Reverse % sign for word boundary.

Author: scossu

scriptshifter/tables/data/arabic.yml

@@ -4,7 +4,8 @@
 ---
 general:
   name: Arabic
-  description: Arabic R2S using a conversion table and S2R using a 3rd party library.
+  description: >
+    Arabic R2S using a conversion table and S2R using a 3rd party library.
   case_sensitive: false
 
   parents:
@@ -16,17 +17,18 @@ roman_to_script:
 
     # Original table by David Bucknum
     # Last updated 25 January 2019
-    # Modified by WK with testing by Arabic Cat Staff LOC-CAIRO 
-    # Additional info from R. Vassie, [n.d.] "Marrying the Arabic and Latin Scripts Conceptually" 
+    # Modified by WK with testing by Arabic Cat Staff LOC-CAIRO
+    # Additional info from R. Vassie, [n.d.] "Marrying the Arabic and Latin
+    # Scripts Conceptually"
 
 
-    # Punctuation marks:    
+    # Punctuation marks:
     "*": "\u066D"
     ",": "\u060C"
     ";": "\u061B"
     "?": "\u061F"
 
-    # Exceptions for specific words 
+    # Exceptions for specific words
     # Allah
     "Alla\u0304h": "\u0627\u0644\u0644\u0647"
 
@@ -66,19 +68,19 @@ roman_to_script:
 
     # "sh[dot below] as in "Ishaq"
 
-    "%sh\u0323%": "\u0633\u062D"
+    "sh\u0323": "\u0633\u062D"
 
     # "s[prime]h" combos
 
-    "%s\u02B9h%": "\u0633\u0647"
+    "s\u02B9h": "\u0633\u0647"
 
     # "th[dot below]"
 
-    "%th\u0323%": "\u062A\u062D"
+    "th\u0323": "\u062A\u062D"
 
-    # dh[dot under] 
+    # dh[dot under]
 
-    "%dh\u0323%": "\u062F\u062D"
+    "dh\u0323": "\u062F\u062D"
 
     # La-hu
 
@@ -96,7 +98,9 @@ roman_to_script:
     "mi\u02BEat": "\u0645\u0627\u0626\u0629"
     "mi\u02BCat": "\u0645\u0627\u0626\u0629"
 
-    # Numbers (I have set these to Hindi numbers. Note that Persian and Urdu will technically use \u06F0-06F9. This needs further discussion with PSD as RLIN21 used Hindi numbers, Connexion and Voyager does not.)
+    # Numbers (I have set these to Hindi numbers. Note that Persian and Urdu
+    # will technically use \u06F0-06F9. This needs further discussion with PSD
+    # as RLIN21 used Hindi numbers, Connexion and Voyager does not.)
 
     # Edition statements with Latin number
     "al-T\u0323ab\u02BBah 1": "\u0627\u0644\u0637\u0628\u0639\u0629 1"
@@ -132,15 +136,15 @@ roman_to_script:
     "ka-": "\u0643"
 
     # Vowels and vowel/consonant combinations
-    "%ah": "\u0629"
-    "%at": "\u0629"
+    "ah%": "\u0629"
+    "at%": "\u0629"
 
-    #tanwin
-    "%an": "\u0627"
+    # tanwin
+    "an%": "\u0627"
 
     # ayn-alif combo
-    "%\u02BBa\u0304\u02BE": "\u0639\u0627\u0621"
-    "%\u02BBa\u0304\u02BC": "\u0639\u0627\u0621"
+    "\u02BBa\u0304\u02BE%": "\u0639\u0627\u0621"
+    "\u02BBa\u0304\u02BC%": "\u0639\u0627\u0621"
 
     "\u02BBA\u0304": "\u0639\u0627"
     "\u02BBa\u0304": "\u0639\u0627"
@@ -153,27 +157,27 @@ roman_to_script:
     "\u02BBU": "\u0639"
     "\u02BBu": "\u0639"
 
-    "\u02BBA%": "\u0639"
-    #"\u02BBa%": "\u0639"
+    "%\u02BBA": "\u0639"
+    # "%\u02BBa": "\u0639"
 
     # alif and hamzas for all occasions
 
-    # truncation necessary? It seems to work fine with. 
+    # truncation necessary? It seems to work fine with.
 
