Press n or j to go to the next uncovered block, b, p or k for the previous block.
| 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 | 37x 37x 37x 37x 37x 37x 37x 25x 25x 25x 25x 25x 25x 25x 25x 25x 25x 18x 7x 7x 7x 7x 7x 7x 7x 7x 7x 7x 7x 7x 7x 7x 7x 7x 7x 25x 152x 152x 152x 1x 152x 152x 59x 59x 59x 59x 59x 59x 59x 25x 25x 25x 25x 152x 152x 152x 55x 55x 55x 55x 55x 55x 25x 25x 55x 55x 38x 38x 3x 3x 3x 152x 152x 9x 9x 3x 3x 3x 3x 3x 3x 3x 3x 152x 152x 31x 31x 31x 31x 31x 31x 31x 31x 31x 31x 31x 31x 31x 31x 31x 25x 25x 10x 31x 7x 7x 7x 7x 7x 24x 1x 23x 23x 23x 23x 122x 122x 55x 55x 55x 30x 30x 25x 25x 25x 10x 15x | import { Range } from 'vscode-languageserver-types';
import { XmlParseResult } from './xml-types';
// Inline namespace constants to keep this module dependency-free.
const _RDF = 'http://www.w3.org/1999/02/22-rdf-syntax-ns#';
const _RDFS = 'http://www.w3.org/2000/01/rdf-schema#';
const _OWL = 'http://www.w3.org/2002/07/owl#';
const _SH = 'http://www.w3.org/ns/shacl#';
const _SKOS = 'http://www.w3.org/2004/02/skos/core#';
const _SKOS_XL = 'http://www.w3.org/2008/05/skos-xl#';
// XML NCName character class per the XML Namespaces 1.0 spec:
// letters, digits, hyphens, periods, underscores (and Unicode ranges, approximated by \w).
const _NC_NAME = '[\\w\\-.]';
/**
* A parser for RDF/XML documents that produces an index of namespaces,
* subjects, references and type assertions using a line-based analysis.
*/
export class XmlParser {
/**
* Parses the content of an RDF/XML document.
* @param data The raw XML document text.
* @returns The parsed content data.
*/
parse(data: string): XmlParseResult {
// Comments are not markup: commented-out elements must not be indexed as resources.
const markup = this._blankOutComments(data);
const lines = markup.split('\n');
const result: XmlParseResult = {
namespaces: {},
namespaceDefinitions: {},
subjects: {},
references: {},
typeAssertions: {},
typeDefinitions: {},
textLiteralRanges: []
};
// Parse DOCTYPE for entity definitions
this._parseDoctypeEntities(markup, result);
// Parse namespace definitions and xml:base
this._parseNamespaces(lines, result);
// Parse elements and attributes
this._parseElements(lines, result);
return result;
}
/**
* Replaces the XML comments in a document with spaces. The line breaks are kept, so that
* the ranges of the remaining markup are the same as in the document. A comment that is
* not closed extends to the end of the document.
* @param data The raw XML document text.
* @returns The document text without comments.
