From abd7d2e43b4f4dc7147e5123adc981a7cab16c9d Mon Sep 17 00:00:00 2001 From: Chris Wanstrath Date: Sun, 26 Oct 2025 16:28:56 -0700 Subject: [PATCH 1/4] DotGet function calls --- src/parser/shrimp.grammar | 5 +- src/parser/shrimp.terms.ts | 34 +++++----- src/parser/shrimp.ts | 18 +++--- src/parser/tests/basics.test.ts | 7 ++- src/parser/tests/dot-get.test.ts | 105 ++++++++++++++++++++++++------- 5 files changed, 116 insertions(+), 53 deletions(-) diff --git a/src/parser/shrimp.grammar b/src/parser/shrimp.grammar index 741dad0..8695018 100644 --- a/src/parser/shrimp.grammar +++ b/src/parser/shrimp.grammar @@ -46,7 +46,6 @@ item { consumeToTerminator { PipeExpr | ambiguousFunctionCall | - DotGet | IfExpr | FunctionDef | Assign | @@ -63,7 +62,7 @@ pipeOperand { } FunctionCallOrIdentifier { - Identifier + DotGet | Identifier } ambiguousFunctionCall { @@ -71,7 +70,7 @@ ambiguousFunctionCall { } FunctionCall { - Identifier arg+ + (DotGet | Identifier) arg+ } arg { diff --git a/src/parser/shrimp.terms.ts b/src/parser/shrimp.terms.ts index 75f88be..e7fce78 100644 --- a/src/parser/shrimp.terms.ts +++ b/src/parser/shrimp.terms.ts @@ -19,24 +19,24 @@ export const Program = 17, PipeExpr = 18, FunctionCall = 19, - PositionalArg = 20, - ParenExpr = 21, - FunctionCallOrIdentifier = 22, - BinOp = 23, - ConditionalOp = 24, - FunctionDef = 25, + DotGet = 20, + PositionalArg = 21, + ParenExpr = 22, + FunctionCallOrIdentifier = 23, + BinOp = 24, + ConditionalOp = 25, + FunctionDef = 26, keyword = 50, - Params = 27, - colon = 28, - String = 30, - StringFragment = 31, - Interpolation = 32, - EscapeSeq = 33, - Number = 34, - Boolean = 35, - Regex = 36, - Null = 37, - DotGet = 38, + Params = 28, + colon = 29, + String = 31, + StringFragment = 32, + Interpolation = 33, + EscapeSeq = 34, + Number = 35, + Boolean = 36, + Regex = 37, + Null = 38, Underscore = 39, NamedArg = 40, NamedArgPrefix = 41, diff --git a/src/parser/shrimp.ts b/src/parser/shrimp.ts index 1db89f9..3f0a131 100644 --- a/src/parser/shrimp.ts +++ b/src/parser/shrimp.ts @@ -4,24 +4,24 @@ import {operatorTokenizer} from "./operatorTokenizer" import {tokenizer} from "./tokenizer" import {trackScope} from "./scopeTracker" import {highlighting} from "./highlight" -const spec_Identifier = {__proto__:null,do:52, end:58, null:74, if:88, elseif:96, else:100} +const spec_Identifier = {__proto__:null,do:54, end:60, null:76, if:88, elseif:96, else:100} export const parser = LRParser.deserialize({ version: 14, - states: ".jQVQbOOO#XQcO'#CrO$RQRO'#CsO$aQcO'#DmO$xQbO'#DsOOQ`'#Cu'#CuO%QQbO'#CqO%rOSO'#CzOOQa'#Dq'#DqO&QOpO'#DSO&VQcO'#DpOOQ`'#Dn'#DnO&nQbO'#DmO&|QbO'#EQOOQ`'#DX'#DXO'kQRO'#DaOOQ`'#Dm'#DmO'pQQO'#DlOOQ`'#Dl'#DlOOQ`'#Db'#DbQVQbOOOOQa'#Dp'#DpOOQ`'#Cp'#CpO'xQbO'#DUOOQ`'#Do'#DoOOQ`'#Dc'#DcO(SQbO,59ZO&|QbO,59_O&|QbO,59_OOQ`'#Dd'#DdO(pQbO'#CwO(xQQO,5:_O)iQRO'#CsO)yQRO,59]O*[QRO,59]O*VQQO,59]O+VQQO,59]O+_QbO'#C|O+gQWO'#C}OOOO'#Dy'#DyOOOO'#Df'#DfO+{OSO,59fOOQa,59f,59fO,ZO`O,59nO,`QbO'#DgO,eQbO,59YO,vQRO,5:lO,}QQO,5:lO-SQbO,59{OOQ`,5:W,5:WOOQ`-E7`-E7`OOQ`,59p,59pOOQ`-E7a-E7aOOQa1G.y1G.yO-^QcO1G.yOOQ`-E7b-E7bO-xQbO1G/yO&|QbO,59`O&|QbO,59`OOQa1G.w1G.wOOOO,59h,59hOOOO,59i,59iOOOO-E7d-E7dOOQa1G/Q1G/QOOQa1G/Y1G/YO!QQbO'#CrOOQ`,5:R,5:ROOQ`-E7e-E7eO.VQbO1G0WOOQ`1G/g1G/gO.dQbO7+%eO.iQbO7+%fOOQO1G.z1G.zO.vQRO1G.zOOQ`'#DZ'#DZOOQ`7+%r7+%rO/QQbO7+%sOOQ`<lAN>lO&|QbO'#D]OOQ`'#Dh'#DhO0_QbOAN>yO0jQQO'#D_OOQ`AN>yAN>yO0oQbOAN>yO0tQRO,59wO0{QQO,59wOOQ`-E7f-E7fOOQ`G24eG24eO1QQbOG24eO1VQQO,59yO1[QQO1G/cOOQ`LD*PLD*PO.iQbO1G/eO/QQbO7+$}OOQ`7+%P7+%POOQ`<mAN>mO&|QbO'#D]OOQ`'#Dh'#DhO0bQbOAN>yO0mQQO'#D_OOQ`AN>yAN>yO0rQbOAN>yO0wQRO,59wO1OQQO,59wOOQ`-E7f-E7fOOQ`G24eG24eO1TQbOG24eO1YQQO,59yO1_QQO1G/cOOQ`LD*PLD*PO.lQbO1G/eO/TQbO7+$}OOQ`7+%P7+%POOQ`< spec_Identifier[value] || -1}], - tokenPrec: 