Created
January 30, 2018 19:46
-
-
Save tonyb486/9050807f9e09fe1ef15360d34c75eeba to your computer and use it in GitHub Desktop.
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
#!/usr/bin/env python3 | |
import sys, csv, sqlite3 | |
csv.field_size_limit(sys.maxsize) | |
conn = sqlite3.connect("patent.db") | |
cur = conn.cursor() | |
cur.execute('''CREATE TABLE patent | |
(id varchar(20), type varchar(20), number varchar(20), | |
country varchar(20), date date, abstract text, title text, | |
kind varchar(10), num_claims int, filename varchar(120))''') | |
print("Adding patent table...") | |
with open("patent.tsv") as tsvfile: | |
reader = csv.reader(tsvfile, delimiter="\t") | |
for i, row in enumerate(reader): | |
try: cur.execute("INSERT INTO patent VALUES (?, ?, ?, ?, ?, ?, ?, ?, ?, ?)", row) | |
except: print("\nWARNING: Failure with row %d." % i) | |
if i%100000 == 0: | |
sys.stdout.write("\rpatent row: %10d" %i) | |
sys.stdout.flush() | |
conn.commit() | |
print("\nAdding cpc_current table...") | |
cur.execute('''CREATE TABLE cpc_current | |
(uuid varchar(36), patent_id varchar(20), section_id varchar(10), | |
subsection_id varchar(20), group_id varchar(20), subgroup_id varchar(20), | |
category varchar(20), sequence int)''') | |
with open("cpc_current.tsv") as tsvfile: | |
reader = csv.reader(tsvfile, delimiter="\t") | |
for i, row in enumerate(reader): | |
try: cur.execute("INSERT INTO cpc_current VALUES (?, ?, ?, ?, ?, ?, ?, ?)", row) | |
except: print("\nWARNING: Failure with row %d." % i) | |
if i%100000 == 0: | |
sys.stdout.write("\rcpc_current row: %10d" %i) | |
sys.stdout.flush() | |
conn.commit() | |
print("\nComplete.") | |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment