Question

您好我是python中的初学者，我正在尝试执行此程序来为集合文件创建反向索引：

import sys
import re
from porterStemmer import PorterStemmer
from collections import defaultdict
from array import array
import gc

porter=PorterStemmer()

class CreateIndex:

def __init__(self):
    self.index=defaultdict(list)    #the inverted index


def getStopwords(self):
    '''get stopwords from the stopwords file'''
    f=open(self.stopwordsFile, 'r')
    stopwords=[line.rstrip() for line in f]
    self.sw=dict.fromkeys(stopwords)
    f.close()


def getTerms(self, line):
    '''given a stream of text, get the terms from the text'''
    line=line.lower()
    line=re.sub(r'[^a-z0-9 ]',' ',line) #put spaces instead of non-alphanumeric characters
    line=line.split()
    line=[x for x in line if x not in self.sw]  #eliminate the stopwords
    line=[ porter.stem(word, 0, len(word)-1) for word in line]
    return line


def parseCollection(self):
    ''' returns the id, title and text of the next page in the collection '''
    doc=[]
    for line in self.collFile:
        if line=='</page>\n':
            break
        doc.append(line)

    curPage=''.join(doc)
    pageid=re.search('<id>(.*?)</id>', curPage, re.DOTALL)
    pagetitle=re.search('<title>(.*?)</title>', curPage, re.DOTALL)
    pagetext=re.search('<text>(.*?)</text>', curPage, re.DOTALL)

    if pageid==None or pagetitle==None or pagetext==None:
        return {}

    d={}
    d['id']=pageid.group(1)
    d['title']=pagetitle.group(1)
    d['text']=pagetext.group(1)

    return d


def writeIndexToFile(self):
    '''write the inverted index to the file'''
    f=open(self.indexFile, 'w')
    for term in self.index.iterkeys():
        postinglist=[]
        for p in self.index[term]:
            docID=p[0]
            positions=p[1]
            postinglist.append(':'.join([str(docID) ,','.join(map(str,positions))]))
        print >> f, ''.join((term,'|',';'.join(postinglist)))

    f.close()


def getParams(self):
    '''get the parameters stopwords file, collection file, and the output index file'''
    param=sys.argv
    self.stopwordsFile=param[0]
    self.collectionFile=param[1]
    self.indexFile=param[2]


def createIndex(self):
    '''main of the program, creates the index'''
    self.getParams()
    self.collFile=open(self.collectionFile,'r')
    self.getStopwords()

    #bug in python garbage collector!
    #appending to list becomes O(N) instead of O(1) as the size grows if gc is enabled.
    gc.disable()

    pagedict={}
    pagedict=self.parseCollection()
    #main loop creating the index
    while pagedict != {}:                    
        lines='\n'.join((pagedict['title'],pagedict['text']))
        pageid=int(pagedict['id'])
        terms=self.getTerms(lines)

        #build the index for the current page
        termdictPage={}
        for position, term in enumerate(terms):
            try:
                termdictPage[term][1].append(position)
            except:
                termdictPage[term]=[pageid, array('I',[position])]

        #merge the current page index with the main index
        for termpage, postingpage in termdictPage.iteritems():
            self.index[termpage].append(postingpage)

        pagedict=self.parseCollection()


    gc.enable()

    self.writeIndexToFile()


if __name__=="__main__":
c=CreateIndex()
c.createIndex()

它说sys.argv中只有一个参数...

其他参数应该怎么出现？

Answer 1

在getParams函数中，您可以看到您的代码请求3个参数。当你打电话给你的节目时：

python your_program.py
# sys.argv[0] = 'your_program.py'

它有一个参数。所以你还需要两个：

python your_program.py arg_1 arg_2
# sys.argv[0] = 'your_program.py'
# sys.argv[1] = 'arg_1'
# sys.argv[2] = 'arg_2

Python应返回多于1个参数

1 个答案: