def test_more(self):
from ferenda import DocumentRepository
d = DocumentRepository()
rows = [{
'uri': 'http://ex.org/1',
'dcterms_title': 'Abc',
'dcterms_issued': '2009-04-02'
}, {
'uri': 'http://ex.org/2',
'dcterms_title': 'Abcd',
'dcterms_issued': '2010-06-30'
}, {
'uri': 'http://ex.org/3',
'dcterms_title': 'Dfg',
'dcterms_issued': '2010-08-01'
}]
from rdflib.namespace import DCTERMS
facets = [Facet(DCTERMS.title), Facet(DCTERMS.issued)]
pagesets = d.toc_pagesets(rows, facets)
expected = {
('dcterms_title', 'a'): [[Link('Abc', uri='http://ex.org/1')],
[Link('Abcd', uri='http://ex.org/2')]],
('dcterms_title', 'd'): [[Link('Dfg', uri='http://ex.org/3')]],
('dcterms_issued', '2009'): [[Link('Abc', uri='http://ex.org/1')]],
('dcterms_issued', '2010'): [[Link('Abcd', uri='http://ex.org/2')],
[Link('Dfg', uri='http://ex.org/3')]]
}
got = d.toc_select_for_pages(rows, pagesets, facets)
self.assertEqual(expected, got)
def remove_rootsegments(item, rootsegments):
linktext = str(item[0])
prefix = "»".join(rootsegments)
assert linktext.startswith(
prefix), "Tried to remove prefix %s from %s" % (prefix,
linktext)
prefixlen = len(prefix)
if prefixlen:
prefixlen += 1 # removes extra "»", but not if rootsegments is empty
if linktext[prefixlen:]:
return [Link(linktext[prefixlen:], uri=item[0].uri)]
else:
return []
def toc_generate_page_body(self, documentlist, nav):
# move documentlist into a ordereddict keyed on url,
# concatenating rpubl_konsolideringsunderlag as we go
documents = OrderedDict()
# make sure all rpubl:KonsolideradGrundforfattning comes first in the list
for row in documentlist:
row = dict(row)
if row['rdf_type'] == str(RPUBL.KonsolideradGrundforfattning):
if row['uri'] not in documents:
documents[row['uri']] = row
# transform single value to a list, so we can
# append more if other rows are about the same
# rpubl:KonsolideradGrundforfattning
row['rpubl_konsolideringsunderlag'] = [
row['rpubl_konsolideringsunderlag']
]
else:
documents[
row['uri']]['rpubl_konsolideringsunderlag'].append(
row['rpubl_konsolideringsunderlag'])
# then the rest
for row in documentlist:
if row['rdf_type'] != str(RPUBL.KonsolideradGrundforfattning):
documents[row['uri']] = row
# now that we have all documents, check if some of them change
# some other of them
for uri in list(documents):
row = documents[uri]
if 'rpubl_andrar' in row:
if row['rpubl_andrar'] not in documents:
self.log.warning(
"%(uri)s: changes %(rpubl_andrar)s, but that doc doesn't exist"
% row)
continue
if 'andras_av' not in documents[row['rpubl_andrar']]:
documents[row['rpubl_andrar']]['andras_av'] = []
documents[row['rpubl_andrar']]['andras_av'].insert(0, uri)
documents.move_to_end(uri)
dl = html.DL(role='main')
for uri in list(documents):
if uri not in documents:
continue # we must have removed it earlier in the loop
row = documents[uri]
label = row.get('dcterms_title',
row.get('dcterms_identifier', '(Titel saknas)'))
if row['dcterms_identifier'] not in label:
label = "%s: %s" % (row['dcterms_identifier'], label)
# in most cases we want to link this thing, but not if
# this is the base act of a non-consolidated act (we link
# to it in the DD element below instead)
if (row['rdf_type'] == str(RPUBL.KonsolideradGrundforfattning)
or 'andras_av' not in row):
label = Link(label, uri=uri)
dl.append(html.DT([label]))
