Move some shared code to a localetools module

The time-zone script was importing two functions from the locale data
generation script. Move them to a separate module, to which I'll
shortly add some more shared utilities. Cleaned up some imports in the
process.

Combined qlocalexml2cpp's and xpathlit's error classes into a new
Error class in the new module and made it a bit more like a proper
python error class.

Task-number: QTBUG-81344
Change-Id: Idbe0139ba9aaa2f823b8f7216dee1d2539c18b75
Reviewed-by: Cristian Maureira-Fredes <cristian.maureira-fredes@qt.io>

6 files changed, 105 insertions, 75 deletions

diff --git a/util/locale_database/cldr2qlocalexml.py b/util/locale_database/cldr2qlocalexml.py
index fba8d7fdd5..41795ff634 100755
--- a/util/locale_database/cldr2qlocalexml.py
+++ b/util/locale_database/cldr2qlocalexml.py
@@ -58,14 +58,14 @@ import re
 import textwrap
 
 import enumdata
-import xpathlite
-from xpathlite import DraftResolution, findAlias, findEntry, findTagsInFile
+from localetools import Error
+from xpathlite import DraftResolution, findAlias, findEntry, findTagsInFile, codeMapsFromFile, \
+    _findEntryInFile as findEntryInFile
 from dateconverter import convert_date
 from qlocalexml import Locale, QLocaleXmlWriter
 
 # TODO: make calendars a command-line option
 calendars = ['gregorian', 'persian', 'islamic'] # 'hebrew'
-findEntryInFile = xpathlite._findEntryInFile
 def wrappedwarn(err, prefix, tokens):
     return err.write(
         '\n'.join(textwrap.wrap(prefix + ', '.join(tokens),
@@ -116,19 +116,19 @@ def raiseUnknownCode(code, form, cache={}):
     type of code to look up.  Do not pass further parameters (the next
     will deprive you of the cache).
 
-    Raises xpathlite.Error with a suitable message, that includes the
-    unknown code's full name if found.
+    Raises localetools.Error with a suitable message, that includes
+    the unknown code's full name if found.
 
     Relies on global cldr_dir being set before it's called; see tail
     of this file.
     """
     if not cache:
-        cache.update(xpathlite.codeMapsFromFile(os.path.join(cldr_dir, 'en.xml')))
+        cache.update(codeMapsFromFile(os.path.join(cldr_dir, 'en.xml')))
     name = cache[form].get(code)
     msg = 'unknown %s code "%s"' % (form, code)
     if name:
         msg += ' - could use "%s"' % name
-    raise xpathlite.Error(msg)
+    raise Error(msg)
 
 def parse_list_pattern_part_format(pattern):
     # This is a very limited parsing of the format for list pattern part only.
@@ -182,7 +182,7 @@ def generateLocaleInfo(path):
     # skip legacy/compatibility ones
     alias = findAlias(path)
     if alias:
-        raise xpathlite.Error('alias to "%s"' % alias)
+        raise Error('Alias to "{}"'.format(alias))
 
     def code(tag):
         return findEntryInFile(path, 'identity/' + tag, attribute="type")[0]
@@ -224,7 +224,7 @@ def _generateLocaleInfo(path, language_code, script_code, country_code, variant_
     # ### actually there is only one locale with variant: en_US_POSIX
     #     does anybody care about it at all?
     if variant_code:
-        raise xpathlite.Error('we do not support variants ("%s")' % variant_code)
+        raise Error('We do not support variants ("{}")'.format(variant_code))
 
