@bbob/parser - npm Package Compare versions

Comparing version 1.0.5 to 1.0.7

lib/char.js

@@ -14,2 +14,3 @@ const N = '\n'.charCodeAt(0);
 const SLASH = '/'.charCodeAt(0);
+const BACKSLASH = '\\'.charCodeAt(0);
 
@@ -35,2 +36,3 @@ const PLACEHOLDER_SPACE_TAB = '    ';
   PLACEHOLDER_SPACE,
+  BACKSLASH,
 };

lib/Parser.js

@@ -15,10 +15,6 @@ const {
 
-const {
-  SLASH,
-  getChar,
-} = require('./char');
-
 const Tokenizer = require('./Tokenizer');
+const TagNode = require('./TagNode');
 
-const createTagNode = (tag, attrs = {}, content = []) => ({ tag, attrs, content });
+const createTagNode = (tag, attrs = {}, content = []) => new TagNode(tag, attrs, content);
 
@@ -37,7 +33,3 @@ /**
   constructor(input, options = {}) {
-    this.tokenizer = new Tokenizer(input, {
-      onToken: (token) => {
-        this.parseToken(token);
-      },
-    });
+    this.createTokenizer(input);
 
@@ -48,13 +40,24 @@ this.options = options;
     this.nestedNodes = [];
-    this.curTags = [];
-    this.curTagsAttrName = [];
+    this.tagNodes = [];
+    this.tagNodesAttrName = [];
   }
 
-  isNestedTag(token) {
+  createTokenizer(input) {
+    this.tokenizer = new Tokenizer(input, {
+      onToken: (token) => {
+        this.parseToken(token);
+      },
+    });
+  }
+
+  isTagNested(token) {
     return this.tokenizer.isTokenNested(token);
   }
 
-  getCurTag() {
-    if (this.curTags.length) {
-      return this.curTags[this.curTags.length - 1];
+  /**
+   * @return {TagNode}
+   */
+  getTagNode() {
+    if (this.tagNodes.length) {
+      return this.tagNodes[this.tagNodes.length - 1];
     }
@@ -65,29 +68,29 @@
 
-  createCurTag(token) {
-    this.curTags.push(createTagNode(getTokenValue(token)));
+  createTagNode(token) {
+    this.tagNodes.push(createTagNode(getTokenValue(token)));
   }
 
-  createCurTagAttrName(token) {
-    this.curTagsAttrName.push(getTokenValue(token));
+  createTagNodeAttrName(token) {
+    this.tagNodesAttrName.push(getTokenValue(token));
   }
 
-  getCurTagAttrName() {
-    if (this.curTagsAttrName.length) {
-      return this.curTagsAttrName[this.curTagsAttrName.length - 1];
+  getTagNodeAttrName() {
+    if (this.tagNodesAttrName.length) {
+      return this.tagNodesAttrName[this.tagNodesAttrName.length - 1];
     }
 
-    return this.getCurTag().tag;
+    return this.getTagNode().tag;
   }
 
-  clearCurTagAttrName() {
-    if (this.curTagsAttrName.length) {
-      this.curTagsAttrName.pop();
+  clearTagNodeAttrName() {
+    if (this.tagNodesAttrName.length) {
+      this.tagNodesAttrName.pop();
     }
   }
 
-  clearCurTag() {
-    if (this.curTags.length) {
-      this.curTags.pop();
+  clearTagNode() {
+    if (this.tagNodes.length) {
+      this.tagNodes.pop();
 
-      this.clearCurTagAttrName();
+      this.clearTagNodeAttrName();
     }
@@ -111,9 +114,9 @@ }
     if (isTagStart(token)) {
-      this.createCurTag(token);
+      this.createTagNode(token);
 
