From 771dd885f7158b8d2492dcd0aa65b42f169dc600 Mon Sep 17 00:00:00 2001 From: Pairi Daiza Date: Fri, 27 Nov 2020 09:42:04 +0100 Subject: [PATCH 1/3] +Add Chinese test files of issue #2981 in library "test/test_files/encoding/Txtfiles" --- test/test_files/encoding/Txtfiles/GB2312-80 (issue #2981).txt | 1 + test/test_files/encoding/Txtfiles/HZ-GB2312 (issue #2981).txt | 1 + .../UTF-8}/Complex-script-samples (issue #2019).txt | 0 test/test_files/{others => encoding/UTF-8}/jquery_long_line.txt | 0 test/test_files/{others => encoding/UTF-8}/strange.txt | 0 5 files changed, 2 insertions(+) create mode 100644 test/test_files/encoding/Txtfiles/GB2312-80 (issue #2981).txt create mode 100644 test/test_files/encoding/Txtfiles/HZ-GB2312 (issue #2981).txt rename test/test_files/{others => encoding/UTF-8}/Complex-script-samples (issue #2019).txt (100%) rename test/test_files/{others => encoding/UTF-8}/jquery_long_line.txt (100%) rename test/test_files/{others => encoding/UTF-8}/strange.txt (100%) diff --git a/test/test_files/encoding/Txtfiles/GB2312-80 (issue #2981).txt b/test/test_files/encoding/Txtfiles/GB2312-80 (issue #2981).txt new file mode 100644 index 000000000..4830c4eee --- /dev/null +++ b/test/test_files/encoding/Txtfiles/GB2312-80 (issue #2981).txt @@ -0,0 +1 @@ +您好A \ No newline at end of file diff --git a/test/test_files/encoding/Txtfiles/HZ-GB2312 (issue #2981).txt b/test/test_files/encoding/Txtfiles/HZ-GB2312 (issue #2981).txt new file mode 100644 index 000000000..b27511b40 --- /dev/null +++ b/test/test_files/encoding/Txtfiles/HZ-GB2312 (issue #2981).txt @@ -0,0 +1 @@ +~{Dz:C~}A \ No newline at end of file diff --git a/test/test_files/others/Complex-script-samples (issue #2019).txt b/test/test_files/encoding/UTF-8/Complex-script-samples (issue #2019).txt similarity index 100% rename from test/test_files/others/Complex-script-samples (issue #2019).txt rename to test/test_files/encoding/UTF-8/Complex-script-samples (issue #2019).txt diff --git a/test/test_files/others/jquery_long_line.txt b/test/test_files/encoding/UTF-8/jquery_long_line.txt similarity index 100% rename from test/test_files/others/jquery_long_line.txt rename to test/test_files/encoding/UTF-8/jquery_long_line.txt diff --git a/test/test_files/others/strange.txt b/test/test_files/encoding/UTF-8/strange.txt