     language_id = enumdata.languageCodeToId(language_code)
     if language_id <= 0:
@@ -283,23 +283,23 @@ def _generateLocaleInfo(path, language_code, script_code, country_code, variant_
     numbering_system = None
     try:
         numbering_system = findEntry(path, "numbers/defaultNumberingSystem")
-    except xpathlite.Error:
+    except Error:
         pass
     def findEntryDef(path, xpath, value=''):
         try:
             return findEntry(path, xpath)
-        except xpathlite.Error:
+        except Error:
             return value
     def get_number_in_system(path, xpath, numbering_system):
         if numbering_system:
             try:
                 return findEntry(path, xpath + "[numberSystem=" + numbering_system + "]")
-            except xpathlite.Error:
+            except Error:
                 # in CLDR 1.9 number system was refactored for numbers (but not for currency)
                 # so if previous findEntry doesn't work we should try this:
                 try:
                     return findEntry(path, xpath.replace("/symbols/", "/symbols[numberSystem=" + numbering_system + "]/"))
-                except xpathlite.Error:
+                except Error:
                     # fallback to default
                     pass
         return findEntry(path, xpath)
@@ -368,7 +368,7 @@ def _generateLocaleInfo(path, language_code, script_code, country_code, variant_
         for count in ('many', 'few', 'two', 'other', 'zero', 'one'):
             try:
                 ans = findEntry(path, stem + 'unitPattern[count=%s]' % count)
-            except xpathlite.Error:
+            except Error:
                 continue
 
             # TODO: epxloit count-handling, instead of discarding placeholders
@@ -498,7 +498,7 @@ def _parseLocale(l):
     country = "AnyCountry"
 
     if l == "und":
-        raise xpathlite.Error("we are treating unknown locale like C")
+        raise Error('We treat unknown locale like C')
 
     parsed = splitLocale(l)
     language_code = parsed.next()
@@ -511,19 +511,19 @@ def _parseLocale(l):
     if language_code != "und":
         language_id = enumdata.languageCodeToId(language_code)
         if language_id == -1:
-            raise xpathlite.Error('unknown language code "%s"' % language_code)
+            raise Error('Unknown language code "{}"'.format(language_code))
         language = enumdata.language_list[language_id][0]
 
     if script_code:
         script_id = enumdata.scriptCodeToId(script_code)
         if script_id == -1:
-            raise xpathlite.Error('unknown script code "%s"' % script_code)
+            raise Error('Unknown script code "{}"'.format(script_code))
         script = enumdata.script_list[script_id][0]
 
     if country_code:
         country_id = enumdata.countryCodeToId(country_code)
         if country_id == -1:
-            raise xpathlite.Error('unknown country code "%s"' % country_code)
+            raise Error('Unknown country code "{}"'.format(country_code))
         country = enumdata.country_list[country_id][0]
 
     return (language, script, country)
@@ -538,11 +538,13 @@ def likelySubtags(root, err):
         try:
             from_language, from_script, from_country = _parseLocale(tmp[u"from"])
             to_language, to_script, to_country = _parseLocale(tmp[u"to"])
-        except xpathlite.Error as e:
-            if tmp[u'to'].startswith(tmp[u'from']) and str(e) == 'unknown language code "%s"' % tmp[u'from']:
-                skips.append(tmp[u'to'])
+        except Error as e:
+            if (tmp['to'].startswith(tmp['from'])
+                and e.message == 'Unknown language code "{}"'.format(tmp['from'])):
+                skips.append(tmp['to'])
             else:
-                sys.stderr.write('skipping likelySubtag "%s" -> "%s" (%s)\n' % (tmp[u"from"], tmp[u"to"], str(e)))
+                sys.stderr.write('skipping likelySubtag "{}" -> "{}" ({})\n'.format(
+                        tmp[u"from"], tmp[u"to"], e.message))
             continue
         # substitute according to http://www.unicode.org/reports/tr35/#Likely_Subtags
         if to_country == "AnyCountry" and from_country != to_country:
@@ -612,8 +614,8 @@ def main(args, out, err):
             if not l:
                 skips.append(file)
                 continue
-        except xpathlite.Error as e:
-            sys.stderr.write('skipping defaultContent locale "{}" ({})\n'.format(file, str(e)))
+        except Error as e:
+            sys.stderr.write('skipping defaultContent locale "{}" ({})\n'.format(file, e.message))
             continue
 
         locale_database[(l.language_id, l.script_id, l.country_id, l.variant_code)] = l
@@ -628,8 +630,8 @@ def main(args, out, err):
             if not l:
                 skips.append(file)
                 continue
-        except xpathlite.Error as e:
-            sys.stderr.write('skipping file "{}" ({})\n'.format(file, str(e)))
+        except Error as e:
+            sys.stderr.write('skipping file "{}" ({})\n'.format(file, e.message))
             continue
 
