def addBookToDB(rc, bookUrl, siteFormat):
bookText = getFromStorage(bookUrl)
bookData = {
'bookUrl': bookUrl,
'bookText': bookText
}
if siteFormat == 'gutenberg':
parseGutenberg(bookData)
addNewBook(rc, bookData)
def getLocationsOfWordInBook(rc, wordId, bookId, wordText):
cursor = rc["db"].cursor()
selectQuery = 'SELECT *' \
'FROM sadnadb.wordsInBooks wb, sadnadb.books b ' \
'WHERE wb.wordId = %s and wb.bookId = b.id and b.id = %s '
cursor.execute(selectQuery, (wordId, bookId))
result = cursor.fetchall()
wordLocations = []
bookFileLocation = result[0][15]
for r in result:
wordLocations += [{
'lineNumber': r[2],
'wordNumber': r[3],
'charLocation': r[4],
'sentenceNumber': r[5],
'paragraphNumber': r[6],
'wordNumberInLine': r[7]
}]
bookText = getFromStorage(bookFileLocation)
bookLines = bookText.split('\r\n')
for temp in wordLocations:
ln = temp['lineNumber']
tempLine = bookLines[ln].lower()
tempPos = tempLine.find(wordText)
if tempPos != -1:
parts = [bookLines[ln][:tempPos], bookLines[ln][tempPos + len(wordText):]]
temp['cite1'] = bookLines[ln - 1].decode('utf-8') + '\r\n' + parts[0].decode('utf-8')
temp['cite2'] = parts[1].decode('utf-8') + '\r\n' + bookLines[ln + 1].decode('utf-8')
temp['originalWordText'] = bookLines[ln][tempPos:tempPos + len(wordText)].decode('utf-8')
else:
temp['cite'] = bookLines[ln - 1] + '\r\n' + \
bookLines[ln] + '\r\n' + \
bookLines[ln + 1]
temp['cite'] = temp['cite'].decode('utf-8')
return wordLocations
