hi guys, sorry am feeling a bit prolifit lately.
today's show, is: 〈Fuck Python〉 http://xahlee.org/comp/fuck_python.html ------------------------------------ Fuck Python By Xah Lee, 2012-04-08 fuck Python. just fucking spend 2 hours and still going. here's the short story. so recently i switched to a Windows version of python. Now, Windows version takes path using win backslash, instead of cygwin slash. This fucking broke my find/replace scripts that takes a dir level as input. Because i was counting slashes. Ok no problem. My sloppiness. After all, my implementation wasn't portable. So, let's fix it. After a while, discovered there's the 「os.sep」. Ok, replace 「"/"」 to 「os.sep」, done. Then, bang, all hell went lose. Because, the backslash is used as escape in string, so any regex that manipulate path got fucked majorly. So, now you need to find a quoting mechanism. Then, fuck python doc incomprehensible scattered comp-sci-r-us BNF shit. Then, fuck python for “os.path” and “os” modules then string object and string functions inconsistent ball. And FUCK Guido who wants to fuck change python for his idiotic OOP concept of “elegance” so that some of these are deprecated. So after several exploration of “repr()”, “format()”, “‹str›.count()”, “os.path.normpath()”, “re.split()”, “len(re.search().group())” etc, after a long time, let's use “re.escape()”. 2 hours has passed. Also, discovered that “os.path.walk” is now deprecated, and one is supposed to use the sparkling “os.walk”. In the process of refreshing my python, the “os.path.walk” semantics is really one fucked up fuck. Meanwhile, the “os.walk” went into incomprehensible OOP object and iterators fuck. now, it's close to 3 hours. This fix is supposed to be done in 10 min. I'd have done it in elisp in just 10 minutes if not for my waywardness. This is Before def process_file(dummy, current_dir, file_list): current_dir_level = len(re.split("/", current_dir)) - len(re.split("/", input_dir)) cur_file_level = current_dir_level+1 if min_level <= cur_file_level <= max_level: for a_file in file_list: if re.search(r"\.html$", a_file, re.U) and os.path.isfile(current_dir + "/" + a_file): replace_string_in_file(current_dir + "/" + a_file) This is After def process_file(dummy, current_dir, file_list): current_dir = os.path.normpath(current_dir) cur_dir_level = re.sub( "^" + re.escape(input_dir), "", current_dir).count( os.sep) cur_file_level = cur_dir_level + 1 if min_level <= cur_file_level <= max_level: for a_file in file_list: if re.search(r"\.html$", a_file, re.U) and os.path.isfile(current_dir + re.escape(os.sep) + a_file): replace_string_in_file(current_dir + os.sep + a_file) # print "%d %s" % (cur_file_level, (current_dir + os.sep + a_file)) Complete File # -*- coding: utf-8 -*- # Python # find & replace strings in a dir import os, sys, shutil, re # if this this is not empty, then only these files will be processed my_files = [] input_dir = "c:/Users/h3/web/xahlee_org/lojban/hrefgram2/" input_dir = "/cygdrive/c/Users/h3/web/zz" input_dir = "c:/Users/h3/web/xahlee_org/" min_level = 2; # files and dirs inside input_dir are level 1. max_level = 2; # inclusive print_no_change = False find_replace_list = [ ( u"""<iframe style="width:100%;border:none" src="http://xahlee.org/ footer.html"></iframe>""", u"""<iframe style="width:100%;border:none" src="../footer.html"></ iframe>""", ), ] def replace_string_in_file(file_path): "Replaces all findStr by repStr in file file_path" temp_fname = file_path + "~lc~" backup_fname = file_path + "~bk~" # print "reading:", file_path input_file = open(file_path, "rb") file_content = unicode(input_file.read(), "utf-8") input_file.close() num_replaced = 0 for a_pair in find_replace_list: num_replaced += file_content.count(a_pair[0]) output_text = file_content.replace(a_pair[0], a_pair[1]) file_content = output_text if num_replaced > 0: print "◆ ", num_replaced, " ", file_path.replace("\\", "/") shutil.copy2(file_path, backup_fname) output_file = open(file_path, "r+b") output_file.read() # we do this way instead of “os.rename” to preserve file creation date output_file.seek(0) output_file.write(output_text.encode("utf-8")) output_file.truncate() output_file.close() else: if print_no_change == True: print "no change:", file_path # os.remove(file_path) # os.rename(temp_fname, file_path) def process_file(dummy, current_dir, file_list): current_dir = os.path.normpath(current_dir) cur_dir_level = re.sub( "^" + re.escape(input_dir), "", current_dir).count( os.sep) cur_file_level = cur_dir_level + 1 if min_level <= cur_file_level <= max_level: for a_file in file_list: if re.search(r"\.html$", a_file, re.U) and os.path.isfile(current_dir + re.escape(os.sep) + a_file): replace_string_in_file(current_dir + os.sep + a_file) # print "%d %s" % (cur_file_level, (current_dir + os.sep + a_file)) input_dir = os.path.normpath(input_dir) if (len(my_files) != 0): for my_file in my_files: replace_string_in_file(os.path.normpath(my_file) ) else: os.path.walk(input_dir, process_file, "dummy") print "Done." -- http://mail.python.org/mailman/listinfo/python-list
