RomanNum3ral
/
scrapy
mirror of https://github.com/scrapy/scrapy.git
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity

Rename "regexp" prefix to "re"

This commit is contained in:
Paul Tremberth 2014-01-15 15:00:25 +01:00
parent 88c8a523a7
commit 827c0cf51f
3 changed files with 13 additions and 13 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
docs/topics/selectors.rst
View File

@ -250,7 +250,7 @@ and come with these pre-registered namespaces to use in XPath expressions:
====== ==================================== =======================
prefix namespace usage
====== ==================================== =======================
regexp http://exslt.org/regular-expressions `regular expressions`_
re http://exslt.org/regular-expressions `regular expressions`_
set http://exslt.org/sets `set manipulation`_
====== ==================================== =======================
@ -276,7 +276,7 @@ Example selecting links in list item with a "class" attribute ending with a digi
>>> sel = Selector(text=doc, type="html")
>>> sel.xpath('//li//@href').extract()
[u'link1.html', u'link2.html', u'link3.html', u'link4.html', u'link5.html']
>>> sel.xpath('//li[regexp:test(@class, "item-\d$")]//@href').extract()
>>> sel.xpath('//li[re:test(@class, "item-\d$")]//@href').extract()
[u'link1.html', u'link2.html', u'link4.html', u'link5.html']
>>>

2
scrapy/selector/unified.py
View File

@ -47,7 +47,7 @@ class Selector(object_ref):
_default_type = None
_default_namespaces = {
"regexp": "http://exslt.org/regular-expressions",
"re": "http://exslt.org/regular-expressions",
# supported in libxslt:
# set:difference

20
scrapy/tests/test_selector.py
View File

@ -352,36 +352,36 @@ class ExsltTestCase(unittest.TestCase):
response = TextResponse(url="http://example.com", body=body)
sel = self.sscls(response)
# regexp:test()
# re:test()
self.assertEqual(
sel.xpath(
'//input[regexp:test(@name, "[A-Z]+", "i")]').extract(),
[x.extract() for x in sel.xpath('//input[regexp:test(@name, "[A-Z]+", "i")]')])
'//input[re:test(@name, "[A-Z]+", "i")]').extract(),
[x.extract() for x in sel.xpath('//input[re:test(@name, "[A-Z]+", "i")]')])
self.assertEqual(
[x.extract()
for x in sel.xpath(
'//a[regexp:test(@href, "\.html$")]/text()')],
'//a[re:test(@href, "\.html$")]/text()')],
[u'first link', u'second link'])
self.assertEqual(
[x.extract()
for x in sel.xpath(
'//a[regexp:test(@href, "first")]/text()')],
'//a[re:test(@href, "first")]/text()')],
[u'first link'])
self.assertEqual(
[x.extract()
for x in sel.xpath(
'//a[regexp:test(@href, "second")]/text()')],
'//a[re:test(@href, "second")]/text()')],
[u'second link'])
# regexp:match() is rather special: it returns a node-set of <match> nodes
# re:match() is rather special: it returns a node-set of <match> nodes
#[u'<match>http://www.bayes.co.uk/xml/index.xml?/xml/utils/rechecker.xml</match>',
#u'<match>http</match>',
#u'<match>www.bayes.co.uk</match>',
#u'<match></match>',
#u'<match>/xml/index.xml?/xml/utils/rechecker.xml</match>']
self.assertEqual(
sel.xpath('regexp:match(//a[regexp:test(@href, "\.xml$")]/@href,'
sel.xpath('re:match(//a[re:test(@href, "\.xml$")]/@href,'
'"(\w+):\/\/([^/:]+)(:\d*)?([^# ]*)")/text()').extract(),
[u'http://www.bayes.co.uk/xml/index.xml?/xml/utils/rechecker.xml',
u'http',
@ -391,9 +391,9 @@ class ExsltTestCase(unittest.TestCase):
# regexp:replace()
# re:replace()
self.assertEqual(
sel.xpath('regexp:replace(//a[regexp:test(@href, "\.xml$")]/@href,'
sel.xpath('re:replace(//a[re:test(@href, "\.xml$")]/@href,'
'"(\w+)://(.+)(\.xml)", "","https://\\2.html")').extract(),
[u'https://www.bayes.co.uk/xml/index.xml?/xml/utils/rechecker.html'])