From 73e3e76be5cb5a02f24be06abe994550da215bd7 Mon Sep 17 00:00:00 2001 From: Victor Stinner Date: Mon, 16 May 2011 17:16:18 +0200 Subject: Issue #12057: Convert CJK encoding testcase BLOB into multiple text files --- Lib/test/cjkencodings/big5-utf8.txt | 9 + Lib/test/cjkencodings/big5.txt | 9 + Lib/test/cjkencodings/big5hkscs-utf8.txt | 2 + Lib/test/cjkencodings/big5hkscs.txt | 2 + Lib/test/cjkencodings/cp949-utf8.txt | 9 + Lib/test/cjkencodings/cp949.txt | 9 + Lib/test/cjkencodings/euc_jisx0213-utf8.txt | 8 + Lib/test/cjkencodings/euc_jisx0213.txt | 8 + Lib/test/cjkencodings/euc_jp-utf8.txt | 7 + Lib/test/cjkencodings/euc_jp.txt | 7 + Lib/test/cjkencodings/euc_kr-utf8.txt | 7 + Lib/test/cjkencodings/euc_kr.txt | 7 + Lib/test/cjkencodings/gb18030-utf8.txt | 15 + Lib/test/cjkencodings/gb18030.txt | 15 + Lib/test/cjkencodings/gb2312-utf8.txt | 6 + Lib/test/cjkencodings/gb2312.txt | 6 + Lib/test/cjkencodings/gbk-utf8.txt | 14 + Lib/test/cjkencodings/gbk.txt | 14 + Lib/test/cjkencodings/johab-utf8.txt | 9 + Lib/test/cjkencodings/johab.txt | 9 + Lib/test/cjkencodings/shift_jis-utf8.txt | 7 + Lib/test/cjkencodings/shift_jis.txt | 7 + Lib/test/cjkencodings/shift_jisx0213-utf8.txt | 8 + Lib/test/cjkencodings/shift_jisx0213.txt | 8 + Lib/test/cjkencodings_test.py | 1019 ------------------------- 25 files changed, 202 insertions(+), 1019 deletions(-) create mode 100644 Lib/test/cjkencodings/big5-utf8.txt create mode 100644 Lib/test/cjkencodings/big5.txt create mode 100644 Lib/test/cjkencodings/big5hkscs-utf8.txt create mode 100644 Lib/test/cjkencodings/big5hkscs.txt create mode 100644 Lib/test/cjkencodings/cp949-utf8.txt create mode 100644 Lib/test/cjkencodings/cp949.txt create mode 100644 Lib/test/cjkencodings/euc_jisx0213-utf8.txt create mode 100644 Lib/test/cjkencodings/euc_jisx0213.txt create mode 100644 Lib/test/cjkencodings/euc_jp-utf8.txt create mode 100644 Lib/test/cjkencodings/euc_jp.txt create mode 100644 Lib/test/cjkencodings/euc_kr-utf8.txt create mode 100644 Lib/test/cjkencodings/euc_kr.txt create mode 100644 Lib/test/cjkencodings/gb18030-utf8.txt create mode 100644 Lib/test/cjkencodings/gb18030.txt create mode 100644 Lib/test/cjkencodings/gb2312-utf8.txt create mode 100644 Lib/test/cjkencodings/gb2312.txt create mode 100644 Lib/test/cjkencodings/gbk-utf8.txt create mode 100644 Lib/test/cjkencodings/gbk.txt create mode 100644 Lib/test/cjkencodings/johab-utf8.txt create mode 100644 Lib/test/cjkencodings/johab.txt create mode 100644 Lib/test/cjkencodings/shift_jis-utf8.txt create mode 100644 Lib/test/cjkencodings/shift_jis.txt create mode 100644 Lib/test/cjkencodings/shift_jisx0213-utf8.txt create mode 100644 Lib/test/cjkencodings/shift_jisx0213.txt delete mode 100644 Lib/test/cjkencodings_test.py diff --git a/Lib/test/cjkencodings/big5-utf8.txt b/Lib/test/cjkencodings/big5-utf8.txt new file mode 100644 index 0000000..a0a534a --- /dev/null +++ b/Lib/test/cjkencodings/big5-utf8.txt @@ -0,0 +1,9 @@ +如何在 Python 中使用既有的 C library? +　在資訊科技快速發展的今天, 開發及測試軟體的速度是不容忽視的 +課題. 