[Python-modules-commits] [chardet] 02/12: Import chardet_3.0.4.orig.tar.gz
Daniele Tricoli
eriol-guest at moszumanska.debian.org
Sun Jun 18 21:58:33 UTC 2017
This is an automated email from the git hooks/post-receive script.
eriol-guest pushed a commit to branch master
in repository chardet.
commit 3225b88a15307c172fb0d8ac1a41240b8c3fb348
Author: Daniele Tricoli <eriol at mornie.org>
Date: Sun Jun 18 16:50:33 2017 +0200
Import chardet_3.0.4.orig.tar.gz
---
MANIFEST.in | 8 +-
NOTES.rst | 140 ++
PKG-INFO | 38 +-
README.rst | 28 +-
chardet.egg-info/PKG-INFO | 38 +-
chardet.egg-info/SOURCES.txt | 409 +++-
chardet.egg-info/entry_points.txt | 2 +-
chardet/__init__.py | 31 +-
chardet/big5freq.py | 545 +----
chardet/big5prober.py | 15 +-
chardet/chardistribution.py | 146 +-
chardet/charsetgroupprober.py | 110 +-
chardet/charsetprober.py | 119 +-
chardet/cli/__init__.py | 1 +
chardet/{ => cli}/chardetect.py | 21 +-
chardet/codingstatemachine.py | 67 +-
chardet/compat.py | 16 +-
chardet/constants.py | 39 -
chardet/cp949prober.py | 19 +-
chardet/enums.py | 76 +
chardet/escprober.py | 97 +-
chardet/escsm.py | 128 +-
chardet/eucjpprober.py | 82 +-
chardet/euckrfreq.py | 415 +---
chardet/euckrprober.py | 15 +-
chardet/euctwfreq.py | 719 +++---
chardet/euctwprober.py | 19 +-
chardet/gb2312freq.py | 195 +-
chardet/gb2312prober.py | 19 +-
chardet/hebrewprober.py | 157 +-
chardet/jisfreq.py | 250 +-
chardet/jpcntx.py | 124 +-
chardet/langbulgarianmodel.py | 25 +-
chardet/langcyrillicmodel.py | 82 +-
chardet/langgreekmodel.py | 28 +-
chardet/langhebrewmodel.py | 17 +-
chardet/langhungarianmodel.py | 24 +-
chardet/langthaimodel.py | 13 +-
chardet/langturkishmodel.py | 193 ++
chardet/latin1prober.py | 48 +-
chardet/mbcharsetprober.py | 85 +-
chardet/mbcsgroupprober.py | 6 +-
chardet/mbcssm.py | 298 +--
chardet/sbcharsetprober.py | 150 +-
chardet/sbcsgroupprober.py | 30 +-
chardet/sjisprober.py | 85 +-
chardet/universaldetector.py | 326 ++-
chardet/utf8prober.py | 58 +-
chardet/version.py | 9 +
docs/.gitignore | 1 +
docs/Makefile | 177 ++
docs/README.md | 3 +
docs/api/chardet.rst | 310 +++
docs/api/modules.rst | 7 +
docs/conf.py | 263 +++
docs/faq.rst | 105 +
docs/how-it-works.rst | 164 ++
docs/index.rst | 25 +
docs/make.bat | 242 ++
docs/supported-encodings.rst | 30 +
docs/usage.rst | 88 +
setup.cfg | 13 +-
setup.py | 37 +-
test.py | 128 ++
tests/Big5/0804.blogspot.com.xml | 325 +++
.../_chromium_Big5_with_no_encoding_specified.html | 16 +
tests/Big5/_ude_1.txt | 14 +
tests/Big5/blog.worren.net.xml | 296 +++
tests/Big5/carbonxiv.blogspot.com.xml | 216 ++
tests/Big5/catshadow.blogspot.com.xml | 261 +++
tests/Big5/coolloud.org.tw.xml | 293 +++
tests/Big5/digitalwall.com.xml | 38 +
tests/Big5/ebao.us.xml | 109 +
tests/Big5/fudesign.blogspot.com.xml | 160 ++
tests/Big5/kafkatseng.blogspot.com.xml | 62 +
tests/Big5/ke207.blogspot.com.xml | 249 ++
tests/Big5/leavesth.blogspot.com.xml | 314 +++
tests/Big5/letterlego.blogspot.com.xml | 1123 +++++++++
tests/Big5/linyijen.blogspot.com.xml | 178 ++
tests/Big5/marilynwu.blogspot.com.xml | 103 +
tests/Big5/myblog.pchome.com.tw.xml | 52 +
tests/Big5/oui-design.com.xml | 76 +
tests/Big5/sanwenji.blogspot.com.xml | 1075 +++++++++
tests/Big5/sinica.edu.tw.xml | 250 ++
tests/Big5/sylvia1976.blogspot.com.xml | 45 +
tests/Big5/tlkkuo.blogspot.com.xml | 119 +
tests/Big5/unoriginalblog.com.xml | 229 ++
tests/Big5/upsaid.com.xml | 188 ++
tests/Big5/willythecop.blogspot.com.xml | 224 ++
tests/Big5/ytc.blogspot.com.xml | 308 +++
tests/CP932/hardsoft.at.webry.info.xml | 911 ++++++++
tests/CP932/www2.chuo-u.ac.jp-suishin.xml | 140 ++
tests/CP932/y-moto.com.xml | 606 +++++
tests/CP949/ricanet.com.xml | 411 ++++
tests/EUC-JP/_mozilla_bug426271_text-euc-jp.html | 11 +
tests/EUC-JP/_mozilla_bug431054_text.html | 5 +
tests/EUC-JP/_mozilla_bug620106_text.html | 1045 +++++++++
tests/EUC-JP/_ude_1.txt | 39 +
tests/EUC-JP/aivy.co.jp.xml | 167 ++
tests/EUC-JP/akaname.main.jp.xml | 274 +++
tests/EUC-JP/arclamp.jp.xml | 985 ++++++++
tests/EUC-JP/aristrist.s57.xrea.com.xml | 577 +++++
tests/EUC-JP/artifact-jp.com.xml | 108 +
tests/EUC-JP/atom.ycf.nanet.co.jp.xml | 360 +++
tests/EUC-JP/azito.under.jp.xml | 167 ++
tests/EUC-JP/azoz.org.xml | 198 ++
tests/EUC-JP/blog.kabu-navi.com.atom.xml | 541 +++++
tests/EUC-JP/blog.kabu-navi.com.xml | 539 +++++
tests/EUC-JP/bphrs.net.xml | 263 +++
tests/EUC-JP/ch.kitaguni.tv.xml | 421 ++++
tests/EUC-JP/club.h14m.org.xml | 133 ++
tests/EUC-JP/contents-factory.com.xml | 167 ++
tests/EUC-JP/furusatonoeki.cutegirl.jp.xml | 167 ++
tests/EUC-JP/manana.moo.jp.xml | 167 ++
tests/EUC-JP/mimizun.com.xml | 167 ++
tests/EUC-JP/misuzilla.org.xml | 209 ++
tests/EUC-JP/overcube.com.atom.xml | 1242 ++++++++++
tests/EUC-JP/overcube.com.xml | 77 +
tests/EUC-JP/pinkupa.com.xml | 167 ++
tests/EUC-JP/rdf.ycf.nanet.co.jp.xml | 167 ++
tests/EUC-JP/siesta.co.jp.aozora.xml | 877 +++++++
tests/EUC-JP/tls.org.xml | 259 +++
tests/EUC-JP/yukiboh.moo.jp.xml | 184 ++
...ium_windows-949_with_no_encoding_specified.html | 13 +
tests/EUC-KR/_mozilla_bug9357_text.html | 15 +
tests/EUC-KR/_ude_euc1.txt | 1 +
tests/EUC-KR/_ude_euc2.txt | 7 +
tests/EUC-KR/acnnewswire.net.xml | 6 +
tests/EUC-KR/alogblog.com.xml | 141 ++
tests/EUC-KR/arts.egloos.com.xml | 219 ++
tests/EUC-KR/birder.egloos.com.xml | 301 +++
tests/EUC-KR/blog.bd-lab.com.xml | 147 ++
tests/EUC-KR/blog.empas.com.xml | 45 +
tests/EUC-KR/blog.rss.naver.com.xml | 149 ++
tests/EUC-KR/calmguy.egloos.com.xml | 489 ++++
tests/EUC-KR/chisato.info.xml | 1170 ++++++++++
tests/EUC-KR/console.linuxstudy.pe.kr.xml | 196 ++
tests/EUC-KR/critique.or.kr.xml | 118 +
tests/EUC-KR/epitaph.egloos.com.xml | 262 +++
tests/EUC-KR/ittrend.egloos.com.xml | 287 +++
tests/EUC-KR/jely.egloos.com.xml | 143 ++
tests/EUC-KR/jely.pe.kr.xml | 339 +++
tests/EUC-KR/jowchung.oolim.net.xml | 306 +++
tests/EUC-KR/kina.egloos.com.xml | 206 ++
tests/EUC-KR/lennon81.egloos.com.xml | 125 +
tests/EUC-KR/oroll.egloos.com.xml | 171 ++
tests/EUC-KR/poliplus.egloos.com.xml | 168 ++
tests/EUC-KR/scarletkh2.egloos.com.xml | 238 ++
tests/EUC-KR/siwoo.org.xml | 285 +++
tests/EUC-KR/sparcs.kaist.ac.kr.xml | 136 ++
tests/EUC-KR/tori02.egloos.com.xml | 483 ++++
tests/EUC-KR/willis.egloos.com.xml | 203 ++
tests/EUC-KR/xenix.egloos.com.xml | 379 ++++
tests/EUC-KR/yunho.egloos.com.xml | 203 ++
tests/EUC-KR/zangsalang.egloos.com.xml | 213 ++
tests/EUC-TW/_ude_euc-tw1.txt | 14 +
tests/GB2312/14.blog.westca.com.xml | 180 ++
tests/GB2312/2.blog.westca.com.xml | 320 +++
...ium_gb18030_with_no_encoding_specified.html.xml | 20 +
tests/GB2312/_mozilla_bug171813_text.html | 36 +
tests/GB2312/acnnewswire.net.xml | 6 +
tests/GB2312/bbs.blogsome.com.xml | 205 ++
tests/GB2312/cappuccinos.3322.org.xml | 169 ++
tests/GB2312/chen56.blogcn.com.xml | 30 +
tests/GB2312/cindychen.com.xml | 250 ++
tests/GB2312/cnblog.org.xml | 95 +
tests/GB2312/coverer.com.xml | 95 +
tests/GB2312/eighthday.blogspot.com.xml | 158 ++
tests/GB2312/godthink.blogsome.com.xml | 102 +
tests/GB2312/jjgod.3322.org.xml | 175 ++
tests/GB2312/lily.blogsome.com.xml | 272 +++
tests/GB2312/luciferwang.blogcn.com.xml | 30 +
tests/GB2312/pda.blogsome.com.xml | 112 +
tests/GB2312/softsea.net.xml | 915 ++++++++
tests/GB2312/w3cn.org.xml | 176 ++
tests/GB2312/xy15400.blogcn.com.xml | 30 +
tests/IBM855/_ude_1.txt | 5 +
tests/IBM855/aif.ru.health.xml | 131 ++
tests/IBM855/aug32.hole.ru.xml | 18 +
tests/IBM855/aviaport.ru.xml | 221 ++
tests/IBM855/blog.mlmaster.com.xml | 170 ++
tests/IBM855/forum.template-toolkit.ru.1.xml | 428 ++++
tests/IBM855/forum.template-toolkit.ru.4.xml | 130 ++
tests/IBM855/forum.template-toolkit.ru.6.xml | 486 ++++
tests/IBM855/forum.template-toolkit.ru.8.xml | 228 ++
tests/IBM855/forum.template-toolkit.ru.9.xml | 55 +
tests/IBM855/greek.ru.xml | 59 +
tests/IBM855/intertat.ru.xml | 6 +
tests/IBM855/janulalife.blogspot.com.xml | 165 ++
tests/IBM855/kapranoff.ru.xml | 161 ++
tests/IBM855/money.rin.ru.xml | 112 +
tests/IBM855/music.peeps.ru.xml | 112 +
tests/IBM855/newsru.com.xml | 351 +++
tests/IBM855/susu.ac.ru.xml | 32 +
tests/IBM866/_ude_1.txt | 5 +
tests/IBM866/aif.ru.health.xml | 131 ++
tests/IBM866/aug32.hole.ru.xml | 18 +
tests/IBM866/aviaport.ru.xml | 149 ++
tests/IBM866/blog.mlmaster.com.xml | 170 ++
tests/IBM866/forum.template-toolkit.ru.1.xml | 428 ++++
tests/IBM866/forum.template-toolkit.ru.4.xml | 130 ++
tests/IBM866/forum.template-toolkit.ru.6.xml | 486 ++++
tests/IBM866/forum.template-toolkit.ru.8.xml | 228 ++
tests/IBM866/forum.template-toolkit.ru.9.xml | 55 +
tests/IBM866/greek.ru.xml | 84 +
tests/IBM866/intertat.ru.xml | 6 +
tests/IBM866/janulalife.blogspot.com.xml | 165 ++
tests/IBM866/kapranoff.ru.xml | 161 ++
tests/IBM866/money.rin.ru.xml | 112 +
tests/IBM866/music.peeps.ru.xml | 112 +
tests/IBM866/newsru.com.xml | 351 +++
tests/IBM866/susu.ac.ru.xml | 32 +
...chromium_KOI8-R_with_no_encoding_specified.html | 9 +
