@markuplint/html-parser - npm Package Compare versions

Comparing version 1.2.0 to 1.3.0

lib/attr-tokenizer.js

 "use strict";
 Object.defineProperty(exports, "__esModule", { value: true });
-const ml_ast_1 = require("@markuplint/ml-ast");
+const parser_utils_1 = require("@markuplint/parser-utils");
 // eslint-disable-next-line no-control-regex
@@ -21,35 +21,35 @@ const reAttrsInStartTag = /(\s*)([^\x00-\x1f\x7f-\x9f "'>/=]+)(?:(\s*)(=)(\s*)(?:(?:"([^"]*)")|(?:'([^']*)')|([^\s]*)))?/;
     let offset = startOffset;
-    const attrToken = ml_ast_1.tokenizer(raw, line, col, offset);
+    const attrToken = parser_utils_1.tokenizer(raw, line, col, offset);
     line = attrToken.startLine;
     col = attrToken.startCol;
     offset = attrToken.startOffset;
-    const spacesBeforeName = ml_ast_1.tokenizer(spacesBeforeAttrString, line, col, offset);
+    const spacesBeforeName = parser_utils_1.tokenizer(spacesBeforeAttrString, line, col, offset);
     line = spacesBeforeName.endLine;
     col = spacesBeforeName.endCol;
     offset = spacesBeforeName.endOffset;
-    const name = ml_ast_1.tokenizer(nameChars, line, col, offset);
+    const name = parser_utils_1.tokenizer(nameChars, line, col, offset);
     line = name.endLine;
     col = name.endCol;
     offset = name.endOffset;
-    const spacesBeforeEqual = ml_ast_1.tokenizer(spacesBeforeEqualChars, line, col, offset);
+    const spacesBeforeEqual = parser_utils_1.tokenizer(spacesBeforeEqualChars, line, col, offset);
     line = spacesBeforeEqual.endLine;
     col = spacesBeforeEqual.endCol;
     offset = spacesBeforeEqual.endOffset;
-    const equal = ml_ast_1.tokenizer(equalChars, line, col, offset);
+    const equal = parser_utils_1.tokenizer(equalChars, line, col, offset);
     line = equal.endLine;
     col = equal.endCol;
     offset = equal.endOffset;
-    const spacesAfterEqual = ml_ast_1.tokenizer(spacesAfterEqualChars, line, col, offset);
+    const spacesAfterEqual = parser_utils_1.tokenizer(spacesAfterEqualChars, line, col, offset);
     line = spacesAfterEqual.endLine;
     col = spacesAfterEqual.endCol;
     offset = spacesAfterEqual.endOffset;
-    const startQuote = ml_ast_1.tokenizer(quoteChars, line, col, offset);
+    const startQuote = parser_utils_1.tokenizer(quoteChars, line, col, offset);
     line = startQuote.endLine;
     col = startQuote.endCol;
     offset = startQuote.endOffset;
-    const value = ml_ast_1.tokenizer(valueChars, line, col, offset);
+    const value = parser_utils_1.tokenizer(valueChars, line, col, offset);
     line = value.endLine;
     col = value.endCol;
     offset = value.endOffset;
-    const endQuote = ml_ast_1.tokenizer(quoteChars, line, col, offset);
+    const endQuote = parser_utils_1.tokenizer(quoteChars, line, col, offset);
     line = endQuote.endLine;
@@ -60,3 +60,3 @@ col = endQuote.endCol;
         type: 'html-attr',
-        uuid: ml_ast_1.uuid(),
+        uuid: parser_utils_1.uuid(),
         raw: attrToken.raw,
@@ -63,0 +63,0 @@ startOffset: attrToken.startOffset,

lib/flatten-nodes.js

@@ -8,61 +8,7 @@ "use strict";
 const ml_ast_1 = require("@markuplint/ml-ast");
+const parser_utils_1 = require("@markuplint/parser-utils");
 const remove_deprecated_node_1 = require("./remove-deprecated-node");
 const tag_splitter_1 = __importDefault(require("./tag-splitter"));
 function flattenNodes(nodeTree, rawHtml) {
-    const nodeOrders = [];
-    let prevLine = 1;
-    let prevCol = 1;
-    let currentStartOffset = 0;
-    let currentEndOffset = 0;
-    /**
-     * pushing list
-     */
-    ml_ast_1.walk(nodeTree, node => {
-        currentStartOffset = node.startOffset;
-        const diff = currentStartOffset - currentEndOffset;
-        if (diff > 0) {
-            const html = rawHtml.slice(currentEndOffset, currentStartOffset);
-            /**
-             * first white spaces
-             */
-            if (/^\s+$/.test(html)) {
-                const spaces = html;
-                const textNode = {
-                    uuid: ml_ast_1.uuid(),
-                    raw: spaces,
-                    startOffset: currentEndOffset,
-                    endOffset: currentEndOffset + spaces.length,
-                    startLine: prevLine,
-                    endLine: ml_ast_1.getEndLine(spaces, prevLine),
-                    startCol: prevCol,
-                    endCol: ml_ast_1.getEndCol(spaces, prevCol),
-                    nodeName: '#text',
-                    type: ml_ast_1.MLASTNodeType.Text,
-                    parentNode: node.parentNode,
-                    prevNode: node.prevNode,
-                    nextNode: node,
-                    isFragment: false,
-                    isGhost: false,
-                };
-                node.prevNode = textNode;
-                if (node.parentNode && node.parentNode.childNodes) {
-                    node.parentNode.childNodes.unshift(textNode);
-                }
-                nodeOrders.push(textNode);
-            }
-            else if (/^<\/[a-z0-9][a-z0-9:-]*>$/i.test(html)) {
-                // close tag
-            }
-            else {
-                // never
-            }
-        }
-        currentEndOffset = currentStartOffset + node.raw.length;
-        prevLine = node.endLine;
-        prevCol = node.endCol;
-        // for ghost nodes
-        node.startOffset = node.startOffset || currentStartOffset;
-        node.endOffset = node.endOffset || currentEndOffset;
-        nodeOrders.push(node);
-    });
+    const nodeOrders = arrayize(nodeTree, rawHtml);
     {
@@ -96,5 +42,5 @@ /**
                         prevWreckagesText.startLine = startLine;
-                        prevWreckagesText.endLine = ml_ast_1.getEndLine(raw, startLine);
+                        prevWreckagesText.endLine = parser_utils_1.getEndLine(raw, startLine);
                         prevWreckagesText.startCol = startCol;
-                        prevWreckagesText.endCol = ml_ast_1.getEndCol(raw, startCol);
+                        prevWreckagesText.endCol = parser_utils_1.getEndCol(raw, startCol);
                     }
@@ -145,3 +91,3 @@ }
                     const lastTextNode = {
-                        uuid: ml_ast_1.uuid(),
+                        uuid: parser_utils_1.uuid(),
                         raw: lastTextContent,
@@ -151,5 +97,5 @@ startOffset: lastOffset,
                         startLine: line,
-                        endLine: ml_ast_1.getEndLine(lastTextContent, line),
+                        endLine: parser_utils_1.getEndLine(lastTextContent, line),
                         startCol: col,
-                        endCol: ml_ast_1.getEndCol(lastTextContent, col),
+                        endCol: parser_utils_1.getEndCol(lastTextContent, col),
                         nodeName: '#text',
@@ -242,1 +188,60 @@ type: ml_ast_1.MLASTNodeType.Text,
 exports.flattenNodes = flattenNodes;
+function arrayize(nodeTree, rawHtml) {
+    const nodeOrders = [];
+    let prevLine = 1;
+    let prevCol = 1;
+    let currentStartOffset = 0;
+    let currentEndOffset = 0;
+    /**
+     * pushing list
+     */
+    parser_utils_1.walk(nodeTree, node => {
+        currentStartOffset = node.startOffset;
+        const diff = currentStartOffset - currentEndOffset;
+        if (diff > 0) {
+            const html = rawHtml.slice(currentEndOffset, currentStartOffset);
+            /**
+             * first white spaces
+             */
+            if (/^\s+$/.test(html)) {
+                const spaces = html;
+                const textNode = {
+                    uuid: parser_utils_1.uuid(),
+                    raw: spaces,
+                    startOffset: currentEndOffset,
+                    endOffset: currentEndOffset + spaces.length,
+                    startLine: prevLine,
+                    endLine: parser_utils_1.getEndLine(spaces, prevLine),
+                    startCol: prevCol,
+                    endCol: parser_utils_1.getEndCol(spaces, prevCol),
+                    nodeName: '#text',
+                    type: ml_ast_1.MLASTNodeType.Text,
+                    parentNode: node.parentNode,
+                    prevNode: node.prevNode,
+                    nextNode: node,
+                    isFragment: false,
+                    isGhost: false,
+                };
+                node.prevNode = textNode;
+                if (node.parentNode && node.parentNode.childNodes) {
+                    node.parentNode.childNodes.unshift(textNode);
+                }
+                nodeOrders.push(textNode);
+            }
+            else if (/^<\/[a-z0-9][a-z0-9:-]*>$/i.test(html)) {
+                // close tag
+            }
+            else {
+                // never
+            }
+        }
+        currentEndOffset = currentStartOffset + node.raw.length;
+        prevLine = node.endLine;
+        prevCol = node.endCol;
+        // for ghost nodes
+        node.startOffset = node.startOffset || currentStartOffset;
+        node.endOffset = node.endOffset || currentEndOffset;
+        nodeOrders.push(node);
+    });
+    return nodeOrders;
+}

lib/parse-raw-tag.js

@@ -6,5 +6,5 @@ "use strict";
 Object.defineProperty(exports, "__esModule", { value: true });
-const ml_ast_1 = require("@markuplint/ml-ast");
 const const_1 = require("./const");
 const attr_tokenizer_1 = __importDefault(require("./attr-tokenizer"));
+const parser_utils_1 = require("@markuplint/parser-utils");
 // eslint-disable-next-line no-control-regex
@@ -47,7 +47,7 @@ const reAttrsInStartTag = /\s*[^\x00-\x1f\x7f-\x9f "'>/=]+(?:\s*=\s*(?:(?:"[^"]*")|(?:'[^']*')|[^\s]*))?/;
     const endTokens = reEndTokens.exec(raw);
-    const selfClosingSolidus = ml_ast_1.tokenizer(endTokens && endTokens[1], line, col, offset);
+    const selfClosingSolidus = parser_utils_1.tokenizer(endTokens && endTokens[1], line, col, offset);
     line = selfClosingSolidus.endLine;
     col = selfClosingSolidus.endCol;
     offset = selfClosingSolidus.endOffset;
-    const endSpace = ml_ast_1.tokenizer(endTokens && endTokens[2], line, col, offset);
+    const endSpace = parser_utils_1.tokenizer(endTokens && endTokens[2], line, col, offset);
     return {
@@ -54,0 +54,0 @@ tagName,

lib/parse.d.ts

@@ -1,2 +0,2 @@
-import { Parse } from '@markuplint/ml-ast';
+import type { Parse } from '@markuplint/ml-ast';
 export declare const parse: Parse;

