Skip to content

Detect "" always as quoted string column #131

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

Merged
merged 1 commit into from
Mar 26, 2019
Merged

Detect "" always as quoted string column #131

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
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
12 changes: 9 additions & 3 deletions src/guesstype.jl
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -52,7 +52,7 @@ function getquotechar(x)
return '\0'
end

function guesstoken(x, opts, prevent_quote_wrap, @nospecialize(prev_guess)=Unknown(), nastrings=NA_STRINGS, stringarraytype=StringArray)
function guesstoken(x, opts, prevent_quote_wrap, @nospecialize(prev_guess=Unknown()), nastrings=NA_STRINGS, stringarraytype=StringArray)
q = getquotechar(x)

if isa(prev_guess, StringToken)
Expand All @@ -65,8 +65,14 @@ function guesstoken(x, opts, prevent_quote_wrap, @nospecialize(prev_guess)=Unkno
else
prev_inner = prev_guess
end
inner_token = guesstoken(strip(strip(x, q)), opts, true, prev_inner, nastrings, stringarraytype)
return Quoted(inner_token, opts.quotechar, opts.escapechar)
inner_string = strip(strip(x, q))
if inner_string==""
# If we come across a "", we classify it as a string column no matter what
return Quoted(StringToken(stringarraytype<:StringArray ? StrRange : String), opts.quotechar, opts.escapechar)
else
inner_token = guesstoken(inner_string, opts, true, prev_inner, nastrings, stringarraytype)
return Quoted(inner_token, opts.quotechar, opts.escapechar)
end
elseif isa(prev_guess, Quoted)
# but this token is not quoted
return Quoted(guesstoken(x, opts, true, prev_guess.inner, nastrings, stringarraytype), opts.quotechar, opts.escapechar)
Expand Down
10 changes: 5 additions & 5 deletions test/runtests.jl
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -370,11 +370,11 @@ import TextParse: guesstoken, Unknown, Numeric, DateTimeToken, StrRange
@test guesstoken("\"1\"", opts, false, Quoted(Numeric(Int), opts.quotechar, opts.escapechar)) == Quoted(Numeric(Int), opts.quotechar, opts.escapechar)

# Test quoting with Nullable tokens
@test guesstoken("\"\"", opts, false, Quoted(Unknown(), opts.quotechar, opts.escapechar)) == Quoted(NAToken(Unknown()), opts.quotechar, opts.escapechar)
@test guesstoken("\"\"", opts, false, Quoted(NAToken(Unknown()), opts.quotechar, opts.escapechar)) == Quoted(NAToken(Unknown()), opts.quotechar, opts.escapechar)
@test guesstoken("\"\"", opts, false, Quoted(Numeric(Int), opts.quotechar, opts.escapechar)) == Quoted(NAToken(Numeric(Int)), opts.quotechar, opts.escapechar)
@test guesstoken("\"\"", opts, false, Unknown()) == Quoted(NAToken(Unknown()), opts.quotechar, opts.escapechar)
@test guesstoken("\"\"", opts, false, Numeric(Int)) == Quoted(NAToken(Numeric(Int)), opts.quotechar, opts.escapechar)
@test guesstoken("\"\"", opts, false, Quoted(Unknown(), opts.quotechar, opts.escapechar)) == Quoted(StringToken(StrRange), opts.quotechar, opts.escapechar)
@test guesstoken("\"\"", opts, false, Quoted(NAToken(Unknown()), opts.quotechar, opts.escapechar)) == Quoted(StringToken(StrRange), opts.quotechar, opts.escapechar)
@test guesstoken("\"\"", opts, false, Quoted(Numeric(Int), opts.quotechar, opts.escapechar)) == Quoted(StringToken(StrRange), opts.quotechar, opts.escapechar)
@test guesstoken("\"\"", opts, false, Unknown()) == Quoted(StringToken(StrRange), opts.quotechar, opts.escapechar)
@test guesstoken("\"\"", opts, false, Numeric(Int)) == Quoted(StringToken(StrRange), opts.quotechar, opts.escapechar)
@test guesstoken("", opts, false, Quoted(Numeric(Int), opts.quotechar, opts.escapechar)) == Quoted(NAToken(Numeric(Int)), opts.quotechar, opts.escapechar)
@test guesstoken("", opts, false, Quoted(NAToken(Numeric(Int)), opts.quotechar, opts.escapechar)) == Quoted(NAToken(Numeric(Int)), opts.quotechar, opts.escapechar)
@test guesstoken("1", opts, false, Quoted(NAToken(Numeric(Int)), opts.quotechar, opts.escapechar)) == Quoted(NAToken(Numeric(Int)), opts.quotechar, opts.escapechar)
Expand Down