similarity index 100% rename from test/test_files/others/strange.txt rename to test/test_files/encoding/UTF-8/strange.txt From ced66694de5ec1d30644a97aa4cffe2a5f4a7fe1 Mon Sep 17 00:00:00 2001 From: Pairi Daiza Date: Fri, 27 Nov 2020 12:04:04 +0100 Subject: [PATCH 2/3] +chg: Add more characters to accurately identify the encoding --- .../encoding/Txtfiles/GB2312-80 (issue #2981).txt | 6 +++++- .../encoding/Txtfiles/HZ-GB2312 (issue #2981).txt | 6 +++++- 2 files changed, 10 insertions(+), 2 deletions(-) diff --git a/test/test_files/encoding/Txtfiles/GB2312-80 (issue #2981).txt b/test/test_files/encoding/Txtfiles/GB2312-80 (issue #2981).txt index 4830c4eee..1fffed294 100644 --- a/test/test_files/encoding/Txtfiles/GB2312-80 (issue #2981).txt +++ b/test/test_files/encoding/Txtfiles/GB2312-80 (issue #2981).txt @@ -1 +1,5 @@ -您好A \ No newline at end of file +您好A 您好A 您好A 您好A 您好A 您好A 您好A 您好A 您好A 您好A 您好A 您好A 您好A 您好A 您好A +您好A 您好A 您好A 您好A 您好A 您好A 您好A 您好A 您好A 您好A 您好A 您好A 您好A 您好A 您好A +您好A 您好A 您好A 您好A 您好A 您好A 您好A 您好A 您好A 您好A 您好A 您好A 您好A 您好A 您好A +您好A 您好A 您好A 您好A 您好A 您好A 您好A 您好A 您好A 您好A 您好A 您好A 您好A 您好A 您好A +您好A 您好A 您好A 您好A 您好A 您好A 您好A 您好A 您好A 您好A 您好A 您好A 您好A 您好A 您好A diff --git a/test/test_files/encoding/Txtfiles/HZ-GB2312 (issue #2981).txt b/test/test_files/encoding/Txtfiles/HZ-GB2312 (issue #2981).txt index b27511b40..6572422a5 100644 --- a/test/test_files/encoding/Txtfiles/HZ-GB2312 (issue #2981).txt +++ b/test/test_files/encoding/Txtfiles/HZ-GB2312 (issue #2981).txt @@ -1 +1,5 @@ -~{Dz:C~}A \ No newline at end of file +~{Dz:C~}A ~{Dz:C~}A ~{Dz:C~}A ~{Dz:C~}A ~{Dz:C~}A ~{Dz:C~}A ~{Dz:C~}A ~{Dz:C~}A ~{Dz:C~}A ~{Dz:C~}A ~{Dz:C~}A ~{Dz:C~}A ~{Dz:C~}A ~{Dz:C~}A ~{Dz:C~}A +~{Dz:C~}A ~{Dz:C~}A ~{Dz:C~}A ~{Dz:C~}A ~{Dz:C~}A ~{Dz:C~}A ~{Dz:C~}A ~{Dz:C~}A ~{Dz:C~}A ~{Dz:C~}A ~{Dz:C~}A ~{Dz:C~}A ~{Dz:C~}A ~{Dz:C~}A ~{Dz:C~}A +~{Dz:C~}A ~{Dz:C~}A ~{Dz:C~}A ~{Dz:C~}A ~{Dz:C~}A ~{Dz:C~}A ~{Dz:C~}A ~{Dz:C~}A ~{Dz:C~}A ~{Dz:C~}A ~{Dz:C~}A ~{Dz:C~}A ~{Dz:C~}A ~{Dz:C~}A ~{Dz:C~}A +~{Dz:C~}A ~{Dz:C~}A ~{Dz:C~}A ~{Dz:C~}A ~{Dz:C~}A ~{Dz:C~}A ~{Dz:C~}A ~{Dz:C~}A ~{Dz:C~}A ~{Dz:C~}A ~{Dz:C~}A ~{Dz:C~}A ~{Dz:C~}A ~{Dz:C~}A ~{Dz:C~}A +~{Dz:C~}A ~{Dz:C~}A ~{Dz:C~}A ~{Dz:C~}A ~{Dz:C~}A ~{Dz:C~}A ~{Dz:C~}A ~{Dz:C~}A ~{Dz:C~}A ~{Dz:C~}A ~{Dz:C~}A ~{Dz:C~}A ~{Dz:C~}A ~{Dz:C~}A ~{Dz:C~}A From