Sun, 28 May 2006

:: First Post

This is the first post in my blog.

[12:31] 评注(4) | # 永久链接 ^{.t2t

.moin} | add into del.icio.us

:: /Zen/pythonic/tryt2t.py

PREFORMATTER_ID = 'txt2tags'
FILE_EXT = 't2t'
__version__ = '$Id: tryt2t.py 299 2006-01-16 09:24:05Z zoomq $'
__author__ = 'Zoom.Quiet <Zoom dot Quiet  at gmail.com>'
#T2T = "/usr/local/bin/txt2tags"
T2T = "t2t"


def cb_entryparser(args):
    args['t2t'] = parse
    #args[FILE_EXT] = readfile
    return args


"""
def parse(filename):
    #html = publish_string(story, writer_name='html')
    import os
    act = T2T+" -t html -H --toc %s"%filename
    html = act
    html += os.popen(act).read().strip()
    #return html[html.find('<body>') + 6:html.find('</body>')]
    return html
"""
#def parse(filename, request):
def parse(filename):
    import os, sys
    from StringIO import StringIO
    # open own source
    #config = request.getConfiguration()
    act = T2T+" -t html -H --toc -o - %s"%filename
    #source = open(filename).read()
    #out = StringIO()

    #html = os.popen(act).read().strip()
    print act
    #print os.popen(act).read().strip()
    # write colorized version to "python.html"
    #Parser(source, out).format(None, None)

    #print out.getvalue()
    """
    entryData = {'body' : out.getvalue(),
                 'title' : filename.replace(config['datadir'], '')}
    return entryData
    """


parse("py-code-rule.t2t")

[12:31] 评注(0) | # 永久链接 ^{.t2t

.moin} | add into del.icio.us

del.icio.us | 分类 /Zen/pythonic

:: /Techic/py4zh/zh2utf8.py

"""Auto converter encodings to utf8
It will test utf8,gbk,big5,jp,kr to converter

发件人: HuangJiahua <jhuangjiahua@gmail.com> 
邮送域: googlegroups.com
回复: python-cn@googlegroups.com
收件人: "python.cn" <python-cn@googlegroups.com>
日期: 2006-1-16 上午12:11
主题: Re: 请问怎样得到一个文件的编码？
http://groups.google.com/group/python-cn/browse_frm/thread/3544d5a05783dc96

"""

#!/usr/bin/python
# coding:UTF-8
# Author: Huang Jiahua <jhuangjiahua@gmail.com>
#测试的编码类型
encc=''
def zh2utf8(stri):
       """Auto converter encodings to utf8

       It will test utf8,gbk,big5,jp,kr to converter"""
       global encc
       for c in ('utf-8', 'gbk', 'big5', 'jp',
'euc_kr','utf16','utf32'):
               encc = c
               try:
                       return stri.decode(c).encode('utf8')
               except:
                       pass
       encc = 'unk'
       return stri

if __name__=="__main__":
       # 命令行测试
       import sys
##      sys.setappdefaultencoding('unicode')
       if len(sys.argv) > 1:
               stri = sys.argv[1]
       else:
               stri = sys.stdin.read()
       print zh2utf8(stri)
       print 'encc:',encc

[12:31] 评注(0) | # 永久链接 ^{.t2t

.moin} | add into del.icio.us

del.icio.us | 分类 /Techic/py4zh

:: /Techic/py4zh/autoDetectXMLEncoding.py

"""http://aspn.activestate.com/ASPN/Cookbook/Python/Recipe/52257
Title: Auto-detect XML encoding
Submitter: Paul Prescod (other recipes)
Last Updated: 2001/03/14
Version no: 1.0
Category: XML
推荐:: 发件人: 清风 <paradise.qingfeng@gmail.com>        
回复: python-chinese@lists.python.cn
收件人: python-chinese@lists.python.cn
日期: 2006-1-18 上午1:27
主题: Re: [python-chinese] 如何取得一个文本的编码格式？
"""
import codecs, encodings

"""Caller will hand this library a buffer and ask it to either convert
it or auto-detect the type."""

# None represents a potentially variable byte. "##" in the XML spec... 
autodetect_dict={ # bytepattern     : ("name",              
                (0x00, 0x00, 0xFE, 0xFF) : ("ucs4_be"),
                (0xFF, 0xFE, 0x00, 0x00) : ("ucs4_le"),
                (0xFE, 0xFF, None, None) : ("utf_16_be"),
                (0xFF, 0xFE, None, None) : ("utf_16_le"),
                (0x00, 0x3C, 0x00, 0x3F) : ("utf_16_be"),
                (0x3C, 0x00, 0x3F, 0x00) : ("utf_16_le"),
                (0x3C, 0x3F, 0x78, 0x6D): ("utf_8"),
                (0x4C, 0x6F, 0xA7, 0x94): ("EBCDIC")
                 }

def autoDetectXMLEncoding(buffer):
    """ buffer -> encoding_name
    The buffer should be at least 4 bytes long.
        Returns None if encoding cannot be detected.
        Note that encoding_name might not have an installed
        decoder (e.g. EBCDIC)
    """
    # a more efficient implementation would not decode the whole
    # buffer at once but otherwise we'd have to decode a character at
    # a time looking for the quote character...that's a pain

    encoding = "utf_8" # according to the XML spec, this is the default
                          # this code successively tries to refine the default
                          # whenever it fails to refine, it falls back to 
                          # the last place encoding was set.
    bytes = (byte1, byte2, byte3, byte4) = tuple(map(ord, buffer[0:4]))
    enc_info = autodetect_dict.get(bytes, None)

    if not enc_info: # try autodetection again removing potentially 
                     # variable bytes
        bytes = (byte1, byte2, None, None)
        enc_info = autodetect_dict.get(bytes)


    if enc_info:
        encoding = enc_info # we've got a guess... these are
                            #the new defaults

        # try to find a more precise encoding using xml declaration
        secret_decoder_ring = codecs.lookup(encoding)[1]
        (decoded,length) = secret_decoder_ring(buffer)
        first_line = decoded.split("\n")[0]
        if first_line and first_line.startswith(u"<?xml"):
            encoding_pos = first_line.find(u"encoding")
            if encoding_pos!=-1:
                # look for double quote
                quote_pos=first_line.find('"', encoding_pos)

                if quote_pos==-1:                 # look for single quote
                    quote_pos=first_line.find("'", encoding_pos)

                if quote_pos>-1:
                    quote_char,rest=(first_line[quote_pos],
                                                first_line[quote_pos+1:])
                    encoding=rest[:rest.find(quote_char)]

    return encoding