# groups of base+change acts may be present wether we have
# consolidated acts or not, and they might be grouped a
# little differently, but we need to do the same things
# with them.
relevant_docs = []
if row['rdf_type'] == str(RPUBL.KonsolideradGrundforfattning):
relevant_docs = row['rpubl_konsolideringsunderlag']
elif 'andras_av' in row:
relevant_docs = [uri] + row['andras_av']
if relevant_docs:
fs = []
for f in relevant_docs:
if f in documents:
fs.append(
Link(documents[f]['dcterms_identifier'],
uri=documents[f]['uri']))
fs.append(", ")
del documents[f]
if fs:
dl.append(
html.DD(
["Grund- och ändringsförfattningar: ", *fs[:-1]]))
return Body([nav, dl])
def toc_item(self, binding, row):
# note: look at binding to determine which pageset is being
# constructed in case you want to present documents in
# different ways depending on that.
from ferenda.elements import Link
return [row['identifier'] + ": ", Link(row['title'], uri=row['uri'])]
class TOC(RepoTester):
results1 = json.load(open("test/files/datasets/results1.json"))
results2 = json.load(open("test/files/datasets/results2.json"))
results2data = Graph().parse(open("test/files/datasets/results2data.ttl"),
format="turtle")
pagesets = [
TocPageset('Sorted by title', [
TocPage('a', 'Documents starting with "a"', 'dcterms_title', 'a'),
TocPage('d', 'Documents starting with "d"', 'dcterms_title', 'd'),
TocPage('h', 'Documents starting with "h"', 'dcterms_title', 'h'),
TocPage('l', 'Documents starting with "l"', 'dcterms_title', 'l')
], DCTERMS.title),
TocPageset('Sorted by publication year', [
TocPage('1791', 'Documents published in 1791', 'dcterms_issued',
'1791'),
TocPage('1859', 'Documents published in 1859', 'dcterms_issued',
'1859'),
TocPage('1937', 'Documents published in 1937', 'dcterms_issued',
'1937'),
TocPage('1939', 'Documents published in 1939', 'dcterms_issued',
'1939'),
TocPage('1943', 'Documents published in 1943', 'dcterms_issued',
'1943'),
TocPage('1954', 'Documents published in 1954', 'dcterms_issued',
'1954')
], DCTERMS.issued)
]
pagesets2 = [
TocPageset('Sorted by publisher', [
TocPage('Analytical Biochemistry',
'Documents published in Analytical Biochemistry',
'dcterms_publisher', 'analytical'),
TocPage('Journal of Biological Chemistry',
'Documents published in Journal of Biological Chemistry',
'dcterms_publisher', 'biochem'),
TocPage('Nature', 'Documents published in Nature',
'dcterms_publisher', 'nature'),
], DCTERMS.publisher)
]
documentlists = {
('dcterms_issued', '1791'): [[
Link("Dream of the Red Chamber",
uri='http://example.org/books/Dream_of_the_Red_Chamber')
]],
('dcterms_issued', '1859'): [[
Link("A Tale of Two Cities",
uri='http://example.org/books/A_Tale_of_Two_Cities')
]],
('dcterms_issued', '1937'):
[[Link("The Hobbit", uri='http://example.org/books/The_Hobbit')]],
('dcterms_issued', '1939'): [[
Link("And Then There Were None",
uri='http://example.org/books/And_Then_There_Were_None')
]],
('dcterms_issued', '1943'): [[
Link("The Little Prince",
uri='http://example.org/books/The_Little_Prince')
]],
('dcterms_issued', '1954'): [[
Link("The Lord of the Rings",
uri='http://example.org/books/The_Lord_of_the_Rings')
]],
('dcterms_title', 'a'):
[[
Link("And Then There Were None",
uri='http://example.org/books/And_Then_There_Were_None')
],
[
Link("A Tale of Two Cities",
uri='http://example.org/books/A_Tale_of_Two_Cities')
]],
('dcterms_title', 'd'): [[
Link("Dream of the Red Chamber",
uri='http://example.org/books/Dream_of_the_Red_Chamber')
]],
('dcterms_title', 'h'):
[[Link("The Hobbit", uri='http://example.org/books/The_Hobbit')]],
('dcterms_title', 'l'):
[[
Link("The Little Prince",
uri='http://example.org/books/The_Little_Prince')
],
[
Link("The Lord of the Rings",
