Mercurial Repositories > eric / file comparison
comparison: UtilitiesPython2/Tools.py
UtilitiesPython2/Tools.py
- branch
- Py2 comp.
- changeset 3456
- 96232974dcdb
- parent 3178
- f25fc1364c88
- parent 3445
- bf95eac5ce12
- child 3484
- 645c12de6b0c
equal
deleted
inserted
replaced
| 3178:f25fc1364c88 | 3456:96232974dcdb |
|---|---|
| 1 # -*- coding: utf-8 -*- | |
| 2 | |
| 3 # Copyright (c) 2011 - 2014 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 | |
| 19 def get_coding(text): | |
| 20 """ | |
| 21 Function to get the coding of a text. | |
| 22 | |
| 23 @param text text to inspect (string) | |
| 24 @return coding string | |
| 25 """ | |
| 26 lines = text.splitlines() | |
| 27 for coding in coding_regexps: | |
| 28 coding_re = coding[1] | |
| 29 head = lines[:coding[0]] | |
| 30 for l in head: | |
| 31 m = coding_re.search(l) | |
| 32 if m: | |
| 33 return m.group(1).lower() | |
| 34 return None | |
| 35 | |
| 36 | |
| 37 def decode(text): | |
| 38 """ | |
| 39 Function to decode a text. | |
| 40 | |
| 41 @param text text to decode (string) | |
| 42 @return decoded text and encoding | |
| 43 """ | |
| 44 try: | |
| 45 if text.startswith(BOM_UTF8): | |
| 46 # UTF-8 with BOM | |
| 47 return unicode(text[len(BOM_UTF8):], 'utf-8'), 'utf-8-bom' | |
| 48 elif text.startswith(BOM_UTF16): | |
| 49 # UTF-16 with BOM | |
| 50 return unicode(text[len(BOM_UTF16):], 'utf-16'), 'utf-16' | |
| 51 elif text.startswith(BOM_UTF32): | |
| 52 # UTF-32 with BOM | |
| 53 return unicode(text[len(BOM_UTF32):], 'utf-32'), 'utf-32' | |
| 54 coding = get_coding(text) | |
| 55 if coding: | |
| 56 return unicode(text, coding), coding | |
| 57 except (UnicodeError, LookupError): | |
| 58 pass | |
| 59 | |
| 60 # Assume UTF-8 | |
| 61 try: | |
| 62 return unicode(text, 'utf-8'), 'utf-8-guessed' | |
| 63 except (UnicodeError, LookupError): | |
| 64 pass | |
| 65 | |
| 66 # Assume Latin-1 (behaviour before 3.7.1) | |
| 67 return unicode(text, "latin-1"), 'latin-1-guessed' | |
| 68 | |
| 69 | |
| 70 def readEncodedFile(filename): | |
| 71 """ | |
| 72 Function to read a file and decode its contents into proper text. | |
| 73 | |
| 74 @param filename name of the file to read (string) | |
| 75 @return tuple of decoded text and encoding (string, string) | |
| 76 """ | |
| 77 f = open(filename) | |
| 78 text = f.read() | |
| 79 f.close() | |
| 80 return decode(text) | |
| 81 | |
| 82 | |
| 83 def normalizeCode(codestring): | |
| 84 """ | |
| 85 Function to normalize the given code. | |
| 86 | |
| 87 @param codestring code to be normalized (string) | |
| 88 @return normalized code (string) | |
| 89 """ | |
| 90 if type(codestring) == type(u""): | |
| 91 codestring = codestring.encode('utf-8') | |
| 92 codestring = codestring.replace("\r\n", "\n").replace("\r", "\n") | |
| 93 | |
| 94 if codestring and codestring[-1] != '\n': | |
| 95 codestring = codestring + '\n' | |
| 96 | |
| 97 return codestring | |
| 98 | |
| 99 | |
| 100 def extractLineFlags(line, startComment="#", endComment=""): | |
| 101 """ | |
| 102 Function to extract flags starting and ending with '__' from a line | |
| 103 comment. | |
| 104 | |
| 105 @param line line to extract flags from (string) | |
| 106 @keyparam startComment string identifying the start of the comment (string) | |
| 107 @keyparam endComment string identifying the end of a comment (string) | |
| 108 @return list containing the extracted flags (list of strings) | |
| 109 """ | |
| 110 flags = [] | |
| 111 | |
| 112 pos = line.rfind(startComment) | |
| 113 if pos >= 0: | |
| 114 comment = line[pos + len(startComment):].strip() | |
| 115 if endComment: | |
| 116 comment = comment.replace("endComment", "") | |
| 117 flags = [f.strip() for f in comment.split() | |
| 118 if (f.startswith("__") and f.endswith("__"))] | |
| 119 return flags | |
| 120 | |
| 121 # | |
| 122 # eflag: FileType = Python2 |