tests/KOI8-R/_ude_1.txt | 5 +
tests/KOI8-R/aif.ru.health.xml | 131 ++
tests/KOI8-R/aug32.hole.ru.xml | 20 +
tests/KOI8-R/aviaport.ru.xml | 290 +++
tests/KOI8-R/blog.mlmaster.com.xml | 174 ++
tests/KOI8-R/forum.template-toolkit.ru.1.xml | 428 ++++
tests/KOI8-R/forum.template-toolkit.ru.4.xml | 130 ++
tests/KOI8-R/forum.template-toolkit.ru.6.xml | 486 ++++
tests/KOI8-R/forum.template-toolkit.ru.8.xml | 228 ++
tests/KOI8-R/forum.template-toolkit.ru.9.xml | 55 +
tests/KOI8-R/greek.ru.xml | 85 +
tests/KOI8-R/intertat.ru.xml | 6 +
tests/KOI8-R/janulalife.blogspot.com.xml | 165 ++
tests/KOI8-R/kapranoff.ru.xml | 167 ++
tests/KOI8-R/koi.kinder.ru.xml | 372 +++
tests/KOI8-R/money.rin.ru.xml | 114 +
tests/KOI8-R/music.peeps.ru.xml | 112 +
tests/KOI8-R/newsru.com.xml | 351 +++
tests/KOI8-R/susu.ac.ru.xml | 190 ++
tests/MacCyrillic/_ude_1.txt | 5 +
tests/MacCyrillic/aif.ru.health.xml | 131 ++
tests/MacCyrillic/aug32.hole.ru.xml | 18 +
tests/MacCyrillic/aviaport.ru.xml | 289 +++
tests/MacCyrillic/blog.mlmaster.com.xml | 170 ++
tests/MacCyrillic/forum.template-toolkit.ru.4.xml | 130 ++
tests/MacCyrillic/forum.template-toolkit.ru.6.xml | 486 ++++
tests/MacCyrillic/forum.template-toolkit.ru.8.xml | 228 ++
tests/MacCyrillic/forum.template-toolkit.ru.9.xml | 55 +
tests/MacCyrillic/greek.ru.xml | 45 +
tests/MacCyrillic/intertat.ru.xml | 6 +
tests/MacCyrillic/kapranoff.ru.xml | 161 ++
tests/MacCyrillic/koi.kinder.ru.xml | 68 +
tests/MacCyrillic/money.rin.ru.xml | 112 +
tests/MacCyrillic/music.peeps.ru.xml | 112 +
tests/MacCyrillic/newsru.com.xml | 351 +++
tests/MacCyrillic/susu.ac.ru.xml | 24 +
tests/README.txt | 5 +
tests/SHIFT_JIS/10e.org.xml | 676 ++++++
tests/SHIFT_JIS/1affliate.com.xml | 1493 ++++++++++++
...omium_Shift-JIS_with_no_encoding_specified.html | 11 +
tests/SHIFT_JIS/_ude_1.txt | 1 +
tests/SHIFT_JIS/_ude_2.txt | 39 +
tests/SHIFT_JIS/_ude_3.txt | 39 +
tests/SHIFT_JIS/_ude_4.txt | 946 ++++++++
tests/SHIFT_JIS/accessories-brand.com.xml | 325 +++
tests/SHIFT_JIS/amefoot.net.xml | 1147 ++++++++++
tests/SHIFT_JIS/andore.com.inami.xml | 181 ++
tests/SHIFT_JIS/andore.com.money.xml | 167 ++
tests/SHIFT_JIS/andore.com.xml | 172 ++
tests/SHIFT_JIS/blog.inkase.net.xml | 603 +++++
tests/SHIFT_JIS/blog.paseri.ne.jp.xml | 316 +++
tests/SHIFT_JIS/bloglelife.com.xml | 471 ++++
tests/SHIFT_JIS/brag.zaka.to.xml | 205 ++
tests/SHIFT_JIS/celeb.lalalu.com.xml | 554 +++++
tests/SHIFT_JIS/clickablewords.com.xml | 367 +++
tests/SHIFT_JIS/do.beginnersrack.com.xml | 874 +++++++
tests/SHIFT_JIS/dogsinn.jp.xml | 427 ++++
tests/SHIFT_JIS/grebeweb.net.xml | 444 ++++
tests/SHIFT_JIS/milliontimes.jp.xml | 568 +++++
tests/SHIFT_JIS/moon-light.ne.jp.xml | 152 ++
tests/SHIFT_JIS/nextbeaut.com.xml | 347 +++
tests/SHIFT_JIS/ooganemochi.com.xml | 72 +
tests/SHIFT_JIS/perth-on.net.xml | 60 +
tests/SHIFT_JIS/sakusaka-silk.net.xml | 1111 +++++++++
tests/SHIFT_JIS/setsuzei119.jp.xml | 949 ++++++++
tests/SHIFT_JIS/tamuyou.haun.org.xml | 363 +++
tests/SHIFT_JIS/yasuhisa.com.xml | 89 +
tests/TIS-620/_mozilla_bug488426_text.html | 5 +
tests/TIS-620/opentle.org.xml | 176 ++
tests/TIS-620/pharmacy.kku.ac.th.analyse1.xml | 195 ++
tests/TIS-620/pharmacy.kku.ac.th.centerlab.xml | 207 ++
tests/TIS-620/pharmacy.kku.ac.th.healthinfo-ne.xml | 273 +++
tests/TIS-620/trickspot.boxchart.com.xml | 172 ++
tests/UTF-16/bom-utf-16-be.srt | Bin 0 -> 1714 bytes
tests/UTF-16/bom-utf-16-le.srt | Bin 0 -> 1714 bytes
tests/UTF-32/bom-utf-32-be.srt | Bin 0 -> 3428 bytes
tests/UTF-32/bom-utf-32-le.srt | Bin 0 -> 3428 bytes
tests/__pycache__/__init__.cpython-35.pyc | Bin 0 -> 125 bytes
.../__pycache__/test_chardet.cpython-35-PYTEST.pyc | Bin 0 -> 4295 bytes
...mium_iso-8859-1_with_no_encoding_specified.html | 10 +
tests/ascii/_mozilla_bug638318_text.html | Bin 0 -> 1108 bytes
tests/ascii/howto.diveintomark.org.xml | 77 +
tests/iso-2022-jp/_ude_1.txt | 39 +
tests/iso-2022-kr/_ude_iso1.txt | 1 +
tests/iso-2022-kr/_ude_iso2.txt | 7 +
tests/iso-8859-1/_ude_1.txt | 15 +
tests/iso-8859-1/_ude_2.txt | 21 +
tests/iso-8859-1/_ude_3.txt | 17 +
tests/iso-8859-1/_ude_4.txt | 14 +
tests/iso-8859-1/_ude_5.txt | 21 +
tests/iso-8859-1/_ude_6.txt | 18 +
tests/iso-8859-2-hungarian/auto-apro.hu.xml | 474 ++++
tests/iso-8859-2-hungarian/cigartower.hu.xml | 87 +
tests/iso-8859-2-hungarian/escience.hu.xml | 12 +
tests/iso-8859-2-hungarian/hirtv.hu.xml | 104 +
tests/iso-8859-2-hungarian/honositomuhely.hu.xml | 74 +
