Skip to content

use Parquet.jl named tuples iterator: RecordCursor #25

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
tanmaykm wants to merge 4 commits into
base: master
Choose a base branch
from
Open

use Parquet.jl named tuples iterator: RecordCursor #25

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
4 commits
Select commit Hold shift + click to select a range
614afb0
use Parquet.jl named tuples iterator: RecordCursor
tanmaykm May 17, 2020
819ad40
update Parquet.jl compat version
tanmaykm May 18, 2020
129240f
upperbound for Parquet.jl compat version
tanmaykm May 21, 2020
2656eb2
Merge branch 'master' into tan/recordcursor
tanmaykm May 26, 2020
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
2 changes: 1 addition & 1 deletion Project.toml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -22,7 +22,7 @@ DataValues = "^0.4.5"
FileIO = "1"
IterableTables = "0.9, 0.10, 0.11, 1"
IteratorInterfaceExtensions = "^0.1.1, 1"
Parquet = "0.2, 0.3, 0.4"
Parquet = "0.5"
TableShowUtils = "0.2"
TableTraits = "0.4, 1"
julia = "1"
47 changes: 2 additions & 45 deletions src/ParquetFiles.jl
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -23,33 +23,6 @@ function Base.show(io::IO, ::MIME"application/vnd.dataresource+json", source::Pa
end
Base.Multimedia.showable(::MIME"application/vnd.dataresource+json", source::ParquetFile) = true

struct ParquetNamedTupleIterator{T,T_row}
rc::RecCursor
nrows::Int
end

function Base.eltype(itr::ParquetNamedTupleIterator{T,T_row}) where {T,T_row}
return T
end

function Base.length(itr::ParquetNamedTupleIterator)
return itr.nrows
end

@generated function Base.iterate(itr::ParquetNamedTupleIterator{T,T_row}, state...) where {T,T_row}
names = fieldnames(T)
quote
y = iterate(itr.rc, state...)
if y === nothing
return nothing
else
v = y[1]
next_state = y[2]
return T(($([fieldtype(T, i) <: String ? :(String(copy(v.$(names[i])))) : :(v.$(names[i])) for i = 1:length(names)]...),)), next_state
end
end
end

function fileio_load(f::FileIO.File{FileIO.format"Parquet"})
return ParquetFile(f.filename)
end
Expand All @@ -58,24 +31,8 @@ IteratorInterfaceExtensions.isiterable(x::ParquetFile) = true
TableTraits.isiterabletable(x::ParquetFile) = true

function IteratorInterfaceExtensions.getiterator(file::ParquetFile)
p = ParFile(file.filename)

T_row_name = Symbol("RCType$(String(gensym())[3:end])")

schema(JuliaConverter(ParquetFiles), p, T_row_name)

T_row = eval(T_row_name)

col_names = fieldnames(T_row)
col_types = [i <: Vector{UInt8} ? String : i for i in T_row.types]

T = NamedTuple{(col_names...,),Tuple{col_types...}}

rc = RecCursor(p, 1:nrows(p), colnames(p), JuliaBuilder(p, T_row))

it = ParquetNamedTupleIterator{T,T_row}(rc, nrows(p))

return it
p = ParFile(file.filename; map_logical_types=true)
return RecordCursor(p)
end

end # module
2 changes: 1 addition & 1 deletion test/runtests.jl
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -25,7 +25,7 @@ using Test
@test ar[1] == (n_nationkey = 0, n_name = "ALGERIA", n_regionkey = 0, n_comment = " haggle. carefully final deposits detect slyly agai")

@test sprint((stream, data)->show(stream, "text/html", data), pqf)[1:100] == "<table><thead><tr><th>n_nationkey</th><th>n_name</th><th>n_regionkey</th><th>n_comment</th></tr></th"
@test sprint((stream, data)->show(stream, "application/vnd.dataresource+json", data), pqf)[1:100] == "{\"schema\":{\"fields\":[{\"name\":\"n_nationkey\",\"type\":\"integer\"},{\"name\":\"n_name\",\"type\":\"string\"},{\"nam"
@test sprint((stream, data)->show(stream, "application/vnd.dataresource+json", data), pqf)[1:100] == "{\"schema\":{\"fields\":[{\"name\":\"n_nationkey\",\"type\":\"string\"},{\"name\":\"n_name\",\"type\":\"string\"},{\"name"
@test sprint(show, pqf)[1:100] == "25x4 Parquet file\nn_nationkey │ n_name │ n_regionkey\n────────────┼─"
@test showable("text/html", pqf) == true
@test showable("application/vnd.dataresource+json", pqf) == true
Expand Down