summaryrefslogtreecommitdiff
path: root/spec/ruby/language/regexp
diff options
context:
space:
mode:
Diffstat (limited to 'spec/ruby/language/regexp')
-rw-r--r--spec/ruby/language/regexp/back-references_spec.rb9
-rw-r--r--spec/ruby/language/regexp/character_classes_spec.rb11
-rw-r--r--spec/ruby/language/regexp/encoding_spec.rb51
-rw-r--r--spec/ruby/language/regexp/escapes_spec.rb84
-rw-r--r--spec/ruby/language/regexp/repetition_spec.rb8
5 files changed, 130 insertions, 33 deletions
diff --git a/spec/ruby/language/regexp/back-references_spec.rb b/spec/ruby/language/regexp/back-references_spec.rb
index 26750c20c5..627c8daace 100644
--- a/spec/ruby/language/regexp/back-references_spec.rb
+++ b/spec/ruby/language/regexp/back-references_spec.rb
@@ -22,6 +22,15 @@ describe "Regexps with back-references" do
$10.should == "0"
end
+ it "returns nil for numbered variable with too large index" do
+ -> {
+ eval(<<~CODE).should == nil
+ "a" =~ /(.)/
+ eval('$4294967296')
+ CODE
+ }.should complain(/warning: ('|`)\$4294967296' is too big for a number variable, always nil/)
+ end
+
it "will not clobber capture variables across threads" do
cap1, cap2, cap3 = nil
"foo" =~ /(o+)/
diff --git a/spec/ruby/language/regexp/character_classes_spec.rb b/spec/ruby/language/regexp/character_classes_spec.rb
index 0cf1e9b6f4..98d431a817 100644
--- a/spec/ruby/language/regexp/character_classes_spec.rb
+++ b/spec/ruby/language/regexp/character_classes_spec.rb
@@ -609,10 +609,13 @@ describe "Regexp with character classes" do
"루비(Ruby)".match(/\p{Hangul}+/u).to_a.should == ["루비"]
end
- ruby_bug "#17340", ''...'3.0' do
- it "raises a RegexpError for an unterminated unicode property" do
- -> { Regexp.new('\p{') }.should raise_error(RegexpError)
- end
+ it "supports negated property condition" do
+ "a".match(eval("/\P{L}/")).should be_nil
+ "1".match(eval("/\P{N}/")).should be_nil
+ end
+
+ it "raises a RegexpError for an unterminated unicode property" do
+ -> { Regexp.new('\p{') }.should raise_error(RegexpError)
end
it "supports \\X (unicode 9.0 with UTR #51 workarounds)" do
diff --git a/spec/ruby/language/regexp/encoding_spec.rb b/spec/ruby/language/regexp/encoding_spec.rb
index 8e2a294b95..0571b2d3cf 100644
--- a/spec/ruby/language/regexp/encoding_spec.rb
+++ b/spec/ruby/language/regexp/encoding_spec.rb
@@ -4,18 +4,18 @@ require_relative '../fixtures/classes'
describe "Regexps with encoding modifiers" do
it "supports /e (EUC encoding)" do
- match = /./e.match("\303\251".force_encoding(Encoding::EUC_JP))
- match.to_a.should == ["\303\251".force_encoding(Encoding::EUC_JP)]
+ match = /./e.match("\303\251".dup.force_encoding(Encoding::EUC_JP))
+ match.to_a.should == ["\303\251".dup.force_encoding(Encoding::EUC_JP)]
end
it "supports /e (EUC encoding) with interpolation" do
- match = /#{/./}/e.match("\303\251".force_encoding(Encoding::EUC_JP))
- match.to_a.should == ["\303\251".force_encoding(Encoding::EUC_JP)]
+ match = /#{/./}/e.match("\303\251".dup.force_encoding(Encoding::EUC_JP))
+ match.to_a.should == ["\303\251".dup.force_encoding(Encoding::EUC_JP)]
end
it "supports /e (EUC encoding) with interpolation /o" do
- match = /#{/./}/e.match("\303\251".force_encoding(Encoding::EUC_JP))
- match.to_a.should == ["\303\251".force_encoding(Encoding::EUC_JP)]
+ match = /#{/./}/e.match("\303\251".dup.force_encoding(Encoding::EUC_JP))
+ match.to_a.should == ["\303\251".dup.force_encoding(Encoding::EUC_JP)]
end
it 'uses EUC-JP as /e encoding' do
@@ -38,6 +38,10 @@ describe "Regexps with encoding modifiers" do
