我的代码使用MARCReader导入一个MARC文件，并将字符串与可接受的答案列表进行比较。如果来自MARC的字符串在我的列表中没有匹配，它将被添加到错误列表中。这在Windows 7上的Python 2.7.4安装中已经工作多年，没有问题。我最近买了一台Windows 10机器，并安装了Python 2.7.10，现在带有非标准字符的字符串无法匹配。问题不仅仅是Python 2.7.10;我在这台新机器上安装了从2.7.4到2.7.10的每个版本，并遇到了同样的问题。在Windows 7机器上新安装Python 2.7.10也会遇到这个问题。
我已经删去了不相关的函数，并且我已经大幅删减了主列表。在这个例子中，"acad
# -*- coding: utf-8 -*-
from aipmarc import get_catdb, get_bibno, parse_date
from phfawstemplate import browsepage #, nutchpage, eadpage, titlespage
from pymarc import MARCReader, marc8_to_unicode
from time import strftime
from umlautsort import alafiling
import urllib2
import sys
import os
import string
def make_newrepos_list(list, fn): # Create list of unexpected repositories found in the MArcout database dump
output = "These new repositories are not yet included in the master list in phfaws.py. Please add the repository code (in place of ""NEWCODE*""), and the URL (in place of ""TEST""), and then add these lines to phfaws.py. Please keep the list alphabetical. nYou can find repository codes at http://www.loc.gov/marc/organizations/ n n"
for row in list:
output = '%s reposmasterlist.append([u"%s", "%s", "%s"])n' % (output, row[0], row[1], row[2])
fh = open(fn,'w')
fh.write(output.encode("utf-8"))
fh.close()
def main(marcfile):
reader = MARCReader(file(marcfile))
'''
Creating list of preset repository codes.
'''
reposmasterlist =[[u"American Institute of Physics", "MdCpAIP", "http://www.aip.org/history/nbl/index.html"]]
reposmasterlist.append([u"Académie des Sciences", "FrACADEMIE", "http://www.academie-sciences.fr/fr/Transmettre-les-connaissances/inventaires-des-fonds-d-archives-personnelles.html"])
reposmasterlist.append([u"American Association for the Advancement of Science", "daaas", "http://archives.aaas.org/"])
newreposcounter = 0
newrepos = ""
newreposlist = []
findingaidcounter = 0
reposcounter = 0
for record in reader:
if record['903']: # Get only records where 903a="PHFAWS"
phfawsfull = record.get_fields('903')
for field in phfawsfull:
phfawsnote = field['a']
if 'PHFAWS' in phfawsnote:
if record['852'] is not None: # Get only records where 852/repository is not blank
repository = record.get_fields('852')
for field in repository:
reposname = field['a']
reposname = marc8_to_unicode(reposname) # Convert repository name from MARC file to Unicode
reposname = reposname.rstrip('.,')
reposcode = None
reposurl = None
for row in reposmasterlist: # Match field 852 repository against the master list.
if row[0] == reposname: # If it's in the master list, use the master list to populate our repository-related fields
reposcode = row[1]
reposurl = row[2]
if record['856'] is not None: # Get only records where 856 is not blank and includes "online finding aid"
links = record.get_fields('856')
for field in links:
linksthree = field['3']
if linksthree is not None and "online finding aid" in linksthree:
if reposcode == None: # If this record's repository wasn't in the master list, add to list of new repositories
newreposcounter += 1
newrepos = '%s %s n' % (newrepos, reposname)
reposcode = "NEWCODE" + str(newreposcounter)
reposurl = "TEST"
reposmasterlist.append([reposname, reposcode, reposurl])
newreposlist.append([reposname, reposcode, reposurl])
human_url = field['u']
else:
pass
else:
pass
else:
pass
else:
pass
else:
pass
# Output list of new repositories
newreposlist.sort(key = lambda rep: rep[0])
if newreposcounter != 0:
status = '%d new repositories found. you must add information on these repositories, then run phfaws.py again. Please see the newly updated rewrepos.txt for details.' % (newreposcounter)
sys.stderr.write(status)
make_newrepos_list(newreposlist, 'newrepos.txt')
if __name__ == '__main__':
try:
mf = sys.argv[1]
sys.exit(main(mf))
except IndexError:
sys.exit('Usage: %s <marcfile>' % sys.argv[0])
编辑:我发现，简单地注释出"reposname = marc8_to_unicode(reposname)"行得到我想要的结果。我仍然不明白这是为什么，因为这是一个必要的步骤之前。
编辑:我发现，简单地注释出"reposname = marc8_to_unicode(reposname)"行得到我想要的结果。我还是不明白这是为什么，因为这是一个必要的步骤。
这表明你的数据库中字符串的编码从MARC8更改为Unicode。你最近有没有升级你的编目系统?