Skip to content

Commit

Permalink
Fix some more bugs in Unihan_Variants.txt
Browse files Browse the repository at this point in the history
Resolves: ibus/ibus#2323
  • Loading branch information
mike-fabian committed Jun 9, 2021
1 parent 521054f commit 5ed1cc1
Show file tree
Hide file tree
Showing 3 changed files with 29 additions and 16 deletions.
16 changes: 8 additions & 8 deletions engine/chinese_variants.py
Original file line number Diff line number Diff line change
Expand Up @@ -791,7 +791,7 @@
u'争': 1,
u'于': 1,
u'亏': 1,
u'云': 1,
u'云': 3,
u'亚': 1,
u'亞': 2,
u'产': 1,
Expand Down Expand Up @@ -1126,7 +1126,7 @@
u'后': 3,
u'向': 3,
u'吒': 2,
u'吓': 1,
u'吓': 3,
u'吕': 1,
u'吗': 1,
u'吣': 1,
Expand Down Expand Up @@ -1569,7 +1569,7 @@
u'尴': 1,
u'尵': 2,
u'尷': 2,
u'尸': 1,
u'尸': 3,
u'尽': 1,
u'层': 1,
u'屃': 1,
Expand Down Expand Up @@ -1776,7 +1776,7 @@
u'從': 2,
u'徠': 2,
u'御': 1,
u'復': 2,
u'復': 3,
u'徵': 3,
u'徹': 2,
u'徿': 2,
Expand Down Expand Up @@ -2007,7 +2007,7 @@
u'換': 2,
u'揮': 2,
u'揽': 1,
u'揾': 1,
u'揾': 3,
u'揿': 1,
u'搀': 1,
u'搁': 1,
Expand Down Expand Up @@ -3103,7 +3103,7 @@
u'眦': 1,
u'眬': 1,
u'眾': 2,
u'着': 1,
u'着': 3,
u'睁': 1,
u'睍': 2,
u'睏': 2,
Expand Down Expand Up @@ -4370,7 +4370,7 @@
u'裌': 2,
u'補': 2,
u'裝': 2,
u'裡': 2,
u'裡': 3,
u'裢': 1,
u'裣': 1,
u'裤': 1,
Expand Down Expand Up @@ -5487,7 +5487,7 @@
u'釁': 2,
u'釃': 2,
u'釅': 2,
u'采': 1,
u'采': 3,
u'释': 1,
u'釋': 2,
u'里': 1,
Expand Down
16 changes: 8 additions & 8 deletions tools/Unihan_Variants.txt
Original file line number Diff line number Diff line change
Expand Up @@ -1031,7 +1031,7 @@ U+4E8E kSemanticVariant U+6275<kLau U+65BC<kLau
U+4E8E kTraditionalVariant U+65BC
U+4E8F kSemanticVariant U+65BC<kMatthews U+6275<kMatthews
U+4E8F kTraditionalVariant U+8667
U+4E91 kTraditionalVariant U+96F2
U+4E91 kTraditionalVariant U+4E91 U+96F2
U+4E94 kSemanticVariant U+3405<kMatthews
U+4E94 kSpecializedSemanticVariant U+4F0D<kMeyerWempe
U+4E95 kSpecializedSemanticVariant U+4E3C
Expand Down Expand Up @@ -1722,7 +1722,7 @@ U+5411 kSimplifiedVariant U+5411
U+5411 kTraditionalVariant U+5411 U+66CF
U+5412 kSemanticVariant U+54A4<kMatthews
U+5412 kSimplifiedVariant U+54A4
U+5413 kTraditionalVariant U+5687
U+5413 kTraditionalVariant U+5413 U+5687
U+5415 kTraditionalVariant U+5442
U+5417 kTraditionalVariant U+55CE
U+541A kSemanticVariant U+54BF<kMatthews,kMeyerWempe
Expand Down Expand Up @@ -2575,7 +2575,7 @@ U+5C35 kSimplifiedVariant U+2AA07
U+5C37 kSemanticVariant U+5C32<kLau,kMatthews
U+5C37 kSimplifiedVariant U+5C34
U+5C38 kSemanticVariant U+5C4D<kMeyerWempe
U+5C38 kTraditionalVariant U+5C4D
U+5C38 kTraditionalVariant U+5C38 U+5C4D
U+5C3B kSemanticVariant U+4BCC<kMatthews
U+5C3D kSemanticVariant U+76E1<kLau,kMatthews
U+5C3D kTraditionalVariant U+5118 U+76E1
Expand Down Expand Up @@ -2934,7 +2934,7 @@ U+5FA1 kSpecializedSemanticVariant U+99AD<kMeyerWempe
U+5FA1 kTraditionalVariant U+79A6
U+5FA4 kSemanticVariant U+5065<kFenn
U+5FA7 kSemanticVariant U+904D<kMatthews,kMeyerWempe
U+5FA9 kSimplifiedVariant U+590D