/#{/./}/n.match("\303\251").to_a.should == ["\303"]
end
+ it "warns when using /n with a match string with non-ASCII characters and an encoding other than ASCII-8BIT" do
+ -> { /./n.match("\303\251".dup.force_encoding('utf-8')) }.should complain(%r{historical binary regexp match /.../n against UTF-8 string})
+ end
+
it 'uses US-ASCII as /n encoding if all chars are 7-bit' do
/./n.encoding.should == Encoding::US_ASCII
end
@@ -59,18 +63,18 @@ describe "Regexps with encoding modifiers" do
end
it "supports /s (Windows_31J encoding)" do
- match = /./s.match("\303\251".force_encoding(Encoding::Windows_31J))
- match.to_a.should == ["\303".force_encoding(Encoding::Windows_31J)]
+ match = /./s.match("\303\251".dup.force_encoding(Encoding::Windows_31J))
+ match.to_a.should == ["\303".dup.force_encoding(Encoding::Windows_31J)]
end
it "supports /s (Windows_31J encoding) with interpolation" do
- match = /#{/./}/s.match("\303\251".force_encoding(Encoding::Windows_31J))
- match.to_a.should == ["\303".force_encoding(Encoding::Windows_31J)]
+ match = /#{/./}/s.match("\303\251".dup.force_encoding(Encoding::Windows_31J))
+ match.to_a.should == ["\303".dup.force_encoding(Encoding::Windows_31J)]
end
it "supports /s (Windows_31J encoding) with interpolation and /o" do
- match = /#{/./}/s.match("\303\251".force_encoding(Encoding::Windows_31J))
- match.to_a.should == ["\303".force_encoding(Encoding::Windows_31J)]
+ match = /#{/./}/s.match("\303\251".dup.force_encoding(Encoding::Windows_31J))
+ match.to_a.should == ["\303".dup.force_encoding(Encoding::Windows_31J)]
end
it 'uses Windows-31J as /s encoding' do
@@ -82,15 +86,15 @@ describe "Regexps with encoding modifiers" do
end
it "supports /u (UTF8 encoding)" do
- /./u.match("\303\251".force_encoding('utf-8')).to_a.should == ["\u{e9}"]
+ /./u.match("\303\251".dup.force_encoding('utf-8')).to_a.should == ["\u{e9}"]
end
it "supports /u (UTF8 encoding) with interpolation" do
- /#{/./}/u.match("\303\251".force_encoding('utf-8')).to_a.should == ["\u{e9}"]
+ /#{/./}/u.match("\303\251".dup.force_encoding('utf-8')).to_a.should == ["\u{e9}"]
end
it "supports /u (UTF8 encoding) with interpolation and /o" do
- /#{/./}/u.match("\303\251".force_encoding('utf-8')).to_a.should == ["\u{e9}"]
+ /#{/./}/u.match("\303\251".dup.force_encoding('utf-8')).to_a.should == ["\u{e9}"]
end
it 'uses UTF-8 as /u encoding' do
@@ -117,14 +121,27 @@ describe "Regexps with encoding modifiers" do
-> { /\A[[:space:]]*\z/ =~ " ".encode("UTF-16LE") }.should raise_error(Encoding::CompatibilityError)
end
+ it "raises Encoding::CompatibilityError when the regexp has a fixed, non-ASCII-compatible encoding" do
+ -> { Regexp.new("".dup.force_encoding("UTF-16LE"), Regexp::FIXEDENCODING) =~ " ".encode("UTF-8") }.should raise_error(Encoding::CompatibilityError)
+ end
+
+ it "raises Encoding::CompatibilityError when the regexp has a fixed encoding and the match string has non-ASCII characters" do
+ -> { Regexp.new("".dup.force_encoding("US-ASCII"), Regexp::FIXEDENCODING) =~ "\303\251".dup.force_encoding('UTF-8') }.should raise_error(Encoding::CompatibilityError)
+ end
+
+ it "raises ArgumentError when trying to match a broken String" do
+ s = "\x80".dup.force_encoding('UTF-8')
+ -> { s =~ /./ }.should raise_error(ArgumentError, "invalid byte sequence in UTF-8")
+ end
+
it "computes the Regexp Encoding for each interpolated Regexp instance" do
make_regexp = -> str { /#{str}/ }
- r = make_regexp.call("été".force_encoding(Encoding::UTF_8))
+ r = make_regexp.call("été".dup.force_encoding(Encoding::UTF_8))
r.should.fixed_encoding?
