mysqldb/python を使用して、一部のデータを mysql db にプッシュしています。
このスクリプトは、一連の XML ファイルを解析してデータを取得します。
MySQL サーバーが終了したようで、トランザクションの途中で「#2002 - サーバーが応答していません (またはローカル MySQL サーバーのソケットが正しく構成されていません)」というエラーが表示されます - 実行するたびに別の場所で (転倒している特定のデータではないと想定しています...）
〜12または13ファイルに達するまで完全に機能し、次のエラーが表示されます：
Error 2003: Can't connect to MySQL server on 'localhost' (10055)
Traceback (most recent call last):
File "sigFileParser.py", line 113, in <module>
doParser(sigfile_filename)
File "sigFileParser.py", line 106, in
doParser
doFormatsPush(packedFormats)
File "sigFileParser.py", line 27, in
doFormatsPush
sys.exit (1)
NameError: global name 'sys' is not defined
エラーが発生すると、MySQL コンソールまたは PHOPmyadmin 経由でアクセスできなくなります
しばらく離れると、MySQL に戻ることができます
MySQL テーブル:
CREATE TABLE IF NOT EXISTS patterns
(Version int(3),
DateCreated DATETIME,
SigID int(4),
SigSpecificity CHAR(10),
ByteSeqReference CHAR(12),
MinFragLength int(4),
Position int(4),
SubSeqMaxOffset int(4),
SubSeqMinOffset int(4),
Pattern TEXT)
と
CREATE TABLE IF NOT EXISTS formats
(Version int(3),
DateCreated DATETIME,
FormatID int(4),
FormatName TEXT,
PUID TEXT,
FormatVersion TEXT,
FormatMIMEType TEXT,
InternalSignatureID int(4),
Extension TEXT,
HasPriorityOverFileFormatID int(4))
パイコード
from lxml import etree
import re, os, MySQLdb
def doPatternPush(packedPatterns):
try:
db = MySQLdb.connect (host = "localhost", user = "root", passwd = "", db = "sigfiles")
c = db.cursor()
c.execute('''INSERT INTO sigfiles.patterns
(Version,DateCreated,SigID,SigSpecificity,ByteSeqReference,MinFragLength,Position,SubSeqMaxOffset,SubSeqMinOffset,Pattern)
VALUES (%s, %s, %s, %s, %s, %s, %s, %s, %s, %s)''', packedPatterns)
db.commit()
except MySQLdb.Error, e:
print "Error %d: %s" % (e.args[0], e.args[1])
sys.exit (1)
return (db)
def doFormatsPush(packedFormats):
try:
db = MySQLdb.connect (host = "localhost", user = "root", passwd = "", db = "sigfiles")
c = db.cursor()
c.execute('''INSERT INTO sigfiles.formats
(Version,DateCreated,FormatID,FormatName,PUID,FormatVersion,FormatMIMEType,InternalSignatureID,Extension,HasPriorityOverFileFormatID)
VALUES (%s, %s, %s, %s, %s, %s, %s, %s, %s, %s)''', packedFormats)
db.commit()
except MySQLdb.Error, e:
print "Error %d: %s" % (e.args[0], e.args[1])
sys.exit (1)
return(db)
def doParser(sigfile_filename):
tree = etree.parse(sigfile_filename)
root = tree.getroot()
attributes = root.attrib
if 'DateCreated' in root.attrib:
DateCreated = (attributes["DateCreated"])
if 'Version' in root.attrib:
Version = (attributes["Version"])
##--------- get internal sig details ------------------
for a in range (len(root[0])): #loops for sig ID
attributes = root[0][a].attrib
SigID=(attributes["ID"])
SigSpecificity = (attributes["Specificity"])
for b in range (len(root[0][a])): # loops for sequence pattern inside each sig
attributes = root[0][a][b].attrib
if 'Reference' in root[0][a][b].attrib:
ByteSeqReference = (attributes["Reference"])
else:
ByteSeqReference = "NULL"
attributes = root[0][a][b][0].attrib
if 'MinFragLength' in root[0][a][b][0].attrib:
MinFragLength=(attributes["MinFragLength"])
else:
MinFragLength=''
if 'Position' in root[0][a].attrib:
Position=(attributes["Position"])
else:
Position=''
if 'SubSeqMaxOffset' in root[0][a][b][0].attrib:
SubSeqMaxOffset=(attributes["SubSeqMaxOffset"])
else:
SubSeqMaxOffsee = ''
if 'SubSeqMinOffset' in root[0][a][b][0].attrib:
SubSeqMinOffset=(attributes["SubSeqMinOffset"])
else:
SubSeqMinOffset = ''
Pattern = root[0][a][b][0][0].text
packedPatterns = [Version,DateCreated,SigID,SigSpecificity,ByteSeqReference,MinFragLength,Position,SubSeqMaxOffset,SubSeqMinOffset,Pattern]
doPatternPush(packedPatterns)
##-------- get format ID details-------------
for a in range (len(root[1])):
attributes = root[1][a].attrib
if 'ID' in root[1][a].attrib:
FormatID = (attributes['ID'])
else:
FormatID = "NULL"
if 'Name' in root[1][a].attrib:
FormatName = (attributes['Name'])
else:
FormatName = "NULL"
if 'PUID' in root[1][a].attrib:
PUID = (attributes['PUID'])
else:
PUID = "NULL"
if 'Version' in root[1][a].attrib:
FormatVersion = (attributes['Version'])
else:
FormatVersion = "NULL"
if 'MIMEType' in root[1][a].attrib:
FormatMIMEType = (attributes['MIMEType'])
else:
FormatMIMEType = "NULL"
InternalSignatureID,Extension,HasPriorityOverFileFormatID = ('', 'NULL', '')
for b in range (len(root[1][a])): #extracts the tags for each format ID
tagType = root[1][a][b].tag
tagText = root[1][a][b].text
tagType = re.sub('{http://www.nationalarchives.gov.uk/pronom/SignatureFile}', '', tagType)
if tagType == 'InternalSignatureID':
InternalSignatureID = tagText
elif tagType == 'Extension':
Extension = tagText
HasPriorityOverFileFormatID = ''
else:
HasPriorityOverFileFormatID = tagText
Extension = 'NULL'
packedFormats = [Version,DateCreated,FormatID,FormatName,PUID,FormatVersion,FormatMIMEType,InternalSignatureID,Extension,HasPriorityOverFileFormatID]
doFormatsPush(packedFormats)
if __name__ == "__main__":
path = "C:\Users\NDHA\Desktop\droid sigs all"
for (path, dirs, files) in os.walk(path):
for file in files:
sigfile_filename = str(path)+"\\"+str(file)
doParser(sigfile_filename)
print sigfile_filename
db.close()
すべての XML はここから取得されます: http://www.nationalarchives.gov.uk/aboutapps/pronom/droid-signature-files.htm