Linkification Data files and tooling

unicodetools/data/links/LinkFormattingTest.txt

@@ -0,0 +1,58 @@
+# LinkFormattingTest.txt
+# Date: 2025-12-03 23:00:53 GMT 
+# © 2025 Unicode®, Inc.
+# Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries.
+# For terms of use and license, see https://www.unicode.org/terms_of_use.html
+#
+# The usage and stability of these values is covered in https://www.unicode.org/reports/tr58/
+#
+# Format: Each line has the following fields:
+# Scheme/host
+# Path
+# Query
+# Fragment
+# Result — with minimal escaping
+#
+# Empty lines, and lines starting with # are ignored.
+# Otherwise # is treated like any other character.
+#
+# The Path, Query, and Fragment may contain escapes when characters would otherwise be 
+# syntax characters in that part. For example, a literal / within a path would be \/.
+# ================================================
+Format:	
+
+# Path only					
+https://example.com;	α;	;	;	https://example.com/α
+
+# Query only					
+https://example.com;	;	α;	;	https://example.com?α
+
+# Fragment only					
+https://example.com;	;	;	α;	https://example.com#α
+
+# All parts					
+https://example.com;	αβγ/δεζ;	θ=ικλ&μ=γξο;	πρς;	https://example.com/αβγ/δεζ?θ=ικλ&μ=γξο#πρς
+
+# Escape ? in Path					
+https://example.com;	α?μπ;	;	;	https://example.com/α%3Fμπ
+
+# Escape # in Path/Query					
+https://example.com;	α#β;	γ=δ#ε;	;	https://example.com/α%23β?γ=δ%23ε
+
+# Escape hard (' ')					
+https://example.com;	αβ γ/δεζ;	θ=ικ λ&=γξο;	πρ σ;	https://example.com/αβ%20γ/δεζ?θ=ικ%20λ&=γξο#πρ%20σ
+
+# Escape soft ('.') unless followed by include					
+https://example.com;	αβγ./δεζ.;	θ=ικ.λ&=γξο.;	πρς.;	https://example.com/αβγ./δεζ.?θ=ικ.λ&=γξο.#πρς%2E
+
+# Escape unmatched brackets					
+https://example.com;	α(β));	γ(δ));	ε(ζ));	https://example.com/α(β)%29?γ(δ)%29#ε(ζ)%29
+
+# Query with escapes					
+https://example.com;	;	α\=\&=\=\&=%;	;	https://example.com?α%3D%26%=%3D%26%
+
+# Path with escapes					
+https://example.com;	α/β\/γ;	;	;	https://example.com/α/β%2Fγ
+
+# Query with escapes					
+https://example.com;	;	α\=\&%=\=\&=%;	;	https://example.com?α%3D%26%=%3D%26%

