This is an archive of the discontinued LLVM Phabricator instance.

Differential D125458

[mlir] Significantly overhaul the textmate grammar
ClosedPublic

Authored by rriddle on May 12 2022, 3:03 AM.

Details

Reviewers
mehdi_amini
jpienaar
Commits
rG86f5caeee955: [mlir] Significantly overhaul the textmate grammar
Summary

The current grammar is really crusty, only supports a handful of
cases, and is also out-of-date after various refactorings. This commit
refactors the textmate grammar to handle significantly more cases,
and now provides proper coloring for a majority of cases (including
dialect attributes, operations, types, etc.)

Diff Detail

Event Timeline

rriddle created this revision.May 12 2022, 3:03 AM
Herald added a project: Restricted Project. · View Herald TranscriptMay 12 2022, 3:03 AM
Herald added subscribers: sdasgup3, wenzhicui, wrengr and 20 others. · View Herald Transcript
rriddle requested review of this revision.May 12 2022, 3:03 AM
Herald added a project: Restricted Project. · View Herald TranscriptMay 12 2022, 3:03 AM
Herald added subscribers: stephenneuendorffer, nicolasvasilache. · View Herald Transcript
rriddle added reviewers: mehdi_amini, jpienaar.May 12 2022, 3:04 AM
rriddle added a comment.May 12 2022, 3:06 AM

I validated the results using most of our upstream test cases. I may have missed some potential edge cases, but this is a much better iteration point that what we had before. There are a few places where we miscolor, but that is mostly because it's impossible in some cases to differentiate a region from an attribute dictionary.

Harbormaster completed remote builds in B164068: Diff 428895.May 12 2022, 4:25 AM
rriddle updated this revision to Diff 428991.May 12 2022, 10:16 AM
Harbormaster completed remote builds in B164135: Diff 428991.May 12 2022, 11:19 AM
jpienaar accepted this revision.May 12 2022, 3:09 PM

LGTM, could you add a before and after screenshot of a test? (Just for easy visual check)

This revision is now accepted and ready to land.May 12 2022, 3:09 PM
rriddle added a comment.May 12 2022, 3:25 PM

Here is a quick screencap of PDL before and after:

Closed by commit rG86f5caeee955: [mlir] Significantly overhaul the textmate grammar (authored by rriddle). · Explain WhyMay 12 2022, 3:50 PM
This revision was automatically updated to reflect the committed changes.
rriddle added a commit: rG86f5caeee955: [mlir] Significantly overhaul the textmate grammar.

