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

define getindex on regex matches to return captures. #11566

Merged
merged 4 commits into from
Jul 2, 2015
Merged

define getindex on regex matches to return captures. #11566

Show file tree
Hide file tree
Changes from 1 commit
Commits
Show all changes
4 commits
Select commit Hold shift + click to select a range
14a02da
define getindex on regex matches to return captures.
malmaud Jun 3, 2015
0479e7a
Store capture names as symbols instead of strings
malmaud Jun 3, 2015
1b0127c
Don't cache capture names in regex object
malmaud Jun 24, 2015
1b8d47a
Added manual section on accessing groups
malmaud Jul 2, 2015
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
Next Next commit
define getindex on regex matches to return captures.
  • Loading branch information
@malmaud
malmaud committed Jun 3, 2015
commit 14a02da08df84807e2c674b0736527c80d7997d2
19 changes: 19 additions & 0 deletions base/pcre.jl
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -140,4 +140,23 @@ function substring_number_from_name(re, name)
(Ptr{Void}, Cstring), re, name)
end

function capture_names(re)
name_count = info(re, INFO_NAMECOUNT, UInt32)
name_entry_size = info(re, INFO_NAMEENTRYSIZE, UInt32)
nametable_ptr = info(re, INFO_NAMETABLE, Ptr{UInt8})
names = Dict{Int, ASCIIString}()
for i=1:name_count
offset = (i-1)*name_entry_size + 1
# The capture group index corresponding to name 'i' is stored as a
# big-endian 16-bit value.
high_byte = UInt16(unsafe_load(nametable_ptr, offset))
low_byte = UInt16(unsafe_load(nametable_ptr, offset+1))
idx = (high_byte << 8) | low_byte
# The capture group name is a null-terminated string located directly
# after the index.
names[idx] = bytestring(nametable_ptr+offset+1)
end
names
end

end # module
23 changes: 20 additions & 3 deletions base/regex.jl
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -15,6 +15,8 @@ type Regex
extra::Ptr{Void}
ovec::Vector{Csize_t}
match_data::Ptr{Void}
capture_name_to_idx::Dict{ASCIIString, Int}
idx_to_capture_name::Dict{Int, ASCIIString}


function Regex(pattern::AbstractString, compile_options::Integer,
Expand All @@ -29,7 +31,8 @@ type Regex
throw(ArgumentError("invalid regex match options: $match_options"))
end
re = compile(new(pattern, compile_options, match_options, C_NULL,
C_NULL, Csize_t[], C_NULL))
C_NULL, Csize_t[], C_NULL,
Dict{ASCIIString, Int}(), Dict{Int, ASCIIString}()))
finalizer(re, re->begin
re.regex == C_NULL || PCRE.free_re(re.regex)
re.match_data == C_NULL || PCRE.free_match_data(re.match_data)
Expand Down Expand Up @@ -57,6 +60,10 @@ function compile(regex::Regex)
PCRE.jit_compile(regex.regex)
regex.match_data = PCRE.create_match_data(regex.regex)
regex.ovec = PCRE.get_ovec(regex.match_data)
regex.idx_to_capture_name = PCRE.capture_names(regex.regex)
for (i, name) in regex.idx_to_capture_name
regex.capture_name_to_idx[name] = i
end
end
regex
end
Expand Down Expand Up @@ -92,6 +99,7 @@ immutable RegexMatch
captures::Vector{Union(Void,SubString{UTF8String})}
offset::Int
offsets::Vector{Int}
regex::Regex
end

function show(io::IO, m::RegexMatch)
Expand All @@ -100,7 +108,10 @@ function show(io::IO, m::RegexMatch)
if !isempty(m.captures)
print(io, ", ")
for i = 1:length(m.captures)
print(io, i, "=")
# If the capture group is named, show the name.
# Otherwise show its index.
capture_name = get(m.regex.idx_to_capture_name, i, i)
print(io, capture_name, "=")
show(io, m.captures[i])
if i < length(m.captures)
print(io, ", ")
Expand All @@ -110,6 +121,12 @@ function show(io::IO, m::RegexMatch)
print(io, ")")
end

# Capture group extraction
getindex(m::RegexMatch, idx::Int) = m.captures[idx]
function getindex(m::RegexMatch, name::AbstractString)
m[m.regex.capture_name_to_idx[name]]
end

function ismatch(r::Regex, s::AbstractString, offset::Integer=0)
compile(r)
return PCRE.exec(r.regex, bytestring(s), offset, r.match_options,
Expand All @@ -136,7 +153,7 @@ function match(re::Regex, str::UTF8String, idx::Integer, add_opts::UInt32=UInt32
cap = Union(Void,SubString{UTF8String})[
ovec[2i+1] == PCRE.UNSET ? nothing : SubString(str, ovec[2i+1]+1, ovec[2i+2]) for i=1:n ]
off = Int[ ovec[2i+1]+1 for i=1:n ]
RegexMatch(mat, cap, ovec[1]+1, off)
RegexMatch(mat, cap, ovec[1]+1, off, re)
end

match(re::Regex, str::Union(ByteString,SubString), idx::Integer, add_opts::UInt32=UInt32(0)) =
Expand Down
4 changes: 4 additions & 0 deletions test/regex.jl
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -37,3 +37,7 @@ show(buf, r"")
# regex match / search string must be a ByteString
@test_throws ArgumentError match(r"test", utf32("this is a test"))
@test_throws ArgumentError search(utf32("this is a test"), r"test")

# Named subpatterns
m = match(r"(?<a>.)(.)(?<b>.)", "xyz")
@test (m["a"], m[2], m["b"]) == ("x", "y", "z")