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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 | 60x 266x 266x 266x 508x 508x 2x 506x 24x 482x 144x 338x 12x 326x 69x 41x 266x 266x 266x 983x 983x 983x 2x 981x 379x 602x 264x 52x 52x 5x 5x 1x 4x 1x 3x 3x 3x 3x 3x 3x 2x 1x 22x 22x 12x 12x 12x 10x 9266x 9266x 9266x 9266x 9266x 9266x 9266x 62x 51x 11x 8x 3x 1x 888x 888x 886x 2x 88x 1346x 1346x 2x 1344x 1344x 21x 1323x 1323x 30x 30x 30x 272x 1x 271x 271x 3x 268x 268x 1x 267x 267x 1x 266x 266x 266x 50x 46x 3x 1x 41x 1x 40x 40x 12x 1x 2x 12x 6x 6x 4x 2x 6x 6x 5x 1x 20x 20x 1x 19x 12x 6x 1x | /**
* Note: Do not add import from 'vscode' here. This file is used in the
* language server where vscode is not available.
*/
import { RDF } from "@faubulous/mentor-rdf";
import { IToken, RdfToken } from "@faubulous/mentor-rdf-parsers";
import { Range } from "vscode-languageserver-types";
import { countLeadingWhitespace, countTrailingWhitespace } from "./string";
/**
* A zero-based position in a document (compatible with `vscode.Position` and LSP `Position`).
*/
export interface TokenPosition {
line: number;
character: number;
}
/**
* Maps namespace IRIs to prefixes.
*/
export interface NamespaceMap {
[key: string]: string;
}
/**
* Maps namespace prefixes to IRIs.
*/
export interface PrefixMap {
[key: string]: string;
}
/**
* A tuple of a namespace prefix and an associated IRI.
*/
export interface PrefixDefinition {
prefix: string;
uri: string;
}
/**
* Gets the position of a token in a document.
* @param token A token.
* @returns The position of the token.
*/
export function getTokenPosition(token: IToken): Range {
return {
start: {
line: token.startLine ? token.startLine - 1 : 0,
character: token.startColumn ? token.startColumn - 1 : 0,
},
end: {
line: token.endLine ? token.endLine - 1 : 0,
character: token.endColumn ? token.endColumn : 0
}
};
}
/**
* Gets the index of the token at a given position.
* @param tokens The document tokens.
* @param position A zero-based position in the document (e.g. a vscode.Position or LSP Position).
* @returns The index of the token at the given position, or -1 if no token is found.
*/
export function getTokenIndexAtPosition(tokens: IToken[], position: { line: number; character: number }): number {
// The tokens are 1-based, but the position is 0-based.
const l = position.line + 1;
const n = position.character;
for (let i = _getFirstTokenIndexEndingOnOrAfterLine(tokens, l); i < tokens.length; i++) {
const token = tokens[i];
if (!token.startLine || !token.endLine || !token.startColumn || !token.endColumn) {
continue;
}
if (token.startLine > l) {
break;
}
// If the token starts and ends on the same line and column, then the position must be inside the token.
if (token.startLine == l && token.endLine == l && token.startColumn <= n && n <= token.endColumn) {
return i;
}
// If we have a multi-line token and the position is between start and end, then we have a match.
if (token.startLine < l && token.endLine > l) {
return i;
}
// If the token ends on the same line and the position is before the end column, then we have a match.
if (token.endLine == l && token.endColumn >= n) {
return i;
}
}
return -1;
}
/**
* Gets the index of the first token that ends on or after the given line, by binary search
* over tokens in document order. The tokens before it cannot contain a position on that
* line, so a search for a position can start there instead of at the first token.
* @param tokens The document tokens, in document order.
* @param line A one-based line number.
* @returns The index to start the search at.
*/
function _getFirstTokenIndexEndingOnOrAfterLine(tokens: IToken[], line: number): number {
let low = 0;
let high = tokens.length;
while (low < high) {
const middle = (low + high) >>> 1;
const endLine = tokens[middle].endLine;
// Without a position the order cannot be decided; the search continues linearly from here.
if (!endLine) {
return low;
}
if (endLine < line) {
low = middle + 1;
} else {
high = middle;
}
}
return low;
}
/**
* Gets the first token at a given position.
* @param tokens The document tokens.
* @param position A zero-based position in the document.
* @returns The token at the given position, if it exists, undefined otherwise.
*/
export function getTokenAtPosition(tokens: IToken[], position: TokenPosition): IToken | undefined {
const index = getTokenIndexAtPosition(tokens, position);
return index >= 0 ? tokens[index] : undefined;
}
/**
* Gets the token that precedes the given position.
* @param tokens The document tokens.
* @param position A zero-based position in the document.
* @returns The token before the given position, if it exists, undefined otherwise.
