UCD.js | Unicode Character Database for JavaScript

0 linesOpen Raw Download
# LinkFormattingTest.txt
# Date: 2025-12-26, 00:24:58 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: This is not a file with semicolon-delimited fields.
# Instead, it consists of paired lines, separated by empty lines and/or comment lines.
# The first line of each pair is the source, fully escaped.
# The second line of each pair is the result, minimally escaped.
# 
# Comments are lines that begin with a #.
# 
# The fully-escaped field percent-escapes all literal syntax characters and all characters above ASCII.
# The minimally-escaped field is the more readable format described in UTS #58.
# Each pair also has a comment line for the internal structure of the URL.
# 𝑺 = the schema
# 𝑯 = the host (typically just a domain name) the internal structure is not broken down.
# 𝑷 = indicates one of the labels in the path. So /seg1/seg2 becomes 𝑷=seg1 𝑷=seg1
# 𝑸 = each key in the query. So &θ=ικλ&μ=γξο becomes 𝑸=θ 𝑽=ικλ 𝑸=μ 𝑽=γξο.
# 𝑽 = a value for the preceding key
# 𝑭 = a fragment. So #reserved:~:text=Reserved,into:~:text=open,closed becomes 𝑭=reserved 𝑫=Reserved,into 𝑫=text=open,closed
# 𝑫 = a fragment-directive
# ================================================
# 

# Selected test cases

# Path only					
# {𝑺=https:// 𝑯=example.com 𝑷=α}
https://example.com/%CE%B1
https://example.com/α

# Query only					
# {𝑺=https:// 𝑯=example.com 𝑸=α}
https://example.com?%CE%B1
https://example.com?α

# Fragment only					
# {𝑺=https:// 𝑯=example.com 𝑭=α}
https://example.com#%CE%B1
https://example.com#α

# All parts					
# {𝑺=https:// 𝑯=example.com 𝑷=αβγ 𝑷=δεζ 𝑸=θ 𝑽=ικλ 𝑸=μ 𝑽=γξο 𝑭=πρς}
https://example.com/%CE%B1%CE%B2%CE%B3/%CE%B4%CE%B5%CE%B6?%CE%B8=%CE%B9%CE%BA%CE%BB&%CE%BC=%CE%B3%CE%BE%CE%BF#%CF%80%CF%81%CF%82
https://example.com/αβγ/δεζ?θ=ικλ&μ=γξο#πρς

# Escape soft at end of Path (with nothing following)				
# {𝑺=https:// 𝑯=example.com 𝑷=αβγ 𝑷=δ.εζ.}
https://example.com/%CE%B1%CE%B2%CE%B3/%CE%B4.%CE%B5%CE%B6.
https://example.com/αβγ/δ.εζ%2E

# Escape soft at end of Query (with nothing following)				
# {𝑺=https:// 𝑯=example.com 𝑷=αβγ 𝑷=δ.εζ. 𝑸=θ 𝑽=ικλ 𝑸=μ 𝑽=γ.ξο.}
https://example.com/%CE%B1%CE%B2%CE%B3/%CE%B4.%CE%B5%CE%B6.?%CE%B8=%CE%B9%CE%BA%CE%BB&%CE%BC=%CE%B3.%CE%BE%CE%BF.
https://example.com/αβγ/δ.εζ.?θ=ικλ&μ=γ.ξο%2E

# Escape soft at end of Fragment (with nothing following)				
# {𝑺=https:// 𝑯=example.com 𝑷=αβγ 𝑷=δ.εζ 𝑸=θ 𝑽=ικλ 𝑸=μ 𝑽=γ.ξο 𝑭=π.ρς.}
https://example.com/%CE%B1%CE%B2%CE%B3/%CE%B4.%CE%B5%CE%B6?%CE%B8=%CE%B9%CE%BA%CE%BB&%CE%BC=%CE%B3.%CE%BE%CE%BF#%CF%80.%CF%81%CF%82.
https://example.com/αβγ/δ.εζ?θ=ικλ&μ=γ.ξο#π.ρς%2E

# Escape ? in Path					
# {𝑺=https:// 𝑯=example.com 𝑷=α?μπ}
https://example.com/%CE%B1%3F%CE%BC%CF%80
https://example.com/α%3Fμπ

