Test Autofill's ability to merge duplicate profiles and...

chrome/test/functional/dataset_converter.py

+#!/usr/bin/python
+# Copyright (c) 2011 The Chromium Authors. All rights reserved.
+# Use of this source code is governed by a BSD-style license that can be
+# found in the LICENSE file.
+
+"""Converts profile datasets to dictionary list for Autofill profiles.
+
+Used for test autofill.AutoFillTest.testMergeDuplicateProfilesInAutofill.
+"""
+
+import codecs
+import logging
+import os
+import re
+import sys
+
+
+class NullHandler(logging.Handler):
+  def emit(self, record):
+    pass

[dennis_jeffrey, 2011/02/16 19:43:29]

Right now it looks like you will never see any logging messages because all logs
are going through this NullHandler.  I think what you should do here is to set
the logging level dynamically, based on what is requested by the user:

(1) The user might be a PyAuto test, in which case they can pass the desired
verbosity level as input to the DatasetConverter constructor.

(2) The user might be running this as a standalone program using the main()
function, in which case you might want to provide a command-line option that can
let the user specify the desired logging level.

[dyu1, 2011/02/17 20:38:06]

Done.

+

[dennis_jeffrey, 2011/02/16 19:43:29]

Put one more blank line here, to separate these two classes.

[dyu1, 2011/02/17 20:38:06]

Done.

+class DatasetConverter(object):
+  _fields = [
+    u'NAME_FIRST',
+    u'NAME_MIDDLE',
+    u'NAME_LAST',
+    u'EMAIL_ADDRESS',
+    u'COMPANY_NAME',
+    u'ADDRESS_HOME_LINE1',
+    u'ADDRESS_HOME_LINE2',
+    u'ADDRESS_HOME_CITY',
+    u'ADDRESS_HOME_STATE',
+    u'ADDRESS_HOME_ZIP',
+    u'ADDRESS_HOME_COUNTRY',
+    u'PHONE_HOME_WHOLE_NUMBER',
+    u'PHONE_FAX_WHOLE_NUMBER',
+  ]
+  _record_length = len(_fields)
+  _output_pattern = u'{'
+  for key in _fields:
+    _output_pattern += u"u'%s': u'%%s', " % key
+  _output_pattern = _output_pattern[:-1] + '},'
+  _re_single_quote = re.compile("'", re.UNICODE)
+  _logger = logging.getLogger(__name__)
+  _logger.addHandler(NullHandler())
+
+  def __init__(self, input_filename, output_filename=None):
+    """Constructs a dataset converter object.
+
+    Full input pattern:
+      '(?P<NAME_FIRST>.*?)\|(?P<MIDDLE_NAME>.*?)\|(?P<NAME_LAST>.*?)\|
+      (?P<EMAIL_ADDRESS>.*?)\|(?P<COMPANY_NAME>.*?)\|(?P<ADDRESS_HOME_LINE1>.*?)
+      \|(?P<ADDRESS_HOME_LINE2>.*?)\|(?P<ADDRESS_HOME_CITY>.*?)\|
+      (?P<ADDRESS_HOME_STATE>.*?)\|(?P<ADDRESS_HOME_ZIP>.*?)\|
+      (?P<ADDRESS_HOME_COUNTRY>.*?)\|
+      (?P<PHONE_HOME_WHOLE_NUMBER>.*?)\|(?P<PHONE_FAX_WHOLE_NUMBER>.*?)$'
+
+    Full ouput pattern:
+      "{u'NAME_FIRST': u'%s', u'NAME_MIDDLE': u'%s', u'NAME_LAST': u'%s',
+      u'EMAIL_ADDRESS': u'%s', u'COMPANY_NAME': u'%s', u'ADDRESS_HOME_LINE1':
+      u'%s', u'ADDRESS_HOME_LINE2': u'%s', u'ADDRESS_HOME_CITY': u'%s',
+      u'ADDRESS_HOME_STATE': u'%s', u'ADDRESS_HOME_ZIP': u'%s',
+      u'ADDRESS_HOME_COUNTRY': u'%s', u'PHONE_HOME_WHOLE_NUMBER': u'%s',
+      u'PHONE_FAX_WHOLE_NUMBER': u'%s',},"
+
+    args:

[dennis_jeffrey, 2011/02/16 19:43:29]

Capitalize "a" in "args".

[dyu1, 2011/02/17 20:38:06]

Done.

+      input_filename: name and path of the input dataset.
+      output_filename: name and path of the converted file, default is none.

[dennis_jeffrey, 2011/02/16 19:43:29]

Since this method can now possibly raise "IOError", you should add a "Raises:"
section after the "Args:" section of this comment.

[dyu1, 2011/02/17 20:38:06]

Done.

+    """
+    self._input_filename = os.path.join(os.path.dirname(sys.argv[0]),
+                                        input_filename)
+    if not os.path.isfile(self._input_filename):
+      raise IOError('File "%s" does not exist' % self._input_filename)
+    self._output_filename = output_filename
+
+  def _CreateDictionaryFromRecord(self, line):
+    """Constructs and returns a dictionary from a record in the dataset file.
+
+    Escapes single quotation first and uses split('|') to separate values.
+    Example:
+      Take an argument as a string u'John|Doe|Mountain View'
+      and returns a dictionary
+      {
+      u'NAME_FIRST': u'John',
+      u'NAME_LAST': u'Doe',
+      u'ADDRESS_HOME_CITY': u'Mountain View',
+      }
+
+    Args:
+      line: row of record from the dataset file.

[dennis_jeffrey, 2011/02/16 19:43:29]

Maybe a variable name of "record" might be better than "line"?  Each line
represents a record, right?

[dyu1, 2011/02/17 20:38:06]

Done.

+
+    Returns:
+      out_record: a dictionary that comes from conversion of a single line.
+                  same as the output_record.

[dennis_jeffrey, 2011/02/16 19:43:29]

In the "Returns:" section, I think you don't need to list the variable name that
is returned.  This is because when you want to know what is returned from a
function, you don't care what variable internal to the function stored that
value; all you care about is what kind of thing is actually returned.  So in
this case, I think you can just say something like this:

Returns:
  A dictionary representing a a single record from the
  dataset file.

[dyu1, 2011/02/17 20:38:06]

Done.

+    """
+    # Ignore irrelevant record lines that does not contain '|'.

[dennis_jeffrey, 2011/02/16 19:43:29]

"does" --> "do"

[dyu1, 2011/02/17 20:38:06]

Done.

+    if not '|' in line:
+      return
+    # Escaping single quote: "'" -> "\'"
+    line = self._re_single_quote.sub(r"\'", line)
+    line_list = line.split('|')
+    if line_list:
+      # Check for case when a line may have more or less fields than expected.
+      if len(line_list) != self._record_length:
+        self._logger.warning(
+            'A "|" seperated line has %d fields instead of %d: %s' % (

[dennis_jeffrey, 2011/02/16 19:43:29]

"seperated" --> "separated"

[dyu1, 2011/02/17 20:38:06]

Done.

+                len(line_list), self._record_length, line))
+        return
+      out_record = {}
+      i = 0
+      for key in self._fields:
+        out_record[key] = line_list[i]
+        i += 1
+      return out_record
+
+  def _Convert(self, input_file, output_file):
+    """The real conversion takes place here.
+
+    The output pattern takes place in this function. Each field needs to be

[dennis_jeffrey, 2011/02/16 19:43:29]

What does it mean for an "output pattern" to "take place"?

[dyu1, 2011/02/17 20:38:06]

Removed this function.

On 2011/02/16 19:43:29, dennis_jeffrey wrote:

+    formatted in order to give the converted line.
+
+    Args:
+      input_file: dataset input file.
+      output_file: the converted dictionary list output file.
+
+    Returns:
+      list_of_dict: list that holds all the dictionaries.

[dennis_jeffrey, 2011/02/16 19:43:29]

Can remove the returned variable name "list_of_dict" here.

[dyu1, 2011/02/17 20:38:06]

Done.

+    """
+    list_of_dict = []
+    i = 0
+    if output_file:
+      output_file.write('[')
+      output_file.write(os.linesep)
+    for line in input_file.readlines():
+      line = line.strip()
+      if not line:
+        continue
+      line = unicode(line, 'UTF-8')
+      output_record = self._CreateDictionaryFromRecord(line)
+      if output_record:
+        i += 1
+        list_of_dict.append(output_record)
+        output_line = self._output_pattern % tuple(
+            [output_record[key] for key in self._fields])
+        if output_file:
+          output_file.write(output_line)
+          output_file.write(os.linesep)
+        self._logger.info('%d: %s' % (i, line.encode(sys.stdout.encoding,
+                                                     'ignore')))
+        self._logger.info('\tconverted to: %s' %
+                          output_line.encode(sys.stdout.encoding, 'ignore'))
+    if output_file:
+      output_file.write(']')
+      output_file.write(os.linesep)
+    self._logger.info('%d lines converted SUCCESSFULLY!' % i)
+    self._logger.info('--- FINISHED ---')
+    return list_of_dict
+
+  def Convert(self):
+    """Uses values of the two data attributes of the current objects."""

[dennis_jeffrey, 2011/02/16 19:43:29]

I think a more descriptive comment might be something like this:

"""Wrapper function to convert input data into the desired output format."""

[dyu1, 2011/02/17 20:38:06]

Done.

+    with open(self._input_filename) as input_file:
+      if self._output_filename:
+        with codecs.open(self._output_filename, mode='wb',
+                         encoding='utf-8-sig') as output_file:
+          return self._Convert(input_file, output_file)
+      else:
+        return self._Convert(input_file, None)
+
+
+def main():
+  c = DatasetConverter(r'../data/autofill/dataset.txt',
+                       r'../data/autofill/dataset_duplicate-profiles.txt')
+  c.Convert()
+
+if __name__ == '__main__':
+  main()