         locale_database[(l.language_id, l.script_id, l.country_id, l.variant_code)] = l
diff --git a/util/locale_database/cldr2qtimezone.py b/util/locale_database/cldr2qtimezone.py
index 4c3609056d..7816abc9e1 100755
--- a/util/locale_database/cldr2qtimezone.py
+++ b/util/locale_database/cldr2qtimezone.py
@@ -54,20 +54,14 @@ The XML structure is as follows:
 
 import os
 import sys
+import re
 import datetime
 import tempfile
-import enumdata
-import xpathlite
-from  xpathlite import DraftResolution
-import re
-import qlocalexml2cpp
 
-findAlias = xpathlite.findAlias
-findEntry = xpathlite.findEntry
-findEntryInFile = xpathlite._findEntryInFile
-findTagsInFile = xpathlite.findTagsInFile
-unicode2hex = qlocalexml2cpp.unicode2hex
-wrap_list = qlocalexml2cpp.wrap_list
+import enumdata
+from localetools import unicode2hex, wrap_list, Error
+from xpathlite import DraftResolution, findAlias, findEntry, findTagsInFile, \
+    _findEntryInFile as findEntryInFile
 
 class ByteArrayData:
     def __init__(self):
@@ -343,13 +337,13 @@ if mapTimezones:
             else:
                 data['countryId'] = enumdata.countryCodeToId(data['countryCode'])
                 if data['countryId'] < 0:
-                    raise xpathlite.Error("Unknown Country Code \"%s\"" % data['countryCode'])
+                    raise Error('Unknown Country Code "{}"'.format(data['countryCode']))
                 data['country'] = enumdata.country_list[data['countryId']][0]
                 windowsIdDict[data['windowsKey'], data['countryId']] = data
     if badZones:
         sys.stderr.write('\n\t'.join(["\nUnknown Windows ID, please add:"] + sorted(badZones))
                          + "\nto the windowIdList in cldr2qtimezone.py\n\n")
-        raise xpathlite.Error("Unknown Windows IDs")
+        raise Error('Unknown Windows IDs')
 
 print "Input file parsed, now writing data"
 
diff --git a/util/locale_database/localetools.py b/util/locale_database/localetools.py
new file mode 100644
index 0000000000..0d5c2acbbb
--- /dev/null
+++ b/util/locale_database/localetools.py
@@ -0,0 +1,65 @@
+#############################################################################
+##
+## Copyright (C) 2020 The Qt Company Ltd.
+## Contact: https://www.qt.io/licensing/
+##
+## This file is part of the test suite of the Qt Toolkit.
+##
+## $QT_BEGIN_LICENSE:GPL-EXCEPT$
+## Commercial License Usage
+## Licensees holding valid commercial Qt licenses may use this file in
+## accordance with the commercial license agreement provided with the
+## Software or, alternatively, in accordance with the terms contained in
+## a written agreement between you and The Qt Company. For licensing terms
+## and conditions see https://www.qt.io/terms-conditions. For further
+## information use the contact form at https://www.qt.io/contact-us.
+##
+## GNU General Public License Usage
+## Alternatively, this file may be used under the terms of the GNU
+## General Public License version 3 as published by the Free Software
+## Foundation with exceptions as appearing in the file LICENSE.GPL3-EXCEPT
+## included in the packaging of this file. Please review the following
+## information to ensure the GNU General Public License requirements will
+## be met: https://www.gnu.org/licenses/gpl-3.0.html.
+##
+## $QT_END_LICENSE$
+##
+#############################################################################
+"""Utilities shared among the CLDR extraction tools.
+Functions:
+  unicode2hex() -- converts unicode text to UCS-2 in hex form.
+  wrap_list() -- map list to comma-separated string, 20 entries per line.
+
+Classes:
+  Error -- A shared error class.
+"""
+
+class Error (StandardError):
+    __upinit = StandardError.__init__
+    def __init__(self, msg, *args):
+        self.__upinit(msg, *args)
+        self.message = msg
+    def __str__(self):
+        return self.message
+
+def unicode2hex(s):
+    lst = []
+    for x in s:
+        v = ord(x)
+        if v > 0xFFFF:
+            # make a surrogate pair
+            # copied from qchar.h
+            high = (v >> 10) + 0xd7c0
+            low = (v % 0x400 + 0xdc00)
+            lst.append(hex(high))
+            lst.append(hex(low))
+        else:
+            lst.append(hex(v))
+    return lst
+
+def wrap_list(lst):
+    def split(lst, size):
+        while lst:
+            head, lst = lst[:size], lst[size:]
+            yield head
+    return ",\n".join(", ".join(x) for x in split(lst, 20))
diff --git a/util/locale_database/qlocalexml.py b/util/locale_database/qlocalexml.py
index 8289bd785a..0b962157d2 100644
--- a/util/locale_database/qlocalexml.py
+++ b/util/locale_database/qlocalexml.py
@@ -39,7 +39,7 @@ Support:
 from __future__ import print_function
 from xml.sax.saxutils import escape
 