tests/iso-8859-2-hungarian/saraspatak.hu.xml | 112 +
tests/iso-8859-2-hungarian/shamalt.uw.hu.mk.xml | 163 ++
tests/iso-8859-2-hungarian/shamalt.uw.hu.mr.xml | 68 +
tests/iso-8859-2-hungarian/shamalt.uw.hu.mv.xml | 163 ++
tests/iso-8859-2-hungarian/shamalt.uw.hu.xml | 113 +
.../iso-8859-2-hungarian/ugyanmar.blogspot.com.xml | 239 ++
tests/iso-8859-5-bulgarian/aero-bg.com.xml | 182 ++
tests/iso-8859-5-bulgarian/bbc.co.uk.popshow.xml | 195 ++
tests/iso-8859-5-bulgarian/bpm.cult.bg.2.xml | 186 ++
tests/iso-8859-5-bulgarian/bpm.cult.bg.4.xml | 89 +
tests/iso-8859-5-bulgarian/bpm.cult.bg.9.xml | 214 ++
.../iso-8859-5-bulgarian/bpm.cult.bg.medusa.4.xml | 89 +
tests/iso-8859-5-bulgarian/bpm.cult.bg.xml | 52 +
.../debian.gabrovo.com.news.xml | 67 +
tests/iso-8859-5-bulgarian/debian.gabrovo.com.xml | 37 +
tests/iso-8859-5-bulgarian/doncho.net.comments.xml | 62 +
tests/iso-8859-5-bulgarian/ecloga.cult.bg.xml | 89 +
tests/iso-8859-5-bulgarian/ide.li.xml | 54 +
tests/iso-8859-5-bulgarian/linux-bg.org.xml | 95 +
...mium_ISO-8859-5_with_no_encoding_specified.html | 9 +
tests/iso-8859-5-cyrillic/aif.ru.health.xml | 131 ++
tests/iso-8859-5-cyrillic/aug32.hole.ru.xml | 18 +
tests/iso-8859-5-cyrillic/aviaport.ru.xml | 221 ++
tests/iso-8859-5-cyrillic/blog.mlmaster.com.xml | 170 ++
.../forum.template-toolkit.ru.1.xml | 428 ++++
.../forum.template-toolkit.ru.4.xml | 130 ++
.../forum.template-toolkit.ru.6.xml | 486 ++++
.../forum.template-toolkit.ru.8.xml | 228 ++
.../forum.template-toolkit.ru.9.xml | 55 +
tests/iso-8859-5-cyrillic/greek.ru.xml | 45 +
tests/iso-8859-5-cyrillic/intertat.ru.xml | 6 +
.../janulalife.blogspot.com.xml | 165 ++
tests/iso-8859-5-cyrillic/kapranoff.ru.xml | 161 ++
tests/iso-8859-5-cyrillic/money.rin.ru.xml | 112 +
tests/iso-8859-5-cyrillic/music.peeps.ru.xml | 112 +
tests/iso-8859-5-cyrillic/newsru.com.xml | 351 +++
tests/iso-8859-5-cyrillic/susu.ac.ru.xml | 24 +
...mium_ISO-8859-6_with_no_encoding_specified.html | 9 +
...mium_ISO-8859-7_with_no_encoding_specified.html | 9 +
tests/iso-8859-7-greek/_ude_greek.txt | 1 +
tests/iso-8859-7-greek/disabled.gr.xml | 181 ++
tests/iso-8859-7-greek/hotstation.gr.xml | 68 +
tests/iso-8859-7-greek/naftemporiki.gr.bus.xml | 122 +
tests/iso-8859-7-greek/naftemporiki.gr.cmm.xml | 113 +
tests/iso-8859-7-greek/naftemporiki.gr.fin.xml | 122 +
tests/iso-8859-7-greek/naftemporiki.gr.mrk.xml | 124 +
tests/iso-8859-7-greek/naftemporiki.gr.mrt.xml | 122 +
tests/iso-8859-7-greek/naftemporiki.gr.spo.xml | 122 +
tests/iso-8859-7-greek/naftemporiki.gr.wld.xml | 122 +
tests/iso-8859-9-turkish/divxplanet.com.xml | 6 +
tests/iso-8859-9-turkish/subtitle.srt | 95 +
tests/iso-8859-9-turkish/wikitop_tr_ISO-8859-9.txt | 33 +
tests/utf-8-sig/_ude_4.txt | 39 +
tests/utf-8-sig/bom-utf-8.srt | 35 +
..._chromium_UTF-8_with_no_encoding_specified.html | 9 +
tests/utf-8/_mozilla_bug306272_text.html | 9 +
tests/utf-8/_mozilla_bug426271_text-utf-8.html | 11 +
tests/utf-8/_ude_1.txt | 1 +
tests/utf-8/_ude_2.txt | 7 +
tests/utf-8/_ude_3.txt | 1 +
tests/utf-8/_ude_5.txt | 5 +
tests/utf-8/_ude_greek.txt | 1 +
tests/utf-8/_ude_he1.txt | 3 +
tests/utf-8/_ude_he2.txt | 5 +
tests/utf-8/_ude_he3.txt | 1 +
tests/utf-8/_ude_russian.txt | 5 +
tests/utf-8/anitabee.blogspot.com.xml | 415 ++++
tests/utf-8/balatonblog.typepad.com.xml | 387 ++++
tests/utf-8/boobooo.blogspot.com.xml | 196 ++
tests/utf-8/linuxbox.hu.xml | 188 ++
tests/utf-8/pihgy.hu.xml | 156 ++
tests/utf-8/weblabor.hu.2.xml | 121 +
tests/utf-8/weblabor.hu.xml | 172 ++
.../windows-1250-hungarian/bbc.co.uk.hu.forum.xml | 330 +++
.../bbc.co.uk.hu.learningenglish.xml | 280 +++
.../bbc.co.uk.hu.pressreview.xml | 265 +++
tests/windows-1250-hungarian/bbc.co.uk.hu.xml | 710 ++++++
tests/windows-1250-hungarian/objektivhir.hu.xml | 183 ++
.../torokorszag.blogspot.com.xml | 2202 ++++++++++++++++++
tests/windows-1251-bulgarian/bbc.co.uk.popshow.xml | 389 ++++
tests/windows-1251-bulgarian/bpm.cult.bg.2.xml | 193 ++
tests/windows-1251-bulgarian/bpm.cult.bg.3.xml | 174 ++
tests/windows-1251-bulgarian/bpm.cult.bg.4.xml | 183 ++
tests/windows-1251-bulgarian/bpm.cult.bg.9.xml | 214 ++
.../bpm.cult.bg.medusa.4.xml | 183 ++
tests/windows-1251-bulgarian/bpm.cult.bg.xml | 128 ++
.../debian.gabrovo.com.news.xml | 69 +
.../windows-1251-bulgarian/debian.gabrovo.com.xml | 39 +
.../windows-1251-bulgarian/doncho.net.comments.xml | 127 ++
tests/windows-1251-bulgarian/doncho.net.xml | 199 ++