uri='http://example.org/books/The_Lord_of_the_Rings')
]]
}
facets = [
Facet(rdftype=RDF.type),
Facet(rdftype=DCTERMS.title),
Facet(rdftype=DCTERMS.issued)
]
def setUp(self):
super(TOC, self).setUp()
resources = self.datadir + os.sep + "rsrc" + os.sep + "resources.xml"
util.ensure_dir(resources)
shutil.copy2(
"%s/files/base/rsrc/resources.xml" % os.path.dirname(__file__),
resources)
def tearDown(self):
# make sure self.repo is always newly initialized, not reused
super(TOC, self).tearDown()
if hasattr(TOC, 'repo'):
delattr(TOC, 'repo')
def test_toc(self):
# tests the main TOC method, not the helper methods (they are
# tested separately)
self.repo.facets = MagicMock()
self.repo.facet_select = MagicMock()
self.repo.facet_query = MagicMock()
self.repo.faceted_data = MagicMock()
self.repo.log = Mock()
self.repo.toc_pagesets = Mock()
self.repo.toc_select_for_pages = Mock()
self.repo.toc_generate_pages = Mock()
self.repo.toc_generate_first_page = Mock()
with patch('json.dump'):
self.repo.toc()
# assert facet_query was properly called, error and info msg
# was printed
self.assertEqual("http://*****:*****@rel='stylesheet']")
self.assertEqual(len(css), 3) # bootstrap, ferenda and sfs (?!)
self.assertRegex(css[2].get('href'), '^../../../rsrc/css')
# 2.2 JS links, relativized correctly?
js = t.findall("body/script")
self.assertEqual(len(js),
5) # jquery, bootstrap, hammer, typeahead, ferenda
self.assertRegex(js[4].get('src'), '^../../../rsrc/js')
# 2.3 <nav id="toc"> correct (c.f 1.2)
navlinks = t.findall(".//nav[@id='toc']//li/a")
self.assertEqual(len(navlinks), 9)
self.assertEqual(navlinks[0].get("href"),
'http://*****:*****@class='main-container']/article (c.f 1.3)
docs = t.findall(".//ul[@role='main']/li/a")
self.assertEqual(len(docs), 2)
# "And..." should go before "A Tale..."
self.assertEqual(docs[0].text, 'And Then There Were None')
self.assertEqual(docs[0].attrib['href'],
'http://example.org/books/And_Then_There_Were_None')
# 2.5 site name correct
header = t.find(".//div[@class='navbar-header']/a")
self.assertEqual(header.text, 'testsite')
# 2.6 main article header correct?
header = t.find(".//article/h1")
self.assertEqual(header.text, 'Documents starting with "a"')
def test_generate_page_staticsite(self):
self.repo.config.staticsite = True
self.repo.config.removeinvalidlinks = False
path = self.repo.toc_generate_page(
'dcterms_title', 'a', self.documentlists[('dcterms_title', 'a')],
self.pagesets)
t = etree.parse(path)
# TOC link should be relativized
navlinks = t.findall(".//nav[@id='toc']//li/a")
self.assertEqual('d.html', navlinks[0].get("href"))
self.assertEqual('../dcterms_issued/1791.html',
navlinks[3].get("href"))
header = t.find(".//div[@class='navbar-header']/a")
# from /base/toc/title/a.html -> /index.html = 3 levels up
self.assertEqual('../../../index.html', header.get("href"))
headernavlinks = t.findall(".//ul[@class='nav navbar-nav']/li/a")
self.assertEqual('../index.html', headernavlinks[0].get("href"))
# docs (which in this case use non-base-repo-contained URIs, should be unaffected
docs = t.findall(".//ul[@role='main']/li/a")
self.assertEqual('http://example.org/books/And_Then_There_Were_None',
docs[0].get("href"))
self.repo.config.removeinvalidlinks = True
def test_generate_pages(self):
paths = self.repo.toc_generate_pages(self.documentlists, self.pagesets)
self.assertEqual(len(paths), 10)
#print("=============%s====================" % paths[0])
#with open(paths[0]) as fp:
# print(fp.read())
for path in paths:
self.assertTrue(os.path.exists(path))
def test_generate_first_page(self):
path = self.repo.toc_generate_first_page(self.documentlists,
self.pagesets)
self.assertEqual(path, self.p("base/toc/index.html"))
self.assertTrue(os.path.exists(path))
tree = etree.parse(path)
