Split util module for zip code

BUG=
TEST=
REF_BUG=
REF_CL=132211827
REF_TIME=2016-09-05T14:10:24+09:00
REF_TIME_RAW=1473052224 +0900

src/data/version/mozc_version_template.bzl

@@ -30,7 +30,7 @@
 
 MAJOR=2
 MINOR=18
-BUILD=2608
+BUILD=2609
 REVISION=102
 # This version represents the version of Mozc IME engine (converter, predictor,
 # etc.).  This version info is included both in the Mozc server and in the Mozc

src/dictionary/gen_zip_code_seed.py

@@ -51,12 +51,13 @@
 
 __author__ = "toshiyuki"
 
-import codecs
 import optparse
 import re
 import sys
 import unicodedata
 
+from dictionary import zip_code_util
+
 
 ZIP_CODE_LABEL = 'ZIP_CODE'
 ZIP_CODE_COST = 7000
@@ -85,8 +86,8 @@ class ZipEntry(object):
 
 def ProcessZipCodeCSV(file_name):
   """Process zip code csv."""
-  csv_lines = ReadCSV(file_name)
+  csv_lines = zip_code_util.ReadCSV(file_name)
-  merged_csv_lines = MergeCSV(csv_lines)
+  merged_csv_lines = zip_code_util.MergeCSV(csv_lines)
   for tokens in merged_csv_lines:
     for entry in ReadZipCodeEntries(tokens[2], tokens[6], tokens[7], tokens[8]):
       entry.Output()
@@ -94,95 +95,12 @@ def ProcessZipCodeCSV(file_name):
 
 def ProcessJigyosyoCSV(file_name):
   """Process jigyosyo csv."""
-  for tokens in ReadCSV(file_name):
+  for tokens in zip_code_util.ReadCSV(file_name):
     entry = ReadJigyosyoEntry(tokens[7], tokens[3], tokens[4],
                               tokens[5], tokens[2])
     entry.Output()
 
 
-def ReadCSV(file_name):
-  """Read CSV file."""
-  # Do not use csv reader module because it does not support unicode
-  return [GetCells(line) for line in codecs.open(file_name,
-                                                 'r',
-                                                 'shift_jis',
-                                                 errors='replace')]
-
-
-def GetCells(line):
-  """Get cells."""
-  # [A, B, C, ..] from "A","B ",C,..
-  return [column.strip('"').strip() for column in line.strip().split(',')]
-
-
-def MergeCSV(csv_lines):
-  """Merge CSV."""
-  # When the flag says a zip code have no multiple entry while we can see
-  # multiple line for that zip code, we have to merge them.
-  zip_count = {}
-  ret = []
-  for entry in csv_lines:
-    zip_code = entry[2]
-    zip_count[zip_code] = zip_count.get(zip_code, 0) + 1
-    if not ShouldMerge(zip_count, entry):
-      ret.append(entry)
-    else:
-      last_entry = ret[-1]
-      last_entry[8] += entry[8]  # '町域'
-  return ret
-
-
-def ShouldMerge(zip_count, entry):
-  """Return true if this entry should be merged to the previous entry."""
-  zip_code = entry[2]
-  flag_multi = (entry[12] == '1')
-  should_merge = (zip_count[zip_code] > 1 and not flag_multi)
-  should_merge_special = ShouldMergeSpecial(entry)
-  return should_merge or should_merge_special
-
-
-class SpecialMergeZip(object):
-  """Container class for special zip code entry to be merged."""
-
-  def __init__(self, zip_code, pref, city, towns):
-    self.zip_code = zip_code
-    self.pref = pref
-    self.city = city
-    self.towns = towns
-
-
-_SPECIAL_CASES = [
-    SpecialMergeZip(u'5900111', u'大阪府', u'堺市中区', [u'三原台']),
-    SpecialMergeZip(u'8710046', u'大分県', u'中津市',
-                    [u'金谷', u'西堀端', u'東堀端', u'古金谷']),
-    SpecialMergeZip(u'9218046', u'石川県', u'金沢市',
-                    [u'大桑町', u'三小牛町']),
-    ]
-
-
-def ShouldMergeSpecial(entry):
-  """Return true for special cases to be merged."""
-  zip_code = entry[2]
-  level1 = entry[6]
-  level2 = entry[7]
-  level3 = entry[8]
-  for special_case in _SPECIAL_CASES:
-    if (zip_code == special_case.zip_code and
-        level1 == special_case.pref and
-        level2 == special_case.city and
-        ContinuedLine(level3, special_case.towns)):
-      return True
-  return False
-
-
-def ContinuedLine(level3, towns):
-  """Return true if this seems continued line."""
-  for town in towns:
-    if level3.startswith(town):
-      return False
-  return True
-
-
 def ReadZipCodeEntries(zip_code, level1, level2, level3):
   """Read zip code entries."""
   return [ZipEntry(zip_code, u''.join([level1, level2, town]))

