Fix some test strings.

tests/data/script_samples/korean.csv

@@ -98,7 +98,7 @@ korean_names,경복흥,Kyŏng Pok-hŭng,,Hangul; from Y. Lee,
 korean_names,경천흥,Kyŏng Ch'ŏn-hŭng,,Hangul; from Y. Lee,
 korean_names,계봉우,Kye Pong-u,,Hangul; from Y. Lee,
 korean_names,계용묵,Kye Yong-muk,,Hangul; from Y. Lee,
-korean_names,계응상,Kye ŭng-sang,,Hangul; from Y. Lee,
+korean_names,계응상,Kye Ŭng-sang,,Hangul; from Y. Lee,
 korean_names,계정식,Kye Chŏng-sik,,Hangul; from Y. Lee,
 korean_names,고경리,Ko Kyŏng-ri,,Hangul; from Y. Lee,
 korean_names,고경명,Ko Kyŏng-myŏng,,Hangul; from Y. Lee,
@@ -107,7 +107,7 @@ korean_names,고경허,Ko Kyŏng-hŏ,,Hangul; from Y. Lee,
 korean_names,고경흠,Ko Kyŏng-hŭm,,Hangul; from Y. Lee,
 korean_names,고광수,Ko Kwang-su,,Hangul; from Y. Lee,
 korean_names,고광순,Ko Kwang-sun,,Hangul; from Y. Lee,
-korean_names,고광욱,Ko kwang-uk,,Hangul; from Y. Lee,
+korean_names,고광욱,Ko Kwang-uk,,Hangul; from Y. Lee,
 korean_names,고광자,Ko Kwang-ja,,Hangul; from Y. Lee,
 korean_names,고덕무,Ko Tŏng-mu,,Hangul; from Y. Lee,
 korean_names,고두환,Ko Tu-hwan,,Hangul; from Y. Lee,
@@ -438,8 +438,8 @@ korean_names,나월환,Na Wŏr-hwan,,Hangul; from Y. Lee,
 korean_names,남유상,Nam Yu-sang,,Hangul; from Y. Lee,
 korean_names,남유용,Nam Yu-yong,,Hangul; from Y. Lee,
 korean_names,남윤전,Nam Yun-jŏn,,Hangul; from Y. Lee,
-korean_names,남응운,Nam ŭng-un,,Hangul; from Y. Lee,
-korean_names,남응중,Nam ŭng-jung,,Hangul; from Y. Lee,
+korean_names,남응운,Nam Ŭng-un,,Hangul; from Y. Lee,
+korean_names,남응중,Nam Ŭng-jung,,Hangul; from Y. Lee,
 korean_names,남이공,Nam I-gong,,Hangul; from Y. Lee,
 korean_names,남이성,Nam I-sŏng,,Hangul; from Y. Lee,
 korean_names,남이신,Nam I-sin,,Hangul; from Y. Lee,
@@ -941,14 +941,14 @@ korean_names,黃仲寶,Hwang Chung-bo,,Hancha; From Y. Lee,
 korean_names,黃俊良,Hwang Chun-nyang,,Hancha; From Y. Lee,
 korean_names,黃信德,Hwang Sin-dŏk,,Hancha; From Y. Lee,
 korean_names,黃允吉,Hwang Yun-gil,,Hancha; From Y. Lee,
-korean_names,남궁 억,Namgung Ŏk,,From Elaine Kim: 2 character last name + 1 character given name,
-korean_names,독고 영,Tokko Yŏng,,From Elaine Kim: 2 character last name + 1 character given name,
-korean_names,선우 정,Sŏnu Chŏng,,From Elaine Kim: 2 character last name + 1 character given name,
-korean_names,선우 종원,Sŏnu Chong-wŏn,,From Elaine Kim: 2 character last name + 2 character given name,
-korean_names,남궁 지영,Namgung Chi-yŏng,,From Elaine Kim: 2 character last name + 2 character given name,
-korean_names,선우 은숙,Sŏnu Ŭn-suk,,From Elaine Kim: 2 character last name + 2 character given name,
-korean_nonames,성철 선사,Sŏngch'ŏl Sŏnsa,"{""capitalize"": ""all""}",From Elaine Kim: No surname,
-korean_nonames,법현,Pŏphyŏn,"{""capitalize"": ""all""}",From Elaine Kim: No surname,
+korean_names,남궁 억,Namgung Ŏk,,From Elaine Kim: 2 character last name + 1 character given name,
+korean_names,독고 영,Tokko Yŏng,,From Elaine Kim: 2 character last name + 1 character given name,
+korean_names,선우 정,Sŏnu Chŏng,,From Elaine Kim: 2 character last name + 1 character given name,
+korean_names,선우 종원,Sŏnu Chong-wŏn,,From Elaine Kim: 2 character last name + 2 character given name,
+korean_names,남궁 지영,Namgung Chi-yŏng,,From Elaine Kim: 2 character last name + 2 character given name,
+korean_names,선우 은숙,Sŏnu Ŭn-suk,,From Elaine Kim: 2 character last name + 2 character given name,
+korean_nonames,성철 선사,Sŏngch'ŏl Sŏnsa,"{""capitalize"": ""all""}",From Elaine Kim: No surname,
+korean_nonames,법현,Pŏphyŏn,"{""capitalize"": ""all""}",From Elaine Kim: No surname,
 korean_nonames,민주화 이후 국정 운영,Minjuhwa ihu kukchŏng unyŏng,"{""capitalize"": ""first""}",,
 korean_nonames,曉城　趙　明基　博士　追慕　佛教　史學　論文集,Hyosŏng Cho Myŏng-gi Paksa ch'umo Pulgyo sahak nonmunjip,"{""capitalize"": ""first""}",Not Chinese,
 korean_nonames,결단력,Kyŏltannyŏk,"{""capitalize"": ""first""}",From Elaine Kim,

