KCL: Support non-ASCII identifiers (#7525)

Both human and LLMs want to write KCL code in non-English languages. This is important and we should support it.

Note that errors are currently a bit broken with non-ASCII identifiers, see #4327
This commit is contained in:
Adam Chalmers
2025-06-19 09:10:21 -05:00
committed by GitHub
parent 9eaacc2a51
commit 9dd6e3e852
12 changed files with 655 additions and 11 deletions

View File

@ -0,0 +1,18 @@
---
source: kcl-lib/src/simulation_tests.rs
description: Artifact commands non_english_identifiers.kcl
---
{
"rust/kcl-lib/tests/non_english_identifiers/input.kcl": [],
"std::appearance": [],
"std::array": [],
"std::math": [],
"std::prelude": [],
"std::sketch": [],
"std::solid": [],
"std::sweep": [],
"std::transform": [],
"std::turns": [],
"std::types": [],
"std::units": []
}

View File

@ -0,0 +1,6 @@
---
source: kcl-lib/src/simulation_tests.rs
description: Artifact graph flowchart non_english_identifiers.kcl
extension: md
snapshot_kind: binary
---

View File

@ -0,0 +1,3 @@
```mermaid
flowchart LR
```

View File

@ -0,0 +1,284 @@
---
source: kcl-lib/src/simulation_tests.rs
description: Result of parsing non_english_identifiers.kcl
---
{
"Ok": {
"body": [
{
"commentStart": 0,
"declaration": {
"commentStart": 0,
"end": 0,
"id": {
"commentStart": 0,
"end": 0,
"name": "comprimentoTotal",
"start": 0,
"type": "Identifier"
},
"init": {
"commentStart": 0,
"end": 0,
"raw": "100",
"start": 0,
"type": "Literal",
"type": "Literal",
"value": {
"value": 100.0,
"suffix": "None"
}
},
"start": 0,
"type": "VariableDeclarator"
},
"end": 0,
"kind": "const",
"start": 0,
"type": "VariableDeclaration",
"type": "VariableDeclaration"
},
{
"commentStart": 0,
"declaration": {
"commentStart": 0,
"end": 0,
"id": {
"commentStart": 0,
"end": 0,
"name": "亞當",
"start": 0,
"type": "Identifier"
},
"init": {
"commentStart": 0,
"end": 0,
"raw": "100",
"start": 0,
"type": "Literal",
"type": "Literal",
"value": {
"value": 100.0,
"suffix": "None"
}
},
"start": 0,
"type": "VariableDeclarator"
},
"end": 0,
"kind": "const",
"start": 0,
"type": "VariableDeclaration",
"type": "VariableDeclaration"
},
{
"commentStart": 0,
"declaration": {
"commentStart": 0,
"end": 0,
"id": {
"commentStart": 0,
"end": 0,
"name": "comprimentoRosca",
"start": 0,
"type": "Identifier"
},
"init": {
"commentStart": 0,
"end": 0,
"left": {
"abs_path": false,
"commentStart": 0,
"end": 0,
"name": {
"commentStart": 0,
"end": 0,
"name": "亞當",
"start": 0,
"type": "Identifier"
},
"path": [],
"start": 0,
"type": "Name",
"type": "Name"
},
"operator": "*",
"right": {
"commentStart": 0,
"end": 0,
"raw": "0.8",
"start": 0,
"type": "Literal",
"type": "Literal",
"value": {
"value": 0.8,
"suffix": "None"
}
},
"start": 0,
"type": "BinaryExpression",
"type": "BinaryExpression"
},
"start": 0,
"type": "VariableDeclarator"
},
"end": 0,
"kind": "const",
"start": 0,
"type": "VariableDeclaration",
"type": "VariableDeclaration"
},
{
"commentStart": 0,
"declaration": {
"commentStart": 0,
"end": 0,
"id": {
"commentStart": 0,
"end": 0,
"name": "comprimentoCabeça",
"start": 0,
"type": "Identifier"
},
"init": {
"commentStart": 0,
"end": 0,
"left": {
"abs_path": false,
"commentStart": 0,
"end": 0,
"name": {
"commentStart": 0,
"end": 0,
"name": "comprimentoTotal",
"start": 0,
"type": "Identifier"
},
"path": [],
"start": 0,
"type": "Name",
"type": "Name"
},
"operator": "-",
"right": {
"abs_path": false,
"commentStart": 0,
"end": 0,
"name": {
"commentStart": 0,
"end": 0,
"name": "comprimentoRosca",
"start": 0,
"type": "Identifier"
},
"path": [],
"start": 0,
"type": "Name",
"type": "Name"
},
"start": 0,
"type": "BinaryExpression",
"type": "BinaryExpression"
},
"start": 0,
"type": "VariableDeclarator"
},
"end": 0,
"kind": "const",
"start": 0,
"type": "VariableDeclaration",
"type": "VariableDeclaration"
},
{
"commentStart": 0,
"end": 0,
"expression": {
"arguments": [
{
"type": "LabeledArg",
"label": {
"commentStart": 0,
"end": 0,
"name": "isEqualTo",
"start": 0,
"type": "Identifier"
},
"arg": {
"commentStart": 0,
"end": 0,
"raw": "20",
"start": 0,
"type": "Literal",
"type": "Literal",
"value": {
"value": 20.0,
"suffix": "None"
}
}
}
],
"callee": {
"abs_path": false,
"commentStart": 0,
"end": 0,
"name": {
"commentStart": 0,
"end": 0,
"name": "assert",
"start": 0,
"type": "Identifier"
},
"path": [],
"start": 0,
"type": "Name"
},
"commentStart": 0,
"end": 0,
"start": 0,
"type": "CallExpressionKw",
"type": "CallExpressionKw",
"unlabeled": {
"abs_path": false,
"commentStart": 0,
"end": 0,
"name": {
"commentStart": 0,
"end": 0,
"name": "comprimentoCabeça",
"start": 0,
"type": "Identifier"
},
"path": [],
"start": 0,
"type": "Name",
"type": "Name"
}
},
"start": 0,
"type": "ExpressionStatement",
"type": "ExpressionStatement"
}
],
"commentStart": 0,
"end": 0,
"nonCodeMeta": {
"nonCodeNodes": {
"2": [
{
"commentStart": 0,
"end": 0,
"start": 0,
"type": "NonCodeNode",
"value": {
"type": "inlineComment",
"value": "80% do comprimento total é roscado",
"style": "line"
}
}
]
},
"startNodes": []
},
"start": 0
}
}

