Browse Source

Update unicode.org URLs

Use https, consistent host name, remove references to ftp.  Also
update the URLs for CLDR, which has moved from Trac to GitHub.
master
Peter Eisentraut 1 month ago
parent
commit
bdb839cbde
9 changed files with 31 additions and 31 deletions
  1. +8
    -8
      contrib/unaccent/generate_unaccent_rules.py
  2. +1
    -1
      doc/src/sgml/acronyms.sgml
  3. +4
    -4
      doc/src/sgml/charset.sgml
  4. +7
    -7
      src/backend/utils/mb/Unicode/Makefile
  5. +2
    -2
      src/backend/utils/mb/Unicode/UCS_to_BIG5.pl
  6. +2
    -2
      src/backend/utils/mb/Unicode/UCS_to_JOHAB.pl
  7. +2
    -2
      src/backend/utils/mb/Unicode/UCS_to_most.pl
  8. +1
    -1
      src/common/unicode/Makefile
  9. +4
    -4
      src/common/unicode_norm.c

+ 8
- 8
contrib/unaccent/generate_unaccent_rules.py View File

@@ -24,9 +24,9 @@
# Latin-ASCII.xml, the latest data sets released can be browsed directly
# via [3]. Note that this script is compatible with at least release 29.
#
# [1] http://unicode.org/Public/8.0.0/ucd/UnicodeData.txt
# [2] http://unicode.org/cldr/trac/export/14746/tags/release-34/common/transforms/Latin-ASCII.xml
# [3] https://unicode.org/cldr/trac/browser/tags
# [1] https://www.unicode.org/Public/8.0.0/ucd/UnicodeData.txt
# [2] https://raw.githubusercontent.com/unicode-org/cldr/release-34/common/transforms/Latin-ASCII.xml
# [3] https://github.com/unicode-org/cldr/tags

# BEGIN: Python 2/3 compatibility - remove when Python 2 compatibility dropped
# The approach is to be Python3 compatible with Python2 "backports".
@@ -113,7 +113,7 @@ def is_mark(codepoint):

def is_letter_with_marks(codepoint, table):
"""Returns true for letters combined with one or more marks."""
# See http://www.unicode.org/reports/tr44/tr44-14.html#General_Category_Values
# See https://www.unicode.org/reports/tr44/tr44-14.html#General_Category_Values

# Letter may have no combining characters, in which case it has
# no marks.
@@ -226,7 +226,7 @@ def special_cases():
return charactersSet

def main(args):
# http://www.unicode.org/reports/tr44/tr44-14.html#Character_Decomposition_Mappings
# https://www.unicode.org/reports/tr44/tr44-14.html#Character_Decomposition_Mappings
decomposition_type_pattern = re.compile(" *<[^>]*> *")

table = {}
@@ -243,7 +243,7 @@ def main(args):
for line in unicodeDataFile:
fields = line.split(";")
if len(fields) > 5:
# http://www.unicode.org/reports/tr44/tr44-14.html#UnicodeData.txt
# https://www.unicode.org/reports/tr44/tr44-14.html#UnicodeData.txt
general_category = fields[2]
decomposition = fields[5]
decomposition = re.sub(decomposition_type_pattern, ' ', decomposition)
@@ -281,8 +281,8 @@ def main(args):

if __name__ == "__main__":
parser = argparse.ArgumentParser(description='This script builds unaccent.rules on standard output when given the contents of UnicodeData.txt and Latin-ASCII.xml given as arguments.')
parser.add_argument("--unicode-data-file", help="Path to formatted text file corresponding to UnicodeData.txt. See <http://unicode.org/Public/8.0.0/ucd/UnicodeData.txt>.", type=str, required=True, dest='unicodeDataFilePath')
parser.add_argument("--latin-ascii-file", help="Path to XML file from Unicode Common Locale Data Repository (CLDR) corresponding to Latin-ASCII transliterator (Latin-ASCII.xml). See <http://unicode.org/cldr/trac/export/12304/tags/release-28/common/transforms/Latin-ASCII.xml>.", type=str, dest='latinAsciiFilePath')
parser.add_argument("--unicode-data-file", help="Path to formatted text file corresponding to UnicodeData.txt.", type=str, required=True, dest='unicodeDataFilePath')
parser.add_argument("--latin-ascii-file", help="Path to XML file from Unicode Common Locale Data Repository (CLDR) corresponding to Latin-ASCII transliterator (Latin-ASCII.xml).", type=str, dest='latinAsciiFilePath')
parser.add_argument("--no-ligatures-expansion", help="Do not expand ligatures and do not use Unicode CLDR Latin-ASCII transliterator. By default, this option is not enabled and \"--latin-ascii-file\" argument is required. If this option is enabled, \"--latin-ascii-file\" argument is optional and ignored.", action="store_true", dest='noLigaturesExpansion')
args = parser.parse_args()