-      if (this.isNestedTag(token)) {
-        this.nestedNodes.push(this.getCurTag());
+      if (this.isTagNested(token)) {
+        this.nestedNodes.push(this.getTagNode());
       } else {
-        this.appendNode(this.getCurTag());
-        this.clearCurTag();
+        this.appendNode(this.getTagNode());
+        this.clearTagNode();
       }
@@ -125,3 +128,3 @@ }
     if (isTagEnd(token)) {
-      this.clearCurTag();
+      this.clearTagNode();
 
@@ -153,12 +156,14 @@ const lastNestedNode = this.nestedNodes.pop();
 
-  handleCurTag(token) {
-    if (this.getCurTag()) {
+  handleTagNode(token) {
+    const tagNode = this.getTagNode();
+
+    if (tagNode) {
       if (isAttrNameToken(token)) {
-        this.createCurTagAttrName(token);
-        this.getCurTag().attrs[this.getCurTagAttrName()] = null;
+        this.createTagNodeAttrName(token);
+        tagNode.attr(this.getTagNodeAttrName(), null);
       } else if (isAttrValueToken(token)) {
-        this.getCurTag().attrs[this.getCurTagAttrName()] = getTokenValue(token);
-        this.clearCurTagAttrName();
+        tagNode.attr(this.getTagNodeAttrName(), getTokenValue(token));
+        this.clearTagNodeAttrName();
       } else if (isTextToken(token)) {
-        this.getCurTag().content.push(getTokenValue(token));
+        tagNode.append(getTokenValue(token));
       }
@@ -172,3 +177,3 @@ } else if (isTextToken(token)) {
     this.handleTagToken(token);
-    this.handleCurTag(token);
+    this.handleTagNode(token);
   }
@@ -195,20 +200,2 @@
 
-  findNestedTags() {
-    const tags = (this.tokens || []).filter(isTagToken).reduce((acc, token) => {
-      acc[getTokenValue(token)] = true;
-
-      return acc;
-    }, {});
-
-    const closeChar = getChar(SLASH);
-
-    return Object.keys(tags).reduce((arr, key) => {
-      if (tags[key] && tags[closeChar + key]) {
-        arr.push(key);
-      }
-
-      return arr;
-    }, []);
-  }
-
   isAllowedTag(value) {
@@ -223,5 +210,3 @@ if (this.options.onlyAllowTags && this.options.onlyAllowTags.length) {
 
-new Parser('[Verse 2]').parse();
-
 module.exports = Parser;
 module.exports.createTagNode = createTagNode;

lib/Token.js

@@ -25,8 +25,7 @@ const {
 
-const isTextToken = (token) => {
-  const type = token[TOKEN_TYPE_ID];
+const isTextToken = token =>
+  token[TOKEN_TYPE_ID] === TOKEN_TYPE_SPACE ||
+    token[TOKEN_TYPE_ID] === TOKEN_TYPE_NEW_LINE ||
+    token[TOKEN_TYPE_ID] === TOKEN_TYPE_WORD;
 
-  return type === TOKEN_TYPE_SPACE || type === TOKEN_TYPE_NEW_LINE || type === TOKEN_TYPE_WORD;
-};
-
 const isTagToken = token => token[TOKEN_TYPE_ID] === TOKEN_TYPE_TAG;
@@ -65,2 +64,6 @@ const isTagEnd = token => getTokenValue(token).charCodeAt(0) === SLASH;
 
+  isEmpty() {
+    return !!this.type;
+  }
+
   isText() {
@@ -67,0 +70,0 @@ return isTextToken(this);

lib/Tokenizer.js

@@ -7,2 +7,3 @@ const {
   SLASH,
+  BACKSLASH,
 } = require('./char');
@@ -18,7 +19,8 @@ const Token = require('./Token');
     this.rowPos = 0;
-    this.index = 0;
+    // eslint-disable-next-line no-bitwise
+    this.index = 2 ** 32;
 
     this.tokenIndex = -1;
     this.tokens = new Array(Math.floor(this.buffer.length));
-    this.dummyToken = createTokenOfType('', '', '', '');
+    this.dummyToken = null; // createTokenOfType('', '', '', '');
 
