def load_moby(self):
import shakespeare.model as model
pkg = 'shksprdata'
fileobj = pkg_resources.resource_stream(pkg, '/moby/metadata.txt')
def norm_work_name(out):
out = out.replace('_moby', '')
out = out.replace('life_and_death_of_king_john', 'john')
out = out.replace('labor', 'labour')
out = out.replace('part_iii', 'part_3')
out = out.replace('part_ii', 'part_2')
out = out.replace('part_i', 'part_1')
return out
material = model.load_material(fileobj, norm_work_name=norm_work_name)
for item in material:
if not item.resources:
model.Resource(
locator_type=u'cache',
locator='moby/html/%s.html' % item.name,
format=u'html',
material=item,
)
model.Resource(
locator_type=u'cache',
locator=u'moby/pdf/%s.pdf' % item.name,
format=u'pdf',
material=item,
)
model.Session.commit()
def load_moby(self):
import shakespeare.model as model
pkg = 'shksprdata'
fileobj = pkg_resources.resource_stream(pkg, '/moby/metadata.txt')
def norm_work_name(out):
out = out.replace('_moby', '')
out = out.replace('life_and_death_of_king_john', 'john')
out = out.replace('labor', 'labour')
out = out.replace('part_iii', 'part_3')
out = out.replace('part_ii', 'part_2')
out = out.replace('part_i', 'part_1')
return out
material = model.load_material(fileobj, norm_work_name=norm_work_name)
for item in material:
if not item.resources:
model.Resource(
locator_type=u'cache',
locator='moby/html/%s.html' % item.name,
format=u'html',
material=item,
)
model.Resource(
locator_type=u'cache',
locator=u'moby/pdf/%s.pdf' % item.name,
format=u'pdf',
material=item,
)
model.Session.commit()
def load_gutenberg(self):
import shakespeare.model as model
pkg = 'shksprdata'
fileobj = pkg_resources.resource_stream(pkg, '/gutenberg/metadata.txt')
def norm_work_name(out):
if out.endswith('_f'):
out = out[:-2]
out = out.replace('_gut', '')
out = out.replace('anthonie', 'antony')
out = out.replace('errours', 'errors')
out = out.replace('all_is', "alls")
out = out.replace('loves_labour_', 'loves_labours_')
out = out.replace('dreame', 'dream')
out = out.replace('twelfe-', 'twelfth_')
out = out.replace('tragedy_of_', '')
return out
material = model.load_material(fileobj, norm_work_name=norm_work_name)
for item in material:
if not item.resources:
locator = u'%s::/gutenberg/%s.txt' % (pkg, item.name)
res = model.Resource(
locator_type=u'package',
locator=locator,
format=u'txt',
material=item,
)
model.Session.commit()
def load_gutenberg(self):
import shakespeare.model as model
pkg = 'shksprdata'
fileobj = pkg_resources.resource_stream(pkg, '/gutenberg/metadata.txt')
def norm_work_name(out):
if out.endswith('_f'):
out = out[:-2]
out = out.replace('_gut', '')
out = out.replace('anthonie', 'antony')
out = out.replace('errours', 'errors')
out = out.replace('all_is', "alls")
out = out.replace('loves_labour_', 'loves_labours_')
out = out.replace('dreame', 'dream')
out = out.replace('twelfe-', 'twelfth_')
out = out.replace('tragedy_of_', '')
return out
material = model.load_material(fileobj, norm_work_name=norm_work_name)
for item in material:
if not item.resources:
locator = u'%s::/gutenberg/%s.txt' % (pkg, item.name)
res = model.Resource(
locator_type=u'package',
locator=locator,
format=u'txt',
material=item,
)
model.Session.commit()
