summaryrefslogtreecommitdiffstats
path: root/util
diff options
context:
space:
mode:
Diffstat (limited to 'util')
-rwxr-xr-xutil/bin/ukrepl109
1 files changed, 109 insertions, 0 deletions
diff --git a/util/bin/ukrepl b/util/bin/ukrepl
new file mode 100755
index 00000000..9b084027
--- /dev/null
+++ b/util/bin/ukrepl
@@ -0,0 +1,109 @@
+#!/usr/bin/python2
+# -*- coding: utf-8 -*-
+import sys
+
+wont_change = { ' ' : ' ' ,
+ '\n' : '\n'
+ }
+def fixed_width_replace(char): #f
+ if char in wont_change: return unicode(char)
+ else:
+ try:
+ if not 32 < ord(char) < 126: raise Exception("not in range")
+ return unichr(0xFF00 + ord(char)-32)
+ except:
+ return char
+
+cyrillic_dict = {
+ 'A' : u'А', 'a' : 'а','Ä' : u'Ӓ', 'ä' : u'ӓ',
+ 'B' : u'В',
+ 'c' : u'с',
+ 'E' : u'Е',
+ 'e' : u'е',
+ 'H' : u'Н',
+ 'I' : u'І', 'i' : u'і',
+ 'j' : u'ј','J' : u'Ј',
+ 'K' : u'К',
+ 'M' : u'М',
+ 'O' : u'О', 'o' : u'о', 'Ö' : u'Ӧ', 'ö' : u'ӧ',
+ 'P' : u'Р', 'p' : u'р',
+ 'S' : u'Ѕ',
+ 'T' : u'г'
+ }
+
+def cyrillic_replace(char): #c
+ return cyrillic_dict.get(char,char)
+historic_latin_dict = {
+ 'B' : u'Ɓ',
+ 'b' : u'ƅ',
+ 'u' : u'ư',
+ 'U' : u'Ư',
+ '' : 'Ǟ',
+ #'5' : 'ƽ',
+ 'o' : 'ơ',
+ 'O' : 'Ơ',
+ '5' : 'Ƽ'
+ }
+def historic_latin(char): #H
+ return historic_latin_dict.get(char,char)
+punctuation_dict = {
+ '!' : u'ǃ',
+ '\'': u'’',
+ '\"': u'ˮ',
+ '(' : u'⟨',
+ ')' : u'⟩',
+ ':' : u'ː',
+ ' ' : u' ',
+ # all different spaces, made for perfect trolling
+ #' ' : u' ',
+ #' ' : u' ',
+ #' ' : u'⁠',
+ #'-' : u'‒',
+ #'-' : u'—',
+ #'-' : u'―',
+ #'-' : u'‐',
+ #'-' : u'⁃',
+ '-' : u'–',
+ '_' : u'−',
+ '~' : u'⁓',
+ #'~' : u'∼',
+ #'~' : u'〜',
+
+ }
+def punctuation(char): #p
+ return punctuation_dict.get(char,char)
+def helpme():
+ print "usage %s [modes]" % sys.argv[0]
+ print "modes:"
+ print " c -- cyrillic replace"
+ print " f -- fixed width"
+ print " p -- replace punctuation"
+ print " H -- replace with historic latin chars"
+ print " h -- this message"
+ sys.exit(0)
+
+#parsing happens inside the nested loop
+modes = ''.join(sys.argv[1:])
+# sane defaults if no mode given
+if not modes : modes = "f"
+
+if 'h' in modes: helpme()
+
+for line in sys.stdin:
+ for char in line:
+ for mode in modes:
+ if mode is 'c':
+ char = cyrillic_replace(char)
+ elif mode is 'f':
+ char = fixed_width_replace(char)
+ elif mode is 'H':
+ char = historic_latin(char)
+ elif mode is 'p':
+ char = punctuation(char)
+ else:
+ print "unknown mode %c" % mode
+ helpme()
+ try:
+ sys.stdout.write(char)
+ except:
+ sys.stdout.write(char.encode("utf-8"))