# Escape #, =, & in Path/Query					
# {𝑺=https:// 𝑯=example.com 𝑷=α#β 𝑸=γ 𝑽=δ#ε}
https://example.com/%CE%B1#%CE%B2?%CE%B3=%CE%B4#%CE%B5
https://example.com/α%23β?γ=δ%23ε

# Escape hard (' ')					
# {𝑺=https:// 𝑯=example.com 𝑷=αβ γ 𝑷=δεζ 𝑸=θ 𝑽=ικ λ 𝑸= 𝑽=γξο 𝑭=πρ σ}
https://example.com/%CE%B1%CE%B2%20%CE%B3/%CE%B4%CE%B5%CE%B6?%CE%B8=%CE%B9%CE%BA%20%CE%BB&=%CE%B3%CE%BE%CE%BF#%CF%80%CF%81%20%CF%83
https://example.com/αβ%20γ/δεζ?θ=ικ%20λ&=γξο#πρ%20σ

# Escape soft ('.') unless followed by include					
# {𝑺=https:// 𝑯=example.com 𝑷=αβγ. 𝑷=δεζ. 𝑸=θ 𝑽=ικ.λ 𝑸= 𝑽=γξο. 𝑭=πρς.}
https://example.com/%CE%B1%CE%B2%CE%B3./%CE%B4%CE%B5%CE%B6.?%CE%B8=%CE%B9%CE%BA.%CE%BB&=%CE%B3%CE%BE%CE%BF.#%CF%80%CF%81%CF%82.
https://example.com/αβγ./δεζ.?θ=ικ.λ&=γξο.#πρς%2E

# Escape unmatched brackets					
# {𝑺=https:// 𝑯=example.com 𝑷=α(β) 𝑸=γ(δ) 𝑭=ε(ζ))}
https://example.com/%CE%B1(%CE%B2)?%CE%B3(%CE%B4)#%CE%B5(%CE%B6))
https://example.com/α(β)?γ(δ)#ε(ζ)%29

# {𝑺=https:// 𝑯=example.com 𝑷=α(β) 𝑸=γ(δ))}
https://example.com/%CE%B1(%CE%B2)?%CE%B3(%CE%B4))
https://example.com/α(β)?γ(δ)%29

# {𝑺=https:// 𝑯=example.com 𝑷=α(β) 𝑭=ε(ζ))}
https://example.com/%CE%B1(%CE%B2)#%CE%B5(%CE%B6))
https://example.com/α(β)#ε(ζ)%29

# {𝑺=https:// 𝑯=example.com 𝑷=α(β))}
https://example.com/%CE%B1(%CE%B2))
https://example.com/α(β)%29

# {𝑺=https:// 𝑯=example.com 𝑸=γ(δ) 𝑭=ε(ζ))}
https://example.com?%CE%B3(%CE%B4)#%CE%B5(%CE%B6))
https://example.com?γ(δ)#ε(ζ)%29

# {𝑺=https:// 𝑯=example.com 𝑸=γ(δ))}
https://example.com?%CE%B3(%CE%B4))
https://example.com?γ(δ)%29

# {𝑺=https:// 𝑯=example.com 𝑭=ε(ζ))}
https://example.com#%CE%B5(%CE%B6))
https://example.com#ε(ζ)%29

# No escape for matched brackets					
# {𝑺=https:// 𝑯=example.com 𝑷=α(β) 𝑸=γ(δ) 𝑭=ε(ζ)}
https://example.com/%CE%B1(%CE%B2)?%CE%B3(%CE%B4)#%CE%B5(%CE%B6)
https://example.com/α(β)?γ(δ)#ε(ζ)

# {𝑺=https:// 𝑯=example.com 𝑷=α(β) 𝑸=γ(δ)}
https://example.com/%CE%B1(%CE%B2)?%CE%B3(%CE%B4)
https://example.com/α(β)?γ(δ)

# {𝑺=https:// 𝑯=example.com 𝑷=α(β) 𝑭=ε(ζ)}
https://example.com/%CE%B1(%CE%B2)#%CE%B5(%CE%B6)
https://example.com/α(β)#ε(ζ)

# {𝑺=https:// 𝑯=example.com 𝑷=α(β)}
https://example.com/%CE%B1(%CE%B2)
https://example.com/α(β)

# {𝑺=https:// 𝑯=example.com 𝑸=γ(δ) 𝑭=ε(ζ)}
https://example.com?%CE%B3(%CE%B4)#%CE%B5(%CE%B6)
https://example.com?γ(δ)#ε(ζ)

# {𝑺=https:// 𝑯=example.com 𝑸=γ(δ)}
https://example.com?%CE%B3(%CE%B4)
https://example.com?γ(δ)

# {𝑺=https:// 𝑯=example.com 𝑭=ε(ζ)}
https://example.com#%CE%B5(%CE%B6)
https://example.com#ε(ζ)

# Path with escaped separator
# {𝑺=https:// 𝑯=example.com 𝑷=α 𝑷=β/γ}
https://example.com/%CE%B1/%CE%B2/%CE%B3
https://example.com/α/β%2Fγ

# Path with escapes (% is escaped only if followed by 2 hex digits [0-9A-fa-f)
# {𝑺=https:// 𝑯=example.com 𝑷=α 𝑷=β%41γ%ε%}
https://example.com/%CE%B1/%CE%B2%2541%CE%B3%%CE%B5%
https://example.com/α/β%2541γ%ε%

# Query with escapes (& separates key-value pairs, so handle literal &)	
# {𝑺=https:// 𝑯=example.com 𝑸=α& 𝑽=β 𝑸=γ 𝑽=&δ}
https://example.com?%CE%B1&=%CE%B2&%CE%B3=&%CE%B4
https://example.com?α%26=β&γ=%26δ

# Query with escapes (= separates keys and values, so handle literal =)	
# {𝑺=https:// 𝑯=example.com 𝑸=α=β 𝑽=γ=δ}
https://example.com?%CE%B1=%CE%B2=%CE%B3=%CE%B4
https://example.com?α%3Dβ=γ%3Dδ

# Query with escapes (% is escaped only if followed by 2 hex digits [0-9A-fa-f)
# {𝑺=https:// 𝑯=example.com 𝑸=α%β 𝑽=γ%δ}
https://example.com?%CE%B1%%CE%B2=%CE%B3%%CE%B4
https://example.com?α%β=γ%δ

# Path and Query with quoted syntax characters
# {𝑺=https:// 𝑯=example.com 𝑷=α 𝑷=b/?#c 𝑸=αβ 𝑽=γ&ζ=#Ξ 𝑸=k 𝑽=v 𝑭=frag}
https://example.com/%CE%B1/b/%3F#c?%CE%B1%CE%B2=%CE%B3&%CE%B6=#%CE%9E&k=v#frag
https://example.com/α/b%2F%3F%23c?αβ=γ%26ζ%3D%23Ξ&k=v#frag


# Wikipedia test cases

# {𝑺=https:// 𝑯=ru.wikinews.org 𝑷=wiki 𝑷=Категория:Вселенная}
https://ru.wikinews.org/wiki/%D0%9A%D0%B0%D1%82%D0%B5%D0%B3%D0%BE%D1%80%D0%B8%D1%8F:%D0%92%D1%81%D0%B5%D0%BB%D0%B5%D0%BD%D0%BD%D0%B0%D1%8F
https://ru.wikinews.org/wiki/Категория:Вселенная

# {𝑺=https:// 𝑯=av.wikipedia.org 𝑷=wiki 𝑷=Ракь_(планета)}
https://av.wikipedia.org/wiki/%D0%A0%D0%B0%D0%BA%D1%8C_(%D0%BF%D0%BB%D0%B0%D0%BD%D0%B5%D1%82%D0%B0)
https://av.wikipedia.org/wiki/Ракь_(планета)

# {𝑺=https:// 𝑯=bo.wikipedia.org 𝑷=wiki 𝑷=སའི་གོ་ལ།}
https://bo.wikipedia.org/wiki/%E0%BD%A6%E0%BD%A0%E0%BD%B2%E0%BC%8B%E0%BD%82%E0%BD%BC%E0%BC%8B%E0%BD%A3%E0%BC%8D
https://bo.wikipedia.org/wiki/སའི་གོ་ལ།

# {𝑺=https:// 𝑯=fiu-vro.wikipedia.org 𝑷=wiki 𝑷=Maa_(hod'otäht)}
https://fiu-vro.wikipedia.org/wiki/Maa_(hod'ot%C3%A4ht)
https://fiu-vro.wikipedia.org/wiki/Maa_(hod'otäht)

# {𝑺=https:// 𝑯=ty.wikipedia.org 𝑷=wiki 𝑷=’Afirita}
https://ty.wikipedia.org/wiki/’Afirita
https://ty.wikipedia.org/wiki/’Afirita

