Mercurial Repositories > eric / file comparison
comparison: UtilitiesPython2/Py2SyntaxChecker.py
UtilitiesPython2/Py2SyntaxChecker.py
- changeset 795
- 917f1945355c
- child 802
- e8882d16384c
equal
deleted
inserted
replaced
| 794:e338e1e8f3ca | 795:917f1945355c |
|---|---|
| 1 # -*- coding: utf-8 -*- | |
| 2 | |
| 3 # Copyright (c) 2011 Detlev Offenbach <detlev@die-offenbachs.de> | |
| 4 # | |
| 5 | |
| 6 """ | |
| 7 Module implementing the syntax check for Python 2. | |
| 8 """ | |
| 9 | |
| 10 import sys | |
| 11 import re | |
| 12 import traceback | |
| 13 from codecs import BOM_UTF8, BOM_UTF16, BOM_UTF32 | |
| 14 | |
| 15 coding_regexps = [ | |
| 16 (2, re.compile(r'''coding[:=]\s*([-\w_.]+)''')), | |
| 17 (1, re.compile(r'''<\?xml.*\bencoding\s*=\s*['"]([-\w_.]+)['"]\?>''')), | |
| 18 ] | |
| 19 | |
| 20 def get_coding(text): | |
| 21 """ | |
| 22 Function to get the coding of a text. | |
| 23 | |
| 24 @param text text to inspect (string) | |
| 25 @return coding string | |
| 26 """ | |
| 27 lines = text.splitlines() | |
| 28 for coding in coding_regexps: | |
| 29 coding_re = coding[1] | |
| 30 head = lines[:coding[0]] | |
| 31 for l in head: | |
| 32 m = coding_re.search(l) | |
| 33 if m: | |
| 34 return m.group(1).lower() | |
| 35 return None | |
| 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 def compile(file): | |
| 70 """ | |
| 71 Function to compile one Python source file to Python bytecode. | |
| 72 | |
| 73 @param file source filename (string) | |
| 74 @return A tuple indicating status (1 = an error was found), the | |
| 75 filename, the linenumber, the code string and the error message | |
| 76 (boolean, string, string, string, string). The values are only | |
| 77 valid, if the status equals 1. | |
| 78 """ | |
| 79 import __builtin__ | |
| 80 try: | |
| 81 f = open(file) | |
| 82 codestring, encoding = decode(f.read()) | |
| 83 f.close() | |
| 84 except IOError, msg: | |
| 85 return (1, file, "1", "", "I/O Error: %s" % unicode(msg)) | |
| 86 | |
| 87 if type(codestring) == type(u""): | |
| 88 codestring = codestring.encode('utf-8') | |
| 89 codestring = codestring.replace("\r\n","\n") | |
| 90 codestring = codestring.replace("\r","\n") | |
| 91 | |
| 92 if codestring and codestring[-1] != '\n': | |
| 93 codestring = codestring + '\n' | |
| 94 | |
| 95 try: | |
| 96 if type(file) == type(u""): | |
| 97 file = file.encode('utf-8') | |
| 98 | |
| 99 if file.endswith('.ptl'): | |
| 100 try: | |
| 101 import quixote.ptl_compile | |
| 102 except ImportError: | |
| 103 return (0, None, None, None, None) | |
| 104 template = quixote.ptl_compile.Template(codestring, file) | |
| 105 template.compile() | |
| 106 codeobject = template.code | |
| 107 else: | |
| 108 codeobject = __builtin__.compile(codestring, file, 'exec') | |
| 109 except SyntaxError, detail: | |
| 110 lines = traceback.format_exception_only(SyntaxError, detail) | |
| 111 match = re.match('\s*File "(.+)", line (\d+)', | |
| 112 lines[0].replace('<string>', '%s' % file)) | |
| 113 if match is not None: | |
| 114 fn, line = match.group(1, 2) | |
| 115 if lines[1].startswith('SyntaxError:'): | |
| 116 code = "" | |
| 117 error = re.match('SyntaxError: (.+)', lines[1]).group(1) | |
| 118 else: | |
| 119 code = re.match('(.+)', lines[1]).group(1) | |
| 120 error = "" | |
| 121 for seLine in lines[2:]: | |
| 122 if seLine.startswith('SyntaxError:'): | |
| 123 error = re.match('SyntaxError: (.+)', seLine).group(1) | |
| 124 else: | |
| 125 fn = detail.filename | |
| 126 line = detail.lineno and detail.lineno or 1 | |
| 127 code = "" | |
| 128 error = detail.msg | |
| 129 return (1, fn, line, code, error) | |
| 130 except ValueError, detail: | |
| 131 try: | |
| 132 fn = detail.filename | |
| 133 line = detail.lineno | |
| 134 error = detail.msg | |
| 135 except AttributeError: | |
| 136 fn = file | |
| 137 line = 1 | |
| 138 error = unicode(detail) | |
| 139 code = "" | |
| 140 return (1, fn, line, code, error) | |
| 141 except StandardError, detail: | |
| 142 try: | |
| 143 fn = detail.filename | |
| 144 line = detail.lineno | |
| 145 code = "" | |
| 146 error = detail.msg | |
| 147 return (1, fn, line, code, error) | |
| 148 except: # this catchall is intentional | |
| 149 pass | |
| 150 | |
| 151 return (0, None, None, None, None) | |
| 152 | |
| 153 if __name__ == "__main__": | |
| 154 if len(sys.argv) != 2: | |
| 155 print "ERROR" | |
| 156 print "" | |
| 157 print "" | |
| 158 print "" | |
| 159 print "No file name given." | |
| 160 else: | |
| 161 filename = sys.argv[1] | |
| 162 res, fname, line, code, error = compile(filename) | |
| 163 | |
| 164 if res: | |
| 165 print "ERROR" | |
| 166 else: | |
| 167 print "NO_ERROR" | |
| 168 print fname | |
| 169 print line | |
| 170 print code | |
| 171 print error | |
| 172 | |
| 173 sys.exit(0) | |
| 174 | |
| 175 # | |
| 176 # eflag: FileType = Python2 |
