def extract_uitspraak(ruling_tree):
from lxml.etree import XPath
xpath_strs = [
"/open-rechtspraak/rvr:uitspraak/rvr:section//rvr:*/text()[contains(., 'DE UITSPRAAK')]/"
"ancestor::rvr:section/descendant-or-self::text() | "
"/open-rechtspraak/rvr:uitspraak/rvr:section//rvr:*/text()[contains(., 'DE UITSPRAAK')]/"
"ancestor::rvr:section/following-sibling::rvr:section/descendant-or-self::text()",
'/open-rechtspraak/rvr:uitspraak/rvr:section[@role="beslissing"][last()]/descendant-or-self::text()',
"/open-rechtspraak/rvr:uitspraak/rvr:section/rvr:title/text()[contains(., 'eslissing')][last()]//"
"ancestor::rvr:section/descendant-or-self::text()"
]
xpaths = (XPath(
xpath_str, namespaces=NAMESPACE_PREFIX_MAP)
for xpath_str in xpath_strs)
items = tuple('\n'.join(xpath(ruling_tree)) for xpath in xpaths)
if len(items) >= 1:
if len(items) <= 3:
return filter_out_wijzers(
clean(items[0])) # TODO: if != '' ; precedence of XPaths
elif len(items) > 3:
assert False
else:
return None
def extract_standpunt_adv(ruling_tree):
from lxml.etree import XPath
xpath_strs = [
"/open-rechtspraak/rvr:uitspraak/rvr:section//rvr:parablock/rvr:para/"
"descendant-or-self::*[contains(text(), 'standpunt van de verdediging')]/"
"ancestor::rvr:para/following-sibling::rvr:para/text()",
"/open-rechtspraak/rvr:uitspraak/rvr:section//rvr:paragroup/"
"descendant-or-self::*[contains(text(), 'standpunt van de Verdediging') " # TODO: unneeded
"or contains(text(), 'standpunt van de verdediging')"
"or contains(text(), 'standpunt van verdediging')]/" # TODO: unneeded
"parent::*/descendant::rvr:parablock/descendant::*/text()"
] # ,
# "/open-rechtspraak/rvr:uitspraak/rvr:section//rvr:para/"
# "rvr:emphasis[text()='Het standpunt van de verdediging']/"
# "ancestor::rvr:para/following-sibling::rvr:*/text()"]
xpaths = (XPath(
xpath_str, namespaces=NAMESPACE_PREFIX_MAP)
for xpath_str in xpath_strs)
items = tuple('\n'.join(xpath(ruling_tree)) for xpath in xpaths)
if len(items) == 1:
return clean(items[0])
elif len(items) > 1:
assert False
else:
return None
def extract_uitspraak(ruling_tree):
from lxml.etree import XPath
xpath_strs = [
"/open-rechtspraak/rvr:uitspraak/rvr:section//rvr:*/text()[contains(., 'DE UITSPRAAK')]/"
"ancestor::rvr:section/descendant-or-self::text() | "
"/open-rechtspraak/rvr:uitspraak/rvr:section//rvr:*/text()[contains(., 'DE UITSPRAAK')]/"
"ancestor::rvr:section/following-sibling::rvr:section/descendant-or-self::text()",
'/open-rechtspraak/rvr:uitspraak/rvr:section[@role="beslissing"][last()]/descendant-or-self::text()',
"/open-rechtspraak/rvr:uitspraak/rvr:section/rvr:title/text()[contains(., 'eslissing')][last()]//"
"ancestor::rvr:section/descendant-or-self::text()"
]
xpaths = (XPath(xpath_str, namespaces=NAMESPACE_PREFIX_MAP)
for xpath_str in xpath_strs)
items = tuple('\n'.join(xpath(ruling_tree)) for xpath in xpaths)
if len(items) >= 1:
if len(items) <= 3:
return filter_out_wijzers(clean(
items[0])) # TODO: if != '' ; precedence of XPaths
elif len(items) > 3:
assert False
else:
return None
def extract_standpunt_adv(ruling_tree):
from lxml.etree import XPath
xpath_strs = [
"/open-rechtspraak/rvr:uitspraak/rvr:section//rvr:parablock/rvr:para/"
"descendant-or-self::*[contains(text(), 'standpunt van de verdediging')]/"
"ancestor::rvr:para/following-sibling::rvr:para/text()",
"/open-rechtspraak/rvr:uitspraak/rvr:section//rvr:paragroup/"
"descendant-or-self::*[contains(text(), 'standpunt van de Verdediging') " # TODO: unneeded
"or contains(text(), 'standpunt van de verdediging')"
"or contains(text(), 'standpunt van verdediging')]/" # TODO: unneeded
"parent::*/descendant::rvr:parablock/descendant::*/text()"
] # ,
# "/open-rechtspraak/rvr:uitspraak/rvr:section//rvr:para/"
# "rvr:emphasis[text()='Het standpunt van de verdediging']/"
# "ancestor::rvr:para/following-sibling::rvr:*/text()"]
xpaths = (XPath(xpath_str, namespaces=NAMESPACE_PREFIX_MAP)
for xpath_str in xpath_strs)
items = tuple('\n'.join(xpath(ruling_tree)) for xpath in xpaths)
if len(items) == 1:
return clean(items[0])
elif len(items) > 1:
assert False
else:
return None
def extract_tenlastelegging(ruling_tree):
from lxml.etree import XPath
xpaths = (XPath(
"/open-rechtspraak/rvr:uitspraak/rvr:section/rvr:title/"
"descendant-or-self::*/text()[contains(., 'tenlastelegging')]/ancestor::rvr:section"