# {𝑺=https:// 𝑯=ab.wikipedia.org 𝑷=wiki 𝑷=Вашингтон,_Џьорџь}
https://ab.wikipedia.org/wiki/%D0%92%D0%B0%D1%88%D0%B8%D0%BD%D0%B3%D1%82%D0%BE%D0%BD,_%D0%8F%D1%8C%D0%BE%D1%80%D1%9F%D1%8C
https://ab.wikipedia.org/wiki/Вашингтон,_Џьорџь

# {𝑺=https:// 𝑯=mni.wikipedia.org 𝑷=wiki 𝑷=ꯅ꯭ꯌꯨ_ꯌꯣꯔ꯭ꯛ_ꯁꯤꯇꯤꯒꯤ_ꯌꯨ.ꯑꯦꯁ.}
https://mni.wikipedia.org/wiki/ꯅ꯭ꯌꯨ_ꯌꯣꯔ꯭ꯛ_ꯁꯤꯇꯤꯒꯤ_ꯌꯨ.ꯑꯦꯁ.
https://mni.wikipedia.org/wiki/ꯅ꯭ꯌꯨ_ꯌꯣꯔ꯭ꯛ_ꯁꯤꯇꯤꯒꯤ_ꯌꯨ.ꯑꯦꯁ.

# {𝑺=https:// 𝑯=azb.wikipedia.org 𝑷=wiki 𝑷=واشینقتن،_دی.سی.}
https://azb.wikipedia.org/wiki/%D9%88%D8%A7%D8%B4%DB%8C%D9%86%D9%82%D8%AA%D9%86%D8%8C_%D8%AF%DB%8C.%D8%B3%DB%8C.
https://azb.wikipedia.org/wiki/واشینقتن،_دی.سی.

# {𝑺=https:// 𝑯=mad.wikipedia.org 𝑷=wiki 𝑷=Tasè’}
https://mad.wikipedia.org/wiki/Tas%C3%A8’
https://mad.wikipedia.org/wiki/Tasè’

# {𝑺=https:// 𝑯=wuu.wikipedia.org 𝑷=wiki 𝑷=聖保羅（巴西）}
https://wuu.wikipedia.org/wiki/聖保羅（巴西）
https://wuu.wikipedia.org/wiki/聖保羅（巴西）

# {𝑺=https:// 𝑯=vep.wikipedia.org 𝑷=wiki 𝑷=Brüssel'}
https://vep.wikipedia.org/wiki/Br%C3%BCssel'
https://vep.wikipedia.org/wiki/Brüssel'

# {𝑺=https:// 𝑯=tw.wikipedia.org 𝑷=wiki 𝑷=Wiase_Nyinaa_Wɛbsaet_(_World_Wide_Web;_WWW_)}
https://tw.wikipedia.org/wiki/Wiase_Nyinaa_W%C9%9Bbsaet_(_World_Wide_Web;_WWW_)
https://tw.wikipedia.org/wiki/Wiase_Nyinaa_Wɛbsaet_(_World_Wide_Web;_WWW_)

# {𝑺=https:// 𝑯=ja.wikibooks.org 𝑷=wiki 𝑷=植物学 𝑷=植物とはどのような生き物か？}
https://ja.wikibooks.org/wiki/植物学/植物とはどのような生き物か？
https://ja.wikibooks.org/wiki/植物学/植物とはどのような生き物か？

# {𝑺=https:// 𝑯=bn.wikibooks.org 𝑷=wiki 𝑷=উইকিশৈশব:দেশসমূহ_(অ-হ) 𝑷=ইসরায়েল}
https://bn.wikibooks.org/wiki/%E0%A6%89%E0%A6%87%E0%A6%95%E0%A6%BF%E0%A6%B6%E0%A7%88%E0%A6%B6%E0%A6%AC:%E0%A6%A6%E0%A7%87%E0%A6%B6%E0%A6%B8%E0%A6%AE%E0%A7%82%E0%A6%B9_(%E0%A6%85-%E0%A6%B9)/%E0%A6%87%E0%A6%B8%E0%A6%B0%E0%A6%BE%E0%A6%AF%E0%A6%BC%E0%A7%87%E0%A6%B2
https://bn.wikibooks.org/wiki/উইকিশৈশব:দেশসমূহ_(অ-হ)/ইসরায়েল