為加快開發及測試的速度, 我們便常希望能利用一些已開發好的 +library, 並有一個 fast prototyping 的 programming language 可 +供使用. 目前有許許多多的 library 是以 C 寫成, 而 Python 是一個 +fast prototyping 的 programming language. 故我們希望能將既有的 +C library 拿到 Python 的環境中測試及整合. 其中最主要也是我們所 +要討論的問題就是: + diff --git a/Lib/test/cjkencodings/big5.txt b/Lib/test/cjkencodings/big5.txt new file mode 100644 index 0000000..f442495 --- /dev/null +++ b/Lib/test/cjkencodings/big5.txt @@ -0,0 +1,9 @@ +pb Python ϥάJ C library? +@bTާֳtoi, }oδճn骺t׬Oe +D. [ֶ}oδժt, ڭ̫K`ƱQΤ@Ǥw}on +library, æ@ fast prototyping programming language i +Ѩϥ. ثe\\hh library OH C g, Python O@ +fast prototyping programming language. Gڭ̧ƱNJ +C library Python ҤդξX. 䤤̥Dn]Oڭ̩ +nQתDNO: + diff --git a/Lib/test/cjkencodings/big5hkscs-utf8.txt b/Lib/test/cjkencodings/big5hkscs-utf8.txt new file mode 100644 index 0000000..f744ce9 --- /dev/null +++ b/Lib/test/cjkencodings/big5hkscs-utf8.txt @@ -0,0 +1,2 @@ +𠄌Ě鵮罓洆 +ÊÊ̄ê êê̄ diff --git a/Lib/test/cjkencodings/big5hkscs.txt b/Lib/test/cjkencodings/big5hkscs.txt new file mode 100644 index 0000000..81c42b3 --- /dev/null +++ b/Lib/test/cjkencodings/big5hkscs.txt @@ -0,0 +1,2 @@ +E\sڍ +fb diff --git a/Lib/test/cjkencodings/cp949-utf8.txt b/Lib/test/cjkencodings/cp949-utf8.txt new file mode 100644 index 0000000..5655e38 --- /dev/null +++ b/Lib/test/cjkencodings/cp949-utf8.txt @@ -0,0 +1,9 @@ +똠방각하 펲시콜라 + +㉯㉯납!! 因九月패믤릔궈 ⓡⓖ훀¿¿¿ 긍뒙 ⓔ뎨 ㉯. . +亞영ⓔ능횹 . . . . 서울뤄 뎐학乙 家훀 ! ! !ㅠ.ㅠ +흐흐흐 ㄱㄱㄱ☆ㅠ_ㅠ 어릨 탸콰긐 뎌응 칑九들乙 ㉯드긐 +설릌 家훀 . . . . 굴애쉌 ⓔ궈 ⓡ릘㉱긐 因仁川女中까즼 +와쒀훀 ! ! 亞영ⓔ 家능궈 ☆上관 없능궈능 亞능뒈훀 글애듴 +ⓡ려듀九 싀풔숴훀 어릨 因仁川女中싁⑨들앜!! ㉯㉯납♡ ⌒⌒* + diff --git a/Lib/test/cjkencodings/cp949.txt b/Lib/test/cjkencodings/cp949.txt new file mode 100644 index 0000000..16549aa --- /dev/null +++ b/Lib/test/cjkencodings/cp949.txt @@ -0,0 +1,9 @@ +c氢 ݶ + +!! Вp ިR ѵ . . +䬿Ѵ . . . . ʫR ! ! !. + ٤_  O h O +j ʫR . . . . ֚f ѱ ސtƒO  +;R ! ! 䬿 ʫɱ ߾ ɱŴ 䬴ɵR ۾֊ +޷ ǴR  Ĩ!! ҡ* + diff --git a/Lib/test/cjkencodings/euc_jisx0213-utf8.txt b/Lib/test/cjkencodings/euc_jisx0213-utf8.txt new file mode 100644 index 0000000..9a56a2e --- /dev/null +++ b/Lib/test/cjkencodings/euc_jisx0213-utf8.txt @@ -0,0 +1,8 @@ +Python の開発は、1990 年ごろから開始されています。 +開発者の Guido van Rossum は教育用のプログラミング言語「ABC」の開発に参加していましたが、ABC は実用上の目的にはあまり適していませんでした。 +このため、Guido はより実用的なプログラミング言語の開発を開始し、英国 BBS 放送のコメディ番組「モンティ パイソン」のファンである Guido はこの言語を「Python」と名づけました。 +このような背景から生まれた Python の言語設計は、「シンプル」で「習得が容易」という目標に重点が置かれています。 +多くのスクリプト系言語ではユーザの目先の利便性を優先して色々な機能を言語要素として取り入れる場合が多いのですが、Python ではそういった小細工が追加されることはあまりありません。 +言語自体の機能は最小限に押さえ、必要な機能は拡張モジュールとして追加する、というのが Python のポリシーです。 + +ノか゚ ト゚ トキ喝塀 𡚴𪎌 麀齁𩛰 diff --git a/Lib/test/cjkencodings/euc_jisx0213.txt b/Lib/test/cjkencodings/euc_jisx0213.txt new file mode 100644 index 0000000..51e9268 --- /dev/null +++ b/Lib/test/cjkencodings/euc_jisx0213.txt @@ -0,0 +1,8 @@ +Python γȯϡ1990 ǯ鳫ϤƤޤ +ȯԤ Guido van Rossum ϶ѤΥץߥ󥰸ABCפγȯ˻äƤޤABC ϼѾŪˤϤޤŬƤޤǤ +ΤᡢGuido ϤŪʥץߥ󥰸γȯ򳫻Ϥѹ BBS Υǥȡ֥ƥ ѥפΥեǤ Guido ϤθPythonפ̾Ťޤ +Τ褦طʤޤ줿 Python θ߷פϡ֥ץפǡֽưספȤɸ˽֤Ƥޤ +¿ΥץȷϸǤϥ桼ͥ褷ƿʵǽǤȤƼ礬¿ΤǤPython ǤϤäٹɲä뤳ȤϤޤꤢޤ +켫ΤεǽϺǾ¤˲ɬפʵǽϳĥ⥸塼Ȥɲä롢ȤΤ Python ΥݥꥷǤ + +Τ ȥ ԏ diff --git a/Lib/test/cjkencodings/euc_jp-utf8.txt b/Lib/test/cjkencodings/euc_jp-utf8.txt new file mode 100644 index 0000000..7763250 --- /dev/null +++ b/Lib/test/cjkencodings/euc_jp-utf8.txt @@ -0,0 +1,7 @@ +Python の開発は、1990 年ごろから開始されています。 +開発者の Guido van Rossum は教育用のプログラミング言語「ABC」の開発に参加していましたが、ABC は実用上の目的にはあまり適していませんでした。 +このため、Guido はより実用的なプログラミング言語の開発を開始し、英国 BBS 放送のコメディ番組「モンティ パイソン」のファンである Guido はこの言語を「Python」と名づけました。 +このような背景から生まれた Python の言語設計は、「シンプル」で「習得が容易」という目標に重点が置かれています。 +多くのスクリプト系言語ではユーザの目先の利便性を優先して色々な機能を言語要素として取り入れる場合が多いのですが、Python ではそういった小細工が追加されることはあまりありません。 +言語自体の機能は最小限に押さえ、必要な機能は拡張モジュールとして追加する、というのが Python のポリシーです。 + diff --git a/Lib/test/cjkencodings/euc_jp.txt b/Lib/test/cjkencodings/euc_jp.txt new file mode 100644 index 0000000..9da6b5d --- /dev/null +++ b/Lib/test/cjkencodings/euc_jp.txt @@ -0,0 +1,7 @@ +Python γȯϡ1990 ǯ鳫ϤƤޤ +ȯԤ Guido van Rossum ϶ѤΥץߥ󥰸ABCפγȯ˻äƤޤABC ϼѾŪˤϤޤŬƤޤǤ +ΤᡢGuido ϤŪʥץߥ󥰸γȯ򳫻Ϥѹ BBS Υǥȡ֥ƥ ѥפΥեǤ Guido ϤθPythonפ̾Ťޤ +Τ褦طʤޤ줿 Python θ߷פϡ֥ץפǡֽưספȤɸ˽֤Ƥޤ +¿ΥץȷϸǤϥ桼ͥ褷ƿʵǽǤȤƼ礬¿ΤǤPython ǤϤäٹɲä뤳ȤϤޤꤢޤ +켫ΤεǽϺǾ¤˲ɬפʵǽϳĥ⥸塼Ȥɲä롢ȤΤ Python ΥݥꥷǤ + diff --git a/Lib/test/cjkencodings/euc_kr-utf8.txt b/Lib/test/cjkencodings/euc_kr-utf8.txt new file mode 100644 index 0000000..16c3741 --- /dev/null +++ b/Lib/test/cjkencodings/euc_kr-utf8.txt @@ -0,0 +1,7 @@ +◎ 파이썬(Python)은 배우기 쉽고, 강력한 프로그래밍 언어입니다. 파이썬은 +효율적인 고수준 데이터 구조와 간단하지만 효율적인 객체지향프로그래밍을 +지원합니다. 파이썬의 우아(優雅)한 문법과 동적 타이핑, 그리고 인터프리팅 +환경은 파이썬을 스크립팅과 여러 분야에서와 대부분의 플랫폼에서의 빠른 +애플리케이션 개발을 할 수 있는 이상적인 언어로 만들어줍니다. + +☆첫가끝: 날아라 쓔쓔쓩~ 닁큼! 뜽금없이 전홥니다. 뷁. 그런거 읎다. diff --git a/Lib/test/cjkencodings/euc_kr.txt b/Lib/test/cjkencodings/euc_kr.txt new file mode 100644 index 0000000..f68dd35 --- /dev/null +++ b/Lib/test/cjkencodings/euc_kr.txt @@ -0,0 +1,7 @@ + ̽(Python) , α׷ Դϴ. ̽ +ȿ ȿ üα׷ +մϴ. ̽ () Ÿ, ׸ +ȯ ̽ ũð о߿ κ ÷ +ø̼ ִ ̻ ݴϴ. + +ù: ƶ ԤФԤԤФԾ~ ԤҤŭ! ԤѤݾ ԤȤϴ. ԤΤ. ׷ ԤѤ. diff --git a/Lib/test/cjkencodings/gb18030-utf8.txt b/Lib/test/cjkencodings/gb18030-utf8.txt new file mode 100644 index 0000000..2060d25 --- /dev/null +++ b/Lib/test/cjkencodings/gb18030-utf8.txt @@ -0,0 +1,15 @@ +Python（派森）语言是一种功能强大而完善的通用型计算机程序设计语言， +已经具有十多年的发展历史，成熟且稳定。这种语言具有非常简捷而清晰 +的语法特点，适合完成各种高层任务，几乎可以在所有的操作系统中 +运行。这种语言简单而强大，适合各种人士学习使用。目前，基于这 +种语言的相关技术正在飞速的发展，用户数量急剧扩大，相关的资源非常多。 +如何在 Python 中使用既有的 C library? +　在資訊科技快速發展的今天, 開發及測試軟體的速度是不容忽視的 +課題. 為加快開發及測試的速度, 我們便常希望能利用一些已開發好的 +library, 並有一個 fast prototyping 的 programming language 可 +供使用. 目前有許許多多的 library 是以 C 寫成, 而 Python 是一個 +fast prototyping 的 programming language. 故我們希望能將既有的 +C library 拿到 Python 的環境中測試及整合. 