lib/parse.js

@@ -7,9 +7,6 @@ "use strict";
 exports.parse = void 0;
-const ml_ast_1 = require("@markuplint/ml-ast");
+const create_tree_1 = require("./create-tree");
 const flatten_nodes_1 = require("./flatten-nodes");
 const parser_utils_1 = require("@markuplint/parser-utils");
 const is_document_fragment_1 = __importDefault(require("./is-document-fragment"));
-const parse5_1 = __importDefault(require("parse5"));
-const parse_raw_tag_1 = __importDefault(require("./parse-raw-tag"));
-const P5_OPTIONS = { sourceCodeLocationInfo: true };
 const parse = (rawCode, offsetOffset = 0, offsetLine = 0, offsetColumn = 0, isIgnoringFrontMatter) => {
@@ -20,6 +17,4 @@ if (isIgnoringFrontMatter) {
     const isFragment = is_document_fragment_1.default(rawCode);
-    const doc = isFragment
-        ? parse5_1.default.parseFragment(rawCode, P5_OPTIONS)
-        : parse5_1.default.parse(rawCode, P5_OPTIONS);
-    const nodeList = flatten_nodes_1.flattenNodes(traverse(doc, null, rawCode, offsetOffset, offsetLine, offsetColumn), rawCode);
+    const nodeTree = create_tree_1.createTree(rawCode, isFragment, offsetOffset, offsetLine, offsetColumn);
+    const nodeList = flatten_nodes_1.flattenNodes(nodeTree, rawCode);
     return {
@@ -31,219 +26,1 @@ nodeList,
 exports.parse = parse;
-function traverse(rootNode, parentNode, rawHtml, offsetOffset, offsetLine, offsetColumn) {
-    const nodeList = [];
-    const childNodes = getChildNodes(rootNode);
-    let prevNode = null;
-    for (const p5node of childNodes) {
-        const node = nodeize(p5node, prevNode, parentNode, rawHtml, offsetOffset, offsetLine, offsetColumn);
-        if (!node) {
-            continue;
-        }
-        if (prevNode) {
-            if (node.type !== ml_ast_1.MLASTNodeType.EndTag) {
-                prevNode.nextNode = node;
-            }
-            node.prevNode = prevNode;
-        }
-        prevNode = node;
-        nodeList.push(node);
-    }
-    return nodeList;
-}
-function nodeize(originNode, prevNode, parentNode, rawHtml, offsetOffset, offsetLine, offsetColumn) {
-    const nextNode = null;
-    if (!originNode.sourceCodeLocation) {
-        const prevToken = prevNode || parentNode;
-        const startOffset = prevToken ? prevToken.endOffset : 0;
-        const endOffset = prevToken ? prevToken.endOffset : 0;
-        const startLine = prevToken ? prevToken.endLine : 0;
-        const endLine = prevToken ? prevToken.endLine : 0;
-        const startCol = prevToken ? prevToken.endCol : 0;
-        const endCol = prevToken ? prevToken.endCol : 0;
-        const node = {
-            uuid: ml_ast_1.uuid(),
-            raw: '',
-            startOffset: startOffset + offsetOffset,
-            endOffset: endOffset + offsetOffset,
-            startLine: startLine + offsetLine,
-            endLine: endLine + offsetLine,
-            startCol: startCol + (startLine === 1 ? offsetColumn : 0),
-            endCol: endCol + (endLine === 1 ? offsetColumn : 0),
-            nodeName: originNode.nodeName,
-            type: ml_ast_1.MLASTNodeType.OmittedTag,
-            namespace: originNode.namespaceURI,
-            parentNode,
-            prevNode,
-            nextNode,
-            isFragment: false,
-            isGhost: true,
-        };
-        node.childNodes = traverse(originNode, node, rawHtml, offsetOffset, offsetLine, offsetColumn);
-        return node;
-    }
-    const { startOffset, endOffset, startLine, endLine, startCol, endCol } = originNode.sourceCodeLocation;
-    const raw = rawHtml.slice(startOffset, endOffset || startOffset);
-    switch (originNode.nodeName) {
-        case '#documentType': {
-            return {
-                uuid: ml_ast_1.uuid(),
-                raw,
-                // @ts-ignore
-                name: originNode.name || '',
-                // @ts-ignore
-                publicId: originNode.publicId || '',
-                // @ts-ignore
-                systemId: originNode.systemId || '',
-                startOffset: startOffset + offsetOffset,
-                endOffset: endOffset + offsetOffset,
-                startLine: startLine + offsetLine,
-                endLine: endLine + offsetLine,
-                startCol: startCol + (startLine === 1 ? offsetColumn : 0),
-                endCol: endCol + (endLine === 1 ? offsetColumn : 0),
-                nodeName: '#doctype',
-                type: ml_ast_1.MLASTNodeType.Doctype,
-                parentNode,
-                prevNode,
-                _addPrevNode: 102,
-                nextNode,
-                isFragment: false,
-                isGhost: false,
-            };
-        }
-        case '#text': {
-            const node = {
-                uuid: ml_ast_1.uuid(),
-                raw,
-                startOffset: startOffset + offsetOffset,
-                endOffset: endOffset + offsetOffset,
-                startLine: startLine + offsetLine,
-                endLine: endLine + offsetLine,
-                startCol: startCol + (startLine === 1 ? offsetColumn : 0),
-                endCol: endCol + (endLine === 1 ? offsetColumn : 0),
-                nodeName: '#text',
-                type: ml_ast_1.MLASTNodeType.Text,
-                parentNode,
-                prevNode,
-                nextNode,
-                isFragment: false,
-                isGhost: false,
-            };
-            return node;
-        }
-        case '#comment': {
