From 866da8686217e1573e56679ff776769fc5dd1dd1 Mon Sep 17 00:00:00 2001 From: Chris Wanstrath Date: Thu, 6 Nov 2025 13:32:31 -0800 Subject: [PATCH] curly -> Curly --- src/parser/shrimp.grammar | 4 +- src/parser/shrimp.terms.ts | 84 ++++++++++++++++---------------- src/parser/shrimp.ts | 18 +++---- src/parser/tests/strings.test.ts | 15 +++--- src/parser/tokenizer.ts | 6 +-- 5 files changed, 65 insertions(+), 62 deletions(-) diff --git a/src/parser/shrimp.grammar b/src/parser/shrimp.grammar index a101691..91a9faf 100644 --- a/src/parser/shrimp.grammar +++ b/src/parser/shrimp.grammar @@ -37,7 +37,7 @@ finally { @specialize[@name=keyword] } throw { @specialize[@name=keyword] } null { @specialize[@name=Null] } -@external tokens tokenizer from "./tokenizer" { Identifier, AssignableIdentifier, Word, IdentifierBeforeDot, curlyString } +@external tokens tokenizer from "./tokenizer" { Identifier, AssignableIdentifier, Word, IdentifierBeforeDot, CurlyString } @external specialize {Identifier} specializeKeyword from "./tokenizer" { Do } @precedence { @@ -206,7 +206,7 @@ expression { } String { - "'" stringContent* "'" | curlyString + "'" stringContent* "'" | CurlyString } } diff --git a/src/parser/shrimp.terms.ts b/src/parser/shrimp.terms.ts index 3b5dc00..b5b68e0 100644 --- a/src/parser/shrimp.terms.ts +++ b/src/parser/shrimp.terms.ts @@ -23,45 +23,45 @@ export const AssignableIdentifier = 21, Word = 22, IdentifierBeforeDot = 23, - curlyString = 85, - Do = 24, - Comment = 25, - Program = 26, - PipeExpr = 27, - FunctionCall = 28, - DotGet = 29, - Number = 30, - ParenExpr = 31, - IfExpr = 32, - keyword = 70, - ConditionalOp = 34, - String = 35, - StringFragment = 36, - Interpolation = 37, - EscapeSeq = 38, - Boolean = 39, - Regex = 40, - Dict = 41, - NamedArg = 42, - NamedArgPrefix = 43, - FunctionDef = 44, - Params = 45, - NamedParam = 46, - Null = 47, - colon = 48, - CatchExpr = 49, - Block = 51, - FinallyExpr = 52, - Underscore = 55, - Array = 56, - ElseIfExpr = 57, - ElseExpr = 59, - FunctionCallOrIdentifier = 60, - BinOp = 61, - PositionalArg = 62, - WhileExpr = 64, - FunctionCallWithBlock = 66, - TryExpr = 67, - Throw = 69, - CompoundAssign = 71, - Assign = 72 + CurlyString = 24, + Do = 25, + Comment = 