其中最主要也是我們所 +要討論的問題就是: +파이썬은 강력한 기능을 지닌 범용 컴퓨터 프로그래밍 언어다. + diff --git a/Lib/test/cjkencodings/gb18030.txt b/Lib/test/cjkencodings/gb18030.txt new file mode 100644 index 0000000..5d1f6dc --- /dev/null +++ b/Lib/test/cjkencodings/gb18030.txt @@ -0,0 +1,15 @@ +PythonɭһֹǿƵͨͼԣ +ѾʮķչʷȶԾзdzݶ +﷨ص㣬ʺɸָ߲񣬼еIJϵͳ +СԼ򵥶ǿʺϸʿѧϰʹáĿǰ +ԵؼڷٵķչûصԴdzࡣ + Python ʹüе C library? +YӍƼٰlչĽ, _lyԇܛwٶDzݺҕ +n}. ӿ_lyԇٶ, ҂㳣ϣһЩ_lõ +library, Kһ fast prototyping programming language +ʹ. ĿǰSS library C , Python һ +fast prototyping programming language. ҂ϣ܌е +C library õ Python ĭhМyԇ. ҪҲ҂ +ҪӑՓĆ}: +51332131 760463 858635 3195 0930 435755 5509899304 292599. + diff --git a/Lib/test/cjkencodings/gb2312-utf8.txt b/Lib/test/cjkencodings/gb2312-utf8.txt new file mode 100644 index 0000000..efb7d8f --- /dev/null +++ b/Lib/test/cjkencodings/gb2312-utf8.txt @@ -0,0 +1,6 @@ +Python（派森）语言是一种功能强大而完善的通用型计算机程序设计语言， +已经具有十多年的发展历史，成熟且稳定。这种语言具有非常简捷而清晰 +的语法特点，适合完成各种高层任务，几乎可以在所有的操作系统中 +运行。这种语言简单而强大，适合各种人士学习使用。目前，基于这 +种语言的相关技术正在飞速的发展，用户数量急剧扩大，相关的资源非常多。 + diff --git a/Lib/test/cjkencodings/gb2312.txt b/Lib/test/cjkencodings/gb2312.txt new file mode 100644 index 0000000..1536ac1 --- /dev/null +++ b/Lib/test/cjkencodings/gb2312.txt @@ -0,0 +1,6 @@ +PythonɭһֹǿƵͨͼԣ +ѾʮķչʷȶԾзdzݶ +﷨ص㣬ʺɸָ߲񣬼еIJϵͳ +СԼ򵥶ǿʺϸʿѧϰʹáĿǰ +ԵؼڷٵķչûصԴdzࡣ + diff --git a/Lib/test/cjkencodings/gbk-utf8.txt b/Lib/test/cjkencodings/gbk-utf8.txt new file mode 100644 index 0000000..75bbd31 --- /dev/null +++ b/Lib/test/cjkencodings/gbk-utf8.txt @@ -0,0 +1,14 @@ +Python（派森）语言是一种功能强大而完善的通用型计算机程序设计语言， +已经具有十多年的发展历史，成熟且稳定。这种语言具有非常简捷而清晰 +的语法特点，适合完成各种高层任务，几乎可以在所有的操作系统中 +运行。这种语言简单而强大，适合各种人士学习使用。目前，基于这 +种语言的相关技术正在飞速的发展，用户数量急剧扩大，相关的资源非常多。 +如何在 Python 中使用既有的 C library? +　在資訊科技快速發展的今天, 開發及測試軟體的速度是不容忽視的 +課題. 為加快開發及測試的速度, 我們便常希望能利用一些已開發好的 +library, 並有一個 fast prototyping 的 programming language 可 +供使用. 目前有許許多多的 library 是以 C 寫成, 而 Python 是一個 +fast prototyping 的 programming language. 故我們希望能將既有的 +C library 拿到 Python 的環境中測試及整合. 其中最主要也是我們所 +要討論的問題就是: + diff --git a/Lib/test/cjkencodings/gbk.txt b/Lib/test/cjkencodings/gbk.txt new file mode 100644 index 0000000..8788f8a --- /dev/null +++ b/Lib/test/cjkencodings/gbk.txt @@ -0,0 +1,14 @@ +PythonɭһֹǿƵͨͼԣ +ѾʮķչʷȶԾзdzݶ +﷨ص㣬ʺɸָ߲񣬼еIJϵͳ +СԼ򵥶ǿʺϸʿѧϰʹáĿǰ +ԵؼڷٵķչûصԴdzࡣ + Python ʹüе C library? +YӍƼٰlչĽ, _lyԇܛwٶDzݺҕ +n}. ӿ_lyԇٶ, ҂㳣ϣһЩ_lõ +library, Kһ fast prototyping programming language +ʹ. ĿǰSS library C , Python һ +fast prototyping programming language. ҂ϣ܌е +C library õ Python ĭhМyԇ. ҪҲ҂ +ҪӑՓĆ}: + diff --git a/Lib/test/cjkencodings/johab-utf8.txt b/Lib/test/cjkencodings/johab-utf8.txt new file mode 100644 index 0000000..5655e38 --- /dev/null +++ b/Lib/test/cjkencodings/johab-utf8.txt @@ -0,0 +1,9 @@ +똠방각하 펲시콜라 + +㉯㉯납!! 因九月패믤릔궈 ⓡⓖ훀¿¿¿ 긍뒙 ⓔ뎨 ㉯. . +亞영ⓔ능횹 . . . . 서울뤄 뎐학乙 家훀 ! ! !ㅠ.ㅠ +흐흐흐 ㄱㄱㄱ☆ㅠ_ㅠ 어릨 탸콰긐 뎌응 칑九들乙 ㉯드긐 +설릌 家훀 . . . . 굴애쉌 ⓔ궈 ⓡ릘㉱긐 因仁川女中까즼 +와쒀훀 ! ! 