U+5FA9 kSimplifiedVariant U+5FA9 U+590D
U+5FAC kSemanticVariant U+5F77<kLau
U+5FAD kSemanticVariant U+509C<kMatthews
U+5FB5 kSimplifiedVariant U+5F81 U+5FB5
Expand Down Expand Up @@ -3392,7 +3392,7 @@ U+63F7 kZVariant U+633F U+63D2
U+63F8 kSemanticVariant U+6942<kLau U+6463<kMatthews
U+63FA kZVariant U+6416 U+6447
U+63FD kTraditionalVariant U+652C
U+63FE kTraditionalVariant U+6435
U+63FE kTraditionalVariant U+63FE U+6435
U+63FF kTraditionalVariant U+64B3
U+6400 kTraditionalVariant U+6519
U+6401 kTraditionalVariant U+64F1
Expand Down Expand Up @@ -5354,7 +5354,7 @@ U+773E kSemanticVariant U+8846<kLau,kMatthews U+2009D<kLau
U+773E kSimplifiedVariant U+4F17
U+7740 kSemanticVariant U+8457
U+7740 kSpecializedSemanticVariant U+8457<kFenn
U+7740 kTraditionalVariant U+8457
U+7740 kTraditionalVariant U+7740 U+8457
U+7741 kTraditionalVariant U+775C
U+774D kSimplifiedVariant U+2AFA2
U+774F kSemanticVariant U+56F0<kFenn
Expand Down Expand Up @@ -7400,7 +7400,7 @@ U+88DC kSimplifiedVariant U+8865
U+88DD kSimplifiedVariant U+88C5
U+88E0 kSemanticVariant U+88D9<kFenn
U+88E1 kSemanticVariant U+88CF<kHKGlyph,kLau,kMatthews
U+88E1 kSimplifiedVariant U+91CC
U+88E1 kSimplifiedVariant U+88E1 U+91CC
U+88E1 kSpecializedSemanticVariant U+88CF<kMeyerWempe
U+88E2 kTraditionalVariant U+8933
U+88E3 kTraditionalVariant U+895D
Expand Down Expand Up @@ -8906,7 +8906,7 @@ U+91C1 kSemanticVariant U+8845<kMatthews,kMeyerWempe
U+91C1 kSimplifiedVariant U+8845
U+91C3 kSimplifiedVariant U+917E
U+91C5 kSimplifiedVariant U+917D
U+91C7 kTraditionalVariant U+57F0 U+63A1
U+91C7 kTraditionalVariant U+91C7 U+57F0 U+63A1
U+91CA kTraditionalVariant U+91CB
U+91CB kSimplifiedVariant U+91CA
U+91CC kTraditionalVariant U+88E1
Expand Down
13 changes: 13 additions & 0 deletions tools/generate-chinese-variants.py
Original file line number Diff line number Diff line change
Expand Up @@ -274,6 +274,19 @@ def detect_chinese_category(phrase):
u'乾': 3, # U+4E7E
u'著': 3, # U+8457 Patch by Heiher <[email protected]>
u'只': 3, # U+53EA, see: https://github.com/kaio/ibus-table/issues/74
# Problems reported in https://github.com/ibus/ibus/issues/2323
u'着': 3, # U+7740, used in HK
u'枱': 3, # U+67B1, used in HK (correct already, no SC variant entry in Unihan_Variants.txt)
u'云': 3, # U+4E91, used in HK and TW
u'裡': 3, # U+88E1, (Untypable in S) used in all places same meaning as 裏
u'復': 3, # U+5FA9, (Untypable in S) used in all places same meaning in S, diff in T
u'采': 3, # U+91C7, (Untypable in T) used in Hong Kong, not sure about TW
# http://dict.revised.moe.edu.tw/cgi-bin/cbdic/gsweb.cgi has 采, i.e. probably
# it is used in TW
u'吓': 3, # U+5413, (Untypable in T) used in Cantonese.
u'尸': 3, # U+5C38, (Untypable in T) idk where it is used, but Cangjie has that as a radical.
u'揾': 3, # U+63FE, used in HK
# (TW seems to use only 搵, see http://dict.revised.moe.edu.tw/cgi-bin/cbdic/gsweb.cgi)
}

def test_detection(generated_script) -> int:
Expand Down

0 comments on commit 5ed1cc1

Please sign in to comment.