Merge remote-tracking branch 'origin/main' into less-parsing

Reviewed-on: #26

CLAUDE.md

@@ -200,7 +200,7 @@ function parseExpression(input: string) {
 - **Not in scope** → Parses as `Word("obj.prop")` → compiles to `PUSH 'obj.prop'` (treated as file path/string)
 
 Implementation files:
-- **src/parser/scopeTracker.ts**: ContextTracker that maintains immutable scope chain
+- **src/parser/parserScopeContext.ts**: ContextTracker that maintains immutable scope chain
 - **src/parser/tokenizer.ts**: External tokenizer checks `stack.context` to decide if dot creates DotGet or Word
 - Scope tracking: Captures variables from assignments (`x = 5`) and function parameters (`fn x:`)
 - See `src/parser/tests/dot-get.test.ts` for comprehensive examples

src/compiler/tests/pipe.test.ts

@@ -78,4 +78,18 @@ describe('pipe expressions', () => {
       div = do a b: a / b end
       sub 3 1 | div (sub 110 9 | sub 1) _ | div 5`).toEvaluateTo(10)
   })
+
+  test('pipe with prelude functions (list.reverse and list.map)', () => {
+    expect(`
+      double = do x: x * 2 end
+      range 1 3 | list.reverse | list.map double
+    `).toEvaluateTo([6, 4, 2])
+  })
+
+  test('pipe with prelude function (echo)', () => {
+    expect(`
+      get-msg = do: 'hello' end
+      get-msg | echo
+    `).toEvaluateTo(null)
+  })
 })

src/parser/shrimp.grammar

@@ -1,6 +1,6 @@
 @external propSource highlighting from "./highlight"
 
-@context trackScope from "./scopeTracker"
+@context trackScope from "./parserScopeContext"
 
 @skip { space | Comment }
 

src/parser/shrimp.ts

@@ -2,7 +2,7 @@
 import {LRParser, LocalTokenGroup} from "@lezer/lr"
 import {operatorTokenizer} from "./operatorTokenizer"
 import {tokenizer, specializeKeyword} from "./tokenizer"
-import {trackScope} from "./scopeTracker"
+import {trackScope} from "./parserScopeContext"
 import {highlighting} from "./highlight"
 const spec_Identifier = {__proto__:null,if:66, null:94, catch:100, finally:106, end:108, else:116, while:130, try:136, throw:140}
 export const parser = LRParser.deserialize({

src/parser/tokenizer.ts

@@ -119,7 +119,13 @@ const consumeWordToken = (
     }
 
     // Track identifier validity: must be lowercase, digit, dash, or emoji/unicode
-    if (!isLowercaseLetter(ch) && !isDigit(ch) && ch !== 45 /* - */ && ch !== 63 /* ? */ && !isEmojiOrUnicode(ch)) {
+    if (
+      !isLowercaseLetter(ch) &&
+      !isDigit(ch) &&
+      ch !== 45 /* - */ &&
+      ch !== 63 /* ? */ &&
+      !isEmojiOrUnicode(ch)
+    ) {
       if (!canBeWord) break
       isValidIdentifier = false
     }
@@ -159,7 +165,9 @@ const checkForDotGet = (input: InputStream, stack: Stack, pos: number): number |
 
   // If identifier is in scope, this is property access (e.g., obj.prop)
   // If not in scope, it should be consumed as a Word (e.g., file.txt)
-  return context?.scope.has(identifierText) || globals.includes(identifierText) ? IdentifierBeforeDot : null
+  return context?.scope.has(identifierText) || globals.includes(identifierText)
+    ? IdentifierBeforeDot
+    : null
 }
 
 // Decide between AssignableIdentifier and Identifier using grammar state + peek-ahead
@@ -187,7 +195,10 @@ const chooseIdentifierToken = (input: InputStream, stack: Stack): number => {
   const nextCh2 = getFullCodePoint(input, peekPos + 1)
 
   // Check for compound assignment operators: +=, -=, *=, /=, %=
-  if ([43/* + */, 45/* - */, 42/* * */, 47/* / */, 37/* % */].includes(nextCh) && nextCh2 === 61/* = */) {
+  if (
+    [43 /* + */, 45 /* - */, 42 /* * */, 47 /* / */, 37 /* % */].includes(nextCh) &&
+    nextCh2 === 61 /* = */
+  ) {
     // Found compound operator, check if it's followed by whitespace
     const charAfterOp = getFullCodePoint(input, peekPos + 2)
     if (isWhiteSpace(charAfterOp) || charAfterOp === -1 /* EOF */) {

src/testSetup.ts

@@ -1,6 +1,7 @@
 import { expect } from 'bun:test'
 import { parser } from '#parser/shrimp'
 import { setGlobals } from '#parser/tokenizer'
+import { globals as prelude } from '#prelude'
 import { $ } from 'bun'
 import { assert, errorMessage } from '#utils/utils'
 import { Compiler } from '#compiler/compiler'
@@ -43,7 +44,8 @@ expect.extend({
   toMatchTree(received: unknown, expected: string, globals?: Record<string, any>) {
     assert(typeof received === 'string', 'toMatchTree can only be used with string values')
 