26, + Program = 27, + PipeExpr = 28, + FunctionCall = 29, + DotGet = 30, + Number = 31, + ParenExpr = 32, + IfExpr = 33, + keyword = 71, + ConditionalOp = 35, + String = 36, + StringFragment = 37, + Interpolation = 38, + EscapeSeq = 39, + Boolean = 40, + Regex = 41, + Dict = 42, + NamedArg = 43, + NamedArgPrefix = 44, + FunctionDef = 45, + Params = 46, + NamedParam = 47, + Null = 48, + colon = 49, + CatchExpr = 50, + Block = 52, + FinallyExpr = 53, + Underscore = 56, + Array = 57, + ElseIfExpr = 58, + ElseExpr = 60, + FunctionCallOrIdentifier = 61, + BinOp = 62, + PositionalArg = 63, + WhileExpr = 65, + FunctionCallWithBlock = 67, + TryExpr = 68, + Throw = 70, + CompoundAssign = 72, + Assign = 73 diff --git a/src/parser/shrimp.ts b/src/parser/shrimp.ts index a2086b6..ea588a3 100644 --- a/src/parser/shrimp.ts +++ b/src/parser/shrimp.ts @@ -4,24 +4,24 @@ import {operatorTokenizer} from "./operatorTokenizer" import {tokenizer, specializeKeyword} from "./tokenizer" 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} +const spec_Identifier = {__proto__:null,if:68, null:96, catch:102, finally:108, end:110, else:118, while:132, try:138, throw:142} export const parser = LRParser.deserialize({ version: 14, - states: "9bQYQbOOO!gOSO'#DPOOQa'#DP'#DPOOQa'#DV'#DVO#sQbO'#DfO%XQcO'#E_OOQa'#E_'#E_O&bQcO'#E_O'dQcO'#E^O'zQcO'#E^O)jQRO'#DOO*yQcO'#EXO+TQcO'#EXO+eQbO'#C{O,cOpO'#CyOOQ`'#EY'#EYO,hQbO'#EXO,rQRO'#DuOOQ`'#EX'#EXO-WQQO'#EWOOQ`'#EW'#EWOOQ`'#Dw'#DwQYQbOOO-`QbO'#DYO-kQbO'#C|O.cQbO'#DnO/ZQQO'#DqO.cQbO'#DsO/`QbO'#DRO/hQWO'#DSOOOO'#Ea'#EaOOOO'#Dx'#DxO/|OSO,59kOOQa,59k,59kOOQ`'#Dy'#DyO0[QbO,5:QO0cQbO'#DWO0mQQO,59qOOQa,5:Q,5:QO0xQbO,5:QOOQa'#E^'#E^OOQ`'#Dl'#DlOOQ`'#Em'#EmOOQ`'#EQ'#EQO1SQbO,59dO1|QbO,5:bO.cQbO,59jO.cQbO,59jO.cQbO,59jO.cQbO,5:VO.cQbO,5:VO.cQbO,5:VO2^QRO,59gO2eQRO,59gO2pQRO,59gO2kQQO,59gO3RQQO,59gO3ZObO,59eO3fQbO'#ERO3qQbO,59cO4]QbO,5:[O1|QbO,5:aOOQ`,5:r,5:rOOQ`-E7u-E7uOOQ`'#Dz'#DzO4pQbO'#DZO4{QbO'#D[OOQO'#D{'#D{O4sQQO'#DZO5^QQO,59tO5cQcO'#E^O6wQRO'#E]O7OQRO'#E]OOQO'#E]'#E]O7ZQQO,59hO7`QRO,5:YO7gQRO,5:YO4]QbO,5:]O7rQcO,5:_O8nQcO,5:_O8xQcO,5:_OOOO,59m,59mOOOO,59n,59nOOOO-E7v-E7vOOQa1G/V1G/VOOQ`-E7w-E7wO9YQQO1G/]OOQa1G/l1G/lO9eQbO1G/lOOQ`,59r,59rOOQO'#D}'#D}O9YQQO1G/]OOQa1G/]1G/]OOQ`'#EO'#EOO9eQbO1G/lOOQ`-