# check content of path, particularly that css/js refs
# and pageset links are correct. Also, that the selected
# indexpage is indeed the first (eg. title/a)
# (NOTE: the first page in the first pageset (by title/a) isn't linked. The second one (by title/d) is).
self.assertEqual(
"http://*****:*****@id='toc']").findall(".//a")[0].get("href"))
self.assertEqual(
"https://maxcdn.bootstrapcdn.com/bootstrap/3.3.7/css/bootstrap.min.css",
tree.find(".//link").get("href"))
self.assertEqual('Documents starting with "a"',
tree.find(".//article/h1").text)
def test_more(self):
from ferenda import DocumentRepository
d = DocumentRepository()
rows = [{
'uri': 'http://ex.org/1',
'dcterms_title': 'Abc',
'dcterms_issued': '2009-04-02'
}, {
'uri': 'http://ex.org/2',
'dcterms_title': 'Abcd',
'dcterms_issued': '2010-06-30'
}, {
'uri': 'http://ex.org/3',
'dcterms_title': 'Dfg',
'dcterms_issued': '2010-08-01'
}]
from rdflib.namespace import DCTERMS
facets = [Facet(DCTERMS.title), Facet(DCTERMS.issued)]
pagesets = d.toc_pagesets(rows, facets)
expected = {
('dcterms_title', 'a'): [[Link('Abc', uri='http://ex.org/1')],
[Link('Abcd', uri='http://ex.org/2')]],
('dcterms_title', 'd'): [[Link('Dfg', uri='http://ex.org/3')]],
('dcterms_issued', '2009'): [[Link('Abc', uri='http://ex.org/1')]],
('dcterms_issued', '2010'): [[Link('Abcd', uri='http://ex.org/2')],
[Link('Dfg', uri='http://ex.org/3')]]
}
got = d.toc_select_for_pages(rows, pagesets, facets)
self.assertEqual(expected, got)
def test_link(self):
x = Link("Link text", uri="http://example.org/")
self.assertEqual(str(x), "Link text")
self.assertEqual(repr(x), "Link('Link text', uri=http://example.org/)")
# -*- coding: utf-8 -*-
from __future__ import unicode_literals
# begin
from ferenda import CitationParser, URIFormatter, citationpatterns, uriformats
from ferenda.elements import Link
citparser = CitationParser()
citparser.add_grammar(citationpatterns.url)
formatter = URIFormatter(("url", uriformats.url))
res = []
text = "An example: http://example.org/. That is all."
for node in citparser.parse_string(text):
if isinstance(node, str):
# non-linked text, add and continue
res.append(node)
if isinstance(node, tuple):
(text, match) = node
uri = formatter.format(match)
if uri:
res.append(Link(uri, text, rel="dcterms:references"))
# end
return_value = True
def makeitem(self, text):
return [
Link(text,
uri="https://lagen.nu/begrepp/" +
text.replace("»", "//").replace(" ", "_"))
]
def toc_item(self, binding, row):
return [
row['dcterms_identifier'] + ": ",
Link(row['dcterms_title'], uri=row['uri'])
]
def toc_item(self, binding, row):
from ferenda.elements import Link
return [
row['dcterms_identifier'] + ": ",
Link(row['dcterms_title'], uri=row['uri'])
]