753 + tokenPrec: 756 }) diff --git a/src/parser/tests/basics.test.ts b/src/parser/tests/basics.test.ts index 3299ff3..1158bb1 100644 --- a/src/parser/tests/basics.test.ts +++ b/src/parser/tests/basics.test.ts @@ -319,9 +319,10 @@ describe('DotGet whitespace sensitivity', () => { AssignableIdentifier basename Eq = Number 5 - DotGet - IdentifierBeforeDot basename - Identifier prop`) + FunctionCallOrIdentifier + DotGet + IdentifierBeforeDot basename + Identifier prop`) }) test('space before dot - NOT DotGet, parses as division', () => { diff --git a/src/parser/tests/dot-get.test.ts b/src/parser/tests/dot-get.test.ts index fd1aacb..f2461bc 100644 --- a/src/parser/tests/dot-get.test.ts +++ b/src/parser/tests/dot-get.test.ts @@ -20,9 +20,10 @@ describe('DotGet', () => { AssignableIdentifier obj Eq = Number 5 - DotGet - IdentifierBeforeDot obj - Identifier prop + FunctionCallOrIdentifier + DotGet + IdentifierBeforeDot obj + Identifier prop `) }) @@ -33,9 +34,10 @@ describe('DotGet', () => { Params AssignableIdentifier config colon : - DotGet - IdentifierBeforeDot config - Identifier path + FunctionCallOrIdentifier + DotGet + IdentifierBeforeDot config + Identifier path keyword end `) }) @@ -47,9 +49,10 @@ describe('DotGet', () => { Params AssignableIdentifier x colon : - DotGet - IdentifierBeforeDot x - Identifier prop + FunctionCallOrIdentifier + DotGet + IdentifierBeforeDot x + Identifier prop keyword end Word x.prop `) @@ -66,12 +69,14 @@ end`).toMatchTree(` AssignableIdentifier x AssignableIdentifier y colon : - DotGet - IdentifierBeforeDot x - Identifier foo - DotGet - IdentifierBeforeDot y - Identifier bar + FunctionCallOrIdentifier + DotGet + IdentifierBeforeDot x + Identifier foo + FunctionCallOrIdentifier + DotGet + IdentifierBeforeDot y + Identifier bar keyword end `) }) @@ -86,17 +91,19 @@ end`).toMatchTree(` Params AssignableIdentifier x colon : - DotGet - IdentifierBeforeDot x - Identifier outer + FunctionCallOrIdentifier + DotGet + IdentifierBeforeDot x + Identifier outer FunctionDef keyword do Params AssignableIdentifier y colon : - DotGet - IdentifierBeforeDot y - Identifier inner + FunctionCallOrIdentifier + DotGet + IdentifierBeforeDot y + Identifier inner keyword end keyword end `) @@ -117,6 +124,62 @@ end`).toMatchTree(` `) }) + test('dot get works as bare function', () => { + expect('io = dict print=echo; io.print').toMatchTree(` + Assign + AssignableIdentifier io + Eq = + FunctionCall + Identifier dict + NamedArg + NamedArgPrefix print= + Identifier echo + FunctionCallOrIdentifier + DotGet + IdentifierBeforeDot io + Identifier print + `) + }) + + test('dot get works as function w/ args', () => { + expect('io = dict print=echo; io.print heya').toMatchTree(` + Assign + AssignableIdentifier io + Eq = + FunctionCall + Identifier dict + NamedArg + NamedArgPrefix print= + Identifier echo + FunctionCall + DotGet + IdentifierBeforeDot io + Identifier print + PositionalArg + Identifier heya + `) + }) + + test('dot get works as function in parens', () => { + expect('io = dict print=echo; (io.print heya)').toMatchTree(` + Assign + AssignableIdentifier io + Eq = + FunctionCall + Identifier dict + NamedArg + NamedArgPrefix print= + Identifier echo + ParenExpr + FunctionCall + DotGet + IdentifierBeforeDot io + Identifier print + PositionalArg + Identifier heya + `) + }) + test('mixed file paths and dot get', () => { expect('config = 42; cat readme.txt; echo config.path').toMatchTree(` Assign -- 2.50.1 From 972fd25fda2eba12fb378de08ce221321d78715e Mon Sep 17 00:00:00 2001 From: Chris Wanstrath Date: Sun, 26 Oct 2025 22:23:46 -0700 Subject: [PATCH 2/4] update params scope detection, add array.1 (dotget array indices) --- src/compiler/utils.ts | 4 +- src/parser/scopeTracker.ts | 26 +++++---- src/parser/shrimp.grammar | 9 +-- src/parser/shrimp.terms.ts | 35 ++++++------ src/parser/shrimp.ts | 22 ++++---- src/parser/tests/basics.test.ts | 6 +- src/parser/tests/dot-get.test.ts | 88 ++++++++++++++++++++++++++---- src/parser/tests/functions.test.ts | 26 ++++----- src/parser/tests/multiline.test.ts | 12 ++-- src/parser/tests/pipes.test.ts | 18 +++++- src/parser/tokenizer.ts | 7 ++- 11 files changed, 172 insertions(+), 81 deletions(-) diff --git a/src/compiler/utils.ts b/src/compiler/utils.ts index 312962f..cbdd1bc 100644 --- a/src/compiler/utils.ts +++ b/src/compiler/utils.ts @@ -70,9 +70,9 @@ export const getFunctionDefParts = (node: SyntaxNode, input: string) => { } const paramNames = getAllChildren(paramsNode).map((param) => { - if (param.type.id !== terms.AssignableIdentifier) { + if (param.type.id !== terms.Identifier) { throw new CompilerError( - `FunctionDef params must be AssignableIdentifiers, got ${param.type.name}`, + `FunctionDef params must be Identifier, got ${param.type.name}`, param.from, param.to ) diff --git a/src/parser/scopeTracker.ts b/src/parser/scopeTracker.ts index 8854cad..af2a32c 100644 --- a/src/parser/scopeTracker.ts +++ b/src/parser/scopeTracker.ts @@ -57,26 +57,30 @@ const readIdentifierText = (input: InputStream, start: number, end: number): str return text } +let inParams = false + export const trackScope = new ContextTracker({ start: new TrackerContext(new Scope(null, new Set())), shift(context, term, stack, input) { - if (term !== terms.AssignableIdentifier) return context + if (term == terms.Do) inParams = true - const text = readIdentifierText(input, input.pos, stack.pos) - return new TrackerContext(context.scope, [...context.pendingIds, text]) + if (term === terms.AssignableIdentifier) { + const text = readIdentifierText(input, input.pos, stack.pos) + return new TrackerContext(Scope.add(context.scope, text), context.pendingIds) + } + + if (inParams && term === terms.Identifier) { + const text = readIdentifierText(input, input.pos, stack.pos) + return new TrackerContext(context.scope, [...context.pendingIds, text]) + } + + return context }, reduce(context, term) { - // Add assignment variable to scope - if (term === terms.Assign) { - const varName = context.pendingIds.at(-1) - if (!varName) return context - return new TrackerContext(Scope.add(context.scope, varName), context.pendingIds.slice(0, -1)) - } - - // Push