*/
export function getTokenBeforePosition(tokens: IToken[], position: TokenPosition): IToken | undefined {
const index = getTokenIndexAtPosition(tokens, position);
if (index > 0) {
// Found token at position, return previous one
return tokens[index - 1];
} else if (index === 0) {
// At first token, no previous token
return undefined;
} else {
// No token at position (index === -1), find last token before this position
const l = position.line + 1;
const n = position.character;
for (let i = tokens.length - 1; i >= 0; i--) {
const token = tokens[i];
Iif (!token.endLine || !token.endColumn) continue;
// If token ends before the cursor position, it's the one we want
if (token.endLine < l || (token.endLine === l && token.endColumn <= n)) {
return token;
}
}
}
return undefined;
}
/**
* Indicates whether the token at the given position is a namespace prefix.
* @param token A token.
* @param position The position in the document.
* @returns `true` if the cursor is on the prefix of the token, `false` otherwise.
*/
export function isPrefixTokenAtPosition(token: IToken, position: TokenPosition): boolean {
const { start } = getTokenPosition(token);
switch (token.tokenType.name) {
case RdfToken.PNAME_NS.name:
case RdfToken.PNAME_LN.name: {
const i = token.image.indexOf(":");
const n = position.character - start.character;
return n <= i;
}
default: {
return false;
}
}
}
/**
* Gets the whitespace-adjusted range of a token as an LSP `Range`.
*
* The millan parser incorrectly parses some tokens with leading and trailing whitespace;
* the start and end positions are adjusted to account for this.
* @param token A token.
* @returns The range covering the token's non-whitespace content.
*/
export function getTokenRange(token: IToken): Range {
const startLine = token.startLine ? token.startLine - 1 : 0;
const startCharacter = token.startColumn ? token.startColumn - 1 : 0;
const startWhitespace = countLeadingWhitespace(token.image);
const endLine = token.endLine ? token.endLine - 1 : 0;
const endCharacter = token.endColumn ? token.endColumn - 1 : 0;
const endWhitespace = countTrailingWhitespace(token.image);
return {
start: {
line: startLine,
character: startCharacter + startWhitespace
},
end: {
line: endLine,
character: endCharacter - endWhitespace + 1
}
};
}
/**
* Get the IRI from either an IRI or prefixed name tokens.
* @param token A token.
* @returns A URI or undefined.
*/
export function getIriFromToken(prefixes: PrefixMap, token: IToken): string | undefined {
if (token.tokenType.name === RdfToken.IRIREF.name) {
return getIriFromIriReference(token.image);
} else if (token.tokenType.name === RdfToken.PNAME_LN.name || token.tokenType.name === RdfToken.PNAME_NS.name) {
return getIriFromPrefixedName(prefixes, token.image);
} else if (token.payload?.blankNodeId) {
return token.payload.blankNodeId;
}
}
/**
* Get the URI from an IRI reference.
* @param value A URI reference.
* @returns A URI string wihout angle brackets.
*/
export function getIriFromIriReference(value: string): string {
const v = value.trim();
if (v.length >= 2 && v.startsWith('<') && v.endsWith('>')) {
return v.substring(1, v.length - 1);
} else {
return v;
}
}
/**
* The reserved character escapes of a local name (`PN_LOCAL_ESC`), e.g. `\-` in `ex:a\-b`.
*/
const LOCAL_NAME_ESCAPE = /\\([_~.\-!$&'()*+,;=/?#@%])/g;
/**
* Get the IRI from a prefixed name, as the RDF readers resolve it: the prefix ends at the
* first colon, as the local name may contain colons, e.g. `ex:a:b`, and the reserved
* character escapes of the local name are resolved, e.g. `ex:a\-b` is `…a-b`.
* Percent-encodings are part of the IRI and are kept.
* @param prefixes The namespace IRIs by prefix.
* @param name A prefixed name.
* @returns The IRI, or `undefined` if the name has no colon or its prefix is not declared.
*/
export function getIriFromPrefixedName(prefixes: PrefixMap, name: string): string | undefined {
// Located with indexOf instead of split, which allocates an array per name: this runs for
// every prefixed name in a document.
const colon = name.indexOf(':');
if (colon < 0) {
return undefined;
}
const namespaceIri = prefixes[name.substring(0, colon)];
if (!namespaceIri) {
return undefined;
}
const localName = name.substring(colon + 1);
return namespaceIri + (localName.includes('\\') ? localName.replace(LOCAL_NAME_ESCAPE, '$1') : localName);
}
/**
* Get the namespace IRI of a prefixed name; the prefix ends at the first colon.
* @param prefixes The namespace IRIs by prefix.
* @param name A prefixed name.
* @returns The namespace IRI, or `undefined` if the name has no colon or its prefix is not declared.
*/
export function getNamespaceIriFromPrefixedName(prefixes: PrefixMap, name: string): string | undefined {
const colon = name.indexOf(':');
Iif (colon < 0) {
return undefined;
}
return prefixes[name.substring(0, colon)];
}
/**
* Get the namespace definition from a list of tokens.