+ 1
- 1
doc/src/sgml/acronyms.sgml View File

@@ -728,7 +728,7 @@
<term><acronym>UTF</acronym></term>
<listitem>
<para>
<ulink url="http://www.unicode.org/">Unicode Transformation
<ulink url="https://www.unicode.org/">Unicode Transformation
Format</ulink>
</para>
</listitem>

+ 4
- 4
doc/src/sgml/charset.sgml View File

@@ -832,12 +832,12 @@ CREATE COLLATION german (provider = libc, locale = 'de_DE');
</varlistentry>
</variablelist>

See <ulink url="http://unicode.org/reports/tr35/tr35-collation.html">Unicode
See <ulink url="https://www.unicode.org/reports/tr35/tr35-collation.html">Unicode
Technical Standard #35</ulink>
and <ulink url="https://tools.ietf.org/html/bcp47">BCP 47</ulink> for
details. The list of possible collation types (<literal>co</literal>
subtag) can be found in
the <ulink url="http://www.unicode.org/repos/cldr/trunk/common/bcp47/collation.xml">CLDR
the <ulink url="https://github.com/unicode-org/cldr/blob/master/common/bcp47/collation.xml">CLDR
repository</ulink>.
The <ulink url="https://ssl.icu-project.org/icu-bin/locexp">ICU Locale
Explorer</ulink> can be used to check the details of a particular locale
@@ -900,7 +900,7 @@ CREATE COLLATION french FROM "fr-x-icu";
different Unicode normal forms. It is up to the collation provider to
actually implement such insensitive comparisons; the deterministic flag
only determines whether ties are to be broken using bytewise comparison.
See also <ulink url="https://unicode.org/reports/tr10">Unicode Technical
See also <ulink url="https://www.unicode.org/reports/tr10">Unicode Technical
Standard 10</ulink> for more information on the terminology.
</para>

@@ -1926,7 +1926,7 @@ RESET client_encoding;
</varlistentry>

<varlistentry>
<term><ulink url="http://www.unicode.org/"></ulink></term>
<term><ulink url="https://www.unicode.org/"></ulink></term>

<listitem>
<para>

+ 7
- 7
src/backend/utils/mb/Unicode/Makefile View File

@@ -119,7 +119,7 @@ DOWNLOAD = wget -O $@ --no-use-server-timestamps
#DOWNLOAD = curl -o $@

BIG5.TXT CNS11643.TXT:
$(DOWNLOAD) http://ftp.unicode.org/Public/MAPPINGS/OBSOLETE/EASTASIA/OTHER/$(@F)
$(DOWNLOAD) https://www.unicode.org/Public/MAPPINGS/OBSOLETE/EASTASIA/OTHER/$(@F)

euc-jis-2004-std.txt sjis-0213-2004-std.txt:
$(DOWNLOAD) http://x0213.org/codetable/$(@F)
@@ -131,19 +131,19 @@ GB2312.TXT:
$(DOWNLOAD) 'http://trac.greenstone.org/browser/trunk/gsdl/unicode/MAPPINGS/EASTASIA/GB/GB2312.TXT?rev=1842&format=txt'

JIS0212.TXT:
$(DOWNLOAD) http://ftp.unicode.org/Public/MAPPINGS/OBSOLETE/EASTASIA/JIS/$(@F)
$(DOWNLOAD) https://www.unicode.org/Public/MAPPINGS/OBSOLETE/EASTASIA/JIS/$(@F)

JOHAB.TXT KSX1001.TXT:
$(DOWNLOAD) http://ftp.unicode.org/Public/MAPPINGS/OBSOLETE/EASTASIA/KSC/$(@F)
$(DOWNLOAD) https://www.unicode.org/Public/MAPPINGS/OBSOLETE/EASTASIA/KSC/$(@F)

KOI8-R.TXT KOI8-U.TXT:
$(DOWNLOAD) http://ftp.unicode.org/Public/MAPPINGS/VENDORS/MISC/$(@F)
$(DOWNLOAD) https://www.unicode.org/Public/MAPPINGS/VENDORS/MISC/$(@F)

$(ISO8859TEXTS):
$(DOWNLOAD) http://ftp.unicode.org/Public/MAPPINGS/ISO8859/$(@F)
$(DOWNLOAD) https://www.unicode.org/Public/MAPPINGS/ISO8859/$(@F)

