From 17971922dfe7f8d52d09cfb527526cae8f92fa44 Mon Sep 17 00:00:00 2001 From: CoprDistGit Date: Thu, 9 Mar 2023 17:45:20 +0000 Subject: automatic import of python-unidecode --- python-unidecode.spec | 186 ++++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 186 insertions(+) create mode 100644 python-unidecode.spec (limited to 'python-unidecode.spec') diff --git a/python-unidecode.spec b/python-unidecode.spec new file mode 100644 index 0000000..4c1d660 --- /dev/null +++ b/python-unidecode.spec @@ -0,0 +1,186 @@ +%global _empty_manifest_terminate_build 0 +Name: python-Unidecode +Version: 1.3.6 +Release: 1 +Summary: ASCII transliterations of Unicode text +License: GPL +URL: https://pypi.org/project/Unidecode/ +Source0: https://mirrors.nju.edu.cn/pypi/web/packages/0b/25/37c77fc07821cd06592df3f18281f5e716bc891abd6822ddb9ff941f821e/Unidecode-1.3.6.tar.gz +BuildArch: noarch + + +%description +It often happens that you have text data in Unicode, but you need to +represent it in ASCII. For example when integrating with legacy code that +doesn't support Unicode, or for ease of entry of non-Roman names on a US +keyboard, or when constructing ASCII machine identifiers from human-readable +Unicode strings that should still be somewhat intelligible. A popular example +of this is when making an URL slug from an article title. +**Unidecode is not a replacement for fully supporting Unicode for strings in +your program. There are a number of caveats that come with its use, +especially when its output is directly visible to users. Please read the rest +of this README before using Unidecode in your project.** +In most of examples listed above you could represent Unicode characters as +``???`` or ``\\15BA\\15A0\\1610``, to mention two extreme cases. But that's +nearly useless to someone who actually wants to read what the text says. +What Unidecode provides is a middle road: the function ``unidecode()`` takes +Unicode data and tries to represent it in ASCII characters (i.e., the +universally displayable characters between 0x00 and 0x7F), where the +compromises taken when mapping between two character sets are chosen to be +near what a human with a US keyboard would choose. +The quality of resulting ASCII representation varies. For languages of +western origin it should be between perfect and good. On the other hand +transliteration (i.e., conveying, in Roman letters, the pronunciation +expressed by the text in some other writing system) of languages like +Chinese, Japanese or Korean is a very complex issue and this library does +not even attempt to address it. It draws the line at context-free +character-by-character mapping. So a good rule of thumb is that the further +the script you are transliterating is from Latin alphabet, the worse the +transliteration will be. +Generally Unidecode produces better results than simply stripping accents from +characters (which can be done in Python with built-in functions). It is based +on hand-tuned character mappings that for example also contain ASCII +approximations for symbols and non-Latin alphabets. +**Note that some people might find certain transliterations offending.** Most +common examples include characters that are used in multiple languages. A user +expects a character to be transliterated in their language but Unidecode uses a +transliteration for a different language. It's best to not use Unidecode for +strings that are directly visible to users of your application. See also the +*Frequently Asked Questions* section for more info on common problems. +This is a Python port of ``Text::Unidecode`` Perl module by Sean M. Burke +. + +%package -n python3-Unidecode +Summary: ASCII transliterations of Unicode text +Provides: python-Unidecode +BuildRequires: python3-devel +BuildRequires: python3-setuptools +BuildRequires: python3-pip +%description -n python3-Unidecode +It often happens that you have text data in Unicode, but you need to +represent it in ASCII. For example when integrating with legacy code that +doesn't support Unicode, or for ease of entry of non-Roman names on a US +keyboard, or when constructing ASCII machine identifiers from human-readable +Unicode strings that should still be somewhat intelligible. A popular example +of this is when making an URL slug from an article title. +**Unidecode is not a replacement for fully supporting Unicode for strings in +your program. There are a number of caveats that come with its use, +especially when its output is directly visible to users. Please read the rest +of this README before using Unidecode in your project.** +In most of examples listed above you could represent Unicode characters as +``???