*/
private _blankOutComments(data: string): string {
return data.replace(/<!--[\s\S]*?(-->|$)/g, comment => comment.replace(/[^\n]/g, ' '));
}
private _parseDoctypeEntities(data: string, result: XmlParseResult): void {
// Match DOCTYPE section
const doctype = data.match(/<!DOCTYPE[^>]*\[([^\]]*)\]>/s);
if (!doctype) {
return;
}
const lines = data.substring(0, data.indexOf(doctype[0]) + doctype[0].length).split('\n');
const doctypeContent = doctype[1];
const doctypeStartLine = lines.length - doctypeContent.split('\n').length;
// Find ENTITY definitions
const entityRegex = new RegExp(`<!ENTITY\\s+(${_NC_NAME}+)\\s+"([^"]+)">`, 'g');
let match;
while ((match = entityRegex.exec(doctypeContent)) !== null) {
const prefix = match[1];
const namespaceIri = match[2];
// Find line number for this entity
const beforeMatch = doctypeContent.substring(0, match.index);
const lineOffset = beforeMatch.split('\n').length - 1;
const lineNumber = doctypeStartLine + lineOffset;
// Find column position
const lineStart = beforeMatch.lastIndexOf('\n') + 1;
const lineText = doctypeContent.substring(lineStart);
const column = lineText.indexOf(prefix);
result.namespaces[prefix] = namespaceIri;
Eif (!result.namespaceDefinitions[prefix]) {
result.namespaceDefinitions[prefix] = [];
}
result.namespaceDefinitions[prefix].push(Range.create(
lineNumber, column,
lineNumber, column + prefix.length
));
}
}
private _parseNamespaces(lines: string[], result: XmlParseResult): void {
for (let lineNumber = 0; lineNumber < lines.length; lineNumber++) {
const line = lines[lineNumber];
// Check for xml:base attribute
const base = line.match(/xml:base\s*=\s*["']([^"']+)["']/i);
if (base) {
result.baseIri = base[1];
}
// Find xmlns definitions
const xmlnsRegex = new RegExp(`xmlns:(${_NC_NAME}+)\\s*=\\s*["']([^"']+)["']`, 'gi');
let nsMatch;
while ((nsMatch = xmlnsRegex.exec(line)) !== null) {
const prefix = nsMatch[1];
const namespaceIri = nsMatch[2];
const column = nsMatch.index + 6; // "xmlns:" length
result.namespaces[prefix] = namespaceIri;
Eif (!result.namespaceDefinitions[prefix]) {
result.namespaceDefinitions[prefix] = [];
}
result.namespaceDefinitions[prefix].push(Range.create(
lineNumber, column,
lineNumber, column + prefix.length
));
}
}
}
private _parseElements(lines: string[], result: XmlParseResult): void {
// Track element positions for text literal detection
let inElement = false;
let elementEndLine = -1;
let elementEndColumn = -1;
for (let lineNumber = 0; lineNumber < lines.length; lineNumber++) {
const line = lines[lineNumber];
// Find opening tags with prefixes (e.g., <owl:Class, <rdf:Property)
const tagRegex = new RegExp(`<(${_NC_NAME}+):(${_NC_NAME}+)`, 'g');
let tag;
while ((tag = tagRegex.exec(line)) !== null) {
const prefix = tag[1];
const namespaceIri = result.namespaces[prefix];
const localName = tag[2];
const fullName = `${prefix}:${localName}`;
const column = tag.index + 1; // After '<'
if (namespaceIri && !this._isXmlSpecificTagName(prefix, localName, namespaceIri)) {
const iri = namespaceIri + localName;
this._addRangeToIndex(result.references, iri, Range.create(
lineNumber, column,
lineNumber, column + fullName.length
));
}
// Track element end for text literal detection
const tagEnd = line.indexOf('>', tag.index);
if (tagEnd !== -1) {
const isSelfClosing = line[tagEnd - 1] === '/';
if (!isSelfClosing) {
inElement = true;
elementEndLine = lineNumber;
elementEndColumn = tagEnd + 1;
}
}
}
// Find rdf:about, rdf:resource, rdf:datatype attributes
this._parseRdfAttributes(line, lineNumber, result);
// Track text content for literal ranges
if (inElement) {
const closeTagMatch = line.match(new RegExp(`<\\/(${_NC_NAME}+:${_NC_NAME}+)>`));
if (closeTagMatch) {
const textEndColumn = line.indexOf(closeTagMatch[0]);
