diff options
Diffstat (limited to 'dev-python/beautifulsoup')
| -rw-r--r-- | dev-python/beautifulsoup/Manifest | 24 | ||||
| -rw-r--r-- | dev-python/beautifulsoup/beautifulsoup-3.1.0.1-r1.ebuild | 49 | ||||
| -rw-r--r-- | dev-python/beautifulsoup/beautifulsoup-4.1.3-r1.ebuild | 16 | ||||
| -rw-r--r-- | dev-python/beautifulsoup/beautifulsoup-4.2.0.ebuild | 19 | ||||
| -rw-r--r-- | dev-python/beautifulsoup/files/beautifulsoup-3.1.0.1-python-3.patch | 949 | ||||
| -rw-r--r-- | dev-python/beautifulsoup/files/bfs-4.2.0-no-lxml.patch | 67 | ||||
| -rw-r--r-- | dev-python/beautifulsoup/metadata.xml | 3 |
7 files changed, 94 insertions, 1033 deletions
diff --git a/dev-python/beautifulsoup/Manifest b/dev-python/beautifulsoup/Manifest index cc5ca6ff8852..8e4b4c6e873a 100644 --- a/dev-python/beautifulsoup/Manifest +++ b/dev-python/beautifulsoup/Manifest @@ -1,29 +1,13 @@ ------BEGIN PGP SIGNED MESSAGE----- -Hash: SHA256 - -AUX beautifulsoup-3.1.0.1-python-3.patch 42319 SHA256 ff316866451fa89bcd55f2a12590960df0d1c5b099cb94ca8e2d684024536a97 SHA512 7e29d0cfa4f927c9df87902adc7bd037ebeb9f2389ace2370253e453309bde7dd4a58247e24e2caa0cc2ae73ad65480973fed6397bb987bf9715fa4515dac1c1 WHIRLPOOL bcdfe4f601fb69f579bb55021c244cb9861946bfba8253c5ab5ed5426266abf798832c8eacc5208bd2e0baa9ccf0e6f74eded73e76289c5560891b86b557d489 -DIST BeautifulSoup-3.1.0.1.tar.gz 71460 SHA256 820a80f473240d9d30047f36c959d530a699a732500662dd8b03e1d3ccad12a8 SHA512 812969faf454a58d849921836ed07ec9a950f34fb31e29e118cdf1a75a533370e430f417402b5a5016d23b2d3a1c44a1cf5fde5b3bfd1bc98c50036edd51c0d6 WHIRLPOOL a199585817dcabcc6327c3836a66128605ebf92a6663b5c660125061a797485a504d300791bcd43e0e94e4f08ca59c01f65f42481da07b1240350cbfc6ea6b0c +AUX bfs-4.2.0-no-lxml.patch 2462 SHA256 d28f5b8d33a674e6349fc5376a30d2c74a8029a7839e7f13a7701fc9a20b5563 SHA512 4d6f1db9cff0007c824340da94cfa001a7afaef2cbc6ce95f669c72221ffeb2a975688f449bd66c0163bc90328329471577d8562e31dabbff610f30bfd0a8592 WHIRLPOOL f495c2588dd7a3d11d0802212d072b3d0ef02d8c55edb9546b2117d7867b0ebcd4a41411f3a2de9e34f57db8e72030b3e290dbe60300bc4bd8f2b94d1f5193e1 DIST BeautifulSoup-3.2.0.tar.gz 31056 SHA256 a0ea3377a1055bf2e17594c0808414afb65e11f25ce8998f1ed3e9b871de6ff6 SHA512 2bee35d0d0f3909eb09fe74c5ed1ebccb9fa134e200f5e9f00266fe1f3453d1794e920dbe4129fd3f445abe19a5acaa7dab207b2e752ac0102ae5fd9441df8ce WHIRLPOOL a537228dd5b686fd8d033eb4329ecf79fdcdfaf9e5ec4eed9a2b25aba0f41ddc980dbca6cefe26b24b721a0fe0d4804974b504767e034eef35c07ad99ef51f37 DIST BeautifulSoup-3.2.1.tar.gz 31224 SHA256 f5ba85e907e7dfd78e44e4000b3eaef3a650aefc57831e8a645702db2e5b50db SHA512 365b7b045a2069cf437877543577bc0aa99256a6dc4c9743670b46bfceab5494a06628012d6eccecfe99c25d5c9e0c65814964b47026f15ba1a538444cfb7789 WHIRLPOOL c2f84b29421d0153fb1fecc87d63e00a61182e03bc0683132babca5d6c94143b4875a60a19124a36e4e6e78ce80bff9e1e81b37335700efc14084da933307e26 DIST beautifulsoup4-4.1.3.tar.gz 131292 SHA256 a295b93b30e1126f3fd64edc106f6939349280dde2ba47cef1e5a92dad9319bf SHA512 79ed4f65bcb5599a0d278d5462a67e80f532cdddcb753e0703b28347d84512165ee0bffd09795a501f3b55e6e4869354f04efdceae9de9093a4d85381fee660e WHIRLPOOL 53713ca72b5a409b3755e28d69de65b7994fb387d21ba9a1827f3e4dda2355f318660f69a706825ecb3852447823ffb8bae2cee6bacc093e6ad73347852f29c6 DIST beautifulsoup4-4.2.0.tar.gz 138400 SHA256 9565ce6f6d28808007ab6248c37d59a49934e358276da5d3ac211ea1ccfd0782 SHA512 50c7514f2a1de49df6300d292e1f00e746b341e9c70dbfc3508663870ddf92f5c8e0ea981dc7742f888428845e90bce2cce8b158e8548039be4c2c06ee76db97 WHIRLPOOL 95db573c6c291d27187af9403694bcff27add7ad378b105df96f988074480b7a1491710681a93f1396dfa33cfa8c493637564ab7fc228e9e92659c385aa769a2 -EBUILD beautifulsoup-3.1.0.1-r1.ebuild 1322 SHA256 1842b02302d10443ccb2fd8936fcdcc27ea4f13b0a81b65c96e5cbfaa7aa4b70 SHA512 ce26dc242f5c0e8535431dfc30b67262f628f8431fe4cd6c7cc1ff7ff79c41e5d7c050300bd4598d7e0e7125d099008ac47f0641cbd95cc5297495cd5293c316 WHIRLPOOL 764fbfeb89a37d8ad8b0891343f9e992edff735d6108281f61c83aa14978239bc8a3a4da19f7bcdbb19c447cdf638f13596cf2c6891b28786d9e84aad8e6ad13 EBUILD beautifulsoup-3.2.0.ebuild 1128 SHA256 562ccb3c02dedd76df2e0853bf040443b94d44450162daa39339f00adcdfb82a SHA512 b54870de0e10b191d90b17a7695eb74cad253a6a3f06621cdd86c722bc4ffba2f0d2e216c8d3da13d4a4894d2aa5c08f21299748351224e21772d985fcccfffb WHIRLPOOL 8aeaf761c91bd819860a68b910d252e07e55a0461b3d5a75ecbf0edcc051d43f34cbce4df6b5a0aa0d182b727d8e5b5d807e7091ff1d206bd3411f3a711bb814 EBUILD beautifulsoup-3.2.1-r1.ebuild 1009 SHA256 1800cc0ed032ee002d4f29ca805e2c0abd6dd81954a5aa098e37bd3bf843fb95 SHA512 379e343e470447eb37e61c40c79692a44e17b0b6f3d12f6d2663d9cf2d47ab00ccb66e6ea184502bf40f755277b16eafb53685efdaddbd1dbe36649fe5370327 WHIRLPOOL bc3b3d3719d90672f8492c6df4d74ac09330c370b1b8653e8c3d02f9b73a5971a50d5fb3b1b13fa9c986944e2495d228841ae1e901a0af4b2481735406e1e732 EBUILD beautifulsoup-3.2.1.ebuild 1136 SHA256 7f64d7e6d2877eec779d5df93d7612647a205ef62b066c7aee5606f7cb080d52 SHA512 6fa414de24084e6cb9f37db24fb40c8fca01104ccefe7114b5d880899284fa12aed02d25cd9247ed9ce0d0780bc234bfd68347638d8beef9c39d82ae9a8f11e7 WHIRLPOOL 154e07b1641bb6c73151fa2f7fac00a273ca20f6fb22129876ded9c8a9101437e66f44a49d74bac70290a2bbead9d123deda55322fdfe544235666c2b97125e7 -EBUILD beautifulsoup-4.1.3-r1.ebuild 1284 SHA256 affe563f8db2596b0c5acf71092dd8cd22147ea70c8603b32cb01c2246588998 SHA512 3fa663b4a77754d758af79da0fea4def7ade81f7f05980f5d9cfe9f7f9199a41a5b02adaf91b9c907b6308bf4cb4e97c883332076f57820e5c62855dbe1a7842 WHIRLPOOL 3b6feef4a1d758ea6f3bcb1f7ea8060086d548aa60fb41f04af5efa1455fa2f1d260c22690bd90e84bc2cb4936603915194e4706f0306f52d8ac6dbc177c8d74 +EBUILD beautifulsoup-4.1.3-r1.ebuild 1465 SHA256 53d33b66e0935b093f32ed5bc27aee8a16f2e51dcd0234ce210c56432a972d6c SHA512 1550d56bd7c868ffba7bd7c321a29bd6a7b3e8f5390571c30e6892fd379b2c8b77b160f7780f9d411c6c97f5fbd4947d3d8042b889069627d45770de7740a4db WHIRLPOOL 34420738bca71d6be877cd376eff35443fa3ccfa58fb540c84bc3df5e3d702ce8581eca4fa7ae1932b1b0a9f226053658d712178e3ea57a273b697ba3e070024 EBUILD beautifulsoup-4.1.3.ebuild 1373 SHA256 213867555347809a1fa6e5c4e9a41a1459ddc17d0cc6a763a6f53f92de251b47 SHA512 38bee8dc5953bfcc6ef1e9e0a30dc52463c07b088d6f3cbceafedb1e7981f3873ef7a0645b99c9aa86a15a021127e48b76666de4675a5bccadf43e5d16f9f0be WHIRLPOOL cbbf07d608bea1f533aad98e13a7169e30059cbe47c23def7b0e6406ccfee0c4de96b6fa04593d383e929bea958a5fc3446a669a70295dffc8ea8888a89c833c -EBUILD beautifulsoup-4.2.0.ebuild 1262 SHA256 8e5c585ff7124c1678f03c5e4c623b37cacef011558ac06aefb0018812176175 SHA512 862161e93cf187ab62a6424f151a7df4ae31a411d4d471f8ff8716eeafa72d9e4b8bd2ec0e073d586f3185c45651558d07d9b814ac71ff4340aa5fc6fe4e7b73 WHIRLPOOL aac7256e3ee8c9344527e79e6109a3fe4ad19dedbc23d97d1faa63e48cfed2f12d31206b9494df6a4ec58b0c41a110cad0eb2373e9496d4cb2c774149c6b69e8 +EBUILD beautifulsoup-4.2.0.ebuild 1545 SHA256 c897a253f4a7c119547be9fa9ffe042f97084eaf0bea45cede01c294667c6df9 SHA512 51956b04517aff0f3c2f8586fe4e86e3ebccd2b4cb6668103bb88f47e484f2af662cdf8c43a70cfb4542ccbdcdaaaa6db13f6ad107fb38e1d1a10f9234eb3375 WHIRLPOOL 2c842ec4f7fea3d798ea74a3874511442ca49d01b6f3a4bbfa1b54d015ff5f7b35a7e67f905ae346cce88978fda66e685f8b251b0bdc9cb6b3a9115c4769f962 MISC ChangeLog 12047 SHA256 474be0b21284a6a09a9a18767efcfbdaee0e60e0b86d101e0945197ca9423030 SHA512 f2a5a9180e9cebf8e0a6b15ad5ff938912fddf50c53dd60d5e40195e04741cc5a6b5982a6f1e3b4d95c1758065dcea45fb9b629f2bd941c71709c815a3d9923d WHIRLPOOL 4ea37c60a59486b0f378cbb61b8c6e1007b1a7a0ba474ff9b0b50b6862d192623d73105096da5f1015d5c374c3eb55fe13585d07ab02561b48b9b0c330eaa516 -MISC metadata.xml 640 SHA256 c24a9868c6b553732e13ee16e41586d8003da55cbdde41d684e4260108f6da51 SHA512 db0d5d29bc3a9de492c06a8c46d34797ade006804ade98b889acfa143417d4aca83ae0b0e73e0207a602fcc3bf0a96d3bb6b60a083a5407e3ab700dc4c4d9433 WHIRLPOOL 930aeab34aca3409796fc06941389e6d3d65f666abe6b30033b5da7af1fa78fab8c16c4190d0276e936c20ca6f0a14929815acd32331f3017458f9ff94bdd456 ------BEGIN PGP SIGNATURE----- -Version: GnuPG v2.0.19 (GNU/Linux) - -iQEcBAEBCAAGBQJRlyc3AAoJEEqz6FtPBkyjmIUIAJyFV5NAXvniCvN+yGCWxc8M -lH4qKH/z/WygirMDucF7TbAH6cd9q2gqtMwpYmpM92jHpx44hUlYhcIRfNnd2dmU -R56q0oVkTuYham+7Z3zwvzXyJErgxneNDFFSA9qMdkjiJGfZKEe9lA+szKkMB0S8 -bcO2TgQEkCyMr4+bVT+ZEvsL00p3j26gmjPRvrSmM9W9jqaZ6tp4eDVgrjASJblh -f2HBVmeBuQryJyvIZE/MClZfXSPfxtC4/qmTVcEjWBZBzU2hhBSpDH6qyNKEdmXE -yc/Tw/b2r1Lo85qw1HzFxv4WQ6uU9XLQcd5DG7kD1bULJ1PxFnbzZhSpyYyZfCM= -=guvV ------END PGP SIGNATURE----- +MISC metadata.xml 705 SHA256 3cf5d32b59791adafd4388a987fe8cf8b60c1c86a67d94b4ff1de8fb76881caf SHA512 9d6f5cdef3b1b438a23086c3312e9d8059cea96557d5676d8e80fb4ca597d4525eab0ca0f9f237348aa243e8598fb3d24a461fcac679808fd2c740ee7b86f25c WHIRLPOOL 4a107e5e9f57e14f029cc444eb2529c25eb4717512d5776e3c99b27e920a62fe9ecb47c351489b0583a31ce363a5c693d1ee1c666e48267afff6c3daf666173f diff --git a/dev-python/beautifulsoup/beautifulsoup-3.1.0.1-r1.ebuild b/dev-python/beautifulsoup/beautifulsoup-3.1.0.1-r1.ebuild deleted file mode 100644 index 6e1bdb067e77..000000000000 --- a/dev-python/beautifulsoup/beautifulsoup-3.1.0.1-r1.ebuild +++ /dev/null @@ -1,49 +0,0 @@ -# Copyright 1999-2012 Gentoo Foundation -# Distributed under the terms of the GNU General Public License v2 -# $Header: /var/cvsroot/gentoo-x86/dev-python/beautifulsoup/beautifulsoup-3.1.0.1-r1.ebuild,v 1.16 2012/10/13 18:41:14 armin76 Exp $ - -EAPI="3" -PYTHON_DEPEND="3" -SUPPORT_PYTHON_ABIS="1" -# Avoid collisions with python-2 slot. -RESTRICT_PYTHON_ABIS="2.* *-jython" - -inherit distutils eutils - -MY_PN="BeautifulSoup" -MY_P="${MY_PN}-${PV}" - -DESCRIPTION="HTML/XML parser for quick-turnaround applications like screen-scraping." -HOMEPAGE="http://www.crummy.com/software/BeautifulSoup/ http://pypi.python.org/pypi/BeautifulSoup" -SRC_URI="http://www.crummy.com/software/${MY_PN}/download/${MY_P}.tar.gz" - -LICENSE="BSD" -SLOT="python-3" -KEYWORDS="~alpha amd64 arm ~hppa ~ia64 ppc ppc64 ~s390 ~sh ~sparc x86 ~x86-fbsd ~x86-freebsd ~amd64-linux ~x86-linux ~x86-macos ~x86-solaris" -IUSE="" - -DEPEND="" -RDEPEND="!dev-python/beautifulsoup:0" - -S="${WORKDIR}/${MY_P}" - -PYTHON_MODNAME="BeautifulSoup.py BeautifulSoupTests.py" - -src_prepare() { - distutils_src_prepare - epatch "${FILESDIR}/${P}-python-3.patch" -} - -src_test() { - testing() { - PYTHONPATH="build-${PYTHON_ABI}/lib" "$(PYTHON)" BeautifulSoupTests.py - } - python_execute_function testing -} - -src_install() { - distutils_src_install - - # Delete useless files. - rm -fr "${ED}usr/bin" -} diff --git a/dev-python/beautifulsoup/beautifulsoup-4.1.3-r1.ebuild b/dev-python/beautifulsoup/beautifulsoup-4.1.3-r1.ebuild index 042a0e937eaf..22f4c60b2b77 100644 --- a/dev-python/beautifulsoup/beautifulsoup-4.1.3-r1.ebuild +++ b/dev-python/beautifulsoup/beautifulsoup-4.1.3-r1.ebuild @@ -1,6 +1,6 @@ # Copyright 1999-2013 Gentoo Foundation # Distributed under the terms of the GNU General Public License v2 -# $Header: /var/cvsroot/gentoo-x86/dev-python/beautifulsoup/beautifulsoup-4.1.3-r1.ebuild,v 1.6 2013/05/03 07:07:04 idella4 Exp $ +# $Header: /var/cvsroot/gentoo-x86/dev-python/beautifulsoup/beautifulsoup-4.1.3-r1.ebuild,v 1.7 2013/05/22 15:29:59 idella4 Exp $ EAPI=5 @@ -18,12 +18,14 @@ SRC_URI="mirror://pypi/${MY_P:0:1}/${MY_PN}/${MY_P}.tar.gz" LICENSE="MIT" SLOT="4" KEYWORDS="~alpha amd64 ~arm ~hppa ~ia64 ~mips ~ppc ~ppc64 ~s390 ~sh ~sparc x86 ~amd64-fbsd ~x86-fbsd ~x86-freebsd ~amd64-linux ~x86-linux ~x64-macos ~x86-macos ~sparc-solaris ~x86-solaris" -IUSE="doc test" - -DEPEND="doc? ( dev-python/sphinx[${PYTHON_USEDEP}] ) - test? ( dev-python/nose[${PYTHON_USEDEP}] - dev-python/lxml[${PYTHON_USEDEP}] )" -RDEPEND="" +# new html5 awaits keywording of html5lib in Bug 471002 +IUSE="doc +lxml test" +# pending Bug 471002; html5? ( dev-python/html5lib[$(python_gen_usedep 'python{2_6,2_7}' pypy2_0)] ) + +RDEPEND="lxml? ( dev-python/lxml[${PYTHON_USEDEP}] )" +DEPEND="${RDEPEND} + doc? ( dev-python/sphinx[${PYTHON_USEDEP}] ) + test? ( dev-python/nose[${PYTHON_USEDEP}] )" S="${WORKDIR}/${MY_P}" diff --git a/dev-python/beautifulsoup/beautifulsoup-4.2.0.ebuild b/dev-python/beautifulsoup/beautifulsoup-4.2.0.ebuild index 35f90600d2a6..cd5beb513e45 100644 --- a/dev-python/beautifulsoup/beautifulsoup-4.2.0.ebuild +++ b/dev-python/beautifulsoup/beautifulsoup-4.2.0.ebuild @@ -1,9 +1,9 @@ # Copyright 1999-2013 Gentoo Foundation # Distributed under the terms of the GNU General Public License v2 -# $Header: /var/cvsroot/gentoo-x86/dev-python/beautifulsoup/beautifulsoup-4.2.0.ebuild,v 1.1 2013/05/18 07:01:07 radhermit Exp $ +# $Header: /var/cvsroot/gentoo-x86/dev-python/beautifulsoup/beautifulsoup-4.2.0.ebuild,v 1.2 2013/05/22 15:29:59 idella4 Exp $ EAPI=5 -PYTHON_COMPAT=( python{2_6,2_7,3_1,3_2,3_3} ) +PYTHON_COMPAT=( python{2_6,2_7,3_1,3_2,3_3} pypy2_0 ) inherit distutils-r1 @@ -18,16 +18,19 @@ SRC_URI="mirror://pypi/${MY_P:0:1}/${MY_PN}/${MY_P}.tar.gz" LICENSE="MIT" SLOT="4" KEYWORDS="~alpha ~amd64 ~arm ~hppa ~ia64 ~mips ~ppc ~ppc64 ~s390 ~sh ~sparc ~x86 ~amd64-fbsd ~x86-fbsd ~x86-freebsd ~amd64-linux ~x86-linux ~x64-macos ~x86-macos ~sparc-solaris ~x86-solaris" -IUSE="doc test" +# new html5 awaits keywording of html5lib in Bug 471002 +IUSE="doc +lxml test" +# pending Bug 471002; html5? ( dev-python/html5lib[$(python_gen_usedep 'python{2_6,2_7}' pypy2_0)] ) -DEPEND="doc? ( dev-python/sphinx[${PYTHON_USEDEP}] ) - test? ( - dev-python/nose[${PYTHON_USEDEP}] - dev-python/lxml[${PYTHON_USEDEP}] - )" +RDEPEND="lxml? ( dev-python/lxml[$(python_gen_usedep 'python{2_6,2_7}' 'python3*')] )" +DEPEND="${RDEPEND} + doc? ( dev-python/sphinx[${PYTHON_USEDEP}] ) + test? ( dev-python/nose[${PYTHON_USEDEP}] )" S=${WORKDIR}/${MY_P} +PATCHES=( "${FILESDIR}"/bfs-${PV}-no-lxml.patch ) + python_compile_all() { if use doc; then emake -C doc html diff --git a/dev-python/beautifulsoup/files/beautifulsoup-3.1.0.1-python-3.patch b/dev-python/beautifulsoup/files/beautifulsoup-3.1.0.1-python-3.patch deleted file mode 100644 index adcbb43dd078..000000000000 --- a/dev-python/beautifulsoup/files/beautifulsoup-3.1.0.1-python-3.patch +++ /dev/null @@ -1,949 +0,0 @@ ---- BeautifulSoup.py -+++ BeautifulSoup.py -@@ -76,7 +76,7 @@ - SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE, DAMMIT. - - """ --from __future__ import generators -+ - - __author__ = "Leonard Richardson (leonardr@segfault.org)" - __version__ = "3.1.0.1" -@@ -84,12 +84,12 @@ - __license__ = "New-style BSD" - - import codecs --import markupbase -+import _markupbase - import types - import re --from HTMLParser import HTMLParser, HTMLParseError -+from html.parser import HTMLParser, HTMLParseError - try: -- from htmlentitydefs import name2codepoint -+ from html.entities import name2codepoint - except ImportError: - name2codepoint = {} - try: -@@ -98,18 +98,18 @@ - from sets import Set as set - - #These hacks make Beautiful Soup able to parse XML with namespaces --markupbase._declname_match = re.compile(r'[a-zA-Z][-_.:a-zA-Z0-9]*\s*').match -+_markupbase._declname_match = re.compile(r'[a-zA-Z][-_.:a-zA-Z0-9]*\s*').match - - DEFAULT_OUTPUT_ENCODING = "utf-8" - - # First, the classes that represent markup elements. - --def sob(unicode, encoding): -+def sob(str, encoding): - """Returns either the given Unicode string or its encoding.""" - if encoding is None: -- return unicode -+ return str - else: -- return unicode.encode(encoding) -+ return str.encode(encoding) - - class PageElement: - """Contains the navigational information for some part of the page -@@ -178,8 +178,8 @@ - return lastChild - - def insert(self, position, newChild): -- if (isinstance(newChild, basestring) -- or isinstance(newChild, unicode)) \ -+ if (isinstance(newChild, str) -+ or isinstance(newChild, str)) \ - and not isinstance(newChild, NavigableString): - newChild = NavigableString(newChild) - -@@ -334,7 +334,7 @@ - g = generator() - while True: - try: -- i = g.next() -+ i = g.__next__() - except StopIteration: - break - if i: -@@ -385,22 +385,22 @@ - def toEncoding(self, s, encoding=None): - """Encodes an object to a string in some encoding, or to Unicode. - .""" -- if isinstance(s, unicode): -+ if isinstance(s, str): - if encoding: - s = s.encode(encoding) - elif isinstance(s, str): - if encoding: - s = s.encode(encoding) - else: -- s = unicode(s) -+ s = str(s) - else: - if encoding: - s = self.toEncoding(str(s), encoding) - else: -- s = unicode(s) -+ s = str(s) - return s - --class NavigableString(unicode, PageElement): -+class NavigableString(str, PageElement): - - def __new__(cls, value): - """Create a new NavigableString. -@@ -410,12 +410,12 @@ - passed in to the superclass's __new__ or the superclass won't know - how to handle non-ASCII characters. - """ -- if isinstance(value, unicode): -- return unicode.__new__(cls, value) -- return unicode.__new__(cls, value, DEFAULT_OUTPUT_ENCODING) -+ if isinstance(value, str): -+ return str.__new__(cls, value) -+ return str.__new__(cls, value, DEFAULT_OUTPUT_ENCODING) - - def __getnewargs__(self): -- return (unicode(self),) -+ return (str(self),) - - def __getattr__(self, attr): - """text.string gives you text. This is for backwards -@@ -424,7 +424,7 @@ - if attr == 'string': - return self - else: -- raise AttributeError, "'%s' object has no attribute '%s'" % (self.__class__.__name__, attr) -+ raise AttributeError("'%s' object has no attribute '%s'" % (self.__class__.__name__, attr)) - - def encode(self, encoding=DEFAULT_OUTPUT_ENCODING): - return self.decode().encode(encoding) -@@ -435,23 +435,23 @@ - class CData(NavigableString): - - def decodeGivenEventualEncoding(self, eventualEncoding): -- return u'<![CDATA[' + self + u']]>' -+ return '<![CDATA[' + self + ']]>' - - class ProcessingInstruction(NavigableString): - - def decodeGivenEventualEncoding(self, eventualEncoding): - output = self -- if u'%SOUP-ENCODING%' in output: -+ if '%SOUP-ENCODING%' in output: - output = self.substituteEncoding(output, eventualEncoding) -- return u'<?' + output + u'?>' -+ return '<?' + output + '?>' - - class Comment(NavigableString): - def decodeGivenEventualEncoding(self, eventualEncoding): -- return u'<!--' + self + u'-->' -+ return '<!--' + self + '-->' - - class Declaration(NavigableString): - def decodeGivenEventualEncoding(self, eventualEncoding): -- return u'<!' + self + u'>' -+ return '<!' + self + '>' - - class Tag(PageElement): - -@@ -460,7 +460,7 @@ - def _invert(h): - "Cheap function to invert a hash." - i = {} -- for k,v in h.items(): -+ for k,v in list(h.items()): - i[v] = k - return i - -@@ -479,23 +479,23 @@ - escaped.""" - x = match.group(1) - if self.convertHTMLEntities and x in name2codepoint: -- return unichr(name2codepoint[x]) -+ return chr(name2codepoint[x]) - elif x in self.XML_ENTITIES_TO_SPECIAL_CHARS: - if self.convertXMLEntities: - return self.XML_ENTITIES_TO_SPECIAL_CHARS[x] - else: -- return u'&%s;' % x -+ return '&%s;' % x - elif len(x) > 0 and x[0] == '#': - # Handle numeric entities - if len(x) > 1 and x[1] == 'x': -- return unichr(int(x[2:], 16)) -+ return chr(int(x[2:], 16)) - else: -- return unichr(int(x[1:])) -+ return chr(int(x[1:])) - - elif self.escapeUnrecognizedEntities: -- return u'&%s;' % x -+ return '&%s;' % x - else: -- return u'&%s;' % x -+ return '&%s;' % x - - def __init__(self, parser, name, attrs=None, parent=None, - previous=None): -@@ -524,7 +524,7 @@ - return kval - return (k, re.sub("&(#\d+|#x[0-9a-fA-F]+|\w+);", - self._convertEntities, val)) -- self.attrs = map(convert, self.attrs) -+ self.attrs = list(map(convert, self.attrs)) - - def get(self, key, default=None): - """Returns the value of the 'key' attribute for the tag, or -@@ -533,7 +533,7 @@ - return self._getAttrMap().get(key, default) - - def has_key(self, key): -- return self._getAttrMap().has_key(key) -+ return key in self._getAttrMap() - - def __getitem__(self, key): - """tag[key] returns the value of the 'key' attribute for the tag, -@@ -551,7 +551,7 @@ - def __contains__(self, x): - return x in self.contents - -- def __nonzero__(self): -+ def __bool__(self): - "A tag is non-None even if it has no contents." - return True - -@@ -577,14 +577,14 @@ - #We don't break because bad HTML can define the same - #attribute multiple times. - self._getAttrMap() -- if self.attrMap.has_key(key): -+ if key in self.attrMap: - del self.attrMap[key] - - def __call__(self, *args, **kwargs): - """Calling a tag like a function is the same as calling its - findAll() method. Eg. tag('a') returns a list of all the A tags - found within this tag.""" -- return apply(self.findAll, args, kwargs) -+ return self.findAll(*args, **kwargs) - - def __getattr__(self, tag): - #print "Getattr %s.%s" % (self.__class__, tag) -@@ -592,7 +592,7 @@ - return self.find(tag[:-3]) - elif tag.find('__') != 0: - return self.find(tag) -- raise AttributeError, "'%s' object has no attribute '%s'" % (self.__class__, tag) -+ raise AttributeError("'%s' object has no attribute '%s'" % (self.__class__, tag)) - - def __eq__(self, other): - """Returns true iff this tag has the same name, the same attributes, -@@ -868,7 +868,7 @@ - if isinstance(markupName, Tag): - markup = markupName - markupAttrs = markup -- callFunctionWithTagData = callable(self.name) \ -+ callFunctionWithTagData = hasattr(self.name, '__call__') \ - and not isinstance(markupName, Tag) - - if (not self.name) \ -@@ -880,7 +880,7 @@ - else: - match = True - markupAttrMap = None -- for attr, matchAgainst in self.attrs.items(): -+ for attr, matchAgainst in list(self.attrs.items()): - if not markupAttrMap: - if hasattr(markupAttrs, 'get'): - markupAttrMap = markupAttrs -@@ -921,16 +921,16 @@ - if self._matches(markup, self.text): - found = markup - else: -- raise Exception, "I don't know how to match against a %s" \ -- % markup.__class__ -+ raise Exception("I don't know how to match against a %s" \ -+ % markup.__class__) - return found - - def _matches(self, markup, matchAgainst): - #print "Matching %s against %s" % (markup, matchAgainst) - result = False -- if matchAgainst == True and type(matchAgainst) == types.BooleanType: -+ if matchAgainst == True and type(matchAgainst) == bool: - result = markup != None -- elif callable(matchAgainst): -+ elif hasattr(matchAgainst, '__call__'): - result = matchAgainst(markup) - else: - #Custom match methods take the tag as an argument, but all -@@ -938,7 +938,7 @@ - if isinstance(markup, Tag): - markup = markup.name - if markup is not None and not isString(markup): -- markup = unicode(markup) -+ markup = str(markup) - #Now we know that chunk is either a string, or None. - if hasattr(matchAgainst, 'match'): - # It's a regexp object. -@@ -947,10 +947,10 @@ - and (markup is not None or not isString(matchAgainst))): - result = markup in matchAgainst - elif hasattr(matchAgainst, 'items'): -- result = markup.has_key(matchAgainst) -+ result = matchAgainst in markup - elif matchAgainst and isString(markup): -- if isinstance(markup, unicode): -- matchAgainst = unicode(matchAgainst) -+ if isinstance(markup, str): -+ matchAgainst = str(matchAgainst) - else: - matchAgainst = str(matchAgainst) - -@@ -971,13 +971,13 @@ - """Convenience method that works with all 2.x versions of Python - to determine whether or not something is listlike.""" - return ((hasattr(l, '__iter__') and not isString(l)) -- or (type(l) in (types.ListType, types.TupleType))) -+ or (type(l) in (list, tuple))) - - def isString(s): - """Convenience method that works with all 2.x versions of Python - to determine whether or not something is stringlike.""" - try: -- return isinstance(s, unicode) or isinstance(s, basestring) -+ return isinstance(s, str) or isinstance(s, str) - except NameError: - return isinstance(s, str) - -@@ -989,7 +989,7 @@ - for portion in args: - if hasattr(portion, 'items'): - #It's a map. Merge it. -- for k,v in portion.items(): -+ for k,v in list(portion.items()): - built[k] = v - elif isList(portion) and not isString(portion): - #It's a list. Map each item to the default. -@@ -1034,7 +1034,7 @@ - object, possibly one with a %SOUP-ENCODING% slot into which an - encoding will be plugged later.""" - if text[:3] == "xml": -- text = u"xml version='1.0' encoding='%SOUP-ENCODING%'" -+ text = "xml version='1.0' encoding='%SOUP-ENCODING%'" - self._toStringSubclass(text, ProcessingInstruction) - - def handle_comment(self, text): -@@ -1044,7 +1044,7 @@ - def handle_charref(self, ref): - "Handle character references as data." - if self.soup.convertEntities: -- data = unichr(int(ref)) -+ data = chr(int(ref)) - else: - data = '&#%s;' % ref - self.handle_data(data) -@@ -1056,7 +1056,7 @@ - data = None - if self.soup.convertHTMLEntities: - try: -- data = unichr(name2codepoint[ref]) -+ data = chr(name2codepoint[ref]) - except KeyError: - pass - -@@ -1147,7 +1147,7 @@ - lambda x: '<!' + x.group(1) + '>') - ] - -- ROOT_TAG_NAME = u'[document]' -+ ROOT_TAG_NAME = '[document]' - - HTML_ENTITIES = "html" - XML_ENTITIES = "xml" -@@ -1236,14 +1236,14 @@ - def _feed(self, inDocumentEncoding=None, isHTML=False): - # Convert the document to Unicode. - markup = self.markup -- if isinstance(markup, unicode): -+ if isinstance(markup, str): - if not hasattr(self, 'originalEncoding'): - self.originalEncoding = None - else: - dammit = UnicodeDammit\ - (markup, [self.fromEncoding, inDocumentEncoding], - smartQuotesTo=self.smartQuotesTo, isHTML=isHTML) -- markup = dammit.unicode -+ markup = dammit.str - self.originalEncoding = dammit.originalEncoding - self.declaredHTMLEncoding = dammit.declaredHTMLEncoding - if markup: -@@ -1269,8 +1269,8 @@ - def isSelfClosingTag(self, name): - """Returns true iff the given string is the name of a - self-closing tag according to this parser.""" -- return self.SELF_CLOSING_TAGS.has_key(name) \ -- or self.instanceSelfClosingTags.has_key(name) -+ return name in self.SELF_CLOSING_TAGS \ -+ or name in self.instanceSelfClosingTags - - def reset(self): - Tag.