亞영ⓔ 家능궈 ☆上관 없능궈능 亞능뒈훀 글애듴 +ⓡ려듀九 싀풔숴훀 어릨 因仁川女中싁⑨들앜!! ㉯㉯납♡ ⌒⌒* + diff --git a/Lib/test/cjkencodings/johab.txt b/Lib/test/cjkencodings/johab.txt new file mode 100644 index 0000000..067781b --- /dev/null +++ b/Lib/test/cjkencodings/johab.txt @@ -0,0 +1,9 @@ +wba \ũa + +s!! gÚ zٯٯٯ w ѕ . . + Date: Tue, 17 May 2011 01:18:33 +0200 Subject: Issue #11614: Fix test_linecache, cjkencodings_test.py doesn't exist anymore --- Lib/test/test_linecache.py | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/Lib/test/test_linecache.py b/Lib/test/test_linecache.py index 407bebc..b5f80a4 100644 --- a/Lib/test/test_linecache.py +++ b/Lib/test/test_linecache.py @@ -9,7 +9,7 @@ from test import test_support as support FILENAME = linecache.__file__ INVALID_NAME = '!@$)(!@#_1' EMPTY = '' -TESTS = 'cjkencodings_test inspect_fodder inspect_fodder2 mapping_tests' +TESTS = 'inspect_fodder inspect_fodder2 mapping_tests' TESTS = TESTS.split() TEST_PATH = os.path.dirname(support.__file__) MODULES = "linecache abc".split() -- cgit v0.12 From 4dd89ce6bfb635176d8c9185c148ca11ed207728 Mon Sep 17 00:00:00 2001 From: Senthil Kumaran Date: Tue, 17 May 2011 10:12:18 +0800 Subject: Fix closes issue #12088 - fixes the tarfile.extractall issue when the symlinks/hardlink was broken. It handles now in a graceful manner (No exception is raised, behavior similar GNU tar). --- Lib/tarfile.py | 4 +++- Lib/test/test_tarfile.py | 60 ++++++++++++++++++++++++++++++++++++++++++++++++ 2 files changed, 63 insertions(+), 1 deletion(-) diff --git a/Lib/tarfile.py b/Lib/tarfile.py index 105a758..6b9303e 100644 --- a/Lib/tarfile.py +++ b/Lib/tarfile.py @@ -2239,12 +2239,14 @@ class TarFile(object): if hasattr(os, "symlink") and hasattr(os, "link"): # For systems that support symbolic and hard links. if tarinfo.issym(): - if os.path.exists(targetpath): + if os.path.lexists(targetpath): os.unlink(targetpath) os.symlink(tarinfo.linkname, targetpath) else: # See extract(). if os.path.exists(tarinfo._link_target): + if os.path.lexists(targetpath): + os.unlink(targetpath) os.link(tarinfo._link_target, targetpath) else: self._extract_member(self._find_link_target(tarinfo), targetpath) diff --git a/Lib/test/test_tarfile.py b/Lib/test/test_tarfile.py index f78f9ce..6962f8e 100644 --- a/Lib/test/test_tarfile.py +++ b/Lib/test/test_tarfile.py @@ -872,6 +872,66 @@ class WriteTest(WriteTestBase): os.unlink(temparchive) shutil.rmtree(tempdir) + @unittest.skipUnless(hasattr(os, 'symlink'), "needs os.symlink") + def test_extractall_broken_symlinks(self): + # Test if extractall works properly when tarfile contains broken + # symlinks + tempdir = os.path.join(TEMPDIR, "testsymlinks") + temparchive = os.path.join(TEMPDIR, "testsymlinks.tar") + os.mkdir(tempdir) + try: + source_file = os.path.join(tempdir,'source') + target_file = os.path.join(tempdir,'symlink') + with open(source_file,'w') as f: + f.write('something\n') + os.symlink(source_file, target_file) + tar = tarfile.open(temparchive,'w') + tar.add(target_file, arcname=os.path.basename(target_file)) + tar.close() + # remove the real file + os.unlink(source_file) + # Let's extract it to the location which contains the symlink + tar = tarfile.open(temparchive,'r') + # this should not raise OSError: [Errno 