-    if (globals) setGlobals(Object.keys(globals))
+    const allGlobals = { ...prelude, ...(globals || {}) }
+    setGlobals(Object.keys(allGlobals))
     const tree = parser.parse(received)
     const actual = treeToString(tree, received)
     const normalizedExpected = trimWhitespace(expected)
@@ -99,9 +101,10 @@ expect.extend({
     assert(typeof received === 'string', 'toEvaluateTo can only be used with string values')
 
     try {
-      if (globals) setGlobals(Object.keys(globals))
+      const allGlobals = { ...prelude, ...(globals || {}) }
+      setGlobals(Object.keys(allGlobals))
       const compiler = new Compiler(received)
-      const result = await run(compiler.bytecode, globals)
+      const result = await run(compiler.bytecode, allGlobals)
       let value = VMResultToValue(result)
 
       // Just treat regex as strings for comparison purposes

src/tests/shrimp.test.ts

@@ -50,4 +50,4 @@ describe('Shrimp', () => {
     await shrimp.run('abc = nothing')
     expect(shrimp.get('abc')).toEqual('nothing')
   })
-})
+})

vscode-extension/server/src/editorScopeAnalyzer.test.ts

@@ -1,10 +1,10 @@
 import { test, expect, describe } from 'bun:test'
-import { ScopeTracker } from './scopeTracker'
+import { EditorScopeAnalyzer } from './editorScopeAnalyzer'
 import { TextDocument } from 'vscode-languageserver-textdocument'
 import { parser } from '../../../src/parser/shrimp'
 import * as Terms from '../../../src/parser/shrimp.terms'
 
-describe('ScopeTracker', () => {
+describe('EditorScopeAnalyzer', () => {
   test('top-level assignment is in scope', () => {
     const code = 'x = 5\necho x'
     const { tree, tracker } = parseAndGetScope(code)
@@ -135,11 +135,17 @@ end`
     const xInEcho = identifiers[identifiers.length - 1]
     expect(tracker.isInScope('x', xInEcho)).toBe(true)
   })
+
+  test('the prelude functions are always in scope', () => {
+    const code = `echo "Hello, World!"`
+    const { tree, tracker } = parseAndGetScope(code)
+    expect(tracker.isInScope('echo', tree.topNode)).toBe(true)
+  })
 })
 
 const parseAndGetScope = (code: string) => {
   const document = TextDocument.create('test://test.sh', 'shrimp', 1, code)
   const tree = parser.parse(code)
-  const tracker = new ScopeTracker(document)
+  const tracker = new EditorScopeAnalyzer(document)
   return { document, tree, tracker }
 }

vscode-extension/server/src/editorScopeAnalyzer.ts

@@ -1,17 +1,20 @@
 import { SyntaxNode } from '@lezer/common'
 import { TextDocument } from 'vscode-languageserver-textdocument'
 import * as Terms from '../../../src/parser/shrimp.terms'
+import { globals } from '../../../src/prelude'
 
 /**
  * Tracks variables in scope at a given position in the parse tree.
  * Used to distinguish identifiers (in scope) from words (not in scope).
  */
-export class ScopeTracker {
+export class EditorScopeAnalyzer {
   private document: TextDocument
   private scopeCache = new Map<number, Set<string>>()
 
   constructor(document: TextDocument) {
     this.document = document
+    const preludeKeys = Object.keys(globals)
+    this.scopeCache.set(0, new Set(preludeKeys))
   }
 
   /**

vscode-extension/server/src/semanticTokens.ts

@@ -7,7 +7,7 @@ import {
   SemanticTokenTypes,
   SemanticTokenModifiers,
 } from 'vscode-languageserver/node'
-import { ScopeTracker } from './scopeTracker'
+import { EditorScopeAnalyzer } from './editorScopeAnalyzer'
 
 export const TOKEN_TYPES = [
   SemanticTokenTypes.function,
@@ -30,7 +30,7 @@ export const TOKEN_MODIFIERS = [
 
 export function buildSemanticTokens(document: TextDocument, tree: Tree): number[] {
   const builder = new SemanticTokensBuilder()
-  const scopeTracker = new ScopeTracker(document)
+  const scopeTracker = new EditorScopeAnalyzer(document)
 
   walkTree(tree.topNode, document, builder, scopeTracker)
 
@@ -75,7 +75,7 @@ function walkTree(
   node: SyntaxNode,
   document: TextDocument,
   builder: SemanticTokensBuilder,
-  scopeTracker: ScopeTracker
+  scopeTracker: EditorScopeAnalyzer
 ) {
   // Special handling for NamedArgPrefix to split "name=" into two tokens
   if (node.type.id === Terms.NamedArgPrefix) {
@@ -102,7 +102,7 @@ type TokenInfo = { type: number; modifiers: number } | undefined
 function getTokenType(
   node: SyntaxNode,
   document: TextDocument,
-  scopeTracker: ScopeTracker
+  scopeTracker: EditorScopeAnalyzer
 ): TokenInfo {
   const nodeTypeId = node.type.id
   const parentTypeId = node.parent?.type.id