-    "%i\u0304\u02BEah": "\u064A\u0626\u0629"
-    "%i\u0304\u02BCah": "\u064A\u0626\u0629"
+    "i\u0304\u02BEah%": "\u064A\u0626\u0629"
+    "i\u0304\u02BCah%": "\u064A\u0626\u0629"
 
-    "%i\u0304\u02BEat": "\u064A\u0626\u0629"
-    "%i\u0304\u02BCat": "\u064A\u0626\u0629"
+    "i\u0304\u02BEat%": "\u064A\u0626\u0629"
+    "i\u0304\u02BCat%": "\u064A\u0626\u0629"
 
-    "%i\u02BEa\u0304": "\u0626\u0627"
-    "%i\u02BCa\u0304": "\u0626\u0627"
+    "i\u02BEa\u0304%": "\u0626\u0627"
+    "i\u02BCa\u0304%": "\u0626\u0627"
 
-    "%i\u02BE": "\u0626"
-    "%i\u02BC": "\u0626"
+    "i\u02BE%": "\u0626"
+    "i\u02BC%": "\u0626"
     "a\u0304\u02BEa\u0304": "\u0627\u0621\u0627"
     "a\u0304\u02BCa\u0304": "\u0627\u0621\u0627"
-     
+
     "a\u02BE": "\u0623"
     "a\u02BC": "\u0623"
     "\u02BEi": "\u0626"
@@ -198,64 +202,66 @@ roman_to_script:
     "a\u0304\u02BEi": "\u0627\u0626"
     "a\u0304\u02BC": "\u0627\u0621"
     "a\u0304\u02BE": "\u0627\u0621"
-    "A\u0304%": "\u0622"
-    "a\u0304%": "\u0622"
+    "%A\u0304": "\u0622"
+    "%a\u0304": "\u0622"
     "A\u0304": "\u0627"
     "a\u0304": "\u0627"
 
-    # These next two lines were intended to convert to alif-ayn when it is at the beginning of a word, definite or indefinine (i.e. al-a[ayn]ma[macron]l or [space]a[ayn]ma[macron]l" 
-    "A\u02BB%": "\u0623\u0639"
-    "a\u02BB%": "\u0623\u0639"
+    # These next two lines were intended to convert to alif-ayn when it is at
+    # # the beginning of a word, definite or indefinine (i.e.
+    # al-a[ayn]ma[macron]l or [space]a[ayn]ma[macron]l"
+    "%A\u02BB": "\u0623\u0639"
+    "%a\u02BB": "\u0623\u0639"
     "a\u02BB": "\u0639"
     "A\u0301": "\u0649"
     "a\u0301": "\u0649"
 
     "ayy": "\u064A"
-    "A%": "\u0623"
-    "a%": "\u0627"
+    "%A": "\u0623"
+    "%a": "\u0627"
     "A": "\u0623"
     "a": ""
 
     # I - Capital I at beginning of word is usually alif hamzah-below.
 
-    "%i\u0304": "\u064A"
+    "i\u0304%": "\u064A"
     "i\u0304y": "\u064A"
     "iy": "\u064A"
-    "I\u0304%": "\u0625\u064A"
+    "%I\u0304": "\u0625\u064A"
     "i\u0304": "\u064A"
-    "\u02BBI%": "\u0639"
+    "%\u02BBI": "\u0639"
 
-    #"i\u02BB": "\u0625\u0639"
+    # "i\u02BB": "\u0625\u0639"
 
     "I\u02BE": "\u0627\u0626"
     "I\u02BC": "\u0627\u0626"
     "i\u02BE": "\u0626"
     "i\u02BC": "\u0627\u0626"
 
-    "I%": "\u0625"
-    "i%": "\u0625"
+    "%I": "\u0625"
+    "%i": "\u0625"
     "I": "\u0625"
     "i": ""
 
-    # U 
+    # U
 
     "u\u0304\u02BE": "\u0624"
     "u\u0304\u02BC": "\u0624"
-    "U\u0304w%": "\u0623\u0648"
-    "u\u0304w%": "\u0623\u0648"
-    "U\u0304%": "\u0623\u0648"
-    "u\u0304%": "\u0623\u0648"
+    "%U\u0304w": "\u0623\u0648"
+    "%u\u0304w": "\u0623\u0648"
+    "%U\u0304": "\u0623\u0648"
+    "%u\u0304": "\u0623\u0648"
     "u\u0304w": "\u0648"
     "u\u0304": "\u0648"
     "u\u02BE": "\u0624"
     "u\u02BC": "\u0624"
 
-    "U%": "\u0623"
-    "u%": "\u0623"
+    "%U": "\u0623"
+    "%u": "\u0623"
     "U": "\u0623"
     "u": ""
 
-    # Consonants, with tashdid added 
+    # Consonants, with tashdid added
 
     "B": "\u0628"
     "bb": "\u0628"
@@ -352,8 +358,8 @@ roman_to_script:
     # hamza - not romanized
     # "\u0621"
     # hamza (alone in final position)
-    "%\u02BE": "\u0621"
-    "%\u02BC": "\u0621"
+    "\u02BE%": "\u0621"
+    "\u02BC%": "\u0621"
 
