I need to read some large files (from 50k to 100k lines), structured in groups separated by empty lines. Each group start at the same pattern \"No.999999999 dd/mm/yyyy ZZZ
Another version with only one combined regular expression:
#!/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()
It looks good overall, but why do you have the line:
rpi = (line for line in rpi)
You can already iterate over the file object without this intermediate step.
It would be easier to help if you had a specific concern. Performance will depend greatly on the efficiency of the particular regex engine you are using. 100K lines in a single file doesn't sound that big, but again it all depends on your environment.
I use Expresso in my .NET development to test expressions for accuracy and performance. A Google search turned up Kodos, a GUI Python regex authoring tool.
That is pretty good. Below some suggestions, let me know if you like'em:
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()
I wouldn't use regex here. If you know that your lines will be starting with fixed strings, why not check those strings and write a logic around it?
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
Consider the above code as just the pseudocode.