From daccbbd9c73a5292ea9d6746560d7009e5aa666d Mon Sep 17 00:00:00 2001
From: Terry Truong <terry06890@gmail.com>
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/enwiki/lookupPage.py | 34 +++++++++++++++++-----------------
 1 file changed, 17 insertions(+), 17 deletions(-)

(limited to 'backend/tolData/enwiki/lookupPage.py')

diff --git a/backend/tolData/enwiki/lookupPage.py b/backend/tolData/enwiki/lookupPage.py
index e7b95f0..427aa7a 100755
--- a/backend/tolData/enwiki/lookupPage.py
+++ b/backend/tolData/enwiki/lookupPage.py
@@ -1,6 +1,6 @@
 #!/usr/bin/python3
 
-import sys, re
+import sys
 import bz2
 import sqlite3
 
@@ -12,24 +12,24 @@ db, and prints the corresponding <page>.
 parser.add_argument("title", help="The title to look up")
 args = parser.parse_args()
 
-dumpFile = "enwiki-20220501-pages-articles-multistream.xml.bz2"
-indexDb = "dumpIndex.db"
-pageTitle = args.title.replace("_", " ")
+dumpFile = 'enwiki-20220501-pages-articles-multistream.xml.bz2'
+indexDb = 'dumpIndex.db'
+pageTitle = args.title.replace('_', ' ')
 
-print("Looking up offset in index db")
+print('Looking up offset in index db')
 dbCon = sqlite3.connect(indexDb)
 dbCur = dbCon.cursor()
-query = "SELECT title, offset, next_offset FROM offsets WHERE title = ?"
+query = 'SELECT title, offset, next_offset FROM offsets WHERE title = ?'
 row = dbCur.execute(query, (pageTitle,)).fetchone()
-if row == None:
-	print("Title not found")
+if row is None:
+	print('Title not found')
 	sys.exit(0)
 _, pageOffset, endOffset = row
 dbCon.close()
-print(f"Found chunk at offset {pageOffset}")
+print(f'Found chunk at offset {pageOffset}')
 
-print("Reading from wiki dump")
-content = []
+print('Reading from wiki dump')
+content: list[str] = []
 with open(dumpFile, mode='rb') as file:
 	# Get uncompressed chunk
 	file.seek(pageOffset)
@@ -42,25 +42,25 @@ with open(dumpFile, mode='rb') as file:
 	pageNum = 0
 	while not found:
 		line = lines[lineIdx]
-		if line.lstrip() == "<page>":
+		if line.lstrip() == '<page>':
 			pageNum += 1
 			if pageNum > 100:
-				print("ERROR: Did not find title after 100 pages")
+				print('ERROR: Did not find title after 100 pages')
 				break
 			lineIdx += 1
 			titleLine = lines[lineIdx]
 			if titleLine.lstrip() == '<title>' + pageTitle + '</title>':
 				found = True
-				print(f"Found title in chunk as page {pageNum}")
+				print(f'Found title in chunk as page {pageNum}')
 				content.append(line)
 				content.append(titleLine)
 				while True:
 					lineIdx += 1
 					line = lines[lineIdx]
 					content.append(line)
-					if line.lstrip() == "</page>":
+					if line.lstrip() == '</page>':
 						break
 		lineIdx += 1
 
-print("Content: ")
-print("\n".join(content))
+print('Content: ')
+print('\n'.join(content))
-- 
cgit v1.2.3