     # Do not know what, if anything, is needed here:
     # tatweel:
@@ -380,8 +386,6 @@ roman_to_script:
     # "\u0671"
 
 
-
-
 script_to_roman:
   hooks:
     post_config:

scriptshifter/tables/data/bulgarian.yml

@@ -38,8 +38,8 @@ script_to_roman:
     "\u044C": ""
     "\u042C": ""
     "\u044A": ""
-    "\u042A%": "u\u0306"
-    "\u042A": ""
+    "\u042A%": ""  # Final
+    "\u042A": "u\u0306"
     "\u0413": "G"
     "\u0433": "g"
     "\u0416": "Zh"

scriptshifter/tables/data/divehi_thaana.yml

@@ -30,8 +30,8 @@ roman_to_script:
     "h\u032E": "\u0781\u07B0"
 
     # THAANA LETTER ALIFU FINAL WITH SUKUN (LOW LINE 0332)
-    "%H\u0332": "\u0787\u07B0"
-    "%h\u0332": "\u0787\u07B0"
+    "H\u0332%": "\u0787\u07B0"
+    "h\u0332%": "\u0787\u07B0"
     "H": "\u0780"
     "h": "\u0780"
     "S\u0301": "\u0781"
@@ -70,13 +70,13 @@ roman_to_script:
     "F": "\u078A"
     "ff": "\u0787\u07B0\u078A"
     "f": "\u078A"
-    # THAANA LETTER "D/d" WITH DOT BELOW (0323) 
+    # THAANA LETTER "D/d" WITH DOT BELOW (0323)
     "D\u0323": "\u0791"
     "d\u0323": "\u0791"
     "D": "\u078B"
     "dd": "\u0787\u07B0\u078B"
     "d": "\u078B"
-    # THAANA LETTER "T/t" WITH DOT BELOW (0323) 
+    # THAANA LETTER "T/t" WITH DOT BELOW (0323)
     "T\u0323": "\u0793"
     "t\u0323": "\u0793"
     "T\u0324T": "\u078C\u07B0\u078C"
@@ -169,7 +169,7 @@ roman_to_script:
     "ghgh": "\u0787\u07B0\u07A3"
     "gh": "\u07A3"
 
-    # THAANA EXTENSION FOR ARABIC LETTER QAAFU 
+    # THAANA EXTENSION FOR ARABIC LETTER QAAFU
     "Q": "\u07A4"
     "qq": "\u0787\u07B0\u07A4"
     "q": "\u07A4"
@@ -181,24 +181,24 @@ roman_to_script:
 
     # INITIAL (AND UPPERCASE) VOWELS THAT CONVERT
     # TO ALIF FOLLOWED BY VOWEL (ALIF OMITTED IN ROMANIZATION)
-    "A\u0304%": "\u0787\u07A7"
-    "A%": "\u0787\u07A6"
+    "%A\u0304": "\u0787\u07A7"
+    "%A": "\u0787\u07A6"
     "\u0020a\u0304": "\u0020\u0787\u07A7"
     "\u0020a": "\u0020\u0787\u07A6"
-    "E\u0304%": "\u0787\u07AD"
-    "E%": "\u0787\u07AC"
+    "%E\u0304": "\u0787\u07AD"
+    "%E": "\u0787\u07AC"
     "\u0020e\u0304": "\u0020\u0787\u07AD"
     "\u0020e": "\u0020\u0787\u07AC"
-    "I\u0304%": "\u0787\u07A9"
-    "I%": "\u0787\u07A8"
+    "%I\u0304": "\u0787\u07A9"
+    "%I": "\u0787\u07A8"
     "\u0020i\u0304": "\u0020\u0787\u07A9"
     "\u0020i": "\u0020\u0787\u07A8"
-    "O\u0304%": "\u0787\u07AF"
-    "O%": "\u0787\u07AE"
+    "%O\u0304": "\u0787\u07AF"
+    "%O": "\u0787\u07AE"
     "\u0020o\u0304": "\u0020\u0787\u07AF"
     "\u0020o": "\u0020\u0787\u07AE"
-    "U\u0304%": "\u0787\u07AB"
-    "U%": "\u0787\u07AB"
+    "%U\u0304": "\u0787\u07AB"
+    "%U": "\u0787\u07AB"
     "\u0020u\u0304": "\u0020\u0787\u07AB"
     "\u0020u": "\u0020\u0787\u07AB"
 
@@ -301,7 +301,7 @@ script_to_roman:
     "\u0787\u07B0\u078A": "ff"
     "\u078A": "f"
 
-    # THAANA LETTER "D/d" WITH DOT BELOW (0323) 
+    # THAANA LETTER "D/d" WITH DOT BELOW (0323)
     "\u0787\u07B0\u0791": "d\u0323d\u0323"
     "\u0791": "d\u0323"
 
@@ -386,7 +386,7 @@ script_to_roman:
     "\u0787\u07B0\u07A3": "ghgh"
     "\u07A3": "gh"
 
-    # THAANA EXTENSION FOR ARABIC LETTER QAAFU 
+    # THAANA EXTENSION FOR ARABIC LETTER QAAFU
     "\u0787\u07B0\u07A4": "qq"
     "\u07A4": "q"