E8O-E8OOOQ`1G/|1G/|OOQa1G/U1G/UO:pQcO1G/UO:wQcO1G/UO;OQcO1G/UOOQa1G/q1G/qO;wQcO1G/qOUQbO'#DaO>uQbO1G/vOOQ`1G/{1G/{OOQ`-E7x-E7xO?QQQO,59uOOQO,59v,59vOOQO-E7y-E7yO?YQbO1G/`O4]QbO1G/SO4]QbO1G/tO?mQbO1G/wO?xQQO7+$wOOQa7+$w7+$wO@TQbO7+%WOOQa7+%W7+%WOOQO-E7{-E7{OOQ`-E7|-E7|OOQ`'#D|'#D|O@_QQO'#D|O@dQbO'#EjOOQ`,59{,59{OATQbO'#D_OAYQQO'#DbOOQ`7+%b7+%bOA_QbO7+%bOAdQbO7+%bOAlQbO7+$zOAwQbO7+$zOBeQbO7+$nOBmQbO7+%`OOQ`7+%c7+%cOBrQbO7+%cOBwQbO7+%cOOQa<hAN>hOOQ`AN>QAN>QOD_QbOAN>QODdQbOAN>QOOQ`-E7}-E7}OOQ`AN=tAN=tODlQbOAN=tO-kQbO,5:RO4]QbO,5:TOOQ`AN>iAN>iOOQ`7+%P7+%POOQ`G23lG23lODqQbOG23lPDvQbO'#DgOOQ`G23`G23`OD{QQO1G/mOOQ`1G/o1G/oOOQ`LD)WLD)WO4]QbO7+%XOOQ`<UQbO'#DbO>uQbO1G/wOOQ`1G/|1G/|OOQ`-E7y-E7yO?QQQO,59vOOQO,59w,59wOOQO-E7z-E7zO?YQbO1G/aO4]QbO1G/TO4]QbO1G/uO?mQbO1G/xO?xQQO7+$xOOQa7+$x7+$xO@TQbO7+%XOOQa7+%X7+%XOOQO-E7|-E7|OOQ`-E7}-E7}OOQ`'#D}'#D}O@_QQO'#D}O@dQbO'#EjOOQ`,59|,59|OATQbO'#D`OAYQQO'#DcOOQ`7+%c7+%cOA_QbO7+%cOAdQbO7+%cOAlQbO7+${OAwQbO7+${OBeQbO7+$oOBmQbO7+%aOOQ`7+%d7+%dOBrQbO7+%dOBwQbO7+%dOOQa<iAN>iOOQ`AN>RAN>ROD_QbOAN>RODdQbOAN>ROOQ`-E8O-E8OOOQ`AN=uAN=uODlQbOAN=uO-kQbO,5:SO4]QbO,5:UOOQ`AN>jAN>jOOQ`7+%Q7+%QOOQ`G23mG23mODqQbOG23mPDvQbO'#DhOOQ`G23aG23aOD{QQO1G/nOOQ`1G/p1G/pOOQ`LD)XLD)XO4]QbO7+%YOOQ`<c#Y#o,w#o;'S#{;'S;=`$d<%lO#{U>j[wQtSOt#{uw#{x}#{}!O,w!O!_#{!_!`-r!`#O#{#P#T#{#T#o,w#o;'S#{;'S;=`$d<%lO#{^?g[#WWtSOt#{uw#{x}#{}!O,w!O!_#{!_!`-r!`#O#{#P#T#{#T#o,w#o;'S#{;'S;=`$d<%lO#{^@d[#YWtSOt#{uw#{x}#{}!O,w!O!_#{!_!`-r!`#O#{#P#T#{#T#o,w#o;'S#{;'S;=`$d<%lO#{^Aa^#XWtSOt#{uw#{x}#{}!O,w!O!_#{!_!`-r!`#O#{#P#T#{#T#f,w#f#gB]#g#o,w#o;'S#{;'S;=`$d<%lO#{UBb^tSOt#{uw#{x}#{}!O,w!O!_#{!_!`-r!`#O#{#P#T#{#T#i,w#i#j=b#j#o,w#o;'S#{;'S;=`$d<%lO#{UCeU!aQtSOt#{uw#{x#O#{#P;'S#{;'S;=`$d<%lO#{~C|O#b~", + tokenData: "C|~R|OX#{XY$jYZ%TZp#{pq$jqs#{st%ntu'tuw#{wx'yxy(Oyz(iz{#{{|)S|}#{}!O+v!O!P#{!P!Q.]!Q![)q![!]6x!]!^%T!^!}#{!}#O7c#O#P9X#P#Q9^#Q#R#{#R#S9w#S#T#{#T#Y,w#Y#Z:b#Z#b,w#b#c?`#c#f,w#f#g@]#g#h,w#h#iAY#i#o,w#o#p#{#p#qC^#q;'S#{;'S;=`$d<%l~#{~O#{~~CwS$QUuSOt#{uw#{x#O#{#P;'S#{;'S;=`$d<%lO#{S$gP;=`<%l#{^$qUuS!yYOt#{uw#{x#O#{#P;'S#{;'S;=`$d<%lO#{U%[UuS#]QOt#{uw#{x#O#{#P;'S#{;'S;=`$d<%lO#{^%sWuSOp#{pq&]qt#{uw#{x#O#{#P;'S#{;'S;=`$d<%lO#{^&dZjYuSOY&]YZ#{Zt&]tu'Vuw&]wx'Vx#O&]#O#P'V#P;'S&];'S;=`'n<%lO&]Y'[SjYOY'VZ;'S'V;'S;=`'h<%lO'VY'kP;=`<