Mercurial Repositories > eric / file comparison
comparison: UtilitiesPython2/Tools.py
UtilitiesPython2/Tools.py
- changeset 805
- 83ca4d1ff648
- child 945
- 8cd4d08fa9f6
- child 1510
- e75ecf2bd9dd
equal
deleted
inserted
replaced
| 804:3465556892de | 805:83ca4d1ff648 |
|---|---|
| 1 # -*- coding: utf-8 -*- | |
| 2 | |
| 3 # Copyright (c) 2011 Detlev Offenbach <detlev@die-offenbachs.de> | |
| 4 # | |
| 5 | |
| 6 """ | |
| 7 Module implementing tool functions. | |
| 8 """ | |
| 9 | |
| 10 import re | |
| 11 from codecs import BOM_UTF8, BOM_UTF16, BOM_UTF32 | |
| 12 | |
| 13 coding_regexps = [ | |
| 14 (2, re.compile(r'''coding[:=]\s*([-\w_.]+)''')), | |
| 15 (1, re.compile(r'''<\?xml.*\bencoding\s*=\s*['"]([-\w_.]+)['"]\?>''')), | |
| 16 ] | |
| 17 | |
| 18 def get_coding(text): | |
| 19 """ | |
| 20 Function to get the coding of a text. | |
| 21 | |
| 22 @param text text to inspect (string) | |
| 23 @return coding string | |
| 24 """ | |
| 25 lines = text.splitlines() | |
| 26 for coding in coding_regexps: | |
| 27 coding_re = coding[1] | |
| 28 head = lines[:coding[0]] | |
| 29 for l in head: | |
| 30 m = coding_re.search(l) | |
| 31 if m: | |
| 32 return m.group(1).lower() | |
| 33 return None | |
| 34 | |
| 35 def decode(text): | |
| 36 """ | |
| 37 Function to decode a text. | |
| 38 | |
| 39 @param text text to decode (string) | |
| 40 @return decoded text and encoding | |
| 41 """ | |
| 42 try: | |
| 43 if text.startswith(BOM_UTF8): | |
| 44 # UTF-8 with BOM | |
| 45 return unicode(text[len(BOM_UTF8):], 'utf-8'), 'utf-8-bom' | |
| 46 elif text.startswith(BOM_UTF16): | |
| 47 # UTF-16 with BOM | |
| 48 return unicode(text[len(BOM_UTF16):], 'utf-16'), 'utf-16' | |
| 49 elif text.startswith(BOM_UTF32): | |
| 50 # UTF-32 with BOM | |
| 51 return unicode(text[len(BOM_UTF32):], 'utf-32'), 'utf-32' | |
| 52 coding = get_coding(text) | |
| 53 if coding: | |
| 54 return unicode(text, coding), coding | |
| 55 except (UnicodeError, LookupError): | |
| 56 pass | |
| 57 | |
| 58 # Assume UTF-8 | |
| 59 try: | |
| 60 return unicode(text, 'utf-8'), 'utf-8-guessed' | |
| 61 except (UnicodeError, LookupError): | |
| 62 pass | |
| 63 | |
| 64 # Assume Latin-1 (behaviour before 3.7.1) | |
| 65 return unicode(text, "latin-1"), 'latin-1-guessed' | |
| 66 | |
| 67 def readEncodedFile(filename): | |
| 68 """ | |
| 69 Function to read a file and decode it's contents into proper text. | |
| 70 | |
| 71 @param filename name of the file to read (string) | |
| 72 @return tuple of decoded text and encoding (string, string) | |
| 73 """ | |
| 74 f = open(filename) | |
| 75 text = f.read() | |
| 76 f.close() | |
| 77 return decode(text) | |
| 78 | |
| 79 def normalizeCode(codestring): | |
| 80 """ | |
| 81 Function to normalize the given code. | |
| 82 | |
| 83 @param codestring code to be normalized (string) | |
| 84 @return normalized code (string) | |
| 85 """ | |
| 86 if type(codestring) == type(u""): | |
| 87 codestring = codestring.encode('utf-8') | |
| 88 codestring = codestring.replace("\r\n","\n").replace("\r","\n") | |
| 89 | |
| 90 if codestring and codestring[-1] != '\n': | |
| 91 codestring = codestring + '\n' | |
| 92 | |
| 93 return codestring | |
| 94 | |
| 95 # | |
| 96 # eflag: FileType = Python2 |