r.encoding.should == Encoding::UTF_8
- r = make_regexp.call("abc".force_encoding(Encoding::UTF_8))
+ r = make_regexp.call("abc".dup.force_encoding(Encoding::UTF_8))
r.should_not.fixed_encoding?
r.encoding.should == Encoding::US_ASCII
end
diff --git a/spec/ruby/language/regexp/escapes_spec.rb b/spec/ruby/language/regexp/escapes_spec.rb
index 2e5fe5ad2e..16a4d8c23b 100644
--- a/spec/ruby/language/regexp/escapes_spec.rb
+++ b/spec/ruby/language/regexp/escapes_spec.rb
@@ -2,8 +2,10 @@
require_relative '../../spec_helper'
require_relative '../fixtures/classes'
+# TODO: synchronize with spec/core/regexp/new_spec.rb -
+# escaping is also tested there
describe "Regexps with escape characters" do
- it "they're supported" do
+ it "supports escape sequences" do
/\t/.match("\t").to_a.should == ["\t"] # horizontal tab
/\v/.match("\v").to_a.should == ["\v"] # vertical tab
/\n/.match("\n").to_a.should == ["\n"] # newline
@@ -15,9 +17,7 @@ describe "Regexps with escape characters" do
# \nnn octal char (encoded byte value)
end
- it "support quoting meta-characters via escape sequence" do
- /\\/.match("\\").to_a.should == ["\\"]
- /\//.match("/").to_a.should == ["/"]
+ it "supports quoting meta-characters via escape sequence" do
# parenthesis, etc
/\(/.match("(").to_a.should == ["("]
/\)/.match(")").to_a.should == [")"]
@@ -25,6 +25,8 @@ describe "Regexps with escape characters" do
/\]/.match("]").to_a.should == ["]"]
/\{/.match("{").to_a.should == ["{"]
/\}/.match("}").to_a.should == ["}"]
+ /\</.match("<").to_a.should == ["<"]
+ /\>/.match(">").to_a.should == [">"]
# alternation separator
/\|/.match("|").to_a.should == ["|"]
# quantifiers
@@ -37,11 +39,81 @@ describe "Regexps with escape characters" do
/\$/.match("$").to_a.should == ["$"]
end
+ it "supports quoting meta-characters via escape sequence when used as a terminator" do
+ # parenthesis, etc
+ # %r[[, %r((, etc literals - are forbidden
+ %r(\().match("(").to_a.should == ["("]
+ %r(\)).match(")").to_a.should == [")"]
+ %r)\().match("(").to_a.should == ["("]
+ %r)\)).match(")").to_a.should == [")"]
+
+ %r[\[].match("[").to_a.should == ["["]
+ %r[\]].match("]").to_a.should == ["]"]
+ %r]\[].match("[").to_a.should == ["["]
+ %r]\]].match("]").to_a.should == ["]"]
+
+ %r{\{}.match("{").to_a.should == ["{"]
+ %r{\}}.match("}").to_a.should == ["}"]
+ %r}\{}.match("{").to_a.should == ["{"]
+ %r}\}}.match("}").to_a.should == ["}"]
+
+ %r<\<>.match("<").to_a.should == ["<"]
+ %r<\>>.match(">").to_a.should == [">"]
+ %r>\<>.match("<").to_a.should == ["<"]
+ %r>\>>.match(">").to_a.should == [">"]
+
+ # alternation separator
+ %r|\||.match("|").to_a.should == ["|"]
+ # quantifiers
+ %r?\??.match("?").to_a.should == ["?"]
+ %r.\...match(".").to_a.should == ["."]