__init__(self, self, self.ROOT_TAG_NAME) -@@ -1305,7 +1305,7 @@ - - def endData(self, containerClass=NavigableString): - if self.currentData: -- currentData = u''.join(self.currentData) -+ currentData = ''.join(self.currentData) - if (currentData.translate(self.STRIP_ASCII_SPACES) == '' and - not set([tag.name for tag in self.tagStack]).intersection( - self.PRESERVE_WHITESPACE_TAGS)): -@@ -1368,7 +1368,7 @@ - - nestingResetTriggers = self.NESTABLE_TAGS.get(name) - isNestable = nestingResetTriggers != None -- isResetNesting = self.RESET_NESTING_TAGS.has_key(name) -+ isResetNesting = name in self.RESET_NESTING_TAGS - popTo = None - inclusive = True - for i in range(len(self.tagStack)-1, 0, -1): -@@ -1381,7 +1381,7 @@ - if (nestingResetTriggers != None - and p.name in nestingResetTriggers) \ - or (nestingResetTriggers == None and isResetNesting -- and self.RESET_NESTING_TAGS.has_key(p.name)): -+ and p.name in self.RESET_NESTING_TAGS): - - #If we encounter one of the nesting reset triggers - #peculiar to this tag, or we encounter another tag -@@ -1399,7 +1399,7 @@ - if self.quoteStack: - #This is not a real tag. - #print "<%s> is not real!" % name -- attrs = ''.join(map(lambda(x, y): ' %s="%s"' % (x, y), attrs)) -+ attrs = ''.join([' %s="%s"' % (x_y[0], x_y[1]) for x_y in attrs]) - self.handle_data('<%s%s>' % (name, attrs)) - return - self.endData() -@@ -1493,7 +1493,7 @@ - BeautifulStoneSoup before writing your own subclass.""" - - def __init__(self, *args, **kwargs): -- if not kwargs.has_key('smartQuotesTo'): -+ if 'smartQuotesTo' not in kwargs: - kwargs['smartQuotesTo'] = self.HTML_ENTITIES - kwargs['isHTML'] = True - BeautifulStoneSoup.__init__(self, *args, **kwargs) -@@ -1677,7 +1677,7 @@ - parent._getAttrMap() - if (isinstance(tag, Tag) and len(tag.contents) == 1 and - isinstance(tag.contents[0], NavigableString) and -- not parent.attrMap.has_key(tag.name)): -+ tag.name not in parent.attrMap): - parent[tag.name] = tag.contents[0] - BeautifulStoneSoup.popTag(self) - -@@ -1751,9 +1751,9 @@ - self._detectEncoding(markup, isHTML) - self.smartQuotesTo = smartQuotesTo - self.triedEncodings = [] -- if markup == '' or isinstance(markup, unicode): -+ if markup == '' or isinstance(markup, str): - self.originalEncoding = None -- self.unicode = unicode(markup) -+ self.str = str(markup) - return - - u = None -@@ -1766,7 +1766,7 @@ - if u: break - - # If no luck and we have auto-detection library, try that: -- if not u and chardet and not isinstance(self.markup, unicode): -+ if not u and chardet and not isinstance(self.markup, str): - u = self._convertFrom(chardet.detect(self.markup)['encoding']) - - # As a last resort, try utf-8 and windows-1252: -@@ -1775,7 +1775,7 @@ - u = self._convertFrom(proposed_encoding) - if u: break - -- self.unicode = u -+ self.str = u - if not u: self.originalEncoding = None - - def _subMSChar(self, match): -@@ -1783,7 +1783,7 @@ - entity.""" - orig = match.group(1) - sub = self.MS_CHARS.get(orig) -- if type(sub) == types.TupleType: -+ if type(sub) == tuple: - if self.smartQuotesTo == 'xml': - sub = '&#x'.encode() + sub[1].encode() + ';'.encode() - else: -@@ -1804,7 +1804,7 @@ - if self.smartQuotesTo and proposed.lower() in("windows-1252", - "iso-8859-1", - "iso-8859-2"): -- smart_quotes_re = "([\x80-\x9f])" -+ smart_quotes_re = b"([\x80-\x9f])" - smart_quotes_compiled = re.compile(smart_quotes_re) - markup = smart_quotes_compiled.sub(self._subMSChar, markup) - -@@ -1813,7 +1813,7 @@ - u = self._toUnicode(markup, proposed) - self.markup = u - self.originalEncoding = proposed -- except Exception, e: -+ except Exception as e: - # print "That didn't work!" - # print e - return None -@@ -1842,7 +1842,7 @@ - elif data[:4] == '\xff\xfe\x00\x00': - encoding = 'utf-32le' - data = data[4:] -- newdata = unicode(data, encoding) -+ newdata = str(data, encoding) - return newdata - - def _detectEncoding(self, xml_data, isHTML=False): -@@ -1855,41 +1855,41 @@ - elif xml_data[:4] == '\x00\x3c\x00\x3f': - # UTF-16BE - sniffed_xml_encoding = 'utf-16be' -- xml_data = unicode(xml_data, 'utf-16be').encode('utf-8') -+ xml_data = str(xml_data, 'utf-16be').encode('utf-8') - elif (len(xml_data) >= 4) and (xml_data[:2] == '\xfe\xff') \ - and (xml_data[2:4] != '\x00\x00'): - # UTF-16BE with BOM - sniffed_xml_encoding = 'utf-16be' -- xml_data = unicode(xml_data[2:], 'utf-16be').encode('utf-8') -+ xml_data = str(xml_data[2:], 'utf-16be').encode('utf-8') - elif xml_data[:4] == '\x3c\x00\x3f\x00': - # UTF-16LE - sniffed_xml_encoding = 'utf-16le' -- xml_data = unicode(xml_data, 'utf-16le').encode('utf-8') -+ xml_data = str(xml_data, 'utf-16le').encode('utf-8') - elif (len(xml_data) >= 4) and (xml_data[:2] == '\xff\xfe') and \ - (xml_data[2:4] != '\x00\x00'): - # UTF-16LE with BOM - sniffed_xml_encoding = 'utf-16le' -- xml_data = unicode(xml_data[2:], 'utf-16le').encode('utf-8') -+ xml_data = str(xml_data[2:], 'utf-16le').encode('utf-8') - elif xml_data[:4] == '\x00\x00\x00\x3c': - # UTF-32BE - sniffed_xml_encoding = 'utf-32be' -- xml_data = unicode(xml_data, 'utf-32be').encode('utf-8') -+ xml_data = str(xml_data, 'utf-32be').encode('utf-8') - elif xml_data[:4] == '\x3c\x00\x00\x00': - # UTF-32LE - sniffed_xml_encoding = 'utf-32le' -- xml_data = unicode(xml_data, 'utf-32le').encode('utf-8') -+ xml_data = str(xml_data, 'utf-32le').encode('utf-8') - elif xml_data[:4] == '\x00\x00\xfe\xff': - # UTF-32BE with BOM - sniffed_xml_encoding = 'utf-32be' -- xml_data = unicode(xml_data[4:], 'utf-32be').encode('utf-8') -+ xml_data = str(xml_data[4:], 'utf-32be').encode('utf-8') - elif xml_data[:4] == '\xff\xfe\x00\x00': - # UTF-32LE with BOM - sniffed_xml_encoding = 'utf-32le' -- xml_data = unicode(xml_data[4:], 'utf-32le').encode('utf-8') -+ xml_data = str(xml_data[4:], 'utf-32le').encode('utf-8') - elif xml_data[:3] == '\xef\xbb\xbf': - # UTF-8 with BOM - sniffed_xml_encoding = 'utf-8' -- xml_data = unicode(xml_data[3:], 'utf-8').encode('utf-8') -+ xml_data = str(xml_data[3:], 'utf-8').encode('utf-8') - else: - sniffed_xml_encoding = 'ascii' - pass -@@ -1954,41 +1954,41 @@ - 250,251,252,253,254,255) - import string - c.EBCDIC_TO_ASCII_MAP = string.maketrans( \ -- ''.join(map(chr, range(256))), ''.join(map(chr, emap))) -+ ''.join(map(chr, list(range(256)))), ''.join(map(chr, emap))) - return s.translate(c.EBCDIC_TO_ASCII_MAP) - -- MS_CHARS = { '\x80' : ('euro', '20AC'), -- '\x81' : ' ', -- '\x82' : ('sbquo', '201A'), -- '\x83' : ('fnof', '192'), -- '\x84' : ('bdquo', '201E'), -- '\x85' : ('hellip', '2026'), -- '\x86' : ('dagger', '2020'), -- '\x87' : ('Dagger', '2021'), -- '\x88' : ('circ', '2C6'), -- '\x89' : ('permil', '2030'), -- '\x8A' : ('Scaron', '160'), -- '\x8B' : ('lsaquo', '2039'), -- '\x8C' : ('OElig', '152'), -- '\x8D' : '?', -- '\x8E' : ('#x17D', '17D'), -- '\x8F' : '?', -- '\x90' : '?', -- '\x91' : ('lsquo', '2018'), -- '\x92' : ('rsquo', '2019'), -- '\x93' : ('ldquo', '201C'), -- '\x94' : ('rdquo', '201D'), -- '\x95' : ('bull', '2022'), -- '\x96' : ('ndash', '2013'), -- '\x97' : ('mdash', '2014'), -- '\x98' : ('tilde', '2DC'), -- '\x99' : ('trade', '2122'), -- '\x9a' : ('scaron', '161'), -- '\x9b' : ('rsaquo', '203A'), -- '\x9c' : ('oelig', '153'), -- '\x9d' : '?', -- '\x9e' : ('#x17E', '17E'), -- '\x9f' : ('Yuml', ''),} -+ MS_CHARS = { b'\x80' : ('euro', '20AC'), -+ b'\x81' : ' ', -+ b'\x82' : ('sbquo', '201A'), -+ b'\x83' : ('fnof', '192'), -+ b'\x84' : ('bdquo', '201E'), -+ b'\x85' : ('hellip', '2026'), -+ b'\x86' : ('dagger', '2020'), -+ b'\x87' : ('Dagger', '2021'), -+ b'\x88' : ('circ', '2C6'), -+ b'\x89' : ('permil', '2030'), -+ b'\x8A' : ('Scaron', '160'), -+ b'\x8B' : ('lsaquo', '2039'), -+ b'\x8C' : ('OElig', '152'), -+ b'\x8D' : '?', -+ b'\x8E' : ('#x17D', '17D'), -+ b'\x8F' : '?', -+ b'\x90' : '?', -+ b'\x91' : ('lsquo', '2018'), -+ b'\x92' : ('rsquo', '2019'), -+ b'\x93' : ('ldquo', '201C'), -+ b'\x94' : ('rdquo', '201D'), -+ b'\x95' : ('bull', '2022'), -+ b'\x96' : ('ndash', '2013'), -+ b'\x97' : ('mdash', '2014'), -+ b'\x98' : ('tilde', '2DC'), -+ b'\x99' : ('trade', '2122'), -+ b'\x9a' : ('scaron', '161'), -+ b'\x9b' : ('rsaquo', '203A'), -+ b'\x9c' : ('oelig', '153'), -+ b'\x9d' : '?', -+ b'\x9e' : ('#x17E', '17E'), -+ b'\x9f' : ('Yuml', ''),} - - ####################################################################### - -@@ -1997,4 +1997,4 @@ - if __name__ == '__main__': - import sys - soup = BeautifulSoup(sys.stdin) -- print soup.prettify() -+ print(soup.prettify()) ---- BeautifulSoupTests.py -+++ BeautifulSoupTests.py -@@ -82,7 +82,7 @@ - def testFindAllText(self): - soup = BeautifulSoup("<html>\xbb</html>") - self.assertEqual(soup.findAll(text=re.compile('.*')), -- [u'\xbb']) -+ ['\xbb']) - - def testFindAllByRE(self): - import re -@@ -215,7 +215,7 @@ - soup = BeautifulSoup(self.x, parseOnlyThese=strainer) - self.assertEquals(len(soup), 10) - -- strainer = SoupStrainer(text=lambda(x):x[8]=='3') -+ strainer = SoupStrainer(text=lambda x:x[8]=='3') - soup = BeautifulSoup(self.x, parseOnlyThese=strainer) - self.assertEquals(len(soup), 3) - -@@ -256,7 +256,7 @@ - self.assertEqual(copied.decode(), self.soup.decode()) - - def testUnicodePickle(self): -- import cPickle as pickle -+ import pickle as pickle - html = "<b>" + chr(0xc3) + "</b>" - soup = BeautifulSoup(html) - dumped = pickle.dumps(soup, pickle.HIGHEST_PROTOCOL) -@@ -586,23 +586,23 @@ - self.assertEquals(soup.decode(), "<<sacré bleu!>>") - - soup = BeautifulStoneSoup(text, convertEntities=htmlEnt) -- self.assertEquals(soup.decode(), u"<<sacr\xe9 bleu!>>") -+ self.assertEquals(soup.decode(), "<<sacr\xe9 bleu!>>") - - # Make sure the "XML", "HTML", and "XHTML" settings work. - text = "<™'" - soup = BeautifulStoneSoup(text, convertEntities=xmlEnt) -- self.assertEquals(soup.decode(), u"<™'") -+ self.assertEquals(soup.decode(), "<™'") - - soup = BeautifulStoneSoup(text, convertEntities=htmlEnt) -- self.assertEquals(soup.decode(), u"<\u2122'") -+ self.assertEquals(soup.decode(), "<\u2122'") - - soup = BeautifulStoneSoup(text, convertEntities=xhtmlEnt) -- self.assertEquals(soup.decode(), u"<\u2122'") -+ self.assertEquals(soup.decode(), "<\u2122'") - - def testNonBreakingSpaces(self): - soup = BeautifulSoup("<a> </a>", - convertEntities=BeautifulStoneSoup.HTML_ENTITIES) -- self.assertEquals(soup.decode(), u"<a>\xa0\xa0</a>") -+ self.assertEquals(soup.decode(), "<a>\xa0\xa0</a>") - - def testWhitespaceInDeclaration(self): - self.assertSoupEquals('<! DOCTYPE>', '<!DOCTYPE>') -@@ -617,27 +617,27 @@ - self.assertSoupEquals('<b>hello there</b>') - - def testEntitiesInAttributeValues(self): -- self.assertSoupEquals('<x t="xñ">', '<x t="x\xc3\xb1"></x>', -+ self.assertSoupEquals('<x t="xñ">', b'<x t="x\xc3\xb1"></x>', - encoding='utf-8') -- self.assertSoupEquals('<x t="xñ">', '<x t="x\xc3\xb1"></x>', -+ self.assertSoupEquals('<x t="xñ">', b'<x t="x\xc3\xb1"></x>', - encoding='utf-8') - - soup = BeautifulSoup('<x t=">™">', - convertEntities=BeautifulStoneSoup.HTML_ENTITIES) -- self.assertEquals(soup.decode(), u'<x t=">\u2122"></x>') -+ self.assertEquals(soup.decode(), '<x t=">\u2122"></x>') - - uri = "http://crummy.com?sacré&bleu" - link = '<a href="%s"></a>' % uri - - soup = BeautifulSoup(link, convertEntities=BeautifulSoup.HTML_ENTITIES) - self.assertEquals(soup.decode(), -- link.replace("é", u"\xe9")) -+ link.replace("é", "\xe9")) - - uri = "http://crummy.com?sacré&bleu" - link = '<a href="%s"></a>' % uri - soup = BeautifulSoup(link, convertEntities=BeautifulSoup.HTML_ENTITIES) - self.assertEquals(soup.a['href'], -- uri.replace("é", u"\xe9")) -+ uri.replace("é", "\xe9")) - - def testNakedAmpersands(self): - html = {'convertEntities':BeautifulStoneSoup.HTML_ENTITIES} -@@ -663,13 +663,13 @@ - smart quote fixes.""" - - def testUnicodeDammitStandalone(self): -- markup = "<foo>\x92</foo>" -+ markup = b"<foo>\x92</foo>" - dammit = UnicodeDammit(markup) -- self.assertEquals(dammit.unicode, "<foo>’</foo>") -+ self.assertEquals(dammit.str, "<foo>’</foo>") - -- hebrew = "\xed\xe5\xec\xf9" -+ hebrew = b"\xed\xe5\xec\xf9" - dammit = UnicodeDammit(hebrew, ["iso-8859-8"]) -- self.assertEquals(dammit.unicode, u'\u05dd\u05d5\u05dc\u05e9') -+ self.assertEquals(dammit.str, '\u05dd\u05d5\u05dc\u05e9') - self.assertEquals(dammit.originalEncoding, 'iso-8859-8') - - def testGarbageInGarbageOut(self): -@@ -677,13 +677,13 @@ - asciiSoup = BeautifulStoneSoup(ascii) - self.assertEquals(ascii, asciiSoup.decode()) - -- unicodeData = u"<foo>\u00FC</foo>" -+ unicodeData = "<foo>\u00FC</foo>" - utf8 = unicodeData.encode("utf-8") -- self.assertEquals(utf8, '<foo>\xc3\xbc</foo>') -+ self.assertEquals(utf8, b'<foo>\xc3\xbc</foo>') - - unicodeSoup = BeautifulStoneSoup(unicodeData) - self.assertEquals(unicodeData, unicodeSoup.decode()) -- self.assertEquals(unicodeSoup.foo.string, u'\u00FC') -+ self.assertEquals(unicodeSoup.foo.string, '\u00FC') - - utf8Soup = BeautifulStoneSoup(utf8, fromEncoding='utf-8') - self.assertEquals(utf8, utf8Soup.encode('utf-8')) -@@ -696,18 +696,18 @@ - - def testHandleInvalidCodec(self): - for bad_encoding in ['.utf8', '...', 'utF---16.!']: -- soup = BeautifulSoup(u"Räksmörgås".encode("utf-8"), -+ soup = BeautifulSoup("Räksmörgås".encode("utf-8"), - fromEncoding=bad_encoding) - self.assertEquals(soup.originalEncoding, 'utf-8') - - def testUnicodeSearch(self): -- html = u'<html><body><h1>Räksmörgås</h1></body></html>' -+ html = '<html><body><h1>Räksmörgås</h1></body></html>' - soup = BeautifulSoup(html) -- self.assertEqual(soup.find(text=u'Räksmörgås'),u'Räksmörgås') -+ self.assertEqual(soup.find(text='Räksmörgås'),'Räksmörgås') - - def testRewrittenXMLHeader(self): -- euc_jp = '<?xml version="1.0 encoding="euc-jp"?