%l'V^'qP;=`<%l&]~'yO#U~~(OO#S~U(VUuS#OQOt#{uw#{x#O#{#P;'S#{;'S;=`$d<%lO#{U(pUuS#`QOt#{uw#{x#O#{#P;'S#{;'S;=`$d<%lO#{U)XWuSOt#{uw#{x!Q#{!Q![)q![#O#{#P;'S#{;'S;=`$d<%lO#{U)xYuSoQOt#{uw#{x!O#{!O!P*h!P!Q#{!Q![)q![#O#{#P;'S#{;'S;=`$d<%lO#{U*mWuSOt#{uw#{x!Q#{!Q![+V![#O#{#P;'S#{;'S;=`$d<%lO#{U+^WuSoQOt#{uw#{x!Q#{!Q![+V![#O#{#P;'S#{;'S;=`$d<%lO#{U+{^uSOt#{uw#{x}#{}!O,w!O!Q#{!Q![)q![!_#{!_!`-r!`#O#{#P#T#{#T#o,w#o;'S#{;'S;=`$d<%lO#{U,|[uSOt#{uw#{x}#{}!O,w!O!_#{!_!`-r!`#O#{#P#T#{#T#o,w#o;'S#{;'S;=`$d<%lO#{U-yU|QuSOt#{uw#{x#O#{#P;'S#{;'S;=`$d<%lO#{U.bWuSOt#{uw#{x!P#{!P!Q.z!Q#O#{#P;'S#{;'S;=`$d<%lO#{U/P^uSOY/{YZ#{Zt/{tu1Ouw/{wx1Ox!P/{!P!Q#{!Q!}/{!}#O5q#O#P3^#P;'S/{;'S;=`6r<%lO/{U0S^uSyQOY/{YZ#{Zt/{tu1Ouw/{wx1Ox!P/{!P!Q3s!Q!}/{!}#O5q#O#P3^#P;'S/{;'S;=`6r<%lO/{Q1TXyQOY1OZ!P1O!P!Q1p!Q!}1O!}#O2_#O#P3^#P;'S1O;'S;=`3m<%lO1OQ1sP!P!Q1vQ1{UyQ#Z#[1v#]#^1v#a#b1v#g#h1v#i#j1v#m#n1vQ2bVOY2_Z#O2_#O#P2w#P#Q1O#Q;'S2_;'S;=`3W<%lO2_Q2zSOY2_Z;'S2_;'S;=`3W<%lO2_Q3ZP;=`<%l2_Q3aSOY1OZ;'S1O;'S;=`3m<%lO1OQ3pP;=`<%l1OU3xWuSOt#{uw#{x!P#{!P!Q4b!Q#O#{#P;'S#{;'S;=`$d<%lO#{U4ibuSyQOt#{uw#{x#O#{#P#Z#{#Z#[4b#[#]#{#]#^4b#^#a#{#a#b4b#b#g#{#g#h4b#h#i#{#i#j4b#j#m#{#m#n4b#n;'S#{;'S;=`$d<%lO#{U5v[uSOY5qYZ#{Zt5qtu2_uw5qwx2_x#O5q#O#P2w#P#Q/{#Q;'S5q;'S;=`6l<%lO5qU6oP;=`<%l5qU6uP;=`<%l/{U7PUuS!RQOt#{uw#{x#O#{#P;'S#{;'S;=`$d<%lO#{U7jW#[QuSOt#{uw#{x!_#{!_!`8S!`#O#{#P;'S#{;'S;=`$d<%lO#{U8XVuSOt#{uw#{x#O#{#P#Q8n#Q;'S#{;'S;=`$d<%lO#{U8uU#ZQuSOt#{uw#{x#O#{#P;'S#{;'S;=`$d<%lO#{~9^O#V~U9eU#_QuSOt#{uw#{x#O#{#P;'S#{;'S;=`$d<%lO#{U:OUuS!YQOt#{uw#{x#O#{#P;'S#{;'S;=`$d<%lO#{U:g]uSOt#{uw#{x}#{}!O,w!O!_#{!_!`-r!`#O#{#P#T#{#T#U;`#U#o,w#o;'S#{;'S;=`$d<%lO#{U;e^uSOt#{uw#{x}#{}!O,w!O!_#{!_!`-r!`#O#{#P#T#{#T#`,w#`#ac#Y#o,w#o;'S#{;'S;=`$d<%lO#{U>j[xQuSOt#{uw#{x}#{}!O,w!O!_#{!_!`-r!`#O#{#P#T#{#T#o,w#o;'S#{;'S;=`$d<%lO#{^?g[#WWuSOt#{uw#{x}#{}!O,w!O!_#{!_!`-r!`#O#{#P#T#{#T#o,w#o;'S#{;'S;=`$d<%lO#{^@d[#YWuSOt#{uw#{x}#{}!O,w!O!_#{!_!`-r!`#O#{#P#T#{#T#o,w#o;'S#{;'S;=`$d<%lO#{^Aa^#XWuSOt#{uw#{x}#{}!O,w!O!_#{!_!`-r!`#O#{#P#T#{#T#f,w#f#gB]#g#o,w#o;'S#{;'S;=`$d<%lO#{UBb^uSOt#{uw#{x}#{}!O,w!O!_#{!_!`-r!`#O#{#P#T#{#T#i,w#i#j=b#j#o,w#o;'S#{;'S;=`$d<%lO#{UCeU!bQuSOt#{uw#{x#O#{#P;'S#{;'S;=`$d<%lO#{~C|O#b~", tokenizers: [operatorTokenizer, 1, 2, 3, tokenizer, new LocalTokenGroup("[~RP!O!PU~ZO!