$(filter-out CP8%,$(WINTEXTS)) CP932.TXT CP950.TXT:
$(DOWNLOAD) http://ftp.unicode.org/Public/MAPPINGS/VENDORS/MICSFT/WINDOWS/$(@F)
$(DOWNLOAD) https://www.unicode.org/Public/MAPPINGS/VENDORS/MICSFT/WINDOWS/$(@F)

$(filter CP8%,$(WINTEXTS)):
$(DOWNLOAD) http://ftp.unicode.org/Public/MAPPINGS/VENDORS/MICSFT/PC/$(@F)
$(DOWNLOAD) https://www.unicode.org/Public/MAPPINGS/VENDORS/MICSFT/PC/$(@F)

+ 2
- 2
src/backend/utils/mb/Unicode/UCS_to_BIG5.pl View File

@@ -8,8 +8,8 @@
# map files provided by Unicode organization.
# Unfortunately it is prohibited by the organization
# to distribute the map files. So if you try to use this script,
# you have to obtain the map files from the organization's ftp site.
# ftp://www.unicode.org/Public/MAPPINGS/
# you have to obtain the map files from the organization's download site.
# https://www.unicode.org/Public/MAPPINGS/
#
# Our "big5" comes from BIG5.TXT, with the addition of the characters
# in the range 0xf9d6-0xf9dc from CP950.TXT.

+ 2
- 2
src/backend/utils/mb/Unicode/UCS_to_JOHAB.pl View File

@@ -8,8 +8,8 @@
# map files provided by Unicode organization.
# Unfortunately it is prohibited by the organization
# to distribute the map files. So if you try to use this script,
# you have to obtain the map files from the organization's ftp site.
# ftp://www.unicode.org/Public/MAPPINGS/
# you have to obtain the map files from the organization's download site.
# https://www.unicode.org/Public/MAPPINGS/
# We assume the file include three tab-separated columns:
# JOHAB code in hex
# UCS-2 code in hex

+ 2
- 2
src/backend/utils/mb/Unicode/UCS_to_most.pl View File

@@ -8,8 +8,8 @@
# map files provided by Unicode organization.
# Unfortunately it is prohibited by the organization
# to distribute the map files. So if you try to use this script,
# you have to obtain the map files from the organization's ftp site.
# ftp://www.unicode.org/Public/MAPPINGS/
# you have to obtain the map files from the organization's download site.
# https://www.unicode.org/Public/MAPPINGS/
# We assume the file include three tab-separated columns:
# source character set code in hex
# UCS-2 code in hex

+ 1
- 1
src/common/unicode/Makefile View File

@@ -23,7 +23,7 @@ DOWNLOAD = wget -O $@ --no-use-server-timestamps
# These files are part of the Unicode Character Database. Download
# them on demand.
UnicodeData.txt CompositionExclusions.txt NormalizationTest.txt:
$(DOWNLOAD) http://unicode.org/Public/UNIDATA/$(@F)
$(DOWNLOAD) https://www.unicode.org/Public/UNIDATA/$(@F)

# Generation of conversion tables used for string normalization with
# UTF-8 strings.

+ 4
- 4
src/common/unicode_norm.c View File

@@ -3,7 +3,7 @@
* Normalize a Unicode string to NFKC form
*
* This implements Unicode normalization, per the documentation at
* http://www.unicode.org/reports/tr15/.
* https://www.unicode.org/reports/tr15/.
*
* Portions Copyright (c) 2017-2019, PostgreSQL Global Development Group
*
@@ -109,7 +109,7 @@ get_decomposed_size(pg_wchar code)
/*
* Fast path for Hangul characters not stored in tables to save memory as
* decomposition is algorithmic. See
* http://unicode.org/reports/tr15/tr15-18.html, annex 10 for details on
* https://www.unicode.org/reports/tr15/tr15-18.html, annex 10 for details on
* the matter.
*/
if (code >= SBASE && code < SBASE + SCOUNT)
@@ -234,7 +234,7 @@ decompose_code(pg_wchar code, pg_wchar **result, int *current)
/*
* Fast path for Hangul characters not stored in tables to save memory as
* decomposition is algorithmic. See
* http://unicode.org/reports/tr15/tr15-18.html, annex 10 for details on
* https://www.unicode.org/reports/tr15/tr15-18.html, annex 10 for details on
* the matter.
*/
if (code >= SBASE && code < SBASE + SCOUNT)
@@ -362,7 +362,7 @@ unicode_normalize_kc(const pg_wchar *input)
continue;

/*
* Per Unicode (http://unicode.org/reports/tr15/tr15-18.html) annex 4,
* Per Unicode (https://www.unicode.org/reports/tr15/tr15-18.html) annex 4,
* a sequence of two adjacent characters in a string is an
* exchangeable pair if the combining class (from the Unicode
* Character Database) for the first character is greater than the

Loading…
Cancel
Save