-    brackets = opts.brackets;
-  }
+  // quotes support
+  const quotes = opts.quotes === true || typeof opts.quotes === 'undefined'
+    ? defaults.quotes
+    : opts.quotes;
 
-  var tokens = [];
-  var stack = [];
-  var arr = [''];
-  var sep = opts.sep;
-  var len = str.length;
-  var idx = -1;
-  var closeIdx;
+  const openChars = brackets ? Object.keys(brackets) : [];
+  const closeChars = brackets ? Object.values(brackets) : [];
+  const quoteChars = union(Object.keys(quotes), Object.values(quotes));
+  const openStr = brackets ? escape(openChars) : '';
+  const closeStr = brackets ? escape(closeChars) : '';
+  const quoteStr = quotes ? escape(quoteChars) : '';
+  const textRegexp = new RegExp(`^[^\\\\${sep + openStr + closeStr + quoteStr}]+`);
 
-  function expected() {
-    if (brackets && stack.length) {
-      return brackets[stack[stack.length - 1]];
+  /**
+   * Handlers
+   */
+
+  lexer.capture('escape', /^\\(.)/, function(token) {
+    token.escaped = true;
+    if (opts.keepEscaping !== true && token.value !== '\\\\') {
+      token.value = token.value.slice(1);
     }
-  }
+    if (fn) fn.call(this, token);
+    return token;
+  });
 
-  while (++idx < len) {
-    var ch = str[idx];
-    var next = str[idx + 1];
-    var tok = { val: ch, idx: idx, arr: arr, str: str };
-    tokens.push(tok);
+  lexer.capture('separator', toRegexp(escape(sep.split(''))), function(token) {
+    if (fn) fn.call(this, token);
 
-    if (ch === '\\') {
-      tok.val = keepEscaping(opts, str, idx) === true ? (ch + next) : next;
-      tok.escaped = true;
-      if (typeof fn === 'function') {
-        fn(tok);
-      }
-      arr[arr.length - 1] += tok.val;
-      idx++;
-      continue;
+    if (typeof token.split === 'function' && token.split() === false) {
+      return token;
     }
+    if (lexer.split(token) === false) {
+      return token;
+    }
 
-    if (brackets && brackets[ch]) {
-      stack.push(ch);
-      var e = expected();
-      var i = idx + 1;
+    if (!this.stack.length && this.last(this.stash) !== '') {
+      this.stash.push('');
+    }
+    if (!this.isInside('quote') && !this.isInside('bracket')) {
+      token.value = '';
+    }
+    return token;
+  });
 
-      if (str.indexOf(e, i + 1) !== -1) {
-        while (stack.length && i < len) {
-          var s = str[++i];
-          if (s === '\\') {
-            s++;
-            continue;
-          }
+  lexer.capture('text', textRegexp, (token) => {
+    if (fn) fn.call(lexer, token);
+    return token;
+  });
 
-          if (quotes[s]) {
-            i = getClosingQuote(str, quotes[s], i + 1);
-            continue;
-          }
+  if (quotes) {
+    lexer.capture('quote', toRegexp(quoteStr), function(token) {
+      if (this.isInside('bracket')) return token;
 
-          e = expected();
-          if (stack.length && str.indexOf(e, i + 1) === -1) {
-            break;
-          }
+      let val = token.match[0];
+      token.append = false;
 
-          if (brackets[s]) {
-            stack.push(s);
-            continue;
-          }
-
-          if (e === s) {
-            stack.pop();
-          }
-        }
+      if (!keepQuotes(val, opts)) {
+        token.value = '';
       }
 
-      closeIdx = i;
-      if (closeIdx === -1) {
-        arr[arr.length - 1] += ch;
-        continue;
-      }
+      if (this.isClose(val)) {
+        const open = this.stack.pop();
+        open.closed = true;
+        this.unwind(open, true);
+        this.append(token.value);
 
-      ch = str.slice(idx, closeIdx + 1);
-      tok.val = ch;
-      tok.idx = idx = closeIdx;
-    }
-
-    if (quotes[ch]) {
-      closeIdx = getClosingQuote(str, quotes[ch], idx + 1);
-      if (closeIdx === -1) {
-        arr[arr.length - 1] += ch;
-        continue;
+      } else {
+        token.isClose = value => value === quotes[val];
+        token.queue = [];
+        this.stack.push(token);
       }
+      return token;
+    });
+  }
 
-      if (keepQuotes(ch, opts) === true) {
-        ch = str.slice(idx, closeIdx + 1);
-      } else {
-        ch = str.slice(idx + 1, closeIdx);
+  if (brackets) {
+    lexer.capture('bracket', toRegexp(openStr), function(token) {
+      token.isClose = value => value === brackets[token.value];
+      token.append = false;
+      token.queue = [];
+      this.stack.push(token);
+      return token;
+    });
+    lexer.capture('bracket.close', toRegexp(closeStr), function(token) {
+      if (this.isClose(token.value)) {
+        const open = this.stack.pop();
+        open.value += open.queue.join('');
+        this.append(open.value);
       }
+      return token;
+    });
+  }
 
