python - 读取带有不正确标记的字典的文件

Question

我有一个包含字典列表的文件，其中大多数都错误地用引号标记。示例如下:

{game:Available,player:Available,location:"Chelsea, London, England",time:Available}
{"game":"Available","player":"Available","location":"Chelsea, London, England","time":"Available","date":"Available"}

正如您所看到的，字典之间的键也可能有所不同。

我尝试使用 json 模块或 csv 模块的 DictReader 来读取该内容，但每次我都会遇到困难，因为“”始终出现在位置值中，但并不总是出现在其他键或值中。到目前为止，我看到两种可能性:

1. 将“,”替换为“;”在位置值中，并删除所有引号。
2. 为每个值和键添加引号(位置除外)。

PS:我的最后一点是能够格式化所有这些字典来创建一个 SQL 表，其中的列是所有字典的并集，每一行都是我的字典之一，当缺少值时为空白。

Answer 1

我认为这是一个非常完整的代码。

首先我创建了以下文件:

{surprise : "perturbating at start  ", game:Available Universal Dices Game,
    player:FTROE875574,location
:"Lakeview School, Kingsmere Boulevard, Saskatoon, Saskatchewan , Canada",time:15h18}

{"game":"Available","   player":"LOI4531",
"location":  "Perth, Australia","time":"08h13","date":"Available"}

{"game":Available,player:PLLI874,location:"Chelsea, London, England",time:20h35}

{special:"midnight happening",game:"Available","player":YTR44,
"location":"Paris, France","time":"02h24"
,
"date":"Available"}

{game:Available,surprise:"  hretyuuhuhu  ",player:FT875,location
:,"time":11h22}

{"game":"Available","player":"LOI4531","location":
"Damas,Syria","time":"unavailable","date":"Available"}

{"surprise   " : GARAMANANATALA Tower ,  game:Available Dices,player  :
  PuLuLu874,location:"  Westminster, London, England  ",time:20h01}

{"game":"Available",special:"overnight",   "player":YTR44,"location":
"Madrid, Spain"    ,     "time":
"12h33",
date:"Available"
}

.

.

然后以下代码分两个阶段处理文件的内容:

• 首先，遍历内容，收集所有字典中的所有介入键

• 推导字典posis，它为每个键给出其对应值在一行中必须占据的位置

• 其次，由于再次运行该文件，行被逐个构建并收集在列表行中

顺便请注意，与键位置或“位置”关联的值的条件受到尊重。

.

import re

dicreg = re.compile('(?<=\{)[^}]*}')

kvregx = re.compile('[ \r\n]*'
                    '(" *)?((location)|[^:]+?)(?(1) *")'
                    '[ \r\n]*'
                    ':'
                    '[ \r\n]*'
                    '(?(3)|(" *)?)([^:]*?)(?(4) *")'
                    '[ \r\n]*(?:,(?=[^,]+?:)|\})')


checking_dict = {}
checking_list = []

filename = 'zzz.txt'

with open(filename) as f:

    ######## First part: to gather all the keys in all the dictionaries

    prec,chunk = '','go'
    ecr = []
    while chunk:
        chunk = f.read(120)
        ss = ''.join((prec,chunk))
        ecr.append('\n\n------------------------------------------------------------\nss   == %r' %ss)
        mat_dic = None
        for mat_dic in dicreg.finditer(ss):
            ecr.append('\nmmmmmmm dictionary found in ss mmmmmmmmmmmmmm')
            for mat_kv in kvregx.finditer(mat_dic.group()):
                k,v = mat_kv.group(2,5)
                ecr.append('%s  :  %s' % (k,v))
                if k in checking_list:
                    checking_dict[k] += 1
                else:
                    checking_list.append(k)
                    checking_dict[k] = 1
        if mat_dic:
            prec = ss[mat_dic.end():]
        else:
            prec += chunk

    print '\n'.join(ecr)
    print '\n\n\nchecking_dict == %s\n\nchecking_list        == %s' %(checking_dict,checking_list)

    ######## The keys are sorted in order that the less frequent ones are at the end
    checking_list.sort(key=lambda k: checking_dict[k], reverse=True)
    posis = dict((k,i) for i,k in enumerate(checking_list))
    print '\nchecking_list sorted == %s\n\nposis == %s' % (checking_list,posis)