View File

@ -0,0 +1,5 @@
comprimentoTotal = 100
亞當 = 100
comprimentoRosca = 亞當 * 0.8 // 80% do comprimento total é roscado
comprimentoCabeça = comprimentoTotal - comprimentoRosca
assert(comprimentoCabeça, isEqualTo = 20)

View File

@ -0,0 +1,229 @@
---
source: kcl-lib/src/simulation_tests.rs
description: Operations executed non_english_identifiers.kcl
---
{
"rust/kcl-lib/tests/non_english_identifiers/input.kcl": [
{
"type": "VariableDeclaration",
"name": "comprimentoTotal",
"value": {
"type": "Number",
"value": 100.0,
"ty": {
"type": "Default",
"len": {
"type": "Mm"
},
"angle": {
"type": "Degrees"
}
}
},
"visibility": "default",
"nodePath": {
"steps": [
{
"type": "ProgramBodyItem",
"index": 0
},
{
"type": "VariableDeclarationDeclaration"
},
{
"type": "VariableDeclarationInit"
}
]
},
"sourceRange": []
},
{
"type": "VariableDeclaration",
"name": "亞當",
"value": {
"type": "Number",
"value": 100.0,
"ty": {
"type": "Default",
"len": {
"type": "Mm"
},
"angle": {
"type": "Degrees"
}
}
},
"visibility": "default",
"nodePath": {
"steps": [
{
"type": "ProgramBodyItem",
"index": 1
},
{
"type": "VariableDeclarationDeclaration"
},
{
"type": "VariableDeclarationInit"
}
]
},
"sourceRange": []
},
{
"type": "VariableDeclaration",
"name": "comprimentoRosca",
"value": {
"type": "Number",
"value": 80.0,
"ty": {
"type": "Default",
"len": {
"type": "Mm"
},
"angle": {
"type": "Degrees"
}
}
},
"visibility": "default",
"nodePath": {
"steps": [
{
"type": "ProgramBodyItem",
"index": 2
},
{
"type": "VariableDeclarationDeclaration"
},
{
"type": "VariableDeclarationInit"
}
]
},
"sourceRange": []
},
{
"type": "VariableDeclaration",
"name": "comprimentoCabeça",
"value": {
"type": "Number",
"value": 20.0,
"ty": {
"type": "Default",
"len": {
"type": "Mm"
},
"angle": {
"type": "Degrees"
}
}
},
"visibility": "default",
"nodePath": {
"steps": [
{
"type": "ProgramBodyItem",
"index": 3
},
{
"type": "VariableDeclarationDeclaration"
},
{
"type": "VariableDeclarationInit"
}
]
},
"sourceRange": []
}
],
"std::appearance": [],
"std::array": [],
"std::math": [
{
"type": "VariableDeclaration",
"name": "PI",
"value": {
"type": "Number",
"value": 3.141592653589793,
"ty": {
"type": "Unknown"
}
},
"visibility": "export",
"nodePath": {
"steps": []
},
"sourceRange": []
},
{
"type": "VariableDeclaration",
"name": "E",
"value": {
"type": "Number",
"value": 2.718281828459045,
"ty": {
"type": "Known",
"type": "Count"
}
},
"visibility": "export",
"nodePath": {
"steps": []
},
"sourceRange": []
},
{
"type": "VariableDeclaration",
"name": "TAU",
"value": {
"type": "Number",
"value": 6.283185307179586,
"ty": {
"type": "Known",
"type": "Count"
}
},
"visibility": "export",
"nodePath": {
"steps": []
},
"sourceRange": []
}
],
"std::prelude": [
{
"type": "VariableDeclaration",
"name": "START",
"value": {
"type": "String",
"value": "start"
},
"visibility": "export",
"nodePath": {
"steps": []
},
"sourceRange": []
},
{
"type": "VariableDeclaration",
"name": "END",
"value": {
"type": "String",
"value": "end"
},
"visibility": "export",
"nodePath": {
"steps": []
},
"sourceRange": []
}
],
"std::sketch": [],
"std::solid": [],
"std::sweep": [],
"std::transform": [],
"std::turns": [],
"std::types": [],
"std::units": []
}

View File

@ -0,0 +1,58 @@
---
source: kcl-lib/src/simulation_tests.rs
description: Variables in memory after executing non_english_identifiers.kcl
---
{
"comprimentoCabeça": {
"type": "Number",
"value": 20.0,
"ty": {
"type": "Default",
"len": {
"type": "Mm"
},
"angle": {
"type": "Degrees"
}
}
},
"comprimentoRosca": {
"type": "Number",
"value": 80.0,
"ty": {
"type": "Default",
"len": {
"type": "Mm"
},
"angle": {
"type": "Degrees"
}
}
},
"comprimentoTotal": {
"type": "Number",
"value": 100.0,
"ty": {
"type": "Default",
"len": {
"type": "Mm"
},
"angle": {
"type": "Degrees"
}
}
},
"亞當": {
"type": "Number",
"value": 100.0,
"ty": {
"type": "Default",
"len": {
"type": "Mm"
},
"angle": {
"type": "Degrees"
}
}
}
}

Binary file not shown.

After

Width:  |  Height:  |  Size: 19 KiB

View File

@ -0,0 +1,9 @@
---
source: kcl-lib/src/simulation_tests.rs
description: Result of unparsing non_english_identifiers.kcl
---
comprimentoTotal = 100
亞當 = 100
comprimentoRosca = 亞當 * 0.8 // 80% do comprimento total é roscado
comprimentoCabeça = comprimentoTotal - comprimentoRosca
assert(comprimentoCabeça, isEqualTo = 20)