From fa191726b9bfb92af816cc4b246537afb18388a3e9ff99295a251c66eab544c0 Mon Sep 17 00:00:00 2001 From: Matej Cepl Date: Sat, 29 Oct 2022 11:47:59 +0000 Subject: [PATCH] Accepting request 1031656 from home:yarunachalam:branches:devel:languages:python - Update to 3.0.0 Added * Extend the capability of explain=True when cp_isolation contains at most two entries (min one), will log in details of the Mess-detector results Support for alternative language frequency set in charset_normalizer.assets.FREQUENCIES Add parameter language_threshold in from_bytes, from_path and from_fp to adjust the minimum expected coherence ratio normalizer --version now specify if current version provide extra speedup (meaning mypyc compilation whl) * Changed Build with static metadata using 'build' frontend Make the language detection stricter Optional: Module md.py can be compiled using Mypyc to provide an extra speedup up to 4x faster than v2.1 * Fixed CLI with opt --normalize fail when using full path for files TooManyAccentuatedPlugin induce false positive on the mess detection when too few alpha character have been fed to it Sphinx warnings when generating the documentation * Removed Coherence detector no longer return 'Simple English' instead return 'English' Coherence detector no longer return 'Classical Chinese' instead return 'Chinese' Breaking: Method first() and best() from CharsetMatch UTF-7 will no longer appear as "detected" without a recognized SIG/mark (is unreliable/conflict with ASCII) Breaking: Class aliases CharsetDetector, CharsetDoctor, CharsetNormalizerMatch and CharsetNormalizerMatches Breaking: Top-level function normalize Breaking: Properties chaos_secondary_pass, coherence_non_latin and w_counter from CharsetMatch Support for the backport unicodedata2 OBS-URL: https://build.opensuse.org/request/show/1031656 OBS-URL: https://build.opensuse.org/package/show/devel:languages:python/python-charset-normalizer?expand=0&rev=31 --- charset_normalizer-2.1.1.tar.gz | 3 --- charset_normalizer-3.0.0.tar.gz | 3 +++ python-charset-normalizer.changes | 27 +++++++++++++++++++++++++++ python-charset-normalizer.spec | 2 +- 4 files changed, 31 insertions(+), 4 deletions(-) delete mode 100644 charset_normalizer-2.1.1.tar.gz create mode 100644 charset_normalizer-3.0.0.tar.gz diff --git a/charset_normalizer-2.1.1.tar.gz b/charset_normalizer-2.1.1.tar.gz deleted file mode 100644 index f39141e..0000000 --- a/charset_normalizer-2.1.1.tar.gz +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:6a6a202ec93ccde145ebf40e9dda7b1cd246d576533e12b8dfeaf1202e5eb912 -size 86023 diff --git a/charset_normalizer-3.0.0.tar.gz b/charset_normalizer-3.0.0.tar.gz new file mode 100644 index 0000000..2fd8a0f --- /dev/null +++ b/charset_normalizer-3.0.0.tar.gz @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7988228e24f8e3fdca28dde813ea3e8bbefb8ecea609a3c34230689fe50b054d +size 88411 diff --git a/python-charset-normalizer.changes b/python-charset-normalizer.changes index 1fc110a..2466be4 100644 --- a/python-charset-normalizer.changes +++ b/python-charset-normalizer.changes @@ -1,3 +1,30 @@ +------------------------------------------------------------------- +Thu Oct 27 22:18:02 UTC 2022 - Yogalakshmi Arunachalam + +- Update to 3.0.0 + Added + * Extend the capability of explain=True when cp_isolation contains at most two entries (min one), will log in details of the Mess-detector results + Support for alternative language frequency set in charset_normalizer.assets.FREQUENCIES + Add parameter language_threshold in from_bytes, from_path and from_fp to adjust the minimum expected coherence ratio + normalizer --version now specify if current version provide extra speedup (meaning mypyc compilation whl) + * Changed + Build with static metadata using 'build' frontend + Make the language detection stricter + Optional: Module md.py can be compiled using Mypyc to provide an extra speedup up to 4x faster than v2.1 + * Fixed + CLI with opt --normalize fail when using full path for files + TooManyAccentuatedPlugin induce false positive on the mess detection when too few alpha character have been fed to it + Sphinx warnings when generating the documentation + * Removed + Coherence detector no longer return 'Simple English' instead return 'English' + Coherence detector no longer return 'Classical Chinese' instead return 'Chinese' + Breaking: Method first() and best() from CharsetMatch + UTF-7 will no longer appear as "detected" without a recognized SIG/mark (is unreliable/conflict with ASCII) + Breaking: Class aliases CharsetDetector, CharsetDoctor, CharsetNormalizerMatch and CharsetNormalizerMatches + Breaking: Top-level function normalize + Breaking: Properties chaos_secondary_pass, coherence_non_latin and w_counter from CharsetMatch + Support for the backport unicodedata2 + ------------------------------------------------------------------- Sat Sep 17 15:46:10 UTC 2022 - Dirk Müller diff --git a/python-charset-normalizer.spec b/python-charset-normalizer.spec index 77dee9e..592a07e 100644 --- a/python-charset-normalizer.spec +++ b/python-charset-normalizer.spec @@ -19,7 +19,7 @@ %{?!python_module:%define python_module() python3-%{**}} %define skip_python2 1 Name: python-charset-normalizer -Version: 2.1.1 +Version: 3.0.0 Release: 0 Summary: Python Universal Charset detector License: MIT