@tinta-lang/syntax 0.0.0-stage → 0.1.0-dev.0

package/vendor/micromark-util-resolve-all/index.js

@@ -0,0 +1,32 @@
+/**
+ * @import {Event, Resolver, TokenizeContext} from 'micromark-util-types'
+ */
+
+/**
+ * Call all `resolveAll`s.
+ *
+ * @param {ReadonlyArray<{resolveAll?: Resolver | undefined}>} constructs
+ *   List of constructs, optionally with `resolveAll`s.
+ * @param {Array<Event>} events
+ *   List of events.
+ * @param {TokenizeContext} context
+ *   Context used by `tokenize`.
+ * @returns {Array<Event>}
+ *   Changed events.
+ */
+export function resolveAll(constructs, events, context) {
+  /** @type {Array<Resolver>} */
+  const called = []
+  let index = -1
+
+  while (++index < constructs.length) {
+    const resolve = constructs[index].resolveAll
+
+    if (resolve && !called.includes(resolve)) {
+      events = resolve(events, context)
+      called.push(resolve)
+    }
+  }
+
+  return events
+}

package/vendor/micromark-util-resolve-all/license

@@ -0,0 +1,22 @@
+(The MIT License)
+
+Copyright (c) Titus Wormer <tituswormer@gmail.com>
+
+Permission is hereby granted, free of charge, to any person obtaining
+a copy of this software and associated documentation files (the
+'Software'), to deal in the Software without restriction, including
+without limitation the rights to use, copy, modify, merge, publish,
+distribute, sublicense, and/or sell copies of the Software, and to
+permit persons to whom the Software is furnished to do so, subject to
+the following conditions:
+
+The above copyright notice and this permission notice shall be
+included in all copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED 'AS IS', WITHOUT WARRANTY OF ANY KIND,
+EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
+MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.
+IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY
+CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT,
+TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH THE
+SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE.

package/vendor/micromark-util-resolve-all/package.json

@@ -0,0 +1,48 @@
+{
+  "name": "micromark-util-resolve-all",
+  "version": "2.0.1",
+  "description": "micromark utility to resolve subtokens",
+  "license": "MIT",
+  "keywords": [
+    "micromark",
+    "util",
+    "utility",
+    "resolve"
+  ],
+  "repository": "https://github.com/micromark/micromark/tree/main/packages/micromark-util-resolve-all",
+  "bugs": "https://github.com/micromark/micromark/issues",
+  "funding": [
+    {
+      "type": "GitHub Sponsors",
+      "url": "https://github.com/sponsors/unifiedjs"
+    },
+    {
+      "type": "OpenCollective",
+      "url": "https://opencollective.com/unified"
+    }
+  ],
+  "author": "Titus Wormer <tituswormer@gmail.com> (https://wooorm.com)",
+  "contributors": [
+    "Titus Wormer <tituswormer@gmail.com> (https://wooorm.com)"
+  ],
+  "sideEffects": false,
+  "type": "module",
+  "files": [
+    "index.d.ts.map",
+    "index.d.ts",
+    "index.js"
+  ],
+  "exports": "./index.js",
+  "dependencies": {
+    "micromark-util-types": "^2.0.0"
+  },
+  "xo": {
+    "envs": [
+      "shared-node-browser"
+    ],
+    "prettier": true,
+    "rules": {
+      "unicorn/prefer-code-point": "off"
+    }
+  }
+}

package/vendor/micromark-util-sanitize-uri/index.js

@@ -0,0 +1,107 @@
+import { asciiAlphanumeric } from 'micromark-util-character';
+import { encode } from 'micromark-util-encode';
+/**
+ * Make a value safe for injection as a URL.
+ *
+ * This encodes unsafe characters with percent-encoding and skips already
+ * encoded sequences (see `normalizeUri`).
+ * Further unsafe characters are encoded as character references (see
+ * `micromark-util-encode`).
+ *
+ * A regex of allowed protocols can be given, in which case the URL is
+ * sanitized.
+ * For example, `/^(https?|ircs?|mailto|xmpp)$/i` can be used for `a[href]`, or
+ * `/^https?$/i` for `img[src]` (this is what `github.com` allows).
+ * If the URL includes an unknown protocol (one not matched by `protocol`, such
+ * as a dangerous example, `javascript:`), the value is ignored.
+ *
+ * @param {string | null | undefined} url
+ *   URI to sanitize.
+ * @param {RegExp | null | undefined} [protocol]
+ *   Allowed protocols.
+ * @returns {string}
+ *   Sanitized URI.
+ */
+export function sanitizeUri(url, protocol) {
+  const value = encode(normalizeUri(url || ''));
+  if (!protocol) {
+    return value;
+  }
+  const colon = value.indexOf(':');
+  const questionMark = value.indexOf('?');
+  const numberSign = value.indexOf('#');
+  const slash = value.indexOf('/');
+  if (
+  // If there is no protocol, it’s relative.
+  colon < 0 ||
+  // If the first colon is after a `?`, `#`, or `/`, it’s not a protocol.
+  slash > -1 && colon > slash || questionMark > -1 && colon > questionMark || numberSign > -1 && colon > numberSign ||
+  // It is a protocol, it should be allowed.
+  protocol.test(value.slice(0, colon))) {
+    return value;
+  }
+  return '';
+}
+
+/**
+ * Normalize a URL.
+ *
+ * Encode unsafe characters with percent-encoding, skipping already encoded
+ * sequences.
+ *
+ * @param {string} value
+ *   URI to normalize.
+ * @returns {string}
+ *   Normalized URI.
+ */
+export function normalizeUri(value) {
+  /** @type {Array<string>} */
+  const result = [];
+  let index = -1;
+  let start = 0;
+  let skip = 0;
+  while (++index < value.length) {
+    const code = value.charCodeAt(index);
+    /** @type {string} */
+    let replace = '';
+
+    // A correct percent encoded value.
+    if (code === 37 && asciiAlphanumeric(value.charCodeAt(index + 1)) && asciiAlphanumeric(value.charCodeAt(index + 2))) {
+      skip = 2;
+    }
+    // ASCII.
+    else if (code < 128) {
+      if (!/[!#$&-;=?-Z_a-z~]/.test(String.fromCharCode(code))) {
+        replace = String.fromCharCode(code);
+      }
+    }
+    // Astral.
+    else if (code > 55_295 && code < 57_344) {
+      const next = value.charCodeAt(index + 1);
+
+      // A correct surrogate pair.
+      if (code < 56_320 && next > 56_319 && next < 57_344) {
+        replace = String.fromCharCode(code, next);
+        skip = 1;
+      }
+      // Lone surrogate.
+      else {
+        replace = "\uFFFD";
+      }
+    }
+    // Unicode.
+    else {
+      replace = String.fromCharCode(code);
+    }
+    if (replace) {
+      result.push(value.slice(start, index), encodeURIComponent(replace));
+      start = index + skip + 1;
+      replace = '';
+    }
+    if (skip) {
+      index += skip;
+      skip = 0;
+    }
+  }
+  return result.join('') + value.slice(start);
+}

package/vendor/micromark-util-sanitize-uri/license

@@ -0,0 +1,22 @@
+(The MIT License)
+
+Copyright (c) Titus Wormer <tituswormer@gmail.com>
+
+Permission is hereby granted, free of charge, to any person obtaining
+a copy of this software and associated documentation files (the
+'Software'), to deal in the Software without restriction, including
+without limitation the rights to use, copy, modify, merge, publish,
+distribute, sublicense, and/or sell copies of the Software, and to
+permit persons to whom the Software is furnished to do so, subject to
+the following conditions:
+
+The above copyright notice and this permission notice shall be
+included in all copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED 'AS IS', WITHOUT WARRANTY OF ANY KIND,
+EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
+MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.
+IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY
+CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT,
+TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH THE
+SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE.

