Merge branch 'word_boundaries' into test

Author: scossu

scriptshifter/tables/__init__.py

@@ -84,12 +84,12 @@ def __init__(self, content):
         # Standalone has precedence, then initial, then final, then medial.
         # This is somewhat arbitrary and may change if special cases arise.
         # WB markers are moved to flags to allow default comparison.
-        if self.content.endswith(TOKEN_WB_MARKER):
-            self.flags |= BOW
-            self.content = self.content.rstrip(TOKEN_WB_MARKER)
         if self.content.startswith(TOKEN_WB_MARKER):
-            self.flags |= EOW
+            self.flags |= BOW
             self.content = self.content.lstrip(TOKEN_WB_MARKER)
+        if self.content.endswith(TOKEN_WB_MARKER):
+            self.flags |= EOW
+            self.content = self.content.rstrip(TOKEN_WB_MARKER)
 
     def __lt__(self, other):
         """
@@ -115,9 +115,9 @@ def __lt__(self, other):
         if (
                 (self.flags > 0 or other.flags > 0)
                 and self.content == other.content):
-            logger.debug(f"{self.content} flags: {self.flags}")
-            logger.debug(f"{other.content} flags: {other.flags}")
-            logger.debug("Performing flags comparison.")
+            # logger.debug(f"{self.content} flags: {self.flags}")
+            # logger.debug(f"{other.content} flags: {other.flags}")
+            # logger.debug("Performing flags comparison.")
 
             return self.flags > other.flags
 
@@ -202,6 +202,8 @@ def populate_table(conn, tname, tdata):
 
     @param tdata(dict): Table data.
     """
+    logger.info(f"Populating table: {tname}")
+
     res = conn.execute(
         """INSERT INTO tbl_language (
             name, label, marc_code, description

scriptshifter/tables/data/_ignore_base.yml

@@ -1,9 +1,9 @@
+---
 general:
   name: Common ignore list.
 
 roman_to_script:
   ignore:
-    - " "
     - "at head of title"
     - "colophon"
     - "date of publication not identified"
@@ -38,8 +38,6 @@ roman_to_script:
     - "\\b[\u2021$][0-9a-z]\\b"
 
 script_to_roman:
-  ignore:
-    - " "
   ignore_ptn:
     # MARC sub-field markers.
     - "\\b[\u2021$][0-9a-z]\\b"

scriptshifter/tables/data/greek_classical.yml

@@ -404,7 +404,8 @@ script_to_roman:
     "\u0399": "I"
     "\u039A": "K"
     "\u039B": "L"
-    "\u039C\u03C0%": "B"
+    "%\u039C\u03A0": "B"
+    "%\u039C\u03C0": "B"
     "\u039C": "M"
     "\u039D\u03C4%": "\u1E0E"
     "\u039D": "N"
@@ -461,10 +462,11 @@ script_to_roman:
     "\u03B2": "b"
     "\u03B3\u03B3": "ng"
     "\u03B3\u03BA": "nk"
-    "\u0393\u03BA%": "Gk"
-    "\u03B3\u03BA%": "gk"
     "%\u0393\u03BA": "Gk"
+    "%\u0393\u039A": "GK"
+    "\u0393\u039A%": "GK"
     "%\u03B3\u03BA": "gk"
+    "\u03B3\u03BA%": "gk"
     "\u03B3\u03BE": "nx"
     "\u03B3\u03C7": "nch"
     "\u03B3": "g"
@@ -494,9 +496,9 @@ script_to_roman:
     "\u03B9": "i"
     "\u03BA": "k"
     "\u03BB": "l"
-    "\u03BC\u03C0%": "b"
+    "%\u03BC\u03C0": "b"
     "\u03BC": "m"
-    "\u03BD\u03C4%": "\u1E0F"
+    "%\u03BD\u03C4": "\u1E0F"
     "\u03BD": "n"
     "\u03BE": "x"
     "\u1F41": "ho"
@@ -611,6 +613,8 @@ roman_to_script:
     "Au": "\u0391\u03C5"
     "au": "\u03B1\u03C5"
     "a\u0301": "\u03AC"
+    "%B": "\u039C\u03C0"
+    "%b": "\u03BC\u03C0"
     "B": "\u0392"
     "b": "\u03B2"
     "b\u0333": "\u03D0"
@@ -699,7 +703,7 @@ roman_to_script:
     "m": "\u03BC"
     "nch": "\u03B3\u03C7"
     "ng": "\u03B3\u03B3"
-    "%nk%": "\u03B3\u03BA"
+    "nk": "\u03B3\u03BA"
     "nx": "\u03B3\u03BE"
     "No\u0332": "\u2116"
     "N": "\u039D"
@@ -749,7 +753,7 @@ roman_to_script:
     # "S": "\u03F9"  # FIXME ambiguous.
     "S": "\u03A3"
     # "s": "\u03F2"  # FIXME ambiguous.
-    "%s": "\u03C2"
+    "s%": "\u03C2"
     "s": "\u03C3"
     "T\u0333H\u0333": "\u03F4"
     "t\u0333h\u0333": "\u03D1"