* @param tokens The document tokens.
* @param token A prefix name declaration token.
* @returns A namespace definition or undefined.
*/
export function getNamespaceDefinition(tokens: IToken[], token: IToken): PrefixDefinition | undefined {
if (token?.tokenType.name !== RdfToken.PREFIX.name && token?.tokenType.name !== RdfToken.TTL_PREFIX.name) {
return;
}
const n = tokens.indexOf(token);
if (n >= tokens.length - 2) {
return;
}
const prefixToken = tokens[n + 1];
if (prefixToken?.tokenType.name !== RdfToken.PNAME_NS.name) {
return;
}
const uriToken = tokens[n + 2];
if (uriToken?.tokenType.name !== RdfToken.IRIREF.name) {
return;
}
const prefix = prefixToken.image.substring(0, prefixToken.image.length - 1);
const uri = getIriFromIriReference(uriToken.image);
return { prefix, uri };
}
/**
* Get the unquoted string value from a literal token.
* Strips the surrounding quote characters from single-quoted, double-quoted,
* and long (triple-quoted) string literal tokens.
* @param token A literal token.
* @returns The unquoted string value.
*/
export function getUnquotedLiteralValue(token: IToken): string {
switch (token?.tokenType.name) {
case RdfToken.STRING_LITERAL_QUOTE.name:
case RdfToken.STRING_LITERAL_SINGLE_QUOTE.name:
return token.image.substring(1, token.image.length - 1);
case RdfToken.STRING_LITERAL_LONG_QUOTE.name:
case RdfToken.STRING_LITERAL_LONG_SINGLE_QUOTE.name:
return token.image.substring(3, token.image.length - 3);
}
return token.image;
}
export type TripleComonentType = "subject" | "predicate" | "object" | undefined;
export function getTripleComponentType(tokens: IToken[], tokenIndex: number): TripleComonentType {
if (tokenIndex < 1) {
// If there is no previous token, we are at the beginning of the document.
// It must either be followed by a prefix declaration or a subject.
return "subject";
}
const p = tokens[tokenIndex - 1];
switch (p.tokenType.name) {
case RdfToken.PERIOD.name: {
// A dot is always followed by a subject.
return "subject";
}
case RdfToken.LCURLY.name: {
// The start of a SPARQL group graph pattern is followed by a subject.
return "subject";
}
case RdfToken.SEMICOLON.name: {
// A semicolon is always followed by a predicate.
return "predicate";
}
case RdfToken.A.name: {
// A type assertion is always followed by an object.
return "object";
}
case RdfToken.VAR1.name:
case RdfToken.VAR2.name: {
// A SPARQL variable can be a subject or a predicate; disambiguate by
// looking at the token before it.
const q = tokens[tokenIndex - 2];
switch (q?.tokenType.name) {
case undefined:
case RdfToken.PERIOD.name:
case RdfToken.LCURLY.name: {
// The variable opened a triple pattern → it was the subject.
return "predicate";
}
case RdfToken.VAR1.name:
case RdfToken.VAR2.name:
case RdfToken.PNAME_LN.name:
case RdfToken.IRIREF.name:
case RdfToken.SEMICOLON.name: {
// The variable followed a subject or a semicolon → it was the predicate.
return "object";
}
}
break;
}
case RdfToken.PNAME_LN.name:
case RdfToken.IRIREF.name: {
// This could either be a predicate or an object.
const q = tokens[tokenIndex - 2];
switch (q?.tokenType.name) {
case RdfToken.SEMICOLON.name:
case RdfToken.LBRACKET.name:
case RdfToken.PNAME_LN.name:
case RdfToken.IRIREF.name:
case RdfToken.VAR1.name:
case RdfToken.VAR2.name: {
return "object";
}
case RdfToken.PERIOD.name: {
return "predicate";
}
}
}
}
}
/**
* Indicates whether the token at the given index is the object of a type
* assertion, i.e. whether the preceding predicate is the `a` keyword or
* an IRI / prefixed name that resolves to `rdf:type`.
* @param tokens The document tokens.
* @param tokenIndex The index of the (object) token to check.
* @param prefixes The namespace prefixes defined in the document, used to expand prefixed names.
* @returns `true` if the preceding predicate asserts an rdf:type relation.
*/
export function isTypeAssertionObject(tokens: IToken[], tokenIndex: number, prefixes: PrefixMap): boolean {
const p = tokens[tokenIndex - 1];
if (!p) {
return false;
}
switch (p.tokenType.name) {
case RdfToken.A.name: {
return true;
}
case RdfToken.PNAME_LN.name: {
return getIriFromPrefixedName(prefixes, p.image) === RDF.type;
}
case RdfToken.IRIREF.name: {
return getIriFromIriReference(p.image) === RDF.type;
}
default: {
return false;
}
}
} |