unicodetools/data/links/LinkPairedOpener.txt

@@ -0,0 +1,86 @@
+# LinkPairedOpener.txt
+# Date: 2025-12-03 23:00:53 GMT 
+# © 2025 Unicode®, Inc.
+# Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries.
+# For terms of use and license, see https://www.unicode.org/terms_of_use.html
+#
+# The usage and stability of these values is covered in https://www.unicode.org/reports/tr58/
+#
+
+# ================================================
+
+# Property:	LinkPairedOpener
+
+#  All code points not explicitly listed for LinkPairedOpener
+#  have the value undefined.
+
+# @missing: 0000..10FFFF; undefined
+
+# ================================================
+
+0029          ; 0028 # 1.1        RIGHT PARENTHESIS
+003E          ; 003C # 1.1        GREATER-THAN SIGN
+005D          ; 005B # 1.1        RIGHT SQUARE BRACKET
+007D          ; 007B # 1.1        RIGHT CURLY BRACKET
+0F3B          ; 0F3A # 2.0        TIBETAN MARK GUG RTAGS GYAS
+0F3D          ; 0F3C # 2.0        TIBETAN MARK ANG KHANG GYAS
+169C          ; 169B # 3.0        OGHAM REVERSED FEATHER MARK
+2046          ; 2045 # 1.1        RIGHT SQUARE BRACKET WITH QUILL
+207E          ; 207D # 1.1        SUPERSCRIPT RIGHT PARENTHESIS
+208E          ; 208D # 1.1        SUBSCRIPT RIGHT PARENTHESIS
+2309          ; 2308 # 1.1        RIGHT CEILING
+230B          ; 230A # 1.1        RIGHT FLOOR
+2769          ; 2768 # 3.2        MEDIUM RIGHT PARENTHESIS ORNAMENT
+276B          ; 276A # 3.2        MEDIUM FLATTENED RIGHT PARENTHESIS ORNAMENT
+276D          ; 276C # 3.2        MEDIUM RIGHT-POINTING ANGLE BRACKET ORNAMENT
+276F          ; 276E # 3.2        HEAVY RIGHT-POINTING ANGLE QUOTATION MARK ORNAMENT
+2771          ; 2770 # 3.2        HEAVY RIGHT-POINTING ANGLE BRACKET ORNAMENT
+2773          ; 2772 # 3.2        LIGHT RIGHT TORTOISE SHELL BRACKET ORNAMENT
+2775          ; 2774 # 3.2        MEDIUM RIGHT CURLY BRACKET ORNAMENT
+27C6          ; 27C5 # 4.1        RIGHT S-SHAPED BAG DELIMITER
+27E7          ; 27E6 # 3.2        MATHEMATICAL RIGHT WHITE SQUARE BRACKET
+27E9          ; 27E8 # 3.2        MATHEMATICAL RIGHT ANGLE BRACKET
+27EB          ; 27EA # 3.2        MATHEMATICAL RIGHT DOUBLE ANGLE BRACKET
+27ED          ; 27EC # 5.1        MATHEMATICAL RIGHT WHITE TORTOISE SHELL BRACKET
+27EF          ; 27EE # 5.1        MATHEMATICAL RIGHT FLATTENED PARENTHESIS
+2984          ; 2983 # 3.2        RIGHT WHITE CURLY BRACKET
+2986          ; 2985 # 3.2        RIGHT WHITE PARENTHESIS
+2988          ; 2987 # 3.2        Z NOTATION RIGHT IMAGE BRACKET
+298A          ; 2989 # 3.2        Z NOTATION RIGHT BINDING BRACKET
+298C          ; 298B # 3.2        RIGHT SQUARE BRACKET WITH UNDERBAR
+298E          ; 298F # 3.2        RIGHT SQUARE BRACKET WITH TICK IN BOTTOM CORNER
+2990          ; 298D # 3.2        RIGHT SQUARE BRACKET WITH TICK IN TOP CORNER
+2992          ; 2991 # 3.2        RIGHT ANGLE BRACKET WITH DOT
+2994          ; 2993 # 3.2        RIGHT ARC GREATER-THAN BRACKET
+2996          ; 2995 # 3.2        DOUBLE RIGHT ARC LESS-THAN BRACKET
+2998          ; 2997 # 3.2        RIGHT BLACK TORTOISE SHELL BRACKET
+29D9          ; 29D8 # 3.2        RIGHT WIGGLY FENCE
+29DB          ; 29DA # 3.2        RIGHT DOUBLE WIGGLY FENCE
+29FD          ; 29FC # 3.2        RIGHT-POINTING CURVED ANGLE BRACKET
+2E23          ; 2E22 # 5.1        TOP RIGHT HALF BRACKET
+2E25          ; 2E24 # 5.1        BOTTOM RIGHT HALF BRACKET
+2E27          ; 2E26 # 5.1        RIGHT SIDEWAYS U BRACKET
+2E29          ; 2E28 # 5.1        RIGHT DOUBLE PARENTHESIS
+2E56          ; 2E55 # 14.0       RIGHT SQUARE BRACKET WITH STROKE
+2E58          ; 2E57 # 14.0       RIGHT SQUARE BRACKET WITH DOUBLE STROKE
+2E5A          ; 2E59 # 14.0       TOP HALF RIGHT PARENTHESIS
+2E5C          ; 2E5B # 14.0       BOTTOM HALF RIGHT PARENTHESIS
+3009          ; 3008 # 1.1        RIGHT ANGLE BRACKET
+300B          ; 300A # 1.1        RIGHT DOUBLE ANGLE BRACKET
+300D          ; 300C # 1.1        RIGHT CORNER BRACKET
+300F          ; 300E # 1.1        RIGHT WHITE CORNER BRACKET
+3011          ; 3010 # 1.1        RIGHT BLACK LENTICULAR BRACKET
+3015          ; 3014 # 1.1        RIGHT TORTOISE SHELL BRACKET
+3017          ; 3016 # 1.1        RIGHT WHITE LENTICULAR BRACKET
+3019          ; 3018 # 1.1        RIGHT WHITE TORTOISE SHELL BRACKET
+301B          ; 301A # 1.1        RIGHT WHITE SQUARE BRACKET
+FE5A          ; FE59 # 1.1        SMALL RIGHT PARENTHESIS
+FE5C          ; FE5B # 1.1        SMALL RIGHT CURLY BRACKET
+FE5E          ; FE5D # 1.1        SMALL RIGHT TORTOISE SHELL BRACKET
+FF09          ; FF08 # 1.1        FULLWIDTH RIGHT PARENTHESIS
+FF3D          ; FF3B # 1.1        FULLWIDTH RIGHT SQUARE BRACKET
+FF5D          ; FF5B # 1.1        FULLWIDTH RIGHT CURLY BRACKET
+FF60          ; FF5F # 3.2        FULLWIDTH RIGHT WHITE PARENTHESIS
+FF63          ; FF62 # 1.1        HALFWIDTH RIGHT CORNER BRACKET
+
+# Total code points: 64