-      tok.val = ch;
-      tok.idx = idx = closeIdx;
+  /**
+   * Custom lexer methods
+   */
+
+  lexer.isClose = function(ch) {
+    const open = this.stack.last;
+    if (open && typeof open.isClose === 'function') {
+      return open.isClose(ch);
     }
+  };
 
-    if (typeof fn === 'function') {
-      fn(tok, tokens);
-      ch = tok.val;
-      idx = tok.idx;
+  lexer.append = function(val) {
+    if (!val) return;
+    const last = this.stack.last;
+    if (last && Array.isArray(last.queue)) {
+      last.queue.push(val);
+    } else {
+      this.stash[this.stash.length - 1] += val;
     }
+  };
 
-    if (tok.val === sep && tok.split !== false) {
-      arr.push('');
-      continue;
+  // add queued strings back to the stash
+  lexer.unwind = function(token, append) {
+    switch (token && token.type) {
+      case 'bracket':
+        const segs = token.queue.join('').split('.');
+        this.append(token.value);
+        this.append(segs.shift());
+        this.stash = this.stash.concat(segs);
+        break;
+      case 'quote':
+        const quote = token.closed && !keepQuotes(token.match[0], opts) ? '' : token.match[0];
+        this.append(quote);
+        this.append(token.queue.shift());
+
+        while (token.queue.length) {
+          const val = token.queue.shift();
+          if (append) {
+            this.append(val);
+            continue;
+          }
+
+          if (val !== sep) {
+            this.stash.push(val);
+          }
+        }
+        break;
+      default: {
+        break;
+      }
     }
+  };
 
-    arr[arr.length - 1] += tok.val;
+  // start tokenizing
+  lexer.tokenize(str);
+
+  // ensure the stack is empty
+  if (lexer.options.strict === true) {
+    lexer.fail();
   }
 
-  return arr;
+  lexer.unwind(lexer.stack.pop());
+  lexer.fail();
+  return lexer.stash;
 };
 
-function getClosingQuote(str, ch, i, brackets) {
-  var idx = str.indexOf(ch, i);
-  if (str.charAt(idx - 1) === '\\') {
-    return getClosingQuote(str, ch, idx + 1);
-  }
-  return idx;
+function toRegexp(str) {
+  return new RegExp(`^(?=.)[${str}]`);
 }
 
-function keepQuotes(ch, opts) {
-  if (opts.keepDoubleQuotes === true && (ch === '"' || ch === '“' || ch === '”')) return true;
-  if (opts.keepSingleQuotes === true && ch === "'") return true;
-  return opts.keepQuotes;
+function escape(arr) {
+  return '\\' + arr.join('\\');
 }
 
-function keepEscaping(opts, str, idx) {
-  if (typeof opts.keepEscaping === 'function') {
-    return opts.keepEscaping(str, idx);
+function keepQuotes(ch, opts) {
+  if (opts.keepSmartQuotes === true && (ch === '“' || ch === '”')) {
+    return true;
   }
-  return opts.keepEscaping === true || str[idx + 1] === '\\';
+  if (opts.keepDoubleQuotes === true && ch === '"') {
+    return true;
+  }
+  if (opts.keepSingleQuotes === true && ch === '\'') {
+    return true;
+  }
+  if (opts.keepBackticks === true && ch === '`') {
+    return true;
+  }
+  return opts.keepQuotes;
 }

package.json

 {
   "name": "split-string",
   "description": "Split a string on a character except when the character is escaped.",
-  "version": "4.0.0",
+  "version": "5.0.0",
   "homepage": "https://github.com/jonschlinkert/split-string",
@@ -24,10 +24,12 @@ "author": "Jon Schlinkert (https://github.com/jonschlinkert)",
   "scripts": {
-    "test": "mocha"
+    "test": "nyc mocha"
   },
   "dependencies": {
-    "extend-shallow": "^3.0.0"
+    "arr-union": "^3.1.0",
+    "snapdragon-lexer": "^2.0.0"
   },
   "devDependencies": {
+    "mocha": "^3.5.3",
     "gulp-format-md": "^1.0.0",
-    "mocha": "^3.5.3"
+    "nyc": "^11.4.1"
   },
@@ -40,2 +42,8 @@ "keywords": [
   ],
+  "nyc": {
+    "reporter": [
+      "lcov",
+      "text-summary"
+    ]
+  },
   "verb": {
@@ -42,0 +50,0 @@ "toc": false,

README.md

@@ -31,3 +31,3 @@ # split-string [![NPM version](https://img.shields.io/npm/v/split-string.svg?style=flat)](https://www.npmjs.com/package/split-string) [![NPM monthly downloads](https://img.shields.io/npm/dm/split-string.svg?style=flat)](https://npmjs.org/package/split-string) [![NPM total downloads](https://img.shields.io/npm/dt/split-string.svg?style=flat)](https://npmjs.org/package/split-string) [![Linux Build Status](https://img.shields.io/travis/jonschlinkert/split-string.svg?style=flat&label=Travis)](https://travis-ci.org/jonschlinkert/split-string)
 
