def parse():
"""
Parses data directory for citations.
"""
data = parser.search_report_data()
for report in data:
for entry in report:
base_patent = entry['patnum_root']
parse_csv(config.data_dir + '/' + base_patent + '/' + base_patent + '.export.csv')
def lines(patnum, pdf):
filename = pdf.replace(".pdf", ".txt")
data = parser.search_report_data(config.data_dir + patnum, filename)
lines = []
for reportfile in data:
for entry in reportfile:
line = entry['country'] + '.' + entry['patnum'] + '.' + entry['kindcode']
if _has_xml(patnum, entry['country'] + '.' + entry['patnum']):
line += ' <span class="xml-available">(XML available)</span>'
lines.append(line)
for ref in entry['refs']:
lines.append(ref)
return dict(references=lines, patnum=patnum)
def parse(epo = False, bz2 = False, clef=False):
data = parser.search_report_data()
for report in data:
for entry in report:
cited_patent = entry['country'] + '.' + entry['patnum']
base_patent = entry['patnum_root']
if bz2:
download_from_bz2_marec(base_patent, cited_patent)
elif epo:
download_from_epo(base_patent, cited_patent)
elif clef:
download_from_clef(base_patent, cited_patent)
else:
download_from_marec(base_patent, cited_patent)
def scan(restrict, restrict_cited):
"""
Scan data dir for search reports and parses them for
citations.
"""
data = parser.search_report_data()
for report in data:
for entry in report:
refs = entry['refs']
doc = entry['country'] + "." + entry['patnum']
patnum = entry['patnum_root']
if restrict and patnum != restrict:
continue
for ref in refs:
if ref:
if restrict_cited and doc != restrict_cited:
continue
print "processing ", patnum, doc, ref
process(patnum, doc, ref)
download.get_pdf_page(country, patnum, kindcode, page + offset, target_folder, "column-" + str(column))
return kindcode, startpage
def _get_whitelist():
whitelist = []
try:
for line in open('whitelist.txt', 'r').readlines():
line = line.replace('\n', '')
whitelist.append(line)
except:
whitelist = False
return whitelist
data = parser.search_report_data()
whitelist = _get_whitelist()
open('perf.cited.txt', 'w').write('')
dl = []
for reportfile in data:
for entry in reportfile:
patnum = entry['patnum']
country = entry['country']
to_download = entry['country'] + '.' + patnum
if country == 'WO':
to_download = detected.normalize_wo_patnum(patnum)
from base import parser
testdata = parser.search_report_data('testdata/')
data = parser.search_report_data()
def find(key, value, data):
found = False
for set in data:
if set[key] == value:
found = True
return found
for set in testdata:
for property in set:
patnum = property['patnum']
country = property['country']
kindcode = property['kindcode']
print find('patnum', patnum, set)
print find('country', country, set)
print find('kindcode', kindcode, set)