Revision Contents

PathSize
mlir/
utils/
textmate/
413 lines

Diff 429091

mlir/utils/textmate/mlir.json

{ {
"name": "MLIR",
"fileTypes": [ "fileTypes": [
"mlir" "mlir"
], ],
"repository": { "patterns": [
"attribute": { {
"match": "\\W[\\w_][\\w\\d_.$]*\\s*=", "include": "#comment"
"name": "meta.attribute.mlir" },
}, {
"branch_target": { "include": "#string"
"match": "\\^bb[\\w\\d_$\\.-]+",
"name": "entity.name.label.mlir"
}, },
{
"include": "#top_level_entity"
}
],
"repository": {
"comment": { "comment": {
"match": "\/\/.*$", "match": "\/\/.*$",
"name": "comment.line.double-slash.mlir" "name": "comment.line.double-slash.mlir"
}, },
"identifier": { "number": {
"match": "[\\%#@][\\w_][\\w\\d_.$]*", "patterns": [
{
"match": "(\\W)?([0-9]+\\.[0-9]*)([eE][+-]?[0-9]+)?",
"name": "constant.numeric.mlir"
},
{
"match": "([\\W])?(0x[0-9a-zA-Z]+)",
"captures": { "captures": {
"0": { "2": {
"name": "variable.mlir" "name": "constant.numeric.mlir"
}
} }
}, },
"name": "meta.identifier.mlir" {
}, "match": "([\\Wx])?([0-9]+)",
"integer": {
"match": "[\\Wx]([0-9]+)",
"captures": { "captures": {
"1": { "2": {
"name": "constant.numeric.mlir" "name": "constant.numeric.mlir"
} }
}, }
"name": "meta.identifier.mlir" }
]
}, },
"string": { "string": {
"end": "\"",
"begin": "\"", "begin": "\"",
"beginCaptures": { "beginCaptures": {
"0": { "0": {
"name": "punctuation.definition.string.begin.mlir" "name": "punctuation.definition.string.begin.mlir"
} }
}, },
"patterns": [ "patterns": [
{ {
"match": "\\\\[nt\"]", "match": "\\\\[nt\"]",
"name": "constant.character.escape.mlir" "name": "constant.character.escape.mlir"
},
{
"match": "\\\\.",
"name": "invalid.illegal.mlir"
} }
], ],
"end": "\"",
"endCaptures": { "endCaptures": {
"0": { "0": {
"name": "punctuation.definition.string.end.mlir" "name": "punctuation.definition.string.end.mlir"
} }
}, },
"name": "string.quoted.double.mlir" "name": "string.quoted.double.mlir"
}, },
"types": { "top_level_entity": {
"match": "[\\Wx](index|i[1-9][0-9]*|f16|bf16|f32|f64|memref|tensor|vector)\\b", "patterns": [
{
"include": "#attribute_alias_def"
},
{
"include": "#type_alias_def"
},
{
"include": "#operation_body"
}
]
},
"attribute_alias_def": {
"match": "^\\s*(\\#\\w+)\\b\\s+\\=",
"captures": { "captures": {
"1": { "1": {
"name": "storage.type.mlir" "name": "constant.language.mlir"
}
} }
}, },
"name": "meta.types.simple.mlir" "type_alias_def": {
"match": "^\\s*(\\!\\w+)\\b\\s+\\=",
"captures": {
"1": {
"name": "entity.name.type.mlir"
}
} }
}, },
"operation": {
"patterns": [
{
"match": "^\\s*(\\%[\\%\\w\\:\\,\\s]+)\\s+\\=\\s+([\\w\\.\\$\\-]+)\\b",
"captures": {
"1": {
"patterns": [ "patterns": [
{ {
"include": "#ssa_value"
}
]
},
"2": {
"name": "variable.other.enummember.mlir"
}
}
},
{
"match": "^\\s*([\\w\\.\\$\\-]+)\\b(?=[^\\<\\:])",
"name": "variable.other.enummember.mlir"
}
]
},
"operation_body": {
"patterns": [
{
"include": "#operation"
},
{
"include": "#region_body_or_attr_dict"
},
{
"include": "#comment" "include": "#comment"
}, },
{ {
"include": "#ssa_value"
},
{
"include": "#block"
},
{
"include": "#attribute_value"
},
{
"include": "#bare_identifier"
}
]
},
"region_body_or_attr_dict": {
"patterns": [
{
"begin": "\\{\\s*(?=\\%|\\/|\\^)",
"patterns": [
{
"include": "#operation_body"
}
],
"end": "\\}"
},
{
"begin": "\\{\\s*(?=[^\\}]*$)",
"patterns": [
{
"include": "#operation_body"
}
],
"end": "\\}"
},
{
"begin": "\\{\\s*(?=\\%)",
"patterns": [
{
"include": "#operation_body"
}
],
"end": "\\}"
},
{
"begin": "\\{\\s*(?=.*$)",