-from xpathlite import Error
+from localetools import Error
 
 # Tools used by Locale:
 def camel(seq):
diff --git a/util/locale_database/qlocalexml2cpp.py b/util/locale_database/qlocalexml2cpp.py
index eb76f02faa..c54c3953ae 100755
--- a/util/locale_database/qlocalexml2cpp.py
+++ b/util/locale_database/qlocalexml2cpp.py
@@ -37,9 +37,10 @@ import os
 import sys
 import tempfile
 import datetime
-from enumdata import language_aliases, country_aliases, script_aliases
 
 from qlocalexml import QLocaleXmlReader
+from enumdata import language_aliases, country_aliases, script_aliases
+from localetools import unicode2hex, wrap_list, Error
 
 # TODO: Make calendars a command-line parameter
 # map { CLDR name: Qt file name }
@@ -59,19 +60,6 @@ generated_template = """
 
 """
 
-class Error:
-    def __init__(self, msg):
-        self.msg = msg
-    def __str__(self):
-        return self.msg
-
-def wrap_list(lst):
-    def split(lst, size):
-        while lst:
-            head, lst = lst[:size], lst[size:]
-            yield head
-    return ",\n".join(", ".join(x) for x in split(lst, 20))
-
 def fixedScriptName(name, dupes):
     # Don't .capitalize() as some names are already camel-case (see enumdata.py):
     name = ''.join(word[0].upper() + word[1:] for word in name.split())
@@ -127,21 +115,6 @@ def compareLocaleKeys(key1, key2):
     return key1[1] - key2[1]
 
 
-def unicode2hex(s):
-    lst = []
-    for x in s:
-        v = ord(x)
-        if v > 0xFFFF:
-            # make a surrogate pair
-            # copied from qchar.h
-            high = (v >> 10) + 0xd7c0
-            low = (v % 0x400 + 0xdc00)
-            lst.append(hex(high))
-            lst.append(hex(low))
-        else:
-            lst.append(hex(v))
-    return lst
-
 class StringDataToken:
     def __init__(self, index, length):
         if index > 0xFFFF or length > 0xFFFF:
diff --git a/util/locale_database/xpathlite.py b/util/locale_database/xpathlite.py
index 97efaaab41..3da8b24656 100644
--- a/util/locale_database/xpathlite.py
+++ b/util/locale_database/xpathlite.py
@@ -31,6 +31,8 @@ import sys
 import os
 import xml.dom.minidom
 
+from localetools import Error
+
 class DraftResolution:
     # See http://www.unicode.org/cldr/process.html for description
     unconfirmed = 'unconfirmed'
@@ -43,12 +45,6 @@ class DraftResolution:
     def toInt(self):
         return DraftResolution._values[self.resolution]
 
-class Error:
-    def __init__(self, msg):
-        self.msg = msg
-    def __str__(self):
-        return self.msg
-
 doc_cache = {}
 def parseDoc(file):
     if not doc_cache.has_key(file):