-            return {
-                uuid: ml_ast_1.uuid(),
-                raw,
-                startOffset: startOffset + offsetOffset,
-                endOffset: endOffset + offsetOffset,
-                startLine: startLine + offsetLine,
-                endLine: endLine + offsetLine,
-                startCol: startCol + (startLine === 1 ? offsetColumn : 0),
-                endCol: endCol + (endLine === 1 ? offsetColumn : 0),
-                nodeName: '#comment',
-                type: ml_ast_1.MLASTNodeType.Comment,
-                parentNode,
-                prevNode,
-                nextNode,
-                isFragment: false,
-                isGhost: false,
-            };
-        }
-        default: {
-            const tagLoc = originNode.sourceCodeLocation.startTag;
-            const startTagRaw = originNode.sourceCodeLocation.startTag
-                ? rawHtml.slice(tagLoc.startOffset, tagLoc.endOffset)
-                : rawHtml.slice(startOffset, endOffset || startOffset);
-            const tagTokens = parse_raw_tag_1.default(startTagRaw, startLine, startCol, startOffset, offsetOffset, offsetLine, offsetColumn);
-            const tagName = tagTokens.tagName;
-            let endTag = null;
-            const endTagLoc = originNode.sourceCodeLocation.endTag;
-            if (endTagLoc) {
-                const { startOffset, endOffset, startLine, endLine, startCol, endCol } = endTagLoc;
-                const endTagRaw = rawHtml.slice(startOffset, endOffset);
-                const endTagTokens = parse_raw_tag_1.default(endTagRaw, startLine, startCol, startOffset, offsetOffset, offsetLine, offsetColumn);
-                const endTagName = endTagTokens.tagName;
-                endTag = {
-                    uuid: ml_ast_1.uuid(),
-                    raw: endTagRaw,
-                    startOffset: startOffset + offsetOffset,
-                    endOffset: endOffset + offsetOffset,
-                    startLine: startLine + offsetLine,
-                    endLine: endLine + offsetLine,
-                    startCol: startCol + (startLine === 1 ? offsetColumn : 0),
-                    endCol: endCol + (endLine === 1 ? offsetColumn : 0),
-                    nodeName: endTagName,
-                    type: ml_ast_1.MLASTNodeType.EndTag,
-                    namespace: originNode.namespaceURI,
-                    attributes: endTagTokens.attrs,
-                    parentNode,
-                    prevNode,
-                    nextNode,
-                    pearNode: null,
-                    isFragment: false,
-                    isGhost: false,
-                    tagOpenChar: '</',
-                    tagCloseChar: '>',
-                };
-            }
-            const _endOffset = startOffset + startTagRaw.length;
-            const _endLine = ml_ast_1.getEndLine(startTagRaw, startLine);
-            const _endCol = ml_ast_1.getEndCol(startTagRaw, startCol);
-            const startTag = {
-                uuid: ml_ast_1.uuid(),
-                raw: startTagRaw,
-                startOffset: startOffset + offsetOffset,
-                endOffset: _endOffset + offsetOffset,
-                startLine: startLine + offsetLine,
-                endLine: _endLine + offsetLine,
-                startCol: startCol + (startLine === 1 ? offsetColumn : 0),
-                endCol: _endCol + (startLine === _endLine ? offsetColumn : 0),
-                nodeName: tagName,
-                type: ml_ast_1.MLASTNodeType.StartTag,
-                namespace: originNode.namespaceURI,
-                attributes: tagTokens.attrs,
-                parentNode,
-                prevNode,
-                nextNode,
-                pearNode: endTag,
-                selfClosingSolidus: tagTokens.selfClosingSolidus,
-                endSpace: tagTokens.endSpace,
-                isFragment: false,
-                isGhost: false,
-                tagOpenChar: '<',
-                tagCloseChar: '>',
-            };
-            if (endTag) {
-                endTag.pearNode = startTag;
-            }
-            startTag.childNodes = traverse(originNode, startTag, rawHtml, offsetOffset, offsetLine, offsetColumn);
-            return startTag;
-        }
-    }
-}
-/**
- * getChildNodes
- *
- * - If node has "content" property then parse as document fragment.
- * - If node is <noscript> then that childNodes is a TextNode. But parse as document fragment it for disabled script.
- */
-function getChildNodes(rootNode) {
-    if (rootNode.nodeName === 'noscript') {
-        const textNode = rootNode.childNodes[0];
-        if (!textNode || textNode.nodeName !== '#text') {
-            return [];
-        }
-        // @ts-ignore
-        const html = textNode.value;
-        // @ts-ignore
-        const { startOffset, startLine, startCol } = rootNode.sourceCodeLocation;
-        const breakCount = startLine - 1;
-        const indentWidth = startCol - 1;
-        const spaces = ' '.repeat(startOffset - Math.max(breakCount, 0) - Math.max(indentWidth, 0)) +
-            '\n'.repeat(breakCount) +
-            ' '.repeat(indentWidth);
-        const fragment = parse5_1.default.parseFragment(`${spaces}<x-script>${html}</x-script>`, P5_OPTIONS);
-        const childNodes = fragment.childNodes[spaces ? 1 : 0].childNodes;
-        return childNodes;
-    }
-    return rootNode.content ? rootNode.content.childNodes : rootNode.childNodes;
-}

