| OLD | NEW |
|---|
| (Empty) |
| 1 #!/usr/bin/env python | |
| 2 # Copyright (c) 2011 The Chromium Authors. All rights reserved. | |
| 3 # Use of this source code is governed by a BSD-style license that can be | |
| 4 # found in the LICENSE file. | |
| 5 | |
| 6 """Converts profile datasets to dictionary list for Autofill profiles. | |
| 7 | |
| 8 Used for test autofill.AutofillTest.testMergeDuplicateProfilesInAutofill. | |
| 9 Can be used as a stand alone script with -h to print out help text by running: | |
| 10 python autofill_dataset_converter.py -h | |
| 11 """ | |
| 12 | |
| 13 import codecs | |
| 14 import logging | |
| 15 import os | |
| 16 import re | |
| 17 import sys | |
| 18 | |
| 19 | |
| 20 class _NullHandler(logging.Handler): | |
| 21 """Prevents warning when running in quiet mode.""" | |
| 22 def emit(self, record): | |
| 23 pass | |
| 24 | |
| 25 | |
| 26 class DatasetConverter(object): | |
| 27 _fields = [ | |
| 28 u'NAME_FIRST', | |
| 29 u'NAME_MIDDLE', | |
| 30 u'NAME_LAST', | |
| 31 u'EMAIL_ADDRESS', | |
| 32 u'COMPANY_NAME', | |
| 33 u'ADDRESS_HOME_LINE1', | |
| 34 u'ADDRESS_HOME_LINE2', | |
| 35 u'ADDRESS_HOME_CITY', | |
| 36 u'ADDRESS_HOME_STATE', | |
| 37 u'ADDRESS_HOME_ZIP', | |
| 38 u'ADDRESS_HOME_COUNTRY', | |
| 39 u'PHONE_HOME_WHOLE_NUMBER', | |
| 40 ] | |
| 41 _record_length = len(_fields) | |
| 42 _output_pattern = u'{' | |
| 43 for key in _fields: | |
| 44 _output_pattern += u"u'%s': u'%%s', " % key | |
| 45 _output_pattern = _output_pattern[:-1] + '},' | |
| 46 _re_single_quote = re.compile("'", re.UNICODE) | |
| 47 _logger = logging.getLogger(__name__) | |
| 48 _logger.addHandler(_NullHandler()) | |
| 49 _log_handlers = {'StreamHandler': None} | |
| 50 | |
| 51 def __init__(self, input_filename, output_filename=None, | |
| 52 logging_level=None): | |
| 53 """Constructs a dataset converter object. | |
| 54 | |
| 55 Full input pattern: | |
| 56 '(?P<NAME_FIRST>.*?)\|(?P<MIDDLE_NAME>.*?)\|(?P<NAME_LAST>.*?)\| | |
| 57 (?P<EMAIL_ADDRESS>.*?)\|(?P<COMPANY_NAME>.*?)\|(?P<ADDRESS_HOME_LINE1>.*?) | |
| 58 \|(?P<ADDRESS_HOME_LINE2>.*?)\|(?P<ADDRESS_HOME_CITY>.*?)\| | |
| 59 (?P<ADDRESS_HOME_STATE>.*?)\|(?P<ADDRESS_HOME_ZIP>.*?)\| | |
| 60 (?P<ADDRESS_HOME_COUNTRY>.*?)\|(?P<PHONE_HOME_WHOLE_NUMBER>.*?)$' | |
| 61 | |
| 62 Full ouput pattern: | |
| 63 "{u'NAME_FIRST': u'%s', u'NAME_MIDDLE': u'%s', u'NAME_LAST': u'%s', | |
| 64 u'EMAIL_ADDRESS': u'%s', u'COMPANY_NAME': u'%s', u'ADDRESS_HOME_LINE1': | |
| 65 u'%s', u'ADDRESS_HOME_LINE2': u'%s', u'ADDRESS_HOME_CITY': u'%s', | |
| 66 u'ADDRESS_HOME_STATE': u'%s', u'ADDRESS_HOME_ZIP': u'%s', | |
| 67 u'ADDRESS_HOME_COUNTRY': u'%s', u'PHONE_HOME_WHOLE_NUMBER': u'%s',}," | |
| 68 | |
| 69 Args: | |
| 70 input_filename: name and path of the input dataset. | |
| 71 output_filename: name and path of the converted file, default is none. | |
| 72 logging_level: set verbosity levels, default is ERROR. | |
| 73 | |
| 74 Raises: | |
| 75 IOError: error if input file does not exist. | |
| 76 """ | |
| 77 if logging_level: | |
| 78 if not self._log_handlers['StreamHandler']: | |