17] File exists + try: + tar.extractall(path=tempdir) + except OSError: + self.fail("extractall failed with broken symlinked files") + finally: + tar.close() + finally: + os.unlink(temparchive) + shutil.rmtree(tempdir) + + @unittest.skipUnless(hasattr(os, 'link'), "needs os.link") + def test_extractall_hardlinks(self): + # Test if extractall works properly when tarfile contains symlinks + tempdir = os.path.join(TEMPDIR, "testsymlinks") + temparchive = os.path.join(TEMPDIR, "testsymlinks.tar") + os.mkdir(tempdir) + try: + source_file = os.path.join(tempdir,'source') + target_file = os.path.join(tempdir,'symlink') + with open(source_file,'w') as f: + f.write('something\n') + os.link(source_file, target_file) + tar = tarfile.open(temparchive,'w') + tar.add(source_file, arcname=os.path.basename(source_file)) + tar.add(target_file, arcname=os.path.basename(target_file)) + tar.close() + # Let's extract it to the location which contains the symlink + tar = tarfile.open(temparchive,'r') + # this should not raise OSError: [Errno 17] File exists + try: + tar.extractall(path=tempdir) + except OSError: + self.fail("extractall failed with linked files") + finally: + tar.close() + finally: + os.unlink(temparchive) + shutil.rmtree(tempdir) + class StreamWriteTest(WriteTestBase): mode = "w|" -- cgit v0.12 From b429c5748125f5e63fbb26c85b8e49b43e62b405 Mon Sep 17 00:00:00 2001 From: Ezio Melotti Date: Tue, 17 May 2011 05:17:35 +0300 Subject: #12093: fix typo in struct doc. Patch by Sandro Tosi. --- Doc/library/struct.rst | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/Doc/library/struct.rst b/Doc/library/struct.rst index 0b8052c..18f6a83 100644 --- a/Doc/library/struct.rst +++ b/Doc/library/struct.rst @@ -314,7 +314,7 @@ the result in a named tuple:: >>> from collections import namedtuple >>> Student = namedtuple('Student', 'name serialnum school gradelevel') - >>> Student._make(unpack('<10sHHb', s)) + >>> Student._make(unpack('<10sHHb', record)) Student(name='raymond ', serialnum=4658, school=264, gradelevel=8) The ordering of format characters may have an impact on size since the padding -- cgit v0.12 From bfbd1a2fd4f304e780d7652daf425fb473097abe Mon Sep 17 00:00:00 2001 From: Ezio Melotti Date: Tue, 17 May 2011 05:39:22 +0300 Subject: #12092: backport rephrasing of a paragraph in the tutorial. --- Doc/tutorial/controlflow.rst | 7 +++---- 1 file changed, 3 insertions(+), 4 deletions(-) diff --git a/Doc/tutorial/controlflow.rst b/Doc/tutorial/controlflow.rst index de93beb..5c7ca4e 100644 --- a/Doc/tutorial/controlflow.rst +++ b/Doc/tutorial/controlflow.rst @@ -455,10 +455,9 @@ and of course it would print:: shopkeeper : Michael Palin sketch : Cheese Shop Sketch -Note that the :meth:`sort` method of the list of keyword argument names is -called before printing the contents of the ``keywords`` dictionary; if this is -not done, the order in which the arguments are printed is