    ######## Now, the file is read again to build a list of rows 

    f.seek(0,0)  # the file's pointer is move backed to the beginning of the file

    prec,chunk = '','go'
    base = [ '' for i in xrange(len(checking_list))]
    rows = []
    while chunk:
        chunk = f.read(110)
        ss = ''.join((prec,chunk))
        mat_dic = None
        for mat_dic in dicreg.finditer(ss):
            li = base[:]
            for mat_kv in kvregx.finditer(mat_dic.group()):
                k,v = mat_kv.group(2,5)
                li[posis[k]] = v
            rows.append(li)
        if mat_dic:
            prec = ss[mat_dic.end():]
        else:
            prec += chunk


    print '\n\n%s\n%s' % (checking_list,30*'___')
    print '\n'.join(str(li) for li in rows)

结果

------------------------------------------------------------
ss   == '{surprise : "perturbating at start  ", game:Available Universal Dices Game,\n    player:FTROE875574,location\n:"Lakeview S'


------------------------------------------------------------
ss   == '{surprise : "perturbating at start  ", game:Available Universal Dices Game,\n    player:FTROE875574,location\n:"Lakeview School, Kingsmere Boulevard, Saskatoon, Saskatchewan , Canada",time:15h18}\n\n{"game":"Available","   player":"LOI4531",\n"l'

mmmmmmm dictionary found in ss mmmmmmmmmmmmmm
surprise  :  perturbating at start
game  :  Available Universal Dices Game
player  :  FTROE875574
location  :  "Lakeview School, Kingsmere Boulevard, Saskatoon, Saskatchewan , Canada"
time  :  15h18


------------------------------------------------------------
ss   == '\n\n{"game":"Available","   player":"LOI4531",\n"location":  "Perth, Australia","time":"08h13","date":"Available"}\n\n{"game":Available,player:PLLI874,location:"Chelsea, Lo'

mmmmmmm dictionary found in ss mmmmmmmmmmmmmm
game  :  Available
player  :  LOI4531
location  :  "Perth, Australia"
time  :  08h13
date  :  Available


------------------------------------------------------------
ss   == '\n\n{"game":Available,player:PLLI874,location:"Chelsea, London, England",time:20h35}\n\n{special:"midnight happening",game:"Available","player":YTR44,\n"location":"Paris, France","t'

mmmmmmm dictionary found in ss mmmmmmmmmmmmmm
game  :  Available
player  :  PLLI874
location  :  "Chelsea, London, England"
time  :  20h35


------------------------------------------------------------
ss   == '\n\n{special:"midnight happening",game:"Available","player":YTR44,\n"location":"Paris, France","time":"02h24"\n,\n"date":"Available"}\n\n{game:Available,surprise:"  hretyuuhuhu  ",player:FT875,location\n:,"time":11h22}\n\n{"'

mmmmmmm dictionary found in ss mmmmmmmmmmmmmm
special  :  midnight happening
game  :  Available
player  :  YTR44
location  :  "Paris, France"
time  :  02h24
date  :  Available

mmmmmmm dictionary found in ss mmmmmmmmmmmmmm
game  :  Available
surprise  :  hretyuuhuhu
player  :  FT875
location  :  
time  :  11h22


------------------------------------------------------------
ss   == '\n\n{"game":"Available","player":"LOI4531","location":\n"Damas,Syria","time":"unavailable","date":"Available"}\n\n{"surprise   " '

mmmmmmm dictionary found in ss mmmmmmmmmmmmmm
game  :  Available
player  :  LOI4531
location  :  "Damas,Syria"
time  :  unavailable
date  :  Available


------------------------------------------------------------
ss   == '\n\n{"surprise   " : GARAMANANATALA Tower ,  game:Available Dices,player  :\n  PuLuLu874,location:"  Westminster, London, England  ",time:20'


------------------------------------------------------------
ss   == '\n\n{"surprise   " : GARAMANANATALA Tower ,  game:Available Dices,player  :\n  PuLuLu874,location:"  Westminster, London, England  ",time:20h01}\n\n{"game":"Available",special:"overnight",   "player":YTR44,"location":\n"Madrid, Spain"    ,     "time":\n"12h33",\nda'

mmmmmmm dictionary found in ss mmmmmmmmmmmmmm
surprise  :  GARAMANANATALA Tower
game  :  Available Dices
player  :  PuLuLu874
location  :  "  Westminster, London, England  "
time  :  20h01


------------------------------------------------------------
ss   == '\n\n{"game":"Available",special:"overnight",   "player":YTR44,"location":\n"Madrid, Spain"    ,     "time":\n"12h33",\ndate:"Available"\n}'

mmmmmmm dictionary found in ss mmmmmmmmmmmmmm
game  :  Available
special  :  overnight
player  :  YTR44
location  :  "Madrid, Spain"
time  :  12h33
date  :  Available


------------------------------------------------------------
ss   == ''



checking_dict == {'player': 8, 'game': 8, 'location': 8, 'time': 8, 'date': 4, 'surprise': 3, 'special': 2}

checking_list        == ['surprise', 'game', 'player', 'location', 'time', 'date', 'special']

checking_list sorted == ['game', 'player', 'location', 'time', 'date', 'surprise', 'special']

posis == {'player': 1, 'game': 0, 'location': 2, 'time': 3, 'date': 4, 'surprise': 5, 'special': 6}


['game', 'player', 'location', 'time', 'date', 'surprise', 'special']
__________________________________________________________________________________________
['Available Universal Dices Game', 'FTROE875574', '"Lakeview School, Kingsmere Boulevard, Saskatoon, Saskatchewan , Canada"', '15h18', '', 'perturbating at start', '']
['Available', 'LOI4531', '"Perth, Australia"', '08h13', 'Available', '', '']
['Available', 'PLLI874', '"Chelsea, London, England"', '20h35', '', '', '']
['Available', 'YTR44', '"Paris, France"', '02h24', 'Available', '', 'midnight happening']
['Available', 'FT875', '', '11h22', '', 'hretyuuhuhu', '']
['Available', 'LOI4531', '"Damas,Syria"', 'unavailable', 'Available', '', '']
['Available Dices', 'PuLuLu874', '"  Westminster, London, England  "', '20h01', '', 'GARAMANANATALA Tower', '']
['Available', 'YTR44', '"Madrid, Spain"', '12h33', 'Available', '', 'overnight']

.

.

我把上面的代码写成一个数GB的巨大文件，无法完全读取:对这样一个非常大的文件的处理必须一个又一个地 block 完成。这就是为什么有说明:

while chunk:
    chunk = f.read(120)
    ss = ''.join((prec,chunk))
    ecr.append('\n\n------------------------------------------------------------\nss   == %r' %ss)
    mat_dic = None
    for mat_dic in dicreg.finditer(ss):
        ............
        ...............
    if mat_dic:
        prec = ss[mat_dic.end():]
    else:
        prec += chunk

但是，显然，如果文件不太大，因此可以一次性读取，则可以简化代码:

import re

dicreg = re.compile('(?<=\{)[^}]*}')

kvregx = re.compile('[ \r\n]*'
                    '(" *)?((location)|[^:]+?)(?(1) *")'
                    '[ \r\n]*'
                    ':'
                    '[ \r\n]*'
                    '(?(3)|(" *)?)([^:]*?)(?(4) *")'
                    '[ \r\n]*(?:,(?=[^,]+?:)|\})')


checking_dict = {}
checking_list = []

filename = 'zzz.txt'

with open(filename) as f:
    content = f.read()




######## First part: to gather all the keys in all the dictionaries

ecr = []

for mat_dic in dicreg.finditer(content):
    ecr.append('\nmmmmmmm dictionary found in ss mmmmmmmmmmmmmm')
    for mat_kv in kvregx.finditer(mat_dic.group()):
        k,v = mat_kv.group(2,5)
        ecr.append('%s  :  %s' % (k,v))
        if k in checking_list:
            checking_dict[k] += 1
        else:
            checking_list.append(k)
            checking_dict[k] = 1


print '\n'.join(ecr)
print '\n\n\nchecking_dict == %s\n\nchecking_list        == %s' %(checking_dict,checking_list)

######## The keys are sorted in order that the less frequent ones are at the end
checking_list.sort(key=lambda k: checking_dict[k], reverse=True)
posis = dict((k,i) for i,k in enumerate(checking_list))
print '\nchecking_list sorted == %s\n\nposis == %s' % (checking_list,posis)



######## Now, the file is read again to build a list of rows 


base = [ '' for i in xrange(len(checking_list))]
rows = []

for mat_dic in dicreg.finditer(content):
    li = base[:]
    for mat_kv in kvregx.finditer(mat_dic.group()):
        k,v = mat_kv.group(2,5)
        li[posis[k]] = v
    rows.append(li)


print '\n\n%s\n%s' % (checking_list,30*'___')
print '\n'.join(str(li) for li in rows)