`` or ``\\15BA\\15A0\\1610``, to mention two extreme cases. But that's +nearly useless to someone who actually wants to read what the text says. +What Unidecode provides is a middle road: the function ``unidecode()`` takes +Unicode data and tries to represent it in ASCII characters (i.e., the +universally displayable characters between 0x00 and 0x7F), where the +compromises taken when mapping between two character sets are chosen to be +near what a human with a US keyboard would choose. +The quality of resulting ASCII representation varies. For languages of +western origin it should be between perfect and good. On the other hand +transliteration (i.e., conveying, in Roman letters, the pronunciation +expressed by the text in some other writing system) of languages like +Chinese, Japanese or Korean is a very complex issue and this library does +not even attempt to address it. It draws the line at context-free +character-by-character mapping. So a good rule of thumb is that the further +the script you are transliterating is from Latin alphabet, the worse the +transliteration will be. +Generally Unidecode produces better results than simply stripping accents from +characters (which can be done in Python with built-in functions). It is based +on hand-tuned character mappings that for example also contain ASCII +approximations for symbols and non-Latin alphabets. +**Note that some people might find certain transliterations offending.** Most +common examples include characters that are used in multiple languages. A user +expects a character to be transliterated in their language but Unidecode uses a +transliteration for a different language. It's best to not use Unidecode for +strings that are directly visible to users of your application. See also the +*Frequently Asked Questions* section for more info on common problems. +This is a Python port of ``Text::Unidecode`` Perl module by Sean M. Burke +. + +%package help +Summary: Development documents and examples for Unidecode +Provides: python3-Unidecode-doc +%description help +It often happens that you have text data in Unicode, but you need to +represent it in ASCII. For example when integrating with legacy code that +doesn't support Unicode, or for ease of entry of non-Roman names on a US +keyboard, or when constructing ASCII machine identifiers from human-readable +Unicode strings that should still be somewhat intelligible. A popular example +of this is when making an URL slug from an article title. +**Unidecode is not a replacement for fully supporting Unicode for strings in +your program. There are a number of caveats that come with its use, +especially when its output is directly visible to users. Please read the rest +of this README before using Unidecode in your project.** +In most of examples listed above you could represent Unicode characters as +``???`` or ``\\15BA\\15A0\\1610``, to mention two extreme cases. But that's +nearly useless to someone who actually wants to read what the text says. +What Unidecode provides is a middle road: the function ``unidecode()`` takes +Unicode data and tries to represent it in ASCII characters (i.e., the +universally displayable characters between 0x00 and 0x7F), where the +compromises taken when mapping between two character sets are chosen to be +near what a human with a US keyboard would choose. +The quality of resulting ASCII representation varies. For languages of +western origin it should be between perfect and good. On the other hand +transliteration (i.e., conveying, in Roman letters, the pronunciation +expressed by the text in some other writing system) of languages like +Chinese, Japanese or Korean is a very complex issue and this library does +not even attempt to address it. It draws the line at context-free +character-by-character mapping. So a good rule of thumb is that the further +the script you are transliterating is from Latin alphabet, the worse the +transliteration will be. +Generally Unidecode produces better results than simply stripping accents from +characters (which can be done in Python with built-in functions). It is based +on hand-tuned character mappings that for example also contain ASCII +approximations for symbols and non-Latin alphabets. +**Note that some people might find certain transliterations offending.** Most +common examples include characters that are used in multiple languages. A user +expects a character to be transliterated in their language but Unidecode uses a +transliteration for a different language. It's best to not use Unidecode for +strings that are directly visible to users of your application. See also the +*Frequently Asked Questions* section for more info on common problems. +This is a Python port of ``Text::Unidecode`` Perl module by Sean M. Burke +. + +%prep +%autosetup -n Unidecode-1.3.6 + +%build +%py3_build + +%install +%py3_install +install -d -m755 %{buildroot}/%{_pkgdocdir} +if [ -d doc ]; then cp -arf doc %{buildroot}/%{_pkgdocdir}; fi +if [ -d docs ]; then cp -arf docs %{buildroot}/%{_pkgdocdir}; fi +if [ -d example ]; then cp -arf example %{buildroot}/%{_pkgdocdir}; fi +if [ -d examples ]; then cp -arf examples %{buildroot}/%{_pkgdocdir}; fi +pushd %{buildroot} +if [ -d usr/lib ]; then + find usr/lib -type f -printf "/%h/%f\n" >> filelist.lst +fi +if [ -d usr/lib64 ]; then + find usr/lib64 -type f -printf "/%h/%f\n" >> filelist.lst +fi +if [ -d usr/bin ]; then + find usr/bin -type f -printf "/%h/%f\n" >> filelist.lst +fi +if [ -d usr/sbin ]; then + find usr/sbin -type f -printf "/%h/%f\n" >> filelist.lst +fi +touch doclist.lst +if [ -d usr/share/man ]; then + find usr/share/man -type f -printf "/%h/%f.gz\n" >> doclist.lst +fi +popd +mv %{buildroot}/filelist.lst . +mv %{buildroot}/doclist.lst . + +%files -n python3-Unidecode -f filelist.lst +%dir %{python3_sitelib}/* + +%files help -f doclist.lst +%{_docdir}/* + +%changelog +* Thu Mar 09 2023 Python_Bot - 1.3.6-1 +- Package Spec generated -- cgit v1.2.3