>\n<foo>\n\xa4\xb3\xa4\xec\xa4\xcfEUC-JP\xa4\xc7\xa5\xb3\xa1\xbc\xa5\xc7\xa5\xa3\xa5\xf3\xa5\xb0\xa4\xb5\xa4\xec\xa4\xbf\xc6\xfc\xcb\xdc\xb8\xec\xa4\xce\xa5\xd5\xa5\xa1\xa5\xa4\xa5\xeb\xa4\xc7\xa4\xb9\xa1\xa3\n</foo>\n' -- utf8 = "<?xml version='1.0' encoding='utf-8'?>\n<foo>\n\xe3\x81\x93\xe3\x82\x8c\xe3\x81\xafEUC-JP\xe3\x81\xa7\xe3\x82\xb3\xe3\x83\xbc\xe3\x83\x87\xe3\x82\xa3\xe3\x83\xb3\xe3\x82\xb0\xe3\x81\x95\xe3\x82\x8c\xe3\x81\x9f\xe6\x97\xa5\xe6\x9c\xac\xe8\xaa\x9e\xe3\x81\xae\xe3\x83\x95\xe3\x82\xa1\xe3\x82\xa4\xe3\x83\xab\xe3\x81\xa7\xe3\x81\x99\xe3\x80\x82\n</foo>\n" -+ euc_jp = b'<?xml version="1.0 encoding="euc-jp"?>\n<foo>\n\xa4\xb3\xa4\xec\xa4\xcfEUC-JP\xa4\xc7\xa5\xb3\xa1\xbc\xa5\xc7\xa5\xa3\xa5\xf3\xa5\xb0\xa4\xb5\xa4\xec\xa4\xbf\xc6\xfc\xcb\xdc\xb8\xec\xa4\xce\xa5\xd5\xa5\xa1\xa5\xa4\xa5\xeb\xa4\xc7\xa4\xb9\xa1\xa3\n</foo>\n' -+ utf8 = b"<?xml version='1.0' encoding='utf-8'?>\n<foo>\n\xe3\x81\x93\xe3\x82\x8c\xe3\x81\xafEUC-JP\xe3\x81\xa7\xe3\x82\xb3\xe3\x83\xbc\xe3\x83\x87\xe3\x82\xa3\xe3\x83\xb3\xe3\x82\xb0\xe3\x81\x95\xe3\x82\x8c\xe3\x81\x9f\xe6\x97\xa5\xe6\x9c\xac\xe8\xaa\x9e\xe3\x81\xae\xe3\x83\x95\xe3\x82\xa1\xe3\x82\xa4\xe3\x83\xab\xe3\x81\xa7\xe3\x81\x99\xe3\x80\x82\n</foo>\n" - soup = BeautifulStoneSoup(euc_jp) - if soup.originalEncoding != "euc-jp": - raise Exception("Test failed when parsing euc-jp document. " -@@ -718,12 +718,12 @@ - self.assertEquals(soup.originalEncoding, "euc-jp") - self.assertEquals(soup.renderContents('utf-8'), utf8) - -- old_text = "<?xml encoding='windows-1252'><foo>\x92</foo>" -+ old_text = b"<?xml encoding='windows-1252'><foo>\x92</foo>" - new_text = "<?xml version='1.0' encoding='utf-8'?><foo>’</foo>" - self.assertSoupEquals(old_text, new_text) - - def testRewrittenMetaTag(self): -- no_shift_jis_html = '''<html><head>\n<meta http-equiv="Content-language" content="ja" /></head><body><pre>\n\x82\xb1\x82\xea\x82\xcdShift-JIS\x82\xc5\x83R\x81[\x83f\x83B\x83\x93\x83O\x82\xb3\x82\xea\x82\xbd\x93\xfa\x96{\x8c\xea\x82\xcc\x83t\x83@\x83C\x83\x8b\x82\xc5\x82\xb7\x81B\n</pre></body></html>''' -+ no_shift_jis_html = b'''<html><head>\n<meta http-equiv="Content-language" content="ja" /></head><body><pre>\n\x82\xb1\x82\xea\x82\xcdShift-JIS\x82\xc5\x83R\x81[\x83f\x83B\x83\x93\x83O\x82\xb3\x82\xea\x82\xbd\x93\xfa\x96{\x8c\xea\x82\xcc\x83t\x83@\x83C\x83\x8b\x82\xc5\x82\xb7\x81B\n</pre></body></html>''' - soup = BeautifulSoup(no_shift_jis_html) - - # Beautiful Soup used to try to rewrite the meta tag even if the -@@ -733,16 +733,16 @@ - soup = BeautifulSoup(no_shift_jis_html, parseOnlyThese=strainer) - self.assertEquals(soup.contents[0].name, 'pre') - -- meta_tag = ('<meta content="text/html; charset=x-sjis" ' -- 'http-equiv="Content-type" />') -+ meta_tag = (b'<meta content="text/html; charset=x-sjis" ' -+ b'http-equiv="Content-type" />') - shift_jis_html = ( -- '<html><head>\n%s\n' -- '<meta http-equiv="Content-language" content="ja" />' -- '</head><body><pre>\n' -- '\x82\xb1\x82\xea\x82\xcdShift-JIS\x82\xc5\x83R\x81[\x83f' -- '\x83B\x83\x93\x83O\x82\xb3\x82\xea\x82\xbd\x93\xfa\x96{\x8c' -- '\xea\x82\xcc\x83t\x83@\x83C\x83\x8b\x82\xc5\x82\xb7\x81B\n' -- '</pre></body></html>') % meta_tag -+ b'<html><head>\n' + meta_tag + b'\n' -+ b'<meta http-equiv="Content-language" content="ja" />' -+ b'</head><body><pre>\n' -+ b'\x82\xb1\x82\xea\x82\xcdShift-JIS\x82\xc5\x83R\x81[\x83f' -+ b'\x83B\x83\x93\x83O\x82\xb3\x82\xea\x82\xbd\x93\xfa\x96{\x8c' -+ b'\xea\x82\xcc\x83t\x83@\x83C\x83\x8b\x82\xc5\x82\xb7\x81B\n' -+ b'</pre></body></html>') - soup = BeautifulSoup(shift_jis_html) - if soup.originalEncoding != "shift-jis": - raise Exception("Test failed when parsing shift-jis document " -@@ -755,59 +755,59 @@ - content_type_tag = soup.meta['content'] - self.assertEquals(content_type_tag[content_type_tag.find('charset='):], - 'charset=%SOUP-ENCODING%') -- content_type = str(soup.meta) -+ content_type = soup.meta.decode() - index = content_type.find('charset=') - self.assertEqual(content_type[index:index+len('charset=utf8')+1], - 'charset=utf-8') - content_type = soup.meta.encode('shift-jis') -- index = content_type.find('charset=') -+ index = content_type.find(b'charset=') - self.assertEqual(content_type[index:index+len('charset=shift-jis')], - 'charset=shift-jis'.encode()) - - self.assertEquals(soup.encode('utf-8'), ( -- '<html><head>\n' -- '<meta content="text/html; charset=utf-8" ' -- 'http-equiv="Content-type" />\n' -- '<meta http-equiv="Content-language" content="ja" />' -- '</head><body><pre>\n' -- '\xe3\x81\x93\xe3\x82\x8c\xe3\x81\xafShift-JIS\xe3\x81\xa7\xe3' -- '\x82\xb3\xe3\x83\xbc\xe3\x83\x87\xe3\x82\xa3\xe3\x83\xb3\xe3' -- '\x82\xb0\xe3\x81\x95\xe3\x82\x8c\xe3\x81\x9f\xe6\x97\xa5\xe6' -- '\x9c\xac\xe8\xaa\x9e\xe3\x81\xae\xe3\x83\x95\xe3\x82\xa1\xe3' -- '\x82\xa4\xe3\x83\xab\xe3\x81\xa7\xe3\x81\x99\xe3\x80\x82\n' -- '</pre></body></html>')) -+ b'<html><head>\n' -+ b'<meta content="text/html; charset=utf-8" ' -+ b'http-equiv="Content-type" />\n' -+ b'<meta http-equiv="Content-language" content="ja" />' -+ b'</head><body><pre>\n' -+ b'\xe3\x81\x93\xe3\x82\x8c\xe3\x81\xafShift-JIS\xe3\x81\xa7\xe3' -+ b'\x82\xb3\xe3\x83\xbc\xe3\x83\x87\xe3\x82\xa3\xe3\x83\xb3\xe3' -+ b'\x82\xb0\xe3\x81\x95\xe3\x82\x8c\xe3\x81\x9f\xe6\x97\xa5\xe6' -+ b'\x9c\xac\xe8\xaa\x9e\xe3\x81\xae\xe3\x83\x95\xe3\x82\xa1\xe3' -+ b'\x82\xa4\xe3\x83\xab\xe3\x81\xa7\xe3\x81\x99\xe3\x80\x82\n' -+ b'</pre></body></html>')) - self.assertEquals(soup.encode("shift-jis"), - shift_jis_html.replace('x-sjis'.encode(), - 'shift-jis'.encode())) - -- isolatin = """<html><meta http-equiv="Content-type" content="text/html; charset=ISO-Latin-1" />Sacr\xe9 bleu!</html>""" -+ isolatin = b"""<html><meta http-equiv="Content-type" content="text/html; charset=ISO-Latin-1" />Sacr\xe9 bleu!