def convert(fp):
rows = csv.reader(fp)
rows.next() # header
root = ET.fromstring('<entities type="federal-body"></entities>')
root.attrib['updated'] = utc.now_isoformat()
for row in rows:
eid, epid, ename, abbr, hist, leader = [
c.decode('cp1252').strip() for c in row
]
entity = ET.SubElement(root, 'entity')
entity.attrib['id'] = "{:0>4s}".format(eid)
if epid:
entity.attrib['parent-id'] = "{:0>4s}".format(epid) if epid else ''
name = ET.SubElement(entity, 'name')
name.set('role', 'official')
name.text = ename
if hist:
name = ET.SubElement(entity, 'name')
name.set('role', 'historical')
name.text = hist
if leader:
name = ET.SubElement(entity, 'name')
name.set('role', 'leadership')
name.text = leader
if abbr:
name = ET.SubElement(entity, 'abbr')
name.text = abbr
return root
def convert(fp):
rows = csv.reader(fp)
rows.next() # header
root = ET.fromstring('<entities type="federal-body"></entities>')
root.attrib['updated'] = utc.now_isoformat()
for row in rows:
eid, epid, ename, abbr, hist, leader = [c.decode('cp1252').strip() for c in row]
entity = ET.SubElement(root, 'entity')
entity.attrib['id'] = "{:0>4s}".format(eid)
if epid:
entity.attrib['parent-id'] = "{:0>4s}".format(epid) if epid else ''
name = ET.SubElement(entity, 'name')
name.set('role', 'official')
name.text = ename
if hist:
name = ET.SubElement(entity, 'name')
name.set('role', 'historical')
name.text = hist
if leader:
name = ET.SubElement(entity, 'name')
name.set('role', 'leadership')
name.text = leader
if abbr:
name = ET.SubElement(entity, 'abbr')
name.text = abbr
return root
def doc2xml(billversions):
billversionET = ET.Element("entities",
type="billversion",
description="Definitions of Common Versions of Bills",
source="http://www.gpo.gov/help/about_congressional_bills.htm",
updated=utc.now_isoformat())
for bill in billversions:
d = bill._asdict()
d['chambers'] = ' '.join(sorted(d['chambers']))
version = d['version']
del d['version']
bv = ET.SubElement(billversionET, 'entity', **d)
ET.SubElement(bv, 'name', role="official").text = version
return billversionET
def convert(infile, outfile):
reader = csv.reader(infile)
reader.next() # discard header
acts = ET.Element('entities', type="act", updated=utc.now_isoformat())
for row in reader:
row = [c.decode('CP1252').strip() for c in row]
row = map(normalize_name, row)
act = ET.SubElement(acts, 'entity', id=row[0])
name = ET.SubElement(act, 'name')
name.text = row[0]
for extraname in row[2:]:
if extraname:
name = ET.SubElement(act, 'name')
name.text = extraname
lookup = ET.ElementTree(acts)
lookup.write(outfile, encoding="utf-8")
def convert(infile, outfile):
reader = csv.reader(infile)
reader.next() # discard header
acts = ET.Element('entities',
type="act",
updated=utc.now_isoformat()
)
for row in reader:
row = [c.decode('CP1252').strip() for c in row]
row = map(normalize_name, row)
act = ET.SubElement(acts, 'entity', id=row[0])
name = ET.SubElement(act, 'name')
name.text = row[0]
for extraname in row[2:]:
if extraname:
name = ET.SubElement(act, 'name')
name.text = extraname
lookup = ET.ElementTree(acts)
lookup.write(outfile, encoding="utf-8")