tests/data/script_samples/unclassified.csv

@@ -3,9 +3,6 @@ armenian,Ա Բ Գ Դ Ե Զ Է Ը Թ Ժ Ի Լ Խ Ծ Կ Հ Ձ Ղ Ճ Մ Յ Ն Շ Ո
 georgian,ადგილობრივი თვითმმართველობის კოდექსი : საქართველოს ორგანული კანონი; 2018 წლის 7 სექტებრის მდგომარეობით.,Adgilobrivi tʻvitʻmmartʻvelobis kodekʻsi : Sakʻartʻvelos organuli kanoni; 2018 clis 7 sekʻtembris mdgomareobitʻ.,,
 hindi,परमहंस की पीड़ा : महान क्रांतिकारी रामप्रसाद बिस्मिल के जीवन पर आधारित उपन्यास,Paramahaṃsa kī pīṛā : mahāna krāntikārī Rāmaprasāda Bismila ke jīvana para ādhārita upanyāsa,,
 mongolian_mongol_bichig,ᠳᠠᠶᠢᠴᠢᠩ ᠭᠦᠷᠦᠨ ᠦ ᠦᠶ ᠡ ᠶᠢᠨ ᠥᠯᠠᠨ ᠺᠡᠯᠡᠨ ᠦ ᠦᠰᠦᠭ ᠬᠠᠪᠰᠸᠷᠸᠭᠰᠠᠨ ᠰᠸᠷᠪᠸᠯᠵᠢ ᠪᠢᠴᠢᠭ ᠦᠨ ᠰᠸᠳᠸᠯᠸᠯ,Dayicing gu̇ru̇n-u̇ u̇y-e-yin olan kelen-u̇ u̇su̇g qabsuruġsan surbulji bicig-u̇n sudulul,,
-,نظام الحكم في عمان : من إمامة الإنتخاب الى السلطنة الوراثية,Niẓām al-ḥukm fī ʻUmān : min imāmat al-intikhāb ilá al-salṭanah al-wirāthīyah,,
-,ندوة علاقات مصر بدول حوض النيل في ظل رئاسة مصر للاتحاد الإفريقي‏,Nadwat ʻAlāqāt Miṣr bi-Duwal Ḥawḍ al-Nīl fī ẓill Riʼāsat Miṣr lil-Ittiḥād al-Ifrīqī,,
-,تهذيب البيان والجمع في الفرق بين التكليف والوضع,Tahdhīb al-bayān wa-al-jamʻ fī al-farq bayna al-taklīf wa-al-waḍʻ,,
 ,আগবাৰীত  ফুলিলে  সোনে  মোৰ  চম্পা,Āgabārīta phulile soṇe mora campā,,
 ,Milli dövlətçilik hərəkatının yüksəlişi və Xalq Cümhuriyyəti dövründə Azərbaycançılıq ideyası,Milli dövlätçilik häräkatının yüksälişi vä Xalq Cümhuriyyäti dövründä azärbaycançılıq ideyası,,
 ,مجنون مجنون دوشون منى  شعر توپلوسو ,Macnūn macnūn düşün manī : şiʻr toplūsū,,
@@ -31,8 +28,8 @@ mongolian_mongol_bichig,ᠳᠠᠶᠢᠴᠢᠩ ᠭᠦᠷᠦᠨ ᠦ ᠦᠶ ᠡ
 ,बुनाः त्याः पि : नियात्रा ,Bunāḥ tyāḥ pi : niyātr,,
 ,ਪੰਜਾਬੀ ਲੋਕ-ਸਾਹਿਤ ਵਿਚ ਸੈਨਿਕ,Pañjābī loka-sāhita wica sainika,,
 ,پنجابی وچ 20 ہندی کہانیاں,Panjābiī vic 20 Hindī kahāniyān̲,,
-,‏جامعه ايران در دوران رضا شاه,Jāmiʻah-i Īrān dar dawrān-i Riz̤ā Shāh,,
-,بچه‌هاى بد,Bachchahʹhā-yi bad,,
+,جامعه ايران در دوران رضا شاه,Jāmiʻah-i Īrān dar dawrān-i Riz̤ā Shāh,,
+,بچههاى بد,Bachchahʹhā-yi bad,,
 ,چې لاس دې نه راکاوه,Che lās de nah rākāwah,,
 ,संस्कृतानिबन्धञ्जलिः,Saṃskr̥tanibandhāñjali,,
 ,انسائيڪلوپيڊيا سنڌيانا,Insāʼiklopīḍiyā Sindhiyānā,,