-**Bad**
+**This is bad**
 
@@ -42,3 +42,3 @@ ```js
 
-**Good**
+**This is good**
 
@@ -124,8 +124,10 @@ ```js
 
-// support only the specified brackets
-split('[a.b].(c.d)', {brackets: {'[': ']'}});
-//=> [ '[a.b]', '(c', 'd)' ]
+// support only the specified bracket types
+split('«a.b».⟨c.d⟩', {brackets: {'«': '»', '⟨': '⟩'}});
+//=> [ '«a.b»', '⟨c.d⟩' ]
+split('a.{a.[{b.c}].d}.e', {brackets: {'[': ']'}});
+//=> [ 'a', '{a', '[{b.c}]', 'd}', 'e' ]
 ```
 
-### options.sep
+### options.separator
 
@@ -136,3 +138,3 @@ **Type**: `string`
 
-The separator/character to split on.
+The separator/character to split on. Aliased as `options.sep` for backwards compatibility with versions <4.0.
 
@@ -142,6 +144,6 @@ **Example**
 ```js
-split('a.b,c', {sep: ','});
+split('a.b,c', {separator: ','});
 //=> ['a.b', 'c']
 
-// you can also pass the separator as string as the last argument
+// you can also pass the separator as a string as the last argument
 split('a.b,c', ',');
@@ -237,8 +239,8 @@ //=> ['a.b', 'c']
 ```js
-var arr = split('a.b', function(tok) {
-  if (tok.arr[tok.arr.length - 1] === 'a') {
-    tok.split = false;
+var res = split('a.b', function(token) {
+  if (token.tokens[0] === 'a') {
+    token.split = false;
   }
 });
-console.log(arr);
+console.log(res);
 //=> ['a.b']
@@ -249,11 +251,17 @@ ```
 
-The `tok` object has the following properties:
+The `token` object has the following properties:
 
-* `tok.val` (string) The current value about to be pushed onto the result array
-* `tok.idx` (number) the current index in the string
-* `tok.str` (string) the entire string
-* `tok.arr` (array) the result array
+* `token.val` (string) The current value about to be pushed onto the result array
+* `token.index` (number) the current index in the string
+* `token.input` (string) the entire input string
+* `token.tokens` (array) the result array
 
 ## Release history
 
+### v4.0.0 - 2017-11-22
+
+**Changed**
+
+* `options.quotes` should now be formatted as an object
+
 ### v3.0.0 - 2017-06-17
@@ -284,3 +292,2 @@
 </details>
-
 <details>
@@ -312,3 +319,3 @@ <summary><strong>Building docs</strong></summary>
 | --- | --- |
-| 34 | [jonschlinkert](https://github.com/jonschlinkert) |
+| 36 | [jonschlinkert](https://github.com/jonschlinkert) |
 | 10 | [doowb](https://github.com/doowb) |
@@ -320,2 +327,3 @@
 
+* [linkedin/in/jonschlinkert](https://linkedin.com/in/jonschlinkert)
 * [github/jonschlinkert](https://github.com/jonschlinkert)
@@ -326,3 +334,3 @@ * [twitter/jonschlinkert](https://twitter.com/jonschlinkert)
 
-Copyright © 2017, [Jon Schlinkert](https://github.com/jonschlinkert).
+Copyright © 2018, [Jon Schlinkert](https://github.com/jonschlinkert).
 Released under the [MIT License](LICENSE).
@@ -332,2 +340,2 @@
 
-_This file was generated by [verb-generate-readme](https://github.com/verbose/verb-generate-readme), v0.6.0, on November 22, 2017._
+_This file was generated by [verb-generate-readme](https://github.com/verbose/verb-generate-readme), v0.6.0, on January 08, 2018._

New alerts

Major refactor

Supply chain risk

Package has recently undergone a major refactor. It may be unstable or indicate significant internal changes. Use caution when updating to versions that include significant changes.

Found 1 instance in 1 package

Improved metrics

Total package byte prevSize

16272

increased by16%

Lines of code

190

increased by24.18%

Number of lines in readme file

329

increased by2.49%

Worsened metrics

Dependency count

2

increased by100%

Dev dependency count

3

increased by50%

Number of medium supply chain risk alerts

1

increased byInfinity%

Dependency changes

• + Addedarr-union@^3.1.0

• + Addedsnapdragon-lexer@^2.0.0

• + Added@sellside/emitter@1.2.1(transitive)

• + Addedarr-union@3.1.0(transitive)

• + Addedkind-of@6.0.3(transitive)

• + Addedsnapdragon-handlers@1.0.0(transitive)

• + Addedsnapdragon-lexer@2.0.0(transitive)

• + Addedsnapdragon-stack@1.0.1(transitive)

• + Addedsnapdragon-token@3.0.1(transitive)

• + Addeduse@3.1.1(transitive)

• - Removedextend-shallow@^3.0.0

• - Removedassign-symbols@1.0.0(transitive)

• - Removedextend-shallow@3.0.2(transitive)

• - Removedis-extendable@1.0.1(transitive)

• - Removedis-plain-object@2.0.4(transitive)

• - Removedisobject@3.0.1(transitive)