tests/windows-1251-bulgarian/ecloga.cult.bg.xml | 89 +
tests/windows-1251-bulgarian/ide.li.xml | 80 +
tests/windows-1251-bulgarian/informator.org.xml | 68 +
tests/windows-1251-bulgarian/linux-bg.org.xml | 97 +
tests/windows-1251-bulgarian/rinennor.org.xml | 98 +
...um_windows-1251_with_no_encoding_specified.html | 9 +
tests/windows-1251-cyrillic/_ude_1.txt | 5 +
tests/windows-1251-cyrillic/aif.ru.health.xml | 131 ++
tests/windows-1251-cyrillic/anthropology.ru.xml | 176 ++
tests/windows-1251-cyrillic/aug32.hole.ru.xml | 18 +
tests/windows-1251-cyrillic/aviaport.ru.xml | 289 +++
tests/windows-1251-cyrillic/blog.mlmaster.com.xml | 170 ++
.../forum.template-toolkit.ru.1.xml | 428 ++++
.../forum.template-toolkit.ru.4.xml | 130 ++
.../forum.template-toolkit.ru.6.xml | 486 ++++
.../forum.template-toolkit.ru.8.xml | 228 ++
.../forum.template-toolkit.ru.9.xml | 55 +
tests/windows-1251-cyrillic/greek.ru.xml | 45 +
tests/windows-1251-cyrillic/intertat.ru.xml | 6 +
.../janulalife.blogspot.com.xml | 165 ++
tests/windows-1251-cyrillic/kapranoff.ru.xml | 161 ++
tests/windows-1251-cyrillic/money.rin.ru.xml | 112 +
tests/windows-1251-cyrillic/music.peeps.ru.xml | 112 +
tests/windows-1251-cyrillic/newsru.com.xml | 351 +++
tests/windows-1252/_mozilla_bug421271_text.html | 5 +
tests/windows-1252/github_bug_9.txt | 4 +
...um_windows-1254_with_no_encoding_specified.html | 9 +
...mium_ISO-8859-8_with_no_encoding_specified.html | 9 +
...um_windows-1255_with_no_encoding_specified.html | 9 +
tests/windows-1255-hebrew/_ude_he1.txt | 3 +
tests/windows-1255-hebrew/_ude_he2.txt | 5 +
tests/windows-1255-hebrew/_ude_he3.txt | 1 +
tests/windows-1255-hebrew/carshops.co.il.xml | 2385 ++++++++++++++++++++
tests/windows-1255-hebrew/exego.net.2.xml | 49 +
tests/windows-1255-hebrew/hagada.org.il.xml | 108 +
tests/windows-1255-hebrew/halemo.net.edoar.xml | 338 +++
tests/windows-1255-hebrew/hevra.org.il.xml | 68 +
.../hydepark.hevre.co.il.7957.xml | 9 +
tests/windows-1255-hebrew/info.org.il.xml | 179 ++
tests/windows-1255-hebrew/infomed.co.il.xml | 194 ++
tests/windows-1255-hebrew/law.co.il.xml | 100 +
tests/windows-1255-hebrew/maakav.org.xml | 68 +
tests/windows-1255-hebrew/neviim.net.xml | 126 ++
tests/windows-1255-hebrew/notes.co.il.50.xml | 35 +
tests/windows-1255-hebrew/notes.co.il.6.xml | 10 +
tests/windows-1255-hebrew/notes.co.il.7.xml | 46 +
tests/windows-1255-hebrew/notes.co.il.8.xml | 55 +
tests/windows-1255-hebrew/pcplus.co.il.xml | 118 +
tests/windows-1255-hebrew/sharks.co.il.xml | 100 +
tests/windows-1255-hebrew/whatsup.org.il.xml | 146 ++
...um_windows-1256_with_no_encoding_specified.html | 9 +
450 files changed, 81376 insertions(+), 2907 deletions(-)
diff --git a/MANIFEST.in b/MANIFEST.in
index 30f762c..60e3964 100644
--- a/MANIFEST.in
+++ b/MANIFEST.in
@@ -1,4 +1,6 @@
-include README.rst
-include COPYING
include LICENSE
-recursive-include docs *.html *.css *.png *.gif
+include *.rst
+include requirements.txt
+include test.py
+recursive-include docs *
+recursive-include tests *
diff --git a/NOTES.rst b/NOTES.rst
new file mode 100644
index 0000000..ea05225
--- /dev/null
+++ b/NOTES.rst
@@ -0,0 +1,140 @@
+Class Hierarchy for chardet
+===========================
+
+Universal Detector
+------------------
+Has a list of probers.
+
+CharSetProber
+-------------
+Mostly abstract parent class.
+
+CharSetGroupProber
+------------------
+Runs a bunch of related probers at the same time and decides which is best.
+
+SBCSGroupProber
+---------------
+SBCS = Single-ByteCharSet. Runs a bunch of SingleByteCharSetProbers. Always
+contains the same SingleByteCharSetProbers.
+
+SingleByteCharSetProber
+-----------------------
+A CharSetProber that is used for detecting single-byte encodings by using
+a "precedence matrix" (i.e., a character bigram model).
+
+MBCSGroupProber
+---------------
+Runs a bunch of MultiByteCharSetProbers. It also uses a UTF8Prober, which is
+essentially a MultiByteCharSetProber that only has a state machine. Always
+contains the same MultiByteCharSetProbers.
+
+MultiByteCharSetProber
+----------------------
+A CharSetProber that uses both a character unigram model (or "character
+distribution analysis") and an independent state machine for trying to
+detect and encoding.
+
+CodingStateMachine
+------------------
+Used for "coding scheme" detection, where we just look for either invalid
+byte sequences or sequences that only occur for that particular encoding.