}~~", 11)], - topRules: {"Program":[0,26]}, + topRules: {"Program":[0,27]}, specialized: [{term: 20, get: (value: any, stack: any) => (specializeKeyword(value, stack) << 1), external: specializeKeyword},{term: 20, get: (value: keyof typeof spec_Identifier) => spec_Identifier[value] || -1}], tokenPrec: 1658 }) diff --git a/src/parser/tests/strings.test.ts b/src/parser/tests/strings.test.ts index 288315b..22f780b 100644 --- a/src/parser/tests/strings.test.ts +++ b/src/parser/tests/strings.test.ts @@ -131,27 +131,30 @@ describe('string escape sequences', () => { describe('curly strings', () => { test('work on one line', () => { expect('{ one two three }').toMatchTree(` - String one two three + String + CurlyString { one two three } `) }) test('work on multiple lines', () => { - expect(`{ + expect(`{ one two three }`).toMatchTree(` - String + String + CurlyString { one two - three `) + three }`) }) test('can contain other curlies', () => { expect(`{ { one } two { three } }`).toMatchTree(` - String { one } + String + CurlyString { { one } two - { three } `) + { three } }`) }) }) \ No newline at end of file diff --git a/src/parser/tokenizer.ts b/src/parser/tokenizer.ts index 0f1ffac..45d901b 100644 --- a/src/parser/tokenizer.ts +++ b/src/parser/tokenizer.ts @@ -1,5 +1,5 @@ import { ExternalTokenizer, InputStream, Stack } from '@lezer/lr' -import { Identifier, AssignableIdentifier, Word, IdentifierBeforeDot, Do, curlyString } from './shrimp.terms' +import { Identifier, AssignableIdentifier, Word, IdentifierBeforeDot, Do, CurlyString } from './shrimp.terms' // doobie doobie do (we need the `do` keyword to know when we're defining params) export function specializeKeyword(ident: string) { @@ -164,7 +164,7 @@ const consumeRestOfWord = (input: InputStream, startPos: number, canBeWord: bool } const consumeCurlyString = (input: InputStream, stack: Stack) => { - if (!stack.canShift(curlyString)) return + if (!stack.canShift(CurlyString)) return let depth = 0 let pos = 0 @@ -185,7 +185,7 @@ const consumeCurlyString = (input: InputStream, stack: Stack) => { pos++ } - input.acceptToken(curlyString, pos) + input.acceptToken(CurlyString, pos) } // Check if this identifier is in scope (for property access detection)