</html>""" - soup = BeautifulSoup(isolatin) - - utf8 = isolatin.replace("ISO-Latin-1".encode(), "utf-8".encode()) -- utf8 = utf8.replace("\xe9", "\xc3\xa9") -+ utf8 = utf8.replace(b"\xe9", b"\xc3\xa9") - self.assertSoupEquals(soup.encode("utf-8"), utf8, encoding='utf-8') - - def testHebrew(self): -- iso_8859_8= '<HEAD>\n<TITLE>Hebrew (ISO 8859-8) in Visual Directionality</TITLE>\n\n\n\n</HEAD>\n<BODY>\n<H1>Hebrew (ISO 8859-8) in Visual Directionality</H1>\n\xed\xe5\xec\xf9\n</BODY>\n' -- utf8 = '<head>\n<title>Hebrew (ISO 8859-8) in Visual Directionality</title>\n</head>\n<body>\n<h1>Hebrew (ISO 8859-8) in Visual Directionality</h1>\n\xd7\x9d\xd7\x95\xd7\x9c\xd7\xa9\n</body>\n' -+ iso_8859_8= b'<HEAD>\n<TITLE>Hebrew (ISO 8859-8) in Visual Directionality</TITLE>\n\n\n\n</HEAD>\n<BODY>\n<H1>Hebrew (ISO 8859-8) in Visual Directionality</H1>\n\xed\xe5\xec\xf9\n</BODY>\n' -+ utf8 = b'<head>\n<title>Hebrew (ISO 8859-8) in Visual Directionality</title>\n</head>\n<body>\n<h1>Hebrew (ISO 8859-8) in Visual Directionality</h1>\n\xd7\x9d\xd7\x95\xd7\x9c\xd7\xa9\n</body>\n' - soup = BeautifulStoneSoup(iso_8859_8, fromEncoding="iso-8859-8") - self.assertEquals(soup.encode('utf-8'), utf8) - - def testSmartQuotesNotSoSmartAnymore(self): -- self.assertSoupEquals("\x91Foo\x92 <!--blah-->", -+ self.assertSoupEquals(b"\x91Foo\x92 <!--blah-->", - '‘Foo’ <!--blah-->') - - def testDontConvertSmartQuotesWhenAlsoConvertingEntities(self): -- smartQuotes = "Il a dit, \x8BSacré bleu!\x9b" -+ smartQuotes = b"Il a dit, \x8BSacré bleu!\x9b" - soup = BeautifulSoup(smartQuotes) - self.assertEquals(soup.decode(), - 'Il a dit, ‹Sacré bleu!›') - soup = BeautifulSoup(smartQuotes, convertEntities="html") - self.assertEquals(soup.encode('utf-8'), -- 'Il a dit, \xe2\x80\xb9Sacr\xc3\xa9 bleu!\xe2\x80\xba') -+ b'Il a dit, \xe2\x80\xb9Sacr\xc3\xa9 bleu!\xe2\x80\xba') - - def testDontSeeSmartQuotesWhereThereAreNone(self): -- utf_8 = "\343\202\261\343\203\274\343\202\277\343\202\244 Watch" -+ utf_8 = b"\343\202\261\343\203\274\343\202\277\343\202\244 Watch" - self.assertSoupEquals(utf_8, encoding='utf-8') - - ---- setup.py -+++ setup.py -@@ -19,19 +19,19 @@ - suite = loader.loadTestsFromModule(BeautifulSoupTests) - suite.run(result) - if not result.wasSuccessful(): -- print "Unit tests have failed!" -+ print("Unit tests have failed!") - for l in result.errors, result.failures: - for case, error in l: -- print "-" * 80 -+ print("-" * 80) - desc = case.shortDescription() - if desc: -- print desc -- print error -- print '''If you see an error like: "'ascii' codec can't encode character...", see\nthe Beautiful Soup documentation:\n http://www.crummy.com/software/BeautifulSoup/documentation.html#Why%20can't%20Beautiful%20Soup%20print%20out%20the%20non-ASCII%20characters%20I%20gave%20it?''' -- print "This might or might not be a problem depending on what you plan to do with\nBeautiful Soup." -+ print(desc) -+ print(error) -+ print('''If you see an error like: "'ascii' codec can't encode character...", see\nthe Beautiful Soup documentation:\n http://www.crummy.com/software/BeautifulSoup/documentation.html#Why%20can't%20Beautiful%20Soup%20print%20out%20the%20non-ASCII%20characters%20I%20gave%20it?''') -+ print("This might or might not be a problem depending on what you plan to do with\nBeautiful Soup.") - if sys.argv[1] == 'sdist': -- print -- print "I'm not going to make a source distribution since the tests don't pass." -+ print() -+ print("I'm not going to make a source distribution since the tests don't pass.") - sys.exit(1) - - setup(name="BeautifulSoup", diff --git a/dev-python/beautifulsoup/files/bfs-4.2.0-no-lxml.patch b/dev-python/beautifulsoup/files/bfs-4.2.0-no-lxml.patch new file mode 100644 index 000000000000..75ae98b1ef45 --- /dev/null +++ b/dev-python/beautifulsoup/files/bfs-4.2.0-no-lxml.patch @@ -0,0 +1,67 @@ +=== modified file 'bs4/testing.py' +--- bs4/testing.py 2013-05-07 12:19:02 +0000 ++++ bs4/testing.py 2013-05-20 13:19:16 +0000 +@@ -464,6 +464,18 @@ + self.assertEqual( + soup.encode("utf-8"), markup) + ++ def test_formatter_processes_script_tag_for_xml_documents(self): ++ doc = """ ++ <script type="text/javascript"> ++ </script> ++""" ++ soup = BeautifulSoup(doc, "xml") ++ # lxml would have stripped this while parsing, but we can add ++ # it later. ++ soup.script.string = 'console.log("< < hey > > ");' ++ encoded = soup.encode() ++ self.assertTrue(b"< < hey > >" in encoded) ++ + def test_popping_namespaced_tag(self): + markup = '<rss xmlns:dc="foo"><dc:creator>b</dc:creator><dc:date>2012-07-02T20:33:42Z</dc:date><dc:rights>c</dc:rights><image>d</image></rss>' + soup = self.soup(markup) + +=== modified file 'bs4/tests/test_lxml.py' +--- bs4/tests/test_lxml.py 2013-05-09 19:36:30 +0000 ++++ bs4/tests/test_lxml.py 2013-05-20 13:19:16 +0000 +@@ -10,6 +10,7 @@ + LXML_VERSION = lxml.etree.LXML_VERSION + except ImportError, e: + LXML_PRESENT = False ++ LXML_VERSION = (0,) + + from bs4 import ( + BeautifulSoup, +@@ -47,7 +48,7 @@ + # test if an old version of lxml is installed. + + @skipIf( +- LXML_VERSION < (2,3,5,0), ++ not LXML_PRESENT or LXML_VERSION < (2,3,5,0), + "Skipping doctype test for old version of lxml to avoid segfault.") + def test_empty_doctype(self): + soup = self.soup("<!DOCTYPE>") + +=== modified file 'bs4/tests/test_tree.py' +--- bs4/tests/test_tree.py 2013-05-14 12:39:16 +0000 ++++ bs4/tests/test_tree.py 2013-05-20 13:19:16 +0000 +@@ -1344,18 +1344,6 @@ + encoded = BeautifulSoup(doc).encode() + self.assertTrue(b"< < hey > >" in encoded) + +- def test_formatter_processes_script_tag_for_xml_documents(self): +- doc = """ +- <script type="text/javascript"> +- </script> +-""" +- soup = BeautifulSoup(doc, "xml") +- # lxml would have stripped this while parsing, but we can add +- # it later. +- soup.script.string = 'console.log("< < hey > > ");' +- encoded = soup.encode() +- self.assertTrue(b"< < hey > >" in encoded) +- + def test_prettify_leaves_preformatted_text_alone(self): + soup = self.soup("<div> foo <pre> \tbar\n \n </pre> baz ") + # Everything outside the <pre> tag is reformatted, but everything + diff --git a/dev-python/beautifulsoup/metadata.xml b/dev-python/beautifulsoup/metadata.xml index 236732af0c82..d0eccb96021d 100644 --- a/dev-python/beautifulsoup/metadata.xml +++ b/dev-python/beautifulsoup/metadata.xml @@ -13,4 +13,7 @@ <upstream> <remote-id type="pypi">beautifulsoup4</remote-id> </upstream> + <use> + <flag name='lxml'>An optional serialiser</flag> + </use> </pkgmetadata> |