c03c7290642b1bd3796b5cf20d4ac8744ec84a34 Mon Sep 17 00:00:00 2001 From: Pairi Daiza Date: Fri, 27 Nov 2020 13:58:44 +0100 Subject: [PATCH 3/3] +chg: Add new Chinese files with more characters --- .../encoding/Txtfiles/GB2312-80 (issue #2981).txt | 5 ----- .../encoding/Txtfiles/GB2312-80-new (issue #2981).txt | 7 +++++++ .../encoding/Txtfiles/HZ-GB2312 (issue #2981).txt | 5 ----- .../encoding/Txtfiles/HZ-GB2312-new (issue #2981).txt | 7 +++++++ .../encoding/UTF-8/Unicode UTF-8-new (issue #2981).txt | 7 +++++++ 5 files changed, 21 insertions(+), 10 deletions(-) delete mode 100644 test/test_files/encoding/Txtfiles/GB2312-80 (issue #2981).txt create mode 100644 test/test_files/encoding/Txtfiles/GB2312-80-new (issue #2981).txt delete mode 100644 test/test_files/encoding/Txtfiles/HZ-GB2312 (issue #2981).txt create mode 100644 test/test_files/encoding/Txtfiles/HZ-GB2312-new (issue #2981).txt create mode 100644 test/test_files/encoding/UTF-8/Unicode UTF-8-new (issue #2981).txt diff --git a/test/test_files/encoding/Txtfiles/GB2312-80 (issue #2981).txt b/test/test_files/encoding/Txtfiles/GB2312-80 (issue #2981).txt deleted file mode 100644 index 1fffed294..000000000 --- a/test/test_files/encoding/Txtfiles/GB2312-80 (issue #2981).txt +++ /dev/null @@ -1,5 +0,0 @@ -您好A 您好A 您好A 您好A 您好A 您好A 您好A 您好A 您好A 您好A 您好A 您好A 您好A 您好A 您好A -您好A 您好A 您好A 您好A 您好A 您好A 您好A 您好A 您好A 您好A 您好A 您好A 您好A 您好A 您好A -您好A 您好A 您好A 您好A 您好A 您好A 您好A 您好A 您好A 您好A 您好A 您好A 您好A 您好A 您好A -您好A 您好A 您好A 您好A 您好A 您好A 您好A 您好A 您好A 您好A 您好A 您好A 您好A 您好A 您好A -您好A 您好A 您好A 您好A 您好A 您好A 您好A 您好A 您好A 您好A 您好A 您好A 您好A 您好A 您好A diff --git a/test/test_files/encoding/Txtfiles/GB2312-80-new (issue #2981).txt b/test/test_files/encoding/Txtfiles/GB2312-80-new (issue #2981).txt new file mode 100644 index 000000000..0c8a74add --- /dev/null +++ b/test/test_files/encoding/Txtfiles/GB2312-80-new (issue #2981).txt @@ -0,0 +1,7 @@ +早期的记事本只提供最基本的功能,例如文字查找功能。 +较新版本的Windows所搭载的新版记事本可以支持查找及取代功能,快捷键是(Ctrl + H), +而Ctrl + F则是传统的查找功能。 +在一些旧版的Windows中,例如Windows 95、Windows 98、Windows Me和Windows 3.1, +其所内置的记事本有64k的文件大小的编辑限制,源自 Windows 的文本框控件的限制 +(此控件默认只能编辑 32767 个字符[1]); +这一限制在 Windows XP 中已被克服。 \ No newline at end of file diff --git a/test/test_files/encoding/Txtfiles/HZ-GB2312 (issue #2981).txt b/test/test_files/encoding/Txtfiles/HZ-GB2312 (issue #2981).txt deleted file mode 100644 index 6572422a5..000000000 --- a/test/test_files/encoding/Txtfiles/HZ-GB2312 (issue #2981).txt +++ /dev/null @@ -1,5 +0,0 @@ -~{Dz:C~}A ~{Dz:C~}A ~{Dz:C~}A ~{Dz:C~}A ~{Dz:C~}A ~{Dz:C~}A ~{Dz:C~}A ~{Dz:C~}A ~{Dz:C~}A ~{Dz:C~}A ~{Dz:C~}A ~{Dz:C~}A ~{Dz:C~}A ~{Dz:C~}A ~{Dz:C~}A -~{Dz:C~}A ~{Dz:C~}A ~{Dz:C~}A ~{Dz:C~}A ~{Dz:C~}A ~{Dz:C~}A ~{Dz:C~}A ~{Dz:C~}A ~{Dz:C~}A ~{Dz:C~}A ~{Dz:C~}A ~{Dz:C~}A ~{Dz:C~}A ~{Dz:C~}A ~{Dz:C~}A -~{Dz:C~}A ~{Dz:C~}A ~{Dz:C~}A ~{Dz:C~}A ~{Dz:C~}A ~{Dz:C~}A ~{Dz:C~}A ~{Dz:C~}A ~{Dz:C~}A ~{Dz:C~}A ~{Dz:C~}A ~{Dz:C~}A ~{Dz:C~}A ~{Dz:C~}A ~{Dz:C~}A -~{Dz:C~}A ~{Dz:C~}A ~{Dz:C~}A ~{Dz:C~}A ~{Dz:C~}A ~{Dz:C~}A ~{Dz:C~}A ~{Dz:C~}A ~{Dz:C~}A ~{Dz:C~}A ~{Dz:C~}A ~{Dz:C~}A ~{Dz:C~}A ~{Dz:C~}A ~{Dz:C~}A -~{Dz:C~}A ~{Dz:C~}A ~{Dz:C~}A ~{Dz:C~}A ~{Dz:C~}A ~{Dz:C~}A ~{Dz:C~}A ~{Dz:C~}A ~{Dz:C~}A ~{Dz:C~}A ~{Dz:C~}A ~{Dz:C~}A ~{Dz:C~}A ~{Dz:C~}A ~{Dz:C~}A diff --git a/test/test_files/encoding/Txtfiles/HZ-GB2312-new (issue #2981).txt b/test/test_files/encoding/Txtfiles/HZ-GB2312-new (issue #2981).txt new file mode 100644 index 000000000..1368c32b5 --- /dev/null +++ b/test/test_files/encoding/Txtfiles/HZ-GB2312-new (issue #2981).txt @@ -0,0 +1,7 @@ +~{TgFZ5DV;La9)Wn;y1>5D9&D\#,@}HgNDWV2iUR9&D\!#~} +~{=OPB0f1>5D~}Windows~{Ky4nTX5DPB0f?IRTV'3V2iUR<0H!4z9&D\#,?l=]<|JG#(~}Ctrl + H~{#)#,~} +~{6x~}Ctrl + F~{TrJG4+M35D2iUR9&D\!#~} +~{TZR;P)>I0f5D~}Windows~{VP#,@}Hg~}Windows 95~{!"~}Windows 98~{!"~}Windows Me~{:M~}Windows 3.1~{#,~} +~{FdKyDZVC5DSP~}64k~{5DND<~4sP!5D1`<-O^VF#,T4WT~} Windows ~{5DND1>?r?X<~5DO^VF~} +~{#(4K?X<~D,HOV;D\1`<-~} 32767 ~{8vWV7{~}[1]~{#)#;~} +~{UbR;O^VFTZ~} Windows XP ~{VPRQ1;?K7~!# \ No newline at end of file diff --git a/test/test_files/encoding/UTF-8/Unicode UTF-8-new (issue #2981).txt b/test/test_files/encoding/UTF-8/Unicode UTF-8-new (issue #2981).txt new file mode 100644 index 000000000..720eb84f9 --- /dev/null +++ b/test/test_files/encoding/UTF-8/Unicode UTF-8-new (issue #2981).txt @@ -0,0 +1,7 @@ +鏃╂湡鐨勮浜嬫湰鍙彁渚涙渶鍩烘湰鐨勫姛鑳斤紝渚嬪鏂囧瓧鏌ユ壘鍔熻兘銆 +杈冩柊鐗堟湰鐨刉indows鎵鎼浇鐨勬柊鐗堣浜嬫湰鍙互鏀寔鏌ユ壘鍙婂彇浠e姛鑳斤紝蹇嵎閿槸锛圕trl + H锛夛紝 +鑰孋trl + F鍒欐槸浼犵粺鐨勬煡鎵惧姛鑳姐 +鍦ㄤ竴浜涙棫鐗堢殑Windows涓紝渚嬪Windows 95銆乄indows 98銆乄indows Me鍜學indows 3.1锛 +鍏舵墍鍐呯疆鐨勮浜嬫湰鏈64k鐨勬枃浠跺ぇ灏忕殑缂栬緫闄愬埗锛屾簮鑷 Windows 鐨勬枃鏈鎺т欢鐨勯檺鍒 +锛堟鎺т欢榛樿鍙兘缂栬緫 32767 涓瓧绗1]锛夛紱 +杩欎竴闄愬埗鍦 Windows XP 涓凡琚厠鏈嶃 \ No newline at end of file