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

chrome/test/functional/dataset-converter.py

Index: chrome/test/functional/dataset-converter.py
===================================================================
--- chrome/test/functional/dataset-converter.py	(revision 0)
+++ chrome/test/functional/dataset-converter.py	(revision 0)
@@ -0,0 +1,151 @@
+#!/usr/bin/python
+# Copyright (c) 2010 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.
+
+
+"""Takes in a CSV profiles file and outputs to a pyAuto dictionary list format
+for converting Autofill Prfofile datasets.
+
+Used for test autofill.AutoFillTest.testMergeDuplicateProfilesInAutofill.
+"""
+
+# Specify input and output filename can be full
+# path: 'c:\folder\file' or '/home/folder/file'
+INPUT_FILE = r"../data/autofill/dataset.txt"
+OUTPUT_FILE = r"../data/autofill/dataset_duplicate-profiles.txt"
+
+# Controls output display on the screen.
+DISPLAY_INPUT_LINES = True
+DISPLAY_CONVERTED_LINES = False
+
+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',
+]
+
+import codecs
+import re
+import sys
+
+class Converter(object):
+  def __init__(self, fields, filein, fileout):
+    """
+    The pattern is a regular expression which has named parenthesis groups
+    like this (?P<name>...) in order to match the '|' separated fields.
+    If we had only the NAME_FIRST and NAME_MIDDLE fields (e.g 'Jared|JV') our
+    pattern would be: "(?P<NAME_FIRST>.*?)\|(?P<NAME_MIDDLE>.*?)$"
+
+    This means that '(?P<NAME_FIRST> regexp)\|' matches whatever regular
+    expression is inside the parentheses, and indicates the start and end of a
+    group; the contents of a group can be retrieved after a match has been
+    performed using the symbolic group name 'NAME_FIRST'.
+
+    The regexp is '.*?'. '.*' which means to match 0 or more repetitions of any
+    character. The following '?' makes the regexp non-greedy meaning it will
+    stop at the first occurrence of the '|' character (escaped in the pattern).
+
+    For '(?P<NAME_MIDDLE>.*?)$' there is no '|' at the end, so we have '$' to
+    indicate the end of the line.
+
+    From the full pattern, we construct once from the FIELDS list.
+
+    The out_line_pattern for one field: "{u'NAME_FIRST': u'%s',"
+    is ready to accept the value for the 'NAME_FIRST' field once it is extracted
+    from an input line using the above group pattern.
+
+    'pattern' is used in __gerRec(line) to construct and return a dictionary
+    from a line.
+
+    'out_line_pattern' is used in 'convert()' to construct the final dataset
+    line that will be printed to the output file.
+    """
+    self.fields = fields[:]
+    self.pattern = '(?P<%s>.*?)' %fields[0]
+    for key in fields[1:]:
+      self.pattern += '\|(?P<%s>.*?)' %key
+    self.pattern = self.pattern + "$"
+
+    self.out_line_pattern = u"{"
+    for key in fields:
+      self.out_line_pattern += u"u'%s': u'%s', " %(key, "%s")
+    self.out_line_pattern = self.out_line_pattern[:-1] + "},\n"
+
+    self.filein = filein
+    self.fileout = fileout
+
+  def __getRec(self, line):
+    """
+    Constructs and returns a dictionary from a line using patterns.
+    See constructor above.
+    """
+    rePat = re.compile("'", re.UNICODE)
+    line = rePat.sub(r"\'", line)
+    rePat = re.compile(self.pattern, re.UNICODE)
+    m = rePat.match(line)
+    if m:
+      outrec = {}
+      for key in self.fields:
+        outrec[key] = m.group(key)
+      return outrec
+
+  def convert(self, display_input_lines, display_converted_lines):
+    """
+    The out_line_pattern is here. Each field needs to be formatted with a tuple
+    of values for each containing '%s'.
+    This is done in the line:
+      out_line = self.out_line_pattern %tuple(
+          [outrec[key] for key in self.fields])
+    For two fiels, translates to:
+      out_line = "{u'NAME_FIRST': u'%s', u'MIDDLE_NAME': u'%s',}," % (
+          outrec['NAME_FIRST'], outrec['MIDDLE_NAME'])
+    """
+    with open(self.filein) as fin:
+      with codecs.open(self.fileout, mode = "wb",
+                       encoding = "utf-8-sig") as fout:
+        i = 0
+        fout.write("[\n")
+        for line in fin.readlines():
+          line = line.strip()
+          if not line:
+            continue
+          line = unicode(line, 'UTF-8')
+          outrec = self.__getRec(line)
+          if outrec:
+            i += 1
+            out_line = self.out_line_pattern %tuple(
+                [outrec[key] for key in self.fields])
+            fout.write(out_line)
+            if display_input_lines:
+              print "\n%d: %s" %(i, line.encode(sys.stdout.encoding, 'ignore'))
+            if display_converted_lines:
+              print "\tconverted to: %s" %out_line.encode(
+                  sys.stdout.encoding, 'ignore')
+            else:
+              if not display_input_lines and not i % 10:
+                print "\t%d lines converted so far!" %i
+
+        fout.write("]\n")
+    print
+    print "%d lines converted SUCCESSFULLY!" %i
+    print "--- FINISHED ---"
+    print
+
+
+def main():
+  c = Converter(FIELDS, INPUT_FILE, OUTPUT_FILE)
+  c.convert(DISPLAY_INPUT_LINES, DISPLAY_CONVERTED_LINES)
+
+if __name__ == '__main__':
+  main()