src/dictionary/zip_code_util.py

@@ -0,0 +1,116 @@
+# -*- coding: utf-8 -*-
+# Copyright 2010-2016, Google Inc.
+# All rights reserved.
+#
+# Redistribution and use in source and binary forms, with or without
+# modification, are permitted provided that the following conditions are
+# met:
+#
+#     * Redistributions of source code must retain the above copyright
+# notice, this list of conditions and the following disclaimer.
+#     * Redistributions in binary form must reproduce the above
+# copyright notice, this list of conditions and the following disclaimer
+# in the documentation and/or other materials provided with the
+# distribution.
+#     * Neither the name of Google Inc. nor the names of its
+# contributors may be used to endorse or promote products derived from
+# this software without specific prior written permission.
+#
+# THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
+# "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
+# LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
+# A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
+# OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
+# SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
+# LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
+# DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
+# THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
+# (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
+# OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+
+"""Util module for Japanese postal(ZIP) code."""
+
+import codecs
+
+
+def ReadCSV(file_name):
+  """Read CSV file."""
+  # Do not use csv reader module because it does not support unicode
+  return [GetCells(line) for line in codecs.open(file_name,
+                                                 'r',
+                                                 'shift_jis',
+                                                 errors='replace')]
+
+
+def GetCells(line):
+  """Get cells."""
+  # [A, B, C, ..] from "A","B ",C,..
+  return [column.strip('"').strip() for column in line.strip().split(',')]
+
+
+def MergeCSV(csv_lines):
+  """Merge CSV."""
+  # When the flag says a zip code have no multiple entry while we can see
+  # multiple line for that zip code, we have to merge them.
+  zip_count = {}
+  ret = []
+  for entry in csv_lines:
+    zip_code = entry[2]
+    zip_count[zip_code] = zip_count.get(zip_code, 0) + 1
+    if not ShouldMerge(zip_count, entry):
+      ret.append(entry)
+    else:
+      last_entry = ret[-1]
+      last_entry[8] += entry[8]  # '町域'
+  return ret
+
+
+def ShouldMerge(zip_count, entry):
+  """Return true if this entry should be merged to the previous entry."""
+  zip_code = entry[2]
+  flag_multi = (entry[12] == '1')
+  should_merge = (zip_count[zip_code] > 1 and not flag_multi)
+  should_merge_special = ShouldMergeSpecial(entry)
+  return should_merge or should_merge_special
+
+
+class SpecialMergeZip(object):
+  """Container class for special zip code entry to be merged."""
+
+  def __init__(self, zip_code, pref, city, towns):
+    self.zip_code = zip_code
+    self.pref = pref
+    self.city = city
+    self.towns = towns
+
+
+_SPECIAL_CASES = [
+    SpecialMergeZip(u'5900111', u'大阪府', u'堺市中区', [u'三原台']),
+    SpecialMergeZip(u'8710046', u'大分県', u'中津市',
+                    [u'金谷', u'西堀端', u'東堀端', u'古金谷']),
+    SpecialMergeZip(u'9218046', u'石川県', u'金沢市',
+                    [u'大桑町', u'三小牛町']),
+    ]
+
+
+def ShouldMergeSpecial(entry):
+  """Return true for special cases to be merged."""
+  zip_code = entry[2]
+  level1 = entry[6]
+  level2 = entry[7]
+  level3 = entry[8]
+  for special_case in _SPECIAL_CASES:
+    if (zip_code == special_case.zip_code and
+        level1 == special_case.pref and
+        level2 == special_case.city and
+        ContinuedLine(level3, special_case.towns)):
+      return True
+  return False
+
+
+def ContinuedLine(level3, towns):
+  """Return true if this seems continued line."""
+  for town in towns:
+    if level3.startswith(town):
+      return False
+  return True