+
+CharDistributionAnalysis
+------------------------
+Used for character unigram distribution encoding detection. Takes a mapping
+from characters to a "frequency order" (i.e., what frequency rank that byte has
+in the given encoding) and a "typical distribution ratio", which is the number
+of occurrences of the 512 most frequently used characters divided by the number
+of occurrences of the rest of the characters for a typical document.
+The "characters" in this case are 2-byte sequences and they are first converted
+to an "order" (name comes from ord() function, I believe). This "order" is used
+to index into the frequency order table to determine the frequency rank of that
+byte sequence. The reason this extra step is necessary is that the frequency
+rank table is language-specific (and not encoding-specific).
+
+
+What's where
+============
+
+
+Bigram files
+------------
+
+- ``hebrewprober.py``
+- ``jpcntxprober.py``
+- ``langbulgarianmodel.py``
+- ``langcyrillicmodel.py``
+- ``langgreekmodel.py``
+- ``langhebrewmodel.py``
+- ``langhungarianmodel.py``
+- ``langthaimodel.py``
+- ``latin1prober.py``
+- ``sbcharsetprober.py``
+- ``sbcsgroupprober.py``
+
+
+Coding Scheme files
+-------------------
+
+- ``escprober.py``
+- ``escsm.py``
+- ``utf8prober.py``
+- ``codingstatemachine.py``
+- ``mbcssmprober.py``
+
+
+Unigram files
+-------------
+
+- ``big5freqprober.py``
+- ``chardistribution.py``
+- ``euckrfreqprober.py``
+- ``euctwfreqprober.py``
+- ``gb2312freqprober.py``
+- ``jisfreqprober.py``
+
+Multibyte probers
+-----------------
+
+- ``big5prober.py``
+- ``cp949prober.py``
+- ``eucjpprober.py``
+- ``euckrprober.py``
+- ``euctwprober.py``
+- ``gb2312prober.py``
+- ``mbcharsetprober.py``
+- ``mbcsgroupprober.py``
+- ``sjisprober.py``
+
+Misc files
+----------
+
+- ``__init__.py`` (currently has ``detect`` function in it)
+- ``compat.py``
+- ``enums.py``
+- ``universaldetector.py``
+- ``version.py``
+
+
+Useful links
+============
+
+This is just a collection of information that I've found useful or thought
+might be useful in the future:
+
+- `BOM by Encoding`_
+
+- `A Composite Approach to Language/Encoding Detection`_
+
+- `What Every Programmer Absolutely...`_
+
+- The actual `source`_
+
+
+.. _BOM by Encoding:
+ https://en.wikipedia.org/wiki/Byte_order_mark#Representations_of_byte_order_marks_by_encoding
+.. _A Composite Approach to Language/Encoding Detection:
+ http://www-archive.mozilla.org/projects/intl/UniversalCharsetDetection.html
+.. _What Every Programmer Absolutely...: http://kunststube.net/encoding/
+.. _source: https://mxr.mozilla.org/mozilla/source/intl/chardet/
diff --git a/PKG-INFO b/PKG-INFO
index 8ffe8f6..57aa091 100644
--- a/PKG-INFO
+++ b/PKG-INFO
@@ -1,28 +1,46 @@
Metadata-Version: 1.1
Name: chardet
-Version: 2.3.0
+Version: 3.0.4
Summary: Universal encoding detector for Python 2 and 3
Home-page: https://github.com/chardet/chardet
-Author: Ian Cordasco
-Author-email: graffatcolmingov at gmail.com
+Author: Daniel Blanchard
+Author-email: dan.blanchard at gmail.com
License: LGPL
Description: Chardet: The Universal Character Encoding Detector
--------------------------------------------------
+ .. image:: https://img.shields.io/travis/chardet/chardet/stable.svg
+ :alt: Build status
+ :target: https://travis-ci.org/chardet/chardet
+
+ .. image:: https://img.shields.io/coveralls/chardet/chardet/stable.svg
+ :target: https://coveralls.io/r/chardet/chardet
+
+ .. image:: https://img.shields.io/pypi/v/chardet.svg
+ :target: https://warehouse.python.org/project/chardet/
+ :alt: Latest version on PyPI
+
+ .. image:: https://img.shields.io/pypi/l/chardet.svg
+ :alt: License
+
+
Detects
- ASCII, UTF-8, UTF-16 (2 variants), UTF-32 (4 variants)
- Big5, GB2312, EUC-TW, HZ-GB-2312, ISO-2022-CN (Traditional and Simplified Chinese)
- EUC-JP, SHIFT_JIS, CP932, ISO-2022-JP (Japanese)
- EUC-KR, ISO-2022-KR (Korean)
- KOI8-R, MacCyrillic, IBM855, IBM866, ISO-8859-5, windows-1251 (Cyrillic)
- - ISO-8859-2, windows-1250 (Hungarian)
- ISO-8859-5, windows-1251 (Bulgarian)
- - windows-1252 (English)
+ - ISO-8859-1, windows-1252 (Western European languages)
- ISO-8859-7, windows-1253 (Greek)
- ISO-8859-8, windows-1255 (Visual and Logical Hebrew)
- TIS-620 (Thai)
- Requires Python 2.6 or later
+ .. note::
+ Our ISO-8859-2 and windows-1250 (Hungarian) probers have been temporarily
+ disabled until we can retrain the models.
+
+ Requires Python 2.6, 2.7, or 3.3+.
Installation
------------
@@ -31,6 +49,10 @@ Description: Chardet: The Universal Character Encoding Detector
pip install chardet
+ Documentation
+ -------------
+
+ For users, docs are now available at https://chardet.readthedocs.io/.