# {𝑺=https:// 𝑯=haw.wikipedia.org 𝑷=wiki 𝑷=Puke_noi‘i_kū‘ikena}
https://haw.wikipedia.org/wiki/Puke_noi‘i_k%C5%AB‘ikena
https://haw.wikipedia.org/wiki/Puke_noi‘i_kū‘ikena

# {𝑺=https:// 𝑯=new.wikipedia.org 𝑷=wiki 𝑷=विन्सेन्ट_भ्यान_ग:}
https://new.wikipedia.org/wiki/%E0%A4%B5%E0%A4%BF%E0%A4%A8%E0%A5%8D%E0%A4%B8%E0%A5%87%E0%A4%A8%E0%A5%8D%E0%A4%9F_%E0%A4%AD%E0%A5%8D%E0%A4%AF%E0%A4%BE%E0%A4%A8_%E0%A4%97:
https://new.wikipedia.org/wiki/विन्सेन्ट_भ्यान_ग:

# {𝑺=https:// 𝑯=he.wikipedia.org 𝑷=wiki 𝑷=נאט"ו}
https://he.wikipedia.org/wiki/%D7%A0%D7%90%D7%98%22%D7%95
https://he.wikipedia.org/wiki/נאט"ו

# {𝑺=https:// 𝑯=ks.wikipedia.org 𝑷=wiki 𝑷=شارٕک۔}
https://ks.wikipedia.org/wiki/%D8%B4%D8%A7%D8%B1%D9%95%DA%A9%DB%94
https://ks.wikipedia.org/wiki/شارٕک۔

# {𝑺=https:// 𝑯=zh.wikipedia.org 𝑷=wiki 𝑷=联合国教育、科学及文化组织}
https://zh.wikipedia.org/wiki/联合国教育、科学及文化组织
https://zh.wikipedia.org/wiki/联合国教育、科学及文化组织

# {𝑺=https:// 𝑯=am.wikipedia.org 𝑷=wiki 𝑷=«የሰብዓዊ_መብት_አቀፋዊ_መግለጽ»}
https://am.wikipedia.org/wiki/%C2%ABየሰብዓዊ_መብት_አቀፋዊ_መግለጽ%C2%BB
https://am.wikipedia.org/wiki/«የሰብዓዊ_መብት_አቀፋዊ_መግለጽ»

# {𝑺=https:// 𝑯=bo.wikipedia.org 𝑷=wiki 𝑷=༼མ་ཧ་བ་ར་ཏ།༽}
https://bo.wikipedia.org/wiki/%E0%BC%BC%E0%BD%98%E0%BC%8B%E0%BD%A7%E0%BC%8B%E0%BD%96%E0%BC%8B%E0%BD%A2%E0%BC%8B%E0%BD%8F%E0%BC%8D%E0%BC%BD
https://bo.wikipedia.org/wiki/༼མ་ཧ་བ་ར་ཏ།༽

# {𝑺=https:// 𝑯=am.wikipedia.org 𝑷=wiki 𝑷=አፈ፡ታሪክ}
https://am.wikipedia.org/wiki/አፈ፡ታሪክ
https://am.wikipedia.org/wiki/አፈ፡ታሪክ

# {𝑺=https:// 𝑯=it.wikibooks.org 𝑷=wiki 𝑷=Questo_è_l'ebraismo!}
https://it.wikibooks.org/wiki/Questo_%C3%A8_l'ebraismo!
https://it.wikibooks.org/wiki/Questo_è_l'ebraismo!

# {𝑺=https:// 𝑯=my.wikipedia.org 𝑷=wiki 𝑷=ခို၊_ချိုးနှင့်_အလားတူငှက်များ}
https://my.wikipedia.org/wiki/%E1%80%81%E1%80%AD%E1%80%AF%E1%81%8A_%E1%80%81%E1%80%BB%E1%80%AD%E1%80%AF%E1%80%B8%E1%80%94%E1%80%BE%E1%80%84%E1%80%B7%E1%80%BA_%E1%80%A1%E1%80%9C%E1%80%AC%E1%80%B8%E1%80%90%E1%80%B0%E1%80%84%E1%80%BE%E1%80%80%E1%80%BA%E1%80%99%E1%80%BB%E1%80%AC%E1%80%B8
https://my.wikipedia.org/wiki/ခို၊_ချိုးနှင့်_အလားတူငှက်များ