lib/tag-splitter.js

 "use strict";
 Object.defineProperty(exports, "__esModule", { value: true });
-const ml_ast_1 = require("@markuplint/ml-ast");
+const parser_utils_1 = require("@markuplint/parser-utils");
 const const_1 = require("./const");
@@ -88,6 +88,6 @@ function tagSplitter(raw, line, col) {
         }
-        line = ml_ast_1.getEndLine(node, line);
-        col = ml_ast_1.getEndCol(node, col);
+        line = parser_utils_1.getEndLine(node, line);
+        col = parser_utils_1.getEndCol(node, col);
     }
     return result;
 }

package.json

 {
 	"name": "@markuplint/html-parser",
-	"version": "1.2.0",
+	"version": "1.3.0",
 	"description": "HTML parser for markuplint",
@@ -20,10 +20,10 @@ "repository": "[e-mail]:markuplint/markuplint.git",
 	"devDependencies": {
-		"@types/parse5": "^5.0.3"
+		"@types/parse5": "^6.0.0"
 	},
 	"dependencies": {
-		"@markuplint/ml-ast": "^1.2.0",
-		"@markuplint/parser-utils": "^1.1.0",
+		"@markuplint/ml-ast": "^1.3.0",
+		"@markuplint/parser-utils": "^1.2.0",
 		"parse5": "^6.0.1"
 	},
-	"gitHead": "1806f99b6429b73ce498f6ecf641efc2400f47dd"
+	"gitHead": "15e11fd74042d8b378387644d36cd882962a9ec8"
 }

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

Number of package files

27

increased by8%

Lines of code

974

increased by3.95%

Worsened metrics

Total package byte prevSize

194024

decreased by-29.6%

Dependency changes

• Updated@markuplint/ml-ast@^1.3.0

• Updated@markuplint/parser-utils@^1.2.0