【Python】Java转Python的一些水土不服

regular expression

java

String text = "你好啊，我的名字叫Ethan Hunt";
text = text.replaceAll("(.*?)([a-zA-Z]+)(.*?)", "$1<$2>$3");
System.out.println(text);

python

import re
text = '你好啊，我的名字叫Ethan Hunt'.decode('utf-8')
regex = re.sub(ur'(.*?)([a-z_A-Z]+)(.*?)', ur'\1<\2>\3', text)
print regex

你好啊，我的名字叫<Ethan> <Hunt>

如果想要多次使用而避免重复编译：

import re
regex = re.compile(ur'(.*?)([a-z_A-Z]+)(.*?)')
for content in some_file:
    content = regex.sub(ur'\1<\2>\3', content)

String.substring

text = 'Hello World'
print text[6:]

World

Also,

String.charAt

text = 'Hello World'
print text[1]

e

class toString

class Pair:
    def __init__(self, a, b):
        self.a = a
        self.b = b

    def __repr__(self):
        return '<Pair a:%d b:%d>' % (self.a, self.b)

    def __str__(self):
        return 'str <Pair a:%d b:%d>' % (self.a, self.b)

p = Pair(1, 2)
print p
print repr(p)
print str(p)
lst = [p]
print lst

str <Pair a:1 b:2>
<Pair a:1 b:2>
str <Pair a:1 b:2>
[<Pair a:1 b:2>]

获取文件所在目录的上一级目录

import os
os.path.abspath(os.path.join(os.path.dirname(__file__),os.path.pardir))

编码问题：csv - CSV File Reading and Writing

import csv, codecs, cStringIO

class UTF8Recoder:
    """
    Iterator that reads an encoded stream and reencodes the input to UTF-8
    """
    def __init__(self, f, encoding):
        self.reader = codecs.getreader(encoding)(f)

    def __iter__(self):
        return self

    def next(self):
        return self.reader.next().encode("utf-8")

class UnicodeReader:
    """
    A CSV reader which will iterate over lines in the CSV file "f",
    which is encoded in the given encoding.
    """

    def __init__(self, f, dialect=csv.excel, encoding="utf-8", **kwds):
        f = UTF8Recoder(f, encoding)
        self.reader = csv.reader(f, dialect=dialect, **kwds)

    def next(self):
        row = self.reader.next()
        return [unicode(s, "utf-8") for s in row]

    def __iter__(self):
        return self

class UnicodeWriter:
    """
    A CSV writer which will write rows to CSV file "f",
    which is encoded in the given encoding.
    """

    def __init__(self, f, dialect=csv.excel, encoding="utf-8", **kwds):
        # Redirect output to a queue
        self.queue = cStringIO.StringIO()
        self.writer = csv.writer(self.queue, dialect=dialect, **kwds)
        self.stream = f
        self.encoder = codecs.getincrementalencoder(encoding)()

    def writerow(self, row):
        self.writer.writerow([s.encode("utf-8") for s in row])
        # Fetch UTF-8 output from the queue ...
        data = self.queue.getvalue()
        data = data.decode("utf-8")
        # ... and reencode it into the target encoding
        data = self.encoder.encode(data)
        # write to the target stream
        self.stream.write(data)
        # empty queue
        self.queue.truncate(0)

    def writerows(self, rows):
        for row in rows:
            self.writerow(row)

Shanghai
2015.12.07