@@ -32,2 +34,14 @@ this.wordToken = this.dummyToken;
     this.options = options;
+
+    this.charMap = {
+      [TAB]: this.charSPACE.bind(this),
+      [SPACE]: this.charSPACE.bind(this),
+      [N]: this.charN.bind(this),
+      [OPEN_BRAKET]: this.charOPENBRAKET.bind(this),
+      [CLOSE_BRAKET]: this.charCLOSEBRAKET.bind(this),
+      [EQ]: this.charEQ.bind(this),
+      [QUOTEMARK]: this.charQUOTEMARK.bind(this),
+      [BACKSLASH]: this.charBACKSLASH.bind(this),
+      default: this.charWORD.bind(this),
+    };
   }
@@ -47,2 +61,11 @@
 
+  skipChar(num) {
+    this.index += num;
+    this.colPos += num;
+  }
+
+  seekChar(num) {
+    return this.buffer.charCodeAt(this.index + num);
+  }
+
   nextCol() {
@@ -57,3 +80,3 @@ this.colPos += 1;
   flushWord() {
-    if (this.wordToken[Token.TYPE_ID] && this.wordToken[Token.VALUE_ID]) {
+    if (this.inWord() && this.wordToken[Token.VALUE_ID]) {
       this.appendToken(this.wordToken);
@@ -65,3 +88,3 @@ this.wordToken = this.createWordToken('');
   createWord(value, line, row) {
-    if (this.wordToken[Token.TYPE_ID] === '') {
+    if (!this.inWord()) {
       this.wordToken = this.createWordToken(value, line, row);
@@ -72,6 +95,6 @@ }
   flushTag() {
-    if (this.tagToken[Token.TYPE_ID]) {
+    if (this.inTag()) {
       // [] and [=] tag case
       if (this.tagToken[Token.VALUE_ID] === '') {
-        const value = this.attrValueToken[Token.TYPE_ID] ? getChar(EQ) : '';
+        const value = this.inAttrValue() ? getChar(EQ) : '';
         const word = getChar(OPEN_BRAKET) + value + getChar(CLOSE_BRAKET);
@@ -84,3 +107,3 @@
 
-        if (this.attrValueToken[Token.TYPE_ID]) {
+        if (this.inAttrValue()) {
           this.attrValueToken = this.dummyToken;
@@ -92,3 +115,3 @@ }
 
-      if (this.attrNameToken[Token.TYPE_ID] && !this.attrValueToken[Token.TYPE_ID]) {
+      if (this.inAttrName() && !this.inAttrValue()) {
         this.tagToken[Token.VALUE_ID] += PLACEHOLDER_SPACE + this.attrNameToken[Token.VALUE_ID];
@@ -104,4 +127,4 @@ this.attrNameToken = this.dummyToken;
   flushUnclosedTag() {
-    if (this.tagToken[Token.TYPE_ID]) {
-      const value = this.tagToken[Token.VALUE_ID] + (this.attrValueToken[Token.VALUE_ID] ? getChar(EQ) : '');
+    if (this.inTag()) {
+      const value = this.tagToken[Token.VALUE_ID] + (this.attrValueToken && this.attrValueToken[Token.VALUE_ID] ? getChar(EQ) : '');
 
@@ -115,3 +138,3 @@ this.tagToken[Token.TYPE_ID] = Token.TYPE_WORD;
 
-      if (this.attrValueToken[Token.TYPE_ID]) {
+      if (this.inAttrValue()) {
         this.attrValueToken = this.dummyToken;
@@ -123,3 +146,3 @@ }
   flushAttrNames() {
-    if (this.attrNameToken[Token.TYPE_ID]) {
+    if (this.inAttrName()) {
       this.attrTokens.push(this.attrNameToken);
@@ -129,3 +152,4 @@ this.attrNameToken = this.dummyToken;
 
-    if (this.attrValueToken[Token.TYPE_ID]) {
+    if (this.inAttrValue()) {
+      this.attrValueToken.quoted = undefined;
       this.attrTokens.push(this.attrValueToken);
@@ -144,9 +168,14 @@ this.attrValueToken = this.dummyToken;
   charSPACE(charCode) {
+    const spaceCode = charCode === TAB ? PLACEHOLDER_SPACE_TAB : PLACEHOLDER_SPACE;
+
     this.flushWord();
 
-    if (this.tagToken[Token.TYPE_ID]) {
-      this.attrNameToken = this.createAttrNameToken('');
+    if (this.inTag()) {
+      if (this.inAttrValue() && this.attrValueToken.quoted) {
+        this.attrValueToken[Token.VALUE_ID] += spaceCode;
+      } else {
+        this.flushAttrNames();
+        this.attrNameToken = this.createAttrNameToken('');
+      }
     } else {
-      const spaceCode = charCode === TAB ? PLACEHOLDER_SPACE_TAB : PLACEHOLDER_SPACE;
-
       this.appendToken(this.createSpaceToken(spaceCode));
@@ -173,12 +202,19 @@ }
   charCLOSEBRAKET() {
+    this.nextCol();
     this.flushTag();
     this.flushAttrNames();
     this.flushAttrs();
-
-    this.nextCol();
   }
 
   charEQ(charCode) {
-    if (this.tagToken[Token.TYPE_ID]) {
+    const nextCharCode = this.seekChar(1);
+    const isNextQuotemark = nextCharCode === QUOTEMARK;
+
+    if (this.inTag()) {
       this.attrValueToken = this.createAttrValueToken('');
+
+      if (isNextQuotemark) {
+        this.attrValueToken.quoted = true;
+        this.skipChar(1);
+      }
     } else {
@@ -192,5 +228,11 @@ this.wordToken[Token.VALUE_ID] += getChar(charCode);
   charQUOTEMARK(charCode) {
-    if (this.attrValueToken[Token.TYPE_ID] && this.attrValueToken[Token.VALUE_ID] > 0) {
+    const prevCharCode = this.seekChar(-1);
+    const isPrevBackslash = prevCharCode === BACKSLASH;
+
+    if (this.inAttrValue() &&
+        this.attrValueToken[Token.VALUE_ID] &&
+        this.attrValueToken.quoted &&
+        !isPrevBackslash) {
       this.flushAttrNames();
-    } else if (this.tagToken[Token.TYPE_ID] === '') {
+    } else if (!this.inTag()) {
       this.wordToken[Token.VALUE_ID] += getChar(charCode);
@@ -202,9 +244,27 @@ }
 
+  charBACKSLASH() {
+    const nextCharCode = this.seekChar(1);
+    const isNextQuotemark = nextCharCode === QUOTEMARK;
+
+    if (this.inAttrValue() &&
+        this.attrValueToken[Token.VALUE_ID] &&
+        this.attrValueToken.quoted &&
+        isNextQuotemark
+    ) {
+      this.attrValueToken[Token.VALUE_ID] += getChar(nextCharCode);
+      this.skipChar(1);
+    }
+
+    this.nextCol();
+  }
+
   charWORD(charCode) {
-    if (this.tagToken[Token.TYPE_ID] && this.attrValueToken[Token.TYPE_ID]) {
-      this.attrValueToken[Token.VALUE_ID] += getChar(charCode);
-    } else if (this.tagToken[Token.TYPE_ID] && this.attrNameToken[Token.TYPE_ID]) {
-      this.attrNameToken[Token.VALUE_ID] += getChar(charCode);
-    } else if (this.tagToken[Token.TYPE_ID]) {
-      this.tagToken[Token.VALUE_ID] += getChar(charCode);
+    if (this.inTag()) {
+      if (this.inAttrValue()) {
+        this.attrValueToken[Token.VALUE_ID] += getChar(charCode);
+      } else if (this.inAttrName()) {
+        this.attrNameToken[Token.VALUE_ID] += getChar(charCode);
+      } else {
+        this.tagToken[Token.VALUE_ID] += getChar(charCode);
+      }
     } else {
@@ -220,37 +280,10 @@ this.createWord();
   tokenize() {
+    this.index = 0;
     while (this.index < this.buffer.length) {
       const charCode = this.buffer.charCodeAt(this.index);
 
-      switch (charCode) {
-        case TAB:
-        case SPACE:
-          this.charSPACE(charCode);
-          break;
+      (this.charMap[charCode] || this.charMap.default)(charCode);
 
-        case N:
-          this.charN(charCode);
-          break;
-
-        case OPEN_BRAKET:
-          this.charOPENBRAKET();
-          break;
-
-        case CLOSE_BRAKET:
-          this.charCLOSEBRAKET();
-          break;
-
-        case EQ:
-          this.charEQ(charCode);
-          break;
-
-        case QUOTEMARK:
-          this.charQUOTEMARK(charCode);
-          break;
-
-        default:
-          this.charWORD(charCode);
-          break;
-      }
-
-      this.index += 1;
+      // eslint-disable-next-line no-plusplus
+      ++this.index;
     }
@@ -266,2 +299,18 @@
 
+  inWord() {
+    return this.wordToken && this.wordToken[Token.TYPE_ID];
+  }
+
+  inTag() {
+    return this.tagToken && this.tagToken[Token.TYPE_ID];
+  }
+
+  inAttrValue() {
+    return this.attrValueToken && this.attrValueToken[Token.TYPE_ID];
+  }
+
+  inAttrName() {
+    return this.attrNameToken && this.attrNameToken[Token.TYPE_ID];
+  }
+
   createWordToken(value = '', line = this.colPos, row = this.rowPos) {
@@ -297,5 +346,2 @@ return createTokenOfType(Token.TYPE_WORD, value, line, row);
 
-// warm up tokenizer to elimitate code branches that never execute
-new Tokenizer('[b param="hello"]Sample text[/b]\n\t[Chorus 2] x html([a. title][, alt][, classes]) x [=] [/y]').tokenize();
-
 module.exports = Tokenizer;
@@ -302,0 +348,0 @@ module.exports.createTokenOfType = createTokenOfType;

package.json

 {
   "name": "@bbob/parser",
-  "version": "1.0.5",
+  "version": "1.0.7",
   "description": "Fast, flexible, and lean implementation of BBcode parser",
@@ -21,3 +21,4 @@ "homepage": "https://github.com/JiLiZART/bbob",
   ],
-  "main": "./lib/index.js",
+  "main": "lib/index.js",
+  "browser": "dist/umd.js",
   "repository": {
@@ -28,2 +29,4 @@ "type": "git",
   "scripts": {
+    "build": "../../node_modules/.bin/rollup -c",
+    "dev": "../../node_modules/.bin/rollup -c -w",
     "test": "../../node_modules/.bin/jest --",
@@ -38,3 +41,5 @@ "cover": "../../node_modules/.bin/jest --coverage",
   },
-  "files": ["lib"]
+  "files": [
+    "lib"
+  ]
 }

README.md

@@ -1,2 +0,15 @@
-# bbob-parser
-Fast BB Code parser written in pure javascript, no dependencies
+# @bbob/parser
+
+Parses BBCode and returns AST Tree looks like
+
+```json
+[
+    {
+        tag: 'url',
+        attrs: {
+            url: 'https://github.com/JiLiZART/bbob/tree/master/packages/bbob-parser'
+        },
+        content: ['hello', ' ', 'world!']
+    }
+]
+```

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

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

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

40554

increased by137.92%

Number of package files

10

increased by25%

Lines of code

1292

increased by136.2%

Number of lines in readme file

16

increased by433.33%

Worsened metrics

Number of medium supply chain risk alerts

1

increased byInfinity%

No dependency changes