使用pymarc marc8_to_unicode的Python字符串比較不再起作用

Question

我的代碼使用MARCReader導入了MARC文件，並將字符串與可接受答案的列表進行比較。 如果MARC中的字符串在我的列表中不匹配，它將被添加到錯誤列表中。 這在Windows 7上的Python 2.7.4安裝中已經有效了多年，沒有任何問題。 我最近有一台Windows 10計算機並安裝了Python 2.7.10，現在帶有非標准字符的字符串無法匹配。 問題不僅僅在於Python 2.7.10； 我已經在此新計算機上安裝了從2.7.4到2.7.10的每個版本，並遇到了相同的問題。 在Windows 7計算機上重新安裝Python 2.7.10也會解決此問題。

我已經修剪掉了不相關的功能，並且已經大幅修剪了主列表。 在此示例中，“Académiedes Sciences”是現有的存儲庫，但是“Acadm̌iedes Sciences”現在出現在我們的新存儲庫列表中。

# -*- 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])

編輯：我發現僅注釋掉“ reposname = marc8_to_unicode（reposname）”行就可以得到想要的結果。 我仍然不明白為什么會這樣，因為這是之前的必要步驟。

Answer 1

編輯：我發現僅注釋掉“ reposname = marc8_to_unicode（reposname）”行就可以得到想要的結果。 我仍然不明白為什么會這樣，因為這是之前的必要步驟。

這向我表明，數據庫中字符串的編碼已從MARC8更改為Unicode。 您最近升級了編目系統嗎？