package/vendor/micromark-util-sanitize-uri/package.json

@@ -0,0 +1,59 @@
+{
+  "name": "micromark-util-sanitize-uri",
+  "version": "2.0.1",
+  "description": "micromark utility to sanitize urls",
+  "license": "MIT",
+  "keywords": [
+    "micromark",
+    "util",
+    "utility",
+    "sanitize",
+    "clear",
+    "url"
+  ],
+  "repository": "https://github.com/micromark/micromark/tree/main/packages/micromark-util-sanitize-uri",
+  "bugs": "https://github.com/micromark/micromark/issues",
+  "funding": [
+    {
+      "type": "GitHub Sponsors",
+      "url": "https://github.com/sponsors/unifiedjs"
+    },
+    {
+      "type": "OpenCollective",
+      "url": "https://opencollective.com/unified"
+    }
+  ],
+  "author": "Titus Wormer <tituswormer@gmail.com> (https://wooorm.com)",
+  "contributors": [
+    "Titus Wormer <tituswormer@gmail.com> (https://wooorm.com)"
+  ],
+  "sideEffects": false,
+  "type": "module",
+  "files": [
+    "dev/",
+    "index.d.ts.map",
+    "index.d.ts",
+    "index.js"
+  ],
+  "exports": {
+    "development": "./dev/index.js",
+    "default": "./index.js"
+  },
+  "dependencies": {
+    "micromark-util-character": "^2.0.0",
+    "micromark-util-encode": "^2.0.0",
+    "micromark-util-symbol": "^2.0.0"
+  },
+  "scripts": {
+    "build": "micromark-build"
+  },
+  "xo": {
+    "envs": [
+      "shared-node-browser"
+    ],
+    "prettier": true,
+    "rules": {
+      "unicorn/prefer-code-point": "off"
+    }
+  }
+}