new scope and add all parameters if (term === terms.Params) { + inParams = false let newScope = context.scope.push() if (context.pendingIds.length > 0) { newScope = Scope.add(newScope, ...context.pendingIds) diff --git a/src/parser/shrimp.grammar b/src/parser/shrimp.grammar index 8695018..3c517ce 100644 --- a/src/parser/shrimp.grammar +++ b/src/parser/shrimp.grammar @@ -28,6 +28,7 @@ } @external tokens tokenizer from "./tokenizer" { Identifier, AssignableIdentifier, Word, IdentifierBeforeDot } +@external specialize {Identifier} specializeKeyword from "./tokenizer" { Do } @precedence { pipe @left, @@ -91,11 +92,11 @@ FunctionDef { } singleLineFunctionDef { - @specialize[@name=keyword] Params colon consumeToTerminator @specialize[@name=keyword] + Do Params colon consumeToTerminator @specialize[@name=keyword] } multilineFunctionDef { - @specialize[@name=keyword] Params colon newlineOrSemicolon block @specialize[@name=keyword] + Do Params colon newlineOrSemicolon block @specialize[@name=keyword] } IfExpr { @@ -134,7 +135,7 @@ ConditionalOp { } Params { - AssignableIdentifier* + Identifier* } Assign { @@ -163,7 +164,7 @@ expression { @skip {} { DotGet { - IdentifierBeforeDot dot Identifier + IdentifierBeforeDot dot (Number | Identifier) } String { "'" stringContent* "'" } diff --git a/src/parser/shrimp.terms.ts b/src/parser/shrimp.terms.ts index e7fce78..36e7098 100644 --- a/src/parser/shrimp.terms.ts +++ b/src/parser/shrimp.terms.ts @@ -16,24 +16,25 @@ export const AssignableIdentifier = 14, Word = 15, IdentifierBeforeDot = 16, - Program = 17, - PipeExpr = 18, - FunctionCall = 19, - DotGet = 20, - PositionalArg = 21, - ParenExpr = 22, - FunctionCallOrIdentifier = 23, - BinOp = 24, - ConditionalOp = 25, - FunctionDef = 26, + Do = 17, + Program = 18, + PipeExpr = 19, + FunctionCall = 20, + DotGet = 21, + Number = 22, + PositionalArg = 23, + ParenExpr = 24, + FunctionCallOrIdentifier = 25, + BinOp = 26, + ConditionalOp = 27, + FunctionDef = 28, + Params = 29, + colon = 30, keyword = 50, - Params = 28, - colon = 29, - String = 31, - StringFragment = 32, - Interpolation = 33, - EscapeSeq = 34, - Number = 35, + String = 32, + StringFragment = 33, + Interpolation = 34, + EscapeSeq = 35, Boolean = 36, Regex = 37, Null = 38, diff --git a/src/parser/shrimp.ts b/src/parser/shrimp.ts index 3f0a131..1dfa9d0 100644 --- a/src/parser/shrimp.ts +++ b/src/parser/shrimp.ts @@ -1,27 +1,27 @@ // This file was generated by lezer-generator. You probably shouldn't edit it. import {LRParser, LocalTokenGroup} from "@lezer/lr" import {operatorTokenizer} from "./operatorTokenizer" -import {tokenizer} from "./tokenizer" +import {tokenizer, specializeKeyword} from "./tokenizer" import {trackScope} from "./scopeTracker" import {highlighting} from "./highlight" -const spec_Identifier = {__proto__:null,do:54, end:60, null:76, if:88, elseif:96, else:100} +const spec_Identifier = {__proto__:null,end:62, null:76, if:88, elseif:96, else:100} export const parser = LRParser.deserialize({ version: 14, - states: ".jQVQbOOO!QOpO'#CpO#^QcO'#CsO$WQRO'#CtO$fQcO'#DmO$}QbO'#DtOOQ`'#Cv'#CvO%VQbO'#CrO%wOSO'#C{OOQa'#Dr'#DrO&VQcO'#DqOOQ`'#Dn'#DnO&nQbO'#DmO&|QbO'#EQOOQ`'#DX'#DXO'kQRO'#DaOOQ`'#Dm'#DmO'pQQO'#DlOOQ`'#Dl'#DlOOQ`'#Db'#DbQVQbOOO'xO`O,59[OOQa'#Dq'#DqOOQ`'#Cq'#CqO'}QbO'#DUOOQ`'#Dp'#DpOOQ`'#Dc'#DcO(XQbO,59ZO&|QbO,59`O&|QbO,59`OOQ`'#Dd'#DdO(uQbO'#CxO(}QQO,5:`O)nQRO'#CtO*OQRO,59^O*aQRO,59^O*[QQO,59^O+[QQO,59^O+dQbO'#C}O+lQWO'#DOOOOO'#Dz'#DzOOOO'#Df'#DfO,QOSO,59gOOQa,59g,59gO,`QbO'#DgO,hQbO,59YO,yQRO,5:lO-QQQO,5:lO-VQbO,59{OOQ`,5:W,5:WOOQ`-E7`-E7`OOQa1G.v1G.vOOQ`,59p,59pOOQ`-E7a-E7aOOQa1G.z1G.zO-aQcO1G.zOOQ`-E7b-E7bO-{QbO1G/zO&|QbO,59aO&|QbO,59aOOQa1G.x1G.xOOOO,59i,59iOOOO,59j,59jOOOO-E7d-E7dOOQa1G/R1G/RO!VQbO'#CsOOQ`,5:R,5:ROOQ`-E7e-E7eO.YQbO1G0WOOQ`1G/g1G/gO.gQbO7+%fO.lQbO7+%gOOQO1G.{1G.{O.yQRO1G.{OOQ`'#DZ'#DZOOQ`7+%r7+%rO/TQbO7+%sOOQ`<mAN>mO&|QbO'#D]OOQ`'#Dh'#DhO0bQbOAN>yO0mQQO'#D_OOQ`AN>yAN>yO0rQbOAN>yO0wQRO,59wO1OQQO,59wOOQ`-E7f-E7fOOQ`G24eG24eO1TQbOG24eO1YQQO,59yO1_QQO1G/cOOQ`LD*PLD*PO.lQbO1G/eO/TQbO7+$}OOQ`7+%P7+%POOQ`<mAN>mO&|QbO'#D]OOQ`'#Dh'#DhO0eQbOAN>yO0pQQO'#D_OOQ`AN>yAN>yO0uQbOAN>yO0zQRO,59wO1RQQO,59wOOQ`-E7f-E7fOOQ`G24eG24eO1WQbOG24eO1]QQO,59yO1bQQO1G/cOOQ`LD*PLD*PO.oQbO1G/eO/WQbO7+$}OOQ`7+%P7+%POOQ`< spec_Identifier[value] || -1}], - tokenPrec: 756 + topRules: {"Program":[0,18]}, + specialized: [{term: 13, get: (value: any, stack: any) => (specializeKeyword(value, stack) << 1), external: specializeKeyword},{term: 13, get: (value: keyof typeof spec_Identifier) => spec_Identifier[value] || -1}], + tokenPrec: 759 }) diff --git a/src/parser/tests/basics.test.ts b/src/parser/tests/basics.test.ts index 1158bb1..f9f5e28 100644 --- a/src/parser/tests/basics.test.ts +++ b/src/parser/tests/basics.test.ts @@ -299,10 +299,10 @@ describe('Assign', () => { AssignableIdentifier add Eq = FunctionDef - keyword do + Do do Params - AssignableIdentifier a - AssignableIdentifier b + Identifier a + Identifier b colon : BinOp Identifier a diff --git a/src/parser/tests/dot-get.test.ts b/src/parser/tests/dot-get.test.ts index f2461bc..bcec05f 100644 --- a/src/parser/tests/dot-get.test.ts +++ b/src/parser/tests/dot-get.test.ts @@ -30,9 +30,9 @@ describe('DotGet', () => { test('function parameters are in scope within function body', () => { expect('do config: config.path end').toMatchTree(` FunctionDef - keyword do + Do do Params - AssignableIdentifier config + Identifier config colon : FunctionCallOrIdentifier DotGet @@ -45,9 +45,9 @@ describe('DotGet', () => { test('parameters out of scope outside function', () => { expect('do x: x.prop end; x.prop').toMatchTree(` FunctionDef - keyword do + Do do Params - AssignableIdentifier x + Identifier x colon : FunctionCallOrIdentifier DotGet @@ -64,10 +64,10 @@ describe('DotGet', () => { y.bar end`).toMatchTree(` FunctionDef - keyword do + Do do Params - AssignableIdentifier x - AssignableIdentifier y + Identifier x + Identifier y colon : FunctionCallOrIdentifier DotGet @@ -87,18 +87,18 @@ end`).toMatchTree(` do y: y.inner end end`).toMatchTree(` FunctionDef - keyword do + Do do Params - AssignableIdentifier x + Identifier x colon : FunctionCallOrIdentifier DotGet IdentifierBeforeDot x Identifier outer FunctionDef - keyword do + Do do Params - AssignableIdentifier y + Identifier y colon : FunctionCallOrIdentifier DotGet @@ -208,4 +208,70 @@ end`).toMatchTree(` PositionalArg Identifier prop`) }) + + test('readme.1 is Word when readme not in scope', () => { + expect('readme.1').toMatchTree(`Word readme.1`) + }) + + test('readme.1 is Word when used in function', () => { + expect('echo readme.1').toMatchTree(` + FunctionCall + Identifier echo + PositionalArg + Word readme.1`) + }) + + test('obj.1 is DotGet when obj is assigned', () => { + expect('obj = 5; obj.1').toMatchTree(` + Assign + AssignableIdentifier obj + Eq = + Number 5 + FunctionCallOrIdentifier + DotGet + IdentifierBeforeDot obj + Number 1 + `) + }) + + test('obj.1 arg is DotGet when obj is assigned', () => { + expect('obj = 5; obj.1').toMatchTree(` + Assign + AssignableIdentifier obj + Eq = + Number 5 + FunctionCallOrIdentifier + DotGet + IdentifierBeforeDot obj + Number 1 + `) + }) + + test('dot get index works as function w/ args', () => { + expect(`io = list (do x: echo x end); io.0 heya`).toMatchTree(` + Assign + AssignableIdentifier io + Eq = + FunctionCall + Identifier list + PositionalArg + ParenExpr + FunctionDef + Do do + Params + Identifier x + colon : + FunctionCall + Identifier echo + PositionalArg + Identifier x + keyword end + FunctionCall + DotGet + IdentifierBeforeDot io + Number 0 + PositionalArg + Identifier heya + `) + }) }) diff --git a/src/parser/tests/functions.test.ts b/src/parser/tests/functions.test.ts index 8fb1419..9249101 100644 --- a/src/parser/tests/functions.test.ts +++ b/src/parser/tests/functions.test.ts @@ -60,7 +60,7 @@ describe('Do', () => { test('parses function no parameters', () => { expect('do: 1 end').toMatchTree(` FunctionDef - keyword do + Do do Params colon : Number 1 @@ -70,9 +70,9 @@ describe('Do', () => { test('parses function with single parameter', () => { expect('do x: x + 1 end').toMatchTree(` FunctionDef - keyword do + Do do Params - AssignableIdentifier x + Identifier x colon : BinOp Identifier x @@ -84,10 +84,10 @@ describe('Do', () => { test('parses function with multiple parameters', () => { expect('do x y: x * y end').toMatchTree(` FunctionDef - keyword do + Do do Params - AssignableIdentifier x - AssignableIdentifier y + Identifier x + Identifier y colon : BinOp Identifier x @@ -102,10 +102,10 @@ describe('Do', () => { x + 9 end`).toMatchTree(` FunctionDef - keyword do + Do do Params - AssignableIdentifier x - AssignableIdentifier y + Identifier x + Identifier y colon : BinOp Identifier x @@ -124,9 +124,9 @@ end`).toMatchTree(` AssignableIdentifier fnnn Eq = FunctionDef - keyword do + Do do Params - AssignableIdentifier x + Identifier x colon : FunctionCallOrIdentifier Identifier x @@ -139,9 +139,9 @@ end`).toMatchTree(` AssignableIdentifier enddd Eq = FunctionDef - keyword do + Do do Params - AssignableIdentifier x + Identifier x colon : FunctionCallOrIdentifier Identifier x diff --git a/src/parser/tests/multiline.test.ts b/src/parser/tests/multiline.test.ts index 27bddc7..0d0a40d 100644 --- a/src/parser/tests/multiline.test.ts +++ b/src/parser/tests/multiline.test.ts @@ -24,10 +24,10 @@ describe('multiline', () => { AssignableIdentifier add Eq = FunctionDef - keyword do + Do do Params - AssignableIdentifier a - AssignableIdentifier b + Identifier a + Identifier b colon : Assign AssignableIdentifier result @@ -61,10 +61,10 @@ end Number 3 FunctionDef - keyword do + Do do Params - AssignableIdentifier x - AssignableIdentifier y + Identifier x + Identifier y colon : FunctionCallOrIdentifier Identifier x diff --git a/src/parser/tests/pipes.test.ts