gitbase
gitbase copied to clipboard
src-d
uast_extract does not allow to extract nested properties
There is currently no way to allow extraction of nested properties of a node, which would be useful for getting, for example, the line and column of the position.
It's doable, but we have to discuss in what format we want to return extracted data. Here is a one big object in json:
[
{
"@pos": {
"@type": "uast:Positions",
"end": {
"@type": "uast:Position",
"col": 8,
"line": 4,
"offset": 31
},
"start": {
"@type": "uast:Position",
"col": 5,
"line": 4,
"offset": 28
}
},
"@role": [
"Function",
"Declaration",
"Name",
"Identifier"
],
"@token": "sum",
"@type": "FunctionDef",
"args": {
"@pos": {
"@type": "uast:Positions"
},
"@role": [
"Function",
"Declaration",
"Argument",
"Incomplete"
],
"@type": "arguments",
"args": [
{
"@pos": {
"@type": "uast:Positions",
"end": {
"@type": "uast:Position",
"col": 10,
"line": 4,
"offset": 33
},
"start": {
"@type": "uast:Position",
"col": 9,
"line": 4,
"offset": 32
}
},
"@role": [
"Function",
"Declaration",
"Argument",
"Name"
],
"@token": "a",
"@type": "arg",
"annotation": null,
"noops_previous": {
"@pos": {
"@type": "uast:Positions",
"end": {
"@type": "uast:Position",
"col": 1,
"line": 3,
"offset": 23
},
"start": {
"@type": "uast:Position",
"col": 1,
"line": 1,
"offset": 0
}
},
"@role": [
"Noop"
],
"@type": "PreviousNoops",
"lines": [
{
"@pos": {
"@type": "uast:Positions",
"start": {
"@type": "uast:Position",
"col": 1,
"line": 2,
"offset": 1
}
},
"@role": [
"Comment",
"Noop"
],
"@token": "#!/usr/bin/env python\\n",
"@type": "NoopLine"
}
]
}
},
{
"@pos": {
"@type": "uast:Positions",
"end": {
"@type": "uast:Position",
"col": 13,
"line": 4,
"offset": 36
},
"start": {
"@type": "uast:Position",
"col": 12,
"line": 4,
"offset": 35
}
},
"@role": [
"Function",
"Declaration",
"Argument",
"Name"
],
"@token": "b",
"@type": "arg",
"annotation": null
}
]
},
"body": {
"@role": [
"Function",
"Declaration",
"Body"
],
"@type": "FunctionDef.body",
"body_stmts": [
{
"@pos": {
"@type": "uast:Positions",
"end": {
"@type": "uast:Position",
"col": 8,
"line": 5,
"offset": 46
},
"start": {
"@type": "uast:Position",
"col": 2,
"line": 5,
"offset": 40
}
},
"@role": [
"Return",
"Statement"
],
"@token": "return",
"@type": "Return",
"value": {
"@pos": {
"@type": "uast:Positions",
"start": {
"@type": "uast:Position",
"col": 9,
"line": 5,
"offset": 47
}
},
"@role": [
"Expression",
"Binary"
],
"@type": "BinOp",
"left": {
"@pos": {
"@type": "uast:Positions",
"end": {
"@type": "uast:Position",
"col": 10,
"line": 5,
"offset": 48
},
"start": {
"@type": "uast:Position",
"col": 9,
"line": 5,
"offset": 47
}
},
"@role": [
"Identifier",
"Expression",
"Binary",
"Left"
],
"@token": "a",
"@type": "Name",
"ctx": "Load"
},
"op": {
"@pos": {
"@type": "uast:Positions"
},
"@role": [
"Operator",
"Arithmetic",
"Add",
"Binary"
],
"@token": "+",
"@type": "Add"
},
"right": {
"@pos": {
"@type": "uast:Positions",
"end": {
"@type": "uast:Position",
"col": 14,
"line": 5,
"offset": 52
},
"start": {
"@type": "uast:Position",
"col": 13,
"line": 5,
"offset": 51
}
},
"@role": [
"Identifier",
"Expression",
"Binary",
"Right"
],
"@token": "b",
"@type": "Name",
"ctx": "Load"
}
}
}
]
},
"decorator_list": {
"@role": [
"Function",
"Declaration",
"Incomplete"
],
"@type": "FunctionDef.decorators",
"decorators": []
},
"returns": null
},
{
"@pos": {
"@type": "uast:Positions",
"end": {
"@type": "uast:Position",
"col": 10,
"line": 5,
"offset": 48
},
"start": {
"@type": "uast:Position",
"col": 9,
"line": 5,
"offset": 47
}
},
"@role": [
"Identifier",
"Expression",
"Binary",
"Left"
],
"@token": "a",
"@type": "Name",
"ctx": "Load"
},
{
"@pos": {
"@type": "uast:Positions",
"end": {
"@type": "uast:Position",
"col": 14,
"line": 5,
"offset": 52
},
"start": {
"@type": "uast:Position",
"col": 13,
"line": 5,
"offset": 51
}
},
"@role": [
"Identifier",
"Expression",
"Binary",
"Right"
],
"@token": "b",
"@type": "Name",
"ctx": "Load"
},
{
"@pos": {
"@type": "uast:Positions",
"end": {
"@type": "uast:Position",
"col": 10,
"line": 7,
"offset": 63
},
"start": {
"@type": "uast:Position",
"col": 7,
"line": 7,
"offset": 60
}
},
"@role": [
"Identifier",
"Expression",
"Call",
"Callee"
],
"@token": "sum",
"@type": "Name",
"ctx": "Load"
},
{
"@pos": {
"@type": "uast:Positions",
"end": {
"@type": "uast:Position",
"col": 6,
"line": 7,
"offset": 59
},
"start": {
"@type": "uast:Position",
"col": 1,
"line": 7,
"offset": 54
}
},
"@role": [
"Identifier",
"Expression",
"Call",
"Callee"
],
"@token": "print",
"@type": "Name",
"ctx": "Load",
"noops_previous": {
"@pos": {
"@type": "uast:Positions",
"end": {
"@type": "uast:Position",
"col": 1,
"line": 6,
"offset": 53
},
"start": {
"@type": "uast:Position",
"col": 1,
"line": 6,
"offset": 53
}
},
"@role": [
"Noop"
],
"@type": "PreviousNoops",
"lines": []
}
}
]
Same as we're retuning now, right? As for the syntax, maybe jsonpath? we already use it in JSON_EXTRACT UDF.
@erizocosmico - this is what we get from bblfsh (whole node) converted to json. But the question is about extract. So far, extract returns a slice of all extracted sub-node values, e.g.:
["FunctionDef","Name","Name","Name","Name"]
["sum","a","b","sum","print"]
[["Function","Declaration","Name","Identifier"],["Identifier","Expression","Binary","Left"],["Identifier","Expression","Binary","Right"],["Identifier","Expression","Call","Callee"],["Identifier","Expression","Call","Callee"]]