"patterns": [
{
"include": "#attribute_dictionary_body"
}
],
"end": "\\}"
}
]
},
"attribute_value": {
"patterns": [
{
"include": "#string" "include": "#string"
}, },
{ {
"match": "\\b(func)\\b\\s*(|private|public)\\s*(@[\\w_][\\w\\d_.$]*)", "include": "#comment"
"captures": { },
{
"include": "#number"
},
{
"match": "\\b(false|true|unit)\\b",
"name": "constant.language.mlir"
},
{
"begin": "\\b(affine_map|affine_set)\\s*\\<",
"beginCaptures": {
"1": { "1": {
"name": "keyword.function.mlir" "name": "constant.language.mlir"
}
}, },
"2": { "patterns": [
"name": "keyword.function.mlir" {
"match": "\\b(ceildiv|floordiv|mod|symbol)\\b",
"name": "entity.name.function.mlir"
},
{
"match": "\\b([\\w\\.\\$\\-]+)\\b",
"name": "variable.mlir"
},
{
"include": "#number"
}
],
"end": "\\)\\>"
},
{
"begin": "\\b(dense|opaque|sparse)\\s*\\<",
"beginCaptures": {
"1": {
"name": "constant.language.mlir"
}
},
"patterns": [
{
"include": "#attribute_value"
}
],
"end": "\\>"
},
{
"begin": "\\[",
"patterns": [
{
"include": "#attribute_value"
},
{
"include": "#operation_body"
}
],
"end": "\\]"
},
{
"begin": "\\{",
"patterns": [
{
"include": "#attribute_dictionary_body"
}
],
"end": "\\}"
}, },
"3": { {
"match": "(\\@[\\w+\\$\\-\\.]*)",
"name": "entity.name.function.mlir" "name": "entity.name.function.mlir"
},
{
"begin": "(\\#[\\w\\$\\-\\.]+)\\<",
"beginCaptures": {
"1": {
"name": "constant.language.mlir"
} }
}, },
"name": "support.function.mlir" "patterns": [
{
"include": "#attribute_value"
}, },
{ {
"match": "\\b(attributes|br|call|constant|loc|return)\\b", "match": "\\-\\>|\\>\\="
"name": "keyword.module.mlir"
}, },
{ {
"include": "#identifier" "include": "#bare_identifier"
}
],
"end": "\\>"
}, },
{ {
"include": "#branch_target" "match": "\\#[\\w\\$\\-\\.]+\\b",
"name": "constant.language.mlir"
}, },
{ {
"include": "#attribute" "include": "#type_value"
}, },
{ {
"include": "#types" "begin": "\\<",
"patterns": [
{
"include": "#attribute_value"
}, },
{ {
"include": "#integer" "include": "#bare_identifier"
} }
], ],
"name": "MLIR", "end": "\\>"
"scopeName": "source.mlir" }
]
},
"attribute_dictionary_body": {
"patterns": [
{
"include": "#comment"
},
{
"include": "#string"
},
{
"include": "#attribute_value"
},
{
"match": "(\\%)?\\b([\\w\\.\\-\\$\\:0-9]+)\\b\\s*(?=\\=|\\,|\\})",
"name": "variable.other.mlir"
}
]
},
"type_value": {
"patterns": [
{
"begin": "(\\![\\w\\$\\-\\.]+)\\<",
"beginCaptures": {
"1": {
"name": "entity.name.type.mlir"
}
},
"patterns": [
{
"include": "#attribute_value"
},
{
"match": "\\-\\>|\\>\\=",
"name": "punctuation.other.mlir"
},
{
"include": "#bare_identifier"
}
],
"end": "\\>"
},
{
"match": "\\![\\w\\$\\-\\.]+\\b",
"name": "entity.name.type.mlir"
},
{
"begin": "(complex|memref|tensor|tuple|vector)\\<",
"beginCaptures": {
"1": {
"name": "entity.name.type.mlir"
}
},
"patterns": [
{
"match": "[\\?x0-9\\[\\]]+",
"captures": {
"0": {
"patterns": [
{
"include": "#number"
}
]
} }
}
},
{
"include": "#attribute_value"
},
{
"match": "\\-\\>|\\>\\=",
"name": "punctuation.other.mlir"
},
{
"include": "#bare_identifier"
}
],
"end": "\\>"
},
{
"match": "bf16|f16|f32|f64|f80|f128|index|none|(u|s)?i[0-9]+",
"name": "entity.name.type.mlir"
}
]
},
"bare_identifier": {
"match": "\\b([\\w\\.\\$\\-]+)\\b",
"name": "keyword.other.mlir"
},
"ssa_value": {
"match": "\\%[\\w\\.\\$\\:\\#]+",
"name": "variable.other.mlir"
},
"block": {
"match": "\\^[\\w\\d_$\\.-]+",
"name": "keyword.control.mlir"
}
},
"scopeName": "source.mlir"
}
No newline at end of file