From daccbbd9c73a5292ea9d6746560d7009e5aa666d Mon Sep 17 00:00:00 2001 From: Terry Truong Date: Wed, 7 Sep 2022 11:37:37 +1000 Subject: Add python type annotations Also use consistent quote symbols Also use 'is None' instead of '== None' Also use 'if list1' instead of 'if len(list1) > 0' --- backend/tolData/eol/genImagesListDb.py | 28 ++++++++++++++-------------- 1 file changed, 14 insertions(+), 14 deletions(-) (limited to 'backend/tolData/eol/genImagesListDb.py') diff --git a/backend/tolData/eol/genImagesListDb.py b/backend/tolData/eol/genImagesListDb.py index 4dcb6d9..808292d 100755 --- a/backend/tolData/eol/genImagesListDb.py +++ b/backend/tolData/eol/genImagesListDb.py @@ -1,6 +1,6 @@ #!/usr/bin/python3 -import sys, os, re +import os, re import csv import sqlite3 @@ -10,25 +10,25 @@ Generates a sqlite db from a directory of CSV files holding EOL image data """, formatter_class=argparse.RawDescriptionHelpFormatter) parser.parse_args() -imagesListDir = "imagesList/" -dbFile = "imagesList.db" +imagesListDir = 'imagesList/' +dbFile = 'imagesList.db' -print("Creating database") +print('Creating database') dbCon = sqlite3.connect(dbFile) dbCur = dbCon.cursor() -dbCur.execute("CREATE TABLE images" \ - " (content_id INT PRIMARY KEY, page_id INT, source_url TEXT, copy_url TEXT, license TEXT, copyright_owner TEXT)") -dbCur.execute("CREATE INDEX images_pid_idx ON images(page_id)") -print("Reading CSV files") +dbCur.execute('CREATE TABLE images' \ + ' (content_id INT PRIMARY KEY, page_id INT, source_url TEXT, copy_url TEXT, license TEXT, copyright_owner TEXT)') +dbCur.execute('CREATE INDEX images_pid_idx ON images(page_id)') +print('Reading CSV files') csvFilenames = os.listdir(imagesListDir) for filename in csvFilenames: - print(f"Processing {imagesListDir}{filename}") - with open(imagesListDir + filename, newline="") as file: - for (contentId, pageId, sourceUrl, copyUrl, license, owner) in csv.reader(file): - if re.match(r"^[a-zA-Z]", contentId): # Skip header line + print(f'Processing {imagesListDir}{filename}') + with open(imagesListDir + filename, newline='') as file: + for contentId, pageId, sourceUrl, copyUrl, license, owner in csv.reader(file): + if re.match(r'^[a-zA-Z]', contentId): # Skip header line continue - dbCur.execute("INSERT INTO images VALUES (?, ?, ?, ?, ?, ?)", + dbCur.execute('INSERT INTO images VALUES (?, ?, ?, ?, ?, ?)', (int(contentId), int(pageId), sourceUrl, copyUrl, license, owner)) -print("Closing database") +print('Closing database') dbCon.commit() dbCon.close() -- cgit v1.2.3