Skip to content
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

allow non-ascii characters in printf format strings #23899

Merged
merged 3 commits into from
Sep 29, 2017
Merged

allow non-ascii characters in printf format strings #23899

Show file tree
Hide file tree
Changes from 1 commit
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
5298861
fixed issue #23880
KlausC Sep 27, 2017
2c8c7f8
error in comment
KlausC Sep 27, 2017
c685e8f
throw ArgumentError if non-ascii character after flags
KlausC Sep 28, 2017
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
15 changes: 8 additions & 7 deletions base/printf.jl
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -36,23 +36,24 @@ end
### printf format string parsing ###

function parse(s::AbstractString)
# parse format string in to stings and format tuples
# parse format string into strings and format tuples
list = []
i = j = start(s)
j1 = 0 # invariant: j1 == prevind(s, j-1)
Copy link
Member

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

@KlausC minor issue; if I understand it correctly the comment should read:

# invariant: j1 == prevind(s, j)

Copy link
Contributor Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

you are right!

while !done(s,j)
c, k = next(s,j)
if c == '%'
isempty(s[i:j-1]) || push!(list, s[i:j-1])
i > j1 || push!(list, s[i:j1])
flags, width, precision, conversion, k = parse1(s,k)
'\'' in flags && error("printf format flag ' not yet supported")
conversion == 'n' && error("printf feature %n not supported")
push!(list, conversion == '%' ? "%" : (flags,width,precision,conversion))
i = j = k
else
j = k
i = k
end
j1 = j
j = k
end
isempty(s[i:end]) || push!(list, s[i:end])
i > endof(s) || push!(list, s[i:end])
# coalesce adjacent strings
i = 1
while i < length(list)
Expand Down Expand Up @@ -98,7 +99,7 @@ function parse1(s::AbstractString, k::Integer)
while c in "#0- + '"
c, k = next_or_die(s,k)
end
flags = String(s[j:k-2])
flags = String(s[j:k-2]) # exploiting that all specifier characters are one-byte.
# parse width
while '0' <= c <= '9'
width = 10*width + c-'0'
Expand Down
12 changes: 12 additions & 0 deletions test/printf.jl
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -272,3 +272,15 @@ end

# Check bug with trailing nul printing BigFloat
@test (@sprintf("%.330f", BigFloat(1)))[end] != '\0'

# Check utf8 strings #23880
@test (@sprintf("X%d", 2)) == "X2"
@test (@sprintf("\u00d0%d", 2)) == "\u00d02"
@test (@sprintf("\u0f00%d", 2)) == "\u0f002"
@test (@sprintf("\U0001ffff%d", 2)) == "\U0001ffff2"
@test (@sprintf("%dX%d", 1, 2)) == "1X2"
@test (@sprintf("%d\u00d0%d", 1, 2)) == "1\u00d02"
@test (@sprintf("%d\u0f00%d", 1, 2)) == "1\u0f002"
@test (@sprintf("%d\U0001ffff%d", 1, 2)) == "1\U0001ffff2"
@test (@sprintf("%d\u2203%d\u0203", 1, 2)) == "1\u22032\u0203"