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
Prev Previous commit
Next Next commit
Don't cache capture names in regex object
  • Loading branch information
@malmaud
malmaud committed Jun 24, 2015
commit 1b0127cd7af78b5e9a769a667bb17739c19641fd
19 changes: 7 additions & 12 deletions base/regex.jl
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -15,9 +15,6 @@ type Regex
extra::Ptr{Void}
ovec::Vector{Csize_t}
match_data::Ptr{Void}
capture_name_to_idx::Dict{Symbol, Int}
idx_to_capture_name::Dict{Int, Symbol}


function Regex(pattern::AbstractString, compile_options::Integer,
match_options::Integer)
Expand All @@ -31,8 +28,7 @@ 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,
Dict{Symbol, Int}(), Dict{Int, Symbol}()))
C_NULL, Csize_t[], C_NULL))
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 @@ -60,10 +56,6 @@ 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)
for (idx, name) in PCRE.capture_names(regex.regex)
regex.capture_name_to_idx[Symbol(name)] = idx
regex.idx_to_capture_name[idx] = Symbol(name)
end
end
regex
end
Expand Down Expand Up @@ -105,12 +97,13 @@ end
function show(io::IO, m::RegexMatch)
print(io, "RegexMatch(")
show(io, m.match)
idx_to_capture_name = PCRE.capture_names(m.regex.regex)
if !isempty(m.captures)
print(io, ", ")
for i = 1:length(m.captures)
# If the capture group is named, show the name.
# Otherwise show its index.
capture_name = get(m.regex.idx_to_capture_name, i, i)
capture_name = get(idx_to_capture_name, i, i)
print(io, capture_name, "=")
show(io, m.captures[i])
if i < length(m.captures)
Expand All @@ -122,9 +115,11 @@ function show(io::IO, m::RegexMatch)
end

# Capture group extraction
getindex(m::RegexMatch, idx::Int) = m.captures[idx]
getindex(m::RegexMatch, idx::Integer) = m.captures[idx]
function getindex(m::RegexMatch, name::Symbol)
m[m.regex.capture_name_to_idx[name]]
idx = PCRE.substring_number_from_name(m.regex.regex, name)
idx <= 0 && error("no capture group named $name found in regex")
m[idx]
end
getindex(m::RegexMatch, name::AbstractString) = m[Symbol(name)]

Expand Down
1 change: 1 addition & 0 deletions test/regex.jl
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -41,3 +41,4 @@ show(buf, r"")
# Named subpatterns
m = match(r"(?<a>.)(.)(?<b>.)", "xyz")
@test (m[:a], m[2], m["b"]) == ("x", "y", "z")
@test sprint(show, m) == "RegexMatch(\"xyz\", a=\"x\", 2=\"y\", b=\"z\")"