Command-line Tool
-----------------
@@ -64,7 +86,9 @@ Classifier: Programming Language :: Python :: 2
Classifier: Programming Language :: Python :: 2.6
Classifier: Programming Language :: Python :: 2.7
Classifier: Programming Language :: Python :: 3
-Classifier: Programming Language :: Python :: 3.2
Classifier: Programming Language :: Python :: 3.3
+Classifier: Programming Language :: Python :: 3.4
+Classifier: Programming Language :: Python :: 3.5
+Classifier: Programming Language :: Python :: 3.6
Classifier: Topic :: Software Development :: Libraries :: Python Modules
Classifier: Topic :: Text Processing :: Linguistic
diff --git a/README.rst b/README.rst
index 7df8f56..ebff9d9 100644
--- a/README.rst
+++ b/README.rst
@@ -1,20 +1,38 @@
Chardet: The Universal Character Encoding Detector
--------------------------------------------------
+.. image:: https://img.shields.io/travis/chardet/chardet/stable.svg
+ :alt: Build status
+ :target: https://travis-ci.org/chardet/chardet
+
+.. image:: https://img.shields.io/coveralls/chardet/chardet/stable.svg
+ :target: https://coveralls.io/r/chardet/chardet
+
+.. image:: https://img.shields.io/pypi/v/chardet.svg
+ :target: https://warehouse.python.org/project/chardet/
+ :alt: Latest version on PyPI
+
+.. image:: https://img.shields.io/pypi/l/chardet.svg
+ :alt: License
+
+
Detects
- ASCII, UTF-8, UTF-16 (2 variants), UTF-32 (4 variants)
- Big5, GB2312, EUC-TW, HZ-GB-2312, ISO-2022-CN (Traditional and Simplified Chinese)
- EUC-JP, SHIFT_JIS, CP932, ISO-2022-JP (Japanese)
- EUC-KR, ISO-2022-KR (Korean)
- KOI8-R, MacCyrillic, IBM855, IBM866, ISO-8859-5, windows-1251 (Cyrillic)
- - ISO-8859-2, windows-1250 (Hungarian)
- ISO-8859-5, windows-1251 (Bulgarian)
- - windows-1252 (English)
+ - ISO-8859-1, windows-1252 (Western European languages)
- ISO-8859-7, windows-1253 (Greek)
- ISO-8859-8, windows-1255 (Visual and Logical Hebrew)
- TIS-620 (Thai)
-Requires Python 2.6 or later
+.. note::
+ Our ISO-8859-2 and windows-1250 (Hungarian) probers have been temporarily
+ disabled until we can retrain the models.
+
+Requires Python 2.6, 2.7, or 3.3+.
Installation
------------
@@ -23,6 +41,10 @@ Install from `PyPI <https://pypi.python.org/pypi/chardet>`_::
pip install chardet
+Documentation
+-------------
+
+For users, docs are now available at https://chardet.readthedocs.io/.
Command-line Tool
-----------------
diff --git a/chardet.egg-info/PKG-INFO b/chardet.egg-info/PKG-INFO
index 8ffe8f6..57aa091 100644
--- a/chardet.egg-info/PKG-INFO
+++ b/chardet.egg-info/PKG-INFO
@@ -1,28 +1,46 @@
Metadata-Version: 1.1
Name: chardet
-Version: 2.3.0
+Version: 3.0.4
Summary: Universal encoding detector for Python 2 and 3
Home-page: https://github.com/chardet/chardet
-Author: Ian Cordasco
-Author-email: graffatcolmingov at gmail.com
+Author: Daniel Blanchard
+Author-email: dan.blanchard at gmail.com
License: LGPL
Description: Chardet: The Universal Character Encoding Detector
--------------------------------------------------
+ .. image:: https://img.shields.io/travis/chardet/chardet/stable.svg
+ :alt: Build status
+ :target: https://travis-ci.org/chardet/chardet
+
+ .. image:: https://img.shields.io/coveralls/chardet/chardet/stable.svg
+ :target: https://coveralls.io/r/chardet/chardet
+
+ .. image:: https://img.shields.io/pypi/v/chardet.svg
+ :target: https://warehouse.python.org/project/chardet/
+ :alt: Latest version on PyPI
+
+ .. image:: https://img.shields.io/pypi/l/chardet.svg
+ :alt: License
+
+
Detects
- ASCII, UTF-8, UTF-16 (2 variants), UTF-32 (4 variants)
- Big5, GB2312, EUC-TW, HZ-GB-2312, ISO-2022-CN (Traditional and Simplified Chinese)
- EUC-JP, SHIFT_JIS, CP932, ISO-2022-JP (Japanese)
- EUC-KR, ISO-2022-KR (Korean)
- KOI8-R, MacCyrillic, IBM855, IBM866, ISO-8859-5, windows-1251 (Cyrillic)
- - ISO-8859-2, windows-1250 (Hungarian)
- ISO-8859-5, windows-1251 (Bulgarian)
- - windows-1252 (English)
+ - ISO-8859-1, windows-1252 (Western European languages)
- ISO-8859-7, windows-1253 (Greek)
- ISO-8859-8, windows-1255 (Visual and Logical Hebrew)
- TIS-620 (Thai)
- Requires Python 2.6 or later
+ .. note::
+ Our ISO-8859-2 and windows-1250 (Hungarian) probers have been temporarily
+ disabled until we can retrain the models.
+
+ Requires Python 2.6, 2.7, or 3.3+.
Installation
------------
@@ -31,6 +49,10 @@ Description: Chardet: The Universal Character Encoding Detector
pip install chardet
+ Documentation
+ -------------
+
+ For users, docs are now available at https://chardet.readthedocs.io/.
Command-line Tool
-----------------
@@ -64,7 +86,9 @@ Classifier: Programming Language :: Python :: 2
Classifier: Programming Language :: Python :: 2.6
Classifier: Programming Language :: Python :: 2.7
Classifier: Programming Language :: Python :: 3
-Classifier: Programming Language :: Python :: 3.2
Classifier: Programming Language :: Python :: 3.3
+Classifier: Programming Language :: Python :: 3.4
+Classifier: Programming Language :: Python :: 3.5
+Classifier: Programming Language :: Python :: 3.6
Classifier: Topic :: Software Development :: Libraries :: Python Modules
Classifier: Topic :: Text Processing :: Linguistic
diff --git a/chardet.egg-info/SOURCES.txt b/chardet.egg-info/SOURCES.txt
index b78feb4..e88a215 100644
--- a/chardet.egg-info/SOURCES.txt
+++ b/chardet.egg-info/SOURCES.txt