"//*[not(local-name()='nr')]/text()",
namespaces=NAMESPACE_PREFIX_MAP), )
items = tuple('\n'.join(xpath(ruling_tree)) for xpath in xpaths)
if len(items) == 1:
return clean(items[0])
else:
return None
def extract_tenlastelegging(ruling_tree):
from lxml.etree import XPath
xpaths = (XPath(
"/open-rechtspraak/rvr:uitspraak/rvr:section/rvr:title/"
"descendant-or-self::*/text()[contains(., 'tenlastelegging')]/ancestor::rvr:section"
"//*[not(local-name()='nr')]/text()",
namespaces=NAMESPACE_PREFIX_MAP), )
items = tuple('\n'.join(xpath(ruling_tree)) for xpath in xpaths)
if len(items) == 1:
return clean(items[0])
else:
return None
def extract_standpunt_ovj(ruling_tree):
from lxml.etree import XPath
xpath_strs = (
"/open-rechtspraak/rvr:uitspraak/rvr:section//rvr:parablock/rvr:para/"
"descendant-or-self::*[contains(text(), 'standpunt van de officier van justitie') "
"or contains(text(), 'standpunt van de officieren van justitie') "
"or contains(text(), 'standpunt van het Openbaar Ministerie') "
"or contains(text(), 'standpunt van het openbaar ministerie')]/"
"ancestor::rvr:para/following-sibling::rvr:para/text() | "
"/open-rechtspraak/rvr:uitspraak/rvr:section//rvr:para/rvr:emphasis/"
"descendant-or-self::*/text()[contains(., ' eis van de officier van justitie') or "
"contains(., ' eis van de officieren van justitie')]/"
"ancestor::rvr:para/following-sibling::rvr:para/text()",
"/open-rechtspraak/rvr:uitspraak/rvr:section//rvr:paragroup/"
"descendant-or-self::*[contains(text(), 'standpunt van de officier van justitie') "
"or contains(text(), 'standpunt van de officieren van justitie') "
"or contains(text(), 'standpunt van het Openbaar Ministerie') "
"or contains(text(), 'standpunt van het openbaar ministerie')]/"
"parent::*/descendant::rvr:parablock/descendant::*/text()",
"/open-rechtspraak/rvr:uitspraak/rvr:section//rvr:para/" # TODO: remove, strafoplegging != bewijs
"rvr:emphasis[text()='De vordering van de officier van justitie' or "
"text()='De vordering van de officieren van justitie']/"
"ancestor::rvr:para/following-sibling::rvr:*/text()" # ,
# "/open-rechtspraak/rvr:uitspraak/rvr:section/rvr:parablock/rvr:para/rvr:emphasis"
, )
xpaths = (XPath(
xpath_str, namespaces=NAMESPACE_PREFIX_MAP)
for xpath_str in xpath_strs)
items = tuple('\n'.join(xpath(ruling_tree)) for xpath in xpaths)
if len(items) > 0:
if len(items) <= 2:
return clean(items[0])
elif len(items) > 2:
assert False
else:
return None
def extract_standpunt_ovj(ruling_tree):
from lxml.etree import XPath
xpath_strs = (
"/open-rechtspraak/rvr:uitspraak/rvr:section//rvr:parablock/rvr:para/"
"descendant-or-self::*[contains(text(), 'standpunt van de officier van justitie') "
"or contains(text(), 'standpunt van de officieren van justitie') "
"or contains(text(), 'standpunt van het Openbaar Ministerie') "
"or contains(text(), 'standpunt van het openbaar ministerie')]/"
"ancestor::rvr:para/following-sibling::rvr:para/text() | "
"/open-rechtspraak/rvr:uitspraak/rvr:section//rvr:para/rvr:emphasis/"
"descendant-or-self::*/text()[contains(., ' eis van de officier van justitie') or "
"contains(., ' eis van de officieren van justitie')]/"
"ancestor::rvr:para/following-sibling::rvr:para/text()",
"/open-rechtspraak/rvr:uitspraak/rvr:section//rvr:paragroup/"
"descendant-or-self::*[contains(text(), 'standpunt van de officier van justitie') "
"or contains(text(), 'standpunt van de officieren van justitie') "
"or contains(text(), 'standpunt van het Openbaar Ministerie') "
"or contains(text(), 'standpunt van het openbaar ministerie')]/"
"parent::*/descendant::rvr:parablock/descendant::*/text()",
"/open-rechtspraak/rvr:uitspraak/rvr:section//rvr:para/" # TODO: remove, strafoplegging != bewijs
"rvr:emphasis[text()='De vordering van de officier van justitie' or "
"text()='De vordering van de officieren van justitie']/"
"ancestor::rvr:para/following-sibling::rvr:*/text()" # ,
# "/open-rechtspraak/rvr:uitspraak/rvr:section/rvr:parablock/rvr:para/rvr:emphasis"
,
)
xpaths = (XPath(xpath_str, namespaces=NAMESPACE_PREFIX_MAP)
for xpath_str in xpath_strs)
items = tuple('\n'.join(xpath(ruling_tree)) for xpath in xpaths)
if len(items) > 0:
if len(items) <= 2:
return clean(items[0])
elif len(items) > 2:
assert False
else:
return None