undefined. - +Note that the list of keyword argument names is created by sorting the result +of the keywords dictionary's ``keys()`` method before printing its contents; +if this is not done, the order in which the arguments are printed is undefined. .. _tut-arbitraryargs: -- cgit v0.12 From 372954e059956aab354d9abfa7fcdcaca40a6079 Mon Sep 17 00:00:00 2001 From: Ronald Oussoren Date: Tue, 17 May 2011 13:22:30 +0200 Subject: (backport)Fix #10154 and #10090: locale normalizes the UTF-8 encoding to "UTF-8" instead of "UTF8" On MacOSX and OpenBSD (and possibly other BSDs) "en_US.UTF-8" is a valid locale while "en_US.UTF8" is not. As the former works on Linux as well it is better to normalize to that value. --- Lib/locale.py | 2 +- Misc/NEWS | 3 +++ 2 files changed, 4 insertions(+), 1 deletion(-) diff --git a/Lib/locale.py b/Lib/locale.py index 921f4f6..bb4aa37 100644 --- a/Lib/locale.py +++ b/Lib/locale.py @@ -621,7 +621,7 @@ locale_encoding_alias = { 'tactis': 'TACTIS', 'euc_jp': 'eucJP', 'euc_kr': 'eucKR', - 'utf_8': 'UTF8', + 'utf_8': 'UTF-8', 'koi8_r': 'KOI8-R', 'koi8_u': 'KOI8-U', # XXX This list is still incomplete. If you know more diff --git a/Misc/NEWS b/Misc/NEWS index 23f77e5..3262205 100644 --- a/Misc/NEWS +++ b/Misc/NEWS @@ -80,6 +80,9 @@ Core and Builtins Library ------- +- Issue #10154, #10090: change the normalization of UTF-8 to "UTF-8" instead + of "UTF8" in the locale module as the latter is not supported MacOSX and OpenBSD. + - Issue #9516: avoid errors in sysconfig when MACOSX_DEPLOYMENT_TARGET is set in shell. -- cgit v0.12 From b13cacf677c335d43be20675b406923acc1b74a7 Mon Sep 17 00:00:00 2001 From: Ronald Oussoren Date: Tue, 17 May 2011 15:13:46 +0200 Subject: (backport) Fixes #11088: IDLE crashes when using F5 to run a script on OSX with Tk 8.5 Without this patch IDLE will crash reliably on OSX when Tkinter is linked to TkCocoa 8.5.x. To reproduce: * Create a new file (script.py) with the following two lines: x = raw_input('prompt: ') print x * Save the script * Run the script using the F5 keyboard shortcut (running from the menu works fine) The patch is a fairly crude hack, but we haven't found a better workaround for this Tk bug yet. --- Lib/idlelib/ScriptBinding.py | 17 +++++++++++++++++ Misc/NEWS | 3 +++ 2 files changed, 20 insertions(+) diff --git a/Lib/idlelib/ScriptBinding.py b/Lib/idlelib/ScriptBinding.py index 9a16e3c..1139b30 100644 --- a/Lib/idlelib/ScriptBinding.py +++ b/Lib/idlelib/ScriptBinding.py @@ -26,6 +26,7 @@ import tkMessageBox from idlelib import PyShell from idlelib.configHandler import idleConf +from idlelib import macosxSupport IDENTCHARS = string.ascii_letters + string.digits + "_" @@ -53,6 +54,9 @@ class ScriptBinding: self.flist = self.editwin.flist self.root = self.editwin.root + if macosxSupport.runningAsOSXApp(): + self.editwin.text_frame.bind('<>', self._run_module_event) + def check_module_event(self, event): filename = self.getfilename() if not filename: @@ -166,6 +170,19 @@ class ScriptBinding: interp.runcode(code) return 'break' + if macosxSupport.runningAsOSXApp(): + # Tk-Cocoa in MacOSX is broken until at least + # Tk 8.5.9, and without this rather + # crude workaround IDLE would hang when a user + # tries to run a module using the keyboard shortcut + # (the menu item works fine). + _run_module_event = run_module_event + + def run_module_event(self, event): + self.editwin.text_frame.after(200, + lambda: self.editwin.text_frame.event_generate('<>')) + return 'break' + def getfilename(self): """Get source filename. If not saved, offer to save (or create) file diff --git a/Misc/NEWS b/Misc/NEWS index 3262205..c666d3e 100644 --- a/Misc/NEWS +++ b/Misc/NEWS @@ -80,6 +80,9 @@ Core and Builtins Library ------- +- Issue #11088: don't crash when using F5 to run a script in IDLE on MacOSX + with Tk 8.5. + - Issue #10154, #10090: change the normalization of UTF-8 to "UTF-8" instead of "UTF8" in the locale module as the latter is not supported MacOSX and OpenBSD. -- cgit v0.12 From 2c5e28ebc21b8517cfaa3075dabb81f963be0303 Mon Sep 17 00:00:00 2001 From: Victor Stinner Date: Tue, 17 May 2011 15:49:56 +0200 Subject: Issue #12057: Fix .hgeol and test_multibytecodec_support for the conversion of the CJK encoding testcase BLOB into multiple text files. --- .hgeol | 3 ++- Lib/test/test_multibytecodec_support.py | 17 ++++++++++++----- 2 files changed, 14 insertions(+), 6 deletions(-) diff --git a/.hgeol b/.hgeol index e1c1992..fe66605 100644 --- a/.hgeol +++ b/.hgeol @@ -27,8 +27,9 @@ **.zip = BIN Lib/email/test/data/msg_26.txt = BIN -Lib/test/sndhdrdata/sndhdr.* = BIN +Lib/test/cjkencodings/* = BIN Lib/test/decimaltestdata/*.decTest = BIN +Lib/test/sndhdrdata/sndhdr.* = BIN # All other files (which presumably are human-editable) are "native". # This must be the last rule! diff --git a/Lib/test/test_multibytecodec_support.py b/Lib/test/test_multibytecodec_support.py index 0639032..9452909 100644 --- a/Lib/test/test_multibytecodec_support.py +++ b/Lib/test/test_multibytecodec_support.py @@ -4,8 +4,11 @@ # Common Unittest Routines for CJK codecs # -import sys, codecs -import unittest, re +import codecs +import os +import re +import sys +import unittest from httplib import HTTPException from test import test_support from StringIO import StringIO @@ -326,6 +329,10 @@ class TestBase_Mapping(unittest.TestCase): self.fail('Decoding failed while testing %s -> %s: %s' % ( repr(csetch), repr(unich), exc.reason)) -def load_teststring(encoding): - from test import cjkencodings_test - return cjkencodings_test.teststring[encoding] +def load_teststring(name): + dir = os.path.join(os.path.dirname(__file__), 'cjkencodings') + with open(os.path.join(dir, name + '.txt'), 'rb') as f: + encoded = f.read() + with open(os.path.join(dir, name + '-utf8.txt'), 'rb') as f: + utf8 = f.read() + return encoded, utf8 -- cgit v0.12