package/vendor/micromark-util-subtokenize/index.js

@@ -0,0 +1,228 @@
+/**
+ * @import {Chunk, Event, Token} from 'micromark-util-types'
+ */
+
+import { splice } from 'micromark-util-chunked';
+import { SpliceBuffer } from './lib/splice-buffer.js';
+
+// Hidden API exposed for testing.
+export { SpliceBuffer } from './lib/splice-buffer.js';
+
+/**
+ * Tokenize subcontent.
+ *
+ * @param {Array<Event>} eventsArray
+ *   List of events.
+ * @returns {boolean}
+ *   Whether subtokens were found.
+ */
+// eslint-disable-next-line complexity
+export function subtokenize(eventsArray) {
+  /** @type {Record<string, number>} */
+  const jumps = {};
+  let index = -1;
+  /** @type {Event} */
+  let event;
+  /** @type {number | undefined} */
+  let lineIndex;
+  /** @type {number} */
+  let otherIndex;
+  /** @type {Event} */
+  let otherEvent;
+  /** @type {Array<Event>} */
+  let parameters;
+  /** @type {Array<Event>} */
+  let subevents;
+  /** @type {boolean | undefined} */
+  let more;
+  const events = new SpliceBuffer(eventsArray);
+  while (++index < events.length) {
+    while (index in jumps) {
+      index = jumps[index];
+    }
+    event = events.get(index);
+
+    // Add a hook for the GFM tasklist extension, which needs to know if text
+    // is in the first content of a list item.
+    if (index && event[1].type === "chunkFlow" && events.get(index - 1)[1].type === "listItemPrefix") {
+      subevents = event[1]._tokenizer.events;
+      otherIndex = 0;
+      if (otherIndex < subevents.length && subevents[otherIndex][1].type === "lineEndingBlank") {
+        otherIndex += 2;
+      }
+      if (otherIndex < subevents.length && subevents[otherIndex][1].type === "content") {
+        while (++otherIndex < subevents.length) {
+          if (subevents[otherIndex][1].type === "content") {
+            break;
+          }
+          if (subevents[otherIndex][1].type === "chunkText") {
+            subevents[otherIndex][1]._isInFirstContentOfListItem = true;
+            otherIndex++;
+          }
+        }
+      }
+    }
+
+    // Enter.
+    if (event[0] === 'enter') {
+      if (event[1].contentType) {
+        Object.assign(jumps, subcontent(events, index));
+        index = jumps[index];
+        more = true;
+      }
+    }
+    // Exit.
+    else if (event[1]._container) {
+      otherIndex = index;
+      lineIndex = undefined;
+      while (otherIndex--) {
+        otherEvent = events.get(otherIndex);
+        if (otherEvent[1].type === "lineEnding" || otherEvent[1].type === "lineEndingBlank") {
+          if (otherEvent[0] === 'enter') {
+            if (lineIndex) {
+              events.get(lineIndex)[1].type = "lineEndingBlank";
+            }
+            otherEvent[1].type = "lineEnding";
+            lineIndex = otherIndex;
+          }
+        } else if (otherEvent[1].type === "linePrefix" || otherEvent[1].type === "listItemIndent") {
+          // Move past.
+        } else {
+          break;
+        }
+      }
+      if (lineIndex) {
+        // Fix position.
+        event[1].end = {
+          ...events.get(lineIndex)[1].start
+        };
+
+        // Switch container exit w/ line endings.
+        parameters = events.slice(lineIndex, index);
+        parameters.unshift(event);
+        events.splice(lineIndex, index - lineIndex + 1, parameters);
+      }
+    }
+  }
+
+  // The changes to the `events` buffer must be copied back into the eventsArray
+  splice(eventsArray, 0, Number.POSITIVE_INFINITY, events.slice(0));
+  return !more;
+}
+
+/**
+ * Tokenize embedded tokens.
+ *
+ * @param {SpliceBuffer<Event>} events
+ *   Events.
+ * @param {number} eventIndex
+ *   Index.
+ * @returns {Record<string, number>}
+ *   Gaps.
+ */
+function subcontent(events, eventIndex) {
+  const token = events.get(eventIndex)[1];
+  const context = events.get(eventIndex)[2];
+  let startPosition = eventIndex - 1;
+  /** @type {Array<number>} */
+  const startPositions = [];
+  let tokenizer = token._tokenizer;
+  if (!tokenizer) {
+    tokenizer = context.parser[token.contentType](token.start);
+    if (token._contentTypeTextTrailing) {
+      tokenizer._contentTypeTextTrailing = true;
+    }
+  }
+  const childEvents = tokenizer.events;
+  /** @type {Array<[number, number]>} */
+  const jumps = [];
+  /** @type {Record<string, number>} */
+  const gaps = {};
+  /** @type {Array<Chunk>} */
+  let stream;
+  /** @type {Token | undefined} */
+  let previous;
+  let index = -1;
+  /** @type {Token | undefined} */
+  let current = token;
+  let adjust = 0;
+  let start = 0;
+  const breaks = [start];
+
+  // Loop forward through the linked tokens to pass them in order to the
+  // subtokenizer.
+  while (current) {
+    // Find the position of the event for this token.
+    while (events.get(++startPosition)[1] !== current) {
+      // Empty.
+    }
+    startPositions.push(startPosition);
+    if (!current._tokenizer) {
+      stream = context.sliceStream(current);
+      if (!current.next) {
+        stream.push(null);
+      }
+      if (previous) {
+        tokenizer.defineSkip(current.start);
+      }
+      if (current._isInFirstContentOfListItem) {
+        tokenizer._gfmTasklistFirstContentOfListItem = true;
+      }
+      tokenizer.write(stream);
+      if (current._isInFirstContentOfListItem) {
+        tokenizer._gfmTasklistFirstContentOfListItem = undefined;
+      }
+    }
+
+    // Unravel the next token.
+    previous = current;
+    current = current.next;
+  }
+
+  // Now, loop back through all events (and linked tokens), to figure out which
+  // parts belong where.
+  current = token;
+  while (++index < childEvents.length) {
+    if (
+    // Find a void token that includes a break.
+    childEvents[index][0] === 'exit' && childEvents[index - 1][0] === 'enter' && childEvents[index][1].type === childEvents[index - 1][1].type && childEvents[index][1].start.line !== childEvents[index][1].end.line) {
+      start = index + 1;
+      breaks.push(start);
+      // Help GC.
+      current._tokenizer = undefined;
+      current.previous = undefined;
+      current = current.next;
+    }
+  }
+
+  // Help GC.
+  tokenizer.events = [];
+
+  // If there’s one more token (which is the cases for lines that end in an
+  // EOF), that’s perfect: the last point we found starts it.
+  // If there isn’t then make sure any remaining content is added to it.
+  if (current) {
+    // Help GC.
+    current._tokenizer = undefined;
+    current.previous = undefined;
+  } else {
+    breaks.pop();
+  }
+
+  // Now splice the events from the subtokenizer into the current events,
+  // moving back to front so that splice indices aren’t affected.
+  index = breaks.length;
+  while (index--) {
+    const slice = childEvents.slice(breaks[index], breaks[index + 1]);
+    const start = startPositions.pop();
+    jumps.push([start, start + slice.length - 1]);
+    events.splice(start, 2, slice);
+  }
+  jumps.reverse();
+  index = -1;
+  while (++index < jumps.length) {
+    gaps[adjust + jumps[index][0]] = adjust + jumps[index][1];
+    adjust += jumps[index][1] - jumps[index][0] - 1;
+  }
+  return gaps;
+}