tommy/libpostal
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

[transliteration] adding german-ascii transliteration to Estonian to handle umlauts (ä => ae, etc.)

Browse Source
This commit is contained in:
Al
2017-01-02 13:51:56 -05:00
parent b2b7f6f155
commit 600b40d2f6
1 changed files with 7 additions and 5 deletions
Download Patch File Download Diff File Expand all files Collapse all files

12
scripts/geodata/i18n/transliteration_rules.py
View File

@@ -1205,19 +1205,19 @@ extra_transforms = {
(STEP_TRANSFORM, 'latin-ascii'), (STEP_TRANSFORM, 'latin-ascii'),
], ],
# Swedish/Danish/Norwegian transliterations not handled by standard NFD or Latin-ASCII
'scandinavian-ascii': [ 'scandinavian-ascii': [
(STEP_RULESET, [ (STEP_RULESET, [
# ø => oe
# Swedish transliterations not handled by standard NFD normalization
(u'"\\xc3\\xb8"', '2', CONTEXT_TYPE_NONE, '0', 'NULL', '0', CONTEXT_TYPE_NONE, '0', 'NULL', '0', u'"oe"', '2', 'NULL', '0', 'NULL', '0'), (u'"\\xc3\\xb8"', '2', CONTEXT_TYPE_NONE, '0', 'NULL', '0', CONTEXT_TYPE_NONE, '0', 'NULL', '0', u'"oe"', '2', 'NULL', '0', 'NULL', '0'),
# Å => Aa if followed by lower case Latin letter # Ø => Oe if followed by lower case Latin letter
(u'"\\xc3\\x98"', '2', CONTEXT_TYPE_NONE, '0', 'NULL', '0', CONTEXT_TYPE_REGEX, '1', latin_lower_rule, str(latin_lower_rule_len), u'"Oe"', '2', 'NULL', '0', 'NULL', '0'), (u'"\\xc3\\x98"', '2', CONTEXT_TYPE_NONE, '0', 'NULL', '0', CONTEXT_TYPE_REGEX, '1', latin_lower_rule, str(latin_lower_rule_len), u'"Oe"', '2', 'NULL', '0', 'NULL', '0'),
# Å => AA otherwise # Ø => OE otherwise
(u'"\\xc3\\x98"', '2', CONTEXT_TYPE_NONE, '0', 'NULL', '0', CONTEXT_TYPE_NONE, '0', 'NULL', '0', u'"OE"', '2', 'NULL', '0', 'NULL', '0'), (u'"\\xc3\\x98"', '2', CONTEXT_TYPE_NONE, '0', 'NULL', '0', CONTEXT_TYPE_NONE, '0', 'NULL', '0', u'"OE"', '2', 'NULL', '0', 'NULL', '0'),
# Swedish transliterations not handled by standard NFD normalization # å => aa
(u'"\\xc3\\xa5"', '2', CONTEXT_TYPE_NONE, '0', 'NULL', '0', CONTEXT_TYPE_NONE, '0', 'NULL', '0', u'"aa"', '2', 'NULL', '0', 'NULL', '0'), (u'"\\xc3\\xa5"', '2', CONTEXT_TYPE_NONE, '0', 'NULL', '0', CONTEXT_TYPE_NONE, '0', 'NULL', '0', u'"aa"', '2', 'NULL', '0', 'NULL', '0'),
# Å => Aa if followed by lower case Latin letter # Å => Aa if followed by lower case Latin letter
@@ -1522,6 +1522,7 @@ script_transliterators = {
'cherokee': None, 'cherokee': None,
'common': {None: ['latin-ascii'], 'common': {None: ['latin-ascii'],
'de': ['german-ascii'], 'de': ['german-ascii'],
'et': ['german-ascii'],
'da': ['scandinavian-ascii', 'latin-ascii'], 'da': ['scandinavian-ascii', 'latin-ascii'],
'nb': ['scandinavian-ascii', 'latin-ascii'], 'nb': ['scandinavian-ascii', 'latin-ascii'],
'sv': ['scandinavian-ascii', 'latin-ascii'], 'sv': ['scandinavian-ascii', 'latin-ascii'],
@@ -1560,6 +1561,7 @@ script_transliterators = {
'lao': None, 'lao': None,
'latin': {None: ['latin-ascii'], 'latin': {None: ['latin-ascii'],
'de': ['german-ascii'], 'de': ['german-ascii'],
'et': ['german-ascii'],
'da': ['scandinavian-ascii', 'latin-ascii'], 'da': ['scandinavian-ascii', 'latin-ascii'],
'nb': ['scandinavian-ascii', 'latin-ascii'], 'nb': ['scandinavian-ascii', 'latin-ascii'],
'sv': ['scandinavian-ascii', 'latin-ascii'], 'sv': ['scandinavian-ascii', 'latin-ascii'],