b/src/parser/tests/pipes.test.ts index 9d105b3..9e87114 100644 --- a/src/parser/tests/pipes.test.ts +++ b/src/parser/tests/pipes.test.ts @@ -75,13 +75,27 @@ describe('pipe expressions', () => { Identifier each PositionalArg FunctionDef - keyword do + Do do Params - AssignableIdentifier x + Identifier x colon : FunctionCallOrIdentifier Identifier x keyword end `) }) + + test(`double trouble (do keyword isn't over eager)`, () => { + expect(` + double 2 | double`).toMatchTree(` + PipeExpr + FunctionCall + Identifier double + PositionalArg + Number 2 + operator | + FunctionCallOrIdentifier + Identifier double + `) + }) }) diff --git a/src/parser/tokenizer.ts b/src/parser/tokenizer.ts index 8963ffb..beea8e2 100644 --- a/src/parser/tokenizer.ts +++ b/src/parser/tokenizer.ts @@ -1,5 +1,10 @@ import { ExternalTokenizer, InputStream, Stack } from '@lezer/lr' -import { Identifier, AssignableIdentifier, Word, IdentifierBeforeDot } from './shrimp.terms' +import { Identifier, AssignableIdentifier, Word, IdentifierBeforeDot, Do } from './shrimp.terms' + +// doobie doobie do (we need the `do` keyword to know when we're defining params) +export function specializeKeyword(ident: string) { + return ident === 'do' ? Do : -1 +} // The only chars that can't be words are whitespace, apostrophes, closing parens, and EOF. -- 2.50.1 From 219142140c256c9d6fb277d5d9f3be32666adbca Mon Sep 17 00:00:00 2001 From: Chris Wanstrath Date: Sun, 26 Oct 2025 22:32:07 -0700 Subject: [PATCH 3/4] compile dot number too --- src/compiler/utils.ts | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/src/compiler/utils.ts b/src/compiler/utils.ts index cbdd1bc..bcf0587 100644 --- a/src/compiler/utils.ts +++ b/src/compiler/utils.ts @@ -219,9 +219,9 @@ export const getDotGetParts = (node: SyntaxNode, input: string) => { ) } - if (property.type.id !== terms.Identifier) { + if (property.type.id !== terms.Identifier && property.type.id !== terms.Number) { throw new CompilerError( - `DotGet property must be an Identifier, got ${property.type.name}`, + `DotGet property must be an Identifier or Number, got ${property.type.name}`, property.from, property.to ) -- 2.50.1 From 318142dfbbac3adcdaa53b83951dd73226e8e38c Mon Sep 17 00:00:00 2001 From: Corey Johnson Date: Mon, 27 Oct 2025 12:45:59 -0700 Subject: [PATCH 4/4] Update shrimp.ts --- src/parser/shrimp.ts | 16 ++++++++-------- 1 file changed, 8 insertions(+), 8 deletions(-) diff --git a/src/parser/shrimp.ts b/src/parser/shrimp.ts index 1dfa9d0..1289469 100644 --- a/src/parser/shrimp.ts +++ b/src/parser/shrimp.ts @@ -7,11 +7,11 @@ import {highlighting} from "./highlight" const spec_Identifier = {__proto__:null,end:62, null:76, if:88, elseif:96, else:100} export const parser = LRParser.deserialize({ version: 14, - states: ".jQVQbOOO!QOpO'#CqO#^QcO'#CuO$WQRO'#CvO$fQcO'#DmO$}QbO'#DtOOQ`'#Cx'#CxO%VQbO'#CtO%wOSO'#C|OOQa'#Dr'#DrO&VQcO'#DqOOQ`'#Dn'#DnO&nQbO'#DmO&|QbO'#EQOOQ`'#DX'#DXO'kQRO'#DaOOQ`'#Dm'#DmO'pQQO'#DlOOQ`'#Dl'#DlOOQ`'#Db'#DbQVQbOOO'xObO,59]OOQa'#Dq'#DqOOQ`'#Cs'#CsO(QQbO'#DUOOQ`'#Dp'#DpOOQ`'#Dc'#DcO([QbO,59[O&|QbO,59bO&|QbO,59bOOQ`'#Dd'#DdO(xQbO'#CyO)QQQO,5:`O)qQRO'#CvO*RQRO,59`O*dQRO,59`O*_QQO,59`O+_QQO,59`O+gQbO'#DOO+oQWO'#DPOOOO'#Dz'#DzOOOO'#Df'#DfO,TOSO,59hOOQa,59h,59hO,cQbO'#DgO,kQbO,59ZO,|QRO,5:lO-TQQO,5:lO-YQbO,59{OOQ`,5:W,5:WOOQ`-E7`-E7`OOQa1G.w1G.wOOQ`,59p,59pOOQ`-E7a-E7aOOQa1G.