@@ -1,19 +1,20 @@
LICENSE
MANIFEST.in
+NOTES.rst
README.rst
setup.cfg
setup.py
+test.py
chardet/__init__.py
chardet/big5freq.py
chardet/big5prober.py
-chardet/chardetect.py
chardet/chardistribution.py
chardet/charsetgroupprober.py
chardet/charsetprober.py
chardet/codingstatemachine.py
chardet/compat.py
-chardet/constants.py
chardet/cp949prober.py
+chardet/enums.py
chardet/escprober.py
chardet/escsm.py
chardet/eucjpprober.py
@@ -32,6 +33,7 @@ chardet/langgreekmodel.py
chardet/langhebrewmodel.py
chardet/langhungarianmodel.py
chardet/langthaimodel.py
+chardet/langturkishmodel.py
chardet/latin1prober.py
chardet/mbcharsetprober.py
chardet/mbcsgroupprober.py
@@ -41,8 +43,409 @@ chardet/sbcsgroupprober.py
chardet/sjisprober.py
chardet/universaldetector.py
chardet/utf8prober.py
+chardet/version.py
chardet.egg-info/PKG-INFO
chardet.egg-info/SOURCES.txt
chardet.egg-info/dependency_links.txt
chardet.egg-info/entry_points.txt
-chardet.egg-info/top_level.txt
\ No newline at end of file
+chardet.egg-info/top_level.txt
+chardet/cli/__init__.py
+chardet/cli/chardetect.py
+docs/.gitignore
+docs/Makefile
+docs/README.md
+docs/conf.py
+docs/faq.rst
+docs/how-it-works.rst
+docs/index.rst
+docs/make.bat
+docs/supported-encodings.rst
+docs/usage.rst
+docs/api/chardet.rst
+docs/api/modules.rst
+tests/README.txt
+tests/Big5/0804.blogspot.com.xml
+tests/Big5/_chromium_Big5_with_no_encoding_specified.html
+tests/Big5/_ude_1.txt
+tests/Big5/blog.worren.net.xml
+tests/Big5/carbonxiv.blogspot.com.xml
+tests/Big5/catshadow.blogspot.com.xml
+tests/Big5/coolloud.org.tw.xml
+tests/Big5/digitalwall.com.xml
+tests/Big5/ebao.us.xml
+tests/Big5/fudesign.blogspot.com.xml
+tests/Big5/kafkatseng.blogspot.com.xml
+tests/Big5/ke207.blogspot.com.xml
+tests/Big5/leavesth.blogspot.com.xml
+tests/Big5/letterlego.blogspot.com.xml
+tests/Big5/linyijen.blogspot.com.xml
+tests/Big5/marilynwu.blogspot.com.xml
+tests/Big5/myblog.pchome.com.tw.xml
+tests/Big5/oui-design.com.xml
+tests/Big5/sanwenji.blogspot.com.xml
+tests/Big5/sinica.edu.tw.xml
+tests/Big5/sylvia1976.blogspot.com.xml
+tests/Big5/tlkkuo.blogspot.com.xml
+tests/Big5/unoriginalblog.com.xml
+tests/Big5/upsaid.com.xml
+tests/Big5/willythecop.blogspot.com.xml
+tests/Big5/ytc.blogspot.com.xml
+tests/CP932/hardsoft.at.webry.info.xml
+tests/CP932/www2.chuo-u.ac.jp-suishin.xml
+tests/CP932/y-moto.com.xml
+tests/CP949/ricanet.com.xml
+tests/EUC-JP/_mozilla_bug426271_text-euc-jp.html
+tests/EUC-JP/_mozilla_bug431054_text.html
+tests/EUC-JP/_mozilla_bug620106_text.html
+tests/EUC-JP/_ude_1.txt
+tests/EUC-JP/aivy.co.jp.xml
+tests/EUC-JP/akaname.main.jp.xml
+tests/EUC-JP/arclamp.jp.xml
+tests/EUC-JP/aristrist.s57.xrea.com.xml
+tests/EUC-JP/artifact-jp.com.xml
+tests/EUC-JP/atom.ycf.nanet.co.jp.xml
+tests/EUC-JP/azito.under.jp.xml
+tests/EUC-JP/azoz.org.xml
+tests/EUC-JP/blog.kabu-navi.com.atom.xml
+tests/EUC-JP/blog.kabu-navi.com.xml
+tests/EUC-JP/bphrs.net.xml
+tests/EUC-JP/ch.kitaguni.tv.xml
+tests/EUC-JP/club.h14m.org.xml
+tests/EUC-JP/contents-factory.com.xml
+tests/EUC-JP/furusatonoeki.cutegirl.jp.xml
+tests/EUC-JP/manana.moo.jp.xml
+tests/EUC-JP/mimizun.com.xml
+tests/EUC-JP/misuzilla.org.xml
+tests/EUC-JP/overcube.com.atom.xml
+tests/EUC-JP/overcube.com.xml
+tests/EUC-JP/pinkupa.com.xml
+tests/EUC-JP/rdf.ycf.nanet.co.jp.xml
+tests/EUC-JP/siesta.co.jp.aozora.xml
+tests/EUC-JP/tls.org.xml
+tests/EUC-JP/yukiboh.moo.jp.xml
+tests/EUC-KR/_chromium_windows-949_with_no_encoding_specified.html
+tests/EUC-KR/_mozilla_bug9357_text.html
+tests/EUC-KR/_ude_euc1.txt
+tests/EUC-KR/_ude_euc2.txt
+tests/EUC-KR/acnnewswire.net.xml
+tests/EUC-KR/alogblog.com.xml
+tests/EUC-KR/arts.egloos.com.xml
+tests/EUC-KR/birder.egloos.com.xml
+tests/EUC-KR/blog.bd-lab.com.xml
+tests/EUC-KR/blog.empas.com.xml
+tests/EUC-KR/blog.rss.naver.com.xml
+tests/EUC-KR/calmguy.egloos.com.xml
+tests/EUC-KR/chisato.info.xml
+tests/EUC-KR/console.linuxstudy.pe.kr.xml
+tests/EUC-KR/critique.or.kr.xml
+tests/EUC-KR/epitaph.egloos.com.xml
+tests/EUC-KR/ittrend.egloos.com.xml
+tests/EUC-KR/jely.egloos.com.xml
+tests/EUC-KR/jely.pe.kr.xml
+tests/EUC-KR/jowchung.oolim.net.xml
+tests/EUC-KR/kina.egloos.com.xml
+tests/EUC-KR/lennon81.egloos.com.xml
+tests/EUC-KR/oroll.egloos.com.xml
+tests/EUC-KR/poliplus.egloos.com.xml
+tests/EUC-KR/scarletkh2.egloos.com.xml
+tests/EUC-KR/siwoo.org.xml
+tests/EUC-KR/sparcs.kaist.ac.kr.xml
+tests/EUC-KR/tori02.egloos.com.xml
+tests/EUC-KR/willis.egloos.com.xml
+tests/EUC-KR/xenix.egloos.com.xml
+tests/EUC-KR/yunho.egloos.com.xml
+tests/EUC-KR/zangsalang.egloos.com.xml
+tests/EUC-TW/_ude_euc-tw1.txt
+tests/GB2312/14.blog.westca.com.xml
+tests/GB2312/2.blog.westca.com.xml
+tests/GB2312/_chromium_gb18030_with_no_encoding_specified.html.xml
+tests/GB2312/_mozilla_bug171813_text.html
+tests/GB2312/acnnewswire.net.xml
+tests/GB2312/bbs.blogsome.com.xml
+tests/GB2312/cappuccinos.3322.org.xml
+tests/GB2312/chen56.blogcn.com.xml
+tests/GB2312/cindychen.com.xml
+tests/GB2312/cnblog.org.xml
+tests/GB2312/coverer.com.xml
+tests/GB2312/eighthday.blogspot.com.xml
+tests/GB2312/godthink.blogsome.com.xml
... 89635 lines suppressed ...
--
Alioth's /usr/local/bin/git-commit-notice on /srv/git.debian.org/git/python-modules/packages/chardet.git
More information about the Python-modules-commits
mailing list