我需要阅读一些大文件（从50k到100k行），以空行分隔的组结构。每组以相同的模式“No.999999999 dd / mm / yyyy ZZZ”开始。这是一些样本数据。
No.813829461 16/09/1987 270
Tit.SUZANO PAPEL E CELULOSE S.A.（BR / BA）
C.N.P.J./C.I.C./N INPI：16404287000155
Procurador：MARCELLO DO NASCIMENTONo.815326777 28/12/1989 351
Tit.SIGLA SISTEMA GLOBO DE GRAVACOES音频VISUAIS LTDA（BR / RJ）
C.N.P.J./C.I.C./NºINPI:34162651000108
Apres。：Nominativa; Nat。：De Produto
马卡：TRIO TROPICAL
Clas.Prod/Serv:09.40
* DEFERIDOCONFORMESROLUÇÃO123DE 06/01/2006，PUBLICADA NA RPI 1829，DE 24/01/2006。
Procurador：WALDEMAR RODRIGUES PEDRANo.900148764 11/01/2007 LD3
Tit.TIARA BOLSASACALÇADOSLTDA
Procurador：Marcia Ferreira Gomes
*Escritório：Marcas Marcantes e Patents Ltda
*ExigênciaFormalnãoresponseidaSatisfatoriamente，Pedido de Registro de Marca thoughtfulrado inexistente，de acordo com Art。 157 da LPI
*挪威语协会法律协会正式成员：810080140197
我编写了一些相应解析它的代码。有什么我可以提高，以提高可读性或性能？这是我到目前为止所得到的：
import re, pprint
class Despacho(object):
"""
Class to parse each line, applying the regexp and storing the results
for future use
"""
regexp = {
re.compile(r'No.([\d]{9}) ([\d]{2}/[\d]{2}/[\d]{4}) (.*)'): lambda self: self._processo,
re.compile(r'Tit.(.*)'): lambda self: self._titular,
re.compile(r'Procurador: (.*)'): lambda self: self._procurador,
re.compile(r'C.N.P.J./C.I.C./N INPI :(.*)'): lambda self: self._documento,
re.compile(r'Apres.: (.*) ; Nat.: (.*)'): lambda self: self._apresentacao,
re.compile(r'Marca: (.*)'): lambda self: self._marca,
re.compile(r'Clas.Prod/Serv: (.*)'): lambda self: self._classe,
re.compile(r'\*(.*)'): lambda self: self._complemento,
}
def __init__(self):
"""
'complemento' is the only field that can be multiple in a single registry
"""
self.complemento = []
def _processo(self, matches):
self.processo, self.data, self.despacho = matches.groups()
def _titular(self, matches):
self.titular = matches.group(1)
def _procurador(self, matches):
self.procurador = matches.group(1)
def _documento(self, matches):
self.documento = matches.group(1)
def _apresentacao(self, matches):
self.apresentacao, self.natureza = matches.groups()
def _marca(self, matches):
self.marca = matches.group(1)
def _classe(self, matches):
self.classe = matches.group(1)
def _complemento(self, matches):
self.complemento.append(matches.group(1))
def read(self, line):
for pattern in Despacho.regexp:
m = pattern.match(line)
if m:
Despacho.regexp[pattern](self)(m)
def process(rpi):
"""
read data and process each group
"""
rpi = (line for line in rpi)
group = False
for line in rpi:
if line.startswith('No.'):
group = True
d = Despacho()
if not line.strip() and group: # empty line - end of block
yield d
group = False
d.read(line)
arquivo = open('rm1972.txt') # file to process
for desp in process(arquivo):
pprint.pprint(desp.__dict__)
print('--------------')
答案 0 :(得分：2)
这很不错。以下是一些建议，如果你喜欢，请告诉我：
import re
import pprint
import sys
class Despacho(object):
"""
Class to parse each line, applying the regexp and storing the results
for future use
"""
#used a dict with the keys instead of functions.
regexp = {
('processo',
'data',
'despacho'): re.compile(r'No.([\d]{9}) ([\d]{2}/[\d]{2}/[\d]{4}) (.*)'),
('titular',): re.compile(r'Tit.(.*)'),
('procurador',): re.compile(r'Procurador: (.*)'),
('documento',): re.compile(r'C.N.P.J./C.I.C./N INPI :(.*)'),
('apresentacao',
'natureza'): re.compile(r'Apres.: (.*) ; Nat.: (.*)'),
('marca',): re.compile(r'Marca: (.*)'),
('classe',): re.compile(r'Clas.Prod/Serv: (.*)'),
('complemento',): re.compile(r'\*(.*)'),
}
def __init__(self):
"""
'complemento' is the only field that can be multiple in a single registry
"""
self.complemento = []
def read(self, line):
for attrs, pattern in Despacho.regexp.iteritems():
m = pattern.match(line)
if m:
for groupn, attr in enumerate(attrs):
# special case complemento:
if attr == 'complemento':
self.complemento.append(m.group(groupn + 1))
else:
# set the attribute on the object
setattr(self, attr, m.group(groupn + 1))
def __repr__(self):
# defines object printed representation
d = {}
for attrs in self.regexp:
for attr in attrs:
d[attr] = getattr(self, attr, None)
return pprint.pformat(d)
def process(rpi):
"""
read data and process each group
"""
#Useless line, since you're doing a for anyway
#rpi = (line for line in rpi)
group = False
for line in rpi:
if line.startswith('No.'):
group = True
d = Despacho()
if not line.strip() and group: # empty line - end of block
yield d
group = False
d.read(line)
def main():
arquivo = open('rm1972.txt') # file to process
for desp in process(arquivo):
print desp # can print directly here.
print('-' * 20)
return 0
if __name__ == '__main__':
main()
答案 1 :(得分：1)
如果您有特别关注的话，帮助会更容易。性能将在很大程度上取决于您使用的特定正则表达式引擎的效率。单个文件中的100K行听起来不是那么大，但这又取决于您的环境。
我在.NET开发中使用Expresso来测试表达式的准确性和性能。 谷歌搜索出现了Kodos，这是一个GUI Python正则表达式创作工具。
答案 2 :(得分：0)
整体看起来不错，但为什么你有这条线：
rpi = (line for line in rpi)
您可以在没有此中间步骤的情况下迭代文件对象。
答案 3 :(得分：0)
我不会在这里使用正则表达式。如果您知道您的行将以固定字符串开头，为什么不检查这些字符串并在其周围写一个逻辑？
for line in open(file):
if line[0:3]=='No.':
currIndex='No'
map['No']=line[4:]
....
...
else if line.strip()=='':
//store the record in the map and clear the map
else:
//append line to the last index in map.. this is when the record overflows to the next line.
Map[currIndex]=Map[currIndex]+"\n"+line
将上述代码视为伪代码。
答案 4 :(得分：0)
只有一个正则表达式的另一个版本：
#!/usr/bin/python
import re
import pprint
import sys
class Despacho(object):
"""
Class to parse each line, applying the regexp and storing the results
for future use
"""
#used a dict with the keys instead of functions.
regexp = re.compile(
r'No.(?P<processo>[\d]{9}) (?P<data>[\d]{2}/[\d]{2}/[\d]{4}) (?P<despacho>.*)'
r'|Tit.(?P<titular>.*)'
r'|Procurador: (?P<procurador>.*)'
r'|C.N.P.J./C.I.C./N INPI :(?P<documento>.*)'
r'|Apres.: (?P<apresentacao>.*) ; Nat.: (?P<natureza>.*)'
r'|Marca: (?P<marca>.*)'
r'|Clas.Prod/Serv: (?P<classe>.*)'
r'|\*(?P<complemento>.*)')
simplefields = ('processo', 'data', 'despacho', 'titular', 'procurador',
'documento', 'apresentacao', 'natureza', 'marca', 'classe')
def __init__(self):
"""
'complemento' is the only field that can be multiple in a single
registry
"""
self.__dict__ = dict.fromkeys(self.simplefields)
self.complemento = []
def parse(self, line):
m = self.regexp.match(line)
if m:
gd = dict((k, v) for k, v in m.groupdict().items() if v)
if 'complemento' in gd:
self.complemento.append(gd['complemento'])
else:
self.__dict__.update(gd)
def __repr__(self):
# defines object printed representation
return pprint.pformat(self.__dict__)
def process(rpi):
"""
read data and process each group
"""
d = None
for line in rpi:
if line.startswith('No.'):
if d:
yield d
d = Despacho()
d.parse(line)
yield d
def main():
arquivo = file('rm1972.txt') # file to process
for desp in process(arquivo):
print desp # can print directly here.
print '-' * 20
if __name__ == '__main__':
main()