| 79 console = logging.StreamHandler() | |
| 80 console.setLevel(logging_level) | |
| 81 self._log_handlers['StreamHandler'] = console | |
| 82 self._logger.addHandler(console) | |
| 83 self._logger.setLevel(logging_level) | |
| 84 else: | |
| 85 if self._log_handlers['StreamHandler']: | |
| 86 self._logger.removeHandler(self._log_handlers['StreamHandler']) | |
| 87 self._log_handler['StreamHandler'] = None | |
| 88 | |
| 89 self._input_filename = os.path.join(os.path.dirname(sys.argv[0]), | |
| 90 input_filename) | |
| 91 if not os.path.isfile(self._input_filename): | |
| 92 msg = 'File "%s" does not exist' % self._input_filename | |
| 93 self._logger.error(msg) | |
| 94 raise IOError(msg) | |
| 95 self._output_filename = output_filename | |
| 96 | |
| 97 def _CreateDictionaryFromRecord(self, record): | |
| 98 """Constructs and returns a dictionary from a record in the dataset file. | |
| 99 | |
| 100 Escapes single quotation first and uses split('|') to separate values. | |
| 101 The method assumes a valid record always contains at least one "|" | |
| 102 character. | |
| 103 Example: | |
| 104 Take an argument as a string u'John|Doe|Mountain View' | |
| 105 and returns a dictionary | |
| 106 { | |
| 107 u'NAME_FIRST': u'John', | |
| 108 u'NAME_LAST': u'Doe', | |
| 109 u'ADDRESS_HOME_CITY': u'Mountain View', | |
| 110 } | |
| 111 | |
| 112 Args: | |
| 113 record: row of record from the dataset file. | |
| 114 | |
| 115 Returns: | |
| 116 None if the current record line is invalid or a dictionary representing a | |
| 117 single record from the dataset file. | |
| 118 """ | |
| 119 # Ignore irrelevant record lines that do not contain '|'. | |
| 120 if not '|' in record: | |
| 121 return | |
| 122 # Escaping single quote: "'" -> "\'" | |
| 123 record = self._re_single_quote.sub(r"\'", record) | |
| 124 record_list = record.split('|') | |
| 125 if record_list: | |
| 126 # Check for case when a record may have more or less fields than expected. | |
| 127 if len(record_list) != self._record_length: | |
| 128 self._logger.warning( | |
| 129 'A "|" separated line has %d fields instead of %d: %s' % ( | |
| 130 len(record_list), self._record_length, record)) | |
| 131 return | |
| 132 out_record = {} | |
| 133 for i, key in enumerate(self._fields): | |
| 134 out_record[key] = record_list[i] | |
| 135 return out_record | |
| 136 | |
| 137 def Convert(self): | |
| 138 """Function to convert input data into the desired output format. | |
| 139 | |
| 140 Returns: | |
| 141 List that holds all the dictionaries. | |
| 142 """ | |
| 143 input_file = open(self._input_filename) | |
| 144 if self._output_filename: | |
| 145 output_file = codecs.open(self._output_filename, mode='wb', | |
| 146 encoding='utf-8-sig') | |
| 147 else: | |
| 148 output_file = None | |
| 149 try: | |
| 150 list_of_dict = [] | |
| 151 i = 0 | |
| 152 if output_file: | |
| 153 output_file.write('[') | |
| 154 output_file.write(os.linesep) | |
| 155 for line in input_file.readlines(): | |
| 156 line = line.strip() | |
| 157 if not line: | |
| 158 continue | |
| 159 line = unicode(line, 'UTF-8') | |
| 160 output_record = self._CreateDictionaryFromRecord(line) | |
| 161 if output_record: | |
| 162 i += 1 | |
| 163 list_of_dict.append(output_record) | |
| 164 output_line = self._output_pattern % tuple( | |
| 165 [output_record[key] for key in self._fields]) | |
| 166 if output_file: | |
| 167 output_file.write(output_line) | |
| 168 output_file.write(os.linesep) | |
| 169 self._logger.info('%d: %s' % (i, line.encode('UTF-8'))) | |
| 170 self._logger.info('\tconverted to: %s' % output_line.encode('UTF-8')) | |
| 171 if output_file: | |
| 172 output_file.write(']') | |
| 173 output_file.write(os.linesep) | |
| 174 self._logger.info('%d lines converted SUCCESSFULLY!' % i) | |
| 175 self._logger.info('--- FINISHED ---') | |
| 176 return list_of_dict | |
| 177 finally: | |
| 178 if output_file: | |
| 179 output_file.close() | |
| 180 | |
| 181 | |
| 182 def main(): | |
| 183 from optparse import OptionParser | |
| 184 input_filename = os.path.join('..', 'data', 'autofill', 'dataset.txt') | |
| 185 output_filename = os.path.join('..', 'data', 'autofill', | |
| 186 'dataset_duplicate-profiles.txt') | |
| 187 parser = OptionParser() | |
| 188 parser.add_option('-i', '--input', dest='input_filename', | |
| 189 default=input_filename, | |
| 190 help='convert FILE [defaults to "%s"]' % input_filename, | |
| 191 metavar='FILE') | |
| 192 parser.add_option('-o', '--output', dest='output_filename', | |
| 193 default=output_filename, | |
| 194 help='write output to FILE [defaults to "%s"]' % | |
| 195 output_filename, metavar='FILE') | |
| 196 parser.add_option('-v', '--verbose', action='store_true', dest='verbose', | |
| 197 default=True, help='display all [default]') | |
| 198 parser.add_option('-q', '--quiet', action='store_false', dest='verbose', | |
| 199 help='display nothing') | |
| 200 parser.add_option('-l', '--log', dest='logging_level', default=None, | |
| 201 help='specify logging LEVEL: "info", "warning" or "error"', | |
| 202 metavar='LEVEL') | |
| 203 | |
| 204 (options, args) = parser.parse_args() | |
| 205 if args: | |
| 206 parser.print_help() | |
| 207 return 1 | |
| 208 if not options.verbose: | |
| 209 options.logging_level = None | |
| 210 if options.verbose and not options.logging_level: | |
| 211 options.logging_level = 'info' | |
| 212 if options.logging_level: | |
| 213 if 'info' in options.logging_level.lower(): | |
| 214 options.logging_level = logging.INFO | |
| 215 elif 'warn' in options.logging_level.lower(): | |
| 216 options.logging_level = logging.WARNING | |
| 217 elif 'error' in options.logging_level.lower(): | |
| 218 options.logging_level = logging.ERROR | |
| 219 | |
| 220 c = DatasetConverter(options.input_filename, options.output_filename, | |
| 221 options.logging_level) | |
| 222 c.Convert() | |
| 223 return 0 | |
| 224 | |
| 225 | |
| 226 if __name__ == '__main__': | |
| 227 sys.exit(main()) | |
| OLD | NEW |
|---|
Chromium Code Reviews
Issue 10855253:
Convert the autofill pyauto tests to browser tests, and remove all the supporting automation hooks … (Closed)
Base URL: svn://chrome-svn/chrome/trunk/src/