Eif (textEndColumn > elementEndColumn || lineNumber > elementEndLine) {
// Check if there's actual text content
let hasText = false;
Iif (lineNumber === elementEndLine) {
hasText = line.substring(elementEndColumn, textEndColumn).trim().length > 0;
} else {
hasText = true; // Multi-line content, assume text exists
}
Eif (hasText) {
result.textLiteralRanges.push(Range.create(
elementEndLine, elementEndColumn,
lineNumber, textEndColumn
));
}
}
inElement = false;
}
}
}
}
private _parseRdfAttributes(line: string, lineNumber: number, result: XmlParseResult): void {
// Match rdf:about, rdf:resource, rdf:datatype attributes
const attrRegex = /rdf:(about|resource|datatype)\s*=\s*["']([^"']+)["']/gi;
let attrMatch;
while ((attrMatch = attrRegex.exec(line)) !== null) {
const attrName = attrMatch[1].toLowerCase();
const attrValue = attrMatch[2];
// Find the column where the value starts (inside quotes)
const valueStart = line.indexOf(attrValue, attrMatch.index);
const range = Range.create(
lineNumber, valueStart,
lineNumber, valueStart + attrValue.length
);
const iri = this._getIriFromXmlString(attrValue, result.namespaces, result.baseIri);
Eif (iri) {
this._addRangeToIndex(result.references, iri, range);
Eif (attrName === 'about') {
this._addRangeToIndex(result.subjects, iri, range);
// Check if this is a typed subject (not rdf:Description)
const tag = line.match(new RegExp(`<(${_NC_NAME}+):(${_NC_NAME}+)`));
Eif (tag) {
const tagPrefix = tag[1];
const tagLocal = tag[2];
const tagNamespace = result.namespaces[tagPrefix];
// If the tag is not rdf:Description, we treat the subject as
// having the type of the tag name.
if (tagNamespace !== _RDF && tagLocal !== 'Description') {
this._addRangeToIndex(result.typeAssertions, iri, range);
if (this._isDefinitionNamespace(tagNamespace)) {
this._addRangeToIndex(result.typeDefinitions, iri, range);
}
}
}
}
}
}
}
private _getIriFromXmlString(value: string, namespaces: { [key: string]: string }, baseIri?: string): string | undefined {
if (value.startsWith('&')) {
const prefix = value.trim().split(';')[0].substring(1);
const namespaceIri = namespaces[prefix];
Eif (namespaceIri) {
const localName = value.split(';')[1];
return namespaceIri + localName;
}
}
else if (value.startsWith('#') || !value.includes(':')) {
return baseIri ? baseIri + value : value;
} else Eif (value.length > 0) {
const schemeOrPrefix = value.split(':')[0];
Iif (namespaces[schemeOrPrefix]) {
return namespaces[schemeOrPrefix] + value.split(':')[1];
} else {
return value;
}
}
}
private _addRangeToIndex(index: { [key: string]: Range[] }, iri: string, range: Range): void {
if (!index[iri]) {
index[iri] = [range];
} else E{
index[iri].push(range);
}
}
/**
* Indicates whether an element name belongs to the XML or RDF/XML syntax itself, such as
* `rdf:RDF` or `rdf:Description`, rather than denoting a resource. XML names are
* case-sensitive, so the names are compared as written.
* @param prefix The prefix of the element name.
* @param localName The local name of the element name.
* @param namespaceIri The namespace IRI the prefix is bound to.
*/
private _isXmlSpecificTagName(prefix: string, localName: string, namespaceIri: string): boolean {
const _XML = 'http://www.w3.org/XML/1998/namespace';
Iif (namespaceIri === _XML) {
return true;
}
if (namespaceIri === _RDF) {
switch (localName) {
case 'about':
case 'RDF':
case 'resource':
case 'Description':
case 'datatype':
case 'parseType':
return true;
}
}
return false;
}
private _isDefinitionNamespace(namespaceIri: string | undefined): boolean {
Iif (!namespaceIri) return false;
switch (namespaceIri) {
case _RDF:
case _RDFS:
case _OWL:
case _SKOS:
case _SKOS_XL:
case _SH:
return true;
}
return false;
}
}
|