|1G.|O-dQcO1G.|OOQ`-E7b-E7bO.OQbO1G/zO&|QbO,59cO&|QbO,59cOOQa1G.z1G.zOOOO,59j,59jOOOO,59k,59kOOOO-E7d-E7dOOQa1G/S1G/SO!VQbO'#CuOOQ`,5:R,5:ROOQ`-E7e-E7eO.]QbO1G0WOOQ`1G/g1G/gO.jQbO7+%fO.oQbO7+%gOOQO1G.}1G.}O.|QRO1G.}OOQ`'#DZ'#DZOOQ`7+%r7+%rO/WQbO7+%sOOQ`<mAN>mO&|QbO'#D]OOQ`'#Dh'#DhO0eQbOAN>yO0pQQO'#D_OOQ`AN>yAN>yO0uQbOAN>yO0zQRO,59wO1RQQO,59wOOQ`-E7f-E7fOOQ`G24eG24eO1WQbOG24eO1]QQO,59yO1bQQO1G/cOOQ`LD*PLD*PO.oQbO1G/eO/WQbO7+$}OOQ`7+%P7+%POOQ`<nAN>nO'PQbO'#D]OOQ`'#Dh'#DhO0vQbOAN>zO1RQQO'#D_OOQ`AN>zAN>zO1WQbOAN>zO1]QRO,59wO1dQQO,59wOOQ`-E7f-E7fOOQ`G24fG24fO1iQbOG24fO1nQQO,59yO1sQQO1G/cOOQ`LD*QLD*QO.rQbO1G/eO/cQbO7+$}OOQ`7+%P7+%POOQ`<i~RzOX#uXY$dYZ$}Zp#upq$dqs#ust%htu'Puw#uwx'Uxy'Zyz'tz{#u{|(_|}#u}!O(_!O!P#u!P!Q+R!Q![(|![!]3n!]!^$}!^#O#u#O#P4X#P#R#u#R#S4^#S#T#u#T#Y4w#Y#Z6V#Z#b4w#b#c:e#c#f4w#f#g;[#g#h4w#h#idS#zUqSOt#uuw#ux#O#u#P;'S#u;'S;=`$^<%lO#uS$aP;=`<%l#u^$kUqS!_YOt#uuw#ux#O#u#P;'S#u;'S;=`$^<%lO#uU%UUqS!kQOt#uuw#ux#O#u#P;'S#u;'S;=`$^<%lO#u^%oZqS!`YOY%hYZ#uZt%htu&buw%hwx&bx#O%h#O#P&b#P;'S%h;'S;=`&y<%lO%hY&gS!`YOY&bZ;'S&b;'S;=`&s<%lO&bY&vP;=`<%l&b^&|P;=`<%l%h~'UO!p~~'ZO!n~U'bUqS!hQOt#uuw#ux#O#u#P;'S#u;'S;=`$^<%lO#uU'{UqS!mQOt#uuw#ux#O#u#P;'S#u;'S;=`$^<%lO#uU(dWqSOt#uuw#ux!Q#u!Q![(|![#O#u#P;'S#u;'S;=`$^<%lO#uU)TYqSfQOt#uuw#ux!O#u!O!P)s!P!Q#u!Q![(|![#O#u#P;'S#u;'S;=`$^<%lO#uU)xWqSOt#uuw#ux!Q#u!Q![*b![#O#u#P;'S#u;'S;=`$^<%lO#uU*iWqSfQOt#uuw#ux!Q#u!Q![*b![#O#u#P;'S#u;'S;=`$^<%lO#uU+WWqSOt#uuw#ux!P#u!P!Q+p!Q#O#u#P;'S#u;'S;=`$^<%lO#uU+u^qSOY,qYZ#uZt,qtu-tuw,qwx-tx!P,q!P!Q#u!Q!},q!}#O2g#O#P0S#P;'S,q;'S;=`3h<%lO,qU,x^qSuQOY,qYZ#uZt,qtu-tuw,qwx-tx!P,q!P!Q0i!Q!},q!}#O2g#O#P0S#P;'S,q;'S;=`3h<%lO,qQ-yXuQOY-tZ!P-t!P!Q.f!Q!}-t!}#O/T#O#P0S#P;'S-t;'S;=`0c<%lO-tQ.iP!P!Q.lQ.qUuQ#Z#[.l#]#^.l#a#b.l#g#h.l#i#j.l#m#n.lQ/WVOY/TZ#O/T#O#P/m#P#Q-t#Q;'S/T;'S;=`/|<%lO/TQ/pSOY/TZ;'S/T;'S;=`/|<%lO/TQ0PP;=`<%l/TQ0VSOY-tZ;'S-t;'S;=`0c<%lO-tQ0fP;=`<%l-tU0nWqSOt#uuw#ux!P#u!P!Q1W!Q#O#u#P;'S#u;'S;=`$^<%lO#uU1_bqSuQOt#uuw#ux#O#u#P#Z#u#Z#[1W#[#]#u#]#^1W#^#a#u#a#b1W#b#g#u#g#h1W#h#i#u#i#j1W#j#m#u#m#n1W#n;'S#u;'S;=`$^<%lO#uU2l[qSOY2gYZ#uZt2gtu/Tuw2gwx/Tx#O2g#O#P/m#P#Q,q#Q;'S2g;'S;=`3b<%lO2gU3eP;=`<%l2gU3kP;=`<%l,qU3uUqSnQOt#uuw#ux#O#u#P;'S#u;'S;=`$^<%lO#u~4^O!q~U4eUqSwQOt#uuw#ux#O#u#P;'S#u;'S;=`$^<%lO#uU4|YqSOt#uuw#ux!_#u!_!`5l!`#O#u#P#T#u#T#o4w#o;'S#u;'S;=`$^<%lO#uU5sUyQqSOt#uuw#ux#O#u#P;'S#u;'S;=`$^<%lO#uU6[ZqSOt#uuw#ux!_#u!_!`5l!`#O#u#P#T#u#T#U6}#U#o4w#o;'S#u;'S;=`$^<%lO#uU7S[qSOt#uuw#ux!_#u!_!`5l!`#O#u#P#T#u#T#`4w#`#a7x#a#o4w#o;'S#u;'S;=`$^<%lO#uU7}[qSOt#uuw#ux!_#u!_!`5l!`#O#u#P#T#u#T#g4w#g#h8s#h#o4w#o;'S#u;'S;=`$^<%lO#uU8x[qSOt#uuw#ux!_#u!_!`5l!`#O#u#P#T#u#T#X4w#X#Y9n#Y#o4w#o;'S#u;'S;=`$^<%lO#uU9uYtQqSOt#uuw#ux!_#u!_!`5l!`#O#u#P#T#u#T#o4w#o;'S#u;'S;=`$^<%lO#u^:lY!rWqSOt#uuw#ux!_#u!_!`5l!`#O#u#P#T#u#T#o4w#o;'S#u;'S;=`$^<%lO#u^;cY!tWqSOt#uuw#ux!_#u!_!`5l!`#O#u#P#T#u#T#o4w#o;'S#u;'S;=`$^<%lO#u^QUzQqSOt#uuw#ux#O#u#P;'S#u;'S;=`$^<%lO#u~>iO!w~", + tokenizers: [operatorTokenizer, 1, 2, 3, tokenizer, new LocalTokenGroup("[~RP!O!PU~ZO!d~~", 11)], topRules: {"Program":[0,18]}, specialized: [{term: 13, get: (value: any, stack: any) => (specializeKeyword(value, stack) << 1), external: specializeKeyword},{term: 13, get: (value: keyof typeof spec_Identifier) => spec_Identifier[value] || -1}], - tokenPrec: 759 + tokenPrec: 776 }) -- 2.50.1