Created
July 10, 2017 12:32
-
-
Save ammar/af54718c71aead909f8a5af4ec5cc40f to your computer and use it in GitHub Desktop.
WIP: Add support for new absence operator
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
diff --git a/lib/regexp_parser/scanner/scanner.rl b/lib/regexp_parser/scanner/scanner.rl | |
index e200cfc..96b2e70 100644 | |
--- a/lib/regexp_parser/scanner/scanner.rl | |
+++ b/lib/regexp_parser/scanner/scanner.rl | |
@@ -78,6 +78,8 @@ | |
conditional = '(?('; | |
+ absent_operator = '?~'; | |
+ | |
group_comment = '?#' . [^)]* . group_close; | |
group_atomic = '?>'; | |
@@ -540,6 +542,12 @@ | |
emit(:group, :comment, *text(data, ts, te)) | |
}; | |
+ # (?~exp) absent operator: | |
+ # ------------------------------------------------------------------------ | |
+ group_open . absent_operator >group_opened { | |
+ p = scan_absent_operator(p, data, ts, te) | |
+ }; | |
+ | |
# Expression options: | |
# (?imxdau-imx) option on/off | |
# i: ignore case | |
@@ -930,6 +938,41 @@ module Regexp::Scanner | |
p # return the new value of the data pointer | |
end | |
+ def self.scan_absent_operator(p, data, ts, te) | |
+ text = text(data, ts, te).first | |
+ | |
+ exp_char, exp_length = true, 0 | |
+ | |
+ emit(:absent_op, :open, text(data, ts, te).first, ts, te) | |
+ | |
+ # Copy until a closing parenthesis, skipping escaped ones. | |
+ while exp_char | |
+ if data[te + exp_length] | |
+ c = data[te + exp_length].chr | |
+ | |
+ if c == '\\' | |
+ text << c ; p += 1 ; exp_length += 1 | |
+ | |
+ c = data[te + exp_length].chr | |
+ | |
+ text << c ; p += 1 ; exp_length += 1 | |
+ elsif c == ')' | |
+ exp_char = false | |
+ | |
+ emit(:absent_op, :expression, text, ts, te + exp_length) | |
+ #emit(:absent_op, :close, c, ts, te + exp_length) | |
+ | |
+ else | |
+ text << c ; p += 1 ; exp_length += 1 | |
+ end | |
+ else | |
+ raise PrematureEndError.new("absent operator `#{text}'") | |
+ end | |
+ end | |
+ | |
+ p | |
+ end | |
+ | |
# Copy from ts to te from data as text | |
def self.copy(data, range) | |
data[range].pack('c*') | |
diff --git a/test/scanner/test_groups.rb b/test/scanner/test_groups.rb | |
index 5dabb56..aa7062e 100644 | |
--- a/test/scanner/test_groups.rb | |
+++ b/test/scanner/test_groups.rb | |
@@ -55,6 +55,15 @@ class ScannerGroups < Test::Unit::TestCase | |
}) | |
end | |
+ if RUBY_VERSION >= '2.4.1' | |
+ tests.merge!({ | |
+ # Absent operator | |
+ '(?~abc)' => [0, :absent_op, :open, '(?~', 0, 7], | |
+ '(?~def)' => [1, :absent_op, :expression, 'def', 0, 7], | |
+ '(?~xyz)' => [2, :absent_op, :close, ')', 0, 7], | |
+ }) | |
+ end | |
+ | |
tests.each_with_index do |(pattern, (index, type, token, text, ts, te)), count| | |
define_method "test_scanner_#{type}_#{token}_#{count}" do | |
tokens = RS.scan(pattern) | |
diff --git a/test/warnings.yml b/test/warnings.yml | |
index e957c37..f1616c8 100644 | |
--- a/test/warnings.yml | |
+++ b/test/warnings.yml | |
@@ -1,6 +1,6 @@ | |
--- | |
# Unused variable emitted by ragel | |
-- "lib/regexp_parser/scanner.rb:1674: warning: | |
+- "lib/regexp_parser/scanner.rb:1677: warning: | |
assigned but unused variable - testEof" | |
# Unavoidable duplicated character range tests |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment