From 29940d51eb8b6b220d53940ecbc212cea78159ae Mon Sep 17 00:00:00 2001
From: Terry Truong <terry06890@gmail.com>
Date: Tue, 17 May 2022 10:41:12 +1000
Subject: Improve enwiki description extraction

Adjust enwiki code to handle single dump file, and add scripts for
'convenient' page-content lookup.
---
 backend/data/enwiki/lookupPage.py | 66 +++++++++++++++++++++++++++++++++++++++
 1 file changed, 66 insertions(+)
 create mode 100755 backend/data/enwiki/lookupPage.py

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

diff --git a/backend/data/enwiki/lookupPage.py b/backend/data/enwiki/lookupPage.py
new file mode 100755
index 0000000..5d6afe9
--- /dev/null
+++ b/backend/data/enwiki/lookupPage.py
@@ -0,0 +1,66 @@
+#!/usr/bin/python3
+
+import sys, re
+import bz2
+import sqlite3
+
+usageInfo =  f"usage: {sys.argv[0]} title1\n"
+usageInfo += "Looks up a page with title title1 in a wikipedia dump,\n"
+usageInfo += "using a dump index db, and prints the corresponding <page>.\n"
+if len(sys.argv) != 2:
+	print(usageInfo, file=sys.stderr)
+	sys.exit(1)
+
+dumpFile = "enwiki-20220501-pages-articles-multistream.xml.bz2"
+indexDb = "dumpIndex.db"
+pageTitle = sys.argv[1]
+
+# Searching index file
+print("Lookup offset in index db")
+dbCon = sqlite3.connect(indexDb)
+dbCur = dbCon.cursor()
+row = dbCur.execute("SELECT title, offset, next_offset FROM offsets WHERE title = ?",
+	(pageTitle.replace("_", " "),)).fetchone()
+if row == None:
+	print("Title not found")
+	sys.exit(0)
+(_, pageOffset, endOffset) = row
+dbCon.close()
+print("Found chunk at offset {}".format(pageOffset))
+# Read dump file
+print("Reading dump file")
+content = []
+with open(dumpFile, mode='rb') as file:
+	# Get uncompressed chunk
+	file.seek(pageOffset)
+	compressedData = file.read(None if endOffset == -1 else endOffset - pageOffset)
+	data = bz2.BZ2Decompressor().decompress(compressedData).decode()
+	# Look in chunk for page
+	lines = data.splitlines()
+	lineIdx = 0
+	found = False
+	pageNum = 0
+	while not found:
+		line = lines[lineIdx]
+		if line.lstrip() == "<page>":
+			pageNum += 1
+			if pageNum > 100:
+				print("ERROR: Did not find title after 100 pages")
+				break
+			lineIdx += 1
+			titleLine = lines[lineIdx]
+			if titleLine.lstrip() == '<title>' + pageTitle + '</title>':
+				found = True
+				print("Found title in chunk as page {}".format(pageNum))
+				content.append(line)
+				content.append(titleLine)
+				while True:
+					lineIdx += 1
+					line = lines[lineIdx]
+					content.append(line)
+					if line.lstrip() == "</page>":
+						break
+		lineIdx += 1
+# Print content
+print("Content: ")
+print("\n".join(content))
-- 
cgit v1.2.3