Merge branch 'master' of github.com:hiiwave/Tos-Translater

README.md

@@ -50,6 +50,11 @@ Theoretically, it's possible to support more languages without difficulty, inclu
 Since I don't know if there is such demand, and I'm not familiar with those languages, the development of these language support is not done yet. Let me know if you're interested and want to contribute.
 
 
+## Known Issues
+* Market search function would lose effect while using a non-native language.
+So switch to native language whenever you're going to do market search.
+
+
 ## Credits
 This tool is open-sourced by player 波光粼粼 at guild [夏祭](https://forum.gamer.com.tw/C.php?bsn=19840&snA=29788) in tw-tos.
 

mymain.py

@@ -8,10 +8,13 @@
 
 
 matcher = Matcher(lang_en_path, lang_tw_path)
+# matcher.export('tw', 'full', output_path / 'twtos-full')
+matcher.export('tw', 'map', output_path / 'langmap')
+
 # matcher.export('en', 'tw', output_path / 'itos-tw')
 # matcher.export('tw', 'en-opt', output_path / 'twtos-en')
-matcher.export('tw', 'en-opt', Path(r'C:\TreeOfSaviorTW\release\languageData\twtos-en'))
+# matcher.export('tw', 'en-opt', Path(r'C:\TreeOfSaviorTW\release\languageData\twtos-en'))
 # matcher.export('tw', 'dual1', output_path / 'twtos-dual1')
 # matcher.export('tw', 'dual2', output_path / 'twtos-dual2')
 matcher.export('tw', 'dual1', Path(r'C:\TreeOfSaviorTW\release\languageData\twtos-dual1'))
-matcher.export('tw', 'dual2', Path(r'C:\TreeOfSaviorTW\release\languageData\twtos-dual2'))
+matcher.export('tw', 'dual2', Path(r'C:\TreeOfSaviorTW\release\languageData\twtos-dual2'))

tos_languagematcher/exporter/exporter.py

@@ -2,7 +2,6 @@
 import pandas as pd
 import numpy as np
 from abc import ABC, abstractmethod
-import functools
 from tos_languagematcher import TSVS
 
 
@@ -59,15 +58,15 @@ def _make_df_result(self, df, tsv):
 class ExporterEnTw(Exporter):
     def _get_df1(self, tsv):
         return self.df_ens[tsv]
-    
+
     def _make_df_result(self, df, tsv):
         return np.where(~df['tw'].isna(), df['tw'], df['en'])
 
 
 class ExporterTwEn(Exporter):
     def _get_df1(self, tsv):
         return self.df_tws[tsv]
-    
+
     def _make_df_result(self, df, tsv):
         return np.where(~df['en'].isna(), df['en'], df['tw'])
 

tos_languagematcher/exporter/exporter_dual.py

@@ -1,4 +1,8 @@
-from .exporter import *
+from .exporter import Exporter
+import functools
+from abc import abstractmethod
+import pandas as pd
+import numpy as np
 
 
 class ExporterTwDualBase(Exporter):
@@ -57,4 +61,4 @@ def _make_df_initial(self, df):
 
     def _make_df_dual(self, df):
         res = pd.Series(np.where(~df['tw'].isna(), df.en + ' (' + df.tw + ')', df['en']))
-        return res
+        return res

tos_languagematcher/exporter/exporter_factory.py

@@ -1,5 +1,6 @@
-from .exporter import *
-from .exporter_dual import *
+from .exporter import ExporterEnTw, ExporterTwEn, ExporterTwEnopt
+from .exporter_dual import ExporterTwDual1, ExporterTwDual2
+from .exporter_full import ExporterTwFull, ExporterLanguageMap
 
 
 def ExporterFactory(langfrom, langto, output_path):
@@ -13,5 +14,9 @@ def ExporterFactory(langfrom, langto, output_path):
         return ExporterTwDual1(output_path)
     elif (langfrom, langto) == ('tw', 'dual2'):
         return ExporterTwDual2(output_path)
+    elif (langfrom, langto) == ('tw', 'full'):
+        return ExporterTwFull(output_path)
+    elif (langfrom, langto) == ('tw', 'map'):
+        return ExporterLanguageMap(output_path)
     else:
         raise TypeError("Language Not support")

tos_languagematcher/exporter/exporter_full.py

@@ -0,0 +1,45 @@
+from .exporter import Exporter
+import functools
+import numpy as np
+import pandas as pd
+
+
+class ExporterTwFull(Exporter):
+    ''' Similar to ExporterTwEn but remaining zh-tw and korean
+    '''
+    def _get_df1(self, tsv):
+        return self.df_tws[tsv]
+
+    def _make_df_result(self, df, tsv):
+        return np.where(~df['en'].isna(), df['en'], df['tw'])
+
+    # Overwrite
+    def _prepare_df_tsv(self, tsv):
+        ''' Prepare the dataframe of tsv
+        '''
+        df1 = self._get_df1(tsv)
+        dfm = self.tables[tsv]
+        df = pd.merge(df1, dfm, on='korean', how='left')
+        df['result'] = self._make_df_result(df, tsv)
+        self._custom_modify_result(df)
+        df = df[['no', 'tw', 'en', 'korean']]
+        return df
+
+
+class ExporterLanguageMap(ExporterTwFull):
+    ''' Export language mapping tables
+    '''
+    def _prepare_df_tsv(self, tsv):
+        df = super()._prepare_df_tsv(tsv)
+        cond = self._get_nospecialchars_condition(df)
+        df = df[cond]
+        df = df[['tw', 'en', 'korean']]
+        return df
+
+    def _get_nospecialchars_condition(self, df):
+        cond_short = df.tw.str.len() < 15
+        cond_short &= df.en.str.len() < 35
+        special_chars = [',', '.', '!', ':', '%', '{', '}']
+        cond_nospecialchars = functools.reduce(
+            lambda x, y: x & y, [df.en.str.find(c) == -1 for c in special_chars])
+        return cond_nospecialchars