+ %r*\**.match("*").to_a.should == ["*"]
+ %r+\++.match("+").to_a.should == ["+"]
+ # line anchors
+ %r^\^^.match("^").to_a.should == ["^"]
+ %r$\$$.match("$").to_a.should == ["$"]
+ end
+
+ it "supports quoting non-meta-characters via escape sequence when used as a terminator" do
+ non_meta_character_terminators = [
+ '!', '"', '#', '%', '&', "'", ',', '-', ':', ';', '@', '_', '`', '/', '=', '~'
+ ]
+
+ non_meta_character_terminators.each do |c|
+ pattern = eval("%r" + c + "\\" + c + c)
+ pattern.match(c).to_a.should == [c]
+ end
+ end
+
+ it "does not change semantics of escaped non-meta-character when used as a terminator" do
+ all_terminators = [*("!".."/"), *(":".."@"), *("[".."`"), *("{".."~")]
+ meta_character_terminators = ["$", "^", "*", "+", ".", "?", "|", "}", ")", ">", "]"]
+ special_cases = ['(', '{', '[', '<', '\\']
+
+ # it should be equivalent to
+ # [ '!', '"', '#', '%', '&', "'", ',', '-', ':', ';', '@', '_', '`', '/', '=', '~' ]
+ non_meta_character_terminators = all_terminators - meta_character_terminators - special_cases
+
+ non_meta_character_terminators.each do |c|
+ pattern = eval("%r" + c + "\\" + c + c)
+ pattern.should == /#{c}/
+ end
+ end
+
+ it "does not change semantics of escaped meta-character when used as a terminator" do
+ meta_character_terminators = ["$", "^", "*", "+", ".", "?", "|", "}", ")", ">", "]"]
+
+ meta_character_terminators.each do |c|
+ pattern = eval("%r" + c + "\\" + c + c)
+ pattern.should == eval("/\\#{c}/")
+ end
+ end
+
it "allows any character to be escaped" do
/\y/.match("y").to_a.should == ["y"]
end
- it "support \\x (hex characters)" do
+ it "supports \\x (hex characters)" do
/\xA/.match("\nxyz").to_a.should == ["\n"]
/\x0A/.match("\n").to_a.should == ["\n"]
/\xAA/.match("\nA").should be_nil
@@ -53,7 +125,7 @@ describe "Regexps with escape characters" do
# \x{7HHHHHHH} wide hexadecimal char (character code point value)
end
- it "support \\c (control characters)" do
+ it "supports \\c (control characters)" do
#/\c \c@\c`/.match("\00\00\00").to_a.should == ["\00\00\00"]
/\c#\cc\cC/.match("\03\03\03").to_a.should == ["\03\03\03"]
/\c'\cG\cg/.match("\a\a\a").to_a.should == ["\a\a\a"]
diff --git a/spec/ruby/language/regexp/repetition_spec.rb b/spec/ruby/language/regexp/repetition_spec.rb
index 9a191d74e2..d76619688f 100644
--- a/spec/ruby/language/regexp/repetition_spec.rb
+++ b/spec/ruby/language/regexp/repetition_spec.rb
@@ -87,9 +87,7 @@ describe "Regexps with repetition" do
/a+?*/.match("a")[0].should == "a"
/(a+?)*/.match("a")[0].should == "a"
- ruby_bug '#17341', ''...'3.0' do
- /a+?*/.match("aa")[0].should == "aa"
- end
+ /a+?*/.match("aa")[0].should == "aa"
/(a+?)*/.match("aa")[0].should == "aa"
# a+?+ should not be reduced, it should be equivalent to (a+?)+
@@ -100,9 +98,7 @@ describe "Regexps with repetition" do
/a+?+/.match("a")[0].should == "a"
/(a+?)+/.match("a")[0].should == "a"
- ruby_bug '#17341', ''...'3.0' do
- /a+?+/.match("aa")[0].should == "aa"
- end
+ /a+?+/.match("aa")[0].should == "aa"
/(a+?)+/.match("aa")[0].should == "aa"
# both a**? and a+*? should be equivalent to (a+)??
generated by cgit v1.2.3 (git 2.25.1) at 2024-05-27 23:22:46 +0000